From 3606fd6b9703514c7ca6c7f5ec4e92059934c9f6 Mon Sep 17 00:00:00 2001 From: Peter Breitenlohner Date: Thu, 27 Sep 2012 10:01:26 +0000 Subject: chktex 1.7.1 git-svn-id: svn://tug.org/texlive/trunk@27826 c570f23f-e606-0410-a88d-b1316a301751 --- Build/source/texk/README | 4 +- Build/source/texk/chktex/ChangeLog | 6 + Build/source/texk/chktex/Makefile.am | 25 +- Build/source/texk/chktex/Makefile.in | 127 +- Build/source/texk/chktex/aclocal.m4 | 1 - .../texk/chktex/chktex-1.6.6-PATCHES/ChangeLog | 54 - .../texk/chktex/chktex-1.6.6-PATCHES/TL-Changes | 17 - .../chktex/chktex-1.6.6-PATCHES/patch-06-extern | 43 - .../chktex/chktex-1.6.6-PATCHES/patch-07-kpathsea | 28 - Build/source/texk/chktex/chktex-1.6.6/COPYING | 357 -- Build/source/texk/chktex/chktex-1.6.6/ChkTeX.c | 1037 ----- Build/source/texk/chktex/chktex-1.6.6/ChkTeX.h | 323 -- Build/source/texk/chktex/chktex-1.6.6/ChkTeX.pdf | Bin 210637 -> 0 bytes .../source/texk/chktex/chktex-1.6.6/ChkTeX.tex.in | 1690 -------- Build/source/texk/chktex/chktex-1.6.6/ChkTeX.texrc | 6 - Build/source/texk/chktex/chktex-1.6.6/FindErrs.c | 1537 ------- Build/source/texk/chktex/chktex-1.6.6/FindErrs.h | 193 - Build/source/texk/chktex/chktex-1.6.6/MakeHTML.pl | 20 - Build/source/texk/chktex/chktex-1.6.6/Makefile.in | 317 -- Build/source/texk/chktex/chktex-1.6.6/NEWS | 123 - Build/source/texk/chktex/chktex-1.6.6/OpSys.c | 485 --- Build/source/texk/chktex/chktex-1.6.6/OpSys.h | 207 - Build/source/texk/chktex/chktex-1.6.6/Resource.c | 510 --- Build/source/texk/chktex/chktex-1.6.6/Resource.h | 61 - Build/source/texk/chktex/chktex-1.6.6/Test.out | 411 -- Build/source/texk/chktex/chktex-1.6.6/Test.tex | 186 - Build/source/texk/chktex/chktex-1.6.6/Utility.c | 936 ----- Build/source/texk/chktex/chktex-1.6.6/Utility.h | 172 - Build/source/texk/chktex/chktex-1.6.6/aclocal.m4 | 15 - Build/source/texk/chktex/chktex-1.6.6/autogen.sh | 49 - Build/source/texk/chktex/chktex-1.6.6/chktex.1 | 139 - Build/source/texk/chktex/chktex-1.6.6/chktex.el | 56 - Build/source/texk/chktex/chktex-1.6.6/chktexrc | 678 --- Build/source/texk/chktex/chktex-1.6.6/chkweb.1 | 132 - Build/source/texk/chktex/chktex-1.6.6/chkweb.sh | 56 - Build/source/texk/chktex/chktex-1.6.6/config.h.in | 136 - Build/source/texk/chktex/chktex-1.6.6/configure.in | 158 - Build/source/texk/chktex/chktex-1.6.6/deweb.1 | 116 - Build/source/texk/chktex/chktex-1.6.6/deweb.in | 122 - Build/source/texk/chktex/chktex-1.6.6/input.tex | 1 - Build/source/texk/chktex/chktex-1.6.6/lacheck | 27 - .../chktex-1.6.6/m4/ax_cflags_strict_prototypes.m4 | 170 - .../chktex/chktex-1.6.6/m4/vl_prog_cc_warnings.m4 | 111 - Build/source/texk/chktex/chktex-1.6.6/rmeheader.in | 19 - Build/source/texk/chktex/chktex-1.6.6/types.h | 17 - .../texk/chktex/chktex-1.7.1-PATCHES/ChangeLog | 63 + .../texk/chktex/chktex-1.7.1-PATCHES/TL-Changes | 12 + .../chktex/chktex-1.7.1-PATCHES/patch-07-kpathsea | 28 + .../chktex/chktex-1.7.1-PATCHES/patch-08-stpcpy | 17 + .../chktex-1.7.1-PATCHES/patch-09-test-output | 27 + Build/source/texk/chktex/chktex-1.7.1/COPYING | 357 ++ Build/source/texk/chktex/chktex-1.7.1/ChkTeX.c | 1054 +++++ Build/source/texk/chktex/chktex-1.7.1/ChkTeX.h | 340 ++ Build/source/texk/chktex/chktex-1.7.1/ChkTeX.pdf | Bin 0 -> 225402 bytes .../source/texk/chktex/chktex-1.7.1/ChkTeX.tex.in | 1836 +++++++++ Build/source/texk/chktex/chktex-1.7.1/ChkTeX.texrc | 6 + Build/source/texk/chktex/chktex-1.7.1/FindErrs.c | 1970 +++++++++ Build/source/texk/chktex/chktex-1.7.1/FindErrs.h | 196 + Build/source/texk/chktex/chktex-1.7.1/MakeHTML.pl | 20 + Build/source/texk/chktex/chktex-1.7.1/Makefile.in | 322 ++ Build/source/texk/chktex/chktex-1.7.1/NEWS | 146 + Build/source/texk/chktex/chktex-1.7.1/OpSys.c | 485 +++ Build/source/texk/chktex/chktex-1.7.1/OpSys.h | 207 + Build/source/texk/chktex/chktex-1.7.1/README | 22 + Build/source/texk/chktex/chktex-1.7.1/Resource.c | 510 +++ Build/source/texk/chktex/chktex-1.7.1/Resource.h | 62 + Build/source/texk/chktex/chktex-1.7.1/Test.out | 498 +++ Build/source/texk/chktex/chktex-1.7.1/Test.tex | 218 + Build/source/texk/chktex/chktex-1.7.1/Utility.c | 943 +++++ Build/source/texk/chktex/chktex-1.7.1/Utility.h | 178 + Build/source/texk/chktex/chktex-1.7.1/aclocal.m4 | 15 + Build/source/texk/chktex/chktex-1.7.1/autogen.sh | 49 + Build/source/texk/chktex/chktex-1.7.1/chktex.1 | 143 + Build/source/texk/chktex/chktex-1.7.1/chktex.el | 56 + Build/source/texk/chktex/chktex-1.7.1/chktexrc | 780 ++++ Build/source/texk/chktex/chktex-1.7.1/chkweb.1 | 132 + Build/source/texk/chktex/chktex-1.7.1/chkweb.sh | 56 + Build/source/texk/chktex/chktex-1.7.1/config.h.in | 142 + Build/source/texk/chktex/chktex-1.7.1/configure.in | 213 + Build/source/texk/chktex/chktex-1.7.1/deweb.1 | 116 + Build/source/texk/chktex/chktex-1.7.1/deweb.in | 122 + Build/source/texk/chktex/chktex-1.7.1/input.tex | 1 + Build/source/texk/chktex/chktex-1.7.1/lacheck | 27 + .../chktex-1.7.1/m4/ax_cflags_strict_prototypes.m4 | 170 + .../chktex/chktex-1.7.1/m4/vl_prog_cc_warnings.m4 | 111 + Build/source/texk/chktex/chktex-1.7.1/rmeheader.in | 19 + Build/source/texk/chktex/chktex-1.7.1/types.h | 17 + Build/source/texk/chktex/config.h.in | 6 + Build/source/texk/chktex/configure | 108 +- Build/source/texk/chktex/configure.ac | 13 +- Build/source/texk/chktex/regex/COPYING.LIB | 510 +++ Build/source/texk/chktex/regex/README | 122 + Build/source/texk/chktex/regex/regcomp.c | 3800 +++++++++++++++++ Build/source/texk/chktex/regex/regex.c | 31 + Build/source/texk/chktex/regex/regex.h | 556 +++ Build/source/texk/chktex/regex/regex_internal.c | 1717 ++++++++ Build/source/texk/chktex/regex/regex_internal.h | 778 ++++ Build/source/texk/chktex/regex/regexec.c | 4329 ++++++++++++++++++++ Build/source/texk/chktex/version.ac | 2 +- 99 files changed, 23705 insertions(+), 10831 deletions(-) delete mode 100644 Build/source/texk/chktex/chktex-1.6.6-PATCHES/ChangeLog delete mode 100644 Build/source/texk/chktex/chktex-1.6.6-PATCHES/TL-Changes delete mode 100644 Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-06-extern delete mode 100644 Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-07-kpathsea delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/COPYING delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/ChkTeX.c delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/ChkTeX.h delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/ChkTeX.pdf delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/ChkTeX.tex.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/ChkTeX.texrc delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/FindErrs.c delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/FindErrs.h delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/MakeHTML.pl delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Makefile.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/NEWS delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/OpSys.c delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/OpSys.h delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Resource.c delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Resource.h delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Test.out delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Test.tex delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Utility.c delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/Utility.h delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/aclocal.m4 delete mode 100755 Build/source/texk/chktex/chktex-1.6.6/autogen.sh delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/chktex.1 delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/chktex.el delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/chktexrc delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/chkweb.1 delete mode 100755 Build/source/texk/chktex/chktex-1.6.6/chkweb.sh delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/config.h.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/configure.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/deweb.1 delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/deweb.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/input.tex delete mode 100755 Build/source/texk/chktex/chktex-1.6.6/lacheck delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/m4/ax_cflags_strict_prototypes.m4 delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/m4/vl_prog_cc_warnings.m4 delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/rmeheader.in delete mode 100644 Build/source/texk/chktex/chktex-1.6.6/types.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1-PATCHES/ChangeLog create mode 100644 Build/source/texk/chktex/chktex-1.7.1-PATCHES/TL-Changes create mode 100644 Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-07-kpathsea create mode 100644 Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-08-stpcpy create mode 100644 Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-09-test-output create mode 100644 Build/source/texk/chktex/chktex-1.7.1/COPYING create mode 100644 Build/source/texk/chktex/chktex-1.7.1/ChkTeX.c create mode 100644 Build/source/texk/chktex/chktex-1.7.1/ChkTeX.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1/ChkTeX.pdf create mode 100644 Build/source/texk/chktex/chktex-1.7.1/ChkTeX.tex.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/ChkTeX.texrc create mode 100644 Build/source/texk/chktex/chktex-1.7.1/FindErrs.c create mode 100644 Build/source/texk/chktex/chktex-1.7.1/FindErrs.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1/MakeHTML.pl create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Makefile.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/NEWS create mode 100644 Build/source/texk/chktex/chktex-1.7.1/OpSys.c create mode 100644 Build/source/texk/chktex/chktex-1.7.1/OpSys.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1/README create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Resource.c create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Resource.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Test.out create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Test.tex create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Utility.c create mode 100644 Build/source/texk/chktex/chktex-1.7.1/Utility.h create mode 100644 Build/source/texk/chktex/chktex-1.7.1/aclocal.m4 create mode 100755 Build/source/texk/chktex/chktex-1.7.1/autogen.sh create mode 100644 Build/source/texk/chktex/chktex-1.7.1/chktex.1 create mode 100644 Build/source/texk/chktex/chktex-1.7.1/chktex.el create mode 100644 Build/source/texk/chktex/chktex-1.7.1/chktexrc create mode 100644 Build/source/texk/chktex/chktex-1.7.1/chkweb.1 create mode 100755 Build/source/texk/chktex/chktex-1.7.1/chkweb.sh create mode 100644 Build/source/texk/chktex/chktex-1.7.1/config.h.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/configure.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/deweb.1 create mode 100644 Build/source/texk/chktex/chktex-1.7.1/deweb.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/input.tex create mode 100755 Build/source/texk/chktex/chktex-1.7.1/lacheck create mode 100644 Build/source/texk/chktex/chktex-1.7.1/m4/ax_cflags_strict_prototypes.m4 create mode 100644 Build/source/texk/chktex/chktex-1.7.1/m4/vl_prog_cc_warnings.m4 create mode 100644 Build/source/texk/chktex/chktex-1.7.1/rmeheader.in create mode 100644 Build/source/texk/chktex/chktex-1.7.1/types.h create mode 100644 Build/source/texk/chktex/regex/COPYING.LIB create mode 100644 Build/source/texk/chktex/regex/README create mode 100644 Build/source/texk/chktex/regex/regcomp.c create mode 100644 Build/source/texk/chktex/regex/regex.c create mode 100644 Build/source/texk/chktex/regex/regex.h create mode 100644 Build/source/texk/chktex/regex/regex_internal.c create mode 100644 Build/source/texk/chktex/regex/regex_internal.h create mode 100644 Build/source/texk/chktex/regex/regexec.c diff --git a/Build/source/texk/README b/Build/source/texk/README index 3359f93d408..a65533b6d96 100644 --- a/Build/source/texk/README +++ b/Build/source/texk/README @@ -27,8 +27,8 @@ bibtex8 - ? bibtexu - ? http://omega.enstb.org/yannis/bibtexu/ -chktex 1.6.6 - checked 10apr12 - http://mirror.ctan.org/support/chktex/ for pdf, otherwise same as +chktex 1.7.1 - checked 27sep12 + http://mirror.ctan.org/support/chktex/ http://download.savannah.gnu.org/releases/chktex/ cjkutils 4.8.3 - checked 11may12 diff --git a/Build/source/texk/chktex/ChangeLog b/Build/source/texk/chktex/ChangeLog index 30d7cf61ee6..84af563232e 100644 --- a/Build/source/texk/chktex/ChangeLog +++ b/Build/source/texk/chktex/ChangeLog @@ -1,3 +1,9 @@ +2012-09-27 Peter Breitenlohner + + Import chktex-1.7.1. + * regex/* (new): Copied from ../web2c/pdftexdir, for MinGW. + * Makefile.am, configure.ac, version.ac: Adapted. + 2012-08-31 Peter Breitenlohner * Makefile.am: Install chkweb as linked script. diff --git a/Build/source/texk/chktex/Makefile.am b/Build/source/texk/chktex/Makefile.am index 90105364e97..c12f3f575f7 100644 --- a/Build/source/texk/chktex/Makefile.am +++ b/Build/source/texk/chktex/Makefile.am @@ -26,7 +26,7 @@ EXTRA_DIST += $(CHKTEX_TREE)-PATCHES dist-hook: rm -rf `find $(distdir) -name .svn` -INCLUDES = $(KPATHSEA_INCLUDES) +INCLUDES = $(REGEX_INCLUDES) $(KPATHSEA_INCLUDES) AM_CPPFLAGS = -DKPATHSEA AM_CFLAGS = $(WARNING_CFLAGS) @@ -45,6 +45,24 @@ chktex_SOURCES = \ $(CHKTEX_TREE)/Utility.h \ $(CHKTEX_TREE)/types.h +if MINGW32 +REGEX_INCLUDES = -I$(srcdir)/regex +chktex_SOURCES += \ + regex/regex.c \ + regex/regex.h +endif MINGW32 + +## included by regex/regex.c +EXTRA_chktex_SOURCES = \ + regex/regcomp.c \ + regex/regex_internal.c \ + regex/regex_internal.h \ + regex/regexec.c + +EXTRA_DIST += \ + regex/COPYING.LIB \ + regex/README + $(chktex_OBJECTS): $(KPATHSEA_DEPEND) LDADD = $(KPATHSEA_LIBS) @@ -54,6 +72,7 @@ man_MANS = \ $(CHKTEX_TREE)/chkweb.1 \ $(CHKTEX_TREE)/deweb.1 +# scripts perl_scripts = deweb sh_scripts = chkweb scriptsdir = texmf/scripts/chktex @@ -86,10 +105,8 @@ CLEANFILES = $(nodist_bin_SCRIPTS) ## Tests ## TESTS = chktex.test - +EXTRA_DIST += $(TESTS) TESTS_ENVIRONMENT = CHKTEX_TREE=$(CHKTEX_TREE) -EXTRA_DIST += chktex.test - CLEANFILES += chktest diff --git a/Build/source/texk/chktex/Makefile.in b/Build/source/texk/chktex/Makefile.in index cdd1d065bcf..cd6b406bbe5 100644 --- a/Build/source/texk/chktex/Makefile.in +++ b/Build/source/texk/chktex/Makefile.in @@ -53,6 +53,10 @@ POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ bin_PROGRAMS = chktex$(EXEEXT) +@MINGW32_TRUE@am__append_1 = \ +@MINGW32_TRUE@ regex/regex.c \ +@MINGW32_TRUE@ regex/regex.h + DIST_COMMON = $(am__configure_deps) $(dist_pdfdoc_DATA) \ $(srcdir)/../../texk/am/script_links.am $(srcdir)/Makefile.am \ $(srcdir)/Makefile.in $(srcdir)/config.h.in \ @@ -62,18 +66,16 @@ DIST_COMMON = $(am__configure_deps) $(dist_pdfdoc_DATA) \ $(top_srcdir)/../../build-aux/install-sh \ $(top_srcdir)/../../build-aux/ltmain.sh \ $(top_srcdir)/../../build-aux/missing \ - $(top_srcdir)/chktex-1.6.6/ChkTeX.tex.in \ - $(top_srcdir)/chktex-1.6.6/deweb.in $(top_srcdir)/configure \ + $(top_srcdir)/chktex-1.7.1/deweb.in $(top_srcdir)/configure \ ../../build-aux/config.guess ../../build-aux/config.sub \ ../../build-aux/depcomp ../../build-aux/install-sh \ ../../build-aux/ltmain.sh ../../build-aux/missing \ ../../build-aux/texinfo.tex ../../build-aux/ylwrap ChangeLog -@WIN32_TRUE@@WIN32_WRAP_TRUE@am__append_1 = $(wrappers) +@WIN32_TRUE@@WIN32_WRAP_TRUE@am__append_2 = $(wrappers) subdir = . ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/../../m4/kpse-common.m4 \ $(top_srcdir)/../../m4/kpse-kpathsea-flags.m4 \ - $(top_srcdir)/../../m4/kpse-progs.m4 \ $(top_srcdir)/../../m4/kpse-warnings.m4 \ $(top_srcdir)/../../m4/kpse-win32.m4 \ $(top_srcdir)/../../m4/libtool.m4 \ @@ -88,15 +90,24 @@ am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \ configure.lineno config.status.lineno mkinstalldirs = $(install_sh) -d CONFIG_HEADER = config.h -CONFIG_CLEAN_FILES = ChkTeX.tmp deweb.pl +CONFIG_CLEAN_FILES = deweb.pl CONFIG_CLEAN_VPATH_FILES = am__installdirs = "$(DESTDIR)$(bindir)" "$(DESTDIR)$(bindir)" \ "$(DESTDIR)$(texmfdir)" "$(DESTDIR)$(texmfdir)" \ "$(DESTDIR)$(man1dir)" "$(DESTDIR)$(configdir)" \ "$(DESTDIR)$(pdfdocdir)" PROGRAMS = $(bin_PROGRAMS) +am__chktex_SOURCES_DIST = $(CHKTEX_TREE)/ChkTeX.c \ + $(CHKTEX_TREE)/ChkTeX.h $(CHKTEX_TREE)/FindErrs.c \ + $(CHKTEX_TREE)/FindErrs.h $(CHKTEX_TREE)/OpSys.c \ + $(CHKTEX_TREE)/OpSys.h $(CHKTEX_TREE)/Resource.c \ + $(CHKTEX_TREE)/Resource.h $(CHKTEX_TREE)/Utility.c \ + $(CHKTEX_TREE)/Utility.h $(CHKTEX_TREE)/types.h regex/regex.c \ + regex/regex.h +@MINGW32_TRUE@am__objects_1 = regex.$(OBJEXT) am_chktex_OBJECTS = ChkTeX.$(OBJEXT) FindErrs.$(OBJEXT) \ - OpSys.$(OBJEXT) Resource.$(OBJEXT) Utility.$(OBJEXT) + OpSys.$(OBJEXT) Resource.$(OBJEXT) Utility.$(OBJEXT) \ + $(am__objects_1) chktex_OBJECTS = $(am_chktex_OBJECTS) chktex_LDADD = $(LDADD) am__DEPENDENCIES_1 = @@ -143,8 +154,8 @@ CCLD = $(CC) LINK = $(LIBTOOL) --tag=CC $(AM_LIBTOOLFLAGS) $(LIBTOOLFLAGS) \ --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) $(AM_LDFLAGS) \ $(LDFLAGS) -o $@ -SOURCES = $(chktex_SOURCES) -DIST_SOURCES = $(chktex_SOURCES) +SOURCES = $(chktex_SOURCES) $(EXTRA_chktex_SOURCES) +DIST_SOURCES = $(am__chktex_SOURCES_DIST) $(EXTRA_chktex_SOURCES) am__can_run_installinfo = \ case $$AM_UPDATE_INFO_DIR in \ n|no|NO) false;; \ @@ -240,8 +251,6 @@ PACKAGE_TARNAME = @PACKAGE_TARNAME@ PACKAGE_URL = @PACKAGE_URL@ PACKAGE_VERSION = @PACKAGE_VERSION@ PATH_SEPARATOR = @PATH_SEPARATOR@ -PDFLATEX = @PDFLATEX@ -PDF_DEPEND = @PDF_DEPEND@ PERL5 = @PERL5@ RANLIB = @RANLIB@ SED = @SED@ @@ -309,23 +318,23 @@ top_srcdir = @top_srcdir@ # #************************************************************************ ACLOCAL_AMFLAGS = -I ../../m4 -EXTRA_DIST = $(CHKTEX_TREE) $(CHKTEX_TREE)-PATCHES \ - ../../build-aux/relpath chktex.test -INCLUDES = $(KPATHSEA_INCLUDES) +EXTRA_DIST = $(CHKTEX_TREE) $(CHKTEX_TREE)-PATCHES regex/COPYING.LIB \ + regex/README ../../build-aux/relpath $(TESTS) +INCLUDES = $(REGEX_INCLUDES) $(KPATHSEA_INCLUDES) AM_CPPFLAGS = -DKPATHSEA AM_CFLAGS = $(WARNING_CFLAGS) -chktex_SOURCES = \ - $(CHKTEX_TREE)/ChkTeX.c \ - $(CHKTEX_TREE)/ChkTeX.h \ - $(CHKTEX_TREE)/FindErrs.c \ - $(CHKTEX_TREE)/FindErrs.h \ - $(CHKTEX_TREE)/OpSys.c \ - $(CHKTEX_TREE)/OpSys.h \ - $(CHKTEX_TREE)/Resource.c \ - $(CHKTEX_TREE)/Resource.h \ - $(CHKTEX_TREE)/Utility.c \ - $(CHKTEX_TREE)/Utility.h \ - $(CHKTEX_TREE)/types.h +chktex_SOURCES = $(CHKTEX_TREE)/ChkTeX.c $(CHKTEX_TREE)/ChkTeX.h \ + $(CHKTEX_TREE)/FindErrs.c $(CHKTEX_TREE)/FindErrs.h \ + $(CHKTEX_TREE)/OpSys.c $(CHKTEX_TREE)/OpSys.h \ + $(CHKTEX_TREE)/Resource.c $(CHKTEX_TREE)/Resource.h \ + $(CHKTEX_TREE)/Utility.c $(CHKTEX_TREE)/Utility.h \ + $(CHKTEX_TREE)/types.h $(am__append_1) +@MINGW32_TRUE@REGEX_INCLUDES = -I$(srcdir)/regex +EXTRA_chktex_SOURCES = \ + regex/regcomp.c \ + regex/regex_internal.c \ + regex/regex_internal.h \ + regex/regexec.c LDADD = $(KPATHSEA_LIBS) man_MANS = \ @@ -333,10 +342,12 @@ man_MANS = \ $(CHKTEX_TREE)/chkweb.1 \ $(CHKTEX_TREE)/deweb.1 + +# scripts perl_scripts = deweb sh_scripts = chkweb scriptsdir = texmf/scripts/chktex -nodist_bin_SCRIPTS = $(am__append_1) +nodist_bin_SCRIPTS = $(am__append_2) all_scripts = $(lua_scripts) $(perl_scripts) $(shell_scripts) @WIN32_TRUE@@WIN32_WRAP_TRUE@wrappers = $(all_scripts:=.exe) @WIN32_TRUE@@WIN32_WRAP_TRUE@runscript = $(top_srcdir)/../../texk/texlive/w32_wrapper/runscript.exe @@ -409,9 +420,7 @@ $(srcdir)/config.h.in: @MAINTAINER_MODE_TRUE@ $(am__configure_deps) distclean-hdr: -rm -f config.h stamp-h1 -ChkTeX.tmp: $(top_builddir)/config.status $(top_srcdir)/chktex-1.6.6/ChkTeX.tex.in - cd $(top_builddir) && $(SHELL) ./config.status $@ -deweb.pl: $(top_builddir)/config.status $(top_srcdir)/chktex-1.6.6/deweb.in +deweb.pl: $(top_builddir)/config.status $(top_srcdir)/chktex-1.7.1/deweb.in cd $(top_builddir) && $(SHELL) ./config.status $@ install-binPROGRAMS: $(bin_PROGRAMS) @$(NORMAL_INSTALL) @@ -579,6 +588,10 @@ distclean-compile: @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/OpSys.Po@am__quote@ @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/Resource.Po@am__quote@ @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/Utility.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regcomp.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regex.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regex_internal.Po@am__quote@ +@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/regexec.Po@am__quote@ .c.o: @am__fastdepCC_TRUE@ $(COMPILE) -MT $@ -MD -MP -MF $(DEPDIR)/$*.Tpo -c -o $@ $< @@ -671,6 +684,62 @@ Utility.obj: $(CHKTEX_TREE)/Utility.c @AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ @am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o Utility.obj `if test -f '$(CHKTEX_TREE)/Utility.c'; then $(CYGPATH_W) '$(CHKTEX_TREE)/Utility.c'; else $(CYGPATH_W) '$(srcdir)/$(CHKTEX_TREE)/Utility.c'; fi` +regex.o: regex/regex.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regex.o -MD -MP -MF $(DEPDIR)/regex.Tpo -c -o regex.o `test -f 'regex/regex.c' || echo '$(srcdir)/'`regex/regex.c +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regex.Tpo $(DEPDIR)/regex.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regex.c' object='regex.o' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regex.o `test -f 'regex/regex.c' || echo '$(srcdir)/'`regex/regex.c + +regex.obj: regex/regex.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regex.obj -MD -MP -MF $(DEPDIR)/regex.Tpo -c -o regex.obj `if test -f 'regex/regex.c'; then $(CYGPATH_W) 'regex/regex.c'; else $(CYGPATH_W) '$(srcdir)/regex/regex.c'; fi` +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regex.Tpo $(DEPDIR)/regex.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regex.c' object='regex.obj' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regex.obj `if test -f 'regex/regex.c'; then $(CYGPATH_W) 'regex/regex.c'; else $(CYGPATH_W) '$(srcdir)/regex/regex.c'; fi` + +regcomp.o: regex/regcomp.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regcomp.o -MD -MP -MF $(DEPDIR)/regcomp.Tpo -c -o regcomp.o `test -f 'regex/regcomp.c' || echo '$(srcdir)/'`regex/regcomp.c +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regcomp.Tpo $(DEPDIR)/regcomp.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regcomp.c' object='regcomp.o' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regcomp.o `test -f 'regex/regcomp.c' || echo '$(srcdir)/'`regex/regcomp.c + +regcomp.obj: regex/regcomp.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regcomp.obj -MD -MP -MF $(DEPDIR)/regcomp.Tpo -c -o regcomp.obj `if test -f 'regex/regcomp.c'; then $(CYGPATH_W) 'regex/regcomp.c'; else $(CYGPATH_W) '$(srcdir)/regex/regcomp.c'; fi` +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regcomp.Tpo $(DEPDIR)/regcomp.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regcomp.c' object='regcomp.obj' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regcomp.obj `if test -f 'regex/regcomp.c'; then $(CYGPATH_W) 'regex/regcomp.c'; else $(CYGPATH_W) '$(srcdir)/regex/regcomp.c'; fi` + +regex_internal.o: regex/regex_internal.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regex_internal.o -MD -MP -MF $(DEPDIR)/regex_internal.Tpo -c -o regex_internal.o `test -f 'regex/regex_internal.c' || echo '$(srcdir)/'`regex/regex_internal.c +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regex_internal.Tpo $(DEPDIR)/regex_internal.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regex_internal.c' object='regex_internal.o' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regex_internal.o `test -f 'regex/regex_internal.c' || echo '$(srcdir)/'`regex/regex_internal.c + +regex_internal.obj: regex/regex_internal.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regex_internal.obj -MD -MP -MF $(DEPDIR)/regex_internal.Tpo -c -o regex_internal.obj `if test -f 'regex/regex_internal.c'; then $(CYGPATH_W) 'regex/regex_internal.c'; else $(CYGPATH_W) '$(srcdir)/regex/regex_internal.c'; fi` +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regex_internal.Tpo $(DEPDIR)/regex_internal.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regex_internal.c' object='regex_internal.obj' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regex_internal.obj `if test -f 'regex/regex_internal.c'; then $(CYGPATH_W) 'regex/regex_internal.c'; else $(CYGPATH_W) '$(srcdir)/regex/regex_internal.c'; fi` + +regexec.o: regex/regexec.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regexec.o -MD -MP -MF $(DEPDIR)/regexec.Tpo -c -o regexec.o `test -f 'regex/regexec.c' || echo '$(srcdir)/'`regex/regexec.c +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regexec.Tpo $(DEPDIR)/regexec.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regexec.c' object='regexec.o' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regexec.o `test -f 'regex/regexec.c' || echo '$(srcdir)/'`regex/regexec.c + +regexec.obj: regex/regexec.c +@am__fastdepCC_TRUE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -MT regexec.obj -MD -MP -MF $(DEPDIR)/regexec.Tpo -c -o regexec.obj `if test -f 'regex/regexec.c'; then $(CYGPATH_W) 'regex/regexec.c'; else $(CYGPATH_W) '$(srcdir)/regex/regexec.c'; fi` +@am__fastdepCC_TRUE@ $(am__mv) $(DEPDIR)/regexec.Tpo $(DEPDIR)/regexec.Po +@AMDEP_TRUE@@am__fastdepCC_FALSE@ source='regex/regexec.c' object='regexec.obj' libtool=no @AMDEPBACKSLASH@ +@AMDEP_TRUE@@am__fastdepCC_FALSE@ DEPDIR=$(DEPDIR) $(CCDEPMODE) $(depcomp) @AMDEPBACKSLASH@ +@am__fastdepCC_FALSE@ $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS) -c -o regexec.obj `if test -f 'regex/regexec.c'; then $(CYGPATH_W) 'regex/regexec.c'; else $(CYGPATH_W) '$(srcdir)/regex/regexec.c'; fi` + mostlyclean-libtool: -rm -f *.lo diff --git a/Build/source/texk/chktex/aclocal.m4 b/Build/source/texk/chktex/aclocal.m4 index 7fbb8b80b65..0a8ae70fecd 100644 --- a/Build/source/texk/chktex/aclocal.m4 +++ b/Build/source/texk/chktex/aclocal.m4 @@ -982,7 +982,6 @@ AC_SUBST([am__untar]) m4_include([../../m4/kpse-common.m4]) m4_include([../../m4/kpse-kpathsea-flags.m4]) -m4_include([../../m4/kpse-progs.m4]) m4_include([../../m4/kpse-warnings.m4]) m4_include([../../m4/kpse-win32.m4]) m4_include([../../m4/libtool.m4]) diff --git a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/ChangeLog b/Build/source/texk/chktex/chktex-1.6.6-PATCHES/ChangeLog deleted file mode 100644 index 18880faf5f6..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/ChangeLog +++ /dev/null @@ -1,54 +0,0 @@ -2012-07-23 Peter Breitenlohner - - * patch-07-kpathsea (new): With -DKPATHSEA now using kpathsea. - -2012-04-16 Peter Breitenlohner - - * patch-06-extern: Remove the obsolete ASM_HASHWORD stuff (for - Amiga) avoiding extern decls from *.c files. - -2012-04-10 Karl Berry - - * patch-01-const, - * patch-02-bug, - * patch-03-texlive, - * patch-04-strcpy-bug, - * patch-05-ctype-bug: apparently installed upstream, yay. - - * patch-06-extern: not installed, but HashWord and HASH_TYPE are - only used in that one .c file anyway, so it seems fine to me for - them to be defined there. Admittedly the function should be static. - Did not apply or change, sorry. - - * TL-Changes: update for chktex 1.6.6. - -2012-03-29 Peter Breitenlohner - - * patch-06-extern (new): Move decls from Utility.c to Utility.h. - -2010-06-13 Peter Breitenlohner - - * patch-05-ctype-bug (new): Bug fix: - Cast all arguments of isalpha() and similar to 'unsigned char'. - Patch from Jukka Salmi [tlbuild, 10 Jun 2010]. - -2010-05-21 Peter Breitenlohner - - * patch-01-const: Change OutputFormat and PipeOutputFormat back - to non-const. - -2010-05-20 Peter Breitenlohner - - * patch-04-strcpy-bug (new): Bug fixes: - (GetLTXArg): Avoid strcpy() with overlapping args. - (PreProcess): Do not access Buf[-1]. - -2010-05-06 Peter Breitenlohner - - * patch-02-bug (new): Bug fix - * patch-03-texlive (new): Handle global rc file for TeX Live. - -2010-05-02 Peter Breitenlohner - - * patch-01-const (new): Avoid compiler warnings (const). - diff --git a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/TL-Changes b/Build/source/texk/chktex/chktex-1.6.6-PATCHES/TL-Changes deleted file mode 100644 index 607d2d5ff34..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/TL-Changes +++ /dev/null @@ -1,17 +0,0 @@ -Changes applied to the chktex-1.6.6 tree as obtained from: - http://mirror.ctan.org/support/chktex/ -- includes ChkTeX.pdf, - otherwise the same as - http://download.savannah.gnu.org/releases/chktex/chktex-1.6.6.tar.gz - -Remove: - autom4te.cache/ - configure - install-sh - stamp-h.in - -Rename: - chkweb -> chkweb.sh - -Add execute permissions: - chkweb.sh - diff --git a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-06-extern b/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-06-extern deleted file mode 100644 index f99a34f9f6c..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-06-extern +++ /dev/null @@ -1,43 +0,0 @@ - Remove the obsolete ASM_HASHWORD stuff (for Amiga) - avoiding extern decls from *.c files. - -diff -ur chktex-1.6.6.orig/Utility.c chktex-1.6.6/Utility.c ---- chktex-1.6.6.orig/Utility.c 2010-12-18 22:18:49.000000000 +0100 -+++ chktex-1.6.6/Utility.c 2012-04-16 14:20:46.000000000 +0200 -@@ -31,12 +31,7 @@ - #include "Resource.h" - #include "OpSys.h" - --#ifdef ASM_HASHWORD --extern unsigned short HashWord(const char *a); --typedef unsigned short HASH_TYPE; --#else - typedef unsigned long HASH_TYPE; --#endif - - /***************************** SUPPORT FUNCTIONS ************************/ - -@@ -389,14 +384,12 @@ - /*************************** HASH INDEX **************************/ - - /* -- * Hashes a string. The string ought be rather short. We use an asm -- * version the Amiga; note that this returns an unsigned short instead. -+ * Hashes a string. The string ought be rather short. - * - * The algorithm was designed by Peter Weinberger. This version was - * adapted from Dr Dobb's Journal April 1996 page 26. - */ - --#ifndef ASM_HASHWORD - static unsigned long HashWord(const char *str) - { - register unsigned long h = 0, hbit, c; -@@ -411,7 +404,6 @@ - - return (h); - } --#endif - - /* - * Inserts a string into a hash index. Note: You'll have to diff --git a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-07-kpathsea b/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-07-kpathsea deleted file mode 100644 index d102abd0b6e..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6-PATCHES/patch-07-kpathsea +++ /dev/null @@ -1,28 +0,0 @@ -diff -ur chktex-1.6.6.orig/ChkTeX.c chktex-1.6.6/ChkTeX.c ---- chktex-1.6.6.orig/ChkTeX.c 2010-12-18 22:18:13.000000000 +0100 -+++ chktex-1.6.6/ChkTeX.c 2012-07-23 21:29:45.000000000 +0200 -@@ -27,7 +27,9 @@ - */ - - -+#ifndef KPATHSEA - #include "getopt.h" -+#endif - #include "ChkTeX.h" - #include "OpSys.h" - #include "Utility.h" -diff -ur chktex-1.6.6.orig/ChkTeX.h chktex-1.6.6/ChkTeX.h ---- chktex-1.6.6.orig/ChkTeX.h 2010-12-18 22:10:05.000000000 +0100 -+++ chktex-1.6.6/ChkTeX.h 2012-07-23 23:14:51.000000000 +0200 -@@ -38,6 +38,11 @@ - # include CONFIG_H_NAME - #endif - -+#ifdef KPATHSEA -+#include -+#include -+#endif -+ - #include - #include - #include diff --git a/Build/source/texk/chktex/chktex-1.6.6/COPYING b/Build/source/texk/chktex/chktex-1.6.6/COPYING deleted file mode 100644 index d4e8cec1128..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/COPYING +++ /dev/null @@ -1,357 +0,0 @@ - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - - The GNU General Public License version 2 is included below for your reference. - ------------------------------------------------------------------------- - GNU GENERAL PUBLIC LICENSE - Version 2, June 1991 - - Copyright (C) 1989, 1991 Free Software Foundation, Inc. - 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA - Everyone is permitted to copy and distribute verbatim copies - of this license document, but changing it is not allowed. - - Preamble - - The licenses for most software are designed to take away your -freedom to share and change it. By contrast, the GNU General Public -License is intended to guarantee your freedom to share and change free -software--to make sure the software is free for all its users. This -General Public License applies to most of the Free Software -Foundation's software and to any other program whose authors commit to -using it. (Some other Free Software Foundation software is covered by -the GNU Library General Public License instead.) You can apply it to -your programs, too. - - When we speak of free software, we are referring to freedom, not -price. Our General Public Licenses are designed to make sure that you -have the freedom to distribute copies of free software (and charge for -this service if you wish), that you receive source code or can get it -if you want it, that you can change the software or use pieces of it -in new free programs; and that you know you can do these things. - - To protect your rights, we need to make restrictions that forbid -anyone to deny you these rights or to ask you to surrender the rights. -These restrictions translate to certain responsibilities for you if you -distribute copies of the software, or if you modify it. - - For example, if you distribute copies of such a program, whether -gratis or for a fee, you must give the recipients all the rights that -you have. You must make sure that they, too, receive or can get the -source code. And you must show them these terms so they know their -rights. - - We protect your rights with two steps: (1) copyright the software, and -(2) offer you this license which gives you legal permission to copy, -distribute and/or modify the software. - - Also, for each author's protection and ours, we want to make certain -that everyone understands that there is no warranty for this free -software. If the software is modified by someone else and passed on, we -want its recipients to know that what they have is not the original, so -that any problems introduced by others will not reflect on the original -authors' reputations. - - Finally, any free program is threatened constantly by software -patents. We wish to avoid the danger that redistributors of a free -program will individually obtain patent licenses, in effect making the -program proprietary. To prevent this, we have made it clear that any -patent must be licensed for everyone's free use or not licensed at all. - - The precise terms and conditions for copying, distribution and -modification follow. - - GNU GENERAL PUBLIC LICENSE - TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION - - 0. This License applies to any program or other work which contains -a notice placed by the copyright holder saying it may be distributed -under the terms of this General Public License. The "Program", below, -refers to any such program or work, and a "work based on the Program" -means either the Program or any derivative work under copyright law: -that is to say, a work containing the Program or a portion of it, -either verbatim or with modifications and/or translated into another -language. (Hereinafter, translation is included without limitation in -the term "modification".) Each licensee is addressed as "you". - -Activities other than copying, distribution and modification are not -covered by this License; they are outside its scope. The act of -running the Program is not restricted, and the output from the Program -is covered only if its contents constitute a work based on the -Program (independent of having been made by running the Program). -Whether that is true depends on what the Program does. - - 1. You may copy and distribute verbatim copies of the Program's -source code as you receive it, in any medium, provided that you -conspicuously and appropriately publish on each copy an appropriate -copyright notice and disclaimer of warranty; keep intact all the -notices that refer to this License and to the absence of any warranty; -and give any other recipients of the Program a copy of this License -along with the Program. - -You may charge a fee for the physical act of transferring a copy, and -you may at your option offer warranty protection in exchange for a fee. - - 2. You may modify your copy or copies of the Program or any portion -of it, thus forming a work based on the Program, and copy and -distribute such modifications or work under the terms of Section 1 -above, provided that you also meet all of these conditions: - - a) You must cause the modified files to carry prominent notices - stating that you changed the files and the date of any change. - - b) You must cause any work that you distribute or publish, that in - whole or in part contains or is derived from the Program or any - part thereof, to be licensed as a whole at no charge to all third - parties under the terms of this License. - - c) If the modified program normally reads commands interactively - when run, you must cause it, when started running for such - interactive use in the most ordinary way, to print or display an - announcement including an appropriate copyright notice and a - notice that there is no warranty (or else, saying that you provide - a warranty) and that users may redistribute the program under - these conditions, and telling the user how to view a copy of this - License. (Exception: if the Program itself is interactive but - does not normally print such an announcement, your work based on - the Program is not required to print an announcement.) - -These requirements apply to the modified work as a whole. If -identifiable sections of that work are not derived from the Program, -and can be reasonably considered independent and separate works in -themselves, then this License, and its terms, do not apply to those -sections when you distribute them as separate works. But when you -distribute the same sections as part of a whole which is a work based -on the Program, the distribution of the whole must be on the terms of -this License, whose permissions for other licensees extend to the -entire whole, and thus to each and every part regardless of who wrote it. - -Thus, it is not the intent of this section to claim rights or contest -your rights to work written entirely by you; rather, the intent is to -exercise the right to control the distribution of derivative or -collective works based on the Program. - -In addition, mere aggregation of another work not based on the Program -with the Program (or with a work based on the Program) on a volume of -a storage or distribution medium does not bring the other work under -the scope of this License. - - 3. You may copy and distribute the Program (or a work based on it, -under Section 2) in object code or executable form under the terms of -Sections 1 and 2 above provided that you also do one of the following: - - a) Accompany it with the complete corresponding machine-readable - source code, which must be distributed under the terms of Sections - 1 and 2 above on a medium customarily used for software interchange; or, - - b) Accompany it with a written offer, valid for at least three - years, to give any third party, for a charge no more than your - cost of physically performing source distribution, a complete - machine-readable copy of the corresponding source code, to be - distributed under the terms of Sections 1 and 2 above on a medium - customarily used for software interchange; or, - - c) Accompany it with the information you received as to the offer - to distribute corresponding source code. (This alternative is - allowed only for noncommercial distribution and only if you - received the program in object code or executable form with such - an offer, in accord with Subsection b above.) - -The source code for a work means the preferred form of the work for -making modifications to it. For an executable work, complete source -code means all the source code for all modules it contains, plus any -associated interface definition files, plus the scripts used to -control compilation and installation of the executable. However, as a -special exception, the source code distributed need not include -anything that is normally distributed (in either source or binary -form) with the major components (compiler, kernel, and so on) of the -operating system on which the executable runs, unless that component -itself accompanies the executable. - -If distribution of executable or object code is made by offering -access to copy from a designated place, then offering equivalent -access to copy the source code from the same place counts as -distribution of the source code, even though third parties are not -compelled to copy the source along with the object code. - - 4. You may not copy, modify, sublicense, or distribute the Program -except as expressly provided under this License. Any attempt -otherwise to copy, modify, sublicense or distribute the Program is -void, and will automatically terminate your rights under this License. -However, parties who have received copies, or rights, from you under -this License will not have their licenses terminated so long as such -parties remain in full compliance. - - 5. You are not required to accept this License, since you have not -signed it. However, nothing else grants you permission to modify or -distribute the Program or its derivative works. These actions are -prohibited by law if you do not accept this License. Therefore, by -modifying or distributing the Program (or any work based on the -Program), you indicate your acceptance of this License to do so, and -all its terms and conditions for copying, distributing or modifying -the Program or works based on it. - - 6. Each time you redistribute the Program (or any work based on the -Program), the recipient automatically receives a license from the -original licensor to copy, distribute or modify the Program subject to -these terms and conditions. You may not impose any further -restrictions on the recipients' exercise of the rights granted herein. -You are not responsible for enforcing compliance by third parties to -this License. - - 7. If, as a consequence of a court judgment or allegation of patent -infringement or for any other reason (not limited to patent issues), -conditions are imposed on you (whether by court order, agreement or -otherwise) that contradict the conditions of this License, they do not -excuse you from the conditions of this License. If you cannot -distribute so as to satisfy simultaneously your obligations under this -License and any other pertinent obligations, then as a consequence you -may not distribute the Program at all. For example, if a patent -license would not permit royalty-free redistribution of the Program by -all those who receive copies directly or indirectly through you, then -the only way you could satisfy both it and this License would be to -refrain entirely from distribution of the Program. - -If any portion of this section is held invalid or unenforceable under -any particular circumstance, the balance of the section is intended to -apply and the section as a whole is intended to apply in other -circumstances. - -It is not the purpose of this section to induce you to infringe any -patents or other property right claims or to contest validity of any -such claims; this section has the sole purpose of protecting the -integrity of the free software distribution system, which is -implemented by public license practices. Many people have made -generous contributions to the wide range of software distributed -through that system in reliance on consistent application of that -system; it is up to the author/donor to decide if he or she is willing -to distribute software through any other system and a licensee cannot -impose that choice. - -This section is intended to make thoroughly clear what is believed to -be a consequence of the rest of this License. - - 8. If the distribution and/or use of the Program is restricted in -certain countries either by patents or by copyrighted interfaces, the -original copyright holder who places the Program under this License -may add an explicit geographical distribution limitation excluding -those countries, so that distribution is permitted only in or among -countries not thus excluded. In such case, this License incorporates -the limitation as if written in the body of this License. - - 9. The Free Software Foundation may publish revised and/or new versions -of the General Public License from time to time. Such new versions will -be similar in spirit to the present version, but may differ in detail to -address new problems or concerns. - -Each version is given a distinguishing version number. If the Program -specifies a version number of this License which applies to it and "any -later version", you have the option of following the terms and conditions -either of that version or of any later version published by the Free -Software Foundation. If the Program does not specify a version number of -this License, you may choose any version ever published by the Free Software -Foundation. - - 10. If you wish to incorporate parts of the Program into other free -programs whose distribution conditions are different, write to the author -to ask for permission. For software which is copyrighted by the Free -Software Foundation, write to the Free Software Foundation; we sometimes -make exceptions for this. Our decision will be guided by the two goals -of preserving the free status of all derivatives of our free software and -of promoting the sharing and reuse of software generally. - - NO WARRANTY - - 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY -FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN -OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES -PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED -OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF -MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS -TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE -PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, -REPAIR OR CORRECTION. - - 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING -WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR -REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, -INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING -OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED -TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY -YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER -PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE -POSSIBILITY OF SUCH DAMAGES. - - END OF TERMS AND CONDITIONS - - How to Apply These Terms to Your New Programs - - If you develop a new program, and you want it to be of the greatest -possible use to the public, the best way to achieve this is to make it -free software which everyone can redistribute and change under these terms. - - To do so, attach the following notices to the program. It is safest -to attach them to the start of each source file to most effectively -convey the exclusion of warranty; and each file should have at least -the "copyright" line and a pointer to where the full notice is found. - - - Copyright (C) 19yy - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, - USA. - -Also add information on how to contact you by electronic and paper mail. - -If the program is interactive, make it output a short notice like this -when it starts in an interactive mode: - - Gnomovision version 69, Copyright (C) 19yy name of author - Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. - This is free software, and you are welcome to redistribute it - under certain conditions; type `show c' for details. - -The hypothetical commands `show w' and `show c' should show the appropriate -parts of the General Public License. Of course, the commands you use may -be called something other than `show w' and `show c'; they could even be -mouse-clicks or menu items--whatever suits your program. - -You should also get your employer (if you work as a programmer) or your -school, if any, to sign a "copyright disclaimer" for the program, if -necessary. Here is a sample; alter the names: - - Yoyodyne, Inc., hereby disclaims all copyright interest in the program - `Gnomovision' (which makes passes at compilers) written by James Hacker. - - , 1 April 1989 - Ty Coon, President of Vice - -This General Public License does not permit incorporating your program into -proprietary programs. If your program is a subroutine library, you may -consider it more useful to permit linking proprietary applications with the -library. If this is what you want to do, use the GNU Library General -Public License instead of this License. diff --git a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.c b/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.c deleted file mode 100644 index 1af5621f31d..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.c +++ /dev/null @@ -1,1037 +0,0 @@ -/* - * ChkTeX, finds typographic errors in (La)TeX files. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - - -#ifndef KPATHSEA -#include "getopt.h" -#endif -#include "ChkTeX.h" -#include "OpSys.h" -#include "Utility.h" -#include "FindErrs.h" -#include "Resource.h" -#include - -#undef MSG -#define MSG(num, type, inuse, ctxt, text) {num, type, inuse, ctxt, text}, - -struct ErrMsg PrgMsgs[pmMaxFault + 1] = { - PRGMSGS {pmMaxFault, etErr, TRUE, 0, INTERNFAULT} -}; - -struct Stack CharStack = { - 0L -}, InputStack = - -{ -0L}, EnvStack = - -{ -0L}; - -/************************************************************************/ - -const char BrOrder[NUMBRACKETS + 1] = "()[]{}"; - -unsigned long Brackets[NUMBRACKETS]; - -/************************************************************************/ - - -/* - * Have to do things this way, to ease some checking throughout the - * program. - */ - - -NEWBUF(TmpBuffer, BUFSIZ); -NEWBUF(ReadBuffer, BUFSIZ); - -static const char *Banner = - "ChkTeX v" PACKAGE_VERSION " - Copyright 1995-96 Jens T. Berger Thielemann.\n" -#ifdef __OS2__ - "OS/2 port generated with emx compiler, by Wolfgang Fritsch, " -#elif defined(__MSDOS__) - "MS-DOS port by Bj\\o rn Ove Thue, " -#endif - "\n"; - -static const char *BigBanner = - "ChkTeX comes with ABSOLUTELY NO WARRANTY; details on this and\n" - "distribution conditions in the GNU General Public License file.\n" - "Type \"ChkTeX -h\" for help, \"ChkTeX -i\" for distribution info.\n" - "Author: Jens Berger, Spektrumvn. 4, N-0666 Oslo, Norway.\n" - "E-mail: \n" - "Press " STDIN_BREAK " to terminate stdin input.\n"; - -static const char *Distrib = - "\n" - "This program is free software; you can redistribute it and/or modify\n" - "it under the terms of the GNU General Public License as published by\n" - "the Free Software Foundation; either version 2 of the License, or\n" - "(at your option) any later version.\n" - "\n" - "This program is distributed in the hope that it will be useful,\n" - "but WITHOUT ANY WARRANTY; without even the implied warranty of\n" - "MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n" - "GNU General Public License for more details.\n" - "\n" - "You should have received a copy of the GNU General Public License\n" - "along with this program; if not, write to the Free Software\n" - "Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.\n"; - -static const char *OnText = "On"; - -static const char *OffText = "Off"; - -static const char *HowHelp = - "-h or --help gives usage information. See also ChkTeX.{ps,dvi}.\n"; - -static const char *HelpText = - "\n" - "\n" - " Usage of ChkTeX v" PACKAGE_VERSION "\n" - " ~~~~~~~~~~~~~~~~~~~~\n" - "\n" - " Template\n" - " ~~~~~~~~\n" - "chktex [-hiqrW] [-v[0-...]] [-l ] [-[wemn] <[1-42]|all>]\n" - " [-d[0-...]] [-p ] [-o ] [-[btxgI][0|1]]\n" - " file1 file2 ...\n" - "\n" - "----------------------------------------------------------------------\n" - " Description of options:\n" - " ~~~~~~~~~~~~~~~~~~~~~~~\n" - "Misc. options\n" - "~~~~~~~~~~~~~\n" - " -h --help : This text.\n" - " -i --license : Show distribution information\n" - " -l --localrc : Read local .chktexrc formatted file.\n" - " -d --debug : Debug information. Give it a number.\n" - " -r --reset : Reset settings to default.\n" - "\n" - "Muting warning messages:\n" - "~~~~~~~~~~~~~~~~~~~~~~~~\n" - " -w --warnon : Makes msg # given a warning and turns it on.\n" - " -e --erroron : Makes msg # given an error and turns it on.\n" - " -m --msgon : Makes msg # given a message and turns it on.\n" - " -n --nowarn : Mutes msg # given.\n" - "\n" - "Output control flags:\n" - "~~~~~~~~~~~~~~~~~~~~~\n" - " -v --verbosity : How errors are displayed.\n" - " Default 1, 0=Less, 2=Fancy, 3=lacheck.\n" - " -V --pipeverb : How errors are displayed when stdout != tty.\n" - " Defaults to the same as -v.\n" - " -s --splitchar : String used to split fields when doing -v0\n" - " -o --output : Redirect error report to a file.\n" - " -q --quiet : Shuts up about version information.\n" - " -p --pseudoname: Input file-name when reporting.\n" - " -f --format : Format to use for output\n" - "\n" - "Boolean switches (1 -> enables / 0 -> disables):\n" - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" - " -b --backup : Backup output file.\n" - " -x --wipeverb : Ignore contents of `\\verb' commands.\n" - " -g --globalrc : Read global .chktexrc file.\n" - " -I --inputfiles: Execute \\input statements.\n" - " -H --headererr : Show errors found in front of \\begin{document}\n" - "\n" - "Miscellaneous switches:\n" - "~~~~~~~~~~~~~~~~~~~~~~~\n" - " -W --version : Version information\n" - "\n" - "----------------------------------------------------------------------\n" - "If no LaTeX files are specified on the command line, we will read from\n" - "stdin. For explanation of warning/error messages, please consult the\n" - "main document ChkTeX.dvi or ChkTeX.ps.\n"; - - - - -/* - * Options we will set. - * - */ - -enum Quote Quote; - -char VerbNormal[] = "%k %n in %f line %l: %m\n" "%r%s%t\n" "%u\n"; - -#define DEF(type, name, value) type name = value; -OPTION_DEFAULTS STATE_VARS; -#undef DEF -FILE *OutputFile = NULL; - -char *PrgName; - -int StdInTTY, StdOutTTY; - -/* - * End of config params. - */ - -static int ParseArgs(int argc, char **argv); -static void ShowIntStatus(void); -static int OpenOut(void); -static int ShiftArg(char **Argument); - - -/* - * Duplicates all arguments, and appends an asterix to each of them. - */ - -static void AddStars(struct WordList *wl) -{ - unsigned long Count, CmdLen; - char *Data; - - FORWL(Count, *wl) - { - Data = wl->Stack.Data[Count]; - CmdLen = strlen(Data); - if (Data[CmdLen - 1] != '*') - { - strcpy(TmpBuffer, Data); - strcat(TmpBuffer, "*"); - InsertWord(TmpBuffer, wl); - } - } -} - -/* - * Sets up all the lists. - * - */ - -static void SetupLists(void) -{ - unsigned long i; - - AddStars(&VerbEnvir); - AddStars(&MathEnvir); - - MakeLower(&UserWarnCase); - - ListRep(&WipeArg, ':', 0); - ListRep(&NoCharNext, ':', 0); - -#define ThisItem ((char *) AbbrevCase.Stack.Data[i]) - - FORWL(i, AbbrevCase) - { - if (isalpha((unsigned char)ThisItem[0])) - { - ThisItem[0] = toupper((unsigned char)ThisItem[0]); - InsertWord(ThisItem, &Abbrev); - ThisItem[0] = tolower((unsigned char)ThisItem[0]); - } - InsertWord(ThisItem, &Abbrev); - } -} - -#define NOCOMMON(a,b) NoCommon(&a,#a,&b,#b) - -/* - * Checks that two lists don't have any common element. - */ - -static void -NoCommon(struct WordList *a, const char *aName, - struct WordList *b, const char *bName) -{ - unsigned long i; - - FORWL(i, *a) - { - if (HasWord((char *) a->Stack.Data[i], b)) - PrintPrgErr(pmNoCommon, a->Stack.Data[i], aName, bName); - } -} - -/* - * Expands the tabs in a string to regular intervals sized - * TSize. - */ - -static void ExpandTabs(char *From, char *To, long TSize) -{ - char *Next; - char *Orig; - unsigned long Diff; - - Next = From; - Orig = To; - - while ((Next = strchr(From, '\t'))) - { - if ((Diff = Next - From)) - { - strncpy(To, From, Diff); - To += Diff; - Diff = TSize - ((To - Orig) % TSize); - } - else - Diff = TSize; - - memset(To, ' ', Diff); - To += Diff; - - From = ++Next; - } - strcpy(To, From); -} - - -int main(int argc, char **argv) -{ - int retval = EXIT_FAILURE, CurArg; - unsigned long Count; - int StdInUse = FALSE; - long Tab = 8; - -#ifdef __LOCALIZED - - InitStrings(); -#endif - - OutputFile = stdout; - PrgName = argv[0]; - -#undef KEY -#undef LCASE -#undef LIST -#undef LNEMPTY -#define KEY(a, def) -#define LCASE(a) -#define LIST(a) -#define LNEMPTY(a) InsertWord("", &a); - - RESOURCE_INFO; - - while (SetupVars()) - ReadRC(ConfigFile); - - if (CmdLine.Stack.Used) - { - ParseArgs(CmdLine.Stack.Used, (char **) CmdLine.Stack.Data); - CmdLine.Stack.Used = 1L; - } - - if ((CurArg = ParseArgs((unsigned long) argc, argv))) - { - if (CmdLine.Stack.Used) - { - ParseArgs(CmdLine.Stack.Used, (char **) CmdLine.Stack.Data); - CmdLine.Stack.Used = 1L; - } - - if (!Quiet || LicenseOnly) - fprintf(stderr, Banner); - - if (CurArg == argc) - UsingStdIn = TRUE; - -#if defined(HAVE_FILENO) && defined(HAVE_ISATTY) - - StdInTTY = isatty(fileno(stdin)); - StdOutTTY = isatty(fileno(stdout)); -#else - - StdInTTY = StdOutTTY = TRUE; -#endif - - SetupTerm(); - - if ((UsingStdIn && StdInTTY && !Quiet) || LicenseOnly) - { - fprintf(stderr, BigBanner); - } - - if (!StdOutTTY && PipeOutputFormat) - OutputFormat = PipeOutputFormat; - - if (LicenseOnly) - { - fprintf(stderr, Distrib); - } - else - { - SetupLists(); - if (QuoteStyle) - { - if (!strcasecmp(QuoteStyle, "LOGICAL")) - Quote = quLogic; - else if (!strcasecmp(QuoteStyle, "TRADITIONAL")) - Quote = quTrad; - else - { - PrintPrgErr(pmQuoteStyle, QuoteStyle); - Quote = quTrad; - } - } - - if (DebugLevel) - ShowIntStatus(); - - NOCOMMON(Italic, NonItalic); - NOCOMMON(Italic, ItalCmd); - NOCOMMON(LowDots, CenterDots); - - if (TabSize && isdigit((unsigned char)*TabSize)) - Tab = strtol(TabSize, NULL, 10); - - if (OpenOut()) - { - for (;;) - { - for (Count = 0; Count < NUMBRACKETS; Count++) - Brackets[Count] = 0L; - -#define DEF(type, name, value) name = value; - - STATE_VARS -#undef DEF - if (UsingStdIn) - { - if (StdInUse) - break; - else - { - StdInUse = TRUE; - PushFile("stdin", stdin, &InputStack); - } - } - else - { - if (CurArg <= argc) - { - const char *filename = NULL; - if (CurArg < argc) - filename = argv[CurArg++]; - - if (!PushFileName(filename, &InputStack)) - break; - } - } - - if (StkTop(&InputStack) && OutputFile) - { - while (!ferror(OutputFile) - && StkTop(&InputStack) - && !ferror(CurStkFile(&InputStack)) - && FGetsStk(ReadBuffer, BUFSIZ - 1, - &InputStack)) - { - - /* Make all spaces ordinary spaces */ - - strrep(ReadBuffer, '\n', ' '); - strrep(ReadBuffer, '\r', ' '); - ExpandTabs(ReadBuffer, TmpBuffer, Tab); - strcpy(ReadBuffer, TmpBuffer); - - strcat(ReadBuffer, " "); - FindErr(ReadBuffer, CurStkLine(&InputStack)); - } - - PrintStatus(CurStkLine(&InputStack)); - retval = EXIT_SUCCESS; - } - } - } - } - } - return retval; -} - -/* - * Opens the output file handle & possibly renames - */ - -static int OpenOut(void) -{ - int Success = TRUE; - - if (*OutputName) - { - if (BackupOut && fexists(OutputName)) - { - strcpy(TmpBuffer, OutputName); - AddAppendix(TmpBuffer, BAKAPPENDIX); - - if (fexists(TmpBuffer)) - remove(TmpBuffer); - - if (!rename(OutputName, TmpBuffer)) - PrintPrgErr(pmRename, OutputName, TmpBuffer); - else - { - PrintPrgErr(pmRenameErr, OutputName, TmpBuffer); - Success = FALSE; - } - - } - - if (Success) - { - if (!(OutputFile = fopen(OutputName, "w"))) - { - PrintPrgErr(pmOutOpen); - Success = FALSE; - } - } - } - else - OutputFile = stdout; - - return (Success); -} - -#ifndef STRIP_DEBUG -static void ShowWL(const char *Name, const struct WordList *wl) -{ - unsigned long i, j, percent; - - fprintf(stderr, "Name: %12s", Name); - - if (DebugLevel & FLG_DbgListInfo) - { - fprintf(stderr, ", MaxLen: %3ld, Entries: %3ld, ", - wl->MaxLen, wl->Stack.Used); - - if (wl->Hash.Index && wl->Stack.Used) - { - for (i = j = 0; i < HASH_SIZE; i++) - { - if (wl->Hash.Index[i]) - j++; - } - percent = (j * 10000) / wl->Stack.Used; - - - fprintf(stderr, "Hash usage: %3ld.%02ld%%", - percent / 100, percent % 100); - } - else - fprintf(stderr, "No hash table."); - } - - fputc('\n', stderr); - - if (DebugLevel & FLG_DbgListCont) - { - FORWL(i, *wl) fprintf(stderr, "\t%s\n", (char *) wl->Stack.Data[i]); - } -} -#endif - -#define BOOLDISP(var) ((var)? OnText : OffText) -#define SHOWSTAT(text, arg) fprintf(stderr, "\t" text ": %s\n", arg) -#define BOOLSTAT(name, var) SHOWSTAT(name, BOOLDISP(var)) -#define SHOWSTR(text, arg) fprintf(stderr, "%s:\n\t%s\n", text, arg); - - -/* - * Prints some of the internal flags; mainly for debugging purposes - */ - -static void ShowIntStatus(void) -{ -#ifndef STRIP_DEBUG - unsigned long Cnt; - const char *String; - const char *iuStr = ""; - - if (DebugLevel & FLG_DbgMsgs) - { - fprintf(stderr, "There are %d warnings/error messages available:\n", - emMaxFault - emMinFault - 1); - - for (Cnt = emMinFault + 1; Cnt < emMaxFault; Cnt++) - { - switch (LaTeXMsgs[Cnt].Type) - { - case etWarn: - String = "Warning"; - break; - case etErr: - String = "Error"; - break; - case etMsg: - String = "Message"; - break; - default: - String = ""; - break; - } - - switch (LaTeXMsgs[Cnt].InUse) - { - case iuOK: - iuStr = "In use"; - break; - case iuNotUser: - iuStr = "User muted"; - break; - case iuNotSys: - iuStr = "System muted"; - break; - } - - fprintf(stderr, "Number: %2ld, Type: %s, Status: %s\n" - "\tText: %s\n\n", - Cnt, String, iuStr, LaTeXMsgs[Cnt].Message); - } - } - -#undef KEY -#undef LCASE -#undef LNEMPTY -#undef LIST - -#define LNEMPTY LIST -#define LIST(a) ShowWL(#a, &a); -#define LCASE(a) LIST(a); LIST(a ## Case); -#define KEY(a,def) SHOWSTR(#a, a); - - - if (DebugLevel & (FLG_DbgListInfo | FLG_DbgListCont)) - { - RESOURCE_INFO; - } - - if (DebugLevel & FLG_DbgOtherInfo) - { - SHOWSTR("Outputformat", OutputFormat); - - fprintf(stderr, "Current flags include:\n"); - - BOOLSTAT("Read global resource", GlobalRC); - BOOLSTAT("Wipe verbose commands", WipeVerb); - BOOLSTAT("Backup outfile", BackupOut); - BOOLSTAT("Quiet mode", Quiet); - BOOLSTAT("Show license", LicenseOnly); - BOOLSTAT("Use stdin", UsingStdIn); - BOOLSTAT("\\input files", InputFiles); - BOOLSTAT("Output header errors", HeadErrOut); - } -#endif -} - -/* - * Resets all stacks. - * - */ - -#undef KEY -#undef LCASE -#undef LNEMPTY -#undef LIST - -#define LNEMPTY LIST -#define LIST(a) ClearWord(&a); -#define LCASE(a) LIST(a); LIST(a ## Case); -#define KEY(a,def) a = def; - -static void ResetStacks(void) -{ - RESOURCE_INFO; - -} - -/* - * Resets all flags (not wordlists) to their default values. Sets - * Outputfile to stdout. - * - */ - -static void ResetSettings(void) -{ - -#define DEF(type, name, value) name = value; - OPTION_DEFAULTS -#undef DEF - if (OutputFile != stdout) - { - fclose(OutputFile); - OutputFile = stdout; - } -} - -/* - * Reads a numerical argument from the argument. Supports concatenation - * of arguments (main purpose) - */ - -static int ParseNumArg(long *Dest, /* Where to put the value */ - long Default, /* Value to put in if no in argue */ - char **Argument) /* optarg or similar */ -{ - if (Argument && *Argument && isdigit((unsigned char)**Argument)) - *Dest = strtol(*Argument, Argument, 10); - else - *Dest = Default; - - return (ShiftArg(Argument)); -} - -/* - * Same as above; however, will toggle the boolean if user doesn't - * supply value - */ - -static int ParseBoolArg(int *Dest, /* Boolean value */ - char **Argument) /* optarg or similar */ -{ - long D = *Dest ? 1L : 0L; - int Retval; - - Retval = ParseNumArg(&D, *Dest ? 0L : 1L, Argument); - - *Dest = D ? TRUE : FALSE; - - return (Retval); -} - -/* - * Returns the first character in the string passed, updates the - * string pointer, if the string is non-empty. - * - * 0 if the string is empty. - */ - -static int ShiftArg(char **Argument) /* optarg or similar */ -{ - if (Argument && *Argument && **Argument) - return (*((char *) (*Argument)++)); - else - return 0; -} - -/* - * Parses an argv similar array. - */ - -static int ParseArgs(int argc, char **argv) -{ - /* Needed for option parsing. */ - - static const struct option long_options[] = { - {"help", no_argument, 0L, 'h'}, - {"localrc", required_argument, 0L, 'l'}, - {"output", required_argument, 0L, 'o'}, - {"warnon", required_argument, 0L, 'w'}, - {"erroron", required_argument, 0L, 'e'}, - {"msgon", required_argument, 0L, 'm'}, - {"nowarn", required_argument, 0L, 'n'}, - {"verbosity", optional_argument, 0L, 'v'}, - {"pipeverb", optional_argument, 0L, 'V'}, - {"debug", required_argument, 0L, 'd'}, - {"reset", no_argument, 0L, 'r'}, - {"quiet", no_argument, 0L, 'q'}, - {"license", no_argument, 0L, 'i'}, - {"splitchar", required_argument, 0L, 's'}, - {"format", required_argument, 0L, 'f'}, - {"pseudoname", required_argument, 0L, 'p'}, - - {"inputfiles", optional_argument, 0L, 'I'}, - {"backup", optional_argument, 0L, 'b'}, - {"globalrc", optional_argument, 0L, 'g'}, - {"wipeverb", optional_argument, 0L, 'x'}, - {"tictoc", optional_argument, 0L, 't'}, - {"headererr", optional_argument, 0L, 'H'}, - {"version", no_argument, 0L, 'W'}, - - {0L, 0L, 0L, 0L} - }; - - int option_index = 0L, c, i, nextc, ErrType; - - int Retval = FALSE, InUse; - int Success, Foo; - long Err, Verb = 1, PipeVerb = 1; - - enum - { - aeNoErr = 0, - aeArg, /* missing/bad required argument */ - aeOpt, /* unknown option returned */ - aeHelp, /* just a call for help */ - aeMem /* no memory */ - } ArgErr = aeNoErr; - - optind = 0; - - while (!ArgErr && - ((c = getopt_long((int) argc, argv, - "b::d:e:f:g::hH::I::il:m:n:o:p:qrs:t::v::V::w:Wx::", - long_options, &option_index)) != EOF)) - { - while (c) - { - nextc = 0; - switch (c) - { - case 's': - if (!(Delimit = strdup(optarg))) - { - PrintPrgErr(pmStrDupErr); - ArgErr = aeMem; - } - - break; - case 'p': - if (!(PseudoInName = strdup(optarg))) - { - PrintPrgErr(pmStrDupErr); - ArgErr = aeMem; - } - - break; - - case 'd': -#ifdef STRIP_DEBUG - - PrintPrgErr(pmNoDebugFlag); -#else - - nextc = ParseNumArg(&DebugLevel, 0xffff, &optarg); -#endif - - break; - case 'i': - LicenseOnly = TRUE; - - nextc = ShiftArg(&optarg); - break; - case 'q': - Quiet = TRUE; - - nextc = ShiftArg(&optarg); - break; - - LOOP(warntype, case 'w': - ErrType = etWarn; InUse = iuOK; LAST(warntype); case 'e': - ErrType = etErr; InUse = iuOK; LAST(warntype); case 'm': - ErrType = etMsg; InUse = iuOK; LAST(warntype); case 'n': - ErrType = etMsg; InUse = iuNotUser; LAST(warntype);) if (isdigit((unsigned char)*optarg)) - { - nextc = ParseNumArg(&Err, -1, &optarg); - if (betw(emMinFault, Err, emMaxFault)) - { - LaTeXMsgs[Err].Type = ErrType; - LaTeXMsgs[Err].InUse = InUse; - } - else - { - ArgErr = aeOpt; - PrintPrgErr(pmWarnNumErr); - } - } - else if (!strcasecmp(optarg, "all")) - { - for (i = emMinFault + 1; i < emMaxFault; i++) - { - LaTeXMsgs[i].Type = ErrType; - LaTeXMsgs[i].InUse = InUse; - } - } - else - { - ArgErr = aeOpt; - PrintPrgErr(pmWarnNumErr); - } - - break; - - case 'g': - nextc = ParseBoolArg(&GlobalRC, &optarg); - if (!GlobalRC) - { - ResetStacks(); - } - break; - - case 'r': - ResetSettings(); - nextc = ShiftArg(&optarg); - break; - - case 'l': - if (optarg) - ReadRC(optarg); - break; - - case 'f': - if (!(OutputFormat = strdup(optarg))) - { - PrintPrgErr(pmStrDupErr); - ArgErr = aeMem; - } - break; - - case 'v': - nextc = ParseNumArg(&Verb, 2, &optarg); - - if (Verb < (long) OutFormat.Stack.Used) - OutputFormat = strdup(OutFormat.Stack.Data[Verb]); - else - { - PrintPrgErr(pmVerbLevErr); - ArgErr = aeArg; - } - break; - case 'V': - nextc = ParseNumArg(&PipeVerb, 1, &optarg); - - if (PipeVerb < (long) OutFormat.Stack.Used) - PipeOutputFormat = strdup(OutFormat.Stack.Data[PipeVerb]); - else - { - PrintPrgErr(pmVerbLevErr); - ArgErr = aeArg; - } - break; - - case 'o': - if (optarg) - { - if (*OutputName) - { - PrintPrgErr(pmOutTwice); - ArgErr = aeOpt; - } - else - { - if (!(OutputName = strdup(optarg))) - { - PrintPrgErr(pmStrDupErr); - ArgErr = aeMem; - } - } - } - - break; - - case 't': - nextc = ParseBoolArg(&Foo, &optarg); - break; - case 'x': - nextc = ParseBoolArg(&WipeVerb, &optarg); - break; - case 'b': - nextc = ParseBoolArg(&BackupOut, &optarg); - break; - case 'I': - nextc = ParseBoolArg(&InputFiles, &optarg); - break; - case 'H': - nextc = ParseBoolArg(&HeadErrOut, &optarg); - break; - case 'W': - printf(Banner); - exit(EXIT_SUCCESS); - case '?': - default: - fputs(Banner, stderr); - fputs(HowHelp, stderr); - exit(EXIT_FAILURE); - break; - case 'h': - ArgErr = aeHelp; - break; - } - c = nextc; - } - } - - if ((argc > optind) && !strcmp(argv[optind], "?")) - ArgErr = aeHelp; - - if (ArgErr) - { - fputs(Banner, stderr); - fputs(BigBanner, stderr); - fputs(HelpText, stderr); - Success = FALSE; - } - else - Success = TRUE; - - if (Success) - Retval = optind; - - return (Retval); -} - -/* - * Outputs a program error. - */ - - -void PrintPrgErr(enum PrgErrNum Error, ...) -{ - const char *Type; - va_list MsgArgs; - - if (betw(pmMinFault, Error, pmMaxFault)) - { - switch (PrgMsgs[Error].Type) - { - case etWarn: - Type = "WARNING"; - break; - case etMsg: - Type = "NOTE"; - break; - default: - case etErr: - Type = "ERROR"; - break; - } - fprintf(stderr, "%s: %s -- ", PrgName, Type); - - va_start(MsgArgs, Error); - vfprintf(stderr, PrgMsgs[Error].Message, MsgArgs); - va_end(MsgArgs); - fputc('\n', stderr); - - if (PrgMsgs[Error].Type == etErr) - exit(EXIT_FAILURE); - } -} - -void ErrPrintf(const char *fmt, ...) -{ - va_list MsgArgs; - - va_start(MsgArgs, fmt); - vfprintf(stderr, fmt, MsgArgs); - va_end(MsgArgs); -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.h b/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.h deleted file mode 100644 index 3fa1e018ced..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.h +++ /dev/null @@ -1,323 +0,0 @@ -/* - * ChkTeX, header file for main program. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#ifndef CHKTEX_H -#define CHKTEX_H 1 -#if defined(HAVE_CONFIG_H) || defined(CONFIG_H_NAME) -# ifndef CONFIG_H_NAME -# define CONFIG_H_NAME "config.h" -# endif -# ifndef HAVE_CONFIG_H -# define HAVE_CONFIG_H 1 -# endif -# include CONFIG_H_NAME -#endif - -#ifdef KPATHSEA -#include -#include -#endif - -#include -#include -#include - -#ifdef HAVE_STDARG_H -# include -#else -#error Sorry, ChkTeX needs an _ANSI_ compiler w/stdarg.h installed to compile. -#endif - -#ifndef HAVE_VPRINTF -#error Sorry, ChkTeX needs an _ANSI_ compiler w/vprintf() to compile. -#endif - -#include -#include -#include - -#ifdef HAVE_UNISTD_H -# include -#endif - -#ifdef HAVE_LIMITS_H -# include -#endif - -#ifdef HAVE_STRINGS_H -# include -#endif - -#include "types.h" - -#ifndef LONG_MAX -# define LONG_MAX (0x7fffffff) -#endif - -#ifndef CHAR_BIT -# define CHAR_BIT (8) -#endif - -#include "FindErrs.h" - -#if defined(HAVE_FILENO) && defined(HAVE_ISATTY) -# include -#endif - -/* - * Define aliases for preprocessor statements - */ - -#if defined(__unix__) || defined(__unix) || defined(unix) -#undef __unix__ -#define __unix__ 1 -#elif defined(MSDOS) || defined(__MSDOS__) || defined(__msdos__) -#undef __MSDOS__ -#define __MSDOS__ 1 -#endif - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * NOTE: All macros below should return FALSE (0) if the input - * character is 0. - * - * The next macro should return TRUE if LaTeX (and you?) considers - * the character `c' as a space, which should be detected when - * we're checking whether commands are terminated by spaces. - * - * Note: If you wish to change this macro, you'll have to update - * the main loop in FindErrs.c as well. - */ - -#define LATEX_SPACE(c) (c > 0 && c <= ' ') - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - - - - - - -#define betw(a,b,c) ((a < b) && (b < c)) -#define within(a,b,c) ((a <= b) && (b <= c)) - -#ifndef min -# define min(a,b) ((a)<=(b)?(a):(b)) -#endif - -#ifndef max -# define max(a,b) ((a)>(b)?(a):(b)) -#endif - -#ifndef abs -# define abs(a) (a>=0?a:(-a)) -#endif - -#define LOOP(name, body) {{body} _end__##name:;} -#define LAST(name) goto _end__##name - -#define NUMBRACKETS 6 - -#define NEWBUF(name,len) \ -static char _ ## name [len + (WALLBYTES<<1)] = {0}; \ -char *name = &_ ## name[WALLBYTES] - -#define INTFAULTMSG "INTERNAL FAULT OCCURED! PLEASE SUBMIT A BUG REPORT!\n" - -#define INTERNFAULT INTFAULTMSG - -#define BITDEF1(a) BIT_ ## a -#define BITDEF2(a) FLG_ ## a = (1<'.")\ - MSG(pmNoTermData, etErr, TRUE, 0,\ - "Could not access the termcap data base.")\ - MSG(pmNoTermDefd, etErr, TRUE, 0,\ - "Terminal type `%s' is not defined.")\ - MSG(pmNoRegExp, etWarn, TRUE, 0,\ - "Regular expressions not compiled in. Please recompile.")\ - MSG(pmNoCommon, etErr, TRUE, 0,\ - "`%s' can't be a member of both `%s' and `%s'.") \ - MSG(pmNoOpenDir, etWarn, TRUE, 0, \ - "Could not open the directory `%s'.") \ - MSG(pmNoDebugFlag, etWarn, TRUE, 0, \ - "This version of doesn't support the -d flag. Please recompile.") -#undef MSG -#define MSG(num, type, inuse, ctxt, text) num, - enum PrgErrNum - { - PRGMSGS pmMaxFault - }; -#undef MSG - - extern struct ErrMsg PrgMsgs[pmMaxFault + 1]; - - struct ErrInfo - { - char *Data; - const char *LineBuf; - const char *File; - unsigned long Line, Column, ErrLen; - enum - { - efNone = 0x00, - efNoItal = 0x01, - efItal = 0x02 - } Flags; - }; - - extern char *ReadBuffer; - extern char *CmdBuffer; - extern char *TmpBuffer; - - extern const char BrOrder[NUMBRACKETS + 1]; - - extern unsigned long Brackets[NUMBRACKETS]; - - - extern FILE *OutputFile, *InputFile; - -#define OPTION_DEFAULTS \ - DEF(int, GlobalRC, TRUE) \ - DEF(int, WipeVerb, TRUE) \ - DEF(int, BackupOut, TRUE) \ - DEF(int, Quiet, FALSE) \ - DEF(int, LicenseOnly, FALSE) \ - DEF(int, UsingStdIn, FALSE) \ - DEF(int, InputFiles, TRUE) \ - DEF(int, HeadErrOut, TRUE) \ - DEF(const char *, OutputName, "") \ - DEF(const char *, PseudoInName, NULL) \ - DEF(char *, OutputFormat, VerbNormal) \ - DEF(char *, PipeOutputFormat, NULL) \ - DEF(const char *, Delimit, ":") \ - DEF(long, DebugLevel, 0) - -#define STATE_VARS \ - DEF(enum ItState, ItState, itOff) /* Are we doing italics? */ \ - DEF(int, AtLetter, FALSE) /* Whether `@' is a letter or not. */ \ - DEF(int, InHeader, TRUE) /* Whether we're in the header */ \ - DEF(int, VerbMode, FALSE) /* Whether we're in complete ignore-mode */ \ - DEF(long, MathMode, 0) /* Whether we're in math mode or not */ \ - DEF(const char *, VerbStr, "") /* String we'll terminate verbmode upon */ \ - DEF(unsigned long, ErrPrint, 0) /* # errors printed */ \ - DEF(unsigned long, WarnPrint, 0) /* # warnings printed */ \ - DEF(unsigned long, UserSupp, 0) /* # user suppressed warnings */ - -#define DEF(type, name, value) extern type name; - OPTION_DEFAULTS STATE_VARS -#undef DEF - extern struct Stack CharStack, InputStack, EnvStack; - - enum Quote - { - quLogic, - quTrad - }; - - extern enum Quote Quote; - extern int StdInTTY, StdOutTTY, UsingStdIn; - - int main(int argc, char **argv); - void PrintPrgErr(enum PrgErrNum, ...); - void ErrPrintf(const char *fmt, ...); - - extern char *PrgName; - -#endif /* CHKTEX_H */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.pdf b/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.pdf deleted file mode 100644 index 9bc5f24e639..00000000000 Binary files a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.pdf and /dev/null differ diff --git a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.tex.in b/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.tex.in deleted file mode 100644 index aa6e61d2a5e..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.tex.in +++ /dev/null @@ -1,1690 +0,0 @@ -%% -%% ChkTeX v@PACKAGE_VERSION@, LaTeX documentation for ChkTeX program. -%% Copyright (C) 1995-96 Jens T. Berger Thielemann -%% -%% This program is free software; you can redistribute it and/or modify -%% it under the terms of the GNU General Public License as published by -%% the Free Software Foundation; either version 2 of the License, or -%% (at your option) any later version. -%% -%% This program is distributed in the hope that it will be useful, -%% but WITHOUT ANY WARRANTY; without even the implied warranty of -%% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -%% GNU General Public License for more details. -%% -%% You should have received a copy of the GNU General Public License -%% along with this program; if not, write to the Free Software -%% Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -%% -%% Contact the author at: -%% Jens Berger -%% Spektrumvn. 4 -%% N-0666 Oslo -%% Norway -%% E-mail: -%% -%% NOTE: This file is written in LaTeX, and should be compiled -%% before viewing. If you don't know how to do this, consult -%% your local TeX guru. If you don't possess LaTeX, you are -%% assumed to not need this program; so there's no text version -%% of this file... -%% -%% You may still be able to view the DVI or PostScript versions of -%% this file, though, they are included in the archive. -%% - - - -\documentclass[a4paper]{article} -%latex -\usepackage{array, tabularx, verbatim, multicol} -\usepackage[T1]{fontenc} -\nonfrenchspacing -\newcounter{errornum} -\setcounter{errornum}{1} -%endlatex -\newcommand{\jtbt}{Jens~T. Berger~Thielemann} -\newcommand{\Cmd}[1]{``\texttt{#1}''} -\newcommand{\rsrc}{``\texttt{chktexrc}''} -\newcommand{\chktex}{Chk\TeX} - -%latex -\newcolumntype{Y}{>{\raggedright\arraybackslash}X} -\newcommand{\fmted}[1]{% - {\noindent\large% - \begin{tabularx}{\linewidth}{lY}% - \bf Warning \theerrornum: & \texttt{#1}% - \end{tabularx}}\stepcounter{errornum}\nopagebreak[4]} - -\newenvironment{errdesc}[1]{\noindent\fmted{#1}\begin{quote}}{\end{quote}% -\pagebreak[3]} - -\newenvironment{html}{\comment}{\endcomment} -\newenvironment{rawhtml}{\comment}{\endcomment} - -\makeatletter -\@namedef{errdesc*}#1{\begin{errdesc}{\textit{#1}}} -\@namedef{enderrdesc*}{\end{errdesc}} -\makeatother - - -\newenvironment{errexam} -{ -\vskip 0pt plus 5pt -\begin{center} -} -{\end{center}} -\columnseprule 0.1pt - -%!\newcommand{\BS}{\verb@\@} -%!\newcommand{\chktex}{ChkTeX} -%!\newcommand{\slash}{/} -%endlatex - - -\title{\chktex\ v@PACKAGE_VERSION@} -\author{Jens~T. Berger~Thielemann} -\date{\today} - - -\begin{document} -\maketitle - -%latex -\newcommand{\BS}{\char`\\} -%endlatex -\section{Introduction} - -This program has been written in frustration because some constructs in -\LaTeX\ are sometimes non-intuitive, and easy to forget. It is -\emph{not} a replacement for the built-in checker in \LaTeX\@; however it -catches some typographic errors \LaTeX\ oversees. In other words, it -is Lint for \LaTeX. Filters are also provided for checking the -\LaTeX\ parts of CWEB documents. - -It is written in ANSI C and compiles silently under GCC using -\Cmd{-Wall -ansi -pedantic} and almost all warning flags. This means -that you can compile \& use the program on your favorite machine. -Full source included. - -The program also supports output formats suitable for further -processing by editors or other programs, making errors easy to cycle through. -Software is provided for beautifully interfacing against the -AUC-\TeX\ Emacs mode, CygnusED, GoldEd and various Amiga message browsers. - -The program itself does not have any machine requirements; However compiling -for other platforms has not been done for a long time now so the code has been -removed. If interest rises it can be resurrected. - - -\section{Features} -\chktex\ begins to get quite a few bells \& whistles now. However, you -should be aware of that in most cases, all this is transparent to the user. -As you will see, \chktex\ offers the ability to adapt to many environments -and configurations. - -\begin{itemize} -\item Supports over 40 warnings. Warnings include: -%latex - \begin{multicols}{2} - \begin{flushleft} -%endlatex - \begin{itemize} - \item Commands terminated with space. Ignores \Cmd{\BS{}tt}, etc. - \item Space in front of references instead of \Cmd{\~{}}. - \item Forgetting to group parenthesis characters when - sub-\slash{}super\-scripting. - \item Italic correction (\Cmd{\BS/}) mistakes (double, - missing, unnecessary). - \item Parenthesis and environment matching. - \item Ellipsis detection; also checks whether to use - \Cmd{\BS{}dots}, \Cmd{\BS{}cdots} or \Cmd{\BS{}ldots}. - \item Enforcement of normal space after abbreviation. Detects - most abbreviations automagically. - \item Enforcement of end-of-sentence space when the last - sentence ended with capital letter. - \item Math-mode on/off detection. - \item Quote checking, both wrong types (\Cmd{"}) and wrong - direction. - \item Recommends splitting three quotes in a row. - \item Searching for user patterns. - \item Displays comments. - \item Space in front of \Cmd{\BS{}label} and similar commands. - \item Use of \Cmd{x} instead of \Cmd{\$\BS{}times\$} between numbers. - \item Multiple spaces in input which will be rendered as one - space (or multiple spaces, where that is undesirable). - \item Warns about text which may be ignored. - \item Mathematical operators typeset as variables. - \item No space in front of/after parenthesis. - \item Demands a consistent quote style. - \item Punctuation inside inner math mode/outside display math - mode. - \item Use of \TeX\ primitives where \LaTeX\ equivalents are - available. - \item Space in front of footnotes. - \item Bogus characters following commands. - \end{itemize} -%latex - \end{flushleft} - \end{multicols} -%endlatex -\item Fully customizable. Intelligent resource format makes it - possible to make \chktex\ respect your \LaTeX\ setup. Even - command-line options may be specified globally in the \rsrc\ file. -\item Supports \Cmd{\BS{}input} command; both \TeX\ and \LaTeX\ version. - Actually includes the files. \Cmd{TEXINPUTS}-equivalent search path. -\item Intelligent warning/error handling. The user may promote/mute - warnings to suit his preferences. You may also mute warnings in the - header of a file; thus killing much unwanted garbage. -\item Scripts included for checking CWEB files written in \LaTeX. - (Requires perl v5). -\item Supports both \LaTeX\ 2.09 and \LaTeXe{}. -\item Flexible output handling. Has some predefined formats and lets - the user specify his own format. Uses a \Cmd{printf()} similar - syntax. \Cmd{lacheck} compatible mode included for interfacing with - the AUC-\TeX\ Emacs mode. -\item Written in ANSI C\@. \Cmd{configure} script included for easy - setup and installation on UNIX systems. -\end{itemize} - -Still, it is important to realize that the output from \chktex\ is -only intended as a \emph{guide} to fixing faults. However, it is by -no means always correct. This means that correct \LaTeX\ code may -produce errors in \chktex, and vice versa: Incorrect \LaTeX\ code may pass -silently through. - - - -\section{Legal stuff} - -\chktex{}, documentation, installations scripts, CWEB filters and other -materials provided are copyright \copyright\ 1995--96 Jens~T. -Berger~Thielemann, unless explicitly stated otherwise. - -This program is free software; you can redistribute it and/or modify it -under the terms of the GNU General Public License as published by the Free -Software Foundation; either version 2 of the License, or (at your option) -any later version. - -This program is distributed in the hope that it will be useful, but WITHOUT -ANY WARRANTY\@; without even the implied warranty of MERCHANTABILITY or -FITNESS FOR A PARTICULAR PURPOSE\@. See the GNU General Public License for -more details. - -You should have received a copy of the GNU General Public License -along with this program; if not, write to: -\begin{quote} - The Free Software Foundation, Inc. \\ - 51 Franklin Street \\ - Fifth Floor \\ - Boston \\ - MA 02110-1301 \\ - USA -\end{quote} - - -\section{Availability} - -This program will be uploaded to CTAN\@; thus it can be -found at any mirrors of those. - -\section{Installation} - -A few words on installation on various platforms: - -\begin{description} -\item[UNIX:] Type \Cmd{configure}, \Cmd{make} and finally - \Cmd{make~install}. To make sure everything proceeded correctly, - type \Cmd{make~check}. If you don't have superuser privileges and thus - access to the default system areas, you should type - \Cmd{configure~--help} to help you set up correct paths. - - If you haven't installed any software like this before, that is - distributed in source form, here are some guidelines to help you - install it locally at your account. Please note that a mail to the - system administrator may be less work for you. - - We assume that you have put the archive (\Cmd{chktex.tar.gz}) in a - subdir of yours, with path \Cmd{\~{}/tmp}. We further assume that - your shell is \Cmd{csh} or \Cmd{tcsh}. Do the following: - - \begin{enumerate} - \item First of all, unpack the archive contents. - -\begin{verbatim} -> cd ~/tmp -> gunzip chktex.tar.gz -> tar xf chktex.tar -\end{verbatim} - - \item Now, we can configure the program. There are some - configuration options you should know about: - \begin{description} - \item[\Cmd{--enable-emacs-hack}:] Install a small file which - adds \chktex\ to the command menu of AUC-\TeX. This is to be - considered as a hack, and may break in future versions of - AUC-\TeX. It works fine under AUC-\TeX\ v2.9, though. - - This option needs the path of your elisp directory as argument, - e.g. \Cmd{--enable-emacs-hack=/home/myself/elisp} or similar. - - You'll also have to add the following line to your \Cmd{.emacs} - file: -\begin{verbatim} -(require 'chktex) -\end{verbatim} - You can now access \chktex\ from the \Cmd{Command} menu in - AUC-\TeX. To cycle through the messages, type \verb#C-x `#. - - \item[\Cmd{--enable-lacheck-replace}] This enables a quick - hack for making the AUC-\TeX\ Emacs mode use \chktex\ instead of - lacheck. This is done by installing a stub script which - ``overrides'' the original lacheck executable. - - While more stable than the previous solution, this is also - significantly less elegant --- in computing terms, this is the - ``brute force'' approach. - - \item[\Cmd{--enable-debug-info}] \chktex\ has an ability to spit - out various diagnostic messages using the \Cmd{-d} flag. This - behaviour is on by default. By adding the flag - \Cmd{--disable-debug-info} to the commandline, this will not be - compiled in. - - This may be useful if you're running short of disk space (the - time savings are neglible). - \end{description} - - If you are installing the program on your local account, use the - following command: - -\begin{verbatim} -> configure --prefix ~/ -\end{verbatim} - - Add eventual extra flags as specified above. This command will - generate a significant amount of output, this can usually be ignored. - - \item Finally, we can just build the program and install it. - -\begin{verbatim} -> make -> make install -\end{verbatim} - - \item Finished! The program is now installed and ready to use. You - may now tell other people to put your bindir in their path in - order to benefit from your work. All that remains is to make the - shell aware of your installation. - -\begin{verbatim} -> rehash -\end{verbatim} - - To make the remaining parts of your system aware of this, you'll - have to log out and re-log in, I'm afraid. However, you should delay this - until you've completed this installation procedure. - - \item If you wish to make sure that everything is OK (you ought to), - you may now ask \chktex\ to do a self-test: - -\begin{verbatim} -> make check -\end{verbatim} - - \end{enumerate} - -\item[Other platforms:] First of all, you have to copy the - \Cmd{config.h.in} file to a file named \Cmd{config.h}. Then, edit - it to reflect your system. Do the same with \Cmd{OpSys.h} (this - file has been reduced significantly). If you wish, you may define - \Cmd{DATADIR} to the path you want the global resource file to be - put. - - Now, I would suggest that you take a peak at the \Cmd{OpSys.c} - file, and edit it appropiately, for more - comfort. This should not be necessary, though, at least not the - first time. - - Finally, you may now compile and link all \verb@.c@ files. Do not - forget to define \Cmd{HAVE\_CONFIG\_H} to 1 (on the command-line, - for instance). If the \Cmd{config.h} you wish to use has another - name, define \Cmd{CONFIG\_H\_NAME} to that (in that case, don't - define \Cmd{HAVE\_CONFIG\_H}). - - Put the directory path of the \rsrc\ file in a environment variable - named \Cmd{CHKTEXRC}. The files \Cmd{deweb.in} and \Cmd{chkweb} - should be moved to a directory in your path. These files may need - further setup, as they haven't got the location of perl - initialized. - - If your compiler/the compiled program complains (or crashes!), you - may try the hints listed below. Please note that it only makes - sense to try these hints if your compiler fails to produce a working - program. - - \begin{enumerate} - \item Increase the preprocessor buffers and line buffers. The - \chktex{} sources define macros sized 3--4k (expanding to about - the same), and passes arguments sized about 1k. - \item Use the magic switch which lets us use large - \Cmd{switch(\dots)\{\dots\}} statements; some of these statements - have about 120 \Cmd{case} entries. - \item The sources require that at least the first 12 of each - identifier is significant. - \end{enumerate} -\end{description} -\paragraph{Note:} You \emph{must} install the new \rsrc\ file; \chktex\ will -fail to function otherwise! - - After doing this, you may enhance \chktex' behaviour by -reading/editing the \rsrc\ file. - -%latex -\section{Usage} - -\subsection{\chktex} - -\subsubsection{Synopsis} - -A UNIX-compliant template format follows: - -\newcommand{\Group}[1]{\mbox{[#1]}} -\begin{tabularx}{.95\linewidth}{lY} - \texttt{chktex} & \ttfamily \Group{-hiqrW} \Group{-v[0-\dots]} \Group{-l - } \Group{-[wemn] <[1-42]|all>} \Group{-d[0-\ldots]} \Group{-p - } \Group{-o } \Group{-[btxgI][0|1]} - file1 file2 \dots -\end{tabularx} - - -\subsubsection{Options} - -These are the options \chktex\ currently accepts. -Please note that single-lettered options requiring a numerical or no -argument may be concatenated. E.g.\ saying \Cmd{-v0qb0w2} is the -same as saying \Cmd{-v0~-q~-b0~-w2}, except for being less to -type. - -Enough general talk; here's a rather detailed description of all -options: -\begin{description} -\item[Misc.\ options:] General options which aren't related to some - specific subpart of \chktex. - \begin{description} - \item[\texttt{-h [--help]}] Gives you a command summary. - \item[\texttt{-i [--license]}] Shows distribution information. - \item[\texttt{-l [--localrc]}] Reads a resource-file formatted - as the global resource-file \rsrc, in addition to the global - resource-file. This option needs the name of the resource-file - as a parameter. See also \texttt{-g}. - \item[\texttt{-r [--reset]}] This will reset all settings to their - defaults. This may be useful if you use the \texttt{CMDLINE} - directive in your \rsrc\ file, and wish to do something - unusual. - \item[\texttt{-d [--debug]}] Needs a numeric argument; a bitmask - telling what to output. The values below may be added in order - to output multiple debugging info. - - \begin{tabularx}\linewidth{cX} - \bf Value & \bf Dumps\ldots\\ - 1 & All warnings available and their current status. \\ - 2 & Statistics for all lists in the resource file. \\ - 4 & The contents of all lists in the resource file. \\ - 8 & Misc.\ other status information. \\ - 16 & Run-time info (note that this isn't widely used). \\ - \end{tabularx} - The info is produced after all switches and resource files have - been processed. - - It is possible to install versions of \chktex\ that ignore this - flag; this means that it is not certain that this flag works. - \item[\texttt{-W [--version]}] Displays version information, and exits. - \end{description} -\item[Muting warning messages:] Controls whether and in what form - error messages will appear. Usually they accept a specific warning - number (e.g.\ \Cmd{-w2}), but you may also say \Cmd{all} (e.g.\ - \Cmd{-wall}) which does the operation on \emph{all} warnings. - \begin{description} - \item[\texttt{-w [--warnon]}] Makes the message number passed as - parameter a warning and turns it on. - \item[\texttt{-e [--erroron]}] Makes the message number passed as - parameter an error and turns it on. - \item[\texttt{-m [--msgon]}] Makes the message number passed as - parameter a message and turns it on. Messages are not counted. - \item[\texttt{-n [--nowarn]}] Turns the warning/error number passed - as a parameter off. - \end{description} -\item[Output control flags:] Determines the appearance and - destination of the error reports. - \begin{description} - \item[\texttt{-q [--quiet]}] Shuts up about copyright information. - \item[\texttt{-o [--output]}] Normally, all errors are piped to \texttt{stdout}. - Using this option with a parameter, errors will be sent to the - named file instead. Only information relative to the \LaTeX\ file - will be sent to that file. Memory problems and similar will as as - always be sent to \texttt{stderr}. If a file with the name given - already exists, it will be renamed to \Cmd{foobar.bak} - (\Cmd{foobar.\$cl} under MS-DOS), \Cmd{foobar} being the name of - the file. See also \Cmd{-b}. - - \item[\texttt{-v [--verbosity]}] Specifies how much and how you - wish the error reports to be displayed. This is specified in the - \rsrc\ file; we'll list the default values below. If you wish, - you may thus edit the \rsrc\ file to add or modify new formats. - - The default is mode 1 (that is, the \emph{second} entry in the - \rsrc\ file), using \texttt{-v} without any parameter will give you - mode 2. - - \begin{description} - \item[0] Will show the information in a way that should be - suitable for further parsing by \texttt{awk}, \texttt{sed} or - similar. The format is as follows: -\begin{verbatim} -File:Line:Column:Warning number:Warning message -\end{verbatim} - The colons may be replaced with another string; use the - \verb@-s@ switch for this. - - As the program does not output all errors in quite order, this - output format is also suitable for piping through \Cmd{sort}. - \item[1] Shows the information in a way which is more - comprehensible for humans, but which still doesn't need - anything but a glass tty. - \item[2] Shows the information in a fancy way, using escape - codes and stuff. It is the indeed most readable of all - modes; however, it needs proper set up of the \Cmd{ChkTeX.h} - at compilation time. UNIX boxes, however, will find the - information automatically. - \item[3] Shows the information suitable for parsing by Emacs; - this is the same format as \texttt{lacheck} uses. More formally, - it is the following: -\begin{verbatim} -"File", line Line: Warning message -\end{verbatim} - - To utilize this, type \verb@M-x compile RET@. Delete whatever - is written in the minibuffer, and type - \verb@chktex -v3 texfile.tex@, and you should be able to - browse through the - error messages. Use \verb@C-x `@ to parse the messages. - \item[4] More or less the same as \verb@-v3@, but also includes - information on where the error actually was found. Takes somewhat - longer time to parse, but much more informative in use. - \end{description} - - \item[\texttt{-f [--format]}] Specifies the format of the output. - This is done using a format similar to \Cmd{printf()}, where we - support the specifiers listed below. - - \smallskip - \newcommand{\Pf}[1]{\texttt{\%#1} &} - \begin{tabularx}{\linewidth}{cX} - \bf Code & \bf Description \\ - \Pf{b} String to print \textbf{b}etween fields (from \texttt{-s} - option).\\ - \Pf{c} \textbf{C}olumn position of error. \\ - \Pf{d} Length of error (\textbf{d}igit). \\ - \Pf{f} Current \textbf{f}ilename.\\ - \Pf{i} Turn on \textbf{i}nverse printing mode.\\ - \Pf{I} Turn off \textbf{i}nverse printing mode.\\ - \Pf{k} \textbf{k}ind of error (warning, error, message).\\ - \Pf{l} \textbf{l}ine number of error.\\ - \Pf{m} Warning \textbf{m}essage.\\ - \Pf{n} Warning \textbf{n}umber.\\ - \Pf{u} An \textbf{u}nderlining line (like the one which - appears when using \Cmd{-v1}).\\ - \Pf{r} Part of line in front of error ($\mbox{`S'} - - 1$).\\ - \Pf{s} Part of line which contains error (\textbf{s}tring).\\ - \Pf{t} Part of line after error ($\mbox{`S'} + 1$). - \end{tabularx} - \smallskip - - Other characters will be passed literally; thus you can say - \Cmd{\%\%} to achieve a single percent sign in the output. - Please note that we may introduce other specifiers in the future, - so don't abuse this feature for other characters. - - Also, note that we do \emph{not} support field lengths (yet). - This may come in the future, if I get the time\dots - - The \texttt{-v} command is implemented by indexing into the \rsrc\ - file; read that for seeing how each format is implemented. If - you find yourself using a particular format often by using the - -f switch, consider putting it in the \rsrc\ file instead. - \item[\texttt{-V [--pipeverb]}] Which entry we'll use in the \rsrc\ - file whenever \texttt{stdout} isn't a terminal. - - The default is to use the same mode as specified with the - \texttt{-v} switch; using \texttt{-V} without any parameter will give you - mode 1. - - This switch was implemented because GNU less has problems with - the escape codes \chktex\ uses for displaying inverse text. - Under UNIX, there's another way around, though, which is slightly - more elegant. Add the following line to your \Cmd{.envir} file: -\begin{verbatim} -setenv LESS -r -\end{verbatim} - - \item[\texttt{-p [--pseudoname]}] With this switch, you can provide - the filename which will be used when we report the errors. This - may be useful in scripts, especially when doing pipes. It is in - other words similar to C's \verb@#line@ directive. - - We will only assume this name for the uppermost file; files that - this one in turn \verb@\@\verb@input@ are presented under their original - names. This seems most logical to me. - - \item[\texttt{-s [--splitchar]}] String to use instead of the - colons when doing \texttt{-v0}; e.g.\ this string will be output - between the fields. - - \end{description} -\item[Boolean switches:] Common for all of these are that they - take an optional parameter. If it is \texttt{0}, the feature will - be disabled, if it is \texttt{1}, it will be enabled. All these - features are on by default; and are toggled if you don't give - any parameter. - - \begin{description} - \item[\texttt{-b [--backup]}] If you use the \texttt{-o} switch, and the - named outputfile exists, it will be renamed to \texttt{filename.bak}. - \item[\texttt{-I [--inputfiles]}] Execute \verb@\@\verb@input@ - statements; e.g.\ include the file in the input. Our input parsing - does of course nest; we use an input-stack to keep track of this. - \item[\texttt{-H [--headererr]}] Show errors found in front of the - \verb@\begin{document}@ line. Some people keep \emph{lots} of - pure \TeX\ code there, which errors can't be detected reliably - (in other words, we will in most cases just produce a lot of - garbage). - \item[\texttt{-g [--globalrc]}] Read in the global resource file. This - switch may be useful together with the \texttt{-l} option. - \item[\texttt{-t [--tictoc]}] Display a twirling baton, to show that - we're working. \texttt{-v0} does an \texttt{-t0}, too, as it assumes - that the user then uses the program non-interactively. This is - now a no-op. - \item[\texttt{-x [--wipeverb]}] Ignore the ``\verb@\verb@'' command - found within the \LaTeX\ file and its argument is completely by - the checking routines. This is done by simply overwriting them. - If you somehow don't like that (for instance, you would like to - count brackets inside those commands, too), use this switch. - \end{description} -\end{description} - - -If you don't specify any input \LaTeX-files on the commandline, we'll -read from \texttt{stdin}. To abort \texttt{stdin} input, press the -following keycombinations: - -\smallskip -\begin{tabular}{ll} - \bf Machine & \bf Key-combination \\ - UNIX & $\fbox{\texttt{Ctrl}} + \fbox{\texttt{D}}$ \\ - MS-DOS & $\fbox{\texttt{Ctrl}} + \fbox{Z}$, followed by return. -\end{tabular} -\smallskip - -By default, we're using the 1994 version of GNU's \Cmd{getopt()} -routine. - -\begin{itemize} -\item Options may be given in any order; the names of the \LaTeX-files - do not have to be the last arguments. This behaviour may be turned - off by creating an environment variable named \Cmd{POSIXLY\_CORRECT}. -\item The special argument \Cmd{--} forces an end of - option-scanning. -\item Long-named options begin with \Cmd{--} instead of \Cmd{-}. - Their names may be abbreviated as long as the abbreviation is unique - or is an exact match for some defined option. If they have an - argument, it follows the option name in the argument, separated from - the option name by a \Cmd{=}, or else the in next argument. -\end{itemize} - -\subsubsection{The \rsrc\ file} - -You should also take a look at the \rsrc\ file. As it is -self-documenting, you should be able to get the meaning of each -keyword by simply reading the file. The method for \emph{finding it}, -however, has grown rather complex. An outline is given below. - -If \chktex\ finds multiple files when searching, each and everyone -will be read in the order specified below. The \Cmd{Keyword = \{ item - item \dots \}} may thus be necessary to reset previously defined -lists. - -In this list, \Cmd{\$foo} is assumed to be the environment variable -\Cmd{foo}: - -\begin{enumerate} -\item First, we'll take a look at the directory which was specified as - \Cmd{DATADIR} during compilation. On UNIX boxes, this usually - evaluates to something similar to - \Cmd{/usr/local/share/chktexrc}, under MS-DOS it is set - to \Cmd{\BS{}emtex\BS{}data\BS{}chktexrc}. - -\item Look in the following system directories: - - \begin{tabular}{ll} - \bf Machine & \bf Directory \\ - UNIX & \Cmd{\$HOME/.chktexrc} or \Cmd{\$LOGDIR/.chktexrc} \\ - MSDOS & Program installation path - \end{tabular} - -\item Look for it in the directory pointed to by an environment - variable, as specified in the table below: - - \begin{tabularx}\linewidth{lY} - \bf Machine & \bf Directory \\ - UNIX & \Cmd{\$CHKTEXRC/.chktexrc} \\ - MSDOS & \Cmd{\$CHKTEXRC\BS{}chktexrc}, \Cmd{\$CHKTEX\_HOME\BS - chktexrc} or \Cmd{\$EMTEXDIR\BS{}data\BS{}chktexrc} - \end{tabularx} - -\item Look for it in the current directory. On UNIX boxes, - we expect the filename to be \Cmd{.chktexrc}; on other machines - \Cmd{chktexrc}. - -\end{enumerate} - -If you for some reason wish to undo what the previous files may have -done, you may say \Cmd{CmdLine \{ -g0 -r \}} somewhere in the \rsrc\ -file; this will reset all previous settings. - - -\subsubsection{Hints} -I've tried to collect some advice that may be useful --- if you have a -favourite hint, feel free to send it to me! - -\begin{itemize} -\item If you use \Cmd{german.sty}; it may be wise to put \Cmd{-n18} in - the \Cmd{CmdLine} entry in the \rsrc\ file. This will probably reduce - the amount of false warnings significantly. -\item Put \Cmd{-v} in the \Cmd{CmdLine} entry of the \rsrc\ file; this - makes the fancy printing the default. -\item If you're working on a large project, it may pay off to make a - local resource file which is included in addition to the global - one. In this one, add the necessary info to reduce the amount of - false warnings --- these usually don't do anything but hide the - real warnings. -\item Create a total ignore environment, which \chktex\ will ignore - completely. In here, you can place all that code which outsmarts - \chktex\ completely. For instance, add the following lines at the top - of your \LaTeX\ file: -\begin{verbatim} -% ChkTeX will ignore material within this environment -\newenvironment{ignore}{}{} -\end{verbatim} - In addition, you should add the item \Cmd{ignore} to the \Cmd{VerbEnvir} - entry in the \rsrc\ file. -\end{itemize} -\subsubsection{Bugs} - -No fatal ones, I think, but the program currently has some problems when a -\LaTeX\ command/parameter stretch over a two lines --- some extra spaces -may be inserted into the input. I regard the program as fairly well -tested; using the SAS/C \Cmd{cover} utility I was able to make sure that -approximately 95\% of the code has actually been run successfully in the -final version. This does indeed leave some lines; most of these are -procedure terminating brackets or ``can't happen'' lines, though. - -We've got some problems when isolating the arguments of a command. -Although improved, it will certainly fail in certain cases; \chktex\ -can for instance not handle arguments stretching over two lines. This -also means that \Cmd{WIPEARG} entries in the \rsrc\ file will only -have the first half of their argument wiped if the argument stretches -over two lines. We will, however, take care not to wipe parenthesis -in such cases, in order to avoid false warnings. - -Before submitting a bug report, please first see whether the problem can be -solved by editing the \rsrc\ file appropiately. - - - -\subsection{ChkWEB} - -This shell script is provided for checking CWEB files. The template is -as follows: -\begin{verbatim} -chkweb [options] file1 file2 ... -\end{verbatim} -As you may see from the script, it is only a trivial interface towards -\texttt{deweb} and \chktex. It does not support any individual options -on the command line --- all options found will be passed onto \chktex. -If \Cmd{--} or a filename is found, the remaining parameters will be -ignored. -The only real intelligence it features is that it will try to append -\verb@.w@ to filenames it can't find. - -If no filenames are given, we will read from \texttt{stdin}. - -\subsection{DeWEB} - -This program strips away C code and CWEB commands from CWEB sources. -It is called with the following synopsis: - -\begin{verbatim} -deweb file1 file2 ... -\end{verbatim} - -\texttt{deweb} filters away all C \&\ CWEB commands from a CWEB source -code. This leaves only the \LaTeX\ code. This stripped code, in turn, -may then be passed to a suitable syntax checker for \LaTeX, like -\chktex\ and \texttt{lacheck}, or spell-checkers like \texttt{ispell}. - -When \texttt{deweb} strips away the C code from your CWEB source, it tries to -preserve line breaks. This means that the error reports from {\it your - favorite tool\/} will be correct regarding to line numbers. In most -cases, the column position will also be correct. This significantly -simplifies finding the errors in the \LaTeX\ source (in contrast to the -output from \texttt{cweave}, which output is truly difficult to figure -anything out from). - -\texttt{deweb} accepts a list of filenames on the argument line, and will send -its output to \texttt{stdout}. If no filenames are given, it will read from -stdin, acting as a filter. No options are currently accepted. - -Macho users may try to pipe the output from \texttt{deweb} directly into -\LaTeX, theoretically, this should work. This would ease the debugging of -the \LaTeX\ code significantly, as when \LaTeX\ complains about wrong -syntax, you'll be able to find the erroneous line much more easily. Don't -expect that the output looks very much like the final one, though. - -\texttt{deweb} should now understand all correct \texttt{CWEB} opcodes. If it -complains about not understanding a correct opcode, please inform the -author. - -\subsubsection{Bugs} - -\texttt{deweb} will not even \emph{compile} under Perl versions before perl -v5. Unfortunately, this means that we can't even tell the user why we -failed; Perl will just complain about not being able to compile the -regexps. - -\section{Explanation of error messages} -Below is a description of all error-messages \chktex\ outputs. -Error messages set in {\it italic type\/} are turned off by default. -Where margin paragraphs are listed in the text, they refer to the -keyword in the \rsrc\ file which controls the discussed warning. - -\newcommand\Keyword[1]{\marginpar{\texttt{\hfill\\ #1}}} - -\smallskip\pagebreak[2] -\Keyword{Silent} -\begin{errdesc}{Command terminated with space.} - You tried to terminate a command with a blank space. Usually, this - is an error as these are ignored by \LaTeX. In most cases, you would - like to have a real space there. - - \begin{errexam} - \verb@\LaTeX@\underline{\tt }\verb@is a typesetter.@ \\* - \LaTeX is a typesetter. \\* - \smallskip - \verb@\LaTeX\ is a typesetter.@ \\* - \LaTeX\ is a typesetter. \\* - \end{errexam} -\end{errdesc} - -\Keyword{Linker} -\begin{errdesc}{Non-breaking space (`\~{}') should have been used.} - When reading a document, it is not very pretty when references are - split across lines. If you use the \verb@~@ character, \LaTeX\ will - assign a very high penalty for splitting a line at that point. - \chktex\ issues this warning if you have forgot to do this. - - \begin{errexam} - \verb@Please refer to figure@\underline{\tt\ }\verb@\ref{foo}.@ \\* - Please refer to figure 11. \\* % Gotta cheat here! :) - \smallskip - \verb@Please refer to figure~\ref{foo}.@ \\* - Please refer to figure~11. \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{You should enclose the previous parenthesis with `\{\}'.} - - This is a warning which you may ignore, but for maximum aestethic - pleasure, you should enclose your bracket characters with `\{\}'s. - - \begin{errexam} - \verb@$@\underline{\tt\ }\verb@[(ab)^{-1}]@\underline{\tt\ }\verb@\^{-2}$@ \\* - $[(ab)^{-1}]^{-2}$ \\* - \smallskip - \verb@${[{(ab)}^{-1}]}^{-2}$@ \\* - ${[(ab)^{-1}]}^{-2}$ \\* - \end{errexam} -\end{errdesc} - -\Keyword{Italic\\ItalCmd\\NonItalic} -\begin{errdesc}{Italic correction (`\BS/') found in non-italic - buffer.} - If you try to use the \verb@\/@ command when \chktex\ believes that - the buffer is not outputted as italic, you'll get this warning. - - \begin{errexam} - \verb@This is an@\underline{\tt\BS/}\verb@ example@ \\* - This is an\/ example. \\* - \smallskip - \verb@This is an example.@ \\* - This is an example. \\* - \end{errexam} -\end{errdesc} - -\Keyword{Italic\\ItalCmd\\NonItalic} -\begin{errdesc}{Italic correction (`\BS/') found more than once.} - If the buffer is italic, and you try to use the \verb@\/@ command - more than once, you'll get this warning. - - \begin{errexam} - \verb@This {\it example\/@\underline{\tt\BS/}\verb@} is not amusing.@ \\* - This {\it example\/\/} is not amusing. \\* - \smallskip - \verb@This {\it example\/} is not amusing.@ \\* - This {\it example\/} is not amusing. \\* - \end{errexam} -\end{errdesc} - -\Keyword{Italic\\ItalCmd\\NonItalic} -\begin{errdesc}{No italic correction (`\BS/') found.} - You get this error if \chktex\ believes that you are switching from - italic to non-italic, and you've forgot to use the \verb@\/@ command - to insert that extra little spacing. If you use the \Cmd{em} option, - you may ignore this warning. - - \begin{errexam} - \verb@This {\it example@\underline{\tt\ }\verb@} is not amusing, either.@ \\* - This {\it example} is not amusing, either. \\* - \smallskip - \verb@This {\it example\/} is not amusing, either.@ \\* - This {\it example\/} is not amusing, either. \\* - \end{errexam} -\end{errdesc} - -\Keyword{IJAccent} -\begin{errdesc}{Accent command `command' needs use of `command'.} - If you're using accenting commands, `i' and `j' should lose their - dots before they get accented. This is accomplished by using the - \verb@\i@, \verb@\j@, \verb@\imath@ and \verb@\jmath@ command. - - \begin{errexam} - \verb@This is an example of use of accents: \'{@\underline{\tt i}\verb@}.@ \\* - This is an example of use of accents: \'{i}. \\* - \smallskip - \verb@This is an example of use of accents: \'{\i}.@ \\* - This is an example of use of accents: \'{\i}. \\* - \end{errexam} -\end{errdesc} - -\Keyword{HyphDash\\NumDash\\WordDash} -\begin{errdesc}{Wrong length of dash may have been used.} - This warning suggests that a wrong number of dashes may have been - used. It does this by classifying the dash according to the the - character in front and after the dashes. - - If they are of the same type, \chktex\ will determine which keyword - to use in the \rsrc\ file. If not, it will shut up and accept that - it doesn't know. - - \begin{tabular}{ll} - \bf Character type & \bf Keyword in \rsrc\ file \\* - Space & \texttt{WordDash} \\* - Number & \texttt{NumDash} \\* - Alphabetic character & \texttt{HyphDash} \\* - \end{tabular} - - This is more or less correct, according to my references. Hopefully - this check can be even more improved (suggestions?). - - \begin{errexam} - \verb@It wasn't anything @\underline{\tt-}\verb@ just a 2@\underline - {\tt---}\verb@3 star@\underline{\tt--}\verb@shots.@ \\* - It wasn't anything - just a 2---3 star--shots. \\* - \smallskip - \verb@It wasn't anything --- just a 2--3 star-shots@ \\* - It wasn't anything --- just a 2--3 star-shots. \\* - \end{errexam} -\end{errdesc} - - -\fmted{`\%s' expected, found `\%s'.} -\begin{errdesc}{Solo `\%s' found.} - Either brackets or environments don't match. - \chktex\ expects to find matching brackets/environments in the - same order as their opposites were found, and no closing delimiters - which haven't been preceded by an opening one. - - While bracket matching is not an explicit error, it is usually a - sign that something is wrong. - -\end{errdesc} - -\Keyword{CenterDots\\LowDots} -\begin{errdesc}{You should use `\%s' to achieve an ellipsis.} - Simply typing three \Cmd{.} in a row will not give a perfect spacing - withing the between the dots. The \verb@\ldots@ is much more - suitable for this. - - In math mode, you should also distinguish between \verb@\cdots@ and - \verb@\ldots@; take a look at the example below. - - \begin{errexam} - \newcommand{\td}{\underline{\tt...}} - \verb@Foo@\td\verb@bar. $1,@\td\verb@,3$. $1+@\td\verb@+3$. $1,@% - \underline{\tt\BS{}cdots}\verb@,3$.@ \\* - Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. \\* - \smallskip - \verb@Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$.@ \\* - Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$. \\ - \end{errexam} -\end{errdesc} - -\Keyword{Abbrev} -\begin{errdesc}{Interword spacing (`\BS\ ') should perhaps be used.} - - One of the specified abbreviations were found. Unless you have - previously said \verb@\frenchspacing@, you'll have incorrect - spacing, which one should avoid if possible. - - \begin{errexam} - \verb@This is an example, i.e.@\underline{\tt\ }\verb@an demonstration.@ \\* - This is an example, i.e. an demonstration. \\* - \smallskip - \verb@This is an example, i.e.\ an demonstration.@ \\* - This is an example, i.e.\ an demonstration. \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{Intersentence spacing (`\BS{}@') should perhaps be used.} - - \LaTeX' detection of whether a period ends a sentence or not, is - only based upon the character in front of the period. If it's - uppercase, it assumes that it does not end a sentence. While this - may be correct in many cases, it may be incorrect in others. - \chktex\ thus outputs this warning in every such case. - - \begin{errexam} - \verb@I've seen an UFO!@\underline{\tt\ }\verb@Right over there!@ \\* - I've seen an UFO! Right over there! \\* - \smallskip - \verb+I've seen an UFO\@! Right over there!+ \\* - I've seen an UFO\@! Right over there! \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{Could not find argument for command.} - - \chktex\ will in some cases need the argument of a function to - detect an error. As \chktex\ currently processes the \LaTeX\ file on - a line-by-line basis, it won't find the argument if the command - which needed it was on the previous line. On the other hand, this - \emph{may} also be an error; you ought to check it to be safe. - - \begin{errexam} - \verb@$\hat$@ \\* - This will give a \LaTeX\ error\dots \\* - \smallskip - \verb@$\hat{a}$@ \\* - $\hat{a}$ \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{No match found for `\%s'.} - - This warning is triggered if we find a single, \emph{opening} - bracket or environment. While bracket matching is not an explicit - error, it is usually a sign that something is wrong. - -\end{errdesc} - -\Keyword{MathEnvir} -\begin{errdesc}{Mathmode still on at end of LaTeX file.} - This error is triggered if you at some point have turned on - mathmode, and \chktex\ couldn't see that you remembered to turn it - off. - -\end{errdesc} - -\begin{errdesc}{Number of `character' doesn't match the number of `character'.} - - Should be self-explanatory. \chktex\ didn't find the same number of - an opening bracket as it found of a closing bracket. - -\end{errdesc} - -\begin{errdesc}{You should use either `` or '' as an alternative to `\,"\,'.} - Self-explanatory. Look in the example, and you'll understand why. - - \begin{errexam} - \verb@This is an @\underline{\tt"}\verb@example@\underline{\tt"} \\* - This is an "example" \\* - \smallskip - \verb@This is an ``example''@ \\* - This is an ``example'' \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{You should use "'" (ASCII 39) instead of - "'" (ASCII 180).} On some keyboards you might get the wrong quote. - This quote looks, IMHO, \emph{ugly} compared to the standard - quotes, it doesn't even come out as a quote! Just see in the - example. - - - \begin{errexam} - \verb@``There@\underline{\tt '}\verb@s quotes and there@\underline{\tt '}\verb@s quotes@ - \underline{\tt ''} \\* % '' - ``There´s quotes and there´s quotes´´ \\* % '' - \smallskip - \verb@``There's quotes and there's quotes''@ \\* - ``There's quotes and there's quotes'' \\* - \end{errexam} -\end{errdesc} - -\Keyword{Userwarn} -\begin{errdesc}{User-specified pattern found.} - A substring you've specified using \texttt{USERWARN} in the \rsrc\ file, - has been found. -\end{errdesc} - -\begin{errdesc*}{This command might not be intended.} - I implemented this because a friend of mine kept on making these - mistakes. Easily done if you haven't gotten quite into the syntax - of \LaTeX. - - \begin{errexam} - \verb@\LaTeX\ is an extension of \TeX@\underline{\tt\BS.