From 7ce0811299d8127ecd4eff9d16c73e4972cd2c32 Mon Sep 17 00:00:00 2001 From: Karl Berry Date: Tue, 18 Dec 2012 00:16:57 +0000 Subject: latexdiff (17dec12) git-svn-id: svn://tug.org/texlive/trunk@28564 c570f23f-e606-0410-a88d-b1316a301751 --- .../linked_scripts/latexdiff/latexdiff-vc.pl | 122 +- .../texlive/linked_scripts/latexdiff/latexdiff.pl | 963 ++++- .../linked_scripts/latexdiff/latexrevise.pl | 48 +- Master/texmf-dist/doc/latex/latexdiff/CHANGES | 138 - Master/texmf-dist/doc/latex/latexdiff/LICENSE | 280 -- Master/texmf-dist/doc/latex/latexdiff/Makefile | 64 - Master/texmf-dist/doc/latex/latexdiff/README | 98 - .../doc/latex/latexdiff/contrib/latexdiff-wrap | 192 - .../doc/latex/latexdiff/contrib/latexdiff.spec | 58 - .../doc/latex/latexdiff/example/example-draft.tex | 59 - .../doc/latex/latexdiff/example/example-rev.tex | 60 - Master/texmf-dist/doc/latex/latexdiff/latexdiff | 2783 -------------- .../texmf-dist/doc/latex/latexdiff/latexdiff-fast | 3344 ----------------- .../doc/latex/latexdiff/latexdiff-man.pdf | Bin 192975 -> 0 bytes Master/texmf-dist/doc/support/latexdiff/COPYING | 623 +++ Master/texmf-dist/doc/support/latexdiff/README | 107 + .../support/latexdiff/contrib/README.latexchanges | 13 + .../doc/support/latexdiff/contrib/latexchanges.py | 67 + .../doc/support/latexdiff/contrib/latexdiff-wrap | 192 + .../doc/support/latexdiff/contrib/latexdiff.spec | 58 + .../doc/support/latexdiff/doc/example-diff.tex | 89 + .../doc/support/latexdiff/doc/latexdiff-man.pdf | Bin 0 -> 193735 bytes .../doc/support/latexdiff/doc/latexdiff-man.tex | 355 ++ .../support/latexdiff/example/example-draft.tex | 59 + .../doc/support/latexdiff/example/example-rev.tex | 60 + Master/texmf-dist/doc/support/latexdiff/latexdiff | 3400 +++++++++++++++++ .../doc/support/latexdiff/latexdiff-fast | 3961 ++++++++++++++++++++ .../texmf-dist/scripts/latexdiff/latexdiff-vc.pl | 122 +- Master/texmf-dist/scripts/latexdiff/latexdiff.pl | 963 ++++- Master/texmf-dist/scripts/latexdiff/latexrevise.pl | 48 +- Master/texmf/doc/man/man1/latexdiff-vc.1 | 75 +- Master/texmf/doc/man/man1/latexdiff-vc.man1.pdf | Bin 8339 -> 8547 bytes Master/texmf/doc/man/man1/latexdiff.1 | 266 +- Master/texmf/doc/man/man1/latexdiff.man1.pdf | Bin 30073 -> 34808 bytes Master/texmf/doc/man/man1/latexrevise.1 | 58 +- Master/texmf/doc/man/man1/latexrevise.man1.pdf | Bin 8667 -> 8915 bytes Master/tlpkg/libexec/ctan2tds | 22 +- 37 files changed, 11071 insertions(+), 7676 deletions(-) delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/CHANGES delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/LICENSE delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/Makefile delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/README delete mode 100755 Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff-wrap delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff.spec delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/example/example-draft.tex delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/example/example-rev.tex delete mode 100755 Master/texmf-dist/doc/latex/latexdiff/latexdiff delete mode 100755 Master/texmf-dist/doc/latex/latexdiff/latexdiff-fast delete mode 100644 Master/texmf-dist/doc/latex/latexdiff/latexdiff-man.pdf create mode 100644 Master/texmf-dist/doc/support/latexdiff/COPYING create mode 100644 Master/texmf-dist/doc/support/latexdiff/README create mode 100644 Master/texmf-dist/doc/support/latexdiff/contrib/README.latexchanges create mode 100644 Master/texmf-dist/doc/support/latexdiff/contrib/latexchanges.py create mode 100755 Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff-wrap create mode 100644 Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff.spec create mode 100644 Master/texmf-dist/doc/support/latexdiff/doc/example-diff.tex create mode 100644 Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.pdf create mode 100644 Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.tex create mode 100644 Master/texmf-dist/doc/support/latexdiff/example/example-draft.tex create mode 100644 Master/texmf-dist/doc/support/latexdiff/example/example-rev.tex create mode 100755 Master/texmf-dist/doc/support/latexdiff/latexdiff create mode 100755 Master/texmf-dist/doc/support/latexdiff/latexdiff-fast diff --git a/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff-vc.pl b/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff-vc.pl index 3e9a3f246de..16b0dea5e7d 100755 --- a/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff-vc.pl +++ b/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff-vc.pl @@ -1,41 +1,54 @@ -#!/usr/bin/perl -w -# Place the following 2 lines at beginning to make script independent of location of perl -#eval 'exec perl -w -S $0 ${1+"$@"}' -# if 0; # not running under some shell +#!/usr/bin/env perl # # latexdiff-vc - wrapper script for applying latexdiff to rcs managed files # and for automatised creation of postscript or pdf from difference file # -# Copyright (C) 2005 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2005-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) +# +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# # # Contributors: S Utcke, H Bruyninckx # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file # +# version 1.0.2: - option --so to use latexdiff-so +# version 1.0.1 (change version numbering to match that of latexdiff) +# - Option --fast to use latexdiff-fast, +# - git support (thanks to Bjørn Magnus Mathisen, Santi Béjar, Pietro Battiston and Stefan Alfredson for patches) - UNTESTED # version 0.25: # - bbl is allowed as alternative extension (instead of .tex) -# +# version 0.26a +# - Bug fix: it copes now correctly with the possibility that there are no changes between current +# and archived version use Getopt::Long ; use Pod::Usage qw/pod2usage/ ; use File::Temp qw/tempdir/ ; use File::Basename qw/dirname/; use strict ; +use warnings ; + +my $versionstring=< 1); my ($file1,$file2,$diff,$diffbase,$answer,$options,$infile,$append,$dirname,$cwd); my (@files,@ldoptions,@tmpfiles,@ptmpfiles,@difffiles); # , - Getopt::Long::Configure('pass_through','bundling'); GetOptions('revision|r:s' => \@revs, 'cvs' => \$cvs, 'rcs' => \$rcs, 'svn' => \$svn, + 'git' => \$git, 'dir|d:s' => \$dir, + 'fast' => \$fast, + 'so' => \$so, 'postscript|ps' => \$postscript, 'pdf' => \$pdf, 'force' => \$force, @@ -63,32 +78,47 @@ if ( $help ) { } if ( $version ) { - die "This is LATEXDIFF-VC 0.25\n" ; + die $versionstring ; +} + +if ( $so ) { + $latexdiff='latexdiff-so'; +} +if ( $fast ) { + die "Cannot specify more than one of --fast or --so " if ($so); + $latexdiff='latexdiff-fast'; } if ( $cvs ) { $vc="CVS"; } if ( $rcs ) { - die "Cannot specify more than one of --cvs, --rcs or --svn." if ($vc); + die "Cannot specify more than one of --cvs, --rcs --svn or --git." if ($vc); $vc="RCS"; } if ( $svn ) { - die "Cannot specify more than one of --cvs, --rcs or --svn." if ($vc); + die "Cannot specify more than one of --cvs, --rcs --svn or --git." if ($vc); $vc="SVN"; } +if ( $git ) { + die "Cannot specify more than one of --cvs, --rcs, --svn or --git." if ($vc); + $vc="GIT"; +} + -# check whether the first file name got misinterpreted as an option to an empty -r option -if ( @revs && -f $revs[$#revs] ) { +# check whether the first file name or first passed-through option for latexdiff got misinterpreted as an option to an empty -r option +if ( @revs && ( -f $revs[$#revs] || $revs[$#revs] =~ /^-/ ) ) { unshift @ARGV,$revs[$#revs]; $revs[$#revs]=""; } -# check whether the first file name got misinterpreted as an option to an empty -d option -if ( defined($dir) && -f $dir ) { +# check whether the first file name or first passed-through option for latexdiff got misinterpreted as an option to an empty -d option +if ( defined($dir) && ( -f $dir || $dir =~ /^-/ ) ) { unshift @ARGV,$dir; $dir=""; } +#print "DEBUG: latexdiff-vc command line: ", join(" ",@ARGV), "\n"; + $file2=pop @ARGV; ( defined($file2) && $file2 =~ /\.(tex|bbl)$/ ) or pod2usage("Must specify at least one tex or bbl file"); @@ -101,6 +131,8 @@ if (! $vc && scalar(@revs)>0 ) { $vc="RCS"; } elsif ( $0 =~ /-svn$/ ) { $vc="SVN"; + } elsif ( $0 =~ /-git$/ ) { + $vc="GIT"; } elsif ( -e "CVSROOT" || defined($ENV{"CVSROOT"}) ) { print STDERR "Guess you are using CVS ...\n"; $vc="CVS"; @@ -110,6 +142,9 @@ if (! $vc && scalar(@revs)>0 ) { } elsif ( -d ".svn" ) { print STDERR "Guess you are using SVN ...\n"; $vc="SVN"; + } elsif ( -d ".git" ) { + print STDERR "Guess you are using GIT ...\n"; + $vc="GIT"; } else { print STDERR "Cannot figure out version control system, so I default to CVS\n"; $vc="CVS"; @@ -117,7 +152,7 @@ if (! $vc && scalar(@revs)>0 ) { } if (defined($dir) && $dir=~/^\.\/?/ ) { - print STDERR "You wrote selected -dir=. but you do not really like to do that, do you ?\n"; + print STDERR "You wrote -dir=. but you do not really like to do that, do you ?\n"; exit 10 } @@ -131,6 +166,12 @@ if ( scalar(@revs)>0 ) { } elsif ( $vc eq "SVN" ) { $diffcmd = "svn diff -r "; $patchcmd = "patch -R -p0"; + } elsif ( $vc eq "GIT" ) { + $diffcmd = "git diff -r --relative --no-prefix "; + $patchcmd = "patch -R -p0"; + # alternatively: + # $diffcmd = "git diff "; + # $patchcmd = "patch -R -p1"; } else { print STDERR "Unknown versioning system $vc \n"; exit 10; @@ -189,13 +230,22 @@ while ( $infile=$file2=shift @files ) { ($file1=$infile) =~ s/\.(tex|bbl)/-oldtmp-$$.$1/ ; push @tmpfiles,$file1; # compare file with previous version ($revs[0]="") or specified version - system("$diffcmd$revs[0] $infile| $patchcmd -o$file1") ; + ### system("$diffcmd$revs[0] $infile| $patchcmd -o$file1") ; + if (system("$diffcmd$revs[0] $infile | $patchcmd -o$file1")==0 and -z $file1 ) { + # no differences detected, i.e. file is equal to current version + system("\cp $infile $file1"); + } } elsif ( scalar(@revs) == 2 ) { ($file1=$infile) =~ s/\.(tex|bbl)/-oldtmp-$$.$1/ ; $file2 =~ s/\.(tex|bbl)/-newtmp-$$.$1/ ; push @tmpfiles,$file2; - system("$diffcmd$revs[1] $infile | $patchcmd -o$file2") ; - system("$diffcmd$revs[0] $infile | $patchcmd -o$file1") ; + ; + if (system("$diffcmd$revs[1] $infile | $patchcmd -o$file2")==0 and -z $file2 ) { + system("\cp $infile $file2"); + } + if (system("$diffcmd$revs[0] $infile | $patchcmd -o$file1")==0 and -z $file1 ) { + system("\cp $infile $file1"); + }; } if ( -z $file1 || -z $file2) { @@ -315,7 +365,7 @@ B [ F ] [ F ][ B<--posts =head1 DESCRIPTION I is a wrapper script that applies I to a -file, or multiple files under version control (CVS or RCS), and optionally runs the +file, or multiple files under version control (CVS, RCS or SVN), and optionally runs the sequence of C and C or C commands necessary to produce pdf or postscript output of the difference tex file(s). It can also be applied to a pair of files to automatise the generation of difference @@ -325,7 +375,7 @@ file in postscript or pdf format. =over 4 -=item B<--rcs>, B<--svn>, or B<--cvs> +=item B<--rcs>, B<--svn>, B<--cvs>, or B<--git> Set the version system. If no version system is specified, latexdiff-vc will venture a guess. @@ -335,8 +385,8 @@ the respective versioning system. However, this default can still be overridden =item B<-r>, B<-r> F or B<--revision>, B<--revision=>F -Choose revision (under RCS, CVS or SVN). One or two B<-r> options can be -specified, and the resulting in different behaviour: +Choose revision (under RCS, CVS, SVN or GIT). One or two B<-r> options can be +specified, and they result in different behaviour: =over 4 @@ -372,6 +422,10 @@ to the original filename, creating the directory and subdirectories should they not exist already. This is particularly useful in order to clone a complete directory hierarchy. Optionally, a pathname F can be specified, which is prepended instead of C. +=item B<--fast> or B<--so> + +Use C or C, respectively (instead of C). + =item B<--ps> or B<--postscript> Generate postscript output from difference file. This will run the @@ -417,13 +471,19 @@ limited to Unix-like systems. It also requires the RCS version control system and latex to be installed on the system. Modules from Perl 5.8 or higher are required. +=head1 BUG REPORTING + Please submit bug reports through +the latexdiff project page I or send +to I. Include the serial number of I +(option C<--version>) +. =head1 AUTHOR -Copyright (C) 2005 Frederik Tilmann +Copyright (C) 2005,2012 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 Contributors: S Utcke, H Bruyninckx =cut diff --git a/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff.pl b/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff.pl index 03c70c3ac4e..865fc4853b1 100755 --- a/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff.pl +++ b/Build/source/texk/texlive/linked_scripts/latexdiff/latexdiff.pl @@ -1,24 +1,58 @@ -#!/usr/bin/perl -w +#!/usr/bin/env perl +##!/usr/bin/perl -w # latexdiff - differences two latex files on the word level # and produces a latex file with the differences marked up. # -# Copyright (C) 2004-2007 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2004-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file # +# Version 1.0.1 - treat \big,\bigg etc. equivalently to \left and +# \right - include starred version in MATHENV - apply +# - flatten recursively and --flatten expansion is now +# aware of comments (thanks to Tim Connors for patch) +# - Change to post-processing for more reliability for +# deleted math environments +# - On linux systems, recognise and remove DOS style newlines +# - Provide markup for some special preamble commands (\title, +# \author,\date, +# - configurable by setting context2cmd +# - for styles using ulem package, remove \emph and \text.. from list of +# safe commands in order to allow linebreaks within the +# highlighted sections. +# - for ulem style, now show citations by enclosing them in \mbox commands. +# This unfortunately implies linebreaks within citations no longer function, +# so this functionality can be turned off (Option --disable-citation-markup). +# With --enable-citation-markup, the mbox markup is forced for other styles) +# - new substyle COLOR. This is particularly useful for marking up citations +# and some special post-processing is implemented to retain cite +# commands in deleted blocks. +# - four different levels of math-markup +# - Option --driver for choosing driver for modes employing changebar package +# - accept \\* as valid command (and other commands of form \.*). Also accept +# \ (backslashed newline) +# - some typo fixes, include commands defined in preamble as safe commands +# (Sebastian Gouezel) +# - include compared filenames as comments as line 2 and 3 of +# the preamble (can be modified with option --label, and suppressed with +# --no-label), option --visible-label to show files in generated pdf or dvi +# at the beginning of main document +# # Version 0.5 A number of minor improvements based on feedback # Deleted blocks are now shown before added blocks # Package specific processing @@ -499,14 +533,15 @@ import Algorithm::Diff qw(traverse_sequences); use Getopt::Long ; use strict ; +use warnings; use utf8 ; my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); my ($versionstring)=< 0, + WHOLE => 1, + COARSE => 2, + FINE => 3 +}; + + +my (@configlist,@labels, @appendsafelist,@excludesafelist, @appendtextlist,@excludetextlist, @appendcontext1list,@appendcontext2list, @@ -592,9 +648,11 @@ my ($pkg,%packages); $type='UNDERLINE'; $subtype='SAFE'; $floattype='FLOATSAFE'; +$mathmarkup=COARSE; $verbose=0; -$debug=1; +# output debug and intermediate files, set to 0 in final distribution +$debug=0; # define character properties sub IsNonAsciiPunct { return <<'END' # Unicode punctuation but excluding ASCII punctuation +utf8::IsPunct @@ -608,8 +666,7 @@ END } - - my %verbhash; +my %verbhash; Getopt::Long::Configure('bundling'); GetOptions('type|t=s' => \$type, @@ -618,6 +675,9 @@ GetOptions('type|t=s' => \$type, 'config|c=s' => \@configlist, 'preamble|p=s' => \$preamblefile, 'encoding|e=s' => \$encoding, + 'label|L=s' => \@labels, + 'no-label' => \$nolabel, + 'visible-label' => \$visiblelabel, 'exclude-safecmd|A=s' => \@excludesafelist, 'replace-safecmd=s' => \$replacesafe, 'append-safecmd|a=s' => \@appendsafelist, @@ -634,9 +694,13 @@ GetOptions('type|t=s' => \$type, 'show-config' => \$showconfig, 'show-all' => \$showall, 'packages=s' => \@packagelist, + 'allow-spaces' => \$allowspaces, + 'math-markup=s' => \$mathmarkup, + 'enable-citation-markup' => \$enablecitmark, + 'disable-citation-markup' => \$disablecitmark, 'verbose|V' => \$verbose, 'ignore-warnings' => \$ignorewarnings, - 'allow-spaces' => \$allowspaces, + 'driver=s'=> \$driver, 'flatten' => \$flatten, 'version' => \$version, 'help|h|H' => \$help); @@ -656,6 +720,22 @@ if (defined($showall)){ $showpreamble=$showsafe=$showtext=$showconfig=1; } +if (defined($mathmarkup)) { + $mathmarkup=~tr/a-z/A-Z/; + if ( $mathmarkup eq 'OFF' ){ + $mathmarkup=OFF; + } elsif ( $mathmarkup eq 'WHOLE' ){ + $mathmarkup=WHOLE; + } elsif ( $mathmarkup eq 'COARSE' ){ + $mathmarkup=COARSE; + } elsif ( $mathmarkup eq 'FINE' ){ + $mathmarkup=FINE; + } elsif ( $mathmarkup !~ m/^[0123]$/ ) { + die "Illegal value: ($mathmarkup) for option--math-markup. Possible values: OFF,WHOLE,COARSE,FINE,0- "; + } + # else use numerical value +} + # setting extra preamble commands if (defined($preamblefile)) { $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); @@ -663,6 +743,10 @@ if (defined($preamblefile)) { $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); } +if ( defined($driver) ) { + # for changebar only + $latexdiffpreamble=~s/\[dvips\]/[$driver]/sg; +} # setting up @SAFECMDLIST and @SAFECMDEXCL if (defined($replacesafe)) { init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); @@ -679,9 +763,25 @@ foreach $excludesafe ( @excludesafelist ) { # Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode # (there is a conflict between citation and ulem package, see # package documentation) +# Use post-processing + if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { push (@SAFECMDLIST, qr/^cite.*$/); +} else { + ### Experimental: disable text and emph commands + push (@SAFECMDLIST, qr/^cite.*$/) unless $disablecitmark; + push(@SAFECMDEXCL, qr/^emph$/, qr/^text..$/); + # replace \cite{..} by \mbox{\cite{..}} in added or deleted blocks in post-processing + if ( uc($subtype) eq "COLOR" or uc($subtype) eq "DVIPSCOL" ) { + # remove \cite command again from list of safe commands + pop @SAFECMDLIST; + # deleted cite commands + $CITE2CMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite-type commands which should be reinstated in deleted blocks + } else { + $CITECMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite commands which need to be protected within an mbox in UNDERLINE and other modes using ulem + } } +$CITECMD='(?:cite\w*|nocite)' if $enablecitmark ; # as above for explicit selection # setting up @TEXTCMDLIST and @TEXTCMDEXCL if (defined($replacetext)) { @@ -718,9 +818,6 @@ foreach $appendcontext2 ( @appendcontext2list ) { init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); } - - - # setting configuration variables @config=(); foreach $config ( @configlist ) { @@ -754,6 +851,11 @@ foreach $assign ( @config ) { else { die "Unknown variable $1 in assignment.";} } +if ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) { + push(@MATHTEXTCMDLIST,qr/^MATHBLOCK(?:$MATHENV|$MATHARRENV|SQUAREBRACKET)$/); +} + + foreach $pkg ( @packagelist ) { map { $packages{$_}="" } split(/,/,$pkg) ; @@ -776,12 +878,13 @@ if ($showtext) { print_regex_arr(@TEXTCMDLIST); print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; print_regex_arr(@CONTEXT1CMDLIST); - print "\nContext2 commands (last argument textual, command ant its argument will be disabled in deleted passages):\n"; + print "\nContext2 commands (last argument textual, command and its argument will be disabled in deleted passages):\n"; print_regex_arr(@CONTEXT2CMDLIST); print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; print_regex_arr(@TEXTCMDEXCL); } + if ($showconfig) { print "Configuration variables:\n"; print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; @@ -813,14 +916,21 @@ if ($allowspaces) { push @TEXTCMDLIST, @CONTEXT1CMDLIST; push @TEXTCMDLIST, @CONTEXT2CMDLIST; +push @TEXTCMDLIST, @MATHTEXTCMDLIST if $mathmarkup==COARSE; + +# internal additions to SAFECMDLIST +push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/); + # Patterns. These are used by some of the subroutines, too # I can only define them down here because value of extraspace depends on an option - my $pat0 = '(?:[^{}]|\\\{|\\\})*'; - my $pat1 = '(?:[^{}]|\\\{|\\\}|\{'.$pat0.'\})*'; - my $pat2 = '(?:[^{}]|\\\{|\\\}|\{'.$pat1.'\})*'; # - my $pat3 = '(?:[^{}]|\\\{|\\\}|\{'.$pat2.'\})*'; - my $pat4 = '(?:[^{}]|\\\{|\\\}|\{'.$pat3.'\})*'; + my $pat0 = '(?:[^{}])*'; + my $pat1 = '(?:[^{}]|\{'.$pat0.'\})*'; + my $pat2 = '(?:[^{}]|\{'.$pat1.'\})*'; + my $pat3 = '(?:[^{}]|\{'.$pat2.'\})*'; + my $pat4 = '(?:[^{}]|\{'.$pat3.'\})*'; + my $pat5 = '(?:[^{}]|\{'.$pat4.'\})*'; + my $pat6 = '(?:[^{}]|\{'.$pat5.'\})*'; my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; my $quotemarks = '(?:\'\')|(?:\`\`)'; @@ -831,19 +941,44 @@ push @TEXTCMDLIST, @CONTEXT2CMDLIST; my $coords= '[\-.,\s\d]*'; # word: sequence of letters or accents followed by letter my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; - my $cmdleftright='\\\\(?:left|right)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; + my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; - my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat4 . '\}|\(' . $coords .'\))'.$extraspace.')*'; - my $oneletcmd='\\\\.(?:\['.$brat0.'\]|\{'. $pat4 . '\})*'; + my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat6 . '\}|\(' . $coords .'\))'.$extraspace.')*'; + my $backslashnl='\\\\\n'; + my $oneletcmd='\\\\.\*?(?:\['.$brat0.'\]|\{'. $pat6 . '\})*'; my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; -# my $math='\$(?:[^$]|\\\$)*\$'; +## the current maths command cannot cope with newline within the math expression + my $comment='%.*?\n'; - my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; + my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${backslashnl}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; # now we are done setting up and can start working my ($oldfile, $newfile) = @ARGV; +# check for existence of input files +if ( ! -e $oldfile ) { + die "Input file $oldfile does not exist."; +} +if ( ! -e $newfile ) { + die "Input file $newfile does not exist."; +} + + +# set the labels to be included into the file +my ($oldtime,$newtime,$oldlabel,$newlabel); +if (defined($labels[0])) { + $oldlabel=$labels[0] ; +} else { + $oldtime=localtime((stat($oldfile))[9]); + $oldlabel="$oldfile " . " "x(length($newfile)-length($oldfile)) . $oldtime; +} +if (defined($labels[1])) { + $newlabel=$labels[1] ; +} else { + $newtime=localtime((stat($newfile))[9]); + $newlabel="$newfile " . " "x(length($oldfile)-length($newfile)) . $newtime; +} $encoding=guess_encoding($newfile) unless defined($encoding); @@ -872,10 +1007,19 @@ if ($flatten) { $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); } +my @auxlines; if ( length $oldpreamble && length $newpreamble ) { + # pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands) + # and marking up content with latexdiff markup + @auxlines=preprocess_preamble($oldpreamble,$newpreamble); + @oldpreamble = split /\n/, $oldpreamble; @newpreamble = split /\n/, $newpreamble; - + + # If a command is defined in the preamble of the new file, and only uses safe commands, then it can be considered to be safe) (contribution S. Gouezel) + # Base this assessment on the new preamble + add_safe_commands($newpreamble); + %packages=list_packages(@newpreamble) unless %packages; if (defined $packages{"hyperref"} ) { print STDERR "hyperref package detected.\n" if $verbose ; @@ -883,13 +1027,23 @@ if ( length $oldpreamble && length $newpreamble ) { $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); } + print STDERR "Differencing preamble.\n" if $verbose; + # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct unshift @newpreamble,''; unshift @oldpreamble,''; - print STDERR "Differencing preamble.\n" if $verbose; @diffpreamble = linediff(\@oldpreamble, \@newpreamble); # remove dummy line again shift @diffpreamble; + # add filenames, modification time and latexdiff mark + defined($nolabel) or splice @diffpreamble,1,0, + "%DIF LATEXDIFF DIFFERENCE FILE", + ,"%DIF DEL $oldlabel", + "%DIF ADD $newlabel"; + if ( @auxlines ) { + push @diffpreamble,"%DIF DELETED TITLE COMMANDS FOR MARKUP"; + push @diffpreamble,join("\n",@auxlines); + } push @diffpreamble,$latexdiffpreamble; push @diffpreamble,'\begin{document}'; } @@ -900,7 +1054,7 @@ elsif ( !length $oldpreamble && !length $newpreamble ) { exit(2); } -if (defined $packages{"amsmath"} ) { +if (defined $packages{"amsmath"} or defined $packages{"amsart"} or defined $packages{"amsbook"} ) { print STDERR "amsmath package detected.\n" if $verbose ; $MATHARRREPL='align*'; } @@ -912,9 +1066,22 @@ my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); # run difference algorithm @diffbody=bodydiff($oldbody, $newbody); $diffbo=join("",@diffbody); +if ( $debug ) { + open(RAWDIFF,">","latexdiff.debug.bodydiff"); + print RAWDIFF $diffbo; + close(RAWDIFF); +} print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; postprocess($diffbo); $diffall =join("\n",@diffpreamble) ; +# add visible labels +if (defined($visiblelabel)) { + # Give information right after \begin{document} (or at the beginning of the text for files without preamble + ### if \date command is used, add information to \date argument, otherwise give right after \begin{document} + ### $diffall=~s/(\\date$extraspace(?:\[$brat0\])?$extraspace)\{($pat6)\}/$1\{$2 \\ LATEXDIFF comparison \\ Old: $oldlabel \\ New: $newlabel \}/ or + $diffbo = "\\begin{verbatim}LATEXDIFF comparison\nOld: $oldlabel\nNew: $newlabel\\end{verbatim}\n$diffbo" ; +} + $diffall .= "$newleadin$diffbo" ; $diffall .= "\\end{document}$newpost" if length $newpreamble ; if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { @@ -971,6 +1138,9 @@ sub read_file_with_encoding { $output=Encode::decode($encoding,$output); } close FILE; + if ($^O eq "linux" ) { + $output =~ s/\r\n/\n/g ; + } return $output; } @@ -995,13 +1165,66 @@ sub list_packages { return (%packages); } +# Subroutine add_safe_commands modified from version provided by S. Gouezel +# add_safe_commands($preamble) +# scans the argument for \newcommand and \DeclareMathOperator, +# and adds the created commands which are clearly safe to @SAFECMDLIST +sub add_safe_commands { + my ($preamble)=@_; + my $added_command = 1; + + $preamble=~s/(?catfile($dirname,$fname), "\n"; - # content of file becomes replacement value, add \newpage if the command was include - $replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die - "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; - $newpage=(defined($2)? " \\newpage " : "") ; - "$newpage$replacement$newpage"; - }/exg; + print STDERR "DEBUG looking for file ",File::Spec->catfile($dirname,$fname), "\n" if $debug; + # content of file becomes replacement value (use recursion), add \newpage if the command was include + ###$replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + $replacement=flatten(read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding), $preamble,$filename,$encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + # \include always starts a new page; use explicit \newpage command to simulate this + $begline=(defined($1)? $1 : "") ; + $newpage=(defined($3)? " \\newpage " : "") ; + "$begline$newpage$replacement$newpage"; + }/exgm; return($text); } @@ -1133,13 +1359,29 @@ sub bodydiff { my @oldwords = splitlatex($oldwords); print STDERR "Parsing $newfile \n" if $verbose; my @newwords = splitlatex($newwords); - my $token; + + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; pass1(\@oldwords, \@newwords); print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold2.tex"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew2.tex"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } @retwords=pass2(\@oldwords, \@newwords); @@ -1156,6 +1398,9 @@ sub bodydiff { # a latex command sub splitlatex { my ($string) = @_ ; + # if input is empty, return empty list + length($string)>0 or return (); + my @retval=($string =~ m/$pat/osg); if (length($string) != length(join("",@retval))) { @@ -1241,7 +1486,7 @@ sub pass1 { # print STDERR "Unchanged block $cnt, $last1,$last2 \n"; if ($cnt < $MINWORDSBLOCK && $cnt==scalar ( - grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat4\})*)/o + grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat6\})*)/o && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) && scalar(@dummy=split(" ",$2))<3 ) } @$block) ) { @@ -1373,7 +1618,7 @@ sub extracttextblocks { for ($i=0;$i< scalar @$block;$i++) { ($token,$index)=@{ $block->[$i] }; # store pure text blocks - if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*)/o + if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*)/o && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { # we have text or a command which can be treated as text @@ -1427,7 +1672,7 @@ sub extractcommands { # $2: \cmd # $3: last argument # $4: } + trailing spaces - if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) + if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { # push(@$retval,[ $2,$index,$1,$3,$4 ]); ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; @@ -1521,7 +1766,7 @@ sub pass2 { # braces, ampersands, or comments # mark comments with $comment # exclude all other exceptions from scope of open, close like this -# ($openmark, $open,...,$close, $opencomd,command, command,$closecmd, $open, ..., $close, $closemark) +# ($openmark, $open,...,$close, $opencmd,command, command,$closecmd, $open, ..., $close, $closemark) # If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block sub marktags { my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; @@ -1553,21 +1798,30 @@ sub marktags { $noncomment=1; } # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns - if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()([\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { + # also note that second pattern will match \\ + # Note: the second pattern should really be $word =~ /^\\(?!\()(\\|[\w*@]+)/, ie * replaced by + + # and then all commands \" \' etc declared safe. But as I don't have a complete list of one letter + # commands, and nobody has complained so far, I will eave this as is + if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()(\\|[\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { # word is a command or other significant token (not in SAFECMDLIST) ## same conditions as in subroutine extractcommand: # check if token is an alphanumeric command sequence with at least one non-optional argument # \cmd[...]{...}{last argument} # Capturing in the following results in these associations # $1: \cmd[...]{...}{ - # $2: \cmd + # $2: cmd # $3: last argument # $4: } + trailing spaces - ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat4\})*\{)($pat4)(\}\s*)$/so ) - if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { - # word is a text command - we mark up the interior of the word. But if we are in a deleted block ($cmdcomment=1) and - # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) + ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat6\})*\{)($pat6)(\}\s*)$/so ) + if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && (iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL)|| iscmd($2,\@MATHTEXTCMDLIST,\@MATHTEXTCMDEXCL)) + && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { + # Condition 1: word is a command? - if yes, $1,$2,.. will be set as above + # Condition 2: word is a text command - we mark up the interior of the word. There is a separate check for MATHTEXTCMDLIST + # because for $mathmarkup=WHOLE, the commands should not be split in pass1 (ie. math mode commands are not in + # TEXTCMDLIST, but the interior of MATHTEXT commands should be highlighted in both deleted and added blocks + # Condition 3: But if we are in a deleted block ($cmdcomment=1) and + # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) # Because we do not want to disable this command # here we do not use $opencmd and $closecmd($opencmd is empty) if ($cmd==1) { @@ -1587,7 +1841,15 @@ sub marktags { # to suppress linebreak after opening parentheses, which is important # for latexrevise push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } else { + } elsif ( iscmd($commandword,,\@MATHTEXTCMDLIST, \@MATHTEXTCMDEXCL) ) { + # MATHBLOCK pseudo command: consider all commands safe, except & and \\ + # Keep these commands even in deleted blocks, hence set $opencmd and $closecmd (5th and 6th argument of marktags) to + # "" + local @SAFECMDLIST=(".*"); + local @SAFECMDEXCL=('\\','\\\\'); + push(@$retval,$command,marktags("","",$open,$close,"","",$comment,\@argtext)#@argtext + ,$closingbracket); + } else { # normal textcmd or context1cmd in an added block push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); } @@ -1619,6 +1881,9 @@ sub marktags { # preprocess($string, ..) # carry out the following pre-processing steps for all arguments: # 1. Remove leading white-space +# Change \{ to \LEFTBRACE and \} to \RIGHTBRACE +# #. change begin and end commands within comments to BEGINDIF, ENDDIF +# so they don't disturb the pattern matching (if there are several \begin or \end in one line # 2. mark all first empty line (in block of several) with \PAR tokens # 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier # 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) @@ -1628,8 +1893,11 @@ sub marktags { # 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} # 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} # b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} +# 9. Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv +# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH} +# into \MATHBLOCKmath{...} commands, where MATH/math is any valid math environment -# 9. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. +# 10. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. # # NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file # names or labels but it does not matter because they are converted back in the postprocessing step @@ -1639,21 +1907,39 @@ sub preprocess { for (@_) { s/^(\s*)//s; push(@leadin,$1); + # Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE + s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL +# d. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# For added blocks: # c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es -# 2. Remove DIFadd, DIFdel, DIFFaddbegin , ... from picture environments +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# 2. If --block-math-markup option set: Convert \MATHBLOCKmath{..} commands back to environments +# +# Convert all PICTUREblock{..} commands back to the appropriate environments # 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties # within floats (currently recognised float environments: plate,table,figure # plus starred varieties). @@ -1729,7 +2027,7 @@ sub fromhash { # 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always # on a line by themselves, similarly for table environment # 4, undo renaming of the \begin and \end in comments - +# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\} # # Note have to manually synchronize substitution commands below and # DIF.. command names in the header @@ -1747,6 +2045,11 @@ sub postprocess { s/ STOP$//; # Replace \RIGHTBRACE by } s/\\RIGHTBRACE/}/g; + + # change citation commands within comments to protect from processing + if ($CITECMD){ + 1 while s/(%.*)\\($CITECMD)/$1\\CITEDIF$2/m ; + } # Check all deleted blocks: where a deleted block contains a matching \begin and # \end environment (these will be disabled by a %DIFDELCMD statements), enable # these commands again (such that for example displayed math in a deleted equation @@ -1763,55 +2066,72 @@ sub postprocess { ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in ### an error # displayed math environments - $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; - # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above - $delblock=~ s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL + $delblock=~ s/\\MATHBLOCK($MATHENV)\{($pat6)\}/\\MATHBLOCK$MATHREPL\{$2\}/sg; + $delblock=~ s/\\MATHBLOCK($MATHARRENV)\{($pat6)\}/\\MATHBLOCK$MATHARRREPL\{$2\}/sg; } - # b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement # subtracting one from the respective counter to keep numbering consistent with new file - $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + + # c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es while ( $delblock =~ m/($math)(\s*)/sg ) { $cnt2=0; @@ -1822,7 +2142,18 @@ sub postprocess { substr($delblock,$begin2,$len2)=$mathblock; pos($delblock) = $begin2 + length($mathblock); } - + if ($CITE2CMD) { + $delblock=~s/($DELCMDOPEN\s*\\($CITE2CMD)(.*)$DELCMDCLOSE)/ + # Replacement code + {my ($aux,$all); + $aux=$all=$1; + $aux=~s#\n?($DELCMDOPEN|$DELCMDCLOSE)##g; + $all."$aux$AUXCMD\n";}/sge; + } + # or protect \cite commands with \mbox + if ($CITECMD) { + $delblock=~s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat6\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } # splice in modified delblock substr($_,$begin,$len)=$delblock; pos = $begin + length($delblock); @@ -1842,7 +2173,10 @@ sub postprocess { substr($addblock,$begin2,$len2)=$mathblock; pos($addblock) = $begin2 + length($mathblock); } - + if ($CITECMD) { + my $addblockbefore=$addblock; + $addblock=~ s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat2\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } # splice in modified addblock substr($_,$begin,$len)=$addblock; pos = $begin + length($addblock); @@ -1853,6 +2187,7 @@ sub postprocess { # change begin and end commands within comments such that they # don't disturb the pattern matching (if there are several \begin or \end in one line # this substitution is insufficient but that appears unlikely) + # This needs to be repeated here to also get rid of DIFdelcmd-protected environments s/(%.*)\\begin\{(.*)$/$1\\BEGINDIF\{$2/mg ; s/(%.*)\\end\{(.