}\verb@ Right?@ \\* - \LaTeX\ is an extension of \TeX\. Right? \\* - \smallskip - \verb@\LaTeX\ is an extension of \TeX. Right?@ \\* - \LaTeX\ is an extension of \TeX. Right? \\* - \end{errexam} -\end{errdesc*} - -\begin{errdesc*}{Comment displayed.} - \chktex\ dumps all comments it finds, which in some cases is useful. - I usually keep all my notes in the comments, and like to review them - before I ship the final version. For commenting out parts of the - document, the \Cmd{comment} environment is better suited. - -\end{errdesc*} - - -\begin{errdesc}{Either ''\BS,' or '\BS,'' will look better.} - - This error is generated whenever you try to typeset three quotes in - a row; this will not look pretty, and one of them should be - separated from the rest. - - \begin{errexam} - \underline{\tt```}\verb@Hello', I heard him said'', she remembered.@ \\* - ```Hello', I heard him said'', she remembered. \\* - \smallskip - \verb@``\,`Hello', I heard him said'', she remembered.@ \\* - ``\,`Hello', I heard him said'', she remembered. - \end{errexam} -\end{errdesc} - -\Keyword{PostLink} -\begin{errdesc}{Delete this space to maintain correct pagereferences.} - This message, issued when a space is found in front of a - \verb@\index@, \verb@\label@ or similar command (can be set in the - \rsrc\ file). Sometimes, this space may cause that the word and the - index happens on separate pages, if a pagebreak happens just there. - - You might also use this warning to warn you about spaces in front of - footnotes; however, the warning text may not be entirely correct - then. - - \begin{errexam} - \verb@Indexing text@\underline{\tt\ }\verb@\index{text} is fun!@ \\* - \smallskip - \verb@Indexing text\index{text} is fun!@ \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{You might wish to put this between a pair of `\{\}'} - - This warning is given whenever \chktex\ finds a \Cmd{\^{ }}' or a - \Cmd{\_} followed by either two or more numberic digits or two or - more alphabetic characters. In most situations, this means that - you've forgotten some \{\}'s. - - \begin{errexam} - \verb@$5\cdot10^@\underline{\tt10}\verb@$@ \\* - $5\cdot10^10$ \\* - \smallskip - \verb@$5\cdot10^{10}$@ \\* - $5\cdot10^{10}$ - \end{errexam} -\end{errdesc} - -\begin{errdesc}{You ought to remove spaces in front of punctuation.} - - This warning is issued if \chktex\ finds space in front of an - end-of-sentence character. - - \begin{errexam} - \verb@Do you understand@\underline{\tt\ }\verb@?@ \\* - Do you understand ? \\* - \smallskip - \verb@Do you understand?@ \\* - Do you understand? \\* - \end{errexam} -\end{errdesc} - -\begin{errdesc}{Could not execute LaTeX command.} - - Some \LaTeX\ commands will be interpreted by \chktex; however, some - of them are sensible to errors in the \LaTeX\ source. Most notably, - the \verb@\@\verb@input@ command relies on that the input file exists\dots - -\end{errdesc} - -\Keyword{Italic\\ItalCmd\\NonItalic} -\begin{errdesc}{Don't use \BS/ in front of small punctuation.} - Italic correction should generally \emph{not} be used in front of - small punctuation characters like `.' and `,'; as it looks better - when the preceding italic character leans ``over'' the punctum or - comma. - - \begin{errexam} - \verb@It is just a {\it test@\underline{\tt\BS/}\verb@}, don't think anything else.@ \\* - It is just a {\it test\/}, don't think anything else. \\* - \smallskip - \verb@It is just a {\it test}, don't think anything else.@ \\* - It is just a {\it test}, don't think anything else. - \end{errexam} -\end{errdesc} - -\begin{errdesc}{\$\BS{}times\$ may look prettier here.} - In ASCII environments, it is usual to use the `x' character as an - infix operator to denote a dimension. The mathemathical symbol - $\times$ provided by the \verb@$\times$@ command is better suited for - this. - - \begin{errexam} - \verb@The program opens a screen sized 640@\underline{\tt x}\verb@200 pixels.@ \\* - The program opens a screen sized 640x200 pixels. \\* - \smallskip - \verb@The program opens a screen sized $640\times200$ pixels.@ \\* - The program opens a screen sized $640\times200$ pixels. - \end{errexam} -\end{errdesc} - -\begin{errdesc*}{Multiple spaces detected in output.} - - This warning, intended for the novice, will remind you that even if - you \emph{type} multiple spaces in your input, only a single space - will come out. Some ways to come around this is listed below. - - \begin{errexam} - \verb@White is a beautiful colour.@ \\* - White is a beautiful colour. \\* - \smallskip - \verb@White~~~~~{ }{ }{ }\ \ \ is a beautiful colour.@ \\* - White~~~~~{ }{ }{ }\ \ \ is a beautiful colour. \\ - \end{errexam} -\end{errdesc*} - -\Keyword{VerbEnvir} -\begin{errdesc}{This text may be ignored.} - Certain implementations of the \verb@verbatim@ environment and - derivations of that, ignore all text on the same line as - \verb@\end{verbatim}@. This will warn you about this. - - -\end{errdesc} - -\fmted{Use ` to begin quotation, not '.}\hfill\\ -\fmted{Use ' to end quotation, not `.}\hfill\\ -\begin{errdesc}{Don't mix quotes.} - - Proper quotations should start with a \verb@`@ and end with a - \verb@'@; anything else isn't very pretty. Both these warnings are - relative to this; look in the example below. - - \begin{errexam} - \verb@There are @\underline{\tt`'}% - \verb@examples'' and there are ``examples@\underline{\tt``}\verb@.@ \\* - There are `'examples'' and there are ``examples``. \\* - \smallskip - \verb@There are ``examples'' and there are ``examples''.@ \\* - There are ``examples'' and there are ``examples''. - \end{errexam} -\end{errdesc} - -\Keyword{MathRoman} -\begin{errdesc}{You should perhaps use `cmd' instead.} - Most mathematical operators should be set as standard roman font, - instead of the math italic \LaTeX\ uses for variables. For many - operators, \LaTeX\ provides a pre-defined command which will typeset - the operator correctly. Look below for an illustration of the point. - - \begin{errexam} - \verb@$@\underline{\tt sin}\verb@^2 x + @\underline{\tt cos}\verb@^2 x = 1$@ \\* - $sin^2 x + cos^2 x= 1$ \\* - \smallskip - \verb@$\sin^2 x + \cos^2 x = 1$@ \\* - $\sin^2 x + \cos^2 x = 1$ - \end{errexam} -\end{errdesc} - -\fmted{You should put a space in front of/after parenthesis.}\hfill\\ -\begin{errdesc}{You should avoid spaces in front of/after parenthesis.} - Outside math mode, you should put a space in front of any group of - opening parenthesis, and no spaces after. If you have several after - each other, you should of course not put a space in between each; - look in the example below. Likewise, there should not be spaces in - front of closing parenthesis, but there should be at least one - after. - - - - \begin{errexam} - \verb@This@\underline{\tt( }\verb@an example@\underline{\tt( }% - \verb@Nuff said@\underline{\tt\ }\verb@)), illustrates@\underline{\tt( }% - \verb@``my''@\underline{\tt\ )}\verb@point.@\\ - This( an example( Nuff said )), illustrates( ``my'' )point. \\ - \smallskip - \verb@This (an example (Nuff said)), illustrates (``my'') point.@\\ - This (an example (Nuff said)), illustrates (``my'') point.\\ - \end{errexam} -\end{errdesc} - -\Keyword{QuoteStyle} -\begin{errdesc}{You should not use punctuation in front of/after - quotes.} - % - For best looking documents, you should decide on how you - wish to put quotes relative to punctuation. \chktex\ recognizes two - styles; you may specify which you use in the \rsrc\ file. A - description on each style follows: - \begin{description} - \item[Traditional:] This style is the most visually pleasing. It - always puts the punctuation \emph{in front of} the quotes, which - gives a continuous bottom line. - - However, it may in certain cases be ambigious. Consider the - following example from a fictious \Cmd{vi(1)} - tutorial (quote taken from the Jargon file): - \begin{center} - \verb@Then delete a line from the file by typing ``dd.''@ \\* - Then delete a line from the file by typing ``dd.'' - \end{center} - That would be very bad --- because the reader would be prone to - type the string d-d-dot, and it happens that in \Cmd{vi(1)} dot - repeats the last command accepted. The net result would be to - delete \emph{two} lines! This problem is avoided using logical - style, described below. - \pagebreak[3] - \item[Logical:] This style uses quotes as balanced delimiters like - parentheses. While this is not the most visual pleasing, it is - can't be misunderstood. The above sentence would then become: - \nopagebreak - \begin{center} - \verb@Then delete a line from the file by typing ``dd''.@ \\* - Then delete a line from the file by typing ``dd''. - \end{center} - \nopagebreak - \end{description} - -\end{errdesc} - -\begin{errdesc}{Double space found.} - This warning is triggered whenever \chktex\ finds a space in front - of a hard space, or vice versa. This will be rendered as two spaces - (which you usually don't wish). - - \begin{errexam} - \verb@For output codes, see table@\underline{\tt\ }% - \verb@~@\underline{\tt\ }\verb@\ref{foo}.@ \\* - For output codes, see table ~ 1.1.\\* - \smallskip - \verb@For output codes, see table~\ref{foo}.@ \\* - For output codes, see table~1.1. - \end{errexam} -\end{errdesc} - -\Keyword{MathEnvir} -\begin{errdesc}{You should put punctuation outside inner/inside - display math mode.} - As recommended in the \TeX{}book, you should try to put punctuation - outside inner math mode, as this is gets formatted better. - - Similarily, you should let any final punctuation in display math - mode end up within it. Look at the following example, which was - taken from the \TeX{}book: - \begin{errexam} - \verb@for $x = a@\underline{\tt,}\verb@b$, or $c$.@\\* - for $x = a,b$, or $c$. \\* - \smallskip - \verb@for $x = a$, $b$, or $c$.@\\* - for $x = a$, $b$, or $c$.\\* - \end{errexam} - -\end{errdesc} - -\Keyword{Primitives} -\begin{errdesc*}{You ought to not use primitive TeX in LaTeX code.} - This warning is triggered whenever you use a raw \TeX\ command - which has been replaced by a \LaTeX\ equivalent. If you consider - yourself a purist (or want to be sure your code works under \LaTeX3), - you should use the \LaTeX\ equivalent. -\end{errdesc*} - -\Keyword{NotPreSpaced} -\begin{errdesc}{You should remove spaces in front of `\%s'} - - Some commands should not be prepended by a space character, for cosmetical - reasons. This notes you of this whenever this has happened. - - \begin{errexam} - \verb@This is a footnote@\underline{\tt\ }\verb@\footnotemark[1] mark.@\\* - This is a footnote ${}^1$ mark. \\* - \smallskip - \verb@This is a footnote\footnotemark[1] mark.@\\* - This is a footnote${}^1$ mark. \\* - \end{errexam} -\end{errdesc} - -\Keyword{NoCharNext} -\begin{errdesc}{`\%s' is normally not followed by `\%c'.} - \LaTeX' error message when calling \verb@\left \{@ instead of - \verb@left \{@ is unfortunately rather poor. This warning detects - this and similar errors. -\end{errdesc} - -\section{Future plans} - -In a somewhat prioritized sequence, this is what I'd like to put into the -program --- if I have the time. - -\begin{itemize} -\item Do a final fix for maths mode. Currently, \chktex\ doesn't - recognize constructions like - \verb@$$a+b\text{for $a \leq 0$}$$@, i.e.\ embedded math mode. - -\item Support for regular expressions as user patterns. I'll do it at - once I get the GNU \Cmd{rx} package up and running (it doesn't - produce correct include files). - -\item De-linearize the checker. Currently, it works on a line-by-line - basis, in most respects, at least. I hope to be able to remove this - barrier; as this will reduce the amount of false warnings - somewhat. - -\item Probably some more warnings/errors; just have to think them out - first. Suggestions are appreciated --- I've ``stolen'' most that - similar programs provides, and am running out of ideas, really. - - It would also be nice to investigate the field of ``globally'' - oriented warnings; i.e.\ warnings regarding the document as a - whole. Currently, \chktex\ operates mainly on a local/``greedy'' - basis. - - If you have suggestions/ideas on this topic, they're certainly - welcome, including references to literature. - -\item Fix a few more bugs. -\end{itemize} - -\section{Notes} - -\subsection{Wish to help?} - -As most other living creatures, I have only a limited amount of time. If -you like \chktex\ and would like to help improving it, here's a few things -I would like to receive. The following ideas are given: - -\begin{itemize} -\item Does anyone have a $\mbox{\LaTeX}\rightarrow \mbox{\texttt{troff}}$ - conversion program? It would be really nice if I could extract the - relevant sections from this manual, and present them as a man page. - I will not, however, convert this manual to \TeX{}info in order to - be able to do this; IMHO \TeX{}info documents have far too limited - typographic possibilities. - - This doesn't mean that I'm not willing to restructure the document - at all. This manual already uses some kind of preprocessing in order - to achieve HTML output via \LaTeX2\texttt{html}, I'm willing to do the - same in order to produce \texttt{troff} output. - -\item Help me port the program! This is a prioritized one. It's no fun - writing ANSI C when people haven't got a C compiler. - - Of course, I'll provide whatever help necessary to modify the sources - to fit to the new platform. Take contact if you're interested. I will - include your compiled binary in the distribution, and give you - credit where appropiate. - - Just one request: If you have to modify the sources in order to make - \chktex\ compile \& work on the new platform, \emph{please} enclose your - changes in something like \Cmd{\#ifdef \_\_PLATFORM\_\_\dots code\dots\#endif}! - It makes life so much easier later, when we try to merge the two - source trees. - -\item Reports on problems configuring and compiling \chktex\ on supported - (and unsupported) systems are welcomed. - -\item Filters for other file formats. I do believe that there are - several formats using \LaTeX\ for its formatting purposes, combining - that with something else. If you can write a program or script which - filters everything away but the \LaTeX\ code, it will surely be - appreciated (and included). Look at the \verb@deweb@ script to see - what I mean. - -\item Arexx interfaces for other editors are also welcomed; these - should be rather fast to write. They should to the following: - \begin{enumerate} - \item Get the filename of the active file. - \item If possible, save the file to disk if there has been any - changes. - \item Call the program \Cmd{ChkTeX.rexx} with the filename as the - only parameter. - \end{enumerate} - -\item If somebody out there actually possesses (and uses) GoldED, it - would be nice if they checked whether the ARexx script included - actually work. If not, please send me a fixed copy; perhaps also - one which supports point 2 above, too. If it does work, then please - tell me so, so I can remove this item. - - I don't have GoldEd in my possession; the script was just modelled - after Juergen Zeschky's, (\texttt{}) - $\mbox{PGP}\leftrightarrow\mbox{GoldED}$ interface. - -\item If you update the \rsrc\ file in anyway that is not strictly - local, I would appreciate to receive your updated version. - -\item Suggestions for new warnings are always welcomed. Both formal - (i.e.\ regexps or similar) and non-formal (plain English) descriptions - are welcomed. -\end{itemize} - -Of course, people doing any of this will be mentioned in this document, and -thus receive eternal glory and appreciation. - -\subsection{Caps and stuff} - -This program uses the \Cmd{getopt()} routine, as supplied from GNU\@. -The source included in this distribution has been modified slightly. -To make the use of C2LOCAL easier, portions which were -\verb@#ifdef@'ed out, have now been commented out. - -Where trademarks have been used, the author is aware of that they -belong to someone, and has tried to stick to the original caps. - -\section{About the author} - -A quick summary of who I am and what I do: - -I'm 21 years old, and live in Oslo, the capital of Norway. I'm -currently studying maths and computer science at the -University~of~Oslo; planning to get a degree within mathematical -modeling, with a dash of physics and emphazing the computer part of -the study. More precisely, in autumn'96 my studies consist of -mathematical analysis, statistics \& probability calculations plus -studying the relationship between society and computers. - -At home I now possess 4 computers, of which 1 is regular use: A -vanilla Amiga 1200, expanded only by a HD\@. The others are a -\texttt{80286} PC and an Amiga 500, both semi-out-of-order. The last -one is a Commodore VIC-20, which for some peculiar reason never seems -to be used. Plans are to get a Linux-capable PC, though. - -Most of the time in front of these computers (including SGI Indy's and -SPARC stations at our university) is spent on C and shell programming, -plus some text-processing. - - % I am also involved in writing the document - % for {\sc Isaac} --- Interactive Simulation as an Alternative to - % Advanced Calculations. This is planned to help newcomers to physics, - % by providing a computer program which enables one to simulate most - % experiments relating to classical mechanics. - % - -C and shell programming are not my only knowledge areas regarding -computers, however. I write the following languages more or less: -Perl, Motorola \texttt{68000} assembly code, ARexx, Simula, C++, \LaTeX, -HTML, AmigaGuide, Amos Basic and Installer LISP\@. Once I also -mastered Commodore Basic V2, the ``language'' included with my VIC-20. - -However, I also try to not to end up as a computer nerd. Thus, in -addition to the compulsory (?) interest for computers, I am a scout. -Still running into the woods, climbing the trees, falling down and -climbing up once more, in other words. To be more specific, I am a -now a troop leader for `Ulven' scout-group; Norwegian Scouts -Association. I am also a active rover in `V{\aa}lerenga' scout-group. - -Certainly a lot more to tell (I play the piano and like cross-country -skiing, for instance); but I'll stop here before you fall -asleep\dots - - -\section{Thanks} - -The author wishes to thank the following people (in alphabetical order): - -\def\Name#1#2{% -\item[] - \setbox0=\hbox{ - \begin{tabular}{l} - \textbf{#1} \\ - \texttt{#2} \\ - \end{tabular} - } \usebox0\\ } - -\begin{description} - - \Name{Russ Bubley}{russ@scs.leeds.ac.uk} - He has been the main external beta-tester for this program, sending - me loads and loads of understandable and reproducible bug reports. - If you somehow think that \chktex\ is well-behaved and free from - bugs, send warm thoughts to Russ. He has also provided ideas for - enhanced checks and so forth. - - In addition, he sent me a huge list of 238 common English - abbreviations, for inclusion in the \rsrc\ file! Together with the - enhanced abbreviation recognizer, I do now believe most - abbreviations should be catched\dots - - Finally, he has also given me valuable hints for improving the - program's outputting routine, and given me lots of suggestions for - filtering unnecessary/false warnings away. - - \Name{Gerd B\"ohm}{Gerd.Boehm@physik.uni-regensburg.de} - Improved and bug-fixed the MS-DOS port of \chktex\ v1.4, sending me - ready-to-yank code patches. The original port didn't respect all - the peculiarities of the MS-DOS file-system, unfortunately. - - \Name{Lars Frellesen}{frelle@math-tech.dk} Sent a few bug reports - regarding the filtering of messages. He has also helped me to - expand the \Cmd{SILENT} keyword in the \rsrc\ file. - - \Name{Wolfgang Fritsch}{fritsch@hmi.de} - Author of the OS/2 port, which he did using the emx compiler. - Please direct questions regarding strictly to that port to him (I - would like to receive a carbon copy, though). - - \Name{Stefan Gerberding}{stefan@inferenzsysteme.informatik.th-darmstadt.de} - First one to report the Enforcer hit in v1.2 when using \chktex\ as - a pipe. Also came with suggestions to make \chktex\ more easily - compile on early gcc compilers. - - He has also kept on beta-testing later versions of \chktex, giving - me bug-reports and enhancements requests. - - \Name{Kasper B. Graversen}{kbg2001@internet.dk} Lots of creative - suggestions and improvements. Several of the warnings implemented - were based on his ideas. In addition, he has given advice for - improving the existing warnings. - - Has also provided some OS-oriented code. - - \Name{Frank Luithle}{f\_luithle@outside.sb.sub.de} - Wrote a translation for v1.0. Unfortunately, he remained unreachable - after that\dots:-/ - - \Name{Nat}{nat@nataa.frmug.fr.net} - Reported the same bug as Gerberding. In addition, he taught me a - few tricks regarding the use of gcc + made me understand that the - ANSI standard isn't unambigious; at least the \verb@getenv()@ call - seem to be open for interpretations. Many possible - incompatibilities have been removed due to these lessons. - - \Name{Michael Sanders}{sanders@umich.edu} - Has found some of the bugs in this beast; both obscure and - long-lived. Has also provided motivation to clarify this document. - - \Name{Bj\o rn Ove Thue}{bjort@ifi.uio.no} - Author of the MSDOS port; please direct questions regarding - strictly to that port to him (I would like to receive a carbon - copy, though). - - \Name{Martin Ward}{Martin.Ward@durham.ac.uk} - Sent a few bug-reports; also gave me information upon where to find - regexp code. He also provided a Perl script for checking ordinary - text, which ideas I was able to implement in \chktex. In addition, - he sent me the source code for \verb@lacheck@; which also inspired some - of the warnings. -\end{description} - -%endlatex -\section{Contacting the author} - -If you wish to contact me for any reason or would like to participate in -the development of \chktex, please write to: -%latex -\begin{samepage} -%endlatex - \begin{quote} - Jens Berger \\ - Spektrumvn. 4 \\ - N-0666 Oslo \\ - Norway \\ - E-mail: \texttt{} - \end{quote} -%latex -\end{samepage} -%endlatex -Any signs of intelligent life are welcomed; that should exclude piracy. - -Since the original author is unreachable, the maintainer these days is: -%latex -\begin{samepage} -%endlatex - \begin{quote} - Baruch Even \\ - E-mail: \texttt{} - \end{quote} -%latex -\end{samepage} -%endlatex - -\medskip\noindent -Have fun. - -\end{document} - diff --git a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.texrc b/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.texrc deleted file mode 100644 index e990c71d1be..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/ChkTeX.texrc +++ /dev/null @@ -1,6 +0,0 @@ -# Ignore file for ChkTeX.tex, since it shows many errors in its examples -# it raises many errors when checking ChkTeX.tex with chktex itself. - -VerbEnvir { errexam errdesc } - -WipeArg { \Cmd:{} } diff --git a/Build/source/texk/chktex/chktex-1.6.6/FindErrs.c b/Build/source/texk/chktex/chktex-1.6.6/FindErrs.c deleted file mode 100644 index 45a6b02bfe5..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/FindErrs.c +++ /dev/null @@ -1,1537 +0,0 @@ -/* - * ChkTeX, error searching & report routines. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - - -#include "ChkTeX.h" -#include "FindErrs.h" -#include "OpSys.h" -#include "Utility.h" -#include "Resource.h" - -/***************************** ERROR MESSAGES ***************************/ - -#undef MSG -#define MSG(num, type, inuse, ctxt, text) {num, type, inuse, ctxt, text}, - -struct ErrMsg LaTeXMsgs[emMaxFault + 1] = { - ERRMSGS {emMaxFault, etErr, iuOK, 0, INTERNFAULT} -}; - -#define istex(c) (isalpha((unsigned char)c) || (AtLetter && (c == '@'))) -#define CTYPE(func) \ -static int my_##func(int c) \ -{ \ - return(func(c)); \ -} - -#define INUSE(c) (LaTeXMsgs[(enum ErrNum) c].InUse == iuOK) - -#define PSERR2(pos,len,err,a,b) \ - PrintError(CurStkName(&InputStack), RealBuf, pos, len, Line, err, a, b) - -#define PSERRA(pos,len,err,a) \ - PrintError(CurStkName(&InputStack), RealBuf, pos, len, Line, err, a) - -#define HEREA(len, err, a) PSERRA(BufPtr - Buf - 1, len, err, a) -#define PSERR(pos,len,err) PSERRA(pos,len,err,"") - -#define HERE(len, err) HEREA(len, err, "") - -#define SKIP_BACK(ptr, c, check) \ - while((c = *ptr--)) \ - { \ - if (!(check)) break; \ - } \ - ptr++; - -#define SKIP_AHEAD(ptr, c, check) \ - while((c = *ptr++)) \ - { \ - if (!(check)) \ - break; \ - } \ - ptr--; - - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * A list of characters LaTeX considers as an end-of-sentence characters, which - * should be detected when whether sentence spacing is correct. - * - */ -static const char LTX_EosPunc[] = { '.', ':', '?', '!', 0 }; - -/* - * General punctuation characters used on your system. - */ -static const char LTX_GenPunc[] = { ',', ';', 0 }; - -/* - * A list of characters LaTeX considers as an small punctuation characters, - * which should not be preceded by a \/. - */ -static const char LTX_SmallPunc[] = { '.', ',', 0 }; - - -static unsigned long Line; - -static const char *RealBuf; -static char *LineCpy; -static char *BufPtr; - -static int ItFlag = efNone; - -NEWBUF(Buf, BUFSIZ); -NEWBUF(CmdBuffer, BUFSIZ); -NEWBUF(ArgBuffer, BUFSIZ); - -static enum ErrNum PerformCommand(const char *Cmd, char *Arg); - -#ifdef isdigit -CTYPE(isdigit) -#else -# define my_isdigit isdigit -#endif - -#ifdef isalpha -CTYPE(isalpha) -#else -# define my_isalpha isalpha -#endif - -/* - * Reads in a TeX token from Src and puts it in Dest. - * - */ - - -static char *GetLTXToken(char *Src, char *Dest) -{ - int Char; - - if (Src && *Src) - { - if (*Src == '\\') - { - *Dest++ = *Src++; - Char = *Dest++ = *Src++; - - if (istex(Char)) - { - while (istex(Char)) - Char = *Dest++ = *Src++; - - Src--; - Dest--; - } - - } - else - *Dest++ = *Src++; - *Dest = 0; - } - else - Src = NULL; - - return (Src); -} - - -/* - * Scans the `SrcBuf' for a LaTeX arg, and puts that arg into `Dest'. - * `Until' specifies what we'll copy. Assume the text is - * "{foo}bar! qux} baz". - * GET_TOKEN => "{foo}" - * GET_STRIP_TOKEN => "foo" - * '!' => "{foo}bar!" (i.e. till the first "!") - * Returns NULL if we can't find the argument, ptr to the first character - * after the argument in other cases. - * - * If one of the tokens found is in the wl wordlist, and we're in the - * outer most paren, and Until isn't a single character, we'll stop. - * You may pass NULL as wl. - * - * We assume that you've previously skipped over leading spaces. - * - */ - -#define GET_TOKEN 256 -#define GET_STRIP_TOKEN 257 - -static char *GetLTXArg(char *SrcBuf, char *OrigDest, const int Until, - struct WordList *wl) -{ - char *Retval; - char *TmpPtr; - char *Dest = OrigDest; - unsigned long DeliCnt = 0; - - *Dest = 0; - TmpPtr = SrcBuf; - - switch (Until) - { - case GET_STRIP_TOKEN: - case GET_TOKEN: - while ((Retval = GetLTXToken(TmpPtr, Dest))) - { - switch (*Dest) - { - case '{': - DeliCnt++; - break; - case '}': - DeliCnt--; - } - Dest += Retval - TmpPtr; - TmpPtr = Retval; - - if (!DeliCnt || ((DeliCnt == 1) && wl && HasWord(Dest, wl))) - break; - } - - if (Retval && (*OrigDest == '{') && (Until == GET_STRIP_TOKEN)) - { - int len = strlen(OrigDest+1); - memmove(OrigDest, OrigDest + 1, len + 1); - /* Strip the last '}' off */ - OrigDest[len-1] = 0; - } - break; - default: - DeliCnt = TRUE; - while ((Retval = GetLTXArg(TmpPtr, Dest, GET_TOKEN, NULL))) - { - if (*Dest == Until) - DeliCnt = FALSE; - - Dest += Retval - TmpPtr; - TmpPtr = Retval; - - if (!DeliCnt) - break; - } - break; - } - *Dest = 0; - - return (Retval); -} - - -static char *MakeCpy(void) -{ - if (!LineCpy) - LineCpy = strdup(RealBuf); - - if (!LineCpy) - PrintPrgErr(pmStrDupErr); - - return (LineCpy); -} - -static char *PreProcess(void) -{ - /* First, kill comments. */ - - char *TmpPtr; - - strcpy(Buf, RealBuf); - - TmpPtr = Buf; - - while ((TmpPtr = strchr(TmpPtr, '%'))) - { - if (TmpPtr == Buf || TmpPtr[-1] != '\\') - { - PSERR(TmpPtr - Buf, 1, emComment); - *TmpPtr = 0; - break; - } - TmpPtr++; - } - return (Buf); -} - -/* - * Interpret environments - */ - -static void PerformEnv(char *Env, int Begin) -{ - static char VBStr[BUFSIZ] = ""; - - if (HasWord(Env, &MathEnvir)) - { - MathMode += Begin ? 1 : -1; - MathMode = max(MathMode, 0); - } - - if (Begin && HasWord(Env, &VerbEnvir)) - { - VerbMode = TRUE; - strcpy(VBStr, "\\end{"); - strcat(VBStr, Env); - strcat(VBStr, "}"); - VerbStr = VBStr; - } -} - -static char *SkipVerb(void) -{ - char *TmpPtr = BufPtr; - int TmpC; - - if (VerbMode && BufPtr) - { - if (!(TmpPtr = strstr(BufPtr, VerbStr))) - BufPtr = &BufPtr[strlen(BufPtr)]; - else - { - VerbMode = FALSE; - BufPtr = &TmpPtr[strlen(VerbStr)]; - SKIP_AHEAD(BufPtr, TmpC, LATEX_SPACE(TmpC)); - if (*BufPtr) - PSERR(BufPtr - Buf, strlen(BufPtr) - 2, emIgnoreText); - } - } - return (TmpPtr); -} - -#define CHECKDOTS(wordlist, dtval) \ -for(i = 0; (i < wordlist.Stack.Used) && !(Back && Front); i++) \ - { if(!strafter(PstPtr, wordlist.Stack.Data[i])) \ - Back = dtval; \ - if(!strinfront(PrePtr, wordlist.Stack.Data[i])) \ - Front = dtval; } - - - -/* - * Checks that the dots are correct - */ - -static enum DotLevel CheckDots(char *PrePtr, char *PstPtr) -{ - unsigned long i; - int TmpC; - enum DotLevel Front = dtUnknown, Back = dtUnknown; - - if (MathMode) - { - PrePtr--; -#define SKIP_EMPTIES(macro, ptr) macro(ptr, TmpC, \ -(LATEX_SPACE(TmpC) || (TmpC == '{') || (TmpC == '}'))) - - SKIP_EMPTIES(SKIP_BACK, PrePtr); - SKIP_EMPTIES(SKIP_AHEAD, PstPtr); - - CHECKDOTS(CenterDots, dtCDots); - - if (!(Front && Back)) - { - CHECKDOTS(LowDots, dtLDots); - } - return (Front & Back); - } - else - return (dtLDots); - -} - -static const char *Dot2Str(enum DotLevel dl) -{ - const char *Retval = INTERNFAULT; - switch (dl) - { - case dtUnknown: - Retval = "\\cdots or \\ldots"; - break; - case dtDots: - Retval = "\\dots"; - break; - case dtCDots: - Retval = "\\cdots"; - break; - case dtLDots: - Retval = "\\ldots"; - break; - } - return Retval; -} - -/* - * Wipes a command, according to the definition in WIPEARG - */ - -static void WipeArgument(const char *Cmd, char *CmdPtr) -{ - unsigned long CmdLen = strlen(Cmd); - const char *Format; - char *TmpPtr; - int c, TmpC; - - if (Cmd && *Cmd) - { - TmpPtr = &CmdPtr[CmdLen]; - Format = &Cmd[CmdLen + 1]; - - while (TmpPtr && *TmpPtr && *Format) - { - switch (c = *Format++) - { - case '*': - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - if (*TmpPtr == '*') - TmpPtr++; - break; - case '[': - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - if (*TmpPtr == '[') - TmpPtr = GetLTXArg(TmpPtr, ArgBuffer, ']', NULL); - break; - case '{': - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - TmpPtr = GetLTXArg(TmpPtr, ArgBuffer, GET_TOKEN, NULL); - case '}': - case ']': - break; - default: - PrintPrgErr(pmWrongWipeTemp, &Cmd[strlen(Cmd) + 1]); - break; - } - } - - if (TmpPtr) - strwrite(CmdPtr, VerbClear, TmpPtr - CmdPtr); - else - strxrep(CmdPtr, "()[]{}", *VerbClear); - } -} - -/* - * Checks italic. - * - */ - -static void CheckItal(const char *Cmd) -{ - int TmpC; - char *TmpPtr; - if (HasWord(Cmd, &NonItalic)) - ItState = itOff; - else if (HasWord(Cmd, &Italic)) - ItState = itOn; - else if (HasWord(Cmd, &ItalCmd)) - { - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - if (*TmpPtr == '{') - { - ItFlag = ItState ? efItal : efNoItal; - ItState = itOn; - } - } -} - -/* - * Interpret isolated commands. - * - */ - -static void PerformBigCmd(char *CmdPtr) -{ - char *TmpPtr; - const char *ArgEndPtr; - unsigned long CmdLen = strlen(CmdBuffer); - int TmpC; - enum ErrNum ErrNum; - struct ErrInfo *ei; - - enum DotLevel dotlev, realdl = dtUnknown; - - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - - ArgEndPtr = GetLTXArg(TmpPtr, ArgBuffer, GET_STRIP_TOKEN, NULL); - - /* Kill `\verb' commands */ - - if (WipeVerb) - { - if (!strcmp(CmdBuffer, "\\verb")) - { - if (*BufPtr && (*BufPtr != '*' || BufPtr[1])) - { - if (*BufPtr == '*') - TmpPtr = strchr(&BufPtr[2], BufPtr[1]); - else - TmpPtr = strchr(&BufPtr[1], *BufPtr); - if (TmpPtr) - strwrite(CmdPtr, VerbClear, (TmpPtr - CmdPtr) + 1); - else - PSERR(CmdPtr - Buf, 5, emNoArgFound); - } - } - } - - if (HasWord(CmdBuffer, &IJAccent)) - { - if (ArgEndPtr) - { - TmpPtr = ArgBuffer; - SKIP_AHEAD(TmpPtr, TmpC, TmpC == '{'); /* } */ - - if ((*TmpPtr == 'i') || (*TmpPtr == 'j')) - PrintError(CurStkName(&InputStack), RealBuf, - CmdPtr - Buf, - (long) strlen(CmdBuffer), Line, - emAccent, CmdBuffer, *TmpPtr, - MathMode ? "math" : ""); - } - else - PSERR(CmdPtr - Buf, CmdLen, emNoArgFound); - } - - if (HasWord(CmdBuffer, &NotPreSpaced) && isspace((unsigned char)CmdPtr[-1])) - PSERRA(CmdPtr - Buf - 1, 1, emRemPSSpace, CmdBuffer); - - if ((TmpPtr = HasWord(CmdBuffer, &NoCharNext))) - { - char *BPtr = BufPtr; - - TmpPtr += strlen(TmpPtr) + 1; - SKIP_AHEAD(BPtr, TmpC, LATEX_SPACE(TmpC)); - - if (strchr(TmpPtr, *BPtr)) - { - PSERR2(CmdPtr - Buf, CmdLen, emNoCharMean, CmdBuffer, *BPtr); - } - } - - if (!strcmp(CmdBuffer, "\\begin") || !strcmp(CmdBuffer, "\\end")) - { - if (ArgEndPtr) - { - if (!strcmp(ArgBuffer, "document")) - InHeader = FALSE; - - if (CmdBuffer[1] == 'b') - { - if (!(PushErr(ArgBuffer, Line, CmdPtr - Buf, - CmdLen, MakeCpy(), &EnvStack))) - PrintPrgErr(pmNoStackMem); - } - else - { - if ((ei = PopErr(&EnvStack))) - { - if (strcmp(ei->Data, ArgBuffer)) - PrintError(CurStkName(&InputStack), RealBuf, - CmdPtr - Buf, - (long) strlen(CmdBuffer), - Line, emExpectC, ei->Data, ArgBuffer); - - FreeErrInfo(ei); - } - else - PrintError(CurStkName(&InputStack), RealBuf, - CmdPtr - Buf, - (long) strlen(CmdBuffer), - Line, emSoloC, ArgBuffer); - } - - PerformEnv(ArgBuffer, (int) CmdBuffer[1] == 'b'); - } - else - PSERR(CmdPtr - Buf, CmdLen, emNoArgFound); - } - - CheckItal(CmdBuffer); - - if ((ErrNum = PerformCommand(CmdBuffer, BufPtr))) - PSERR(CmdPtr - Buf, CmdLen, ErrNum); - - if (!strcmp(CmdBuffer, "\\cdots")) - realdl = dtCDots; - - if (!strcmp(CmdBuffer, "\\ldots")) - realdl = dtLDots; - - if (!strcmp(CmdBuffer, "\\dots")) - realdl = dtLDots; - - if (realdl != dtUnknown) - { - dotlev = CheckDots(CmdPtr, BufPtr); - if (dotlev && (dotlev != realdl)) - { - const char *cTmpPtr = Dot2Str(dotlev); - PSERRA(CmdPtr - Buf, CmdLen, emEllipsis, cTmpPtr); - } - } - - if ((TmpPtr = HasWord(CmdBuffer, &WipeArg))) - WipeArgument(TmpPtr, CmdPtr); -} - -/* - * Check user abbreviations. Pass a pointer to the `.'; - * also ensure that it's followed by spaces, etc. - * - * Note: We assume that all abbrevs have been transferred from - * AbbrevCase into Abbrev. - */ - -static void CheckAbbrevs(const char *Buffer) -{ - long i; - char *TmpPtr; - const char *AbbPtr; - - if (INUSE(emInterWord)) - { - TmpPtr = TmpBuffer + Abbrev.MaxLen + 2; - *TmpPtr = 0; - AbbPtr = Buffer; - - for (i = Abbrev.MaxLen; i >= 0; i--) - { - *--TmpPtr = *AbbPtr--; - if (!isalpha((unsigned char)*AbbPtr) && HasWord(TmpPtr, &Abbrev)) - PSERR(Buffer - Buf + 1, 1, emInterWord); - if (!*AbbPtr) - break; - } - } -} - - -/* - * Check misc. things which can't be included in the main loop. - * - */ - -static void CheckRest(void) -{ - unsigned long Count; - long CmdLen; - char *UsrPtr; - - /* Search for user-specified warnings */ - - if (INUSE(emUserWarn)) - { - strcpy(TmpBuffer, Buf); - FORWL(Count, UserWarn) - { - for (UsrPtr = TmpBuffer; - (UsrPtr = strstr(UsrPtr, UserWarn.Stack.Data[Count])); - UsrPtr++) - { - CmdLen = strlen(UserWarn.Stack.Data[Count]); - PSERR(UsrPtr - TmpBuffer, CmdLen, emUserWarn); - } - } - - - strlwr(TmpBuffer); - - FORWL(Count, UserWarnCase) - { - for (UsrPtr = TmpBuffer; - (UsrPtr = strstr(UsrPtr, UserWarnCase.Stack.Data[Count])); - UsrPtr++) - { - CmdLen = strlen(UserWarnCase.Stack.Data[Count]); - PSERR(UsrPtr - TmpBuffer, CmdLen, emUserWarn); - } - } - } -} - - -/* - * Checks that the dash-len is correct. - */ - -static void CheckDash(void) -{ - char *TmpPtr; - int TmpC; - long TmpCount, Len; - struct WordList *wl = NULL; - unsigned long i; - int Errored; - char *PrePtr = &BufPtr[-2]; - - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, TmpC == '-'); - TmpCount = TmpPtr - BufPtr + 1; - - if (MathMode) - { - if (TmpCount > 1) - HERE(TmpCount, emWrongDash); - } - else - { - if (LATEX_SPACE(*PrePtr) && LATEX_SPACE(*TmpPtr)) - wl = &WordDash; - if (isdigit((unsigned char)*PrePtr) && isdigit((unsigned char)*TmpPtr)) - wl = &NumDash; - if (isalpha((unsigned char)*PrePtr) && isalpha((unsigned char)*TmpPtr)) - wl = &HyphDash; - - if (wl) - { - Errored = TRUE; - FORWL(i, *wl) - { - Len = strtol(wl->Stack.Data[i], NULL, 0); - if (TmpCount == Len) - { - Errored = FALSE; - break; - } - } - if (Errored) - HERE(TmpCount, emWrongDash); - } - } -} - -/* - * Pushes and pops nesting characters. - * - */ - -static void HandleBracket(int Char) -{ - unsigned long BrOffset; /* Offset into BrOrder array */ - struct ErrInfo *ei; - int TmpC, Match; - char ABuf[2], BBuf[2]; - char *TmpPtr; - - AddBracket(Char); - - if ((BrOffset = BrackIndex(Char)) != ~0UL) - { - if (BrOffset & 1) /* Closing bracket of some sort */ - { - if ((ei = PopErr(&CharStack))) - { - Match = MatchBracket(*(ei->Data)); - if (ei->Flags & efNoItal) - { - if (ItState == itOn) - { - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, TmpC == '}'); - - if (!strchr(LTX_SmallPunc, *TmpPtr)) - HERE(1, emNoItFound); - } - - ItState = FALSE; - } - else if (ei->Flags & efItal) - ItState = TRUE; - FreeErrInfo(ei); - } - else - Match = 0; - - if (Match != Char) - { - ABuf[0] = Match; - BBuf[0] = Char; - ABuf[1] = BBuf[1] = 0; - if (Match) - PrintError(CurStkName(&InputStack), RealBuf, - BufPtr - Buf - 1, 1, Line, emExpectC, - ABuf, BBuf); - else - HEREA(1, emSoloC, BBuf); - } - - } - else /* Opening bracket of some sort */ - { - if ((ei = PushChar(Char, Line, BufPtr - Buf - 1, - &CharStack, MakeCpy()))) - { - if (Char == '{') - { - switch (ItFlag) - { - default: - ei->Flags = ItFlag; - ItFlag = efNone; - break; - case efNone: - ei->Flags |= ItState ? efItal : efNoItal; - } - } - } - - else - PrintPrgErr(pmNoStackMem); - } - } -} - - - -/* - * Searches the `Buf' for possible errors, and prints the errors. `Line' - * is supplied for error printing. - */ - -int FindErr(const char *_RealBuf, const unsigned long _Line) -{ - char *CmdPtr; /* We'll have to copy each command out. */ - char *PrePtr; /* Ptr to char in front of command, NULL if - * the cmd appears as the first character */ - char *TmpPtr; /* Temporary pointer */ - char *ErrPtr; /* Ptr to where an error started */ - - int TmpC, /* Just a temp var used throughout the proc. */ - MatchC, Char; /* Char. currently processed */ - unsigned long CmdLen; /* Length of misc. things */ - int MixingQuotes; - - int (*pstcb) (int c); - - enum DotLevel dotlev; - - LineCpy = NULL; - - if (_RealBuf) - { - RealBuf = _RealBuf; - Line = _Line; - - BufPtr = PreProcess(); - - BufPtr = SkipVerb(); - - while (BufPtr && *BufPtr) - { - PrePtr = BufPtr - 1; - Char = *BufPtr++; - if (isspace((unsigned char)Char)) - Char = ' '; - - switch (Char) - { - case '~': - TmpPtr = NULL; - if (isspace((unsigned char)*PrePtr)) - TmpPtr = PrePtr; - else if (isspace((unsigned char)*BufPtr)) - TmpPtr = BufPtr; - - if (TmpPtr) - PSERR(TmpPtr - Buf, 1, emDblSpace); - break; - - case 'X': - case 'x': - TmpPtr = PrePtr; - - SKIP_BACK(TmpPtr, TmpC, - (LATEX_SPACE(TmpC) || strchr("{}$", TmpC))); - - if (isdigit((unsigned char)*TmpPtr)) - { - TmpPtr = BufPtr; - - SKIP_AHEAD(TmpPtr, TmpC, - (LATEX_SPACE(TmpC) || strchr("{}$", TmpC))); - - if (isdigit((unsigned char)*TmpPtr)) - HERE(1, emUseTimes); - } - /* FALLTHRU */ - /* CTYPE: isalpha() */ - case 'a': - case 'b': - case 'c': - case 'd': - case 'e': - case 'f': - case 'g': - case 'h': - case 'i': - case 'j': - case 'k': - case 'l': - case 'm': - case 'n': - case 'o': - case 'p': - case 'q': - case 'r': - case 's': - case 't': - case 'u': - case 'v': - case 'w': /* case 'x': */ - case 'y': - case 'z': - - case 'A': - case 'B': - case 'C': - case 'D': - case 'E': - case 'F': - case 'G': - case 'H': - case 'I': - case 'J': - case 'K': - case 'L': - case 'M': - case 'N': - case 'O': - case 'P': - case 'Q': - case 'R': - case 'S': - case 'T': - case 'U': - case 'V': - case 'W': /* case 'X': */ - case 'Y': - case 'Z': - if (!isalpha((unsigned char)*PrePtr) && (*PrePtr != '\\') && MathMode) - { - TmpPtr = BufPtr; - CmdPtr = CmdBuffer; - do - { - *CmdPtr++ = Char; - Char = *TmpPtr++; - } - while (isalpha((unsigned char)Char)); - - *CmdPtr = 0; - - if (HasWord(CmdBuffer, &MathRoman)) - HEREA(strlen(CmdBuffer), emWordCommand, CmdBuffer); - } - - break; - case ' ': - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - - if (*TmpPtr && *PrePtr) - { - if ((TmpPtr - BufPtr) > 0) - { - HERE(TmpPtr - BufPtr + 1, emMultiSpace); - strwrite(BufPtr, VerbClear, TmpPtr - BufPtr - 1); - } - } - break; - - case '.': - if ((Char == *BufPtr) && (Char == BufPtr[1])) - { - const char *cTmpPtr; - dotlev = CheckDots(&PrePtr[1], &BufPtr[2]); - cTmpPtr = Dot2Str(dotlev); - HEREA(3, emEllipsis, cTmpPtr); - } - - /* Regexp: "([^A-Z@.])\.[.!?:;]*\s+[a-z]" */ - - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, strchr(LTX_GenPunc, TmpC)); - if (LATEX_SPACE(*TmpPtr)) - { - if (!isupper((unsigned char)*PrePtr) && (*PrePtr != '@') && - (*PrePtr != '.')) - { - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - if (islower((unsigned char)*TmpPtr)) - PSERR(BufPtr - Buf, 1, emInterWord); - else - CheckAbbrevs(&BufPtr[-1]); - } - } - - /* FALLTHRU */ - case ':': - case '?': - case '!': - case ';': - /* Regexp: "[A-Z][A-Z][.!?:;]\s+" */ - - if (isspace((unsigned char)*BufPtr) && isupper((unsigned char)*PrePtr) && - (isupper((unsigned char)PrePtr[-1]) || (Char != '.'))) - HERE(1, emInterSent); - - /* FALLTHRU */ - case ',': - if (isspace((unsigned char)*PrePtr) && - !(isdigit((unsigned char)*BufPtr) && - ((BufPtr[-1] == '.') || (BufPtr[-1] == ',')))) - PSERR(PrePtr - Buf, 1, emSpacePunct); - - if (MathMode && - (((*BufPtr == '$') && (BufPtr[1] != '$')) || - (!strafter(BufPtr, "\\)")))) - HEREA(1, emPunctMath, "outside inner"); - - if (!MathMode && - (((*PrePtr == '$') && (PrePtr[-1] == '$')) || - (!strinfront(PrePtr, "\\]")))) - HEREA(1, emPunctMath, "inside display"); - - break; - case '\'': - case '`': - if ((Char == *BufPtr) && (Char == BufPtr[1])) - { - PrintError(CurStkName(&InputStack), RealBuf, - BufPtr - Buf - 1, 3, Line, - emThreeQuotes, - Char, Char, Char, Char, Char, Char); - } - - if (Char == '\'') - MatchC = '`'; - else - MatchC = '\''; - - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, TmpC == Char); - - MixingQuotes = FALSE; - - if ((*TmpPtr == MatchC) || (*TmpPtr == '\"') || - (*TmpPtr == '´')) - MixingQuotes = TRUE; - - SKIP_AHEAD(TmpPtr, TmpC, strchr("`\'\"´", TmpC)); - - if (MixingQuotes) - HERE(TmpPtr - BufPtr + 1, emQuoteMix); - - switch (Char) - { - case '\'': - if (isalpha((unsigned char)*TmpPtr) && - (strchr(LTX_GenPunc, *PrePtr) || isspace((unsigned char)*PrePtr))) - HERE(TmpPtr - BufPtr + 1, emBeginQ); - - /* Now check quote style */ -#define ISPUNCT(ptr) (strchr(LTX_GenPunc, *ptr) && (ptr[-1] != '\\')) - - /* We ignore all single words/abbreviations in quotes */ - - { - char *WordPtr = PrePtr; - SKIP_BACK(WordPtr, TmpC, (isalnum((unsigned char)TmpC) || - strchr(LTX_GenPunc, TmpC))); - - if (*WordPtr != '`') - { - if (*PrePtr && (Quote != quTrad) - && ISPUNCT(PrePtr)) - PSERRA(PrePtr - Buf, 1, - emQuoteStyle, "in front of"); - - if (*TmpPtr && (Quote != quLogic) - && ISPUNCT(TmpPtr)) - PSERRA(TmpPtr - Buf, 1, - emQuoteStyle, "after"); - } - } - - break; - case '`': - if (isalpha((unsigned char)*PrePtr) && - (strchr(LTX_GenPunc, *TmpPtr) || isspace((unsigned char)*TmpPtr))) - HERE(TmpPtr - BufPtr + 1, emEndQ); - break; - } - BufPtr = TmpPtr; - break; - case '"': - HERE(1, emUseQuoteLiga); - break; - - /* One of these are unnecessary, but what the heck... */ - case 180: /* ´. NOTE: '\xb4' gets converted to - something */ - case ~(0xff & (~180)): /* This yields 0xff...fb4 in */ - /* arbitrary precision. */ - - HERE(1, emUseOtherQuote); - break; - - case '_': - case '^': - if (*PrePtr != '\\') - { - TmpPtr = PrePtr; - SKIP_BACK(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - - CmdLen = 1; - - switch (*TmpPtr) - { - /*{ */ - case '}': - if (PrePtr[-1] != '\\') - break; - - CmdLen++; - PrePtr--; - /* FALLTHRU */ - /*[( */ - case ')': - case ']': - PSERR(PrePtr - Buf, CmdLen, emEnclosePar); - } - - TmpPtr = BufPtr; - SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); - - ErrPtr = TmpPtr; - - if (isalpha((unsigned char)*TmpPtr)) - pstcb = &my_isalpha; - else if (isdigit((unsigned char)*TmpPtr)) - pstcb = &my_isdigit; - else - break; - - while ((*pstcb) (*TmpPtr++)) - ; - TmpPtr--; - - if ((TmpPtr - ErrPtr) > 1) - PSERR(ErrPtr - Buf, TmpPtr - ErrPtr, emEmbrace); - } - break; - case '-': - CheckDash(); - break; - case '\\': /* Command encountered */ - BufPtr = GetLTXToken(--BufPtr, CmdBuffer); - - if (LATEX_SPACE(*PrePtr)) - { - if (HasWord(CmdBuffer, &Linker)) - PSERR(PrePtr - Buf, 1, emNBSpace); - if (HasWord(CmdBuffer, &PostLink)) - PSERR(PrePtr - Buf, 1, emFalsePage); - } - - if (LATEX_SPACE(*BufPtr) && !MathMode && - (!HasWord(CmdBuffer, &Silent)) && - (strlen(CmdBuffer) != 2)) - { - PSERR(BufPtr - Buf, 1, emSpaceTerm); - } - else if ((*BufPtr == '\\') && (!isalpha((unsigned char)BufPtr[1])) && - (!LATEX_SPACE(BufPtr[1]))) - PSERR(BufPtr - Buf, 2, emNotIntended); - - PerformBigCmd(PrePtr + 1); - BufPtr = SkipVerb(); - - break; - - case '(': - if (*PrePtr && !LATEX_SPACE(*PrePtr) && !isdigit((unsigned char)*PrePtr) - && !strchr("([{`~", *PrePtr)) - { - if (PrePtr[-1] != '\\') /* Short cmds */ - { - TmpPtr = PrePtr; - SKIP_BACK(TmpPtr, TmpC, istex(TmpC)); - if (*TmpPtr != '\\') /* Long cmds */ - PSERRA(BufPtr - Buf - 1, 1, emSpaceParen, - "in front of"); - } - } - if (isspace((unsigned char)*BufPtr)) - PSERRA(BufPtr - Buf, 1, emNoSpaceParen, "after"); - HandleBracket(Char); - break; - - case ')': - if (isspace((unsigned char)*PrePtr)) - PSERRA(BufPtr - Buf - 1, 1, emNoSpaceParen, - "in front of"); - if (isalpha((unsigned char)*BufPtr)) - PSERRA(BufPtr - Buf, 1, emSpaceParen, "after"); - HandleBracket(Char); - break; - - case '}': - case '{': - case '[': - case ']': - HandleBracket(Char); - break; - case '$': - if (*PrePtr != '\\') - { - if (*BufPtr == '$') - BufPtr++; - MathMode ^= TRUE; - } - - break; - } - } - - if (!VerbMode) - { - CheckRest(); - } - } - - return (TRUE); -} - -/* - * Tries to create plural forms for words. Put a '%s' where a - * suffix should be put, e.g. "warning%s". Watch your %'s! - */ - -static void Transit(FILE * fh, unsigned long Cnt, const char *Str) -{ - switch (Cnt) - { - case 0: - fputs("No ", fh); - fprintf(fh, Str, "s"); - break; - case 1: - fputs("One ", fh); - fprintf(fh, Str, ""); - break; - default: - fprintf(fh, "%ld ", Cnt); - fprintf(fh, Str, "s"); - break; - } -} - -/* - * Prints the status/conclusion after doing all the testing, including - * bracket stack status, math mode, etc. - */ - -void PrintStatus(unsigned long Lines) -{ - unsigned long Cnt; - struct ErrInfo *ei; - - - while ((ei = PopErr(&CharStack))) - { - PrintError(ei->File, ei->LineBuf, ei->Column, - ei->ErrLen, ei->Line, emNoMatchC, (char *) ei->Data); - FreeErrInfo(ei); - } - - while ((ei = PopErr(&EnvStack))) - { - PrintError(ei->File, ei->LineBuf, ei->Column, - ei->ErrLen, ei->Line, emNoMatchC, (char *) ei->Data); - FreeErrInfo(ei); - } - - if (MathMode) - { - PrintError(CurStkName(&InputStack), "", 0L, 0L, Lines, emMathStillOn); - } - - for (Cnt = 0L; Cnt < (NUMBRACKETS >> 1); Cnt++) - { - if (Brackets[Cnt << 1] != Brackets[(Cnt << 1) + 1]) - { - PrintError(CurStkName(&InputStack), "", 0L, 0L, Lines, - emNoMatchCC, - BrOrder[Cnt << 1], BrOrder[(Cnt << 1) + 1]); - } - } - - if (!Quiet) - { - Transit(stderr, ErrPrint, "error%s printed; "); - Transit(stderr, WarnPrint, "warning%s printed; "); - Transit(stderr, UserSupp, "user suppressed warning%s printed.\n"); - } -} - - - -/* - * Uses OutputFormat. Be sure that `String' - * does not contain tabs, newlines, etc. - * Prints a formatted string. Formatting codes understood: - * %b - string to print Between fields (from -s option) - * %c - Column position of error - * %d - lenght of error (Digit) - * %f - current Filename - * %i - Turn on inverse printing mode. - * %I - Turn off inverse printing mode. - * %k - Kind of error (warning, error, message) - * %l - Line number of error - * %m - warning Message - * %n - warning Number - * %u - an Underlining line (like the one which appears when using -v1) - * %r - part of line in front of error ('S' - 1) - * %s - part of line which contains error (String) - * %t - part of line after error ('S' + 1) - */ - - -void -PrintError(const char *File, const char *String, - const long Position, const long Len, - const long LineNo, const enum ErrNum Error, ...) -{ - static /* Just to reduce stack usage... */ - char PrintBuffer[BUFSIZ]; - va_list MsgArgs; - - char *LastNorm = OutputFormat; - char *of; - int c; - - enum Context Context; - - if (betw(emMinFault, Error, emMaxFault)) - { - switch (LaTeXMsgs[Error].InUse) - { - case iuOK: - do - { - Context = LaTeXMsgs[Error].Context; - - if (!HeadErrOut) - Context |= ctOutHead; - -#define RGTCTXT(Ctxt, Var) if((Context & Ctxt) && !(Var)) break; - - RGTCTXT(ctInMath, MathMode); - RGTCTXT(ctOutMath, !MathMode); - RGTCTXT(ctInHead, InHeader); - RGTCTXT(ctOutHead, !InHeader); - - switch (LaTeXMsgs[Error].Type) - { - case etWarn: - WarnPrint++; - break; - case etErr: - ErrPrint++; - break; - case etMsg: - break; - } - - while ((of = strchr(LastNorm, '%'))) - { - c = *of; - *of = 0; - - fputs(LastNorm, OutputFile); - - *of++ = c; - - switch (c = *of++) - { - case 'b': - fputs(Delimit, OutputFile); - break; - case 'c': - fprintf(OutputFile, "%ld", Position + 1); - break; - case 'd': - fprintf(OutputFile, "%ld", Len); - break; - case 'f': - fputs(File, OutputFile); - break; - case 'i': - fputs(ReverseOn, OutputFile); - break; - case 'I': - fputs(ReverseOff, OutputFile); - break; - case 'k': - switch (LaTeXMsgs[Error].Type) - { - case etWarn: - fprintf(OutputFile, "Warning"); - break; - case etErr: - fprintf(OutputFile, "Error"); - break; - case etMsg: - fprintf(OutputFile, "Message"); - break; - } - break; - case 'l': - fprintf(OutputFile, "%ld", LineNo); - break; - case 'm': - va_start(MsgArgs, Error); - vfprintf(OutputFile, - LaTeXMsgs[Error].Message, MsgArgs); - va_end(MsgArgs); - break; - case 'n': - fprintf(OutputFile, "%d", Error); - break; - case 'u': - sfmemset(PrintBuffer, ' ', (long) Position); - - sfmemset(&PrintBuffer[Position], '^', Len); - PrintBuffer[Position + Len] = 0; - fputs(PrintBuffer, OutputFile); - break; - case 'r': - substring(String, PrintBuffer, 0L, Position); - fputs(PrintBuffer, OutputFile); - break; - case 's': - substring(String, PrintBuffer, Position, Len); - fputs(PrintBuffer, OutputFile); - break; - case 't': - substring(String, PrintBuffer, - Position + Len, LONG_MAX); - fputs(PrintBuffer, OutputFile); - break; - default: - fputc(c, OutputFile); - break; - } - LastNorm = of; - } - fputs(LastNorm, OutputFile); - } - while (FALSE); - break; - case iuNotUser: - UserSupp++; - break; - case iuNotSys: - break; - } - } -} - -/* - * All commands isolated is routed through this command, so we can - * update global statuses like math mode and whether @ is a letter - * or not. - */ - -static enum ErrNum PerformCommand(const char *Cmd, char *Arg) -{ - const char *Argument = ""; - enum ErrNum en = emMinFault; - int TmpC; - - if (!strcmp(Cmd, "\\makeatletter")) - AtLetter = TRUE; - else if (!strcmp(Cmd, "\\makeatother")) - AtLetter = FALSE; - else if (InputFiles && - !(strcmp(Cmd, "\\input") && strcmp(Cmd, "\\include"))) - { - SKIP_AHEAD(Arg, TmpC, LATEX_SPACE(TmpC)); - if (*Arg == '{') /* } */ - { - if (GetLTXArg(Arg, TmpBuffer, GET_STRIP_TOKEN, NULL)) - Argument = TmpBuffer; - } - else - Argument = strip(Arg, STRP_BTH); - - if (!(Argument && PushFileName(Argument, &InputStack))) - en = emNoCmdExec; - } - else if (HasWord(Cmd, &Primitives)) - en = emTeXPrim; - else if (*Cmd == '\\') - { - /* Quicker check of single lettered commands. */ - switch (Cmd[1]) - { - case '(': - case '[': - MathMode = TRUE; - break; - case ']': - case ')': - MathMode = FALSE; - break; - case '/': - switch (ItState) - { - case itOn: - ItState = itCorrected; - Argument = Arg; - - SKIP_AHEAD(Argument, TmpC, TmpC == '{' || TmpC == '}'); - - if (strchr(".,", *Argument)) - en = emItPunct; - - break; - case itCorrected: - en = emItDup; - break; - case itOff: - en = emItInNoIt; - } - break; - } - } - - return (en); -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/FindErrs.h b/Build/source/texk/chktex/chktex-1.6.6/FindErrs.h deleted file mode 100644 index 47f98c5e6aa..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/FindErrs.h +++ /dev/null @@ -1,193 +0,0 @@ -/* - * ChkTeX, header file for main program. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#ifndef FINDERRS_H -#define FINDERRS_H -#include "ChkTeX.h" - - -#undef ERRMSGS -#undef MSG - -#define ERRMSGS \ - MSG(emMinFault, etErr, iuOK, ctNone,\ - INTERNFAULT)\ - MSG(emSpaceTerm, etWarn, iuOK, ctOutMath,\ - "Command terminated with space.")\ - MSG(emNBSpace, etWarn, iuOK, ctNone,\ - "Non-breaking space (`~') should have been used.")\ - MSG(emEnclosePar, etWarn, iuOK, ctInMath,\ - "You should enclose the previous parenthesis with `{}\'.")\ - MSG(emItInNoIt, etWarn, iuOK, ctNone,\ - "Italic correction (`\\/') found in non-italic buffer.")\ - MSG(emItDup, etWarn, iuOK, ctNone,\ - "Italic correction (`\\/') found more than once.")\ - MSG(emNoItFound, etWarn, iuOK, ctNone,\ - "No italic correction (`\\/') found.")\ - MSG(emAccent, etWarn, iuOK, ctNone,\ - "Accent command `%s' needs use of `\\%c%s'.")\ - MSG(emWrongDash, etWarn, iuOK, ctOutMath,\ - "Wrong length of dash may have been used.")\ - MSG(emExpectC, etWarn, iuOK, ctNone,\ - "`%s' expected, found `%s'.")\ - MSG(emSoloC, etWarn, iuOK, ctNone,\ - "Solo `%s' found.")\ - MSG(emEllipsis, etWarn, iuOK, ctNone,\ - "You should use %s to achieve an ellipsis.")\ - MSG(emInterWord, etWarn, iuOK, ctOutMath,\ - "Interword spacing (`\\ ') should perhaps be used.")\ - MSG(emInterSent, etWarn, iuOK, ctOutMath,\ - "Intersentence spacing (`\\@') should perhaps be used.")\ - MSG(emNoArgFound, etErr, iuOK, ctNone,\ - "Could not find argument for command.")\ - MSG(emNoMatchC, etWarn, iuOK, ctOutMath,\ - "No match found for `%s'.")\ - MSG(emMathStillOn, etWarn, iuOK, ctNone,\ - "Mathmode still on at end of LaTeX file.")\ - MSG(emNoMatchCC, etWarn, iuOK, ctNone,\ - "Number of `%c' doesn't match the number of `%c'!")\ - MSG(emUseQuoteLiga, etWarn, iuOK, ctNone,\ - "Use either `` or '' as an alternative to `\"'.")\ - MSG(emUseOtherQuote, etWarn, iuOK, ctNone,\ - "Use \"'\" (ASCII 39) instead of \"´\" (ASCII 180).")\ - MSG(emUserWarn, etWarn, iuOK, ctNone,\ - "User-specified pattern found.")\ - MSG(emNotIntended, etWarn, iuNotSys, ctNone,\ - "This command might not be intended.")\ - MSG(emComment, etMsg, iuNotSys, ctNone,\ - "Comment displayed.")\ - MSG(emThreeQuotes, etWarn, iuOK, ctNone,\ - "Either %c\\,%c%c or %c%c\\,%c will look better.")\ - MSG(emFalsePage, etWarn, iuOK, ctOutMath,\ - "Delete this space to maintain correct pagereferences.")\ - MSG(emEmbrace, etWarn, iuOK, ctInMath,\ - "You might wish to put this between a pair of `{}'")\ - MSG(emSpacePunct, etWarn, iuOK, ctOutMath,\ - "You ought to remove spaces in front of punctuation.")\ - MSG(emNoCmdExec, etWarn, iuOK, ctNone,\ - "Could not execute LaTeX command.")\ - MSG(emItPunct, etWarn, iuOK, ctNone,\ - "Don't use \\/ in front of small punctuation.")\ - MSG(emUseTimes, etWarn, iuOK, ctNone,\ - "$\\times$ may look prettier here.")\ - MSG(emMultiSpace, etWarn, iuNotSys, ctOutMath,\ - "Multiple spaces detected in input.")\ - MSG(emIgnoreText, etWarn, iuOK, ctNone,\ - "This text may be ignored.")\ - MSG(emBeginQ, etWarn, iuOK, ctOutMath,\ - "Use ` to begin quotation, not '.")\ - MSG(emEndQ, etWarn, iuOK, ctOutMath,\ - "Use ' to end quotation, not `.")\ - MSG(emQuoteMix, etWarn, iuOK, ctNone,\ - "Don't mix quotes.")\ - MSG(emWordCommand, etWarn, iuOK, ctInMath,\ - "You should perhaps use `\\%s' instead.")\ - MSG(emSpaceParen, etWarn, iuOK, ctOutMath,\ - "You should put a space %s parenthesis.")\ - MSG(emNoSpaceParen, etWarn, iuOK, ctOutMath,\ - "You should avoid spaces %s parenthesis.")\ - MSG(emQuoteStyle, etWarn, iuOK, ctOutMath,\ - "You should not use punctuation %s quotes.")\ - MSG(emDblSpace, etWarn, iuOK, ctOutMath,\ - "Double space found.")\ - MSG(emPunctMath, etWarn, iuOK, ctNone,\ - "You should put punctuation %s math mode.")\ - MSG(emTeXPrim, etWarn, iuNotSys, ctNone,\ - "You ought to not use primitive TeX in LaTeX code.")\ - MSG(emRemPSSpace, etWarn, iuOK, ctOutMath,\ - "You should remove spaces in front of `%s'") \ - MSG(emNoCharMean, etWarn, iuOK, ctNone,\ - "`%s' is normally not followed by `%c'.") - -#undef MSG -#define MSG(num, type, inuse, ctxt, text) num, - -enum ErrNum -{ - ERRMSGS emMaxFault -}; -#undef MSG - -enum Context -{ - ctNone = 0x00, - ctInMath = 0x01, - ctOutMath = 0x02, - ctInHead = 0x04, - ctOutHead = 0x08 -}; - -struct ErrMsg -{ - enum ErrNum Number; - enum - { - etMsg, - etWarn, - etErr - } Type; - - enum - { - iuNotSys, - iuNotUser, - iuOK - } InUse; - - /* Requirements posed upon environment */ - enum Context Context; - - const char *Message; -}; - -enum ItState -{ - itOff, - itOn, - itCorrected -}; - - -enum DotLevel -{ - dtUnknown = 0x0, - dtCDots = 0x1, - dtLDots = 0x2, - dtDots = 0x4 -}; - -extern struct ErrMsg LaTeXMsgs[emMaxFault + 1]; - -extern char *OutputFormat; - -int FindErr(const char *, const unsigned long); -void PrintError(const char *, const char *, const long, const long, - const long, const enum ErrNum, ...); -void PrintStatus(unsigned long Lines); - -#endif /* FINDERRS */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/MakeHTML.pl b/Build/source/texk/chktex/chktex-1.6.6/MakeHTML.pl deleted file mode 100644 index 6bdbadcf127..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/MakeHTML.pl +++ /dev/null @@ -1,20 +0,0 @@ -# Remove parts of code enclosed in %latex/%endlatex tags - -$latexonly = 0; - -while(<>) -{ - $latexonly = 1 if /^%latex/i; - $latexonly = 0 if /^%endlatex/i; - - - if($latexonly) { - if(/^%!(.*)/) - { - print $1; - } - } - else { - print; - } -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/Makefile.in b/Build/source/texk/chktex/chktex-1.6.6/Makefile.in deleted file mode 100644 index ed28c2d92a2..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Makefile.in +++ /dev/null @@ -1,317 +0,0 @@ -# -# Makefile for ChkTeX project, creates the stuff. -# Copyright (C) 1996 Jens T. Berger Thielemann -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -# -# Contact the author at: -# Jens Berger -# Spektrumvn. 4 -# N-0666 Oslo -# Norway -# E-mail: -# - - -prefix=@prefix@ -exec_prefix=@exec_prefix@ -bindir=@bindir@ -datarootdir=@datarootdir@ -datadir=@datadir@ -sysconfdir=@sysconfdir@ -srcdir=@srcdir@ -mandir=@mandir@ -INSTALL=@INSTALL@ -INSTALL_PROGRAM=@INSTALL_PROGRAM@ -INSTALL_DATA=@INSTALL_DATA@ -MKDIR_P=@MKDIR_P@ -ELISPDIR=@ELISPDIR@ -CLEAN=@CLEAN@ - -CC=@CC@ -CFLAGS=@CFLAGS@ -CPPFLAGS=@CPPFLAGS@ -I$(srcdir) -I. $(DEFS) $(USRDEFS) -DEFS=@DEFS@ -LIBS=@LIBS@ -LDFLAGS=@LDFLAGS@ -LN_S=@LN_S@ -LATEX=@LATEX@ -DVIPS=@DVIPS@ -PS2PDF=ps2pdf -PERL5=@PERL5@ -LATEX2HTML=@LATEX2HTML@ -LYNX=@LYNX@ -GROFF=@GROFF@ -SHELL=/bin/sh - -BUILT_SCRIPTS=@BUILT_SCRIPTS@ -SCRIPTS=@SCRIPTS@ - -USRDEFS=-DSYSCONFDIR=\"$(sysconfdir)\" -D__unix__ - -VPATH=$(srcdir) - -##################################################################### - -EXTRA_DIST=configure.in Makefile.in stamp-h.in config.h.in rmeheader.in \ - MakeHTML.pl ChkTeX.tex.in aclocal.m4 NEWS \ - chktex.el chkweb deweb.in COPYING chktex.1 chkweb.1 deweb.1 \ - Test.tex input.tex Test.out configure install-sh lacheck chktexrc \ - $(wildcard m4/*.m4) - -# created by configure -CONFIG_DIST=ChkTeX.tex - -# created at make time -BUILT_DIST=chktex.doc chkweb.doc deweb.doc README ChkTeX.dvi - -CSOURCES=ChkTeX.c FindErrs.c OpSys.c Resource.c Utility.c - -# The sources are the C sources and possibly the files with the same base name -# but ending with .h -SOURCEFILES=$(CSOURCES) $(wildcard $(CSOURCES:.c=.h)) types.h - -DISTFILES=$(EXTRA_DIST) $(SOURCEFILES) - -all: chktex - -DISTDIR:=chktex-@PACKAGE_VERSION@ -dist: $(DISTDIR).tar.gz -$(DISTDIR).tar.gz: $(DISTFILES) $(CONFIG_DIST) $(BUILT_DIST) html - rm -r $(DISTDIR) 2>/dev/null ; true - $(MKDIR_P) $(DISTDIR) - for f in $(DISTFILES) ; do \ - cp $(srcdir)/$$f $(DISTDIR) ; \ - done - cp $(CONFIG_DIST) $(BUILT_DIST) $(DISTDIR) - $(MKDIR_P) $(DISTDIR)/html - cp HTML/ChkTeX/*.{html,css} $(DISTDIR)/html - rm -f $(DISTDIR).tar.gz - tar --owner=0 --group=0 -chzf $@ $(DISTDIR) - rm -rf $(DISTDIR) - -######################################################################## - -.c.o: - $(CC) $(CPPFLAGS) $(CFLAGS) -c $< -o $@ -CLEAN+=$(CSOURCES:.c=.o) - -.%.d: %.c - $(CC) -M $(CPPFLAGS) $< > $@.tmp - sed 's,\($*\)\.o *:,\1.o $@ : Makefile,g' $@.tmp > $@ - -rm -f $@.tmp 2>/dev/null - -DEPFILES=$(patsubst %.c,.%.d,$(CSOURCES)) -CLEAN+=$(DEPFILES) - -ifeq ($(findstring clean,$(MAKECMDGOALS)),) -include $(DEPFILES) -endif - -###################### MAIN DEPENDENCIES ################################ - -OBJS= ChkTeX.o FindErrs.o OpSys.o Resource.o Utility.o - -MAKETEST= (builddir=`pwd` ; cd $(srcdir) ; $${builddir}/chktex -mall -r -g0 -lchktexrc -v5 Test.tex) - -$(srcdir)/Test.out: - -rm -f $(srcdir)/Test.out - $(MAKETEST) 1> $(srcdir)/Test.out - -check: chktex - @echo ">>> Testing that checking algorithms work correctly..." - @-rm -f chktest - $(MAKETEST) 1> chktest - @if cmp -s chktest $(srcdir)/Test.out; then \ - echo ">>> OK!"; \ - rm -f chktest; \ - else \ - echo "***WARNING***"; \ - echo "Problems when checking compilation. This may or may not"; \ - echo "be a problem; anyway, I'm giving you a diff from what the"; \ - echo "results were *supposed* to be..."; \ - diff -u chktest $(srcdir)/Test.out; \ - fi - - -chktex: $(OBJS) - $(CC) $(LDFLAGS) -o chktex $(OBJS) $(LIBS) - -install: chktex ChkTeX.dvi - $(MKDIR_P) $(DESTDIR)$(bindir) - for program in chktex $(BUILT_SCRIPTS); do \ - $(INSTALL_PROGRAM) $$program $(DESTDIR)$(bindir); \ - done - for program in $(SCRIPTS); do \ - $(INSTALL_PROGRAM) $(srcdir)/$$program $(DESTDIR)$(bindir); \ - done - $(MKDIR_P) $(DESTDIR)$(sysconfdir) - $(INSTALL_DATA) $(srcdir)/chktexrc $(DESTDIR)$(sysconfdir) - if (eval echo "$(BUILT_SCRIPTS)") | egrep deweb >/dev/null 2>&1; then \ - $(MKDIR_P) $(DESTDIR)$(mandir)/man1; \ - cp $(srcdir)/deweb.1 $(DESTDIR)$(mandir)/man1; \ - fi - if (eval echo "$(ELISPDIR)") | egrep "/" >/dev/null 2>&1; then \ - $(INSTALL_DATA) $(srcdir)/chktex.el $(DESTDIR)$(ELISPDIR); \ - fi - - - -uninstall: - for program in chktex $(SCRIPTS) $(BUILT_SCRIPTS); do \ - rm -f $(DESTDIR)$(bindir)/$$program; \ - done - rm -f $(DESTDIR)$(sysconfdir)/chktexrc $(DESTDIR)$(mandir)/man1/deweb.1 - if (eval echo "$(ELISPDIR)") | egrep "/" >/dev/null 2>&1; then \ - rm -f $(DESTDIR)$(ELISPDIR)/chktex.el ; \ - fi - -test: - chktex -v2 -mall $(srcdir)/Test.tex | less -r - -indent: - indent -npsl -bli0 -npcs -nut -i4 $(SOURCEFILES) - -mostlyclean: clean - -clean: - rm -rf $(CLEAN) $(BUILT_DIST) $(DISTDIR).tar.gz \ - *.aux *.log *.pdf *.dvi *.ps \ - chktex HTML rme chktest - -distclean: clean - rm -rf $(CONFIG_DIST) *.cache *.status *.log *.tar.gz \ - deweb Makefile autom4te.cache config.h - -maintainer-clean: distclean - rm -rf *.rme install-sh config.guess config.sub aclocal.m4 \ - configure missing rmeheader stamp-h mkinstalldirs tags - -dvi: ChkTeX.dvi - -ifneq ($(LATEX2HTML),) -html: ChkTeX.tex MakeHTML.pl - -rm -r HTML - $(MKDIR_P) HTML - $(PERL5) $(srcdir)/MakeHTML.pl ChkTeX.tex > HTML/ChkTeX.tex - cd HTML; $(LATEX2HTML) ChkTeX.tex - $(PERL5) -i -pe 's% %%gi;s%\s+([.,?!])%$$1%g;' HTML/ChkTeX/*.html - -README: ChkTeX.tex rmeheader MakeHTML.pl - rm -rf rme - $(MKDIR_P) rme - $(PERL5) $(srcdir)/MakeHTML.pl ChkTeX.tex > rme/ChkTeX.tex - cd rme; $(LATEX2HTML) -split 0 ChkTeX.tex - $(PERL5) -i -pe 's%LA%La%g;s%TEX%TeX%g;s%(.*)%$$1%g' rme/ChkTeX/*.html - $(PERL5) -i -pe 's% %%gi;s%\s+([.,?!])%$$1%g;' rme/ChkTeX/*.html - $(LYNX) -dump rme/ChkTeX/ChkTeX.html > rme/ChkTeX.rme - cp rmeheader README - $(PERL5) -e 'undef $$/;$$_=<>;($$_)=/(.*INTRODUCTION(.|\n)*?)[ \t]+ABOUT THIS DOCUMENT/i;s/[ \t]+\n/\n/g;s/\n\n\n/\n/g;s/\[\d+\]//g;print;' rme/ChkTeX.rme >> README - rm -rf rme -else -html README: - @echo "latex2html is unavailable on this system, cant create target $@."; exit 1 -endif - -###################### AUTOCONF REMAKING ################################ - -$(srcdir)/configure: configure.in aclocal.m4 - cd $(srcdir) && autoconf - -#autoheader might not change config.h.in, so touch a stamp file. -$(srcdir)/config.h.in: stamp-h.in -$(srcdir)/stamp-h.in: configure.in aclocal.m4 - cd $(srcdir) && autoheader - echo timestamp > $(srcdir)/stamp-h.in - -config.h: stamp-h -stamp-h: config.h.in config.status - ./config.status - -ChkTeX.tex: ChkTeX.tex.in - ./config.status ChkTeX.tex - -Makefile: Makefile.in config.status - ./config.status - -config.status: configure - ./config.status --recheck - -###################### INDIVIDUAL DEPENDENCIES ########################## - -%.doc: %.1 - $(GROFF) $< > $@ - -ChkTeX.dvi: ChkTeX.tex -ifdef LATEX - $(LATEX) ChkTeX.tex -else - echo "No latex program found by configure" - false -endif - -ChkTeX.ps: ChkTeX.dvi - $(DVIPS) -o ChkTeX.ps ChkTeX.dvi - -ChkTeX.pdf: ChkTeX.ps - $(PS2PDF) $< $@ - -cover: - -./chktex -h - -./chktex Test.tex - -./chktex -v2 -t -o tmptmptmp - - * Fixed some memory issues - * Do not increase line number when the line was very long - * Some fixes for TexLive - -1.6.5 (??), released by Jean-Marc Lasgouttes - - * Fix bug where ChkTeX generates a warning about missing space before - parenthesis when the parenthesis is at start of line. - * Update ChkTeX.tex.in to use proper LaTeX2e markup. - * Update the build machinery a bit. - -1.6.4 (2007-10-20), released by Baruch Even - - * For some reason 1.6.3 did not include all the changes it was supposed to - have, this release should fix it. One such issue is the MacOS X - compilation. - * Include some updates to the default chktexrc from Jean-Marc Lasgouttes. - -1.6.3, released by Baruch Even - - * Support DESTDIR for installation to help distributions. - * Apply old standing patch from Jean-Marc Lasgouttes to compile outside the - directory. - * Enable compilation on MacOS X. - * Fix various coding issues. - - -Original versions from Jens T. Berger Thielemann: -================================================= - -Modifications and additions since v1.6: - - * Improved the build system - * Better fixes for memory access errors - -Modifications and additions since v1.5: - - * Fixed a crash when running from emacs - * Fixed a crash when checking our own manual - * Added \verb* support - -Modifications and additions since v1.4: - - ** New warnings - - * No space or similar in front/after parenthesis. - * Demands a consistent quote style. - * Double spaces in input which will not be rendered as one. - * Punctuation malplaced regarding to math mode. - * Warns about TeX primitives. - * Space in front of footnotes. - * Bogus \left and \right commands. - - ** Program - - * The abbreviation recognizer has (for the last time?) been - redesigned. We now produce far less false warnings, catch more - cases and do all this faster than before. Seems like a win. Done - much of the same with the italic correction detection part, - too. - * Some bugs have been silently fixed. Hot spots in the program have - been optimized; in certain cases this in fact doubles the speed! - * Along with this goes more code elegance and utilization of macro - processing and the C language. Take a look at Resource.[ch]. - - * It's possible to specify separate output-formats depending on - whether you are sending the output to a file/pipe or to a - terminal. - - * Column positions are finally correct; we now expand tabs - correctly. - * ChkTeX will now recursively search for \input'ed - files, both in the document and on the commandline. See the - chktexrc file for more info. - * The debug switch is now more intelligent; if you wish to hack - a bit on ChkTeX for yourself, it is possible to produce - selective debugging output. The feature can also be disabled - altogether. - * MS-DOS and OS/2 version of the program is now more flexible - and well-behaved, thanks to Gerd Boehm. - * You may now say -wall to make all messages warnings, and - turn them on. - * Uses termcap on UNIX boxes; this should ensure that -v2 - (or more precisely: %i and %I works regardless to - what terminal you are using. - - ** Resource file - - * You may now specify both case-sensitive and case-insensitive user - patterns in the chktexrc file. In addition; it is now possible to - reset/clear lists. - * You can now specify how many optional or required arguments - WIPEARG should wipe; it also behaves somewhat more intelligently - when the arguments stretch over multiple lines. - * Global files will be read in addition to local ones. The searching - order has also been reversed in order to make this more - intelligent. - - ** Other - - * The documentation has been polished and should now be easier - to use in practical situations. - * check target in Makefile, so you can check that the installation - succeeded. In fact, the Makefile has been enhanced in several other - ways too, amongst other it is now GNU conforming. - * deweb is now documented; you may say "man deweb" to get a few - words of advice. The support script (chkweb) does now behave as the - remaining package (accepting stdin input and flags). - * I've written an Emacs hack which magically adds ChkTeX to the list - of AUC-TeX commands; thus making the use of the program even more - trivial. For those of you who don't wish to mess with Emacs, I've - included a trivial lacheck <-> ChkTeX interface. This means that you - now can use ChkTeX just as easily as lacheck when you're running - AUC-TeX. - * Added an ARexx script which lets ChkTeX talk to VBrowse, the - message browser of Volker Barthelmann's freely distributable ANSI - C compiler. The browser itself is available on Aminet as - dev/c/vbcc.lha. diff --git a/Build/source/texk/chktex/chktex-1.6.6/OpSys.c b/Build/source/texk/chktex/chktex-1.6.6/OpSys.c deleted file mode 100644 index d2891b08581..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/OpSys.c +++ /dev/null @@ -1,485 +0,0 @@ -/* - * ChkTeX, operating system specific code for ChkTeX. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - - -/* - * Some functions which have to be made different from OS to OS, - * unfortunately...:\ - * - */ - -#include "ChkTeX.h" -#include "OpSys.h" -#include "Utility.h" - -#ifdef HAVE_SYS_STAT_H -# include -#endif -#ifdef HAVE_STAT_H -# include -#endif - -#if HAVE_DIRENT_H -# include -# define NAMLEN(dirent) strlen((dirent)->d_name) -#else -# define dirent direct -# define NAMLEN(dirent) (dirent)->d_namlen -# if HAVE_SYS_NDIR_H -# include -# endif -# if HAVE_SYS_DIR_H -# include -# endif -# if HAVE_NDIR_H -# include -# endif -#endif - -#if defined(HAVE_OPENDIR) && defined(HAVE_CLOSEDIR) && \ - defined(HAVE_READDIR) && defined(HAVE_STAT) && \ - defined(S_IFDIR) && defined(SLASH) -# define USE_RECURSE 1 -#else -# define USE_RECURSE 0 -#endif - -#if defined(HAVE_LIBTERMCAP) || defined(HAVE_LIBTERMLIB) -# define USE_TERMCAP 1 -#endif - - -#ifdef USE_TERMCAP -# ifdef HAVE_TERMCAP_H -# include -# elif HAVE_TERMLIB_H -# include -# else -int tgetent(char *BUFFER, char *TERMTYPE); -char *tgetstr(char *NAME, char **AREA); -# endif -static char term_buffer[2048]; -#endif - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * This is the name of the global resource file. - */ - -#ifndef SYSCONFDIR -# if defined(__unix__) -# define SYSCONFDIR "/usr/local/lib/" -# elif defined(__MSDOS__) -# define SYSCONFDIR "\\emtex\\data\\" -# else -# define SYSCONFDIR -# endif -#endif -#define RCBASENAME "chktexrc" - -#ifdef __MSDOS__ -# define LOCALRCFILE RCBASENAME -#else -# define LOCALRCFILE "." RCBASENAME -#endif - -char ConfigFile[BUFSIZ] = LOCALRCFILE; -const char *ReverseOn; -const char *ReverseOff; - - -static int HasFile(char *Dir, const char *Filename, const char *App); - -#if USE_RECURSE -static int SearchFile(char *Dir, const char *Filename, const char *App); -#endif /* USE_RECURSE */ - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - - -/* - * Modify this one to suit your needs. In any case, it should fill - * the ConfigFile (sized BUFLEN) buffer above with full name & path - * for the configuration file. The macro RCFILE will give you the - * filename part of the file, if you need that. - * - * Note: This routine will be called several times. Your mission will - * be to look in each location, and see whether a .chktexrc file exist - * there. - * - * If you choose to do nothing, only the current directory will be - * searched. - * - */ - - -enum LookIn -{ - liMin, - liSysDir, - liUsrDir, - liEnvir, - liCurDir, - liNFound, - liMax -}; - - -int SetupVars(void) -{ - char *Env; -#ifdef __MSDOS__ - - char *Ptr; -#endif - - static enum LookIn i = liMin; - static int FoundFile; - - while (++i < liMax) - { - switch (i) - { - case liCurDir: /* Current directory */ - strcpy(ConfigFile, LOCALRCFILE); - break; - case liEnvir: /* Environment defined */ -#ifdef __MSDOS__ - - if ((Env = getenv("CHKTEXRC")) || (Env = getenv("CHKTEX_HOME"))) -#else - - if ((Env = getenv("CHKTEXRC"))) -#endif - - { - strcpy(ConfigFile, Env); - tackon(ConfigFile, LOCALRCFILE); - } - else -#ifdef __MSDOS__ - if ((Env = getenv("EMTEXDIR"))) - { - strcpy(ConfigFile, Env); - tackon(ConfigFile, "data"); - tackon(ConfigFile, LOCALRCFILE); - } - else -#endif - - *ConfigFile = 0; - break; - case liUsrDir: /* User dir for resource files */ -#if defined(__unix__) - - if ((Env = getenv("HOME")) || (Env = getenv("LOGDIR"))) - { - strcpy(ConfigFile, Env); - tackon(ConfigFile, LOCALRCFILE); - } - else -#elif defined(__MSDOS__) - - strcpy(ConfigFile, PrgName); - if ((Ptr = strrchr(ConfigFile, '\\')) || - (Ptr = strchr(ConfigFile, ':'))) - strcpy(++Ptr, RCBASENAME); - else -#endif - *ConfigFile = 0; - - break; - case liSysDir: /* System dir for resource files */ -#ifdef TEX_LIVE - if ((Env = getenv("CHKTEX_CONFIG"))) - { - strcpy(ConfigFile, Env); - } - else - { - FILE *f; - *ConfigFile = 0; - if ((f = popen("kpsewhich -expand-var='$TEXMFMAIN'", "r"))) - { - if (1 == fscanf(f, "%1024s", ConfigFile)) - { - tackon(ConfigFile, "chktex"); - tackon(ConfigFile, RCBASENAME); - } - (void)pclose(f); - } - } -#else /* TEX_LIVE */ -#if defined(__unix__) || defined(__MSDOS__) - strcpy(ConfigFile, SYSCONFDIR); - tackon(ConfigFile, RCBASENAME); -#else - *ConfigFile = 0; -#endif -#endif /* TEX_LIVE */ - - break; - case liNFound: - case liMin: - case liMax: - *ConfigFile = 0; - if (!FoundFile) - PrintPrgErr(pmNoRsrc); - } - - if (*ConfigFile && fexists(ConfigFile)) - break; - } - FoundFile |= *ConfigFile; - - return (*ConfigFile); -} - - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * This function should initialize the global variables ReverseOn - * and ReverseOff to magic cookies, which when printed, makes the - * text in between stand out. - */ - -void SetupTerm(void) -{ -#ifdef USE_TERMCAP - char *termtype = getenv("TERM"); - int success; - char *buffer; - static char str_so[3] = "so", str_se[3] = "se"; - - if (termtype) - { - - success = tgetent(term_buffer, termtype); - if (success < 0) - PrintPrgErr(pmNoTermData); - if (success == 0) - PrintPrgErr(pmNoTermDefd); - - buffer = (char *) malloc(sizeof(term_buffer)); - ReverseOn = tgetstr(str_so, &buffer); - ReverseOff = tgetstr(str_se, &buffer); - - if (ReverseOn && ReverseOff) - return; - } -#endif - - ReverseOn = PRE_ERROR_STR; - ReverseOff = POST_ERROR_STR; -} - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * Concatenates the `File' string to the `Dir' string, leaving the result - * in the `Dir' buffer. Takes care of inserting `directory' characters; - * if we've got the strings "/usr/foo" and "bar", we'll get - * "/usr/foo/bar". - * - * Behaviour somewhat controlled by the macros SLASH and DIRCHARS in the - * OpSys.h file. - * - */ - -void tackon(char *Dir, const char *File) -{ - int EndC; - unsigned long SLen; - - if (Dir && (SLen = strlen(Dir))) - { - EndC = Dir[SLen - 1]; - if (!(strchr(DIRCHARS, EndC))) - { - Dir[SLen++] = SLASH; - Dir[SLen] = 0L; - } - } - - strcat(Dir, File); -} - -/* - * This function should add the appendix App to the filename Name. - * If the resulting filename gets too long due to this, it may - * overwrite the old appendix. - * - * Name may be assumed to be a legal filename under your OS. - * - * The appendix should contain a leading dot. - */ - -void AddAppendix(char *Name, const char *App) -{ -#ifdef __MSDOS__ - char *p; - - if ((p = strrchr(Name, '.'))) - strcpy(p, App); - else - strcat(Name, App); -#else - /* - * NOTE! This may fail if your system has a claustrophobic file - * name length limit. - */ - strcat(Name, App); -#endif - -} - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - - -/* - * Locates a file, given a wordlist containing paths. If a - * dir ends in a double SLASH, we'll search it recursively. - * - * We assume that - * a) a deeper level in the dir. tree. has a longer path than - * one above. - * b) adding a level doesn't change any of the previous levels. - * - * If this function returns TRUE, Dest is guaranteed to contain - * path & name of the found file. - * - * FALSE indicates that the file was not found; Dest is then - * unspecified. - */ - - -int LocateFile(const char *Filename, /* File to search for */ - char *Dest, /* Where to put final file */ - const char *App, /* Extra optional appendix */ - struct WordList *wl) /* List of paths, entries - * ending in // will be recursed - */ -{ - unsigned long i; -#if USE_RECURSE - - unsigned long Len; -#endif - - FORWL(i, *wl) - { - strcpy(Dest, wl->Stack.Data[i]); - -#if USE_RECURSE - - Len = strlen(Dest); - - if (Len && (Dest[Len - 1] == SLASH) && (Dest[Len - 2] == SLASH)) - { - Dest[Len - 1] = Dest[Len - 2] = 0; - if (SearchFile(Dest, Filename, App)) - return (TRUE); - } - else -#endif /* USE_RECURSE */ - - { - if (HasFile(Dest, Filename, App)) - return (TRUE); - } - } - return (FALSE); -} - -static int HasFile(char *Dir, const char *Filename, const char *App) -{ - int DirLen = strlen(Dir); - - tackon(Dir, Filename); - if (fexists(Dir)) - return (TRUE); - - if (App) - { - AddAppendix(Dir, App); - if (fexists(Dir)) - return (TRUE); - } - - Dir[DirLen] = 0; - return (FALSE); - -} - - -#if USE_RECURSE -static int SearchFile(char *Dir, const char *Filename, const char *App) -{ - struct stat *statbuf; - struct dirent *de; - DIR *dh; - - int DirLen = strlen(Dir); - int Found = FALSE; - - DEBUG(("Searching %s for %s\n", Dir, Filename)); - - if (HasFile(Dir, Filename, App)) - return (TRUE); - else - { - if ((statbuf = malloc(sizeof(struct stat)))) - { - if ((dh = opendir(Dir))) - { - while (!Found && (de = readdir(dh))) - { - Dir[DirLen] = 0; - if (strcmp(de->d_name, ".") && strcmp(de->d_name, "..")) - { - tackon(Dir, de->d_name); - - if (!stat(Dir, statbuf)) - { - if ((statbuf->st_mode & S_IFMT) == S_IFDIR) - Found = SearchFile(Dir, Filename, App); - } - } - } - closedir(dh); - } - else - PrintPrgErr(pmNoOpenDir, Dir); - free(statbuf); - } - } - return (Found); -} -#endif /* USE_RECURSE */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/OpSys.h b/Build/source/texk/chktex/chktex-1.6.6/OpSys.h deleted file mode 100644 index 7ce3f1b5270..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/OpSys.h +++ /dev/null @@ -1,207 +0,0 @@ -/* - * ChkTeX, operating system specific code for ChkTeX. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#ifndef OPSYS_H -#define OPSYS_H - -#include "ChkTeX.h" -#include "Utility.h" - -/********************************************************************/ -/**************** START OF USER SETTABLE PREFERENCES ****************/ - -/* - * Note: This file contains most defines you'll wish to change if you - * wish to adopt ChkTeX to a new system. It is, as you might notice, - * heavily documented. If you wish to get into the internals of ChkTeX, - * the interesting stuff is at the bottom of this file, and in the .c - * files. However, you should also take a look at the "config.h.in" file - * in this directory if you haven't got a shell able to run the "configure" - * script. - * - * This program relies heavily on that the system which - * automagically free()'s all malloc()'ed memory, works. The program - * itself does not call free() very much. This is because we're doing - * lots of tiny allocations, and a properly designed pooling system will - * hopefully do a quicker job than we'll be able to do. So there. - * - * To keep things simple, we trust that the fclose()'ing of fopen()'ed - * also happens automagically. - * - * Please use the getopt included, as we will modify optarg during - * command processing. - * - * You may wish to modify the SetupVars() (OpSys.c) to better suit your - * preferences. In any case, it should put the filename (and full path) - * of the `.chktexrc' file into the ConfigFile array. The array is sized - * BUFSIZ bytes. - * - * The program does also assume that __unix__ is defined if the source is - * compiled on a UNIX machine. - * - */ - - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * Here you should define what codes which should be returned to the - * shell upon success/failure. - * - */ - -#ifndef EXIT_FAILURE -# define EXIT_FAILURE 1 -#endif - -#ifndef EXIT_SUCCESS -# define EXIT_SUCCESS 0 -#endif - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * SLASH should be defined to the character your computer uses to - * separate files/directories. Most systems use '/', messydos uses - * '\'. - * - * DIRCHARS should be defined to the characters a directory entry - * may end on. On Amigas, this is ":/" (either "FOO:BAR/" or "FOO:"), - * Unix uses only "/", while messydos uses ":\\". - * - * This data will be used to automatically concatenate a directory - * path and a filename. - * - * Adjust both to suit your needs. - */ - - -#ifdef TEX_LIVE -#if defined(__MSDOS__) || defined(WIN32) -# define SLASH '\\' -# define DIRCHARS ":\\" -#else -# define SLASH '/' -# define DIRCHARS "/" -#endif -#else /* TEX_LIVE */ -#if defined(__unix__) -# define SLASH '/' -#elif defined(__MSDOS__) -# define SLASH '\\' -#endif - -#if defined(__unix__) -# define DIRCHARS "/" -#elif defined(__MSDOS__) -# define DIRCHARS ":\\" -#endif -#endif /* TEX_LIVE */ - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * Here, define what key-combination which is used to abort stdin - * keyboard input. It should be a string, as we we'll type it out as - * information to the user. - */ - -#if defined(__unix__) -# define STDIN_BREAK "Ctrl-D" -#elif defined(__MSDOS__) -# define STDIN_BREAK "Ctrl-Z + Enter" -#else -# define STDIN_BREAK "stdin break combination" -#endif - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * For fancy printing of commands, we'll use these strings to turn - * on/off the error indication. The codes listed here are ANSI - * compatible; if you don't have that type of terminal, you may wish - * to adjust this. Use "chktex -v2 Test.tex" to check the effects of - * these macros. Note: These strings will be printf()'ed, so watch your - * %'s. - * - * Under UNIX, we'll ignore these values and use termcap instead, where - * that is installed. - * - * If these strings can't be specified statically, you'll have to add - * code in the SetupTerm() function. - * - * PRE_ERROR_STR is of course printed in front of each location we - * wish to show as an error, and POST_ERROR_STR after each location. - * - * The codes #defined here, will switch back- and foreground colours. - * We're using '\033[' as escape character, some terminals may like - * '\233' better. - * - */ - -# define PRE_ERROR_STR "\033[7m" -# define POST_ERROR_STR "\033[0m" - - -/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ - -/* - * This macro should contain the appendix for backup files, which - * will be appended onto the original filename. It should contain - * a leading dot. - */ - -#ifdef __MSDOS__ -# define BAKAPPENDIX ".$cl" -#else -# define BAKAPPENDIX ".bak" -#endif - -/***************** END OF USER SETTABLE PREFERENCES *****************/ -/********************************************************************/ - -#ifndef WORDLIST_DEFINED -struct WordList; -#endif -/* Sorry; there are now cyclic dependencies in the -* source tree. :-/ -*/ - -extern const char *ReverseOn; -extern const char *ReverseOff; -extern char ConfigFile[BUFSIZ]; - -char *MatchFileName(char *String); -int SetupVars(void); -void SetupTerm(void); -void AddAppendix(char *Name, const char *App); -void tackon(char *, const char *); -int LocateFile(const char *Filename, char *Dest, const char *App, - struct WordList *wl); - -#endif /* OPSYS_H */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/Resource.c b/Build/source/texk/chktex/chktex-1.6.6/Resource.c deleted file mode 100644 index c30e73acd6d..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Resource.c +++ /dev/null @@ -1,510 +0,0 @@ -/* - * ChkTeX, resource file reader. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#include "ChkTeX.h" -#include "OpSys.h" -#include "Utility.h" -#include "Resource.h" - -#define LNEMPTY(a) struct WordList a = {0, 1, {0}, {0}}; -#define LIST(a) struct WordList a = {0, 0, {0}, {0}}; -#define LCASE(a) LIST(a) LIST(a ## Case) -#define KEY(a,def) const char *a = def; - -RESOURCE_INFO -#undef KEY -#undef LCASE -#undef LNEMPTY -#undef LIST - struct KeyWord -{ - const char *Name; - const char **String; /* Keyword = item */ - struct WordList *List, /* Case-sensitive strings */ - *CaseList; /* Case-insensitive strings */ -}; - -#define LNEMPTY LIST -#define LIST(name) {#name, NULL, &name, NULL}, -#define LCASE(name) {#name, NULL, &name, &name ## Case}, -#define KEY(name,def) {#name, &name, NULL, NULL}, - -struct KeyWord Keys[] = { - RESOURCE_INFO {NULL, NULL, NULL, NULL} -}; - -#undef KEY -#undef LCASE -#undef LNEMPTY -#undef LIST - - -/***************************** RESOURCE HANDLING **************************/ - -#define TOKENBITS(name) enum name { \ - BIT(Eof), /* End-of-file */ \ - BIT(Open), /* { */ \ - BIT(Close), /* } */ \ - BIT(BrOpen), /* [ */ \ - BIT(BrClose), /* ] */ \ - BIT(Equal), /* = */ \ - BIT(Word), /* Keyword */ \ - BIT(Item) /* List item */ \ -}; - -#undef BIT -#define BIT BITDEF1 -TOKENBITS(Token_BIT) -#undef BIT -#define BIT BITDEF2 - TOKENBITS(Token) - static enum Token Expect; - static unsigned long RsrcLine; - - static enum Token ReadWord(char *, FILE *); - static char MapChars(char **String); - - - -/* - * Parses the contents of a resource file. - * - * Format: - * Keyword { item1 item2 ... } [ item1 item2 ... ] - * Keyword [ item1 item2 ... ] { item1 item2 ... } - * Keyword = { item1 item2 ... } - * Keyword = [ item1 item2 ... ] - * Keyword = item - * - * Returns whether the attempt was a successful one. - */ - - int ReadRC(const char *Filename) -{ - const char *String = NULL; - int Success = FALSE; - FILE *fh; - enum Token Token; - unsigned long Counter; - - struct KeyWord *CurWord = NULL; - - /* Interpret incoming words as ... */ - enum - { - whList, /* List elements */ - whCaseList, /* Case insensitive list elements */ - whEqual, /* Solo elements */ - whNone /* List items not accepted */ - } What = whNone; - - - RsrcLine = 0; - Expect = FLG_Word | FLG_Eof; - - if ((fh = fopen(Filename, "r"))) - { - Success = TRUE; - do - { - Token = ReadWord(ReadBuffer, fh); - if (!(Expect & Token)) - { - switch (Token) - { - case FLG_Item: - String = "item"; - break; - case FLG_Word: - String = "word"; - break; - case FLG_Equal: - String = "`='"; - break; - case FLG_Open: - String = "`{'"; - break; - case FLG_Close: - String = "`}'"; - break; - case FLG_BrOpen: - String = "`['"; - break; - case FLG_BrClose: - String = "`]'"; - break; - case FLG_Eof: - String = "EOF"; - break; - } - PrintPrgErr(pmFaultFmt, Filename, RsrcLine, String); - Success = FALSE; - Token = FLG_Eof; - } - - switch (Token) - { - case FLG_Word: - for (Counter = 0; Keys[Counter].Name; Counter++) - { - if (!strcasecmp(ReadBuffer, Keys[Counter].Name)) - { - CurWord = &Keys[Counter]; - Expect = (CurWord->List ? FLG_Open : 0) | - (CurWord->CaseList ? FLG_BrOpen : 0) | FLG_Equal; - break; - } - } - if (!Keys[Counter].Name) - { - PrintPrgErr(pmKeyWord, ReadBuffer, Filename); - Success = FALSE; - Token = FLG_Eof; - } - break; - case FLG_Item: - switch (What) - { - case whEqual: - if (!(*(CurWord->String) = strdup(ReadBuffer))) - { - PrintPrgErr(pmStrDupErr); - Token = FLG_Eof; - Success = FALSE; - } - - What = whNone; - Expect = FLG_Word | FLG_Eof; - break; - case whCaseList: - if (!InsertWord(ReadBuffer, CurWord->CaseList)) - { - Token = FLG_Eof; - Success = FALSE; - } - break; - case whList: - if (!InsertWord(ReadBuffer, CurWord->List)) - { - Token = FLG_Eof; - Success = FALSE; - } - break; - case whNone: - PrintPrgErr(pmAssert); - } - break; - case FLG_Equal: - What = whEqual; - Expect = (CurWord->List ? FLG_Open : 0) | - (CurWord->CaseList ? FLG_BrOpen : 0) | - (CurWord->String ? FLG_Item : 0); - break; - case FLG_BrOpen: - if (What == whEqual) - ClearWord(CurWord->CaseList); - What = whCaseList; - Expect = FLG_Item | FLG_BrClose; - break; - case FLG_Open: - if (What == whEqual) - ClearWord(CurWord->List); - What = whList; - Expect = FLG_Item | FLG_Close; - break; - case FLG_BrClose: - case FLG_Close: - Expect = (CurWord->List ? FLG_Open : 0) | - (CurWord->CaseList ? FLG_BrOpen : 0) | - FLG_Equal | FLG_Word | FLG_Eof; - What = whNone; - break; - case FLG_Eof: - break; - } - } - while (Token != FLG_Eof); - - fclose(fh); - } - else - PrintPrgErr(pmRsrcOpen, Filename); - - return (Success); -} - -/* - * Reads a token from the `.chktexrc' file; if the token is - * FLG_Item or FLG_Word, Buffer will contain the plaintext of the - * token. If not, the contents are undefined. - */ - -static enum Token ReadWord(char *Buffer, FILE * fh) -{ - static char *String = NULL; - static char StatBuf[BUFSIZ]; - enum Token Retval = FLG_Eof; - - unsigned short Chr; - - char *Ptr; - int OnceMore = TRUE, Cont = TRUE; - - if (Buffer) - { - do - { - if (!(String && *String)) - { - if (fgets(StatBuf, BUFSIZ - 1, fh)) - String = strip(StatBuf, STRP_RGT); - RsrcLine++; - } - - Ptr = Buffer; - if (String && (String = strip(String, STRP_LFT))) - { - switch (Chr = *String) - { - case 0: - case CMNT: - String = NULL; - break; - case QUOTE: /* Quoted argument */ - Cont = TRUE; - String++; - - while (Cont) - { - switch (Chr = *String++) - { - case 0: - case QUOTE: - Cont = FALSE; - break; - case ESCAPE: - if (!(Chr = MapChars(&String))) - break; - - /* FALLTHRU */ - default: - *Ptr++ = Chr; - } - } - *Ptr = 0; - Retval = FLG_Item; - OnceMore = FALSE; - break; - -#define DONEKEY (FLG_Open | FLG_Equal | FLG_BrOpen) -#define DONELIST (FLG_Close | FLG_BrClose) -#define TOKEN(c, ctxt, tk) case c: if(Expect & (ctxt)) Retval = tk; LAST(token); - - LOOP(token, - TOKEN('{', DONEKEY, FLG_Open); - TOKEN('[', DONEKEY, FLG_BrOpen); - TOKEN('=', DONEKEY, FLG_Equal); - TOKEN(']', DONELIST, FLG_BrClose); - TOKEN('}', DONELIST, FLG_Close); - ); - if (Retval != FLG_Eof) - { - OnceMore = FALSE; - String++; - break; - } - - /* FALLTHRU */ - - default: /* Non-quoted argument */ - OnceMore = FALSE; - if (Expect & FLG_Word) - { - while (Cont) - { - Chr = *String++; - if (isalpha((unsigned char)Chr)) - *Ptr++ = Chr; - else - Cont = FALSE; - } - String--; - Retval = FLG_Word; - } - else /* Expect & FLG_Item */ - { - while (Cont) - { - switch (Chr = *String++) - { - case CMNT: - case 0: - String = NULL; - Cont = FALSE; - break; - case ESCAPE: - if (!(Chr = MapChars(&String))) - break; - - *Ptr++ = Chr; - break; - default: - if (!isspace((unsigned char)Chr)) - *Ptr++ = Chr; - else - Cont = FALSE; - } - } - Retval = FLG_Item; - } - - if (!(Buffer[0])) - { - PrintPrgErr(pmEmptyToken); - if (*String) - String++; - } - *Ptr = 0; - break; - } - } - else - OnceMore = FALSE; - } - while (OnceMore); - } - return (Retval); -} - - - -/* - * Translates escape codes. Give it a pointer to the char after the - * escape char, and we'll return what it maps to. - */ - -#define MAP(a,b) case a: Tmp = b; break; - -static char MapChars(char **String) -{ - int Chr, Tmp = 0; - unsigned short Cnt; - - Chr = *((char *) (*String)++); - - switch (tolower((unsigned char)Chr)) - { - MAP(QUOTE, QUOTE); - MAP(ESCAPE, ESCAPE); - MAP(CMNT, CMNT); - MAP('n', '\n'); - MAP('r', '\r'); - MAP('b', '\b'); - MAP('t', '\t'); - MAP('f', '\f'); - MAP('{', '{'); - MAP('}', '}'); - MAP('[', '['); - MAP(']', ']'); - MAP('=', '='); - MAP(' ', ' '); - case 'x': - Tmp = 0; - - for (Cnt = 0; Cnt < 2; Cnt++) - { - Chr = *((*String)++); - if (isxdigit((unsigned char)Chr)) - { - Chr = toupper((unsigned char)Chr); - Tmp = (Tmp << 4) + Chr; - - if (isdigit((unsigned char)Chr)) - Tmp -= '0'; - else - Tmp -= 'A' - 10; - } - else - { - if (Chr) - { - PrintPrgErr(pmNotPSDigit, Chr, "hex"); - Tmp = 0; - } - break; - } - } - break; - case '0': - case '1': - case '2': - case '3': - case '4': - case '5': - case '6': - case '7': - - Tmp = Chr - '0'; - - for (Cnt = 0; Cnt < 2; Cnt++) - { - Chr = *((*String)++); - if (within('0', Chr, '7')) - Tmp = (Tmp * 8) + Chr - '0'; - else - { - if (Chr) - { - PrintPrgErr(pmNotPSDigit, Chr, "octal"); - Tmp = 0; - } - break; - } - } - break; - case 'd': - for (Cnt = 0; Cnt < 3; Cnt++) - { - if (isdigit((unsigned char)(Chr = *((*String)++)))) - Tmp = (Tmp * 10) + Chr - '0'; - else - { - if (Chr) - { - PrintPrgErr(pmNotPSDigit, Chr, ""); - Tmp = 0; - } - break; - } - } - break; - default: - PrintPrgErr(pmEscCode, ESCAPE, Chr); - } - return (Tmp); -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/Resource.h b/Build/source/texk/chktex/chktex-1.6.6/Resource.h deleted file mode 100644 index 7f23333d3ff..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Resource.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * ChkTeX, resource file reader. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#ifndef RESOURCE_H -#define RESOURCE_H - -#include "ChkTeX.h" - -#define QUOTE '\"' /* Char used to quote text containing blanks */ -#define ESCAPE '!' /* Char used to access special characters */ -#define CMNT '#' /* Char used as comment */ - -#define RESOURCE_INFO \ - LIST(Silent) LIST(Linker) LIST(IJAccent) LIST(Italic)\ - LIST(ItalCmd) LIST(PostLink) LIST(WipeArg) LIST(VerbEnvir)\ - LIST(MathEnvir) LIST(MathRoman) LIST(HyphDash) LIST(NumDash)\ - LIST(WordDash) LIST(CenterDots) LIST(LowDots) LIST(OutFormat)\ - LIST(Primitives) LIST(NotPreSpaced) LIST(NonItalic) LIST(NoCharNext)\ - LNEMPTY(CmdLine) LNEMPTY(TeXInputs)\ - LCASE(Abbrev) LCASE(UserWarn)\ - KEY(VerbClear, "|") KEY(QuoteStyle, "Traditional") KEY(TabSize, "8") - -#define LIST(a) extern struct WordList a; -#define LNEMPTY LIST -#define LCASE(a) LIST(a) LIST(a ## Case) -#define KEY(a,def) extern const char *a; - -RESOURCE_INFO -#undef KEY -#undef LCASE -#undef LNEMPTY -#undef LIST -int ReadRC(const char *); - - -#endif /* RESOURCE */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/Test.out b/Build/source/texk/chktex/chktex-1.6.6/Test.out deleted file mode 100644 index 5d31418f3f3..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Test.out +++ /dev/null @@ -1,411 +0,0 @@ -Message 30 in Test.tex: Multiple spaces detected in input. - o To test the program upon it - ^^^ -Message 30 in Test.tex: Multiple spaces detected in input. - o To show off some of the features - ^^^ -Message 22 in Test.tex: Comment displayed. -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% -^ -Message 22 in Test.tex: Comment displayed. -% Warning 1 -^ -Message 1 in Test.tex: Command terminated with space. -\foo This is an error. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 2 -^ -Message 2 in Test.tex: Non-breaking space (`~') should have been used. -This is a faulty reference to \ref{foo} - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 3 -^ -Message 3 in Test.tex: You should enclose the previous parenthesis with `{}'. -$[(ab)^{-1}]^{-2}$ is not beautiful - ^ -Message 3 in Test.tex: You should enclose the previous parenthesis with `{}'. -$[(ab)^{-1}]^{-2}$ is not beautiful - ^ -Message 30 in Test.tex: Multiple spaces detected in input. -$[(ab)^{-1}]^{-2}$ is not beautiful - ^^ -Message 22 in Test.tex: Comment displayed. -% Warning 4-6, 28 -^ -Message 6 in Test.tex: No italic correction (`\/') found. -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^ -Message 42 in Test.tex: You should remove spaces in front of `\/' -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^^ -Message 28 in Test.tex: Don't use \/ in front of small punctuation. -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^^ -Message 42 in Test.tex: You should remove spaces in front of `\/' -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^ -Message 5 in Test.tex: Italic correction (`\/') found more than once. -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. - ^^ -Message 22 in Test.tex: Comment displayed. -% LaTeX2e -^ -Message 42 in Test.tex: You should remove spaces in front of `\/' -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^^ -Message 42 in Test.tex: You should remove spaces in front of `\/' -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. - ^^ -Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. -Testing \textem{italic\/} in this \textit{sentence}, as \textem{you see}. - ^^ -Message 22 in Test.tex: Comment displayed. -% Warning 7 -^ -Message 7 in Test.tex: Accent command `\'' needs use of `\i'. -This \'is a test of $\hat{j}$ accents. - ^^ -Message 7 in Test.tex: Accent command `\hat' needs use of `\jmath'. -This \'is a test of $\hat{j}$ accents. - ^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 8 -^ -Message 8 in Test.tex: Wrong length of dash may have been used. -It wasn't anything - just a 2---3 star--shots. - ^ -Message 8 in Test.tex: Wrong length of dash may have been used. -It wasn't anything - just a 2---3 star--shots. - ^^^ -Message 8 in Test.tex: Wrong length of dash may have been used. -It wasn't anything - just a 2---3 star--shots. - ^^ -Message 22 in Test.tex: Comment displayed. -% From Knuths TeXbook Chapter 14 -^ -Message 22 in Test.tex: Comment displayed. -% "How TeX Breaks Paragraphs into Lines", fourth paragraph: -^ -Message 22 in Test.tex: Comment displayed. -% Warning 9-10 -^ -Message 22 in Test.tex: Comment displayed. -% Brackets: -^ -Message 10 in Test.tex: Solo `)' found. -)}{[])} }}}]]]))) -^ -Message 10 in Test.tex: Solo `}' found. -)}{[])} }}}]]]))) - ^ -Message 9 in Test.tex: `}' expected, found `)'. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `}' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `}' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `}' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `}' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `]' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `]' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `]' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `)' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `)' found. -)}{[])} }}}]]]))) - ^ -Message 10 in Test.tex: Solo `)' found. -)}{[])} }}}]]]))) - ^ -Message 22 in Test.tex: Comment displayed. -% Envs: -^ -Message 9 in Test.tex: `baz' expected, found `quux'. -\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} - ^^^^ -Message 9 in Test.tex: `quux' expected, found `baz'. -\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} - ^^^^ -Message 10 in Test.tex: Solo `asoi' found. -\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} - ^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 11 -^ -Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. - ^^^ -Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. - ^^^ -Message 11 in Test.tex: You should use \cdots to achieve an ellipsis. -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. - ^^^ -Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. - ^^^^^^ -Message 11 in Test.tex: You should use \cdots to achieve an ellipsis. -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. - ^^^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 12 -^ -Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. -1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar - ^ -Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. -1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar - ^ -Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. -1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 13 -^ -Message 13 in Test.tex: Intersentence spacing (`\@') should perhaps be used. -Look at THIS! It's an error. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 14 -^ -Message 1 in Test.tex: Command terminated with space. -\hat - ^ -Message 14 in Test.tex: Could not find argument for command. -\hat -^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 18,19 -^ -Message 18 in Test.tex: Use either `` or '' as an alternative to `"'. -Is this an "example", or is it an ´example´. - ^ -Message 18 in Test.tex: Use either `` or '' as an alternative to `"'. -Is this an "example", or is it an ´example´. - ^ -Message 19 in Test.tex: Use "'" (ASCII 39) instead of "´" (ASCII 180). -Is this an "example", or is it an ´example´. - ^ -Message 19 in Test.tex: Use "'" (ASCII 39) instead of "´" (ASCII 180). -Is this an "example", or is it an ´example´. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 20 -^ -Message 20 in Test.tex: User-specified pattern found. -That bug is \unknown\ to me. - ^^^^^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 21 -^ -Message 21 in Test.tex: This command might not be intended. -\LaTeX\ is an extension of \TeX\. Right? - ^^ -Message 22 in Test.tex: Comment displayed. -% Warning 23 -^ -Message 23 in Test.tex: Either `\,`` or ``\,` will look better. -```Hello', I heard him said'', she remembered. -^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 24 -^ -Message 24 in Test.tex: Delete this space to maintain correct pagereferences. -Indexing text \index{text} is fun! - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 25 -^ -Message 25 in Test.tex: You might wish to put this between a pair of `{}' -$5\cdot10^10$ - ^^ -Message 22 in Test.tex: Comment displayed. -% Warning 26 -^ -Message 26 in Test.tex: You ought to remove spaces in front of punctuation. -Do you understand ? - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 27 -^ -Message 1 in input.tex: Command terminated with space. -\this is a test of whether the file is actually inputted... - ^ -Message 11 in input.tex: You should use \ldots to achieve an ellipsis. -\this is a test of whether the file is actually inputted... - ^^^ -Message 1 in input.tex: Command terminated with space. -\this is a test of whether the file is actually inputted... - ^ -Message 11 in input.tex: You should use \ldots to achieve an ellipsis. -\this is a test of whether the file is actually inputted... - ^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 29 -^ -Message 29 in Test.tex: $\times$ may look prettier here. -The program opens a screen sized 640x200 pixels - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 30 -^ -Message 30 in Test.tex: Multiple spaces detected in input. -White is a beautiful colour. - ^^^^^^^^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 31 -^ -Message 31 in Test.tex: This text may be ignored. -\end{verbatim} foo bar - ^^^^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 32-34 -^ -Message 32 in Test.tex: Use ` to begin quotation, not '. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^ -Message 33 in Test.tex: Use ' to end quotation, not `. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^ -Message 32 in Test.tex: Use ` to begin quotation, not '. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^^ -Message 33 in Test.tex: Use ' to end quotation, not `. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^^ -Message 34 in Test.tex: Don't mix quotes. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^^^ -Message 34 in Test.tex: Don't mix quotes. -This is either an 'example`, an ''example`` or an `"`example'`'. - ^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 35 -^ -Message 35 in Test.tex: You should perhaps use `\sin' instead. -$sin^2 + cos^2 = 1$ - ^^^ -Message 35 in Test.tex: You should perhaps use `\cos' instead. -$sin^2 + cos^2 = 1$ - ^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 36-37 -^ -Message 36 in Test.tex: You should put a space in front of parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 37 in Test.tex: You should avoid spaces after parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 36 in Test.tex: You should put a space in front of parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 37 in Test.tex: You should avoid spaces after parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 37 in Test.tex: You should avoid spaces in front of parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 36 in Test.tex: You should put a space in front of parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 37 in Test.tex: You should avoid spaces after parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 37 in Test.tex: You should avoid spaces in front of parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 36 in Test.tex: You should put a space after parenthesis. -This( an example( Nuff said )), illustrates( ``my'' )point. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 38 -^ -Message 38 in Test.tex: You should not use punctuation in front of quotes. -``An example,'' he said, ``would be great.'' - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 39 -^ -Message 39 in Test.tex: Double space found. -For output codes, see table ~\ref{tab:fmtout}. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 40 -^ -Message 40 in Test.tex: You should put punctuation outside inner math mode. -$\this,$ and $$this$$. - ^ -Message 40 in Test.tex: You should put punctuation inside display math mode. -$\this,$ and $$this$$. - ^ -Message 22 in Test.tex: Comment displayed. -% Warning 41 -^ -Message 1 in Test.tex: Command terminated with space. -foo \above qux - ^ -Message 41 in Test.tex: You ought to not use primitive TeX in LaTeX code. -foo \above qux - ^^^^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 42 -^ -Message 42 in Test.tex: You should remove spaces in front of `\footnote' -This is a footnote \footnote{foo}. - ^ -Message 22 in Test.tex: Comment displayed. -% Verb check -^ -Message 14 in Test.tex: Could not find argument for command. -\verb# -^^^^^ -Message 31 in Test.tex: This text may be ignored. -\end{verbatim} FOO - ^^^ -Message 22 in Test.tex: Comment displayed. -% Warning 16,15 -^ -Message 16 in Test.tex: Mathmode still on at end of LaTeX file. - - -Message 17 in Test.tex: Number of `(' doesn't match the number of `)'! - - -Message 17 in Test.tex: Number of `[' doesn't match the number of `]'! - - -Message 17 in Test.tex: Number of `{' doesn't match the number of `}'! - - diff --git a/Build/source/texk/chktex/chktex-1.6.6/Test.tex b/Build/source/texk/chktex/chktex-1.6.6/Test.tex deleted file mode 100644 index c848fac7837..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Test.tex +++ /dev/null @@ -1,186 +0,0 @@ -Note: This file was written with only two purposes in mind: - o To test the program upon it - o To show off some of the features - -Most of the file does thus consist of lots of pseudo-commands, which -are nonsense in a TeXnical manner. - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -% Warning 1 - -\foo This is an error. -\smallskip This is a not. $\foo Neither$ is this. - -% Warning 2 - -This is a faulty reference to \ref{foo} -This is not a faulty reference to~\ref{foo} - -% Warning 3 - -$[(ab)^{-1}]^{-2}$ is not beautiful -${{[{(ab)}^{-1}]}}^{-2}$ is beautiful - -% Warning 4-6, 28 - -Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. -Testing {\it italic\/} in this {\em sentence}, as {\em you see}. - -% LaTeX2e - -Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. -Testing \textem{italic\/} in this \textit{sentence}, as \textem{you see}. - -% Warning 7 - -This \'is a test of $\hat{j}$ accents. -This \'{\i}s a test of $\hat{\jmath}$ accents. - -% Warning 8 - -It wasn't anything - just a 2---3 star--shots. -It wasn't anything --- just a 2--3 star-shots. -It's just a start-shot. -is also used to send cross-calls (xc) and cross-traps (xt) to other -% From Knuths TeXbook Chapter 14 -% "How TeX Breaks Paragraphs into Lines", fourth paragraph: -in plain TeX---are the key - -% Warning 9-10 - -% Brackets: - -)}{[])} }}}]]]))) -{[]} ((([[[{{{}}}]]]))) - -% Envs: - -\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} - -\begin{foo} \begin{bar} \end{bar}\end{foo} - -% Warning 11 - -Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. -Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$. $1\cdot\cdots\cdot3$. - -% Warning 12 - -1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar -1st.\ foo Inc.\ ab.cd.\ foo ab.cd.\ Foo.\ bar - -% Warning 13 - -Look at THIS! It's an error. -Look at THIS\@! It's an error. D. E. Knuth. - -% Warning 14 - -\hat -\hat{a} - -% Warning 18,19 - -Is this an "example", or is it an ´example´. -Is this an `example', or is it an `example'. - -% Warning 20 - -That bug is \unknown\ to me. - -% Warning 21 - -\LaTeX\ is an extension of \TeX\. Right? -\LaTeX\ is an extension of \TeX. Right? - -% Warning 23 - -```Hello', I heard him said'', she remembered. -``\,`Hello', I heard him said'', she remembered. - -% Warning 24 - -Indexing text \index{text} is fun! -Indexing text\index{text} is fun! - -% Warning 25 - -$5\cdot10^10$ -$5\cdot10^{10}$ - -% Warning 26 - -Do you understand ? -Do you understand? - -% Warning 27 - -\input input.tex -\input input - -% Warning 29 -The program opens a screen sized 640x200 pixels -The program opens a screen sized $640\times200$ pixels - -% Warning 30 - -White is a beautiful colour. -White is a beautiful colour. - -% Warning 31 -\begin{verbatim} -\this is -\end{verbatim} foo bar - -% Warning 32-34 - -This is either an 'example`, an ''example`` or an `"`example'`'. -This is either an `example', an ``example'' or an ``example''. - -% Warning 35 - -$sin^2 + cos^2 = 1$ -$\sin^2 + \cos^2 = 1$ - -% Warning 36-37 - -This( an example( Nuff said )), illustrates( ``my'' )point. -This (an example (Nuff said)), illustrates (``my'') point. - -% Warning 38 -``An example,'' he said, ``would be great.'' -``An example'', he said, ``would be great''. - -% Warning 39 - -For output codes, see table ~\ref{tab:fmtout}. -For output codes, see table~\ref{tab:fmtout}. - -% Warning 40 -$\this,$ and $$this$$. -$\this$, and $$this.$$ - -% Warning 41 -foo \above qux -\frac{foo}{qux} - -% Warning 42 -This is a footnote \footnote{foo}. -This is a footnote\footnote{foo}. - - -% Verb check - -\verb@\this is )() lots of errors, etc. Or what?@ -\verb# - -\begin{verbatim} -\this is -\end{verbatim} FOO - -% Warning 16,15 - -$$( - - diff --git a/Build/source/texk/chktex/chktex-1.6.6/Utility.c b/Build/source/texk/chktex/chktex-1.6.6/Utility.c deleted file mode 100644 index 165c8d223c1..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Utility.c +++ /dev/null @@ -1,936 +0,0 @@ -/* - * ChkTeX, utility functions. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#include "ChkTeX.h" -#include "Utility.h" -#include "Resource.h" -#include "OpSys.h" - -typedef unsigned long HASH_TYPE; - -/***************************** SUPPORT FUNCTIONS ************************/ - - -/* - * Copies a string with a maximum length of `len' starting at `pos' in - * `source' into `dest'. - * Returns -1 if the pos value is beyond the length of the source value, - * else NULL. - */ - - -short substring(const char *source, char *dest, unsigned long pos, long len) -{ - const char *Start; - short Retval = -1; - - if (len >= 0) - { - if (strlen(source) > pos) - { - Start = &source[pos]; - - while ((len-- > 0) && (*dest++ = *Start++)) - ; - - if (len == -1) - Retval = 0; - } - } - else - Retval = 0L; - - *dest = 0; - - return (Retval); -} - - -/* - * Determine whether a file exists. - * - */ - - -int fexists(const char *Filename) -{ - int Retval; - -#if defined(F_OK) && defined(R_OK) && defined(HAVE_ACCESS) - - Retval = access(Filename, F_OK | R_OK) == 0; -#else - - FILE *fh; - - if (fh = fopen(Filename, "r")) - { - Retval = TRUE; - fclose(fh); - } - else - Retval = FALSE; -#endif - - return (Retval); -} - - - -/* - * 'Safe' memset() replacement. - * Just tries to check the parameters, so that the risk of killing - * innocent memory is lowered. - * Please note that the `n' parameter now is an signed longword, not - * an size_t. Won't permit that `n' exceeds BUFLEN, nor negative sizes. - * Returns `to' if some memset()'ing was done, NULL if not. - */ - -void *sfmemset(void *to, int c, long n) -{ - if (to && (n > 0)) - { - n = min(n, BUFSIZ); - - return (memset(to, c, (size_t) n)); - } - return (NULL); -} - - -/* - * Quick replace function - * Replaces every occurrence of a character in a string with another one. - */ - -void strrep(char *String, /* String to replace within. */ - const char From, /* Character to search for. */ - const char To) /* Character to put instead. */ -{ - register int c; - while ((c = *String++)) - { - if (c == From) - String[-1] = To; - } -} - -/* - * Replaces every char not in Prot with To in Buf - */ - -void strxrep(char *Buf, const char *Prot, const char To) -{ - int c; - - while ((c = *Buf)) - { - if (!strchr(Prot, c)) - *Buf = To; - Buf++; - } -} - -/* - * Strips tail and/or front of a string - * Kills trailing/leading spaces. The macro/function LATEX_SPACE(char c) - * is used to decide whether a space should be skipped. This function - * should return TRUE if the character should be skipped, FALSE if not. - * Returns the string which was passed onto it. - */ - - -char *strip(char *str, /* String to strip */ - const enum Strip flags) -/* One of the following: */ -/* STRP_LFT - Strips leading blanks */ -/* STRP_RGT - Strips trailing blanks */ -/* STRP_BTH - Strips on both sides */ -{ - char *bufptr = str; - char *nlptr; - char c; - - if (bufptr && (c = *bufptr)) - { - if (flags & STRP_LFT) - { - if (LATEX_SPACE(c) && c) - { - do - { - c = *++bufptr; - } - while (LATEX_SPACE(c) && c); - } - } - - if (flags & STRP_RGT) - { - if (c && *bufptr) - { - nlptr = bufptr; - - while (*++nlptr) - ; - - do - { - *nlptr = 0; - c = *--nlptr; - } - while (LATEX_SPACE(c) && c && (nlptr > bufptr)); - - } - else - *bufptr = 0; - } - } - return (bufptr); -} - - -/* - * Converts all the chars in the string passed into lowercase. - */ - -#ifndef HAVE_STRLWR -char *strlwr(char *String) -{ - char *Bufptr; - char TmpC; - - for (Bufptr = String; (TmpC = *Bufptr); Bufptr++) - *Bufptr = tolower((unsigned char)TmpC); - - return (String); -} -#endif - -/* - * Returns a duplicate of the string passed. - */ - -#ifndef HAVE_STRDUP -char *strdup(const char *String) -{ - char *Retval = NULL; - size_t Len; - - if (String) - { - Len = strlen(String) + 1; - if ((Retval = malloc(Len))) - memcpy(Retval, String, Len); - } - - return (Retval); -} -#endif - -/* - * Does the same as strdup, but adds a zero-filled padding, length extra bytes. - */ - -char *strdupx(const char *String, int Extra) -{ - char *Retval = NULL; - size_t Len; - - if (String) - { - Len = strlen(String) + 1 + Extra; - if ((Retval = malloc(Len))) - strncpy(Retval, String, Len); - } - - return (Retval); -} - -/* - * Case-insensitive comparison of two strings. - */ - -#ifndef HAVE_STRCASECMP -int strcasecmp(const char *a, const char *b) -{ - int aa, bb; - - do - { - aa = *a++; - bb = *b++; - } - while (aa && (tolower((unsigned char)aa) == tolower((unsigned char)bb))); - /* bb != 0 is implicit */ - - return (tolower((unsigned char)aa) - tolower((unsigned char)bb)); -} -#endif - -/* - * Not all reallocs are intelligent enough to handle NULL's as - * parameters. This fixes this. - */ - -void *saferealloc(void *b, size_t n) -{ - void *Retval = NULL; - - if (b) - { - if (n) - Retval = realloc(b, n); - else - free(b); - } - else - Retval = malloc(n); - - return (Retval); -} - -/* - * Repeatedly writes the From string over To so that we overwrite Len bytes. - * Does nothing if passed empty/NULL string. - */ - -void strwrite(char *To, const char *From, unsigned long Len) -{ - unsigned long i, j; - unsigned long FromLen = strlen(From); - - Len = min(Len, BUFSIZ); - - if (To && From) - { - switch (FromLen) - { - case 0: - break; - case 1: - memset(To, *From, Len); - break; - default: - for (i = j = 0; i < Len; i++, j++) - { - if (j >= FromLen) - j = 0; - To[i] = From[j]; - } - } - } -} - -/* - * Checks whether Cmp comes after Str. - * - */ - -int strafter(const char *Str, const char *Cmp) -{ - return (strncmp(Str, Cmp, strlen(Cmp))); -} - -/* - * Checks whether Cmp comes before Str. Returns 0 if so, non-zero if not. - * - */ - -int strinfront(const char *Str, const char *Cmp) -{ - int CmpLen; - - if ((CmpLen = strlen(Cmp))) - { - Cmp += CmpLen; - Str++; - - while ((*--Cmp == *--Str) && (--CmpLen > 0)) - ; - - return (CmpLen); - } - else - return (1); -} - - -/*************************** HASH INDEX **************************/ - -/* - * Hashes a string. The string ought be rather short. - * - * The algorithm was designed by Peter Weinberger. This version was - * adapted from Dr Dobb's Journal April 1996 page 26. - */ - -static unsigned long HashWord(const char *str) -{ - register unsigned long h = 0, hbit, c; - - while ((c = *str++)) - { - h = (h << 4) ^ c; - if ((hbit = h & 0xf0000000)) - h ^= hbit >> 24; - h &= ~hbit; - } - - return (h); -} - -/* - * Inserts a string into a hash index. Note: You'll have to - * duplicate the string yourself. - */ - -void InsertHash(char *a, struct Hash *h) -{ - struct HashEntry **he, *newhe; - - if (!h->Index) - { - if (!((h->Index = calloc(HASH_SIZE, sizeof(struct HashEntry *))))) - PrintPrgErr(pmWordListErr); - } - - he = &h->Index[HashWord(a) % HASH_SIZE]; - - if ((newhe = malloc(sizeof(struct HashEntry)))) - { - newhe->Next = *he; - newhe->Str = a; - *he = newhe; - } - else - PrintPrgErr(pmWordListErr); -} - -/* - * Checks whether a string previously has been registered in a - * hash index. - */ - -char *HasHash(const char *a, const struct Hash *h) -{ - struct HashEntry *he; - HASH_TYPE i; /* Special magic to optimize SAS/C */ - - /* Do we have a hash? */ - if (!h->Index) - return NULL; - - /* Find entry in hash */ - i = HashWord(a); - i %= HASH_SIZE; - he = h->Index[i]; - - /* Search in the entry for the item */ - while (he) - { - if (!strcmp(he->Str, a)) - return (he->Str); - else - he = he->Next; - } - return (NULL); -} - -/* - * Clears a hash table. - */ - -void ClearHash(struct Hash *h) -{ - if (h && h->Index) - memset(h->Index, '\0', HASH_SIZE * sizeof(struct HashEntry *)); -} - -/* - * Rehashes a wordlist. If you change any of the elem's, you must - * call this. - * - */ - -static void ReHash(struct WordList *WL) -{ - unsigned long i = 0; - - ClearHash(&WL->Hash); - FORWL(i, *WL) InsertHash(WL->Stack.Data[i], &WL->Hash); -} - -/*************************** WORDLIST HANDLING **************************/ - -/* - * Inserts a duplicate of `Word' into the `Wordlist' structure. You do thus - * not need to make a duplicate of `Word' yourself. - */ - -int InsertWord(const char *Word, struct WordList *WL) -{ - char *WrdCpy; - unsigned long Len; - - if ((WrdCpy = strdupx(Word, WALLBYTES))) - { - if (StkPush(WrdCpy, &WL->Stack)) - { - Len = strlen(Word); - if (WL->MaxLen < Len) - WL->MaxLen = Len; - - InsertHash(WrdCpy, &WL->Hash); - return (TRUE); - } - - free(WrdCpy); - } - - return (FALSE); -} - -/* - * Clears a WordList; removing all items. - */ - -void ClearWord(struct WordList *WL) -{ - if (WL) - { - WL->Stack.Used = 0; - WL->MaxLen = 0; - ClearHash(&WL->Hash); - if (WL->NonEmpty) - InsertWord("", WL); - } -} - -/* - * Query whether a `Word' is previously InsertWord()'ed into the WL - * structure. Does case-sensitive comparison. - * - * Returns the data in the list. - */ - - -char *HasWord(const char *Word, struct WordList *WL) -{ - return HasHash(Word, &WL->Hash); -} - -/* - * Make all the words in a list lower case for later case-insensitive - * comparison. - */ - -void MakeLower(struct WordList *wl) -{ - unsigned long i; - FORWL(i, *wl) strlwr(wl->Stack.Data[i]); - ReHash(wl); -} - -/* - * Calls strrep on each argument in a list. - */ - -void ListRep(struct WordList *wl, const char From, const char To) -{ - unsigned long i; - FORWL(i, *wl) strrep(wl->Stack.Data[i], From, To); - ReHash(wl); -} - - - -/************************** GENERIC STACK ******************************/ - -/* - * Push something onto a stack. Returns TRUE if successful, else FALSE. - * Note: You can not push a NULL Data element. - */ - -int StkPush(void *Data, struct Stack *Stack) -{ - unsigned long NewSize; - void **NewBuf; - - if (Data && Stack) - { - if (Stack->Used >= Stack->Size) - { - NewSize = Stack->Size + MINPUDDLE; - - if ((NewBuf = saferealloc(Stack->Data, - (size_t) NewSize * sizeof(void *)))) - { - Stack->Size = NewSize; - Stack->Data = NewBuf; - } - else - return (FALSE); - } - - Stack->Data[Stack->Used++] = Data; - return (TRUE); - } - - return (FALSE); -} - -/* - * Pops an element from the stack. - * - */ - -void *StkPop(struct Stack *Stack) -{ - void *Retval = NULL; - - if (Stack && (Stack->Used > 0)) - { - Retval = Stack->Data[--Stack->Used]; - -#ifdef NO_DIRTY_TRICKS - - { - void **NewBuf; - - if (Stack->Used < (Stack->Size / 2)) - { - unsigned long NewSize; - NewSize = Stack->Size - MINPUDDLE; - NewSize = max(NewSize, MINPUDDLE); - - if (NewBuf = saferealloc(Stack->Data, - (size_t) NewSize * sizeof(void *))) - { - Stack->Size = NewSize; - Stack->Data = NewBuf; - } - } - } -#endif - - } - return (Retval); -} - -/* - * Returns the topmost element of the stack. - */ - -void *StkTop(struct Stack *Stack) -{ - if (Stack && (Stack->Used > 0)) - return (Stack->Data[Stack->Used - 1]); - else - return (NULL); -} - -/****************************** INPUT STACK *****************************/ - -int PushFileName(const char *Name, struct Stack *stack) -{ - FILE *fh = NULL; - static char NameBuf[BUFSIZ]; - - if (Name && stack) - { - if (LocateFile(Name, NameBuf, ".tex", &TeXInputs)) - { - if ((fh = fopen(NameBuf, "r"))) - { - return (PushFile(NameBuf, fh, stack)); - } - } - PrintPrgErr(pmNoTeXOpen, Name); - } - return (FALSE); -} - - -int PushFile(const char *Name, FILE * fh, struct Stack *stack) -{ - struct FileNode *fn; - - if (Name && fh && stack) - { - if ((fn = malloc(sizeof(struct FileNode)))) - { - if ((fn->Name = strdup(Name))) - { - fn->fh = fh; - fn->Line = 0L; - if (StkPush(fn, stack)) - return (TRUE); - free(fn->Name); - } - free(fn); - } - PrintPrgErr(pmNoStackMem); - } - - return (FALSE); -} - -char *FGetsStk(char *Dest, unsigned long len, struct Stack *stack) -{ - struct FileNode *fn; - char *Retval = NULL; - - if ((fn = StkTop(stack))) - { - do - { - Retval = fgets(Dest, (int)len, fn->fh); - if (Retval) { - if (Retval[strlen(Retval)-1] == '\n') - fn->Line++; - break; - } - - fn = StkPop(stack); - fclose(fn->fh); - free(fn); - - } - while (!Retval && (fn = StkTop(stack))); - } - - return (Retval); -} - -const char *CurStkName(struct Stack *stack) -{ - struct FileNode *fn; - static const char *LastName = ""; - - if (PseudoInName && (stack->Used <= 1)) - return (PseudoInName); - else - { - if ((fn = StkTop(stack))) - return (LastName = fn->Name); - else - return (LastName); - } -} - - -FILE *CurStkFile(struct Stack * stack) -{ - struct FileNode *fn; - - if ((fn = StkTop(stack))) - return (fn->fh); - else - return (NULL); -} - -unsigned long CurStkLine(struct Stack *stack) -{ - struct FileNode *fn; - static unsigned long LastLine = 0L; - - if ((fn = StkTop(stack))) - return (LastLine = fn->Line); - else - return (LastLine); -} - - - -/************************** CHARACTER STACK ******************************/ - -/* - * Pushes the character on the stack. - */ - -struct ErrInfo *PushChar(const char c, const unsigned long Line, - const unsigned long Column, struct Stack *Stk, - const char *LineCpy) -{ - char Buf[2]; - - Buf[0] = c; - Buf[1] = 0; - - return (PushErr(Buf, Line, Column, 1, LineCpy, Stk)); -} - -struct ErrInfo *PushErr(const char *Data, const unsigned long Line, - const unsigned long Column, - const unsigned long ErrLen, const char *LineCpy, - struct Stack *Stk) -{ - struct ErrInfo *ci; - - if ((ci = malloc(sizeof(struct ErrInfo)))) - { - if ((ci->Data = strdup(Data))) - { - ci->File = CurStkName(&InputStack); - ci->Line = Line; - ci->ErrLen = ErrLen; - ci->Column = Column; - ci->LineBuf = LineCpy; - ci->Flags = efNone; - - if (StkPush(ci, Stk)) - return (ci); - } - else - PrintPrgErr(pmStrDupErr); - free(ci); - } - - return (NULL); -} - -/* - * Finds the uppermost entry in the stack with a data matching - * String. - */ - -struct ErrInfo *TopMatch(struct Stack *Stack, char *String) -{ - int i; - struct ErrInfo *retval = NULL; - - if (Stack && String) - { - for (i = Stack->Used - 1; i >= 0; i--) - { - if (!strcmp(String, ((struct ErrInfo *) Stack->Data[i])->Data)) - { - retval = (struct ErrInfo *) Stack->Data[i]; - break; - } - } - } - return (retval); -} - -/* - * Returns and removes a character from the stack, returns NULL if - * the stack is empty. - */ - - -struct ErrInfo *PopErr(struct Stack *Stack) -{ - return ((struct ErrInfo *) StkPop(Stack)); -} - -/* - * Same as PopChar(), but lets the error alone on the stack. - */ - - -struct ErrInfo *TopErr(struct Stack *Stack) -{ - return ((struct ErrInfo *) StkTop(Stack)); -} - -/* - * Free all resources associated with a struct FreeInfo. - */ - -void FreeErrInfo(struct ErrInfo *ei) -{ - if (ei) - { - if (ei->Data) - free(ei->Data); - - free(ei); - } -} - - -/************************* OPEN/CLOSE COUNTING **************************/ - -/* - * Returns the index a given bracket (`()[]{}') character has in the - * BrOrder array. Returns ~0 if the character was not a bracket. - */ - -long BrackIndex(const char c) -{ - switch (c) - { - case '(': - return (0); - case ')': - return (1); - case '[': - return (2); - case ']': - return (3); - case '{': - return (4); - case '}': - return (5); - default: - return (~0L); - } -} - -/* - * Counts brackets for you. Give it a bracket, and it will update the - * corresponding counter. - */ - -void AddBracket(const char c) -{ - long Index; - - if ((Index = BrackIndex(c)) != -1) - Brackets[Index]++; - -} - -/* - * Returns the character that matches the given bracket, NULL if `c' - * wasn't a bracket character. - */ - -char MatchBracket(const char c) -{ - unsigned long Index; - char Char = 0; - - - if ((Index = BrackIndex(c)) != ~0UL) - Char = BrOrder[Index ^ 1]; - - return (Char); -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/Utility.h b/Build/source/texk/chktex/chktex-1.6.6/Utility.h deleted file mode 100644 index 1293b8548f4..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/Utility.h +++ /dev/null @@ -1,172 +0,0 @@ -/* - * ChkTeX, utility functions -- header file. - * Copyright (C) 1995-96 Jens T. Berger Thielemann - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - * Contact the author at: - * Jens Berger - * Spektrumvn. 4 - * N-0666 Oslo - * Norway - * E-mail: - * - * - */ - -#ifndef UTILITY_H -#define UTILITY_H 1 - -#include "ChkTeX.h" -#include "OpSys.h" - -/* - * How many indexes we'll allocate first time - */ -#define MINPUDDLE 256 - -/* - * How many bytes we want in front/end of each char buffer. > 2 - */ -#define WALLBYTES 4 - -#ifndef HASH_SIZE -# define HASH_SIZE 1009 /* A reasonably large prime */ -#endif - -#define FORWL(ind, list) for(ind = 0; ind < (list).Stack.Used; ind++) - - -enum Strip -{ - STRP_LFT = 0x01, - STRP_RGT = 0x02, - STRP_BTH = 0x03 -}; - -struct HashEntry -{ - struct HashEntry *Next; - char *Str; -}; - -struct Hash -{ - struct HashEntry **Index; -}; - -struct Stack -{ - void **Data; - unsigned long Size, Used; -}; - -struct WordList -{ - unsigned long MaxLen; - int NonEmpty; - struct Stack Stack; - struct Hash Hash; -}; -#define WORDLIST_DEFINED - -struct FileNode -{ - char *Name; - FILE *fh; - unsigned long Line; -}; - -/* Rotates x n bits left (should be an int, long, etc.) */ -#define ROTATEL(x,n) ((x<>((CHAR_BIT*sizeof(x)) - n))) - -/* Rotates x n bits right (should be an int, long, etc.) */ -#define ROTATER(x,n) ((x>>n) | (x<<((CHAR_BIT*sizeof(x)) - n))) - -int fexists(const char *Filename); - -void *sfmemset(void *to, int c, long n); -void *saferealloc(void *old, size_t newsize); - -int strafter(const char *Str, const char *Cmp); -void strrep(char *String, const char From, const char To); -void strxrep(char *Buf, const char *Prot, const char To); -char *strip(char *String, const enum Strip What); -void strwrite(char *To, const char *From, unsigned long Len); -int strinfront(const char *Str, const char *Cmp); -char *strdupx(const char *String, int Extra); -void strmove(char *a, const char *b); - -void ClearHash(struct Hash *h); -void InsertHash(char *a, struct Hash *h); -char *HasHash(const char *a, const struct Hash *h); - -int InsertWord(const char *Word, struct WordList *WL); -char *HasWord(const char *Word, struct WordList *WL); -void MakeLower(struct WordList *wl); -void ListRep(struct WordList *wl, const char From, const char To); -void ClearWord(struct WordList *WL); - -int StkPush(void *Data, struct Stack *Stack); -void *StkPop(struct Stack *Stack); -void *StkTop(struct Stack *Stack); - -FILE *CurStkFile(struct Stack *stack); -const char *CurStkName(struct Stack *stack); -unsigned long CurStkLine(struct Stack *stack); -char *FGetsStk(char *Dest, unsigned long len, struct Stack *stack); -int PushFileName(const char *Name, struct Stack *stack); -int PushFile(const char *, FILE *, struct Stack *); - - -void FreeErrInfo(struct ErrInfo *ei); -struct ErrInfo *PushChar(const char c, const unsigned long Line, - const unsigned long Column, struct Stack *Stk, - const char *LineCpy); -struct ErrInfo *PushErr(const char *Data, const unsigned long Line, - const unsigned long Column, - const unsigned long ErrLen, const char *LineCpy, - struct Stack *Stk); -struct ErrInfo *TopChar(struct Stack *Stack); -struct ErrInfo *TopErr(struct Stack *Stack); -struct ErrInfo *PopErr(struct Stack *Stack); -struct ErrInfo *TopMatch(struct Stack *Stack, char *String); - -long BrackIndex(char const c); -void AddBracket(char const c); -char MatchBracket(char const); - - - -short substring(const char *source, char *dest, unsigned long pos, long len); - -#ifndef HAVE_STRLWR -# define strlwr mystrlwr -char *mystrlwr(char *String); -#endif - -#ifndef HAVE_STRDUP -# define strdup mystrdup -char *mystrdup(const char *String); -#endif - - -#ifndef HAVE_STRCASECMP -int strcasecmp(char *a, char *b); -#endif - - - -#endif /* UTILITY_H */ diff --git a/Build/source/texk/chktex/chktex-1.6.6/aclocal.m4 b/Build/source/texk/chktex/chktex-1.6.6/aclocal.m4 deleted file mode 100644 index 52c43e7af14..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/aclocal.m4 +++ /dev/null @@ -1,15 +0,0 @@ -# generated automatically by aclocal 1.10 -*- Autoconf -*- - -# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, -# 2005, 2006 Free Software Foundation, Inc. -# This file is free software; the Free Software Foundation -# gives unlimited permission to copy and/or distribute it, -# with or without modifications, as long as this notice is preserved. - -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY, to the extent permitted by law; without -# even the implied warranty of MERCHANTABILITY or FITNESS FOR A -# PARTICULAR PURPOSE. - -m4_include([m4/ax_cflags_strict_prototypes.m4]) -m4_include([m4/vl_prog_cc_warnings.m4]) diff --git a/Build/source/texk/chktex/chktex-1.6.6/autogen.sh b/Build/source/texk/chktex/chktex-1.6.6/autogen.sh deleted file mode 100755 index 0982233b129..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/autogen.sh +++ /dev/null @@ -1,49 +0,0 @@ -#!/bin/sh - -ACLOCAL="aclocal -I m4" -AUTOHEADER="autoheader" -AUTOMAKE="automake --add-missing --copy --foreign" -AUTOCONF="autoconf" - -# Delete old cache directories. -# automake will stop if their contents was created by an earlier version. -rm -rf autom4te.cache - -# Generate the Makefiles and configure files -echo "Building macros..." -if ( $ACLOCAL --version ) < /dev/null > /dev/null 2>&1; then - $ACLOCAL -else - echo "aclocal not found -- aborting" - exit 1 -fi - -echo "Building config header template..." -if ( $AUTOHEADER --version ) < /dev/null > /dev/null 2>&1; then - $AUTOHEADER - echo timestamp > stamp-h.in -else - echo "autoheader not found -- aborting" - exit 1 -fi - -# We do not really need automake, but want to install programs like install-sh. -echo "Installing some useful programs..." -if ( $AUTOMAKE --version ) < /dev/null > /dev/null 2>&1; then - $AUTOMAKE 2>/dev/null -else - echo "automake not found -- aborting" - exit 1 -fi - -echo "Building configure..." -if ( $AUTOCONF --version ) < /dev/null > /dev/null 2>&1; then - $AUTOCONF -else - echo "autoconf not found -- aborting" - exit 1 -fi - -echo -echo 'run "./configure ; make"' -echo diff --git a/Build/source/texk/chktex/chktex-1.6.6/chktex.1 b/Build/source/texk/chktex/chktex-1.6.6/chktex.1 deleted file mode 100644 index 914076926a8..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/chktex.1 +++ /dev/null @@ -1,139 +0,0 @@ -.TH chktex 1 "March 30, 2001" -.AT 3 -.SH NAME -chktex \- finds typographic errors in LaTeX. -.SH SYNOPSIS -.B chktex -.I [-hiqrW] [-v[0-...]] [-l ] [-[wemn] <[1-42]|all>] -.I [-d[0-...]] [-p ] [-o ] [-[btxgI][0|1]] -.B file1 file2 ... -.SH DESCRIPTION -.I chktex -finds typographic errors in -.I LaTeX -. -.SH OPTIONS -.PP -Miscellaneous options: -.TP -.B "-h --help" -Print a help screen. -.TP -.B "-i --license" -Show distribution information. -.TP -.B "-l --localrc" -Read local .chktexrc formatted file. -.TP -.B "-d --debug" -Debug information. Give it a number. -.TP -.B "-r --reset" -Reset settings to default. -.PP -Muting warning messages: -.TP -.B "-w --warnon" -Makes msg # given a warning and turns it on. -.TP -.B "-e --erroron" -Makes msg # given an error and turns it on. -.TP -.B "-m --msgon" -Makes msg # given a message and turns it on. -.TP -.B "-n --nowarn" -Mutes msg # given. - -.PP -Output control flags: -.TP -.B "-v --verbosity" -How errors are displayed. -Default 1, 0=Less, 2=Fancy, 3=lacheck. -.TP -.B "-V --pipeverb" -How errors are displayed when stdout != tty. -Defaults to the same as -v. -.TP -.B "-s --splitchar" -String used to split fields when doing -v0 -.TP -.B "-o --output" -Redirect error report to a file. -.TP -.B "-q --quiet" -Shuts up about version information. -.TP -.B "-p --pseudoname" -Input file-name when reporting. -.TP -.B "-f --format" -Format to use for output - -.PP -Boolean switches (1 -> enables / 0 -> disables): -.TP -.B "-b --backup" -Backup output file. -.TP -.B "-x --wipeverb" -Ignore contents of `\\verb' commands. -.TP -.B "-g --globalrc" -Read global .chktexrc file. -.TP -.B "-I --inputfiles" -Execute \\input statements. -.TP -.B "-H --headererr" -Show errors found in front of \\begin{document} -.PP Miscellaneous switches: -.TP -.B "-W --version" -Version information - -.PP -If no LaTeX files are specified on the command line, we will read from -stdin. For explanation of warning/error messages, please consult the -main document /usr/share/doc/chktex/ChkTeX.dvi.gz. - -.SH DISTRIBUTION -Copyright (C) 1996 Jens T. Berger Thielemann -.PP -This program is free software; you can redistribute it and/or modify -it under the terms of the -.I GNU General Public License -as published by -the Free Software Foundation; either version 2 of the License, or -(at your option) any later version. -.PP -This program is distributed in the hope that it will be useful, -but -.B WITHOUT ANY WARRANTY; -without even the implied warranty of -.B MERCHANTABILITY -or -.B FITNESS FOR A PARTICULAR PURPOSE. -See the -.I GNU General Public License -for more details. -.PP -You should have received a copy of the -.B GNU General Public License -along with this program; if not, write to the -.I Free Software Foundation, Inc., -59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - -.SH ENVIRONMENT -No environment variables are used. -.SH FILES -None. -.SH AUTHOR -Jens T. Berger Thielemann, -.I -.PP -This manual page was cobbled together by Clint Adams , -based on the output of "chktex --help" and deweb(1). -.SH "SEE ALSO" -.B deweb(1), chkweb(1) diff --git a/Build/source/texk/chktex/chktex-1.6.6/chktex.el b/Build/source/texk/chktex/chktex-1.6.6/chktex.el deleted file mode 100644 index 8e02be26c9e..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/chktex.el +++ /dev/null @@ -1,56 +0,0 @@ -;;; chktex.el --- quick hack to add ChkTeX capability to AUC-TeX mode -;; -;; -;; Keywords: LaTeX, AUC-TeX, ChkTeX -;; -;; ChkTeX, quick hack to add ChkTeX in LaTeX menu. -;; Copyright (C) 1995-96 Jens T. Berger Thielemann -;; -;; This program is free software; you can redistribute it and/or modify -;; it under the terms of the GNU General Public License as published by -;; the Free Software Foundation; either version 2 of the License, or -;; (at your option) any later version. -;; -;; This program is distributed in the hope that it will be useful, -;; but WITHOUT ANY WARRANTY; without even the implied warranty of -;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -;; GNU General Public License for more details. -;; -;; You should have received a copy of the GNU General Public License -;; along with this program; if not, write to the Free Software -;; Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -;; -;; Contact the author at: -;; Jens Berger -;; Spektrumvn. 4 -;; N-0666 Oslo -;; Norway -;; E-mail: -;; -;; -;;; Commentary: -;; -;; This tiny hack will add a "ChkTeX" item to the command menu of -;; AUC-TeX, thus making the use of ChkTeX much more comfortable from -;; within AUC-TeX (`LaTeX-mode'). -;; -;; INSTALLATION -;; -;; 1. Put this file somewhere in your loading path. -;; 2. Add the line -;; (require 'chktex) -;; to your .emacs file -;; -;; It is doubtful whether byte-compiling this file gains anything. -;; -;;; Code: -;; - -(eval-after-load 'tex - '(progn - (add-to-list 'TeX-command-list - '("ChkTeX" "chktex -v3 %s" TeX-run-compile nil t)))) - -(provide 'chktex) - -;;; chktex.el ends here diff --git a/Build/source/texk/chktex/chktex-1.6.6/chktexrc b/Build/source/texk/chktex/chktex-1.6.6/chktexrc deleted file mode 100644 index 72889e2d707..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/chktexrc +++ /dev/null @@ -1,678 +0,0 @@ -## -## ChkTeX, example resource file for ChkTeX. -## Copyright (C) 1995-96 Jens T. Berger Thielemann -## -## This program is free software; you can redistribute it and/or modify -## it under the terms of the GNU General Public License as published by -## the Free Software Foundation; either version 2 of the License, or -## (at your option) any later version. -## -## This program is distributed in the hope that it will be useful, -## but WITHOUT ANY WARRANTY; without even the implied warranty of -## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -## GNU General Public License for more details. -## -## You should have received a copy of the GNU General Public License -## along with this program; if not, write to the Free Software -## Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -## -## Contact the author at: -## Jens Berger -## Spektrumvn. 4 -## N-0666 Oslo -## Norway -## E-mail: -## - -##################################################################### -# -# Note: The format has changed slightly (again). The { ... } -# syntax does now mean case-sensitive comparing, while [ ... ] means -# case-insensitive comparing of the keywords. Case-insensitive -# comparing of the keywords is only supported on a few of the -# keywords (it's not meaningful in all contexts, and it slows ChkTeX -# down). Keywords supporting this are marked throughout the file. -# -# You may also reset a list by saying "KEYWORD = { ... }"; it will -# then be set equal to the contents of the list you specify. -# -# Comments begin with `#', and continues for the rest of the line. -# Blank lines plus leading and trailing spaces are of course ignored. -# -# The general format of this file is the following: -# -# KEYWORD { item item ...} [ item item ... ] /* Adds items */ -# -# KEYWORD [ item item ...] { item item ... } /* Adds items */ -# -# KEYWORD = item -# -# KEYWORD = { item item ... } /* Clears list before adding */ -# -# KEYWORD = [ item item ... ] /* Clears list before adding */ -# -# This does _not_ mean that you may alternate the forms; certain -# keywords demands a list, other a single value. You thus have to -# look at the examples of their use. -# -# Please also note that if you specify a list-keyword twice, we'll -# concatenate the lists. If you you specify a item-keyword twice, -# we'll kill the previous value. -# -# We are slightly context-sensitive when detecting tokens like "}" -# and "]"; they have to be preceded by a space. This generally makes -# life easier. -# -# Items are separated by spaces. Newlines are considered as spaces, -# but can't be escaped. You may surround items with quotes (`"') to -# easily put spaces into them. -# -# Escape sequences available: -# -# Sequence Resulting character -# ! A space (type `! ', not just a exclamation mark) -# !" " -# !# # -# !! ! -# !{ { -# !} } -# ![ [ -# !] ] -# != = -# !b Backspace -# !n New line -# !r Carriage return -# !t Tab -# !f Form feed -# !xNN NN must be a hexadecimal number (00 - ff), -# _both_ characters must be included. -# !dNNN DDD must be a decimal number (000 - 255), all -# three characters must be included. Unspecified -# results if DDD > 255. -# !NNN DDD must be a octal number (000 - 377), all -# three characters must be included. Unspecified -# results if DDD > 377. -# -# Minor note: As you can see, most of these escape sequences are -# equal to those in C (with some extensions); however, we use ! -# instead of \ as escape character for obvious reasons. -# -# -# Quick summary of keywords follows. Keywords marked with a * accept -# keywords accepting case-insensitive lists. -# -# Abbrev* - A list of abbreviations not automatically catched. -# CenterDots - Commands/characters which should have \cdots in -# between. -# CmdLine - Default commandline options. These will be -# processed before the ones you give on the command -# line. -# HyphDash \ -# NumDash - No. of dashes allowed in different contexts. -# WordDash / -# IJAccent - Commands which puts an accent _over_ their -# argument. -# Italic - Commands immediately turning on italic mode. -# ItalCmd - Commands putting their argument into italic. -# Linker - Commands which should have a non-breaking space in -# front. -# LowDots - Commands/characters which should have \ldots in -# between. -# MathEnvir - Environments which turn on math mode. -# MathRoman - Mathematical operators with LaTeX replacement -# defined. -# NoCharNext - Insists on that certain commands aren't followed by -# certain characters. -# NonItalic - Commands immediately turning off italic mode. -# NotPreSpaced- Commands which should not have a space in front of -# them. -# Primitives - Primitive TeX commands. -# PostLink - Commands which generates a page reference. -# OutFormat - Formats to use for output. See the -f & -v switch -# in the main doc. -# QuoteStyle - Either "Traditional" or "Logical". See main doc, -# warning 38. -# Silent - These commands do not produce any textual output; -# and are thus allowed to have a space after them. -# TabSize - Tab size you are using. -# TeXInputs - Paths to search \input and \include files for. -# UserWarn* - These strings will be searched for throughout the -# text. -# VerbEnvir - Environments which contents should be ignored. -# VerbClear - String we will overwrite unwanted data with. -# WipeArg - Commands (with arguments) which should be ignored -# in the checking. -# - - -##################################################################### -# -# Enter which type of quote-style you are using here. Currently, we -# support the following styles: -# -# Style Example of use -# Traditional "An example," he said, "would be great." -# Logical "An example", he said, "would be great". -# - -QuoteStyle = Logical - -##################################################################### -# -# Enter here what interval you have between your tabs. Only regular -# intervals are supported. -# - -TabSize = 8 - -##################################################################### -# -# Here, you can put default commandline options; most users would for -# instance like to put -v2 here. -# - -CmdLine -{ - -} - -##################################################################### -# -# These patterns will be searched for through the text; no matter -# whether they appear as normal text, commands or whatever. -# Currently case-sensitive. -# -# I usually define a special command like this: -# -# \def\unknown{\large\bf??} -# -# which I use whenever there is some information I don't have at the -# moment of writing. Thus, it makes sense to search for it. -# -# You should be able to develop your own uses for this. -# - -UserWarn -{ - - \unknown -### -# -# Another example; one should write \chktex or Chk\TeX - never ChkTeX. -# -### - - ChkTeX -} -[ - -### -# -# You may put case-insensitive patterns here. -# -### - -] - -##################################################################### -# -# Here you can list the path of where ChkTeX should look for files it -# \inputs. The // postfix is now supported; if you append a double -# path-separator we'll recursively search that directory directories. -# MS-DOS users must append \\ instead, e.g. "C:\EMTEX\\". -# -# If you under either MS-DOS or UNIX wish to search an entire -# partition or the complete directory tree, you must use *three* -# slashes, e.g. "c:\\\" or "///". This may be considered to be a bug. -# -# By default, we'll search the current directory (not recursively, -# put "//" in the list for this); any paths specified below will be -# searched in addition to this. -# - -TeXInputs -{ - -} - -##################################################################### -# -# Here you may specify more outputformats for use with the -v option, -# it simply indexes into this list. Remember to use ! instead of \, -# though. -# -# For explanation of how % fields expand; look at ChkTeX.{dvi,ps}. -# -# We will by default select entry number _two_ in this list (we count -# from 0), and -v without any parameter selects entry number _three_. -# - -OutFormat -{ - -# -v0; silent mode -%f%b%l%b%c%b%n%b%m!n - -# -v1; normal mode -"%k %n in %f line %l: %m!n%r%s%t!n%u!n" - -# -v2; fancy mode -"%k %n in %f line %l: %m!n%r%i%s%I%t!n!n" - -# -v3; lacheck mode -"!"%f!", line %l: %m!n" - -# -v4; verbose lacheck mode -"!"%f!", line %l: %m!n%r%s%t!n%u!n" - -# -v5; no line number, ease auto-test -"%k %n in %f: %m!n%r%s%t!n%u!n" - -} - - - -##################################################################### -# -# These commands should be ignored when detecting whether a command -# is ended by a space. -# - -Silent -{ - \rm \em \bf \it \sl \sf \sc \tt \selectfont - \rmfamily \sffamily \ttfamily \mdseries \bfseries - \slshape \scshape \relax - \vskip \pagebreak \nopagebreak - - \textrm \textem \textbf \textit \textsl \textsf \textsc \texttt - - \clearpage \ddots \dotfill \flushbottom \fussy \indent \linebreak - \onecolumn \pagebreak \pushtabs \poptabs \scriptsize \sloppy - \twocolumn \vdots - \today \kill \newline \thicklines \thinlines - - \columnsep \space \item \tiny \footnotesize \small \normalsize - \normal \large \Large \LARGE \huge \Huge \printindex - - \newpage \listoffigures \listoftables \tableofcontents - \maketitle \makeindex - - \hline \hrule \vrule - - \centering - - \bigskip \medskip \smallskip - - \noindent \expandafter - - \makeatletter \makeatother - - \columnseprule - - \textwidth \textheight \hsize \vsize - - \if \fi - - \csname \endcsname - - \z@ \p@ \@warning \typeout - - \dots \ldots \input \endinput \nextline \leavevmode \cdots -- \appendix \listfiles \and \quad - \vfill \vfil \hfill \hfil \topmargin \oddsidemargin - \frenchspacing \nonfrenchspacing - \begingroup \endgroup \par - - \vrefwarning \upshape \headheight \headsep \hoffset \voffset - \cdot \qquad - \left \right -} - -##################################################################### -# -# Here, you can specify the length of various dashes. We sort the -# dash according to which type of characters that are on the left and -# right of of it. We are only conclusive if they are the same. -# -# We associate as follows: -# -# Name Type of character on each side -# HyphDash Alphabetic (foo-bar) -# NumDash Numeric (2--3) -# WordDash Space (like this --- see?) -# -# Below you specify how many dashes which are legal in each case. We -# define 0 as an magic constant which always generates an error. You -# may specify more than one legal dash-length. -# -# Let's look at an example. You use the following dash-syntax: -# -# foo-bar -# 2--3 -# like this---see? -# -# -# HYPHDASH { 1 3 } # Either a hyphen, or inter-word -# NUMDASH { 2 } # Between words -# WORDDASH { 0 } # We never use this -# - -HyphDash -{ - 1 3 -} - -NumDash -{ - 2 -} - -WordDash -{ - 3 -} - -##################################################################### -# -# This keyword indicates commands which argument isn't LaTeX code, -# and which thus should be ignored. -# -# After the command, you may place arguments that you wish that -# should be wiped in the process; use [] for optional arguments, {} -# for required ones and * if the command supports an alternative -# variant. These should be separated from the command with a colon. -# -# For instance, if you would like to wipe the \newcommand command, -# you would declare it as \newcommand:*[][]{} -# -# These commands may be "executed" before they're wiped, so you will -# typically also wish to list filehandling commands and similar here. -# - -WipeArg -{ - \label:{} \ref:{} \vref:{} \pageref:{} \index:{} \cite:[]{} - \input:{} \verbatiminput:[]{} \listinginput:[]{}{} - \verbatimtabinput:[]{} \include:{} \includeonly:{} - \bibitem:[]{} -} - -##################################################################### -# -# These environments contains material which will be typeset as -# mathematics by LaTeX. This turns on/off some warnings. -# -# We will automagically append a * to each keyword. -# - -MathEnvir -{ - displaymath math eqnarray array equation - align alignat gather flalign multline -} - -##################################################################### -# -# These environments contains material which contents should be -# ignored. -# -# We will automagically append a * to each keyword. -# - -VerbEnvir -{ - verbatim comment listing verbatimtab rawhtml errexam picture texdraw -} - -##################################################################### -# -# ChkTeX does automagically catch most abbreviations; the ones we -# need to list here, are those which are most likely to be followed -# by a word with an upper-case letter (that is not the beginning of a -# new sentence). -# -# The case-insensitive abbreviations are not really case-insensitive, -# it seems to be more practical to only let the first character be -# case-insensitive, while the remaining are case-sensitive. -# -# To speed up the searching process somewhat, we require that these -# end in a `.', this should not be a problem. -# -# Much of this work (both the abbreviations below, and the regexps -# necessary to catch the remaining automatically) have been provided -# by Russ Bubley, . -# - - -Abbrev -{ -# Ordinals -1st. 2nd. 3rd. 4th. -# Titles -Mr. Mrs. Miss. Ms. Dr. Prof. St. - -# -# Days -# Mon. Tue. Wed. Thu. Fri. Sat. Sun. -# -# Months -# Jan. Feb. Mar. Apr. May. Jun. Jul. Aug. Sep. Oct. Nov. Dec. -# -# Letters -# Kt. Jr. -# -# Corporate -# Co. Ltd. -# -# Addresses -# Rd. Dr. St. Ave. Cres. Gdns. Sq. Circ. Terr. Pl. Arc. La. Clo. Ho. Est. Gn. -# -# Misc. -# oe. pbab. ps. rsvp. Tx. -} -[ -### -# -# The first letter is case-insensitive in the abbrevs in this -# list. Due to the nature of the checking algorithm used for -# this, entries consisting of only one character will be -# silently ignored. -# -## - -# Latin -# cf. "et al." etc. qed. qv. viz. -# -# Corporate -# inc. plc. -# -# Misc -# fax. pcs. qty. tel. misc. -] - -##################################################################### -# -# Commands which accent characters, meaning that \i or \j (\imath and -# \jmath in mathmode) should be used instead of `i' and `j' -# - -IJAccent -{ - \hat \check \breve \acute \grave \tilde \bar \vec \dot \ddot - - \' \` \^ \" \~ \= \. \u \v \H \t - -### -# -# The remaining accent commands (\c,\d,\b) put their accent _under_ -# the character, not above, and should thus be used with normal i's -# and j's. -# -### - -} - -##################################################################### -# -# Commands which, when the group is terminated, needs italic -# correction. -# - -Italic -{ - \it \em \sl - \itshape \slshape -} - -##################################################################### -# -# Commands which makes the font non-italic. -# - -NonItalic -{ - \bf \rm \sf \tt \sc - \upshape -} - -##################################################################### -# -# Commands which puts their argument into italic (and thus possibly -# needs italic correction in the end). -# -# This is currently empty, since \textit, \textsl and \emph do that -# automatically. -# - -ItalCmd -{ -} - -##################################################################### -# -# These commands all have in common that a pagebreak right in front -# of them is highly undesirable; thus there should be no space in -# front of them. -# - -PostLink -{ - \index \label -} - -##################################################################### -# -# These commands should not have a space in front of them for various -# reasons. I.e. much the same as POSTLINK, but produces another -# warning. -# - -NotPreSpaced -{ - \footnote \footnotemark \/ -} - -##################################################################### -# -# The commands listed here, should be prepended with a `~', as in -# "look in table~\ref{foo}", to avoid the references being split -# across lines. -# - -Linker -{ - \ref \vref \pageref \cite -} - -##################################################################### -# -# Commands/characters which should have \cdots in between, e.g. -# $1+2+3+\cdots+n$. -# - -CenterDots -{ - = + - \cdot \div & \times \geq \leq < > -} - -##################################################################### -# -# Commands/characters which should have \ldots in between, e.g. -# $1,2,3,\ldots,n$. -# - -LowDots -{ - . , ; -} - -##################################################################### -# -# In maths mode, there are certain aliases for mathematical operators -# like sin, cos, etc. Ignore the leading backslash in the commands, -# and so forth. You should list these below. -# - -MathRoman -{ - log lg ln lim limsup liminf sin arcsin sinh cos arccos cosh tan - arctan tanh cot coth sec csc max min sup inf arg ker dim hom det - exp Pr gcd deg bmod pmod mod -} - -##################################################################### -# -# These TeX commands have become unnecessary, as there are LaTeX cmds -# that does the same. Purists should thus avoid these in their code. -# -# (These are a spell-corrected version of those lacheck uses). -# - -Primitives -{ - \above \advance \catcode \chardef \closein \closeout \copy \count - \countdef \cr \crcr \csname \delcode \dimendef \dimen \divide - \expandafter \font \hskip \vskip \openout -} - -##################################################################### -# -# Format: \command:characters -# -# We'll emit a warning if any of characters are found after the -# command. -# - -NoCharNext -{ - \left:{}$ \right:{}$ -} - -##################################################################### -# -# We're killing \verb@...@ commands and the arguments of the commands -# listed above in WIPEARG by overwriting them with a string or a -# single character. -# -# This should not contain an alphabetic character (in case the user -# writes (\foo\verb@bar@), neither should it contain be one of LaTeX' -# reserved characters (`#$%&~_^\{}'), or any parenthesis character -# ('()[]{}'). If possible, don't use a punctuation character, -# either, or any spacing character. -# -# The asterix is also unsuitable, as some commands behave in another -# way if they are postpended with an asterix. Which more or less -# leaves us with the pipe. -# -# Please note that this may also be a _string_, which will be -# repeated until the proper length is reached. -# - -VerbClear = "|" - -# -# All for now - have fun. -# -##################################################################### - diff --git a/Build/source/texk/chktex/chktex-1.6.6/chkweb.1 b/Build/source/texk/chktex/chktex-1.6.6/chkweb.1 deleted file mode 100644 index 5cb7063f786..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/chkweb.1 +++ /dev/null @@ -1,132 +0,0 @@ -.TH chkweb 1 "March 30, 2001" -.AT 3 -.SH NAME -chkweb \- runs the LaTeX parts of a CWEB file through chktex -.SH SYNOPSIS -.B chkweb -.I [-hiqrW] [-l ] [-[wemn] <[1-42]|all>] -.I [-d[0-...]] [-o ] [-[btxgI][0|1]] -.B file1 file2 ... -.SH DESCRIPTION -.I chkweb -runs the -.I LaTeX -parts of a CWEB file through chktex. -.SH OPTIONS -.PP -Miscellaneous options: -.TP -.B "-h --help" -Print a help screen. -.TP -.B "-i --license" -Show distribution information. -.TP -.B "-l --localrc" -Read local .chktexrc formatted file. -.TP -.B "-d --debug" -Debug information. Give it a number. -.TP -.B "-r --reset" -Reset settings to default. -.PP -Muting warning messages: -.TP -.B "-w --warnon" -Makes msg # given a warning and turns it on. -.TP -.B "-e --erroron" -Makes msg # given an error and turns it on. -.TP -.B "-m --msgon" -Makes msg # given a message and turns it on. -.TP -.B "-n --nowarn" -Mutes msg # given. - -.PP -Output control flags: -.TP -.B "-V --pipeverb" -How errors are displayed when stdout != tty. -Defaults to the same as -v. -.TP -.B "-s --splitchar" -String used to split fields when doing -v0 -.TP -.B "-o --output" -Redirect error report to a file. -.TP -.B "-q --quiet" -Shuts up about version information. -.TP -.B "-f --format" -Format to use for output - -.PP -Boolean switches (1 -> enables / 0 -> disables): -.TP -.B "-b --backup" -Backup output file. -.TP -.B "-x --wipeverb" -Ignore contents of `\\verb' commands. -.TP -.B "-g --globalrc" -Read global .chktexrc file. -.TP -.B "-I --inputfiles" -Execute \\input statements. -.TP -.B "-H --headererr" -Show errors found in front of \\begin{document} -.PP Miscellaneous switches: -.TP -.B "-W --version" -Version information - -.PP -If no LaTeX files are specified on the command line, we will read from -stdin. For explanation of warning/error messages, please consult the -main document /usr/share/doc/chktex/ChkTeX.dvi.gz. - -.SH DISTRIBUTION -Copyright (C) 1996 Jens T. Berger Thielemann -.PP -This program is free software; you can redistribute it and/or modify -it under the terms of the -.I GNU General Public License -as published by -the Free Software Foundation; either version 2 of the License, or -(at your option) any later version. -.PP -This program is distributed in the hope that it will be useful, -but -.B WITHOUT ANY WARRANTY; -without even the implied warranty of -.B MERCHANTABILITY -or -.B FITNESS FOR A PARTICULAR PURPOSE. -See the -.I GNU General Public License -for more details. -.PP -You should have received a copy of the -.B GNU General Public License -along with this program; if not, write to the -.I Free Software Foundation, Inc., -59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - -.SH ENVIRONMENT -No environment variables are used. -.SH FILES -None. -.SH AUTHOR -Jens T. Berger Thielemann, -.I -.PP -This manual page was cobbled together by Clint Adams , -based on the output of "chktex --help" and deweb(1). -.SH "SEE ALSO" -.B deweb(1), chktex(1) diff --git a/Build/source/texk/chktex/chktex-1.6.6/chkweb.sh b/Build/source/texk/chktex/chktex-1.6.6/chkweb.sh deleted file mode 100755 index 8d6361d1097..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/chkweb.sh +++ /dev/null @@ -1,56 +0,0 @@ -#! /bin/sh - -# ChkWEB v1.0, runs the LaTeX parts of a CWEB file through ChkTeX. -# Copyright (C) 1996 Jens T. Berger Thielemann -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -# -# Contact the author at: -# Jens Berger -# Spektrumvn. 4 -# N-0666 Oslo -# Norway -# E-mail: - - -params= - -for p -do - case $p in - --) break - ;; - -*) params="$params $p" - shift - ;; - *) break - ;; - esac -done - - -if test "$1" = ""; then - deweb | chktex -v3 $params -else - for file - do - if test -f $file; then - deweb $file | chktex -p $file -v3 $params - else - deweb $file.w | chktex -p $file.w -v3 $params - fi - done -fi - diff --git a/Build/source/texk/chktex/chktex-1.6.6/config.h.in b/Build/source/texk/chktex/chktex-1.6.6/config.h.in deleted file mode 100644 index 273502cac45..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/config.h.in +++ /dev/null @@ -1,136 +0,0 @@ -/* config.h.in. Generated from configure.in by autoheader. */ - -/* Define to 1 if you have the `access' function. */ -#undef HAVE_ACCESS - -/* Define to 1 if you have the `closedir' function. */ -#undef HAVE_CLOSEDIR - -/* Define to 1 if you have the header file, and it defines `DIR'. - */ -#undef HAVE_DIRENT_H - -/* Define to 1 if you don't have `vprintf' but do have `_doprnt.' */ -#undef HAVE_DOPRNT - -/* Define to 1 if you have the `fileno' function. */ -#undef HAVE_FILENO - -/* Define to 1 if you have the header file. */ -#undef HAVE_INTTYPES_H - -/* Define to 1 if you have the `isatty' function. */ -#undef HAVE_ISATTY - -/* Define to 1 if you have the `termcap' library (-ltermcap). */ -#undef HAVE_LIBTERMCAP - -/* Define to 1 if you have the `termlib' library (-ltermlib). */ -#undef HAVE_LIBTERMLIB - -/* Define to 1 if you have the header file. */ -#undef HAVE_LIMITS_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_MEMORY_H - -/* Define to 1 if you have the header file, and it defines `DIR'. */ -#undef HAVE_NDIR_H - -/* Define to 1 if you have the `opendir' function. */ -#undef HAVE_OPENDIR - -/* Define to 1 if you have the `readdir' function. */ -#undef HAVE_READDIR - -/* Define to 1 if you have the `stat' function. */ -#undef HAVE_STAT - -/* Define to 1 if you have the header file. */ -#undef HAVE_STAT_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_STDARG_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_STDINT_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_STDLIB_H - -/* Define to 1 if you have the `strcasecmp' function. */ -#undef HAVE_STRCASECMP - -/* Define to 1 if you have the `strdup' function. */ -#undef HAVE_STRDUP - -/* Define to 1 if you have the header file. */ -#undef HAVE_STRINGS_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_STRING_H - -/* Define to 1 if you have the `strlwr' function. */ -#undef HAVE_STRLWR - -/* Define to 1 if you have the `strtol' function. */ -#undef HAVE_STRTOL - -/* Define to 1 if you have the header file, and it defines `DIR'. - */ -#undef HAVE_SYS_DIR_H - -/* Define to 1 if you have the header file, and it defines `DIR'. - */ -#undef HAVE_SYS_NDIR_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_SYS_STAT_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_SYS_TYPES_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_TERMCAP_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_TERMLIB_H - -/* Define to 1 if you have the header file. */ -#undef HAVE_UNISTD_H - -/* Define to 1 if you have the `vprintf' function. */ -#undef HAVE_VPRINTF - -/* Define to the address where bug reports for this package should be sent. */ -#undef PACKAGE_BUGREPORT - -/* Define to the full name of this package. */ -#undef PACKAGE_NAME - -/* Define to the full name and version of this package. */ -#undef PACKAGE_STRING - -/* Define to the one symbol short name of this package. */ -#undef PACKAGE_TARNAME - -/* Define to the version of this package. */ -#undef PACKAGE_VERSION - -/* Define to 1 if you have the ANSI C header files. */ -#undef STDC_HEADERS - -/* "Strip debug info" */ -#undef STRIP_DEBUG - -/* Define to empty if `const' does not conform to ANSI C. */ -#undef const - -/* Define to `__inline__' or `__inline' if that's what the C compiler - calls it, or to nothing if 'inline' is not supported under any name. */ -#ifndef __cplusplus -#undef inline -#endif - -/* Define to `unsigned int' if does not define. */ -#undef size_t diff --git a/Build/source/texk/chktex/chktex-1.6.6/configure.in b/Build/source/texk/chktex/chktex-1.6.6/configure.in deleted file mode 100644 index 5637cb68662..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/configure.in +++ /dev/null @@ -1,158 +0,0 @@ -dnl -dnl ChkTeX, configuration file. -dnl Copyright (C) 1995-96 Jens T. Berger Thielemann -dnl -dnl This program is free software; you can redistribute it and/or modify -dnl it under the terms of the GNU General Public License as published by -dnl the Free Software Foundation; either version 2 of the License, or -dnl (at your option) any later version. -dnl -dnl This program is distributed in the hope that it will be useful, -dnl but WITHOUT ANY WARRANTY; without even the implied warranty of -dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -dnl GNU General Public License for more details. -dnl -dnl You should have received a copy of the GNU General Public License -dnl along with this program; if not, write to the Free Software -dnl Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -dnl -dnl Contact the author at: -dnl Jens Berger -dnl Spektrumvn. 4 -dnl N-0666 Oslo -dnl Norway -dnl E-mail: -dnl -dnl - - -dnl Process this file with autoconf to produce a configure script. -AC_INIT(ChkTeX, 1.6.6) -AC_SUBST(SCRIPTS) -AC_SUBST(BUILT_SCRIPTS) -AC_SUBST(ELISPDIR) -ELISPDIR= -AC_SUBST(CLEAN) -CLEAN= - -AC_ARG_ENABLE(lacheck-replace,[ - --enable-lacheck-replace: Installs a lacheck replacement for the - AUC-TeX interface. (Default: no).],, -enable_lacheck_replace=no) - -AC_ARG_ENABLE(emacs-hack,[ - --enable-emacs-hack: Installs a Elisp file, which makes ChkTeX - available in Emacs. Must be followed by - the path of your elisp files (e.g. - "--enable-emacs-hack=/usr/lib/emacs/"). - (Default: no).],, -enable_emacs_hack=no) - -AC_ARG_ENABLE(debug-info,[ - --enable-debug-info: Compile in miscellaneous runtime debugging - information. (Default: yes).],, -enable_debug_info=yes) - -AC_ARG_ENABLE(coverage-testing,[ - --enable-coverage-testing: Activate coverage testing with gcov. (Default: no)],, -enable_coverage_testing=no) - -AC_MSG_CHECKING(whether lacheck replacement should be installed) -if test "$enable_lacheck_replace" = "yes"; then - SCRIPTS="$SCRIPTS lacheck" - AC_MSG_RESULT(yes) -else - AC_MSG_RESULT(no) -fi - -AC_MSG_CHECKING(whether runtime debug info should be used) -if test "$enable_debug_info" = "yes"; then - AC_MSG_RESULT(yes) -else - AC_DEFINE(STRIP_DEBUG, 1, "Strip debug info") - AC_MSG_RESULT(no) -fi - -AC_MSG_CHECKING(whether the emacs hack should be installed) -case $enable_emacs_hack in - no) AC_MSG_RESULT(no) - ;; - /*|*/*) ELISPDIR=$enable_emacs_hack - AC_MSG_RESULT(yes) - ;; - *) echo; - AC_MSG_ERROR(--enable-emacs-hack needs the *full path* of Elisp files) - ;; -esac - -AC_MSG_CHECKING(whether coverage testing is enabled) -if test "$enable_coverage_testing" = "yes"; then - AC_MSG_RESULT(yes) - CFLAGS="${CFLAGS} -fprofile-arcs -ftest-coverage -O0" - CLEAN="${CLEAN} \$(wildcard *.bb *.bbg *.da *.gcov)" -else - AC_MSG_RESULT(no) -fi - -dnl Check compiler and flags -AC_PROG_CC -AX_CFLAGS_STRICT_PROTOTYPES -VL_PROG_CC_WARNINGS - -dnl Checks for programs. -AC_PROG_INSTALL -AC_PROG_LN_S -AC_PROG_MKDIR_P -AC_PATH_PROGS(PERL5, perl5 perl, no, $PATH:/usr/bin:/usr/local/bin) -if test "$PERL5" != no; then - AC_MSG_CHECKING(whether perl is v5 or higher) - if $PERL5 -e 'exit($] >= 5)'; then - PERL5=no - AC_MSG_RESULT(no) - else - AC_MSG_RESULT(yes) - fi -fi - -if test "$PERL5" != no; then - BUILT_SCRIPTS="$BUILT_SCRIPTS deweb" - SCRIPTS="$SCRIPTS chkweb" -else - AC_MSG_WARN(chkweb will not be installed since you do not have perl5.) -fi - -AC_CHECK_PROGS(GROFF, 'groff -man -P-bu -Tlatin1' 'nroff -man', 'nroff -man') - -AC_PATH_PROG(LATEX, latex, no) -dnl if test "$LATEX" = no; then -dnl AC_MSG_ERROR([No LaTeX on the system, cannot find latex program.]) -dnl fi - -AC_PATH_PROG(DVIPS, dvips) - -AC_PATH_PROG(LYNX, lynx) -AC_PATH_PROG(LATEX2HTML, latex2html) - -dnl Checks for libraries. -AC_CHECK_LIB(termlib, tgetent) -AC_CHECK_LIB(termcap, tgetent) - -dnl Checks for header files. -AC_HEADER_STDC -AC_HEADER_DIRENT -AC_CHECK_HEADERS(limits.h stat.h strings.h stdarg.h dnl -sys/stat.h termcap.h termlib.h unistd.h) - -dnl Checks for typedefs, structures, and compiler characteristics. -AC_C_CONST -AC_C_INLINE -AC_TYPE_SIZE_T - -dnl Checks for library functions. -AC_FUNC_VPRINTF -AC_CHECK_FUNCS(access closedir fileno isatty opendir readdir stat dnl -strcasecmp strdup strlwr strtol) - -AC_CONFIG_HEADER(config.h) -AC_CONFIG_FILES([stamp-h], [echo timestamp > stamp-h]) -AC_OUTPUT(Makefile deweb rmeheader ChkTeX.tex) diff --git a/Build/source/texk/chktex/chktex-1.6.6/deweb.1 b/Build/source/texk/chktex/chktex-1.6.6/deweb.1 deleted file mode 100644 index 43770aa1fd3..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/deweb.1 +++ /dev/null @@ -1,116 +0,0 @@ -.TH deweb 1 "June 8, 1996" -.AT 3 -.SH NAME -deweb \- strips away C & CWEB commands from CWEB sources -.SH SYNOPSIS -.B deweb -[ -.B file1 file2 ... -] -.SH DESCRIPTION -.I deweb -filters away all C & CWEB commands from a CWEB source code. This -leaves only the -.I LaTeX -code. This stripped code, in turn, may then -be passed to a suitable syntax checker for LaTeX, like -.I ChkTeX -and -.I lacheck, -or spell-checkers like -.I ispell. -.PP -The -.I chkweb -tool, included in the -.I ChkTeX -distribution will do just this; writing similar scripts should be -trivial. -.PP -When -.I deweb -strips away the C code from your CWEB source, it tries to preserve line breaks. -This means that the error reports from -.I -will be correct regarding to line numbers. In most cases, -the column position -will also be correct. This significantly simplifies -finding the errors in the -.I LaTeX -source (in contrast to the output from -.I cweave, -which output is truly difficult to figure anything out from). -.PP -.I deweb -accepts a list of filenames on the argument line, and will send its output -to -.I stdout. -If no filenames are given, it will read from stdin, acting as -a filter. No options are currently accepted. -.PP -Macho users may try to pipe the output from -.I deweb -directly into -.I LaTeX, -theoretically, this should work. This would ease the debugging -of the -.I LaTeX -code significantly, as when -.I LaTeX -complains about wrong syntax, you'll be able to find the erroneous -line much more easily. Don't expect that the output looks very much -like the final one, though. -.PP -.I deweb -should now understand all correct -.I CWEB -opcodes. If it complains about not understanding a correct opcode, -please inform the author. -.SH DISTRIBUTION -Copyright (C) 1996 Jens T. Berger Thielemann -.PP -This program is free software; you can redistribute it and/or modify -it under the terms of the -.I GNU General Public License -as published by -the Free Software Foundation; either version 2 of the License, or -(at your option) any later version. -.PP -This program is distributed in the hope that it will be useful, -but -.B WITHOUT ANY WARRANTY; -without even the implied warranty of -.B MERCHANTABILITY -or -.B FITNESS FOR A PARTICULAR PURPOSE. -See the -.I GNU General Public License -for more details. -.PP -You should have received a copy of the -.B GNU General Public License -along with this program; if not, write to the -.I Free Software Foundation, Inc., -51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -.SH ENVIRONMENT -No environment variables are used. -.SH FILES -None. -.SH AUTHOR -Jens T. Berger Thielemann, -.I -.SH "SEE ALSO" -.B cweave(1), perl(1), chktex, lacheck(1), ispell(1) -.SH BUGS -Doesn't even -.B compile -under -.I Perl -versions before perl v5. Unfortunately, this means that we can't even -tell the user why we failed; -.I Perl -will just complain about not being able to compile the regexps. -.PP -The program will try to swallow the whole input file at once, instead of -processing it on a line\-by\-line basis. -.ex diff --git a/Build/source/texk/chktex/chktex-1.6.6/deweb.in b/Build/source/texk/chktex/chktex-1.6.6/deweb.in deleted file mode 100644 index 91750e636a2..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/deweb.in +++ /dev/null @@ -1,122 +0,0 @@ -#! @PERL5@ -# deweb v1.2, kills the C sections of a CWEB file, for passing to ChkTeX. -# Copyright (C) 1996 Jens T. Berger Thielemann -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -# -# Contact the author at: -# Jens Berger -# Spektrumvn. 4 -# N-0666 Oslo -# Norway -# E-mail: -# -# -# - -print STDERR "DeWEB v1.2 - Copyright 1996 Jens T. Berger Thielemann\n"; - -undef $/; -$texmode = 1; -$_ = <>; - -while(/\@/) -{ - &out($`); - $_ = $'; - - if(/^@/) { - $_ = $'; - &out('@'); - next; - } - - if(/^([\s\n])/) { - $_ = $'; - print "\n" if $1 eq "\n"; - $texmode = 1; - next; - } - - if(/^[cpd]/i) { - $_ = $'; - $texmode = 0; - next; - } - - if(/^\,/i) { - $_ = $'; - print '\,'; - next; - } - - if(m!^/!) { - $_ = $'; - print '\\\\'; - next; - } - - if(/^[h\&\|\;\#\+]/i || /^i.*/i) { - $_ = $'; - next; - } - - if(/^\*[0-9\*]?((.|\n)*?\.)/) { - $_ = $'; - print $1; - $texmode = 1; - next; - } - - if(/^[<(^.t!]((.|\n)*?)\@\>/i) { - $_ = $'; - print '{'.$1.'}'; - $texmode = 0; - next; - } - - if(/^[=]((.|\n)*?)\@\>/) { - $_ = $'; - print &printnl($1); - next; - } - - if(/^[fsl](\s+\S+\s+\S+)|^\'(.|\n)*?\'|^\[((.|\n)*?)\@\]/i) { - $_ = $'; - print &printnl($+); - next; - } - - @line = split(/\n/, $_, 2); - print STDERR "Unknown opcode, ignored. Buffer:\n$line[0]\n"; - -} - -print $_; - -sub printnl { - my($foo); - if(defined $_[0]) { - $foo = $_[0]; - $foo =~ s/.//g; - } else { - $foo = ""; - } - $foo; -} - -sub out { - print $texmode? $_[0] : &printnl($_[0]); -} diff --git a/Build/source/texk/chktex/chktex-1.6.6/input.tex b/Build/source/texk/chktex/chktex-1.6.6/input.tex deleted file mode 100644 index 76bc301ff25..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/input.tex +++ /dev/null @@ -1 +0,0 @@ -\this is a test of whether the file is actually inputted... diff --git a/Build/source/texk/chktex/chktex-1.6.6/lacheck b/Build/source/texk/chktex/chktex-1.6.6/lacheck deleted file mode 100755 index da75d360dee..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/lacheck +++ /dev/null @@ -1,27 +0,0 @@ -#! /bin/sh - -# lacheck replacement 1.0, lacheck <-> ChkTeX interface (UNIX). -# Copyright (C) 1996 Jens T. Berger Thielemann -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. -# -# Contact the author at: -# Jens Berger -# Spektrumvn. 4 -# N-0666 Oslo -# Norway -# E-mail: - -chktex -v3 $* diff --git a/Build/source/texk/chktex/chktex-1.6.6/m4/ax_cflags_strict_prototypes.m4 b/Build/source/texk/chktex/chktex-1.6.6/m4/ax_cflags_strict_prototypes.m4 deleted file mode 100644 index 06ec9e2f27b..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/m4/ax_cflags_strict_prototypes.m4 +++ /dev/null @@ -1,170 +0,0 @@ -# =========================================================================== -# http://autoconf-archive.cryp.to/ax_cflags_strict_prototypes.html -# =========================================================================== -# -# SYNOPSIS -# -# AX_CFLAGS_STRICT_PROTOTYPES [(shellvar [,default, [A/NA]] -# -# DESCRIPTION -# -# Try to find a compiler option that requires strict prototypes. -# -# The sanity check is done by looking at sys/signal.h which has a set of -# macro-definitions SIG_DFL and SIG_IGN that are cast to the local -# signal-handler type. If that signal-handler type is not fully qualified -# then the system headers are not seen as strictly prototype clean. -# -# For the GNU CC compiler it will be -fstrict-prototypes -# -Wstrict-prototypes The result is added to the shellvar being CFLAGS by -# default. -# -# DEFAULTS: -# -# - $1 shell-variable-to-add-to : CFLAGS -# - $2 add-value-if-not-found : nothing -# - $3 action-if-found : add value to shellvariable -# - $4 action-if-not-found : nothing -# -# LAST MODIFICATION -# -# 2008-04-12 -# -# COPYLEFT -# -# Copyright (c) 2008 Guido U. Draheim -# -# This program is free software; you can redistribute it and/or modify it -# under the terms of the GNU General Public License as published by the -# Free Software Foundation; either version 2 of the License, or (at your -# option) any later version. -# -# This program is distributed in the hope that it will be useful, but -# WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General -# Public License for more details. -# -# You should have received a copy of the GNU General Public License along -# with this program. If not, see . -# -# As a special exception, the respective Autoconf Macro's copyright owner -# gives unlimited permission to copy, distribute and modify the configure -# scripts that are the output of Autoconf when processing the Macro. You -# need not follow the terms of the GNU General Public License when using -# or distributing such scripts, even though portions of the text of the -# Macro appear in them. The GNU General Public License (GPL) does govern -# all other use of the material that constitutes the Autoconf Macro. -# -# This special exception to the GPL applies to versions of the Autoconf -# Macro released by the Autoconf Macro Archive. When you make and -# distribute a modified version of the Autoconf Macro, you may extend this -# special exception to the GPL to apply to your modified version as well. - -AC_DEFUN([AX_CFLAGS_STRICT_PROTOTYPES],[dnl -AS_VAR_PUSHDEF([FLAGS],[CFLAGS])dnl -AS_VAR_PUSHDEF([VAR],[ac_cv_cflags_strict_prototypes])dnl -AC_CACHE_CHECK([m4_ifval($1,$1,FLAGS) for strict prototypes], -VAR,[VAR="no, unknown" - AC_LANG_SAVE - AC_LANG_C - ac_save_[]FLAGS="$[]FLAGS" -for ac_arg dnl -in "-pedantic % -fstrict-prototypes -Wstrict-prototypes" dnl GCC - "-pedantic % -Wstrict-prototypes" dnl try to warn atleast - "-pedantic % -Wmissing-prototypes" dnl or another warning - "-pedantic % -Werror-implicit-function-declaration" dnl - "-pedantic % -Wimplicit-function-declaration" dnl - # -do FLAGS="$ac_save_[]FLAGS "`echo $ac_arg | sed -e 's,%%.*,,' -e 's,%,,'` - AC_TRY_COMPILE([],[return 0;], - [VAR=`echo $ac_arg | sed -e 's,.*% *,,'` ; break]) -done -case ".$VAR" in - .|.no|.no,*) ;; - *) # sanity check with signal() from sys/signal.h - cp config.log config.tmp - AC_TRY_COMPILE([#include ],[ - if (signal (SIGINT, SIG_IGN) == SIG_DFL) return 1; - if (signal (SIGINT, SIG_IGN) != SIG_DFL) return 2;], - dnl the original did use test -n `$CC testprogram.c` - [if test `diff config.log config.tmp | grep -i warning | wc -l` != 0 -then if test `diff config.log config.tmp | grep -i warning | wc -l` != 1 -then VAR="no, suppressed, signal.h," ; fi ; fi], - [VAR="no, suppressed, signal.h"]) - rm config.tmp - ;; -esac - FLAGS="$ac_save_[]FLAGS" - AC_LANG_RESTORE -]) -case ".$VAR" in - .ok|.ok,*) m4_ifvaln($3,$3) ;; - .|.no|.no,*) m4_ifvaln($4,$4,[m4_ifval($2,[ - AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"]) - m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"])]) ;; - *) m4_ifvaln($3,$3,[ - if echo " $[]m4_ifval($1,$1,FLAGS) " | grep " $VAR " 2>&1 >/dev/null - then AC_RUN_LOG([: m4_ifval($1,$1,FLAGS) does contain $VAR]) - else AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR"]) - m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR" - fi ]) ;; -esac -AS_VAR_POPDEF([VAR])dnl -AS_VAR_POPDEF([FLAGS])dnl -]) - -dnl the only difference - the LANG selection... and the default FLAGS - -AC_DEFUN([AX_CXXFLAGS_STRICT_PROTOTYPES],[dnl -AS_VAR_PUSHDEF([FLAGS],[CXXFLAGS])dnl -AS_VAR_PUSHDEF([VAR],[ac_cv_cxxflags_strict_prototypes])dnl -AC_CACHE_CHECK([m4_ifval($1,$1,FLAGS) for strict prototypes], -VAR,[VAR="no, unknown" - AC_LANG_SAVE - AC_LANG_CPLUSPLUS - ac_save_[]FLAGS="$[]FLAGS" -for ac_arg dnl -in "-pedantic -Werror % -fstrict-prototypes -Wstrict-prototypes" dnl GCC - "-pedantic -Werror % -Wstrict-prototypes" dnl try to warn atleast - "-pedantic -Werror % -Wmissing-prototypes" dnl try to warn atleast - "-pedantic -Werror % -Werror-implicit-function-declaration" dnl - "-pedantic -Werror % -Wimplicit-function-declaration" dnl - "-pedantic % -Wstrict-prototypes %% no, unsupported in C++" dnl oops - # -do FLAGS="$ac_save_[]FLAGS "`echo $ac_arg | sed -e 's,%%.*,,' -e 's,%,,'` - AC_TRY_COMPILE([],[return 0;], - [VAR=`echo $ac_arg | sed -e 's,.*% *,,'` ; break]) -done -case ".$VAR" in - .|.no|.no,*) ;; - *) # sanity check with signal() from sys/signal.h - cp config.log config.tmp - AC_TRY_COMPILE([#include ],[ - if (signal (SIGINT, SIG_IGN) == SIG_DFL) return 1; - if (signal (SIGINT, SIG_IGN) != SIG_DFL) return 2;], - dnl the original did use test -n `$CC testprogram.c` - [if test `diff config.log config.tmp | grep -i warning | wc -l` != 0 -then if test `diff config.log config.tmp | grep -i warning | wc -l` != 1 -then VAR="no, suppressed, signal.h," ; fi ; fi], - [VAR="no, suppressed, signal.h"]) - rm config.tmp - ;; -esac - FLAGS="$ac_save_[]FLAGS" - AC_LANG_RESTORE -]) -case ".$VAR" in - .ok|.ok,*) m4_ifvaln($3,$3) ;; - .|.no|.no,*) m4_ifvaln($4,$4,[m4_ifval($2,[ - AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"]) - m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"])]) ;; - *) m4_ifvaln($3,$3,[ - if echo " $[]m4_ifval($1,$1,FLAGS) " | grep " $VAR " 2>&1 >/dev/null - then AC_RUN_LOG([: m4_ifval($1,$1,FLAGS) does contain $VAR]) - else AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR"]) - m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR" - fi ]) ;; -esac -AS_VAR_POPDEF([VAR])dnl -AS_VAR_POPDEF([FLAGS])dnl -]) diff --git a/Build/source/texk/chktex/chktex-1.6.6/m4/vl_prog_cc_warnings.m4 b/Build/source/texk/chktex/chktex-1.6.6/m4/vl_prog_cc_warnings.m4 deleted file mode 100644 index fe2f6145450..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/m4/vl_prog_cc_warnings.m4 +++ /dev/null @@ -1,111 +0,0 @@ -AC_DEFUN([VL_PROG_CC_WARNINGS], [ - ansi=$1 - if test -z "$ansi"; then - msg="for C compiler warning flags" - else - msg="for C compiler warning and ANSI conformance flags" - fi - AC_CACHE_CHECK($msg, vl_cv_prog_cc_warnings, [ - if test -n "$CC"; then - cat > conftest.c <&1 | grep -i "WorkShop" > /dev/null 2>&1 && - $CC -c -v -Xc conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-v" - else - vl_cv_prog_cc_warnings="-v -Xc" - fi - - dnl Digital Unix C compiler - elif $CC -V 2>&1 | grep -i "Digital UNIX Compiler" > /dev/null 2>&1 && - $CC -c -verbose -w0 -warnprotos -std1 conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-verbose -w0 -warnprotos" - else - vl_cv_prog_cc_warnings="-verbose -w0 -warnprotos -std1" - fi - - dnl C for AIX Compiler - elif $CC 2>&1 | grep -i "C for AIX Compiler" > /dev/null 2>&1 && - $CC -c -qlanglvl=ansi -qinfo=all conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-qsrcmsg -qinfo=all:noppt:noppc:noobs:nocnd" - else - vl_cv_prog_cc_warnings="-qsrcmsg -qinfo=all:noppt:noppc:noobs:nocnd -qlanglvl=ansi" - fi - - dnl IRIX C compiler - elif $CC -version 2>&1 | grep -i "MIPSpro Compilers" > /dev/null 2>&1 && - $CC -c -fullwarn -ansi -ansiE conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-fullwarn" - else - vl_cv_prog_cc_warnings="-fullwarn -ansi -ansiE" - fi - - dnl HP-UX C compiler - elif what $CC 2>&1 | grep -i "HP C Compiler" > /dev/null 2>&1 && - $CC -c -Aa +w1 conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="+w1" - else - vl_cv_prog_cc_warnings="+w1 -Aa" - fi - - dnl The NEC SX-5 (Super-UX 10) C compiler - elif $CC -V 2>&1 | grep "/SX" > /dev/null 2>&1 && - $CC -c -pvctl[,]fullmsg -Xc conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-pvctl[,]fullmsg" - else - vl_cv_prog_cc_warnings="-pvctl[,]fullmsg -Xc" - fi - - dnl The Cray C compiler (Unicos) - elif $CC -V 2>&1 | grep -i "Cray" > /dev/null 2>&1 && - $CC -c -h msglevel 2 conftest.c > /dev/null 2>&1 && - test -f conftest.o; then - if test -z "$ansi"; then - vl_cv_prog_cc_warnings="-h msglevel 2" - else - vl_cv_prog_cc_warnings="-h msglevel 2 -h conform" - fi - - fi - rm -f conftest.* - fi - if test -n "$vl_cv_prog_cc_warnings"; then - CFLAGS="$CFLAGS $vl_cv_prog_cc_warnings" - else - vl_cv_prog_cc_warnings="unknown" - fi - ]) -])dnl - diff --git a/Build/source/texk/chktex/chktex-1.6.6/rmeheader.in b/Build/source/texk/chktex/chktex-1.6.6/rmeheader.in deleted file mode 100644 index 56ca58ae76e..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/rmeheader.in +++ /dev/null @@ -1,19 +0,0 @@ -Short: v@PACKAGE_VERSION@. Finds typographic errors in LaTeX -Author: (Baruch Even) -Uploader: (Baruch Even) -Type: text/tex -Replaces: text/tex/ChkTeX.lha -Version: @PACKAGE_VERSION@ -URL: http://www.freesoftware.fsf.org/chktex - - - ##### ### ### ######## ### ## - ### ## ## ## ## ## # - @@ @@ @@@ @@ @@ @@ ####### @@ @ - @@ @@@ @@ @@ @@ @@ ## # @@ - && && && &&&& && @@ & && - &&& && && && && && && @@@@ & && - %%%%% %%% %%% %%% %%% %% && %%% %%% v@PACKAGE_VERSION@ - && & - %%%%%%% - diff --git a/Build/source/texk/chktex/chktex-1.6.6/types.h b/Build/source/texk/chktex/chktex-1.6.6/types.h deleted file mode 100644 index a26b95295e4..00000000000 --- a/Build/source/texk/chktex/chktex-1.6.6/types.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Clone of , which could not be included because it's - * (c) Commodore/Escom/Amiga/whatever. - * - */ - -#ifndef EXEC_TYPES_H -#define EXEC_TYPES_H - -#ifndef TRUE -# define TRUE 1L -#endif -#ifndef FALSE -# define FALSE 0L -#endif - -#endif diff --git a/Build/source/texk/chktex/chktex-1.7.1-PATCHES/ChangeLog b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/ChangeLog new file mode 100644 index 00000000000..81d0ce801a0 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/ChangeLog @@ -0,0 +1,63 @@ +2012-09-27 Peter Breitenlohner + + Imported chktex-1.7.1 source tree from: + http://download.savannah.gnu.org/ + * patch-06-extern(removed): Now distributed. + * patch-07-kpathsea: Adapted. + * patch-08-stpcpy (new): Not everyone has stpcpy(). + * patch-09-test-output (new): Our Test.out. + +2012-07-23 Peter Breitenlohner + + * patch-07-kpathsea (new): With -DKPATHSEA now using kpathsea. + +2012-04-16 Peter Breitenlohner + + * patch-06-extern: Remove the obsolete ASM_HASHWORD stuff (for + Amiga) avoiding extern decls from *.c files. + +2012-04-10 Karl Berry + + * patch-01-const, + * patch-02-bug, + * patch-03-texlive, + * patch-04-strcpy-bug, + * patch-05-ctype-bug: apparently installed upstream, yay. + + * patch-06-extern: not installed, but HashWord and HASH_TYPE are + only used in that one .c file anyway, so it seems fine to me for + them to be defined there. Admittedly the function should be static. + Did not apply or change, sorry. + + * TL-Changes: update for chktex 1.6.6. + +2012-03-29 Peter Breitenlohner + + * patch-06-extern (new): Move decls from Utility.c to Utility.h. + +2010-06-13 Peter Breitenlohner + + * patch-05-ctype-bug (new): Bug fix: + Cast all arguments of isalpha() and similar to 'unsigned char'. + Patch from Jukka Salmi [tlbuild, 10 Jun 2010]. + +2010-05-21 Peter Breitenlohner + + * patch-01-const: Change OutputFormat and PipeOutputFormat back + to non-const. + +2010-05-20 Peter Breitenlohner + + * patch-04-strcpy-bug (new): Bug fixes: + (GetLTXArg): Avoid strcpy() with overlapping args. + (PreProcess): Do not access Buf[-1]. + +2010-05-06 Peter Breitenlohner + + * patch-02-bug (new): Bug fix + * patch-03-texlive (new): Handle global rc file for TeX Live. + +2010-05-02 Peter Breitenlohner + + * patch-01-const (new): Avoid compiler warnings (const). + diff --git a/Build/source/texk/chktex/chktex-1.7.1-PATCHES/TL-Changes b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/TL-Changes new file mode 100644 index 00000000000..0cbbc649fd5 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/TL-Changes @@ -0,0 +1,12 @@ +Changes applied to the chktex-1.7.1 tree as obtained from: + http://mirror.ctan.org/support/chktex/chktex-1.7.1.tar.gz + http://download.savannah.gnu.org/releases/chktex/chktex-1.7.1.tar.gz + +Remove: + configure + install-sh + stamp-h.in + +Rename: + chkweb -> chkweb.sh + diff --git a/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-07-kpathsea b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-07-kpathsea new file mode 100644 index 00000000000..f5ae61eb536 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-07-kpathsea @@ -0,0 +1,28 @@ +diff -ur chktex-1.7.1.orig/ChkTeX.c chktex-1.7.1/ChkTeX.c +--- chktex-1.7.1.orig/ChkTeX.c 2012-07-26 12:44:22.000000000 +0200 ++++ chktex-1.7.1/ChkTeX.c 2012-09-27 10:08:21.000000000 +0200 +@@ -27,7 +27,9 @@ + */ + + ++#ifndef KPATHSEA + #include "getopt.h" ++#endif + #include "ChkTeX.h" + #include "OpSys.h" + #include "Utility.h" +diff -ur chktex-1.7.1.orig/ChkTeX.h chktex-1.7.1/ChkTeX.h +--- chktex-1.7.1.orig/ChkTeX.h 2012-08-04 21:28:49.000000000 +0200 ++++ chktex-1.7.1/ChkTeX.h 2012-09-27 10:08:21.000000000 +0200 +@@ -38,6 +38,11 @@ + # include CONFIG_H_NAME + #endif + ++#ifdef KPATHSEA ++#include ++#include ++#endif ++ + #include + #include + #include diff --git a/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-08-stpcpy b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-08-stpcpy new file mode 100644 index 00000000000..e2536cd8fcc --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-08-stpcpy @@ -0,0 +1,17 @@ +diff -ur chktex-1.7.1.orig/FindErrs.c chktex-1.7.1/FindErrs.c +--- chktex-1.7.1.orig/FindErrs.c 2012-08-08 22:27:57.000000000 +0200 ++++ chktex-1.7.1/FindErrs.c 2012-09-27 10:58:01.000000000 +0200 +@@ -33,6 +33,13 @@ + #include "Utility.h" + #include "Resource.h" + ++/* Not everyone has stpcpy() */ ++static inline char * ++stpcpy(char *dest, const char *src) ++{ ++ return strcpy(dest, src) + strlen(src); ++} ++ + #if HAVE_PCRE || HAVE_POSIX_ERE + + #if HAVE_PCRE diff --git a/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-09-test-output b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-09-test-output new file mode 100644 index 00000000000..8206114742c --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1-PATCHES/patch-09-test-output @@ -0,0 +1,27 @@ +diff -ur chktex-1.7.1.orig/Test.out chktex-1.7.1/Test.out +--- chktex-1.7.1.orig/Test.out 2012-08-09 17:11:32.000000000 +0200 ++++ chktex-1.7.1/Test.out 2012-09-27 10:56:14.000000000 +0200 +@@ -418,9 +418,9 @@ + Message 22 in Test.tex: Comment displayed. + % Warning 44 -- user regex -- default message + ^ +-Message 44 in Test.tex: User Regex: intro. ++Message 44 in Test.tex: User Regex: intro.. + You should always write a good intro. +- ^^^^^ ++ ^^^^^^^ + Message 22 in Test.tex: Comment displayed. + % Warning 44 -- user regex -- user message + ^ +@@ -457,9 +457,9 @@ + Message 36 in Test.tex: You should put a space after parenthesis. + Here(on this line only)is a warning $sin(x)$ suppressed. % CHKTEX 35 36 + ^ +-Message 44 in Test.tex: User Regex: -1:Capitalize before references. ++Message 44 in Test.tex: User Regex: 1:Capitalize before references. + In section~\ref{sec:3} we have a warning. +- ^^^^^^^^^^^^ ++ ^^^^^^^^^^^^^ + Message 22 in Test.tex: Comment displayed. + In section~\ref{sec:4} it is suppressed. % chktex -1 + ^ diff --git a/Build/source/texk/chktex/chktex-1.7.1/COPYING b/Build/source/texk/chktex/chktex-1.7.1/COPYING new file mode 100644 index 00000000000..d4e8cec1128 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/COPYING @@ -0,0 +1,357 @@ + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + + The GNU General Public License version 2 is included below for your reference. + +------------------------------------------------------------------------ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) 19yy + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, + USA. + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) 19yy name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + , 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.c b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.c new file mode 100644 index 00000000000..1bddf930e46 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.c @@ -0,0 +1,1054 @@ +/* + * ChkTeX, finds typographic errors in (La)TeX files. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + + +#ifndef KPATHSEA +#include "getopt.h" +#endif +#include "ChkTeX.h" +#include "OpSys.h" +#include "Utility.h" +#include "FindErrs.h" +#include "Resource.h" +#include + +#undef MSG +#define MSG(num, type, inuse, ctxt, text) {num, type, inuse, ctxt, text}, + +struct ErrMsg PrgMsgs[pmMaxFault + 1] = { + PRGMSGS {pmMaxFault, etErr, TRUE, 0, INTERNFAULT} +}; + +struct Stack CharStack = { + 0L +}, InputStack = + +{ +0L}, EnvStack = + +{ +0L}; + +/************************************************************************/ + +const char BrOrder[NUMBRACKETS + 1] = "()[]{}"; + +unsigned long Brackets[NUMBRACKETS]; + +/************************************************************************/ + + +/* + * Have to do things this way, to ease some checking throughout the + * program. + */ + + +NEWBUF(TmpBuffer, BUFSIZ); +NEWBUF(ReadBuffer, BUFSIZ); + +static const char *Banner = + "ChkTeX v" PACKAGE_VERSION " - Copyright 1995-96 Jens T. Berger Thielemann.\n" +#ifdef __OS2__ + "OS/2 port generated with emx compiler, by Wolfgang Fritsch, \n" +#elif defined(__MSDOS__) + "MS-DOS port by Bj\\o rn Ove Thue, \n" +#endif +#if HAVE_PCRE + "Compiled with PCRE regex support." +#else +#if HAVE_POSIX_ERE + "Compiled with POSIX extended regex support." +#else + "Compiled with no regex support." +#endif +#endif + "\n"; + +static const char *BigBanner = + "ChkTeX comes with ABSOLUTELY NO WARRANTY; details on this and\n" + "distribution conditions in the GNU General Public License file.\n" + "Type \"ChkTeX -h\" for help, \"ChkTeX -i\" for distribution info.\n" + "Author: Jens Berger, Spektrumvn. 4, N-0666 Oslo, Norway.\n" + "E-mail: \n" + "Press " STDIN_BREAK " to terminate stdin input.\n"; + +static const char *Distrib = + "\n" + "This program is free software; you can redistribute it and/or modify\n" + "it under the terms of the GNU General Public License as published by\n" + "the Free Software Foundation; either version 2 of the License, or\n" + "(at your option) any later version.\n" + "\n" + "This program is distributed in the hope that it will be useful,\n" + "but WITHOUT ANY WARRANTY; without even the implied warranty of\n" + "MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\n" + "GNU General Public License for more details.\n" + "\n" + "You should have received a copy of the GNU General Public License\n" + "along with this program; if not, write to the Free Software\n" + "Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.\n"; + +static const char *OnText = "On"; + +static const char *OffText = "Off"; + +static const char *HowHelp = + "-h or --help gives usage information. See also ChkTeX.{ps,dvi}.\n"; + +static const char *HelpText = + "\n" + "\n" + " Usage of ChkTeX v" PACKAGE_VERSION "\n" + " ~~~~~~~~~~~~~~~~~~~~~~\n" + "\n" + " Template\n" + " ~~~~~~~~\n" + "chktex [-hiqrW] [-v[0-...]] [-l ] [-[wemn] <[1-42]|all>]\n" + " [-d[0-...]] [-p ] [-o ] [-[btxgI][0|1]]\n" + " file1 file2 ...\n" + "\n" + "----------------------------------------------------------------------\n" + " Description of options:\n" + " ~~~~~~~~~~~~~~~~~~~~~~~\n" + "Misc. options\n" + "~~~~~~~~~~~~~\n" + " -h --help : This text.\n" + " -i --license : Show distribution information\n" + " -l --localrc : Read local .chktexrc formatted file.\n" + " -d --debug : Debug information. Give it a number.\n" + " -r --reset : Reset settings to default.\n" + "\n" + "Muting warning messages:\n" + "~~~~~~~~~~~~~~~~~~~~~~~~\n" + " -w --warnon : Makes msg # given a warning and turns it on.\n" + " -e --erroron : Makes msg # given an error and turns it on.\n" + " -m --msgon : Makes msg # given a message and turns it on.\n" + " -n --nowarn : Mutes msg # given.\n" + " -L --nolinesupp: Disables per-line suppressions.\n" + "\n" + "Output control flags:\n" + "~~~~~~~~~~~~~~~~~~~~~\n" + " -v --verbosity : How errors are displayed.\n" + " Default 1, 0=Less, 2=Fancy, 3=lacheck.\n" + " -V --pipeverb : How errors are displayed when stdout != tty.\n" + " Defaults to the same as -v.\n" + " -s --splitchar : String used to split fields when doing -v0\n" + " -o --output : Redirect error report to a file.\n" + " -q --quiet : Shuts up about version information.\n" + " -p --pseudoname: Input file-name when reporting.\n" + " -f --format : Format to use for output\n" + "\n" + "Boolean switches (1 -> enables / 0 -> disables):\n" + "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + " -b --backup : Backup output file.\n" + " -x --wipeverb : Ignore contents of `\\verb' commands.\n" + " -g --globalrc : Read global .chktexrc file.\n" + " -I --inputfiles: Execute \\input statements.\n" + " -H --headererr : Show errors found in front of \\begin{document}\n" + "\n" + "Miscellaneous switches:\n" + "~~~~~~~~~~~~~~~~~~~~~~~\n" + " -W --version : Version information\n" + "\n" + "----------------------------------------------------------------------\n" + "If no LaTeX files are specified on the command line, we will read from\n" + "stdin. For explanation of warning/error messages, please consult the\n" + "main documentation ChkTeX.dvi, ChkTeX.ps or ChkTeX.pdf.\n"; + + + + +/* + * Options we will set. + * + */ + +enum Quote Quote; + +char VerbNormal[] = "%k %n in %f line %l: %m\n" "%r%s%t\n" "%u\n"; + +#define DEF(type, name, value) type name = value; +OPTION_DEFAULTS; +STATE_VARS; +#undef DEF +FILE *OutputFile = NULL; + +char *PrgName; + +int StdInTTY, StdOutTTY; + +/* + * End of config params. + */ + +static int ParseArgs(int argc, char **argv); +static void ShowIntStatus(void); +static int OpenOut(void); +static int ShiftArg(char **Argument); + + +/* + * Duplicates all arguments, and appends an asterix to each of them. + */ + +static void AddStars(struct WordList *wl) +{ + unsigned long Count, CmdLen; + char *Data; + + FORWL(Count, *wl) + { + Data = wl->Stack.Data[Count]; + CmdLen = strlen(Data); + if (Data[CmdLen - 1] != '*') + { + strcpy(TmpBuffer, Data); + strcat(TmpBuffer, "*"); + InsertWord(TmpBuffer, wl); + } + } +} + +/* + * Sets up all the lists. + * + */ + +static void SetupLists(void) +{ + unsigned long i; + + AddStars(&VerbEnvir); + AddStars(&MathEnvir); + + MakeLower(&UserWarnCase); + + ListRep(&WipeArg, ':', 0); + ListRep(&NoCharNext, ':', 0); + +#define ThisItem ((char *) AbbrevCase.Stack.Data[i]) + + FORWL(i, AbbrevCase) + { + if (isalpha((unsigned char)ThisItem[0])) + { + ThisItem[0] = toupper((unsigned char)ThisItem[0]); + InsertWord(ThisItem, &Abbrev); + ThisItem[0] = tolower((unsigned char)ThisItem[0]); + } + InsertWord(ThisItem, &Abbrev); + } +} + +#define NOCOMMON(a,b) NoCommon(&a,#a,&b,#b) + +/* + * Checks that two lists don't have any common element. + */ + +static void +NoCommon(struct WordList *a, const char *aName, + struct WordList *b, const char *bName) +{ + unsigned long i; + + FORWL(i, *a) + { + if (HasWord((char *) a->Stack.Data[i], b)) + PrintPrgErr(pmNoCommon, a->Stack.Data[i], aName, bName); + } +} + +/* + * Expands the tabs in a string to regular intervals sized + * TSize. + */ + +static void ExpandTabs(char *From, char *To, long TSize) +{ + char *Next; + char *Orig; + unsigned long Diff; + + Next = From; + Orig = To; + + while ((Next = strchr(From, '\t'))) + { + if ((Diff = Next - From)) + { + strncpy(To, From, Diff); + To += Diff; + Diff = TSize - ((To - Orig) % TSize); + } + else + Diff = TSize; + + memset(To, ' ', Diff); + To += Diff; + + From = ++Next; + } + strcpy(To, From); +} + + +int main(int argc, char **argv) +{ + int retval = EXIT_FAILURE, CurArg; + unsigned long Count; + int StdInUse = FALSE; + long Tab = 8; + +#ifdef __LOCALIZED + + InitStrings(); +#endif + + OutputFile = stdout; + PrgName = argv[0]; + +#undef KEY +#undef LCASE +#undef LIST +#undef LNEMPTY +#define KEY(a, def) +#define LCASE(a) +#define LIST(a) +#define LNEMPTY(a) InsertWord("", &a); + + RESOURCE_INFO; + + while (SetupVars()) + ReadRC(ConfigFile); + + if (CmdLine.Stack.Used) + { + ParseArgs(CmdLine.Stack.Used, (char **) CmdLine.Stack.Data); + CmdLine.Stack.Used = 1L; + } + + if ((CurArg = ParseArgs((unsigned long) argc, argv))) + { + if (CmdLine.Stack.Used) + { + ParseArgs(CmdLine.Stack.Used, (char **) CmdLine.Stack.Data); + CmdLine.Stack.Used = 1L; + } + + if (!Quiet || LicenseOnly) + fprintf(stderr, "%s", Banner); + + if (CurArg == argc) + UsingStdIn = TRUE; + +#if defined(HAVE_FILENO) && defined(HAVE_ISATTY) + + StdInTTY = isatty(fileno(stdin)); + StdOutTTY = isatty(fileno(stdout)); +#else + + StdInTTY = StdOutTTY = TRUE; +#endif + + SetupTerm(); + + if ((UsingStdIn && StdInTTY && !Quiet) || LicenseOnly) + { + fprintf(stderr, "%s", BigBanner); + } + + if (!StdOutTTY && PipeOutputFormat) + OutputFormat = PipeOutputFormat; + + if (LicenseOnly) + { + fprintf(stderr, "%s", Distrib); + } + else + { + SetupLists(); + if (QuoteStyle) + { + if (!strcasecmp(QuoteStyle, "LOGICAL")) + Quote = quLogic; + else if (!strcasecmp(QuoteStyle, "TRADITIONAL")) + Quote = quTrad; + else + { + PrintPrgErr(pmQuoteStyle, QuoteStyle); + Quote = quTrad; + } + } + + if (DebugLevel) + ShowIntStatus(); + + NOCOMMON(Italic, NonItalic); + NOCOMMON(Italic, ItalCmd); + NOCOMMON(LowDots, CenterDots); + + if (TabSize && isdigit((unsigned char)*TabSize)) + Tab = strtol(TabSize, NULL, 10); + + if (OpenOut()) + { + for (;;) + { + for (Count = 0; Count < NUMBRACKETS; Count++) + Brackets[Count] = 0L; + +#define DEF(type, name, value) name = value; + STATE_VARS; +#undef DEF + if (UsingStdIn) + { + if (StdInUse) + break; + else + { + StdInUse = TRUE; + PushFile("stdin", stdin, &InputStack); + } + } + else + { + if (CurArg <= argc) + { + const char *filename = NULL; + if (CurArg < argc) + filename = argv[CurArg++]; + + if (!PushFileName(filename, &InputStack)) + break; + } + } + + if (StkTop(&InputStack) && OutputFile) + { + while (!ferror(OutputFile) + && StkTop(&InputStack) + && !ferror(CurStkFile(&InputStack)) + && FGetsStk(ReadBuffer, BUFSIZ - 1, + &InputStack)) + { + + /* Make all spaces ordinary spaces */ + + strrep(ReadBuffer, '\n', ' '); + strrep(ReadBuffer, '\r', ' '); + ExpandTabs(ReadBuffer, TmpBuffer, Tab); + strcpy(ReadBuffer, TmpBuffer); + + strcat(ReadBuffer, " "); + FindErr(ReadBuffer, CurStkLine(&InputStack)); + } + + PrintStatus(CurStkLine(&InputStack)); + retval = EXIT_SUCCESS; + } + } + } + } + } + return retval; +} + +/* + * Opens the output file handle & possibly renames + */ + +static int OpenOut(void) +{ + int Success = TRUE; + + if (*OutputName) + { + if (BackupOut && fexists(OutputName)) + { + strcpy(TmpBuffer, OutputName); + AddAppendix(TmpBuffer, BAKAPPENDIX); + + if (fexists(TmpBuffer)) + remove(TmpBuffer); + + if (!rename(OutputName, TmpBuffer)) + PrintPrgErr(pmRename, OutputName, TmpBuffer); + else + { + PrintPrgErr(pmRenameErr, OutputName, TmpBuffer); + Success = FALSE; + } + + } + + if (Success) + { + if (!(OutputFile = fopen(OutputName, "w"))) + { + PrintPrgErr(pmOutOpen); + Success = FALSE; + } + } + } + else + OutputFile = stdout; + + return (Success); +} + +#ifndef STRIP_DEBUG +static void ShowWL(const char *Name, const struct WordList *wl) +{ + unsigned long i, j, percent; + + fprintf(stderr, "Name: %12s", Name); + + if (DebugLevel & FLG_DbgListInfo) + { + fprintf(stderr, ", MaxLen: %3ld, Entries: %3ld, ", + wl->MaxLen, wl->Stack.Used); + + if (wl->Hash.Index && wl->Stack.Used) + { + for (i = j = 0; i < HASH_SIZE; i++) + { + if (wl->Hash.Index[i]) + j++; + } + percent = (j * 10000) / wl->Stack.Used; + + + fprintf(stderr, "Hash usage: %3ld.%02ld%%", + percent / 100, percent % 100); + } + else + fprintf(stderr, "No hash table."); + } + + fputc('\n', stderr); + + if (DebugLevel & FLG_DbgListCont) + { + FORWL(i, *wl) fprintf(stderr, "\t%s\n", (char *) wl->Stack.Data[i]); + } +} +#endif + +#define BOOLDISP(var) ((var)? OnText : OffText) +#define SHOWSTAT(text, arg) fprintf(stderr, "\t" text ": %s\n", arg) +#define BOOLSTAT(name, var) SHOWSTAT(name, BOOLDISP(var)) +#define SHOWSTR(text, arg) fprintf(stderr, "%s:\n\t%s\n", text, arg); + + +/* + * Prints some of the internal flags; mainly for debugging purposes + */ + +static void ShowIntStatus(void) +{ +#ifndef STRIP_DEBUG + unsigned long Cnt; + const char *String; + const char *iuStr = ""; + + if (DebugLevel & FLG_DbgMsgs) + { + fprintf(stderr, "There are %d warnings/error messages available:\n", + emMaxFault - emMinFault - 1); + + for (Cnt = emMinFault + 1; Cnt < emMaxFault; Cnt++) + { + switch (LaTeXMsgs[Cnt].Type) + { + case etWarn: + String = "Warning"; + break; + case etErr: + String = "Error"; + break; + case etMsg: + String = "Message"; + break; + default: + String = ""; + break; + } + + switch (LaTeXMsgs[Cnt].InUse) + { + case iuOK: + iuStr = "In use"; + break; + case iuNotUser: + iuStr = "User muted"; + break; + case iuNotSys: + iuStr = "System muted"; + break; + } + + fprintf(stderr, "Number: %2ld, Type: %s, Status: %s\n" + "\tText: %s\n\n", + Cnt, String, iuStr, LaTeXMsgs[Cnt].Message); + } + } + +#undef KEY +#undef LCASE +#undef LNEMPTY +#undef LIST + +#define LNEMPTY LIST +#define LIST(a) ShowWL(#a, &a); +#define LCASE(a) LIST(a); LIST(a ## Case); +#define KEY(a,def) SHOWSTR(#a, a); + + + if (DebugLevel & (FLG_DbgListInfo | FLG_DbgListCont)) + { + RESOURCE_INFO; + } + + if (DebugLevel & FLG_DbgOtherInfo) + { + SHOWSTR("Outputformat", OutputFormat); + + fprintf(stderr, "Current flags include:\n"); + + BOOLSTAT("Read global resource", GlobalRC); + BOOLSTAT("Wipe verbose commands", WipeVerb); + BOOLSTAT("Backup outfile", BackupOut); + BOOLSTAT("Quiet mode", Quiet); + BOOLSTAT("Show license", LicenseOnly); + BOOLSTAT("Use stdin", UsingStdIn); + BOOLSTAT("\\input files", InputFiles); + BOOLSTAT("Output header errors", HeadErrOut); + BOOLSTAT("No line suppressions", NoLineSupp); + } +#endif +} + +/* + * Resets all stacks. + * + */ + +#undef KEY +#undef LCASE +#undef LNEMPTY +#undef LIST + +#define LNEMPTY LIST +#define LIST(a) ClearWord(&a); +#define LCASE(a) LIST(a); LIST(a ## Case); +#define KEY(a,def) a = def; + +static void ResetStacks(void) +{ + RESOURCE_INFO; + +} + +/* + * Resets all flags (not wordlists) to their default values. Sets + * Outputfile to stdout. + * + */ + +static void ResetSettings(void) +{ + +#define DEF(type, name, value) name = value; + OPTION_DEFAULTS; +#undef DEF + if (OutputFile != stdout) + { + fclose(OutputFile); + OutputFile = stdout; + } +} + +/* + * Reads a numerical argument from the argument. Supports concatenation + * of arguments (main purpose) + */ + +static int ParseNumArg(long *Dest, /* Where to put the value */ + long Default, /* Value to put in if no in argue */ + char **Argument) /* optarg or similar */ +{ + if (Argument && *Argument && isdigit((unsigned char)**Argument)) + *Dest = strtol(*Argument, Argument, 10); + else + *Dest = Default; + + return (ShiftArg(Argument)); +} + +/* + * Same as above; however, will toggle the boolean if user doesn't + * supply value + */ + +static int ParseBoolArg(int *Dest, /* Boolean value */ + char **Argument) /* optarg or similar */ +{ + long D = *Dest ? 1L : 0L; + int Retval; + + Retval = ParseNumArg(&D, *Dest ? 0L : 1L, Argument); + + *Dest = D ? TRUE : FALSE; + + return (Retval); +} + +/* + * Returns the first character in the string passed, updates the + * string pointer, if the string is non-empty. + * + * 0 if the string is empty. + */ + +static int ShiftArg(char **Argument) /* optarg or similar */ +{ + if (Argument && *Argument && **Argument) + return (*((char *) (*Argument)++)); + else + return 0; +} + +/* + * Parses an argv similar array. + */ + +static int ParseArgs(int argc, char **argv) +{ + /* Needed for option parsing. */ + + static const struct option long_options[] = { + {"help", no_argument, 0L, 'h'}, + {"localrc", required_argument, 0L, 'l'}, + {"output", required_argument, 0L, 'o'}, + {"warnon", required_argument, 0L, 'w'}, + {"erroron", required_argument, 0L, 'e'}, + {"msgon", required_argument, 0L, 'm'}, + {"nowarn", required_argument, 0L, 'n'}, + {"nolinesupp", no_argument, 0L, 'L'}, + {"verbosity", optional_argument, 0L, 'v'}, + {"pipeverb", optional_argument, 0L, 'V'}, + {"debug", required_argument, 0L, 'd'}, + {"reset", no_argument, 0L, 'r'}, + {"quiet", no_argument, 0L, 'q'}, + {"license", no_argument, 0L, 'i'}, + {"splitchar", required_argument, 0L, 's'}, + {"format", required_argument, 0L, 'f'}, + {"pseudoname", required_argument, 0L, 'p'}, + + {"inputfiles", optional_argument, 0L, 'I'}, + {"backup", optional_argument, 0L, 'b'}, + {"globalrc", optional_argument, 0L, 'g'}, + {"wipeverb", optional_argument, 0L, 'x'}, + {"tictoc", optional_argument, 0L, 't'}, + {"headererr", optional_argument, 0L, 'H'}, + {"version", no_argument, 0L, 'W'}, + + {0L, 0L, 0L, 0L} + }; + + int option_index = 0L, c, i, nextc, ErrType; + + int Retval = FALSE, InUse; + int Success, Foo; + long Err, Verb = 1, PipeVerb = 1; + + enum + { + aeNoErr = 0, + aeArg, /* missing/bad required argument */ + aeOpt, /* unknown option returned */ + aeHelp, /* just a call for help */ + aeMem /* no memory */ + } ArgErr = aeNoErr; + + optind = 0; + + while (!ArgErr && + ((c = getopt_long((int) argc, argv, + "b::d:e:f:g::hH::I::il:m:n:Lo:p:qrs:t::v::V::w:Wx::", + long_options, &option_index)) != EOF)) + { + while (c) + { + nextc = 0; + switch (c) + { + case 's': + if (!(Delimit = strdup(optarg))) + { + PrintPrgErr(pmStrDupErr); + ArgErr = aeMem; + } + + break; + case 'p': + if (!(PseudoInName = strdup(optarg))) + { + PrintPrgErr(pmStrDupErr); + ArgErr = aeMem; + } + + break; + + case 'd': +#ifdef STRIP_DEBUG + + PrintPrgErr(pmNoDebugFlag); +#else + + nextc = ParseNumArg(&DebugLevel, 0xffff, &optarg); +#endif + + break; + case 'i': + LicenseOnly = TRUE; + + nextc = ShiftArg(&optarg); + break; + case 'L': + NoLineSupp = TRUE; + + nextc = ShiftArg(&optarg); + break; + case 'q': + Quiet = TRUE; + + nextc = ShiftArg(&optarg); + break; + + LOOP(warntype, case 'w': + ErrType = etWarn; InUse = iuOK; LAST(warntype); case 'e': + ErrType = etErr; InUse = iuOK; LAST(warntype); case 'm': + ErrType = etMsg; InUse = iuOK; LAST(warntype); case 'n': + ErrType = etMsg; InUse = iuNotUser; LAST(warntype);) if (isdigit((unsigned char)*optarg)) + { + nextc = ParseNumArg(&Err, -1, &optarg); + if (betw(emMinFault, Err, emMaxFault)) + { + LaTeXMsgs[Err].Type = ErrType; + LaTeXMsgs[Err].InUse = InUse; + } + else + { + ArgErr = aeOpt; + PrintPrgErr(pmWarnNumErr); + } + } + else if (!strcasecmp(optarg, "all")) + { + for (i = emMinFault + 1; i < emMaxFault; i++) + { + LaTeXMsgs[i].Type = ErrType; + LaTeXMsgs[i].InUse = InUse; + } + } + else + { + ArgErr = aeOpt; + PrintPrgErr(pmWarnNumErr); + } + + break; + + case 'g': + nextc = ParseBoolArg(&GlobalRC, &optarg); + if (!GlobalRC) + { + ResetStacks(); + } + break; + + case 'r': + ResetSettings(); + nextc = ShiftArg(&optarg); + break; + + case 'l': + if (optarg) + ReadRC(optarg); + break; + + case 'f': + if (!(OutputFormat = strdup(optarg))) + { + PrintPrgErr(pmStrDupErr); + ArgErr = aeMem; + } + break; + + case 'v': + nextc = ParseNumArg(&Verb, 2, &optarg); + + if (Verb < (long) OutFormat.Stack.Used) + OutputFormat = strdup(OutFormat.Stack.Data[Verb]); + else + { + PrintPrgErr(pmVerbLevErr); + ArgErr = aeArg; + } + break; + case 'V': + nextc = ParseNumArg(&PipeVerb, 1, &optarg); + + if (PipeVerb < (long) OutFormat.Stack.Used) + PipeOutputFormat = strdup(OutFormat.Stack.Data[PipeVerb]); + else + { + PrintPrgErr(pmVerbLevErr); + ArgErr = aeArg; + } + break; + + case 'o': + if (optarg) + { + if (*OutputName) + { + PrintPrgErr(pmOutTwice); + ArgErr = aeOpt; + } + else + { + if (!(OutputName = strdup(optarg))) + { + PrintPrgErr(pmStrDupErr); + ArgErr = aeMem; + } + } + } + + break; + + case 't': + nextc = ParseBoolArg(&Foo, &optarg); + break; + case 'x': + nextc = ParseBoolArg(&WipeVerb, &optarg); + break; + case 'b': + nextc = ParseBoolArg(&BackupOut, &optarg); + break; + case 'I': + nextc = ParseBoolArg(&InputFiles, &optarg); + break; + case 'H': + nextc = ParseBoolArg(&HeadErrOut, &optarg); + break; + case 'W': + printf("%s", Banner); + exit(EXIT_SUCCESS); + case '?': + default: + fputs(Banner, stderr); + fputs(HowHelp, stderr); + exit(EXIT_FAILURE); + break; + case 'h': + ArgErr = aeHelp; + break; + } + c = nextc; + } + } + + if ((argc > optind) && !strcmp(argv[optind], "?")) + ArgErr = aeHelp; + + if (ArgErr) + { + fputs(Banner, stderr); + fputs(BigBanner, stderr); + fputs(HelpText, stderr); + Success = FALSE; + } + else + Success = TRUE; + + if (Success) + Retval = optind; + + return (Retval); +} + +/* + * Outputs a program error. + */ + + +void PrintPrgErr(enum PrgErrNum Error, ...) +{ + const char *Type; + va_list MsgArgs; + + if (betw(pmMinFault, Error, pmMaxFault)) + { + switch (PrgMsgs[Error].Type) + { + case etWarn: + Type = "WARNING"; + break; + case etMsg: + Type = "NOTE"; + break; + default: + case etErr: + Type = "ERROR"; + break; + } + fprintf(stderr, "%s: %s -- ", PrgName, Type); + + va_start(MsgArgs, Error); + vfprintf(stderr, PrgMsgs[Error].Message, MsgArgs); + va_end(MsgArgs); + fputc('\n', stderr); + + if (PrgMsgs[Error].Type == etErr) + exit(EXIT_FAILURE); + } +} + +void ErrPrintf(const char *fmt, ...) +{ + va_list MsgArgs; + + va_start(MsgArgs, fmt); + vfprintf(stderr, fmt, MsgArgs); + va_end(MsgArgs); +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.h b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.h new file mode 100644 index 00000000000..eaca3227436 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.h @@ -0,0 +1,340 @@ +/* + * ChkTeX, header file for main program. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#ifndef CHKTEX_H +#define CHKTEX_H 1 +#if defined(HAVE_CONFIG_H) || defined(CONFIG_H_NAME) +# ifndef CONFIG_H_NAME +# define CONFIG_H_NAME "config.h" +# endif +# ifndef HAVE_CONFIG_H +# define HAVE_CONFIG_H 1 +# endif +# include CONFIG_H_NAME +#endif + +#ifdef KPATHSEA +#include +#include +#endif + +#include +#include +#include + +#ifdef HAVE_STDARG_H +# include +#else +#error Sorry, ChkTeX needs an _ANSI_ compiler w/stdarg.h installed to compile. +#endif + +#ifndef HAVE_VPRINTF +#error Sorry, ChkTeX needs an _ANSI_ compiler w/vprintf() to compile. +#endif + +#include +#include +#include + +#ifdef HAVE_UNISTD_H +# include +#endif + +#ifdef HAVE_LIMITS_H +# include +#endif + +#ifdef HAVE_STRINGS_H +# include +#endif + +#include "types.h" + +#ifndef LONG_MAX +# define LONG_MAX (0x7fffffff) +#endif + +#ifndef CHAR_BIT +# define CHAR_BIT (8) +#endif + +#include "FindErrs.h" + +#if defined(HAVE_FILENO) && defined(HAVE_ISATTY) +# include +#endif + +/* + * Define aliases for preprocessor statements + */ + +#if defined(__unix__) || defined(__unix) || defined(unix) +#undef __unix__ +#define __unix__ 1 +#elif defined(MSDOS) || defined(__MSDOS__) || defined(__msdos__) +#undef __MSDOS__ +#define __MSDOS__ 1 +#endif + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * NOTE: All macros below should return FALSE (0) if the input + * character is 0. + * + * The next macro should return TRUE if LaTeX (and you?) considers + * the character `c' as a space, which should be detected when + * we're checking whether commands are terminated by spaces. + * + * Note: If you wish to change this macro, you'll have to update + * the main loop in FindErrs.c as well. + */ + +#define LATEX_SPACE(c) (c > 0 && c <= ' ') + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + + + + + + +#define betw(a,b,c) ((a < b) && (b < c)) +#define within(a,b,c) ((a <= b) && (b <= c)) + +#ifndef min +# define min(a,b) ((a)<=(b)?(a):(b)) +#endif + +#ifndef max +# define max(a,b) ((a)>(b)?(a):(b)) +#endif + +#ifndef abs +# define abs(a) (a>=0?a:(-a)) +#endif + +#define LOOP(name, body) {{body} _end__##name:;} +#define LAST(name) goto _end__##name + +#define NUMBRACKETS 6 + +#define NEWBUF(name,len) \ +static char _ ## name [len + (WALLBYTES<<1)] = {0}; \ +char *name = &_ ## name[WALLBYTES] + +#define INTFAULTMSG "INTERNAL FAULT OCCURED! PLEASE SUBMIT A BUG REPORT!\n" + +#define INTERNFAULT INTFAULTMSG + +#define BITDEF1(a) BIT_ ## a +#define BITDEF2(a) FLG_ ## a = (1<'.")\ + MSG(pmNoTermData, etErr, TRUE, 0,\ + "Could not access the termcap data base.")\ + MSG(pmNoTermDefd, etErr, TRUE, 0,\ + "Terminal type `%s' is not defined.")\ + MSG(pmNoRegExp, etWarn, TRUE, 0,\ + "Regular expressions not compiled in. Please recompile.")\ + MSG(pmNoCommon, etErr, TRUE, 0,\ + "`%s' can't be a member of both `%s' and `%s'.") \ + MSG(pmNoOpenDir, etWarn, TRUE, 0, \ + "Could not open the directory `%s'.") \ + MSG(pmNoDebugFlag, etWarn, TRUE, 0, \ + "This version of doesn't support the -d flag. Please recompile.")\ + MSG(pmNoRegexMem, etErr, TRUE, 0,\ + "Unable to allocate regular expressions - no memory?\n")\ + MSG(pmRegexCompileFailed, etWarn, TRUE, 0,\ + "Compilation of regular expression %s failed with error %s.\n")\ + MSG(pmRegexMatchingError, etErr, TRUE, 0,\ + "PCRE matching error %d.\n") \ + MSG(pmSuppTooHigh, etWarn, TRUE, 0,\ + "Warning %d is numbered too high (max %d) and won't be suppressed.\n") \ +MSG(pmLongLines, etWarn, TRUE, 0,\ + "ChkTeX does not handle lines over %d bytes correctly. Some errors and line numbers may be wrong in this file.") + +#undef MSG +#define MSG(num, type, inuse, ctxt, text) num, +enum PrgErrNum +{ + PRGMSGS pmMaxFault +}; +#undef MSG + +extern struct ErrMsg PrgMsgs[pmMaxFault + 1]; + +struct ErrInfo +{ + char *Data; + const char *LineBuf; + const char *File; + unsigned long Line, Column, ErrLen; + enum + { + efNone = 0x00, + efNoItal = 0x01, + efItal = 0x02, + efNoMath = 0x04, + efMath = 0x08 + } Flags; +}; + +extern char *ReadBuffer; +extern char *CmdBuffer; +extern char *TmpBuffer; + +extern const char BrOrder[NUMBRACKETS + 1]; + +extern unsigned long Brackets[NUMBRACKETS]; + + +extern FILE *OutputFile, *InputFile; + +#define OPTION_DEFAULTS \ + DEF(int, GlobalRC, TRUE) \ + DEF(int, WipeVerb, TRUE) \ + DEF(int, BackupOut, TRUE) \ + DEF(int, Quiet, FALSE) \ + DEF(int, LicenseOnly, FALSE) \ + DEF(int, UsingStdIn, FALSE) \ + DEF(int, InputFiles, TRUE) \ + DEF(int, HeadErrOut, TRUE) \ + DEF(const char *, OutputName, "") \ + DEF(const char *, PseudoInName, NULL) \ + DEF(char *, OutputFormat, VerbNormal) \ + DEF(char *, PipeOutputFormat, NULL) \ + DEF(const char *, Delimit, ":") \ + DEF(long, DebugLevel, 0) \ + DEF(int, NoLineSupp, FALSE) + +#define STATE_VARS \ + DEF(enum ItState, ItState, itOff) /* Are we doing italics? */ \ + DEF(int, AtLetter, FALSE) /* Whether `@' is a letter or not. */ \ + DEF(int, InHeader, TRUE) /* Whether we're in the header */ \ + DEF(int, VerbMode, FALSE) /* Whether we're in complete ignore-mode */ \ + DEF(long, MathMode, 0) /* Whether we're in math mode or not */ \ + DEF(const char *, VerbStr, "") /* String we'll terminate verbmode upon */ \ + DEF(unsigned long, ErrPrint, 0) /* # errors printed */ \ + DEF(unsigned long, WarnPrint, 0) /* # warnings printed */ \ + DEF(unsigned long, UserSupp, 0) /* # user suppressed warnings */ \ + DEF(unsigned long, LineSupp, 0) /* # warnings suppressed on a single line */ \ + DEF(unsigned long long, FileSuppressions, 0) /* # warnings suppressed in a file */ \ + DEF(unsigned long long, UserFileSuppressions, 0) /* # User warnings suppressed in a file */ + +#define DEF(type, name, value) extern type name; +OPTION_DEFAULTS STATE_VARS +#undef DEF +extern struct Stack CharStack, InputStack, EnvStack; + +enum Quote +{ + quLogic, + quTrad +}; + +extern enum Quote Quote; +extern int StdInTTY, StdOutTTY, UsingStdIn; + +int main(int argc, char **argv); +void PrintPrgErr(enum PrgErrNum, ...); +void ErrPrintf(const char *fmt, ...); + +extern char *PrgName; + +#endif /* CHKTEX_H */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.pdf b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.pdf new file mode 100644 index 00000000000..4bebc93ed6f Binary files /dev/null and b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.pdf differ diff --git a/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.tex.in b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.tex.in new file mode 100644 index 00000000000..5ec07632ad9 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.tex.in @@ -0,0 +1,1836 @@ +%% +%% ChkTeX v@PACKAGE_VERSION@, LaTeX documentation for ChkTeX program. +%% Copyright (C) 1995-96 Jens T. Berger Thielemann +%% +%% This program is free software; you can redistribute it and/or modify +%% it under the terms of the GNU General Public License as published by +%% the Free Software Foundation; either version 2 of the License, or +%% (at your option) any later version. +%% +%% This program is distributed in the hope that it will be useful, +%% but WITHOUT ANY WARRANTY; without even the implied warranty of +%% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +%% GNU General Public License for more details. +%% +%% You should have received a copy of the GNU General Public License +%% along with this program; if not, write to the Free Software +%% Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +%% +%% Contact the author at: +%% Jens Berger +%% Spektrumvn. 4 +%% N-0666 Oslo +%% Norway +%% E-mail: +%% +%% NOTE: This file is written in LaTeX, and should be compiled +%% before viewing. If you don't know how to do this, consult +%% your local TeX guru. If you don't possess LaTeX, you are +%% assumed to not need this program; so there's no text version +%% of this file... +%% +%% You may still be able to view the DVI or PostScript versions of +%% this file, though, they are included in the archive. +%% + + + +\documentclass[a4paper]{article} +%latex +\usepackage{array, tabularx, verbatim, multicol} +\usepackage[T1]{fontenc} +\nonfrenchspacing +\newcounter{errornum} +\setcounter{errornum}{1} +%endlatex +\newcommand{\jtbt}{Jens~T. Berger~Thielemann} +\newcommand{\Cmd}[1]{``\texttt{#1}''} +\newcommand{\rsrc}{``\texttt{chktexrc}''} +\newcommand{\chktex}{Chk\TeX} + +%latex +\newcolumntype{Y}{>{\raggedright\arraybackslash}X} +\newcommand{\fmted}[1]{% + {\noindent\large% + \begin{tabularx}{\linewidth}{lY}% + \bf Warning \theerrornum: & \texttt{#1}% + \end{tabularx}}\stepcounter{errornum}\nopagebreak[4]} + +\newenvironment{errdesc}[1]{\noindent\fmted{#1}\begin{quote}}{\end{quote}% +\pagebreak[3]} + +\newenvironment{html}{\comment}{\endcomment} +\newenvironment{rawhtml}{\comment}{\endcomment} + +\makeatletter +\@namedef{errdesc*}#1{\begin{errdesc}{\textit{#1}}} +\@namedef{enderrdesc*}{\end{errdesc}} +\makeatother + + +\newenvironment{errexam} +{ +\vskip 0pt plus 5pt +\begin{center} +} +{\end{center}} +\columnseprule 0.1pt + +%!\newcommand{\BS}{\verb@\@} +%!\newcommand{\chktex}{ChkTeX} +%!\newcommand{\slash}{/} +%endlatex + + +\title{\chktex\ v@PACKAGE_VERSION@} +\author{Jens~T. Berger~Thielemann} +\date{\today} + + +\begin{document} +\maketitle + +%latex +\newcommand{\BS}{\char`\\} +%endlatex +\section{Introduction} + +This program has been written in frustration because some constructs in +\LaTeX\ are sometimes non-intuitive, and easy to forget. It is +\emph{not} a replacement for the built-in checker in \LaTeX\@; however it +catches some typographic errors \LaTeX\ oversees. In other words, it +is Lint for \LaTeX. Filters are also provided for checking the +\LaTeX\ parts of CWEB documents. + +It is written in ANSI C and compiles silently under GCC using +\Cmd{-Wall -ansi -pedantic} and almost all warning flags. This means +that you can compile \& use the program on your favorite machine. +Full source included. + +The program also supports output formats suitable for further +processing by editors or other programs, making errors easy to cycle through. +Software is provided for beautifully interfacing with the +AUC\TeX\ Emacs mode. + +The program itself does not have any machine requirements; However compiling +for other platforms has not been done for a long time now so the code has been +removed. If interest rises it can be resurrected. + + +\section{Features} +\chktex\ begins to get quite a few bells \& whistles now. However, you +should be aware of that in most cases, all this is transparent to the user. +As you will see, \chktex\ offers the ability to adapt to many environments +and configurations. + +\begin{itemize} +\item Supports over 40 warnings. Warnings include: +%latex + \begin{multicols}{2} + \begin{flushleft} +%endlatex + \begin{itemize} + \item Commands terminated with space. Ignores \Cmd{\BS{}tt}, etc. + \item Space in front of references instead of \Cmd{\~{}}. + \item Forgetting to group parenthesis characters when + sub-\slash{}super\-scripting. + \item Italic correction (\Cmd{\BS/}) mistakes (double, + missing, unnecessary). + \item Parenthesis and environment matching. + \item Ellipsis detection; also checks whether to use + \Cmd{\BS{}dots}, \Cmd{\BS{}cdots} or \Cmd{\BS{}ldots}. + \item Enforcement of normal space after abbreviation. Detects + most abbreviations automagically. + \item Enforcement of end-of-sentence space when the last + sentence ended with capital letter. + \item Math-mode on/off detection. + \item Quote checking, both wrong types (\Cmd{"}) and wrong + direction. + \item Recommends splitting three quotes in a row. + \item Searching for user patterns. + \item Displays comments. + \item Space in front of \Cmd{\BS{}label} and similar commands. + \item Use of \Cmd{x} instead of \Cmd{\$\BS{}times\$} between numbers. + \item Multiple spaces in input which will be rendered as one + space (or multiple spaces, where that is undesirable). + \item Warns about text which may be ignored. + \item Mathematical operators typeset as variables. + \item No space in front of/after parenthesis. + \item Demands a consistent quote style. + \item Punctuation inside inner math mode/outside display math + mode. + \item Use of \TeX\ primitives where \LaTeX\ equivalents are + available. + \item Space in front of footnotes. + \item Bogus characters following commands. + \item Ability to suppress warnings on a single line. + \end{itemize} +%latex + \end{flushleft} + \end{multicols} +%endlatex +\item Fully customizable. Intelligent resource format makes it + possible to make \chktex\ respect your \LaTeX\ setup. Even + command-line options may be specified globally in the \rsrc\ file. +\item Supports \Cmd{\BS{}input} command; both \TeX\ and \LaTeX\ version. + Actually includes the files. \Cmd{TEXINPUTS}-equivalent search path. +\item Intelligent warning/error handling. The user may promote/mute + warnings to suit his preferences. You may also mute warnings in the + header of a file; thus killing much unwanted garbage. +\item Scripts included for checking CWEB files written in \LaTeX. + (Requires perl v5). +\item Supports both \LaTeX\ 2.09 and \LaTeXe{}. +\item Flexible output handling. Has some predefined formats and lets + the user specify his own format. Uses a \Cmd{printf()} similar + syntax. \Cmd{lacheck} compatible mode included for interfacing with + the AUC\TeX\ Emacs mode. +\item Written in ANSI C\@. \Cmd{configure} script included for easy + setup and installation on UNIX systems. +\end{itemize} + +Still, it is important to realize that the output from \chktex\ is +only intended as a \emph{guide} to fixing faults. However, it is by +no means always correct. This means that correct \LaTeX\ code may +produce errors in \chktex, and vice versa: Incorrect \LaTeX\ code may pass +silently through. + + + +\section{Legal stuff} + +\chktex{}, documentation, installations scripts, CWEB filters and other +materials provided are copyright \copyright\ 1995--96 Jens~T. +Berger~Thielemann, unless explicitly stated otherwise. + +This program is free software; you can redistribute it and/or modify it +under the terms of the GNU General Public License as published by the Free +Software Foundation; either version 2 of the License, or (at your option) +any later version. + +This program is distributed in the hope that it will be useful, but WITHOUT +ANY WARRANTY\@; without even the implied warranty of MERCHANTABILITY or +FITNESS FOR A PARTICULAR PURPOSE\@. See the GNU General Public License for +more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to: +\begin{quote} + The Free Software Foundation, Inc. \\ + 51 Franklin Street \\ + Fifth Floor \\ + Boston \\ + MA 02110-1301 \\ + USA +\end{quote} + + +\section{Availability} + +This program is on CTAN\@; thus it can be found at any mirrors of those. +It is also part of TeX Live 2011. + +\section{Installation} + +A few words on installation on various platforms: + +\begin{description} +\item[UNIX:] Type \Cmd{configure}, \Cmd{make} and finally + \Cmd{make~install}. To make sure everything proceeded correctly, + type \Cmd{make~check}. If you don't have superuser privileges and thus + access to the default system areas, you should type + \Cmd{configure~-{}-help} to help you set up correct paths. + + If you haven't installed any software like this before, that is + distributed in source form, here are some guidelines to help you + install it locally at your account. Please note that a mail to the + system administrator may be less work for you. + + We assume that you have put the archive (\Cmd{chktex.tar.gz}) in a + subdir of yours, with path \Cmd{\~{}/tmp}. We further assume that + your shell is \Cmd{csh} or \Cmd{tcsh}. Do the following: + + \begin{enumerate} + \item First of all, unpack the archive contents. + +\begin{verbatim} +> cd ~/tmp +> gunzip chktex.tar.gz +> tar xf chktex.tar +\end{verbatim} + + \item Now, we can configure the program. There are some + configuration options you should know about: + \begin{description} + \item[\Cmd{-{}-enable-pcre}:] Allows using PCRE (perl compatible + regular expressions) for use defined warnings. The default is + to use PCRE if it is installed on your system as determined by + \Cmd{pcre-config}. You can use \Cmd{-{}-disable-pcre} if you + plan to distribute this for systems in which you cannot ensure + PCRE will be installed. + + User defined regular expressions are defined using + \texttt{UserWarnRegex} in the \rsrc\ file. See warning~44 for + more information. + + \item[\Cmd{-{}-enable-emacs-hack}:] Install a small file which + adds \chktex\ to the command menu of AUC\TeX. This is to be + considered as a hack, and may break in future versions of + AUC\TeX. It works fine under AUC\TeX\ v2.9, though. + + This option needs the path of your elisp directory as argument, + e.g. \Cmd{-{}-enable-emacs-hack=/home/myself/elisp} or similar. + + You'll also have to add the following line to your \Cmd{.emacs} + file: +\begin{verbatim} +(require 'chktex) +\end{verbatim} + You can now access \chktex\ from the \Cmd{Command} menu in + AUC\TeX. To cycle through the messages, type \verb#C-x `#. + + \item[\Cmd{-{}-enable-lacheck-replace}] This enables a quick + hack for making the AUC\TeX\ Emacs mode use \chktex\ instead of + lacheck. This is done by installing a stub script which + ``overrides'' the original lacheck executable. + + While more stable than the previous solution, this is also + significantly less elegant --- in computing terms, this is the + ``brute force'' approach. + + \item[\Cmd{-{}-enable-debug-info}] \chktex\ has an ability to spit + out various diagnostic messages using the \Cmd{-d} flag. This + behaviour is on by default. By adding the flag + \Cmd{-{}-disable-debug-info} to the commandline, this will not be + compiled in. + + This may be useful if you're running short of disk space (the + time savings are neglible). + \end{description} + + If you are installing the program on your local account, use the + following command: + +\begin{verbatim} +> configure --prefix ~/ +\end{verbatim} + + Add eventual extra flags as specified above. This command will + generate a significant amount of output, this can usually be ignored. + + \item Finally, we can just build the program and install it. + +\begin{verbatim} +> make +> make install +\end{verbatim} + + \item Finished! The program is now installed and ready to use. You + may now tell other people to put your bindir in their path in + order to benefit from your work. All that remains is to make the + shell aware of your installation. + +\begin{verbatim} +> rehash +\end{verbatim} + + To make the remaining parts of your system aware of this, you'll + have to log out and re-log in, I'm afraid. However, you should delay this + until you've completed this installation procedure. + + \item If you wish to make sure that everything is OK (you ought to), + you may now ask \chktex\ to do a self-test: + +\begin{verbatim} +> make check +\end{verbatim} + + \end{enumerate} + +\item[Other platforms:] First of all, you have to copy the + \Cmd{config.h.in} file to a file named \Cmd{config.h}. Then, edit + it to reflect your system. Do the same with \Cmd{OpSys.h} (this + file has been reduced significantly). If you wish, you may define + \Cmd{DATADIR} to the path you want the global resource file to be + put. + + Now, I would suggest that you take a peak at the \Cmd{OpSys.c} + file, and edit it appropiately, for more + comfort. This should not be necessary, though, at least not the + first time. + + Finally, you may now compile and link all \verb@.c@ files. Do not + forget to define \Cmd{HAVE\_CONFIG\_H} to 1 (on the command-line, + for instance). If the \Cmd{config.h} you wish to use has another + name, define \Cmd{CONFIG\_H\_NAME} to that (in that case, don't + define \Cmd{HAVE\_CONFIG\_H}). + + Put the directory path of the \rsrc\ file in a environment variable + named \Cmd{CHKTEXRC}. The files \Cmd{deweb.in} and \Cmd{chkweb} + should be moved to a directory in your path. These files may need + further setup, as they haven't got the location of perl + initialized. + + If your compiler/the compiled program complains (or crashes!), you + may try the hints listed below. Please note that it only makes + sense to try these hints if your compiler fails to produce a working + program. + + \begin{enumerate} + \item Increase the preprocessor buffers and line buffers. The + \chktex{} sources define macros sized 3--4k (expanding to about + the same), and passes arguments sized about 1k. + \item Use the magic switch which lets us use large + \Cmd{switch(\dots)\{\dots\}} statements; some of these statements + have about 120 \Cmd{case} entries. + \item The sources require that at least the first 12 of each + identifier is significant. + \end{enumerate} +\end{description} +\paragraph{Note:} You \emph{must} install the new \rsrc\ file; \chktex\ will +fail to function otherwise! + + After doing this, you may enhance \chktex' behaviour by +reading/editing the \rsrc\ file. + +%latex +\section{Usage} + +\subsection{\chktex} + +\subsubsection{Synopsis} + +A UNIX-compliant template format follows: + +\newcommand{\Group}[1]{\mbox{[#1]}} +\begin{tabularx}{.95\linewidth}{lY} + \texttt{chktex} & \ttfamily \Group{-hiqrW} \Group{-v[0-\dots]} \Group{-l + } \Group{-[wemn] <[1-42]|all>} \Group{-d[0-\ldots]} \Group{-p + } \Group{-o } \Group{-[btxgI][0|1]} + file1 file2 \dots +\end{tabularx} + + +\subsubsection{Options} + +These are the options \chktex\ currently accepts. +Please note that single-lettered options requiring a numerical or no +argument may be concatenated. E.g.