*)$/$1\\ENDDIF\{$2/mg ; @@ -1861,32 +2196,40 @@ sub postprocess { # The next line is complicated. The negative look-ahead insertion makes sure that no \end{$MATHENV} (or other mathematical # environments) are between the \begin{$MATHENV} and \end{MATHMODE} commands. This is necessary as the minimal matching # is not globally minimal but only 'locally' (matching is beginning from the left side of the string) - 1 while s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}((?:.(?!(?:\\end{(?:(?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}|\\begin{MATHMODE})))*?)\\end{MATHMODE}/\\begin{$1}$2\\end{$1}/s; - 1 while s/\\begin{MATHMODE}((?:.(?!\\end{MATHMODE}))*?)\\end{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}/\\begin{$2}$1\\end{$2}/s; - # convert remaining \begin{MATHMODE} \end{MATHMODE} (and not containing & or \\ )into MATHREPL environments - s/\\begin{MATHMODE}((?:(.(?!(?[1])) { + $optargnew=$newhash{$cmd}->[1]; + } else { + $optargnew=""; + } + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + } else { + $optargold=""; + } + + if ( defined($oldhash{$cmd}) ) { + $argold=$oldhash{$cmd}->[2]; + } else { + $argold=""; + } + $argnew=$newhash{$cmd}->[2]; + $argdiff="{" . join("",bodydiff($argold,$argnew)) ."}"; + if ( length $optargnew ) { + $optargdiff="[".join("",bodydiff($optargold,$optargnew))."]" ; + $optargdiff =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g; + $optargdiff =~ s/\\DIFaddend /\\DIFaddendFL /g; + $optargdiff =~ s/\\DIFadd\{/\\DIFaddFL{/g; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + ### print STDERR "DEBUG s/\\Q$newhash{$cmd}->[0]\\E/\\$cmd$optargdiff$argdiff/s\n"; + # Note: \Q and \E force literal interpretation of what it between them but allow + # variable interpolation, such that e.g. \title matches just that and not TAB-itle + $$newpreambleref=~s/\Q$newhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s; + # replace this in old preamble if necessary + if ( defined($oldhash{$cmd}->[0])) { + $$oldpreambleref=~s/\Q$oldhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s ; + } + ### print STDERR "DEBUG NEW PRE ".$$newpreambleref."\n"; + } + + foreach $cmd ( keys %oldhash ) { + # if this has already been dealt with above can just skip + next if defined($newhash{$cmd}) ; + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + $optargdiff="[".join("",bodydiff($optargold,""))."]" ; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + $argdiff="{" . join("",bodydiff($argold,"")) ."}"; + $auxline = "\\$cmd$optargdiff$argdiff"; + $auxline =~s/$/$AUXCMD/sg; + push @auxlines,$auxline; + } + # add auxcmd comment to highlight added lines + return(@auxlines); +} + + + # @diffs=linediff(\@seq1, \@seq2) # mark up lines like this #%DIF mm-mmdnn @@ -2091,7 +2559,7 @@ format as new.tex but has all changes relative to old.tex marked up or commented --subtype=markstyle -s markstyle Add code to preamble for selected style for bracketing commands (e.g. to mark changes in margin) - Available styles: SAFE MARGINAL DVIPSCOL + Available styles: SAFE MARGINAL DVIPSCOL COLOR [ Default: SAFE ] --floattype=markstyle @@ -2207,10 +2675,48 @@ format as new.tex but has all changes relative to old.tex marked up or commented NB For all --show commands, no old.tex or new.tex file needs to be given, and no differencing takes place. +Other configuration options: + --allow-spaces Allow spaces between bracketed or braced arguments to commands [Default requires arguments to directly follow each other without intervening spaces] +--math-markup=level Determine granularity of markup in displayed math environments: + Possible values for level are (both numerical and text labels are acceptable): + off or 0: suppress markup for math environments. Deleted equations will not + appear in diff file. This mode can be used if all the other modes + cause invalid latex code. + whole or 1: Differencing on the level of whole equations. Even trivial changes + to equations cause the whole equation to be marked changed. This + mode can be used if processing in coarse or fine mode results in + invalid latex code. + coarse or 2: Detect changes within equations marked up with a coarse + granularity; changes in equation type (e.g.displaymath to equation) + appear as a change to the complete equation. This mode is recommended + for situations where the content and order of some equations are still + being changed. [Default] + fine or 3: Detect small change in equations and mark up and fine granularity. + This mode is most suitable, if only minor changes to equations are + expected, e.g. correction of typos. + +--disable-citation-markup Suppress citation markup in styles using ulem (UNDERLINE, + FONTSTRIKE, CULINECHBAR) +--enable-citation-markup Protect citation commands in changed sections with \\mbox command + [i.e. use default behaviour for ulem package for other packages] + +Miscelleneous options + +--label=label +-L label Sets the labels used to describe the old and new files. The first use + of this option sets the label describing the old file and the second + use of the option sets the label for the new file. + [Default: use the filename and modification dates for the label] + +--no-label Suppress inclusion of old and new file names as comment in output file + +--visble-label Include old and new filenames (or labels set with --label option) as + visible output + --flatten Replace \\input and \\include commands within body by the content of the files in their argument. If \\includeonly is present in the preamble, only those files are expanded into the document. However, @@ -2218,6 +2724,8 @@ format as new.tex but has all changes relative to old.tex marked up or commented included sections are not expanded. The included files are assumed to be located in the same directories as the old and new master files, respectively, making it possible to organise files into old and new directories. + --flatten is applied recursively, so inputted files can contain further + \\input statements. --help -h Show this help text. @@ -2230,6 +2738,8 @@ format as new.tex but has all changes relative to old.tex marked up or commented Default is to work silently. --version Show version number. + +For further information, consult http://latexdiff.berlios.de EOF } @@ -2392,7 +2902,7 @@ B<-s markstyle> Add code to preamble for selected style for bracketing commands (e.g. to mark changes in margin). This option defines C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. -Available styles: C +Available styles: C [ Default: C ] @@ -2526,7 +3036,7 @@ or table. These commands behave like text commands, except when they occur in a deleted section, when they are disabled, but their argument is shown as deleted text. -=item B<--replace-context1cmd=replace-file> +=item B<--replace-context2cmd=replace-file> =item B<--append-context2cmd=append-file> or =item B<--append-context2cmd="cmd1,cmd2,..."> @@ -2581,18 +3091,70 @@ Combine all --show commands. NB For all --show commands, no C or C file needs to be specified, and no differencing takes place. +=back + +=head2 Other configuration options: + +=over 4 + +=item B<--allow-spaces> + +Allow spaces between bracketed or braced arguments to commands. Note +that this option might have undesirable side effects (unrelated scope +might get lumpeded with preceding commands) so should only be used if the +default produces erroneous results. (Default requires arguments to +directly follow each other without intervening spaces). + +=item B<--math-markup=level> + +Determine granularity of markup in displayed math environments: +Possible values for level are (both numerical and text labels are acceptable): + +C or C<0>: suppress markup for math environments. Deleted equations will not +appear in diff file. This mode can be used if all the other modes +cause invalid latex code. + +C or C<1>: Differencing on the level of whole equations. Even trivial changes +to equations cause the whole equation to be marked changed. This +mode can be used if processing in coarse or fine mode results in +invalid latex code. + +C or C<2>: Detect changes within equations marked up with a coarse +granularity; changes in equation type (e.g.displaymath to equation) +appear as a change to the complete equation. This mode is recommended +for situations where the content and order of some equations are still +being changed. [Default] + +C or C<3>: Detect small change in equations and mark up at fine granularity. +This mode is most suitable, if only minor changes to equations are +expected, e.g. correction of typos. + +=item B<--disable-citation-markup> + +Suppress citation markup in styles using ulem (UNDERLINE, +FONTSTRIKE, CULINECHBAR) + +=item B<--enable-citation-markup> + +Protect citation commands in changed sections with \\mbox command [i.e. use default behaviour for ulem package for other packages] =back =head2 Miscellaneous =over 4 - =item B<--verbose> or B<-V> Output various status information to stderr during processing. Default is to work silently. +=item B<--driver=type> + +Choose driver for changebar package (only relevant for styles using + changebar: CCHANGEBAR CFONTCHBAR CULINECHBAR CHANGEBAR). Possible +drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops + [Default: dvips] + =item B<--ignore-warnings> Suppress warnings about inconsistencies in length between input and @@ -2602,13 +3164,23 @@ syntax unknown to C but the resulting difference argument is often fully functional anyway, particularly if the non-standard latex only occurs in parts of the text which have not changed. -=item B<--allow-spaces> +=item B<--label=label> or +B<-L label> -Allow spaces between bracketed or braced arguments to commands. Note -that this option might have undesirable side effects (unrelated scope -might get lumpeded with preceding commands) so should only be used if the -default produces erroneous results. (Default requires arguments to -directly follow each other without intervening spaces). +Sets the labels used to describe the old and new files. The first use +of this option sets the label describing the old file and the second +use of the option sets the label for the new file, i.e. set both +labels like this C<-L labelold -L labelnew>. +[Default: use the filename and modification dates for the label] + +=item B<--no-label> + +Suppress inclusion of old and new file names as comment in output file + +=item B<--visble-label> + +Include old and new filenames (or labels set with --label option) as +visible output. =item B<--flatten> @@ -2619,11 +3191,12 @@ no recursion is done, i.e. C<\input> and C<\include> commands within included sections are not expanded. The included files are assumed to be located in the same directories as the old and new master files, respectively, making it possible to organise files into old and new directories. +--flatten is applied recursively, so inputted files can contain further +C<\input> statements. -Use of this option is not recommended -primarily the processing time for the large documents is prohibitive, and -the resulting difference document no longer reflects the structure of the -input documents. +Use of this option might result in prohibitive processing times for +larger documents, and the resulting difference document +no longer reflects the structure of the input documents. =item B<--help> or B<-h> @@ -2636,6 +3209,8 @@ Show version number =back + + =head2 Predefined styles =head2 Major types @@ -2704,6 +3279,13 @@ Mark beginning and end of changed blocks with symbols in the margin nearby (usin the standard C<\marginpar> command - note that this sometimes moves somewhat from the intended position. +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. +(It is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete, for example +with citation commands). + =item C An alternative way of marking added passages in blue, and deleted ones in red. Note @@ -2797,26 +3379,49 @@ C<|subsubsection|paragraph|subparagraph)> ] =back -=head1 BUGS +=head1 COMMON PROBLEMS + +=over 10 -UTF-8 support requires a relatively new version of perl (5.8.0 is sufficient -but 5.6.2 up would work OK, too). +=item Citations result in overfull boxes + +There is an incompatibility between the C package, which C uses for underlining and striking out in the UNDERLINE style, +the default style. In order to be able to mark up citations properly, they are placed with an C<\mbox> command in post-processing. As mboxes +cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities: + +1. Use C or C subtype markup (option C<-s COLOR>): If this markup is chosen, then changed citations are no longer marked up +with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color. + +2. Choose option C<--disable-citation-markup> which turns off the marking up of citations: deleted citations are no longer shown, and +added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older) + +=item Changes in complicated mathematical equations result in latex processing errors + +Try options C<--math-markup=whole>. If even that fails, you can turn off mark up for equations with C<--math-markup=off>. + +=back + +=head1 BUGS Option allow-spaces not implemented entirely consistently. It breaks the rules that number and type of white space does not matter, as different numbers of inter-argument spaces are treated as significant. -Please send bug reports -to I. Include the serial number of I +Please submit bug reports on the latexdiff project page I, +send them to user discussion list C (prior subscription +to list required, also on project webpage) +or send them to I. Include the serial number of I (from comments at the top of the source or use B<--version>). If you come across latex files that are error-free and conform to the specifications set out above, and whose differencing still does not result in error-free latex, please send me those files, ideally edited to only contain the -offending passage as long as that still reproduces the problem. +offending passage as long as that still reproduces the problem. If your +file relies on non-standard class files, you must include those. I will not +look at examples where I have trouble to latex the original files. =head1 SEE ALSO -L +L, L =head1 PORTABILITY @@ -2832,13 +3437,15 @@ I requires the I command to be present. =head1 AUTHOR -Copyright (C) 2004-2007 Frederik Tilmann +Version 1.0.2 +Copyright (C) 2004-2012 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 -Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner -Thanks to everyone who send in bug reports. +Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner, +T. Connors, Sebastian Gouezel and many others. +Thanks to the many people who send in bug reports, feature suggestions, and other feedback. =cut @@ -3093,14 +3700,16 @@ sqrt %%END TEXT COMMANDS %%BEGIN CONTEXT1 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text caption %%END CONTEXT1 COMMANDS %%BEGIN CONTEXT2 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text title author +date +institute %%END CONTEXT2 COMMANDS @@ -3198,6 +3807,14 @@ author \providecommand{\DIFdelend}{\protect\nogroupcolor{black}} %DIF END DVIPSCOL PREAMBLE +%DIF COLOR PREAMBLE +\RequirePackage{color} +\providecommand{\DIFaddbegin}{\protect\color{blue}} +\providecommand{\DIFaddend}{\protect\color{black}} +\providecommand{\DIFdelbegin}{\protect\color{red}} +\providecommand{\DIFdelend}{\protect\color{black}} +%DIF END COLOR PREAMBLE + %% FLOAT TYPES diff --git a/Build/source/texk/texlive/linked_scripts/latexdiff/latexrevise.pl b/Build/source/texk/texlive/linked_scripts/latexdiff/latexrevise.pl index 279dac1fc6a..0f333fbb994 100755 --- a/Build/source/texk/texlive/linked_scripts/latexdiff/latexrevise.pl +++ b/Build/source/texk/texlive/linked_scripts/latexdiff/latexrevise.pl @@ -1,30 +1,39 @@ -#!/usr/bin/perl -w +#!/usr/bin/env perl # latexrevise - takes output file of latexdiff and removes either discarded # or appended passages, then deletes all other latexdiff markup # -# Copyright (C) 2004 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2004 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file -# -# Version 0.1 First public release +# Note: version number now keeping up with latexdiff +# Version 1.0.2 Option --version +# Version 1.0.1 no changes to latexrevise # Version 0.3 Updated for compatibility with latexdiff 0.3 output (DIFAUXCMD removal) -# +# Version 0.1 First public release use Getopt::Long ; use strict; +use warnings; + +my $versionstring=< \$accept, 'markup|m=s' => \$markup, 'markup-environment|n=s' => \$markenv, 'no-warnings|q' => \$verbose, + 'version' => \$version, 'verbose|V' => \$verbose, 'help|h|H' => \$help); @@ -87,6 +97,11 @@ if ( $help ) { usage() ; } +if ( $version ) { + die $versionstring ; +} + + if ( ($accept && $decline) || ($accept && $simplify) || ($decline && $simplify) ) { die '-a,-d and -s options are mutually axclusive. Type latexrevise -h to get more help.'; } @@ -493,15 +508,16 @@ which should have been removed already. =head1 BUGS The current version is a beta version which has not yet been -extensively tested, but worked fine locally. Please send bug reports -to I. Include the serial number of I +extensively tested, but worked fine locally. Please submit bug reports through +the latexdiff project page I or send +to I. Include the serial number of I (from comments at the top of the source). If you come across latexdiff output which is not processed correctly by I please include the problem file as well as the old and new files on which it is based, ideally edited to only contain the offending passage as long as that still reproduces the problem. -I gets confused by commented C<\begin{document}> or +Note that I gets confused by commented C<\begin{document}> or C<\end{document}> statements =head1 SEE ALSO @@ -518,6 +534,6 @@ on any platform supporting PERL v5 or higher. Copyright (C) 2004 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 =cut diff --git a/Master/texmf-dist/doc/latex/latexdiff/CHANGES b/Master/texmf-dist/doc/latex/latexdiff/CHANGES deleted file mode 100644 index 18853d35f76..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/CHANGES +++ /dev/null @@ -1,138 +0,0 @@ -Version 0.5 -=========== - -- add \protect in front of all changebar package commands. These prevents error messages - when changes are made to section titles in any styles making use of changebar package - -- For a changed section, the deletion is now reported before the insertion, in common - with standard practice for diff programs - -- "\begin{equation}%" and similar constructs no longer confuse latexdiff - -- deals correctly with some fairly pathological cases of math mode switching - code - should parse but equation numbers and linebreaks might be changed - -- \\[..] is now left alone (previously, this got erroneously interpreted as \ \begin{displaymath}) - -- \(..\) is recognised as a synonym for $...