\ saying \Cmd{-v0qb0w2} is the +same as saying \Cmd{-v0~-q~-b0~-w2}, except for being less to +type. + +Enough general talk; here's a rather detailed description of all +options: +\begin{description} +\item[Misc.\ options:] General options which aren't related to some + specific subpart of \chktex. + \begin{description} + \item[\texttt{-h [-{}-help]}] Gives you a command summary. + \item[\texttt{-i [-{}-license]}] Shows distribution information. + \item[\texttt{-l [-{}-localrc]}] Reads a resource-file formatted + as the global resource-file \rsrc, in addition to the global + resource-file. This option needs the name of the resource-file + as a parameter. See also \texttt{-g}. + \item[\texttt{-r [-{}-reset]}] This will reset all settings to their + defaults. This may be useful if you use the \texttt{CMDLINE} + directive in your \rsrc\ file, and wish to do something + unusual. + \item[\texttt{-d [-{}-debug]}] Needs a numeric argument; a bitmask + telling what to output. The values below may be added in order + to output multiple debugging info. + + \begin{tabularx}\linewidth{cX} + \bf Value & \bf Dumps\ldots\\ + 1 & All warnings available and their current status. \\ + 2 & Statistics for all lists in the resource file. \\ + 4 & The contents of all lists in the resource file. \\ + 8 & Misc.\ other status information. \\ + 16 & Run-time info (note that this isn't widely used). \\ + \end{tabularx} + The info is produced after all switches and resource files have + been processed. + + It is possible to install versions of \chktex\ that ignore this + flag; this means that it is not certain that this flag works. + \item[\texttt{-W [-{}-version]}] Displays version information, and exits. + \end{description} +\item[Muting warning messages:] Controls whether and in what form + error messages will appear. Usually they accept a specific warning + number (e.g.\ \Cmd{-w2}), but you may also say \Cmd{all} (e.g.\ + \Cmd{-wall}) which does the operation on \emph{all} warnings. + \begin{description} + \item[\texttt{-w [-{}-warnon]}] Makes the message number passed as + parameter a warning and turns it on. + \item[\texttt{-e [-{}-erroron]}] Makes the message number passed as + parameter an error and turns it on. + \item[\texttt{-m [-{}-msgon]}] Makes the message number passed as + parameter a message and turns it on. Messages are not counted. + \item[\texttt{-n [-{}-nowarn]}] Turns the warning/error number passed + as a parameter off. + \item[\texttt{-L [-{}-nolinesupp]}] Turns off suppression of messages + on a per line basis. This is meant to be used to ensure that no new + errors have crept into a document while editing. + \end{description} +\item[Output control flags:] Determines the appearance and + destination of the error reports. + \begin{description} + \item[\texttt{-q [-{}-quiet]}] Shuts up about copyright information. + \item[\texttt{-o [-{}-output]}] Normally, all errors are piped to \texttt{stdout}. + Using this option with a parameter, errors will be sent to the + named file instead. Only information relative to the \LaTeX\ file + will be sent to that file. Memory problems and similar will as as + always be sent to \texttt{stderr}. If a file with the name given + already exists, it will be renamed to \Cmd{foobar.bak} + (\Cmd{foobar.\$cl} under MS-DOS), \Cmd{foobar} being the name of + the file. See also \Cmd{-b}. + + \item[\texttt{-v [-{}-verbosity]}] Specifies how much and how you + wish the error reports to be displayed. This is specified in the + \rsrc\ file; we'll list the default values below. If you wish, + you may thus edit the \rsrc\ file to add or modify new formats. + + The default is mode 1 (that is, the \emph{second} entry in the + \rsrc\ file), using \texttt{-v} without any parameter will give you + mode 2. + + \begin{description} + \item[0] Will show the information in a way that should be + suitable for further parsing by \texttt{awk}, \texttt{sed} or + similar. The format is as follows: +\begin{verbatim} +File:Line:Column:Warning number:Warning message +\end{verbatim} + The colons may be replaced with another string; use the + \verb@-s@ switch for this. + + As the program does not output all errors in quite order, this + output format is also suitable for piping through \Cmd{sort}. + \item[1] Shows the information in a way which is more + comprehensible for humans, but which still doesn't need + anything but a glass tty. + \item[2] Shows the information in a fancy way, using escape + codes and stuff. It is the indeed most readable of all + modes; however, it needs proper set up of the \Cmd{ChkTeX.h} + at compilation time. UNIX boxes, however, will find the + information automatically. + \item[3] Shows the information suitable for parsing by Emacs; + this is the same format as \texttt{lacheck} uses. More formally, + it is the following: +\begin{verbatim} +"File", line Line: Warning message +\end{verbatim} + + To utilize this, type \verb@M-x compile RET@. Delete whatever + is written in the minibuffer, and type + \verb@chktex -v3 texfile.tex@, and you should be able to + browse through the + error messages. Use \verb@C-x `@ to parse the messages. + \item[4] More or less the same as \verb@-v3@, but also includes + information on where the error actually was found. Takes somewhat + longer time to parse, but much more informative in use. + \end{description} + + \item[\texttt{-f [-{}-format]}] Specifies the format of the output. + This is done using a format similar to \Cmd{printf()}, where we + support the specifiers listed below. + + \smallskip + \newcommand{\Pf}[1]{\texttt{\%#1} &} + \begin{tabularx}{\linewidth}{cX} + \bf Code & \bf Description \\ + \Pf{b} String to print \textbf{b}etween fields (from \texttt{-s} + option).\\ + \Pf{c} \textbf{C}olumn position of error. \\ + \Pf{d} Length of error (\textbf{d}igit). \\ + \Pf{f} Current \textbf{f}ilename.\\ + \Pf{i} Turn on \textbf{i}nverse printing mode.\\ + \Pf{I} Turn off \textbf{i}nverse printing mode.\\ + \Pf{k} \textbf{k}ind of error (warning, error, message).\\ + \Pf{l} \textbf{l}ine number of error.\\ + \Pf{m} Warning \textbf{m}essage.\\ + \Pf{n} Warning \textbf{n}umber.\\ + \Pf{u} An \textbf{u}nderlining line (like the one which + appears when using \Cmd{-v1}).\\ + \Pf{r} Part of line in front of error ($\mbox{`S'} - + 1$).\\ + \Pf{s} Part of line which contains error (\textbf{s}tring).\\ + \Pf{t} Part of line after error ($\mbox{`S'} + 1$). + \end{tabularx} + \smallskip + + Other characters will be passed literally; thus you can say + \Cmd{\%\%} to achieve a single percent sign in the output. + Please note that we may introduce other specifiers in the future, + so don't abuse this feature for other characters. + + Also, note that we do \emph{not} support field lengths (yet). + This may come in the future, if I get the time\dots + + The \texttt{-v} command is implemented by indexing into the \rsrc\ + file; read that for seeing how each format is implemented. If + you find yourself using a particular format often by using the + -f switch, consider putting it in the \rsrc\ file instead. + \item[\texttt{-V [-{}-pipeverb]}] Which entry we'll use in the \rsrc\ + file whenever \texttt{stdout} isn't a terminal. + + The default is to use the same mode as specified with the + \texttt{-v} switch; using \texttt{-V} without any parameter will give you + mode 1. + + This switch was implemented because GNU less has problems with + the escape codes \chktex\ uses for displaying inverse text. + Under UNIX, there's another way around, though, which is slightly + more elegant. Add the following line to your \Cmd{.envir} file: +\begin{verbatim} +setenv LESS -r +\end{verbatim} + + \item[\texttt{-p [-{}-pseudoname]}] With this switch, you can provide + the filename which will be used when we report the errors. This + may be useful in scripts, especially when doing pipes. It is in + other words similar to C's \verb@#line@ directive. + + We will only assume this name for the uppermost file; files that + this one in turn \verb@\@\verb@input@ are presented under their original + names. This seems most logical to me. + + \item[\texttt{-s [-{}-splitchar]}] String to use instead of the + colons when doing \texttt{-v0}; e.g.\ this string will be output + between the fields. + + \end{description} +\item[Boolean switches:] Common for all of these are that they + take an optional parameter. If it is \texttt{0}, the feature will + be disabled, if it is \texttt{1}, it will be enabled. All these + features are on by default; and are toggled if you don't give + any parameter. + + \begin{description} + \item[\texttt{-b [-{}-backup]}] If you use the \texttt{-o} switch, and the + named outputfile exists, it will be renamed to \texttt{filename.bak}. + \item[\texttt{-I [-{}-inputfiles]}] Execute \verb@\@\verb@input@ + statements; e.g.\ include the file in the input. Our input parsing + does of course nest; we use an input-stack to keep track of this. + \item[\texttt{-H [-{}-headererr]}] Show errors found in front of the + \verb@\begin{document}@ line. Some people keep \emph{lots} of + pure \TeX\ code there, which errors can't be detected reliably + (in other words, we will in most cases just produce a lot of + garbage). + \item[\texttt{-g [-{}-globalrc]}] Read in the global resource file. This + switch may be useful together with the \texttt{-l} option. + \item[\texttt{-t [-{}-tictoc]}] Display a twirling baton, to show that + we're working. \texttt{-v0} does an \texttt{-t0}, too, as it assumes + that the user then uses the program non-interactively. This is + now a no-op. + \item[\texttt{-x [-{}-wipeverb]}] Ignore the ``\verb@\verb@'' command + found within the \LaTeX\ file and its argument is completely by + the checking routines. This is done by simply overwriting them. + If you somehow don't like that (for instance, you would like to + count brackets inside those commands, too), use this switch. + \end{description} +\end{description} + + +If you don't specify any input \LaTeX-files on the commandline, we'll +read from \texttt{stdin}. To abort \texttt{stdin} input, press the +following keycombinations: + +\smallskip +\begin{tabular}{ll} + \bf Machine & \bf Key-combination \\ + UNIX & $\fbox{\texttt{Ctrl}} + \fbox{\texttt{D}}$ \\ + MS-DOS & $\fbox{\texttt{Ctrl}} + \fbox{Z}$, followed by return. +\end{tabular} +\smallskip + +By default, we use GNU's \Cmd{getopt()} routine. + +\begin{itemize} +\item Options may be given in any order; the names of the \LaTeX-files + do not have to be the last arguments. This behaviour may be turned + off by creating an environment variable named \Cmd{POSIXLY\_CORRECT}. +\item The special argument \Cmd{-{}-} forces an end of + option-scanning. +\item Long-named options begin with \Cmd{-{}-} instead of \Cmd{-}. + Their names may be abbreviated as long as the abbreviation is unique + or is an exact match for some defined option. If they have an + argument, it follows the option name in the argument, separated from + the option name by a \Cmd{=}, or else the in next argument. +\end{itemize} + +\subsubsection{The \rsrc\ file} + +You should also take a look at the \rsrc\ file. As it is +self-documenting, you should be able to get the meaning of each +keyword by simply reading the file. In fact, since not all options +are described in this documentation it is necessary that you read +the \rsrc\ file in order to understand them all. The method for +\emph{finding it} has grown rather complex. An outline is given below. + +If \chktex\ finds multiple files when searching, each and every one +will be read in the order specified below. The \Cmd{Keyword = \{ item + item \dots \}} may thus be necessary to reset previously defined +lists. + +In this list, \Cmd{\$foo} is assumed to be the environment variable +\Cmd{foo}: + +\begin{enumerate} +\item First, we'll take a look at the directory which was specified as + \Cmd{DATADIR} during compilation. On UNIX boxes, this usually + evaluates to something similar to + \Cmd{/usr/local/share/chktexrc}, under MS-DOS it is set + to \Cmd{\BS{}emtex\BS{}data\BS{}chktexrc}. + +\item Look in the following system directories: + + \begin{tabular}{ll} + \bf Machine & \bf Directory \\ + UNIX & \Cmd{\$HOME/.chktexrc} or \Cmd{\$LOGDIR/.chktexrc} \\ + MSDOS & Program installation path + \end{tabular} + +\item Look for it in the directory pointed to by an environment + variable, as specified in the table below: + + \begin{tabularx}\linewidth{lY} + \bf Machine & \bf Directory \\ + UNIX & \Cmd{\$CHKTEXRC/.chktexrc} \\ + MSDOS & \Cmd{\$CHKTEXRC\BS{}chktexrc}, \Cmd{\$CHKTEX\_HOME\BS + chktexrc} or \Cmd{\$EMTEXDIR\BS{}data\BS{}chktexrc} + \end{tabularx} + +\item Look for it in the current directory. On UNIX boxes, + we expect the filename to be \Cmd{.chktexrc}; on other machines + \Cmd{chktexrc}. + +\end{enumerate} + +If you for some reason wish to undo what the previous files may have +done, you may say \Cmd{CmdLine \{ -g0 -r \}} somewhere in the \rsrc\ +file; this will reset all previous settings. + +\subsubsection{Per Line and File Suppressions} + +There are many cases in which \chktex{} will give a warning about a +construct which, although it usually indicates a mistake, is +intentional. In these cases it can be extremely annoying to have +this message appear everytime \chktex{} is run. For this reason you +can use \LaTeX{} comments to suppress a certain message on a single +line. This can be done by adding a (case-insensitive) comment at the +end of the line of the form +\begin{center} + \verb+% checktex ##+ +\end{center} +where \verb+##+ is the number of the message to be suppressed. +For example the line +\begin{center} + \verb+$[0,\infty)$+\\* +\end{center} +will produce a warning (number 9) about mismatched \verb+]+ and \verb+)+. +However the lines +\begin{center} + \verb+$[0,\infty)$ % chktex 9+\\* + \verb+$[0,\infty)$ % ChkTeX 9+\\* +\end{center} +will not produce such a message. In this case, message number 17 will +still appear at the end, stating that the numbers of \verb+]+ and +\verb+)+ don't match for the entire file. + +To suppress two different errors on the same line you will need two +instances of \verb+chktex+ in the comment. This format is a little +cumbersome, but it shouldn't be needed often, and hopefully will help +avoid accidental suppressions. +\begin{center} + \verb+Jordan--H\"older on $[0,\infty)$ % chktex 8 chktex 9+\\* +\end{center} + +One problem inherent in line-by-line suppressions is that during editing +another error of the same type may creep into the same line. Therefore, +I suggest using the \texttt{-L} or \texttt{-{}-nolinesupp} option to +disallow line based suppressions once just before the document is finished. +At that point you should go back over all the warnings and decide if they +should be fixed. + +In addition to line-specific suppressions, you can create a suppression which will be in effect for the remainder of the file. +This can be used, for example, to turn off warning 18 (about \verb+"+) in a file which uses a package (like \Cmd{babel}) where \verb+"+ is an active character. +The syntax is nearly the same, namely +\begin{center} + \verb+% checktex-file ##+ +\end{center} + +\subsubsection{Hints} +I've tried to collect some advice that may be useful --- if you have a +favourite hint, feel free to send it to me! + +\begin{itemize} +\item If you use \Cmd{german.sty} or several of \Cmd{babel} languages + which use \verb+"+ as an active character; it may be wise to put \Cmd{-n18} in + the \Cmd{CmdLine} entry in the \rsrc\ file. This will probably reduce + the amount of false warnings significantly. Alternately, you can put + \verb+% checktex-file 18+ in your files which use one of these packages so + that other files will still have these checks performed. +\item Put \Cmd{-v} in the \Cmd{CmdLine} entry of the \rsrc\ file; this + makes the fancy printing the default. +\item If you're working on a large project, it may pay off to make a + local resource file which is included in addition to the global + one. In this one, add the necessary info to reduce the amount of + false warnings --- these usually don't do anything but hide the + real warnings. +\item Create a total ignore environment, which \chktex\ will ignore + completely. In here, you can place all that code which outsmarts + \chktex\ completely. For instance, add the following lines at the top + of your \LaTeX\ file: +\begin{verbatim} +% ChkTeX will ignore material within this environment +\newenvironment{ignore}{}{} +\end{verbatim} + In addition, you should add the item \Cmd{ignore} to the \Cmd{VerbEnvir} + entry in the \rsrc\ file. +\end{itemize} +\subsubsection{Bugs} + +No fatal ones, I think, but the program currently has some problems when a +\LaTeX\ command/parameter stretch over a two lines --- some extra spaces +may be inserted into the input. I regard the program as fairly well +tested; using the SAS/C \Cmd{cover} utility I was able to make sure that +approximately 95\% of the code has actually been run successfully in the +final version. This does indeed leave some lines; most of these are +procedure terminating brackets or ``can't happen'' lines, though. + +We've got some problems when isolating the arguments of a command. +Although improved, it will certainly fail in certain cases; \chktex\ +can for instance not handle arguments stretching over two lines. This +also means that \Cmd{WIPEARG} entries in the \rsrc\ file will only +have the first half of their argument wiped if the argument stretches +over two lines. We will, however, take care not to wipe parenthesis +in such cases, in order to avoid false warnings. + +Long lines are broken up into chunks and handled separately. The exact +length is platform dependent, though is guaranteed to be at least 256 bytes. +The first portions of the line will have line numbers that are 1 less than +they should be. Some errors can be missed and some can be added erroneously. +A warning will be issued if lines are too long. + +Before submitting a bug report, please first see whether the problem can be +solved by editing the \rsrc\ file appropriately. + + + +\subsection{ChkWEB} + +This shell script is provided for checking CWEB files. The template is +as follows: +\begin{verbatim} +chkweb [options] file1 file2 ... +\end{verbatim} +As you may see from the script, it is only a trivial interface towards +\texttt{deweb} and \chktex. It does not support any individual options +on the command line --- all options found will be passed onto \chktex. +If \Cmd{-{}-} or a filename is found, the remaining parameters will be +ignored. +The only real intelligence it features is that it will try to append +\verb@.w@ to filenames it can't find. + +If no filenames are given, we will read from \texttt{stdin}. + +\subsection{DeWEB} + +This program strips away C code and CWEB commands from CWEB sources. +It is called with the following synopsis: + +\begin{verbatim} +deweb file1 file2 ... +\end{verbatim} + +\texttt{deweb} filters away all C \&\ CWEB commands from a CWEB source +code. This leaves only the \LaTeX\ code. This stripped code, in turn, +may then be passed to a suitable syntax checker for \LaTeX, like +\chktex\ and \texttt{lacheck}, or spell-checkers like \texttt{ispell}. + +When \texttt{deweb} strips away the C code from your CWEB source, it tries to +preserve line breaks. This means that the error reports from {\it your + favorite tool\/} will be correct regarding to line numbers. In most +cases, the column position will also be correct. This significantly +simplifies finding the errors in the \LaTeX\ source (in contrast to the +output from \texttt{cweave}, which output is truly difficult to figure +anything out from). + +\texttt{deweb} accepts a list of filenames on the argument line, and will send +its output to \texttt{stdout}. If no filenames are given, it will read from +stdin, acting as a filter. No options are currently accepted. + +Macho users may try to pipe the output from \texttt{deweb} directly into +\LaTeX, theoretically, this should work. This would ease the debugging of +the \LaTeX\ code significantly, as when \LaTeX\ complains about wrong +syntax, you'll be able to find the erroneous line much more easily. Don't +expect that the output looks very much like the final one, though. + +\texttt{deweb} should now understand all correct \texttt{CWEB} opcodes. If it +complains about not understanding a correct opcode, please inform the +author. + +\subsubsection{Bugs} + +\texttt{deweb} will not even \emph{compile} under Perl versions before perl +v5. Unfortunately, this means that we can't even tell the user why we +failed; Perl will just complain about not being able to compile the +regexps. + +\section{Explanation of error messages} +Below is a description of all error-messages \chktex\ outputs. +Error messages set in {\it italic type\/} are turned off by default. +Where margin paragraphs are listed in the text, they refer to the +keyword in the \rsrc\ file which controls the discussed warning. + +\newcommand\Keyword[1]{\marginpar{\texttt{\hfill\\ #1}}} + +\smallskip\pagebreak[2] +\Keyword{Silent} +\begin{errdesc}{Command terminated with space.} + You tried to terminate a command with a blank space. Usually, this + is an error as these are ignored by \LaTeX. In most cases, you would + like to have a real space there. + + You can also specify regular expressions to match commands which can + safely be terminated with a space. They are specified in in the + \rsrc\ file in \texttt{[]}, which in some other cases is used to + indicate case-insensitive matching. + + \begin{errexam} + \verb@\LaTeX@\underline{\tt }\verb@is a typesetter.@ \\* + \LaTeX is a typesetter. \\* + \smallskip + \verb@\LaTeX\ is a typesetter.@ \\* + \LaTeX\ is a typesetter. \\* + \end{errexam} +\end{errdesc} + +\Keyword{Linker} +\begin{errdesc}{Non-breaking space (`\~{}') should have been used.} + When reading a document, it is not very pretty when references are + split across lines. If you use the \verb@~@ character, \LaTeX\ will + assign a very high penalty for splitting a line at that point. + \chktex\ issues this warning if you have forgot to do this. + + \begin{errexam} + \verb@Please refer to figure@\underline{\tt\ }\verb@\ref{foo}.@ \\* + Please refer to figure 11. \\* % Gotta cheat here! :) + \smallskip + \verb@Please refer to figure~\ref{foo}.@ \\* + Please refer to figure~11. \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{You should enclose the previous parenthesis with `\{\}'.} + + This is a warning which you may ignore, but for maximum aestethic + pleasure, you should enclose your bracket characters with `\{\}'s. + + \begin{errexam} + \verb@$@\underline{\tt\ }\verb@[(ab)^{-1}]@\underline{\tt\ }\verb@\^{-2}$@ \\* + $[(ab)^{-1}]^{-2}$ \\* + \smallskip + \verb@${[{(ab)}^{-1}]}^{-2}$@ \\* + ${[(ab)^{-1}]}^{-2}$ \\* + \end{errexam} +\end{errdesc} + +\Keyword{Italic\\ItalCmd\\NonItalic} +\begin{errdesc}{Italic correction (`\BS/') found in non-italic + buffer.} + If you try to use the \verb@\/@ command when \chktex\ believes that + the buffer is not outputted as italic, you'll get this warning. + + \begin{errexam} + \verb@This is an@\underline{\tt\BS/}\verb@ example@ \\* + This is an\/ example. \\* + \smallskip + \verb@This is an example.@ \\* + This is an example. \\* + \end{errexam} +\end{errdesc} + +\Keyword{Italic\\ItalCmd\\NonItalic} +\begin{errdesc}{Italic correction (`\BS/') found more than once.} + If the buffer is italic, and you try to use the \verb@\/@ command + more than once, you'll get this warning. + + \begin{errexam} + \verb@This {\it example\/@\underline{\tt\BS/}\verb@} is not amusing.@ \\* + This {\it example\/\/} is not amusing. \\* + \smallskip + \verb@This {\it example\/} is not amusing.@ \\* + This {\it example\/} is not amusing. \\* + \end{errexam} +\end{errdesc} + +\Keyword{Italic\\ItalCmd\\NonItalic} +\begin{errdesc}{No italic correction (`\BS/') found.} + You get this error if \chktex\ believes that you are switching from + italic to non-italic, and you've forgot to use the \verb@\/@ command + to insert that extra little spacing. If you use the \Cmd{em} option, + you may ignore this warning. + + \begin{errexam} + \verb@This {\it example@\underline{\tt\ }\verb@} is not amusing, either.@ \\* + This {\it example} is not amusing, either. \\* + \smallskip + \verb@This {\it example\/} is not amusing, either.@ \\* + This {\it example\/} is not amusing, either. \\* + \end{errexam} +\end{errdesc} + +\Keyword{IJAccent} +\begin{errdesc}{Accent command `command' needs use of `command'.} + If you're using accenting commands, `i' and `j' should lose their + dots before they get accented. This is accomplished by using the + \verb@\i@, \verb@\j@, \verb@\imath@ and \verb@\jmath@ command. + + \begin{errexam} + \verb@This is an example of use of accents: \'{@\underline{\tt i}\verb@}.@ \\* + This is an example of use of accents: \'{i}. \\* + \smallskip + \verb@This is an example of use of accents: \'{\i}.@ \\* + This is an example of use of accents: \'{\i}. \\* + \end{errexam} +\end{errdesc} + +\Keyword{HyphDash\\NumDash\\WordDash} +\begin{errdesc}{Wrong length of dash may have been used.} + This warning suggests that a wrong number of dashes may have been + used. It does this by classifying the dash according to the the + character in front and after the dashes. + + If they are of the same type, \chktex\ will determine which keyword + to use in the \rsrc\ file. If not, it will shut up and accept that + it doesn't know. + + \begin{tabular}{ll} + \bf Character type & \bf Keyword in \rsrc\ file \\* + Space & \texttt{WordDash} \\* + Number & \texttt{NumDash} \\* + Alphabetic character & \texttt{HyphDash} \\* + \end{tabular} + + This is more or less correct, according to my references. One + complication is that most often a hyphen (single dash) is desired + between letters, but occasionally an n-dash (double dash) is + required. This is the case for theorems named after two people + e.g.\ Jordan--H\"older. A hyphen would indicate that it was one + person with a hyphenated name e.g.\ Gregorio Ricci-Curbastro. + In my experience this is rare enough to be dealt with via line + based suppressions. There is still the problem that no warning + will be raised for Jordan-H\"older, so care must still be taken. + + Some manuals---particularly American manuals---also suggest + \emph{not} adding space around an m-dash (triple dash). + Hopefully this check can be improved even more (suggestions?). + + \begin{errexam} + \verb@It wasn't anything @\underline{\tt-}\verb@ just a 2@\underline + {\tt-{}-{}-}\verb@3 star@\underline{\tt-{}-}\verb@shots.@ \\* + It wasn't anything - just a 2---3 star--shots. \\* + \smallskip + \verb@It wasn't anything --- just a 2--3 star-shots@ \\* + It wasn't anything --- just a 2--3 star-shots. \\* + \end{errexam} +\end{errdesc} + + +\fmted{`\%s' expected, found `\%s'.} +\begin{errdesc}{Solo `\%s' found.} + Either brackets or environments don't match. + \chktex\ expects to find matching brackets/environments in the + same order as their opposites were found, and no closing delimiters + which haven't been preceded by an opening one. + + While bracket matching is not an explicit error, it is usually a + sign that something is wrong. + +\end{errdesc} + +\Keyword{CenterDots\\LowDots} +\begin{errdesc}{You should use `\%s' to achieve an ellipsis.} + Simply typing three \Cmd{.} in a row will not give a perfect spacing + withing the between the dots. The \verb@\ldots@ is much more + suitable for this. + + In math mode, you should also distinguish between \verb@\cdots@ and + \verb@\ldots@; take a look at the example below. + + \begin{errexam} + \newcommand{\td}{\underline{\tt...}} + \verb@Foo@\td\verb@bar. $1,@\td\verb@,3$. $1+@\td\verb@+3$. $1,@% + \underline{\tt\BS{}cdots}\verb@,3$.@ \\* + Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. \\* + \smallskip + \verb@Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$.@ \\* + Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$. \\ + \end{errexam} +\end{errdesc} + +\Keyword{Abbrev} +\begin{errdesc}{Interword spacing (`\BS\ ') should perhaps be used.} + + One of the specified abbreviations were found. Unless you have + previously said \verb@\frenchspacing@, you'll have incorrect + spacing, which one should avoid if possible. + + You can also specify case-insensitive abbreviations in \texttt{[]}, though + only the first letter is actually case-insensitive. + + \begin{errexam} + \verb@This is an example, i.e.@\underline{\tt\ }\verb@an demonstration.@ \\* + This is an example, i.e. an demonstration. \\* + \smallskip + \verb@This is an example, i.e.\ an demonstration.@ \\* + This is an example, i.e.\ an demonstration. \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{Intersentence spacing (`\BS{}@') should perhaps be used.} + + \LaTeX' detection of whether a period ends a sentence or not, is + only based upon the character in front of the period. If it's + uppercase, it assumes that it does not end a sentence. While this + may be correct in many cases, it may be incorrect in others. + \chktex\ thus outputs this warning in every such case. + + \begin{errexam} + \verb@I've seen an UFO!@\underline{\tt\ }\verb@Right over there!@ \\* + I've seen an UFO! Right over there! \\* + \smallskip + \verb+I've seen an UFO\@! Right over there!+ \\* + I've seen an UFO\@! Right over there! \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{Could not find argument for command.} + + \chktex\ will in some cases need the argument of a function to + detect an error. As \chktex\ currently processes the \LaTeX\ file on + a line-by-line basis, it won't find the argument if the command + which needed it was on the previous line. On the other hand, this + \emph{may} also be an error; you ought to check it to be safe. + + \begin{errexam} + \verb@$\hat$@ \\* + This will give a \LaTeX\ error\dots \\* + \smallskip + \verb@$\hat{a}$@ \\* + $\hat{a}$ \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{No match found for `\%s'.} + + This warning is triggered if we find a single, \emph{opening} + bracket or environment. While bracket matching is not an explicit + error, it is usually a sign that something is wrong. + +\end{errdesc} + +\Keyword{MathEnvir} +\begin{errdesc}{Mathmode still on at end of LaTeX file.} + This error is triggered if you at some point have turned on + mathmode, and \chktex\ couldn't see that you remembered to turn it + off. + +\end{errdesc} + +\begin{errdesc}{Number of `character' doesn't match the number of `character'.} + + Should be self-explanatory. \chktex\ didn't find the same number of + an opening bracket as it found of a closing bracket. + +\end{errdesc} + +\begin{errdesc}{You should use either `` or '' as an alternative to `\,"\,'.} + Self-explanatory. Look in the example, and you'll understand why. + + \begin{errexam} + \verb@This is an @\underline{\tt"}\verb@example@\underline{\tt"} \\* + This is an "example" \\* + \smallskip + \verb@This is an ``example''@ \\* + This is an ``example'' \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{You should use "'" (ASCII 39) instead of + "'" (ASCII 180).} On some keyboards you might get the wrong quote. + This quote looks, IMHO, \emph{ugly} compared to the standard + quotes, it doesn't even come out as a quote! Just see in the + example. + + + \begin{errexam} + \verb@``There@\underline{\tt '}\verb@s quotes and there@\underline{\tt '}\verb@s quotes@ + \underline{\tt ''} \\* % '' + ``There´s quotes and there´s quotes´´ \\* % '' + \smallskip + \verb@``There's quotes and there's quotes''@ \\* + ``There's quotes and there's quotes'' \\* + \end{errexam} +\end{errdesc} + +\Keyword{UserWarn} +\begin{errdesc}{User-specified pattern found: \%s.} + A substring you've specified using \texttt{UserWarn} in the \rsrc\ file, + has been found. See also warning~44 which allows using regular + expressions. You can also specify case-insensitive versions in + \texttt{[]}. + % Normally I would use a ref here, but if the numbers change that would be + % hugely backwards incompatible. Also it would require adding special label code. +\end{errdesc} + +\begin{errdesc*}{This command might not be intended.} + I implemented this because a friend of mine kept on making these + mistakes. Easily done if you haven't gotten quite into the syntax + of \LaTeX. + + \begin{errexam} + \verb@\LaTeX\ is an extension of \TeX@\underline{\tt\BS.}\verb@ Right?@ \\* + \LaTeX\ is an extension of \TeX\. Right? \\* + \smallskip + \verb@\LaTeX\ is an extension of \TeX. Right?@ \\* + \LaTeX\ is an extension of \TeX. Right? \\* + \end{errexam} +\end{errdesc*} + +\begin{errdesc*}{Comment displayed.} + \chktex\ dumps all comments it finds, which in some cases is useful. + I usually keep all my notes in the comments, and like to review them + before I ship the final version. For commenting out parts of the + document, the \Cmd{comment} environment is better suited. Setting + this warning allows you to see notes you have left in comments. +\end{errdesc*} + + +\begin{errdesc}{Either ''\BS,' or '\BS,'' will look better.} + + This error is generated whenever you try to typeset three quotes in + a row; this will not look pretty, and one of them should be + separated from the rest. + + \begin{errexam} + \underline{\tt```}\verb@Hello', I heard him said'', she remembered.@ \\* + ```Hello', I heard him said'', she remembered. \\* + \smallskip + \verb@``\,`Hello', I heard him said'', she remembered.@ \\* + ``\,`Hello', I heard him said'', she remembered. + \end{errexam} +\end{errdesc} + +\Keyword{PostLink} +\begin{errdesc}{Delete this space to maintain correct pagereferences.} + This message, issued when a space is found in front of a + \verb@\index@, \verb@\label@ or similar command (can be set in the + \rsrc\ file). Sometimes, this space may cause that the word and the + index happens on separate pages, if a pagebreak happens just there. + + Warning~42 is similar in that it warns about spaces in front of footnotes. + The difference is that the warning text makes more sense for that case. + + \begin{errexam} + \verb@Indexing text@\underline{\tt\ }\verb@\index{text} is fun!@ \\* + \smallskip + \verb@Indexing text\index{text} is fun!@ \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{You might wish to put this between a pair of `\{\}'} + + This warning is given whenever \chktex\ finds a \Cmd{\^{ }}' or a + \Cmd{\_} followed by either two or more numeric digits or two or + more alphabetic characters. In most situations, this means that + you've forgotten some \{\}'s. + + \begin{errexam} + \verb@$5\cdot10^@\underline{\tt10}\verb@$@ \\* + $5\cdot10^10$ \\* + \smallskip + \verb@$5\cdot10^{10}$@ \\* + $5\cdot10^{10}$ + \end{errexam} +\end{errdesc} + +\begin{errdesc}{You ought to remove spaces in front of punctuation.} + + This warning is issued if \chktex\ finds space in front of an + end-of-sentence character. + + \begin{errexam} + \verb@Do you understand@\underline{\tt\ }\verb@?@ \\* + Do you understand ? \\* + \smallskip + \verb@Do you understand?@ \\* + Do you understand? \\* + \end{errexam} +\end{errdesc} + +\begin{errdesc}{Could not execute LaTeX command.} + + Some \LaTeX\ commands will be interpreted by \chktex; however, some + of them are sensible to errors in the \LaTeX\ source. Most notably, + the \verb@\@\verb@input@ command requires that the input file exist\dots + +\end{errdesc} + +\Keyword{Italic\\ItalCmd\\NonItalic} +\begin{errdesc}{Don't use \BS/ in front of small punctuation.} + Italic correction should generally \emph{not} be used in front of + small punctuation characters like `.' and `,'; as it looks better + when the preceding italic character leans ``over'' the punctum or + comma. + + \begin{errexam} + \verb@It is just a {\it test@\underline{\tt\BS/}\verb@}, don't think anything else.@ \\* + It is just a {\it test\/}, don't think anything else. \\* + \smallskip + \verb@It is just a {\it test}, don't think anything else.@ \\* + It is just a {\it test}, don't think anything else. + \end{errexam} +\end{errdesc} + +\begin{errdesc}{\$\BS{}times\$ may look prettier here.} + In ASCII environments, it is usual to use the `x' character as an + infix operator to denote a dimension. The mathemathical symbol + $\times$ provided by the \verb@$\times$@ command is better suited for + this. + + \begin{errexam} + \verb@The program opens a screen sized 640@\underline{\tt x}\verb@200 pixels.@ \\* + The program opens a screen sized 640x200 pixels. \\* + \smallskip + \verb@The program opens a screen sized $640\times200$ pixels.@ \\* + The program opens a screen sized $640\times200$ pixels. + \end{errexam} +\end{errdesc} + +\begin{errdesc*}{Multiple spaces detected in output.} + + This warning, intended for the novice, will remind you that even if + you \emph{type} multiple spaces in your input, only a single space + will come out. Some ways to come around this is listed below. + + \begin{errexam} + \verb@White is a beautiful colour.@ \\* + White is a beautiful colour. \\* + \smallskip + \verb@White~~~~~{ }{ }{ }\ \ \ is a beautiful colour.@ \\* + White~~~~~{ }{ }{ }\ \ \ is a beautiful colour. \\ + \end{errexam} +\end{errdesc*} + +\Keyword{VerbEnvir} +\begin{errdesc}{This text may be ignored.} + Certain implementations of the \verb@verbatim@ environment and + derivations of that, ignore all text on the same line as + \verb@\end{verbatim}@. This will warn you about this. + + +\end{errdesc} + +\fmted{Use ` to begin quotation, not '.}\hfill\\ +\fmted{Use ' to end quotation, not `.}\hfill\\ +\begin{errdesc}{Don't mix quotes.} + + Proper quotations should start with a \verb@`@ and end with a + \verb@'@; anything else isn't very pretty. Both these warnings are + relative to this; look in the example below. + + \begin{errexam} + \verb@There are @\underline{\tt`'}% + \verb@examples'' and there are ``examples@\underline{\tt``}\verb@.@ \\* + There are `'examples'' and there are ``examples``. \\* + \smallskip + \verb@There are ``examples'' and there are ``examples''.@ \\* + There are ``examples'' and there are ``examples''. + \end{errexam} +\end{errdesc} + +\Keyword{MathRoman} +\begin{errdesc}{You should perhaps use `cmd' instead.} + Most mathematical operators should be set as standard roman font, + instead of the math italic \LaTeX\ uses for variables. For many + operators, \LaTeX\ provides a pre-defined command which will typeset + the operator correctly. Look below for an illustration of the point. + + \begin{errexam} + \verb@$@\underline{\tt sin}\verb@^2 x + @\underline{\tt cos}\verb@^2 x = 1$@ \\* + $sin^2 x + cos^2 x= 1$ \\* + \smallskip + \verb@$\sin^2 x + \cos^2 x = 1$@ \\* + $\sin^2 x + \cos^2 x = 1$ + \end{errexam} +\end{errdesc} + +\fmted{You should put a space in front of/after parenthesis.}\hfill\\ +\begin{errdesc}{You should avoid spaces in front of/after parenthesis.} + Outside math mode, you should put a space in front of any group of + opening parenthesis, and no spaces after. If you have several after + each other, you should of course not put a space in between each; + look in the example below. Likewise, there should not be spaces in + front of closing parenthesis, but there should be at least one + after. + + + + \begin{errexam} + \verb@This@\underline{\tt( }\verb@an example@\underline{\tt( }% + \verb@Nuff said@\underline{\tt\ }\verb@)), illustrates@\underline{\tt( }% + \verb@``my''@\underline{\tt\ )}\verb@point.@\\ + This( an example( Nuff said )), illustrates( ``my'' )point. \\ + \smallskip + \verb@This (an example (Nuff said)), illustrates (``my'') point.@\\ + This (an example (Nuff said)), illustrates (``my'') point.\\ + \end{errexam} +\end{errdesc} + +\Keyword{QuoteStyle} +\begin{errdesc}{You should not use punctuation in front of/after + quotes.} + % + For best looking documents, you should decide on how you + wish to put quotes relative to punctuation. \chktex\ recognizes two + styles; you may specify which you use in the \rsrc\ file. A + description on each style follows: + \begin{description} + \item[Traditional:] This style is the most visually pleasing. It + always puts the punctuation \emph{in front of} the quotes, which + gives a continuous bottom line. + + However, it may in certain cases be ambigious. Consider the + following example from a fictious \Cmd{vi(1)} + tutorial (quote taken from the Jargon file): + \begin{center} + \verb@Then delete a line from the file by typing ``dd.''@ \\* + Then delete a line from the file by typing ``dd.'' + \end{center} + That would be very bad --- because the reader would be prone to + type the string d-d-dot, and it happens that in \Cmd{vi(1)} dot + repeats the last command accepted. The net result would be to + delete \emph{two} lines! This problem is avoided using logical + style, described below. + \pagebreak[3] + \item[Logical:] This style uses quotes as balanced delimiters like + parentheses. While this is not the most visual pleasing, it is + can't be misunderstood. The above sentence would then become: + \nopagebreak + \begin{center} + \verb@Then delete a line from the file by typing ``dd''.@ \\* + Then delete a line from the file by typing ``dd''. + \end{center} + \nopagebreak + \end{description} + +\end{errdesc} + +\begin{errdesc}{Double space found.} + This warning is triggered whenever \chktex\ finds a space in front + of a hard space, or vice versa. This will be rendered as two spaces + (which you usually don't wish). + + \begin{errexam} + \verb@For output codes, see table@\underline{\tt\ }% + \verb@~@\underline{\tt\ }\verb@\ref{foo}.@ \\* + For output codes, see table ~ 1.1.\\* + \smallskip + \verb@For output codes, see table~\ref{foo}.@ \\* + For output codes, see table~1.1. + \end{errexam} +\end{errdesc} + +\Keyword{MathEnvir} +\begin{errdesc}{You should put punctuation outside inner/inside + display math mode.} + As recommended in the \TeX{}book, you should try to put punctuation + outside inner math mode, as this is gets formatted better. + + Similarily, you should let any final punctuation in display math + mode end up within it. Look at the following example, which was + taken from the \TeX{}book: + \begin{errexam} + \verb@for $x = a@\underline{\tt,}\verb@b$, or $c$.@\\* + for $x = a,b$, or $c$. \\* + \smallskip + \verb@for $x = a$, $b$, or $c$.@\\* + for $x = a$, $b$, or $c$.\\* + \end{errexam} + +\end{errdesc} + +\Keyword{Primitives} +\begin{errdesc*}{You ought to not use primitive TeX in LaTeX code.} + This warning is triggered whenever you use a raw \TeX\ command + which has been replaced by a \LaTeX\ equivalent. If you consider + yourself a purist (or want to be sure your code works under \LaTeX3), + you should use the \LaTeX\ equivalent. +\end{errdesc*} + +\Keyword{NotPreSpaced} +\begin{errdesc}{You should remove spaces in front of `\%s'} + + Some commands should not be prepended by a space character, for cosmetical + reasons. This notes you of this whenever this has happened. + + \begin{errexam} + \verb@This is a footnote@\underline{\tt\ }\verb@\footnotemark[1] mark.@\\* + This is a footnote ${}^1$ mark. \\* + \smallskip + \verb@This is a footnote\footnotemark[1] mark.@\\* + This is a footnote${}^1$ mark. \\* + \end{errexam} +\end{errdesc} + +\Keyword{NoCharNext} +\begin{errdesc}{`\%s' is normally not followed by `\%c'.} + \LaTeX' error message when calling \verb@\left \{@ instead of + \verb@left \{@ is unfortunately rather poor. This warning detects + this and similar errors. +\end{errdesc} + +\Keyword{UserWarnRegex} +\begin{errdesc}{User Regex:\ \%s.} + A pattern you've specified using \texttt{UserWarnRegex} in the \rsrc\ file, + has been found. See also warning~20 which allows specification of simple + string matching. + + Depending on how \chktex\ was configured, you can use either PCRE regular + expressions, POSIX extended regular expressions, or none at all. + A warning will be issued if \chktex\ was built without regular expression + support, but you try to use one. + + By default the matching portion of the line is printed to help distinguish + between user specified regular expressions. However, if the regular + expression begins with a PCRE comment (which has a syntax of + \verb+(?#+~\dots~\verb+)+), then that comment will be printed instead. + This can be used to remind yourself why you were searching for the problem + or how to fix it. This applies even if POSIX regular expressions are used + since \chktex\ itself parses a single initial PCRE-style comment. + + \emph{Note:} If a regular expression (not a comment) starts with + \texttt{PCRE:} or \texttt{POSIX:} it will be used only if support for that + regular expression engine has been compiled in. It is primarily meant to + make testing easier but, can be used to allow better regular expressions + if PCRE is available. If you want a regular expression that starts with + \texttt{PCRE:} or \texttt{POSIX:} then you can enclose one of the + characters in brackets like \texttt{[P]CRE:}. + + An example, included in the \rsrc\ file, is given below. Remember that you + have to escape (with~\verb+!+) spaces and \verb+#+ as well as a few other + characters. One should always use \verb+\nmid+ instead of \verb+\not\mid+ + because the results are much better. + \begin{errexam} + \verb+\\not! *(\||\\mid)+\\* + \verb+User Regex: \not\mid.+\\* + \end{errexam} + or with an initial comment + \begin{errexam} + \verb+(?!#Always! use! \nmid)\\not! *(\||\\mid)+\\* + \verb+User Regex: Always use \nmid.+ + \end{errexam} + + You can use \verb+% chktex 44+ to suppress user regular expression + warnings on a given line, but this is often undesirable since all such + warnings are suppressed this way. For this reason you can ``name'' user + regular expression warnings with negative numbers. For example + \verb+% chktex 4+ will suppress the system warning number 4, but + \verb+% chktex -4+ will suppress the user regular expression warning + number 4. Since one might wish to add, remove, or rearrange user warnings + in the \rsrc\ file, you must explicitly name particular warnings rather + than relying on position in that file. + + In order to name one, include an initial PCRE-style comment with the first + characters being a number (positive or negative---the absolute value will + be used). The numbers are limited by the number of bits in a \texttt{long}, + usually giving 1--63 as possible names. You can give more than one regular + expression the same name, and suppressing that name will suppress all + regular expressions with that name. + + Using the example from before, all of the following will be suppressed with + \verb+% chktex -4+. Note that the name \emph{will} be printed as written + so that you know which number to suppress. + \begin{errexam} + \verb+(?!#4:Always! use! \nmid)\\not! *(\||\\mid)+\\* + \verb+(?!#-4Always! use! \nmid)\\not! *(\||\\mid)+\\* + \verb+(?!#-4! Always! use! \nmid)\\not! *(\||\\mid)+\\* + \end{errexam} +\end{errdesc} + +\section{Future plans} + +In a somewhat prioritized sequence, this is what I'd like to put into the +program --- if I have the time. + +\begin{itemize} +\item De-linearize the checker. Currently, it works on a line-by-line + basis, in most respects, at least. I hope to be able to remove this + barrier; as this will reduce the amount of false warnings + somewhat. + +\item Probably some more warnings/errors; just have to think them out + first. Suggestions are appreciated --- I've ``stolen'' most that + similar programs provides, and am running out of ideas, really. + + It would also be nice to investigate the field of ``globally'' + oriented warnings; i.e.\ warnings regarding the document as a + whole. Currently, \chktex\ operates mainly on a local/``greedy'' + basis. + + If you have suggestions/ideas on this topic, they're certainly + welcome, including references to literature. + +\item Fix a few more bugs. +\end{itemize} + +\section{Notes} + +\subsection{Wish to help?} + +As most other living creatures, I have only a limited amount of time. If +you like \chktex\ and would like to help improving it, here's a few things +I would like to receive. The following ideas are given: + +\begin{itemize} +\item Does anyone have a $\mbox{\LaTeX}\rightarrow \mbox{\texttt{troff}}$ + conversion program? It would be really nice if I could extract the + relevant sections from this manual, and present them as a man page. + I will not, however, convert this manual to \TeX{}info in order to + be able to do this; IMHO \TeX{}info documents have far too limited + typographic possibilities. + + This doesn't mean that I'm not willing to restructure the document + at all. This manual already uses some kind of preprocessing in order + to achieve HTML output via \LaTeX2\texttt{html}, I'm willing to do the + same in order to produce \texttt{troff} output. + +\item Help me port the program! This is a prioritized one. It's no fun + writing ANSI C when people haven't got a C compiler. + + Of course, I'll provide whatever help necessary to modify the sources + to fit to the new platform. Take contact if you're interested. I will + include your compiled binary in the distribution, and give you + credit where appropiate. + + Just one request: If you have to modify the sources in order to make + \chktex\ compile \& work on the new platform, \emph{please} enclose your + changes in something like \Cmd{\#ifdef \_\_PLATFORM\_\_\dots code\dots\#endif}! + It makes life so much easier later, when we try to merge the two + source trees. + +\item Reports on problems configuring and compiling \chktex\ on supported + (and unsupported) systems are welcomed. + +\item Filters for other file formats. I do believe that there are + several formats using \LaTeX\ for its formatting purposes, combining + that with something else. If you can write a program or script which + filters everything away but the \LaTeX\ code, it will surely be + appreciated (and included). Look at the \verb@deweb@ script to see + what I mean. + +\item Interfaces for other editors are also welcomed. + +\item If you update the \rsrc\ file in anyway that is not strictly + local, I would appreciate to receive your updated version. + +\item Suggestions for new warnings are always welcomed. Both formal + (i.e.\ regexps or similar) and non-formal (plain English) descriptions + are welcomed. +\end{itemize} + +Of course, people doing any of this will be mentioned in this document, and +thus receive eternal glory and appreciation. + +\subsection{Caps and stuff} + +Where trademarks have been used, the author is aware of that they +belong to someone, and has tried to stick to the original caps. + +\section{About the author} + +A quick summary of who I am and what I do: + +I'm 21 years old, and live in Oslo, the capital of Norway. I'm +currently studying maths and computer science at the +University~of~Oslo; planning to get a degree within mathematical +modeling, with a dash of physics and emphazing the computer part of +the study. More precisely, in autumn'96 my studies consist of +mathematical analysis, statistics \& probability calculations plus +studying the relationship between society and computers. + +At home I now possess 4 computers, of which 1 is regular use: A +vanilla Amiga 1200, expanded only by a HD\@. The others are a +\texttt{80286} PC and an Amiga 500, both semi-out-of-order. The last +one is a Commodore VIC-20, which for some peculiar reason never seems +to be used. Plans are to get a Linux-capable PC, though. + +Most of the time in front of these computers (including SGI Indy's and +SPARC stations at our university) is spent on C and shell programming, +plus some text-processing. + + % I am also involved in writing the document + % for {\sc Isaac} --- Interactive Simulation as an Alternative to + % Advanced Calculations. This is planned to help newcomers to physics, + % by providing a computer program which enables one to simulate most + % experiments relating to classical mechanics. + % + +C and shell programming are not my only knowledge areas regarding +computers, however. I write the following languages more or less: +Perl, Motorola \texttt{68000} assembly code, ARexx, Simula, C++, \LaTeX, +HTML, AmigaGuide, Amos Basic and Installer LISP\@. Once I also +mastered Commodore Basic V2, the ``language'' included with my VIC-20. + +However, I also try to not to end up as a computer nerd. Thus, in +addition to the compulsory (?) interest for computers, I am a scout. +Still running into the woods, climbing the trees, falling down and +climbing up once more, in other words. To be more specific, I am a +now a troop leader for `Ulven' scout-group; Norwegian Scouts +Association. I am also a active rover in `V{\aa}lerenga' scout-group. + +Certainly a lot more to tell (I play the piano and like cross-country +skiing, for instance); but I'll stop here before you fall +asleep\dots + + +\section{Thanks} + +The author wishes to thank the following people (in alphabetical order): + +\def\Name#1#2{% +\item[] + \setbox0=\hbox{ + \begin{tabular}{l} + \textbf{#1} \\ + \texttt{#2} \\ + \end{tabular} + } \usebox0\\ } + +\begin{description} + + \Name{Russ Bubley}{russ@scs.leeds.ac.uk} + He has been the main external beta-tester for this program, sending + me loads and loads of understandable and reproducible bug reports. + If you somehow think that \chktex\ is well-behaved and free from + bugs, send warm thoughts to Russ. He has also provided ideas for + enhanced checks and so forth. + + In addition, he sent me a huge list of 238 common English + abbreviations, for inclusion in the \rsrc\ file! Together with the + enhanced abbreviation recognizer, I do now believe most + abbreviations should be caught\dots + + Finally, he has also given me valuable hints for improving the + program's outputting routine, and given me lots of suggestions for + filtering unnecessary/false warnings away. + + \Name{Gerd B\"ohm}{Gerd.Boehm@physik.uni-regensburg.de} + Improved and bug-fixed the MS-DOS port of \chktex\ v1.4, sending me + ready-to-yank code patches. The original port didn't respect all + the peculiarities of the MS-DOS file-system, unfortunately. + + \Name{Antonio DiCesare}{dicesare@vodafone.it} + He provided many feature requests and bug reports for the 1.7.1 + version making it a much better release than it would have otherwise + been. He also helped expand several keywords in the \rsrc\ file. + + \Name{Baruch Even}{chktex@ev-en.org} + Maintainer of \chktex\ for about a decade. + + \Name{Lars Frellesen}{frelle@math-tech.dk} Sent a few bug reports + regarding the filtering of messages. He has also helped me to + expand the \Cmd{SILENT} keyword in the \rsrc\ file. + + \Name{Wolfgang Fritsch}{fritsch@hmi.de} + Author of the OS/2 port, which he did using the emx compiler. + Please direct questions regarding strictly to that port to him (I + would like to receive a carbon copy, though). + + \Name{Stefan Gerberding}{stefan@inferenzsysteme.informatik.th-darmstadt.de} + First one to report the Enforcer hit in v1.2 when using \chktex\ as + a pipe. Also came with suggestions to make \chktex\ more easily + compile on early gcc compilers. + + He has also kept on beta-testing later versions of \chktex, giving + me bug-reports and enhancements requests. + + \Name{Kasper B. Graversen}{kbg2001@internet.dk} Lots of creative + suggestions and improvements. Several of the warnings implemented + were based on his ideas. In addition, he has given advice for + improving the existing warnings. + + Has also provided some OS-oriented code. + + \Name{Frank Luithle}{f\_luithle@outside.sb.sub.de} + Wrote a translation for v1.0. Unfortunately, he remained unreachable + after that\dots:-/ + + \Name{Nat}{nat@nataa.frmug.fr.net} + Reported the same bug as Gerberding. In addition, he taught me a + few tricks regarding the use of gcc + made me understand that the + ANSI standard isn't unambigious; at least the \verb@getenv()@ call + seem to be open for interpretations. Many possible + incompatibilities have been removed due to these lessons. + + \Name{Michael Sanders}{sanders@umich.edu} + Has found some of the bugs in this beast; both obscure and + long-lived. Has also provided motivation to clarify this document. + + \Name{Bj\o rn Ove Thue}{bjort@ifi.uio.no} + Author of the MSDOS port; please direct questions regarding + strictly to that port to him (I would like to receive a carbon + copy, though). + + \Name{Martin Ward}{Martin.Ward@durham.ac.uk} + Sent a few bug-reports; also gave me information upon where to find + regexp code. He also provided a Perl script for checking ordinary + text, which ideas I was able to implement in \chktex. In addition, + he sent me the source code for \verb@lacheck@; which also inspired some + of the warnings. +\end{description} + +%endlatex +\section{Contacting the author} + +If you wish to contact me for any reason or would like to participate in +the development of \chktex, please write to: +%latex +\begin{samepage} +%endlatex + \begin{quote} + Jens Berger \\ + Spektrumvn. 4 \\ + N-0666 Oslo \\ + Norway \\ + E-mail: \texttt{} + \end{quote} +%latex +\end{samepage} +%endlatex +Any signs of intelligent life are welcomed; that should exclude piracy. + +Since the original author is unreachable, the maintainer these days is: +%latex +\begin{samepage} +%endlatex + \begin{quote} + Ivan Andrus \\ + E-mail: \texttt{} + \end{quote} +%latex +\end{samepage} +%endlatex + +\medskip\noindent +Have fun. + +\end{document} + +% Rudimentary support for AUCTeX. +% The "Make" target is my own. +% Local Variables: +% TeX-command-default: "Make" +% TeX-master: "ChkTeX.tex" +% End: diff --git a/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.texrc b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.texrc new file mode 100644 index 00000000000..e990c71d1be --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/ChkTeX.texrc @@ -0,0 +1,6 @@ +# Ignore file for ChkTeX.tex, since it shows many errors in its examples +# it raises many errors when checking ChkTeX.tex with chktex itself. + +VerbEnvir { errexam errdesc } + +WipeArg { \Cmd:{} } diff --git a/Build/source/texk/chktex/chktex-1.7.1/FindErrs.c b/Build/source/texk/chktex/chktex-1.7.1/FindErrs.c new file mode 100644 index 00000000000..4cfc7fa509b --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/FindErrs.c @@ -0,0 +1,1970 @@ +/* + * ChkTeX, error searching & report routines. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + + +#include "ChkTeX.h" +#include "FindErrs.h" +#include "OpSys.h" +#include "Utility.h" +#include "Resource.h" + +/* Not everyone has stpcpy() */ +static inline char * +stpcpy(char *dest, const char *src) +{ + return strcpy(dest, src) + strlen(src); +} + +#if HAVE_PCRE || HAVE_POSIX_ERE + +#if HAVE_PCRE +#include +#else +#include +#endif + +#define REGEX_FLAGS REG_EXTENDED +#define NUM_MATCHES 10 +#define ERROR_STRING_SIZE 100 + +regex_t* RegexArray = NULL; +regex_t* SilentRegex = NULL; +int NumRegexes = 0; + +#endif + +/***************************** ERROR MESSAGES ***************************/ + +#undef MSG +#define MSG(num, type, inuse, ctxt, text) {num, type, inuse, ctxt, text}, + +struct ErrMsg LaTeXMsgs[emMaxFault + 1] = { + ERRMSGS {emMaxFault, etErr, iuOK, 0, INTERNFAULT} +}; + +#define istex(c) (isalpha((unsigned char)c) || (AtLetter && (c == '@'))) +#define CTYPE(func) \ +static int my_##func(int c) \ +{ \ + return(func(c)); \ +} + +#define SUPPRESSED_ON_LINE(c) (LineSuppressions & (1LL<<=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * A list of characters LaTeX considers as an end-of-sentence characters, which + * should be detected when whether sentence spacing is correct. + * + */ +static const char LTX_EosPunc[] = { '.', ':', '?', '!', 0 }; + +/* + * General punctuation characters used on your system. + */ +static const char LTX_GenPunc[] = { ',', ';', 0 }; + +/* + * A list of characters LaTeX considers as an small punctuation characters, + * which should not be preceded by a \/. + */ +static const char LTX_SmallPunc[] = { '.', ',', 0 }; + +/* + * String used to delimit a line suppression. This string must be + * followed immediately by the number of the warning to be suppressed. + * If more than one warning is to be suppressed, then multiple copies + * of LineSuppDelim+number must be used. + */ +const char LineSuppDelim[] = "chktex "; + +/* + * String used to delimit a file suppression. This string must be + * followed immediately by the number of the warning to be suppressed. + * If more than one warning is to be suppressed, then multiple copies + * of FileSuppDelim+number must be used. + */ +const char FileSuppDelim[] = "chktex-file "; + +/* + * A bit field used to hold the suppressions for the current line. + */ +static unsigned long long LineSuppressions; +/* + * A bit field used to hold the suppressions of numbered user warnings + * for the current line. + */ +static unsigned long long UserLineSuppressions; + +static unsigned long Line; + +static const char *RealBuf; +static char *LineCpy; +static char *BufPtr; + +static int ItFlag = efNone; +static int MathFlag = efNone; + +NEWBUF(Buf, BUFSIZ); +NEWBUF(CmdBuffer, BUFSIZ); +NEWBUF(ArgBuffer, BUFSIZ); + +static enum ErrNum PerformCommand(const char *Cmd, char *Arg); + +#ifdef isdigit +CTYPE(isdigit) +#else +# define my_isdigit isdigit +#endif + +#ifdef isalpha +CTYPE(isalpha) +#else +# define my_isalpha isalpha +#endif + +/* + * Reads in a TeX token from Src and puts it in Dest. + * + */ + + +static char *GetLTXToken(char *Src, char *Dest) +{ + int Char; + + if (Src && *Src) + { + if (*Src == '\\') + { + *Dest++ = *Src++; + Char = *Dest++ = *Src++; + + if (istex(Char)) + { + while (istex(Char)) + Char = *Dest++ = *Src++; + + Src--; + Dest--; + } + + } + else + *Dest++ = *Src++; + *Dest = 0; + } + else + Src = NULL; + + return (Src); +} + + +/* + * Scans the `SrcBuf' for a LaTeX arg, and puts that arg into `Dest'. + * `Until' specifies what we'll copy. Assume the text is + * "{foo}bar! qux} baz". + * GET_TOKEN => "{foo}" + * GET_STRIP_TOKEN => "foo" + * '!' => "{foo}bar!" (i.e. till the first "!") + * Returns NULL if we can't find the argument, ptr to the first character + * after the argument in other cases. + * + * If one of the tokens found is in the wl wordlist, and we're in the + * outer most paren, and Until isn't a single character, we'll stop. + * You may pass NULL as wl. + * + * We assume that you've previously skipped over leading spaces. + * + */ + +#define GET_TOKEN 256 +#define GET_STRIP_TOKEN 257 + +static char *GetLTXArg(char *SrcBuf, char *OrigDest, const int Until, + struct WordList *wl) +{ + char *Retval; + char *TmpPtr; + char *Dest = OrigDest; + unsigned long DeliCnt = 0; + + *Dest = 0; + TmpPtr = SrcBuf; + + switch (Until) + { + case GET_STRIP_TOKEN: + case GET_TOKEN: + while ((Retval = GetLTXToken(TmpPtr, Dest))) + { + switch (*Dest) + { + case '{': + DeliCnt++; + break; + case '}': + DeliCnt--; + } + Dest += Retval - TmpPtr; + TmpPtr = Retval; + + if (!DeliCnt || ((DeliCnt == 1) && wl && HasWord(Dest, wl))) + break; + } + + if (Retval && (*OrigDest == '{') && (Until == GET_STRIP_TOKEN)) + { + int len = strlen(OrigDest+1); + memmove(OrigDest, OrigDest + 1, len + 1); + /* Strip the last '}' off */ + OrigDest[len-1] = 0; + } + break; + default: + DeliCnt = TRUE; + while ((Retval = GetLTXArg(TmpPtr, Dest, GET_TOKEN, NULL))) + { + if (*Dest == Until) + DeliCnt = FALSE; + + Dest += Retval - TmpPtr; + TmpPtr = Retval; + + if (!DeliCnt) + break; + } + break; + } + *Dest = 0; + + return (Retval); +} + + +static char *MakeCpy(void) +{ + if (!LineCpy) + LineCpy = strdup(RealBuf); + + if (!LineCpy) + PrintPrgErr(pmStrDupErr); + + return (LineCpy); +} + +static char *PreProcess(void) +{ + char *TmpPtr; + + /* Reset any line suppressions */ + + LineSuppressions = FileSuppressions; + UserLineSuppressions = UserFileSuppressions; + + /* Kill comments. */ + strcpy(Buf, RealBuf); + + TmpPtr = Buf; + + while ((TmpPtr = strchr(TmpPtr, '%'))) + { + char *EscapePtr = TmpPtr; + int NumBackSlashes = 0; + while (EscapePtr != Buf && EscapePtr[-1] == '\\') + { + ++NumBackSlashes; + --EscapePtr; + } + + /* If there is an even number of backslashes, then it's a comment. */ + if ((NumBackSlashes % 2) == 0) + { + PSERR(TmpPtr - Buf, 1, emComment); + *TmpPtr = 0; + /* Check for line suppressions */ + if (!NoLineSupp) + { + int error; + const int MaxSuppressionBits = sizeof(unsigned long long)*8-1; + + /* Convert to lowercase to compare with LineSuppDelim */ + EscapePtr = ++TmpPtr; /* move past NUL terminator */ + while ( *EscapePtr ) + { + *EscapePtr = tolower(*EscapePtr); + ++EscapePtr; + } + + EscapePtr = TmpPtr; /* Save it for later */ + while ((TmpPtr = strstr(TmpPtr, FileSuppDelim))) { + TmpPtr += STRLEN(FileSuppDelim); + error = atoi(TmpPtr); + + if (abs(error) > MaxSuppressionBits) + { + PrintPrgErr(pmSuppTooHigh, error, MaxSuppressionBits); + } + if (error > 0) + { + FileSuppressions |= (1LL << error); + LineSuppressions |= (1LL << error); + } + else + { + UserFileSuppressions |= (1LL << (-error)); + UserLineSuppressions |= (1LL << (-error)); + } + } + TmpPtr = EscapePtr; + + while ((TmpPtr = strstr(TmpPtr, LineSuppDelim))) { + + TmpPtr += STRLEN(LineSuppDelim); + error = atoi(TmpPtr); + + if (abs(error) > MaxSuppressionBits) + { + PrintPrgErr(pmSuppTooHigh, error, MaxSuppressionBits); + } + + if (error > 0) + { + LineSuppressions |= (1LL << error); + } + else + { + UserLineSuppressions |= (1LL << (-error)); + } + } + } + break; + } + TmpPtr++; + } + return (Buf); +} + +/* + * Interpret environments + */ + +static void PerformEnv(char *Env, int Begin) +{ + static char VBStr[BUFSIZ] = ""; + + if (HasWord(Env, &MathEnvir)) + { + MathMode += Begin ? 1 : -1; + MathMode = max(MathMode, 0); + } + + if (Begin && HasWord(Env, &VerbEnvir)) + { + VerbMode = TRUE; + strcpy(VBStr, "\\end{"); + strcat(VBStr, Env); + strcat(VBStr, "}"); + VerbStr = VBStr; + } +} + +static char *SkipVerb(void) +{ + char *TmpPtr = BufPtr; + int TmpC; + + if (VerbMode && BufPtr) + { + if (!(TmpPtr = strstr(BufPtr, VerbStr))) + BufPtr = &BufPtr[strlen(BufPtr)]; + else + { + VerbMode = FALSE; + BufPtr = &TmpPtr[strlen(VerbStr)]; + SKIP_AHEAD(BufPtr, TmpC, LATEX_SPACE(TmpC)); + if (*BufPtr) + PSERR(BufPtr - Buf, strlen(BufPtr) - 2, emIgnoreText); + } + } + return (TmpPtr); +} + +#define CHECKDOTS(wordlist, dtval) \ +for(i = 0; (i < wordlist.Stack.Used) && !(Back && Front); i++) \ + { if(!strafter(PstPtr, wordlist.Stack.Data[i])) \ + Back = dtval; \ + if(!strinfront(PrePtr, wordlist.Stack.Data[i])) \ + Front = dtval; } + + + +/* + * Checks that the dots are correct + */ + +static enum DotLevel CheckDots(char *PrePtr, char *PstPtr) +{ + unsigned long i; + int TmpC; + enum DotLevel Front = dtUnknown, Back = dtUnknown; + + if (MathMode) + { + PrePtr--; +#define SKIP_EMPTIES(macro, ptr) macro(ptr, TmpC, \ +(LATEX_SPACE(TmpC) || (TmpC == '{') || (TmpC == '}'))) + + SKIP_EMPTIES(SKIP_BACK, PrePtr); + SKIP_EMPTIES(SKIP_AHEAD, PstPtr); + + CHECKDOTS(CenterDots, dtCDots); + + if (!(Front && Back)) + { + CHECKDOTS(LowDots, dtLDots); + } + return (Front & Back); + } + else + return (dtLDots); + +} + +static const char *Dot2Str(enum DotLevel dl) +{ + const char *Retval = INTERNFAULT; + switch (dl) + { + case dtUnknown: + Retval = "\\cdots or \\ldots"; + break; + case dtDots: + Retval = "\\dots"; + break; + case dtCDots: + Retval = "\\cdots"; + break; + case dtLDots: + Retval = "\\ldots"; + break; + } + return Retval; +} + +/* + * Wipes a command, according to the definition in WIPEARG + */ + +static void WipeArgument(const char *Cmd, char *CmdPtr) +{ + unsigned long CmdLen = strlen(Cmd); + const char *Format; + char *TmpPtr; + int c, TmpC; + + if (Cmd && *Cmd) + { + TmpPtr = &CmdPtr[CmdLen]; + Format = &Cmd[CmdLen + 1]; + + while (TmpPtr && *TmpPtr && *Format) + { + switch (c = *Format++) + { + case '*': + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + if (*TmpPtr == '*') + TmpPtr++; + break; + case '[': + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + if (*TmpPtr == '[') + TmpPtr = GetLTXArg(TmpPtr, ArgBuffer, ']', NULL); + break; + case '(': + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + if (*TmpPtr == '(') + TmpPtr = GetLTXArg(TmpPtr, ArgBuffer, ')', NULL); + break; + case '{': + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + TmpPtr = GetLTXArg(TmpPtr, ArgBuffer, GET_TOKEN, NULL); + case '}': + case ']': + case ')': + break; + default: + PrintPrgErr(pmWrongWipeTemp, &Cmd[strlen(Cmd) + 1]); + break; + } + } + + if (TmpPtr) + strwrite(CmdPtr+CmdLen, VerbClear, TmpPtr - CmdPtr - CmdLen); + else + strxrep(CmdPtr+CmdLen, "()[]{}", *VerbClear); + } +} + +/* + * Checks italic. + * + */ + +static void CheckItal(const char *Cmd) +{ + int TmpC; + char *TmpPtr; + if (HasWord(Cmd, &NonItalic)) + ItState = itOff; + else if (HasWord(Cmd, &Italic)) + ItState = itOn; + else if (HasWord(Cmd, &ItalCmd)) + { + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + if (*TmpPtr == '{') + { + ItFlag = ItState ? efItal : efNoItal; + ItState = itOn; + } + } +} + +/* + * Interpret isolated commands. + * + */ + +static void PerformBigCmd(char *CmdPtr) +{ + char *TmpPtr; + const char *ArgEndPtr; + unsigned long CmdLen = strlen(CmdBuffer); + int TmpC; + enum ErrNum ErrNum; + struct ErrInfo *ei; + + enum DotLevel dotlev, realdl = dtUnknown; + + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + + ArgEndPtr = GetLTXArg(TmpPtr, ArgBuffer, GET_STRIP_TOKEN, NULL); + + /* Kill `\verb' commands */ + + if (WipeVerb) + { + if (!strcmp(CmdBuffer, "\\verb")) + { + if (*BufPtr && (*BufPtr != '*' || BufPtr[1])) + { + if (*BufPtr == '*') + TmpPtr = strchr(&BufPtr[2], BufPtr[1]); + else + TmpPtr = strchr(&BufPtr[1], *BufPtr); + if (TmpPtr) + strwrite(CmdPtr, VerbClear, (TmpPtr - CmdPtr) + 1); + else + PSERR(CmdPtr - Buf, 5, emNoArgFound); + } + } + } + + if (HasWord(CmdBuffer, &IJAccent)) + { + if (ArgEndPtr) + { + TmpPtr = ArgBuffer; + SKIP_AHEAD(TmpPtr, TmpC, TmpC == '{'); /* } */ + + if ((*TmpPtr == 'i') || (*TmpPtr == 'j')) + PrintError(CurStkName(&InputStack), RealBuf, + CmdPtr - Buf, + (long) strlen(CmdBuffer), Line, + emAccent, CmdBuffer, *TmpPtr, + MathMode ? "math" : ""); + } + else + PSERR(CmdPtr - Buf, CmdLen, emNoArgFound); + } + + if (HasWord(CmdBuffer, &NotPreSpaced) && isspace((unsigned char)CmdPtr[-1])) + PSERRA(CmdPtr - Buf - 1, 1, emRemPSSpace, CmdBuffer); + + if ((TmpPtr = HasWord(CmdBuffer, &NoCharNext))) + { + char *BPtr = BufPtr; + + TmpPtr += strlen(TmpPtr) + 1; + SKIP_AHEAD(BPtr, TmpC, LATEX_SPACE(TmpC)); + + if (strchr(TmpPtr, *BPtr)) + { + PSERR2(CmdPtr - Buf, CmdLen, emNoCharMean, CmdBuffer, *BPtr); + } + } + + if (!strcmp(CmdBuffer, "\\begin") || !strcmp(CmdBuffer, "\\end")) + { + if (ArgEndPtr) + { + if (!strcmp(ArgBuffer, "document")) + InHeader = FALSE; + + if (CmdBuffer[1] == 'b') + { + if (!(PushErr(ArgBuffer, Line, CmdPtr - Buf, + CmdLen, MakeCpy(), &EnvStack))) + PrintPrgErr(pmNoStackMem); + } + else + { + if ((ei = PopErr(&EnvStack))) + { + if (strcmp(ei->Data, ArgBuffer)) + PrintError(CurStkName(&InputStack), RealBuf, + CmdPtr - Buf, + (long) strlen(CmdBuffer), + Line, emExpectC, ei->Data, ArgBuffer); + + FreeErrInfo(ei); + } + else + PrintError(CurStkName(&InputStack), RealBuf, + CmdPtr - Buf, + (long) strlen(CmdBuffer), + Line, emSoloC, ArgBuffer); + } + + PerformEnv(ArgBuffer, (int) CmdBuffer[1] == 'b'); + } + else + PSERR(CmdPtr - Buf, CmdLen, emNoArgFound); + } + + CheckItal(CmdBuffer); + + if ((ErrNum = PerformCommand(CmdBuffer, BufPtr))) + PSERR(CmdPtr - Buf, CmdLen, ErrNum); + + if (!strcmp(CmdBuffer, "\\cdots")) + realdl = dtCDots; + + if (!strcmp(CmdBuffer, "\\ldots")) + realdl = dtLDots; + + if (!strcmp(CmdBuffer, "\\dots")) + realdl = dtLDots; + + if (realdl != dtUnknown) + { + dotlev = CheckDots(CmdPtr, BufPtr); + if (dotlev && (dotlev != realdl)) + { + const char *cTmpPtr = Dot2Str(dotlev); + PSERRA(CmdPtr - Buf, CmdLen, emEllipsis, cTmpPtr); + } + } + + if ((TmpPtr = HasWord(CmdBuffer, &WipeArg))) + WipeArgument(TmpPtr, CmdPtr); +} + +/* + * Check user abbreviations. Pass a pointer to the `.'; + * also ensure that it's followed by spaces, etc. + * + * Note: We assume that all abbrevs have been transferred from + * AbbrevCase into Abbrev. + */ + +static void CheckAbbrevs(const char *Buffer) +{ + long i; + char *TmpPtr; + const char *AbbPtr; + + if (INUSE(emInterWord)) + { + TmpPtr = TmpBuffer + Abbrev.MaxLen + 2; + *TmpPtr = 0; + AbbPtr = Buffer; + + for (i = Abbrev.MaxLen; i >= 0; i--) + { + *--TmpPtr = *AbbPtr--; + if (!isalpha((unsigned char)*AbbPtr) && HasWord(TmpPtr, &Abbrev)) + PSERR(Buffer - Buf + 1, 1, emInterWord); + if (!*AbbPtr) + break; + } + } +} + + +/* + * Check misc. things which can't be included in the main loop. + * + */ + +static void CheckRest(void) +{ + unsigned long Count; + long CmdLen; + char *UsrPtr; + + /* Search for user-specified warnings */ + +#if ! (HAVE_PCRE || HAVE_POSIX_ERE) + + if (INUSE(emUserWarnRegex) && UserWarnRegex.Stack.Used > 0) + { + PrintPrgErr(pmNoRegExp); + ClearWord( &UserWarnRegex ); + } + else if (INUSE(emUserWarn)) + { + strcpy(TmpBuffer, Buf); + } + +#else + + if (INUSE(emUserWarnRegex) && UserWarnRegex.Stack.Used > 0) + { + static char error[ERROR_STRING_SIZE]; + static regmatch_t MatchVector[NUM_MATCHES]; + int rc; + int len = strlen(TmpBuffer); + strcpy(TmpBuffer, Buf); + + /* Compile all regular expressions if not already compiled. */ + if ( !RegexArray && UserWarnRegex.Stack.Used > 0 ) + { + RegexArray = (regex_t*)malloc( sizeof(regex_t) * UserWarnRegex.Stack.Used ); + if (!RegexArray) + { + /* Allocation failed. */ + PrintPrgErr(pmNoRegexMem); + ClearWord(&UserWarnRegex); + NumRegexes = 0; + } + else + { + NumRegexes = 0; + FORWL(Count, UserWarnRegex) + { + char *pattern = UserWarnRegex.Stack.Data[Count]; + char *CommentEnd = NULL; + + /* See if it's got a special name that it goes by. + Only use the comment if it's at the very beginning. */ + if ( strncmp(pattern,"(?#",3) == 0 ) + { + CommentEnd = strchr(pattern, ')'); + /* TODO: check for PCRE/POSIX only regexes */ + *CommentEnd = '\0'; + /* We're leaking a little here, but this was never freed until exit anyway... */ + UserWarnRegex.Stack.Data[NumRegexes] = pattern+3; + + /* Compile past the end of the comment so that it works with POSIX too. */ + pattern = CommentEnd + 1; + } + + /* Ignore PCRE and POSIX specific regexes. + * This is mostly to make testing easier. */ + if ( strncmp(pattern,"PCRE:",5) == 0 ) + { + #if HAVE_PCRE + pattern += 5; + #else + continue; + #endif + } + if ( strncmp(pattern,"POSIX:",6) == 0 ) + { + #if HAVE_POSIX_ERE + pattern += 6; + #else + continue; + #endif + } + + rc = regcomp((regex_t*)(&RegexArray[NumRegexes]), + pattern, REGEX_FLAGS); + + /* Compilation failed: print the error message */ + if (rc != 0) + { + /* TODO: decide whether a non-compiling regex should completely stop, or just be ignored */ + regerror(rc,(regex_t*)(&RegexArray[NumRegexes]), + error, ERROR_STRING_SIZE); + PrintPrgErr(pmRegexCompileFailed, pattern, error); + } + else + { + if ( !CommentEnd ) + { + ((char*)UserWarnRegex.Stack.Data[NumRegexes])[0] = '\0'; + } + ++NumRegexes; + } + } + } + } + + for (Count = 0; Count < NumRegexes; ++Count) + { + int offset = 0; + char *ErrMessage = UserWarnRegex.Stack.Data[Count]; + const int NamedWarning = strlen(ErrMessage) > 0; + + while (offset < len) + { + /* Check if this warning should be suppressed. */ + if (UserLineSuppressions != 0LL && NamedWarning) + { + /* The warning can be named with positive or negative numbers. */ + int UserWarningNumber = abs(atoi(ErrMessage)); + if (UserLineSuppressions & (1LL << UserWarningNumber)) + { + break; + } + } + + rc = regexec( (regex_t*)(&RegexArray[Count]), TmpBuffer+offset, + NUM_MATCHES, MatchVector, 0); + /* Matching failed: handle error cases */ + if (rc != 0) + { + switch(rc) + { + case REG_NOMATCH: + /* no match, no problem */ + break; + default: + regerror(rc, (regex_t*)(&RegexArray[Count]), + error, ERROR_STRING_SIZE); + PrintPrgErr(pmRegexMatchingError, error); + break; + } + + offset = len; /* break out of loop */ + } + else + { +#define MATCH (MatchVector[0]) + if ( NamedWarning ) + { + /* User specified error message */ + PSERR2(offset + MATCH.rm_so, MATCH.rm_eo - MATCH.rm_so, + emUserWarnRegex, + strlen(ErrMessage), ErrMessage); + } + else + { + /* Default -- show the match */ + PSERR2(offset + MATCH.rm_so, MATCH.rm_eo - MATCH.rm_so, + emUserWarnRegex, + MATCH.rm_eo - MATCH.rm_so, + TmpBuffer + offset + MATCH.rm_so); + } + offset += MATCH.rm_eo; +#undef MATCH + } + } + } + } + else if (INUSE(emUserWarn)) + { + strcpy(TmpBuffer, Buf); + } + +#endif + + + if (INUSE(emUserWarn)) + { + FORWL(Count, UserWarn) + { + for (UsrPtr = TmpBuffer; + (UsrPtr = strstr(UsrPtr, UserWarn.Stack.Data[Count])); + UsrPtr++) + { + CmdLen = strlen(UserWarn.Stack.Data[Count]); + PSERRA(UsrPtr - TmpBuffer, CmdLen, emUserWarn, UserWarn.Stack.Data[Count]); + } + } + + strlwr(TmpBuffer); + + FORWL(Count, UserWarnCase) + { + for (UsrPtr = TmpBuffer; + (UsrPtr = strstr(UsrPtr, UserWarnCase.Stack.Data[Count])); + UsrPtr++) + { + CmdLen = strlen(UserWarnCase.Stack.Data[Count]); + PSERRA(UsrPtr - TmpBuffer, CmdLen, emUserWarn, UserWarnCase.Stack.Data[Count]); + } + } + } +} + + +/* + * Checks that the dash-len is correct. + */ + +static void CheckDash(void) +{ + char *TmpPtr; + int TmpC; + long TmpCount, Len; + struct WordList *wl = NULL; + unsigned long i; + int Errored; + char *PrePtr = &BufPtr[-2]; + + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, TmpC == '-'); + TmpCount = TmpPtr - BufPtr + 1; + + if (MathMode) + { + if (TmpCount > 1) + HERE(TmpCount, emWrongDash); + } + else + { + if (LATEX_SPACE(*PrePtr) && LATEX_SPACE(*TmpPtr)) + wl = &WordDash; + if (isdigit((unsigned char)*PrePtr) && isdigit((unsigned char)*TmpPtr)) + wl = &NumDash; + if (isalpha((unsigned char)*PrePtr) && isalpha((unsigned char)*TmpPtr)) + wl = &HyphDash; + + if (wl) + { + Errored = TRUE; + FORWL(i, *wl) + { + Len = strtol(wl->Stack.Data[i], NULL, 0); + if (TmpCount == Len) + { + Errored = FALSE; + break; + } + } + if (Errored) + HERE(TmpCount, emWrongDash); + } + } +} + +/* + * Pushes and pops nesting characters. + * + */ + +static void HandleBracket(int Char) +{ + unsigned long BrOffset; /* Offset into BrOrder array */ + struct ErrInfo *ei; + int TmpC, Match; + char ABuf[2], BBuf[2]; + char *TmpPtr; + + AddBracket(Char); + + if ((BrOffset = BrackIndex(Char)) != ~0UL) + { + if (BrOffset & 1) /* Closing bracket of some sort */ + { + if ((ei = PopErr(&CharStack))) + { + Match = MatchBracket(*(ei->Data)); + /* Return italics to proper state */ + if (ei->Flags & efNoItal) + { + if (ItState == itOn) + { + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, TmpC == '}'); + + /* If the next character is a period or comma, + * or the last character is, then it's not an + * error. */ + /* Checking 2 characters back seems dangerous, + * but it's already done in CheckDash. */ + if ( !strchr(LTX_SmallPunc, *TmpPtr) && + !strchr(LTX_SmallPunc, *(TmpPtr-2)) ) + HERE(1, emNoItFound); + } + + ItState = FALSE; + } + else if (ei->Flags & efItal) + ItState = TRUE; + + /* Same for math mode */ + if (ei->Flags & efMath) + { + MathMode = 1; + } + else if (ei->Flags & efNoMath) + { + MathMode = 0; + } + + FreeErrInfo(ei); + } + else + Match = 0; + + if (Match != Char) + { + ABuf[0] = Match; + BBuf[0] = Char; + ABuf[1] = BBuf[1] = 0; + if (Match) + PrintError(CurStkName(&InputStack), RealBuf, + BufPtr - Buf - 1, 1, Line, emExpectC, + ABuf, BBuf); + else + HEREA(1, emSoloC, BBuf); + } + + } + else /* Opening bracket of some sort */ + { + if ((ei = PushChar(Char, Line, BufPtr - Buf - 1, + &CharStack, MakeCpy()))) + { + if (Char == '{') + { + switch (ItFlag) + { + default: + ei->Flags |= ItFlag; + ItFlag = efNone; + break; + case efNone: + ei->Flags |= ItState ? efItal : efNoItal; + } + + switch (MathFlag) + { + default: + ei->Flags |= MathFlag; + MathFlag = efNone; + break; + case efNone: + ei->Flags |= MathMode ? efMath : efNoMath; + } + } + } + + else + PrintPrgErr(pmNoStackMem); + } + } +} + + +/* + * Checks to see if CmdBuffer matches any of the words in Silent, or + * any of the regular expressions in SilentCase. + * + */ + +int CheckSilentRegex(void) +{ + +#if ! (HAVE_PCRE || HAVE_POSIX_ERE) + + return HasWord(CmdBuffer, &Silent); + +#else + + static char error[ERROR_STRING_SIZE]; + char *pattern; + char *tmp; + int i; + int rc; + int len = 4; /* Enough for the (?:) */ + + /* Initialize regular expression */ + if (INUSE(emSpaceTerm) && SilentCase.Stack.Used > 0) + { + /* Find the total length we need */ + /* There is 1 for | and the final for null terminator */ + FORWL(i, SilentCase) + { + len += strlen( SilentCase.Stack.Data[i] ) + 1; + } + + /* (A|B|...) */ + tmp = (pattern = (char*)malloc( sizeof(char) * len )); + + #if HAVE_PCRE + tmp = stpcpy(tmp,"(?:"); + #else + tmp = stpcpy(tmp,"("); + #endif + + FORWL(i, SilentCase) + { + tmp = stpcpy(tmp, SilentCase.Stack.Data[i]); + *tmp++ = '|'; + } + tmp = stpcpy(--tmp, ")"); + + SilentRegex = malloc( sizeof(regex_t) ); + rc = regcomp(SilentRegex, pattern, REGEX_FLAGS); + + /* Compilation failed: print the error message */ + if (rc != 0) + { + regerror(rc, SilentRegex, error, ERROR_STRING_SIZE); + PrintPrgErr(pmRegexCompileFailed, pattern, error); + SilentRegex = NULL; + } + /* Ensure we won't initialize it again */ + SilentCase.Stack.Used = 0; + free(pattern); + } + + /* Check against the normal */ + if ( HasWord(CmdBuffer, &Silent) ) + return 1; + if (!SilentRegex) + return 0; + + /* Check against the regexes */ + rc = regexec(SilentRegex, CmdBuffer, 0, NULL, 0); + if (rc == 0) + return 1; + + /* Matching failed: handle error cases */ + switch(rc) + { + case REG_NOMATCH: + return 0; + break; + default: + regerror(rc, SilentRegex, error, ERROR_STRING_SIZE); + PrintPrgErr(pmRegexMatchingError, error); + break; + } + return 0; + +#endif +} + +/* + * Searches the `Buf' for possible errors, and prints the errors. `Line' + * is supplied for error printing. + */ + +int FindErr(const char *_RealBuf, const unsigned long _Line) +{ + char *CmdPtr; /* We'll have to copy each command out. */ + char *PrePtr; /* Ptr to char in front of command, NULL if + * the cmd appears as the first character */ + char *TmpPtr; /* Temporary pointer */ + char *ErrPtr; /* Ptr to where an error started */ + + int TmpC, /* Just a temp var used throughout the proc. */ + MatchC, Char; /* Char. currently processed */ + unsigned long CmdLen; /* Length of misc. things */ + int MixingQuotes; + + int (*pstcb) (int c); + + enum DotLevel dotlev; + + LineCpy = NULL; + + if (_RealBuf) + { + RealBuf = _RealBuf; + Line = _Line; + + BufPtr = PreProcess(); + + BufPtr = SkipVerb(); + + while (BufPtr && *BufPtr) + { + PrePtr = BufPtr - 1; + Char = *BufPtr++; + if (isspace((unsigned char)Char)) + Char = ' '; + + switch (Char) + { + case '~': + TmpPtr = NULL; + if (isspace((unsigned char)*PrePtr)) + TmpPtr = PrePtr; + else if (isspace((unsigned char)*BufPtr)) + TmpPtr = BufPtr; + + if (TmpPtr) + PSERR(TmpPtr - Buf, 1, emDblSpace); + break; + + case 'X': + case 'x': + TmpPtr = PrePtr; + + SKIP_BACK(TmpPtr, TmpC, + (LATEX_SPACE(TmpC) || strchr("{}$", TmpC))); + + if (isdigit((unsigned char)*TmpPtr)) + { + TmpPtr = BufPtr; + + SKIP_AHEAD(TmpPtr, TmpC, + (LATEX_SPACE(TmpC) || strchr("{}$", TmpC))); + + if (isdigit((unsigned char)*TmpPtr)) + HERE(1, emUseTimes); + } + /* FALLTHRU */ + /* CTYPE: isalpha() */ + case 'a': + case 'b': + case 'c': + case 'd': + case 'e': + case 'f': + case 'g': + case 'h': + case 'i': + case 'j': + case 'k': + case 'l': + case 'm': + case 'n': + case 'o': + case 'p': + case 'q': + case 'r': + case 's': + case 't': + case 'u': + case 'v': + case 'w': /* case 'x': */ + case 'y': + case 'z': + + case 'A': + case 'B': + case 'C': + case 'D': + case 'E': + case 'F': + case 'G': + case 'H': + case 'I': + case 'J': + case 'K': + case 'L': + case 'M': + case 'N': + case 'O': + case 'P': + case 'Q': + case 'R': + case 'S': + case 'T': + case 'U': + case 'V': + case 'W': /* case 'X': */ + case 'Y': + case 'Z': + if (!isalpha((unsigned char)*PrePtr) && (*PrePtr != '\\') && MathMode) + { + TmpPtr = BufPtr; + CmdPtr = CmdBuffer; + do + { + *CmdPtr++ = Char; + Char = *TmpPtr++; + } + while (isalpha((unsigned char)Char)); + + *CmdPtr = 0; + + if (HasWord(CmdBuffer, &MathRoman)) + HEREA(strlen(CmdBuffer), emWordCommand, CmdBuffer); + } + + break; + case ' ': + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + + if (*TmpPtr && *PrePtr) + { + if ((TmpPtr - BufPtr) > 0) + { + HERE(TmpPtr - BufPtr + 1, emMultiSpace); + strwrite(BufPtr, VerbClear, TmpPtr - BufPtr - 1); + } + } + break; + + case '.': + if ((Char == *BufPtr) && (Char == BufPtr[1])) + { + const char *cTmpPtr; + dotlev = CheckDots(&PrePtr[1], &BufPtr[2]); + cTmpPtr = Dot2Str(dotlev); + HEREA(3, emEllipsis, cTmpPtr); + } + + /* Regexp: "([^A-Z@.])\.[.!?:]*\s+[a-z]" */ + + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, strchr(LTX_EosPunc, TmpC)); + if (LATEX_SPACE(*TmpPtr)) + { + if (!isupper((unsigned char)*PrePtr) && (*PrePtr != '@') && + (*PrePtr != '.')) + { + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + if (islower((unsigned char)*TmpPtr)) + PSERR(BufPtr - Buf, 1, emInterWord); + else + CheckAbbrevs(&BufPtr[-1]); + } + } + + /* FALLTHRU */ + case ':': + case '?': + case '!': + case ';': + /* Regexp: "[A-Z][A-Z][.!?:;]\s+" */ + + if (isspace((unsigned char)*BufPtr) && isupper((unsigned char)*PrePtr) && + (isupper((unsigned char)PrePtr[-1]) || (Char != '.'))) + HERE(1, emInterSent); + + /* FALLTHRU */ + case ',': + if (isspace((unsigned char)*PrePtr) && + !(isdigit((unsigned char)*BufPtr) && + ((BufPtr[-1] == '.') || (BufPtr[-1] == ',')))) + PSERR(PrePtr - Buf, 1, emSpacePunct); + + if (MathMode && + (((*BufPtr == '$') && (BufPtr[1] != '$')) || + (!strafter(BufPtr, "\\)")))) + HEREA(1, emPunctMath, "outside inner"); + + if (!MathMode && + (((*PrePtr == '$') && (PrePtr[-1] == '$')) || + (!strinfront(PrePtr, "\\]")))) + HEREA(1, emPunctMath, "inside display"); + + break; + case '\'': + case '`': + if ((Char == *BufPtr) && (Char == BufPtr[1])) + { + PrintError(CurStkName(&InputStack), RealBuf, + BufPtr - Buf - 1, 3, Line, + emThreeQuotes, + Char, Char, Char, Char, Char, Char); + } + + if (Char == '\'') + MatchC = '`'; + else + MatchC = '\''; + + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, TmpC == Char); + + MixingQuotes = FALSE; + + if ((*TmpPtr == MatchC) || (*TmpPtr == '\"') || + (*TmpPtr == '´')) + MixingQuotes = TRUE; + + SKIP_AHEAD(TmpPtr, TmpC, strchr("`\'\"´", TmpC)); + + if (MixingQuotes) + HERE(TmpPtr - BufPtr + 1, emQuoteMix); + + switch (Char) + { + case '\'': + if (isalpha((unsigned char)*TmpPtr) && + (strchr(LTX_GenPunc, *PrePtr) || isspace((unsigned char)*PrePtr))) + HERE(TmpPtr - BufPtr + 1, emBeginQ); + + /* Now check quote style */ +#define ISPUNCT(ptr) (strchr(LTX_GenPunc, *ptr) && (ptr[-1] != '\\')) + + /* We ignore all single words/abbreviations in quotes */ + + { + char *WordPtr = PrePtr; + SKIP_BACK(WordPtr, TmpC, (isalnum((unsigned char)TmpC) || + strchr(LTX_GenPunc, TmpC))); + + if (*WordPtr != '`') + { + if (*PrePtr && (Quote != quTrad) + && ISPUNCT(PrePtr)) + PSERRA(PrePtr - Buf, 1, + emQuoteStyle, "in front of"); + + if (*TmpPtr && (Quote != quLogic) + && ISPUNCT(TmpPtr)) + PSERRA(TmpPtr - Buf, 1, + emQuoteStyle, "after"); + } + } + + break; + case '`': + if (isalpha((unsigned char)*PrePtr) && + (strchr(LTX_GenPunc, *TmpPtr) || isspace((unsigned char)*TmpPtr))) + HERE(TmpPtr - BufPtr + 1, emEndQ); + break; + } + BufPtr = TmpPtr; + break; + case '"': + HERE(1, emUseQuoteLiga); + break; + + /* One of these are unnecessary, but what the heck... */ + case 180: /* ´. NOTE: '\xb4' gets converted to - something */ + case ~(0xff & (~180)): /* This yields 0xff...fb4 in */ + /* arbitrary precision. */ + + HERE(1, emUseOtherQuote); + break; + + case '_': + case '^': + if (*PrePtr != '\\') + { + TmpPtr = PrePtr; + SKIP_BACK(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + + CmdLen = 1; + + switch (*TmpPtr) + { + /*{ */ + case '}': + if (PrePtr[-1] != '\\') + break; + + CmdLen++; + PrePtr--; + /* FALLTHRU */ + /*[( */ + case ')': + case ']': + PSERR(PrePtr - Buf, CmdLen, emEnclosePar); + } + + TmpPtr = BufPtr; + SKIP_AHEAD(TmpPtr, TmpC, LATEX_SPACE(TmpC)); + + ErrPtr = TmpPtr; + + if (isalpha((unsigned char)*TmpPtr)) + pstcb = &my_isalpha; + else if (isdigit((unsigned char)*TmpPtr)) + pstcb = &my_isdigit; + else + break; + + while ((*pstcb) (*TmpPtr++)) + ; + TmpPtr--; + + if ((TmpPtr - ErrPtr) > 1) + PSERR(ErrPtr - Buf, TmpPtr - ErrPtr, emEmbrace); + } + break; + case '-': + CheckDash(); + break; + case '\\': /* Command encountered */ + BufPtr = GetLTXToken(--BufPtr, CmdBuffer); + + if (LATEX_SPACE(*PrePtr)) + { + if (HasWord(CmdBuffer, &Linker)) + PSERR(PrePtr - Buf, 1, emNBSpace); + if (HasWord(CmdBuffer, &PostLink)) + PSERR(PrePtr - Buf, 1, emFalsePage); + } + + if (LATEX_SPACE(*BufPtr) && !MathMode && + !CheckSilentRegex() && + (strlen(CmdBuffer) != 2)) + { + PSERR(BufPtr - Buf, 1, emSpaceTerm); + } + else if ((*BufPtr == '\\') && (!isalpha((unsigned char)BufPtr[1])) && + (!LATEX_SPACE(BufPtr[1]))) + PSERR(BufPtr - Buf, 2, emNotIntended); + + PerformBigCmd(PrePtr + 1); + BufPtr = SkipVerb(); + + break; + + case '(': + if (*PrePtr && !LATEX_SPACE(*PrePtr) && !isdigit((unsigned char)*PrePtr) + && !strchr("([{`~", *PrePtr)) + { + if (PrePtr[-1] != '\\') /* Short cmds */ + { + TmpPtr = PrePtr; + SKIP_BACK(TmpPtr, TmpC, istex(TmpC)); + if (*TmpPtr != '\\') /* Long cmds */ + PSERRA(BufPtr - Buf - 1, 1, emSpaceParen, + "in front of"); + } + } + if (isspace((unsigned char)*BufPtr)) + PSERRA(BufPtr - Buf, 1, emNoSpaceParen, "after"); + HandleBracket(Char); + break; + + case ')': + if (isspace((unsigned char)*PrePtr)) + PSERRA(BufPtr - Buf - 1, 1, emNoSpaceParen, + "in front of"); + if (isalpha((unsigned char)*BufPtr)) + PSERRA(BufPtr - Buf, 1, emSpaceParen, "after"); + HandleBracket(Char); + break; + + case '}': + case '{': + case '[': + case ']': + HandleBracket(Char); + break; + case '$': + if (*PrePtr != '\\') + { + if (*BufPtr == '$') + BufPtr++; + MathMode ^= TRUE; + } + + break; + } + } + + if (!VerbMode) + { + CheckRest(); + } + + } + + return (TRUE); +} + +/* + * Tries to create plural forms for words. Put a '%s' where a + * suffix should be put, e.g. "warning%s". Watch your %'s! + */ + +static void Transit(FILE * fh, unsigned long Cnt, const char *Str) +{ + switch (Cnt) + { + case 0: + fputs("No ", fh); + fprintf(fh, Str, "s"); + break; + case 1: + fputs("One ", fh); + fprintf(fh, Str, ""); + break; + default: + fprintf(fh, "%ld ", Cnt); + fprintf(fh, Str, "s"); + break; + } +} + +/* + * Prints the status/conclusion after doing all the testing, including + * bracket stack status, math mode, etc. + */ + +void PrintStatus(unsigned long Lines) +{ + unsigned long Cnt; + struct ErrInfo *ei; + + + while ((ei = PopErr(&CharStack))) + { + PrintError(ei->File, ei->LineBuf, ei->Column, + ei->ErrLen, ei->Line, emNoMatchC, (char *) ei->Data); + FreeErrInfo(ei); + } + + while ((ei = PopErr(&EnvStack))) + { + PrintError(ei->File, ei->LineBuf, ei->Column, + ei->ErrLen, ei->Line, emNoMatchC, (char *) ei->Data); + FreeErrInfo(ei); + } + + if (MathMode) + { + PrintError(CurStkName(&InputStack), "", 0L, 0L, Lines, emMathStillOn); + } + + for (Cnt = 0L; Cnt < (NUMBRACKETS >> 1); Cnt++) + { + if (Brackets[Cnt << 1] != Brackets[(Cnt << 1) + 1]) + { + PrintError(CurStkName(&InputStack), "", 0L, 0L, Lines, + emNoMatchCC, + BrOrder[Cnt << 1], BrOrder[(Cnt << 1) + 1]); + } + } + + if (!Quiet) + { + Transit(stderr, ErrPrint, "error%s printed; "); + Transit(stderr, WarnPrint, "warning%s printed; "); + Transit(stderr, UserSupp, "user suppressed warning%s; "); + Transit(stderr, LineSupp, "line suppressed warning%s.\n"); + } +} + + + +/* + * Uses OutputFormat. Be sure that `String' + * does not contain tabs, newlines, etc. + * Prints a formatted string. Formatting codes understood: + * %b - string to print Between fields (from -s option) + * %c - Column position of error + * %d - lenght of error (Digit) + * %f - current Filename + * %i - Turn on inverse printing mode. + * %I - Turn off inverse printing mode. + * %k - Kind of error (warning, error, message) + * %l - Line number of error + * %m - warning Message + * %n - warning Number + * %u - an Underlining line (like the one which appears when using -v1) + * %r - part of line in front of error ('S' - 1) + * %s - part of line which contains error (String) + * %t - part of line after error ('S' + 1) + */ + + +void +PrintError(const char *File, const char *String, + const long Position, const long Len, + const long LineNo, const enum ErrNum Error, ...) +{ + static /* Just to reduce stack usage... */ + char PrintBuffer[BUFSIZ]; + va_list MsgArgs; + + char *LastNorm = OutputFormat; + char *of; + int c; + + enum Context Context; + + if (betw(emMinFault, Error, emMaxFault)) + { + switch (LaTeXMsgs[Error].InUse) + { + case iuOK: + if (SUPPRESSED_ON_LINE(Error)) + { + LineSupp++; + } + else + { + Context = LaTeXMsgs[Error].Context; + + if (!HeadErrOut) + Context |= ctOutHead; + +#define RGTCTXT(Ctxt, Var) if((Context & Ctxt) && !(Var)) break; + + RGTCTXT(ctInMath, MathMode); + RGTCTXT(ctOutMath, !MathMode); + RGTCTXT(ctInHead, InHeader); + RGTCTXT(ctOutHead, !InHeader); + + switch (LaTeXMsgs[Error].Type) + { + case etWarn: + WarnPrint++; + break; + case etErr: + ErrPrint++; + break; + case etMsg: + break; + } + + while ((of = strchr(LastNorm, '%'))) + { + c = *of; + *of = 0; + + fputs(LastNorm, OutputFile); + + *of++ = c; + + switch (c = *of++) + { + case 'b': + fputs(Delimit, OutputFile); + break; + case 'c': + fprintf(OutputFile, "%ld", Position + 1); + break; + case 'd': + fprintf(OutputFile, "%ld", Len); + break; + case 'f': + fputs(File, OutputFile); + break; + case 'i': + fputs(ReverseOn, OutputFile); + break; + case 'I': + fputs(ReverseOff, OutputFile); + break; + case 'k': + switch (LaTeXMsgs[Error].Type) + { + case etWarn: + fprintf(OutputFile, "Warning"); + break; + case etErr: + fprintf(OutputFile, "Error"); + break; + case etMsg: + fprintf(OutputFile, "Message"); + break; + } + break; + case 'l': + fprintf(OutputFile, "%ld", LineNo); + break; + case 'm': + va_start(MsgArgs, Error); + vfprintf(OutputFile, + LaTeXMsgs[Error].Message, MsgArgs); + va_end(MsgArgs); + break; + case 'n': + fprintf(OutputFile, "%d", Error); + break; + case 'u': + sfmemset(PrintBuffer, ' ', (long) Position); + + sfmemset(&PrintBuffer[Position], '^', Len); + PrintBuffer[Position + Len] = 0; + fputs(PrintBuffer, OutputFile); + break; + case 'r': + substring(String, PrintBuffer, 0L, Position); + fputs(PrintBuffer, OutputFile); + break; + case 's': + substring(String, PrintBuffer, Position, Len); + fputs(PrintBuffer, OutputFile); + break; + case 't': + substring(String, PrintBuffer, + Position + Len, LONG_MAX); + fputs(PrintBuffer, OutputFile); + break; + default: + fputc(c, OutputFile); + break; + } + LastNorm = of; + } + fputs(LastNorm, OutputFile); + } + break; + case iuNotUser: + UserSupp++; + break; + case iuNotSys: + break; + } + } +} + +/* + * All commands isolated is routed through this command, so we can + * update global statuses like math mode and whether @ is a letter + * or not. + */ + +static enum ErrNum PerformCommand(const char *Cmd, char *Arg) +{ + const char *Argument = ""; + enum ErrNum en = emMinFault; + int TmpC; + + if (!strcmp(Cmd, "\\makeatletter")) + AtLetter = TRUE; + else if (!strcmp(Cmd, "\\makeatother")) + AtLetter = FALSE; + else if (InputFiles && !(strcmp(Cmd, "\\input") && strcmp(Cmd, "\\include"))) + { + SKIP_AHEAD(Arg, TmpC, LATEX_SPACE(TmpC)); + if (*Arg == '{') /* } */ + { + if (GetLTXArg(Arg, TmpBuffer, GET_STRIP_TOKEN, NULL)) + Argument = TmpBuffer; + } + else + Argument = strip(Arg, STRP_BTH); + + if (!(Argument && PushFileName(Argument, &InputStack))) + en = emNoCmdExec; + } + else if (HasWord(Cmd, &Primitives)) + en = emTeXPrim; + else if (HasWord(Cmd, &MathCmd)) + { + SKIP_AHEAD(Arg, TmpC, LATEX_SPACE(TmpC)); + if (*Arg == '{') + { + MathFlag = MathMode ? efMath : efNoMath; + MathMode = 1; + } + } + else if (HasWord(Cmd, &TextCmd)) + { + SKIP_AHEAD(Arg, TmpC, LATEX_SPACE(TmpC)); + if (*Arg == '{') + { + MathFlag = MathMode ? efMath : efNoMath; + MathMode = 0; + } + } + else if (*Cmd == '\\') + { + /* Quicker check of single lettered commands. */ + switch (Cmd[1]) + { + case '(': + case '[': + MathMode = TRUE; + break; + case ']': + case ')': + MathMode = FALSE; + break; + case '/': + switch (ItState) + { + case itOn: + ItState = itCorrected; + Argument = Arg; + + SKIP_AHEAD(Argument, TmpC, TmpC == '{' || TmpC == '}'); + + if (strchr(".,", *Argument)) + en = emItPunct; + + break; + case itCorrected: + en = emItDup; + break; + case itOff: + en = emItInNoIt; + } + break; + } + } + + return (en); +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/FindErrs.h b/Build/source/texk/chktex/chktex-1.7.1/FindErrs.h new file mode 100644 index 00000000000..c938a365928 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/FindErrs.h @@ -0,0 +1,196 @@ +/* + * ChkTeX, header file for main program. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#ifndef FINDERRS_H +#define FINDERRS_H +#include "ChkTeX.h" + + +#undef ERRMSGS +#undef MSG + +#define ERRMSGS \ + MSG(emMinFault, etErr, iuOK, ctNone,\ + INTERNFAULT)\ + MSG(emSpaceTerm, etWarn, iuOK, ctOutMath,\ + "Command terminated with space.")\ + MSG(emNBSpace, etWarn, iuOK, ctNone,\ + "Non-breaking space (`~') should have been used.")\ + MSG(emEnclosePar, etWarn, iuOK, ctInMath,\ + "You should enclose the previous parenthesis with `{}\'.")\ + MSG(emItInNoIt, etWarn, iuOK, ctNone,\ + "Italic correction (`\\/') found in non-italic buffer.")\ + MSG(emItDup, etWarn, iuOK, ctNone,\ + "Italic correction (`\\/') found more than once.")\ + MSG(emNoItFound, etWarn, iuOK, ctNone,\ + "No italic correction (`\\/') found.")\ + MSG(emAccent, etWarn, iuOK, ctNone,\ + "Accent command `%s' needs use of `\\%c%s'.")\ + MSG(emWrongDash, etWarn, iuOK, ctOutMath,\ + "Wrong length of dash may have been used.")\ + MSG(emExpectC, etWarn, iuOK, ctNone,\ + "`%s' expected, found `%s'.")\ + MSG(emSoloC, etWarn, iuOK, ctNone,\ + "Solo `%s' found.")\ + MSG(emEllipsis, etWarn, iuOK, ctNone,\ + "You should use %s to achieve an ellipsis.")\ + MSG(emInterWord, etWarn, iuOK, ctOutMath,\ + "Interword spacing (`\\ ') should perhaps be used.")\ + MSG(emInterSent, etWarn, iuOK, ctOutMath,\ + "Intersentence spacing (`\\@') should perhaps be used.")\ + MSG(emNoArgFound, etErr, iuOK, ctNone,\ + "Could not find argument for command.")\ + MSG(emNoMatchC, etWarn, iuOK, ctOutMath,\ + "No match found for `%s'.")\ + MSG(emMathStillOn, etWarn, iuOK, ctNone,\ + "Mathmode still on at end of LaTeX file.")\ + MSG(emNoMatchCC, etWarn, iuOK, ctNone,\ + "Number of `%c' doesn't match the number of `%c'!")\ + MSG(emUseQuoteLiga, etWarn, iuOK, ctNone,\ + "Use either `` or '' as an alternative to `\"'.")\ + MSG(emUseOtherQuote, etWarn, iuOK, ctNone,\ + "Use \"'\" (ASCII 39) instead of \"´\" (ASCII 180).")\ + MSG(emUserWarn, etWarn, iuOK, ctNone,\ + "User-specified pattern found: %s.")\ + MSG(emNotIntended, etWarn, iuNotSys, ctNone,\ + "This command might not be intended.")\ + MSG(emComment, etMsg, iuNotSys, ctNone,\ + "Comment displayed.")\ + MSG(emThreeQuotes, etWarn, iuOK, ctNone,\ + "Either %c\\,%c%c or %c%c\\,%c will look better.")\ + MSG(emFalsePage, etWarn, iuOK, ctOutMath,\ + "Delete this space to maintain correct pagereferences.")\ + MSG(emEmbrace, etWarn, iuOK, ctInMath,\ + "You might wish to put this between a pair of `{}'")\ + MSG(emSpacePunct, etWarn, iuOK, ctOutMath,\ + "You ought to remove spaces in front of punctuation.")\ + MSG(emNoCmdExec, etWarn, iuOK, ctNone,\ + "Could not execute LaTeX command.")\ + MSG(emItPunct, etWarn, iuOK, ctNone,\ + "Don't use \\/ in front of small punctuation.")\ + MSG(emUseTimes, etWarn, iuOK, ctNone,\ + "$\\times$ may look prettier here.")\ + MSG(emMultiSpace, etWarn, iuNotSys, ctOutMath,\ + "Multiple spaces detected in input.")\ + MSG(emIgnoreText, etWarn, iuOK, ctNone,\ + "This text may be ignored.")\ + MSG(emBeginQ, etWarn, iuOK, ctOutMath,\ + "Use ` to begin quotation, not '.")\ + MSG(emEndQ, etWarn, iuOK, ctOutMath,\ + "Use ' to end quotation, not `.")\ + MSG(emQuoteMix, etWarn, iuOK, ctNone,\ + "Don't mix quotes.")\ + MSG(emWordCommand, etWarn, iuOK, ctInMath,\ + "You should perhaps use `\\%s' instead.")\ + MSG(emSpaceParen, etWarn, iuOK, ctOutMath,\ + "You should put a space %s parenthesis.")\ + MSG(emNoSpaceParen, etWarn, iuOK, ctOutMath,\ + "You should avoid spaces %s parenthesis.")\ + MSG(emQuoteStyle, etWarn, iuOK, ctOutMath,\ + "You should not use punctuation %s quotes.")\ + MSG(emDblSpace, etWarn, iuOK, ctOutMath,\ + "Double space found.")\ + MSG(emPunctMath, etWarn, iuOK, ctNone,\ + "You should put punctuation %s math mode.")\ + MSG(emTeXPrim, etWarn, iuNotSys, ctNone,\ + "You ought to not use primitive TeX in LaTeX code.")\ + MSG(emRemPSSpace, etWarn, iuOK, ctOutMath,\ + "You should remove spaces in front of `%s'") \ + MSG(emNoCharMean, etWarn, iuOK, ctNone,\ + "`%s' is normally not followed by `%c'.")\ + MSG(emUserWarnRegex, etWarn, iuOK, ctNone,\ + "User Regex: %.*s.") + +#undef MSG +#define MSG(num, type, inuse, ctxt, text) num, + +enum ErrNum +{ + ERRMSGS emMaxFault +}; +#undef MSG + +enum Context +{ + ctNone = 0x00, + ctInMath = 0x01, + ctOutMath = 0x02, + ctInHead = 0x04, + ctOutHead = 0x08 +}; + +struct ErrMsg +{ + enum ErrNum Number; + enum + { + etMsg, + etWarn, + etErr + } Type; + + enum + { + iuNotSys, + iuNotUser, + iuOK + } InUse; + + /* Requirements posed upon environment */ + enum Context Context; + + const char *Message; +}; + +enum ItState +{ + itOff, + itOn, + itCorrected +}; + + +enum DotLevel +{ + dtUnknown = 0x0, + dtCDots = 0x1, + dtLDots = 0x2, + dtDots = 0x4 +}; + +extern struct ErrMsg LaTeXMsgs[emMaxFault + 1]; + +extern char *OutputFormat; + +int CheckSilentRegex(void); +int FindErr(const char *, const unsigned long); +void PrintError(const char *, const char *, const long, const long, + const long, const enum ErrNum, ...); +void PrintStatus(unsigned long Lines); + +#endif /* FINDERRS */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/MakeHTML.pl b/Build/source/texk/chktex/chktex-1.7.1/MakeHTML.pl new file mode 100644 index 00000000000..6bdbadcf127 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/MakeHTML.pl @@ -0,0 +1,20 @@ +# Remove parts of code enclosed in %latex/%endlatex tags + +$latexonly = 0; + +while(<>) +{ + $latexonly = 1 if /^%latex/i; + $latexonly = 0 if /^%endlatex/i; + + + if($latexonly) { + if(/^%!(.*)/) + { + print $1; + } + } + else { + print; + } +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/Makefile.in b/Build/source/texk/chktex/chktex-1.7.1/Makefile.in new file mode 100644 index 00000000000..ee8dda3eead --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Makefile.in @@ -0,0 +1,322 @@ +# +# Makefile for ChkTeX project, creates the stuff. +# Copyright (C) 1996 Jens T. Berger Thielemann +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# Contact the author at: +# Jens Berger +# Spektrumvn. 4 +# N-0666 Oslo +# Norway +# E-mail: +# + + +prefix=@prefix@ +exec_prefix=@exec_prefix@ +bindir=@bindir@ +datarootdir=@datarootdir@ +datadir=@datadir@ +sysconfdir=@sysconfdir@ +srcdir=@srcdir@ +mandir=@mandir@ +INSTALL=@INSTALL@ +INSTALL_PROGRAM=@INSTALL_PROGRAM@ +INSTALL_DATA=@INSTALL_DATA@ +MKDIR_P=@MKDIR_P@ +ELISPDIR=@ELISPDIR@ +CLEAN=@CLEAN@ + +CC=@CC@ +CFLAGS=@CFLAGS@ +CPPFLAGS=@CPPFLAGS@ -I$(srcdir) -I. $(DEFS) $(USRDEFS) +DEFS=@DEFS@ +LIBS=@LIBS@ +LDFLAGS=@LDFLAGS@ +LN_S=@LN_S@ +LATEX=@LATEX@ +DVIPS=@DVIPS@ +PS2PDF=ps2pdf +PERL5=@PERL5@ +LATEX2HTML=@LATEX2HTML@ +LYNX=@LYNX@ +GROFF=@GROFF@ +SHELL=/bin/sh + +BUILT_SCRIPTS=@BUILT_SCRIPTS@ +SCRIPTS=@SCRIPTS@ + +USRDEFS=-DSYSCONFDIR=\"$(sysconfdir)\" -D__unix__ + +VPATH=$(srcdir) + +##################################################################### + +EXTRA_DIST=configure.in Makefile.in stamp-h.in config.h.in rmeheader.in \ + MakeHTML.pl ChkTeX.tex.in aclocal.m4 NEWS \ + chktex.el chkweb deweb.in COPYING chktex.1 chkweb.1 deweb.1 \ + Test.tex input.tex Test.out configure install-sh lacheck chktexrc \ + $(wildcard m4/*.m4) + +# created by configure +CONFIG_DIST=ChkTeX.tex + +# created at make time +BUILT_DIST=chktex.doc chkweb.doc deweb.doc README ChkTeX.dvi + +CSOURCES=ChkTeX.c FindErrs.c OpSys.c Resource.c Utility.c + +# The sources are the C sources and possibly the files with the same base name +# but ending with .h +SOURCEFILES=$(CSOURCES) $(wildcard $(CSOURCES:.c=.h)) types.h + +DISTFILES=$(EXTRA_DIST) $(SOURCEFILES) + +all: chktex + +DISTDIR:=chktex-@PACKAGE_VERSION@ +dist: $(DISTDIR).tar.gz +$(DISTDIR).tar.gz: $(DISTFILES) $(CONFIG_DIST) $(BUILT_DIST) html + rm -r $(DISTDIR) 2>/dev/null ; true + $(MKDIR_P) $(DISTDIR) + for f in $(DISTFILES) ; do \ + cp $(srcdir)/$$f $(DISTDIR) ; \ + done + cp $(CONFIG_DIST) $(BUILT_DIST) $(DISTDIR) + $(MKDIR_P) $(DISTDIR)/html + cp HTML/ChkTeX/*.{html,css} $(DISTDIR)/html + rm -f $(DISTDIR).tar.gz + tar --owner=0 --group=0 -chzf $@ $(DISTDIR) + rm -rf $(DISTDIR) + +######################################################################## + +.c.o: + $(CC) $(CPPFLAGS) $(CFLAGS) -c $< -o $@ +CLEAN+=$(CSOURCES:.c=.o) + +.%.d: %.c + $(CC) -M $(CPPFLAGS) $< > $@.tmp + sed 's,\($*\)\.o *:,\1.o $@ : Makefile,g' $@.tmp > $@ + -rm -f $@.tmp 2>/dev/null + +DEPFILES=$(patsubst %.c,.%.d,$(CSOURCES)) +CLEAN+=$(DEPFILES) + +ifeq ($(findstring clean,$(MAKECMDGOALS)),) +include $(DEPFILES) +endif + +###################### MAIN DEPENDENCIES ################################ + +OBJS= ChkTeX.o FindErrs.o OpSys.o Resource.o Utility.o + +MAKETEST= (builddir=`pwd` ; cd $(srcdir) ; $${builddir}/chktex -mall -r -g0 -lchktexrc -v5 Test.tex) + +$(srcdir)/Test.out: $(srcdir)/Test.tex + -rm -f $(srcdir)/Test.out + @echo "" + @echo "***Warning: creating Test.out***" + @echo "" + $(MAKETEST) 1> $(srcdir)/Test.out + +check: chktex $(srcdir)/Test.out + @echo ">>> Testing that checking algorithms work correctly..." + @-rm -f chktest + $(MAKETEST) 1> chktest + @if cmp -s chktest $(srcdir)/Test.out; then \ + echo ">>> OK!"; \ + rm -f chktest; \ + else \ + echo "***WARNING***"; \ + echo "Problems when checking compilation. This may or may not"; \ + echo "be a problem; anyway, I'm giving you a diff from what the"; \ + echo "results were *supposed* to be..."; \ + diff -u $(srcdir)/Test.out chktest; \ + fi + + +chktex: $(OBJS) + $(CC) $(LDFLAGS) -o chktex $(OBJS) $(LIBS) + +install: chktex ChkTeX.dvi + $(MKDIR_P) $(DESTDIR)$(bindir) + for program in chktex $(BUILT_SCRIPTS); do \ + $(INSTALL_PROGRAM) $$program $(DESTDIR)$(bindir); \ + done + for program in $(SCRIPTS); do \ + $(INSTALL_PROGRAM) $(srcdir)/$$program $(DESTDIR)$(bindir); \ + done + $(MKDIR_P) $(DESTDIR)$(sysconfdir) + $(INSTALL_DATA) $(srcdir)/chktexrc $(DESTDIR)$(sysconfdir) + if (eval echo "$(BUILT_SCRIPTS)") | egrep deweb >/dev/null 2>&1; then \ + $(MKDIR_P) $(DESTDIR)$(mandir)/man1; \ + cp $(srcdir)/deweb.1 $(DESTDIR)$(mandir)/man1; \ + fi + if (eval echo "$(ELISPDIR)") | egrep "/" >/dev/null 2>&1; then \ + $(INSTALL_DATA) $(srcdir)/chktex.el $(DESTDIR)$(ELISPDIR); \ + fi + + + +uninstall: + for program in chktex $(SCRIPTS) $(BUILT_SCRIPTS); do \ + rm -f $(DESTDIR)$(bindir)/$$program; \ + done + rm -f $(DESTDIR)$(sysconfdir)/chktexrc $(DESTDIR)$(mandir)/man1/deweb.1 + if (eval echo "$(ELISPDIR)") | egrep "/" >/dev/null 2>&1; then \ + rm -f $(DESTDIR)$(ELISPDIR)/chktex.el ; \ + fi + +test: + chktex -v2 -mall $(srcdir)/Test.tex | less -r + +indent: + indent -npsl -bli0 -npcs -nut -i4 $(SOURCEFILES) + +mostlyclean: clean + +clean: + rm -rf $(CLEAN) $(BUILT_DIST) $(DISTDIR).tar.gz \ + *.aux *.log *.pdf *.dvi *.ps \ + chktex HTML rme chktest + +distclean: clean + rm -rf $(CONFIG_DIST) *.cache *.status *.log *.tar.gz \ + deweb Makefile autom4te.cache config.h + +maintainer-clean: distclean + rm -rf *.rme install-sh config.guess config.sub aclocal.m4 \ + configure missing rmeheader stamp-h mkinstalldirs tags + +dvi: ChkTeX.dvi + +pdf: ChkTeX.pdf + +ifneq ($(LATEX2HTML),) +html: ChkTeX.tex MakeHTML.pl + -rm -r HTML + $(MKDIR_P) HTML + $(PERL5) $(srcdir)/MakeHTML.pl ChkTeX.tex > HTML/ChkTeX.tex + cd HTML; $(LATEX2HTML) ChkTeX.tex + $(PERL5) -i -pe 's% %%gi;s%\s+([.,?!])%$$1%g;' HTML/ChkTeX/*.html + +README: ChkTeX.tex rmeheader MakeHTML.pl + rm -rf rme + $(MKDIR_P) rme + $(PERL5) $(srcdir)/MakeHTML.pl ChkTeX.tex > rme/ChkTeX.tex + cd rme; $(LATEX2HTML) -split 0 ChkTeX.tex + $(PERL5) -i -pe 's%LA%La%g;s%TEX%TeX%g;s%(.*)%$$1%g' rme/ChkTeX/*.html + $(PERL5) -i -pe 's% %%gi;s%\s+([.,?!])%$$1%g;' rme/ChkTeX/*.html + $(LYNX) -dump rme/ChkTeX/ChkTeX.html > rme/ChkTeX.rme + cp rmeheader README + $(PERL5) -e 'undef $$/;$$_=<>;($$_)=/(.*INTRODUCTION(.|\n)*?)[ \t]+ABOUT THIS DOCUMENT/i;s/[ \t]+\n/\n/g;s/\n\n\n/\n/g;s/\[\d+\]//g;print;' rme/ChkTeX.rme >> README + rm -rf rme +else +html README: + @echo "latex2html is unavailable on this system, cant create target $@."; exit 1 +endif + +###################### AUTOCONF REMAKING ################################ + +$(srcdir)/configure: configure.in aclocal.m4 + cd $(srcdir) && autoconf + +#autoheader might not change config.h.in, so touch a stamp file. +$(srcdir)/config.h.in: stamp-h.in +$(srcdir)/stamp-h.in: configure.in aclocal.m4 + cd $(srcdir) && autoheader + echo timestamp > $(srcdir)/stamp-h.in + +config.h: stamp-h +stamp-h: config.h.in config.status + ./config.status + +ChkTeX.tex: ChkTeX.tex.in + ./config.status ChkTeX.tex + +Makefile: Makefile.in config.status + ./config.status + +config.status: configure + ./config.status --recheck + +###################### INDIVIDUAL DEPENDENCIES ########################## + +%.doc: %.1 + $(GROFF) $< > $@ + +ChkTeX.dvi: ChkTeX.tex +ifdef LATEX + $(LATEX) ChkTeX.tex +else + echo "No latex program found by configure" + false +endif + +ChkTeX.ps: ChkTeX.dvi + $(DVIPS) -o ChkTeX.ps ChkTeX.dvi + +ChkTeX.pdf: ChkTeX.ps + $(PS2PDF) $< $@ + +cover: + -./chktex -h + -./chktex Test.tex + -./chktex -v2 -t -o tmptmptmp + + * Improvements for TeX Live and CTAN + * Fixed bug when checking for interword spacing + * Added warning when a file has lines that are too long which can cause problems + * Added ability to suppress user regular expression warnings by "naming" them + * Added ability to suppress warnings for the rest of the file + * Allow using PCRE or POSIX ERE or neither (at configure time). + Regular expressions can be marked as PCRE or POSIX only. + * Allow () to specify an optional argument in WipeArg to support \cmidrule[](){} + * Allow regular expressions for Silent keyword, specified in [] for "case insensitive" + * Added warning about \hline and vertical rules in tabular environments + * I changed user warnings to be post WipeArg (like they were pre + 1.7.0). I had changed them in 1.7.0 to be pre WipeArg so that I + could match things like \label{...}, but this caused many false + positives by matching in comments, etc. + +1.7.0 (2012-05-28), released by Ivan Andrus + + * Added support for user defined regular expression based warnings + * Added support for macros like \ensuremath and \text + * Added support for suppressing messages on a single line + +1.6.6 (2012-04-07), released by Ivan Andrus + + * Fixed some memory issues + * Do not increase line number when the line was very long + * Some fixes for TexLive + +1.6.5 (??), released by Jean-Marc Lasgouttes + + * Fix bug where ChkTeX generates a warning about missing space before + parenthesis when the parenthesis is at start of line. + * Update ChkTeX.tex.in to use proper LaTeX2e markup. + * Update the build machinery a bit. + +1.6.4 (2007-10-20), released by Baruch Even + + * For some reason 1.6.3 did not include all the changes it was supposed to + have, this release should fix it. One such issue is the MacOS X + compilation. + * Include some updates to the default chktexrc from Jean-Marc Lasgouttes. + +1.6.3, released by Baruch Even + + * Support DESTDIR for installation to help distributions. + * Apply old standing patch from Jean-Marc Lasgouttes to compile outside the + directory. + * Enable compilation on MacOS X. + * Fix various coding issues. + + +Original versions from Jens T. Berger Thielemann: +================================================= + +Modifications and additions since v1.6: + + * Improved the build system + * Better fixes for memory access errors + +Modifications and additions since v1.5: + + * Fixed a crash when running from emacs + * Fixed a crash when checking our own manual + * Added \verb* support + +Modifications and additions since v1.4: + + ** New warnings + + * No space or similar in front/after parenthesis. + * Demands a consistent quote style. + * Double spaces in input which will not be rendered as one. + * Punctuation malplaced regarding to math mode. + * Warns about TeX primitives. + * Space in front of footnotes. + * Bogus \left and \right commands. + + ** Program + + * The abbreviation recognizer has (for the last time?) been + redesigned. We now produce far less false warnings, catch more + cases and do all this faster than before. Seems like a win. Done + much of the same with the italic correction detection part, + too. + * Some bugs have been silently fixed. Hot spots in the program have + been optimized; in certain cases this in fact doubles the speed! + * Along with this goes more code elegance and utilization of macro + processing and the C language. Take a look at Resource.[ch]. + + * It's possible to specify separate output-formats depending on + whether you are sending the output to a file/pipe or to a + terminal. + + * Column positions are finally correct; we now expand tabs + correctly. + * ChkTeX will now recursively search for \input'ed + files, both in the document and on the commandline. See the + chktexrc file for more info. + * The debug switch is now more intelligent; if you wish to hack + a bit on ChkTeX for yourself, it is possible to produce + selective debugging output. The feature can also be disabled + altogether. + * MS-DOS and OS/2 version of the program is now more flexible + and well-behaved, thanks to Gerd Boehm. + * You may now say -wall to make all messages warnings, and + turn them on. + * Uses termcap on UNIX boxes; this should ensure that -v2 + (or more precisely: %i and %I works regardless to + what terminal you are using. + + ** Resource file + + * You may now specify both case-sensitive and case-insensitive user + patterns in the chktexrc file. In addition; it is now possible to + reset/clear lists. + * You can now specify how many optional or required arguments + WIPEARG should wipe; it also behaves somewhat more intelligently + when the arguments stretch over multiple lines. + * Global files will be read in addition to local ones. The searching + order has also been reversed in order to make this more + intelligent. + + ** Other + + * The documentation has been polished and should now be easier + to use in practical situations. + * check target in Makefile, so you can check that the installation + succeeded. In fact, the Makefile has been enhanced in several other + ways too, amongst other it is now GNU conforming. + * deweb is now documented; you may say "man deweb" to get a few + words of advice. The support script (chkweb) does now behave as the + remaining package (accepting stdin input and flags). + * I've written an Emacs hack which magically adds ChkTeX to the list + of AUC-TeX commands; thus making the use of the program even more + trivial. For those of you who don't wish to mess with Emacs, I've + included a trivial lacheck <-> ChkTeX interface. This means that you + now can use ChkTeX just as easily as lacheck when you're running + AUC-TeX. + * Added an ARexx script which lets ChkTeX talk to VBrowse, the + message browser of Volker Barthelmann's freely distributable ANSI + C compiler. The browser itself is available on Aminet as + dev/c/vbcc.lha. diff --git a/Build/source/texk/chktex/chktex-1.7.1/OpSys.c b/Build/source/texk/chktex/chktex-1.7.1/OpSys.c new file mode 100644 index 00000000000..d2891b08581 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/OpSys.c @@ -0,0 +1,485 @@ +/* + * ChkTeX, operating system specific code for ChkTeX. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + + +/* + * Some functions which have to be made different from OS to OS, + * unfortunately...:\ + * + */ + +#include "ChkTeX.h" +#include "OpSys.h" +#include "Utility.h" + +#ifdef HAVE_SYS_STAT_H +# include +#endif +#ifdef HAVE_STAT_H +# include +#endif + +#if HAVE_DIRENT_H +# include +# define NAMLEN(dirent) strlen((dirent)->d_name) +#else +# define dirent direct +# define NAMLEN(dirent) (dirent)->d_namlen +# if HAVE_SYS_NDIR_H +# include +# endif +# if HAVE_SYS_DIR_H +# include +# endif +# if HAVE_NDIR_H +# include +# endif +#endif + +#if defined(HAVE_OPENDIR) && defined(HAVE_CLOSEDIR) && \ + defined(HAVE_READDIR) && defined(HAVE_STAT) && \ + defined(S_IFDIR) && defined(SLASH) +# define USE_RECURSE 1 +#else +# define USE_RECURSE 0 +#endif + +#if defined(HAVE_LIBTERMCAP) || defined(HAVE_LIBTERMLIB) +# define USE_TERMCAP 1 +#endif + + +#ifdef USE_TERMCAP +# ifdef HAVE_TERMCAP_H +# include +# elif HAVE_TERMLIB_H +# include +# else +int tgetent(char *BUFFER, char *TERMTYPE); +char *tgetstr(char *NAME, char **AREA); +# endif +static char term_buffer[2048]; +#endif + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * This is the name of the global resource file. + */ + +#ifndef SYSCONFDIR +# if defined(__unix__) +# define SYSCONFDIR "/usr/local/lib/" +# elif defined(__MSDOS__) +# define SYSCONFDIR "\\emtex\\data\\" +# else +# define SYSCONFDIR +# endif +#endif +#define RCBASENAME "chktexrc" + +#ifdef __MSDOS__ +# define LOCALRCFILE RCBASENAME +#else +# define LOCALRCFILE "." RCBASENAME +#endif + +char ConfigFile[BUFSIZ] = LOCALRCFILE; +const char *ReverseOn; +const char *ReverseOff; + + +static int HasFile(char *Dir, const char *Filename, const char *App); + +#if USE_RECURSE +static int SearchFile(char *Dir, const char *Filename, const char *App); +#endif /* USE_RECURSE */ + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + + +/* + * Modify this one to suit your needs. In any case, it should fill + * the ConfigFile (sized BUFLEN) buffer above with full name & path + * for the configuration file. The macro RCFILE will give you the + * filename part of the file, if you need that. + * + * Note: This routine will be called several times. Your mission will + * be to look in each location, and see whether a .chktexrc file exist + * there. + * + * If you choose to do nothing, only the current directory will be + * searched. + * + */ + + +enum LookIn +{ + liMin, + liSysDir, + liUsrDir, + liEnvir, + liCurDir, + liNFound, + liMax +}; + + +int SetupVars(void) +{ + char *Env; +#ifdef __MSDOS__ + + char *Ptr; +#endif + + static enum LookIn i = liMin; + static int FoundFile; + + while (++i < liMax) + { + switch (i) + { + case liCurDir: /* Current directory */ + strcpy(ConfigFile, LOCALRCFILE); + break; + case liEnvir: /* Environment defined */ +#ifdef __MSDOS__ + + if ((Env = getenv("CHKTEXRC")) || (Env = getenv("CHKTEX_HOME"))) +#else + + if ((Env = getenv("CHKTEXRC"))) +#endif + + { + strcpy(ConfigFile, Env); + tackon(ConfigFile, LOCALRCFILE); + } + else +#ifdef __MSDOS__ + if ((Env = getenv("EMTEXDIR"))) + { + strcpy(ConfigFile, Env); + tackon(ConfigFile, "data"); + tackon(ConfigFile, LOCALRCFILE); + } + else +#endif + + *ConfigFile = 0; + break; + case liUsrDir: /* User dir for resource files */ +#if defined(__unix__) + + if ((Env = getenv("HOME")) || (Env = getenv("LOGDIR"))) + { + strcpy(ConfigFile, Env); + tackon(ConfigFile, LOCALRCFILE); + } + else +#elif defined(__MSDOS__) + + strcpy(ConfigFile, PrgName); + if ((Ptr = strrchr(ConfigFile, '\\')) || + (Ptr = strchr(ConfigFile, ':'))) + strcpy(++Ptr, RCBASENAME); + else +#endif + *ConfigFile = 0; + + break; + case liSysDir: /* System dir for resource files */ +#ifdef TEX_LIVE + if ((Env = getenv("CHKTEX_CONFIG"))) + { + strcpy(ConfigFile, Env); + } + else + { + FILE *f; + *ConfigFile = 0; + if ((f = popen("kpsewhich -expand-var='$TEXMFMAIN'", "r"))) + { + if (1 == fscanf(f, "%1024s", ConfigFile)) + { + tackon(ConfigFile, "chktex"); + tackon(ConfigFile, RCBASENAME); + } + (void)pclose(f); + } + } +#else /* TEX_LIVE */ +#if defined(__unix__) || defined(__MSDOS__) + strcpy(ConfigFile, SYSCONFDIR); + tackon(ConfigFile, RCBASENAME); +#else + *ConfigFile = 0; +#endif +#endif /* TEX_LIVE */ + + break; + case liNFound: + case liMin: + case liMax: + *ConfigFile = 0; + if (!FoundFile) + PrintPrgErr(pmNoRsrc); + } + + if (*ConfigFile && fexists(ConfigFile)) + break; + } + FoundFile |= *ConfigFile; + + return (*ConfigFile); +} + + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * This function should initialize the global variables ReverseOn + * and ReverseOff to magic cookies, which when printed, makes the + * text in between stand out. + */ + +void SetupTerm(void) +{ +#ifdef USE_TERMCAP + char *termtype = getenv("TERM"); + int success; + char *buffer; + static char str_so[3] = "so", str_se[3] = "se"; + + if (termtype) + { + + success = tgetent(term_buffer, termtype); + if (success < 0) + PrintPrgErr(pmNoTermData); + if (success == 0) + PrintPrgErr(pmNoTermDefd); + + buffer = (char *) malloc(sizeof(term_buffer)); + ReverseOn = tgetstr(str_so, &buffer); + ReverseOff = tgetstr(str_se, &buffer); + + if (ReverseOn && ReverseOff) + return; + } +#endif + + ReverseOn = PRE_ERROR_STR; + ReverseOff = POST_ERROR_STR; +} + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * Concatenates the `File' string to the `Dir' string, leaving the result + * in the `Dir' buffer. Takes care of inserting `directory' characters; + * if we've got the strings "/usr/foo" and "bar", we'll get + * "/usr/foo/bar". + * + * Behaviour somewhat controlled by the macros SLASH and DIRCHARS in the + * OpSys.h file. + * + */ + +void tackon(char *Dir, const char *File) +{ + int EndC; + unsigned long SLen; + + if (Dir && (SLen = strlen(Dir))) + { + EndC = Dir[SLen - 1]; + if (!(strchr(DIRCHARS, EndC))) + { + Dir[SLen++] = SLASH; + Dir[SLen] = 0L; + } + } + + strcat(Dir, File); +} + +/* + * This function should add the appendix App to the filename Name. + * If the resulting filename gets too long due to this, it may + * overwrite the old appendix. + * + * Name may be assumed to be a legal filename under your OS. + * + * The appendix should contain a leading dot. + */ + +void AddAppendix(char *Name, const char *App) +{ +#ifdef __MSDOS__ + char *p; + + if ((p = strrchr(Name, '.'))) + strcpy(p, App); + else + strcat(Name, App); +#else + /* + * NOTE! This may fail if your system has a claustrophobic file + * name length limit. + */ + strcat(Name, App); +#endif + +} + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + + +/* + * Locates a file, given a wordlist containing paths. If a + * dir ends in a double SLASH, we'll search it recursively. + * + * We assume that + * a) a deeper level in the dir. tree. has a longer path than + * one above. + * b) adding a level doesn't change any of the previous levels. + * + * If this function returns TRUE, Dest is guaranteed to contain + * path & name of the found file. + * + * FALSE indicates that the file was not found; Dest is then + * unspecified. + */ + + +int LocateFile(const char *Filename, /* File to search for */ + char *Dest, /* Where to put final file */ + const char *App, /* Extra optional appendix */ + struct WordList *wl) /* List of paths, entries + * ending in // will be recursed + */ +{ + unsigned long i; +#if USE_RECURSE + + unsigned long Len; +#endif + + FORWL(i, *wl) + { + strcpy(Dest, wl->Stack.Data[i]); + +#if USE_RECURSE + + Len = strlen(Dest); + + if (Len && (Dest[Len - 1] == SLASH) && (Dest[Len - 2] == SLASH)) + { + Dest[Len - 1] = Dest[Len - 2] = 0; + if (SearchFile(Dest, Filename, App)) + return (TRUE); + } + else +#endif /* USE_RECURSE */ + + { + if (HasFile(Dest, Filename, App)) + return (TRUE); + } + } + return (FALSE); +} + +static int HasFile(char *Dir, const char *Filename, const char *App) +{ + int DirLen = strlen(Dir); + + tackon(Dir, Filename); + if (fexists(Dir)) + return (TRUE); + + if (App) + { + AddAppendix(Dir, App); + if (fexists(Dir)) + return (TRUE); + } + + Dir[DirLen] = 0; + return (FALSE); + +} + + +#if USE_RECURSE +static int SearchFile(char *Dir, const char *Filename, const char *App) +{ + struct stat *statbuf; + struct dirent *de; + DIR *dh; + + int DirLen = strlen(Dir); + int Found = FALSE; + + DEBUG(("Searching %s for %s\n", Dir, Filename)); + + if (HasFile(Dir, Filename, App)) + return (TRUE); + else + { + if ((statbuf = malloc(sizeof(struct stat)))) + { + if ((dh = opendir(Dir))) + { + while (!Found && (de = readdir(dh))) + { + Dir[DirLen] = 0; + if (strcmp(de->d_name, ".") && strcmp(de->d_name, "..")) + { + tackon(Dir, de->d_name); + + if (!stat(Dir, statbuf)) + { + if ((statbuf->st_mode & S_IFMT) == S_IFDIR) + Found = SearchFile(Dir, Filename, App); + } + } + } + closedir(dh); + } + else + PrintPrgErr(pmNoOpenDir, Dir); + free(statbuf); + } + } + return (Found); +} +#endif /* USE_RECURSE */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/OpSys.h b/Build/source/texk/chktex/chktex-1.7.1/OpSys.h new file mode 100644 index 00000000000..7ce3f1b5270 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/OpSys.h @@ -0,0 +1,207 @@ +/* + * ChkTeX, operating system specific code for ChkTeX. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#ifndef OPSYS_H +#define OPSYS_H + +#include "ChkTeX.h" +#include "Utility.h" + +/********************************************************************/ +/**************** START OF USER SETTABLE PREFERENCES ****************/ + +/* + * Note: This file contains most defines you'll wish to change if you + * wish to adopt ChkTeX to a new system. It is, as you might notice, + * heavily documented. If you wish to get into the internals of ChkTeX, + * the interesting stuff is at the bottom of this file, and in the .c + * files. However, you should also take a look at the "config.h.in" file + * in this directory if you haven't got a shell able to run the "configure" + * script. + * + * This program relies heavily on that the system which + * automagically free()'s all malloc()'ed memory, works. The program + * itself does not call free() very much. This is because we're doing + * lots of tiny allocations, and a properly designed pooling system will + * hopefully do a quicker job than we'll be able to do. So there. + * + * To keep things simple, we trust that the fclose()'ing of fopen()'ed + * also happens automagically. + * + * Please use the getopt included, as we will modify optarg during + * command processing. + * + * You may wish to modify the SetupVars() (OpSys.c) to better suit your + * preferences. In any case, it should put the filename (and full path) + * of the `.chktexrc' file into the ConfigFile array. The array is sized + * BUFSIZ bytes. + * + * The program does also assume that __unix__ is defined if the source is + * compiled on a UNIX machine. + * + */ + + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * Here you should define what codes which should be returned to the + * shell upon success/failure. + * + */ + +#ifndef EXIT_FAILURE +# define EXIT_FAILURE 1 +#endif + +#ifndef EXIT_SUCCESS +# define EXIT_SUCCESS 0 +#endif + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * SLASH should be defined to the character your computer uses to + * separate files/directories. Most systems use '/', messydos uses + * '\'. + * + * DIRCHARS should be defined to the characters a directory entry + * may end on. On Amigas, this is ":/" (either "FOO:BAR/" or "FOO:"), + * Unix uses only "/", while messydos uses ":\\". + * + * This data will be used to automatically concatenate a directory + * path and a filename. + * + * Adjust both to suit your needs. + */ + + +#ifdef TEX_LIVE +#if defined(__MSDOS__) || defined(WIN32) +# define SLASH '\\' +# define DIRCHARS ":\\" +#else +# define SLASH '/' +# define DIRCHARS "/" +#endif +#else /* TEX_LIVE */ +#if defined(__unix__) +# define SLASH '/' +#elif defined(__MSDOS__) +# define SLASH '\\' +#endif + +#if defined(__unix__) +# define DIRCHARS "/" +#elif defined(__MSDOS__) +# define DIRCHARS ":\\" +#endif +#endif /* TEX_LIVE */ + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * Here, define what key-combination which is used to abort stdin + * keyboard input. It should be a string, as we we'll type it out as + * information to the user. + */ + +#if defined(__unix__) +# define STDIN_BREAK "Ctrl-D" +#elif defined(__MSDOS__) +# define STDIN_BREAK "Ctrl-Z + Enter" +#else +# define STDIN_BREAK "stdin break combination" +#endif + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * For fancy printing of commands, we'll use these strings to turn + * on/off the error indication. The codes listed here are ANSI + * compatible; if you don't have that type of terminal, you may wish + * to adjust this. Use "chktex -v2 Test.tex" to check the effects of + * these macros. Note: These strings will be printf()'ed, so watch your + * %'s. + * + * Under UNIX, we'll ignore these values and use termcap instead, where + * that is installed. + * + * If these strings can't be specified statically, you'll have to add + * code in the SetupTerm() function. + * + * PRE_ERROR_STR is of course printed in front of each location we + * wish to show as an error, and POST_ERROR_STR after each location. + * + * The codes #defined here, will switch back- and foreground colours. + * We're using '\033[' as escape character, some terminals may like + * '\233' better. + * + */ + +# define PRE_ERROR_STR "\033[7m" +# define POST_ERROR_STR "\033[0m" + + +/* -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- -=><=- */ + +/* + * This macro should contain the appendix for backup files, which + * will be appended onto the original filename. It should contain + * a leading dot. + */ + +#ifdef __MSDOS__ +# define BAKAPPENDIX ".$cl" +#else +# define BAKAPPENDIX ".bak" +#endif + +/***************** END OF USER SETTABLE PREFERENCES *****************/ +/********************************************************************/ + +#ifndef WORDLIST_DEFINED +struct WordList; +#endif +/* Sorry; there are now cyclic dependencies in the +* source tree. :-/ +*/ + +extern const char *ReverseOn; +extern const char *ReverseOff; +extern char ConfigFile[BUFSIZ]; + +char *MatchFileName(char *String); +int SetupVars(void); +void SetupTerm(void); +void AddAppendix(char *Name, const char *App); +void tackon(char *, const char *); +int LocateFile(const char *Filename, char *Dest, const char *App, + struct WordList *wl); + +#endif /* OPSYS_H */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/README b/Build/source/texk/chktex/chktex-1.7.1/README new file mode 100644 index 00000000000..ba098014666 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/README @@ -0,0 +1,22 @@ +ChkTeX +====== + +ChkTeX is a tool to check for common errors in LaTeX files. It also +supports checking CWEB files (uses a perl5 script). It is highly +customizable allowing you turn off any warnings you don't like, as +well as add your own warnings. It works easily with Emacs and AUCTeX, +but should also be easy to interface with other editors. If you have +interfaced ChkTeX with another editor, please contribute how you did +it. + +It is important to remember that ChkTeX is only intended as a *guide* +to fixing faults. It is by no means always correct. This means that +correct LaTeX code may produce errors in ChkTeX, and vice versa: +incorrect LaTeX code may pass silently through. If you have ideas for +new warnings or ways in which current warnings could be improved, +please report them on the +[bug tracker](https://savannah.nongnu.org/bugs/?group=chktex). + +For complete documentation see [the manual](http://www.nongnu.org/chktex/ChkTeX.pdf). + +ChkTeX is released under the GNU Public License version 2 or greater. diff --git a/Build/source/texk/chktex/chktex-1.7.1/Resource.c b/Build/source/texk/chktex/chktex-1.7.1/Resource.c new file mode 100644 index 00000000000..68a4b3196e5 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Resource.c @@ -0,0 +1,510 @@ +/* + * ChkTeX, resource file reader. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#include "ChkTeX.h" +#include "OpSys.h" +#include "Utility.h" +#include "Resource.h" + +#define LNEMPTY(a) struct WordList a = {0, 1, {0}, {0}}; +#define LIST(a) struct WordList a = {0, 0, {0}, {0}}; +#define LCASE(a) LIST(a) LIST(a ## Case) +#define KEY(a,def) const char *a = def; + +RESOURCE_INFO +#undef KEY +#undef LCASE +#undef LNEMPTY +#undef LIST +struct KeyWord +{ + const char *Name; + const char **String; /* Keyword = item */ + struct WordList *List, /* Case-sensitive strings */ + *CaseList; /* Case-insensitive strings */ +}; + +#define LNEMPTY LIST +#define LIST(name) {#name, NULL, &name, NULL}, +#define LCASE(name) {#name, NULL, &name, &name ## Case}, +#define KEY(name,def) {#name, &name, NULL, NULL}, + +struct KeyWord Keys[] = { + RESOURCE_INFO {NULL, NULL, NULL, NULL} +}; + +#undef KEY +#undef LCASE +#undef LNEMPTY +#undef LIST + + +/***************************** RESOURCE HANDLING **************************/ + +#define TOKENBITS(name) enum name { \ + BIT(Eof), /* End-of-file */ \ + BIT(Open), /* { */ \ + BIT(Close), /* } */ \ + BIT(BrOpen), /* [ */ \ + BIT(BrClose), /* ] */ \ + BIT(Equal), /* = */ \ + BIT(Word), /* Keyword */ \ + BIT(Item) /* List item */ \ +}; + +#undef BIT +#define BIT BITDEF1 +TOKENBITS(Token_BIT); +#undef BIT +#define BIT BITDEF2 +TOKENBITS(Token); +static enum Token Expect; +static unsigned long RsrcLine; + +static enum Token ReadWord(char *, FILE *); +static char MapChars(char **String); + + + +/* + * Parses the contents of a resource file. + * + * Format: + * Keyword { item1 item2 ... } [ item1 item2 ... ] + * Keyword [ item1 item2 ... ] { item1 item2 ... } + * Keyword = { item1 item2 ... } + * Keyword = [ item1 item2 ... ] + * Keyword = item + * + * Returns whether the attempt was a successful one. + */ + +int ReadRC(const char *Filename) +{ + const char *String = NULL; + int Success = FALSE; + FILE *fh; + enum Token Token; + unsigned long Counter; + + struct KeyWord *CurWord = NULL; + + /* Interpret incoming words as ... */ + enum + { + whList, /* List elements */ + whCaseList, /* Case insensitive list elements */ + whEqual, /* Solo elements */ + whNone /* List items not accepted */ + } What = whNone; + + + RsrcLine = 0; + Expect = FLG_Word | FLG_Eof; + + if ((fh = fopen(Filename, "r"))) + { + Success = TRUE; + do + { + Token = ReadWord(ReadBuffer, fh); + if (!(Expect & Token)) + { + switch (Token) + { + case FLG_Item: + String = "item"; + break; + case FLG_Word: + String = "word"; + break; + case FLG_Equal: + String = "`='"; + break; + case FLG_Open: + String = "`{'"; + break; + case FLG_Close: + String = "`}'"; + break; + case FLG_BrOpen: + String = "`['"; + break; + case FLG_BrClose: + String = "`]'"; + break; + case FLG_Eof: + String = "EOF"; + break; + } + PrintPrgErr(pmFaultFmt, Filename, RsrcLine, String); + Success = FALSE; + Token = FLG_Eof; + } + + switch (Token) + { + case FLG_Word: + for (Counter = 0; Keys[Counter].Name; Counter++) + { + if (!strcasecmp(ReadBuffer, Keys[Counter].Name)) + { + CurWord = &Keys[Counter]; + Expect = (CurWord->List ? FLG_Open : 0) | + (CurWord->CaseList ? FLG_BrOpen : 0) | FLG_Equal; + break; + } + } + if (!Keys[Counter].Name) + { + PrintPrgErr(pmKeyWord, ReadBuffer, Filename); + Success = FALSE; + Token = FLG_Eof; + } + break; + case FLG_Item: + switch (What) + { + case whEqual: + if (!(*(CurWord->String) = strdup(ReadBuffer))) + { + PrintPrgErr(pmStrDupErr); + Token = FLG_Eof; + Success = FALSE; + } + + What = whNone; + Expect = FLG_Word | FLG_Eof; + break; + case whCaseList: + if (!InsertWord(ReadBuffer, CurWord->CaseList)) + { + Token = FLG_Eof; + Success = FALSE; + } + break; + case whList: + if (!InsertWord(ReadBuffer, CurWord->List)) + { + Token = FLG_Eof; + Success = FALSE; + } + break; + case whNone: + PrintPrgErr(pmAssert); + } + break; + case FLG_Equal: + What = whEqual; + Expect = (CurWord->List ? FLG_Open : 0) | + (CurWord->CaseList ? FLG_BrOpen : 0) | + (CurWord->String ? FLG_Item : 0); + break; + case FLG_BrOpen: + if (What == whEqual) + ClearWord(CurWord->CaseList); + What = whCaseList; + Expect = FLG_Item | FLG_BrClose; + break; + case FLG_Open: + if (What == whEqual) + ClearWord(CurWord->List); + What = whList; + Expect = FLG_Item | FLG_Close; + break; + case FLG_BrClose: + case FLG_Close: + Expect = (CurWord->List ? FLG_Open : 0) | + (CurWord->CaseList ? FLG_BrOpen : 0) | + FLG_Equal | FLG_Word | FLG_Eof; + What = whNone; + break; + case FLG_Eof: + break; + } + } + while (Token != FLG_Eof); + + fclose(fh); + } + else + PrintPrgErr(pmRsrcOpen, Filename); + + return (Success); +} + +/* + * Reads a token from the `.chktexrc' file; if the token is + * FLG_Item or FLG_Word, Buffer will contain the plaintext of the + * token. If not, the contents are undefined. + */ + +static enum Token ReadWord(char *Buffer, FILE * fh) +{ + static char *String = NULL; + static char StatBuf[BUFSIZ]; + enum Token Retval = FLG_Eof; + + unsigned short Chr; + + char *Ptr; + int OnceMore = TRUE, Cont = TRUE; + + if (Buffer) + { + do + { + if (!(String && *String)) + { + if (fgets(StatBuf, BUFSIZ - 1, fh)) + String = strip(StatBuf, STRP_RGT); + RsrcLine++; + } + + Ptr = Buffer; + if (String && (String = strip(String, STRP_LFT))) + { + switch (Chr = *String) + { + case 0: + case CMNT: + String = NULL; + break; + case QUOTE: /* Quoted argument */ + Cont = TRUE; + String++; + + while (Cont) + { + switch (Chr = *String++) + { + case 0: + case QUOTE: + Cont = FALSE; + break; + case ESCAPE: + if (!(Chr = MapChars(&String))) + break; + + /* FALLTHRU */ + default: + *Ptr++ = Chr; + } + } + *Ptr = 0; + Retval = FLG_Item; + OnceMore = FALSE; + break; + +#define DONEKEY (FLG_Open | FLG_Equal | FLG_BrOpen) +#define DONELIST (FLG_Close | FLG_BrClose) +#define TOKEN(c, ctxt, tk) case c: if(Expect & (ctxt)) Retval = tk; LAST(token); + + LOOP(token, + TOKEN('{', DONEKEY, FLG_Open); + TOKEN('[', DONEKEY, FLG_BrOpen); + TOKEN('=', DONEKEY, FLG_Equal); + TOKEN(']', DONELIST, FLG_BrClose); + TOKEN('}', DONELIST, FLG_Close); + ); + if (Retval != FLG_Eof) + { + OnceMore = FALSE; + String++; + break; + } + + /* FALLTHRU */ + + default: /* Non-quoted argument */ + OnceMore = FALSE; + if (Expect & FLG_Word) + { + while (Cont) + { + Chr = *String++; + if (isalpha((unsigned char)Chr)) + *Ptr++ = Chr; + else + Cont = FALSE; + } + String--; + Retval = FLG_Word; + } + else /* Expect & FLG_Item */ + { + while (Cont) + { + switch (Chr = *String++) + { + case CMNT: + case 0: + String = NULL; + Cont = FALSE; + break; + case ESCAPE: + if (!(Chr = MapChars(&String))) + break; + + *Ptr++ = Chr; + break; + default: + if (!isspace((unsigned char)Chr)) + *Ptr++ = Chr; + else + Cont = FALSE; + } + } + Retval = FLG_Item; + } + + if (!(Buffer[0])) + { + PrintPrgErr(pmEmptyToken); + if (*String) + String++; + } + *Ptr = 0; + break; + } + } + else + OnceMore = FALSE; + } + while (OnceMore); + } + return (Retval); +} + + + +/* + * Translates escape codes. Give it a pointer to the char after the + * escape char, and we'll return what it maps to. + */ + +#define MAP(a,b) case a: Tmp = b; break; + +static char MapChars(char **String) +{ + int Chr, Tmp = 0; + unsigned short Cnt; + + Chr = *((char *) (*String)++); + + switch (tolower((unsigned char)Chr)) + { + MAP(QUOTE, QUOTE); + MAP(ESCAPE, ESCAPE); + MAP(CMNT, CMNT); + MAP('n', '\n'); + MAP('r', '\r'); + MAP('b', '\b'); + MAP('t', '\t'); + MAP('f', '\f'); + MAP('{', '{'); + MAP('}', '}'); + MAP('[', '['); + MAP(']', ']'); + MAP('=', '='); + MAP(' ', ' '); + case 'x': + Tmp = 0; + + for (Cnt = 0; Cnt < 2; Cnt++) + { + Chr = *((*String)++); + if (isxdigit((unsigned char)Chr)) + { + Chr = toupper((unsigned char)Chr); + Tmp = (Tmp << 4) + Chr; + + if (isdigit((unsigned char)Chr)) + Tmp -= '0'; + else + Tmp -= 'A' - 10; + } + else + { + if (Chr) + { + PrintPrgErr(pmNotPSDigit, Chr, "hex"); + Tmp = 0; + } + break; + } + } + break; + case '0': + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + + Tmp = Chr - '0'; + + for (Cnt = 0; Cnt < 2; Cnt++) + { + Chr = *((*String)++); + if (within('0', Chr, '7')) + Tmp = (Tmp * 8) + Chr - '0'; + else + { + if (Chr) + { + PrintPrgErr(pmNotPSDigit, Chr, "octal"); + Tmp = 0; + } + break; + } + } + break; + case 'd': + for (Cnt = 0; Cnt < 3; Cnt++) + { + if (isdigit((unsigned char)(Chr = *((*String)++)))) + Tmp = (Tmp * 10) + Chr - '0'; + else + { + if (Chr) + { + PrintPrgErr(pmNotPSDigit, Chr, ""); + Tmp = 0; + } + break; + } + } + break; + default: + PrintPrgErr(pmEscCode, ESCAPE, Chr); + } + return (Tmp); +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/Resource.h b/Build/source/texk/chktex/chktex-1.7.1/Resource.h new file mode 100644 index 00000000000..73b5c8ac60a --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Resource.h @@ -0,0 +1,62 @@ +/* + * ChkTeX, resource file reader. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#ifndef RESOURCE_H +#define RESOURCE_H + +#include "ChkTeX.h" + +#define QUOTE '\"' /* Char used to quote text containing blanks */ +#define ESCAPE '!' /* Char used to access special characters */ +#define CMNT '#' /* Char used as comment */ + +#define RESOURCE_INFO \ + LCASE(Silent) LIST(Linker) LIST(IJAccent) LIST(Italic)\ + LIST(ItalCmd) LIST(PostLink) LIST(WipeArg) LIST(VerbEnvir)\ + LIST(MathEnvir) LIST(MathCmd) LIST(TextCmd) LIST(MathRoman)\ + LIST(HyphDash) LIST(NumDash) LIST(WordDash)\ + LIST(CenterDots) LIST(LowDots) LIST(OutFormat)\ + LIST(Primitives) LIST(NotPreSpaced) LIST(NonItalic) LIST(NoCharNext)\ + LNEMPTY(CmdLine) LNEMPTY(TeXInputs)\ + LCASE(Abbrev) LCASE(UserWarn) LIST(UserWarnRegex)\ + KEY(VerbClear, "|") KEY(QuoteStyle, "Traditional") KEY(TabSize, "8") + +#define LIST(a) extern struct WordList a; +#define LNEMPTY LIST +#define LCASE(a) LIST(a) LIST(a ## Case) +#define KEY(a,def) extern const char *a; + +RESOURCE_INFO +#undef KEY +#undef LCASE +#undef LNEMPTY +#undef LIST +int ReadRC(const char *); + + +#endif /* RESOURCE */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/Test.out b/Build/source/texk/chktex/chktex-1.7.1/Test.out new file mode 100644 index 00000000000..5bea0174f04 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Test.out @@ -0,0 +1,498 @@ +Message 30 in Test.tex: Multiple spaces detected in input. + o To test the program upon it + ^^^ +Message 30 in Test.tex: Multiple spaces detected in input. + o To show off some of the features + ^^^ +Message 22 in Test.tex: Comment displayed. +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +^ +Message 22 in Test.tex: Comment displayed. +% Warning 1 +^ +Message 1 in Test.tex: Command terminated with space. +\foo This is an error. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 2 +^ +Message 2 in Test.tex: Non-breaking space (`~') should have been used. +This is a faulty reference to \ref{foo} + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 3 +^ +Message 3 in Test.tex: You should enclose the previous parenthesis with `{}'. +$[(ab)^{-1}]^{-2}$ is not beautiful + ^ +Message 3 in Test.tex: You should enclose the previous parenthesis with `{}'. +$[(ab)^{-1}]^{-2}$ is not beautiful + ^ +Message 30 in Test.tex: Multiple spaces detected in input. +$[(ab)^{-1}]^{-2}$ is not beautiful + ^^ +Message 22 in Test.tex: Comment displayed. +% Warning 4-6, 28 +^ +Message 6 in Test.tex: No italic correction (`\/') found. +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^ +Message 42 in Test.tex: You should remove spaces in front of `\/' +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^^ +Message 28 in Test.tex: Don't use \/ in front of small punctuation. +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^^ +Message 42 in Test.tex: You should remove spaces in front of `\/' +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^ +Message 5 in Test.tex: Italic correction (`\/') found more than once. +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. + ^^ +Message 22 in Test.tex: Comment displayed. +% LaTeX2e +^ +Message 42 in Test.tex: You should remove spaces in front of `\/' +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^^ +Message 42 in Test.tex: You should remove spaces in front of `\/' +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. + ^^ +Message 4 in Test.tex: Italic correction (`\/') found in non-italic buffer. +Testing \textem{italic\/} in this \textit{sentence}, as \textem{you see}. + ^^ +Message 22 in Test.tex: Comment displayed. +% Warning 7 +^ +Message 7 in Test.tex: Accent command `\'' needs use of `\i'. +This \'is a test of $\hat{j}$ accents. + ^^ +Message 7 in Test.tex: Accent command `\hat' needs use of `\jmath'. +This \'is a test of $\hat{j}$ accents. + ^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 8 +^ +Message 8 in Test.tex: Wrong length of dash may have been used. +It wasn't anything - just a 2---3 star--shots. + ^ +Message 8 in Test.tex: Wrong length of dash may have been used. +It wasn't anything - just a 2---3 star--shots. + ^^^ +Message 8 in Test.tex: Wrong length of dash may have been used. +It wasn't anything - just a 2---3 star--shots. + ^^ +Message 22 in Test.tex: Comment displayed. +% From Knuths TeXbook Chapter 14 +^ +Message 22 in Test.tex: Comment displayed. +% "How TeX Breaks Paragraphs into Lines", fourth paragraph: +^ +Message 22 in Test.tex: Comment displayed. +% Warning 9-10 +^ +Message 22 in Test.tex: Comment displayed. +% Brackets: +^ +Message 10 in Test.tex: Solo `)' found. +)}{[])} }}}]]]))) +^ +Message 10 in Test.tex: Solo `}' found. +)}{[])} }}}]]]))) + ^ +Message 9 in Test.tex: `}' expected, found `)'. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `}' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `}' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `}' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `}' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `]' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `]' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `]' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `)' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `)' found. +)}{[])} }}}]]]))) + ^ +Message 10 in Test.tex: Solo `)' found. +)}{[])} }}}]]]))) + ^ +Message 22 in Test.tex: Comment displayed. +% Envs: +^ +Message 9 in Test.tex: `baz' expected, found `quux'. +\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} + ^^^^ +Message 9 in Test.tex: `quux' expected, found `baz'. +\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} + ^^^^ +Message 10 in Test.tex: Solo `asoi' found. +\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} + ^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 11 +^ +Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. + ^^^ +Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. + ^^^ +Message 11 in Test.tex: You should use \cdots to achieve an ellipsis. +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. + ^^^ +Message 11 in Test.tex: You should use \ldots to achieve an ellipsis. +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. + ^^^^^^ +Message 11 in Test.tex: You should use \cdots to achieve an ellipsis. +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. + ^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 12 +^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 12 in Test.tex: Interword spacing (`\ ') should perhaps be used. +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 13 +^ +Message 13 in Test.tex: Intersentence spacing (`\@') should perhaps be used. +Look at THIS! It's an error. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 14 +^ +Message 1 in Test.tex: Command terminated with space. +\hat + ^ +Message 14 in Test.tex: Could not find argument for command. +\hat +^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 18,19 +^ +Message 18 in Test.tex: Use either `` or '' as an alternative to `"'. +Is this an "example", or is it an ´example´. + ^ +Message 18 in Test.tex: Use either `` or '' as an alternative to `"'. +Is this an "example", or is it an ´example´. + ^ +Message 19 in Test.tex: Use "'" (ASCII 39) instead of "´" (ASCII 180). +Is this an "example", or is it an ´example´. + ^ +Message 19 in Test.tex: Use "'" (ASCII 39) instead of "´" (ASCII 180). +Is this an "example", or is it an ´example´. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 20 +^ +Message 20 in Test.tex: User-specified pattern found: \unknown. +That bug is \unknown\ to me. + ^^^^^^^^ +Message 22 in Test.tex: Comment displayed. +% That bug is \unknown\ to me. +^ +Message 22 in Test.tex: Comment displayed. +% Warning 21 +^ +Message 21 in Test.tex: This command might not be intended. +\LaTeX\ is an extension of \TeX\. Right? + ^^ +Message 22 in Test.tex: Comment displayed. +% Warning 23 +^ +Message 23 in Test.tex: Either `\,`` or ``\,` will look better. +```Hello', I heard him said'', she remembered. +^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 24 +^ +Message 24 in Test.tex: Delete this space to maintain correct pagereferences. +Indexing text \index{text} is fun! + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 25 +^ +Message 25 in Test.tex: You might wish to put this between a pair of `{}' +$5\cdot10^10$ + ^^ +Message 22 in Test.tex: Comment displayed. +% Warning 26 +^ +Message 26 in Test.tex: You ought to remove spaces in front of punctuation. +Do you understand ? + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 27 +^ +Message 1 in input.tex: Command terminated with space. +\this is a test of whether the file is actually inputted... + ^ +Message 11 in input.tex: You should use \ldots to achieve an ellipsis. +\this is a test of whether the file is actually inputted... + ^^^ +Message 1 in input.tex: Command terminated with space. +\this is a test of whether the file is actually inputted... + ^ +Message 11 in input.tex: You should use \ldots to achieve an ellipsis. +\this is a test of whether the file is actually inputted... + ^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 29 +^ +Message 29 in Test.tex: $\times$ may look prettier here. +The program opens a screen sized 640x200 pixels + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 30 +^ +Message 30 in Test.tex: Multiple spaces detected in input. +White is a beautiful colour. + ^^^^^^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 31 +^ +Message 31 in Test.tex: This text may be ignored. +\end{verbatim} foo bar + ^^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 32-34 +^ +Message 32 in Test.tex: Use ` to begin quotation, not '. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^ +Message 33 in Test.tex: Use ' to end quotation, not `. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^ +Message 32 in Test.tex: Use ` to begin quotation, not '. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^^ +Message 33 in Test.tex: Use ' to end quotation, not `. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^^ +Message 34 in Test.tex: Don't mix quotes. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^^^ +Message 34 in Test.tex: Don't mix quotes. +This is either an 'example`, an ''example`` or an `"`example'`'. + ^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 35 +^ +Message 35 in Test.tex: You should perhaps use `\sin' instead. +$sin^2 + cos^2 = 1$ + ^^^ +Message 35 in Test.tex: You should perhaps use `\cos' instead. +$sin^2 + cos^2 = 1$ + ^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 36-37 +^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 37 in Test.tex: You should avoid spaces after parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 37 in Test.tex: You should avoid spaces after parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 37 in Test.tex: You should avoid spaces in front of parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 37 in Test.tex: You should avoid spaces after parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 37 in Test.tex: You should avoid spaces in front of parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 36 in Test.tex: You should put a space after parenthesis. +This( an example( Nuff said )), illustrates( ``my'' )point. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 38 +^ +Message 38 in Test.tex: You should not use punctuation in front of quotes. +``An example,'' he said, ``would be great.'' + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 39 +^ +Message 39 in Test.tex: Double space found. +For output codes, see table ~\ref{tab:fmtout}. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 40 +^ +Message 40 in Test.tex: You should put punctuation outside inner math mode. +$\this,$ and $$this$$. + ^ +Message 40 in Test.tex: You should put punctuation inside display math mode. +$\this,$ and $$this$$. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 41 +^ +Message 1 in Test.tex: Command terminated with space. +foo \above qux + ^ +Message 41 in Test.tex: You ought to not use primitive TeX in LaTeX code. +foo \above qux + ^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 42 +^ +Message 42 in Test.tex: You should remove spaces in front of `\footnote' +This is a footnote \footnote{foo}. + ^ +Message 22 in Test.tex: Comment displayed. +% Warning 43 +^ +Message 43 in Test.tex: `\left' is normally not followed by `{'. +Here is a mistake $\left{x\right}$. + ^^^^^ +Message 43 in Test.tex: `\right' is normally not followed by `}'. +Here is a mistake $\left{x\right}$. + ^^^^^^ +Message 21 in Test.tex: This command might not be intended. +This one triggers warning 22 $\left\{x\right\}$. + ^^ +Message 21 in Test.tex: This command might not be intended. +This one triggers warning 22 $\left\{x\right\}$. + ^^ +Message 22 in Test.tex: Comment displayed. +% Warning 44 -- user regex -- default message +^ +Message 44 in Test.tex: User Regex: intro.. +You should always write a good intro. + ^^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 44 -- user regex -- user message +^ +Message 44 in Test.tex: User Regex: Always use \nmid. +For every $p\not|n$ you have an ugly prime which doesn't divide $n$. + ^^^^^ +Message 22 in Test.tex: Comment displayed. +% Math mode check +^ +Message 35 in Test.tex: You should perhaps use `\sin' instead. +\ensuremath{sin x\text{is not the same as sin x, but is the same as $sin x$}} + ^^^ +Message 35 in Test.tex: You should perhaps use `\sin' instead. +\ensuremath{sin x\text{is not the same as sin x, but is the same as $sin x$}} + ^^^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +Also, $x(3)\text{ is not x(3) but it is $x(3)$}$ + ^ +Message 22 in Test.tex: Comment displayed. +This is\\% a comment. Nothing here should be checked(right)? + ^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +But this is not a \% comment, so we should find this error(right)? + ^ +Message 22 in Test.tex: Comment displayed. +Here(on this line only)is a warning $sin(x)$ suppressed. % chktex 36 chktex 35 + ^ +Message 22 in Test.tex: Comment displayed. +Here(on this line only)is a warning $sin(x)$ suppressed. % CHKTEX 35 36 + ^ +Message 36 in Test.tex: You should put a space in front of parenthesis. +Here(on this line only)is a warning $sin(x)$ suppressed. % CHKTEX 35 36 + ^ +Message 36 in Test.tex: You should put a space after parenthesis. +Here(on this line only)is a warning $sin(x)$ suppressed. % CHKTEX 35 36 + ^ +Message 44 in Test.tex: User Regex: 1:Capitalize before references. +In section~\ref{sec:3} we have a warning. + ^^^^^^^^^^^^^ +Message 22 in Test.tex: Comment displayed. +In section~\ref{sec:4} it is suppressed. % chktex -1 + ^ +Message 22 in Test.tex: Comment displayed. +% In section~\ref{sec:5} we don't have a warning. +^ +Message 44 in Test.tex: User Regex: -2:Vertical rules in tables are ugly. +\begin{tabular*}{1.0\linewidth}[h]{|c|cc|} +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +Message 44 in Test.tex: User Regex: -2:Use \toprule, midrule, or \bottomrule from booktabs. + \hline + ^^^^^^ +Message 22 in Test.tex: Comment displayed. +% Verb check +^ +Message 14 in Test.tex: Could not find argument for command. +\verb# +^^^^^ +Message 31 in Test.tex: This text may be ignored. +\end{verbatim} FOO + ^^^ +Message 22 in Test.tex: Comment displayed. +% Warning 16,15 +^ +Message 16 in Test.tex: Mathmode still on at end of LaTeX file. + + +Message 17 in Test.tex: Number of `(' doesn't match the number of `)'! + + +Message 17 in Test.tex: Number of `[' doesn't match the number of `]'! + + +Message 17 in Test.tex: Number of `{' doesn't match the number of `}'! + + diff --git a/Build/source/texk/chktex/chktex-1.7.1/Test.tex b/Build/source/texk/chktex/chktex-1.7.1/Test.tex new file mode 100644 index 00000000000..503e95ea6e4 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Test.tex @@ -0,0 +1,218 @@ +Note: This file was written with only two purposes in mind: + o To test the program upon it + o To show off some of the features + +Most of the file does thus consist of lots of pseudo-commands, which +are nonsense in a TeXnical manner. + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +% Warning 1 + +\foo This is an error. +\smallskip This is a not. $\foo Neither$ is this. + +% Warning 2 + +This is a faulty reference to \ref{foo} +This is not a faulty reference to~\ref{foo} + +% Warning 3 + +$[(ab)^{-1}]^{-2}$ is not beautiful +${{[{(ab)}^{-1}]}}^{-2}$ is beautiful + +% Warning 4-6, 28 + +Testing {\it italic} in \/ this {\em sentence\/}, as {\em you \/ see\/}. +Testing {\it italic\/} in this {\em sentence,} as {\em you see}. + +% LaTeX2e + +Testing \textem{italic} in \/ this \textit{sentence\/}, as \textem{you \/ see\/}. +Testing \textem{italic\/} in this \textit{sentence}, as \textem{you see}. + +% Warning 7 + +This \'is a test of $\hat{j}$ accents. +This \'{\i}s a test of $\hat{\jmath}$ accents. + +% Warning 8 + +It wasn't anything - just a 2---3 star--shots. +It wasn't anything --- just a 2--3 star-shots. +It's just a start-shot. +is also used to send cross-calls (xc) and cross-traps (xt) to other +% From Knuths TeXbook Chapter 14 +% "How TeX Breaks Paragraphs into Lines", fourth paragraph: +in plain TeX---are the key + +% Warning 9-10 + +% Brackets: + +)}{[])} }}}]]]))) +{[]} ((([[[{{{}}}]]]))) + +% Envs: + +\begin{quux} \begin{baz} \end{quux} \end{baz} \end{asoi} \begin{dobedo} + +\begin{foo} \begin{bar} \end{bar}\end{foo} + +% Warning 11 + +Foo...bar. $1,...,3$. $1+...+3$. $1,\cdots,3$. $1\cdot\ldots\cdot3$. +Foo\dots bar. $1,\ldots,3$. $1+\cdots+3$. $1,\ldots,3$. $1\cdot\cdots\cdot3$. + +% Warning 12 + +1st. Foo Inc. Ab.cd. foo ab.cd. Foo. bar baz., billy.; bob.: joe.! frank.? james.. george +1st.\ foo Inc.\ ab.cd.\ foo ab.cd.\ Foo.\ bar baz., billy.; bob.:\ joe.!\ frank.?\ james..\ george + +% Warning 13 + +Look at THIS! It's an error. +Look at THIS\@! It's an error. D. E. Knuth. + +% Warning 14 + +\hat +\hat{a} + +% Warning 18,19 + +Is this an "example", or is it an ´example´. +Is this an `example', or is it an `example'. + +% Warning 20 + +That bug is \unknown\ to me. +% That bug is \unknown\ to me. + +% Warning 21 + +\LaTeX\ is an extension of \TeX\. Right? +\LaTeX\ is an extension of \TeX. Right? + +% Warning 23 + +```Hello', I heard him said'', she remembered. +``\,`Hello', I heard him said'', she remembered. + +% Warning 24 + +Indexing text \index{text} is fun! +Indexing text\index{text} is fun! + +% Warning 25 + +$5\cdot10^10$ +$5\cdot10^{10}$ + +% Warning 26 + +Do you understand ? +Do you understand? + +% Warning 27 + +\input input.tex +\input input + +% Warning 29 +The program opens a screen sized 640x200 pixels +The program opens a screen sized $640\times200$ pixels + +% Warning 30 + +White is a beautiful colour. +White is a beautiful colour. + +% Warning 31 +\begin{verbatim} +\this is +\end{verbatim} foo bar + +% Warning 32-34 + +This is either an 'example`, an ''example`` or an `"`example'`'. +This is either an `example', an ``example'' or an ``example''. + +% Warning 35 + +$sin^2 + cos^2 = 1$ +$\sin^2 + \cos^2 = 1$ + +% Warning 36-37 + +This( an example( Nuff said )), illustrates( ``my'' )point. +This (an example (Nuff said)), illustrates (``my'') point. + +% Warning 38 +``An example,'' he said, ``would be great.'' +``An example'', he said, ``would be great''. + +% Warning 39 + +For output codes, see table ~\ref{tab:fmtout}. +For output codes, see table~\ref{tab:fmtout}. + +% Warning 40 +$\this,$ and $$this$$. +$\this$, and $$this.$$ + +% Warning 41 +foo \above qux +\frac{foo}{qux} + +% Warning 42 +This is a footnote \footnote{foo}. +This is a footnote\footnote{foo}. + +% Warning 43 +Here is a mistake $\left{x\right}$. +This one triggers warning 22 $\left\{x\right\}$. +Here \chktex\ doesn't complain $\left\lbrace x\right\rbrace$. + +% Warning 44 -- user regex -- default message +You should always write a good intro. +You should always write a good introduction. + +% Warning 44 -- user regex -- user message +For every $p\not|n$ you have an ugly prime which doesn't divide $n$. +For every $p\nmid n$ you have a cute prime which doesn't divide $n$. + +% Math mode check +\ensuremath{sin x\text{is not the same as sin x, but is the same as $sin x$}} +Also, $x(3)\text{ is not x(3) but it is $x(3)$}$ + +This is\\% a comment. Nothing here should be checked(right)? +a broken line. +But this is not a \% comment, so we should find this error(right)? + +Here(on this line only)is a warning $sin(x)$ suppressed. % chktex 36 chktex 35 +Here(on this line only)is a warning $sin(x)$ suppressed. % CHKTEX 35 36 + +In section~\ref{sec:3} we have a warning. +In section~\ref{sec:4} it is suppressed. % chktex -1 +% In section~\ref{sec:5} we don't have a warning. + +\begin{tabular*}{1.0\linewidth}[h]{|c|cc|} + a & b \\ + \hline + c & d +\end{tabular*} + +% Verb check + +\verb@\this is )() lots of errors, etc. Or what?@ +\verb# + +\begin{verbatim} +\this is +\end{verbatim} FOO + +% Warning 16,15 + +$$( diff --git a/Build/source/texk/chktex/chktex-1.7.1/Utility.c b/Build/source/texk/chktex/chktex-1.7.1/Utility.c new file mode 100644 index 00000000000..39beaa6cc83 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Utility.c @@ -0,0 +1,943 @@ +/* + * ChkTeX, utility functions. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#include "ChkTeX.h" +#include "Utility.h" +#include "Resource.h" +#include "OpSys.h" + +typedef unsigned long HASH_TYPE; + +/***************************** SUPPORT FUNCTIONS ************************/ + + +/* + * Copies a string with a maximum length of `len' starting at `pos' in + * `source' into `dest'. + * Returns -1 if the pos value is beyond the length of the source value, + * else NULL. + */ + + +short substring(const char *source, char *dest, unsigned long pos, long len) +{ + const char *Start; + short Retval = -1; + + if (len >= 0) + { + if (strlen(source) > pos) + { + Start = &source[pos]; + + while ((len-- > 0) && (*dest++ = *Start++)) + ; + + if (len == -1) + Retval = 0; + } + } + else + Retval = 0L; + + *dest = 0; + + return (Retval); +} + + +/* + * Determine whether a file exists. + * + */ + + +int fexists(const char *Filename) +{ + int Retval; + +#if defined(F_OK) && defined(R_OK) && defined(HAVE_ACCESS) + + Retval = access(Filename, F_OK | R_OK) == 0; +#else + + FILE *fh; + + if (fh = fopen(Filename, "r")) + { + Retval = TRUE; + fclose(fh); + } + else + Retval = FALSE; +#endif + + return (Retval); +} + + + +/* + * 'Safe' memset() replacement. + * Just tries to check the parameters, so that the risk of killing + * innocent memory is lowered. + * Please note that the `n' parameter now is an signed longword, not + * an size_t. Won't permit that `n' exceeds BUFLEN, nor negative sizes. + * Returns `to' if some memset()'ing was done, NULL if not. + */ + +void *sfmemset(void *to, int c, long n) +{ + if (to && (n > 0)) + { + n = min(n, BUFSIZ); + + return (memset(to, c, (size_t) n)); + } + return (NULL); +} + + +/* + * Quick replace function + * Replaces every occurrence of a character in a string with another one. + */ + +void strrep(char *String, /* String to replace within. */ + const char From, /* Character to search for. */ + const char To) /* Character to put instead. */ +{ + register int c; + while ((c = *String++)) + { + if (c == From) + String[-1] = To; + } +} + +/* + * Replaces every char not in Prot with To in Buf + */ + +void strxrep(char *Buf, const char *Prot, const char To) +{ + int c; + + while ((c = *Buf)) + { + if (!strchr(Prot, c)) + *Buf = To; + Buf++; + } +} + +/* + * Strips tail and/or front of a string + * Kills trailing/leading spaces. The macro/function LATEX_SPACE(char c) + * is used to decide whether a space should be skipped. This function + * should return TRUE if the character should be skipped, FALSE if not. + * Returns the string which was passed onto it. + */ + + +char *strip(char *str, /* String to strip */ + const enum Strip flags) +/* One of the following: */ +/* STRP_LFT - Strips leading blanks */ +/* STRP_RGT - Strips trailing blanks */ +/* STRP_BTH - Strips on both sides */ +{ + char *bufptr = str; + char *nlptr; + char c; + + if (bufptr && (c = *bufptr)) + { + if (flags & STRP_LFT) + { + if (LATEX_SPACE(c) && c) + { + do + { + c = *++bufptr; + } + while (LATEX_SPACE(c) && c); + } + } + + if (flags & STRP_RGT) + { + if (c && *bufptr) + { + nlptr = bufptr; + + while (*++nlptr) + ; + + do + { + *nlptr = 0; + c = *--nlptr; + } + while (LATEX_SPACE(c) && c && (nlptr > bufptr)); + + } + else + *bufptr = 0; + } + } + return (bufptr); +} + + +/* + * Converts all the chars in the string passed into lowercase. + */ + +#ifndef HAVE_STRLWR +char *strlwr(char *String) +{ + char *Bufptr; + char TmpC; + + for (Bufptr = String; (TmpC = *Bufptr); Bufptr++) + *Bufptr = tolower((unsigned char)TmpC); + + return (String); +} +#endif + +/* + * Returns a duplicate of the string passed. + */ + +#ifndef HAVE_STRDUP +char *strdup(const char *String) +{ + char *Retval = NULL; + size_t Len; + + if (String) + { + Len = strlen(String) + 1; + if ((Retval = malloc(Len))) + memcpy(Retval, String, Len); + } + + return (Retval); +} +#endif + +/* + * Does the same as strdup, but adds a zero-filled padding, length extra bytes. + */ + +char *strdupx(const char *String, int Extra) +{ + char *Retval = NULL; + size_t Len; + + if (String) + { + Len = strlen(String) + 1 + Extra; + if ((Retval = malloc(Len))) + strncpy(Retval, String, Len); + } + + return (Retval); +} + +/* + * Case-insensitive comparison of two strings. + */ + +#ifndef HAVE_STRCASECMP +int strcasecmp(const char *a, const char *b) +{ + int aa, bb; + + do + { + aa = *a++; + bb = *b++; + } + while (aa && (tolower((unsigned char)aa) == tolower((unsigned char)bb))); + /* bb != 0 is implicit */ + + return (tolower((unsigned char)aa) - tolower((unsigned char)bb)); +} +#endif + +/* + * Not all reallocs are intelligent enough to handle NULL's as + * parameters. This fixes this. + */ + +void *saferealloc(void *b, size_t n) +{ + void *Retval = NULL; + + if (b) + { + if (n) + Retval = realloc(b, n); + else + free(b); + } + else + Retval = malloc(n); + + return (Retval); +} + +/* + * Repeatedly writes the From string over To so that we overwrite Len bytes. + * Does nothing if passed empty/NULL string. + */ + +void strwrite(char *To, const char *From, unsigned long Len) +{ + unsigned long i, j; + unsigned long FromLen = strlen(From); + + Len = min(Len, BUFSIZ); + + if (To && From) + { + switch (FromLen) + { + case 0: + break; + case 1: + memset(To, *From, Len); + break; + default: + for (i = j = 0; i < Len; i++, j++) + { + if (j >= FromLen) + j = 0; + To[i] = From[j]; + } + } + } +} + +/* + * Checks whether Cmp comes after Str. + * + */ + +int strafter(const char *Str, const char *Cmp) +{ + return (strncmp(Str, Cmp, strlen(Cmp))); +} + +/* + * Checks whether Cmp comes before Str. Returns 0 if so, non-zero if not. + * + */ + +int strinfront(const char *Str, const char *Cmp) +{ + int CmpLen; + + if ((CmpLen = strlen(Cmp))) + { + Cmp += CmpLen; + Str++; + + while ((*--Cmp == *--Str) && (--CmpLen > 0)) + ; + + return (CmpLen); + } + else + return (1); +} + + +/*************************** HASH INDEX **************************/ + +/* + * Hashes a string. The string ought be rather short. + * + * The algorithm was designed by Peter Weinberger. This version was + * adapted from Dr Dobb's Journal April 1996 page 26. + */ + +static unsigned long HashWord(const char *str) +{ + register unsigned long h = 0, hbit, c; + + while ((c = *str++)) + { + h = (h << 4) ^ c; + if ((hbit = h & 0xf0000000)) + h ^= hbit >> 24; + h &= ~hbit; + } + + return (h); +} + +/* + * Inserts a string into a hash index. Note: You'll have to + * duplicate the string yourself. + */ + +void InsertHash(char *a, struct Hash *h) +{ + struct HashEntry **he, *newhe; + + if (!h->Index) + { + if (!((h->Index = calloc(HASH_SIZE, sizeof(struct HashEntry *))))) + PrintPrgErr(pmWordListErr); + } + + he = &h->Index[HashWord(a) % HASH_SIZE]; + + if ((newhe = malloc(sizeof(struct HashEntry)))) + { + newhe->Next = *he; + newhe->Str = a; + *he = newhe; + } + else + PrintPrgErr(pmWordListErr); +} + +/* + * Checks whether a string previously has been registered in a + * hash index. + */ + +char *HasHash(const char *a, const struct Hash *h) +{ + struct HashEntry *he; + HASH_TYPE i; /* Special magic to optimize SAS/C */ + + /* Do we have a hash? */ + if (!h->Index) + return NULL; + + /* Find entry in hash */ + i = HashWord(a); + i %= HASH_SIZE; + he = h->Index[i]; + + /* Search in the entry for the item */ + while (he) + { + if (!strcmp(he->Str, a)) + return (he->Str); + else + he = he->Next; + } + return (NULL); +} + +/* + * Clears a hash table. + */ + +void ClearHash(struct Hash *h) +{ + if (h && h->Index) + memset(h->Index, '\0', HASH_SIZE * sizeof(struct HashEntry *)); +} + +/* + * Rehashes a wordlist. If you change any of the elem's, you must + * call this. + * + */ + +static void ReHash(struct WordList *WL) +{ + unsigned long i = 0; + + ClearHash(&WL->Hash); + FORWL(i, *WL) InsertHash(WL->Stack.Data[i], &WL->Hash); +} + +/*************************** WORDLIST HANDLING **************************/ + +/* + * Inserts a duplicate of `Word' into the `Wordlist' structure. You do thus + * not need to make a duplicate of `Word' yourself. + */ + +int InsertWord(const char *Word, struct WordList *WL) +{ + char *WrdCpy; + unsigned long Len; + + if ((WrdCpy = strdupx(Word, WALLBYTES))) + { + if (StkPush(WrdCpy, &WL->Stack)) + { + Len = strlen(Word); + if (WL->MaxLen < Len) + WL->MaxLen = Len; + + InsertHash(WrdCpy, &WL->Hash); + return (TRUE); + } + + free(WrdCpy); + } + + return (FALSE); +} + +/* + * Clears a WordList; removing all items. + */ + +void ClearWord(struct WordList *WL) +{ + if (WL) + { + WL->Stack.Used = 0; + WL->MaxLen = 0; + ClearHash(&WL->Hash); + if (WL->NonEmpty) + InsertWord("", WL); + } +} + +/* + * Query whether a `Word' is previously InsertWord()'ed into the WL + * structure. Does case-sensitive comparison. + * + * Returns the data in the list. + */ + + +char *HasWord(const char *Word, struct WordList *WL) +{ + return HasHash(Word, &WL->Hash); +} + +/* + * Make all the words in a list lower case for later case-insensitive + * comparison. + */ + +void MakeLower(struct WordList *wl) +{ + unsigned long i; + FORWL(i, *wl) strlwr(wl->Stack.Data[i]); + ReHash(wl); +} + +/* + * Calls strrep on each argument in a list. + */ + +void ListRep(struct WordList *wl, const char From, const char To) +{ + unsigned long i; + FORWL(i, *wl) strrep(wl->Stack.Data[i], From, To); + ReHash(wl); +} + + + +/************************** GENERIC STACK ******************************/ + +/* + * Push something onto a stack. Returns TRUE if successful, else FALSE. + * Note: You can not push a NULL Data element. + */ + +int StkPush(void *Data, struct Stack *Stack) +{ + unsigned long NewSize; + void **NewBuf; + + if (Data && Stack) + { + if (Stack->Used >= Stack->Size) + { + NewSize = Stack->Size + MINPUDDLE; + + if ((NewBuf = saferealloc(Stack->Data, + (size_t) NewSize * sizeof(void *)))) + { + Stack->Size = NewSize; + Stack->Data = NewBuf; + } + else + return (FALSE); + } + + Stack->Data[Stack->Used++] = Data; + return (TRUE); + } + + return (FALSE); +} + +/* + * Pops an element from the stack. + * + */ + +void *StkPop(struct Stack *Stack) +{ + void *Retval = NULL; + + if (Stack && (Stack->Used > 0)) + { + Retval = Stack->Data[--Stack->Used]; + +#ifdef NO_DIRTY_TRICKS + + { + void **NewBuf; + + if (Stack->Used < (Stack->Size / 2)) + { + unsigned long NewSize; + NewSize = Stack->Size - MINPUDDLE; + NewSize = max(NewSize, MINPUDDLE); + + if (NewBuf = saferealloc(Stack->Data, + (size_t) NewSize * sizeof(void *))) + { + Stack->Size = NewSize; + Stack->Data = NewBuf; + } + } + } +#endif + + } + return (Retval); +} + +/* + * Returns the topmost element of the stack. + */ + +void *StkTop(struct Stack *Stack) +{ + if (Stack && (Stack->Used > 0)) + return (Stack->Data[Stack->Used - 1]); + else + return (NULL); +} + +/****************************** INPUT STACK *****************************/ + +int PushFileName(const char *Name, struct Stack *stack) +{ + FILE *fh = NULL; + static char NameBuf[BUFSIZ]; + + if (Name && stack) + { + if (LocateFile(Name, NameBuf, ".tex", &TeXInputs)) + { + if ((fh = fopen(NameBuf, "r"))) + { + return (PushFile(NameBuf, fh, stack)); + } + } + PrintPrgErr(pmNoTeXOpen, Name); + } + return (FALSE); +} + + +int PushFile(const char *Name, FILE * fh, struct Stack *stack) +{ + struct FileNode *fn; + + if (Name && fh && stack) + { + if ((fn = malloc(sizeof(struct FileNode)))) + { + if ((fn->Name = strdup(Name))) + { + fn->fh = fh; + fn->Line = 0L; + if (StkPush(fn, stack)) + return (TRUE); + free(fn->Name); + } + free(fn); + } + PrintPrgErr(pmNoStackMem); + } + + return (FALSE); +} + +char *FGetsStk(char *Dest, unsigned long len, struct Stack *stack) +{ + static short HasSeenLong = 0; + struct FileNode *fn; + char *Retval = NULL; + + if ((fn = StkTop(stack))) + { + do + { + Retval = fgets(Dest, (int)len, fn->fh); + if (Retval) { + if (Retval[strlen(Retval)-1] == '\n') + fn->Line++; + /* We only want the long lines warning once per file */ + else if (!HasSeenLong) + { + PrintPrgErr(pmLongLines, BUFSIZ); + HasSeenLong = 1; + } + break; + } + + fn = StkPop(stack); + fclose(fn->fh); + free(fn); + HasSeenLong = 0; + } + while (!Retval && (fn = StkTop(stack))); + } + + return (Retval); +} + +const char *CurStkName(struct Stack *stack) +{ + struct FileNode *fn; + static const char *LastName = ""; + + if (PseudoInName && (stack->Used <= 1)) + return (PseudoInName); + else + { + if ((fn = StkTop(stack))) + return (LastName = fn->Name); + else + return (LastName); + } +} + + +FILE *CurStkFile(struct Stack * stack) +{ + struct FileNode *fn; + + if ((fn = StkTop(stack))) + return (fn->fh); + else + return (NULL); +} + +unsigned long CurStkLine(struct Stack *stack) +{ + struct FileNode *fn; + static unsigned long LastLine = 0L; + + if ((fn = StkTop(stack))) + return (LastLine = fn->Line); + else + return (LastLine); +} + + + +/************************** CHARACTER STACK ******************************/ + +/* + * Pushes the character on the stack. + */ + +struct ErrInfo *PushChar(const char c, const unsigned long Line, + const unsigned long Column, struct Stack *Stk, + const char *LineCpy) +{ + char Buf[2]; + + Buf[0] = c; + Buf[1] = 0; + + return (PushErr(Buf, Line, Column, 1, LineCpy, Stk)); +} + +struct ErrInfo *PushErr(const char *Data, const unsigned long Line, + const unsigned long Column, + const unsigned long ErrLen, const char *LineCpy, + struct Stack *Stk) +{ + struct ErrInfo *ci; + + if ((ci = malloc(sizeof(struct ErrInfo)))) + { + if ((ci->Data = strdup(Data))) + { + ci->File = CurStkName(&InputStack); + ci->Line = Line; + ci->ErrLen = ErrLen; + ci->Column = Column; + ci->LineBuf = LineCpy; + ci->Flags = efNone; + + if (StkPush(ci, Stk)) + return (ci); + } + else + PrintPrgErr(pmStrDupErr); + free(ci); + } + + return (NULL); +} + +/* + * Finds the uppermost entry in the stack with a data matching + * String. + */ + +struct ErrInfo *TopMatch(struct Stack *Stack, char *String) +{ + int i; + struct ErrInfo *retval = NULL; + + if (Stack && String) + { + for (i = Stack->Used - 1; i >= 0; i--) + { + if (!strcmp(String, ((struct ErrInfo *) Stack->Data[i])->Data)) + { + retval = (struct ErrInfo *) Stack->Data[i]; + break; + } + } + } + return (retval); +} + +/* + * Returns and removes a character from the stack, returns NULL if + * the stack is empty. + */ + + +struct ErrInfo *PopErr(struct Stack *Stack) +{ + return ((struct ErrInfo *) StkPop(Stack)); +} + +/* + * Same as PopChar(), but lets the error alone on the stack. + */ + + +struct ErrInfo *TopErr(struct Stack *Stack) +{ + return ((struct ErrInfo *) StkTop(Stack)); +} + +/* + * Free all resources associated with a struct FreeInfo. + */ + +void FreeErrInfo(struct ErrInfo *ei) +{ + if (ei) + { + if (ei->Data) + free(ei->Data); + + free(ei); + } +} + + +/************************* OPEN/CLOSE COUNTING **************************/ + +/* + * Returns the index a given bracket (`()[]{}') character has in the + * BrOrder array. Returns ~0 if the character was not a bracket. + */ + +long BrackIndex(const char c) +{ + switch (c) + { + case '(': + return (0); + case ')': + return (1); + case '[': + return (2); + case ']': + return (3); + case '{': + return (4); + case '}': + return (5); + default: + return (~0L); + } +} + +/* + * Counts brackets for you. Give it a bracket, and it will update the + * corresponding counter. + */ + +void AddBracket(const char c) +{ + long Index; + + if ((Index = BrackIndex(c)) != -1) + Brackets[Index]++; + +} + +/* + * Returns the character that matches the given bracket, NULL if `c' + * wasn't a bracket character. + */ + +char MatchBracket(const char c) +{ + unsigned long Index; + char Char = 0; + + + if ((Index = BrackIndex(c)) != ~0UL) + Char = BrOrder[Index ^ 1]; + + return (Char); +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/Utility.h b/Build/source/texk/chktex/chktex-1.7.1/Utility.h new file mode 100644 index 00000000000..8afab6b67a0 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/Utility.h @@ -0,0 +1,178 @@ +/* + * ChkTeX, utility functions -- header file. + * Copyright (C) 1995-96 Jens T. Berger Thielemann + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Contact the author at: + * Jens Berger + * Spektrumvn. 4 + * N-0666 Oslo + * Norway + * E-mail: + * + * + */ + +#ifndef UTILITY_H +#define UTILITY_H 1 + +#include "ChkTeX.h" +#include "OpSys.h" + +/* + * How many indexes we'll allocate first time + */ +#define MINPUDDLE 256 + +/* + * How many bytes we want in front/end of each char buffer. > 2 + */ +#define WALLBYTES 4 + +#ifndef HASH_SIZE +# define HASH_SIZE 1009 /* A reasonably large prime */ +#endif + +#define FORWL(ind, list) for(ind = 0; ind < (list).Stack.Used; ind++) + + +enum Strip +{ + STRP_LFT = 0x01, + STRP_RGT = 0x02, + STRP_BTH = 0x03 +}; + +struct HashEntry +{ + struct HashEntry *Next; + char *Str; +}; + +struct Hash +{ + struct HashEntry **Index; +}; + +struct Stack +{ + void **Data; + unsigned long Size, Used; +}; + +struct WordList +{ + unsigned long MaxLen; + int NonEmpty; + struct Stack Stack; + struct Hash Hash; +}; +#define WORDLIST_DEFINED + +struct FileNode +{ + char *Name; + FILE *fh; + unsigned long Line; +}; + +/* Rotates x n bits left (should be an int, long, etc.) */ +#define ROTATEL(x,n) ((x<>((CHAR_BIT*sizeof(x)) - n))) + +/* Rotates x n bits right (should be an int, long, etc.) */ +#define ROTATER(x,n) ((x>>n) | (x<<((CHAR_BIT*sizeof(x)) - n))) + +/* Subtract 1 because sizeof includes the null terminator. + * WARNING: To use this on a variable, the type should be char[] + * rather than char*, since for some versions of gcc these give + * different values. */ +#define STRLEN(x) (sizeof(x)/sizeof(x[0]) - 1) + +int fexists(const char *Filename); + +void *sfmemset(void *to, int c, long n); +void *saferealloc(void *old, size_t newsize); + +int strafter(const char *Str, const char *Cmp); +void strrep(char *String, const char From, const char To); +void strxrep(char *Buf, const char *Prot, const char To); +char *strip(char *String, const enum Strip What); +void strwrite(char *To, const char *From, unsigned long Len); +int strinfront(const char *Str, const char *Cmp); +char *strdupx(const char *String, int Extra); +void strmove(char *a, const char *b); + +void ClearHash(struct Hash *h); +void InsertHash(char *a, struct Hash *h); +char *HasHash(const char *a, const struct Hash *h); + +int InsertWord(const char *Word, struct WordList *WL); +char *HasWord(const char *Word, struct WordList *WL); +void MakeLower(struct WordList *wl); +void ListRep(struct WordList *wl, const char From, const char To); +void ClearWord(struct WordList *WL); + +int StkPush(void *Data, struct Stack *Stack); +void *StkPop(struct Stack *Stack); +void *StkTop(struct Stack *Stack); + +FILE *CurStkFile(struct Stack *stack); +const char *CurStkName(struct Stack *stack); +unsigned long CurStkLine(struct Stack *stack); +char *FGetsStk(char *Dest, unsigned long len, struct Stack *stack); +int PushFileName(const char *Name, struct Stack *stack); +int PushFile(const char *, FILE *, struct Stack *); + + +void FreeErrInfo(struct ErrInfo *ei); +struct ErrInfo *PushChar(const char c, const unsigned long Line, + const unsigned long Column, struct Stack *Stk, + const char *LineCpy); +struct ErrInfo *PushErr(const char *Data, const unsigned long Line, + const unsigned long Column, + const unsigned long ErrLen, const char *LineCpy, + struct Stack *Stk); +struct ErrInfo *TopChar(struct Stack *Stack); +struct ErrInfo *TopErr(struct Stack *Stack); +struct ErrInfo *PopErr(struct Stack *Stack); +struct ErrInfo *TopMatch(struct Stack *Stack, char *String); + +long BrackIndex(char const c); +void AddBracket(char const c); +char MatchBracket(char const); + + + +short substring(const char *source, char *dest, unsigned long pos, long len); + +#ifndef HAVE_STRLWR +# define strlwr mystrlwr +char *mystrlwr(char *String); +#endif + +#ifndef HAVE_STRDUP +# define strdup mystrdup +char *mystrdup(const char *String); +#endif + + +#ifndef HAVE_STRCASECMP +int strcasecmp(char *a, char *b); +#endif + + + +#endif /* UTILITY_H */ diff --git a/Build/source/texk/chktex/chktex-1.7.1/aclocal.m4 b/Build/source/texk/chktex/chktex-1.7.1/aclocal.m4 new file mode 100644 index 00000000000..52c43e7af14 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/aclocal.m4 @@ -0,0 +1,15 @@ +# generated automatically by aclocal 1.10 -*- Autoconf -*- + +# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, +# 2005, 2006 Free Software Foundation, Inc. +# This file is free software; the Free Software Foundation +# gives unlimited permission to copy and/or distribute it, +# with or without modifications, as long as this notice is preserved. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY, to the extent permitted by law; without +# even the implied warranty of MERCHANTABILITY or FITNESS FOR A +# PARTICULAR PURPOSE. + +m4_include([m4/ax_cflags_strict_prototypes.m4]) +m4_include([m4/vl_prog_cc_warnings.m4]) diff --git a/Build/source/texk/chktex/chktex-1.7.1/autogen.sh b/Build/source/texk/chktex/chktex-1.7.1/autogen.sh new file mode 100755 index 00000000000..0982233b129 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/autogen.sh @@ -0,0 +1,49 @@ +#!/bin/sh + +ACLOCAL="aclocal -I m4" +AUTOHEADER="autoheader" +AUTOMAKE="automake --add-missing --copy --foreign" +AUTOCONF="autoconf" + +# Delete old cache directories. +# automake will stop if their contents was created by an earlier version. +rm -rf autom4te.cache + +# Generate the Makefiles and configure files +echo "Building macros..." +if ( $ACLOCAL --version ) < /dev/null > /dev/null 2>&1; then + $ACLOCAL +else + echo "aclocal not found -- aborting" + exit 1 +fi + +echo "Building config header template..." +if ( $AUTOHEADER --version ) < /dev/null > /dev/null 2>&1; then + $AUTOHEADER + echo timestamp > stamp-h.in +else + echo "autoheader not found -- aborting" + exit 1 +fi + +# We do not really need automake, but want to install programs like install-sh. +echo "Installing some useful programs..." +if ( $AUTOMAKE --version ) < /dev/null > /dev/null 2>&1; then + $AUTOMAKE 2>/dev/null +else + echo "automake not found -- aborting" + exit 1 +fi + +echo "Building configure..." +if ( $AUTOCONF --version ) < /dev/null > /dev/null 2>&1; then + $AUTOCONF +else + echo "autoconf not found -- aborting" + exit 1 +fi + +echo +echo 'run "./configure ; make"' +echo diff --git a/Build/source/texk/chktex/chktex-1.7.1/chktex.1 b/Build/source/texk/chktex/chktex-1.7.1/chktex.1 new file mode 100644 index 00000000000..a3dcc13e3dc --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/chktex.1 @@ -0,0 +1,143 @@ +.TH chktex 1 "March 30, 2001" +.AT 3 +.SH NAME +chktex \- finds typographic errors in LaTeX. +.SH SYNOPSIS +.B chktex +.I [-hiqrW] [-v[0-...]] [-l ] [-[wemn] <[1-42]|all>] +.I [-d[0-...]] [-p ] [-o ] [-[btxgI][0|1]] +.B file1 file2 ... +.SH DESCRIPTION +.I chktex +finds typographic errors in +.I LaTeX +. +.SH OPTIONS +.PP +Miscellaneous options: +.TP +.B "-h --help" +Print a help screen. +.TP +.B "-i --license" +Show distribution information. +.TP +.B "-l --localrc" +Read local .chktexrc formatted file. +.TP +.B "-d --debug" +Debug information. Give it a number. +.TP +.B "-r --reset" +Reset settings to default. +.PP +Muting warning messages: +.TP +.B "-w --warnon" +Makes msg # given a warning and turns it on. +.TP +.B "-e --erroron" +Makes msg # given an error and turns it on. +.TP +.B "-m --msgon" +Makes msg # given a message and turns it on. +.TP +.B "-n --nowarn" +Mutes msg # given. +.TP +.B "-L --nolinesupp" +Do not allow per-line suppressions. These are TeX comments of the form +.I "% chktex ##". + +.PP +Output control flags: +.TP +.B "-v --verbosity" +How errors are displayed. +Default 1, 0=Less, 2=Fancy, 3=lacheck. +.TP +.B "-V --pipeverb" +How errors are displayed when stdout != tty. +Defaults to the same as -v. +.TP +.B "-s --splitchar" +String used to split fields when doing -v0 +.TP +.B "-o --output" +Redirect error report to a file. +.TP +.B "-q --quiet" +Shuts up about version information. +.TP +.B "-p --pseudoname" +Input file-name when reporting. +.TP +.B "-f --format" +Format to use for output + +.PP +Boolean switches (1 -> enables / 0 -> disables): +.TP +.B "-b --backup" +Backup output file. +.TP +.B "-x --wipeverb" +Ignore contents of `\\verb' commands. +.TP +.B "-g --globalrc" +Read global .chktexrc file. +.TP +.B "-I --inputfiles" +Execute \\input statements. +.TP +.B "-H --headererr" +Show errors found in front of \\begin{document} +.PP Miscellaneous switches: +.TP +.B "-W --version" +Version information + +.PP +If no LaTeX files are specified on the command line, we will read from +stdin. For explanation of warning/error messages, please consult the +main document /usr/share/doc/chktex/ChkTeX.dvi.gz. + +.SH DISTRIBUTION +Copyright (C) 1996 Jens T. Berger Thielemann +.PP +This program is free software; you can redistribute it and/or modify +it under the terms of the +.I GNU General Public License +as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. +.PP +This program is distributed in the hope that it will be useful, +but +.B WITHOUT ANY WARRANTY; +without even the implied warranty of +.B MERCHANTABILITY +or +.B FITNESS FOR A PARTICULAR PURPOSE. +See the +.I GNU General Public License +for more details. +.PP +You should have received a copy of the +.B GNU General Public License +along with this program; if not, write to the +.I Free Software Foundation, Inc., +59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +.SH ENVIRONMENT +No environment variables are used. +.SH FILES +None. +.SH AUTHOR +Jens T. Berger Thielemann, +.I +.PP +This manual page was cobbled together by Clint Adams , +based on the output of "chktex --help" and deweb(1). +.SH "SEE ALSO" +.B deweb(1), chkweb(1) diff --git a/Build/source/texk/chktex/chktex-1.7.1/chktex.el b/Build/source/texk/chktex/chktex-1.7.1/chktex.el new file mode 100644 index 00000000000..e61334796ca --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/chktex.el @@ -0,0 +1,56 @@ +;;; chktex.el --- quick hack to add ChkTeX capability to AUC-TeX mode +;; +;; +;; Keywords: LaTeX, AUC-TeX, ChkTeX +;; +;; ChkTeX, quick hack to add ChkTeX in LaTeX menu. +;; Copyright (C) 1995-96 Jens T. Berger Thielemann +;; +;; This program is free software; you can redistribute it and/or modify +;; it under the terms of the GNU General Public License as published by +;; the Free Software Foundation; either version 2 of the License, or +;; (at your option) any later version. +;; +;; This program is distributed in the hope that it will be useful, +;; but WITHOUT ANY WARRANTY; without even the implied warranty of +;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +;; GNU General Public License for more details. +;; +;; You should have received a copy of the GNU General Public License +;; along with this program; if not, write to the Free Software +;; Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +;; +;; Contact the author at: +;; Jens Berger +;; Spektrumvn. 4 +;; N-0666 Oslo +;; Norway +;; E-mail: +;; +;; +;;; Commentary: +;; +;; This tiny hack will add a "ChkTeX" item to the command menu of +;; AUC-TeX, thus making the use of ChkTeX much more comfortable from +;; within AUC-TeX (`LaTeX-mode'). +;; +;; INSTALLATION +;; +;; 1. Put this file somewhere in your loading path. +;; 2. Add the line +;; (require 'chktex) +;; to your .emacs file +;; +;; It is doubtful whether byte-compiling this file gains anything. +;; +;;; Code: +;; + +(eval-after-load 'tex + '(progn + (add-to-list 'TeX-command-list + '("ChkTeX" "chktex -v6 %s" TeX-run-compile nil t)))) + +(provide 'chktex) + +;;; chktex.el ends here diff --git a/Build/source/texk/chktex/chktex-1.7.1/chktexrc b/Build/source/texk/chktex/chktex-1.7.1/chktexrc new file mode 100644 index 00000000000..f14c2522972 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/chktexrc @@ -0,0 +1,780 @@ +## +## ChkTeX, example resource file for ChkTeX. +## Copyright (C) 1995-96 Jens T. Berger Thielemann +## +## This program is free software; you can redistribute it and/or modify +## it under the terms of the GNU General Public License as published by +## the Free Software Foundation; either version 2 of the License, or +## (at your option) any later version. +## +## This program is distributed in the hope that it will be useful, +## but WITHOUT ANY WARRANTY; without even the implied warranty of +## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +## GNU General Public License for more details. +## +## You should have received a copy of the GNU General Public License +## along with this program; if not, write to the Free Software +## Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +## +## Contact the author at: +## Jens Berger +## Spektrumvn. 4 +## N-0666 Oslo +## Norway +## E-mail: +## + +##################################################################### +# +# Note: The format has changed slightly (again). The { ... } +# syntax does now mean case-sensitive comparing, while [ ... ] means +# case-insensitive comparing of the keywords. Case-insensitive +# comparing of the keywords is only supported on a few of the +# keywords (it's not meaningful in all contexts, and it slows ChkTeX +# down). Keywords supporting this are marked throughout the file. +# +# You may also reset a list by saying "KEYWORD = { ... }"; it will +# then be set equal to the contents of the list you specify. +# +# Comments begin with `#', and continues for the rest of the line. +# Blank lines plus leading and trailing spaces are of course ignored. +# +# The general format of this file is the following: +# +# KEYWORD { item item ...} [ item item ... ] /* Adds items */ +# +# KEYWORD [ item item ...] { item item ... } /* Adds items */ +# +# KEYWORD = item +# +# KEYWORD = { item item ... } /* Clears list before adding */ +# +# KEYWORD = [ item item ... ] /* Clears list before adding */ +# +# This does _not_ mean that you may alternate the forms; certain +# keywords demands a list, other a single value. You thus have to +# look at the examples of their use. +# +# Please also note that if you specify a list-keyword twice, we'll +# concatenate the lists. If you specify a item-keyword twice, we'll +# kill the previous value. +# +# We are slightly context-sensitive when detecting tokens like "}" +# and "]"; they have to be preceded by a space. This generally makes +# life easier. +# +# Items are separated by spaces. Newlines are considered as spaces, +# but can't be escaped. You may surround items with quotes (`"') to +# easily put spaces into them. +# +# Escape sequences available: +# +# Sequence Resulting character +# ! A space (type `! ', not just a exclamation mark) +# !" " +# !# # +# !! ! +# !{ { +# !} } +# ![ [ +# !] ] +# != = +# !b Backspace +# !n New line +# !r Carriage return +# !t Tab +# !f Form feed +# !xNN NN must be a hexadecimal number (00 - ff), +# _both_ characters must be included. +# !dNNN DDD must be a decimal number (000 - 255), all +# three characters must be included. Unspecified +# results if DDD > 255. +# !NNN DDD must be a octal number (000 - 377), all +# three characters must be included. Unspecified +# results if DDD > 377. +# +# Minor note: As you can see, most of these escape sequences are +# equal to those in C (with some extensions); however, we use ! +# instead of \ as escape character for obvious reasons. +# +# +# Quick summary of keywords follows. Keywords marked with a * accept +# keywords accepting case-insensitive lists. +# +# Abbrev* - A list of abbreviations not automatically caught. +# CenterDots - Commands/characters which should have \cdots in +# between. +# CmdLine - Default commandline options. These will be +# processed before the ones you give on the command +# line. +# HyphDash \ +# NumDash - Number of dashes allowed in different contexts. +# WordDash / +# IJAccent - Commands which puts an accent _over_ their +# argument. +# Italic - Commands immediately turning on italic mode. +# ItalCmd - Commands putting their argument into italic. +# Linker - Commands which should have a non-breaking space in +# front. +# LowDots - Commands/characters which should have \ldots in +# between. +# MathEnvir - Environments which turn on math mode. +# MathCmd - Commands which turn on math mode. +# TextCmd - Commands which turn off math mode. +# MathRoman - Mathematical operators with LaTeX replacement +# defined. +# NoCharNext - Insists on that certain commands aren't followed by +# certain characters. +# NonItalic - Commands immediately turning off italic mode. +# NotPreSpaced- Commands which should not have a space in front of +# them. +# Primitives - Primitive TeX commands. +# PostLink - Commands which generates a page reference. +# OutFormat - Formats to use for output. See the -f & -v switch +# in the main doc. +# QuoteStyle - Either "Traditional" or "Logical". See main doc, +# warning 38. +# Silent - These commands do not produce any textual output; +# and are thus allowed to have a space after them. +# TabSize - Tab size you are using. +# TeXInputs - Paths to search \input and \include files for. +# UserWarn* - These strings will be searched for throughout the +# text. +# VerbEnvir - Environments which contents should be ignored. +# VerbClear - String we will overwrite unwanted data with. +# WipeArg - Commands (with arguments) which should be ignored +# in the checking. +# + + +##################################################################### +# +# Enter which type of quote-style you are using here. Currently, we +# support the following styles: +# +# Style Example of use +# Traditional "An example," he said, "would be great." +# Logical "An example", he said, "would be great". +# + +QuoteStyle = Logical + +##################################################################### +# +# Enter here what interval you have between your tabs. Only regular +# intervals are supported. +# + +TabSize = 8 + +##################################################################### +# +# Here, you can put default commandline options; most users would for +# instance like to put -v2 here. +# + +CmdLine +{ + +} + +##################################################################### +# +# These patterns will be searched for through the text; no matter +# whether they appear as normal text, commands or whatever. +# Currently case-sensitive. They are not found in comments. +# +# I usually define a special command like this: +# +# \def\unknown{\large\bf??} +# +# which I use whenever there is some information I don't have at the +# moment of writing. Thus, it makes sense to search for it. +# +# You should be able to develop your own uses for this. +# + +UserWarn +{ + + \unknown +### +# +# Another example; one should write \chktex or Chk\TeX - never ChkTeX. +# +### + + ChkTeX +} +[ + +### +# +# You may put case-insensitive patterns here. +# +### + +] + + +### +# +# These patterns will be searched for, no matter whether they appear +# as normal text, commands or arguments. However, they will _not_ +# match in verbatim environments. +# +# Remember that you have to escape (with a !) the following +# characters: "#!= as well as spaces and {}[] if they are proceeded by +# a space. +# +# Since these are PCRE regular expressions, you can use (?i) to make +# the expression case insensitive. See the man pages (man pcresyntax) +# or the nicely formatted http://perldoc.perl.org/perlre.html for +# documentation on the regular expression syntax. Note however that +# some the features of perl regular expression are not available such +# as running code (callouts), and replacing. +# +# An initial PCRE comment (?# ... ) can be used change what is +# displayed, thereby reminding yourself how to fix the problem. +# +### +UserWarnRegex +{ + + (?!#Always! use! \nmid)\\not! *(\||\\mid) + + # capitalize section when saying Section 6. + (?!#-1:Capitalize! before! references)PCRE:\b(chapter|(sub)?section|theorem|lemma|proposition|corollary|appendix)~\\ref + (?!#1:Capitalize! before! references)POSIX:([^[:alnum:]]|^)(chapter|(sub)?section|theorem|lemma|proposition|corollary|appendix)~\\ref + + # spell it out. + PCRE:(?i)\bintro\b(?!#Spell! it! out.! This! comment! is! not! used.) + POSIX:([^[:alnum:]]|^)intro([^[:alnum:]]|$) + + # Pretty tables--see http://texdoc.net/texmf-dist/doc/latex/booktabs/booktabs.pdf + (?!#-2:Use! \toprule,! midrule,! or! \bottomrule! from! booktabs)\\hline + # This relies on it being on a single line, and not having anything + # else on that line. With PCRE we could match balanced [] and {}, + # but I wonder if it's worth the complexity... + (?!#-2:Vertical! rules! in! tables! are! ugly)\\begin\{(array|tabularx?\*?)\}(\[.*\])?\{.*\|.*\} + +} + + +##################################################################### +# +# Here you can list the path of where ChkTeX should look for files it +# \inputs. The // postfix is now supported; if you append a double +# path-separator we'll recursively search that directory directories. +# MS-DOS users must append \\ instead, e.g. "C:\EMTEX\\". +# +# If you under either MS-DOS or UNIX wish to search an entire +# partition or the complete directory tree, you must use *three* +# slashes, e.g. "c:\\\" or "///". This may be considered to be a bug. +# +# By default, we'll search the current directory (not recursively, +# put "//" in the list for this); any paths specified below will be +# searched in addition to this. +# + +TeXInputs +{ + +} + +##################################################################### +# +# Here you may specify more output formats for use with the -v option, +# it simply indexes into this list. Remember to use ! instead of \, +# though. +# +# For explanation of how % fields expand; look at ChkTeX.{dvi,ps,pdf}. +# +# We will by default select entry number _two_ in this list (we count +# from 0), and -v without any parameter selects entry number _three_. +# + +OutFormat +{ + +# -v0; silent mode +%f%b%l%b%c%b%n%b%m!n + +# -v1; normal mode +"%k %n in %f line %l: %m!n%r%s%t!n%u!n" + +# -v2; fancy mode +"%k %n in %f line %l: %m!n%r%i%s%I%t!n!n" + +# -v3; lacheck mode +"!"%f!", line %l: %m!n" + +# -v4; verbose lacheck mode +"!"%f!", line %l: %m!n%r%s%t!n%u!n" + +# -v5; no line number, ease auto-test +"%k %n in %f: %m!n%r%s%t!n%u!n" + +# -v6; emacs compilation mode +"!"%f!", line %l.%c:(#%n) %m!n" + +} + + + +##################################################################### +# +# These commands should be ignored when detecting whether a command +# is ended by a space. You can specify regular expressions in the [] +# section in case you have many custom macros that can be safely +# terminated with a space. +# + +Silent +{ + \rm \em \bf \it \sl \sf \sc \tt \selectfont + \rmfamily \sffamily \ttfamily \mdseries \bfseries + \slshape \scshape \relax + \vskip \pagebreak \nopagebreak + + \textrm \textem \textbf \textit \textsl \textsf \textsc \texttt + + \clearpage \ddots \dotfill \flushbottom \fussy \indent \linebreak + \onecolumn \pagebreak \pushtabs \poptabs \scriptsize \sloppy + \twocolumn \vdots + \today \kill \newline \thicklines \thinlines + + \columnsep \space \item \tiny \footnotesize \small \normalsize + \normal \large \Large \LARGE \huge \Huge \printindex + + \newpage \listoffigures \listoftables \tableofcontents + \maketitle \makeindex + + \hline \hrule \vrule + + \centering + + \bigskip \medskip \smallskip + + \noindent \expandafter + + \makeatletter \makeatother + + \columnseprule + + \textwidth \textheight \hsize \vsize + + \if \fi \else + + \csname \endcsname + + \z@ \p@ \@warning \typeout + + \dots \ldots \input \endinput \nextline \leavevmode \cdots + \appendix \listfiles \and \quad + \hskip \vfill \vfil \hfill \hfil \topmargin \oddsidemargin + \frenchspacing \nonfrenchspacing + \begingroup \endgroup \par + + \vrefwarning \upshape \headheight \headsep \hoffset \voffset + \cdot \qquad + \left \right + \qedhere + + \xspace + + \addlinespace \cr \fill \frontmatter + \toprule \midrule \bottomrule + +}[ +# Here you can put regular expressions to match Silent macros. It was +# designed for the case where you have many custom macros sharing a +# common prefix, but can of course be used for other things. + +# \\my.* +] + +##################################################################### +# +# Here, you can specify the length of various dashes. We sort the +# dash according to which type of characters that are on the left and +# right of it. We are only conclusive if they are the same. +# +# We associate as follows: +# +# Name Type of character on each side +# HyphDash Alphabetic (foo-bar) +# NumDash Numeric (2--3) +# WordDash Space (like this --- see?) +# +# Below you specify how many dashes which are legal in each case. We +# define 0 as a magic constant which always generates an error. You +# may specify more than one legal dash-length. +# +# Let's look at an example. You use the following dash-syntax: +# +# foo-bar +# 2--3 +# like this---see? +# +# +# HYPHDASH { 1 3 } # Either a hyphen, or inter-word +# NUMDASH { 2 } # Between words +# WORDDASH { 0 } # We never use this +# + +HyphDash +{ + 1 3 +} + +NumDash +{ + 2 +} + +WordDash +{ + 3 +} + +##################################################################### +# +# This keyword indicates commands whose argument isn't LaTeX code, +# and thus should be ignored. +# +# After the command, you may place arguments that you wish that +# should be wiped in the process; use [] for optional arguments, {} +# for required ones and * if the command supports an alternative +# variant. These should be separated from the command with a colon. +# Some commands (e.g. \cmidrule) use () to delimit and optional +# argument and so this syntax is supported as well. +# +# For instance, if you would like to wipe the \newcommand command, +# you would declare it as \newcommand:*[][]{} +# +# These commands may be "executed" before they're wiped, so you will +# typically also wish to list filehandling commands and similar here. +# + +WipeArg +{ + \label:{} \ref:{} \eqref:{} \vref:{} \pageref:{} \index:[]{} + \cite:[]{} \nocite:{} + \input:{} \verbatiminput:[]{} \listinginput:[]{}{} + \verbatimtabinput:[]{} \include:{} \includeonly:{} + \bibitem:[]{} + \cline:{} \cmidrule:[](){} + \href:{}{} + # Cleveref -- there are many others that could be here as well... + \cref:*{} \cpageref:*{} \crefrange:*{}{} \cpagerefrange:*{}{} + \Cref:*{} \Cpageref:*{} \Crefrange:*{}{} \Cpagerefrange:*{}{} + # natbib + \citet:*[][]{} \citep:*[][]{} \citealt:*{} \citealp:*[]{} \citeauthor:*{} + \Citet:*[][]{} \Citep:*[][]{} \Citealt:*{} \Citealp:*[]{} \Citeauthor:{} + \citetext:{} \citeyear:*{} \citeyearpar:{} +} + +##################################################################### +# +# These environments contain material which will be typeset as +# mathematics by LaTeX. This turns on/off some warnings. +# +# We will automagically append a * to each keyword. +# + +MathEnvir +{ + displaymath math eqnarray array equation + align alignat gather flalign multline +} + +##################################################################### +# +# These commands contain material which will be typeset as mathematics +# by LaTeX. The commands are assumed to have one mandatory argument +# which is in math mode. This turns on/off some warnings. +# + +MathCmd +{ + \ensuremath +} + +##################################################################### +# +# These commands contain material which will _not_ be typeset as +# mathematics by LaTeX even if it would otherwise be in mathmode. The +# commands are assumed to have one mandatory argument which is in text +# mode. This turns on/off some warnings. +# + +TextCmd +{ + \text \intertext \shortintertext \mbox +} + +##################################################################### +# +# These environments contains material which contents should be +# ignored. +# +# We will automagically append a * to each keyword. +# + +VerbEnvir +{ + verbatim comment listing verbatimtab rawhtml errexam picture texdraw + filecontents pgfpicture tikzpicture +} + +##################################################################### +# +# ChkTeX does automagically catch most abbreviations; the ones we +# need to list here, are those which are most likely to be followed +# by a word with an upper-case letter (that is not the beginning of a +# new sentence). +# +# The case-insensitive abbreviations are not really case-insensitive, +# it seems to be more practical to only let the first character be +# case-insensitive, while the remaining are case-sensitive. +# +# To speed up the searching process somewhat, we require that these +# end in a `.', this should not be a problem. +# +# Much of this work (both the abbreviations below, and the regexps +# necessary to catch the remaining automatically) have been provided +# by Russ Bubley, . +# + +Abbrev +{ +# Ordinals +1st. 2nd. 3rd. 4th. +# Titles +Mr. Mrs. Miss. Ms. Dr. Prof. St. + +# +# Days +# Mon. Tue. Wed. Thu. Fri. Sat. Sun. +# +# Months +# Jan. Feb. Mar. Apr. May. Jun. Jul. Aug. Sep. Oct. Nov. Dec. +# +# Letters +# Kt. Jr. +# +# Corporate +# Co. Ltd. +# +# Addresses +# Rd. Dr. St. Ave. Cres. Gdns. Sq. Circ. Terr. Pl. Arc. La. Clo. Ho. Est. Gn. +# +# Misc. +# oe. pbab. ps. rsvp. Tx. +} +[ +### +# +# The first letter is case-insensitive in the abbrevs in this +# list. Due to the nature of the checking algorithm used for +# this, entries consisting of only one character will be +# silently ignored. +# +## + +# Latin +# cf. "et al." etc. qed. qv. viz. +# +# Corporate +# inc. plc. +# +# Misc +# fax. pcs. qty. tel. misc. +] + +##################################################################### +# +# Commands which accent characters, meaning that \i or \j (\imath and +# \jmath in mathmode) should be used instead of `i' and `j' +# + +IJAccent +{ + \hat \check \breve \acute \grave \tilde \bar \vec \dot \ddot + + \' \` \^ \" \~ \= \. \u \v \H \t + +### +# +# The remaining accent commands (\c,\d,\b) put their accent _under_ +# the character, not above, and should thus be used with normal i's +# and j's. +# +### + +} + +##################################################################### +# +# Commands which, when the group is terminated, needs italic +# correction. +# + +Italic +{ + \it \em \sl + \itshape \slshape +} + +##################################################################### +# +# Commands which makes the font non-italic. +# + +NonItalic +{ + \bf \rm \sf \tt \sc + \upshape +} + +##################################################################### +# +# Commands which put their argument into italic (and thus possibly +# needs italic correction in the end). +# +# This is currently empty, since \textit, \textsl and \emph do that +# automatically. +# + +ItalCmd +{ +} + +##################################################################### +# +# These commands all have in common that a pagebreak right in front +# of them is highly undesirable; thus there should be no space in +# front of them. +# + +PostLink +{ + \index \label +} + +##################################################################### +# +# These commands should not have a space in front of them for various +# reasons. I.e. much the same as POSTLINK, but produces another +# warning. +# + +NotPreSpaced +{ + \footnote \footnotemark \/ +} + +##################################################################### +# +# The commands listed here, should be prepended with a `~', as in +# "look in table~\ref{foo}", to avoid the references being split +# across lines. +# + +Linker +{ + \ref \vref \pageref \eqref \cite +} + +##################################################################### +# +# Commands/characters which should have \cdots in between, e.g. +# $1+2+3+\cdots+n$. +# + +CenterDots +{ + = + - \cdot \div & \times \geq \leq < > +} + +##################################################################### +# +# Commands/characters which should have \ldots in between, e.g. +# $1,2,3,\ldots,n$. +# + +LowDots +{ + . , ; +} + +##################################################################### +# +# In maths mode, there are certain aliases for mathematical operators +# like sin, cos, etc. Ignore the leading backslash in the commands, +# and so forth. You should list these below. +# + +MathRoman +{ + log lg ln lim limsup liminf sin arcsin sinh cos arccos cosh tan + arctan tanh cot coth sec csc max min sup inf arg ker dim hom det + exp Pr gcd deg bmod pmod mod +} + +##################################################################### +# +# These TeX commands have become unnecessary, as there are LaTeX +# commands that does the same. Purists should thus avoid these in +# their code. +# +# (These are a spell-corrected version of those lacheck uses). +# + +Primitives +{ + \above \advance \catcode \chardef \closein \closeout \copy \count + \countdef \cr \crcr \csname \delcode \dimendef \dimen \divide + \expandafter \font \hskip \vskip \openout +} + +##################################################################### +# +# Format: \command:characters +# +# We'll emit a warning if any of characters are found after the +# command. +# + +NoCharNext +{ + \left:{}$ \right:{}$ +} + +##################################################################### +# +# We're killing \verb@...@ commands and the arguments of the commands +# listed above in WipeArg by overwriting them with a string or a +# single character. +# +# This should not contain an alphabetic character (in case the user +# writes (\foo\verb@bar@), neither should it contain be one of +# LaTeX's reserved characters (`#$%&~_^\{}'), or any parenthesis +# character ('()[]{}'). If possible, don't use a punctuation +# character, either, or any spacing character. +# +# The asterisk is also unsuitable, as some commands behave in another +# way if they are appended with an asterisk. Which more or less +# leaves us with the pipe. +# +# Please note that this may also be a _string_, which will be +# repeated until the proper length is reached. +# + +VerbClear = "|" + +# +# All for now - have fun. +# +##################################################################### diff --git a/Build/source/texk/chktex/chktex-1.7.1/chkweb.1 b/Build/source/texk/chktex/chktex-1.7.1/chkweb.1 new file mode 100644 index 00000000000..5cb7063f786 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/chkweb.1 @@ -0,0 +1,132 @@ +.TH chkweb 1 "March 30, 2001" +.AT 3 +.SH NAME +chkweb \- runs the LaTeX parts of a CWEB file through chktex +.SH SYNOPSIS +.B chkweb +.I [-hiqrW] [-l ] [-[wemn] <[1-42]|all>] +.I [-d[0-...]] [-o ] [-[btxgI][0|1]] +.B file1 file2 ... +.SH DESCRIPTION +.I chkweb +runs the +.I LaTeX +parts of a CWEB file through chktex. +.SH OPTIONS +.PP +Miscellaneous options: +.TP +.B "-h --help" +Print a help screen. +.TP +.B "-i --license" +Show distribution information. +.TP +.B "-l --localrc" +Read local .chktexrc formatted file. +.TP +.B "-d --debug" +Debug information. Give it a number. +.TP +.B "-r --reset" +Reset settings to default. +.PP +Muting warning messages: +.TP +.B "-w --warnon" +Makes msg # given a warning and turns it on. +.TP +.B "-e --erroron" +Makes msg # given an error and turns it on. +.TP +.B "-m --msgon" +Makes msg # given a message and turns it on. +.TP +.B "-n --nowarn" +Mutes msg # given. + +.PP +Output control flags: +.TP +.B "-V --pipeverb" +How errors are displayed when stdout != tty. +Defaults to the same as -v. +.TP +.B "-s --splitchar" +String used to split fields when doing -v0 +.TP +.B "-o --output" +Redirect error report to a file. +.TP +.B "-q --quiet" +Shuts up about version information. +.TP +.B "-f --format" +Format to use for output + +.PP +Boolean switches (1 -> enables / 0 -> disables): +.TP +.B "-b --backup" +Backup output file. +.TP +.B "-x --wipeverb" +Ignore contents of `\\verb' commands. +.TP +.B "-g --globalrc" +Read global .chktexrc file. +.TP +.B "-I --inputfiles" +Execute \\input statements. +.TP +.B "-H --headererr" +Show errors found in front of \\begin{document} +.PP Miscellaneous switches: +.TP +.B "-W --version" +Version information + +.PP +If no LaTeX files are specified on the command line, we will read from +stdin. For explanation of warning/error messages, please consult the +main document /usr/share/doc/chktex/ChkTeX.dvi.gz. + +.SH DISTRIBUTION +Copyright (C) 1996 Jens T. Berger Thielemann +.PP +This program is free software; you can redistribute it and/or modify +it under the terms of the +.I GNU General Public License +as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. +.PP +This program is distributed in the hope that it will be useful, +but +.B WITHOUT ANY WARRANTY; +without even the implied warranty of +.B MERCHANTABILITY +or +.B FITNESS FOR A PARTICULAR PURPOSE. +See the +.I GNU General Public License +for more details. +.PP +You should have received a copy of the +.B GNU General Public License +along with this program; if not, write to the +.I Free Software Foundation, Inc., +59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +.SH ENVIRONMENT +No environment variables are used. +.SH FILES +None. +.SH AUTHOR +Jens T. Berger Thielemann, +.I +.PP +This manual page was cobbled together by Clint Adams , +based on the output of "chktex --help" and deweb(1). +.SH "SEE ALSO" +.B deweb(1), chktex(1) diff --git a/Build/source/texk/chktex/chktex-1.7.1/chkweb.sh b/Build/source/texk/chktex/chktex-1.7.1/chkweb.sh new file mode 100755 index 00000000000..8d6361d1097 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/chkweb.sh @@ -0,0 +1,56 @@ +#! /bin/sh + +# ChkWEB v1.0, runs the LaTeX parts of a CWEB file through ChkTeX. +# Copyright (C) 1996 Jens T. Berger Thielemann +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# Contact the author at: +# Jens Berger +# Spektrumvn. 4 +# N-0666 Oslo +# Norway +# E-mail: + + +params= + +for p +do + case $p in + --) break + ;; + -*) params="$params $p" + shift + ;; + *) break + ;; + esac +done + + +if test "$1" = ""; then + deweb | chktex -v3 $params +else + for file + do + if test -f $file; then + deweb $file | chktex -p $file -v3 $params + else + deweb $file.w | chktex -p $file.w -v3 $params + fi + done +fi + diff --git a/Build/source/texk/chktex/chktex-1.7.1/config.h.in b/Build/source/texk/chktex/chktex-1.7.1/config.h.in new file mode 100644 index 00000000000..4c5c597974d --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/config.h.in @@ -0,0 +1,142 @@ +/* config.h.in. Generated from configure.in by autoheader. */ + +/* Define to 1 if you have the `access' function. */ +#undef HAVE_ACCESS + +/* Define to 1 if you have the `closedir' function. */ +#undef HAVE_CLOSEDIR + +/* Define to 1 if you have the header file, and it defines `DIR'. + */ +#undef HAVE_DIRENT_H + +/* Define to 1 if you don't have `vprintf' but do have `_doprnt.' */ +#undef HAVE_DOPRNT + +/* Define to 1 if you have the `fileno' function. */ +#undef HAVE_FILENO + +/* Define to 1 if you have the header file. */ +#undef HAVE_INTTYPES_H + +/* Define to 1 if you have the `isatty' function. */ +#undef HAVE_ISATTY + +/* Define to 1 if you have the `termcap' library (-ltermcap). */ +#undef HAVE_LIBTERMCAP + +/* Define to 1 if you have the `termlib' library (-ltermlib). */ +#undef HAVE_LIBTERMLIB + +/* Define to 1 if you have the header file. */ +#undef HAVE_LIMITS_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_MEMORY_H + +/* Define to 1 if you have the header file, and it defines `DIR'. */ +#undef HAVE_NDIR_H + +/* Define to 1 if you have the `opendir' function. */ +#undef HAVE_OPENDIR + +/* "Whether PCRE can be used for user warnings." */ +#undef HAVE_PCRE + +/* "Whether PCRE can be used for user warnings." */ +#undef HAVE_POSIX_ERE + +/* Define to 1 if you have the `readdir' function. */ +#undef HAVE_READDIR + +/* Define to 1 if you have the `stat' function. */ +#undef HAVE_STAT + +/* Define to 1 if you have the header file. */ +#undef HAVE_STAT_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_STDARG_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_STDINT_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_STDLIB_H + +/* Define to 1 if you have the `strcasecmp' function. */ +#undef HAVE_STRCASECMP + +/* Define to 1 if you have the `strdup' function. */ +#undef HAVE_STRDUP + +/* Define to 1 if you have the header file. */ +#undef HAVE_STRINGS_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_STRING_H + +/* Define to 1 if you have the `strlwr' function. */ +#undef HAVE_STRLWR + +/* Define to 1 if you have the `strtol' function. */ +#undef HAVE_STRTOL + +/* Define to 1 if you have the header file, and it defines `DIR'. + */ +#undef HAVE_SYS_DIR_H + +/* Define to 1 if you have the header file, and it defines `DIR'. + */ +#undef HAVE_SYS_NDIR_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_STAT_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_SYS_TYPES_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_TERMCAP_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_TERMLIB_H + +/* Define to 1 if you have the header file. */ +#undef HAVE_UNISTD_H + +/* Define to 1 if you have the `vprintf' function. */ +#undef HAVE_VPRINTF + +/* Define to the address where bug reports for this package should be sent. */ +#undef PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#undef PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#undef PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#undef PACKAGE_TARNAME + +/* Define to the version of this package. */ +#undef PACKAGE_VERSION + +/* Define to 1 if you have the ANSI C header files. */ +#undef STDC_HEADERS + +/* "Strip debug info" */ +#undef STRIP_DEBUG + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `__inline__' or `__inline' if that's what the C compiler + calls it, or to nothing if 'inline' is not supported under any name. */ +#ifndef __cplusplus +#undef inline +#endif + +/* Define to `unsigned int' if does not define. */ +#undef size_t diff --git a/Build/source/texk/chktex/chktex-1.7.1/configure.in b/Build/source/texk/chktex/chktex-1.7.1/configure.in new file mode 100644 index 00000000000..cebe7921f6b --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/configure.in @@ -0,0 +1,213 @@ +dnl +dnl ChkTeX, configuration file. +dnl Copyright (C) 1995-96 Jens T. Berger Thielemann +dnl +dnl This program is free software; you can redistribute it and/or modify +dnl it under the terms of the GNU General Public License as published by +dnl the Free Software Foundation; either version 2 of the License, or +dnl (at your option) any later version. +dnl +dnl This program is distributed in the hope that it will be useful, +dnl but WITHOUT ANY WARRANTY; without even the implied warranty of +dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +dnl GNU General Public License for more details. +dnl +dnl You should have received a copy of the GNU General Public License +dnl along with this program; if not, write to the Free Software +dnl Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +dnl +dnl Contact the author at: +dnl Jens Berger +dnl Spektrumvn. 4 +dnl N-0666 Oslo +dnl Norway +dnl E-mail: +dnl +dnl + + +dnl Process this file with autoconf to produce a configure script. +AC_INIT(ChkTeX, 1.7.1) +AC_SUBST(SCRIPTS) +AC_SUBST(BUILT_SCRIPTS) +AC_SUBST(ELISPDIR) +ELISPDIR= +AC_SUBST(CLEAN) +CLEAN= + +AC_ARG_ENABLE(pcre,[ + --enable-pcre: Use PCRE to allow regular expressions in + user warnings. (Default: yes, if available).],, +enable_pcre=yes) + +AC_ARG_ENABLE(posixre,[ + --enable-posixre: Use POSIX extended regular expressions in + user warnings. (Default: yes, unless using PCRE).],, +enable_posixre=yes) + +AC_ARG_ENABLE(lacheck-replace,[ + --enable-lacheck-replace: Installs a lacheck replacement for the + AUC-TeX interface. (Default: no).],, +enable_lacheck_replace=no) + +AC_ARG_ENABLE(emacs-hack,[ + --enable-emacs-hack: Installs a Elisp file, which makes ChkTeX + available in Emacs. Must be followed by + the path of your elisp files (e.g. + "--enable-emacs-hack=/usr/lib/emacs/"). + (Default: no).],, +enable_emacs_hack=no) + +AC_ARG_ENABLE(debug-info,[ + --enable-debug-info: Compile in miscellaneous runtime debugging + information. (Default: yes).],, +enable_debug_info=yes) + +AC_ARG_ENABLE(coverage-testing,[ + --enable-coverage-testing: Activate coverage testing with gcov. (Default: no)],, +enable_coverage_testing=no) + +AC_MSG_CHECKING(whether lacheck replacement should be installed) +if test "$enable_lacheck_replace" = "yes"; then + SCRIPTS="$SCRIPTS lacheck" + AC_MSG_RESULT(yes) +else + AC_MSG_RESULT(no) +fi + +AC_MSG_CHECKING(whether runtime debug info should be used) +if test "$enable_debug_info" = "yes"; then + AC_MSG_RESULT(yes) +else + AC_DEFINE(STRIP_DEBUG, 1, "Strip debug info") + AC_MSG_RESULT(no) +fi + +AC_MSG_CHECKING(whether the emacs hack should be installed) +case $enable_emacs_hack in + no) AC_MSG_RESULT(no) + ;; + /*|*/*) ELISPDIR=$enable_emacs_hack + AC_MSG_RESULT(yes) + ;; + *) echo; + AC_MSG_ERROR(--enable-emacs-hack needs the *full path* of Elisp files) + ;; +esac + +AC_MSG_CHECKING(whether coverage testing is enabled) +if test "$enable_coverage_testing" = "yes"; then + AC_MSG_RESULT(yes) + CFLAGS="${CFLAGS} -fprofile-arcs -ftest-coverage -O0" + CLEAN="${CLEAN} \$(wildcard *.bb *.bbg *.da *.gcov)" +else + AC_MSG_RESULT(no) +fi + + +dnl Check compiler and flags +AC_PROG_CC +AX_CFLAGS_STRICT_PROTOTYPES +VL_PROG_CC_WARNINGS + +dnl Checks for programs. +AC_PROG_INSTALL +AC_PROG_LN_S +AC_PROG_MKDIR_P +AC_PATH_PROGS(PERL5, perl5 perl, no, $PATH:/usr/bin:/usr/local/bin) +if test "$PERL5" != no; then + AC_MSG_CHECKING(whether perl is v5 or higher) + if $PERL5 -e 'exit($] >= 5)'; then + PERL5=no + AC_MSG_RESULT(no) + else + AC_MSG_RESULT(yes) + fi +fi + +if test "$PERL5" != no; then + BUILT_SCRIPTS="$BUILT_SCRIPTS deweb" + SCRIPTS="$SCRIPTS chkweb" +else + AC_MSG_WARN(chkweb will not be installed since you do not have perl5.) +fi + +AC_CHECK_PROGS(GROFF, 'groff -man -P-bu -Tlatin1' 'nroff -man', 'nroff -man') + +AC_PATH_PROG(LATEX, latex, no) +dnl if test "$LATEX" = no; then +dnl AC_MSG_ERROR([No LaTeX on the system, cannot find latex program.]) +dnl fi + +AC_PATH_PROG(DVIPS, dvips) + +AC_PATH_PROG(LYNX, lynx) +AC_PATH_PROG(LATEX2HTML, latex2html) + +dnl Checks for libraries. +AC_CHECK_LIB(termlib, tgetent) +AC_CHECK_LIB(termcap, tgetent) + +dnl Checks for header files. +AC_HEADER_STDC +AC_HEADER_DIRENT +AC_CHECK_HEADERS(limits.h stat.h strings.h stdarg.h dnl +sys/stat.h termcap.h termlib.h unistd.h) + +dnl Checks for typedefs, structures, and compiler characteristics. +AC_C_CONST +AC_C_INLINE +AC_TYPE_SIZE_T + +dnl Checks for library functions. +AC_FUNC_VPRINTF +AC_CHECK_FUNCS(access closedir fileno isatty opendir readdir stat dnl +strcasecmp strdup strlwr strtol) + + +dnl Check for PCRE regular expression support +AC_MSG_CHECKING(whether PCRE regular expressions are enabled) +AC_MSG_RESULT($enable_pcre) +if test "$enable_pcre" = "yes"; then + AC_CHECK_PROG(WITH_PCRE, pcre-config, yes, no) + if test "$WITH_PCRE" = "yes"; then + AC_DEFINE(HAVE_PCRE, 1, "Whether PCRE can be used for user warnings.") + CFLAGS="${CFLAGS} $(pcre-config --cflags-posix)" + LDFLAGS="${LDFLAGS} $(pcre-config --libs-posix)" + else + AC_DEFINE(HAVE_PCRE, 0, "Whether PCRE can be used for user warnings.") + AC_MSG_WARN(PCRE library not found.) + fi +else + AC_DEFINE(HAVE_PCRE, 0, "Whether PCRE can be used for user warnings.") + AC_MSG_WARN(PCRE regular expressions not enabled.) +fi + +dnl Check for POSIX extended regular expression support +AC_MSG_CHECKING(for POSIX extended regular expressions) +AC_EGREP_CPP([yes], + [#include + #ifdef REG_EXTENDED + yes + # endif + ], posix_ere=yes, posix_ere=no) +AC_MSG_RESULT($posix_ere) +if test "$WITH_PCRE" = "yes"; then + AC_DEFINE(HAVE_POSIX_ERE, 0, "Whether POSIX ERE can be used for user warnings.") +else + if test "$enable_posixre" = "yes"; then + if test "$posix_ere" = "yes"; then + AC_DEFINE(HAVE_POSIX_ERE, 1, "Whether PCRE can be used for user warnings.") + else + AC_DEFINE(HAVE_POSIX_ERE, 0, "Whether PCRE can be used for user warnings.") + fi + else + AC_DEFINE(HAVE_POSIX_ERE, 0, "Whether PCRE can be used for user warnings.") + AC_MSG_WARN(Regular expressions not enabled.) + fi +fi + + +AC_CONFIG_HEADER(config.h) +AC_CONFIG_FILES([stamp-h], [echo timestamp > stamp-h]) +AC_OUTPUT(Makefile deweb rmeheader ChkTeX.tex) diff --git a/Build/source/texk/chktex/chktex-1.7.1/deweb.1 b/Build/source/texk/chktex/chktex-1.7.1/deweb.1 new file mode 100644 index 00000000000..43770aa1fd3 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/deweb.1 @@ -0,0 +1,116 @@ +.TH deweb 1 "June 8, 1996" +.AT 3 +.SH NAME +deweb \- strips away C & CWEB commands from CWEB sources +.SH SYNOPSIS +.B deweb +[ +.B file1 file2 ... +] +.SH DESCRIPTION +.I deweb +filters away all C & CWEB commands from a CWEB source code. This +leaves only the +.I LaTeX +code. This stripped code, in turn, may then +be passed to a suitable syntax checker for LaTeX, like +.I ChkTeX +and +.I lacheck, +or spell-checkers like +.I ispell. +.PP +The +.I chkweb +tool, included in the +.I ChkTeX +distribution will do just this; writing similar scripts should be +trivial. +.PP +When +.I deweb +strips away the C code from your CWEB source, it tries to preserve line breaks. +This means that the error reports from +.I +will be correct regarding to line numbers. In most cases, +the column position +will also be correct. This significantly simplifies +finding the errors in the +.I LaTeX +source (in contrast to the output from +.I cweave, +which output is truly difficult to figure anything out from). +.PP +.I deweb +accepts a list of filenames on the argument line, and will send its output +to +.I stdout. +If no filenames are given, it will read from stdin, acting as +a filter. No options are currently accepted. +.PP +Macho users may try to pipe the output from +.I deweb +directly into +.I LaTeX, +theoretically, this should work. This would ease the debugging +of the +.I LaTeX +code significantly, as when +.I LaTeX +complains about wrong syntax, you'll be able to find the erroneous +line much more easily. Don't expect that the output looks very much +like the final one, though. +.PP +.I deweb +should now understand all correct +.I CWEB +opcodes. If it complains about not understanding a correct opcode, +please inform the author. +.SH DISTRIBUTION +Copyright (C) 1996 Jens T. Berger Thielemann +.PP +This program is free software; you can redistribute it and/or modify +it under the terms of the +.I GNU General Public License +as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. +.PP +This program is distributed in the hope that it will be useful, +but +.B WITHOUT ANY WARRANTY; +without even the implied warranty of +.B MERCHANTABILITY +or +.B FITNESS FOR A PARTICULAR PURPOSE. +See the +.I GNU General Public License +for more details. +.PP +You should have received a copy of the +.B GNU General Public License +along with this program; if not, write to the +.I Free Software Foundation, Inc., +51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +.SH ENVIRONMENT +No environment variables are used. +.SH FILES +None. +.SH AUTHOR +Jens T. Berger Thielemann, +.I +.SH "SEE ALSO" +.B cweave(1), perl(1), chktex, lacheck(1), ispell(1) +.SH BUGS +Doesn't even +.B compile +under +.I Perl +versions before perl v5. Unfortunately, this means that we can't even +tell the user why we failed; +.I Perl +will just complain about not being able to compile the regexps. +.PP +The program will try to swallow the whole input file at once, instead of +processing it on a line\-by\-line basis. +.ex diff --git a/Build/source/texk/chktex/chktex-1.7.1/deweb.in b/Build/source/texk/chktex/chktex-1.7.1/deweb.in new file mode 100644 index 00000000000..91750e636a2 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/deweb.in @@ -0,0 +1,122 @@ +#! @PERL5@ +# deweb v1.2, kills the C sections of a CWEB file, for passing to ChkTeX. +# Copyright (C) 1996 Jens T. Berger Thielemann +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# Contact the author at: +# Jens Berger +# Spektrumvn. 4 +# N-0666 Oslo +# Norway +# E-mail: +# +# +# + +print STDERR "DeWEB v1.2 - Copyright 1996 Jens T. Berger Thielemann\n"; + +undef $/; +$texmode = 1; +$_ = <>; + +while(/\@/) +{ + &out($`); + $_ = $'; + + if(/^@/) { + $_ = $'; + &out('@'); + next; + } + + if(/^([\s\n])/) { + $_ = $'; + print "\n" if $1 eq "\n"; + $texmode = 1; + next; + } + + if(/^[cpd]/i) { + $_ = $'; + $texmode = 0; + next; + } + + if(/^\,/i) { + $_ = $'; + print '\,'; + next; + } + + if(m!^/!) { + $_ = $'; + print '\\\\'; + next; + } + + if(/^[h\&\|\;\#\+]/i || /^i.*/i) { + $_ = $'; + next; + } + + if(/^\*[0-9\*]?((.|\n)*?\.)/) { + $_ = $'; + print $1; + $texmode = 1; + next; + } + + if(/^[<(^.t!]((.|\n)*?)\@\>/i) { + $_ = $'; + print '{'.$1.'}'; + $texmode = 0; + next; + } + + if(/^[=]((.|\n)*?)\@\>/) { + $_ = $'; + print &printnl($1); + next; + } + + if(/^[fsl](\s+\S+\s+\S+)|^\'(.|\n)*?\'|^\[((.|\n)*?)\@\]/i) { + $_ = $'; + print &printnl($+); + next; + } + + @line = split(/\n/, $_, 2); + print STDERR "Unknown opcode, ignored. Buffer:\n$line[0]\n"; + +} + +print $_; + +sub printnl { + my($foo); + if(defined $_[0]) { + $foo = $_[0]; + $foo =~ s/.//g; + } else { + $foo = ""; + } + $foo; +} + +sub out { + print $texmode? $_[0] : &printnl($_[0]); +} diff --git a/Build/source/texk/chktex/chktex-1.7.1/input.tex b/Build/source/texk/chktex/chktex-1.7.1/input.tex new file mode 100644 index 00000000000..76bc301ff25 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/input.tex @@ -0,0 +1 @@ +\this is a test of whether the file is actually inputted... diff --git a/Build/source/texk/chktex/chktex-1.7.1/lacheck b/Build/source/texk/chktex/chktex-1.7.1/lacheck new file mode 100755 index 00000000000..da75d360dee --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/lacheck @@ -0,0 +1,27 @@ +#! /bin/sh + +# lacheck replacement 1.0, lacheck <-> ChkTeX interface (UNIX). +# Copyright (C) 1996 Jens T. Berger Thielemann +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. +# +# Contact the author at: +# Jens Berger +# Spektrumvn. 4 +# N-0666 Oslo +# Norway +# E-mail: + +chktex -v3 $* diff --git a/Build/source/texk/chktex/chktex-1.7.1/m4/ax_cflags_strict_prototypes.m4 b/Build/source/texk/chktex/chktex-1.7.1/m4/ax_cflags_strict_prototypes.m4 new file mode 100644 index 00000000000..06ec9e2f27b --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/m4/ax_cflags_strict_prototypes.m4 @@ -0,0 +1,170 @@ +# =========================================================================== +# http://autoconf-archive.cryp.to/ax_cflags_strict_prototypes.html +# =========================================================================== +# +# SYNOPSIS +# +# AX_CFLAGS_STRICT_PROTOTYPES [(shellvar [,default, [A/NA]] +# +# DESCRIPTION +# +# Try to find a compiler option that requires strict prototypes. +# +# The sanity check is done by looking at sys/signal.h which has a set of +# macro-definitions SIG_DFL and SIG_IGN that are cast to the local +# signal-handler type. If that signal-handler type is not fully qualified +# then the system headers are not seen as strictly prototype clean. +# +# For the GNU CC compiler it will be -fstrict-prototypes +# -Wstrict-prototypes The result is added to the shellvar being CFLAGS by +# default. +# +# DEFAULTS: +# +# - $1 shell-variable-to-add-to : CFLAGS +# - $2 add-value-if-not-found : nothing +# - $3 action-if-found : add value to shellvariable +# - $4 action-if-not-found : nothing +# +# LAST MODIFICATION +# +# 2008-04-12 +# +# COPYLEFT +# +# Copyright (c) 2008 Guido U. Draheim +# +# This program is free software; you can redistribute it and/or modify it +# under the terms of the GNU General Public License as published by the +# Free Software Foundation; either version 2 of the License, or (at your +# option) any later version. +# +# This program is distributed in the hope that it will be useful, but +# WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General +# Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program. If not, see . +# +# As a special exception, the respective Autoconf Macro's copyright owner +# gives unlimited permission to copy, distribute and modify the configure +# scripts that are the output of Autoconf when processing the Macro. You +# need not follow the terms of the GNU General Public License when using +# or distributing such scripts, even though portions of the text of the +# Macro appear in them. The GNU General Public License (GPL) does govern +# all other use of the material that constitutes the Autoconf Macro. +# +# This special exception to the GPL applies to versions of the Autoconf +# Macro released by the Autoconf Macro Archive. When you make and +# distribute a modified version of the Autoconf Macro, you may extend this +# special exception to the GPL to apply to your modified version as well. + +AC_DEFUN([AX_CFLAGS_STRICT_PROTOTYPES],[dnl +AS_VAR_PUSHDEF([FLAGS],[CFLAGS])dnl +AS_VAR_PUSHDEF([VAR],[ac_cv_cflags_strict_prototypes])dnl +AC_CACHE_CHECK([m4_ifval($1,$1,FLAGS) for strict prototypes], +VAR,[VAR="no, unknown" + AC_LANG_SAVE + AC_LANG_C + ac_save_[]FLAGS="$[]FLAGS" +for ac_arg dnl +in "-pedantic % -fstrict-prototypes -Wstrict-prototypes" dnl GCC + "-pedantic % -Wstrict-prototypes" dnl try to warn atleast + "-pedantic % -Wmissing-prototypes" dnl or another warning + "-pedantic % -Werror-implicit-function-declaration" dnl + "-pedantic % -Wimplicit-function-declaration" dnl + # +do FLAGS="$ac_save_[]FLAGS "`echo $ac_arg | sed -e 's,%%.*,,' -e 's,%,,'` + AC_TRY_COMPILE([],[return 0;], + [VAR=`echo $ac_arg | sed -e 's,.*% *,,'` ; break]) +done +case ".$VAR" in + .|.no|.no,*) ;; + *) # sanity check with signal() from sys/signal.h + cp config.log config.tmp + AC_TRY_COMPILE([#include ],[ + if (signal (SIGINT, SIG_IGN) == SIG_DFL) return 1; + if (signal (SIGINT, SIG_IGN) != SIG_DFL) return 2;], + dnl the original did use test -n `$CC testprogram.c` + [if test `diff config.log config.tmp | grep -i warning | wc -l` != 0 +then if test `diff config.log config.tmp | grep -i warning | wc -l` != 1 +then VAR="no, suppressed, signal.h," ; fi ; fi], + [VAR="no, suppressed, signal.h"]) + rm config.tmp + ;; +esac + FLAGS="$ac_save_[]FLAGS" + AC_LANG_RESTORE +]) +case ".$VAR" in + .ok|.ok,*) m4_ifvaln($3,$3) ;; + .|.no|.no,*) m4_ifvaln($4,$4,[m4_ifval($2,[ + AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"]) + m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"])]) ;; + *) m4_ifvaln($3,$3,[ + if echo " $[]m4_ifval($1,$1,FLAGS) " | grep " $VAR " 2>&1 >/dev/null + then AC_RUN_LOG([: m4_ifval($1,$1,FLAGS) does contain $VAR]) + else AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR"]) + m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR" + fi ]) ;; +esac +AS_VAR_POPDEF([VAR])dnl +AS_VAR_POPDEF([FLAGS])dnl +]) + +dnl the only difference - the LANG selection... and the default FLAGS + +AC_DEFUN([AX_CXXFLAGS_STRICT_PROTOTYPES],[dnl +AS_VAR_PUSHDEF([FLAGS],[CXXFLAGS])dnl +AS_VAR_PUSHDEF([VAR],[ac_cv_cxxflags_strict_prototypes])dnl +AC_CACHE_CHECK([m4_ifval($1,$1,FLAGS) for strict prototypes], +VAR,[VAR="no, unknown" + AC_LANG_SAVE + AC_LANG_CPLUSPLUS + ac_save_[]FLAGS="$[]FLAGS" +for ac_arg dnl +in "-pedantic -Werror % -fstrict-prototypes -Wstrict-prototypes" dnl GCC + "-pedantic -Werror % -Wstrict-prototypes" dnl try to warn atleast + "-pedantic -Werror % -Wmissing-prototypes" dnl try to warn atleast + "-pedantic -Werror % -Werror-implicit-function-declaration" dnl + "-pedantic -Werror % -Wimplicit-function-declaration" dnl + "-pedantic % -Wstrict-prototypes %% no, unsupported in C++" dnl oops + # +do FLAGS="$ac_save_[]FLAGS "`echo $ac_arg | sed -e 's,%%.*,,' -e 's,%,,'` + AC_TRY_COMPILE([],[return 0;], + [VAR=`echo $ac_arg | sed -e 's,.*% *,,'` ; break]) +done +case ".$VAR" in + .|.no|.no,*) ;; + *) # sanity check with signal() from sys/signal.h + cp config.log config.tmp + AC_TRY_COMPILE([#include ],[ + if (signal (SIGINT, SIG_IGN) == SIG_DFL) return 1; + if (signal (SIGINT, SIG_IGN) != SIG_DFL) return 2;], + dnl the original did use test -n `$CC testprogram.c` + [if test `diff config.log config.tmp | grep -i warning | wc -l` != 0 +then if test `diff config.log config.tmp | grep -i warning | wc -l` != 1 +then VAR="no, suppressed, signal.h," ; fi ; fi], + [VAR="no, suppressed, signal.h"]) + rm config.tmp + ;; +esac + FLAGS="$ac_save_[]FLAGS" + AC_LANG_RESTORE +]) +case ".$VAR" in + .ok|.ok,*) m4_ifvaln($3,$3) ;; + .|.no|.no,*) m4_ifvaln($4,$4,[m4_ifval($2,[ + AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"]) + m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $2"])]) ;; + *) m4_ifvaln($3,$3,[ + if echo " $[]m4_ifval($1,$1,FLAGS) " | grep " $VAR " 2>&1 >/dev/null + then AC_RUN_LOG([: m4_ifval($1,$1,FLAGS) does contain $VAR]) + else AC_RUN_LOG([: m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR"]) + m4_ifval($1,$1,FLAGS)="$m4_ifval($1,$1,FLAGS) $VAR" + fi ]) ;; +esac +AS_VAR_POPDEF([VAR])dnl +AS_VAR_POPDEF([FLAGS])dnl +]) diff --git a/Build/source/texk/chktex/chktex-1.7.1/m4/vl_prog_cc_warnings.m4 b/Build/source/texk/chktex/chktex-1.7.1/m4/vl_prog_cc_warnings.m4 new file mode 100644 index 00000000000..fe2f6145450 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/m4/vl_prog_cc_warnings.m4 @@ -0,0 +1,111 @@ +AC_DEFUN([VL_PROG_CC_WARNINGS], [ + ansi=$1 + if test -z "$ansi"; then + msg="for C compiler warning flags" + else + msg="for C compiler warning and ANSI conformance flags" + fi + AC_CACHE_CHECK($msg, vl_cv_prog_cc_warnings, [ + if test -n "$CC"; then + cat > conftest.c <&1 | grep -i "WorkShop" > /dev/null 2>&1 && + $CC -c -v -Xc conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-v" + else + vl_cv_prog_cc_warnings="-v -Xc" + fi + + dnl Digital Unix C compiler + elif $CC -V 2>&1 | grep -i "Digital UNIX Compiler" > /dev/null 2>&1 && + $CC -c -verbose -w0 -warnprotos -std1 conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-verbose -w0 -warnprotos" + else + vl_cv_prog_cc_warnings="-verbose -w0 -warnprotos -std1" + fi + + dnl C for AIX Compiler + elif $CC 2>&1 | grep -i "C for AIX Compiler" > /dev/null 2>&1 && + $CC -c -qlanglvl=ansi -qinfo=all conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-qsrcmsg -qinfo=all:noppt:noppc:noobs:nocnd" + else + vl_cv_prog_cc_warnings="-qsrcmsg -qinfo=all:noppt:noppc:noobs:nocnd -qlanglvl=ansi" + fi + + dnl IRIX C compiler + elif $CC -version 2>&1 | grep -i "MIPSpro Compilers" > /dev/null 2>&1 && + $CC -c -fullwarn -ansi -ansiE conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-fullwarn" + else + vl_cv_prog_cc_warnings="-fullwarn -ansi -ansiE" + fi + + dnl HP-UX C compiler + elif what $CC 2>&1 | grep -i "HP C Compiler" > /dev/null 2>&1 && + $CC -c -Aa +w1 conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="+w1" + else + vl_cv_prog_cc_warnings="+w1 -Aa" + fi + + dnl The NEC SX-5 (Super-UX 10) C compiler + elif $CC -V 2>&1 | grep "/SX" > /dev/null 2>&1 && + $CC -c -pvctl[,]fullmsg -Xc conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-pvctl[,]fullmsg" + else + vl_cv_prog_cc_warnings="-pvctl[,]fullmsg -Xc" + fi + + dnl The Cray C compiler (Unicos) + elif $CC -V 2>&1 | grep -i "Cray" > /dev/null 2>&1 && + $CC -c -h msglevel 2 conftest.c > /dev/null 2>&1 && + test -f conftest.o; then + if test -z "$ansi"; then + vl_cv_prog_cc_warnings="-h msglevel 2" + else + vl_cv_prog_cc_warnings="-h msglevel 2 -h conform" + fi + + fi + rm -f conftest.* + fi + if test -n "$vl_cv_prog_cc_warnings"; then + CFLAGS="$CFLAGS $vl_cv_prog_cc_warnings" + else + vl_cv_prog_cc_warnings="unknown" + fi + ]) +])dnl + diff --git a/Build/source/texk/chktex/chktex-1.7.1/rmeheader.in b/Build/source/texk/chktex/chktex-1.7.1/rmeheader.in new file mode 100644 index 00000000000..56ca58ae76e --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/rmeheader.in @@ -0,0 +1,19 @@ +Short: v@PACKAGE_VERSION@. Finds typographic errors in LaTeX +Author: (Baruch Even) +Uploader: (Baruch Even) +Type: text/tex +Replaces: text/tex/ChkTeX.lha +Version: @PACKAGE_VERSION@ +URL: http://www.freesoftware.fsf.org/chktex + + + ##### ### ### ######## ### ## + ### ## ## ## ## ## # + @@ @@ @@@ @@ @@ @@ ####### @@ @ + @@ @@@ @@ @@ @@ @@ ## # @@ + && && && &&&& && @@ & && + &&& && && && && && && @@@@ & && + %%%%% %%% %%% %%% %%% %% && %%% %%% v@PACKAGE_VERSION@ + && & + %%%%%%% + diff --git a/Build/source/texk/chktex/chktex-1.7.1/types.h b/Build/source/texk/chktex/chktex-1.7.1/types.h new file mode 100644 index 00000000000..a26b95295e4 --- /dev/null +++ b/Build/source/texk/chktex/chktex-1.7.1/types.h @@ -0,0 +1,17 @@ +/* + * Clone of , which could not be included because it's + * (c) Commodore/Escom/Amiga/whatever. + * + */ + +#ifndef EXEC_TYPES_H +#define EXEC_TYPES_H + +#ifndef TRUE +# define TRUE 1L +#endif +#ifndef FALSE +# define FALSE 0L +#endif + +#endif diff --git a/Build/source/texk/chktex/config.h.in b/Build/source/texk/chktex/config.h.in index a4eb6d62a07..aa228abcdee 100644 --- a/Build/source/texk/chktex/config.h.in +++ b/Build/source/texk/chktex/config.h.in @@ -79,6 +79,12 @@ /* Define to 1 if you have the `opendir' function. */ #undef HAVE_OPENDIR +/* Whether PCRE can be used for user warnings. */ +#undef HAVE_PCRE + +/* Whether POSIX ERE can be used for user warnings. */ +#undef HAVE_POSIX_ERE + /* Define to 1 if you have the `putenv' function. */ #undef HAVE_PUTENV diff --git a/Build/source/texk/chktex/configure b/Build/source/texk/chktex/configure index 21807be0fb4..80954515836 100755 --- a/Build/source/texk/chktex/configure +++ b/Build/source/texk/chktex/configure @@ -1,6 +1,6 @@ #! /bin/sh # Guess values for system-dependent variables and create Makefiles. -# Generated by GNU Autoconf 2.69 for ChkTeX for TeX Live 1.6.6. +# Generated by GNU Autoconf 2.69 for ChkTeX for TeX Live 1.7.1. # # Report bugs to . # @@ -590,12 +590,12 @@ MAKEFLAGS= # Identity of this package. PACKAGE_NAME='ChkTeX for TeX Live' PACKAGE_TARNAME='chktex-for-tex-live' -PACKAGE_VERSION='1.6.6' -PACKAGE_STRING='ChkTeX for TeX Live 1.6.6' +PACKAGE_VERSION='1.7.1' +PACKAGE_STRING='ChkTeX for TeX Live 1.7.1' PACKAGE_BUGREPORT='tex-k@tug.org' PACKAGE_URL='' -ac_unique_file="chktex-1.6.6/ChkTeX.c" +ac_unique_file="chktex-1.7.1/ChkTeX.c" # Factoring default headers for most tests. ac_includes_default="\ #include @@ -646,8 +646,8 @@ WIN32_WRAP_FALSE WIN32_WRAP_TRUE WIN32_FALSE WIN32_TRUE -PDF_DEPEND -PDFLATEX +MINGW32_FALSE +MINGW32_TRUE WARNING_CFLAGS CPP OTOOL64 @@ -787,8 +787,7 @@ CFLAGS LDFLAGS LIBS CPPFLAGS -CPP -PDFLATEX' +CPP' # Initialize some variables set by options. @@ -1329,7 +1328,7 @@ if test "$ac_init_help" = "long"; then # Omit some internal or obsolete options to make the list less imposing. # This message is too long to be a string in the A/UX 3.1 sh. cat <<_ACEOF -\`configure' configures ChkTeX for TeX Live 1.6.6 to adapt to many kinds of systems. +\`configure' configures ChkTeX for TeX Live 1.7.1 to adapt to many kinds of systems. Usage: $0 [OPTION]... [VAR=VALUE]... @@ -1400,7 +1399,7 @@ fi if test -n "$ac_init_help"; then case $ac_init_help in - short | recursive ) echo "Configuration of ChkTeX for TeX Live 1.6.6:";; + short | recursive ) echo "Configuration of ChkTeX for TeX Live 1.7.1:";; esac cat <<\_ACEOF @@ -1448,7 +1447,6 @@ Some influential environment variables: CPPFLAGS (Objective) C/C++ preprocessor flags, e.g. -I if you have headers in a nonstandard directory CPP C preprocessor - PDFLATEX pdfLaTeX command Use these variables to override the choices made by `configure' or to help it to find libraries and programs with nonstandard names/locations. @@ -1516,7 +1514,7 @@ fi test -n "$ac_init_help" && exit $ac_status if $ac_init_version; then cat <<\_ACEOF -ChkTeX for TeX Live configure 1.6.6 +ChkTeX for TeX Live configure 1.7.1 generated by GNU Autoconf 2.69 Copyright (C) 2012 Free Software Foundation, Inc. @@ -2126,7 +2124,7 @@ cat >config.log <<_ACEOF This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. -It was created by ChkTeX for TeX Live $as_me 1.6.6, which was +It was created by ChkTeX for TeX Live $as_me 1.7.1, which was generated by GNU Autoconf 2.69. Invocation command line was $ $0 $@ @@ -7518,7 +7516,7 @@ fi # Define the identity of the package. PACKAGE='chktex-for-tex-live' - VERSION='1.6.6' + VERSION='1.7.1' cat >>confdefs.h <<_ACEOF @@ -12772,51 +12770,6 @@ WARNING_CFLAGS=$kpse_cv_warning_cflags -for ac_prog in pdflatex -do - # Extract the first word of "$ac_prog", so it can be a program name with args. -set dummy $ac_prog; ac_word=$2 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 -$as_echo_n "checking for $ac_word... " >&6; } -if ${ac_cv_prog_PDFLATEX+:} false; then : - $as_echo_n "(cached) " >&6 -else - if test -n "$PDFLATEX"; then - ac_cv_prog_PDFLATEX="$PDFLATEX" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_PDFLATEX="$ac_prog" - $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done - done -IFS=$as_save_IFS - -fi -fi -PDFLATEX=$ac_cv_prog_PDFLATEX -if test -n "$PDFLATEX"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $PDFLATEX" >&5 -$as_echo "$PDFLATEX" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi - - - test -n "$PDFLATEX" && break -done -test -n "$PDFLATEX" || PDFLATEX="no" - - - for ac_header in stat.h stdarg.h sys/stat.h do : as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh` @@ -12863,15 +12816,19 @@ fi done -test "x$enable_maintainer_mode" = xyes && PDF_DEPEND=ChkTeX.tex - - ac_config_headers="$ac_config_headers config.h" + $as_echo "#define TEX_LIVE 1" >>confdefs.h +$as_echo "#define HAVE_PCRE 0" >>confdefs.h + + +$as_echo "#define HAVE_POSIX_ERE 1" >>confdefs.h + + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for native WIN32 or MINGW32" >&5 $as_echo_n "checking for native WIN32 or MINGW32... " >&6; } if ${kpse_cv_have_win32+:} false; then : @@ -12918,6 +12875,14 @@ fi { $as_echo "$as_me:${as_lineno-$LINENO}: result: $kpse_cv_have_win32" >&5 $as_echo "$kpse_cv_have_win32" >&6; } + if test "x$kpse_cv_have_win32" = xmingw32; then + MINGW32_TRUE= + MINGW32_FALSE='#' +else + MINGW32_TRUE='#' + MINGW32_FALSE= +fi + if test "x$kpse_cv_have_win32" != xno; then WIN32_TRUE= WIN32_FALSE='#' @@ -12935,7 +12900,7 @@ else fi -CHKTEX_TREE=chktex-1.6.6 +CHKTEX_TREE=chktex-1.7.1 PERL5='/usr/bin/env perl' @@ -13354,7 +13319,7 @@ Usage: $0 [OPTIONS] Report bugs to ." lt_cl_version="\ -ChkTeX for TeX Live config.lt 1.6.6 +ChkTeX for TeX Live config.lt 1.7.1 configured by $0, generated by GNU Autoconf 2.69. Copyright (C) 2011 Free Software Foundation, Inc. @@ -14402,9 +14367,7 @@ fi ac_config_files="$ac_config_files Makefile" -ac_config_files="$ac_config_files ChkTeX.tmp:chktex-1.6.6/ChkTeX.tex.in" - -ac_config_files="$ac_config_files deweb.pl:chktex-1.6.6/deweb.in" +ac_config_files="$ac_config_files deweb.pl:chktex-1.7.1/deweb.in" cat >confcache <<\_ACEOF @@ -14544,6 +14507,10 @@ if test -z "${am__fastdepCC_TRUE}" && test -z "${am__fastdepCC_FALSE}"; then as_fn_error $? "conditional \"am__fastdepCC\" was never defined. Usually this means the macro was only invoked conditionally." "$LINENO" 5 fi +if test -z "${MINGW32_TRUE}" && test -z "${MINGW32_FALSE}"; then + as_fn_error $? "conditional \"MINGW32\" was never defined. +Usually this means the macro was only invoked conditionally." "$LINENO" 5 +fi if test -z "${WIN32_TRUE}" && test -z "${WIN32_FALSE}"; then as_fn_error $? "conditional \"WIN32\" was never defined. Usually this means the macro was only invoked conditionally." "$LINENO" 5 @@ -14949,7 +14916,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1 # report actual input values of CONFIG_FILES etc. instead of their # values after options handling. ac_log=" -This file was extended by ChkTeX for TeX Live $as_me 1.6.6, which was +This file was extended by ChkTeX for TeX Live $as_me 1.7.1, which was generated by GNU Autoconf 2.69. Invocation command line was CONFIG_FILES = $CONFIG_FILES @@ -15015,7 +14982,7 @@ _ACEOF cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`" ac_cs_version="\\ -ChkTeX for TeX Live config.status 1.6.6 +ChkTeX for TeX Live config.status 1.7.1 configured by $0, generated by GNU Autoconf 2.69, with options \\"\$ac_cs_config\\" @@ -15428,8 +15395,7 @@ do "libtool") CONFIG_COMMANDS="$CONFIG_COMMANDS libtool" ;; "config.h") CONFIG_HEADERS="$CONFIG_HEADERS config.h" ;; "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;; - "ChkTeX.tmp") CONFIG_FILES="$CONFIG_FILES ChkTeX.tmp:chktex-1.6.6/ChkTeX.tex.in" ;; - "deweb.pl") CONFIG_FILES="$CONFIG_FILES deweb.pl:chktex-1.6.6/deweb.in" ;; + "deweb.pl") CONFIG_FILES="$CONFIG_FILES deweb.pl:chktex-1.7.1/deweb.in" ;; *) as_fn_error $? "invalid argument: \`$ac_config_target'" "$LINENO" 5;; esac diff --git a/Build/source/texk/chktex/configure.ac b/Build/source/texk/chktex/configure.ac index 9be21f06670..a0063c59f64 100644 --- a/Build/source/texk/chktex/configure.ac +++ b/Build/source/texk/chktex/configure.ac @@ -22,9 +22,6 @@ AC_CONFIG_MACRO_DIR([../../m4]) dnl Common code for all programs using libkpathsea. KPSE_COMMON([chktex]) -dnl Checks for programs. -KPSE_CHECK_PDFLATEX - dnl No termlib/termcap/ncurses library for TeX Live dnl Checks for header files. @@ -34,14 +31,15 @@ dnl Checks for library functions. AC_FUNC_VPRINTF AC_CHECK_FUNCS([access closedir fileno isatty opendir readdir stat strcasecmp strdup strlwr strtol]) -dnl Rebuild ChkTeX.pdf if required and maintainer-mode is enabled. -test "x$enable_maintainer_mode" = xyes && PDF_DEPEND=ChkTeX.tex -AC_SUBST([PDF_DEPEND]) - AC_CONFIG_HEADERS([config.h]) + +dnl For TeX Live we always use Posix extended regular expressions AC_DEFINE([TEX_LIVE], 1, [Define to 1 for a TeX Live build.]) +AC_DEFINE([HAVE_PCRE], 0, [Whether PCRE can be used for user warnings.]) +AC_DEFINE([HAVE_POSIX_ERE], 1, [Whether POSIX ERE can be used for user warnings.]) KPSE_CHECK_WIN32 +AM_CONDITIONAL([MINGW32], [test "x$kpse_cv_have_win32" = xmingw32]) AM_CONDITIONAL([WIN32], [test "x$kpse_cv_have_win32" != xno]) AM_CONDITIONAL([WIN32_WRAP], [test -r $srcdir/../../texk/texlive/w32_wrapper/runscript.exe]) @@ -52,7 +50,6 @@ AC_SUBST([PERL5], ['/usr/bin/env perl']) KPSE_KPATHSEA_FLAGS AC_CONFIG_FILES([Makefile]) -AC_CONFIG_FILES([ChkTeX.tmp:chktex-]chktex_version[/ChkTeX.tex.in]) AC_CONFIG_FILES([deweb.pl:chktex-]chktex_version[/deweb.in], [chmod +x deweb.pl]) AC_OUTPUT diff --git a/Build/source/texk/chktex/regex/COPYING.LIB b/Build/source/texk/chktex/regex/COPYING.LIB new file mode 100644 index 00000000000..cf9b6b99726 --- /dev/null +++ b/Build/source/texk/chktex/regex/COPYING.LIB @@ -0,0 +1,510 @@ + + GNU LESSER GENERAL PUBLIC LICENSE + Version 2.1, February 1999 + + Copyright (C) 1991, 1999 Free Software Foundation, Inc. + 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + +[This is the first released version of the Lesser GPL. It also counts + as the successor of the GNU Library Public License, version 2, hence + the version number 2.1.] + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +Licenses are intended to guarantee your freedom to share and change +free software--to make sure the software is free for all its users. + + This license, the Lesser General Public License, applies to some +specially designated software packages--typically libraries--of the +Free Software Foundation and other authors who decide to use it. You +can use it too, but we suggest you first think carefully about whether +this license or the ordinary General Public License is the better +strategy to use in any particular case, based on the explanations +below. + + When we speak of free software, we are referring to freedom of use, +not price. Our General Public Licenses are designed to make sure that +you have the freedom to distribute copies of free software (and charge +for this service if you wish); that you receive source code or can get +it if you want it; that you can change the software and use pieces of +it in new free programs; and that you are informed that you can do +these things. + + To protect your rights, we need to make restrictions that forbid +distributors to deny you these rights or to ask you to surrender these +rights. These restrictions translate to certain responsibilities for +you if you distribute copies of the library or if you modify it. + + For example, if you distribute copies of the library, whether gratis +or for a fee, you must give the recipients all the rights that we gave +you. You must make sure that they, too, receive or can get the source +code. If you link other code with the library, you must provide +complete object files to the recipients, so that they can relink them +with the library after making changes to the library and recompiling +it. And you must show them these terms so they know their rights. + + We protect your rights with a two-step method: (1) we copyright the +library, and (2) we offer you this license, which gives you legal +permission to copy, distribute and/or modify the library. + + To protect each distributor, we want to make it very clear that +there is no warranty for the free library. Also, if the library is +modified by someone else and passed on, the recipients should know +that what they have is not the original version, so that the original +author's reputation will not be affected by problems that might be +introduced by others. +^L + Finally, software patents pose a constant threat to the existence of +any free program. We wish to make sure that a company cannot +effectively restrict the users of a free program by obtaining a +restrictive license from a patent holder. Therefore, we insist that +any patent license obtained for a version of the library must be +consistent with the full freedom of use specified in this license. + + Most GNU software, including some libraries, is covered by the +ordinary GNU General Public License. This license, the GNU Lesser +General Public License, applies to certain designated libraries, and +is quite different from the ordinary General Public License. We use +this license for certain libraries in order to permit linking those +libraries into non-free programs. + + When a program is linked with a library, whether statically or using +a shared library, the combination of the two is legally speaking a +combined work, a derivative of the original library. The ordinary +General Public License therefore permits such linking only if the +entire combination fits its criteria of freedom. The Lesser General +Public License permits more lax criteria for linking other code with +the library. + + We call this license the "Lesser" General Public License because it +does Less to protect the user's freedom than the ordinary General +Public License. It also provides other free software developers Less +of an advantage over competing non-free programs. These disadvantages +are the reason we use the ordinary General Public License for many +libraries. However, the Lesser license provides advantages in certain +special circumstances. + + For example, on rare occasions, there may be a special need to +encourage the widest possible use of a certain library, so that it +becomes a de-facto standard. To achieve this, non-free programs must +be allowed to use the library. A more frequent case is that a free +library does the same job as widely used non-free libraries. In this +case, there is little to gain by limiting the free library to free +software only, so we use the Lesser General Public License. + + In other cases, permission to use a particular library in non-free +programs enables a greater number of people to use a large body of +free software. For example, permission to use the GNU C Library in +non-free programs enables many more people to use the whole GNU +operating system, as well as its variant, the GNU/Linux operating +system. + + Although the Lesser General Public License is Less protective of the +users' freedom, it does ensure that the user of a program that is +linked with the Library has the freedom and the wherewithal to run +that program using a modified version of the Library. + + The precise terms and conditions for copying, distribution and +modification follow. Pay close attention to the difference between a +"work based on the library" and a "work that uses the library". The +former contains code derived from the library, whereas the latter must +be combined with the library in order to run. +^L + GNU LESSER GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License Agreement applies to any software library or other +program which contains a notice placed by the copyright holder or +other authorized party saying it may be distributed under the terms of +this Lesser General Public License (also called "this License"). +Each licensee is addressed as "you". + + A "library" means a collection of software functions and/or data +prepared so as to be conveniently linked with application programs +(which use some of those functions and data) to form executables. + + The "Library", below, refers to any such software library or work +which has been distributed under these terms. A "work based on the +Library" means either the Library or any derivative work under +copyright law: that is to say, a work containing the Library or a +portion of it, either verbatim or with modifications and/or translated +straightforwardly into another language. (Hereinafter, translation is +included without limitation in the term "modification".) + + "Source code" for a work means the preferred form of the work for +making modifications to it. For a library, complete source code means +all the source code for all modules it contains, plus any associated +interface definition files, plus the scripts used to control +compilation and installation of the library. + + Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running a program using the Library is not restricted, and output from +such a program is covered only if its contents constitute a work based +on the Library (independent of the use of the Library in a tool for +writing it). Whether that is true depends on what the Library does +and what the program that uses the Library does. + + 1. You may copy and distribute verbatim copies of the Library's +complete source code as you receive it, in any medium, provided that +you conspicuously and appropriately publish on each copy an +appropriate copyright notice and disclaimer of warranty; keep intact +all the notices that refer to this License and to the absence of any +warranty; and distribute a copy of this License along with the +Library. + + You may charge a fee for the physical act of transferring a copy, +and you may at your option offer warranty protection in exchange for a +fee. + + 2. You may modify your copy or copies of the Library or any portion +of it, thus forming a work based on the Library, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) The modified work must itself be a software library. + + b) You must cause the files modified to carry prominent notices + stating that you changed the files and the date of any change. + + c) You must cause the whole of the work to be licensed at no + charge to all third parties under the terms of this License. + + d) If a facility in the modified Library refers to a function or a + table of data to be supplied by an application program that uses + the facility, other than as an argument passed when the facility + is invoked, then you must make a good faith effort to ensure that, + in the event an application does not supply such function or + table, the facility still operates, and performs whatever part of + its purpose remains meaningful. + + (For example, a function in a library to compute square roots has + a purpose that is entirely well-defined independent of the + application. Therefore, Subsection 2d requires that any + application-supplied function or table used by this function must + be optional: if the application does not supply it, the square + root function must still compute square roots.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Library, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Library, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote +it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Library. + +In addition, mere aggregation of another work not based on the Library +with the Library (or with a work based on the Library) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may opt to apply the terms of the ordinary GNU General Public +License instead of this License to a given copy of the Library. To do +this, you must alter all the notices that refer to this License, so +that they refer to the ordinary GNU General Public License, version 2, +instead of to this License. (If a newer version than version 2 of the +ordinary GNU General Public License has appeared, then you can specify +that version instead if you wish.) Do not make any other change in +these notices. +^L + Once this change is made in a given copy, it is irreversible for +that copy, so the ordinary GNU General Public License applies to all +subsequent copies and derivative works made from that copy. + + This option is useful when you wish to copy part of the code of +the Library into a program that is not a library. + + 4. You may copy and distribute the Library (or a portion or +derivative of it, under Section 2) in object code or executable form +under the terms of Sections 1 and 2 above provided that you accompany +it with the complete corresponding machine-readable source code, which +must be distributed under the terms of Sections 1 and 2 above on a +medium customarily used for software interchange. + + If distribution of object code is made by offering access to copy +from a designated place, then offering equivalent access to copy the +source code from the same place satisfies the requirement to +distribute the source code, even though third parties are not +compelled to copy the source along with the object code. + + 5. A program that contains no derivative of any portion of the +Library, but is designed to work with the Library by being compiled or +linked with it, is called a "work that uses the Library". Such a +work, in isolation, is not a derivative work of the Library, and +therefore falls outside the scope of this License. + + However, linking a "work that uses the Library" with the Library +creates an executable that is a derivative of the Library (because it +contains portions of the Library), rather than a "work that uses the +library". The executable is therefore covered by this License. +Section 6 states terms for distribution of such executables. + + When a "work that uses the Library" uses material from a header file +that is part of the Library, the object code for the work may be a +derivative work of the Library even though the source code is not. +Whether this is true is especially significant if the work can be +linked without the Library, or if the work is itself a library. The +threshold for this to be true is not precisely defined by law. + + If such an object file uses only numerical parameters, data +structure layouts and accessors, and small macros and small inline +functions (ten lines or less in length), then the use of the object +file is unrestricted, regardless of whether it is legally a derivative +work. (Executables containing this object code plus portions of the +Library will still fall under Section 6.) + + Otherwise, if the work is a derivative of the Library, you may +distribute the object code for the work under the terms of Section 6. +Any executables containing that work also fall under Section 6, +whether or not they are linked directly with the Library itself. +^L + 6. As an exception to the Sections above, you may also combine or +link a "work that uses the Library" with the Library to produce a +work containing portions of the Library, and distribute that work +under terms of your choice, provided that the terms permit +modification of the work for the customer's own use and reverse +engineering for debugging such modifications. + + You must give prominent notice with each copy of the work that the +Library is used in it and that the Library and its use are covered by +this License. You must supply a copy of this License. If the work +during execution displays copyright notices, you must include the +copyright notice for the Library among them, as well as a reference +directing the user to the copy of this License. Also, you must do one +of these things: + + a) Accompany the work with the complete corresponding + machine-readable source code for the Library including whatever + changes were used in the work (which must be distributed under + Sections 1 and 2 above); and, if the work is an executable linked + with the Library, with the complete machine-readable "work that + uses the Library", as object code and/or source code, so that the + user can modify the Library and then relink to produce a modified + executable containing the modified Library. (It is understood + that the user who changes the contents of definitions files in the + Library will not necessarily be able to recompile the application + to use the modified definitions.) + + b) Use a suitable shared library mechanism for linking with the + Library. A suitable mechanism is one that (1) uses at run time a + copy of the library already present on the user's computer system, + rather than copying library functions into the executable, and (2) + will operate properly with a modified version of the library, if + the user installs one, as long as the modified version is + interface-compatible with the version that the work was made with. + + c) Accompany the work with a written offer, valid for at least + three years, to give the same user the materials specified in + Subsection 6a, above, for a charge no more than the cost of + performing this distribution. + + d) If distribution of the work is made by offering access to copy + from a designated place, offer equivalent access to copy the above + specified materials from the same place. + + e) Verify that the user has already received a copy of these + materials or that you have already sent this user a copy. + + For an executable, the required form of the "work that uses the +Library" must include any data and utility programs needed for +reproducing the executable from it. However, as a special exception, +the materials to be distributed need not include anything that is +normally distributed (in either source or binary form) with the major +components (compiler, kernel, and so on) of the operating system on +which the executable runs, unless that component itself accompanies +the executable. + + It may happen that this requirement contradicts the license +restrictions of other proprietary libraries that do not normally +accompany the operating system. Such a contradiction means you cannot +use both them and the Library together in an executable that you +distribute. +^L + 7. You may place library facilities that are a work based on the +Library side-by-side in a single library together with other library +facilities not covered by this License, and distribute such a combined +library, provided that the separate distribution of the work based on +the Library and of the other library facilities is otherwise +permitted, and provided that you do these two things: + + a) Accompany the combined library with a copy of the same work + based on the Library, uncombined with any other library + facilities. This must be distributed under the terms of the + Sections above. + + b) Give prominent notice with the combined library of the fact + that part of it is a work based on the Library, and explaining + where to find the accompanying uncombined form of the same work. + + 8. You may not copy, modify, sublicense, link with, or distribute +the Library except as expressly provided under this License. Any +attempt otherwise to copy, modify, sublicense, link with, or +distribute the Library is void, and will automatically terminate your +rights under this License. However, parties who have received copies, +or rights, from you under this License will not have their licenses +terminated so long as such parties remain in full compliance. + + 9. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Library or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Library (or any work based on the +Library), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Library or works based on it. + + 10. Each time you redistribute the Library (or any work based on the +Library), the recipient automatically receives a license from the +original licensor to copy, distribute, link with or modify the Library +subject to these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties with +this License. +^L + 11. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Library at all. For example, if a patent +license would not permit royalty-free redistribution of the Library by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Library. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply, and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 12. If the distribution and/or use of the Library is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Library under this License +may add an explicit geographical distribution limitation excluding those +countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 13. The Free Software Foundation may publish revised and/or new +versions of the Lesser General Public License from time to time. +Such new versions will be similar in spirit to the present version, +but may differ in detail to address new problems or concerns. + +Each version is given a distinguishing version number. If the Library +specifies a version number of this License which applies to it and +"any later version", you have the option of following the terms and +conditions either of that version or of any later version published by +the Free Software Foundation. If the Library does not specify a +license version number, you may choose any version ever published by +the Free Software Foundation. +^L + 14. If you wish to incorporate parts of the Library into other free +programs whose distribution conditions are incompatible with these, +write to the author to ask for permission. For software which is +copyrighted by the Free Software Foundation, write to the Free +Software Foundation; we sometimes make exceptions for this. Our +decision will be guided by the two goals of preserving the free status +of all derivatives of our free software and of promoting the sharing +and reuse of software generally. + + NO WARRANTY + + 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO +WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. +EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR +OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY +KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE +LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME +THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN +WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY +AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU +FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR +CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE +LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING +RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A +FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF +SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH +DAMAGES. + + END OF TERMS AND CONDITIONS +^L + How to Apply These Terms to Your New Libraries + + If you develop a new library, and you want it to be of the greatest +possible use to the public, we recommend making it free software that +everyone can redistribute and change. You can do so by permitting +redistribution under these terms (or, alternatively, under the terms +of the ordinary General Public License). + + To apply these terms, attach the following notices to the library. +It is safest to attach them to the start of each source file to most +effectively convey the exclusion of warranty; and each file should +have at least the "copyright" line and a pointer to where the full +notice is found. + + + + Copyright (C) + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with this library; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +Also add information on how to contact you by electronic and paper mail. + +You should also get your employer (if you work as a programmer) or +your school, if any, to sign a "copyright disclaimer" for the library, +if necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the + library `Frob' (a library for tweaking knobs) written by James + Random Hacker. + + , 1 April 1990 + Ty Coon, President of Vice + +That's all there is to it! + + diff --git a/Build/source/texk/chktex/regex/README b/Build/source/texk/chktex/regex/README new file mode 100644 index 00000000000..9b3e8979205 --- /dev/null +++ b/Build/source/texk/chktex/regex/README @@ -0,0 +1,122 @@ +This is the regex functionality from glibc 2.5 extracted into a +separate library, for Win32. It may be built, from the sources +provided, using the command sequence:-- + + ./configure [--options...] && make + +For a list of available configuration options, run:-- + + ./configure --help + +After building, as above, the resultant DLL, and optionally the +associated development kit, may be installed by:-- + + make install + +while redistributable binary DLL and development library kits may +be created by:-- + + make dist + + +The original sources, on which this port is based, remain +copyright of their respective authors, or of the Free Software +Foundation Inc., as indicated in individual file headers; all are +redistributed with permission, as granted by the GNU Lesser +General Public License. + +This is free software. It is provided AS IS, in the hope that +it may be useful, but WITHOUT WARRANTY OF ANY KIND, not even an +IMPLIED WARRANTY of MERCHANTABILITY, nor of FITNESS FOR ANY +PARTICULAR PURPOSE. + +Permission is granted to redistribute this software, either +"as is" or in modified form, under the terms of the GNU Lesser +General Public License, as published by the Free Software +Foundation; either version 2.1, or (at your option) any later +version. + +You should have received a copy of the GNU Lesser General Public +License along with this software; see the file COPYING.LIB. If +not, write to the Free Software Foundation, 51 Franklin St - +Fifth Floor, Boston, MA 02110-1301, USA. + +The original port of this functionality was implemented by Tor +Lillqvist; I've adapted his work, to make it somewhat more MinGW +friendly. I have *not* modified any of the `C' sources provided +by Tor; nor have I changed the naming conventions he adopted for +generated distributables. I *have*:-- + +1) Replaced Tor's original `Makefile' with an autoconf generated + configure script, and a backwardly compatible `Makefile.in'; + this provides a more flexible build procedure, which I find + more convenient, when cross-compiling on a GNU/Linux host. + +2) Added VPATH support, for `out of tree' builds. + +3) Adapted the build procedure, to avoid a dependency on the `lib' + program from Microsoft's MSVC tool chain. This is achieved by + providing an option to configure, which is disabled by default; + it may by activated by specifying `--enable-msvc-implib' on the + configure command line. If this option is not activated, or if + the MSVC `lib' tool is not present, the Makefile is configured + without binding the rule for building an MSVC compatible import + library, to the default target, (although the rule is left in + place for explicit use). + + If the `--enable-msvc-implib' option is specified, but `lib' is + not present, then configure will issue a warning message, and + will again configure the Makefile without binding this rule to + the default target. + + Only if the `--enable-msvc-implib' option is specified, *and* + the `lib' tool is present, will building of an MSVC compatible + import library be configured as a default deliverable. + +4) Added `install', `install-dll' and `install-dev' targets, to + support direct installation of the DLL, and its associated + development kit. + +5) Changed the default packaging format for distributables, from + Tor's exclusive choice of `zip', to my own preferred `tar.gz'; + `zip' format remains available, as an option, by configuring + with `--enable-dist=zip'. + +6) Added `bindist', `devdist' and `srcdist' targets, for greater + flexibility in building distribution kits. + +The original text of Tor's README file will be found below. + +--Keith Marshall + +I call the DLL libgnurx-0.dll which hopefully should be unique. At +least it isn't "regex.dll" which has been used by the +gnuwin32.sourceforge.net site for *two* incompatible DLLs. (That mess, +and the mess with their build of Henry Spencer's regex library, was +what lead me to build my own GNU regex library. See the +gnuwin32-users mailing list archives from December 2006.) + +The "-0" is so that if at some point I build a release that isn't +binary compatible, I can then increment that and use a different name. + +The import library for gcc is called libgnurx.dll.a, but I also +distribute a copy of it called libregex.a so that configure scripts +that look for -lregex will work. + +Note that none of the wide-character and i18n functionality which is +built when this is part of glibc gets compiled. Thus things like +character classes most probably work only for single-byte codepages. + +Compiling that stuff would drag in lots of glibc's locale handling +stuff which is completely incompatible with Microsoft's C library's +locale handling anyway. Also, I am not sure whether the GNU regex code +is prepared to handle a two-byte wchar_t, or does it assume that +wchar_t is int as it is on Linux? Hmm, actually there is lots of +sizeof(wchar_t) in glibc, so maybe it *is* prepared? Maybe +later... But anyway, it would presumably mean we should have not just +the regex functionality but a larger subset of glibc that would +include all locale, ctype, wchar, mbs, etc stuff, presumably ending up +with a very large part of glibc (not the system calls, +obviously). Indeed, something to save for later, or never... + +--Tor Lillqvist , diff --git a/Build/source/texk/chktex/regex/regcomp.c b/Build/source/texk/chktex/regex/regcomp.c new file mode 100644 index 00000000000..78a1218cf86 --- /dev/null +++ b/Build/source/texk/chktex/regex/regcomp.c @@ -0,0 +1,3800 @@ +/* Extended regular expression matching and search library. + Copyright (C) 2002,2003,2004,2005,2006 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Isamu Hasegawa . + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern, + size_t length, reg_syntax_t syntax); +static void re_compile_fastmap_iter (regex_t *bufp, + const re_dfastate_t *init_state, + char *fastmap); +static reg_errcode_t init_dfa (re_dfa_t *dfa, size_t pat_len); +#ifdef RE_ENABLE_I18N +static void free_charset (re_charset_t *cset); +#endif /* RE_ENABLE_I18N */ +static void free_workarea_compile (regex_t *preg); +static reg_errcode_t create_initial_state (re_dfa_t *dfa); +#ifdef RE_ENABLE_I18N +static void optimize_utf8 (re_dfa_t *dfa); +#endif +static reg_errcode_t analyze (regex_t *preg); +static reg_errcode_t preorder (bin_tree_t *root, + reg_errcode_t (fn (void *, bin_tree_t *)), + void *extra); +static reg_errcode_t postorder (bin_tree_t *root, + reg_errcode_t (fn (void *, bin_tree_t *)), + void *extra); +static reg_errcode_t optimize_subexps (void *extra, bin_tree_t *node); +static reg_errcode_t lower_subexps (void *extra, bin_tree_t *node); +static bin_tree_t *lower_subexp (reg_errcode_t *err, regex_t *preg, + bin_tree_t *node); +static reg_errcode_t calc_first (void *extra, bin_tree_t *node); +static reg_errcode_t calc_next (void *extra, bin_tree_t *node); +static reg_errcode_t link_nfa_nodes (void *extra, bin_tree_t *node); +static int duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint); +static int search_duplicated_node (const re_dfa_t *dfa, int org_node, + unsigned int constraint); +static reg_errcode_t calc_eclosure (re_dfa_t *dfa); +static reg_errcode_t calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, + int node, int root); +static reg_errcode_t calc_inveclosure (re_dfa_t *dfa); +static int fetch_number (re_string_t *input, re_token_t *token, + reg_syntax_t syntax); +static int peek_token (re_token_t *token, re_string_t *input, + reg_syntax_t syntax) internal_function; +static bin_tree_t *parse (re_string_t *regexp, regex_t *preg, + reg_syntax_t syntax, reg_errcode_t *err); +static bin_tree_t *parse_reg_exp (re_string_t *regexp, regex_t *preg, + re_token_t *token, reg_syntax_t syntax, + int nest, reg_errcode_t *err); +static bin_tree_t *parse_branch (re_string_t *regexp, regex_t *preg, + re_token_t *token, reg_syntax_t syntax, + int nest, reg_errcode_t *err); +static bin_tree_t *parse_expression (re_string_t *regexp, regex_t *preg, + re_token_t *token, reg_syntax_t syntax, + int nest, reg_errcode_t *err); +static bin_tree_t *parse_sub_exp (re_string_t *regexp, regex_t *preg, + re_token_t *token, reg_syntax_t syntax, + int nest, reg_errcode_t *err); +static bin_tree_t *parse_dup_op (bin_tree_t *dup_elem, re_string_t *regexp, + re_dfa_t *dfa, re_token_t *token, + reg_syntax_t syntax, reg_errcode_t *err); +static bin_tree_t *parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, + re_token_t *token, reg_syntax_t syntax, + reg_errcode_t *err); +static reg_errcode_t parse_bracket_element (bracket_elem_t *elem, + re_string_t *regexp, + re_token_t *token, int token_len, + re_dfa_t *dfa, + reg_syntax_t syntax, + int accept_hyphen); +static reg_errcode_t parse_bracket_symbol (bracket_elem_t *elem, + re_string_t *regexp, + re_token_t *token); +#ifdef RE_ENABLE_I18N +static reg_errcode_t build_equiv_class (bitset_t sbcset, + re_charset_t *mbcset, + int *equiv_class_alloc, + const unsigned char *name); +static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans, + bitset_t sbcset, + re_charset_t *mbcset, + int *char_class_alloc, + const unsigned char *class_name, + reg_syntax_t syntax); +#else /* not RE_ENABLE_I18N */ +static reg_errcode_t build_equiv_class (bitset_t sbcset, + const unsigned char *name); +static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans, + bitset_t sbcset, + const unsigned char *class_name, + reg_syntax_t syntax); +#endif /* not RE_ENABLE_I18N */ +static bin_tree_t *build_charclass_op (re_dfa_t *dfa, + RE_TRANSLATE_TYPE trans, + const unsigned char *class_name, + const unsigned char *extra, + int non_match, reg_errcode_t *err); +static bin_tree_t *create_tree (re_dfa_t *dfa, + bin_tree_t *left, bin_tree_t *right, + re_token_type_t type); +static bin_tree_t *create_token_tree (re_dfa_t *dfa, + bin_tree_t *left, bin_tree_t *right, + const re_token_t *token); +static bin_tree_t *duplicate_tree (const bin_tree_t *src, re_dfa_t *dfa); +static void free_token (re_token_t *node); +static reg_errcode_t free_tree (void *extra, bin_tree_t *node); +static reg_errcode_t mark_opt_subexp (void *extra, bin_tree_t *node); + +/* This table gives an error message for each of the error codes listed + in regex.h. Obviously the order here has to be same as there. + POSIX doesn't require that we do anything for REG_NOERROR, + but why not be nice? */ + +const char __re_error_msgid[] attribute_hidden = + { +#define REG_NOERROR_IDX 0 + gettext_noop ("Success") /* REG_NOERROR */ + "\0" +#define REG_NOMATCH_IDX (REG_NOERROR_IDX + sizeof "Success") + gettext_noop ("No match") /* REG_NOMATCH */ + "\0" +#define REG_BADPAT_IDX (REG_NOMATCH_IDX + sizeof "No match") + gettext_noop ("Invalid regular expression") /* REG_BADPAT */ + "\0" +#define REG_ECOLLATE_IDX (REG_BADPAT_IDX + sizeof "Invalid regular expression") + gettext_noop ("Invalid collation character") /* REG_ECOLLATE */ + "\0" +#define REG_ECTYPE_IDX (REG_ECOLLATE_IDX + sizeof "Invalid collation character") + gettext_noop ("Invalid character class name") /* REG_ECTYPE */ + "\0" +#define REG_EESCAPE_IDX (REG_ECTYPE_IDX + sizeof "Invalid character class name") + gettext_noop ("Trailing backslash") /* REG_EESCAPE */ + "\0" +#define REG_ESUBREG_IDX (REG_EESCAPE_IDX + sizeof "Trailing backslash") + gettext_noop ("Invalid back reference") /* REG_ESUBREG */ + "\0" +#define REG_EBRACK_IDX (REG_ESUBREG_IDX + sizeof "Invalid back reference") + gettext_noop ("Unmatched [ or [^") /* REG_EBRACK */ + "\0" +#define REG_EPAREN_IDX (REG_EBRACK_IDX + sizeof "Unmatched [ or [^") + gettext_noop ("Unmatched ( or \\(") /* REG_EPAREN */ + "\0" +#define REG_EBRACE_IDX (REG_EPAREN_IDX + sizeof "Unmatched ( or \\(") + gettext_noop ("Unmatched \\{") /* REG_EBRACE */ + "\0" +#define REG_BADBR_IDX (REG_EBRACE_IDX + sizeof "Unmatched \\{") + gettext_noop ("Invalid content of \\{\\}") /* REG_BADBR */ + "\0" +#define REG_ERANGE_IDX (REG_BADBR_IDX + sizeof "Invalid content of \\{\\}") + gettext_noop ("Invalid range end") /* REG_ERANGE */ + "\0" +#define REG_ESPACE_IDX (REG_ERANGE_IDX + sizeof "Invalid range end") + gettext_noop ("Memory exhausted") /* REG_ESPACE */ + "\0" +#define REG_BADRPT_IDX (REG_ESPACE_IDX + sizeof "Memory exhausted") + gettext_noop ("Invalid preceding regular expression") /* REG_BADRPT */ + "\0" +#define REG_EEND_IDX (REG_BADRPT_IDX + sizeof "Invalid preceding regular expression") + gettext_noop ("Premature end of regular expression") /* REG_EEND */ + "\0" +#define REG_ESIZE_IDX (REG_EEND_IDX + sizeof "Premature end of regular expression") + gettext_noop ("Regular expression too big") /* REG_ESIZE */ + "\0" +#define REG_ERPAREN_IDX (REG_ESIZE_IDX + sizeof "Regular expression too big") + gettext_noop ("Unmatched ) or \\)") /* REG_ERPAREN */ + }; + +const size_t __re_error_msgid_idx[] attribute_hidden = + { + REG_NOERROR_IDX, + REG_NOMATCH_IDX, + REG_BADPAT_IDX, + REG_ECOLLATE_IDX, + REG_ECTYPE_IDX, + REG_EESCAPE_IDX, + REG_ESUBREG_IDX, + REG_EBRACK_IDX, + REG_EPAREN_IDX, + REG_EBRACE_IDX, + REG_BADBR_IDX, + REG_ERANGE_IDX, + REG_ESPACE_IDX, + REG_BADRPT_IDX, + REG_EEND_IDX, + REG_ESIZE_IDX, + REG_ERPAREN_IDX + }; + +/* Entry points for GNU code. */ + +/* re_compile_pattern is the GNU regular expression compiler: it + compiles PATTERN (of length LENGTH) and puts the result in BUFP. + Returns 0 if the pattern was valid, otherwise an error string. + + Assumes the `allocated' (and perhaps `buffer') and `translate' fields + are set in BUFP on entry. */ + +const char * +re_compile_pattern (pattern, length, bufp) + const char *pattern; + size_t length; + struct re_pattern_buffer *bufp; +{ + reg_errcode_t ret; + + /* And GNU code determines whether or not to get register information + by passing null for the REGS argument to re_match, etc., not by + setting no_sub, unless RE_NO_SUB is set. */ + bufp->no_sub = !!(re_syntax_options & RE_NO_SUB); + + /* Match anchors at newline. */ + bufp->newline_anchor = 1; + + ret = re_compile_internal (bufp, pattern, length, re_syntax_options); + + if (!ret) + return NULL; + return gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]); +} +#ifdef _LIBC +weak_alias (__re_compile_pattern, re_compile_pattern) +#endif + +/* Set by `re_set_syntax' to the current regexp syntax to recognize. Can + also be assigned to arbitrarily: each pattern buffer stores its own + syntax, so it can be changed between regex compilations. */ +/* This has no initializer because initialized variables in Emacs + become read-only after dumping. */ +reg_syntax_t re_syntax_options; + + +/* Specify the precise syntax of regexps for compilation. This provides + for compatibility for various utilities which historically have + different, incompatible syntaxes. + + The argument SYNTAX is a bit mask comprised of the various bits + defined in regex.h. We return the old syntax. */ + +reg_syntax_t +re_set_syntax (syntax) + reg_syntax_t syntax; +{ + reg_syntax_t ret = re_syntax_options; + + re_syntax_options = syntax; + return ret; +} +#ifdef _LIBC +weak_alias (__re_set_syntax, re_set_syntax) +#endif + +int +re_compile_fastmap (bufp) + struct re_pattern_buffer *bufp; +{ + re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; + char *fastmap = bufp->fastmap; + + memset (fastmap, '\0', sizeof (char) * SBC_MAX); + re_compile_fastmap_iter (bufp, dfa->init_state, fastmap); + if (dfa->init_state != dfa->init_state_word) + re_compile_fastmap_iter (bufp, dfa->init_state_word, fastmap); + if (dfa->init_state != dfa->init_state_nl) + re_compile_fastmap_iter (bufp, dfa->init_state_nl, fastmap); + if (dfa->init_state != dfa->init_state_begbuf) + re_compile_fastmap_iter (bufp, dfa->init_state_begbuf, fastmap); + bufp->fastmap_accurate = 1; + return 0; +} +#ifdef _LIBC +weak_alias (__re_compile_fastmap, re_compile_fastmap) +#endif + +static inline void +__attribute ((always_inline)) +re_set_fastmap (char *fastmap, int icase, int ch) +{ + fastmap[ch] = 1; + if (icase) + fastmap[tolower (ch)] = 1; +} + +/* Helper function for re_compile_fastmap. + Compile fastmap for the initial_state INIT_STATE. */ + +static void +re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state, + char *fastmap) +{ + re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; + int node_cnt; + int icase = (dfa->mb_cur_max == 1 && (bufp->syntax & RE_ICASE)); + for (node_cnt = 0; node_cnt < init_state->nodes.nelem; ++node_cnt) + { + int node = init_state->nodes.elems[node_cnt]; + re_token_type_t type = dfa->nodes[node].type; + + if (type == CHARACTER) + { + re_set_fastmap (fastmap, icase, dfa->nodes[node].opr.c); +#ifdef RE_ENABLE_I18N + if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1) + { + unsigned char *buf = alloca (dfa->mb_cur_max), *p; + wchar_t wc; + mbstate_t state; + + p = buf; + *p++ = dfa->nodes[node].opr.c; + while (++node < dfa->nodes_len + && dfa->nodes[node].type == CHARACTER + && dfa->nodes[node].mb_partial) + *p++ = dfa->nodes[node].opr.c; + memset (&state, '\0', sizeof (state)); + if (mbrtowc (&wc, (const char *) buf, p - buf, + &state) == p - buf + && (__wcrtomb ((char *) buf, towlower (wc), &state) + != (size_t) -1)) + re_set_fastmap (fastmap, 0, buf[0]); + } +#endif + } + else if (type == SIMPLE_BRACKET) + { + int i, ch; + for (i = 0, ch = 0; i < BITSET_WORDS; ++i) + { + int j; + bitset_word_t w = dfa->nodes[node].opr.sbcset[i]; + for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) + if (w & ((bitset_word_t) 1 << j)) + re_set_fastmap (fastmap, icase, ch); + } + } +#ifdef RE_ENABLE_I18N + else if (type == COMPLEX_BRACKET) + { + int i; + re_charset_t *cset = dfa->nodes[node].opr.mbcset; + if (cset->non_match || cset->ncoll_syms || cset->nequiv_classes + || cset->nranges || cset->nchar_classes) + { +# ifdef _LIBC + if (_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES) != 0) + { + /* In this case we want to catch the bytes which are + the first byte of any collation elements. + e.g. In da_DK, we want to catch 'a' since "aa" + is a valid collation element, and don't catch + 'b' since 'b' is the only collation element + which starts from 'b'. */ + const int32_t *table = (const int32_t *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); + for (i = 0; i < SBC_MAX; ++i) + if (table[i] < 0) + re_set_fastmap (fastmap, icase, i); + } +# else + if (dfa->mb_cur_max > 1) + for (i = 0; i < SBC_MAX; ++i) + if (__btowc (i) == WEOF) + re_set_fastmap (fastmap, icase, i); +# endif /* not _LIBC */ + } + for (i = 0; i < cset->nmbchars; ++i) + { + char buf[256]; + mbstate_t state; + memset (&state, '\0', sizeof (state)); + if (__wcrtomb (buf, cset->mbchars[i], &state) != (size_t) -1) + re_set_fastmap (fastmap, icase, *(unsigned char *) buf); + if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1) + { + if (__wcrtomb (buf, towlower (cset->mbchars[i]), &state) + != (size_t) -1) + re_set_fastmap (fastmap, 0, *(unsigned char *) buf); + } + } + } +#endif /* RE_ENABLE_I18N */ + else if (type == OP_PERIOD +#ifdef RE_ENABLE_I18N + || type == OP_UTF8_PERIOD +#endif /* RE_ENABLE_I18N */ + || type == END_OF_RE) + { + memset (fastmap, '\1', sizeof (char) * SBC_MAX); + if (type == END_OF_RE) + bufp->can_be_null = 1; + return; + } + } +} + +/* Entry point for POSIX code. */ +/* regcomp takes a regular expression as a string and compiles it. + + PREG is a regex_t *. We do not expect any fields to be initialized, + since POSIX says we shouldn't. Thus, we set + + `buffer' to the compiled pattern; + `used' to the length of the compiled pattern; + `syntax' to RE_SYNTAX_POSIX_EXTENDED if the + REG_EXTENDED bit in CFLAGS is set; otherwise, to + RE_SYNTAX_POSIX_BASIC; + `newline_anchor' to REG_NEWLINE being set in CFLAGS; + `fastmap' to an allocated space for the fastmap; + `fastmap_accurate' to zero; + `re_nsub' to the number of subexpressions in PATTERN. + + PATTERN is the address of the pattern string. + + CFLAGS is a series of bits which affect compilation. + + If REG_EXTENDED is set, we use POSIX extended syntax; otherwise, we + use POSIX basic syntax. + + If REG_NEWLINE is set, then . and [^...] don't match newline. + Also, regexec will try a match beginning after every newline. + + If REG_ICASE is set, then we considers upper- and lowercase + versions of letters to be equivalent when matching. + + If REG_NOSUB is set, then when PREG is passed to regexec, that + routine will report only success or failure, and nothing about the + registers. + + It returns 0 if it succeeds, nonzero if it doesn't. (See regex.h for + the return codes and their meanings.) */ + +int +regcomp (preg, pattern, cflags) + regex_t *__restrict preg; + const char *__restrict pattern; + int cflags; +{ + reg_errcode_t ret; + reg_syntax_t syntax = ((cflags & REG_EXTENDED) ? RE_SYNTAX_POSIX_EXTENDED + : RE_SYNTAX_POSIX_BASIC); + + preg->buffer = NULL; + preg->allocated = 0; + preg->used = 0; + + /* Try to allocate space for the fastmap. */ + preg->fastmap = re_malloc (char, SBC_MAX); + if (BE (preg->fastmap == NULL, 0)) + return REG_ESPACE; + + syntax |= (cflags & REG_ICASE) ? RE_ICASE : 0; + + /* If REG_NEWLINE is set, newlines are treated differently. */ + if (cflags & REG_NEWLINE) + { /* REG_NEWLINE implies neither . nor [^...] match newline. */ + syntax &= ~RE_DOT_NEWLINE; + syntax |= RE_HAT_LISTS_NOT_NEWLINE; + /* It also changes the matching behavior. */ + preg->newline_anchor = 1; + } + else + preg->newline_anchor = 0; + preg->no_sub = !!(cflags & REG_NOSUB); + preg->translate = NULL; + + ret = re_compile_internal (preg, pattern, strlen (pattern), syntax); + + /* POSIX doesn't distinguish between an unmatched open-group and an + unmatched close-group: both are REG_EPAREN. */ + if (ret == REG_ERPAREN) + ret = REG_EPAREN; + + /* We have already checked preg->fastmap != NULL. */ + if (BE (ret == REG_NOERROR, 1)) + /* Compute the fastmap now, since regexec cannot modify the pattern + buffer. This function never fails in this implementation. */ + (void) re_compile_fastmap (preg); + else + { + /* Some error occurred while compiling the expression. */ + re_free (preg->fastmap); + preg->fastmap = NULL; + } + + return (int) ret; +} +#ifdef _LIBC +weak_alias (__regcomp, regcomp) +#endif + +/* Returns a message corresponding to an error code, ERRCODE, returned + from either regcomp or regexec. We don't use PREG here. */ + +size_t +regerror (errcode, preg, errbuf, errbuf_size) + int errcode; + const regex_t *__restrict preg; + char *__restrict errbuf; + size_t errbuf_size; +{ + const char *msg; + size_t msg_size; + + if (BE (errcode < 0 + || errcode >= (int) (sizeof (__re_error_msgid_idx) + / sizeof (__re_error_msgid_idx[0])), 0)) + /* Only error codes returned by the rest of the code should be passed + to this routine. If we are given anything else, or if other regex + code generates an invalid error code, then the program has a bug. + Dump core so we can fix it. */ + abort (); + + msg = gettext (__re_error_msgid + __re_error_msgid_idx[errcode]); + + msg_size = strlen (msg) + 1; /* Includes the null. */ + + if (BE (errbuf_size != 0, 1)) + { + if (BE (msg_size > errbuf_size, 0)) + { +#if defined HAVE_MEMPCPY || defined _LIBC + *((char *) __mempcpy (errbuf, msg, errbuf_size - 1)) = '\0'; +#else + memcpy (errbuf, msg, errbuf_size - 1); + errbuf[errbuf_size - 1] = 0; +#endif + } + else + memcpy (errbuf, msg, msg_size); + } + + return msg_size; +} +#ifdef _LIBC +weak_alias (__regerror, regerror) +#endif + + +#ifdef RE_ENABLE_I18N +/* This static array is used for the map to single-byte characters when + UTF-8 is used. Otherwise we would allocate memory just to initialize + it the same all the time. UTF-8 is the preferred encoding so this is + a worthwhile optimization. */ +static const bitset_t utf8_sb_map = +{ + /* Set the first 128 bits. */ + [0 ... 0x80 / BITSET_WORD_BITS - 1] = BITSET_WORD_MAX +}; +#endif + + +static void +free_dfa_content (re_dfa_t *dfa) +{ + int i, j; + + if (dfa->nodes) + for (i = 0; i < dfa->nodes_len; ++i) + free_token (dfa->nodes + i); + re_free (dfa->nexts); + for (i = 0; i < dfa->nodes_len; ++i) + { + if (dfa->eclosures != NULL) + re_node_set_free (dfa->eclosures + i); + if (dfa->inveclosures != NULL) + re_node_set_free (dfa->inveclosures + i); + if (dfa->edests != NULL) + re_node_set_free (dfa->edests + i); + } + re_free (dfa->edests); + re_free (dfa->eclosures); + re_free (dfa->inveclosures); + re_free (dfa->nodes); + + if (dfa->state_table) + for (i = 0; i <= dfa->state_hash_mask; ++i) + { + struct re_state_table_entry *entry = dfa->state_table + i; + for (j = 0; j < entry->num; ++j) + { + re_dfastate_t *state = entry->array[j]; + free_state (state); + } + re_free (entry->array); + } + re_free (dfa->state_table); +#ifdef RE_ENABLE_I18N + if (dfa->sb_char != utf8_sb_map) + re_free (dfa->sb_char); +#endif + re_free (dfa->subexp_map); +#ifdef DEBUG + re_free (dfa->re_str); +#endif + + re_free (dfa); +} + + +/* Free dynamically allocated space used by PREG. */ + +void +regfree (preg) + regex_t *preg; +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + if (BE (dfa != NULL, 1)) + free_dfa_content (dfa); + preg->buffer = NULL; + preg->allocated = 0; + + re_free (preg->fastmap); + preg->fastmap = NULL; + + re_free (preg->translate); + preg->translate = NULL; +} +#ifdef _LIBC +weak_alias (__regfree, regfree) +#endif + +/* Entry points compatible with 4.2 BSD regex library. We don't define + them unless specifically requested. */ + +#if defined _REGEX_RE_COMP || defined _LIBC + +/* BSD has one and only one pattern buffer. */ +static struct re_pattern_buffer re_comp_buf; + +char * +# ifdef _LIBC +/* Make these definitions weak in libc, so POSIX programs can redefine + these names if they don't use our functions, and still use + regcomp/regexec above without link errors. */ +weak_function +# endif +re_comp (s) + const char *s; +{ + reg_errcode_t ret; + char *fastmap; + + if (!s) + { + if (!re_comp_buf.buffer) + return gettext ("No previous regular expression"); + return 0; + } + + if (re_comp_buf.buffer) + { + fastmap = re_comp_buf.fastmap; + re_comp_buf.fastmap = NULL; + __regfree (&re_comp_buf); + memset (&re_comp_buf, '\0', sizeof (re_comp_buf)); + re_comp_buf.fastmap = fastmap; + } + + if (re_comp_buf.fastmap == NULL) + { + re_comp_buf.fastmap = (char *) malloc (SBC_MAX); + if (re_comp_buf.fastmap == NULL) + return (char *) gettext (__re_error_msgid + + __re_error_msgid_idx[(int) REG_ESPACE]); + } + + /* Since `re_exec' always passes NULL for the `regs' argument, we + don't need to initialize the pattern buffer fields which affect it. */ + + /* Match anchors at newlines. */ + re_comp_buf.newline_anchor = 1; + + ret = re_compile_internal (&re_comp_buf, s, strlen (s), re_syntax_options); + + if (!ret) + return NULL; + + /* Yes, we're discarding `const' here if !HAVE_LIBINTL. */ + return (char *) gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]); +} + +#ifdef _LIBC +libc_freeres_fn (free_mem) +{ + __regfree (&re_comp_buf); +} +#endif + +#endif /* _REGEX_RE_COMP */ + +/* Internal entry point. + Compile the regular expression PATTERN, whose length is LENGTH. + SYNTAX indicate regular expression's syntax. */ + +static reg_errcode_t +re_compile_internal (regex_t *preg, const char * pattern, size_t length, + reg_syntax_t syntax) +{ + reg_errcode_t err = REG_NOERROR; + re_dfa_t *dfa; + re_string_t regexp; + + /* Initialize the pattern buffer. */ + preg->fastmap_accurate = 0; + preg->syntax = syntax; + preg->not_bol = preg->not_eol = 0; + preg->used = 0; + preg->re_nsub = 0; + preg->can_be_null = 0; + preg->regs_allocated = REGS_UNALLOCATED; + + /* Initialize the dfa. */ + dfa = (re_dfa_t *) preg->buffer; + if (BE (preg->allocated < sizeof (re_dfa_t), 0)) + { + /* If zero allocated, but buffer is non-null, try to realloc + enough space. This loses if buffer's address is bogus, but + that is the user's responsibility. If ->buffer is NULL this + is a simple allocation. */ + dfa = re_realloc (preg->buffer, re_dfa_t, 1); + if (dfa == NULL) + return REG_ESPACE; + preg->allocated = sizeof (re_dfa_t); + preg->buffer = (unsigned char *) dfa; + } + preg->used = sizeof (re_dfa_t); + + err = init_dfa (dfa, length); + if (BE (err != REG_NOERROR, 0)) + { + free_dfa_content (dfa); + preg->buffer = NULL; + preg->allocated = 0; + return err; + } +#ifdef DEBUG + /* Note: length+1 will not overflow since it is checked in init_dfa. */ + dfa->re_str = re_malloc (char, length + 1); + strncpy (dfa->re_str, pattern, length + 1); +#endif + + __libc_lock_init (dfa->lock); + + err = re_string_construct (®exp, pattern, length, preg->translate, + syntax & RE_ICASE, dfa); + if (BE (err != REG_NOERROR, 0)) + { + re_compile_internal_free_return: + free_workarea_compile (preg); + re_string_destruct (®exp); + free_dfa_content (dfa); + preg->buffer = NULL; + preg->allocated = 0; + return err; + } + + /* Parse the regular expression, and build a structure tree. */ + preg->re_nsub = 0; + dfa->str_tree = parse (®exp, preg, syntax, &err); + if (BE (dfa->str_tree == NULL, 0)) + goto re_compile_internal_free_return; + + /* Analyze the tree and create the nfa. */ + err = analyze (preg); + if (BE (err != REG_NOERROR, 0)) + goto re_compile_internal_free_return; + +#ifdef RE_ENABLE_I18N + /* If possible, do searching in single byte encoding to speed things up. */ + if (dfa->is_utf8 && !(syntax & RE_ICASE) && preg->translate == NULL) + optimize_utf8 (dfa); +#endif + + /* Then create the initial state of the dfa. */ + err = create_initial_state (dfa); + + /* Release work areas. */ + free_workarea_compile (preg); + re_string_destruct (®exp); + + if (BE (err != REG_NOERROR, 0)) + { + free_dfa_content (dfa); + preg->buffer = NULL; + preg->allocated = 0; + } + + return err; +} + +/* Initialize DFA. We use the length of the regular expression PAT_LEN + as the initial length of some arrays. */ + +static reg_errcode_t +init_dfa (re_dfa_t *dfa, size_t pat_len) +{ + unsigned int table_size; +#ifndef _LIBC + char *codeset_name; +#endif + + memset (dfa, '\0', sizeof (re_dfa_t)); + + /* Force allocation of str_tree_storage the first time. */ + dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE; + + /* Avoid overflows. */ + if (pat_len == SIZE_MAX) + return REG_ESPACE; + + dfa->nodes_alloc = pat_len + 1; + dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc); + + /* table_size = 2 ^ ceil(log pat_len) */ + for (table_size = 1; ; table_size <<= 1) + if (table_size > pat_len) + break; + + dfa->state_table = calloc (sizeof (struct re_state_table_entry), table_size); + dfa->state_hash_mask = table_size - 1; + + dfa->mb_cur_max = MB_CUR_MAX; +#ifdef _LIBC + if (dfa->mb_cur_max == 6 + && strcmp (_NL_CURRENT (LC_CTYPE, _NL_CTYPE_CODESET_NAME), "UTF-8") == 0) + dfa->is_utf8 = 1; + dfa->map_notascii = (_NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_MAP_TO_NONASCII) + != 0); +#else +# ifdef HAVE_LANGINFO_CODESET + codeset_name = nl_langinfo (CODESET); +# else + codeset_name = getenv ("LC_ALL"); + if (codeset_name == NULL || codeset_name[0] == '\0') + codeset_name = getenv ("LC_CTYPE"); + if (codeset_name == NULL || codeset_name[0] == '\0') + codeset_name = getenv ("LANG"); + if (codeset_name == NULL) + codeset_name = ""; + else if (strchr (codeset_name, '.') != NULL) + codeset_name = strchr (codeset_name, '.') + 1; +# endif + + if (strcasecmp (codeset_name, "UTF-8") == 0 + || strcasecmp (codeset_name, "UTF8") == 0) + dfa->is_utf8 = 1; + + /* We check exhaustively in the loop below if this charset is a + superset of ASCII. */ + dfa->map_notascii = 0; +#endif + +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + { + if (dfa->is_utf8) + dfa->sb_char = (re_bitset_ptr_t) utf8_sb_map; + else + { + int i, j, ch; + + dfa->sb_char = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); + if (BE (dfa->sb_char == NULL, 0)) + return REG_ESPACE; + + /* Set the bits corresponding to single byte chars. */ + for (i = 0, ch = 0; i < BITSET_WORDS; ++i) + for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) + { + wint_t wch = __btowc (ch); + if (wch != WEOF) + dfa->sb_char[i] |= (bitset_word_t) 1 << j; +# ifndef _LIBC + if (isascii (ch) && wch != ch) + dfa->map_notascii = 1; +# endif + } + } + } +#endif + + if (BE (dfa->nodes == NULL || dfa->state_table == NULL, 0)) + return REG_ESPACE; + return REG_NOERROR; +} + +/* Initialize WORD_CHAR table, which indicate which character is + "word". In this case "word" means that it is the word construction + character used by some operators like "\<", "\>", etc. */ + +static void +internal_function +init_word_char (re_dfa_t *dfa) +{ + int i, j, ch; + dfa->word_ops_used = 1; + for (i = 0, ch = 0; i < BITSET_WORDS; ++i) + for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) + if (isalnum (ch) || ch == '_') + dfa->word_char[i] |= (bitset_word_t) 1 << j; +} + +/* Free the work area which are only used while compiling. */ + +static void +free_workarea_compile (regex_t *preg) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_storage_t *storage, *next; + for (storage = dfa->str_tree_storage; storage; storage = next) + { + next = storage->next; + re_free (storage); + } + dfa->str_tree_storage = NULL; + dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE; + dfa->str_tree = NULL; + re_free (dfa->org_indices); + dfa->org_indices = NULL; +} + +/* Create initial states for all contexts. */ + +static reg_errcode_t +create_initial_state (re_dfa_t *dfa) +{ + int first, i; + reg_errcode_t err; + re_node_set init_nodes; + + /* Initial states have the epsilon closure of the node which is + the first node of the regular expression. */ + first = dfa->str_tree->first->node_idx; + dfa->init_node = first; + err = re_node_set_init_copy (&init_nodes, dfa->eclosures + first); + if (BE (err != REG_NOERROR, 0)) + return err; + + /* The back-references which are in initial states can epsilon transit, + since in this case all of the subexpressions can be null. + Then we add epsilon closures of the nodes which are the next nodes of + the back-references. */ + if (dfa->nbackref > 0) + for (i = 0; i < init_nodes.nelem; ++i) + { + int node_idx = init_nodes.elems[i]; + re_token_type_t type = dfa->nodes[node_idx].type; + + int clexp_idx; + if (type != OP_BACK_REF) + continue; + for (clexp_idx = 0; clexp_idx < init_nodes.nelem; ++clexp_idx) + { + re_token_t *clexp_node; + clexp_node = dfa->nodes + init_nodes.elems[clexp_idx]; + if (clexp_node->type == OP_CLOSE_SUBEXP + && clexp_node->opr.idx == dfa->nodes[node_idx].opr.idx) + break; + } + if (clexp_idx == init_nodes.nelem) + continue; + + if (type == OP_BACK_REF) + { + int dest_idx = dfa->edests[node_idx].elems[0]; + if (!re_node_set_contains (&init_nodes, dest_idx)) + { + re_node_set_merge (&init_nodes, dfa->eclosures + dest_idx); + i = 0; + } + } + } + + /* It must be the first time to invoke acquire_state. */ + dfa->init_state = re_acquire_state_context (&err, dfa, &init_nodes, 0); + /* We don't check ERR here, since the initial state must not be NULL. */ + if (BE (dfa->init_state == NULL, 0)) + return err; + if (dfa->init_state->has_constraint) + { + dfa->init_state_word = re_acquire_state_context (&err, dfa, &init_nodes, + CONTEXT_WORD); + dfa->init_state_nl = re_acquire_state_context (&err, dfa, &init_nodes, + CONTEXT_NEWLINE); + dfa->init_state_begbuf = re_acquire_state_context (&err, dfa, + &init_nodes, + CONTEXT_NEWLINE + | CONTEXT_BEGBUF); + if (BE (dfa->init_state_word == NULL || dfa->init_state_nl == NULL + || dfa->init_state_begbuf == NULL, 0)) + return err; + } + else + dfa->init_state_word = dfa->init_state_nl + = dfa->init_state_begbuf = dfa->init_state; + + re_node_set_free (&init_nodes); + return REG_NOERROR; +} + +#ifdef RE_ENABLE_I18N +/* If it is possible to do searching in single byte encoding instead of UTF-8 + to speed things up, set dfa->mb_cur_max to 1, clear is_utf8 and change + DFA nodes where needed. */ + +static void +optimize_utf8 (re_dfa_t *dfa) +{ + int node, i, mb_chars = 0, has_period = 0; + + for (node = 0; node < dfa->nodes_len; ++node) + switch (dfa->nodes[node].type) + { + case CHARACTER: + if (dfa->nodes[node].opr.c >= 0x80) + mb_chars = 1; + break; + case ANCHOR: + switch (dfa->nodes[node].opr.idx) + { + case LINE_FIRST: + case LINE_LAST: + case BUF_FIRST: + case BUF_LAST: + break; + default: + /* Word anchors etc. cannot be handled. */ + return; + } + break; + case OP_PERIOD: + has_period = 1; + break; + case OP_BACK_REF: + case OP_ALT: + case END_OF_RE: + case OP_DUP_ASTERISK: + case OP_OPEN_SUBEXP: + case OP_CLOSE_SUBEXP: + break; + case COMPLEX_BRACKET: + return; + case SIMPLE_BRACKET: + /* Just double check. The non-ASCII range starts at 0x80. */ + assert (0x80 % BITSET_WORD_BITS == 0); + for (i = 0x80 / BITSET_WORD_BITS; i < BITSET_WORDS; ++i) + if (dfa->nodes[node].opr.sbcset[i]) + return; + break; + default: + abort (); + } + + if (mb_chars || has_period) + for (node = 0; node < dfa->nodes_len; ++node) + { + if (dfa->nodes[node].type == CHARACTER + && dfa->nodes[node].opr.c >= 0x80) + dfa->nodes[node].mb_partial = 0; + else if (dfa->nodes[node].type == OP_PERIOD) + dfa->nodes[node].type = OP_UTF8_PERIOD; + } + + /* The search can be in single byte locale. */ + dfa->mb_cur_max = 1; + dfa->is_utf8 = 0; + dfa->has_mb_node = dfa->nbackref > 0 || has_period; +} +#endif + +/* Analyze the structure tree, and calculate "first", "next", "edest", + "eclosure", and "inveclosure". */ + +static reg_errcode_t +analyze (regex_t *preg) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + reg_errcode_t ret; + + /* Allocate arrays. */ + dfa->nexts = re_malloc (int, dfa->nodes_alloc); + dfa->org_indices = re_malloc (int, dfa->nodes_alloc); + dfa->edests = re_malloc (re_node_set, dfa->nodes_alloc); + dfa->eclosures = re_malloc (re_node_set, dfa->nodes_alloc); + if (BE (dfa->nexts == NULL || dfa->org_indices == NULL || dfa->edests == NULL + || dfa->eclosures == NULL, 0)) + return REG_ESPACE; + + dfa->subexp_map = re_malloc (int, preg->re_nsub); + if (dfa->subexp_map != NULL) + { + int i; + for (i = 0; i < preg->re_nsub; i++) + dfa->subexp_map[i] = i; + preorder (dfa->str_tree, optimize_subexps, dfa); + for (i = 0; i < preg->re_nsub; i++) + if (dfa->subexp_map[i] != i) + break; + if (i == preg->re_nsub) + { + free (dfa->subexp_map); + dfa->subexp_map = NULL; + } + } + + ret = postorder (dfa->str_tree, lower_subexps, preg); + if (BE (ret != REG_NOERROR, 0)) + return ret; + ret = postorder (dfa->str_tree, calc_first, dfa); + if (BE (ret != REG_NOERROR, 0)) + return ret; + preorder (dfa->str_tree, calc_next, dfa); + ret = preorder (dfa->str_tree, link_nfa_nodes, dfa); + if (BE (ret != REG_NOERROR, 0)) + return ret; + ret = calc_eclosure (dfa); + if (BE (ret != REG_NOERROR, 0)) + return ret; + + /* We only need this during the prune_impossible_nodes pass in regexec.c; + skip it if p_i_n will not run, as calc_inveclosure can be quadratic. */ + if ((!preg->no_sub && preg->re_nsub > 0 && dfa->has_plural_match) + || dfa->nbackref) + { + dfa->inveclosures = re_malloc (re_node_set, dfa->nodes_len); + if (BE (dfa->inveclosures == NULL, 0)) + return REG_ESPACE; + ret = calc_inveclosure (dfa); + } + + return ret; +} + +/* Our parse trees are very unbalanced, so we cannot use a stack to + implement parse tree visits. Instead, we use parent pointers and + some hairy code in these two functions. */ +static reg_errcode_t +postorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)), + void *extra) +{ + bin_tree_t *node, *prev; + + for (node = root; ; ) + { + /* Descend down the tree, preferably to the left (or to the right + if that's the only child). */ + while (node->left || node->right) + if (node->left) + node = node->left; + else + node = node->right; + + do + { + reg_errcode_t err = fn (extra, node); + if (BE (err != REG_NOERROR, 0)) + return err; + if (node->parent == NULL) + return REG_NOERROR; + prev = node; + node = node->parent; + } + /* Go up while we have a node that is reached from the right. */ + while (node->right == prev || node->right == NULL); + node = node->right; + } +} + +static reg_errcode_t +preorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)), + void *extra) +{ + bin_tree_t *node; + + for (node = root; ; ) + { + reg_errcode_t err = fn (extra, node); + if (BE (err != REG_NOERROR, 0)) + return err; + + /* Go to the left node, or up and to the right. */ + if (node->left) + node = node->left; + else + { + bin_tree_t *prev = NULL; + while (node->right == prev || node->right == NULL) + { + prev = node; + node = node->parent; + if (!node) + return REG_NOERROR; + } + node = node->right; + } + } +} + +/* Optimization pass: if a SUBEXP is entirely contained, strip it and tell + re_search_internal to map the inner one's opr.idx to this one's. Adjust + backreferences as well. Requires a preorder visit. */ +static reg_errcode_t +optimize_subexps (void *extra, bin_tree_t *node) +{ + re_dfa_t *dfa = (re_dfa_t *) extra; + + if (node->token.type == OP_BACK_REF && dfa->subexp_map) + { + int idx = node->token.opr.idx; + node->token.opr.idx = dfa->subexp_map[idx]; + dfa->used_bkref_map |= 1 << node->token.opr.idx; + } + + else if (node->token.type == SUBEXP + && node->left && node->left->token.type == SUBEXP) + { + int other_idx = node->left->token.opr.idx; + + node->left = node->left->left; + if (node->left) + node->left->parent = node; + + dfa->subexp_map[other_idx] = dfa->subexp_map[node->token.opr.idx]; + if (other_idx < BITSET_WORD_BITS) + dfa->used_bkref_map &= ~((bitset_word_t) 1 << other_idx); + } + + return REG_NOERROR; +} + +/* Lowering pass: Turn each SUBEXP node into the appropriate concatenation + of OP_OPEN_SUBEXP, the body of the SUBEXP (if any) and OP_CLOSE_SUBEXP. */ +static reg_errcode_t +lower_subexps (void *extra, bin_tree_t *node) +{ + regex_t *preg = (regex_t *) extra; + reg_errcode_t err = REG_NOERROR; + + if (node->left && node->left->token.type == SUBEXP) + { + node->left = lower_subexp (&err, preg, node->left); + if (node->left) + node->left->parent = node; + } + if (node->right && node->right->token.type == SUBEXP) + { + node->right = lower_subexp (&err, preg, node->right); + if (node->right) + node->right->parent = node; + } + + return err; +} + +static bin_tree_t * +lower_subexp (reg_errcode_t *err, regex_t *preg, bin_tree_t *node) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_t *body = node->left; + bin_tree_t *op, *cls, *tree1, *tree; + + if (preg->no_sub + /* We do not optimize empty subexpressions, because otherwise we may + have bad CONCAT nodes with NULL children. This is obviously not + very common, so we do not lose much. An example that triggers + this case is the sed "script" /\(\)/x. */ + && node->left != NULL + && (node->token.opr.idx >= BITSET_WORD_BITS + || !(dfa->used_bkref_map + & ((bitset_word_t) 1 << node->token.opr.idx)))) + return node->left; + + /* Convert the SUBEXP node to the concatenation of an + OP_OPEN_SUBEXP, the contents, and an OP_CLOSE_SUBEXP. */ + op = create_tree (dfa, NULL, NULL, OP_OPEN_SUBEXP); + cls = create_tree (dfa, NULL, NULL, OP_CLOSE_SUBEXP); + tree1 = body ? create_tree (dfa, body, cls, CONCAT) : cls; + tree = create_tree (dfa, op, tree1, CONCAT); + if (BE (tree == NULL || tree1 == NULL || op == NULL || cls == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + + op->token.opr.idx = cls->token.opr.idx = node->token.opr.idx; + op->token.opt_subexp = cls->token.opt_subexp = node->token.opt_subexp; + return tree; +} + +/* Pass 1 in building the NFA: compute FIRST and create unlinked automaton + nodes. Requires a postorder visit. */ +static reg_errcode_t +calc_first (void *extra, bin_tree_t *node) +{ + re_dfa_t *dfa = (re_dfa_t *) extra; + if (node->token.type == CONCAT) + { + node->first = node->left->first; + node->node_idx = node->left->node_idx; + } + else + { + node->first = node; + node->node_idx = re_dfa_add_node (dfa, node->token); + if (BE (node->node_idx == -1, 0)) + return REG_ESPACE; + } + return REG_NOERROR; +} + +/* Pass 2: compute NEXT on the tree. Preorder visit. */ +static reg_errcode_t +calc_next (void *extra, bin_tree_t *node) +{ + switch (node->token.type) + { + case OP_DUP_ASTERISK: + node->left->next = node; + break; + case CONCAT: + node->left->next = node->right->first; + node->right->next = node->next; + break; + default: + if (node->left) + node->left->next = node->next; + if (node->right) + node->right->next = node->next; + break; + } + return REG_NOERROR; +} + +/* Pass 3: link all DFA nodes to their NEXT node (any order will do). */ +static reg_errcode_t +link_nfa_nodes (void *extra, bin_tree_t *node) +{ + re_dfa_t *dfa = (re_dfa_t *) extra; + int idx = node->node_idx; + reg_errcode_t err = REG_NOERROR; + + switch (node->token.type) + { + case CONCAT: + break; + + case END_OF_RE: + assert (node->next == NULL); + break; + + case OP_DUP_ASTERISK: + case OP_ALT: + { + int left, right; + dfa->has_plural_match = 1; + if (node->left != NULL) + left = node->left->first->node_idx; + else + left = node->next->node_idx; + if (node->right != NULL) + right = node->right->first->node_idx; + else + right = node->next->node_idx; + assert (left > -1); + assert (right > -1); + err = re_node_set_init_2 (dfa->edests + idx, left, right); + } + break; + + case ANCHOR: + case OP_OPEN_SUBEXP: + case OP_CLOSE_SUBEXP: + err = re_node_set_init_1 (dfa->edests + idx, node->next->node_idx); + break; + + case OP_BACK_REF: + dfa->nexts[idx] = node->next->node_idx; + if (node->token.type == OP_BACK_REF) + re_node_set_init_1 (dfa->edests + idx, dfa->nexts[idx]); + break; + + default: + assert (!IS_EPSILON_NODE (node->token.type)); + dfa->nexts[idx] = node->next->node_idx; + break; + } + + return err; +} + +/* Duplicate the epsilon closure of the node ROOT_NODE. + Note that duplicated nodes have constraint INIT_CONSTRAINT in addition + to their own constraint. */ + +static reg_errcode_t +internal_function +duplicate_node_closure (re_dfa_t *dfa, int top_org_node, int top_clone_node, + int root_node, unsigned int init_constraint) +{ + int org_node, clone_node, ret; + unsigned int constraint = init_constraint; + for (org_node = top_org_node, clone_node = top_clone_node;;) + { + int org_dest, clone_dest; + if (dfa->nodes[org_node].type == OP_BACK_REF) + { + /* If the back reference epsilon-transit, its destination must + also have the constraint. Then duplicate the epsilon closure + of the destination of the back reference, and store it in + edests of the back reference. */ + org_dest = dfa->nexts[org_node]; + re_node_set_empty (dfa->edests + clone_node); + clone_dest = duplicate_node (dfa, org_dest, constraint); + if (BE (clone_dest == -1, 0)) + return REG_ESPACE; + dfa->nexts[clone_node] = dfa->nexts[org_node]; + ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + } + else if (dfa->edests[org_node].nelem == 0) + { + /* In case of the node can't epsilon-transit, don't duplicate the + destination and store the original destination as the + destination of the node. */ + dfa->nexts[clone_node] = dfa->nexts[org_node]; + break; + } + else if (dfa->edests[org_node].nelem == 1) + { + /* In case of the node can epsilon-transit, and it has only one + destination. */ + org_dest = dfa->edests[org_node].elems[0]; + re_node_set_empty (dfa->edests + clone_node); + if (dfa->nodes[org_node].type == ANCHOR) + { + /* In case of the node has another constraint, append it. */ + if (org_node == root_node && clone_node != org_node) + { + /* ...but if the node is root_node itself, it means the + epsilon closure have a loop, then tie it to the + destination of the root_node. */ + ret = re_node_set_insert (dfa->edests + clone_node, + org_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + break; + } + constraint |= dfa->nodes[org_node].opr.ctx_type; + } + clone_dest = duplicate_node (dfa, org_dest, constraint); + if (BE (clone_dest == -1, 0)) + return REG_ESPACE; + ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + } + else /* dfa->edests[org_node].nelem == 2 */ + { + /* In case of the node can epsilon-transit, and it has two + destinations. In the bin_tree_t and DFA, that's '|' and '*'. */ + org_dest = dfa->edests[org_node].elems[0]; + re_node_set_empty (dfa->edests + clone_node); + /* Search for a duplicated node which satisfies the constraint. */ + clone_dest = search_duplicated_node (dfa, org_dest, constraint); + if (clone_dest == -1) + { + /* There are no such a duplicated node, create a new one. */ + reg_errcode_t err; + clone_dest = duplicate_node (dfa, org_dest, constraint); + if (BE (clone_dest == -1, 0)) + return REG_ESPACE; + ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + err = duplicate_node_closure (dfa, org_dest, clone_dest, + root_node, constraint); + if (BE (err != REG_NOERROR, 0)) + return err; + } + else + { + /* There are a duplicated node which satisfy the constraint, + use it to avoid infinite loop. */ + ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + } + + org_dest = dfa->edests[org_node].elems[1]; + clone_dest = duplicate_node (dfa, org_dest, constraint); + if (BE (clone_dest == -1, 0)) + return REG_ESPACE; + ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); + if (BE (ret < 0, 0)) + return REG_ESPACE; + } + org_node = org_dest; + clone_node = clone_dest; + } + return REG_NOERROR; +} + +/* Search for a node which is duplicated from the node ORG_NODE, and + satisfies the constraint CONSTRAINT. */ + +static int +search_duplicated_node (const re_dfa_t *dfa, int org_node, + unsigned int constraint) +{ + int idx; + for (idx = dfa->nodes_len - 1; dfa->nodes[idx].duplicated && idx > 0; --idx) + { + if (org_node == dfa->org_indices[idx] + && constraint == dfa->nodes[idx].constraint) + return idx; /* Found. */ + } + return -1; /* Not found. */ +} + +/* Duplicate the node whose index is ORG_IDX and set the constraint CONSTRAINT. + Return the index of the new node, or -1 if insufficient storage is + available. */ + +static int +duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint) +{ + int dup_idx = re_dfa_add_node (dfa, dfa->nodes[org_idx]); + if (BE (dup_idx != -1, 1)) + { + dfa->nodes[dup_idx].constraint = constraint; + if (dfa->nodes[org_idx].type == ANCHOR) + dfa->nodes[dup_idx].constraint |= dfa->nodes[org_idx].opr.ctx_type; + dfa->nodes[dup_idx].duplicated = 1; + + /* Store the index of the original node. */ + dfa->org_indices[dup_idx] = org_idx; + } + return dup_idx; +} + +static reg_errcode_t +calc_inveclosure (re_dfa_t *dfa) +{ + int src, idx, ret; + for (idx = 0; idx < dfa->nodes_len; ++idx) + re_node_set_init_empty (dfa->inveclosures + idx); + + for (src = 0; src < dfa->nodes_len; ++src) + { + int *elems = dfa->eclosures[src].elems; + for (idx = 0; idx < dfa->eclosures[src].nelem; ++idx) + { + ret = re_node_set_insert_last (dfa->inveclosures + elems[idx], src); + if (BE (ret == -1, 0)) + return REG_ESPACE; + } + } + + return REG_NOERROR; +} + +/* Calculate "eclosure" for all the node in DFA. */ + +static reg_errcode_t +calc_eclosure (re_dfa_t *dfa) +{ + int node_idx, incomplete; +#ifdef DEBUG + assert (dfa->nodes_len > 0); +#endif + incomplete = 0; + /* For each nodes, calculate epsilon closure. */ + for (node_idx = 0; ; ++node_idx) + { + reg_errcode_t err; + re_node_set eclosure_elem; + if (node_idx == dfa->nodes_len) + { + if (!incomplete) + break; + incomplete = 0; + node_idx = 0; + } + +#ifdef DEBUG + assert (dfa->eclosures[node_idx].nelem != -1); +#endif + + /* If we have already calculated, skip it. */ + if (dfa->eclosures[node_idx].nelem != 0) + continue; + /* Calculate epsilon closure of `node_idx'. */ + err = calc_eclosure_iter (&eclosure_elem, dfa, node_idx, 1); + if (BE (err != REG_NOERROR, 0)) + return err; + + if (dfa->eclosures[node_idx].nelem == 0) + { + incomplete = 1; + re_node_set_free (&eclosure_elem); + } + } + return REG_NOERROR; +} + +/* Calculate epsilon closure of NODE. */ + +static reg_errcode_t +calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root) +{ + reg_errcode_t err; + unsigned int constraint; + int i, incomplete; + re_node_set eclosure; + incomplete = 0; + err = re_node_set_alloc (&eclosure, dfa->edests[node].nelem + 1); + if (BE (err != REG_NOERROR, 0)) + return err; + + /* This indicates that we are calculating this node now. + We reference this value to avoid infinite loop. */ + dfa->eclosures[node].nelem = -1; + + constraint = ((dfa->nodes[node].type == ANCHOR) + ? dfa->nodes[node].opr.ctx_type : 0); + /* If the current node has constraints, duplicate all nodes. + Since they must inherit the constraints. */ + if (constraint + && dfa->edests[node].nelem + && !dfa->nodes[dfa->edests[node].elems[0]].duplicated) + { + err = duplicate_node_closure (dfa, node, node, node, constraint); + if (BE (err != REG_NOERROR, 0)) + return err; + } + + /* Expand each epsilon destination nodes. */ + if (IS_EPSILON_NODE(dfa->nodes[node].type)) + for (i = 0; i < dfa->edests[node].nelem; ++i) + { + re_node_set eclosure_elem; + int edest = dfa->edests[node].elems[i]; + /* If calculating the epsilon closure of `edest' is in progress, + return intermediate result. */ + if (dfa->eclosures[edest].nelem == -1) + { + incomplete = 1; + continue; + } + /* If we haven't calculated the epsilon closure of `edest' yet, + calculate now. Otherwise use calculated epsilon closure. */ + if (dfa->eclosures[edest].nelem == 0) + { + err = calc_eclosure_iter (&eclosure_elem, dfa, edest, 0); + if (BE (err != REG_NOERROR, 0)) + return err; + } + else + eclosure_elem = dfa->eclosures[edest]; + /* Merge the epsilon closure of `edest'. */ + re_node_set_merge (&eclosure, &eclosure_elem); + /* If the epsilon closure of `edest' is incomplete, + the epsilon closure of this node is also incomplete. */ + if (dfa->eclosures[edest].nelem == 0) + { + incomplete = 1; + re_node_set_free (&eclosure_elem); + } + } + + /* Epsilon closures include itself. */ + re_node_set_insert (&eclosure, node); + if (incomplete && !root) + dfa->eclosures[node].nelem = 0; + else + dfa->eclosures[node] = eclosure; + *new_set = eclosure; + return REG_NOERROR; +} + +/* Functions for token which are used in the parser. */ + +/* Fetch a token from INPUT. + We must not use this function inside bracket expressions. */ + +static void +internal_function +fetch_token (re_token_t *result, re_string_t *input, reg_syntax_t syntax) +{ + re_string_skip_bytes (input, peek_token (result, input, syntax)); +} + +/* Peek a token from INPUT, and return the length of the token. + We must not use this function inside bracket expressions. */ + +static int +internal_function +peek_token (re_token_t *token, re_string_t *input, reg_syntax_t syntax) +{ + unsigned char c; + + if (re_string_eoi (input)) + { + token->type = END_OF_RE; + return 0; + } + + c = re_string_peek_byte (input, 0); + token->opr.c = c; + + token->word_char = 0; +#ifdef RE_ENABLE_I18N + token->mb_partial = 0; + if (input->mb_cur_max > 1 && + !re_string_first_byte (input, re_string_cur_idx (input))) + { + token->type = CHARACTER; + token->mb_partial = 1; + return 1; + } +#endif + if (c == '\\') + { + unsigned char c2; + if (re_string_cur_idx (input) + 1 >= re_string_length (input)) + { + token->type = BACK_SLASH; + return 1; + } + + c2 = re_string_peek_byte_case (input, 1); + token->opr.c = c2; + token->type = CHARACTER; +#ifdef RE_ENABLE_I18N + if (input->mb_cur_max > 1) + { + wint_t wc = re_string_wchar_at (input, + re_string_cur_idx (input) + 1); + token->word_char = IS_WIDE_WORD_CHAR (wc) != 0; + } + else +#endif + token->word_char = IS_WORD_CHAR (c2) != 0; + + switch (c2) + { + case '|': + if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_NO_BK_VBAR)) + token->type = OP_ALT; + break; + case '1': case '2': case '3': case '4': case '5': + case '6': case '7': case '8': case '9': + if (!(syntax & RE_NO_BK_REFS)) + { + token->type = OP_BACK_REF; + token->opr.idx = c2 - '1'; + } + break; + case '<': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = WORD_FIRST; + } + break; + case '>': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = WORD_LAST; + } + break; + case 'b': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = WORD_DELIM; + } + break; + case 'B': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = NOT_WORD_DELIM; + } + break; + case 'w': + if (!(syntax & RE_NO_GNU_OPS)) + token->type = OP_WORD; + break; + case 'W': + if (!(syntax & RE_NO_GNU_OPS)) + token->type = OP_NOTWORD; + break; + case 's': + if (!(syntax & RE_NO_GNU_OPS)) + token->type = OP_SPACE; + break; + case 'S': + if (!(syntax & RE_NO_GNU_OPS)) + token->type = OP_NOTSPACE; + break; + case '`': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = BUF_FIRST; + } + break; + case '\'': + if (!(syntax & RE_NO_GNU_OPS)) + { + token->type = ANCHOR; + token->opr.ctx_type = BUF_LAST; + } + break; + case '(': + if (!(syntax & RE_NO_BK_PARENS)) + token->type = OP_OPEN_SUBEXP; + break; + case ')': + if (!(syntax & RE_NO_BK_PARENS)) + token->type = OP_CLOSE_SUBEXP; + break; + case '+': + if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_PLUS; + break; + case '?': + if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_QUESTION; + break; + case '{': + if ((syntax & RE_INTERVALS) && (!(syntax & RE_NO_BK_BRACES))) + token->type = OP_OPEN_DUP_NUM; + break; + case '}': + if ((syntax & RE_INTERVALS) && (!(syntax & RE_NO_BK_BRACES))) + token->type = OP_CLOSE_DUP_NUM; + break; + default: + break; + } + return 2; + } + + token->type = CHARACTER; +#ifdef RE_ENABLE_I18N + if (input->mb_cur_max > 1) + { + wint_t wc = re_string_wchar_at (input, re_string_cur_idx (input)); + token->word_char = IS_WIDE_WORD_CHAR (wc) != 0; + } + else +#endif + token->word_char = IS_WORD_CHAR (token->opr.c); + + switch (c) + { + case '\n': + if (syntax & RE_NEWLINE_ALT) + token->type = OP_ALT; + break; + case '|': + if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_NO_BK_VBAR)) + token->type = OP_ALT; + break; + case '*': + token->type = OP_DUP_ASTERISK; + break; + case '+': + if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_PLUS; + break; + case '?': + if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) + token->type = OP_DUP_QUESTION; + break; + case '{': + if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) + token->type = OP_OPEN_DUP_NUM; + break; + case '}': + if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) + token->type = OP_CLOSE_DUP_NUM; + break; + case '(': + if (syntax & RE_NO_BK_PARENS) + token->type = OP_OPEN_SUBEXP; + break; + case ')': + if (syntax & RE_NO_BK_PARENS) + token->type = OP_CLOSE_SUBEXP; + break; + case '[': + token->type = OP_OPEN_BRACKET; + break; + case '.': + token->type = OP_PERIOD; + break; + case '^': + if (!(syntax & (RE_CONTEXT_INDEP_ANCHORS | RE_CARET_ANCHORS_HERE)) && + re_string_cur_idx (input) != 0) + { + char prev = re_string_peek_byte (input, -1); + if (!(syntax & RE_NEWLINE_ALT) || prev != '\n') + break; + } + token->type = ANCHOR; + token->opr.ctx_type = LINE_FIRST; + break; + case '$': + if (!(syntax & RE_CONTEXT_INDEP_ANCHORS) && + re_string_cur_idx (input) + 1 != re_string_length (input)) + { + re_token_t next; + re_string_skip_bytes (input, 1); + peek_token (&next, input, syntax); + re_string_skip_bytes (input, -1); + if (next.type != OP_ALT && next.type != OP_CLOSE_SUBEXP) + break; + } + token->type = ANCHOR; + token->opr.ctx_type = LINE_LAST; + break; + default: + break; + } + return 1; +} + +/* Peek a token from INPUT, and return the length of the token. + We must not use this function out of bracket expressions. */ + +static int +internal_function +peek_token_bracket (re_token_t *token, re_string_t *input, reg_syntax_t syntax) +{ + unsigned char c; + if (re_string_eoi (input)) + { + token->type = END_OF_RE; + return 0; + } + c = re_string_peek_byte (input, 0); + token->opr.c = c; + +#ifdef RE_ENABLE_I18N + if (input->mb_cur_max > 1 && + !re_string_first_byte (input, re_string_cur_idx (input))) + { + token->type = CHARACTER; + return 1; + } +#endif /* RE_ENABLE_I18N */ + + if (c == '\\' && (syntax & RE_BACKSLASH_ESCAPE_IN_LISTS) + && re_string_cur_idx (input) + 1 < re_string_length (input)) + { + /* In this case, '\' escape a character. */ + unsigned char c2; + re_string_skip_bytes (input, 1); + c2 = re_string_peek_byte (input, 0); + token->opr.c = c2; + token->type = CHARACTER; + return 1; + } + if (c == '[') /* '[' is a special char in a bracket exps. */ + { + unsigned char c2; + int token_len; + if (re_string_cur_idx (input) + 1 < re_string_length (input)) + c2 = re_string_peek_byte (input, 1); + else + c2 = 0; + token->opr.c = c2; + token_len = 2; + switch (c2) + { + case '.': + token->type = OP_OPEN_COLL_ELEM; + break; + case '=': + token->type = OP_OPEN_EQUIV_CLASS; + break; + case ':': + if (syntax & RE_CHAR_CLASSES) + { + token->type = OP_OPEN_CHAR_CLASS; + break; + } + /* else fall through. */ + default: + token->type = CHARACTER; + token->opr.c = c; + token_len = 1; + break; + } + return token_len; + } + switch (c) + { + case '-': + token->type = OP_CHARSET_RANGE; + break; + case ']': + token->type = OP_CLOSE_BRACKET; + break; + case '^': + token->type = OP_NON_MATCH_LIST; + break; + default: + token->type = CHARACTER; + } + return 1; +} + +/* Functions for parser. */ + +/* Entry point of the parser. + Parse the regular expression REGEXP and return the structure tree. + If an error is occured, ERR is set by error code, and return NULL. + This function build the following tree, from regular expression : + CAT + / \ + / \ + EOR + + CAT means concatenation. + EOR means end of regular expression. */ + +static bin_tree_t * +parse (re_string_t *regexp, regex_t *preg, reg_syntax_t syntax, + reg_errcode_t *err) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_t *tree, *eor, *root; + re_token_t current_token; + dfa->syntax = syntax; + fetch_token (¤t_token, regexp, syntax | RE_CARET_ANCHORS_HERE); + tree = parse_reg_exp (regexp, preg, ¤t_token, syntax, 0, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + eor = create_tree (dfa, NULL, NULL, END_OF_RE); + if (tree != NULL) + root = create_tree (dfa, tree, eor, CONCAT); + else + root = eor; + if (BE (eor == NULL || root == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + return root; +} + +/* This function build the following tree, from regular expression + |: + ALT + / \ + / \ + + + ALT means alternative, which represents the operator `|'. */ + +static bin_tree_t * +parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token, + reg_syntax_t syntax, int nest, reg_errcode_t *err) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_t *tree, *branch = NULL; + tree = parse_branch (regexp, preg, token, syntax, nest, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + + while (token->type == OP_ALT) + { + fetch_token (token, regexp, syntax | RE_CARET_ANCHORS_HERE); + if (token->type != OP_ALT && token->type != END_OF_RE + && (nest == 0 || token->type != OP_CLOSE_SUBEXP)) + { + branch = parse_branch (regexp, preg, token, syntax, nest, err); + if (BE (*err != REG_NOERROR && branch == NULL, 0)) + return NULL; + } + else + branch = NULL; + tree = create_tree (dfa, tree, branch, OP_ALT); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + } + return tree; +} + +/* This function build the following tree, from regular expression + : + CAT + / \ + / \ + + + CAT means concatenation. */ + +static bin_tree_t * +parse_branch (re_string_t *regexp, regex_t *preg, re_token_t *token, + reg_syntax_t syntax, int nest, reg_errcode_t *err) +{ + bin_tree_t *tree, *exp; + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + tree = parse_expression (regexp, preg, token, syntax, nest, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + + while (token->type != OP_ALT && token->type != END_OF_RE + && (nest == 0 || token->type != OP_CLOSE_SUBEXP)) + { + exp = parse_expression (regexp, preg, token, syntax, nest, err); + if (BE (*err != REG_NOERROR && exp == NULL, 0)) + { + return NULL; + } + if (tree != NULL && exp != NULL) + { + tree = create_tree (dfa, tree, exp, CONCAT); + if (tree == NULL) + { + *err = REG_ESPACE; + return NULL; + } + } + else if (tree == NULL) + tree = exp; + /* Otherwise exp == NULL, we don't need to create new tree. */ + } + return tree; +} + +/* This function build the following tree, from regular expression a*: + * + | + a +*/ + +static bin_tree_t * +parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token, + reg_syntax_t syntax, int nest, reg_errcode_t *err) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_t *tree; + switch (token->type) + { + case CHARACTER: + tree = create_token_tree (dfa, NULL, NULL, token); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + { + while (!re_string_eoi (regexp) + && !re_string_first_byte (regexp, re_string_cur_idx (regexp))) + { + bin_tree_t *mbc_remain; + fetch_token (token, regexp, syntax); + mbc_remain = create_token_tree (dfa, NULL, NULL, token); + tree = create_tree (dfa, tree, mbc_remain, CONCAT); + if (BE (mbc_remain == NULL || tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + } + } +#endif + break; + case OP_OPEN_SUBEXP: + tree = parse_sub_exp (regexp, preg, token, syntax, nest + 1, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + break; + case OP_OPEN_BRACKET: + tree = parse_bracket_exp (regexp, dfa, token, syntax, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + break; + case OP_BACK_REF: + if (!BE (dfa->completed_bkref_map & (1 << token->opr.idx), 1)) + { + *err = REG_ESUBREG; + return NULL; + } + dfa->used_bkref_map |= 1 << token->opr.idx; + tree = create_token_tree (dfa, NULL, NULL, token); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + ++dfa->nbackref; + dfa->has_mb_node = 1; + break; + case OP_OPEN_DUP_NUM: + if (syntax & RE_CONTEXT_INVALID_DUP) + { + *err = REG_BADRPT; + return NULL; + } + /* FALLTHROUGH */ + case OP_DUP_ASTERISK: + case OP_DUP_PLUS: + case OP_DUP_QUESTION: + if (syntax & RE_CONTEXT_INVALID_OPS) + { + *err = REG_BADRPT; + return NULL; + } + else if (syntax & RE_CONTEXT_INDEP_OPS) + { + fetch_token (token, regexp, syntax); + return parse_expression (regexp, preg, token, syntax, nest, err); + } + /* else fall through */ + case OP_CLOSE_SUBEXP: + if ((token->type == OP_CLOSE_SUBEXP) && + !(syntax & RE_UNMATCHED_RIGHT_PAREN_ORD)) + { + *err = REG_ERPAREN; + return NULL; + } + /* else fall through */ + case OP_CLOSE_DUP_NUM: + /* We treat it as a normal character. */ + + /* Then we can these characters as normal characters. */ + token->type = CHARACTER; + /* mb_partial and word_char bits should be initialized already + by peek_token. */ + tree = create_token_tree (dfa, NULL, NULL, token); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + break; + case ANCHOR: + if ((token->opr.ctx_type + & (WORD_DELIM | NOT_WORD_DELIM | WORD_FIRST | WORD_LAST)) + && dfa->word_ops_used == 0) + init_word_char (dfa); + if (token->opr.ctx_type == WORD_DELIM + || token->opr.ctx_type == NOT_WORD_DELIM) + { + bin_tree_t *tree_first, *tree_last; + if (token->opr.ctx_type == WORD_DELIM) + { + token->opr.ctx_type = WORD_FIRST; + tree_first = create_token_tree (dfa, NULL, NULL, token); + token->opr.ctx_type = WORD_LAST; + } + else + { + token->opr.ctx_type = INSIDE_WORD; + tree_first = create_token_tree (dfa, NULL, NULL, token); + token->opr.ctx_type = INSIDE_NOTWORD; + } + tree_last = create_token_tree (dfa, NULL, NULL, token); + tree = create_tree (dfa, tree_first, tree_last, OP_ALT); + if (BE (tree_first == NULL || tree_last == NULL || tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + } + else + { + tree = create_token_tree (dfa, NULL, NULL, token); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + } + /* We must return here, since ANCHORs can't be followed + by repetition operators. + eg. RE"^*" is invalid or "", + it must not be "". */ + fetch_token (token, regexp, syntax); + return tree; + case OP_PERIOD: + tree = create_token_tree (dfa, NULL, NULL, token); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + if (dfa->mb_cur_max > 1) + dfa->has_mb_node = 1; + break; + case OP_WORD: + case OP_NOTWORD: + tree = build_charclass_op (dfa, regexp->trans, + (const unsigned char *) "alnum", + (const unsigned char *) "_", + token->type == OP_NOTWORD, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + break; + case OP_SPACE: + case OP_NOTSPACE: + tree = build_charclass_op (dfa, regexp->trans, + (const unsigned char *) "space", + (const unsigned char *) "", + token->type == OP_NOTSPACE, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + break; + case OP_ALT: + case END_OF_RE: + return NULL; + case BACK_SLASH: + *err = REG_EESCAPE; + return NULL; + default: + /* Must not happen? */ +#ifdef DEBUG + assert (0); +#endif + return NULL; + } + fetch_token (token, regexp, syntax); + + while (token->type == OP_DUP_ASTERISK || token->type == OP_DUP_PLUS + || token->type == OP_DUP_QUESTION || token->type == OP_OPEN_DUP_NUM) + { + tree = parse_dup_op (tree, regexp, dfa, token, syntax, err); + if (BE (*err != REG_NOERROR && tree == NULL, 0)) + return NULL; + /* In BRE consecutive duplications are not allowed. */ + if ((syntax & RE_CONTEXT_INVALID_DUP) + && (token->type == OP_DUP_ASTERISK + || token->type == OP_OPEN_DUP_NUM)) + { + *err = REG_BADRPT; + return NULL; + } + } + + return tree; +} + +/* This function build the following tree, from regular expression + (): + SUBEXP + | + +*/ + +static bin_tree_t * +parse_sub_exp (re_string_t *regexp, regex_t *preg, re_token_t *token, + reg_syntax_t syntax, int nest, reg_errcode_t *err) +{ + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + bin_tree_t *tree; + size_t cur_nsub; + cur_nsub = preg->re_nsub++; + + fetch_token (token, regexp, syntax | RE_CARET_ANCHORS_HERE); + + /* The subexpression may be a null string. */ + if (token->type == OP_CLOSE_SUBEXP) + tree = NULL; + else + { + tree = parse_reg_exp (regexp, preg, token, syntax, nest, err); + if (BE (*err == REG_NOERROR && token->type != OP_CLOSE_SUBEXP, 0)) + *err = REG_EPAREN; + if (BE (*err != REG_NOERROR, 0)) + return NULL; + } + + if (cur_nsub <= '9' - '1') + dfa->completed_bkref_map |= 1 << cur_nsub; + + tree = create_tree (dfa, tree, NULL, SUBEXP); + if (BE (tree == NULL, 0)) + { + *err = REG_ESPACE; + return NULL; + } + tree->token.opr.idx = cur_nsub; + return tree; +} + +/* This function parse repetition operators like "*", "+", "{1,3}" etc. */ + +static bin_tree_t * +parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa, + re_token_t *token, reg_syntax_t syntax, reg_errcode_t *err) +{ + bin_tree_t *tree = NULL, *old_tree = NULL; + int i, start, end, start_idx = re_string_cur_idx (regexp); + re_token_t start_token = *token; + + if (token->type == OP_OPEN_DUP_NUM) + { + end = 0; + start = fetch_number (regexp, token, syntax); + if (start == -1) + { + if (token->type == CHARACTER && token->opr.c == ',') + start = 0; /* We treat "{,m}" as "{0,m}". */ + else + { + *err = REG_BADBR; /* {} is invalid. */ + return NULL; + } + } + if (BE (start != -2, 1)) + { + /* We treat "{n}" as "{n,n}". */ + end = ((token->type == OP_CLOSE_DUP_NUM) ? start + : ((token->type == CHARACTER && token->opr.c == ',') + ? fetch_number (regexp, token, syntax) : -2)); + } + if (BE (start == -2 || end == -2, 0)) + { + /* Invalid sequence. */ + if (BE (!(syntax & RE_INVALID_INTERVAL_ORD), 0)) + { + if (token->type == END_OF_RE) + *err = REG_EBRACE; + else + *err = REG_BADBR; + + return NULL; + } + + /* If the syntax bit is set, rollback. */ + re_string_set_index (regexp, start_idx); + *token = start_token; + token->type = CHARACTER; + /* mb_partial and word_char bits should be already initialized by + peek_token. */ + return elem; + } + + if (BE (end != -1 && start > end, 0)) + { + /* First number greater than second. */ + *err = REG_BADBR; + return NULL; + } + } + else + { + start = (token->type == OP_DUP_PLUS) ? 1 : 0; + end = (token->type == OP_DUP_QUESTION) ? 1 : -1; + } + + fetch_token (token, regexp, syntax); + + if (BE (elem == NULL, 0)) + return NULL; + if (BE (start == 0 && end == 0, 0)) + { + postorder (elem, free_tree, NULL); + return NULL; + } + + /* Extract "{n,m}" to "...{0,}". */ + if (BE (start > 0, 0)) + { + tree = elem; + for (i = 2; i <= start; ++i) + { + elem = duplicate_tree (elem, dfa); + tree = create_tree (dfa, tree, elem, CONCAT); + if (BE (elem == NULL || tree == NULL, 0)) + goto parse_dup_op_espace; + } + + if (start == end) + return tree; + + /* Duplicate ELEM before it is marked optional. */ + elem = duplicate_tree (elem, dfa); + old_tree = tree; + } + else + old_tree = NULL; + + if (elem->token.type == SUBEXP) + postorder (elem, mark_opt_subexp, (void *) (long) elem->token.opr.idx); + + tree = create_tree (dfa, elem, NULL, (end == -1 ? OP_DUP_ASTERISK : OP_ALT)); + if (BE (tree == NULL, 0)) + goto parse_dup_op_espace; + + /* This loop is actually executed only when end != -1, + to rewrite {0,n} as ((...?)?)?... We have + already created the start+1-th copy. */ + for (i = start + 2; i <= end; ++i) + { + elem = duplicate_tree (elem, dfa); + tree = create_tree (dfa, tree, elem, CONCAT); + if (BE (elem == NULL || tree == NULL, 0)) + goto parse_dup_op_espace; + + tree = create_tree (dfa, tree, NULL, OP_ALT); + if (BE (tree == NULL, 0)) + goto parse_dup_op_espace; + } + + if (old_tree) + tree = create_tree (dfa, old_tree, tree, CONCAT); + + return tree; + + parse_dup_op_espace: + *err = REG_ESPACE; + return NULL; +} + +/* Size of the names for collating symbol/equivalence_class/character_class. + I'm not sure, but maybe enough. */ +#define BRACKET_NAME_BUF_SIZE 32 + +#ifndef _LIBC + /* Local function for parse_bracket_exp only used in case of NOT _LIBC. + Build the range expression which starts from START_ELEM, and ends + at END_ELEM. The result are written to MBCSET and SBCSET. + RANGE_ALLOC is the allocated size of mbcset->range_starts, and + mbcset->range_ends, is a pointer argument sinse we may + update it. */ + +static reg_errcode_t +internal_function +# ifdef RE_ENABLE_I18N +build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc, + bracket_elem_t *start_elem, bracket_elem_t *end_elem) +# else /* not RE_ENABLE_I18N */ +build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem, + bracket_elem_t *end_elem) +# endif /* not RE_ENABLE_I18N */ +{ + unsigned int start_ch, end_ch; + /* Equivalence Classes and Character Classes can't be a range start/end. */ + if (BE (start_elem->type == EQUIV_CLASS || start_elem->type == CHAR_CLASS + || end_elem->type == EQUIV_CLASS || end_elem->type == CHAR_CLASS, + 0)) + return REG_ERANGE; + + /* We can handle no multi character collating elements without libc + support. */ + if (BE ((start_elem->type == COLL_SYM + && strlen ((char *) start_elem->opr.name) > 1) + || (end_elem->type == COLL_SYM + && strlen ((char *) end_elem->opr.name) > 1), 0)) + return REG_ECOLLATE; + +# ifdef RE_ENABLE_I18N + { + wchar_t wc; + wint_t start_wc; + wint_t end_wc; + wchar_t cmp_buf[6] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'}; + + start_ch = ((start_elem->type == SB_CHAR) ? start_elem->opr.ch + : ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0] + : 0)); + end_ch = ((end_elem->type == SB_CHAR) ? end_elem->opr.ch + : ((end_elem->type == COLL_SYM) ? end_elem->opr.name[0] + : 0)); + start_wc = ((start_elem->type == SB_CHAR || start_elem->type == COLL_SYM) + ? __btowc (start_ch) : start_elem->opr.wch); + end_wc = ((end_elem->type == SB_CHAR || end_elem->type == COLL_SYM) + ? __btowc (end_ch) : end_elem->opr.wch); + if (start_wc == WEOF || end_wc == WEOF) + return REG_ECOLLATE; + cmp_buf[0] = start_wc; + cmp_buf[4] = end_wc; + if (wcscoll (cmp_buf, cmp_buf + 4) > 0) + return REG_ERANGE; + + /* Got valid collation sequence values, add them as a new entry. + However, for !