$ - -- introduce new subclasses of textcmd - context1cmd are text commands which should be disabled in a deleted block, as they - are only meaningful in certain contexts (e.g. \caption). However, their - argument is still marked up as deleted (plain) text, surrounded by a pair of braces. - context2cmd behave like text commands except that they are completely disabled in deleted blocks, - including their arguments. - -- array environments within in-lined maths are now underlined correctly - -- if endfloat package is inferred from preamble, then make sure \begin{figure} and \end{figure} - are always on a line by themselves, similarly for table enviroment - -- if hyperref package is used, make wrapper for \DIFadd and \DIFdel which protects markup from becoming - part of link texts where it causes an error - -- if amsmath package is used, then default eqnarray environement (Variable MATHARRREPL) is set to align - (Default: eqnarray). Also, the standard amsmath equation array environments are now recognised as such. - -- new option --packages - -Version 0.42 November 2006 -========================== - -- the auxiliary commands put in to bring latexdiff into and out of - math mode correctly would sometimes not be consistent. This is no longer the - case - -- If a comment was put between two commands within a deleted block, the - latter command would not be disabled by a DIFDELCMD - - - -Version 0.4 January 2006 -======================== - -- $$ $$ usually accepted for displayed equations (but less robust than \[ \] or displaymath environment) - -- For commands which are in textcmd list but not in safecmd list (e.g. \footnote and \section commands) the content is now marked up if they are added or deleted. (Thanks to S. Utcke for alerting me to this shortcoming of previous versions). The downside of this change is that deleted section heads are now shown, messing up the section numbering - -- added RCS and SVN support to latexdiff-vc (previous name latexdiff-cvs) - -- a fast version (latexdiff-fast) uses the UNIX diff command to speed up the differencing phases. - -Minor bug fixes: - -- Improved parsing of textcmd and safecmd lists, some clarification in manual (Thanks to V. Kuhlmann for fix) - -- All \color commands now \protect'ed (V. Kuhlmann) - -- Picture environment within floats now is cleared up properly (Thanks to V. Kuhlmann for fix) - -- non-matching textcommands right before \end{document} are now parsed correctly - -- updates to textcmd (emph, text..) and safecmd lists (emph) - -- fixed \par bug. Previously, this bug resulted new paragraphs to be merged with the following paragraph. - -- better error checking in latexdiff-vc - -- can specify arbitrary number of files in latexdiff-vc - -- can choose output directory in latexdiff-vc - -Version 0.3 August 2005 -========================== - -- fixed bug where a deleted displayed equation would result in math mode commands - being processed in text mode (the "! Missing $ inserted" error). - -- Improved parsing in math mode: Superscript and subscript and \left,\right are now parsed correctly - -- shell script for providing CVS support - -Minor: - -- fixed a bug in utf8 mode that resulted in many warning messages and - failure to parse properly words with national characters - -- Now works with the latest version of Algorithm::Diff (version 1.19) - -- new options "--allow-spaces" and "--ignore-warnings" - -- Better wording and enhanced context for warning messages - -- '|' character is now recognised as valid math mode character - -- Fixed a bug whereby \begin{document} and \end{document} in comments are nevertheless treated as real begin and end points - -- add \protect in front of \nogroupcolor command in DVIPSCOL subtype (old version broke sometimes according to bug reports although I could not replicate the problem) - -- replace \uline by \uwave in CUNDERLINE style, such that added and deleted text parts look different even in math mode - -- Markup within DIFnomarkup enviroment is removed by latexdiff. This can be used to protect parts - for which latexdiff has trouble creating proper latex code. - -- new markup type FONTSTRIKE - - -Version 0.2 September 2004 -=========================== - -- introduced subtype DVIPSCOL (coloring changed blocks for dvips converter) - -- support for utf8 and other encodings - -Minor: - -- removed buggy COLOR subtype - -- Usage information no longer printed automatically after certain syntactic error messages - -- short options -a, -A, -x, -X now really do what is claimed in the manual - -- bug in failback splitting of input was fixed - -- options --exclude-textcmd, --append-textcmd, --exclude-safecmd, and --append-safecmd - can now take comma-separated list as well as a file as argument. - - - diff --git a/Master/texmf-dist/doc/latex/latexdiff/LICENSE b/Master/texmf-dist/doc/latex/latexdiff/LICENSE deleted file mode 100644 index 960fe7469fe..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/LICENSE +++ /dev/null @@ -1,280 +0,0 @@ - GNU GENERAL PUBLIC LICENSE - Version 2, June 1991 - - Copyright (C) 1989, 1991 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. - - 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 diff --git a/Master/texmf-dist/doc/latex/latexdiff/Makefile b/Master/texmf-dist/doc/latex/latexdiff/Makefile deleted file mode 100644 index 45467307879..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/Makefile +++ /dev/null @@ -1,64 +0,0 @@ -# Modify these paths to the requirements of your own system -# For the current setting you will need root permission but -# it is perfectly acceptable to choose user directories -# -INSTALLPATH = /usr/local -INSTALLMANPATH = $(INSTALLPATH)/man -INSTALLEXECPATH = $(INSTALLPATH)/bin - -default: - @echo "To install stand-alone version type: make install" - @echo " (Note the standard version requires prior installation" - @echo " of the PERL package Algorithm::Diff available from " - @echo " the PERL archive www.cpan.org)" - @echo " " - @echo "To install fast version (using UNIX diff) type: make install fast " - @echo " " - @echo "To install the version which uses the system Algorithm::Diff package type: make install-ext" - @echo " " - -install: install-so - -install-ext: install-latexdiff install-latexrevise install-latexdiff-vc install-man - -install-so: install-latexdiff-so install-latexrevise install-latexdiff-vc install-man - -install-fast: install-latexdiff-fast install-latexrevise install-latexdiff-vc install-man - -install-man: - install latexrevise.1 latexdiff.1 latexdiff-vc.1 $(INSTALLMANPATH)/man1 - -install-latexdiff: - install latexdiff $(INSTALLEXECPATH) - -install-latexdiff-so: - if [ -e $(INSTALLEXECPATH)/latexdiff ]; then rm $(INSTALLEXECPATH)/latexdiff; fi - install latexdiff-so $(INSTALLEXECPATH) - cd $(INSTALLEXECPATH); ln -s latexdiff-so latexdiff - -install-latexdiff-fast: - if [ -e $(INSTALLEXECPATH)/latexdiff ]; then rm $(INSTALLEXECPATH)/latexdiff; fi - install latexdiff-fast $(INSTALLEXECPATH) - cd $(INSTALLEXECPATH); ln -s latexdiff-fast latexdiff - -install-latexrevise: - install latexrevise $(INSTALLEXECPATH) - -install-latexdiff-vc: - install latexdiff-vc $(INSTALLEXECPATH) - cd $(INSTALLEXECPATH); for vcs in cvs rcs svn ; do if [ -e latexdiff-$$vcs ]; then rm latexdiff-$$vcs; fi; ln -s latexdiff-vc latexdiff-$$vcs ; done - -test-ext: - @echo "latexdiff example/example-draft.tex example/example-rev.tex (system Algorithm::Diff)" - ./latexdiff -V example/example-draft.tex example/example-rev.tex > example/example-diff.tex - @echo "Difference file created: example/example-diff.tex" - -test-so: - @echo "latexdiff example/example-draft.tex example/example-rev.tex (stand-alone version)" - ./latexdiff-so -V example/example-draft.tex example/example-rev.tex > example/example-diff.tex - @echo "Difference file created: example/example-diff.tex" - -test-fast: - @echo "latexdiff example/example-draft.tex example/example-rev.tex (stand-alone version)" - ./latexdiff-fast -V example/example-draft.tex example/example-rev.tex > example/example-diff.tex - @echo "Difference file created: example/example-diff.tex" diff --git a/Master/texmf-dist/doc/latex/latexdiff/README b/Master/texmf-dist/doc/latex/latexdiff/README deleted file mode 100644 index 78adffb533a..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/README +++ /dev/null @@ -1,98 +0,0 @@ - -INTRODUCTION - -latexdiff is a Perl script, which compares two latex files and marks -up significant differences between them (i.e. a diff for latex files). - Various options are available for visual markup using standard latex -packages such as "color.sty". Changes not directly affecting visible -text, for example in formatting commands, are still marked in -the latex source. - -A rudimentary revision facilility is provided by another Perl script, -latexrevise, which accepts or rejects all changes. Manual -editing of the difference file can be used to override this default -behaviour and accept or reject selected changes only. - -The author is F Tilmann. - - -REQUIREMENTS - -Perl 5.8 or higher must be installed. - The latexdiff script makes use of the Perl package Algorithm::Diff (available -from www.cpan.org, current version 1.19). You can either install this package, or -use the standalone version of latexdiff, latexdiff-so, which has version 1.15 of -this package inlined and does not require external installation of -the package. Because latexdiff uses internal functions of Algorithm:Diff whose -calling format or availability can change without notice, the preferred method is -now to use the standalone version. - -As an alternative, latexdiff-fast has a modified version of Algorithm::Diff inlined, -which internally uses the UNIX diff command. This version is much faster but is dependent -on an external "diff" command. Subtle differences in the algorithm of Algorithm::Diff and -UNIX-diff mean that the resulting set of differences will generally not be the same as -for the standard latexdiff. In most practical cases, these differences are minor, though. - -INSTALLATION UNIX/LINUX - -The basic installation procedure is almost trivial: - -1. Copy latexdiff, latexrevise and latexdiff-vc into a directory which - is in the search path and make them executable. If the Algorithm::Diff - package is not installed, use latexdiff-so instead of latexdiff. - -2. Copy latexdiff.1 and latexrevise.1 into the correct man directory - -3. Optionally create soft links latexdiff-cvs latexdiff-rcs, and - latexdiff-svn for latexdiff-vc. - -The attached Makefile contains example commands to carry out above -steps as root for a typical UNIX installation. Type - - make install (for the stand alone version) -or - make install-ext (for the version using the external Algorithm::Diff) -or - make install-fast (for the version using the UNIX 'diff' function for fast differencing) - -to get it rolling. You can type - - make test -or - make test-ext -or - make test-fast - -to test the respective versions on a brief example before installation - - -DOCUMENTATION: - -Usage instructions are in the manual latexdiff-man.pdf as well as the -man pages. - -CONTRIBUTIONS - -The directory contrib contains code written by others relating to latexdiff. -Currently this directory contains: - -latexdiff-wrap (Author: V. Kuhlmann) An alternative wrapper script which can be used - instead of latexdiff-vc. Its main use is as a template for customised wrapper scripts. - -latexdiff.spec (Author: T. Doerges) spec file for RPM generation - -The following contributions were incorporated into the latexdiff code, or inspired me to -extend latexdiff in a similar way: J. Paisley, N. Becker, K. Huebner - -LICENSE - -This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 as published by -the Free Software Foundation. - -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 (file LICENSE in the -distribution). - diff --git a/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff-wrap b/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff-wrap deleted file mode 100755 index 894b424de36..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff-wrap +++ /dev/null @@ -1,192 +0,0 @@ -#!/bin/bash -# -# latexdiff-wrap -# -# Wrapper for latexdiff, to -# * provide support for documents consiting of more than 1 latex file -# * provide my common arguments -# -# Copyright (C) by Volker Kuhlmann -# Released under the terms of the GNU General Public License (GPL) Version 2. -# See http://www.gnu.org/ for details. -# -# Volker Kuhlmann -# 5, 6, 7, 12, 16, 17 Oct 2005 -# 31 Jan; 5, 7, 13, 15 Feb 2006 -# - -VERSION="0.6, 15 Feb 2006" -AUTHOR="Volker Kuhlmann " -COPYRIGHT="Copyright (C) 2005-2006" - - -#### -#### Constants and initialised variables -# -diffcmd="latexdiff" -diffrc="$HOME/texmf/latexdiff" -#diffargs="-e latin1 --ignore-warnings -p latexdiff-preamble.sty" -diffargs="-e latin1 --ignore-warnings" -diffargs="$diffargs --append-safecmd $diffrc/safe-cmds" -diffargs="$diffargs --append-textcmd $diffrc/text-cmds" -# Note: Can't use multiple --append-safecmd -# show current command lists: -#diffcmd="$diffcmd --show-safecmd --show-textcmd --show-config" - - -#### -#### Version, Usage, Help -# -show_version() { - echo "${0##*/} version $VERSION -$COPYRIGHT by $AUTHOR" -} - -show_usage() { - echo " -Usage: ${0##*/} OLDDIR NEWDIR DIFFDIR [DIFFARGS --] FILE.tex [...] - ${0##*/} --show [DIFFARGS] -Version $VERSION -$COPYRIGHT by $AUTHOR -" -} - -show_help() { - show_usage - echo "\ -For each FILE.tex, build a new file DIFFDIR/FILE.tex with markup of the changes -which were made from OLDDIR/FILE.tex to NEWDIR/FILE.tex. -Any path given with FILE.tex is stripped off. -Any DIFFARGS are added to the latexdiff call, if present (remember to follow -them with a double-hyphen on its own before the FILE arguments). - -With --show, shows the settings latexdiff would be running with, including the -changes applied by the user. -" -} - -# For scripts not using function library only: -Version() { show_version; exitwith ErrVersion; } -Usage() { show_help; exitwith ErrUsage; } -Help() { test "$1" && exitwith ErrHelp show_help; show_help; exitwith ErrOK; } - - -#### -#### Error/Exit codes -# -exitwith() { - exec 1>&2 # write stdout on stderr instead - case "$1" in - ErrOK) - exit 0;; - ErrVersion|ErrUsage|ErrHelp) - # Output generated by function (program) $2, if given - test -n "$2" && "$2" - exit 1;; - # more codes in here - # more codes in here - ErrBadoption) - echo "Bad option '$2'." - echo "Call with -h for help." - exit 9;; - ErrMissingParameter) - echo "A required parameter for option $2 is missing." - echo "Call with -h for help." - exit 9;; - *) - echo "Internal error: exitwith() called with illegal error code '$1'." - exit 19;; - esac -} - - -#### -#### Parse command line parameters -# - -# If the next arg starts with a "-", collect additional argument for latexdiff -# until "--". -scanextraargs() { - addargs=() - case "$1" in -*) - while [ $# -gt 0 -a "$1" != "--" ]; do - addargs=( "${addargs[@]}" "$1" ) - shift - done - test "$1" == "--" && shift - ;; esac - fileargs=( "$@" ) -} - -case "$1" in - --version) Version;; - --usage) Usage;; - --help|-h|-help) Help;; - --show) - shift - scanextraargs "$@" - (set -x - $diffcmd $diffargs "${addargs[@]}" \ - --show-safecmd --show-textcmd --show-config - ) | fmt - exit $? ;; -esac - -olddir="${1%/}" -newdir="${2%/}" -diffdir="${3%/}" - -if ! [ -d "$olddir" -a -d "$newdir" -a -d "$diffdir" ]; then - Help 1>&2 err -fi - -shift 3 - -scanextraargs "$@" -set -- "${fileargs[@]}" - - - -#### -#### Functions -# -#set -x -Log() { echo 1>&2 "+ $@"; "$@"; } - - -#### -#### Main -# - -# Create output directory, just in case. -(set -x -mkdir -p "$diffdir" -) -while [ $# -gt 0 ]; do - file="${1##*/}" - echo Examining: "$file" - # No point running latexdiff if both files are identical, - # but run latexdiff on top-level LaTeX file in any case. - if cmp --quiet "$olddir/$file" "$newdir/$file" \ - && ! grep -lq '\\begin.*{document}' "$newdir/$file"; then - (set -x - cp -p "$olddir/$file" "$diffdir" - ) - else - # Delete file, to make sure it's not clobbered by redirecting stdout - # in case it's a symlink to te original. - test -f "$diffdir/$file" && (set -x - rm "$diffdir/$file" - ) - # Run latexdiff if both input files are present. - run=1 - test -f "$olddir/$file" || { echo 1>&2 "No file: $olddir/$file"; run=; } - test -f "$newdir/$file" || { echo 1>&2 "No file: $newdir/$file"; run=; } - test -n "$run" && \ - (set -x - $diffcmd $diffargs "${addargs[@]}" \ - "$olddir/$file" "$newdir/$file" > "$diffdir/$file" - ) - fi - shift -done diff --git a/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff.spec b/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff.spec deleted file mode 100644 index 9255a69fea9..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/contrib/latexdiff.spec +++ /dev/null @@ -1,58 +0,0 @@ -Summary: Diff for LaTeX files -Name: latexdiff -Version: 0.5 -Release: 1 -License: GPL -Group: Productivity/Publishing/TeX/Utilities -URL: http://www.tug.org/tex-archive/help/Catalogue/entries/latexdiff.html -Source0: %{name}.zip -BuildArch: noarch -BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root -# only required for 'make install-ext' -# Requires: perl-Algorithm-Diff - - -%description -latexdiff is a Perl script, which compares two latex files and marks -up significant differences between them (i.e. a diff for latex files). - Various options are available for visual markup using standard latex -packages such as "color.sty". Changes not directly affecting visible -text, for example in formatting commands, are still marked in -the latex source. - -(C) 2004 Frederik Tilmann - - -%prep -%setup -n %{name} - - -%build -# quick had to adapt the Makefile -%{__mv} Makefile Makefile.old -%{__sed} \ - -e "s;INSTALLPATH = /usr/local;INSTALLPATH = \${DESTDIR}%{_prefix};" \ - -e "s;INSTALLMANPATH = \$(INSTALLPATH)/man;INSTALLMANPATH = \${DESTDIR}%{_mandir};" \ - Makefile.old > Makefile - - -%install -%{__mkdir_p} $RPM_BUILD_ROOT%{_bindir} -%{__mkdir_p} $RPM_BUILD_ROOT%{_mandir}/man1 - -%makeinstall - - -%clean -[ "${RPM_BUILD_ROOT}" != "/" ] && [ -d "${RPM_BUILD_ROOT}" ] && %{__rm} -rf "${RPM_BUILD_ROOT}" - - -%files -%defattr(-,root,root) -%doc example CHANGES LICENSE README -%{_bindir}/* -%{_mandir}/man*/* - -%changelog -* Thu Jan 4 2007 Till Dörges - 0.5-1 -- Initial build. diff --git a/Master/texmf-dist/doc/latex/latexdiff/example/example-draft.tex b/Master/texmf-dist/doc/latex/latexdiff/example/example-draft.tex deleted file mode 100644 index 593a1707121..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/example/example-draft.tex +++ /dev/null @@ -1,59 +0,0 @@ -\documentclass[12pt,a4paper]{article} - -\setlength{\topmargin}{-0.2in} -\setlength{\textheight}{9.5in} -\setlength{\oddsidemargin}{0.0in} - -\setlength{\textwidth}{6.5in} - -\title{latexdiff Example - Draft version} -\author{F Tilmann} - -\begin{document} -\maketitle - -\section*{Introduction} - -This is an extremely simple document that showcases some of latexdiff features. -Type -\begin{verbatim} -latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex -\end{verbatim} -to create the difference file. You can inspect this file directly. Then run either -\begin{verbatim} -pdflatex example-diff.tex -xpdf example-diff.pdf -\end{verbatim} -or -\begin{verbatim} -latex example-diff.tex -dvips -o example-diff.ps example-diff.dvi -gv example-diff.ps -\end{verbatim} -to display the markup. - -\section*{Another section title} - -A paragraph with a line only in the draft document. More things could be said -were it not for the constraints of time and space. - -More things could be said were it not for the constraints of time and space. - -And here is a tipo. - -Here is a table: - -\begin{tabular}{ll} -Name & Description \\ -\hline -Gandalf & Grey \\ -Saruman & White -\end{tabular} - -And sometimes a whole paragraph gets completely rewritten. In this -case latexdiff marks up the whole paragraph even if some words in it -are identical. -No change, no markup! -\end{document} - - diff --git a/Master/texmf-dist/doc/latex/latexdiff/example/example-rev.tex b/Master/texmf-dist/doc/latex/latexdiff/example/example-rev.tex deleted file mode 100644 index 4bcaf156272..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/example/example-rev.tex +++ /dev/null @@ -1,60 +0,0 @@ -\documentclass[12pt,a4paper]{article} - -\setlength{\topmargin}{-0.2in} -\setlength{\textheight}{9.5in} -\setlength{\oddsidemargin}{0.0in} - -\setlength{\textwidth}{6in} - -\title{latexdiff Example - Revised version} -\author{F Tilmann} -% Note how in the preamble visual markup is never used (even -% if some preamble might eventually end up as visible text.) - -\begin{document} -\maketitle - -\section*{Introduction} - -This is an extremely simple document that showcases some of the latexdiff features. -Type -\begin{verbatim} -latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex -\end{verbatim} -to create the difference file. You can inspect this file directly. Then run either -\begin{verbatim} -pdflatex example-diff.tex -xpdf example-diff.pdf -\end{verbatim} -or -\begin{verbatim} -latex example-diff.tex -dvips -o example-diff.ps example-diff.dvi -gv example-diff.ps -\end{verbatim} -to display the markup. - -\section*{Yet another section title} - - More things could be said were it not for the constraints of time and space. - -A paragraph with a line only in the revised document. More things could be -said were it not for the constraints of time and space. - -And here is a typo. - -Here is a table: - -\begin{tabular}{ll} -Name & Description \\ -\hline -Gandalf & White \\ -Saruman & Evil -\end{tabular} - -And now for something completely different, with not a paragraph in sight. -No change, -no markup! -\end{document} - - diff --git a/Master/texmf-dist/doc/latex/latexdiff/latexdiff b/Master/texmf-dist/doc/latex/latexdiff/latexdiff deleted file mode 100755 index efceea4c2ee..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/latexdiff +++ /dev/null @@ -1,2783 +0,0 @@ -#!/usr/bin/perl -w -# latexdiff - differences two latex files on the word level -# and produces a latex file with the differences marked up. -# -# Copyright (C) 2004-2007 F J Tilmann (tilmann@esc.cam.ac.uk) -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. -# -# 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -# -# Detailed usage information at the end of the file -# -# Version 0.5 A number of minor improvements based on feedback -# Deleted blocks are now shown before added blocks -# Package specific processing -# -# Version 0.43 unreleased typo in list of styles at the end -# Add protect to all \cbstart, \cbend commands -# More robust substitution of deleted math commands -# -# Version 0.42 November 06 Bug fixes only -# -# Version 0.4 March 06 option for fast differencing using UNIX diff command, several minor bug fixes (\par bug, improved highlighting of textcmds) -# -# Version 0.3 August 05 improved parsing of displayed math, --allow-spaces -# option, several minor bug fixes -# -# Version 0.25 October 04 Fix bug with deleted equations, add math mode commands to safecmd, add | to allowed interpunctuation signs -# Version 0.2 September 04 extension to utf-8 and variable encodings -# Version 0.1 August 04 First public release - -use Algorithm::Diff qw(traverse_sequences); - -use Getopt::Long ; -use strict ; -use utf8 ; - -my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); - - -my ($versionstring)=< \$type, - 'subtype|s=s' => \$subtype, - 'floattype|f=s' => \$floattype, - 'config|c=s' => \@configlist, - 'preamble|p=s' => \$preamblefile, - 'encoding|e=s' => \$encoding, - 'exclude-safecmd|A=s' => \@excludesafelist, - 'replace-safecmd=s' => \$replacesafe, - 'append-safecmd|a=s' => \@appendsafelist, - 'exclude-textcmd|X=s' => \@excludetextlist, - 'replace-textcmd=s' => \$replacetext, - 'append-textcmd|x=s' => \@appendtextlist, - 'replace-context1cmd=s' => \$replacecontext1, - 'append-context1cmd=s' => \@appendcontext1list, - 'replace-context2cmd=s' => \$replacecontext2, - 'append-context2cmd=s' => \@appendcontext2list, - 'show-preamble' => \$showpreamble, - 'show-safecmd' => \$showsafe, - 'show-textcmd' => \$showtext, - 'show-config' => \$showconfig, - 'show-all' => \$showall, - 'packages=s' => \@packagelist, - 'verbose|V' => \$verbose, - 'ignore-warnings' => \$ignorewarnings, - 'allow-spaces' => \$allowspaces, - 'flatten' => \$flatten, - 'version' => \$version, - 'help|h|H' => \$help); - -if ( $help ) { - usage() ; -} - - -if ( $version ) { - die $versionstring ; -} - -print STDERR $versionstring if $verbose; - -if (defined($showall)){ - $showpreamble=$showsafe=$showtext=$showconfig=1; -} - -# setting extra preamble commands -if (defined($preamblefile)) { - $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); -} else { - $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); -} - -# setting up @SAFECMDLIST and @SAFECMDEXCL -if (defined($replacesafe)) { - init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); -} else { - init_regex_arr_data(\@SAFECMDLIST, "SAFE COMMANDS"); -} -foreach $appendsafe ( @appendsafelist ) { - init_regex_arr_ext(\@SAFECMDLIST, $appendsafe); -} -foreach $excludesafe ( @excludesafelist ) { - init_regex_arr_ext(\@SAFECMDEXCL, $excludesafe); -} - -# Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode -# (there is a conflict between citation and ulem package, see -# package documentation) -if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { - push (@SAFECMDLIST, qr/^cite.*$/); -} - -# setting up @TEXTCMDLIST and @TEXTCMDEXCL -if (defined($replacetext)) { - init_regex_arr_ext(\@TEXTCMDLIST,$replacetext); -} else { - init_regex_arr_data(\@TEXTCMDLIST, "TEXT COMMANDS"); -} -foreach $appendtext ( @appendtextlist ) { - init_regex_arr_ext(\@TEXTCMDLIST, $appendtext); -} -foreach $excludetext ( @excludetextlist ) { - init_regex_arr_ext(\@TEXTCMDEXCL, $excludetext); -} - - -# setting up @CONTEXT1CMDLIST ( @CONTEXT1CMDEXCL exist but is always empty ) -if (defined($replacecontext1)) { - init_regex_arr_ext(\@CONTEXT1CMDLIST,$replacecontext1); -} else { - init_regex_arr_data(\@CONTEXT1CMDLIST, "CONTEXT1 COMMANDS"); -} -foreach $appendcontext1 ( @appendcontext1list ) { - init_regex_arr_ext(\@CONTEXT1CMDLIST, $appendcontext1); -} - - -# setting up @CONTEXT2CMDLIST ( @CONTEXT2CMDEXCL exist but is always empty ) -if (defined($replacecontext2)) { - init_regex_arr_ext(\@CONTEXT2CMDLIST,$replacecontext2); -} else { - init_regex_arr_data(\@CONTEXT2CMDLIST, "CONTEXT2 COMMANDS"); -} -foreach $appendcontext2 ( @appendcontext2list ) { - init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); -} - - - - -# setting configuration variables -@config=(); -foreach $config ( @configlist ) { - if (-f $config ) { - open(FILE,$config) or die ("Couldn't open configuration file $config: $!"); - while () { - chomp; - next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; - push (@config,$_); - } - close(FILE); - } - else { -# foreach ( split(",",$config) ) { -# push @config,$_; -# } - push @config,split(",",$config) - } -} -foreach $assign ( @config ) { - $assign=~ m/\s*(\w*)\s*=\s*(\S*)\s*$/ or die "Illegal assignment $assign in configuration list (must be variable=value)"; - if ( $1 eq "MINWORDSBLOCK" ) { $MINWORDSBLOCK = $2; } - elsif ( $1 eq "FLOATENV" ) { $FLOATENV = $2 ; } - elsif ( $1 eq "PICTUREENV" ) { $PICTUREENV = $2 ; } - elsif ( $1 eq "MATHENV" ) { $MATHENV = $2 ; } - elsif ( $1 eq "MATHREPL" ) { $MATHREPL = $2 ; } - elsif ( $1 eq "MATHARRENV" ) { $MATHARRENV = $2 ; } - elsif ( $1 eq "MATHARRREPL" ) { $MATHARRREPL = $2 ; } - elsif ( $1 eq "ARRENV" ) { $ARRENV = $2 ; } - elsif ( $1 eq "COUNTERCMD" ) { $COUNTERCMD = $2 ; } - else { die "Unknown variable $1 in assignment.";} -} - - -foreach $pkg ( @packagelist ) { - map { $packages{$_}="" } split(/,/,$pkg) ; -} - -if ($showpreamble) { - print "\nPreamble commands:\n"; - print $latexdiffpreamble ; -} - -if ($showsafe) { - print "\nCommands safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE (unless excluded):\n"; - print_regex_arr(@SAFECMDLIST); - print "\nCommands not safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE :\n"; - print_regex_arr(@SAFECMDEXCL); -} - -if ($showtext) { - print "\nCommands with last argument textual (unless excluded) and safe in every context:\n"; - print_regex_arr(@TEXTCMDLIST); - print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; - print_regex_arr(@CONTEXT1CMDLIST); - print "\nContext2 commands (last argument textual, command ant its argument will be disabled in deleted passages):\n"; - print_regex_arr(@CONTEXT2CMDLIST); - print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; - print_regex_arr(@TEXTCMDEXCL); -} - -if ($showconfig) { - print "Configuration variables:\n"; - print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; - print "FLOATENV=$FLOATENV\n"; - print "PICTUREENV=$PICTUREENV\n"; - print "MATHENV=$MATHENV\n"; - print "MATHREPL=$MATHREPL\n"; - print "MATHARRENV=$MATHARRENV\n"; - print "MATHARRREPL=$MATHARRREPL\n"; - print "ARRENV=$ARRENV\n"; - print "COUNTERCMD=$COUNTERCMD\n"; -} -if ($showconfig || $showtext || $showsafe || $showpreamble) { - exit 0; } -if ( @ARGV != 2 ) { - print STDERR "2 and only 2 non-option arguments required. Write latexdiff -h to get help\n"; - exit(2); -} - -# Are extra spaces between command arguments permissible? -my $extraspace; -if ($allowspaces) { - $extraspace='\s*'; -} else { - $extraspace=''; -} - -# append context lists to text lists (as text property is implied) -push @TEXTCMDLIST, @CONTEXT1CMDLIST; -push @TEXTCMDLIST, @CONTEXT2CMDLIST; - - -# Patterns. These are used by some of the subroutines, too -# I can only define them down here because value of extraspace depends on an option - my $pat0 = '(?:[^{}]|\\\{|\\\})*'; - my $pat1 = '(?:[^{}]|\\\{|\\\}|\{'.$pat0.'\})*'; - my $pat2 = '(?:[^{}]|\\\{|\\\}|\{'.$pat1.'\})*'; # - my $pat3 = '(?:[^{}]|\\\{|\\\}|\{'.$pat2.'\})*'; - my $pat4 = '(?:[^{}]|\\\{|\\\}|\{'.$pat3.'\})*'; - my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; - - my $quotemarks = '(?:\'\')|(?:\`\`)'; - my $punct='[0.,\/\'\`:;\"\?\(\)\[\]!~\p{IsNonAsciiPunct}\p{IsNonAsciiS}]'; - my $number='-?\d*\.\d*'; - my $mathpunct='[+=<>\-\|]'; - my $and = '&'; - my $coords= '[\-.,\s\d]*'; -# word: sequence of letters or accents followed by letter - my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; - my $cmdleftright='\\\\(?:left|right)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; - - my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat4 . '\}|\(' . $coords .'\))'.$extraspace.')*'; - my $oneletcmd='\\\\.(?:\['.$brat0.'\]|\{'. $pat4 . '\})*'; - my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; -# my $math='\$(?:[^$]|\\\$)*\$'; - my $comment='%.*?\n'; - my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; - - - -# now we are done setting up and can start working -my ($oldfile, $newfile) = @ARGV; - -$encoding=guess_encoding($newfile) unless defined($encoding); - -$encoding = "utf8" if $encoding =~ m/^utf8/i ; -if (lc($encoding) eq "utf8" ) { - binmode(STDOUT, ":utf8"); - binmode(STDERR, ":utf8"); -} - -$old=read_file_with_encoding($oldfile,$encoding); -$new=read_file_with_encoding($newfile,$encoding); - - - - -# reset time -exetime(1); -($oldpreamble,$oldbody,$oldpost)=splitdoc($old,'\\\\begin\{document\}','\\\\end\{document\}'); - - -($newpreamble,$newbody,$newpost)=splitdoc($new,'\\\\begin\{document\}','\\\\end\{document\}'); - - -if ($flatten) { - $oldbody=flatten($oldbody,$oldpreamble,$oldfile,$encoding); - $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); -} - -if ( length $oldpreamble && length $newpreamble ) { - @oldpreamble = split /\n/, $oldpreamble; - @newpreamble = split /\n/, $newpreamble; - - %packages=list_packages(@newpreamble) unless %packages; - if (defined $packages{"hyperref"} ) { - print STDERR "hyperref package detected.\n" if $verbose ; - $latexdiffpreamble =~ s/\{\\DIFadd\}/{\\DIFaddtex}/g; - $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; - $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); - } - # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct - unshift @newpreamble,''; - unshift @oldpreamble,''; - print STDERR "Differencing preamble.\n" if $verbose; - @diffpreamble = linediff(\@oldpreamble, \@newpreamble); - # remove dummy line again - shift @diffpreamble; - push @diffpreamble,$latexdiffpreamble; - push @diffpreamble,'\begin{document}'; -} -elsif ( !length $oldpreamble && !length $newpreamble ) { - @diffpreamble=(); -} else { - print STDERR "Either both texts must have preamble or neither text must have the preamble.\n"; - exit(2); -} - -if (defined $packages{"amsmath"} ) { - print STDERR "amsmath package detected.\n" if $verbose ; - $MATHARRREPL='align*'; -} - -print STDERR "Preprocessing body. " if $verbose; -my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); - - -# run difference algorithm -@diffbody=bodydiff($oldbody, $newbody); -$diffbo=join("",@diffbody); -print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; -postprocess($diffbo); -$diffall =join("\n",@diffpreamble) ; -$diffall .= "$newleadin$diffbo" ; -$diffall .= "\\end{document}$newpost" if length $newpreamble ; -if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { - print STDERR "Encoding output file to $encoding\n" if $verbose; - $diffall=Encode::encode($encoding,$diffall); - binmode STDOUT; -} -print $diffall; - - -print STDERR "(",exetime()," s)\n","Done.\n" if $verbose; - - - -## guess_encoding(filename) -## reads the first 20 lines of filename and looks for call of inputenc package -## if found, return the option of this package (encoding), otherwise return ascii -sub guess_encoding { - my ($filename)=@_; - my ($i,$enc); - open (FH, $filename) or die("Couldn't open $filename: $!"); - $i=0; - while () { - next if /^\s*%/; # skip comment lines - if (m/\\usepackage\[(\w*?)\]\{inputenc\}/) { - close(FH); - return($1); - } - last if (++$i > 20 ); # scan at most 20 non-comment lines - } - close(FH); - return("ascii"); -} - - -sub read_file_with_encoding { - my ($output); - my ($filename, $encoding) = @_; - - if (lc($encoding) eq "utf8" ) { - open (FILE, "<:utf8",$filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - } elsif ( lc($encoding) eq "ascii") { - open (FILE, $filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - } else { - require Encode; - open (FILE, "<",$filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - print STDERR "Converting $filename from $encoding to utf8\n" if $verbose; - $output=Encode::decode($encoding,$output); - } - close FILE; - return $output; -} - -# %packages=list_packages(@preamble) -# scans the arguments for \documentclass and \usepackage statements and constructs a hash -# whose keys are the included packages, and whose values are the associated optional arguments -sub list_packages { - my (@preamble)=@_; - my %packages=(); - foreach $line ( @preamble ) { - # get rid of comments - $line=~s/(?catfile($dirname,$fname), "\n"; - # content of file becomes replacement value, add \newpage if the command was include - $replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die - "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; - $newpage=(defined($2)? " \\newpage " : "") ; - "$newpage$replacement$newpage"; - }/exg; - - return($text); -} - - -# print_regex_arr(@arr) -# prints regex array without x-ism expansion put in by pearl to stdout -sub print_regex_arr { - my $dumstring; - $dumstring = join(" ",@_); # PERL generates string (?-xism:^ref$) for quoted refex ^ref$ - $dumstring =~ s/\(\?-xism:\^(.*?)\$\)/$1/g; # remove string and ^,$ marks before output - print $dumstring,"\n"; -} - - -# @lines=extrapream($type) -# reads line from appendix (end of file after __END__ token) -sub extrapream { - my $type; - my @retval=("%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; - my ($copy); - - while (@_) { - $copy=0; - $type=shift ; - if ( -f $type ) { - open (FILE,$type) or die "Cannot open preamble file $type: $!"; - print STDERR "Reading preamble file $type\n" if $verbose ; - while () { - chomp ; - if ( $_ =~ m/%DIF PREAMBLE/ ) { - push (@retval,"$_"); - } else { - push (@retval,"$_ %DIF PREAMBLE"); - } - } - } - else { # not (-f $type) - $type=uc($type); # upcase argument - print STDERR "Preamble Internal Type $type\n" if $verbose; - while () { - if ( m/^%DIF $type/ ) { - $copy=1; } - elsif ( m/^%DIF END $type/ ) { - last; } - chomp; - push (@retval,"$_ %DIF PREAMBLE") if $copy; - } - if ( $copy == 0 ) { - print STDERR "\nPreamble style $type not implemented.\n"; - print STDERR "Write latexdiff -h to get help with available styles\n"; - exit(2); - } - seek DATA,0,0; # rewind DATA handle to file begin - } - } - push (@retval,"%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; - return @retval; -} - - -# ($part1,$part2,$part3)=splitdoc($text,$word1,$word2) -# splits $text into 3 parts at $word1 and $word2. -# if neither $word1 nor $word2 exist, $part1 and $part3 are empty, $part2 is $text -# If only $word1 or $word2 exist but not the other, output an error message. - -# NB this version avoids $` and $' for performance reason although it only makes a tiny difference -# (in one test gain a tenth of a second for a 30s run) -sub splitdoc { - my ($text,$word1,$word2)=@_; - my ($part1,$part2,$part3)=("","",""); - my ($rest,$pos); - - if ( $text =~ m/(^[^%]*)($word1)/mg ) { - $pos=pos $text; - $part1=substr($text,0,$pos-length($2)); - $rest=substr($text,$pos); - if ( $rest =~ m/(^[^%]*)($word2)/mg ) { - $pos=pos $rest; - $part2=substr($rest,0,$pos-length($2)); - $part3=substr($rest,$pos); - } - else { - die "$word1 and $word2 not in the correct order or not present as a pair." ; - } - } else { - $part2=$text; - die "$word2 present but not $word1." if ( $text =~ m/(^[^%]*)$word2/ms ); - } - return ($part1,$part2,$part3); -} - - - - - -# bodydiff($old,$new) -sub bodydiff { - my ($oldwords, $newwords) = @_; - my @retwords; - - print STDERR "(",exetime()," s)\n","Splitting into latex tokens \n" if $verbose; - print STDERR "Parsing $oldfile \n" if $verbose; - my @oldwords = splitlatex($oldwords); - print STDERR "Parsing $newfile \n" if $verbose; - my @newwords = splitlatex($newwords); - my $token; - - print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; - pass1(\@oldwords, \@newwords); - - - print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; - - @retwords=pass2(\@oldwords, \@newwords); - - return(@retwords); -} - - - - -# @words=splitlatex($string) -# split string according to latex rules -# Each element of words is either -# a word (including trailing spaces and punctuation) -# a latex command -sub splitlatex { - my ($string) = @_ ; - my @retval=($string =~ m/$pat/osg); - - if (length($string) != length(join("",@retval))) { - print STDERR "\nWARNING: Inconsistency in length of input string and parsed string:\n This often indicates faulty or non-standard latex code.