_LIBC we have no collation elements: if the + character set is single byte, the single byte character set + that we build below suffices. parse_bracket_exp passes + no MBCSET if dfa->mb_cur_max == 1. */ + if (mbcset) + { + /* Check the space of the arrays. */ + if (BE (*range_alloc == mbcset->nranges, 0)) + { + /* There is not enough space, need realloc. */ + wchar_t *new_array_start, *new_array_end; + int new_nranges; + + /* +1 in case of mbcset->nranges is 0. */ + new_nranges = 2 * mbcset->nranges + 1; + /* Use realloc since mbcset->range_starts and mbcset->range_ends + are NULL if *range_alloc == 0. */ + new_array_start = re_realloc (mbcset->range_starts, wchar_t, + new_nranges); + new_array_end = re_realloc (mbcset->range_ends, wchar_t, + new_nranges); + + if (BE (new_array_start == NULL || new_array_end == NULL, 0)) + return REG_ESPACE; + + mbcset->range_starts = new_array_start; + mbcset->range_ends = new_array_end; + *range_alloc = new_nranges; + } + + mbcset->range_starts[mbcset->nranges] = start_wc; + mbcset->range_ends[mbcset->nranges++] = end_wc; + } + + /* Build the table for single byte characters. */ + for (wc = 0; wc < SBC_MAX; ++wc) + { + cmp_buf[2] = wc; + if (wcscoll (cmp_buf, cmp_buf + 2) <= 0 + && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0) + bitset_set (sbcset, wc); + } + } +# else /* not RE_ENABLE_I18N */ + { + unsigned int ch; + start_ch = ((start_elem->type == SB_CHAR ) ? start_elem->opr.ch + : ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0] + : 0)); + end_ch = ((end_elem->type == SB_CHAR ) ? end_elem->opr.ch + : ((end_elem->type == COLL_SYM) ? end_elem->opr.name[0] + : 0)); + if (start_ch > end_ch) + return REG_ERANGE; + /* Build the table for single byte characters. */ + for (ch = 0; ch < SBC_MAX; ++ch) + if (start_ch <= ch && ch <= end_ch) + bitset_set (sbcset, ch); + } +# endif /* not RE_ENABLE_I18N */ + return REG_NOERROR; +} +#endif /* not _LIBC */ + +#ifndef _LIBC +/* Helper function for parse_bracket_exp only used in case of NOT _LIBC.. + Build the collating element which is represented by NAME. + The result are written to MBCSET and SBCSET. + COLL_SYM_ALLOC is the allocated size of mbcset->coll_sym, is a + pointer argument since we may update it. */ + +static reg_errcode_t +internal_function +# ifdef RE_ENABLE_I18N +build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset, + int *coll_sym_alloc, const unsigned char *name) +# else /* not RE_ENABLE_I18N */ +build_collating_symbol (bitset_t sbcset, const unsigned char *name) +# endif /* not RE_ENABLE_I18N */ +{ + size_t name_len = strlen ((const char *) name); + if (BE (name_len != 1, 0)) + return REG_ECOLLATE; + else + { + bitset_set (sbcset, name[0]); + return REG_NOERROR; + } +} +#endif /* not _LIBC */ + +/* This function parse bracket expression like "[abc]", "[a-c]", + "[[.a-a.]]" etc. */ + +static bin_tree_t * +parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token, + reg_syntax_t syntax, reg_errcode_t *err) +{ +#ifdef _LIBC + const unsigned char *collseqmb; + const char *collseqwc; + uint32_t nrules; + int32_t table_size; + const int32_t *symb_table; + const unsigned char *extra; + + /* Local function for parse_bracket_exp used in _LIBC environement. + Seek the collating symbol entry correspondings to NAME. + Return the index of the symbol in the SYMB_TABLE. */ + + auto inline int32_t + __attribute ((always_inline)) + seek_collating_symbol_entry (name, name_len) + const unsigned char *name; + size_t name_len; + { + int32_t hash = elem_hash ((const char *) name, name_len); + int32_t elem = hash % table_size; + if (symb_table[2 * elem] != 0) + { + int32_t second = hash % (table_size - 2) + 1; + + do + { + /* First compare the hashing value. */ + if (symb_table[2 * elem] == hash + /* Compare the length of the name. */ + && name_len == extra[symb_table[2 * elem + 1]] + /* Compare the name. */ + && memcmp (name, &extra[symb_table[2 * elem + 1] + 1], + name_len) == 0) + { + /* Yep, this is the entry. */ + break; + } + + /* Next entry. */ + elem += second; + } + while (symb_table[2 * elem] != 0); + } + return elem; + } + + /* Local function for parse_bracket_exp used in _LIBC environement. + Look up the collation sequence value of BR_ELEM. + Return the value if succeeded, UINT_MAX otherwise. */ + + auto inline unsigned int + __attribute ((always_inline)) + lookup_collation_sequence_value (br_elem) + bracket_elem_t *br_elem; + { + if (br_elem->type == SB_CHAR) + { + /* + if (MB_CUR_MAX == 1) + */ + if (nrules == 0) + return collseqmb[br_elem->opr.ch]; + else + { + wint_t wc = __btowc (br_elem->opr.ch); + return __collseq_table_lookup (collseqwc, wc); + } + } + else if (br_elem->type == MB_CHAR) + { + return __collseq_table_lookup (collseqwc, br_elem->opr.wch); + } + else if (br_elem->type == COLL_SYM) + { + size_t sym_name_len = strlen ((char *) br_elem->opr.name); + if (nrules != 0) + { + int32_t elem, idx; + elem = seek_collating_symbol_entry (br_elem->opr.name, + sym_name_len); + if (symb_table[2 * elem] != 0) + { + /* We found the entry. */ + idx = symb_table[2 * elem + 1]; + /* Skip the name of collating element name. */ + idx += 1 + extra[idx]; + /* Skip the byte sequence of the collating element. */ + idx += 1 + extra[idx]; + /* Adjust for the alignment. */ + idx = (idx + 3) & ~3; + /* Skip the multibyte collation sequence value. */ + idx += sizeof (unsigned int); + /* Skip the wide char sequence of the collating element. */ + idx += sizeof (unsigned int) * + (1 + *(unsigned int *) (extra + idx)); + /* Return the collation sequence value. */ + return *(unsigned int *) (extra + idx); + } + else if (symb_table[2 * elem] == 0 && sym_name_len == 1) + { + /* No valid character. Match it as a single byte + character. */ + return collseqmb[br_elem->opr.name[0]]; + } + } + else if (sym_name_len == 1) + return collseqmb[br_elem->opr.name[0]]; + } + return UINT_MAX; + } + + /* Local function for parse_bracket_exp used in _LIBC environement. + Build the range expression which starts from START_ELEM, and ends + at END_ELEM. The result are written to MBCSET and SBCSET. + RANGE_ALLOC is the allocated size of mbcset->range_starts, and + mbcset->range_ends, is a pointer argument sinse we may + update it. */ + + auto inline reg_errcode_t + __attribute ((always_inline)) + build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem) + re_charset_t *mbcset; + int *range_alloc; + bitset_t sbcset; + bracket_elem_t *start_elem, *end_elem; + { + unsigned int ch; + uint32_t start_collseq; + uint32_t end_collseq; + + /* Equivalence Classes and Character Classes can't be a range + start/end. */ + if (BE (start_elem->type == EQUIV_CLASS || start_elem->type == CHAR_CLASS + || end_elem->type == EQUIV_CLASS || end_elem->type == CHAR_CLASS, + 0)) + return REG_ERANGE; + + start_collseq = lookup_collation_sequence_value (start_elem); + end_collseq = lookup_collation_sequence_value (end_elem); + /* Check start/end collation sequence values. */ + if (BE (start_collseq == UINT_MAX || end_collseq == UINT_MAX, 0)) + return REG_ECOLLATE; + if (BE ((syntax & RE_NO_EMPTY_RANGES) && start_collseq > end_collseq, 0)) + return REG_ERANGE; + + /* Got valid collation sequence values, add them as a new entry. + However, if we have no collation elements, and the character set + is single byte, the single byte character set that we + build below suffices. */ + if (nrules > 0 || dfa->mb_cur_max > 1) + { + /* Check the space of the arrays. */ + if (BE (*range_alloc == mbcset->nranges, 0)) + { + /* There is not enough space, need realloc. */ + uint32_t *new_array_start; + uint32_t *new_array_end; + int new_nranges; + + /* +1 in case of mbcset->nranges is 0. */ + new_nranges = 2 * mbcset->nranges + 1; + new_array_start = re_realloc (mbcset->range_starts, uint32_t, + new_nranges); + new_array_end = re_realloc (mbcset->range_ends, uint32_t, + new_nranges); + + if (BE (new_array_start == NULL || new_array_end == NULL, 0)) + return REG_ESPACE; + + mbcset->range_starts = new_array_start; + mbcset->range_ends = new_array_end; + *range_alloc = new_nranges; + } + + mbcset->range_starts[mbcset->nranges] = start_collseq; + mbcset->range_ends[mbcset->nranges++] = end_collseq; + } + + /* Build the table for single byte characters. */ + for (ch = 0; ch < SBC_MAX; ch++) + { + uint32_t ch_collseq; + /* + if (MB_CUR_MAX == 1) + */ + if (nrules == 0) + ch_collseq = collseqmb[ch]; + else + ch_collseq = __collseq_table_lookup (collseqwc, __btowc (ch)); + if (start_collseq <= ch_collseq && ch_collseq <= end_collseq) + bitset_set (sbcset, ch); + } + return REG_NOERROR; + } + + /* Local function for parse_bracket_exp used in _LIBC environement. + Build the collating element which is represented by NAME. + The result are written to MBCSET and SBCSET. + COLL_SYM_ALLOC is the allocated size of mbcset->coll_sym, is a + pointer argument sinse we may update it. */ + + auto inline reg_errcode_t + __attribute ((always_inline)) + build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name) + re_charset_t *mbcset; + int *coll_sym_alloc; + bitset_t sbcset; + const unsigned char *name; + { + int32_t elem, idx; + size_t name_len = strlen ((const char *) name); + if (nrules != 0) + { + elem = seek_collating_symbol_entry (name, name_len); + if (symb_table[2 * elem] != 0) + { + /* We found the entry. */ + idx = symb_table[2 * elem + 1]; + /* Skip the name of collating element name. */ + idx += 1 + extra[idx]; + } + else if (symb_table[2 * elem] == 0 && name_len == 1) + { + /* No valid character, treat it as a normal + character. */ + bitset_set (sbcset, name[0]); + return REG_NOERROR; + } + else + return REG_ECOLLATE; + + /* Got valid collation sequence, add it as a new entry. */ + /* Check the space of the arrays. */ + if (BE (*coll_sym_alloc == mbcset->ncoll_syms, 0)) + { + /* Not enough, realloc it. */ + /* +1 in case of mbcset->ncoll_syms is 0. */ + int new_coll_sym_alloc = 2 * mbcset->ncoll_syms + 1; + /* Use realloc since mbcset->coll_syms is NULL + if *alloc == 0. */ + int32_t *new_coll_syms = re_realloc (mbcset->coll_syms, int32_t, + new_coll_sym_alloc); + if (BE (new_coll_syms == NULL, 0)) + return REG_ESPACE; + mbcset->coll_syms = new_coll_syms; + *coll_sym_alloc = new_coll_sym_alloc; + } + mbcset->coll_syms[mbcset->ncoll_syms++] = idx; + return REG_NOERROR; + } + else + { + if (BE (name_len != 1, 0)) + return REG_ECOLLATE; + else + { + bitset_set (sbcset, name[0]); + return REG_NOERROR; + } + } + } +#endif + + re_token_t br_token; + re_bitset_ptr_t sbcset; +#ifdef RE_ENABLE_I18N + re_charset_t *mbcset; + int coll_sym_alloc = 0, range_alloc = 0, mbchar_alloc = 0; + int equiv_class_alloc = 0, char_class_alloc = 0; +#endif /* not RE_ENABLE_I18N */ + int non_match = 0; + bin_tree_t *work_tree; + int token_len; + int first_round = 1; +#ifdef _LIBC + collseqmb = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQMB); + nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); + if (nrules) + { + /* + if (MB_CUR_MAX > 1) + */ + collseqwc = _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQWC); + table_size = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_SYMB_HASH_SIZEMB); + symb_table = (const int32_t *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_SYMB_TABLEMB); + extra = (const unsigned char *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_SYMB_EXTRAMB); + } +#endif + sbcset = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); +#ifdef RE_ENABLE_I18N + mbcset = (re_charset_t *) calloc (sizeof (re_charset_t), 1); +#endif /* RE_ENABLE_I18N */ +#ifdef RE_ENABLE_I18N + if (BE (sbcset == NULL || mbcset == NULL, 0)) +#else + if (BE (sbcset == NULL, 0)) +#endif /* RE_ENABLE_I18N */ + { + *err = REG_ESPACE; + return NULL; + } + + token_len = peek_token_bracket (token, regexp, syntax); + if (BE (token->type == END_OF_RE, 0)) + { + *err = REG_BADPAT; + goto parse_bracket_exp_free_return; + } + if (token->type == OP_NON_MATCH_LIST) + { +#ifdef RE_ENABLE_I18N + mbcset->non_match = 1; +#endif /* not RE_ENABLE_I18N */ + non_match = 1; + if (syntax & RE_HAT_LISTS_NOT_NEWLINE) + bitset_set (sbcset, '\0'); + re_string_skip_bytes (regexp, token_len); /* Skip a token. */ + token_len = peek_token_bracket (token, regexp, syntax); + if (BE (token->type == END_OF_RE, 0)) + { + *err = REG_BADPAT; + goto parse_bracket_exp_free_return; + } + } + + /* We treat the first ']' as a normal character. */ + if (token->type == OP_CLOSE_BRACKET) + token->type = CHARACTER; + + while (1) + { + bracket_elem_t start_elem, end_elem; + unsigned char start_name_buf[BRACKET_NAME_BUF_SIZE]; + unsigned char end_name_buf[BRACKET_NAME_BUF_SIZE]; + reg_errcode_t ret; + int token_len2 = 0, is_range_exp = 0; + re_token_t token2; + + start_elem.opr.name = start_name_buf; + ret = parse_bracket_element (&start_elem, regexp, token, token_len, dfa, + syntax, first_round); + if (BE (ret != REG_NOERROR, 0)) + { + *err = ret; + goto parse_bracket_exp_free_return; + } + first_round = 0; + + /* Get information about the next token. We need it in any case. */ + token_len = peek_token_bracket (token, regexp, syntax); + + /* Do not check for ranges if we know they are not allowed. */ + if (start_elem.type != CHAR_CLASS && start_elem.type != EQUIV_CLASS) + { + if (BE (token->type == END_OF_RE, 0)) + { + *err = REG_EBRACK; + goto parse_bracket_exp_free_return; + } + if (token->type == OP_CHARSET_RANGE) + { + re_string_skip_bytes (regexp, token_len); /* Skip '-'. */ + token_len2 = peek_token_bracket (&token2, regexp, syntax); + if (BE (token2.type == END_OF_RE, 0)) + { + *err = REG_EBRACK; + goto parse_bracket_exp_free_return; + } + if (token2.type == OP_CLOSE_BRACKET) + { + /* We treat the last '-' as a normal character. */ + re_string_skip_bytes (regexp, -token_len); + token->type = CHARACTER; + } + else + is_range_exp = 1; + } + } + + if (is_range_exp == 1) + { + end_elem.opr.name = end_name_buf; + ret = parse_bracket_element (&end_elem, regexp, &token2, token_len2, + dfa, syntax, 1); + if (BE (ret != REG_NOERROR, 0)) + { + *err = ret; + goto parse_bracket_exp_free_return; + } + + token_len = peek_token_bracket (token, regexp, syntax); + +#ifdef _LIBC + *err = build_range_exp (sbcset, mbcset, &range_alloc, + &start_elem, &end_elem); +#else +# ifdef RE_ENABLE_I18N + *err = build_range_exp (sbcset, + dfa->mb_cur_max > 1 ? mbcset : NULL, + &range_alloc, &start_elem, &end_elem); +# else + *err = build_range_exp (sbcset, &start_elem, &end_elem); +# endif +#endif /* RE_ENABLE_I18N */ + if (BE (*err != REG_NOERROR, 0)) + goto parse_bracket_exp_free_return; + } + else + { + switch (start_elem.type) + { + case SB_CHAR: + bitset_set (sbcset, start_elem.opr.ch); + break; +#ifdef RE_ENABLE_I18N + case MB_CHAR: + /* Check whether the array has enough space. */ + if (BE (mbchar_alloc == mbcset->nmbchars, 0)) + { + wchar_t *new_mbchars; + /* Not enough, realloc it. */ + /* +1 in case of mbcset->nmbchars is 0. */ + mbchar_alloc = 2 * mbcset->nmbchars + 1; + /* Use realloc since array is NULL if *alloc == 0. */ + new_mbchars = re_realloc (mbcset->mbchars, wchar_t, + mbchar_alloc); + if (BE (new_mbchars == NULL, 0)) + goto parse_bracket_exp_espace; + mbcset->mbchars = new_mbchars; + } + mbcset->mbchars[mbcset->nmbchars++] = start_elem.opr.wch; + break; +#endif /* RE_ENABLE_I18N */ + case EQUIV_CLASS: + *err = build_equiv_class (sbcset, +#ifdef RE_ENABLE_I18N + mbcset, &equiv_class_alloc, +#endif /* RE_ENABLE_I18N */ + start_elem.opr.name); + if (BE (*err != REG_NOERROR, 0)) + goto parse_bracket_exp_free_return; + break; + case COLL_SYM: + *err = build_collating_symbol (sbcset, +#ifdef RE_ENABLE_I18N + mbcset, &coll_sym_alloc, +#endif /* RE_ENABLE_I18N */ + start_elem.opr.name); + if (BE (*err != REG_NOERROR, 0)) + goto parse_bracket_exp_free_return; + break; + case CHAR_CLASS: + *err = build_charclass (regexp->trans, sbcset, +#ifdef RE_ENABLE_I18N + mbcset, &char_class_alloc, +#endif /* RE_ENABLE_I18N */ + start_elem.opr.name, syntax); + if (BE (*err != REG_NOERROR, 0)) + goto parse_bracket_exp_free_return; + break; + default: + assert (0); + break; + } + } + if (BE (token->type == END_OF_RE, 0)) + { + *err = REG_EBRACK; + goto parse_bracket_exp_free_return; + } + if (token->type == OP_CLOSE_BRACKET) + break; + } + + re_string_skip_bytes (regexp, token_len); /* Skip a token. */ + + /* If it is non-matching list. */ + if (non_match) + bitset_not (sbcset); + +#ifdef RE_ENABLE_I18N + /* Ensure only single byte characters are set. */ + if (dfa->mb_cur_max > 1) + bitset_mask (sbcset, dfa->sb_char); + + if (mbcset->nmbchars || mbcset->ncoll_syms || mbcset->nequiv_classes + || mbcset->nranges || (dfa->mb_cur_max > 1 && (mbcset->nchar_classes + || mbcset->non_match))) + { + bin_tree_t *mbc_tree; + int sbc_idx; + /* Build a tree for complex bracket. */ + dfa->has_mb_node = 1; + br_token.type = COMPLEX_BRACKET; + br_token.opr.mbcset = mbcset; + mbc_tree = create_token_tree (dfa, NULL, NULL, &br_token); + if (BE (mbc_tree == NULL, 0)) + goto parse_bracket_exp_espace; + for (sbc_idx = 0; sbc_idx < BITSET_WORDS; ++sbc_idx) + if (sbcset[sbc_idx]) + break; + /* If there are no bits set in sbcset, there is no point + of having both SIMPLE_BRACKET and COMPLEX_BRACKET. */ + if (sbc_idx < BITSET_WORDS) + { + /* Build a tree for simple bracket. */ + br_token.type = SIMPLE_BRACKET; + br_token.opr.sbcset = sbcset; + work_tree = create_token_tree (dfa, NULL, NULL, &br_token); + if (BE (work_tree == NULL, 0)) + goto parse_bracket_exp_espace; + + /* Then join them by ALT node. */ + work_tree = create_tree (dfa, work_tree, mbc_tree, OP_ALT); + if (BE (work_tree == NULL, 0)) + goto parse_bracket_exp_espace; + } + else + { + re_free (sbcset); + work_tree = mbc_tree; + } + } + else +#endif /* not RE_ENABLE_I18N */ + { +#ifdef RE_ENABLE_I18N + free_charset (mbcset); +#endif + /* Build a tree for simple bracket. */ + br_token.type = SIMPLE_BRACKET; + br_token.opr.sbcset = sbcset; + work_tree = create_token_tree (dfa, NULL, NULL, &br_token); + if (BE (work_tree == NULL, 0)) + goto parse_bracket_exp_espace; + } + return work_tree; + + parse_bracket_exp_espace: + *err = REG_ESPACE; + parse_bracket_exp_free_return: + re_free (sbcset); +#ifdef RE_ENABLE_I18N + free_charset (mbcset); +#endif /* RE_ENABLE_I18N */ + return NULL; +} + +/* Parse an element in the bracket expression. */ + +static reg_errcode_t +parse_bracket_element (bracket_elem_t *elem, re_string_t *regexp, + re_token_t *token, int token_len, re_dfa_t *dfa, + reg_syntax_t syntax, int accept_hyphen) +{ +#ifdef RE_ENABLE_I18N + int cur_char_size; + cur_char_size = re_string_char_size_at (regexp, re_string_cur_idx (regexp)); + if (cur_char_size > 1) + { + elem->type = MB_CHAR; + elem->opr.wch = re_string_wchar_at (regexp, re_string_cur_idx (regexp)); + re_string_skip_bytes (regexp, cur_char_size); + return REG_NOERROR; + } +#endif /* RE_ENABLE_I18N */ + re_string_skip_bytes (regexp, token_len); /* Skip a token. */ + if (token->type == OP_OPEN_COLL_ELEM || token->type == OP_OPEN_CHAR_CLASS + || token->type == OP_OPEN_EQUIV_CLASS) + return parse_bracket_symbol (elem, regexp, token); + if (BE (token->type == OP_CHARSET_RANGE, 0) && !accept_hyphen) + { + /* A '-' must only appear as anything but a range indicator before + the closing bracket. Everything else is an error. */ + re_token_t token2; + (void) peek_token_bracket (&token2, regexp, syntax); + if (token2.type != OP_CLOSE_BRACKET) + /* The actual error value is not standardized since this whole + case is undefined. But ERANGE makes good sense. */ + return REG_ERANGE; + } + elem->type = SB_CHAR; + elem->opr.ch = token->opr.c; + return REG_NOERROR; +} + +/* Parse a bracket symbol in the bracket expression. Bracket symbols are + such as [::], [..], and + [==]. */ + +static reg_errcode_t +parse_bracket_symbol (bracket_elem_t *elem, re_string_t *regexp, + re_token_t *token) +{ + unsigned char ch, delim = token->opr.c; + int i = 0; + if (re_string_eoi(regexp)) + return REG_EBRACK; + for (;; ++i) + { + if (i >= BRACKET_NAME_BUF_SIZE) + return REG_EBRACK; + if (token->type == OP_OPEN_CHAR_CLASS) + ch = re_string_fetch_byte_case (regexp); + else + ch = re_string_fetch_byte (regexp); + if (re_string_eoi(regexp)) + return REG_EBRACK; + if (ch == delim && re_string_peek_byte (regexp, 0) == ']') + break; + elem->opr.name[i] = ch; + } + re_string_skip_bytes (regexp, 1); + elem->opr.name[i] = '\0'; + switch (token->type) + { + case OP_OPEN_COLL_ELEM: + elem->type = COLL_SYM; + break; + case OP_OPEN_EQUIV_CLASS: + elem->type = EQUIV_CLASS; + break; + case OP_OPEN_CHAR_CLASS: + elem->type = CHAR_CLASS; + break; + default: + break; + } + return REG_NOERROR; +} + + /* Helper function for parse_bracket_exp. + Build the equivalence class which is represented by NAME. + The result are written to MBCSET and SBCSET. + EQUIV_CLASS_ALLOC is the allocated size of mbcset->equiv_classes, + is a pointer argument sinse we may update it. */ + +static reg_errcode_t +#ifdef RE_ENABLE_I18N +build_equiv_class (bitset_t sbcset, re_charset_t *mbcset, + int *equiv_class_alloc, const unsigned char *name) +#else /* not RE_ENABLE_I18N */ +build_equiv_class (bitset_t sbcset, const unsigned char *name) +#endif /* not RE_ENABLE_I18N */ +{ +#ifdef _LIBC + uint32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); + if (nrules != 0) + { + const int32_t *table, *indirect; + const unsigned char *weights, *extra, *cp; + unsigned char char_buf[2]; + int32_t idx1, idx2; + unsigned int ch; + size_t len; + /* This #include defines a local function! */ +# include + /* Calculate the index for equivalence class. */ + cp = name; + table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); + weights = (const unsigned char *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_WEIGHTMB); + extra = (const unsigned char *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_EXTRAMB); + indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_INDIRECTMB); + idx1 = findidx (&cp); + if (BE (idx1 == 0 || cp < name + strlen ((const char *) name), 0)) + /* This isn't a valid character. */ + return REG_ECOLLATE; + + /* Build single byte matcing table for this equivalence class. */ + char_buf[1] = (unsigned char) '\0'; + len = weights[idx1]; + for (ch = 0; ch < SBC_MAX; ++ch) + { + char_buf[0] = ch; + cp = char_buf; + idx2 = findidx (&cp); +/* + idx2 = table[ch]; +*/ + if (idx2 == 0) + /* This isn't a valid character. */ + continue; + if (len == weights[idx2]) + { + int cnt = 0; + while (cnt <= len && + weights[idx1 + 1 + cnt] == weights[idx2 + 1 + cnt]) + ++cnt; + + if (cnt > len) + bitset_set (sbcset, ch); + } + } + /* Check whether the array has enough space. */ + if (BE (*equiv_class_alloc == mbcset->nequiv_classes, 0)) + { + /* Not enough, realloc it. */ + /* +1 in case of mbcset->nequiv_classes is 0. */ + int new_equiv_class_alloc = 2 * mbcset->nequiv_classes + 1; + /* Use realloc since the array is NULL if *alloc == 0. */ + int32_t *new_equiv_classes = re_realloc (mbcset->equiv_classes, + int32_t, + new_equiv_class_alloc); + if (BE (new_equiv_classes == NULL, 0)) + return REG_ESPACE; + mbcset->equiv_classes = new_equiv_classes; + *equiv_class_alloc = new_equiv_class_alloc; + } + mbcset->equiv_classes[mbcset->nequiv_classes++] = idx1; + } + else +#endif /* _LIBC */ + { + if (BE (strlen ((const char *) name) != 1, 0)) + return REG_ECOLLATE; + bitset_set (sbcset, *name); + } + return REG_NOERROR; +} + + /* Helper function for parse_bracket_exp. + Build the character class which is represented by NAME. + The result are written to MBCSET and SBCSET. + CHAR_CLASS_ALLOC is the allocated size of mbcset->char_classes, + is a pointer argument sinse we may update it. */ + +static reg_errcode_t +#ifdef RE_ENABLE_I18N +build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset, + re_charset_t *mbcset, int *char_class_alloc, + const unsigned char *class_name, reg_syntax_t syntax) +#else /* not RE_ENABLE_I18N */ +build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset, + const unsigned char *class_name, reg_syntax_t syntax) +#endif /* not RE_ENABLE_I18N */ +{ + int i; + const char *name = (const char *) class_name; + + /* In case of REG_ICASE "upper" and "lower" match the both of + upper and lower cases. */ + if ((syntax & RE_ICASE) + && (strcmp (name, "upper") == 0 || strcmp (name, "lower") == 0)) + name = "alpha"; + +#ifdef RE_ENABLE_I18N + /* Check the space of the arrays. */ + if (BE (*char_class_alloc == mbcset->nchar_classes, 0)) + { + /* Not enough, realloc it. */ + /* +1 in case of mbcset->nchar_classes is 0. */ + int new_char_class_alloc = 2 * mbcset->nchar_classes + 1; + /* Use realloc since array is NULL if *alloc == 0. */ + wctype_t *new_char_classes = re_realloc (mbcset->char_classes, wctype_t, + new_char_class_alloc); + if (BE (new_char_classes == NULL, 0)) + return REG_ESPACE; + mbcset->char_classes = new_char_classes; + *char_class_alloc = new_char_class_alloc; + } + mbcset->char_classes[mbcset->nchar_classes++] = __wctype (name); +#endif /* RE_ENABLE_I18N */ + +#define BUILD_CHARCLASS_LOOP(ctype_func) \ + do { \ + if (BE (trans != NULL, 0)) \ + { \ + for (i = 0; i < SBC_MAX; ++i) \ + if (ctype_func (i)) \ + bitset_set (sbcset, trans[i]); \ + } \ + else \ + { \ + for (i = 0; i < SBC_MAX; ++i) \ + if (ctype_func (i)) \ + bitset_set (sbcset, i); \ + } \ + } while (0) + + if (strcmp (name, "alnum") == 0) + BUILD_CHARCLASS_LOOP (isalnum); + else if (strcmp (name, "cntrl") == 0) + BUILD_CHARCLASS_LOOP (iscntrl); + else if (strcmp (name, "lower") == 0) + BUILD_CHARCLASS_LOOP (islower); + else if (strcmp (name, "space") == 0) + BUILD_CHARCLASS_LOOP (isspace); + else if (strcmp (name, "alpha") == 0) + BUILD_CHARCLASS_LOOP (isalpha); + else if (strcmp (name, "digit") == 0) + BUILD_CHARCLASS_LOOP (isdigit); + else if (strcmp (name, "print") == 0) + BUILD_CHARCLASS_LOOP (isprint); + else if (strcmp (name, "upper") == 0) + BUILD_CHARCLASS_LOOP (isupper); + else if (strcmp (name, "blank") == 0) + BUILD_CHARCLASS_LOOP (isblank); + else if (strcmp (name, "graph") == 0) + BUILD_CHARCLASS_LOOP (isgraph); + else if (strcmp (name, "punct") == 0) + BUILD_CHARCLASS_LOOP (ispunct); + else if (strcmp (name, "xdigit") == 0) + BUILD_CHARCLASS_LOOP (isxdigit); + else + return REG_ECTYPE; + + return REG_NOERROR; +} + +static bin_tree_t * +build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans, + const unsigned char *class_name, + const unsigned char *extra, int non_match, + reg_errcode_t *err) +{ + re_bitset_ptr_t sbcset; +#ifdef RE_ENABLE_I18N + re_charset_t *mbcset; + int alloc = 0; +#endif /* not RE_ENABLE_I18N */ + reg_errcode_t ret; + re_token_t br_token; + bin_tree_t *tree; + + sbcset = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); +#ifdef RE_ENABLE_I18N + mbcset = (re_charset_t *) calloc (sizeof (re_charset_t), 1); +#endif /* RE_ENABLE_I18N */ + +#ifdef RE_ENABLE_I18N + if (BE (sbcset == NULL || mbcset == NULL, 0)) +#else /* not RE_ENABLE_I18N */ + if (BE (sbcset == NULL, 0)) +#endif /* not RE_ENABLE_I18N */ + { + *err = REG_ESPACE; + return NULL; + } + + if (non_match) + { +#ifdef RE_ENABLE_I18N + /* + if (syntax & RE_HAT_LISTS_NOT_NEWLINE) + bitset_set(cset->sbcset, '\0'); + */ + mbcset->non_match = 1; +#endif /* not RE_ENABLE_I18N */ + } + + /* We don't care the syntax in this case. */ + ret = build_charclass (trans, sbcset, +#ifdef RE_ENABLE_I18N + mbcset, &alloc, +#endif /* RE_ENABLE_I18N */ + class_name, 0); + + if (BE (ret != REG_NOERROR, 0)) + { + re_free (sbcset); +#ifdef RE_ENABLE_I18N + free_charset (mbcset); +#endif /* RE_ENABLE_I18N */ + *err = ret; + return NULL; + } + /* \w match '_' also. */ + for (; *extra; extra++) + bitset_set (sbcset, *extra); + + /* If it is non-matching list. */ + if (non_match) + bitset_not (sbcset); + +#ifdef RE_ENABLE_I18N + /* Ensure only single byte characters are set. */ + if (dfa->mb_cur_max > 1) + bitset_mask (sbcset, dfa->sb_char); +#endif + + /* Build a tree for simple bracket. */ + br_token.type = SIMPLE_BRACKET; + br_token.opr.sbcset = sbcset; + tree = create_token_tree (dfa, NULL, NULL, &br_token); + if (BE (tree == NULL, 0)) + goto build_word_op_espace; + +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + { + bin_tree_t *mbc_tree; + /* Build a tree for complex bracket. */ + br_token.type = COMPLEX_BRACKET; + br_token.opr.mbcset = mbcset; + dfa->has_mb_node = 1; + mbc_tree = create_token_tree (dfa, NULL, NULL, &br_token); + if (BE (mbc_tree == NULL, 0)) + goto build_word_op_espace; + /* Then join them by ALT node. */ + tree = create_tree (dfa, tree, mbc_tree, OP_ALT); + if (BE (mbc_tree != NULL, 1)) + return tree; + } + else + { + free_charset (mbcset); + return tree; + } +#else /* not RE_ENABLE_I18N */ + return tree; +#endif /* not RE_ENABLE_I18N */ + + build_word_op_espace: + re_free (sbcset); +#ifdef RE_ENABLE_I18N + free_charset (mbcset); +#endif /* RE_ENABLE_I18N */ + *err = REG_ESPACE; + return NULL; +} + +/* This is intended for the expressions like "a{1,3}". + Fetch a number from `input', and return the number. + Return -1, if the number field is empty like "{,1}". + Return -2, If an error is occured. */ + +static int +fetch_number (re_string_t *input, re_token_t *token, reg_syntax_t syntax) +{ + int num = -1; + unsigned char c; + while (1) + { + fetch_token (token, input, syntax); + c = token->opr.c; + if (BE (token->type == END_OF_RE, 0)) + return -2; + if (token->type == OP_CLOSE_DUP_NUM || c == ',') + break; + num = ((token->type != CHARACTER || c < '0' || '9' < c || num == -2) + ? -2 : ((num == -1) ? c - '0' : num * 10 + c - '0')); + num = (num > RE_DUP_MAX) ? -2 : num; + } + return num; +} + +#ifdef RE_ENABLE_I18N +static void +free_charset (re_charset_t *cset) +{ + re_free (cset->mbchars); +# ifdef _LIBC + re_free (cset->coll_syms); + re_free (cset->equiv_classes); + re_free (cset->range_starts); + re_free (cset->range_ends); +# endif + re_free (cset->char_classes); + re_free (cset); +} +#endif /* RE_ENABLE_I18N */ + +/* Functions for binary tree operation. */ + +/* Create a tree node. */ + +static bin_tree_t * +create_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right, + re_token_type_t type) +{ + re_token_t t; + t.type = type; + return create_token_tree (dfa, left, right, &t); +} + +static bin_tree_t * +create_token_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right, + const re_token_t *token) +{ + bin_tree_t *tree; + if (BE (dfa->str_tree_storage_idx == BIN_TREE_STORAGE_SIZE, 0)) + { + bin_tree_storage_t *storage = re_malloc (bin_tree_storage_t, 1); + + if (storage == NULL) + return NULL; + storage->next = dfa->str_tree_storage; + dfa->str_tree_storage = storage; + dfa->str_tree_storage_idx = 0; + } + tree = &dfa->str_tree_storage->data[dfa->str_tree_storage_idx++]; + + tree->parent = NULL; + tree->left = left; + tree->right = right; + tree->token = *token; + tree->token.duplicated = 0; + tree->token.opt_subexp = 0; + tree->first = NULL; + tree->next = NULL; + tree->node_idx = -1; + + if (left != NULL) + left->parent = tree; + if (right != NULL) + right->parent = tree; + return tree; +} + +/* Mark the tree SRC as an optional subexpression. + To be called from preorder or postorder. */ + +static reg_errcode_t +mark_opt_subexp (void *extra, bin_tree_t *node) +{ + int idx = (int) (long) extra; + if (node->token.type == SUBEXP && node->token.opr.idx == idx) + node->token.opt_subexp = 1; + + return REG_NOERROR; +} + +/* Free the allocated memory inside NODE. */ + +static void +free_token (re_token_t *node) +{ +#ifdef RE_ENABLE_I18N + if (node->type == COMPLEX_BRACKET && node->duplicated == 0) + free_charset (node->opr.mbcset); + else +#endif /* RE_ENABLE_I18N */ + if (node->type == SIMPLE_BRACKET && node->duplicated == 0) + re_free (node->opr.sbcset); +} + +/* Worker function for tree walking. Free the allocated memory inside NODE + and its children. */ + +static reg_errcode_t +free_tree (void *extra, bin_tree_t *node) +{ + free_token (&node->token); + return REG_NOERROR; +} + + +/* Duplicate the node SRC, and return new node. This is a preorder + visit similar to the one implemented by the generic visitor, but + we need more infrastructure to maintain two parallel trees --- so, + it's easier to duplicate. */ + +static bin_tree_t * +duplicate_tree (const bin_tree_t *root, re_dfa_t *dfa) +{ + const bin_tree_t *node; + bin_tree_t *dup_root; + bin_tree_t **p_new = &dup_root, *dup_node = root->parent; + + for (node = root; ; ) + { + /* Create a new tree and link it back to the current parent. */ + *p_new = create_token_tree (dfa, NULL, NULL, &node->token); + if (*p_new == NULL) + return NULL; + (*p_new)->parent = dup_node; + (*p_new)->token.duplicated = 1; + dup_node = *p_new; + + /* Go to the left node, or up and to the right. */ + if (node->left) + { + node = node->left; + p_new = &dup_node->left; + } + else + { + const bin_tree_t *prev = NULL; + while (node->right == prev || node->right == NULL) + { + prev = node; + node = node->parent; + dup_node = dup_node->parent; + if (!node) + return dup_root; + } + node = node->right; + p_new = &dup_node->right; + } + } +} diff --git a/Build/source/texk/chktex/regex/regex.c b/Build/source/texk/chktex/regex/regex.c new file mode 100644 index 00000000000..d816df97794 --- /dev/null +++ b/Build/source/texk/chktex/regex/regex.c @@ -0,0 +1,31 @@ +/* Extended regular expression matching and search library. + Copyright (C) 2002, 2003, 2005 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Isamu Hasegawa . + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +/* On some systems, limits.h sets RE_DUP_MAX to a lower value than + GNU regex allows. Include it before , which correctly + #undefs RE_DUP_MAX and sets it to the right value. */ +#include + +#include +#include + +#include +#include +#include diff --git a/Build/source/texk/chktex/regex/regex.h b/Build/source/texk/chktex/regex/regex.h new file mode 100644 index 00000000000..807c404ec24 --- /dev/null +++ b/Build/source/texk/chktex/regex/regex.h @@ -0,0 +1,556 @@ +/* Definitions for data structures and routines for the regular + expression library. + Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005,2006 + Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#ifndef _REGEX_H +#define _REGEX_H 1 + +#include + +/* Allow the use in C++ code. */ +#ifdef __cplusplus +extern "C" { +#endif + +/* The following two types have to be signed and unsigned integer type + wide enough to hold a value of a pointer. For most ANSI compilers + ptrdiff_t and size_t should be likely OK. Still size of these two + types is 2 for Microsoft C. Ugh... */ +typedef long int s_reg_t; +typedef unsigned long int active_reg_t; + +/* The following bits are used to determine the regexp syntax we + recognize. The set/not-set meanings are chosen so that Emacs syntax + remains the value 0. The bits are given in alphabetical order, and + the definitions shifted by one from the previous bit; thus, when we + add or remove a bit, only one other definition need change. */ +typedef unsigned long int reg_syntax_t; + +/* If this bit is not set, then \ inside a bracket expression is literal. + If set, then such a \ quotes the following character. */ +#define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1) + +/* If this bit is not set, then + and ? are operators, and \+ and \? are + literals. + If set, then \+ and \? are operators and + and ? are literals. */ +#define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1) + +/* If this bit is set, then character classes are supported. They are: + [:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:], + [:space:], [:print:], [:punct:], [:graph:], and [:cntrl:]. + If not set, then character classes are not supported. */ +#define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1) + +/* If this bit is set, then ^ and $ are always anchors (outside bracket + expressions, of course). + If this bit is not set, then it depends: + ^ is an anchor if it is at the beginning of a regular + expression or after an open-group or an alternation operator; + $ is an anchor if it is at the end of a regular expression, or + before a close-group or an alternation operator. + + This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because + POSIX draft 11.2 says that * etc. in leading positions is undefined. + We already implemented a previous draft which made those constructs + invalid, though, so we haven't changed the code back. */ +#define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1) + +/* If this bit is set, then special characters are always special + regardless of where they are in the pattern. + If this bit is not set, then special characters are special only in + some contexts; otherwise they are ordinary. Specifically, + * + ? and intervals are only special when not after the beginning, + open-group, or alternation operator. */ +#define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1) + +/* If this bit is set, then *, +, ?, and { cannot be first in an re or + immediately after an alternation or begin-group operator. */ +#define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1) + +/* If this bit is set, then . matches newline. + If not set, then it doesn't. */ +#define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1) + +/* If this bit is set, then . doesn't match NUL. + If not set, then it does. */ +#define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1) + +/* If this bit is set, nonmatching lists [^...] do not match newline. + If not set, they do. */ +#define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1) + +/* If this bit is set, either \{...\} or {...} defines an + interval, depending on RE_NO_BK_BRACES. + If not set, \{, \}, {, and } are literals. */ +#define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1) + +/* If this bit is set, +, ? and | aren't recognized as operators. + If not set, they are. */ +#define RE_LIMITED_OPS (RE_INTERVALS << 1) + +/* If this bit is set, newline is an alternation operator. + If not set, newline is literal. */ +#define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1) + +/* If this bit is set, then `{...}' defines an interval, and \{ and \} + are literals. + If not set, then `\{...\}' defines an interval. */ +#define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1) + +/* If this bit is set, (...) defines a group, and \( and \) are literals. + If not set, \(...\) defines a group, and ( and ) are literals. */ +#define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1) + +/* If this bit is set, then \ matches . + If not set, then \ is a back-reference. */ +#define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1) + +/* If this bit is set, then | is an alternation operator, and \| is literal. + If not set, then \| is an alternation operator, and | is literal. */ +#define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1) + +/* If this bit is set, then an ending range point collating higher + than the starting range point, as in [z-a], is invalid. + If not set, then when ending range point collates higher than the + starting range point, the range is ignored. */ +#define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1) + +/* If this bit is set, then an unmatched ) is ordinary. + If not set, then an unmatched ) is invalid. */ +#define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1) + +/* If this bit is set, succeed as soon as we match the whole pattern, + without further backtracking. */ +#define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1) + +/* If this bit is set, do not process the GNU regex operators. + If not set, then the GNU regex operators are recognized. */ +#define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1) + +/* If this bit is set, turn on internal regex debugging. + If not set, and debugging was on, turn it off. + This only works if regex.c is compiled -DDEBUG. + We define this bit always, so that all that's needed to turn on + debugging is to recompile regex.c; the calling code can always have + this bit set, and it won't affect anything in the normal case. */ +#define RE_DEBUG (RE_NO_GNU_OPS << 1) + +/* If this bit is set, a syntactically invalid interval is treated as + a string of ordinary characters. For example, the ERE 'a{1' is + treated as 'a\{1'. */ +#define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1) + +/* If this bit is set, then ignore case when matching. + If not set, then case is significant. */ +#define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1) + +/* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only + for ^, because it is difficult to scan the regex backwards to find + whether ^ should be special. */ +#define RE_CARET_ANCHORS_HERE (RE_ICASE << 1) + +/* If this bit is set, then \{ cannot be first in an bre or + immediately after an alternation or begin-group operator. */ +#define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1) + +/* If this bit is set, then no_sub will be set to 1 during + re_compile_pattern. */ +#define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1) + +/* This global variable defines the particular regexp syntax to use (for + some interfaces). When a regexp is compiled, the syntax used is + stored in the pattern buffer, so changing this does not affect + already-compiled regexps. */ +extern reg_syntax_t re_syntax_options; + +/* Define combinations of the above bits for the standard possibilities. + (The [[[ comments delimit what gets put into the Texinfo file, so + don't delete them!) */ +/* [[[begin syntaxes]]] */ +#define RE_SYNTAX_EMACS 0 + +#define RE_SYNTAX_AWK \ + (RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \ + | RE_NO_BK_PARENS | RE_NO_BK_REFS \ + | RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \ + | RE_DOT_NEWLINE | RE_CONTEXT_INDEP_ANCHORS \ + | RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS) + +#define RE_SYNTAX_GNU_AWK \ + ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DEBUG) \ + & ~(RE_DOT_NOT_NULL | RE_INTERVALS | RE_CONTEXT_INDEP_OPS \ + | RE_CONTEXT_INVALID_OPS )) + +#define RE_SYNTAX_POSIX_AWK \ + (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \ + | RE_INTERVALS | RE_NO_GNU_OPS) + +#define RE_SYNTAX_GREP \ + (RE_BK_PLUS_QM | RE_CHAR_CLASSES \ + | RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \ + | RE_NEWLINE_ALT) + +#define RE_SYNTAX_EGREP \ + (RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \ + | RE_NEWLINE_ALT | RE_NO_BK_PARENS \ + | RE_NO_BK_VBAR) + +#define RE_SYNTAX_POSIX_EGREP \ + (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES \ + | RE_INVALID_INTERVAL_ORD) + +/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */ +#define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC + +#define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC + +/* Syntax bits common to both basic and extended POSIX regex syntax. */ +#define _RE_SYNTAX_POSIX_COMMON \ + (RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \ + | RE_INTERVALS | RE_NO_EMPTY_RANGES) + +#define RE_SYNTAX_POSIX_BASIC \ + (_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM | RE_CONTEXT_INVALID_DUP) + +/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes + RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this + isn't minimal, since other operators, such as \`, aren't disabled. */ +#define RE_SYNTAX_POSIX_MINIMAL_BASIC \ + (_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS) + +#define RE_SYNTAX_POSIX_EXTENDED \ + (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \ + | RE_NO_BK_PARENS | RE_NO_BK_VBAR \ + | RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD) + +/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is + removed and RE_NO_BK_REFS is added. */ +#define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \ + (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \ + | RE_NO_BK_PARENS | RE_NO_BK_REFS \ + | RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD) +/* [[[end syntaxes]]] */ + +/* Maximum number of duplicates an interval can allow. Some systems + (erroneously) define this in other header files, but we want our + value, so remove any previous define. */ +#ifdef RE_DUP_MAX +# undef RE_DUP_MAX +#endif +/* If sizeof(int) == 2, then ((1 << 15) - 1) overflows. */ +#define RE_DUP_MAX (0x7fff) + + +/* POSIX `cflags' bits (i.e., information for `regcomp'). */ + +/* If this bit is set, then use extended regular expression syntax. + If not set, then use basic regular expression syntax. */ +#define REG_EXTENDED 1 + +/* If this bit is set, then ignore case when matching. + If not set, then case is significant. */ +#define REG_ICASE (REG_EXTENDED << 1) + +/* If this bit is set, then anchors do not match at newline + characters in the string. + If not set, then anchors do match at newlines. */ +#define REG_NEWLINE (REG_ICASE << 1) + +/* If this bit is set, then report only success or fail in regexec. + If not set, then returns differ between not matching and errors. */ +#define REG_NOSUB (REG_NEWLINE << 1) + + +/* POSIX `eflags' bits (i.e., information for regexec). */ + +/* If this bit is set, then the beginning-of-line operator doesn't match + the beginning of the string (presumably because it's not the + beginning of a line). + If not set, then the beginning-of-line operator does match the + beginning of the string. */ +#define REG_NOTBOL 1 + +/* Like REG_NOTBOL, except for the end-of-line. */ +#define REG_NOTEOL (1 << 1) + +/* Use PMATCH[0] to delimit the start and end of the search in the + buffer. */ +#define REG_STARTEND (1 << 2) + + +/* If any error codes are removed, changed, or added, update the + `re_error_msg' table in regex.c. */ +typedef enum +{ +#ifdef _XOPEN_SOURCE + REG_ENOSYS = -1, /* This will never happen for this implementation. */ +#endif + + REG_NOERROR = 0, /* Success. */ + REG_NOMATCH, /* Didn't find a match (for regexec). */ + + /* POSIX regcomp return error codes. (In the order listed in the + standard.) */ + REG_BADPAT, /* Invalid pattern. */ + REG_ECOLLATE, /* Inalid collating element. */ + REG_ECTYPE, /* Invalid character class name. */ + REG_EESCAPE, /* Trailing backslash. */ + REG_ESUBREG, /* Invalid back reference. */ + REG_EBRACK, /* Unmatched left bracket. */ + REG_EPAREN, /* Parenthesis imbalance. */ + REG_EBRACE, /* Unmatched \{. */ + REG_BADBR, /* Invalid contents of \{\}. */ + REG_ERANGE, /* Invalid range end. */ + REG_ESPACE, /* Ran out of memory. */ + REG_BADRPT, /* No preceding re for repetition op. */ + + /* Error codes we've added. */ + REG_EEND, /* Premature end. */ + REG_ESIZE, /* Compiled pattern bigger than 2^16 bytes. */ + REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */ +} reg_errcode_t; + +/* This data structure represents a compiled pattern. Before calling + the pattern compiler, the fields `buffer', `allocated', `fastmap', + `translate', and `no_sub' can be set. After the pattern has been + compiled, the `re_nsub' field is available. All other fields are + private to the regex routines. */ + +#ifndef RE_TRANSLATE_TYPE +# define RE_TRANSLATE_TYPE unsigned char * +#endif + +struct re_pattern_buffer +{ + /* Space that holds the compiled pattern. It is declared as + `unsigned char *' because its elements are sometimes used as + array indexes. */ + unsigned char *buffer; + + /* Number of bytes to which `buffer' points. */ + unsigned long int allocated; + + /* Number of bytes actually used in `buffer'. */ + unsigned long int used; + + /* Syntax setting with which the pattern was compiled. */ + reg_syntax_t syntax; + + /* Pointer to a fastmap, if any, otherwise zero. re_search uses the + fastmap, if there is one, to skip over impossible starting points + for matches. */ + char *fastmap; + + /* Either a translate table to apply to all characters before + comparing them, or zero for no translation. The translation is + applied to a pattern when it is compiled and to a string when it + is matched. */ + RE_TRANSLATE_TYPE translate; + + /* Number of subexpressions found by the compiler. */ + size_t re_nsub; + + /* Zero if this pattern cannot match the empty string, one else. + Well, in truth it's used only in `re_search_2', to see whether or + not we should use the fastmap, so we don't set this absolutely + perfectly; see `re_compile_fastmap' (the `duplicate' case). */ + unsigned can_be_null : 1; + + /* If REGS_UNALLOCATED, allocate space in the `regs' structure + for `max (RE_NREGS, re_nsub + 1)' groups. + If REGS_REALLOCATE, reallocate space if necessary. + If REGS_FIXED, use what's there. */ +#define REGS_UNALLOCATED 0 +#define REGS_REALLOCATE 1 +#define REGS_FIXED 2 + unsigned regs_allocated : 2; + + /* Set to zero when `regex_compile' compiles a pattern; set to one + by `re_compile_fastmap' if it updates the fastmap. */ + unsigned fastmap_accurate : 1; + + /* If set, `re_match_2' does not return information about + subexpressions. */ + unsigned no_sub : 1; + + /* If set, a beginning-of-line anchor doesn't match at the beginning + of the string. */ + unsigned not_bol : 1; + + /* Similarly for an end-of-line anchor. */ + unsigned not_eol : 1; + + /* If true, an anchor at a newline matches. */ + unsigned newline_anchor : 1; +}; + +typedef struct re_pattern_buffer regex_t; + +/* Type for byte offsets within the string. POSIX mandates this. */ +typedef int regoff_t; + + +/* This is the structure we store register match data in. See + regex.texinfo for a full description of what registers match. */ +struct re_registers +{ + unsigned num_regs; + regoff_t *start; + regoff_t *end; +}; + + +/* If `regs_allocated' is REGS_UNALLOCATED in the pattern buffer, + `re_match_2' returns information about at least this many registers + the first time a `regs' structure is passed. */ +#ifndef RE_NREGS +# define RE_NREGS 30 +#endif + + +/* POSIX specification for registers. Aside from the different names than + `re_registers', POSIX uses an array of structures, instead of a + structure of arrays. */ +typedef struct +{ + regoff_t rm_so; /* Byte offset from string's start to substring's start. */ + regoff_t rm_eo; /* Byte offset from string's start to substring's end. */ +} regmatch_t; + +/* Declarations for routines. */ + +/* Sets the current default syntax to SYNTAX, and return the old syntax. + You can also simply assign to the `re_syntax_options' variable. */ +extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax); + +/* Compile the regular expression PATTERN, with length LENGTH + and syntax given by the global `re_syntax_options', into the buffer + BUFFER. Return NULL if successful, and an error string if not. */ +extern const char *re_compile_pattern (const char *__pattern, size_t __length, + struct re_pattern_buffer *__buffer); + + +/* Compile a fastmap for the compiled pattern in BUFFER; used to + accelerate searches. Return 0 if successful and -2 if was an + internal error. */ +extern int re_compile_fastmap (struct re_pattern_buffer *__buffer); + + +/* Search in the string STRING (with length LENGTH) for the pattern + compiled into BUFFER. Start searching at position START, for RANGE + characters. Return the starting position of the match, -1 for no + match, or -2 for an internal error. Also return register + information in REGS (if REGS and BUFFER->no_sub are nonzero). */ +extern int re_search (struct re_pattern_buffer *__buffer, const char *__string, + int __length, int __start, int __range, + struct re_registers *__regs); + + +/* Like `re_search', but search in the concatenation of STRING1 and + STRING2. Also, stop searching at index START + STOP. */ +extern int re_search_2 (struct re_pattern_buffer *__buffer, + const char *__string1, int __length1, + const char *__string2, int __length2, int __start, + int __range, struct re_registers *__regs, int __stop); + + +/* Like `re_search', but return how many characters in STRING the regexp + in BUFFER matched, starting at position START. */ +extern int re_match (struct re_pattern_buffer *__buffer, const char *__string, + int __length, int __start, struct re_registers *__regs); + + +/* Relates to `re_match' as `re_search_2' relates to `re_search'. */ +extern int re_match_2 (struct re_pattern_buffer *__buffer, + const char *__string1, int __length1, + const char *__string2, int __length2, int __start, + struct re_registers *__regs, int __stop); + + +/* Set REGS to hold NUM_REGS registers, storing them in STARTS and + ENDS. Subsequent matches using BUFFER and REGS will use this memory + for recording register information. STARTS and ENDS must be + allocated with malloc, and must each be at least `NUM_REGS * sizeof + (regoff_t)' bytes long. + + If NUM_REGS == 0, then subsequent matches should allocate their own + register data. + + Unless this function is called, the first search or match using + PATTERN_BUFFER will allocate its own register data, without + freeing the old data. */ +extern void re_set_registers (struct re_pattern_buffer *__buffer, + struct re_registers *__regs, + unsigned int __num_regs, + regoff_t *__starts, regoff_t *__ends); + +#if defined _REGEX_RE_COMP || defined _LIBC +# ifndef _CRAY +/* 4.2 bsd compatibility. */ +extern char *re_comp (const char *); +extern int re_exec (const char *); +# endif +#endif + +/* GCC 2.95 and later have "__restrict"; C99 compilers have + "restrict", and "configure" may have defined "restrict". */ +#ifndef __restrict +# if ! (2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)) +# if defined restrict || 199901L <= __STDC_VERSION__ +# define __restrict restrict +# else +# define __restrict +# endif +# endif +#endif +/* gcc 3.1 and up support the [restrict] syntax. */ +#ifndef __restrict_arr +# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) \ + && !defined __GNUG__ +# define __restrict_arr __restrict +# else +# define __restrict_arr +# endif +#endif + +/* POSIX compatibility. */ +extern int regcomp (regex_t *__restrict __preg, + const char *__restrict __pattern, + int __cflags); + +extern int regexec (const regex_t *__restrict __preg, + const char *__restrict __string, size_t __nmatch, + regmatch_t __pmatch[__restrict_arr], + int __eflags); + +extern size_t regerror (int __errcode, const regex_t *__restrict __preg, + char *__restrict __errbuf, size_t __errbuf_size); + +extern void regfree (regex_t *__preg); + + +#ifdef __cplusplus +} +#endif /* C++ */ + +#endif /* regex.h */ diff --git a/Build/source/texk/chktex/regex/regex_internal.c b/Build/source/texk/chktex/regex/regex_internal.c new file mode 100644 index 00000000000..66154e0ceac --- /dev/null +++ b/Build/source/texk/chktex/regex/regex_internal.c @@ -0,0 +1,1717 @@ +/* Extended regular expression matching and search library. + Copyright (C) 2002, 2003, 2004, 2005, 2006 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Isamu Hasegawa . + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +static void re_string_construct_common (const char *str, int len, + re_string_t *pstr, + RE_TRANSLATE_TYPE trans, int icase, + const re_dfa_t *dfa) internal_function; +static re_dfastate_t *create_ci_newstate (const re_dfa_t *dfa, + const re_node_set *nodes, + unsigned int hash) internal_function; +static re_dfastate_t *create_cd_newstate (const re_dfa_t *dfa, + const re_node_set *nodes, + unsigned int context, + unsigned int hash) internal_function; + +/* Functions for string operation. */ + +/* This function allocate the buffers. It is necessary to call + re_string_reconstruct before using the object. */ + +static reg_errcode_t +internal_function +re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len, + RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) +{ + reg_errcode_t ret; + int init_buf_len; + + /* Ensure at least one character fits into the buffers. */ + if (init_len < dfa->mb_cur_max) + init_len = dfa->mb_cur_max; + init_buf_len = (len + 1 < init_len) ? len + 1: init_len; + re_string_construct_common (str, len, pstr, trans, icase, dfa); + + ret = re_string_realloc_buffers (pstr, init_buf_len); + if (BE (ret != REG_NOERROR, 0)) + return ret; + + pstr->word_char = dfa->word_char; + pstr->word_ops_used = dfa->word_ops_used; + pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; + pstr->valid_len = (pstr->mbs_allocated || dfa->mb_cur_max > 1) ? 0 : len; + pstr->valid_raw_len = pstr->valid_len; + return REG_NOERROR; +} + +/* This function allocate the buffers, and initialize them. */ + +static reg_errcode_t +internal_function +re_string_construct (re_string_t *pstr, const char *str, int len, + RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) +{ + reg_errcode_t ret; + memset (pstr, '\0', sizeof (re_string_t)); + re_string_construct_common (str, len, pstr, trans, icase, dfa); + + if (len > 0) + { + ret = re_string_realloc_buffers (pstr, len + 1); + if (BE (ret != REG_NOERROR, 0)) + return ret; + } + pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; + + if (icase) + { +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + { + while (1) + { + ret = build_wcs_upper_buffer (pstr); + if (BE (ret != REG_NOERROR, 0)) + return ret; + if (pstr->valid_raw_len >= len) + break; + if (pstr->bufs_len > pstr->valid_len + dfa->mb_cur_max) + break; + ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2); + if (BE (ret != REG_NOERROR, 0)) + return ret; + } + } + else +#endif /* RE_ENABLE_I18N */ + build_upper_buffer (pstr); + } + else + { +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + build_wcs_buffer (pstr); + else +#endif /* RE_ENABLE_I18N */ + { + if (trans != NULL) + re_string_translate_buffer (pstr); + else + { + pstr->valid_len = pstr->bufs_len; + pstr->valid_raw_len = pstr->bufs_len; + } + } + } + + return REG_NOERROR; +} + +/* Helper functions for re_string_allocate, and re_string_construct. */ + +static reg_errcode_t +internal_function +re_string_realloc_buffers (re_string_t *pstr, int new_buf_len) +{ +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + { + wint_t *new_wcs = re_realloc (pstr->wcs, wint_t, new_buf_len); + if (BE (new_wcs == NULL, 0)) + return REG_ESPACE; + pstr->wcs = new_wcs; + if (pstr->offsets != NULL) + { + int *new_offsets = re_realloc (pstr->offsets, int, new_buf_len); + if (BE (new_offsets == NULL, 0)) + return REG_ESPACE; + pstr->offsets = new_offsets; + } + } +#endif /* RE_ENABLE_I18N */ + if (pstr->mbs_allocated) + { + unsigned char *new_mbs = re_realloc (pstr->mbs, unsigned char, + new_buf_len); + if (BE (new_mbs == NULL, 0)) + return REG_ESPACE; + pstr->mbs = new_mbs; + } + pstr->bufs_len = new_buf_len; + return REG_NOERROR; +} + + +static void +internal_function +re_string_construct_common (const char *str, int len, re_string_t *pstr, + RE_TRANSLATE_TYPE trans, int icase, + const re_dfa_t *dfa) +{ + pstr->raw_mbs = (const unsigned char *) str; + pstr->len = len; + pstr->raw_len = len; + pstr->trans = trans; + pstr->icase = icase ? 1 : 0; + pstr->mbs_allocated = (trans != NULL || icase); + pstr->mb_cur_max = dfa->mb_cur_max; + pstr->is_utf8 = dfa->is_utf8; + pstr->map_notascii = dfa->map_notascii; + pstr->stop = pstr->len; + pstr->raw_stop = pstr->stop; +} + +#ifdef RE_ENABLE_I18N + +/* Build wide character buffer PSTR->WCS. + If the byte sequence of the string are: + (0), (1), (0), (1), + Then wide character buffer will be: + , WEOF , , WEOF , + We use WEOF for padding, they indicate that the position isn't + a first byte of a multibyte character. + + Note that this function assumes PSTR->VALID_LEN elements are already + built and starts from PSTR->VALID_LEN. */ + +static void +internal_function +build_wcs_buffer (re_string_t *pstr) +{ +#ifdef _LIBC + unsigned char buf[MB_LEN_MAX]; + assert (MB_LEN_MAX >= pstr->mb_cur_max); +#else + unsigned char buf[64]; +#endif + mbstate_t prev_st; + int byte_idx, end_idx, remain_len; + size_t mbclen; + + /* Build the buffers from pstr->valid_len to either pstr->len or + pstr->bufs_len. */ + end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; + for (byte_idx = pstr->valid_len; byte_idx < end_idx;) + { + wchar_t wc; + const char *p; + + remain_len = end_idx - byte_idx; + prev_st = pstr->cur_state; + /* Apply the translation if we need. */ + if (BE (pstr->trans != NULL, 0)) + { + int i, ch; + + for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) + { + ch = pstr->raw_mbs [pstr->raw_mbs_idx + byte_idx + i]; + buf[i] = pstr->mbs[byte_idx + i] = pstr->trans[ch]; + } + p = (const char *) buf; + } + else + p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx; + mbclen = mbrtowc (&wc, p, remain_len, &pstr->cur_state); + if (BE (mbclen == (size_t) -2, 0)) + { + /* The buffer doesn't have enough space, finish to build. */ + pstr->cur_state = prev_st; + break; + } + else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0)) + { + /* We treat these cases as a singlebyte character. */ + mbclen = 1; + wc = (wchar_t) pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; + if (BE (pstr->trans != NULL, 0)) + wc = pstr->trans[wc]; + pstr->cur_state = prev_st; + } + + /* Write wide character and padding. */ + pstr->wcs[byte_idx++] = wc; + /* Write paddings. */ + for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) + pstr->wcs[byte_idx++] = WEOF; + } + pstr->valid_len = byte_idx; + pstr->valid_raw_len = byte_idx; +} + +/* Build wide character buffer PSTR->WCS like build_wcs_buffer, + but for REG_ICASE. */ + +static reg_errcode_t +internal_function +build_wcs_upper_buffer (re_string_t *pstr) +{ + mbstate_t prev_st; + int src_idx, byte_idx, end_idx, remain_len; + size_t mbclen; +#ifdef _LIBC + char buf[MB_LEN_MAX]; + assert (MB_LEN_MAX >= pstr->mb_cur_max); +#else + char buf[64]; +#endif + + byte_idx = pstr->valid_len; + end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; + + /* The following optimization assumes that ASCII characters can be + mapped to wide characters with a simple cast. */ + if (! pstr->map_notascii && pstr->trans == NULL && !pstr->offsets_needed) + { + while (byte_idx < end_idx) + { + wchar_t wc; + + if (isascii (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]) + && mbsinit (&pstr->cur_state)) + { + /* In case of a singlebyte character. */ + pstr->mbs[byte_idx] + = toupper (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]); + /* The next step uses the assumption that wchar_t is encoded + ASCII-safe: all ASCII values can be converted like this. */ + pstr->wcs[byte_idx] = (wchar_t) pstr->mbs[byte_idx]; + ++byte_idx; + continue; + } + + remain_len = end_idx - byte_idx; + prev_st = pstr->cur_state; + mbclen = mbrtowc (&wc, + ((const char *) pstr->raw_mbs + pstr->raw_mbs_idx + + byte_idx), remain_len, &pstr->cur_state); + if (BE (mbclen + 2 > 2, 1)) + { + wchar_t wcu = wc; + if (iswlower (wc)) + { + size_t mbcdlen; + + wcu = towupper (wc); + mbcdlen = wcrtomb (buf, wcu, &prev_st); + if (BE (mbclen == mbcdlen, 1)) + memcpy (pstr->mbs + byte_idx, buf, mbclen); + else + { + src_idx = byte_idx; + goto offsets_needed; + } + } + else + memcpy (pstr->mbs + byte_idx, + pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx, mbclen); + pstr->wcs[byte_idx++] = wcu; + /* Write paddings. */ + for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) + pstr->wcs[byte_idx++] = WEOF; + } + else if (mbclen == (size_t) -1 || mbclen == 0) + { + /* It is an invalid character or '\0'. Just use the byte. */ + int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; + pstr->mbs[byte_idx] = ch; + /* And also cast it to wide char. */ + pstr->wcs[byte_idx++] = (wchar_t) ch; + if (BE (mbclen == (size_t) -1, 0)) + pstr->cur_state = prev_st; + } + else + { + /* The buffer doesn't have enough space, finish to build. */ + pstr->cur_state = prev_st; + break; + } + } + pstr->valid_len = byte_idx; + pstr->valid_raw_len = byte_idx; + return REG_NOERROR; + } + else + for (src_idx = pstr->valid_raw_len; byte_idx < end_idx;) + { + wchar_t wc; + const char *p; + offsets_needed: + remain_len = end_idx - byte_idx; + prev_st = pstr->cur_state; + if (BE (pstr->trans != NULL, 0)) + { + int i, ch; + + for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) + { + ch = pstr->raw_mbs [pstr->raw_mbs_idx + src_idx + i]; + buf[i] = pstr->trans[ch]; + } + p = (const char *) buf; + } + else + p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + src_idx; + mbclen = mbrtowc (&wc, p, remain_len, &pstr->cur_state); + if (BE (mbclen + 2 > 2, 1)) + { + wchar_t wcu = wc; + if (iswlower (wc)) + { + size_t mbcdlen; + + wcu = towupper (wc); + mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st); + if (BE (mbclen == mbcdlen, 1)) + memcpy (pstr->mbs + byte_idx, buf, mbclen); + else if (mbcdlen != (size_t) -1) + { + size_t i; + + if (byte_idx + mbcdlen > pstr->bufs_len) + { + pstr->cur_state = prev_st; + break; + } + + if (pstr->offsets == NULL) + { + pstr->offsets = re_malloc (int, pstr->bufs_len); + + if (pstr->offsets == NULL) + return REG_ESPACE; + } + if (!pstr->offsets_needed) + { + for (i = 0; i < (size_t) byte_idx; ++i) + pstr->offsets[i] = i; + pstr->offsets_needed = 1; + } + + memcpy (pstr->mbs + byte_idx, buf, mbcdlen); + pstr->wcs[byte_idx] = wcu; + pstr->offsets[byte_idx] = src_idx; + for (i = 1; i < mbcdlen; ++i) + { + pstr->offsets[byte_idx + i] + = src_idx + (i < mbclen ? i : mbclen - 1); + pstr->wcs[byte_idx + i] = WEOF; + } + pstr->len += mbcdlen - mbclen; + if (pstr->raw_stop > src_idx) + pstr->stop += mbcdlen - mbclen; + end_idx = (pstr->bufs_len > pstr->len) + ? pstr->len : pstr->bufs_len; + byte_idx += mbcdlen; + src_idx += mbclen; + continue; + } + else + memcpy (pstr->mbs + byte_idx, p, mbclen); + } + else + memcpy (pstr->mbs + byte_idx, p, mbclen); + + if (BE (pstr->offsets_needed != 0, 0)) + { + size_t i; + for (i = 0; i < mbclen; ++i) + pstr->offsets[byte_idx + i] = src_idx + i; + } + src_idx += mbclen; + + pstr->wcs[byte_idx++] = wcu; + /* Write paddings. */ + for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) + pstr->wcs[byte_idx++] = WEOF; + } + else if (mbclen == (size_t) -1 || mbclen == 0) + { + /* It is an invalid character or '\0'. Just use the byte. */ + int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx]; + + if (BE (pstr->trans != NULL, 0)) + ch = pstr->trans [ch]; + pstr->mbs[byte_idx] = ch; + + if (BE (pstr->offsets_needed != 0, 0)) + pstr->offsets[byte_idx] = src_idx; + ++src_idx; + + /* And also cast it to wide char. */ + pstr->wcs[byte_idx++] = (wchar_t) ch; + if (BE (mbclen == (size_t) -1, 0)) + pstr->cur_state = prev_st; + } + else + { + /* The buffer doesn't have enough space, finish to build. */ + pstr->cur_state = prev_st; + break; + } + } + pstr->valid_len = byte_idx; + pstr->valid_raw_len = src_idx; + return REG_NOERROR; +} + +/* Skip characters until the index becomes greater than NEW_RAW_IDX. + Return the index. */ + +static int +internal_function +re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc) +{ + mbstate_t prev_st; + int rawbuf_idx; + size_t mbclen; + wchar_t wc = WEOF; + + /* Skip the characters which are not necessary to check. */ + for (rawbuf_idx = pstr->raw_mbs_idx + pstr->valid_raw_len; + rawbuf_idx < new_raw_idx;) + { + int remain_len; + remain_len = pstr->len - rawbuf_idx; + prev_st = pstr->cur_state; + mbclen = mbrtowc (&wc, (const char *) pstr->raw_mbs + rawbuf_idx, + remain_len, &pstr->cur_state); + if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0)) + { + /* We treat these cases as a single byte character. */ + if (mbclen == 0 || remain_len == 0) + wc = L'\0'; + else + wc = *(unsigned char *) (pstr->raw_mbs + rawbuf_idx); + mbclen = 1; + pstr->cur_state = prev_st; + } + /* Then proceed the next character. */ + rawbuf_idx += mbclen; + } + *last_wc = (wint_t) wc; + return rawbuf_idx; +} +#endif /* RE_ENABLE_I18N */ + +/* Build the buffer PSTR->MBS, and apply the translation if we need. + This function is used in case of REG_ICASE. */ + +static void +internal_function +build_upper_buffer (re_string_t *pstr) +{ + int char_idx, end_idx; + end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; + + for (char_idx = pstr->valid_len; char_idx < end_idx; ++char_idx) + { + int ch = pstr->raw_mbs[pstr->raw_mbs_idx + char_idx]; + if (BE (pstr->trans != NULL, 0)) + ch = pstr->trans[ch]; + if (islower (ch)) + pstr->mbs[char_idx] = toupper (ch); + else + pstr->mbs[char_idx] = ch; + } + pstr->valid_len = char_idx; + pstr->valid_raw_len = char_idx; +} + +/* Apply TRANS to the buffer in PSTR. */ + +static void +internal_function +re_string_translate_buffer (re_string_t *pstr) +{ + int buf_idx, end_idx; + end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; + + for (buf_idx = pstr->valid_len; buf_idx < end_idx; ++buf_idx) + { + int ch = pstr->raw_mbs[pstr->raw_mbs_idx + buf_idx]; + pstr->mbs[buf_idx] = pstr->trans[ch]; + } + + pstr->valid_len = buf_idx; + pstr->valid_raw_len = buf_idx; +} + +/* This function re-construct the buffers. + Concretely, convert to wide character in case of pstr->mb_cur_max > 1, + convert to upper case in case of REG_ICASE, apply translation. */ + +static reg_errcode_t +internal_function +re_string_reconstruct (re_string_t *pstr, int idx, int eflags) +{ + int offset = idx - pstr->raw_mbs_idx; + if (BE (offset < 0, 0)) + { + /* Reset buffer. */ +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); +#endif /* RE_ENABLE_I18N */ + pstr->len = pstr->raw_len; + pstr->stop = pstr->raw_stop; + pstr->valid_len = 0; + pstr->raw_mbs_idx = 0; + pstr->valid_raw_len = 0; + pstr->offsets_needed = 0; + pstr->tip_context = ((eflags & REG_NOTBOL) ? CONTEXT_BEGBUF + : CONTEXT_NEWLINE | CONTEXT_BEGBUF); + if (!pstr->mbs_allocated) + pstr->mbs = (unsigned char *) pstr->raw_mbs; + offset = idx; + } + + if (BE (offset != 0, 1)) + { + /* Should the already checked characters be kept? */ + if (BE (offset < pstr->valid_raw_len, 1)) + { + /* Yes, move them to the front of the buffer. */ +#ifdef RE_ENABLE_I18N + if (BE (pstr->offsets_needed, 0)) + { + int low = 0, high = pstr->valid_len, mid; + do + { + mid = (high + low) / 2; + if (pstr->offsets[mid] > offset) + high = mid; + else if (pstr->offsets[mid] < offset) + low = mid + 1; + else + break; + } + while (low < high); + if (pstr->offsets[mid] < offset) + ++mid; + pstr->tip_context = re_string_context_at (pstr, mid - 1, + eflags); + /* This can be quite complicated, so handle specially + only the common and easy case where the character with + different length representation of lower and upper + case is present at or after offset. */ + if (pstr->valid_len > offset + && mid == offset && pstr->offsets[mid] == offset) + { + memmove (pstr->wcs, pstr->wcs + offset, + (pstr->valid_len - offset) * sizeof (wint_t)); + memmove (pstr->mbs, pstr->mbs + offset, pstr->valid_len - offset); + pstr->valid_len -= offset; + pstr->valid_raw_len -= offset; + for (low = 0; low < pstr->valid_len; low++) + pstr->offsets[low] = pstr->offsets[low + offset] - offset; + } + else + { + /* Otherwise, just find out how long the partial multibyte + character at offset is and fill it with WEOF/255. */ + pstr->len = pstr->raw_len - idx + offset; + pstr->stop = pstr->raw_stop - idx + offset; + pstr->offsets_needed = 0; + while (mid > 0 && pstr->offsets[mid - 1] == offset) + --mid; + while (mid < pstr->valid_len) + if (pstr->wcs[mid] != WEOF) + break; + else + ++mid; + if (mid == pstr->valid_len) + pstr->valid_len = 0; + else + { + pstr->valid_len = pstr->offsets[mid] - offset; + if (pstr->valid_len) + { + for (low = 0; low < pstr->valid_len; ++low) + pstr->wcs[low] = WEOF; + memset (pstr->mbs, 255, pstr->valid_len); + } + } + pstr->valid_raw_len = pstr->valid_len; + } + } + else +#endif + { + pstr->tip_context = re_string_context_at (pstr, offset - 1, + eflags); +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + memmove (pstr->wcs, pstr->wcs + offset, + (pstr->valid_len - offset) * sizeof (wint_t)); +#endif /* RE_ENABLE_I18N */ + if (BE (pstr->mbs_allocated, 0)) + memmove (pstr->mbs, pstr->mbs + offset, + pstr->valid_len - offset); + pstr->valid_len -= offset; + pstr->valid_raw_len -= offset; +#if DEBUG + assert (pstr->valid_len > 0); +#endif + } + } + else + { + /* No, skip all characters until IDX. */ + int prev_valid_len = pstr->valid_len; + +#ifdef RE_ENABLE_I18N + if (BE (pstr->offsets_needed, 0)) + { + pstr->len = pstr->raw_len - idx + offset; + pstr->stop = pstr->raw_stop - idx + offset; + pstr->offsets_needed = 0; + } +#endif + pstr->valid_len = 0; +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + { + int wcs_idx; + wint_t wc = WEOF; + + if (pstr->is_utf8) + { + const unsigned char *raw, *p, *q, *end; + + /* Special case UTF-8. Multi-byte chars start with any + byte other than 0x80 - 0xbf. */ + raw = pstr->raw_mbs + pstr->raw_mbs_idx; + end = raw + (offset - pstr->mb_cur_max); + if (end < pstr->raw_mbs) + end = pstr->raw_mbs; + p = raw + offset - 1; +#ifdef _LIBC + /* We know the wchar_t encoding is UCS4, so for the simple + case, ASCII characters, skip the conversion step. */ + if (isascii (*p) && BE (pstr->trans == NULL, 1)) + { + memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); + /* pstr->valid_len = 0; */ + wc = (wchar_t) *p; + } + else +#endif + for (; p >= end; --p) + if ((*p & 0xc0) != 0x80) + { + mbstate_t cur_state; + wchar_t wc2; + int mlen = raw + pstr->len - p; + unsigned char buf[6]; + size_t mbclen; + + q = p; + if (BE (pstr->trans != NULL, 0)) + { + int i = mlen < 6 ? mlen : 6; + while (--i >= 0) + buf[i] = pstr->trans[p[i]]; + q = buf; + } + /* XXX Don't use mbrtowc, we know which conversion + to use (UTF-8 -> UCS4). */ + memset (&cur_state, 0, sizeof (cur_state)); + mbclen = mbrtowc (&wc2, (const char *) p, mlen, + &cur_state); + if (raw + offset - p <= mbclen + && mbclen < (size_t) -2) + { + memset (&pstr->cur_state, '\0', + sizeof (mbstate_t)); + pstr->valid_len = mbclen - (raw + offset - p); + wc = wc2; + } + break; + } + } + + if (wc == WEOF) + pstr->valid_len = re_string_skip_chars (pstr, idx, &wc) - idx; + if (wc == WEOF) + pstr->tip_context + = re_string_context_at (pstr, prev_valid_len - 1, eflags); + else + pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0) + && IS_WIDE_WORD_CHAR (wc)) + ? CONTEXT_WORD + : ((IS_WIDE_NEWLINE (wc) + && pstr->newline_anchor) + ? CONTEXT_NEWLINE : 0)); + if (BE (pstr->valid_len, 0)) + { + for (wcs_idx = 0; wcs_idx < pstr->valid_len; ++wcs_idx) + pstr->wcs[wcs_idx] = WEOF; + if (pstr->mbs_allocated) + memset (pstr->mbs, 255, pstr->valid_len); + } + pstr->valid_raw_len = pstr->valid_len; + } + else +#endif /* RE_ENABLE_I18N */ + { + int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1]; + pstr->valid_raw_len = 0; + if (pstr->trans) + c = pstr->trans[c]; + pstr->tip_context = (bitset_contain (pstr->word_char, c) + ? CONTEXT_WORD + : ((IS_NEWLINE (c) && pstr->newline_anchor) + ? CONTEXT_NEWLINE : 0)); + } + } + if (!BE (pstr->mbs_allocated, 0)) + pstr->mbs += offset; + } + pstr->raw_mbs_idx = idx; + pstr->len -= offset; + pstr->stop -= offset; + + /* Then build the buffers. */ +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + { + if (pstr->icase) + { + reg_errcode_t ret = build_wcs_upper_buffer (pstr); + if (BE (ret != REG_NOERROR, 0)) + return ret; + } + else + build_wcs_buffer (pstr); + } + else +#endif /* RE_ENABLE_I18N */ + if (BE (pstr->mbs_allocated, 0)) + { + if (pstr->icase) + build_upper_buffer (pstr); + else if (pstr->trans != NULL) + re_string_translate_buffer (pstr); + } + else + pstr->valid_len = pstr->len; + + pstr->cur_idx = 0; + return REG_NOERROR; +} + +static unsigned char +internal_function __attribute ((pure)) +re_string_peek_byte_case (const re_string_t *pstr, int idx) +{ + int ch, off; + + /* Handle the common (easiest) cases first. */ + if (BE (!pstr->mbs_allocated, 1)) + return re_string_peek_byte (pstr, idx); + +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1 + && ! re_string_is_single_byte_char (pstr, pstr->cur_idx + idx)) + return re_string_peek_byte (pstr, idx); +#endif + + off = pstr->cur_idx + idx; +#ifdef RE_ENABLE_I18N + if (pstr->offsets_needed) + off = pstr->offsets[off]; +#endif + + ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; + +#ifdef RE_ENABLE_I18N + /* Ensure that e.g. for tr_TR.UTF-8 BACKSLASH DOTLESS SMALL LETTER I + this function returns CAPITAL LETTER I instead of first byte of + DOTLESS SMALL LETTER I. The latter would confuse the parser, + since peek_byte_case doesn't advance cur_idx in any way. */ + if (pstr->offsets_needed && !isascii (ch)) + return re_string_peek_byte (pstr, idx); +#endif + + return ch; +} + +static unsigned char +internal_function __attribute ((pure)) +re_string_fetch_byte_case (re_string_t *pstr) +{ + if (BE (!pstr->mbs_allocated, 1)) + return re_string_fetch_byte (pstr); + +#ifdef RE_ENABLE_I18N + if (pstr->offsets_needed) + { + int off, ch; + + /* For tr_TR.UTF-8 [[:islower:]] there is + [[: CAPITAL LETTER I WITH DOT lower:]] in mbs. Skip + in that case the whole multi-byte character and return + the original letter. On the other side, with + [[: DOTLESS SMALL LETTER I return [[:I, as doing + anything else would complicate things too much. */ + + if (!re_string_first_byte (pstr, pstr->cur_idx)) + return re_string_fetch_byte (pstr); + + off = pstr->offsets[pstr->cur_idx]; + ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; + + if (! isascii (ch)) + return re_string_fetch_byte (pstr); + + re_string_skip_bytes (pstr, + re_string_char_size_at (pstr, pstr->cur_idx)); + return ch; + } +#endif + + return pstr->raw_mbs[pstr->raw_mbs_idx + pstr->cur_idx++]; +} + +static void +internal_function +re_string_destruct (re_string_t *pstr) +{ +#ifdef RE_ENABLE_I18N + re_free (pstr->wcs); + re_free (pstr->offsets); +#endif /* RE_ENABLE_I18N */ + if (pstr->mbs_allocated) + re_free (pstr->mbs); +} + +/* Return the context at IDX in INPUT. */ + +static unsigned int +internal_function +re_string_context_at (const re_string_t *input, int idx, int eflags) +{ + int c; + if (BE (idx < 0, 0)) + /* In this case, we use the value stored in input->tip_context, + since we can't know the character in input->mbs[-1] here. */ + return input->tip_context; + if (BE (idx == input->len, 0)) + return ((eflags & REG_NOTEOL) ? CONTEXT_ENDBUF + : CONTEXT_NEWLINE | CONTEXT_ENDBUF); +#ifdef RE_ENABLE_I18N + if (input->mb_cur_max > 1) + { + wint_t wc; + int wc_idx = idx; + while(input->wcs[wc_idx] == WEOF) + { +#ifdef DEBUG + /* It must not happen. */ + assert (wc_idx >= 0); +#endif + --wc_idx; + if (wc_idx < 0) + return input->tip_context; + } + wc = input->wcs[wc_idx]; + if (BE (input->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc)) + return CONTEXT_WORD; + return (IS_WIDE_NEWLINE (wc) && input->newline_anchor + ? CONTEXT_NEWLINE : 0); + } + else +#endif + { + c = re_string_byte_at (input, idx); + if (bitset_contain (input->word_char, c)) + return CONTEXT_WORD; + return IS_NEWLINE (c) && input->newline_anchor ? CONTEXT_NEWLINE : 0; + } +} + +/* Functions for set operation. */ + +static reg_errcode_t +internal_function +re_node_set_alloc (re_node_set *set, int size) +{ + set->alloc = size; + set->nelem = 0; + set->elems = re_malloc (int, size); + if (BE (set->elems == NULL, 0)) + return REG_ESPACE; + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +re_node_set_init_1 (re_node_set *set, int elem) +{ + set->alloc = 1; + set->nelem = 1; + set->elems = re_malloc (int, 1); + if (BE (set->elems == NULL, 0)) + { + set->alloc = set->nelem = 0; + return REG_ESPACE; + } + set->elems[0] = elem; + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +re_node_set_init_2 (re_node_set *set, int elem1, int elem2) +{ + set->alloc = 2; + set->elems = re_malloc (int, 2); + if (BE (set->elems == NULL, 0)) + return REG_ESPACE; + if (elem1 == elem2) + { + set->nelem = 1; + set->elems[0] = elem1; + } + else + { + set->nelem = 2; + if (elem1 < elem2) + { + set->elems[0] = elem1; + set->elems[1] = elem2; + } + else + { + set->elems[0] = elem2; + set->elems[1] = elem1; + } + } + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +re_node_set_init_copy (re_node_set *dest, const re_node_set *src) +{ + dest->nelem = src->nelem; + if (src->nelem > 0) + { + dest->alloc = dest->nelem; + dest->elems = re_malloc (int, dest->alloc); + if (BE (dest->elems == NULL, 0)) + { + dest->alloc = dest->nelem = 0; + return REG_ESPACE; + } + memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); + } + else + re_node_set_init_empty (dest); + return REG_NOERROR; +} + +/* Calculate the intersection of the sets SRC1 and SRC2. And merge it to + DEST. Return value indicate the error code or REG_NOERROR if succeeded. + Note: We assume dest->elems is NULL, when dest->alloc is 0. */ + +static reg_errcode_t +internal_function +re_node_set_add_intersect (re_node_set *dest, const re_node_set *src1, + const re_node_set *src2) +{ + int i1, i2, is, id, delta, sbase; + if (src1->nelem == 0 || src2->nelem == 0) + return REG_NOERROR; + + /* We need dest->nelem + 2 * elems_in_intersection; this is a + conservative estimate. */ + if (src1->nelem + src2->nelem + dest->nelem > dest->alloc) + { + int new_alloc = src1->nelem + src2->nelem + dest->alloc; + int *new_elems = re_realloc (dest->elems, int, new_alloc); + if (BE (new_elems == NULL, 0)) + return REG_ESPACE; + dest->elems = new_elems; + dest->alloc = new_alloc; + } + + /* Find the items in the intersection of SRC1 and SRC2, and copy + into the top of DEST those that are not already in DEST itself. */ + sbase = dest->nelem + src1->nelem + src2->nelem; + i1 = src1->nelem - 1; + i2 = src2->nelem - 1; + id = dest->nelem - 1; + for (;;) + { + if (src1->elems[i1] == src2->elems[i2]) + { + /* Try to find the item in DEST. Maybe we could binary search? */ + while (id >= 0 && dest->elems[id] > src1->elems[i1]) + --id; + + if (id < 0 || dest->elems[id] != src1->elems[i1]) + dest->elems[--sbase] = src1->elems[i1]; + + if (--i1 < 0 || --i2 < 0) + break; + } + + /* Lower the highest of the two items. */ + else if (src1->elems[i1] < src2->elems[i2]) + { + if (--i2 < 0) + break; + } + else + { + if (--i1 < 0) + break; + } + } + + id = dest->nelem - 1; + is = dest->nelem + src1->nelem + src2->nelem - 1; + delta = is - sbase + 1; + + /* Now copy. When DELTA becomes zero, the remaining + DEST elements are already in place; this is more or + less the same loop that is in re_node_set_merge. */ + dest->nelem += delta; + if (delta > 0 && id >= 0) + for (;;) + { + if (dest->elems[is] > dest->elems[id]) + { + /* Copy from the top. */ + dest->elems[id + delta--] = dest->elems[is--]; + if (delta == 0) + break; + } + else + { + /* Slide from the bottom. */ + dest->elems[id + delta] = dest->elems[id]; + if (--id < 0) + break; + } + } + + /* Copy remaining SRC elements. */ + memcpy (dest->elems, dest->elems + sbase, delta * sizeof (int)); + + return REG_NOERROR; +} + +/* Calculate the union set of the sets SRC1 and SRC2. And store it to + DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ + +static reg_errcode_t +internal_function +re_node_set_init_union (re_node_set *dest, const re_node_set *src1, + const re_node_set *src2) +{ + int i1, i2, id; + if (src1 != NULL && src1->nelem > 0 && src2 != NULL && src2->nelem > 0) + { + dest->alloc = src1->nelem + src2->nelem; + dest->elems = re_malloc (int, dest->alloc); + if (BE (dest->elems == NULL, 0)) + return REG_ESPACE; + } + else + { + if (src1 != NULL && src1->nelem > 0) + return re_node_set_init_copy (dest, src1); + else if (src2 != NULL && src2->nelem > 0) + return re_node_set_init_copy (dest, src2); + else + re_node_set_init_empty (dest); + return REG_NOERROR; + } + for (i1 = i2 = id = 0 ; i1 < src1->nelem && i2 < src2->nelem ;) + { + if (src1->elems[i1] > src2->elems[i2]) + { + dest->elems[id++] = src2->elems[i2++]; + continue; + } + if (src1->elems[i1] == src2->elems[i2]) + ++i2; + dest->elems[id++] = src1->elems[i1++]; + } + if (i1 < src1->nelem) + { + memcpy (dest->elems + id, src1->elems + i1, + (src1->nelem - i1) * sizeof (int)); + id += src1->nelem - i1; + } + else if (i2 < src2->nelem) + { + memcpy (dest->elems + id, src2->elems + i2, + (src2->nelem - i2) * sizeof (int)); + id += src2->nelem - i2; + } + dest->nelem = id; + return REG_NOERROR; +} + +/* Calculate the union set of the sets DEST and SRC. And store it to + DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ + +static reg_errcode_t +internal_function +re_node_set_merge (re_node_set *dest, const re_node_set *src) +{ + int is, id, sbase, delta; + if (src == NULL || src->nelem == 0) + return REG_NOERROR; + if (dest->alloc < 2 * src->nelem + dest->nelem) + { + int new_alloc = 2 * (src->nelem + dest->alloc); + int *new_buffer = re_realloc (dest->elems, int, new_alloc); + if (BE (new_buffer == NULL, 0)) + return REG_ESPACE; + dest->elems = new_buffer; + dest->alloc = new_alloc; + } + + if (BE (dest->nelem == 0, 0)) + { + dest->nelem = src->nelem; + memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); + return REG_NOERROR; + } + + /* Copy into the top of DEST the items of SRC that are not + found in DEST. Maybe we could binary search in DEST? */ + for (sbase = dest->nelem + 2 * src->nelem, + is = src->nelem - 1, id = dest->nelem - 1; is >= 0 && id >= 0; ) + { + if (dest->elems[id] == src->elems[is]) + is--, id--; + else if (dest->elems[id] < src->elems[is]) + dest->elems[--sbase] = src->elems[is--]; + else /* if (dest->elems[id] > src->elems[is]) */ + --id; + } + + if (is >= 0) + { + /* If DEST is exhausted, the remaining items of SRC must be unique. */ + sbase -= is + 1; + memcpy (dest->elems + sbase, src->elems, (is + 1) * sizeof (int)); + } + + id = dest->nelem - 1; + is = dest->nelem + 2 * src->nelem - 1; + delta = is - sbase + 1; + if (delta == 0) + return REG_NOERROR; + + /* Now copy. When DELTA becomes zero, the remaining + DEST elements are already in place. */ + dest->nelem += delta; + for (;;) + { + if (dest->elems[is] > dest->elems[id]) + { + /* Copy from the top. */ + dest->elems[id + delta--] = dest->elems[is--]; + if (delta == 0) + break; + } + else + { + /* Slide from the bottom. */ + dest->elems[id + delta] = dest->elems[id]; + if (--id < 0) + { + /* Copy remaining SRC elements. */ + memcpy (dest->elems, dest->elems + sbase, + delta * sizeof (int)); + break; + } + } + } + + return REG_NOERROR; +} + +/* Insert the new element ELEM to the re_node_set* SET. + SET should not already have ELEM. + return -1 if an error is occured, return 1 otherwise. */ + +static int +internal_function +re_node_set_insert (re_node_set *set, int elem) +{ + int idx; + /* In case the set is empty. */ + if (set->alloc == 0) + { + if (BE (re_node_set_init_1 (set, elem) == REG_NOERROR, 1)) + return 1; + else + return -1; + } + + if (BE (set->nelem, 0) == 0) + { + /* We already guaranteed above that set->alloc != 0. */ + set->elems[0] = elem; + ++set->nelem; + return 1; + } + + /* Realloc if we need. */ + if (set->alloc == set->nelem) + { + int *new_elems; + set->alloc = set->alloc * 2; + new_elems = re_realloc (set->elems, int, set->alloc); + if (BE (new_elems == NULL, 0)) + return -1; + set->elems = new_elems; + } + + /* Move the elements which follows the new element. Test the + first element separately to skip a check in the inner loop. */ + if (elem < set->elems[0]) + { + idx = 0; + for (idx = set->nelem; idx > 0; idx--) + set->elems[idx] = set->elems[idx - 1]; + } + else + { + for (idx = set->nelem; set->elems[idx - 1] > elem; idx--) + set->elems[idx] = set->elems[idx - 1]; + } + + /* Insert the new element. */ + set->elems[idx] = elem; + ++set->nelem; + return 1; +} + +/* Insert the new element ELEM to the re_node_set* SET. + SET should not already have any element greater than or equal to ELEM. + Return -1 if an error is occured, return 1 otherwise. */ + +static int +internal_function +re_node_set_insert_last (re_node_set *set, int elem) +{ + /* Realloc if we need. */ + if (set->alloc == set->nelem) + { + int *new_elems; + set->alloc = (set->alloc + 1) * 2; + new_elems = re_realloc (set->elems, int, set->alloc); + if (BE (new_elems == NULL, 0)) + return -1; + set->elems = new_elems; + } + + /* Insert the new element. */ + set->elems[set->nelem++] = elem; + return 1; +} + +/* Compare two node sets SET1 and SET2. + return 1 if SET1 and SET2 are equivalent, return 0 otherwise. */ + +static int +internal_function __attribute ((pure)) +re_node_set_compare (const re_node_set *set1, const re_node_set *set2) +{ + int i; + if (set1 == NULL || set2 == NULL || set1->nelem != set2->nelem) + return 0; + for (i = set1->nelem ; --i >= 0 ; ) + if (set1->elems[i] != set2->elems[i]) + return 0; + return 1; +} + +/* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise. */ + +static int +internal_function __attribute ((pure)) +re_node_set_contains (const re_node_set *set, int elem) +{ + unsigned int idx, right, mid; + if (set->nelem <= 0) + return 0; + + /* Binary search the element. */ + idx = 0; + right = set->nelem - 1; + while (idx < right) + { + mid = (idx + right) / 2; + if (set->elems[mid] < elem) + idx = mid + 1; + else + right = mid; + } + return set->elems[idx] == elem ? idx + 1 : 0; +} + +static void +internal_function +re_node_set_remove_at (re_node_set *set, int idx) +{ + if (idx < 0 || idx >= set->nelem) + return; + --set->nelem; + for (; idx < set->nelem; idx++) + set->elems[idx] = set->elems[idx + 1]; +} + + +/* Add the token TOKEN to dfa->nodes, and return the index of the token. + Or return -1, if an error will be occured. */ + +static int +internal_function +re_dfa_add_node (re_dfa_t *dfa, re_token_t token) +{ + int type = token.type; + if (BE (dfa->nodes_len >= dfa->nodes_alloc, 0)) + { + size_t new_nodes_alloc = dfa->nodes_alloc * 2; + int *new_nexts, *new_indices; + re_node_set *new_edests, *new_eclosures; + re_token_t *new_nodes; + + /* Avoid overflows. */ + if (BE (new_nodes_alloc < dfa->nodes_alloc, 0)) + return -1; + + new_nodes = re_realloc (dfa->nodes, re_token_t, new_nodes_alloc); + if (BE (new_nodes == NULL, 0)) + return -1; + dfa->nodes = new_nodes; + new_nexts = re_realloc (dfa->nexts, int, new_nodes_alloc); + new_indices = re_realloc (dfa->org_indices, int, new_nodes_alloc); + new_edests = re_realloc (dfa->edests, re_node_set, new_nodes_alloc); + new_eclosures = re_realloc (dfa->eclosures, re_node_set, new_nodes_alloc); + if (BE (new_nexts == NULL || new_indices == NULL + || new_edests == NULL || new_eclosures == NULL, 0)) + return -1; + dfa->nexts = new_nexts; + dfa->org_indices = new_indices; + dfa->edests = new_edests; + dfa->eclosures = new_eclosures; + dfa->nodes_alloc = new_nodes_alloc; + } + dfa->nodes[dfa->nodes_len] = token; + dfa->nodes[dfa->nodes_len].constraint = 0; +#ifdef RE_ENABLE_I18N + dfa->nodes[dfa->nodes_len].accept_mb = + (type == OP_PERIOD && dfa->mb_cur_max > 1) || type == COMPLEX_BRACKET; +#endif + dfa->nexts[dfa->nodes_len] = -1; + re_node_set_init_empty (dfa->edests + dfa->nodes_len); + re_node_set_init_empty (dfa->eclosures + dfa->nodes_len); + return dfa->nodes_len++; +} + +static inline unsigned int +internal_function +calc_state_hash (const re_node_set *nodes, unsigned int context) +{ + unsigned int hash = nodes->nelem + context; + int i; + for (i = 0 ; i < nodes->nelem ; i++) + hash += nodes->elems[i]; + return hash; +} + +/* Search for the state whose node_set is equivalent to NODES. + Return the pointer to the state, if we found it in the DFA. + Otherwise create the new one and return it. In case of an error + return NULL and set the error code in ERR. + Note: - We assume NULL as the invalid state, then it is possible that + return value is NULL and ERR is REG_NOERROR. + - We never return non-NULL value in case of any errors, it is for + optimization. */ + +static re_dfastate_t * +internal_function +re_acquire_state (reg_errcode_t *err, const re_dfa_t *dfa, + const re_node_set *nodes) +{ + unsigned int hash; + re_dfastate_t *new_state; + struct re_state_table_entry *spot; + int i; + if (BE (nodes->nelem == 0, 0)) + { + *err = REG_NOERROR; + return NULL; + } + hash = calc_state_hash (nodes, 0); + spot = dfa->state_table + (hash & dfa->state_hash_mask); + + for (i = 0 ; i < spot->num ; i++) + { + re_dfastate_t *state = spot->array[i]; + if (hash != state->hash) + continue; + if (re_node_set_compare (&state->nodes, nodes)) + return state; + } + + /* There are no appropriate state in the dfa, create the new one. */ + new_state = create_ci_newstate (dfa, nodes, hash); + if (BE (new_state == NULL, 0)) + *err = REG_ESPACE; + + return new_state; +} + +/* Search for the state whose node_set is equivalent to NODES and + whose context is equivalent to CONTEXT. + Return the pointer to the state, if we found it in the DFA. + Otherwise create the new one and return it. In case of an error + return NULL and set the error code in ERR. + Note: - We assume NULL as the invalid state, then it is possible that + return value is NULL and ERR is REG_NOERROR. + - We never return non-NULL value in case of any errors, it is for + optimization. */ + +static re_dfastate_t * +internal_function +re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa, + const re_node_set *nodes, unsigned int context) +{ + unsigned int hash; + re_dfastate_t *new_state; + struct re_state_table_entry *spot; + int i; + if (nodes->nelem == 0) + { + *err = REG_NOERROR; + return NULL; + } + hash = calc_state_hash (nodes, context); + spot = dfa->state_table + (hash & dfa->state_hash_mask); + + for (i = 0 ; i < spot->num ; i++) + { + re_dfastate_t *state = spot->array[i]; + if (state->hash == hash + && state->context == context + && re_node_set_compare (state->entrance_nodes, nodes)) + return state; + } + /* There are no appropriate state in `dfa', create the new one. */ + new_state = create_cd_newstate (dfa, nodes, context, hash); + if (BE (new_state == NULL, 0)) + *err = REG_ESPACE; + + return new_state; +} + +/* Finish initialization of the new state NEWSTATE, and using its hash value + HASH put in the appropriate bucket of DFA's state table. Return value + indicates the error code if failed. */ + +static reg_errcode_t +register_state (const re_dfa_t *dfa, re_dfastate_t *newstate, + unsigned int hash) +{ + struct re_state_table_entry *spot; + reg_errcode_t err; + int i; + + newstate->hash = hash; + err = re_node_set_alloc (&newstate->non_eps_nodes, newstate->nodes.nelem); + if (BE (err != REG_NOERROR, 0)) + return REG_ESPACE; + for (i = 0; i < newstate->nodes.nelem; i++) + { + int elem = newstate->nodes.elems[i]; + if (!IS_EPSILON_NODE (dfa->nodes[elem].type)) + re_node_set_insert_last (&newstate->non_eps_nodes, elem); + } + + spot = dfa->state_table + (hash & dfa->state_hash_mask); + if (BE (spot->alloc <= spot->num, 0)) + { + int new_alloc = 2 * spot->num + 2; + re_dfastate_t **new_array = re_realloc (spot->array, re_dfastate_t *, + new_alloc); + if (BE (new_array == NULL, 0)) + return REG_ESPACE; + spot->array = new_array; + spot->alloc = new_alloc; + } + spot->array[spot->num++] = newstate; + return REG_NOERROR; +} + +static void +free_state (re_dfastate_t *state) +{ + re_node_set_free (&state->non_eps_nodes); + re_node_set_free (&state->inveclosure); + if (state->entrance_nodes != &state->nodes) + { + re_node_set_free (state->entrance_nodes); + re_free (state->entrance_nodes); + } + re_node_set_free (&state->nodes); + re_free (state->word_trtable); + re_free (state->trtable); + re_free (state); +} + +/* Create the new state which is independ of contexts. + Return the new state if succeeded, otherwise return NULL. */ + +static re_dfastate_t * +internal_function +create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes, + unsigned int hash) +{ + int i; + reg_errcode_t err; + re_dfastate_t *newstate; + + newstate = (re_dfastate_t *) calloc (sizeof (re_dfastate_t), 1); + if (BE (newstate == NULL, 0)) + return NULL; + err = re_node_set_init_copy (&newstate->nodes, nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_free (newstate); + return NULL; + } + + newstate->entrance_nodes = &newstate->nodes; + for (i = 0 ; i < nodes->nelem ; i++) + { + re_token_t *node = dfa->nodes + nodes->elems[i]; + re_token_type_t type = node->type; + if (type == CHARACTER && !node->constraint) + continue; +#ifdef RE_ENABLE_I18N + newstate->accept_mb |= node->accept_mb; +#endif /* RE_ENABLE_I18N */ + + /* If the state has the halt node, the state is a halt state. */ + if (type == END_OF_RE) + newstate->halt = 1; + else if (type == OP_BACK_REF) + newstate->has_backref = 1; + else if (type == ANCHOR || node->constraint) + newstate->has_constraint = 1; + } + err = register_state (dfa, newstate, hash); + if (BE (err != REG_NOERROR, 0)) + { + free_state (newstate); + newstate = NULL; + } + return newstate; +} + +/* Create the new state which is depend on the context CONTEXT. + Return the new state if succeeded, otherwise return NULL. */ + +static re_dfastate_t * +internal_function +create_cd_newstate (const re_dfa_t *dfa, const re_node_set *nodes, + unsigned int context, unsigned int hash) +{ + int i, nctx_nodes = 0; + reg_errcode_t err; + re_dfastate_t *newstate; + + newstate = (re_dfastate_t *) calloc (sizeof (re_dfastate_t), 1); + if (BE (newstate == NULL, 0)) + return NULL; + err = re_node_set_init_copy (&newstate->nodes, nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_free (newstate); + return NULL; + } + + newstate->context = context; + newstate->entrance_nodes = &newstate->nodes; + + for (i = 0 ; i < nodes->nelem ; i++) + { + unsigned int constraint = 0; + re_token_t *node = dfa->nodes + nodes->elems[i]; + re_token_type_t type = node->type; + if (node->constraint) + constraint = node->constraint; + + if (type == CHARACTER && !constraint) + continue; +#ifdef RE_ENABLE_I18N + newstate->accept_mb |= node->accept_mb; +#endif /* RE_ENABLE_I18N */ + + /* If the state has the halt node, the state is a halt state. */ + if (type == END_OF_RE) + newstate->halt = 1; + else if (type == OP_BACK_REF) + newstate->has_backref = 1; + else if (type == ANCHOR) + constraint = node->opr.ctx_type; + + if (constraint) + { + if (newstate->entrance_nodes == &newstate->nodes) + { + newstate->entrance_nodes = re_malloc (re_node_set, 1); + if (BE (newstate->entrance_nodes == NULL, 0)) + { + free_state (newstate); + return NULL; + } + re_node_set_init_copy (newstate->entrance_nodes, nodes); + nctx_nodes = 0; + newstate->has_constraint = 1; + } + + if (NOT_SATISFY_PREV_CONSTRAINT (constraint,context)) + { + re_node_set_remove_at (&newstate->nodes, i - nctx_nodes); + ++nctx_nodes; + } + } + } + err = register_state (dfa, newstate, hash); + if (BE (err != REG_NOERROR, 0)) + { + free_state (newstate); + newstate = NULL; + } + return newstate; +} diff --git a/Build/source/texk/chktex/regex/regex_internal.h b/Build/source/texk/chktex/regex/regex_internal.h new file mode 100644 index 00000000000..b0c4d355abb --- /dev/null +++ b/Build/source/texk/chktex/regex/regex_internal.h @@ -0,0 +1,778 @@ +/* Extended regular expression matching and search library. + Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Isamu Hasegawa . + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#ifndef _REGEX_INTERNAL_H +#define _REGEX_INTERNAL_H 1 + +#include +#include +#include +#include +#include + +#if defined(__MINGW32_VERSION) || defined(_MSC_VER) +#define strcasecmp stricmp +#endif + +#if defined HAVE_LANGINFO_H || defined HAVE_LANGINFO_CODESET || defined _LIBC +# include +#endif +#if defined HAVE_LOCALE_H || defined _LIBC +# include +#endif +#if defined HAVE_WCHAR_H || defined _LIBC +# include +#endif /* HAVE_WCHAR_H || _LIBC */ +#if defined HAVE_WCTYPE_H || defined _LIBC +# include +#endif /* HAVE_WCTYPE_H || _LIBC */ +#if defined HAVE_STDBOOL_H || defined _LIBC +# include +#else +typedef enum { false, true } bool; +#endif /* HAVE_STDBOOL_H || _LIBC */ +#if defined HAVE_STDINT_H || defined _LIBC +# include +#endif /* HAVE_STDINT_H || _LIBC */ +#if defined _LIBC +# include +#else +# define __libc_lock_define(CLASS,NAME) +# define __libc_lock_init(NAME) do { } while (0) +# define __libc_lock_lock(NAME) do { } while (0) +# define __libc_lock_unlock(NAME) do { } while (0) +#endif + +/* In case that the system doesn't have isblank(). */ +#if !defined _LIBC && !defined HAVE_ISBLANK && !defined isblank +# define isblank(ch) ((ch) == ' ' || (ch) == '\t') +#endif + +#ifdef _LIBC +# ifndef _RE_DEFINE_LOCALE_FUNCTIONS +# define _RE_DEFINE_LOCALE_FUNCTIONS 1 +# include +# include +# include +# endif +#endif + +/* This is for other GNU distributions with internationalized messages. */ +#if (HAVE_LIBINTL_H && ENABLE_NLS) || defined _LIBC +# include +# ifdef _LIBC +# undef gettext +# define gettext(msgid) \ + INTUSE(__dcgettext) (_libc_intl_domainname, msgid, LC_MESSAGES) +# endif +#else +# define gettext(msgid) (msgid) +#endif + +#ifndef gettext_noop +/* This define is so xgettext can find the internationalizable + strings. */ +# define gettext_noop(String) String +#endif + +/* For loser systems without the definition. */ +#ifndef SIZE_MAX +# define SIZE_MAX ((size_t) -1) +#endif + +#if (defined MB_CUR_MAX && HAVE_LOCALE_H && HAVE_WCTYPE_H && HAVE_WCHAR_H && HAVE_WCRTOMB && HAVE_MBRTOWC && HAVE_WCSCOLL) || _LIBC +# define RE_ENABLE_I18N +#endif + +#if __GNUC__ >= 3 +# define BE(expr, val) __builtin_expect (expr, val) +#else +# define BE(expr, val) (expr) +# define inline +#endif + +/* Number of single byte character. */ +#define SBC_MAX 256 + +#define COLL_ELEM_LEN_MAX 8 + +/* The character which represents newline. */ +#define NEWLINE_CHAR '\n' +#define WIDE_NEWLINE_CHAR L'\n' + +/* Rename to standard API for using out of glibc. */ +#ifndef _LIBC +# define __wctype wctype +# define __iswctype iswctype +# define __btowc btowc +# define __mempcpy mempcpy +# define __wcrtomb wcrtomb +# define __regfree regfree +# define attribute_hidden +#endif /* not _LIBC */ + +#ifdef __GNUC__ +# define __attribute(arg) __attribute__ (arg) +#else +# define __attribute(arg) +#endif + +extern const char __re_error_msgid[] attribute_hidden; +extern const size_t __re_error_msgid_idx[] attribute_hidden; + +/* An integer used to represent a set of bits. It must be unsigned, + and must be at least as wide as unsigned int. */ +typedef unsigned long int bitset_word_t; +/* All bits set in a bitset_word_t. */ +#define BITSET_WORD_MAX ULONG_MAX +/* Number of bits in a bitset_word_t. */ +#define BITSET_WORD_BITS (sizeof (bitset_word_t) * CHAR_BIT) +/* Number of bitset_word_t in a bit_set. */ +#define BITSET_WORDS (SBC_MAX / BITSET_WORD_BITS) +typedef bitset_word_t bitset_t[BITSET_WORDS]; +typedef bitset_word_t *re_bitset_ptr_t; +typedef const bitset_word_t *re_const_bitset_ptr_t; + +#define bitset_set(set,i) \ + (set[i / BITSET_WORD_BITS] |= (bitset_word_t) 1 << i % BITSET_WORD_BITS) +#define bitset_clear(set,i) \ + (set[i / BITSET_WORD_BITS] &= ~((bitset_word_t) 1 << i % BITSET_WORD_BITS)) +#define bitset_contain(set,i) \ + (set[i / BITSET_WORD_BITS] & ((bitset_word_t) 1 << i % BITSET_WORD_BITS)) +#define bitset_empty(set) memset (set, '\0', sizeof (bitset_t)) +#define bitset_set_all(set) memset (set, '\xff', sizeof (bitset_t)) +#define bitset_copy(dest,src) memcpy (dest, src, sizeof (bitset_t)) + +#define PREV_WORD_CONSTRAINT 0x0001 +#define PREV_NOTWORD_CONSTRAINT 0x0002 +#define NEXT_WORD_CONSTRAINT 0x0004 +#define NEXT_NOTWORD_CONSTRAINT 0x0008 +#define PREV_NEWLINE_CONSTRAINT 0x0010 +#define NEXT_NEWLINE_CONSTRAINT 0x0020 +#define PREV_BEGBUF_CONSTRAINT 0x0040 +#define NEXT_ENDBUF_CONSTRAINT 0x0080 +#define WORD_DELIM_CONSTRAINT 0x0100 +#define NOT_WORD_DELIM_CONSTRAINT 0x0200 + +typedef enum +{ + INSIDE_WORD = PREV_WORD_CONSTRAINT | NEXT_WORD_CONSTRAINT, + WORD_FIRST = PREV_NOTWORD_CONSTRAINT | NEXT_WORD_CONSTRAINT, + WORD_LAST = PREV_WORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT, + INSIDE_NOTWORD = PREV_NOTWORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT, + LINE_FIRST = PREV_NEWLINE_CONSTRAINT, + LINE_LAST = NEXT_NEWLINE_CONSTRAINT, + BUF_FIRST = PREV_BEGBUF_CONSTRAINT, + BUF_LAST = NEXT_ENDBUF_CONSTRAINT, + WORD_DELIM = WORD_DELIM_CONSTRAINT, + NOT_WORD_DELIM = NOT_WORD_DELIM_CONSTRAINT +} re_context_type; + +typedef struct +{ + int alloc; + int nelem; + int *elems; +} re_node_set; + +typedef enum +{ + NON_TYPE = 0, + + /* Node type, These are used by token, node, tree. */ + CHARACTER = 1, + END_OF_RE = 2, + SIMPLE_BRACKET = 3, + OP_BACK_REF = 4, + OP_PERIOD = 5, +#ifdef RE_ENABLE_I18N + COMPLEX_BRACKET = 6, + OP_UTF8_PERIOD = 7, +#endif /* RE_ENABLE_I18N */ + + /* We define EPSILON_BIT as a macro so that OP_OPEN_SUBEXP is used + when the debugger shows values of this enum type. */ +#define EPSILON_BIT 8 + OP_OPEN_SUBEXP = EPSILON_BIT | 0, + OP_CLOSE_SUBEXP = EPSILON_BIT | 1, + OP_ALT = EPSILON_BIT | 2, + OP_DUP_ASTERISK = EPSILON_BIT | 3, + ANCHOR = EPSILON_BIT | 4, + + /* Tree type, these are used only by tree. */ + CONCAT = 16, + SUBEXP = 17, + + /* Token type, these are used only by token. */ + OP_DUP_PLUS = 18, + OP_DUP_QUESTION, + OP_OPEN_BRACKET, + OP_CLOSE_BRACKET, + OP_CHARSET_RANGE, + OP_OPEN_DUP_NUM, + OP_CLOSE_DUP_NUM, + OP_NON_MATCH_LIST, + OP_OPEN_COLL_ELEM, + OP_CLOSE_COLL_ELEM, + OP_OPEN_EQUIV_CLASS, + OP_CLOSE_EQUIV_CLASS, + OP_OPEN_CHAR_CLASS, + OP_CLOSE_CHAR_CLASS, + OP_WORD, + OP_NOTWORD, + OP_SPACE, + OP_NOTSPACE, + BACK_SLASH + +} re_token_type_t; + +#ifdef RE_ENABLE_I18N +typedef struct +{ + /* Multibyte characters. */ + wchar_t *mbchars; + + /* Collating symbols. */ +# ifdef _LIBC + int32_t *coll_syms; +# endif + + /* Equivalence classes. */ +# ifdef _LIBC + int32_t *equiv_classes; +# endif + + /* Range expressions. */ +# ifdef _LIBC + uint32_t *range_starts; + uint32_t *range_ends; +# else /* not _LIBC */ + wchar_t *range_starts; + wchar_t *range_ends; +# endif /* not _LIBC */ + + /* Character classes. */ + wctype_t *char_classes; + + /* If this character set is the non-matching list. */ + unsigned int non_match : 1; + + /* # of multibyte characters. */ + int nmbchars; + + /* # of collating symbols. */ + int ncoll_syms; + + /* # of equivalence classes. */ + int nequiv_classes; + + /* # of range expressions. */ + int nranges; + + /* # of character classes. */ + int nchar_classes; +} re_charset_t; +#endif /* RE_ENABLE_I18N */ + +typedef struct +{ + union + { + unsigned char c; /* for CHARACTER */ + re_bitset_ptr_t sbcset; /* for SIMPLE_BRACKET */ +#ifdef RE_ENABLE_I18N + re_charset_t *mbcset; /* for COMPLEX_BRACKET */ +#endif /* RE_ENABLE_I18N */ + int idx; /* for BACK_REF */ + re_context_type ctx_type; /* for ANCHOR */ + } opr; +#if __GNUC__ >= 2 + re_token_type_t type : 8; +#else + re_token_type_t type; +#endif + unsigned int constraint : 10; /* context constraint */ + unsigned int duplicated : 1; + unsigned int opt_subexp : 1; +#ifdef RE_ENABLE_I18N + unsigned int accept_mb : 1; + /* These 2 bits can be moved into the union if needed (e.g. if running out + of bits; move opr.c to opr.c.c and move the flags to opr.c.flags). */ + unsigned int mb_partial : 1; +#endif + unsigned int word_char : 1; +} re_token_t; + +#define IS_EPSILON_NODE(type) ((type) & EPSILON_BIT) + +struct re_string_t +{ + /* Indicate the raw buffer which is the original string passed as an + argument of regexec(), re_search(), etc.. */ + const unsigned char *raw_mbs; + /* Store the multibyte string. In case of "case insensitive mode" like + REG_ICASE, upper cases of the string are stored, otherwise MBS points + the same address that RAW_MBS points. */ + unsigned char *mbs; +#ifdef RE_ENABLE_I18N + /* Store the wide character string which is corresponding to MBS. */ + wint_t *wcs; + int *offsets; + mbstate_t cur_state; +#endif + /* Index in RAW_MBS. Each character mbs[i] corresponds to + raw_mbs[raw_mbs_idx + i]. */ + int raw_mbs_idx; + /* The length of the valid characters in the buffers. */ + int valid_len; + /* The corresponding number of bytes in raw_mbs array. */ + int valid_raw_len; + /* The length of the buffers MBS and WCS. */ + int bufs_len; + /* The index in MBS, which is updated by re_string_fetch_byte. */ + int cur_idx; + /* length of RAW_MBS array. */ + int raw_len; + /* This is RAW_LEN - RAW_MBS_IDX + VALID_LEN - VALID_RAW_LEN. */ + int len; + /* End of the buffer may be shorter than its length in the cases such + as re_match_2, re_search_2. Then, we use STOP for end of the buffer + instead of LEN. */ + int raw_stop; + /* This is RAW_STOP - RAW_MBS_IDX adjusted through OFFSETS. */ + int stop; + + /* The context of mbs[0]. We store the context independently, since + the context of mbs[0] may be different from raw_mbs[0], which is + the beginning of the input string. */ + unsigned int tip_context; + /* The translation passed as a part of an argument of re_compile_pattern. */ + RE_TRANSLATE_TYPE trans; + /* Copy of re_dfa_t's word_char. */ + re_const_bitset_ptr_t word_char; + /* 1 if REG_ICASE. */ + unsigned char icase; + unsigned char is_utf8; + unsigned char map_notascii; + unsigned char mbs_allocated; + unsigned char offsets_needed; + unsigned char newline_anchor; + unsigned char word_ops_used; + int mb_cur_max; +}; +typedef struct re_string_t re_string_t; + + +struct re_dfa_t; +typedef struct re_dfa_t re_dfa_t; + +#ifndef _LIBC +# ifdef __i386__ +# define internal_function __attribute ((regparm (3), stdcall)) +# else +# define internal_function +# endif +#endif + +static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr, + int new_buf_len) + internal_function; +#ifdef RE_ENABLE_I18N +static void build_wcs_buffer (re_string_t *pstr) internal_function; +static int build_wcs_upper_buffer (re_string_t *pstr) internal_function; +#endif /* RE_ENABLE_I18N */ +static void build_upper_buffer (re_string_t *pstr) internal_function; +static void re_string_translate_buffer (re_string_t *pstr) internal_function; +static unsigned int re_string_context_at (const re_string_t *input, int idx, + int eflags) + internal_function __attribute ((pure)); +#define re_string_peek_byte(pstr, offset) \ + ((pstr)->mbs[(pstr)->cur_idx + offset]) +#define re_string_fetch_byte(pstr) \ + ((pstr)->mbs[(pstr)->cur_idx++]) +#define re_string_first_byte(pstr, idx) \ + ((idx) == (pstr)->valid_len || (pstr)->wcs[idx] != WEOF) +#define re_string_is_single_byte_char(pstr, idx) \ + ((pstr)->wcs[idx] != WEOF && ((pstr)->valid_len == (idx) + 1 \ + || (pstr)->wcs[(idx) + 1] != WEOF)) +#define re_string_eoi(pstr) ((pstr)->stop <= (pstr)->cur_idx) +#define re_string_cur_idx(pstr) ((pstr)->cur_idx) +#define re_string_get_buffer(pstr) ((pstr)->mbs) +#define re_string_length(pstr) ((pstr)->len) +#define re_string_byte_at(pstr,idx) ((pstr)->mbs[idx]) +#define re_string_skip_bytes(pstr,idx) ((pstr)->cur_idx += (idx)) +#define re_string_set_index(pstr,idx) ((pstr)->cur_idx = (idx)) + +#ifdef __GNUC__ +# define alloca(size) __builtin_alloca (size) +# define HAVE_ALLOCA 1 +#elif defined(_MSC_VER) +# include +# define alloca _alloca +# define HAVE_ALLOCA 1 +#else +# error No alloca() +#endif + +#ifndef _LIBC +# if HAVE_ALLOCA +/* The OS usually guarantees only one guard page at the bottom of the stack, + and a page size can be as small as 4096 bytes. So we cannot safely + allocate anything larger than 4096 bytes. Also care for the possibility + of a few compiler-allocated temporary stack slots. */ +# define __libc_use_alloca(n) ((n) < 4032) +# else +/* alloca is implemented with malloc, so just use malloc. */ +# define __libc_use_alloca(n) 0 +# endif +#endif + +#define re_malloc(t,n) ((t *) malloc ((n) * sizeof (t))) +#define re_realloc(p,t,n) ((t *) realloc (p, (n) * sizeof (t))) +#define re_free(p) free (p) + +struct bin_tree_t +{ + struct bin_tree_t *parent; + struct bin_tree_t *left; + struct bin_tree_t *right; + struct bin_tree_t *first; + struct bin_tree_t *next; + + re_token_t token; + + /* `node_idx' is the index in dfa->nodes, if `type' == 0. + Otherwise `type' indicate the type of this node. */ + int node_idx; +}; +typedef struct bin_tree_t bin_tree_t; + +#define BIN_TREE_STORAGE_SIZE \ + ((1024 - sizeof (void *)) / sizeof (bin_tree_t)) + +struct bin_tree_storage_t +{ + struct bin_tree_storage_t *next; + bin_tree_t data[BIN_TREE_STORAGE_SIZE]; +}; +typedef struct bin_tree_storage_t bin_tree_storage_t; + +#define CONTEXT_WORD 1 +#define CONTEXT_NEWLINE (CONTEXT_WORD << 1) +#define CONTEXT_BEGBUF (CONTEXT_NEWLINE << 1) +#define CONTEXT_ENDBUF (CONTEXT_BEGBUF << 1) + +#define IS_WORD_CONTEXT(c) ((c) & CONTEXT_WORD) +#define IS_NEWLINE_CONTEXT(c) ((c) & CONTEXT_NEWLINE) +#define IS_BEGBUF_CONTEXT(c) ((c) & CONTEXT_BEGBUF) +#define IS_ENDBUF_CONTEXT(c) ((c) & CONTEXT_ENDBUF) +#define IS_ORDINARY_CONTEXT(c) ((c) == 0) + +#define IS_WORD_CHAR(ch) (isalnum (ch) || (ch) == '_') +#define IS_NEWLINE(ch) ((ch) == NEWLINE_CHAR) +#define IS_WIDE_WORD_CHAR(ch) (iswalnum (ch) || (ch) == L'_') +#define IS_WIDE_NEWLINE(ch) ((ch) == WIDE_NEWLINE_CHAR) + +#define NOT_SATISFY_PREV_CONSTRAINT(constraint,context) \ + ((((constraint) & PREV_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \ + || ((constraint & PREV_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \ + || ((constraint & PREV_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context))\ + || ((constraint & PREV_BEGBUF_CONSTRAINT) && !IS_BEGBUF_CONTEXT (context))) + +#define NOT_SATISFY_NEXT_CONSTRAINT(constraint,context) \ + ((((constraint) & NEXT_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \ + || (((constraint) & NEXT_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \ + || (((constraint) & NEXT_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context)) \ + || (((constraint) & NEXT_ENDBUF_CONSTRAINT) && !IS_ENDBUF_CONTEXT (context))) + +struct re_dfastate_t +{ + unsigned int hash; + re_node_set nodes; + re_node_set non_eps_nodes; + re_node_set inveclosure; + re_node_set *entrance_nodes; + struct re_dfastate_t **trtable, **word_trtable; + unsigned int context : 4; + unsigned int halt : 1; + /* If this state can accept `multi byte'. + Note that we refer to multibyte characters, and multi character + collating elements as `multi byte'. */ + unsigned int accept_mb : 1; + /* If this state has backreference node(s). */ + unsigned int has_backref : 1; + unsigned int has_constraint : 1; +}; +typedef struct re_dfastate_t re_dfastate_t; + +struct re_state_table_entry +{ + int num; + int alloc; + re_dfastate_t **array; +}; + +/* Array type used in re_sub_match_last_t and re_sub_match_top_t. */ + +typedef struct +{ + int next_idx; + int alloc; + re_dfastate_t **array; +} state_array_t; + +/* Store information about the node NODE whose type is OP_CLOSE_SUBEXP. */ + +typedef struct +{ + int node; + int str_idx; /* The position NODE match at. */ + state_array_t path; +} re_sub_match_last_t; + +/* Store information about the node NODE whose type is OP_OPEN_SUBEXP. + And information about the node, whose type is OP_CLOSE_SUBEXP, + corresponding to NODE is stored in LASTS. */ + +typedef struct +{ + int str_idx; + int node; + state_array_t *path; + int alasts; /* Allocation size of LASTS. */ + int nlasts; /* The number of LASTS. */ + re_sub_match_last_t **lasts; +} re_sub_match_top_t; + +struct re_backref_cache_entry +{ + int node; + int str_idx; + int subexp_from; + int subexp_to; + char more; + char unused; + unsigned short int eps_reachable_subexps_map; +}; + +typedef struct +{ + /* The string object corresponding to the input string. */ + re_string_t input; +#if defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L) + const re_dfa_t *const dfa; +#else + const re_dfa_t *dfa; +#endif + /* EFLAGS of the argument of regexec. */ + int eflags; + /* Where the matching ends. */ + int match_last; + int last_node; + /* The state log used by the matcher. */ + re_dfastate_t **state_log; + int state_log_top; + /* Back reference cache. */ + int nbkref_ents; + int abkref_ents; + struct re_backref_cache_entry *bkref_ents; + int max_mb_elem_len; + int nsub_tops; + int asub_tops; + re_sub_match_top_t **sub_tops; +} re_match_context_t; + +typedef struct +{ + re_dfastate_t **sifted_states; + re_dfastate_t **limited_states; + int last_node; + int last_str_idx; + re_node_set limits; +} re_sift_context_t; + +struct re_fail_stack_ent_t +{ + int idx; + int node; + regmatch_t *regs; + re_node_set eps_via_nodes; +}; + +struct re_fail_stack_t +{ + int num; + int alloc; + struct re_fail_stack_ent_t *stack; +}; + +struct re_dfa_t +{ + re_token_t *nodes; + size_t nodes_alloc; + size_t nodes_len; + int *nexts; + int *org_indices; + re_node_set *edests; + re_node_set *eclosures; + re_node_set *inveclosures; + struct re_state_table_entry *state_table; + re_dfastate_t *init_state; + re_dfastate_t *init_state_word; + re_dfastate_t *init_state_nl; + re_dfastate_t *init_state_begbuf; + bin_tree_t *str_tree; + bin_tree_storage_t *str_tree_storage; + re_bitset_ptr_t sb_char; + int str_tree_storage_idx; + + /* number of subexpressions `re_nsub' is in regex_t. */ + unsigned int state_hash_mask; + int init_node; + int nbackref; /* The number of backreference in this dfa. */ + + /* Bitmap expressing which backreference is used. */ + bitset_word_t used_bkref_map; + bitset_word_t completed_bkref_map; + + unsigned int has_plural_match : 1; + /* If this dfa has "multibyte node", which is a backreference or + a node which can accept multibyte character or multi character + collating element. */ + unsigned int has_mb_node : 1; + unsigned int is_utf8 : 1; + unsigned int map_notascii : 1; + unsigned int word_ops_used : 1; + int mb_cur_max; + bitset_t word_char; + reg_syntax_t syntax; + int *subexp_map; +#ifdef DEBUG + char* re_str; +#endif + __libc_lock_define (, lock) +}; + +#define re_node_set_init_empty(set) memset (set, '\0', sizeof (re_node_set)) +#define re_node_set_remove(set,id) \ + (re_node_set_remove_at (set, re_node_set_contains (set, id) - 1)) +#define re_node_set_empty(p) ((p)->nelem = 0) +#define re_node_set_free(set) re_free ((set)->elems) + + +typedef enum +{ + SB_CHAR, + MB_CHAR, + EQUIV_CLASS, + COLL_SYM, + CHAR_CLASS +} bracket_elem_type; + +typedef struct +{ + bracket_elem_type type; + union + { + unsigned char ch; + unsigned char *name; + wchar_t wch; + } opr; +} bracket_elem_t; + + +/* Inline functions for bitset operation. */ +static inline void +bitset_not (bitset_t set) +{ + int bitset_i; + for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) + set[bitset_i] = ~set[bitset_i]; +} + +static inline void +bitset_merge (bitset_t dest, const bitset_t src) +{ + int bitset_i; + for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) + dest[bitset_i] |= src[bitset_i]; +} + +static inline void +bitset_mask (bitset_t dest, const bitset_t src) +{ + int bitset_i; + for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) + dest[bitset_i] &= src[bitset_i]; +} + +#ifdef RE_ENABLE_I18N +/* Inline functions for re_string. */ +static inline int +internal_function __attribute ((pure)) +re_string_char_size_at (const re_string_t *pstr, int idx) +{ + int byte_idx; + if (pstr->mb_cur_max == 1) + return 1; + for (byte_idx = 1; idx + byte_idx < pstr->valid_len; ++byte_idx) + if (pstr->wcs[idx + byte_idx] != WEOF) + break; + return byte_idx; +} + +static inline wint_t +internal_function __attribute ((pure)) +re_string_wchar_at (const re_string_t *pstr, int idx) +{ + if (pstr->mb_cur_max == 1) + return (wint_t) pstr->mbs[idx]; + return (wint_t) pstr->wcs[idx]; +} + +static int +internal_function __attribute ((pure)) +re_string_elem_size_at (const re_string_t *pstr, int idx) +{ +# ifdef _LIBC + const unsigned char *p, *extra; + const int32_t *table, *indirect; + int32_t tmp; +# include + uint_fast32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); + + if (nrules != 0) + { + table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); + extra = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB); + indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, + _NL_COLLATE_INDIRECTMB); + p = pstr->mbs + idx; + tmp = findidx (&p); + return p - pstr->mbs - idx; + } + else +# endif /* _LIBC */ + return 1; +} +#endif /* RE_ENABLE_I18N */ + +#endif /* _REGEX_INTERNAL_H */ diff --git a/Build/source/texk/chktex/regex/regexec.c b/Build/source/texk/chktex/regex/regexec.c new file mode 100644 index 00000000000..bdfa3550a7d --- /dev/null +++ b/Build/source/texk/chktex/regex/regexec.c @@ -0,0 +1,4329 @@ +/* Extended regular expression matching and search library. + Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Isamu Hasegawa . + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +static reg_errcode_t match_ctx_init (re_match_context_t *cache, int eflags, + int n) internal_function; +static void match_ctx_clean (re_match_context_t *mctx) internal_function; +static void match_ctx_free (re_match_context_t *cache) internal_function; +static reg_errcode_t match_ctx_add_entry (re_match_context_t *cache, int node, + int str_idx, int from, int to) + internal_function; +static int search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx) + internal_function; +static reg_errcode_t match_ctx_add_subtop (re_match_context_t *mctx, int node, + int str_idx) internal_function; +static re_sub_match_last_t * match_ctx_add_sublast (re_sub_match_top_t *subtop, + int node, int str_idx) + internal_function; +static void sift_ctx_init (re_sift_context_t *sctx, re_dfastate_t **sifted_sts, + re_dfastate_t **limited_sts, int last_node, + int last_str_idx) + internal_function; +static reg_errcode_t re_search_internal (const regex_t *preg, + const char *string, int length, + int start, int range, int stop, + size_t nmatch, regmatch_t pmatch[], + int eflags) internal_function; +static int re_search_2_stub (struct re_pattern_buffer *bufp, + const char *string1, int length1, + const char *string2, int length2, + int start, int range, struct re_registers *regs, + int stop, int ret_len) internal_function; +static int re_search_stub (struct re_pattern_buffer *bufp, + const char *string, int length, int start, + int range, int stop, struct re_registers *regs, + int ret_len) internal_function; +static unsigned re_copy_regs (struct re_registers *regs, regmatch_t *pmatch, + int nregs, int regs_allocated) internal_function; +static reg_errcode_t prune_impossible_nodes (re_match_context_t *mctx) + internal_function; +static int check_matching (re_match_context_t *mctx, int fl_longest_match, + int *p_match_first) internal_function; +static int check_halt_state_context (const re_match_context_t *mctx, + const re_dfastate_t *state, int idx) + internal_function; +static void update_regs (const re_dfa_t *dfa, regmatch_t *pmatch, + regmatch_t *prev_idx_match, int cur_node, + int cur_idx, int nmatch) internal_function; +static reg_errcode_t push_fail_stack (struct re_fail_stack_t *fs, + int str_idx, int dest_node, int nregs, + regmatch_t *regs, + re_node_set *eps_via_nodes) + internal_function; +static reg_errcode_t set_regs (const regex_t *preg, + const re_match_context_t *mctx, + size_t nmatch, regmatch_t *pmatch, + int fl_backtrack) internal_function; +static reg_errcode_t free_fail_stack_return (struct re_fail_stack_t *fs) + internal_function; + +#ifdef RE_ENABLE_I18N +static int sift_states_iter_mb (const re_match_context_t *mctx, + re_sift_context_t *sctx, + int node_idx, int str_idx, int max_str_idx) + internal_function; +#endif /* RE_ENABLE_I18N */ +static reg_errcode_t sift_states_backward (const re_match_context_t *mctx, + re_sift_context_t *sctx) + internal_function; +static reg_errcode_t build_sifted_states (const re_match_context_t *mctx, + re_sift_context_t *sctx, int str_idx, + re_node_set *cur_dest) + internal_function; +static reg_errcode_t update_cur_sifted_state (const re_match_context_t *mctx, + re_sift_context_t *sctx, + int str_idx, + re_node_set *dest_nodes) + internal_function; +static reg_errcode_t add_epsilon_src_nodes (const re_dfa_t *dfa, + re_node_set *dest_nodes, + const re_node_set *candidates) + internal_function; +static int check_dst_limits (const re_match_context_t *mctx, + re_node_set *limits, + int dst_node, int dst_idx, int src_node, + int src_idx) internal_function; +static int check_dst_limits_calc_pos_1 (const re_match_context_t *mctx, + int boundaries, int subexp_idx, + int from_node, int bkref_idx) + internal_function; +static int check_dst_limits_calc_pos (const re_match_context_t *mctx, + int limit, int subexp_idx, + int node, int str_idx, + int bkref_idx) internal_function; +static reg_errcode_t check_subexp_limits (const re_dfa_t *dfa, + re_node_set *dest_nodes, + const re_node_set *candidates, + re_node_set *limits, + struct re_backref_cache_entry *bkref_ents, + int str_idx) internal_function; +static reg_errcode_t sift_states_bkref (const re_match_context_t *mctx, + re_sift_context_t *sctx, + int str_idx, const re_node_set *candidates) + internal_function; +static reg_errcode_t merge_state_array (const re_dfa_t *dfa, + re_dfastate_t **dst, + re_dfastate_t **src, int num) + internal_function; +static re_dfastate_t *find_recover_state (reg_errcode_t *err, + re_match_context_t *mctx) internal_function; +static re_dfastate_t *transit_state (reg_errcode_t *err, + re_match_context_t *mctx, + re_dfastate_t *state) internal_function; +static re_dfastate_t *merge_state_with_log (reg_errcode_t *err, + re_match_context_t *mctx, + re_dfastate_t *next_state) + internal_function; +static reg_errcode_t check_subexp_matching_top (re_match_context_t *mctx, + re_node_set *cur_nodes, + int str_idx) internal_function; +#if 0 +static re_dfastate_t *transit_state_sb (reg_errcode_t *err, + re_match_context_t *mctx, + re_dfastate_t *pstate) + internal_function; +#endif +#ifdef RE_ENABLE_I18N +static reg_errcode_t transit_state_mb (re_match_context_t *mctx, + re_dfastate_t *pstate) + internal_function; +#endif /* RE_ENABLE_I18N */ +static reg_errcode_t transit_state_bkref (re_match_context_t *mctx, + const re_node_set *nodes) + internal_function; +static reg_errcode_t get_subexp (re_match_context_t *mctx, + int bkref_node, int bkref_str_idx) + internal_function; +static reg_errcode_t get_subexp_sub (re_match_context_t *mctx, + const re_sub_match_top_t *sub_top, + re_sub_match_last_t *sub_last, + int bkref_node, int bkref_str) + internal_function; +static int find_subexp_node (const re_dfa_t *dfa, const re_node_set *nodes, + int subexp_idx, int type) internal_function; +static reg_errcode_t check_arrival (re_match_context_t *mctx, + state_array_t *path, int top_node, + int top_str, int last_node, int last_str, + int type) internal_function; +static reg_errcode_t check_arrival_add_next_nodes (re_match_context_t *mctx, + int str_idx, + re_node_set *cur_nodes, + re_node_set *next_nodes) + internal_function; +static reg_errcode_t check_arrival_expand_ecl (const re_dfa_t *dfa, + re_node_set *cur_nodes, + int ex_subexp, int type) + internal_function; +static reg_errcode_t check_arrival_expand_ecl_sub (const re_dfa_t *dfa, + re_node_set *dst_nodes, + int target, int ex_subexp, + int type) internal_function; +static reg_errcode_t expand_bkref_cache (re_match_context_t *mctx, + re_node_set *cur_nodes, int cur_str, + int subexp_num, int type) + internal_function; +static int build_trtable (const re_dfa_t *dfa, + re_dfastate_t *state) internal_function; +#ifdef RE_ENABLE_I18N +static int check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, + const re_string_t *input, int idx) + internal_function; +# ifdef _LIBC +static unsigned int find_collation_sequence_value (const unsigned char *mbs, + size_t name_len) + internal_function; +# endif /* _LIBC */ +#endif /* RE_ENABLE_I18N */ +static int group_nodes_into_DFAstates (const re_dfa_t *dfa, + const re_dfastate_t *state, + re_node_set *states_node, + bitset_t *states_ch) internal_function; +static int check_node_accept (const re_match_context_t *mctx, + const re_token_t *node, int idx) + internal_function; +static reg_errcode_t extend_buffers (re_match_context_t *mctx) + internal_function; + +/* Entry point for POSIX code. */ + +/* regexec searches for a given pattern, specified by PREG, in the + string STRING. + + If NMATCH is zero or REG_NOSUB was set in the cflags argument to + `regcomp', we ignore PMATCH. Otherwise, we assume PMATCH has at + least NMATCH elements, and we set them to the offsets of the + corresponding matched substrings. + + EFLAGS specifies `execution flags' which affect matching: if + REG_NOTBOL is set, then ^ does not match at the beginning of the + string; if REG_NOTEOL is set, then $ does not match at the end. + + We return 0 if we find a match and REG_NOMATCH if not. */ + +int +regexec (preg, string, nmatch, pmatch, eflags) + const regex_t *__restrict preg; + const char *__restrict string; + size_t nmatch; + regmatch_t pmatch[]; + int eflags; +{ + reg_errcode_t err; + int start, length; + re_dfa_t *dfa = (re_dfa_t *) preg->buffer; + + if (eflags & ~(REG_NOTBOL | REG_NOTEOL | REG_STARTEND)) + return REG_BADPAT; + + if (eflags & REG_STARTEND) + { + start = pmatch[0].rm_so; + length = pmatch[0].rm_eo; + } + else + { + start = 0; + length = strlen (string); + } + + __libc_lock_lock (dfa->lock); + if (preg->no_sub) + err = re_search_internal (preg, string, length, start, length - start, + length, 0, NULL, eflags); + else + err = re_search_internal (preg, string, length, start, length - start, + length, nmatch, pmatch, eflags); + __libc_lock_unlock (dfa->lock); + return err != REG_NOERROR; +} + +#ifdef _LIBC +# include +versioned_symbol (libc, __regexec, regexec, GLIBC_2_3_4); + +# if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3_4) +__typeof__ (__regexec) __compat_regexec; + +int +attribute_compat_text_section +__compat_regexec (const regex_t *__restrict preg, + const char *__restrict string, size_t nmatch, + regmatch_t pmatch[], int eflags) +{ + return regexec (preg, string, nmatch, pmatch, + eflags & (REG_NOTBOL | REG_NOTEOL)); +} +compat_symbol (libc, __compat_regexec, regexec, GLIBC_2_0); +# endif +#endif + +/* Entry points for GNU code. */ + +/* re_match, re_search, re_match_2, re_search_2 + + The former two functions operate on STRING with length LENGTH, + while the later two operate on concatenation of STRING1 and STRING2 + with lengths LENGTH1 and LENGTH2, respectively. + + re_match() matches the compiled pattern in BUFP against the string, + starting at index START. + + re_search() first tries matching at index START, then it tries to match + starting from index START + 1, and so on. The last start position tried + is START + RANGE. (Thus RANGE = 0 forces re_search to operate the same + way as re_match().) + + The parameter STOP of re_{match,search}_2 specifies that no match exceeding + the first STOP characters of the concatenation of the strings should be + concerned. + + If REGS is not NULL, and BUFP->no_sub is not set, the offsets of the match + and all groups is stroed in REGS. (For the "_2" variants, the offsets are + computed relative to the concatenation, not relative to the individual + strings.) + + On success, re_match* functions return the length of the match, re_search* + return the position of the start of the match. Return value -1 means no + match was found and -2 indicates an internal error. */ + +int +re_match (bufp, string, length, start, regs) + struct re_pattern_buffer *bufp; + const char *string; + int length, start; + struct re_registers *regs; +{ + return re_search_stub (bufp, string, length, start, 0, length, regs, 1); +} +#ifdef _LIBC +weak_alias (__re_match, re_match) +#endif + +int +re_search (bufp, string, length, start, range, regs) + struct re_pattern_buffer *bufp; + const char *string; + int length, start, range; + struct re_registers *regs; +{ + return re_search_stub (bufp, string, length, start, range, length, regs, 0); +} +#ifdef _LIBC +weak_alias (__re_search, re_search) +#endif + +int +re_match_2 (bufp, string1, length1, string2, length2, start, regs, stop) + struct re_pattern_buffer *bufp; + const char *string1, *string2; + int length1, length2, start, stop; + struct re_registers *regs; +{ + return re_search_2_stub (bufp, string1, length1, string2, length2, + start, 0, regs, stop, 1); +} +#ifdef _LIBC +weak_alias (__re_match_2, re_match_2) +#endif + +int +re_search_2 (bufp, string1, length1, string2, length2, start, range, regs, stop) + struct re_pattern_buffer *bufp; + const char *string1, *string2; + int length1, length2, start, range, stop; + struct re_registers *regs; +{ + return re_search_2_stub (bufp, string1, length1, string2, length2, + start, range, regs, stop, 0); +} +#ifdef _LIBC +weak_alias (__re_search_2, re_search_2) +#endif + +static int +re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs, + stop, ret_len) + struct re_pattern_buffer *bufp; + const char *string1, *string2; + int length1, length2, start, range, stop, ret_len; + struct re_registers *regs; +{ + const char *str; + int rval; + int len = length1 + length2; + int free_str = 0; + + if (BE (length1 < 0 || length2 < 0 || stop < 0, 0)) + return -2; + + /* Concatenate the strings. */ + if (length2 > 0) + if (length1 > 0) + { + char *s = re_malloc (char, len); + + if (BE (s == NULL, 0)) + return -2; +#ifdef _LIBC + memcpy (__mempcpy (s, string1, length1), string2, length2); +#else + memcpy (s, string1, length1); + memcpy (s + length1, string2, length2); +#endif + str = s; + free_str = 1; + } + else + str = string2; + else + str = string1; + + rval = re_search_stub (bufp, str, len, start, range, stop, regs, + ret_len); + if (free_str) + re_free ((char *) str); + return rval; +} + +/* The parameters have the same meaning as those of re_search. + Additional parameters: + If RET_LEN is nonzero the length of the match is returned (re_match style); + otherwise the position of the match is returned. */ + +static int +re_search_stub (bufp, string, length, start, range, stop, regs, ret_len) + struct re_pattern_buffer *bufp; + const char *string; + int length, start, range, stop, ret_len; + struct re_registers *regs; +{ + reg_errcode_t result; + regmatch_t *pmatch; + int nregs, rval; + int eflags = 0; + re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; + + /* Check for out-of-range. */ + if (BE (start < 0 || start > length, 0)) + return -1; + if (BE (start + range > length, 0)) + range = length - start; + else if (BE (start + range < 0, 0)) + range = -start; + + __libc_lock_lock (dfa->lock); + + eflags |= (bufp->not_bol) ? REG_NOTBOL : 0; + eflags |= (bufp->not_eol) ? REG_NOTEOL : 0; + + /* Compile fastmap if we haven't yet. */ + if (range > 0 && bufp->fastmap != NULL && !bufp->fastmap_accurate) + re_compile_fastmap (bufp); + + if (BE (bufp->no_sub, 0)) + regs = NULL; + + /* We need at least 1 register. */ + if (regs == NULL) + nregs = 1; + else if (BE (bufp->regs_allocated == REGS_FIXED && + regs->num_regs < bufp->re_nsub + 1, 0)) + { + nregs = regs->num_regs; + if (BE (nregs < 1, 0)) + { + /* Nothing can be copied to regs. */ + regs = NULL; + nregs = 1; + } + } + else + nregs = bufp->re_nsub + 1; + pmatch = re_malloc (regmatch_t, nregs); + if (BE (pmatch == NULL, 0)) + { + rval = -2; + goto out; + } + + result = re_search_internal (bufp, string, length, start, range, stop, + nregs, pmatch, eflags); + + rval = 0; + + /* I hope we needn't fill ther regs with -1's when no match was found. */ + if (result != REG_NOERROR) + rval = -1; + else if (regs != NULL) + { + /* If caller wants register contents data back, copy them. */ + bufp->regs_allocated = re_copy_regs (regs, pmatch, nregs, + bufp->regs_allocated); + if (BE (bufp->regs_allocated == REGS_UNALLOCATED, 0)) + rval = -2; + } + + if (BE (rval == 0, 1)) + { + if (ret_len) + { + assert (pmatch[0].rm_so == start); + rval = pmatch[0].rm_eo - start; + } + else + rval = pmatch[0].rm_so; + } + re_free (pmatch); + out: + __libc_lock_unlock (dfa->lock); + return rval; +} + +static unsigned +re_copy_regs (regs, pmatch, nregs, regs_allocated) + struct re_registers *regs; + regmatch_t *pmatch; + int nregs, regs_allocated; +{ + int rval = REGS_REALLOCATE; + int i; + int need_regs = nregs + 1; + /* We need one extra element beyond `num_regs' for the `-1' marker GNU code + uses. */ + + /* Have the register data arrays been allocated? */ + if (regs_allocated == REGS_UNALLOCATED) + { /* No. So allocate them with malloc. */ + regs->start = re_malloc (regoff_t, need_regs); + regs->end = re_malloc (regoff_t, need_regs); + if (BE (regs->start == NULL, 0) || BE (regs->end == NULL, 0)) + return REGS_UNALLOCATED; + regs->num_regs = need_regs; + } + else if (regs_allocated == REGS_REALLOCATE) + { /* Yes. If we need more elements than were already + allocated, reallocate them. If we need fewer, just + leave it alone. */ + if (BE (need_regs > regs->num_regs, 0)) + { + regoff_t *new_start = re_realloc (regs->start, regoff_t, need_regs); + regoff_t *new_end = re_realloc (regs->end, regoff_t, need_regs); + if (BE (new_start == NULL, 0) || BE (new_end == NULL, 0)) + return REGS_UNALLOCATED; + regs->start = new_start; + regs->end = new_end; + regs->num_regs = need_regs; + } + } + else + { + assert (regs_allocated == REGS_FIXED); + /* This function may not be called with REGS_FIXED and nregs too big. */ + assert (regs->num_regs >= nregs); + rval = REGS_FIXED; + } + + /* Copy the regs. */ + for (i = 0; i < nregs; ++i) + { + regs->start[i] = pmatch[i].rm_so; + regs->end[i] = pmatch[i].rm_eo; + } + for ( ; i < regs->num_regs; ++i) + regs->start[i] = regs->end[i] = -1; + + return rval; +} + +/* Set REGS to hold NUM_REGS registers, storing them in STARTS and + ENDS. Subsequent matches using PATTERN_BUFFER and REGS will use + this memory for recording register information. STARTS and ENDS + must be allocated using the malloc library routine, and must each + be at least NUM_REGS * sizeof (regoff_t) bytes long. + + If NUM_REGS == 0, then subsequent matches should allocate their own + register data. + + Unless this function is called, the first search or match using + PATTERN_BUFFER will allocate its own register data, without + freeing the old data. */ + +void +re_set_registers (bufp, regs, num_regs, starts, ends) + struct re_pattern_buffer *bufp; + struct re_registers *regs; + unsigned num_regs; + regoff_t *starts, *ends; +{ + if (num_regs) + { + bufp->regs_allocated = REGS_REALLOCATE; + regs->num_regs = num_regs; + regs->start = starts; + regs->end = ends; + } + else + { + bufp->regs_allocated = REGS_UNALLOCATED; + regs->num_regs = 0; + regs->start = regs->end = (regoff_t *) 0; + } +} +#ifdef _LIBC +weak_alias (__re_set_registers, re_set_registers) +#endif + +/* Entry points compatible with 4.2 BSD regex library. We don't define + them unless specifically requested. */ + +#if defined _REGEX_RE_COMP || defined _LIBC +int +# ifdef _LIBC +weak_function +# endif +re_exec (s) + const char *s; +{ + return 0 == regexec (&re_comp_buf, s, 0, NULL, 0); +} +#endif /* _REGEX_RE_COMP */ + +/* Internal entry point. */ + +/* Searches for a compiled pattern PREG in the string STRING, whose + length is LENGTH. NMATCH, PMATCH, and EFLAGS have the same + mingings with regexec. START, and RANGE have the same meanings + with re_search. + Return REG_NOERROR if we find a match, and REG_NOMATCH if not, + otherwise return the error code. + Note: We assume front end functions already check ranges. + (START + RANGE >= 0 && START + RANGE <= LENGTH) */ + +static reg_errcode_t +re_search_internal (preg, string, length, start, range, stop, nmatch, pmatch, + eflags) + const regex_t *preg; + const char *string; + int length, start, range, stop, eflags; + size_t nmatch; + regmatch_t pmatch[]; +{ + reg_errcode_t err; + const re_dfa_t *dfa = (const re_dfa_t *) preg->buffer; + int left_lim, right_lim, incr; + int fl_longest_match, match_first, match_kind, match_last = -1; + int extra_nmatch; + int sb, ch; +#if defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L) + re_match_context_t mctx = { .dfa = dfa }; +#else + re_match_context_t mctx; +#endif + char *fastmap = (preg->fastmap != NULL && preg->fastmap_accurate + && range && !preg->can_be_null) ? preg->fastmap : NULL; + RE_TRANSLATE_TYPE t = preg->translate; + +#if !(defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L)) + memset (&mctx, '\0', sizeof (re_match_context_t)); + mctx.dfa = dfa; +#endif + + extra_nmatch = (nmatch > preg->re_nsub) ? nmatch - (preg->re_nsub + 1) : 0; + nmatch -= extra_nmatch; + + /* Check if the DFA haven't been compiled. */ + if (BE (preg->used == 0 || dfa->init_state == NULL + || dfa->init_state_word == NULL || dfa->init_state_nl == NULL + || dfa->init_state_begbuf == NULL, 0)) + return REG_NOMATCH; + +#ifdef DEBUG + /* We assume front-end functions already check them. */ + assert (start + range >= 0 && start + range <= length); +#endif + + /* If initial states with non-begbuf contexts have no elements, + the regex must be anchored. If preg->newline_anchor is set, + we'll never use init_state_nl, so do not check it. */ + if (dfa->init_state->nodes.nelem == 0 + && dfa->init_state_word->nodes.nelem == 0 + && (dfa->init_state_nl->nodes.nelem == 0 + || !preg->newline_anchor)) + { + if (start != 0 && start + range != 0) + return REG_NOMATCH; + start = range = 0; + } + + /* We must check the longest matching, if nmatch > 0. */ + fl_longest_match = (nmatch != 0 || dfa->nbackref); + + err = re_string_allocate (&mctx.input, string, length, dfa->nodes_len + 1, + preg->translate, preg->syntax & RE_ICASE, dfa); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + mctx.input.stop = stop; + mctx.input.raw_stop = stop; + mctx.input.newline_anchor = preg->newline_anchor; + + err = match_ctx_init (&mctx, eflags, dfa->nbackref * 2); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + + /* We will log all the DFA states through which the dfa pass, + if nmatch > 1, or this dfa has "multibyte node", which is a + back-reference or a node which can accept multibyte character or + multi character collating element. */ + if (nmatch > 1 || dfa->has_mb_node) + { + mctx.state_log = re_malloc (re_dfastate_t *, mctx.input.bufs_len + 1); + if (BE (mctx.state_log == NULL, 0)) + { + err = REG_ESPACE; + goto free_return; + } + } + else + mctx.state_log = NULL; + + match_first = start; + mctx.input.tip_context = (eflags & REG_NOTBOL) ? CONTEXT_BEGBUF + : CONTEXT_NEWLINE | CONTEXT_BEGBUF; + + /* Check incrementally whether of not the input string match. */ + incr = (range < 0) ? -1 : 1; + left_lim = (range < 0) ? start + range : start; + right_lim = (range < 0) ? start : start + range; + sb = dfa->mb_cur_max == 1; + match_kind = + (fastmap + ? ((sb || !(preg->syntax & RE_ICASE || t) ? 4 : 0) + | (range >= 0 ? 2 : 0) + | (t != NULL ? 1 : 0)) + : 8); + + for (;; match_first += incr) + { + err = REG_NOMATCH; + if (match_first < left_lim || right_lim < match_first) + goto free_return; + + /* Advance as rapidly as possible through the string, until we + find a plausible place to start matching. This may be done + with varying efficiency, so there are various possibilities: + only the most common of them are specialized, in order to + save on code size. We use a switch statement for speed. */ + switch (match_kind) + { + case 8: + /* No fastmap. */ + break; + + case 7: + /* Fastmap with single-byte translation, match forward. */ + while (BE (match_first < right_lim, 1) + && !fastmap[t[(unsigned char) string[match_first]]]) + ++match_first; + goto forward_match_found_start_or_reached_end; + + case 6: + /* Fastmap without translation, match forward. */ + while (BE (match_first < right_lim, 1) + && !fastmap[(unsigned char) string[match_first]]) + ++match_first; + + forward_match_found_start_or_reached_end: + if (BE (match_first == right_lim, 0)) + { + ch = match_first >= length + ? 0 : (unsigned char) string[match_first]; + if (!fastmap[t ? t[ch] : ch]) + goto free_return; + } + break; + + case 4: + case 5: + /* Fastmap without multi-byte translation, match backwards. */ + while (match_first >= left_lim) + { + ch = match_first >= length + ? 0 : (unsigned char) string[match_first]; + if (fastmap[t ? t[ch] : ch]) + break; + --match_first; + } + if (match_first < left_lim) + goto free_return; + break; + + default: + /* In this case, we can't determine easily the current byte, + since it might be a component byte of a multibyte + character. Then we use the constructed buffer instead. */ + for (;;) + { + /* If MATCH_FIRST is out of the valid range, reconstruct the + buffers. */ + unsigned int offset = match_first - mctx.input.raw_mbs_idx; + if (BE (offset >= (unsigned int) mctx.input.valid_raw_len, 0)) + { + err = re_string_reconstruct (&mctx.input, match_first, + eflags); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + + offset = match_first - mctx.input.raw_mbs_idx; + } + /* If MATCH_FIRST is out of the buffer, leave it as '\0'. + Note that MATCH_FIRST must not be smaller than 0. */ + ch = (match_first >= length + ? 0 : re_string_byte_at (&mctx.input, offset)); + if (fastmap[ch]) + break; + match_first += incr; + if (match_first < left_lim || match_first > right_lim) + { + err = REG_NOMATCH; + goto free_return; + } + } + break; + } + + /* Reconstruct the buffers so that the matcher can assume that + the matching starts from the beginning of the buffer. */ + err = re_string_reconstruct (&mctx.input, match_first, eflags); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + +#ifdef RE_ENABLE_I18N + /* Don't consider this char as a possible match start if it part, + yet isn't the head, of a multibyte character. */ + if (!sb && !re_string_first_byte (&mctx.input, 0)) + continue; +#endif + + /* It seems to be appropriate one, then use the matcher. */ + /* We assume that the matching starts from 0. */ + mctx.state_log_top = mctx.nbkref_ents = mctx.max_mb_elem_len = 0; + match_last = check_matching (&mctx, fl_longest_match, + range >= 0 ? &match_first : NULL); + if (match_last != -1) + { + if (BE (match_last == -2, 0)) + { + err = REG_ESPACE; + goto free_return; + } + else + { + mctx.match_last = match_last; + if ((!preg->no_sub && nmatch > 1) || dfa->nbackref) + { + re_dfastate_t *pstate = mctx.state_log[match_last]; + mctx.last_node = check_halt_state_context (&mctx, pstate, + match_last); + } + if ((!preg->no_sub && nmatch > 1 && dfa->has_plural_match) + || dfa->nbackref) + { + err = prune_impossible_nodes (&mctx); + if (err == REG_NOERROR) + break; + if (BE (err != REG_NOMATCH, 0)) + goto free_return; + match_last = -1; + } + else + break; /* We found a match. */ + } + } + + match_ctx_clean (&mctx); + } + +#ifdef DEBUG + assert (match_last != -1); + assert (err == REG_NOERROR); +#endif + + /* Set pmatch[] if we need. */ + if (nmatch > 0) + { + int reg_idx; + + /* Initialize registers. */ + for (reg_idx = 1; reg_idx < nmatch; ++reg_idx) + pmatch[reg_idx].rm_so = pmatch[reg_idx].rm_eo = -1; + + /* Set the points where matching start/end. */ + pmatch[0].rm_so = 0; + pmatch[0].rm_eo = mctx.match_last; + + if (!preg->no_sub && nmatch > 1) + { + err = set_regs (preg, &mctx, nmatch, pmatch, + dfa->has_plural_match && dfa->nbackref > 0); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + + /* At last, add the offset to the each registers, since we slided + the buffers so that we could assume that the matching starts + from 0. */ + for (reg_idx = 0; reg_idx < nmatch; ++reg_idx) + if (pmatch[reg_idx].rm_so != -1) + { +#ifdef RE_ENABLE_I18N + if (BE (mctx.input.offsets_needed != 0, 0)) + { + pmatch[reg_idx].rm_so = + (pmatch[reg_idx].rm_so == mctx.input.valid_len + ? mctx.input.valid_raw_len + : mctx.input.offsets[pmatch[reg_idx].rm_so]); + pmatch[reg_idx].rm_eo = + (pmatch[reg_idx].rm_eo == mctx.input.valid_len + ? mctx.input.valid_raw_len + : mctx.input.offsets[pmatch[reg_idx].rm_eo]); + } +#else + assert (mctx.input.offsets_needed == 0); +#endif + pmatch[reg_idx].rm_so += match_first; + pmatch[reg_idx].rm_eo += match_first; + } + for (reg_idx = 0; reg_idx < extra_nmatch; ++reg_idx) + { + pmatch[nmatch + reg_idx].rm_so = -1; + pmatch[nmatch + reg_idx].rm_eo = -1; + } + + if (dfa->subexp_map) + for (reg_idx = 0; reg_idx + 1 < nmatch; reg_idx++) + if (dfa->subexp_map[reg_idx] != reg_idx) + { + pmatch[reg_idx + 1].rm_so + = pmatch[dfa->subexp_map[reg_idx] + 1].rm_so; + pmatch[reg_idx + 1].rm_eo + = pmatch[dfa->subexp_map[reg_idx] + 1].rm_eo; + } + } + + free_return: + re_free (mctx.state_log); + if (dfa->nbackref) + match_ctx_free (&mctx); + re_string_destruct (&mctx.input); + return err; +} + +static reg_errcode_t +prune_impossible_nodes (mctx) + re_match_context_t *mctx; +{ + const re_dfa_t *const dfa = mctx->dfa; + int halt_node, match_last; + reg_errcode_t ret; + re_dfastate_t **sifted_states; + re_dfastate_t **lim_states = NULL; + re_sift_context_t sctx; +#ifdef DEBUG + assert (mctx->state_log != NULL); +#endif + match_last = mctx->match_last; + halt_node = mctx->last_node; + sifted_states = re_malloc (re_dfastate_t *, match_last + 1); + if (BE (sifted_states == NULL, 0)) + { + ret = REG_ESPACE; + goto free_return; + } + if (dfa->nbackref) + { + lim_states = re_malloc (re_dfastate_t *, match_last + 1); + if (BE (lim_states == NULL, 0)) + { + ret = REG_ESPACE; + goto free_return; + } + while (1) + { + memset (lim_states, '\0', + sizeof (re_dfastate_t *) * (match_last + 1)); + sift_ctx_init (&sctx, sifted_states, lim_states, halt_node, + match_last); + ret = sift_states_backward (mctx, &sctx); + re_node_set_free (&sctx.limits); + if (BE (ret != REG_NOERROR, 0)) + goto free_return; + if (sifted_states[0] != NULL || lim_states[0] != NULL) + break; + do + { + --match_last; + if (match_last < 0) + { + ret = REG_NOMATCH; + goto free_return; + } + } while (mctx->state_log[match_last] == NULL + || !mctx->state_log[match_last]->halt); + halt_node = check_halt_state_context (mctx, + mctx->state_log[match_last], + match_last); + } + ret = merge_state_array (dfa, sifted_states, lim_states, + match_last + 1); + re_free (lim_states); + lim_states = NULL; + if (BE (ret != REG_NOERROR, 0)) + goto free_return; + } + else + { + sift_ctx_init (&sctx, sifted_states, lim_states, halt_node, match_last); + ret = sift_states_backward (mctx, &sctx); + re_node_set_free (&sctx.limits); + if (BE (ret != REG_NOERROR, 0)) + goto free_return; + } + re_free (mctx->state_log); + mctx->state_log = sifted_states; + sifted_states = NULL; + mctx->last_node = halt_node; + mctx->match_last = match_last; + ret = REG_NOERROR; + free_return: + re_free (sifted_states); + re_free (lim_states); + return ret; +} + +/* Acquire an initial state and return it. + We must select appropriate initial state depending on the context, + since initial states may have constraints like "\<", "^", etc.. */ + +static inline re_dfastate_t * +__attribute ((always_inline)) internal_function +acquire_init_state_context (reg_errcode_t *err, const re_match_context_t *mctx, + int idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + if (dfa->init_state->has_constraint) + { + unsigned int context; + context = re_string_context_at (&mctx->input, idx - 1, mctx->eflags); + if (IS_WORD_CONTEXT (context)) + return dfa->init_state_word; + else if (IS_ORDINARY_CONTEXT (context)) + return dfa->init_state; + else if (IS_BEGBUF_CONTEXT (context) && IS_NEWLINE_CONTEXT (context)) + return dfa->init_state_begbuf; + else if (IS_NEWLINE_CONTEXT (context)) + return dfa->init_state_nl; + else if (IS_BEGBUF_CONTEXT (context)) + { + /* It is relatively rare case, then calculate on demand. */ + return re_acquire_state_context (err, dfa, + dfa->init_state->entrance_nodes, + context); + } + else + /* Must not happen? */ + return dfa->init_state; + } + else + return dfa->init_state; +} + +/* Check whether the regular expression match input string INPUT or not, + and return the index where the matching end, return -1 if not match, + or return -2 in case of an error. + FL_LONGEST_MATCH means we want the POSIX longest matching. + If P_MATCH_FIRST is not NULL, and the match fails, it is set to the + next place where we may want to try matching. + Note that the matcher assume that the maching starts from the current + index of the buffer. */ + +static int +internal_function +check_matching (re_match_context_t *mctx, int fl_longest_match, + int *p_match_first) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err; + int match = 0; + int match_last = -1; + int cur_str_idx = re_string_cur_idx (&mctx->input); + re_dfastate_t *cur_state; + int at_init_state = p_match_first != NULL; + int next_start_idx = cur_str_idx; + + err = REG_NOERROR; + cur_state = acquire_init_state_context (&err, mctx, cur_str_idx); + /* An initial state must not be NULL (invalid). */ + if (BE (cur_state == NULL, 0)) + { + assert (err == REG_ESPACE); + return -2; + } + + if (mctx->state_log != NULL) + { + mctx->state_log[cur_str_idx] = cur_state; + + /* Check OP_OPEN_SUBEXP in the initial state in case that we use them + later. E.g. Processing back references. */ + if (BE (dfa->nbackref, 0)) + { + at_init_state = 0; + err = check_subexp_matching_top (mctx, &cur_state->nodes, 0); + if (BE (err != REG_NOERROR, 0)) + return err; + + if (cur_state->has_backref) + { + err = transit_state_bkref (mctx, &cur_state->nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + } + } + } + + /* If the RE accepts NULL string. */ + if (BE (cur_state->halt, 0)) + { + if (!cur_state->has_constraint + || check_halt_state_context (mctx, cur_state, cur_str_idx)) + { + if (!fl_longest_match) + return cur_str_idx; + else + { + match_last = cur_str_idx; + match = 1; + } + } + } + + while (!re_string_eoi (&mctx->input)) + { + re_dfastate_t *old_state = cur_state; + int next_char_idx = re_string_cur_idx (&mctx->input) + 1; + + if (BE (next_char_idx >= mctx->input.bufs_len, 0) + || (BE (next_char_idx >= mctx->input.valid_len, 0) + && mctx->input.valid_len < mctx->input.len)) + { + err = extend_buffers (mctx); + if (BE (err != REG_NOERROR, 0)) + { + assert (err == REG_ESPACE); + return -2; + } + } + + cur_state = transit_state (&err, mctx, cur_state); + if (mctx->state_log != NULL) + cur_state = merge_state_with_log (&err, mctx, cur_state); + + if (cur_state == NULL) + { + /* Reached the invalid state or an error. Try to recover a valid + state using the state log, if available and if we have not + already found a valid (even if not the longest) match. */ + if (BE (err != REG_NOERROR, 0)) + return -2; + + if (mctx->state_log == NULL + || (match && !fl_longest_match) + || (cur_state = find_recover_state (&err, mctx)) == NULL) + break; + } + + if (BE (at_init_state, 0)) + { + if (old_state == cur_state) + next_start_idx = next_char_idx; + else + at_init_state = 0; + } + + if (cur_state->halt) + { + /* Reached a halt state. + Check the halt state can satisfy the current context. */ + if (!cur_state->has_constraint + || check_halt_state_context (mctx, cur_state, + re_string_cur_idx (&mctx->input))) + { + /* We found an appropriate halt state. */ + match_last = re_string_cur_idx (&mctx->input); + match = 1; + + /* We found a match, do not modify match_first below. */ + p_match_first = NULL; + if (!fl_longest_match) + break; + } + } + } + + if (p_match_first) + *p_match_first += next_start_idx; + + return match_last; +} + +/* Check NODE match the current context. */ + +static int +internal_function +check_halt_node_context (const re_dfa_t *dfa, int node, unsigned int context) +{ + re_token_type_t type = dfa->nodes[node].type; + unsigned int constraint = dfa->nodes[node].constraint; + if (type != END_OF_RE) + return 0; + if (!constraint) + return 1; + if (NOT_SATISFY_NEXT_CONSTRAINT (constraint, context)) + return 0; + return 1; +} + +/* Check the halt state STATE match the current context. + Return 0 if not match, if the node, STATE has, is a halt node and + match the context, return the node. */ + +static int +internal_function +check_halt_state_context (const re_match_context_t *mctx, + const re_dfastate_t *state, int idx) +{ + int i; + unsigned int context; +#ifdef DEBUG + assert (state->halt); +#endif + context = re_string_context_at (&mctx->input, idx, mctx->eflags); + for (i = 0; i < state->nodes.nelem; ++i) + if (check_halt_node_context (mctx->dfa, state->nodes.elems[i], context)) + return state->nodes.elems[i]; + return 0; +} + +/* Compute the next node to which "NFA" transit from NODE("NFA" is a NFA + corresponding to the DFA). + Return the destination node, and update EPS_VIA_NODES, return -1 in case + of errors. */ + +static int +internal_function +proceed_next_node (const re_match_context_t *mctx, int nregs, regmatch_t *regs, + int *pidx, int node, re_node_set *eps_via_nodes, + struct re_fail_stack_t *fs) +{ + const re_dfa_t *const dfa = mctx->dfa; + int i, err; + if (IS_EPSILON_NODE (dfa->nodes[node].type)) + { + re_node_set *cur_nodes = &mctx->state_log[*pidx]->nodes; + re_node_set *edests = &dfa->edests[node]; + int dest_node; + err = re_node_set_insert (eps_via_nodes, node); + if (BE (err < 0, 0)) + return -2; + /* Pick up a valid destination, or return -1 if none is found. */ + for (dest_node = -1, i = 0; i < edests->nelem; ++i) + { + int candidate = edests->elems[i]; + if (!re_node_set_contains (cur_nodes, candidate)) + continue; + if (dest_node == -1) + dest_node = candidate; + + else + { + /* In order to avoid infinite loop like "(a*)*", return the second + epsilon-transition if the first was already considered. */ + if (re_node_set_contains (eps_via_nodes, dest_node)) + return candidate; + + /* Otherwise, push the second epsilon-transition on the fail stack. */ + else if (fs != NULL + && push_fail_stack (fs, *pidx, candidate, nregs, regs, + eps_via_nodes)) + return -2; + + /* We know we are going to exit. */ + break; + } + } + return dest_node; + } + else + { + int naccepted = 0; + re_token_type_t type = dfa->nodes[node].type; + +#ifdef RE_ENABLE_I18N + if (dfa->nodes[node].accept_mb) + naccepted = check_node_accept_bytes (dfa, node, &mctx->input, *pidx); + else +#endif /* RE_ENABLE_I18N */ + if (type == OP_BACK_REF) + { + int subexp_idx = dfa->nodes[node].opr.idx + 1; + naccepted = regs[subexp_idx].rm_eo - regs[subexp_idx].rm_so; + if (fs != NULL) + { + if (regs[subexp_idx].rm_so == -1 || regs[subexp_idx].rm_eo == -1) + return -1; + else if (naccepted) + { + char *buf = (char *) re_string_get_buffer (&mctx->input); + if (memcmp (buf + regs[subexp_idx].rm_so, buf + *pidx, + naccepted) != 0) + return -1; + } + } + + if (naccepted == 0) + { + int dest_node; + err = re_node_set_insert (eps_via_nodes, node); + if (BE (err < 0, 0)) + return -2; + dest_node = dfa->edests[node].elems[0]; + if (re_node_set_contains (&mctx->state_log[*pidx]->nodes, + dest_node)) + return dest_node; + } + } + + if (naccepted != 0 + || check_node_accept (mctx, dfa->nodes + node, *pidx)) + { + int dest_node = dfa->nexts[node]; + *pidx = (naccepted == 0) ? *pidx + 1 : *pidx + naccepted; + if (fs && (*pidx > mctx->match_last || mctx->state_log[*pidx] == NULL + || !re_node_set_contains (&mctx->state_log[*pidx]->nodes, + dest_node))) + return -1; + re_node_set_empty (eps_via_nodes); + return dest_node; + } + } + return -1; +} + +static reg_errcode_t +internal_function +push_fail_stack (struct re_fail_stack_t *fs, int str_idx, int dest_node, + int nregs, regmatch_t *regs, re_node_set *eps_via_nodes) +{ + reg_errcode_t err; + int num = fs->num++; + if (fs->num == fs->alloc) + { + struct re_fail_stack_ent_t *new_array; + new_array = realloc (fs->stack, (sizeof (struct re_fail_stack_ent_t) + * fs->alloc * 2)); + if (new_array == NULL) + return REG_ESPACE; + fs->alloc *= 2; + fs->stack = new_array; + } + fs->stack[num].idx = str_idx; + fs->stack[num].node = dest_node; + fs->stack[num].regs = re_malloc (regmatch_t, nregs); + if (fs->stack[num].regs == NULL) + return REG_ESPACE; + memcpy (fs->stack[num].regs, regs, sizeof (regmatch_t) * nregs); + err = re_node_set_init_copy (&fs->stack[num].eps_via_nodes, eps_via_nodes); + return err; +} + +static int +internal_function +pop_fail_stack (struct re_fail_stack_t *fs, int *pidx, int nregs, + regmatch_t *regs, re_node_set *eps_via_nodes) +{ + int num = --fs->num; + assert (num >= 0); + *pidx = fs->stack[num].idx; + memcpy (regs, fs->stack[num].regs, sizeof (regmatch_t) * nregs); + re_node_set_free (eps_via_nodes); + re_free (fs->stack[num].regs); + *eps_via_nodes = fs->stack[num].eps_via_nodes; + return fs->stack[num].node; +} + +/* Set the positions where the subexpressions are starts/ends to registers + PMATCH. + Note: We assume that pmatch[0] is already set, and + pmatch[i].rm_so == pmatch[i].rm_eo == -1 for 0 < i < nmatch. */ + +static reg_errcode_t +internal_function +set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch, + regmatch_t *pmatch, int fl_backtrack) +{ + const re_dfa_t *dfa = (const re_dfa_t *) preg->buffer; + int idx, cur_node; + re_node_set eps_via_nodes; + struct re_fail_stack_t *fs; + struct re_fail_stack_t fs_body = { 0, 2, NULL }; + regmatch_t *prev_idx_match; + int prev_idx_match_malloced = 0; + +#ifdef DEBUG + assert (nmatch > 1); + assert (mctx->state_log != NULL); +#endif + if (fl_backtrack) + { + fs = &fs_body; + fs->stack = re_malloc (struct re_fail_stack_ent_t, fs->alloc); + if (fs->stack == NULL) + return REG_ESPACE; + } + else + fs = NULL; + + cur_node = dfa->init_node; + re_node_set_init_empty (&eps_via_nodes); + + if (__libc_use_alloca (nmatch * sizeof (regmatch_t))) + prev_idx_match = (regmatch_t *) alloca (nmatch * sizeof (regmatch_t)); + else + { + prev_idx_match = re_malloc (regmatch_t, nmatch); + if (prev_idx_match == NULL) + { + free_fail_stack_return (fs); + return REG_ESPACE; + } + prev_idx_match_malloced = 1; + } + memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch); + + for (idx = pmatch[0].rm_so; idx <= pmatch[0].rm_eo ;) + { + update_regs (dfa, pmatch, prev_idx_match, cur_node, idx, nmatch); + + if (idx == pmatch[0].rm_eo && cur_node == mctx->last_node) + { + int reg_idx; + if (fs) + { + for (reg_idx = 0; reg_idx < nmatch; ++reg_idx) + if (pmatch[reg_idx].rm_so > -1 && pmatch[reg_idx].rm_eo == -1) + break; + if (reg_idx == nmatch) + { + re_node_set_free (&eps_via_nodes); + if (prev_idx_match_malloced) + re_free (prev_idx_match); + return free_fail_stack_return (fs); + } + cur_node = pop_fail_stack (fs, &idx, nmatch, pmatch, + &eps_via_nodes); + } + else + { + re_node_set_free (&eps_via_nodes); + if (prev_idx_match_malloced) + re_free (prev_idx_match); + return REG_NOERROR; + } + } + + /* Proceed to next node. */ + cur_node = proceed_next_node (mctx, nmatch, pmatch, &idx, cur_node, + &eps_via_nodes, fs); + + if (BE (cur_node < 0, 0)) + { + if (BE (cur_node == -2, 0)) + { + re_node_set_free (&eps_via_nodes); + if (prev_idx_match_malloced) + re_free (prev_idx_match); + free_fail_stack_return (fs); + return REG_ESPACE; + } + if (fs) + cur_node = pop_fail_stack (fs, &idx, nmatch, pmatch, + &eps_via_nodes); + else + { + re_node_set_free (&eps_via_nodes); + if (prev_idx_match_malloced) + re_free (prev_idx_match); + return REG_NOMATCH; + } + } + } + re_node_set_free (&eps_via_nodes); + if (prev_idx_match_malloced) + re_free (prev_idx_match); + return free_fail_stack_return (fs); +} + +static reg_errcode_t +internal_function +free_fail_stack_return (struct re_fail_stack_t *fs) +{ + if (fs) + { + int fs_idx; + for (fs_idx = 0; fs_idx < fs->num; ++fs_idx) + { + re_node_set_free (&fs->stack[fs_idx].eps_via_nodes); + re_free (fs->stack[fs_idx].regs); + } + re_free (fs->stack); + } + return REG_NOERROR; +} + +static void +internal_function +update_regs (const re_dfa_t *dfa, regmatch_t *pmatch, + regmatch_t *prev_idx_match, int cur_node, int cur_idx, int nmatch) +{ + int type = dfa->nodes[cur_node].type; + if (type == OP_OPEN_SUBEXP) + { + int reg_num = dfa->nodes[cur_node].opr.idx + 1; + + /* We are at the first node of this sub expression. */ + if (reg_num < nmatch) + { + pmatch[reg_num].rm_so = cur_idx; + pmatch[reg_num].rm_eo = -1; + } + } + else if (type == OP_CLOSE_SUBEXP) + { + int reg_num = dfa->nodes[cur_node].opr.idx + 1; + if (reg_num < nmatch) + { + /* We are at the last node of this sub expression. */ + if (pmatch[reg_num].rm_so < cur_idx) + { + pmatch[reg_num].rm_eo = cur_idx; + /* This is a non-empty match or we are not inside an optional + subexpression. Accept this right away. */ + memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch); + } + else + { + if (dfa->nodes[cur_node].opt_subexp + && prev_idx_match[reg_num].rm_so != -1) + /* We transited through an empty match for an optional + subexpression, like (a?)*, and this is not the subexp's + first match. Copy back the old content of the registers + so that matches of an inner subexpression are undone as + well, like in ((a?))*. */ + memcpy (pmatch, prev_idx_match, sizeof (regmatch_t) * nmatch); + else + /* We completed a subexpression, but it may be part of + an optional one, so do not update PREV_IDX_MATCH. */ + pmatch[reg_num].rm_eo = cur_idx; + } + } + } +} + +/* This function checks the STATE_LOG from the SCTX->last_str_idx to 0 + and sift the nodes in each states according to the following rules. + Updated state_log will be wrote to STATE_LOG. + + Rules: We throw away the Node `a' in the STATE_LOG[STR_IDX] if... + 1. When STR_IDX == MATCH_LAST(the last index in the state_log): + If `a' isn't the LAST_NODE and `a' can't epsilon transit to + the LAST_NODE, we throw away the node `a'. + 2. When 0 <= STR_IDX < MATCH_LAST and `a' accepts + string `s' and transit to `b': + i. If 'b' isn't in the STATE_LOG[STR_IDX+strlen('s')], we throw + away the node `a'. + ii. If 'b' is in the STATE_LOG[STR_IDX+strlen('s')] but 'b' is + thrown away, we throw away the node `a'. + 3. When 0 <= STR_IDX < MATCH_LAST and 'a' epsilon transit to 'b': + i. If 'b' isn't in the STATE_LOG[STR_IDX], we throw away the + node `a'. + ii. If 'b' is in the STATE_LOG[STR_IDX] but 'b' is thrown away, + we throw away the node `a'. */ + +#define STATE_NODE_CONTAINS(state,node) \ + ((state) != NULL && re_node_set_contains (&(state)->nodes, node)) + +static reg_errcode_t +internal_function +sift_states_backward (const re_match_context_t *mctx, re_sift_context_t *sctx) +{ + reg_errcode_t err; + int null_cnt = 0; + int str_idx = sctx->last_str_idx; + re_node_set cur_dest; + +#ifdef DEBUG + assert (mctx->state_log != NULL && mctx->state_log[str_idx] != NULL); +#endif + + /* Build sifted state_log[str_idx]. It has the nodes which can epsilon + transit to the last_node and the last_node itself. */ + err = re_node_set_init_1 (&cur_dest, sctx->last_node); + if (BE (err != REG_NOERROR, 0)) + return err; + err = update_cur_sifted_state (mctx, sctx, str_idx, &cur_dest); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + + /* Then check each states in the state_log. */ + while (str_idx > 0) + { + /* Update counters. */ + null_cnt = (sctx->sifted_states[str_idx] == NULL) ? null_cnt + 1 : 0; + if (null_cnt > mctx->max_mb_elem_len) + { + memset (sctx->sifted_states, '\0', + sizeof (re_dfastate_t *) * str_idx); + re_node_set_free (&cur_dest); + return REG_NOERROR; + } + re_node_set_empty (&cur_dest); + --str_idx; + + if (mctx->state_log[str_idx]) + { + err = build_sifted_states (mctx, sctx, str_idx, &cur_dest); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + + /* Add all the nodes which satisfy the following conditions: + - It can epsilon transit to a node in CUR_DEST. + - It is in CUR_SRC. + And update state_log. */ + err = update_cur_sifted_state (mctx, sctx, str_idx, &cur_dest); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + err = REG_NOERROR; + free_return: + re_node_set_free (&cur_dest); + return err; +} + +static reg_errcode_t +internal_function +build_sifted_states (const re_match_context_t *mctx, re_sift_context_t *sctx, + int str_idx, re_node_set *cur_dest) +{ + const re_dfa_t *const dfa = mctx->dfa; + const re_node_set *cur_src = &mctx->state_log[str_idx]->non_eps_nodes; + int i; + + /* Then build the next sifted state. + We build the next sifted state on `cur_dest', and update + `sifted_states[str_idx]' with `cur_dest'. + Note: + `cur_dest' is the sifted state from `state_log[str_idx + 1]'. + `cur_src' points the node_set of the old `state_log[str_idx]' + (with the epsilon nodes pre-filtered out). */ + for (i = 0; i < cur_src->nelem; i++) + { + int prev_node = cur_src->elems[i]; + int naccepted = 0; + int ret; + +#ifdef DEBUG + re_token_type_t type = dfa->nodes[prev_node].type; + assert (!IS_EPSILON_NODE (type)); +#endif +#ifdef RE_ENABLE_I18N + /* If the node may accept `multi byte'. */ + if (dfa->nodes[prev_node].accept_mb) + naccepted = sift_states_iter_mb (mctx, sctx, prev_node, + str_idx, sctx->last_str_idx); +#endif /* RE_ENABLE_I18N */ + + /* We don't check backreferences here. + See update_cur_sifted_state(). */ + if (!naccepted + && check_node_accept (mctx, dfa->nodes + prev_node, str_idx) + && STATE_NODE_CONTAINS (sctx->sifted_states[str_idx + 1], + dfa->nexts[prev_node])) + naccepted = 1; + + if (naccepted == 0) + continue; + + if (sctx->limits.nelem) + { + int to_idx = str_idx + naccepted; + if (check_dst_limits (mctx, &sctx->limits, + dfa->nexts[prev_node], to_idx, + prev_node, str_idx)) + continue; + } + ret = re_node_set_insert (cur_dest, prev_node); + if (BE (ret == -1, 0)) + return REG_ESPACE; + } + + return REG_NOERROR; +} + +/* Helper functions. */ + +static reg_errcode_t +internal_function +clean_state_log_if_needed (re_match_context_t *mctx, int next_state_log_idx) +{ + int top = mctx->state_log_top; + + if (next_state_log_idx >= mctx->input.bufs_len + || (next_state_log_idx >= mctx->input.valid_len + && mctx->input.valid_len < mctx->input.len)) + { + reg_errcode_t err; + err = extend_buffers (mctx); + if (BE (err != REG_NOERROR, 0)) + return err; + } + + if (top < next_state_log_idx) + { + memset (mctx->state_log + top + 1, '\0', + sizeof (re_dfastate_t *) * (next_state_log_idx - top)); + mctx->state_log_top = next_state_log_idx; + } + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +merge_state_array (const re_dfa_t *dfa, re_dfastate_t **dst, + re_dfastate_t **src, int num) +{ + int st_idx; + reg_errcode_t err; + for (st_idx = 0; st_idx < num; ++st_idx) + { + if (dst[st_idx] == NULL) + dst[st_idx] = src[st_idx]; + else if (src[st_idx] != NULL) + { + re_node_set merged_set; + err = re_node_set_init_union (&merged_set, &dst[st_idx]->nodes, + &src[st_idx]->nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + dst[st_idx] = re_acquire_state (&err, dfa, &merged_set); + re_node_set_free (&merged_set); + if (BE (err != REG_NOERROR, 0)) + return err; + } + } + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +update_cur_sifted_state (const re_match_context_t *mctx, + re_sift_context_t *sctx, int str_idx, + re_node_set *dest_nodes) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err = REG_NOERROR; + const re_node_set *candidates; + candidates = ((mctx->state_log[str_idx] == NULL) ? NULL + : &mctx->state_log[str_idx]->nodes); + + if (dest_nodes->nelem == 0) + sctx->sifted_states[str_idx] = NULL; + else + { + if (candidates) + { + /* At first, add the nodes which can epsilon transit to a node in + DEST_NODE. */ + err = add_epsilon_src_nodes (dfa, dest_nodes, candidates); + if (BE (err != REG_NOERROR, 0)) + return err; + + /* Then, check the limitations in the current sift_context. */ + if (sctx->limits.nelem) + { + err = check_subexp_limits (dfa, dest_nodes, candidates, &sctx->limits, + mctx->bkref_ents, str_idx); + if (BE (err != REG_NOERROR, 0)) + return err; + } + } + + sctx->sifted_states[str_idx] = re_acquire_state (&err, dfa, dest_nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + } + + if (candidates && mctx->state_log[str_idx]->has_backref) + { + err = sift_states_bkref (mctx, sctx, str_idx, candidates); + if (BE (err != REG_NOERROR, 0)) + return err; + } + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +add_epsilon_src_nodes (const re_dfa_t *dfa, re_node_set *dest_nodes, + const re_node_set *candidates) +{ + reg_errcode_t err = REG_NOERROR; + int i; + + re_dfastate_t *state = re_acquire_state (&err, dfa, dest_nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + + if (!state->inveclosure.alloc) + { + err = re_node_set_alloc (&state->inveclosure, dest_nodes->nelem); + if (BE (err != REG_NOERROR, 0)) + return REG_ESPACE; + for (i = 0; i < dest_nodes->nelem; i++) + re_node_set_merge (&state->inveclosure, + dfa->inveclosures + dest_nodes->elems[i]); + } + return re_node_set_add_intersect (dest_nodes, candidates, + &state->inveclosure); +} + +static reg_errcode_t +internal_function +sub_epsilon_src_nodes (const re_dfa_t *dfa, int node, re_node_set *dest_nodes, + const re_node_set *candidates) +{ + int ecl_idx; + reg_errcode_t err; + re_node_set *inv_eclosure = dfa->inveclosures + node; + re_node_set except_nodes; + re_node_set_init_empty (&except_nodes); + for (ecl_idx = 0; ecl_idx < inv_eclosure->nelem; ++ecl_idx) + { + int cur_node = inv_eclosure->elems[ecl_idx]; + if (cur_node == node) + continue; + if (IS_EPSILON_NODE (dfa->nodes[cur_node].type)) + { + int edst1 = dfa->edests[cur_node].elems[0]; + int edst2 = ((dfa->edests[cur_node].nelem > 1) + ? dfa->edests[cur_node].elems[1] : -1); + if ((!re_node_set_contains (inv_eclosure, edst1) + && re_node_set_contains (dest_nodes, edst1)) + || (edst2 > 0 + && !re_node_set_contains (inv_eclosure, edst2) + && re_node_set_contains (dest_nodes, edst2))) + { + err = re_node_set_add_intersect (&except_nodes, candidates, + dfa->inveclosures + cur_node); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&except_nodes); + return err; + } + } + } + } + for (ecl_idx = 0; ecl_idx < inv_eclosure->nelem; ++ecl_idx) + { + int cur_node = inv_eclosure->elems[ecl_idx]; + if (!re_node_set_contains (&except_nodes, cur_node)) + { + int idx = re_node_set_contains (dest_nodes, cur_node) - 1; + re_node_set_remove_at (dest_nodes, idx); + } + } + re_node_set_free (&except_nodes); + return REG_NOERROR; +} + +static int +internal_function +check_dst_limits (const re_match_context_t *mctx, re_node_set *limits, + int dst_node, int dst_idx, int src_node, int src_idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + int lim_idx, src_pos, dst_pos; + + int dst_bkref_idx = search_cur_bkref_entry (mctx, dst_idx); + int src_bkref_idx = search_cur_bkref_entry (mctx, src_idx); + for (lim_idx = 0; lim_idx < limits->nelem; ++lim_idx) + { + int subexp_idx; + struct re_backref_cache_entry *ent; + ent = mctx->bkref_ents + limits->elems[lim_idx]; + subexp_idx = dfa->nodes[ent->node].opr.idx; + + dst_pos = check_dst_limits_calc_pos (mctx, limits->elems[lim_idx], + subexp_idx, dst_node, dst_idx, + dst_bkref_idx); + src_pos = check_dst_limits_calc_pos (mctx, limits->elems[lim_idx], + subexp_idx, src_node, src_idx, + src_bkref_idx); + + /* In case of: + ( ) + ( ) + ( ) */ + if (src_pos == dst_pos) + continue; /* This is unrelated limitation. */ + else + return 1; + } + return 0; +} + +static int +internal_function +check_dst_limits_calc_pos_1 (const re_match_context_t *mctx, int boundaries, + int subexp_idx, int from_node, int bkref_idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + const re_node_set *eclosures = dfa->eclosures + from_node; + int node_idx; + + /* Else, we are on the boundary: examine the nodes on the epsilon + closure. */ + for (node_idx = 0; node_idx < eclosures->nelem; ++node_idx) + { + int node = eclosures->elems[node_idx]; + switch (dfa->nodes[node].type) + { + case OP_BACK_REF: + if (bkref_idx != -1) + { + struct re_backref_cache_entry *ent = mctx->bkref_ents + bkref_idx; + do + { + int dst, cpos; + + if (ent->node != node) + continue; + + if (subexp_idx < BITSET_WORD_BITS + && !(ent->eps_reachable_subexps_map + & ((bitset_word_t) 1 << subexp_idx))) + continue; + + /* Recurse trying to reach the OP_OPEN_SUBEXP and + OP_CLOSE_SUBEXP cases below. But, if the + destination node is the same node as the source + node, don't recurse because it would cause an + infinite loop: a regex that exhibits this behavior + is ()\1*\1* */ + dst = dfa->edests[node].elems[0]; + if (dst == from_node) + { + if (boundaries & 1) + return -1; + else /* if (boundaries & 2) */ + return 0; + } + + cpos = + check_dst_limits_calc_pos_1 (mctx, boundaries, subexp_idx, + dst, bkref_idx); + if (cpos == -1 /* && (boundaries & 1) */) + return -1; + if (cpos == 0 && (boundaries & 2)) + return 0; + + if (subexp_idx < BITSET_WORD_BITS) + ent->eps_reachable_subexps_map + &= ~((bitset_word_t) 1 << subexp_idx); + } + while (ent++->more); + } + break; + + case OP_OPEN_SUBEXP: + if ((boundaries & 1) && subexp_idx == dfa->nodes[node].opr.idx) + return -1; + break; + + case OP_CLOSE_SUBEXP: + if ((boundaries & 2) && subexp_idx == dfa->nodes[node].opr.idx) + return 0; + break; + + default: + break; + } + } + + return (boundaries & 2) ? 1 : 0; +} + +static int +internal_function +check_dst_limits_calc_pos (const re_match_context_t *mctx, int limit, + int subexp_idx, int from_node, int str_idx, + int bkref_idx) +{ + struct re_backref_cache_entry *lim = mctx->bkref_ents + limit; + int boundaries; + + /* If we are outside the range of the subexpression, return -1 or 1. */ + if (str_idx < lim->subexp_from) + return -1; + + if (lim->subexp_to < str_idx) + return 1; + + /* If we are within the subexpression, return 0. */ + boundaries = (str_idx == lim->subexp_from); + boundaries |= (str_idx == lim->subexp_to) << 1; + if (boundaries == 0) + return 0; + + /* Else, examine epsilon closure. */ + return check_dst_limits_calc_pos_1 (mctx, boundaries, subexp_idx, + from_node, bkref_idx); +} + +/* Check the limitations of sub expressions LIMITS, and remove the nodes + which are against limitations from DEST_NODES. */ + +static reg_errcode_t +internal_function +check_subexp_limits (const re_dfa_t *dfa, re_node_set *dest_nodes, + const re_node_set *candidates, re_node_set *limits, + struct re_backref_cache_entry *bkref_ents, int str_idx) +{ + reg_errcode_t err; + int node_idx, lim_idx; + + for (lim_idx = 0; lim_idx < limits->nelem; ++lim_idx) + { + int subexp_idx; + struct re_backref_cache_entry *ent; + ent = bkref_ents + limits->elems[lim_idx]; + + if (str_idx <= ent->subexp_from || ent->str_idx < str_idx) + continue; /* This is unrelated limitation. */ + + subexp_idx = dfa->nodes[ent->node].opr.idx; + if (ent->subexp_to == str_idx) + { + int ops_node = -1; + int cls_node = -1; + for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) + { + int node = dest_nodes->elems[node_idx]; + re_token_type_t type = dfa->nodes[node].type; + if (type == OP_OPEN_SUBEXP + && subexp_idx == dfa->nodes[node].opr.idx) + ops_node = node; + else if (type == OP_CLOSE_SUBEXP + && subexp_idx == dfa->nodes[node].opr.idx) + cls_node = node; + } + + /* Check the limitation of the open subexpression. */ + /* Note that (ent->subexp_to = str_idx != ent->subexp_from). */ + if (ops_node >= 0) + { + err = sub_epsilon_src_nodes (dfa, ops_node, dest_nodes, + candidates); + if (BE (err != REG_NOERROR, 0)) + return err; + } + + /* Check the limitation of the close subexpression. */ + if (cls_node >= 0) + for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) + { + int node = dest_nodes->elems[node_idx]; + if (!re_node_set_contains (dfa->inveclosures + node, + cls_node) + && !re_node_set_contains (dfa->eclosures + node, + cls_node)) + { + /* It is against this limitation. + Remove it form the current sifted state. */ + err = sub_epsilon_src_nodes (dfa, node, dest_nodes, + candidates); + if (BE (err != REG_NOERROR, 0)) + return err; + --node_idx; + } + } + } + else /* (ent->subexp_to != str_idx) */ + { + for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) + { + int node = dest_nodes->elems[node_idx]; + re_token_type_t type = dfa->nodes[node].type; + if (type == OP_CLOSE_SUBEXP || type == OP_OPEN_SUBEXP) + { + if (subexp_idx != dfa->nodes[node].opr.idx) + continue; + /* It is against this limitation. + Remove it form the current sifted state. */ + err = sub_epsilon_src_nodes (dfa, node, dest_nodes, + candidates); + if (BE (err != REG_NOERROR, 0)) + return err; + } + } + } + } + return REG_NOERROR; +} + +static reg_errcode_t +internal_function +sift_states_bkref (const re_match_context_t *mctx, re_sift_context_t *sctx, + int str_idx, const re_node_set *candidates) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err; + int node_idx, node; + re_sift_context_t local_sctx; + int first_idx = search_cur_bkref_entry (mctx, str_idx); + + if (first_idx == -1) + return REG_NOERROR; + + local_sctx.sifted_states = NULL; /* Mark that it hasn't been initialized. */ + + for (node_idx = 0; node_idx < candidates->nelem; ++node_idx) + { + int enabled_idx; + re_token_type_t type; + struct re_backref_cache_entry *entry; + node = candidates->elems[node_idx]; + type = dfa->nodes[node].type; + /* Avoid infinite loop for the REs like "()\1+". */ + if (node == sctx->last_node && str_idx == sctx->last_str_idx) + continue; + if (type != OP_BACK_REF) + continue; + + entry = mctx->bkref_ents + first_idx; + enabled_idx = first_idx; + do + { + int subexp_len; + int to_idx; + int dst_node; + int ret; + re_dfastate_t *cur_state; + + if (entry->node != node) + continue; + subexp_len = entry->subexp_to - entry->subexp_from; + to_idx = str_idx + subexp_len; + dst_node = (subexp_len ? dfa->nexts[node] + : dfa->edests[node].elems[0]); + + if (to_idx > sctx->last_str_idx + || sctx->sifted_states[to_idx] == NULL + || !STATE_NODE_CONTAINS (sctx->sifted_states[to_idx], dst_node) + || check_dst_limits (mctx, &sctx->limits, node, + str_idx, dst_node, to_idx)) + continue; + + if (local_sctx.sifted_states == NULL) + { + local_sctx = *sctx; + err = re_node_set_init_copy (&local_sctx.limits, &sctx->limits); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + local_sctx.last_node = node; + local_sctx.last_str_idx = str_idx; + ret = re_node_set_insert (&local_sctx.limits, enabled_idx); + if (BE (ret < 0, 0)) + { + err = REG_ESPACE; + goto free_return; + } + cur_state = local_sctx.sifted_states[str_idx]; + err = sift_states_backward (mctx, &local_sctx); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + if (sctx->limited_states != NULL) + { + err = merge_state_array (dfa, sctx->limited_states, + local_sctx.sifted_states, + str_idx + 1); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + local_sctx.sifted_states[str_idx] = cur_state; + re_node_set_remove (&local_sctx.limits, enabled_idx); + + /* mctx->bkref_ents may have changed, reload the pointer. */ + entry = mctx->bkref_ents + enabled_idx; + } + while (enabled_idx++, entry++->more); + } + err = REG_NOERROR; + free_return: + if (local_sctx.sifted_states != NULL) + { + re_node_set_free (&local_sctx.limits); + } + + return err; +} + + +#ifdef RE_ENABLE_I18N +static int +internal_function +sift_states_iter_mb (const re_match_context_t *mctx, re_sift_context_t *sctx, + int node_idx, int str_idx, int max_str_idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + int naccepted; + /* Check the node can accept `multi byte'. */ + naccepted = check_node_accept_bytes (dfa, node_idx, &mctx->input, str_idx); + if (naccepted > 0 && str_idx + naccepted <= max_str_idx && + !STATE_NODE_CONTAINS (sctx->sifted_states[str_idx + naccepted], + dfa->nexts[node_idx])) + /* The node can't accept the `multi byte', or the + destination was already thrown away, then the node + could't accept the current input `multi byte'. */ + naccepted = 0; + /* Otherwise, it is sure that the node could accept + `naccepted' bytes input. */ + return naccepted; +} +#endif /* RE_ENABLE_I18N */ + + +/* Functions for state transition. */ + +/* Return the next state to which the current state STATE will transit by + accepting the current input byte, and update STATE_LOG if necessary. + If STATE can accept a multibyte char/collating element/back reference + update the destination of STATE_LOG. */ + +static re_dfastate_t * +internal_function +transit_state (reg_errcode_t *err, re_match_context_t *mctx, + re_dfastate_t *state) +{ + re_dfastate_t **trtable; + unsigned char ch; + +#ifdef RE_ENABLE_I18N + /* If the current state can accept multibyte. */ + if (BE (state->accept_mb, 0)) + { + *err = transit_state_mb (mctx, state); + if (BE (*err != REG_NOERROR, 0)) + return NULL; + } +#endif /* RE_ENABLE_I18N */ + + /* Then decide the next state with the single byte. */ +#if 0 + if (0) + /* don't use transition table */ + return transit_state_sb (err, mctx, state); +#endif + + /* Use transition table */ + ch = re_string_fetch_byte (&mctx->input); + for (;;) + { + trtable = state->trtable; + if (BE (trtable != NULL, 1)) + return trtable[ch]; + + trtable = state->word_trtable; + if (BE (trtable != NULL, 1)) + { + unsigned int context; + context + = re_string_context_at (&mctx->input, + re_string_cur_idx (&mctx->input) - 1, + mctx->eflags); + if (IS_WORD_CONTEXT (context)) + return trtable[ch + SBC_MAX]; + else + return trtable[ch]; + } + + if (!build_trtable (mctx->dfa, state)) + { + *err = REG_ESPACE; + return NULL; + } + + /* Retry, we now have a transition table. */ + } +} + +/* Update the state_log if we need */ +re_dfastate_t * +internal_function +merge_state_with_log (reg_errcode_t *err, re_match_context_t *mctx, + re_dfastate_t *next_state) +{ + const re_dfa_t *const dfa = mctx->dfa; + int cur_idx = re_string_cur_idx (&mctx->input); + + if (cur_idx > mctx->state_log_top) + { + mctx->state_log[cur_idx] = next_state; + mctx->state_log_top = cur_idx; + } + else if (mctx->state_log[cur_idx] == 0) + { + mctx->state_log[cur_idx] = next_state; + } + else + { + re_dfastate_t *pstate; + unsigned int context; + re_node_set next_nodes, *log_nodes, *table_nodes = NULL; + /* If (state_log[cur_idx] != 0), it implies that cur_idx is + the destination of a multibyte char/collating element/ + back reference. Then the next state is the union set of + these destinations and the results of the transition table. */ + pstate = mctx->state_log[cur_idx]; + log_nodes = pstate->entrance_nodes; + if (next_state != NULL) + { + table_nodes = next_state->entrance_nodes; + *err = re_node_set_init_union (&next_nodes, table_nodes, + log_nodes); + if (BE (*err != REG_NOERROR, 0)) + return NULL; + } + else + next_nodes = *log_nodes; + /* Note: We already add the nodes of the initial state, + then we don't need to add them here. */ + + context = re_string_context_at (&mctx->input, + re_string_cur_idx (&mctx->input) - 1, + mctx->eflags); + next_state = mctx->state_log[cur_idx] + = re_acquire_state_context (err, dfa, &next_nodes, context); + /* We don't need to check errors here, since the return value of + this function is next_state and ERR is already set. */ + + if (table_nodes != NULL) + re_node_set_free (&next_nodes); + } + + if (BE (dfa->nbackref, 0) && next_state != NULL) + { + /* Check OP_OPEN_SUBEXP in the current state in case that we use them + later. We must check them here, since the back references in the + next state might use them. */ + *err = check_subexp_matching_top (mctx, &next_state->nodes, + cur_idx); + if (BE (*err != REG_NOERROR, 0)) + return NULL; + + /* If the next state has back references. */ + if (next_state->has_backref) + { + *err = transit_state_bkref (mctx, &next_state->nodes); + if (BE (*err != REG_NOERROR, 0)) + return NULL; + next_state = mctx->state_log[cur_idx]; + } + } + + return next_state; +} + +/* Skip bytes in the input that correspond to part of a + multi-byte match, then look in the log for a state + from which to restart matching. */ +re_dfastate_t * +internal_function +find_recover_state (reg_errcode_t *err, re_match_context_t *mctx) +{ + re_dfastate_t *cur_state; + do + { + int max = mctx->state_log_top; + int cur_str_idx = re_string_cur_idx (&mctx->input); + + do + { + if (++cur_str_idx > max) + return NULL; + re_string_skip_bytes (&mctx->input, 1); + } + while (mctx->state_log[cur_str_idx] == NULL); + + cur_state = merge_state_with_log (err, mctx, NULL); + } + while (*err == REG_NOERROR && cur_state == NULL); + return cur_state; +} + +/* Helper functions for transit_state. */ + +/* From the node set CUR_NODES, pick up the nodes whose types are + OP_OPEN_SUBEXP and which have corresponding back references in the regular + expression. And register them to use them later for evaluating the + correspoding back references. */ + +static reg_errcode_t +internal_function +check_subexp_matching_top (re_match_context_t *mctx, re_node_set *cur_nodes, + int str_idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + int node_idx; + reg_errcode_t err; + + /* TODO: This isn't efficient. + Because there might be more than one nodes whose types are + OP_OPEN_SUBEXP and whose index is SUBEXP_IDX, we must check all + nodes. + E.g. RE: (a){2} */ + for (node_idx = 0; node_idx < cur_nodes->nelem; ++node_idx) + { + int node = cur_nodes->elems[node_idx]; + if (dfa->nodes[node].type == OP_OPEN_SUBEXP + && dfa->nodes[node].opr.idx < BITSET_WORD_BITS + && (dfa->used_bkref_map + & ((bitset_word_t) 1 << dfa->nodes[node].opr.idx))) + { + err = match_ctx_add_subtop (mctx, node, str_idx); + if (BE (err != REG_NOERROR, 0)) + return err; + } + } + return REG_NOERROR; +} + +#if 0 +/* Return the next state to which the current state STATE will transit by + accepting the current input byte. */ + +static re_dfastate_t * +transit_state_sb (reg_errcode_t *err, re_match_context_t *mctx, + re_dfastate_t *state) +{ + const re_dfa_t *const dfa = mctx->dfa; + re_node_set next_nodes; + re_dfastate_t *next_state; + int node_cnt, cur_str_idx = re_string_cur_idx (&mctx->input); + unsigned int context; + + *err = re_node_set_alloc (&next_nodes, state->nodes.nelem + 1); + if (BE (*err != REG_NOERROR, 0)) + return NULL; + for (node_cnt = 0; node_cnt < state->nodes.nelem; ++node_cnt) + { + int cur_node = state->nodes.elems[node_cnt]; + if (check_node_accept (mctx, dfa->nodes + cur_node, cur_str_idx)) + { + *err = re_node_set_merge (&next_nodes, + dfa->eclosures + dfa->nexts[cur_node]); + if (BE (*err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return NULL; + } + } + } + context = re_string_context_at (&mctx->input, cur_str_idx, mctx->eflags); + next_state = re_acquire_state_context (err, dfa, &next_nodes, context); + /* We don't need to check errors here, since the return value of + this function is next_state and ERR is already set. */ + + re_node_set_free (&next_nodes); + re_string_skip_bytes (&mctx->input, 1); + return next_state; +} +#endif + +#ifdef RE_ENABLE_I18N +static reg_errcode_t +internal_function +transit_state_mb (re_match_context_t *mctx, re_dfastate_t *pstate) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err; + int i; + + for (i = 0; i < pstate->nodes.nelem; ++i) + { + re_node_set dest_nodes, *new_nodes; + int cur_node_idx = pstate->nodes.elems[i]; + int naccepted, dest_idx; + unsigned int context; + re_dfastate_t *dest_state; + + if (!dfa->nodes[cur_node_idx].accept_mb) + continue; + + if (dfa->nodes[cur_node_idx].constraint) + { + context = re_string_context_at (&mctx->input, + re_string_cur_idx (&mctx->input), + mctx->eflags); + if (NOT_SATISFY_NEXT_CONSTRAINT (dfa->nodes[cur_node_idx].constraint, + context)) + continue; + } + + /* How many bytes the node can accept? */ + naccepted = check_node_accept_bytes (dfa, cur_node_idx, &mctx->input, + re_string_cur_idx (&mctx->input)); + if (naccepted == 0) + continue; + + /* The node can accepts `naccepted' bytes. */ + dest_idx = re_string_cur_idx (&mctx->input) + naccepted; + mctx->max_mb_elem_len = ((mctx->max_mb_elem_len < naccepted) ? naccepted + : mctx->max_mb_elem_len); + err = clean_state_log_if_needed (mctx, dest_idx); + if (BE (err != REG_NOERROR, 0)) + return err; +#ifdef DEBUG + assert (dfa->nexts[cur_node_idx] != -1); +#endif + new_nodes = dfa->eclosures + dfa->nexts[cur_node_idx]; + + dest_state = mctx->state_log[dest_idx]; + if (dest_state == NULL) + dest_nodes = *new_nodes; + else + { + err = re_node_set_init_union (&dest_nodes, + dest_state->entrance_nodes, new_nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + } + context = re_string_context_at (&mctx->input, dest_idx - 1, + mctx->eflags); + mctx->state_log[dest_idx] + = re_acquire_state_context (&err, dfa, &dest_nodes, context); + if (dest_state != NULL) + re_node_set_free (&dest_nodes); + if (BE (mctx->state_log[dest_idx] == NULL && err != REG_NOERROR, 0)) + return err; + } + return REG_NOERROR; +} +#endif /* RE_ENABLE_I18N */ + +static reg_errcode_t +internal_function +transit_state_bkref (re_match_context_t *mctx, const re_node_set *nodes) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err; + int i; + int cur_str_idx = re_string_cur_idx (&mctx->input); + + for (i = 0; i < nodes->nelem; ++i) + { + int dest_str_idx, prev_nelem, bkc_idx; + int node_idx = nodes->elems[i]; + unsigned int context; + const re_token_t *node = dfa->nodes + node_idx; + re_node_set *new_dest_nodes; + + /* Check whether `node' is a backreference or not. */ + if (node->type != OP_BACK_REF) + continue; + + if (node->constraint) + { + context = re_string_context_at (&mctx->input, cur_str_idx, + mctx->eflags); + if (NOT_SATISFY_NEXT_CONSTRAINT (node->constraint, context)) + continue; + } + + /* `node' is a backreference. + Check the substring which the substring matched. */ + bkc_idx = mctx->nbkref_ents; + err = get_subexp (mctx, node_idx, cur_str_idx); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + + /* And add the epsilon closures (which is `new_dest_nodes') of + the backreference to appropriate state_log. */ +#ifdef DEBUG + assert (dfa->nexts[node_idx] != -1); +#endif + for (; bkc_idx < mctx->nbkref_ents; ++bkc_idx) + { + int subexp_len; + re_dfastate_t *dest_state; + struct re_backref_cache_entry *bkref_ent; + bkref_ent = mctx->bkref_ents + bkc_idx; + if (bkref_ent->node != node_idx || bkref_ent->str_idx != cur_str_idx) + continue; + subexp_len = bkref_ent->subexp_to - bkref_ent->subexp_from; + new_dest_nodes = (subexp_len == 0 + ? dfa->eclosures + dfa->edests[node_idx].elems[0] + : dfa->eclosures + dfa->nexts[node_idx]); + dest_str_idx = (cur_str_idx + bkref_ent->subexp_to + - bkref_ent->subexp_from); + context = re_string_context_at (&mctx->input, dest_str_idx - 1, + mctx->eflags); + dest_state = mctx->state_log[dest_str_idx]; + prev_nelem = ((mctx->state_log[cur_str_idx] == NULL) ? 0 + : mctx->state_log[cur_str_idx]->nodes.nelem); + /* Add `new_dest_node' to state_log. */ + if (dest_state == NULL) + { + mctx->state_log[dest_str_idx] + = re_acquire_state_context (&err, dfa, new_dest_nodes, + context); + if (BE (mctx->state_log[dest_str_idx] == NULL + && err != REG_NOERROR, 0)) + goto free_return; + } + else + { + re_node_set dest_nodes; + err = re_node_set_init_union (&dest_nodes, + dest_state->entrance_nodes, + new_dest_nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&dest_nodes); + goto free_return; + } + mctx->state_log[dest_str_idx] + = re_acquire_state_context (&err, dfa, &dest_nodes, context); + re_node_set_free (&dest_nodes); + if (BE (mctx->state_log[dest_str_idx] == NULL + && err != REG_NOERROR, 0)) + goto free_return; + } + /* We need to check recursively if the backreference can epsilon + transit. */ + if (subexp_len == 0 + && mctx->state_log[cur_str_idx]->nodes.nelem > prev_nelem) + { + err = check_subexp_matching_top (mctx, new_dest_nodes, + cur_str_idx); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + err = transit_state_bkref (mctx, new_dest_nodes); + if (BE (err != REG_NOERROR, 0)) + goto free_return; + } + } + } + err = REG_NOERROR; + free_return: + return err; +} + +/* Enumerate all the candidates which the backreference BKREF_NODE can match + at BKREF_STR_IDX, and register them by match_ctx_add_entry(). + Note that we might collect inappropriate candidates here. + However, the cost of checking them strictly here is too high, then we + delay these checking for prune_impossible_nodes(). */ + +static reg_errcode_t +internal_function +get_subexp (re_match_context_t *mctx, int bkref_node, int bkref_str_idx) +{ + const re_dfa_t *const dfa = mctx->dfa; + int subexp_num, sub_top_idx; + const char *buf = (const char *) re_string_get_buffer (&mctx->input); + /* Return if we have already checked BKREF_NODE at BKREF_STR_IDX. */ + int cache_idx = search_cur_bkref_entry (mctx, bkref_str_idx); + if (cache_idx != -1) + { + const struct re_backref_cache_entry *entry + = mctx->bkref_ents + cache_idx; + do + if (entry->node == bkref_node) + return REG_NOERROR; /* We already checked it. */ + while (entry++->more); + } + + subexp_num = dfa->nodes[bkref_node].opr.idx; + + /* For each sub expression */ + for (sub_top_idx = 0; sub_top_idx < mctx->nsub_tops; ++sub_top_idx) + { + reg_errcode_t err; + re_sub_match_top_t *sub_top = mctx->sub_tops[sub_top_idx]; + re_sub_match_last_t *sub_last; + int sub_last_idx, sl_str, bkref_str_off; + + if (dfa->nodes[sub_top->node].opr.idx != subexp_num) + continue; /* It isn't related. */ + + sl_str = sub_top->str_idx; + bkref_str_off = bkref_str_idx; + /* At first, check the last node of sub expressions we already + evaluated. */ + for (sub_last_idx = 0; sub_last_idx < sub_top->nlasts; ++sub_last_idx) + { + int sl_str_diff; + sub_last = sub_top->lasts[sub_last_idx]; + sl_str_diff = sub_last->str_idx - sl_str; + /* The matched string by the sub expression match with the substring + at the back reference? */ + if (sl_str_diff > 0) + { + if (BE (bkref_str_off + sl_str_diff > mctx->input.valid_len, 0)) + { + /* Not enough chars for a successful match. */ + if (bkref_str_off + sl_str_diff > mctx->input.len) + break; + + err = clean_state_log_if_needed (mctx, + bkref_str_off + + sl_str_diff); + if (BE (err != REG_NOERROR, 0)) + return err; + buf = (const char *) re_string_get_buffer (&mctx->input); + } + if (memcmp (buf + bkref_str_off, buf + sl_str, sl_str_diff) != 0) + /* We don't need to search this sub expression any more. */ + break; + } + bkref_str_off += sl_str_diff; + sl_str += sl_str_diff; + err = get_subexp_sub (mctx, sub_top, sub_last, bkref_node, + bkref_str_idx); + + /* Reload buf, since the preceding call might have reallocated + the buffer. */ + buf = (const char *) re_string_get_buffer (&mctx->input); + + if (err == REG_NOMATCH) + continue; + if (BE (err != REG_NOERROR, 0)) + return err; + } + + if (sub_last_idx < sub_top->nlasts) + continue; + if (sub_last_idx > 0) + ++sl_str; + /* Then, search for the other last nodes of the sub expression. */ + for (; sl_str <= bkref_str_idx; ++sl_str) + { + int cls_node, sl_str_off; + const re_node_set *nodes; + sl_str_off = sl_str - sub_top->str_idx; + /* The matched string by the sub expression match with the substring + at the back reference? */ + if (sl_str_off > 0) + { + if (BE (bkref_str_off >= mctx->input.valid_len, 0)) + { + /* If we are at the end of the input, we cannot match. */ + if (bkref_str_off >= mctx->input.len) + break; + + err = extend_buffers (mctx); + if (BE (err != REG_NOERROR, 0)) + return err; + + buf = (const char *) re_string_get_buffer (&mctx->input); + } + if (buf [bkref_str_off++] != buf[sl_str - 1]) + break; /* We don't need to search this sub expression + any more. */ + } + if (mctx->state_log[sl_str] == NULL) + continue; + /* Does this state have a ')' of the sub expression? */ + nodes = &mctx->state_log[sl_str]->nodes; + cls_node = find_subexp_node (dfa, nodes, subexp_num, + OP_CLOSE_SUBEXP); + if (cls_node == -1) + continue; /* No. */ + if (sub_top->path == NULL) + { + sub_top->path = calloc (sizeof (state_array_t), + sl_str - sub_top->str_idx + 1); + if (sub_top->path == NULL) + return REG_ESPACE; + } + /* Can the OP_OPEN_SUBEXP node arrive the OP_CLOSE_SUBEXP node + in the current context? */ + err = check_arrival (mctx, sub_top->path, sub_top->node, + sub_top->str_idx, cls_node, sl_str, + OP_CLOSE_SUBEXP); + if (err == REG_NOMATCH) + continue; + if (BE (err != REG_NOERROR, 0)) + return err; + sub_last = match_ctx_add_sublast (sub_top, cls_node, sl_str); + if (BE (sub_last == NULL, 0)) + return REG_ESPACE; + err = get_subexp_sub (mctx, sub_top, sub_last, bkref_node, + bkref_str_idx); + if (err == REG_NOMATCH) + continue; + } + } + return REG_NOERROR; +} + +/* Helper functions for get_subexp(). */ + +/* Check SUB_LAST can arrive to the back reference BKREF_NODE at BKREF_STR. + If it can arrive, register the sub expression expressed with SUB_TOP + and SUB_LAST. */ + +static reg_errcode_t +internal_function +get_subexp_sub (re_match_context_t *mctx, const re_sub_match_top_t *sub_top, + re_sub_match_last_t *sub_last, int bkref_node, int bkref_str) +{ + reg_errcode_t err; + int to_idx; + /* Can the subexpression arrive the back reference? */ + err = check_arrival (mctx, &sub_last->path, sub_last->node, + sub_last->str_idx, bkref_node, bkref_str, + OP_OPEN_SUBEXP); + if (err != REG_NOERROR) + return err; + err = match_ctx_add_entry (mctx, bkref_node, bkref_str, sub_top->str_idx, + sub_last->str_idx); + if (BE (err != REG_NOERROR, 0)) + return err; + to_idx = bkref_str + sub_last->str_idx - sub_top->str_idx; + return clean_state_log_if_needed (mctx, to_idx); +} + +/* Find the first node which is '(' or ')' and whose index is SUBEXP_IDX. + Search '(' if FL_OPEN, or search ')' otherwise. + TODO: This function isn't efficient... + Because there might be more than one nodes whose types are + OP_OPEN_SUBEXP and whose index is SUBEXP_IDX, we must check all + nodes. + E.g. RE: (a){2} */ + +static int +internal_function +find_subexp_node (const re_dfa_t *dfa, const re_node_set *nodes, + int subexp_idx, int type) +{ + int cls_idx; + for (cls_idx = 0; cls_idx < nodes->nelem; ++cls_idx) + { + int cls_node = nodes->elems[cls_idx]; + const re_token_t *node = dfa->nodes + cls_node; + if (node->type == type + && node->opr.idx == subexp_idx) + return cls_node; + } + return -1; +} + +/* Check whether the node TOP_NODE at TOP_STR can arrive to the node + LAST_NODE at LAST_STR. We record the path onto PATH since it will be + heavily reused. + Return REG_NOERROR if it can arrive, or REG_NOMATCH otherwise. */ + +static reg_errcode_t +internal_function +check_arrival (re_match_context_t *mctx, state_array_t *path, int top_node, + int top_str, int last_node, int last_str, int type) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err = REG_NOERROR; + int subexp_num, backup_cur_idx, str_idx, null_cnt; + re_dfastate_t *cur_state = NULL; + re_node_set *cur_nodes, next_nodes; + re_dfastate_t **backup_state_log; + unsigned int context; + + subexp_num = dfa->nodes[top_node].opr.idx; + /* Extend the buffer if we need. */ + if (BE (path->alloc < last_str + mctx->max_mb_elem_len + 1, 0)) + { + re_dfastate_t **new_array; + int old_alloc = path->alloc; + path->alloc += last_str + mctx->max_mb_elem_len + 1; + new_array = re_realloc (path->array, re_dfastate_t *, path->alloc); + if (BE (new_array == NULL, 0)) + { + path->alloc = old_alloc; + return REG_ESPACE; + } + path->array = new_array; + memset (new_array + old_alloc, '\0', + sizeof (re_dfastate_t *) * (path->alloc - old_alloc)); + } + + str_idx = path->next_idx ?: top_str; + + /* Temporary modify MCTX. */ + backup_state_log = mctx->state_log; + backup_cur_idx = mctx->input.cur_idx; + mctx->state_log = path->array; + mctx->input.cur_idx = str_idx; + + /* Setup initial node set. */ + context = re_string_context_at (&mctx->input, str_idx - 1, mctx->eflags); + if (str_idx == top_str) + { + err = re_node_set_init_1 (&next_nodes, top_node); + if (BE (err != REG_NOERROR, 0)) + return err; + err = check_arrival_expand_ecl (dfa, &next_nodes, subexp_num, type); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + } + else + { + cur_state = mctx->state_log[str_idx]; + if (cur_state && cur_state->has_backref) + { + err = re_node_set_init_copy (&next_nodes, &cur_state->nodes); + if (BE (err != REG_NOERROR, 0)) + return err; + } + else + re_node_set_init_empty (&next_nodes); + } + if (str_idx == top_str || (cur_state && cur_state->has_backref)) + { + if (next_nodes.nelem) + { + err = expand_bkref_cache (mctx, &next_nodes, str_idx, + subexp_num, type); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + } + cur_state = re_acquire_state_context (&err, dfa, &next_nodes, context); + if (BE (cur_state == NULL && err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + mctx->state_log[str_idx] = cur_state; + } + + for (null_cnt = 0; str_idx < last_str && null_cnt <= mctx->max_mb_elem_len;) + { + re_node_set_empty (&next_nodes); + if (mctx->state_log[str_idx + 1]) + { + err = re_node_set_merge (&next_nodes, + &mctx->state_log[str_idx + 1]->nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + } + if (cur_state) + { + err = check_arrival_add_next_nodes (mctx, str_idx, + &cur_state->non_eps_nodes, + &next_nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + } + ++str_idx; + if (next_nodes.nelem) + { + err = check_arrival_expand_ecl (dfa, &next_nodes, subexp_num, type); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + err = expand_bkref_cache (mctx, &next_nodes, str_idx, + subexp_num, type); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + } + context = re_string_context_at (&mctx->input, str_idx - 1, mctx->eflags); + cur_state = re_acquire_state_context (&err, dfa, &next_nodes, context); + if (BE (cur_state == NULL && err != REG_NOERROR, 0)) + { + re_node_set_free (&next_nodes); + return err; + } + mctx->state_log[str_idx] = cur_state; + null_cnt = cur_state == NULL ? null_cnt + 1 : 0; + } + re_node_set_free (&next_nodes); + cur_nodes = (mctx->state_log[last_str] == NULL ? NULL + : &mctx->state_log[last_str]->nodes); + path->next_idx = str_idx; + + /* Fix MCTX. */ + mctx->state_log = backup_state_log; + mctx->input.cur_idx = backup_cur_idx; + + /* Then check the current node set has the node LAST_NODE. */ + if (cur_nodes != NULL && re_node_set_contains (cur_nodes, last_node)) + return REG_NOERROR; + + return REG_NOMATCH; +} + +/* Helper functions for check_arrival. */ + +/* Calculate the destination nodes of CUR_NODES at STR_IDX, and append them + to NEXT_NODES. + TODO: This function is similar to the functions transit_state*(), + however this function has many additional works. + Can't we unify them? */ + +static reg_errcode_t +internal_function +check_arrival_add_next_nodes (re_match_context_t *mctx, int str_idx, + re_node_set *cur_nodes, re_node_set *next_nodes) +{ + const re_dfa_t *const dfa = mctx->dfa; + int result; + int cur_idx; + reg_errcode_t err = REG_NOERROR; + re_node_set union_set; + re_node_set_init_empty (&union_set); + for (cur_idx = 0; cur_idx < cur_nodes->nelem; ++cur_idx) + { + int naccepted = 0; + int cur_node = cur_nodes->elems[cur_idx]; +#ifdef DEBUG + re_token_type_t type = dfa->nodes[cur_node].type; + assert (!IS_EPSILON_NODE (type)); +#endif +#ifdef RE_ENABLE_I18N + /* If the node may accept `multi byte'. */ + if (dfa->nodes[cur_node].accept_mb) + { + naccepted = check_node_accept_bytes (dfa, cur_node, &mctx->input, + str_idx); + if (naccepted > 1) + { + re_dfastate_t *dest_state; + int next_node = dfa->nexts[cur_node]; + int next_idx = str_idx + naccepted; + dest_state = mctx->state_log[next_idx]; + re_node_set_empty (&union_set); + if (dest_state) + { + err = re_node_set_merge (&union_set, &dest_state->nodes); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&union_set); + return err; + } + } + result = re_node_set_insert (&union_set, next_node); + if (BE (result < 0, 0)) + { + re_node_set_free (&union_set); + return REG_ESPACE; + } + mctx->state_log[next_idx] = re_acquire_state (&err, dfa, + &union_set); + if (BE (mctx->state_log[next_idx] == NULL + && err != REG_NOERROR, 0)) + { + re_node_set_free (&union_set); + return err; + } + } + } +#endif /* RE_ENABLE_I18N */ + if (naccepted + || check_node_accept (mctx, dfa->nodes + cur_node, str_idx)) + { + result = re_node_set_insert (next_nodes, dfa->nexts[cur_node]); + if (BE (result < 0, 0)) + { + re_node_set_free (&union_set); + return REG_ESPACE; + } + } + } + re_node_set_free (&union_set); + return REG_NOERROR; +} + +/* For all the nodes in CUR_NODES, add the epsilon closures of them to + CUR_NODES, however exclude the nodes which are: + - inside the sub expression whose number is EX_SUBEXP, if FL_OPEN. + - out of the sub expression whose number is EX_SUBEXP, if !FL_OPEN. +*/ + +static reg_errcode_t +internal_function +check_arrival_expand_ecl (const re_dfa_t *dfa, re_node_set *cur_nodes, + int ex_subexp, int type) +{ + reg_errcode_t err; + int idx, outside_node; + re_node_set new_nodes; +#ifdef DEBUG + assert (cur_nodes->nelem); +#endif + err = re_node_set_alloc (&new_nodes, cur_nodes->nelem); + if (BE (err != REG_NOERROR, 0)) + return err; + /* Create a new node set NEW_NODES with the nodes which are epsilon + closures of the node in CUR_NODES. */ + + for (idx = 0; idx < cur_nodes->nelem; ++idx) + { + int cur_node = cur_nodes->elems[idx]; + const re_node_set *eclosure = dfa->eclosures + cur_node; + outside_node = find_subexp_node (dfa, eclosure, ex_subexp, type); + if (outside_node == -1) + { + /* There are no problematic nodes, just merge them. */ + err = re_node_set_merge (&new_nodes, eclosure); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&new_nodes); + return err; + } + } + else + { + /* There are problematic nodes, re-calculate incrementally. */ + err = check_arrival_expand_ecl_sub (dfa, &new_nodes, cur_node, + ex_subexp, type); + if (BE (err != REG_NOERROR, 0)) + { + re_node_set_free (&new_nodes); + return err; + } + } + } + re_node_set_free (cur_nodes); + *cur_nodes = new_nodes; + return REG_NOERROR; +} + +/* Helper function for check_arrival_expand_ecl. + Check incrementally the epsilon closure of TARGET, and if it isn't + problematic append it to DST_NODES. */ + +static reg_errcode_t +internal_function +check_arrival_expand_ecl_sub (const re_dfa_t *dfa, re_node_set *dst_nodes, + int target, int ex_subexp, int type) +{ + int cur_node; + for (cur_node = target; !re_node_set_contains (dst_nodes, cur_node);) + { + int err; + + if (dfa->nodes[cur_node].type == type + && dfa->nodes[cur_node].opr.idx == ex_subexp) + { + if (type == OP_CLOSE_SUBEXP) + { + err = re_node_set_insert (dst_nodes, cur_node); + if (BE (err == -1, 0)) + return REG_ESPACE; + } + break; + } + err = re_node_set_insert (dst_nodes, cur_node); + if (BE (err == -1, 0)) + return REG_ESPACE; + if (dfa->edests[cur_node].nelem == 0) + break; + if (dfa->edests[cur_node].nelem == 2) + { + err = check_arrival_expand_ecl_sub (dfa, dst_nodes, + dfa->edests[cur_node].elems[1], + ex_subexp, type); + if (BE (err != REG_NOERROR, 0)) + return err; + } + cur_node = dfa->edests[cur_node].elems[0]; + } + return REG_NOERROR; +} + + +/* For all the back references in the current state, calculate the + destination of the back references by the appropriate entry + in MCTX->BKREF_ENTS. */ + +static reg_errcode_t +internal_function +expand_bkref_cache (re_match_context_t *mctx, re_node_set *cur_nodes, + int cur_str, int subexp_num, int type) +{ + const re_dfa_t *const dfa = mctx->dfa; + reg_errcode_t err; + int cache_idx_start = search_cur_bkref_entry (mctx, cur_str); + struct re_backref_cache_entry *ent; + + if (cache_idx_start == -1) + return REG_NOERROR; + + restart: + ent = mctx->bkref_ents + cache_idx_start; + do + { + int to_idx, next_node; + + /* Is this entry ENT is appropriate? */ + if (!re_node_set_contains (cur_nodes, ent->node)) + continue; /* No. */ + + to_idx = cur_str + ent->subexp_to - ent->subexp_from; + /* Calculate the destination of the back reference, and append it + to MCTX->STATE_LOG. */ + if (to_idx == cur_str) + { + /* The backreference did epsilon transit, we must re-check all the + node in the current state. */ + re_node_set new_dests; + reg_errcode_t err2, err3; + next_node = dfa->edests[ent->node].elems[0]; + if (re_node_set_contains (cur_nodes, next_node)) + continue; + err = re_node_set_init_1 (&new_dests, next_node); + err2 = check_arrival_expand_ecl (dfa, &new_dests, subexp_num, type); + err3 = re_node_set_merge (cur_nodes, &new_dests); + re_node_set_free (&new_dests); + if (BE (err != REG_NOERROR || err2 != REG_NOERROR + || err3 != REG_NOERROR, 0)) + { + err = (err != REG_NOERROR ? err + : (err2 != REG_NOERROR ? err2 : err3)); + return err; + } + /* TODO: It is still inefficient... */ + goto restart; + } + else + { + re_node_set union_set; + next_node = dfa->nexts[ent->node]; + if (mctx->state_log[to_idx]) + { + int ret; + if (re_node_set_contains (&mctx->state_log[to_idx]->nodes, + next_node)) + continue; + err = re_node_set_init_copy (&union_set, + &mctx->state_log[to_idx]->nodes); + ret = re_node_set_insert (&union_set, next_node); + if (BE (err != REG_NOERROR || ret < 0, 0)) + { + re_node_set_free (&union_set); + err = err != REG_NOERROR ? err : REG_ESPACE; + return err; + } + } + else + { + err = re_node_set_init_1 (&union_set, next_node); + if (BE (err != REG_NOERROR, 0)) + return err; + } + mctx->state_log[to_idx] = re_acquire_state (&err, dfa, &union_set); + re_node_set_free (&union_set); + if (BE (mctx->state_log[to_idx] == NULL + && err != REG_NOERROR, 0)) + return err; + } + } + while (ent++->more); + return REG_NOERROR; +} + +/* Build transition table for the state. + Return 1 if succeeded, otherwise return NULL. */ + +static int +internal_function +build_trtable (const re_dfa_t *dfa, re_dfastate_t *state) +{ + reg_errcode_t err; + int i, j, ch, need_word_trtable = 0; + bitset_word_t elem, mask; + bool dests_node_malloced = false; + bool dest_states_malloced = false; + int ndests; /* Number of the destination states from `state'. */ + re_dfastate_t **trtable; + re_dfastate_t **dest_states = NULL, **dest_states_word, **dest_states_nl; + re_node_set follows, *dests_node; + bitset_t *dests_ch; + bitset_t acceptable; + + struct dests_alloc + { + re_node_set dests_node[SBC_MAX]; + bitset_t dests_ch[SBC_MAX]; + } *dests_alloc; + + /* We build DFA states which corresponds to the destination nodes + from `state'. `dests_node[i]' represents the nodes which i-th + destination state contains, and `dests_ch[i]' represents the + characters which i-th destination state accepts. */ + if (__libc_use_alloca (sizeof (struct dests_alloc))) + dests_alloc = (struct dests_alloc *) alloca (sizeof (struct dests_alloc)); + else + { + dests_alloc = re_malloc (struct dests_alloc, 1); + if (BE (dests_alloc == NULL, 0)) + return 0; + dests_node_malloced = true; + } + dests_node = dests_alloc->dests_node; + dests_ch = dests_alloc->dests_ch; + + /* Initialize transiton table. */ + state->word_trtable = state->trtable = NULL; + + /* At first, group all nodes belonging to `state' into several + destinations. */ + ndests = group_nodes_into_DFAstates (dfa, state, dests_node, dests_ch); + if (BE (ndests <= 0, 0)) + { + if (dests_node_malloced) + free (dests_alloc); + /* Return 0 in case of an error, 1 otherwise. */ + if (ndests == 0) + { + state->trtable = (re_dfastate_t **) + calloc (sizeof (re_dfastate_t *), SBC_MAX); + return 1; + } + return 0; + } + + err = re_node_set_alloc (&follows, ndests + 1); + if (BE (err != REG_NOERROR, 0)) + goto out_free; + + if (__libc_use_alloca ((sizeof (re_node_set) + sizeof (bitset_t)) * SBC_MAX + + ndests * 3 * sizeof (re_dfastate_t *))) + dest_states = (re_dfastate_t **) + alloca (ndests * 3 * sizeof (re_dfastate_t *)); + else + { + dest_states = (re_dfastate_t **) + malloc (ndests * 3 * sizeof (re_dfastate_t *)); + if (BE (dest_states == NULL, 0)) + { +out_free: + if (dest_states_malloced) + free (dest_states); + re_node_set_free (&follows); + for (i = 0; i < ndests; ++i) + re_node_set_free (dests_node + i); + if (dests_node_malloced) + free (dests_alloc); + return 0; + } + dest_states_malloced = true; + } + dest_states_word = dest_states + ndests; + dest_states_nl = dest_states_word + ndests; + bitset_empty (acceptable); + + /* Then build the states for all destinations. */ + for (i = 0; i < ndests; ++i) + { + int next_node; + re_node_set_empty (&follows); + /* Merge the follows of this destination states. */ + for (j = 0; j < dests_node[i].nelem; ++j) + { + next_node = dfa->nexts[dests_node[i].elems[j]]; + if (next_node != -1) + { + err = re_node_set_merge (&follows, dfa->eclosures + next_node); + if (BE (err != REG_NOERROR, 0)) + goto out_free; + } + } + dest_states[i] = re_acquire_state_context (&err, dfa, &follows, 0); + if (BE (dest_states[i] == NULL && err != REG_NOERROR, 0)) + goto out_free; + /* If the new state has context constraint, + build appropriate states for these contexts. */ + if (dest_states[i]->has_constraint) + { + dest_states_word[i] = re_acquire_state_context (&err, dfa, &follows, + CONTEXT_WORD); + if (BE (dest_states_word[i] == NULL && err != REG_NOERROR, 0)) + goto out_free; + + if (dest_states[i] != dest_states_word[i] && dfa->mb_cur_max > 1) + need_word_trtable = 1; + + dest_states_nl[i] = re_acquire_state_context (&err, dfa, &follows, + CONTEXT_NEWLINE); + if (BE (dest_states_nl[i] == NULL && err != REG_NOERROR, 0)) + goto out_free; + } + else + { + dest_states_word[i] = dest_states[i]; + dest_states_nl[i] = dest_states[i]; + } + bitset_merge (acceptable, dests_ch[i]); + } + + if (!BE (need_word_trtable, 0)) + { + /* We don't care about whether the following character is a word + character, or we are in a single-byte character set so we can + discern by looking at the character code: allocate a + 256-entry transition table. */ + trtable = state->trtable = + (re_dfastate_t **) calloc (sizeof (re_dfastate_t *), SBC_MAX); + if (BE (trtable == NULL, 0)) + goto out_free; + + /* For all characters ch...: */ + for (i = 0; i < BITSET_WORDS; ++i) + for (ch = i * BITSET_WORD_BITS, elem = acceptable[i], mask = 1; + elem; + mask <<= 1, elem >>= 1, ++ch) + if (BE (elem & 1, 0)) + { + /* There must be exactly one destination which accepts + character ch. See group_nodes_into_DFAstates. */ + for (j = 0; (dests_ch[j][i] & mask) == 0; ++j) + ; + + /* j-th destination accepts the word character ch. */ + if (dfa->word_char[i] & mask) + trtable[ch] = dest_states_word[j]; + else + trtable[ch] = dest_states[j]; + } + } + else + { + /* We care about whether the following character is a word + character, and we are in a multi-byte character set: discern + by looking at the character code: build two 256-entry + transition tables, one starting at trtable[0] and one + starting at trtable[SBC_MAX]. */ + trtable = state->word_trtable = + (re_dfastate_t **) calloc (sizeof (re_dfastate_t *), 2 * SBC_MAX); + if (BE (trtable == NULL, 0)) + goto out_free; + + /* For all characters ch...: */ + for (i = 0; i < BITSET_WORDS; ++i) + for (ch = i * BITSET_WORD_BITS, elem = acceptable[i], mask = 1; + elem; + mask <<= 1, elem >>= 1, ++ch) + if (BE (elem & 1, 0)) + { + /* There must be exactly one destination which accepts + character ch. See group_nodes_into_DFAstates. */ + for (j = 0; (dests_ch[j][i] & mask) == 0; ++j) + ; + + /* j-th destination accepts the word character ch. */ + trtable[ch] = dest_states[j]; + trtable[ch + SBC_MAX] = dest_states_word[j]; + } + } + + /* new line */ + if (bitset_contain (acceptable, NEWLINE_CHAR)) + { + /* The current state accepts newline character. */ + for (j = 0; j < ndests; ++j) + if (bitset_contain (dests_ch[j], NEWLINE_CHAR)) + { + /* k-th destination accepts newline character. */ + trtable[NEWLINE_CHAR] = dest_states_nl[j]; + if (need_word_trtable) + trtable[NEWLINE_CHAR + SBC_MAX] = dest_states_nl[j]; + /* There must be only one destination which accepts + newline. See group_nodes_into_DFAstates. */ + break; + } + } + + if (dest_states_malloced) + free (dest_states); + + re_node_set_free (&follows); + for (i = 0; i < ndests; ++i) + re_node_set_free (dests_node + i); + + if (dests_node_malloced) + free (dests_alloc); + + return 1; +} + +/* Group all nodes belonging to STATE into several destinations. + Then for all destinations, set the nodes belonging to the destination + to DESTS_NODE[i] and set the characters accepted by the destination + to DEST_CH[i]. This function return the number of destinations. */ + +static int +internal_function +group_nodes_into_DFAstates (const re_dfa_t *dfa, const re_dfastate_t *state, + re_node_set *dests_node, bitset_t *dests_ch) +{ + reg_errcode_t err; + int result; + int i, j, k; + int ndests; /* Number of the destinations from `state'. */ + bitset_t accepts; /* Characters a node can accept. */ + const re_node_set *cur_nodes = &state->nodes; + bitset_empty (accepts); + ndests = 0; + + /* For all the nodes belonging to `state', */ + for (i = 0; i < cur_nodes->nelem; ++i) + { + re_token_t *node = &dfa->nodes[cur_nodes->elems[i]]; + re_token_type_t type = node->type; + unsigned int constraint = node->constraint; + + /* Enumerate all single byte character this node can accept. */ + if (type == CHARACTER) + bitset_set (accepts, node->opr.c); + else if (type == SIMPLE_BRACKET) + { + bitset_merge (accepts, node->opr.sbcset); + } + else if (type == OP_PERIOD) + { +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + bitset_merge (accepts, dfa->sb_char); + else +#endif + bitset_set_all (accepts); + if (!(dfa->syntax & RE_DOT_NEWLINE)) + bitset_clear (accepts, '\n'); + if (dfa->syntax & RE_DOT_NOT_NULL) + bitset_clear (accepts, '\0'); + } +#ifdef RE_ENABLE_I18N + else if (type == OP_UTF8_PERIOD) + { + memset (accepts, '\xff', sizeof (bitset_t) / 2); + if (!(dfa->syntax & RE_DOT_NEWLINE)) + bitset_clear (accepts, '\n'); + if (dfa->syntax & RE_DOT_NOT_NULL) + bitset_clear (accepts, '\0'); + } +#endif + else + continue; + + /* Check the `accepts' and sift the characters which are not + match it the context. */ + if (constraint) + { + if (constraint & NEXT_NEWLINE_CONSTRAINT) + { + bool accepts_newline = bitset_contain (accepts, NEWLINE_CHAR); + bitset_empty (accepts); + if (accepts_newline) + bitset_set (accepts, NEWLINE_CHAR); + else + continue; + } + if (constraint & NEXT_ENDBUF_CONSTRAINT) + { + bitset_empty (accepts); + continue; + } + + if (constraint & NEXT_WORD_CONSTRAINT) + { + bitset_word_t any_set = 0; + if (type == CHARACTER && !node->word_char) + { + bitset_empty (accepts); + continue; + } +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + for (j = 0; j < BITSET_WORDS; ++j) + any_set |= (accepts[j] &= (dfa->word_char[j] | ~dfa->sb_char[j])); + else +#endif + for (j = 0; j < BITSET_WORDS; ++j) + any_set |= (accepts[j] &= dfa->word_char[j]); + if (!any_set) + continue; + } + if (constraint & NEXT_NOTWORD_CONSTRAINT) + { + bitset_word_t any_set = 0; + if (type == CHARACTER && node->word_char) + { + bitset_empty (accepts); + continue; + } +#ifdef RE_ENABLE_I18N + if (dfa->mb_cur_max > 1) + for (j = 0; j < BITSET_WORDS; ++j) + any_set |= (accepts[j] &= ~(dfa->word_char[j] & dfa->sb_char[j])); + else +#endif + for (j = 0; j < BITSET_WORDS; ++j) + any_set |= (accepts[j] &= ~dfa->word_char[j]); + if (!any_set) + continue; + } + } + + /* Then divide `accepts' into DFA states, or create a new + state. Above, we make sure that accepts is not empty. */ + for (j = 0; j < ndests; ++j) + { + bitset_t intersec; /* Intersection sets, see below. */ + bitset_t remains; + /* Flags, see below. */ + bitset_word_t has_intersec, not_subset, not_consumed; + + /* Optimization, skip if this state doesn't accept the character. */ + if (type == CHARACTER && !bitset_contain (dests_ch[j], node->opr.c)) + continue; + + /* Enumerate the intersection set of this state and `accepts'. */ + has_intersec = 0; + for (k = 0; k < BITSET_WORDS; ++k) + has_intersec |= intersec[k] = accepts[k] & dests_ch[j][k]; + /* And skip if the intersection set is empty. */ + if (!has_intersec) + continue; + + /* Then check if this state is a subset of `accepts'. */ + not_subset = not_consumed = 0; + for (k = 0; k < BITSET_WORDS; ++k) + { + not_subset |= remains[k] = ~accepts[k] & dests_ch[j][k]; + not_consumed |= accepts[k] = accepts[k] & ~dests_ch[j][k]; + } + + /* If this state isn't a subset of `accepts', create a + new group state, which has the `remains'. */ + if (not_subset) + { + bitset_copy (dests_ch[ndests], remains); + bitset_copy (dests_ch[j], intersec); + err = re_node_set_init_copy (dests_node + ndests, &dests_node[j]); + if (BE (err != REG_NOERROR, 0)) + goto error_return; + ++ndests; + } + + /* Put the position in the current group. */ + result = re_node_set_insert (&dests_node[j], cur_nodes->elems[i]); + if (BE (result < 0, 0)) + goto error_return; + + /* If all characters are consumed, go to next node. */ + if (!not_consumed) + break; + } + /* Some characters remain, create a new group. */ + if (j == ndests) + { + bitset_copy (dests_ch[ndests], accepts); + err = re_node_set_init_1 (dests_node + ndests, cur_nodes->elems[i]); + if (BE (err != REG_NOERROR, 0)) + goto error_return; + ++ndests; + bitset_empty (accepts); + } + } + return ndests; + error_return: + for (j = 0; j < ndests; ++j) + re_node_set_free (dests_node + j); + return -1; +} + +#ifdef RE_ENABLE_I18N +/* Check how many bytes the node `dfa->nodes[node_idx]' accepts. + Return the number of the bytes the node accepts. + STR_IDX is the current index of the input string. + + This function handles the nodes which can accept one character, or + one collating element like '.', '[a-z]', opposite to the other nodes + can only accept one byte. */ + +static int +internal_function +check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, + const re_string_t *input, int str_idx) +{ + const re_token_t *node = dfa->nodes + node_idx; + int char_len, elem_len; + int i; + + if (BE (node->type == OP_UTF8_PERIOD, 0)) + { + unsigned char c = re_string_byte_at (input, str_idx), d; + if (BE (c < 0xc2, 1)) + return 0; + + if (str_idx + 2 > input->len) + return 0; + + d = re_string_byte_at (input, str_idx + 1); + if (c < 0xe0) + return (d < 0x80 || d > 0xbf) ? 0 : 2; + else if (c < 0xf0) + { + char_len = 3; + if (c == 0xe0 && d < 0xa0) + return 0; + } + else if (c < 0xf8) + { + char_len = 4; + if (c == 0xf0 && d < 0x90) + return 0; + } + else if (c < 0xfc) + { + char_len = 5; + if (c == 0xf8 && d < 0x88) + return 0; + } + else if (c < 0xfe) + { + char_len = 6; + if (c == 0xfc && d < 0x84) + return 0; + } + else + return 0; + + if (str_idx + char_len > input->len) + return 0; + + for (i = 1; i < char_len; ++i) + { + d = re_string_byte_at (input, str_idx + i); + if (d < 0x80 || d > 0xbf) + return 0; + } + return char_len; + } + + char_len = re_string_char_size_at (input, str_idx); + if (node->type == OP_PERIOD) + { + if (char_len <= 1) + return 0; + /* FIXME: I don't think this if is needed, as both '\n' + and '\0' are char_len == 1. */ + /* '.' accepts any one character except the following two cases. */ + if ((!(dfa->syntax & RE_DOT_NEWLINE) && + re_string_byte_at (input, str_idx) == '\n') || + ((dfa->syntax & RE_DOT_NOT_NULL) && + re_string_byte_at (input, str_idx) == '\0')) + return 0; + return char_len; + } + + elem_len = re_string_elem_size_at (input, str_idx); + if ((elem_len <= 1 && char_len <= 1) || char_len == 0) + return 0; + + if (node->type == COMPLEX_BRACKET) + { + const re_charset_t *cset = node->opr.mbcset; +# ifdef _LIBC + const unsigned char *pin + = ((const unsigned char *) re_string_get_buffer (input) + str_idx); + int j; + uint32_t nrules; +# endif /* _LIBC */ + int match_len = 0; + wchar_t wc = ((cset->nranges || cset->nchar_classes || cset->nmbchars) + ? re_string_wchar_at (input, str_idx) : 0); + + /* match with multibyte character? */ + for (i = 0; i < cset->nmbchars; ++i) + if (wc == cset->mbchars[i]) + { + match_len = char_len; + goto check_node_accept_bytes_match; + } + /* match with character_class? */ + for (i = 0; i < cset->nchar_classes; ++i) + { + wctype_t wt = cset->char_classes[i]; + if (__iswctype (wc, wt)) + { + match_len = char_len; + goto check_node_accept_bytes_match; + } + } + +# ifdef _LIBC + nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); + if (nrules != 0) + { + unsigned int in_collseq = 0; + const int32_t *table, *indirect; + const unsigned char *weights, *extra; + const char *collseqwc; + int32_t idx; + /* This #include defines a local function! */ +# include + + /* match with collating_symbol? */ + if (cset->ncoll_syms) + extra = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB); + for (i = 0; i < cset->ncoll_syms; ++i) + { + const unsigned char *coll_sym = extra + cset->coll_syms[i]; + /* Compare the length of input collating element and + the length of current collating element. */ + if (*coll_sym != elem_len) + continue; + /* Compare each bytes. */ + for (j = 0; j < *coll_sym; j++) + if (pin[j] != coll_sym[1 + j]) + break; + if (j == *coll_sym) + { + /* Match if every bytes is equal. */ + match_len = j; + goto check_node_accept_bytes_match; + } + } + + if (cset->nranges) + { + if (elem_len <= char_len) + { + collseqwc = _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQWC); + in_collseq = __collseq_table_lookup (collseqwc, wc); + } + else + in_collseq = find_collation_sequence_value (pin, elem_len); + } + /* match with range expression? */ + for (i = 0; i < cset->nranges; ++i) + if (cset->range_starts[i] <= in_collseq + && in_collseq <= cset->range_ends[i]) + { + match_len = elem_len; + goto check_node_accept_bytes_match; + } + + /* match with equivalence_class? */ + if (cset->nequiv_classes) + { + const unsigned char *cp = pin; + table = (const int32_t *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); + weights = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_WEIGHTMB); + extra = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB); + indirect = (const int32_t *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); + idx = findidx (&cp); + if (idx > 0) + for (i = 0; i < cset->nequiv_classes; ++i) + { + int32_t equiv_class_idx = cset->equiv_classes[i]; + size_t weight_len = weights[idx]; + if (weight_len == weights[equiv_class_idx]) + { + int cnt = 0; + while (cnt <= weight_len + && (weights[equiv_class_idx + 1 + cnt] + == weights[idx + 1 + cnt])) + ++cnt; + if (cnt > weight_len) + { + match_len = elem_len; + goto check_node_accept_bytes_match; + } + } + } + } + } + else +# endif /* _LIBC */ + { + /* match with range expression? */ +#if __GNUC__ >= 2 + wchar_t cmp_buf[] = {L'\0', L'\0', wc, L'\0', L'\0', L'\0'}; +#else + wchar_t cmp_buf[] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'}; + cmp_buf[2] = wc; +#endif + for (i = 0; i < cset->nranges; ++i) + { + cmp_buf[0] = cset->range_starts[i]; + cmp_buf[4] = cset->range_ends[i]; + if (wcscoll (cmp_buf, cmp_buf + 2) <= 0 + && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0) + { + match_len = char_len; + goto check_node_accept_bytes_match; + } + } + } + check_node_accept_bytes_match: + if (!cset->non_match) + return match_len; + else + { + if (match_len > 0) + return 0; + else + return (elem_len > char_len) ? elem_len : char_len; + } + } + return 0; +} + +# ifdef _LIBC +static unsigned int +internal_function +find_collation_sequence_value (const unsigned char *mbs, size_t mbs_len) +{ + uint32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); + if (nrules == 0) + { + if (mbs_len == 1) + { + /* No valid character. Match it as a single byte character. */ + const unsigned char *collseq = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQMB); + return collseq[mbs[0]]; + } + return UINT_MAX; + } + else + { + int32_t idx; + const unsigned char *extra = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB); + int32_t extrasize = (const unsigned char *) + _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB + 1) - extra; + + for (idx = 0; idx < extrasize;) + { + int mbs_cnt, found = 0; + int32_t elem_mbs_len; + /* Skip the name of collating element name. */ + idx = idx + extra[idx] + 1; + elem_mbs_len = extra[idx++]; + if (mbs_len == elem_mbs_len) + { + for (mbs_cnt = 0; mbs_cnt < elem_mbs_len; ++mbs_cnt) + if (extra[idx + mbs_cnt] != mbs[mbs_cnt]) + break; + if (mbs_cnt == elem_mbs_len) + /* Found the entry. */ + found = 1; + } + /* Skip the byte sequence of the collating element. */ + idx += elem_mbs_len; + /* Adjust for the alignment. */ + idx = (idx + 3) & ~3; + /* Skip the collation sequence value. */ + idx += sizeof (uint32_t); + /* Skip the wide char sequence of the collating element. */ + idx = idx + sizeof (uint32_t) * (extra[idx] + 1); + /* If we found the entry, return the sequence value. */ + if (found) + return *(uint32_t *) (extra + idx); + /* Skip the collation sequence value. */ + idx += sizeof (uint32_t); + } + return UINT_MAX; + } +} +# endif /* _LIBC */ +#endif /* RE_ENABLE_I18N */ + +/* Check whether the node accepts the byte which is IDX-th + byte of the INPUT. */ + +static int +internal_function +check_node_accept (const re_match_context_t *mctx, const re_token_t *node, + int idx) +{ + unsigned char ch; + ch = re_string_byte_at (&mctx->input, idx); + switch (node->type) + { + case CHARACTER: + if (node->opr.c != ch) + return 0; + break; + + case SIMPLE_BRACKET: + if (!bitset_contain (node->opr.sbcset, ch)) + return 0; + break; + +#ifdef RE_ENABLE_I18N + case OP_UTF8_PERIOD: + if (ch >= 0x80) + return 0; + /* FALLTHROUGH */ +#endif + case OP_PERIOD: + if ((ch == '\n' && !(mctx->dfa->syntax & RE_DOT_NEWLINE)) + || (ch == '\0' && (mctx->dfa->syntax & RE_DOT_NOT_NULL))) + return 0; + break; + + default: + return 0; + } + + if (node->constraint) + { + /* The node has constraints. Check whether the current context + satisfies the constraints. */ + unsigned int context = re_string_context_at (&mctx->input, idx, + mctx->eflags); + if (NOT_SATISFY_NEXT_CONSTRAINT (node->constraint, context)) + return 0; + } + + return 1; +} + +/* Extend the buffers, if the buffers have run out. */ + +static reg_errcode_t +internal_function +extend_buffers (re_match_context_t *mctx) +{ + reg_errcode_t ret; + re_string_t *pstr = &mctx->input; + + /* Double the lengthes of the buffers. */ + ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2); + if (BE (ret != REG_NOERROR, 0)) + return ret; + + if (mctx->state_log != NULL) + { + /* And double the length of state_log. */ + /* XXX We have no indication of the size of this buffer. If this + allocation fail we have no indication that the state_log array + does not have the right size. */ + re_dfastate_t **new_array = re_realloc (mctx->state_log, re_dfastate_t *, + pstr->bufs_len + 1); + if (BE (new_array == NULL, 0)) + return REG_ESPACE; + mctx->state_log = new_array; + } + + /* Then reconstruct the buffers. */ + if (pstr->icase) + { +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + { + ret = build_wcs_upper_buffer (pstr); + if (BE (ret != REG_NOERROR, 0)) + return ret; + } + else +#endif /* RE_ENABLE_I18N */ + build_upper_buffer (pstr); + } + else + { +#ifdef RE_ENABLE_I18N + if (pstr->mb_cur_max > 1) + build_wcs_buffer (pstr); + else +#endif /* RE_ENABLE_I18N */ + { + if (pstr->trans != NULL) + re_string_translate_buffer (pstr); + } + } + return REG_NOERROR; +} + + +/* Functions for matching context. */ + +/* Initialize MCTX. */ + +static reg_errcode_t +internal_function +match_ctx_init (re_match_context_t *mctx, int eflags, int n) +{ + mctx->eflags = eflags; + mctx->match_last = -1; + if (n > 0) + { + mctx->bkref_ents = re_malloc (struct re_backref_cache_entry, n); + mctx->sub_tops = re_malloc (re_sub_match_top_t *, n); + if (BE (mctx->bkref_ents == NULL || mctx->sub_tops == NULL, 0)) + return REG_ESPACE; + } + /* Already zero-ed by the caller. + else + mctx->bkref_ents = NULL; + mctx->nbkref_ents = 0; + mctx->nsub_tops = 0; */ + mctx->abkref_ents = n; + mctx->max_mb_elem_len = 1; + mctx->asub_tops = n; + return REG_NOERROR; +} + +/* Clean the entries which depend on the current input in MCTX. + This function must be invoked when the matcher changes the start index + of the input, or changes the input string. */ + +static void +internal_function +match_ctx_clean (re_match_context_t *mctx) +{ + int st_idx; + for (st_idx = 0; st_idx < mctx->nsub_tops; ++st_idx) + { + int sl_idx; + re_sub_match_top_t *top = mctx->sub_tops[st_idx]; + for (sl_idx = 0; sl_idx < top->nlasts; ++sl_idx) + { + re_sub_match_last_t *last = top->lasts[sl_idx]; + re_free (last->path.array); + re_free (last); + } + re_free (top->lasts); + if (top->path) + { + re_free (top->path->array); + re_free (top->path); + } + free (top); + } + + mctx->nsub_tops = 0; + mctx->nbkref_ents = 0; +} + +/* Free all the memory associated with MCTX. */ + +static void +internal_function +match_ctx_free (re_match_context_t *mctx) +{ + /* First, free all the memory associated with MCTX->SUB_TOPS. */ + match_ctx_clean (mctx); + re_free (mctx->sub_tops); + re_free (mctx->bkref_ents); +} + +/* Add a new backreference entry to MCTX. + Note that we assume that caller never call this function with duplicate + entry, and call with STR_IDX which isn't smaller than any existing entry. +*/ + +static reg_errcode_t +internal_function +match_ctx_add_entry (re_match_context_t *mctx, int node, int str_idx, int from, + int to) +{ + if (mctx->nbkref_ents >= mctx->abkref_ents) + { + struct re_backref_cache_entry* new_entry; + new_entry = re_realloc (mctx->bkref_ents, struct re_backref_cache_entry, + mctx->abkref_ents * 2); + if (BE (new_entry == NULL, 0)) + { + re_free (mctx->bkref_ents); + return REG_ESPACE; + } + mctx->bkref_ents = new_entry; + memset (mctx->bkref_ents + mctx->nbkref_ents, '\0', + sizeof (struct re_backref_cache_entry) * mctx->abkref_ents); + mctx->abkref_ents *= 2; + } + if (mctx->nbkref_ents > 0 + && mctx->bkref_ents[mctx->nbkref_ents - 1].str_idx == str_idx) + mctx->bkref_ents[mctx->nbkref_ents - 1].more = 1; + + mctx->bkref_ents[mctx->nbkref_ents].node = node; + mctx->bkref_ents[mctx->nbkref_ents].str_idx = str_idx; + mctx->bkref_ents[mctx->nbkref_ents].subexp_from = from; + mctx->bkref_ents[mctx->nbkref_ents].subexp_to = to; + + /* This is a cache that saves negative results of check_dst_limits_calc_pos. + If bit N is clear, means that this entry won't epsilon-transition to + an OP_OPEN_SUBEXP or OP_CLOSE_SUBEXP for the N+1-th subexpression. If + it is set, check_dst_limits_calc_pos_1 will recurse and try to find one + such node. + + A backreference does not epsilon-transition unless it is empty, so set + to all zeros if FROM != TO. */ + mctx->bkref_ents[mctx->nbkref_ents].eps_reachable_subexps_map + = (from == to ? ~0 : 0); + + mctx->bkref_ents[mctx->nbkref_ents++].more = 0; + if (mctx->max_mb_elem_len < to - from) + mctx->max_mb_elem_len = to - from; + return REG_NOERROR; +} + +/* Search for the first entry which has the same str_idx, or -1 if none is + found. Note that MCTX->BKREF_ENTS is already sorted by MCTX->STR_IDX. */ + +static int +internal_function +search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx) +{ + int left, right, mid, last; + last = right = mctx->nbkref_ents; + for (left = 0; left < right;) + { + mid = (left + right) / 2; + if (mctx->bkref_ents[mid].str_idx < str_idx) + left = mid + 1; + else + right = mid; + } + if (left < last && mctx->bkref_ents[left].str_idx == str_idx) + return left; + else + return -1; +} + +/* Register the node NODE, whose type is OP_OPEN_SUBEXP, and which matches + at STR_IDX. */ + +static reg_errcode_t +internal_function +match_ctx_add_subtop (re_match_context_t *mctx, int node, int str_idx) +{ +#ifdef DEBUG + assert (mctx->sub_tops != NULL); + assert (mctx->asub_tops > 0); +#endif + if (BE (mctx->nsub_tops == mctx->asub_tops, 0)) + { + int new_asub_tops = mctx->asub_tops * 2; + re_sub_match_top_t **new_array = re_realloc (mctx->sub_tops, + re_sub_match_top_t *, + new_asub_tops); + if (BE (new_array == NULL, 0)) + return REG_ESPACE; + mctx->sub_tops = new_array; + mctx->asub_tops = new_asub_tops; + } + mctx->sub_tops[mctx->nsub_tops] = calloc (1, sizeof (re_sub_match_top_t)); + if (BE (mctx->sub_tops[mctx->nsub_tops] == NULL, 0)) + return REG_ESPACE; + mctx->sub_tops[mctx->nsub_tops]->node = node; + mctx->sub_tops[mctx->nsub_tops++]->str_idx = str_idx; + return REG_NOERROR; +} + +/* Register the node NODE, whose type is OP_CLOSE_SUBEXP, and which matches + at STR_IDX, whose corresponding OP_OPEN_SUBEXP is SUB_TOP. */ + +static re_sub_match_last_t * +internal_function +match_ctx_add_sublast (re_sub_match_top_t *subtop, int node, int str_idx) +{ + re_sub_match_last_t *new_entry; + if (BE (subtop->nlasts == subtop->alasts, 0)) + { + int new_alasts = 2 * subtop->alasts + 1; + re_sub_match_last_t **new_array = re_realloc (subtop->lasts, + re_sub_match_last_t *, + new_alasts); + if (BE (new_array == NULL, 0)) + return NULL; + subtop->lasts = new_array; + subtop->alasts = new_alasts; + } + new_entry = calloc (1, sizeof (re_sub_match_last_t)); + if (BE (new_entry != NULL, 1)) + { + subtop->lasts[subtop->nlasts] = new_entry; + new_entry->node = node; + new_entry->str_idx = str_idx; + ++subtop->nlasts; + } + return new_entry; +} + +static void +internal_function +sift_ctx_init (re_sift_context_t *sctx, re_dfastate_t **sifted_sts, + re_dfastate_t **limited_sts, int last_node, int last_str_idx) +{ + sctx->sifted_states = sifted_sts; + sctx->limited_states = limited_sts; + sctx->last_node = last_node; + sctx->last_str_idx = last_str_idx; + re_node_set_init_empty (&sctx->limits); +} diff --git a/Build/source/texk/chktex/version.ac b/Build/source/texk/chktex/version.ac index 0cfc38830b8..a852157fb4b 100644 --- a/Build/source/texk/chktex/version.ac +++ b/Build/source/texk/chktex/version.ac @@ -8,4 +8,4 @@ dnl dnl -------------------------------------------------------- dnl dnl m4-include this file to define the current chktex version -m4_define([chktex_version], [1.6.6]) +m4_define([chktex_version], [1.7.1]) -- cgit v1.2.3