\n In many cases you can ignore this and the following warning messages.\n Note that character numbers in the following are counted beginning after \\begin{document} and are only approximate." unless $ignorewarnings; - print STDERR "DEBUG Original length ",length($string)," Parsed length ",length(join("",@retval)),"\n" if $debug; - print STDERR "DEBUG Input string: |$string|\n" if (length($string)<500) && $debug; - print STDERR "DEBUG Token parsing: |",join("+",@retval),"|\n" if (length($string)<500) && $debug ; - @retval=(); - # slow way only do this if other m//sg method fails - my $last = 0; - while ( $string =~ m/$pat/osg ) { - my $match=$&; - if ($last + length $& != pos $string ) { - my $pos=pos($string); - my $offset=30<$last ? 30 : $last; - my $dum=substr($string,$last-$offset,$pos-$last+2*$offset); - my $dum1=$dum; - my $cnt=$#retval; - my $i; - $dum1 =~ s/\n/ /g; - unless ($ignorewarnings) { - print STDERR "\n$dum1\n"; - print STDERR " " x 30,"^" x ($pos-$last)," " x 30,"\n"; - print STDERR "Missing characters near word " . (scalar @retval) . " character index: " . $last . "-" . pos($string) . " Length: " . length($match) . " Match: |$match| (expected match marked above).\n"; - } - # put in missing characters `by hand' - push (@retval, substr($dum,$offset,$pos-$last-length($match))); -# Note: there seems to be a bug in substr with utf8 that made the following line output substr which were too long, -# using dum instead appears to work -# push (@retval, substr($string,$last, pos($string)-$last-length($match))); - } - push (@retval, $match); - $last=pos $string; - } - - } - return @retval; -} - - -# pass1( \@seq1,\@seq2) -# Look for differences between seq1 and seq2. -# Where an common-subsequence block is flanked by deleted or appended blocks, -# and is shorter than $MINWORDSBLOCK words it is appended -# to the last deleted or appended word. If the block contains tokens other than words -# or punctuation it is not merged. -# Deleted or appended block consisting of words and safe commands only are -# also merged, to prevent break-up in pass2 (after previous isolated words have been removed) -# If there are commands with textual arguments (e.g. \caption) both in corresponding -# appended and deleted blocks split them such that the command and opening bracket -# are one token, then the rest is split up following standard rules, and the closing -# bracket is a separate token, ie. turn -# "\caption{This is a textual argument}" into -# ("\caption{","This ","is ","a ","textual ","argument","}") -# No return value. Destructively changes sequences -sub pass1 { - my $seq1 = shift ; - my $seq2 = shift ; - - my $len1 = scalar @$seq1; - my $len2 = scalar @$seq2; - my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' - - my ($last1,$last2)=(-1,-1) ; - my $cnt=0; - my $block=[]; - my $addblock=[]; - my $delblock=[]; - my $todo=[]; - my $instruction=[]; - my $i; - my (@delmid,@addmid,@dummy); - - my ($addcmds,$delcmds,$matchindex); - my ($addtextblocks,$deltextblocks); - my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); - my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); - - my $adddiscard = sub { - if ($cnt > 0 ) { - $matblkcnt++; - # just after an unchanged block -# print STDERR "Unchanged block $cnt, $last1,$last2 \n"; - if ($cnt < $MINWORDSBLOCK - && $cnt==scalar ( - grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat4\})*)/o - && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) - && scalar(@dummy=split(" ",$2))<3 ) } - @$block) ) { - # merge identical blocks shorter than $MINWORDSBLOCK - # and only containing ordinary words - # with preceding different word - # We cannot carry out this merging immediately as this - # would change the index numbers of seq1 and seq2 and confuse - # the algorithm, instead we store in @$todo where we have to merge - push(@$todo, [ $last1,$last2,$cnt,@$block ]); - } - $block = []; - $cnt=0; $last1=-1; $last2=-1; - } - }; - my $discard=sub { $deltokcnt++; - &$adddiscard; #($_[0],$_[1]); - push(@$delblock,[ $seq1->[$_[0]],$_[0] ]); - $last1=$_[0] }; - - my $add = sub { $addtokcnt++; - &$adddiscard; #($_[0],$_[1]); - push(@$addblock,[ $seq2->[$_[1]],$_[1] ]); - $last2=$_[1] }; - - my $match = sub { $mattokcnt++; - if ($cnt==0) { # first word of matching sequence after changed sequence or at beginning of word sequence - $deltextblocks = extracttextblocks($delblock); - $delblkcnt++ if scalar @$delblock; - $addtextblocks = extracttextblocks($addblock); - $addblkcnt++ if scalar @$addblock; - - $delcmds = extractcommands($delblock); - $addcmds = extractcommands($addblock); - # keygen(third argument of _longestCommonSubsequence) implies to sort on command (0th elements of $addcmd elements) - # the calling format for longestCommonSubsequence has changed between versions of - # Algorithm::Diff so we need to check which one we are using - if ( $algodiffversion > 1.15 ) { - ### Algorithm::Diff 1.19 - $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, 0, sub { $_[0]->[0] } ); - } else { - ### Algorithm::Diff 1.15 - $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, sub { $_[0]->[0] } ); - } - - for ($i=0 ; $i<=$#$matchindex ; $i++) { - if (defined($matchindex->[$i])){ - $j=$matchindex->[$i]; - @delmid=splitlatex($delcmds->[$i][3]); - @addmid=splitlatex($addcmds->[$j][3]); - while (scalar(@$deltextblocks) && $deltextblocks->[0][0]<$delcmds->[$i][1]) { - my ($index,$block,$cnt)=@{ shift(@$deltextblocks) }; - push(@$todo, [$index,-1,$cnt,@$block]); - } - push(@$todo, [ $delcmds->[$i][1],-1,-1,$delcmds->[$i][2],@delmid,$delcmds->[$i][4]]); - - while (scalar(@$addtextblocks) && $addtextblocks->[0][0]<$addcmds->[$j][1]) { - my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; - push(@$todo, [-1,$index,$cnt,@$block]); - } - push(@$todo, [ -1,$addcmds->[$j][1],-1,$addcmds->[$j][2],@addmid,$addcmds->[$j][4]]); - } - } - # mop up remaining textblocks - while (scalar(@$deltextblocks)) { - my ($index,$block,$cnt)=@{ shift(@$deltextblocks) } ; - push(@$todo, [$index,-1,$cnt,@$block]); - } - while (scalar(@$addtextblocks)) { - my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; - push(@$todo, [-1,$index,$cnt,@$block]); - } - - $addblock=[]; - $delblock=[]; - } - push(@$block,$seq2->[$_[1]]); - $cnt++ }; - - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - - - # now carry out the merging/splitting. Refer to elements relative from - # the end (with negative indices) as these offsets don't change before the instruction is executed - # cnt>0: merged small unchanged groups with previous changed blocks - # cnt==-1: split textual commands into components - foreach $instruction ( @$todo) { - ($last1,$last2,$cnt,@$block)=@$instruction ; - if ($cnt>=0) { - splice(@$seq1,$last1-$len1,1+$cnt,join("",$seq1->[$last1-$len1],@$block)) if $last1>=0; - splice(@$seq2,$last2-$len2,1+$cnt,join("",$seq2->[$last2-$len2],@$block)) if $last2>=0; - } else { - splice(@$seq1,$last1-$len1,1,@$block) if $last1>=0; - splice(@$seq2,$last2-$len2,1,@$block) if $last2>=0; - } - } - - if ($verbose) { - print STDERR "\n"; - print STDERR " $mattokcnt matching tokens in $matblkcnt blocks.\n"; - print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; - print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; - } -} - - -# extracttextblocks(\@blockindex) -# $blockindex has the following format -# [ [ token1, index1 ], [token2, index2],.. ] -# where index refers to the index in the original old or new word sequence -# Returns: reference to an array of the form -# [[ $index, $textblock, $cnt ], .. -# where $index index of block to be merged -# $textblock contains all the words to be merged with the word at $index (but does not contain this word) -# $cnt is length of block -# -# requires: iscmd -# -sub extracttextblocks { - my $block=shift; - my ($i,$token,$index); - my $textblock=[]; - my $last=-1; - my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' - my $retval=[]; - - for ($i=0;$i< scalar @$block;$i++) { - ($token,$index)=@{ $block->[$i] }; - # store pure text blocks - if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*)/o - && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) - && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { - # we have text or a command which can be treated as text - if ($last<0) { - # new pure-text block - $last=$index; - } else { - # add to pure-text block - push(@$textblock, $token); - } - } else { - # it is not text - if (scalar(@$textblock)) { - push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); - } - $textblock=[]; - $last=-1; - } - } - # finish processing a possibly unfinished block before returning - if (scalar(@$textblock)) { - push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); - } - return($retval) -} - - - -# extractcommands( \@blockindex ) -# $blockindex has the following format -# [ [ token1, index1 ], [token2, index2],.. ] -# where index refers to the index in the original old or new word sequence -# Returns: reference to an array of the form -# [ [ "\cmd1", index, "\cmd1[optarg]{arg1}{", "arg2" ,"} " ],.. -# where index is just taken from input array -# command must have a textual argument as last argument -# -# requires: iscmd -# -sub extractcommands { - my $block=shift; - my ($i,$token,$index,$cmd,$open,$mid,$closing); - my $retval=[]; - - for ($i=0;$i< scalar @$block;$i++) { - ($token,$index)=@{ $block->[$i] }; - # check if token is an alphanumeric command sequence with at least one non-optional argument - # \cmd[...]{...}{last argument} - # Capturing in the following results in these associations - # $1: \cmd[...]{...}{ - # $2: \cmd - # $3: last argument - # $4: } + trailing spaces - if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { - # push(@$retval,[ $2,$index,$1,$3,$4 ]); - ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; - $closing =~ s/\}/\\RIGHTBRACE/ ; - push(@$retval,[ $cmd,$index,$open,$mid,$closing ]); - } - } - return $retval; -} - -# iscmd($cmd,\@regexarray,\@regexexcl) checks -# return 1 if $cmd matches any of the patterns in the -# array $@regexarray, and none of the patterns in \@regexexcl, otherwise return 0 -sub iscmd { - my ($cmd,$regexar,$regexexcl)=@_; - my ($ret)=0; - foreach $pat ( @$regexar ) { - if ( $cmd =~ m/^${pat}$/ ) { - $ret=1 ; - last; - } - } - return 0 unless $ret; - foreach $pat ( @$regexexcl ) { - return 0 if ( $cmd =~ m/^${pat}$/ ); - } - return 1; -} - - -# pass2( \@seq1,\@seq2) -# Look for differences between seq1 and seq2. -# Mark begin and end of deleted and appended sequences with tags $DELOPEN and $DELCLOSE -# and $ADDOPEN and $ADDCLOSE, respectively, however exclude { } & and all comands, unless -# they match an element of the whitelist (SAFECMD) -# For words in TEXTCMD but not in SAFECMD, enclose interior with $ADDOPEN and $ADDCLOSE brackets -# Deleted comment lines are marked with %DIF < -# Added comment lines are marked with %DIF > -sub pass2 { - my $seq1 = shift ; - my $seq2 = shift ; - - my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); - my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); - - my $retval = []; - my $delhunk = []; - my $addhunk = []; - - my $discard = sub { $deltokcnt++; - push ( @$delhunk, $seq1->[$_[0]]) }; - - my $add = sub { $addtokcnt++; - push ( @$addhunk, $seq2->[$_[1]]) }; - - my $match = sub { $mattokcnt++; - if ( scalar @$delhunk ) { - $delblkcnt++; - # mark up changes, but comment out commands - push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk); - $delhunk = []; - } - if ( scalar @$addhunk ) { - $addblkcnt++; - # we mark up changes, but simply quote commands - push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk); - $addhunk = []; - } - push(@$retval,$seq2->[$_[1]]) }; - - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - # clear up unprocessed hunks - push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk) if scalar @$delhunk; - push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk) if scalar @$addhunk; - - - if ($verbose) { - print STDERR "\n"; - print STDERR " $mattokcnt matching tokens. \n"; - print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; - print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; - } - - return(@$retval); -} - -# marktags($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,\@block) -# returns ($openmark,$open,$block,$close,$closemark) if @block only contains no commands (except white-listed ones), -# braces, ampersands, or comments -# mark comments with $comment -# exclude all other exceptions from scope of open, close like this -# ($openmark, $open,...,$close, $opencomd,command, command,$closecmd, $open, ..., $close, $closemark) -# If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block -sub marktags { - my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; - my $word; - my (@argtext); - my $retval=[]; - my $noncomment=0; - my $cmd=-1; # -1 at beginning 0: last token written is a ordinary word - # 1: last token written is a command - # for keeping track whether we are just in a command sequence or in a word sequence - my $cmdcomment= ($opencmd =~ m/^%/); # Flag to indicate whether opencmd is a comment (i.e. if we intend to simply comment out changed commands) - my ($command,$commandword,$closingbracket) ; # temporary variables needed below to remember sub-pattern matches - -# split this block to flatten out sequences joined in pass1 - @$block=splitlatex(join "",@$block); - foreach (@$block) { - $word=$_; - if ( $word =~ s/^%/%$comment/ ) { - # a comment - if ($cmd==1) { - push (@$retval,$closecmd) ; - $cmd=-1; - } - push (@$retval,$word); - next; - } - if (! $noncomment) { - push (@$retval,$openmark); - $noncomment=1; - } - # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns - if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()([\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { - # word is a command or other significant token (not in SAFECMDLIST) - ## same conditions as in subroutine extractcommand: - # check if token is an alphanumeric command sequence with at least one non-optional argument - # \cmd[...]{...}{last argument} - # Capturing in the following results in these associations - # $1: \cmd[...]{...}{ - # $2: \cmd - # $3: last argument - # $4: } + trailing spaces - ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat4\})*\{)($pat4)(\}\s*)$/so ) - if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { - # word is a text command - we mark up the interior of the word. But if we are in a deleted block ($cmdcomment=1) and - # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) - # Because we do not want to disable this command - # here we do not use $opencmd and $closecmd($opencmd is empty) - if ($cmd==1) { - push (@$retval,$closecmd) ; - } elsif ($cmd==0) { - push (@$retval,$close) ; - } - $command=$1; $commandword=$2; $closingbracket=$4; - @argtext=splitlatex($3); # split textual argument into tokens - # and mark it up (but we do not need openmark and closemark) - # insert command with initial arguments, marked-up final argument, and closing bracket - if ( $cmdcomment && iscmd($commandword,\@CONTEXT1CMDLIST, \@CONTEXT1CMDEXCL) ) { - # context1cmd in a deleted environment; delete command itself but keep last argument, marked up - push (@$retval,$opencmd); - $command =~ s/\n/\n${opencmd}/sg ; # repeat opencmd at the beginning of each line - # argument, note that the additional comment character is included - # to suppress linebreak after opening parentheses, which is important - # for latexrevise - push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } else { - # normal textcmd or context1cmd in an added block - push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } - push (@$retval,$AUXCMD,"\n") if $cmdcomment ; - $cmd=-1 ; - } else { - # ordinary command - push (@$retval,$opencmd) if $cmd==-1 ; - push (@$retval,$close,$opencmd) if $cmd==0 ; - $word =~ s/\n/\n${opencmd}/sg if $cmdcomment ; # if opencmd is a comment, repeat this at the beginning of every line - push (@$retval,$word); - $cmd=1; - } - } else { - # just an ordinary word or word in SAFECMD - push (@$retval,$open) if $cmd==-1 ; - push (@$retval,$closecmd,$open) if $cmd==1 ; - push (@$retval,$word); - $cmd=0; - } - } - push (@$retval,$close) if $cmd==0; - push (@$retval,$closecmd) if $cmd==1; - - push (@$retval,$closemark) if ($noncomment); - return @$retval; -} - -# preprocess($string, ..) -# carry out the following pre-processing steps for all arguments: -# 1. Remove leading white-space -# 2. mark all first empty line (in block of several) with \PAR tokens -# 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier -# 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) -# into \verb{hash} -# 5. Convert \begin{verbatim} some verbatim text \end{verbatim} into \verbatim{hash} -# 6. Convert _n into \SUBSCRIPTNB{n} and _{nnn} into \SUBSCRIPT{nn} -# 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} -# 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} -# b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} - -# 9. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. -# -# NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file -# names or labels but it does not matter because they are converted back in the postprocessing step -# Returns: leading white space removed in step 1 -sub preprocess { - my @leadin=() ; - for (@_) { - s/^(\s*)//s; - push(@leadin,$1); - s/\n(\s*?)\n((?:\s*\n)*)/\n$1\\PAR\n$2/g ; - s/(?{$hstr}) && $string ne $hash->{$hstr}) { - warn "Repeated hash value for verbatim mode in spite of different content."; - $hstr="-$hstr"; - } - $hash->{$hstr}=$string; - return($hstr); -} - -#string=fromhash(\%hash,$fromstring) -# restores string value stored in hash -#string=fromhash(\%hash,$fromstring,$prependstring) -# additionally begins each line with prependstring -sub fromhash { - my ($hash,$hstr)=($_[0],$_[1]); - my $retstr=$hash->{$hstr}; - if ( $#_ >= 2) { - $retstr =~ s/^/$_[2]/mg; - } - return $retstr; -} - - -# postprocess($string, ..) -# carry out the following post-processing steps for all arguments: -# * Remove STOP token from the end -# * Replace \RIGHTBRACE by } -# 1. Check all deleted blocks: -# a.where a deleted block contains a matching \begin and -# \end environment (these will be disabled by a %DIFDELCMD statements), for selected environment enable enable -# these commands again (such that for example displayed math in a deleted equation -# is properly within math mode. For math mode environments replace numbered equation -# environments with their display only variety (so that equation numbers in new file and -# diff file are identical). Where the correct type of math environment cannot be determined -# use a place holder MATHMODE -# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement -# subtracting one from the respective counter to keep numbering consistent with new file -# Replace all MATHMODE environment commands by the correct environment to achieve matching -# pairs -# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es -# 2. Remove DIFadd, DIFdel, DIFFaddbegin , ... from picture environments -# 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties -# within floats (currently recognised float environments: plate,table,figure -# plus starred varieties). -# 4. Remove empty %DIFDELCMD < lines -# 4. Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \] -# Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$ -# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn} -# 6. Convert \SUBSCRIPTNB{n} into _n and \SUBCRIPT{nn} into _{nnn} -# 7. Expand hashes of verb and verbatim environments -# 8. Convert '\PERCENTAGE ' back into '\%' -# 9.. remove all \PAR tokens -# 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always -# on a line by themselves, similarly for table environment -# 4, undo renaming of the \begin and \end in comments - -# -# Note have to manually synchronize substitution commands below and -# DIF.. command names in the header -sub postprocess { - my ($begin,$len,$cnt,$float,$delblock,$addblock); - # second level blocks - my ($begin2,$cnt2,$len2,$eqarrayblock,$mathblock); - - for (@_) { - - # change $'s in comments to something harmless - 1 while s/(%.*)\$/$1DOLLARDIF/mg ; - - # Remove final STOP token - s/ STOP$//; - # Replace \RIGHTBRACE by } - s/\\RIGHTBRACE/}/g; - # Check all deleted blocks: where a deleted block contains a matching \begin and - # \end environment (these will be disabled by a %DIFDELCMD statements), enable - # these commands again (such that for example displayed math in a deleted equation - # is properly within math mode. For math mode environments replace numbered equation - # environments with their display only variety (so that equation numbers in new file and - # diff file are identical - while ( m/\\DIFdelbegin.*?\\DIFdelend/sg ) { - $cnt=0; - $len=length($&); - $begin=pos($_) - $len; - $delblock=$&; - - - ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in - ### an error - # displayed math environments - $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; - # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above - $delblock=~ s/(?[$_[0]]) }; - my $add = sub { if (! scalar @$block) { - @begin=('a',$_[0],$_[1]) ;} - elsif ( $begin[0] eq 'd' ) { - $begin[0]='c'; $begin[2]=$_[1]; - push(@$block, "%DIF -------") } - push(@$block, $seq2->[$_[1]] . " %DIF > " ) }; - my $match = sub { if ( scalar @$block ) { - if ( $begin[0] eq 'd' && $begin[1]!=$_[0]-1) { - $instring = sprintf "%%DIF %d-%dd%d",$begin[1],$_[0]-1,$begin[2]; } - elsif ( $begin[0] eq 'a' && $begin[2]!=$_[1]-1) { - $instring = sprintf "%%DIF %da%d-%d",$begin[1],$begin[2],$_[1]-1; } - elsif ( $begin[0] eq 'c' ) { - $instring = sprintf "%%DIF %sc%s", - ($begin[1]==$_[0]-1) ? "$begin[1]" : $begin[1]."-".($_[0]-1) , - ($begin[2]==$_[1]-1) ? "$begin[2]" : $begin[2]."-".($_[1]-1) ; } - else { - $instring = sprintf "%%DIF %d%s%d",$begin[1],$begin[0],$begin[2]; } - push @$retseq, $instring,@$block, "%DIF -------" ; - $block = []; - } - push @$retseq, $seq2->[$_[1]] - }; - # key function: remove multiple spaces (such that insertion or deletion of redundant white space is not reported) - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - push @$retseq, @$block if scalar @$block; - - return wantarray ? @$retseq : $retseq ; -} - - - -# init_regex_arr_data(\@array,"TOKEN INIT") -# scans DATA file handel for line "%% TOKEN INIT" line -# then appends each line not beginning with % into array (as a quoted regex) -sub init_regex_arr_data { - my ($arr,$token)=@_; - my ($copy); - while () { - if ( m/^%%BEGIN $token\s*$/ ) { - $copy=1; } - elsif ( m/^%%END $token\s*/ ) { - last; } - chomp; - push (@$arr,qr/^$_$/) if ( $copy && !/^%/ ) ; - } - seek DATA,0,0; # rewind DATA handle to file begin -} - - -# init_regex_arr_ext(\@array,$arg) -# fills array with regular expressions. -# if arg is a file name, then read in list of regular expressions from that file -# (one expression per line) -# Otherwise treat arg as a comma separated list of regular expressions -sub init_regex_arr_ext { - my ($arr,$arg)=@_; - my $regex; - if ( -f $ arg ) { - open(FILE,"$arg") or die ("Couldn't open $arg: $!"); - while () { - chomp; - next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; - push (@$arr,qr/^$_$/); - } - close(FILE); - } - else { - # assume it is a comma-separated list of reg-ex - foreach $regex (split(qr/(?=1) { - $reset=shift; - } - if ($reset) { - $lasttime=times(); - } - else { - $retval=times()-$lasttime; - $lasttime=$lasttime+$retval; - return($retval); - } -} - - -sub usage { - die <<"EOF"; -Usage: $0 [options] old.tex new.tex > diff.tex - -Compares two latex files and writes tex code to stdout, which has the same -format as new.tex but has all changes relative to old.tex marked up or commented. - ---type=markupstyle --t markupstyle Add code to preamble for selected markup style - Available styles: UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE - CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR - [ Default: UNDERLINE ] - ---subtype=markstyle --s markstyle Add code to preamble for selected style for bracketing - commands (e.g. to mark changes in margin) - Available styles: SAFE MARGINAL DVIPSCOL - [ Default: SAFE ] - ---floattype=markstyle --f markstyle Add code to preamble for selected style which - replace standard marking and markup commands within floats - (e.g., marginal remarks cause an error within floats - so marginal marking can be disabled thus) - Available styles: FLOATSAFE IDENTICAL - [ Default: FLOATSAFE ] - ---encoding=enc --e enc Specify encoding of old.tex and new.tex. Typical encodings are - ascii, utf8, latin1, latin9. A list of available encodings can be - obtained by executing - perl -MEncode -e 'print join ("\\n",Encode->encodings( ":all" )) ;' - [Default encoding is utf8 unless the first few lines of the preamble contain - an invocation "\\usepackage[..]{inputenc} in which case the - encoding chosen by this command is asssumed. Note that ASCII (standard - latex) is a subset of utf8] - ---preamble=file --p file Insert file at end of preamble instead of auto-generating - preamble. The preamble must define the following commands - \\DIFaddbegin,\\DIFaddend,\\DIFadd{..}, - \\DIFdelbegin,\\DIFdelend,\\DIFdel{..}, - and varieties for use within floats - \\DIFaddbeginFL,\\DIFaddendFL,\\DIFaddFL{..}, - \\DIFdelbeginFL,\\DIFdelendFL,\\DIFdelFL{..} - (If this option is set -t, -s, and -f options - are ignored.) - ---exclude-safecmd=exclude-file ---exclude-safecmd="cmd1,cmd2,..." --A exclude-file ---replace-safecmd=replace-file ---append-safecmd=append-file ---append-safecmd="cmd1,cmd2,..." --a append-file Exclude from, replace or append to the list of regex - matching commands which are safe to use within the - scope of a \\DIFadd or \\DIFdel command. The file must contain - one Perl-RegEx per line (Comment lines beginning with # or % are - ignored). A literal comma within the comma-separated list must be - escaped thus "\\,", Note that the RegEx needs to match the whole of - the token, i.e., /^regex\$/ is implied and that the initial - "\\" of the command is not included. The --exclude-safecmd - and --append-safecmd options can be combined with the --replace-safecmd - option and can be used repeatedly to add cumulatively to the lists. - ---exclude-textcmd=exclude-file ---exclude-textcmd="cmd1,cmd2,..." --X exclude-file ---replace-textcmd=replace-file ---append-textcmd=append-file ---append-textcmd="cmd1,cmd2,..." --x append-file Exclude from, replace or append to the list of regex - matching commands whose last argument is text. See - entry for --exclude-safecmd directly above for further details. - ---replace-context1cmd=replace-file ---append-context1cmd=append-file ---append-context1cmd="cmd1,cmd2,..." - Replace or append to the list of regex matching commands - whose last argument is text but which require a particular - context to work, e.g. \\caption will only work within a figure - or table. These commands behave like text commands, except when - they occur in a deleted section, when they are disabled, but their - argument is shown as deleted text. - ---replace-context2cmd=replace-file ---append-context2cmd=append-file ---append-context2cmd="cmd1,cmd2,..." - As corresponding commands for context1. The only difference is that - context2 commands are completely disabled in deleted sections, including - their arguments. - - ---config var1=val1,var2=val2,... --c var1=val1,.. Set configuration variables. --c configfile Available variables: - MINWORDSBLOCK (integer) - FLOATENV (RegEx) - PICTUREENV (RegEx) - MATHENV (RegEx) - MATHREPL (String) - MATHARRENV (RegEx) - MATHARRREPL (String) - ARRENV (RegEx) - COUNTERCMD (RegEx) - This option can be repeated. - - ---packages=pkg1,pkg2,.. - Tell latexdiff that .tex file is processed with the packages in list - loaded. This is normally not necessary if the .tex file includes the - preamble, as the preamble is automatically scanned for \\usepackage commands. - Use of the --packages option disables automatic scanning, so if for any - reason package specific parsing needs to be switched off, use --packages=none. - The following packages trigger special behaviour: - endfloat hyperref amsmath - [ Default: scan the preamble for \\usepackage commands to determine - loaded packages.] - ---show-preamble Print generated or included preamble commands to stdout. - ---show-safecmd Print list of regex matching and excluding safe commands. - ---show-textcmd Print list of regex matching and excluding commands with text argument. - ---show-config Show values of configuration variables - ---show-all Show all of the above - - NB For all --show commands, no old.tex or new.tex file needs to be given, and no - differencing takes place. - ---allow-spaces Allow spaces between bracketed or braced arguments to commands - [Default requires arguments to directly follow each other without - intervening spaces] - ---flatten Replace \\input and \\include commands within body by the content - of the files in their argument. If \\includeonly is present in the - preamble, only those files are expanded into the document. However, - no recursion is done, i.e. \\input and \\include commands within - included sections are not expanded. The included files are assumed to - be located in the same directories as the old and new master files, - respectively, making it possible to organise files into old and new directories. - ---help --h Show this help text. - ---ignore-warnings Suppress warnings about inconsistencies in length between input - and parsed strings and missing characters. - ---verbose --V Output various status information to stderr during processing. - Default is to work silently. - ---version Show version number. -EOF -} - -=head1 NAME - -latexdiff - determine and markup differences between two latex files - -=head1 SYNOPSIS - -B [ B ] F F > F - -=head1 DESCRIPTION - -Briefly, I is a utility program to aid in the management of -revisions of latex documents. It compares two valid latex files, here -called C and C, finds significant differences -between them (i.e., ignoring the number of white spaces and position -of line breaks), and adds special commands to highlight the -differences. Where visual highlighting is not possible, e.g. for changes -in the formatting, the differences are -nevertheless marked up in the source. - -The program treats the preamble differently from the main document. -Differences between the preambles are found using line-based -differencing (similarly to the Unix diff command, but ignoring white -spaces). A comment, "S>>" is appended to each added line, i.e. a -line present in C but not in C. Discarded lines - are deactivated by prepending "S>>". Changed blocks are preceded by -comment lines giving information about line numbers in the original files. Where there are insignificant -differences, the resulting file C will be similar to -C. At the end of the preamble, the definitions for I markup commands are inserted. -In differencing the main body of the text, I attempts to -satisfy the following guidelines (in order of priority): - -=over 3 - -=item 1 - -If both C and C are valid LaTeX, then the resulting -C should also be valid LateX. (NB If a few plain TeX commands -are used within C or C then C is not -guaranteed to work but usually will). - -=item 2 - -Significant differences are determined on the level of -individual words. All significant differences, including differences -between comments should be clearly marked in the resulting source code -C. - -=item 3 - -If a changed passage contains text or text-producing commands, then -running C through LateX should produce output where added -and discarded passages are highlighted. - -=item 4 - -Where there are insignificant differences, e.g. in the positioning of -line breaks, C should follow the formatting of C - -=back - -For differencing the same algorithm as I is used but words -instead of lines are compared. An attempt is made to recognize -blocks which are completely changed such that they can be marked up as a unit. -Comments are differenced line by line -but the number of spaces within comments is ignored. Commands including -all their arguments are generally compared as one unit, i.e., no mark-up -is inserted into the arguments of commands. However, for a selected -number of commands (for example, C<\caption> and all sectioning -commands) the last argument is known to be text. This text is -split into words and differenced just as ordinary text (use options to -show and change the list of text commands, see below). As the -algorithm has no detailed knowledge of LaTeX, it assumes all pairs of -curly braces immediately following a command (i.e. a sequence of -letters beginning with a backslash) are arguments for that command. -As a restriction to condition 1 above it is thus necessary to surround -all arguments with curly braces, and to not insert -extraneous spaces. For example, write - - \section{\textem{This is an emphasized section title}} - -and not - - \section {\textem{This is an emphasized section title}} - -or - - \section\textem{This is an emphasized section title} - -even though all varieties are the same to LaTeX (but see -B<--allow-spaces> option which allows the second variety). - -For environments whose content does not conform to standard LaTeX or -where graphical markup does not make sense all markup commands can be -removed by setting the PICTUREENV configuration variable, set by -default to C and C environments; see B<--config> -option). The latter environment (C) can be used to -protect parts of the latex file where the markup results in illegal -markup. You have to surround the offending passage in both the old and -new file by C<\begin{DIFnomarkup}> and C<\end{DIFnomarkup}>. You must -define the environment in the preambles of both old and new -documents. I prefer to define it as a null-environment, - -C<\newenvironment{DIFnomarkup}{}{}> - -but the choice is yours. Any markup within the environment will be -removed, and generally everything within the environment will just be -taken from the new file. - -It is also possible to difference files which do not have a preamble. - In this case, the file is processed in the main document -mode, but the definitions of the markup commands are not inserted. - -All markup commands inserted by I begin with "C<\DIF>". Added -blocks containing words, commands or comments which are in C -but not in C are marked by C<\DIFaddbegin> and C<\DIFaddend>. -Discarded blocks are marked by C<\DIFdelbegin> and C<\DIFdelend>. -Within added blocks all text is highlighted with C<\DIFadd> like this: -C<\DIFadd{Added text block}> -Selected `safe' commands can be contained in these text blocks as well -(use options to show and change the list of safe commands, see below). -All other commands as well as braces "{" and "}" are never put within -the scope of C<\DIFadd>. Added comments are marked by prepending -"S >>". - -Within deleted blocks text is highlighted with C<\DIFdel>. Deleted -comments are marked by prepending "S >>". Non-safe command -and curly braces within deleted blocks are commented out with -"S >>". - - - -=head1 OPTIONS - -=head2 Preamble - -The following options determine the visual markup style by adding the appropriate -command definitions to the preamble. See the end of this section for a description of -available styles. - -=over 4 - -=item B<--type=markupstyle> or -B<-t markupstyle> - -Add code to preamble for selected markup style. This option defines -C<\DIFadd> and C<\DIFdel> commands. -Available styles: - -C - -[ Default: C ] - -=item B<--subtype=markstyle> or -B<-s markstyle> - -Add code to preamble for selected style for bracketing -commands (e.g. to mark changes in margin). This option defines -C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. -Available styles: C - -[ Default: C ] - -=item B<--floattype=markstyle> or -B<-f markstyle> - -Add code to preamble for selected style which -replace standard marking and markup commands within floats -(e.g., marginal remarks cause an error within floats -so marginal marking can be disabled thus). This option defines all -C<\DIF...FL> commands. -Available styles: C - -[ Default: C ] - -=item B<--encoding=enc> or -B<-e enc> - -Specify encoding of old.tex and new.tex. Typical encodings are -C, C, C, C. A list of available encodings can be -obtained by executing - -Cencodings( ":all" )) ;' > - -[Default encoding is utf8 unless the first few lines of the preamble contain -an invocation C<\usepackage[..]{inputenc}> in which case the -encoding chosen by this command is asssumed. Note that ASCII (standard -latex) is a subset of utf8] - -=item B<--preamble=file> or -B<-p file> - -Insert file at end of preamble instead of generating -preamble. The preamble must define the following commands -C<\DIFaddbegin, \DIFaddend, \DIFadd{..}, -\DIFdelbegin,\DIFdelend,\DIFdel{..},> -and varieties for use within floats -C<\DIFaddbeginFL, \DIFaddendFL, \DIFaddFL{..}, -\DIFdelbeginFL, \DIFdelendFL, \DIFdelFL{..}> -(If this option is set B<-t>, B<-s>, and B<-f> options -are ignored.) - -=item B<--packages=pkg1,pkg2,..> - -Tell latexdiff that .tex file is processed with the packages in list -loaded. This is normally not necessary if the .tex file includes the -preamble, as the preamble is automatically scanned for C<\usepackage> commands. -Use of the B<--packages> option disables automatic scanning, so if for any -reason package specific parsing needs to be switched off, use B<--packages=none>. -The following packages trigger special behaviour: - -=over 8 - -=item C - -Configuration variable amsmath is set to C (Default: C) - -=item C - -Ensure that C<\begin{figure}> and C<\end{figure}> always appear by themselves on a line. - -=item C - -Change name of C<\DIFadd> and C<\DIFdel> commands to C<\DIFaddtex> and C<\DIFdeltex> and -define new C<\DIFadd> and C<\DIFdel> commands, which provide a wrapper for these commands, -using them for the text but not for the link defining command (where any markup would cause -errors). - -=back - -[ Default: scan the preamble for C<\\usepackage> commands to determine - loaded packages.] - - - -=item B<--show-preamble> - -Print generated or included preamble commands to stdout. - -=back - -=head2 Configuration - -=over 4 - -=item B<--exclude-safecmd=exclude-file> or -B<-A exclude-file> or B<--exclude-safecmd="cmd1,cmd2,..."> - -=item B<--replace-safecmd=replace-file> - -=item B<--append-safecmd=append-file> or -B<-a append-file> or B<--append-safecmd="cmd1,cmd2,..."> - -Exclude from, replace or append to the list of regular expressions (RegEx) -matching commands which are safe to use within the -scope of a C<\DIFadd> or C<\DIFdel> command. The file must contain -one Perl-RegEx per line (Comment lines beginning with # or % are -ignored). Note that the RegEx needs to match the whole of -the token, i.e., /^regex$/ is implied and that the initial -"\" of the command is not included. -The B<--exclude-safecmd> and B<--append-safecmd> options can be combined with the -B<--replace-safecmd> -option and can be used repeatedly to add cumulatively to the lists. - B<--exclude-safecmd> -and B<--append-safecmd> can also take a comma separated list as input. If a -comma for one of the regex is required, escape it thus "\,". In most cases it -will be necessary to protect the comma-separated list from the shell by putting -it in quotation marks. - -=item B<--exclude-textcmd=exclude-file> or -B<-X exclude-file> or B<--exclude-textcmd="cmd1,cmd2,..."> - -=item B<--replace-textcmd=replace-file> - -=item B<--append-textcmd=append-file> or -B<-x append-file> or B<--append-textcmd="cmd1,cmd2,..."> - -Exclude from, replace or append to the list of regular expressions -matching commands whose last argument is text. See -entry for B<--exclude-safecmd> directly above for further details. - - -=item B<--replace-context1cmd=replace-file> - -=item B<--append-context1cmd=append-file> or -=item B<--append-context1cmd="cmd1,cmd2,..."> - -Replace or append to the list of regex matching commands -whose last argument is text but which require a particular -context to work, e.g. \caption will only work within a figure -or table. These commands behave like text commands, except when -they occur in a deleted section, when they are disabled, but their -argument is shown as deleted text. - -=item B<--replace-context1cmd=replace-file> - -=item B<--append-context2cmd=append-file> or -=item B<--append-context2cmd="cmd1,cmd2,..."> -As corresponding commands for context1. The only difference is that -context2 commands are completely disabled in deleted sections, including -their arguments. - - - -=item B<--config var1=val1,var2=val2,...> or B<-c var1=val1,..> - -=item B<-c configfile> - -Set configuration variables. The option can be repeated to set different -variables (as an alternative to the comma-separated list). -Available variables (see below for further explanations): - -C (integer) - -C (RegEx) - -C (RegEx) - -C (RegEx) - -C (String) - -C (RegEx) - -C (String) - -C (RegEx) - -C (RegEx) - -=item B<--show-safecmd> - -Print list of RegEx matching and excluding safe commands. - -=item B<--show-textcmd> - -Print list of RegEx matching and excluding commands with text argument. - -=item B<--show-config> - -Show values of configuration variables. - -=item B<--show-all> - -Combine all --show commands. - -NB For all --show commands, no C or C file needs to be specified, and no -differencing takes place. - - -=back - -=head2 Miscellaneous - -=over 4 - -=item B<--verbose> or B<-V> - -Output various status information to stderr during processing. -Default is to work silently. - -=item B<--ignore-warnings> - -Suppress warnings about inconsistencies in length between input and -parsed strings and missing characters. These warning messages are -often related to non-standard latex or latex constructions with a -syntax unknown to C but the resulting difference argument -is often fully functional anyway, particularly if the non-standard -latex only occurs in parts of the text which have not changed. - -=item B<--allow-spaces> - -Allow spaces between bracketed or braced arguments to commands. Note -that this option might have undesirable side effects (unrelated scope -might get lumpeded with preceding commands) so should only be used if the -default produces erroneous results. (Default requires arguments to -directly follow each other without intervening spaces). - -=item B<--flatten> - -Replace C<\input> and C<\include> commands within body by the content -of the files in their argument. If C<\includeonly> is present in the -preamble, only those files are expanded into the document. However, -no recursion is done, i.e. C<\input> and C<\include> commands within -included sections are not expanded. The included files are assumed to - be located in the same directories as the old and new master files, -respectively, making it possible to organise files into old and new directories. - -Use of this option is not recommended -primarily the processing time for the large documents is prohibitive, and -the resulting difference document no longer reflects the structure of the -input documents. - -=item B<--help> or -B<-h> - -Show help text - -=item B<--version> - -Show version number - -=back - -=head2 Predefined styles - -=head2 Major types - -The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands C<\DIFadd{...}> and C<\DIFdel{...}> . - -=over 10 - -=item C - -Added text is wavy-underlined and blue, discarded text is struck out and red -(Requires color and ulem packages). Overstriking does not work in displayed math equations such that deleted parts of equation are underlined, not struck out (this is a shortcoming inherent to the ulem package). - -=item C - -Added text is blue and set in sans-serif, and a red footnote is created for each discarded -piece of text. (Requires color package) - -=item C - -Like C but without the use of color. - -=item C - -Added text is blue and set in sans-serif, and discarded text is red and very small size. - -=item C - -Added tex is set in sans-serif, discarded text small and struck out - -=item C - -Added text is blue, and discarded text is red. Additionally, the changed text is marked with a bar in the margin (Requires color and changebar packages). - -=item C - -Like C but with additional changebars (Requires color and changebar packages). - -=item C - -Like C but with additional changebars (Requires color, ulem and changebar packages). - -=item C - -No mark up of text, but mark margins with changebars (Requires changebar package). - -=item C - -No visible markup (but generic markup commands will still be inserted. - -=back - -=head2 Subtypes - -The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: C<\DIFaddbegin, \DIFaddend, \DIFdelbegin, \DIFdelend>) - -=over 10 - -=item C - -No additional markup (Recommended choice) - -=item C - -Mark beginning and end of changed blocks with symbols in the margin nearby (using -the standard C<\marginpar> command - note that this sometimes moves somewhat -from the intended position. - -=item C - -An alternative way of marking added passages in blue, and deleted ones in red. Note -that C only works with the dvips converter, e.g. not pdflatex. -(it is recommeneded to use instead the main types to effect colored markup, -although in some cases coloring with dvipscol can be more complete). - -=back - -=head2 Float Types - -Some of the markup used in the main text might cause problems when used within -floats (e.g. figures or tables). For this reason alternative versions of all -markup commands are used within floats. The float type defines these alternative commands. - -=over 10 - -=item C - -Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is C as C<\marginpar> does not work properly within floats. - -=item C - -Mark additions the same way as in the main text. Deleted environments are marked by angular brackets \[ and \] and the deleted text is set in scriptscript size. This float type should always be used with the C and C markup types as the \footnote command does not work properly in floating environments. - -=item C - -Make no difference between the main text and floats. - -=back - - -=head2 Configuration Variables - -=over 10 - -=item C - -Minimum number of tokens required to form an independent block. This value is -used in the algorithm to detect changes of complete blocks by merging identical text parts of less than C to the preceding added and discarded parts. - -[ Default: 3 ] - -=item C - -Environments whose name matches the regular expression in C are -considered floats. Within these environments, the I markup commands -are replaced by their FL variaties. - -[ Default: S >] - -=item C - -Within environments whose name matches the regular expression in C -all latexdiff markup is removed (in pathologic cases this might lead to - inconsistent markup but this situation should be rare). - -[ Default: S >] - -=item C,C - -If both \begin and \end for a math environment (environment name matching C -or \[ and \]) -are within the same deleted block, they are replaced by a \begin and \end commands for C -rather than being commented out. - -[ Default: C=S >, C=S >] - -=item C,C - -as C,C but for equation arrays - -[ Default: C=S >, C=S >] - -=item C - -If a match to C is found within an inline math environment within a deleted or added block, then the inlined math -is surrounded by C<\mbox{>...C<}>. This is necessary as underlining does not work within inlined array environments. - -[ Default: C=S > - -=item C - -If a command in a deleted block which is also in the textcmd list matches C then an -additional command C<\addtocounter{>FC<}{-1}>, where F is the matching command, is appended in the diff file such that the numbering in the diff file remains synchronized with the -numbering in the new file. - -[ Default: C=C<(?:footnote|part|section|subsection> ... - -C<|subsubsection|paragraph|subparagraph)> ] - -=back - -=head1 BUGS - -UTF-8 support requires a relatively new version of perl (5.8.0 is sufficient -but 5.6.2 up would work OK, too). - -Option allow-spaces not implemented entirely consistently. It breaks -the rules that number and type of white space does not matter, as -different numbers of inter-argument spaces are treated as significant. - -Please send bug reports -to I. Include the serial number of I -(from comments at the top of the source or use B<--version>). If you come across latex -files that are error-free and conform to the specifications set out -above, and whose differencing still does not result in error-free -latex, please send me those files, ideally edited to only contain the -offending passage as long as that still reproduces the problem. - -=head1 SEE ALSO - -L - -=head1 PORTABILITY - -I does not make use of external commands and thus should run -on any platform supporting Perl 5.6 or higher. If files with encodings -other than ASCII or UTF-8 are processed, Perl 5.8 or higher is required. - -The standard version of I requires installation of the Perl package -C (available from I - -I) but a stand-alone -version, I, which has this package inlined, is available, too. -I requires the I command to be present. - -=head1 AUTHOR - -Copyright (C) 2004-2007 Frederik Tilmann - -This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 - -Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner -Thanks to everyone who send in bug reports. - -=cut - -__END__ -%%BEGIN SAFE COMMANDS -% Regex matching commands which can safely be in the -% argument of a \DIFadd or \DIFdel command (leave out the \) -arabic -dashbox -emph -fbox -framebox -hspace -math.* -makebox -mbox -pageref -ref -symbol -raisebox -rule -text.* -shortstack -usebox -dag -ddag -copyright -pounds -S -P -oe -OE -ae -AE -aa -AA -o -O -l -L -frac -ss -sqrt -ldots -cdots -vdots -ddots -alpha -beta -gamma -delta -epsilon -varepsilon -zeta -eta -theta -vartheta -iota -kappa -lambda -mu -nu -xi -pi -varpi -rho -varrho -sigma -varsigma -tau -upsilon -phi -varphi -chi -psi -omega -Gamma -Delta -Theta -Lambda -Xi -Pi -Sigma -Upsilon -Phi -Psi -Omega -ps -mp -times -div -ast -star -circ -bullet -cdot -cap -cup -uplus -sqcap -vee -wedge -setminus -wr -diamond -(?:big)?triangle.* -lhd -rhd -unlhd -unrhd -oplus -ominus -otimes -oslash -odot -bigcirc -d?dagger -amalg -leq -prec -preceq -ll -(?:sq)?su[bp]set(?:eq)? -in -vdash -geq -succ(?:eq)? -gg -ni -dashv -equiv -sim(?:eq)? -asymp -approx -cong -neq -doteq -propto -models -perp -mid -parallel -bowtie -Join -smile -frown -.*arrow -(?:long)?mapsto -.*harpoon.* -leadsto -aleph -hbar -imath -jmath -ell -wp -Re -Im -mho -prime -emptyset -nabla -surd -top -bot -angle -forall -exists -neg -flat -natural -sharp -backslash -partial -infty -Box -Diamond -triangle -clubsuit -diamondsuit -heartsuit -spadesuit -sum -prod -coprod -int -oint -big(?:sq)?c[au]p -bigvee -bigwedge -bigodot -bigotimes -bigoplus -biguplus -(?:arc)?(?:cos|sin|tan|cot)h? -csc -arg -deg -det -dim -exp -gcd -hom -inf -ker -lg -lim -liminf -limsup -ln -log -max -min -Pr -sec -sup -(SUPER|SUB)SCRIPTNB -(SUPER|SUB)SCRIPT -%%END SAFE COMMANDS - -%%BEGIN TEXT COMMANDS -% Regex matching commands with a text argument (leave out the \) -addcontents.* -cc -closing -chapter -dashbox -emph -encl -fbox -framebox -footnote -footnotetext -framebox -part -(sub){0,2}section\*? -(sub)?paragraph\*? -makebox -mbox -opening -parbox -raisebox -savebox -sbox -shortstack -signature -text.* -value -underline -sqrt -(SUPER|SUB)SCRIPT -%%END TEXT COMMANDS - -%%BEGIN CONTEXT1 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text -caption -%%END CONTEXT1 COMMANDS - -%%BEGIN CONTEXT2 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text -title -author -%%END CONTEXT2 COMMANDS - - -%% TYPES (Commands for highlighting changed blocks) - -%DIF UNDERLINE PREAMBLE -\RequirePackage[normalem]{ulem} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}} -\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}} -%DIF END UNDERLINE PREAMBLE - -%DIF CTRADITIONAL PREAMBLE -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\RequirePackage[stable]{footmisc} -\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} -\providecommand{\DIFdel}[1]{{\protect\color{red} [..\footnote{removed: #1} ]}} -%DIF END CTRADITIONAL PREAMBLE - -%DIF TRADITIONAL PREAMBLE -\RequirePackage[stable]{footmisc} -\providecommand{\DIFadd}[1]{{\sf #1}} -\providecommand{\DIFdel}[1]{{[..\footnote{removed: #1} ]}} -%DIF END TRADITIONAL PREAMBLE - -%DIF CFONT PREAMBLE -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} -\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}} -%DIF END CFONT PREAMBLE - -%DIF FONTSTRIKE PREAMBLE -\RequirePackage[normalem]{ulem} -\providecommand{\DIFadd}[1]{{\sf #1}} -\providecommand{\DIFdel}[1]{{\footnotesize \sout{#1}}} -%DIF END FONTSTRIKE PREAMBLE - -%DIF CCHANGEBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}#1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}#1}\protect\cbdelete} -%DIF END CCHANGEBAR PREAMBLE - -%DIF CFONTCHBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\sf #1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\scriptsize #1}\protect\cbdelete} -%DIF END CFONTCHBAR PREAMBLE - -%DIF CULINECHBAR PREAMBLE -\RequirePackage[normalem]{ulem} -\RequirePackage[dvips]{changebar} -\RequirePackage{color} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\uwave{#1}}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\sout{#1}}\protect\cbdelete} -%DIF END CULINECHBAR PREAMBLE - -%DIF CHANGEBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\providecommand{\DIFadd}[1]{\protect\cbstart{#1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete} -%DIF END CHANGEBAR PREAMBLE - -%DIF INVISIBLE PREAMBLE -\providecommand{\DIFadd}[1]{#1} -\providecommand{\DIFdel}[1]{} -%DIF END INVISIBLE PREAMBLE - - -%% SUBTYPES (Markers for beginning and end of changed blocks) - -%DIF SAFE PREAMBLE -\providecommand{\DIFaddbegin}{} -\providecommand{\DIFaddend}{} -\providecommand{\DIFdelbegin}{} -\providecommand{\DIFdelend}{} -%DIF END SAFE PREAMBLE - -%DIF MARGIN PREAMBLE -\providecommand{\DIFaddbegin}{\protect\marginpar{a[}} -\providecommand{\DIFaddend}{\protect\marginpar{]}} -\providecommand{\DIFdelbegin}{\protect\marginpar{d[}} -\providecommand{\DIFdelend}{\protect\marginpar{]}} -%DIF END BRACKET PREAMBLE - -%DIF DVIPSCOL PREAMBLE -%Note: only works with dvips converter -\RequirePackage{color} -\RequirePackage{dvipscol} -\providecommand{\DIFaddbegin}{\protect\nogroupcolor{blue}} -\providecommand{\DIFaddend}{\protect\nogroupcolor{black}} -\providecommand{\DIFdelbegin}{\protect\nogroupcolor{red}} -\providecommand{\DIFdelend}{\protect\nogroupcolor{black}} -%DIF END DVIPSCOL PREAMBLE - - -%% FLOAT TYPES - -%DIF FLOATSAFE PREAMBLE -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} -\providecommand{\DIFaddbeginFL}{} -\providecommand{\DIFaddendFL}{} -\providecommand{\DIFdelbeginFL}{} -\providecommand{\DIFdelendFL}{} -%DIF END FLOATSAFE PREAMBLE - -%DIF IDENTICAL PREAMBLE -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} -\providecommand{\DIFaddbeginFL}{\DIFaddbegin} -\providecommand{\DIFaddendFL}{\DIFaddend} -\providecommand{\DIFdelbeginFL}{\DIFdelbegin} -\providecommand{\DIFdelendFL}{\DIFdelend} -%DIF END IDENTICAL PREAMBLE - -%DIF TRADITIONALSAFE PREAMBLE -% procidecommand color to make this work for TRADITIONAL and CTRADITIONAL -\providecommand{\color}[1]{} -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdel}[1]{{\protect\color{red}[..{\scriptsize {removed: #1}} ]}} -\providecommand{\DIFaddbeginFL}{} -\providecommand{\DIFaddendFL}{} -\providecommand{\DIFdelbeginFL}{} -\providecommand{\DIFdelendFL}{} -%DIF END FLOATSAFE PREAMBLE - -%% SPECIAL PACKAGE PREAMBLE COMMANDS - -% Standard \DIFadd and \DIFdel are redefined as \DIFaddtex and \DIFdeltex -% when hyperref package is included. -%DIF HYPERREF PREAMBLE -\providecommand{\DIFadd}[1]{\texorpdfstring{\DIFaddtex{#1}}{#1}} -\providecommand{\DIFdel}[1]{\texorpdfstring{\DIFdeltex{#1}}{}} -%DIF END HYPERREF PACKAGE diff --git a/Master/texmf-dist/doc/latex/latexdiff/latexdiff-fast b/Master/texmf-dist/doc/latex/latexdiff/latexdiff-fast deleted file mode 100755 index ee6c7419ac9..00000000000 --- a/Master/texmf-dist/doc/latex/latexdiff/latexdiff-fast +++ /dev/null @@ -1,3344 +0,0 @@ -#!/usr/bin/perl -w -# latexdiff - differences two latex files on the word level -# and produces a latex file with the differences marked up. -# -# Copyright (C) 2004-2007 F J Tilmann (tilmann@esc.cam.ac.uk) -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. -# -# 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -# -# Detailed usage information at the end of the file -# -# Version 0.5 A number of minor improvements based on feedback -# Deleted blocks are now shown before added blocks -# Package specific processing -# -# Version 0.43 unreleased typo in list of styles at the end -# Add protect to all \cbstart, \cbend commands -# More robust substitution of deleted math commands -# -# Version 0.42 November 06 Bug fixes only -# -# Version 0.4 March 06 option for fast differencing using UNIX diff command, several minor bug fixes (\par bug, improved highlighting of textcmds) -# -# Version 0.3 August 05 improved parsing of displayed math, --allow-spaces -# option, several minor bug fixes -# -# Version 0.25 October 04 Fix bug with deleted equations, add math mode commands to safecmd, add | to allowed interpunctuation signs -# Version 0.2 September 04 extension to utf-8 and variable encodings -# Version 0.1 August 04 First public release - -# Inserted block for differenceing -# use Algorithm::Diff qw(traverse_sequences); -# in standard version -# The following BEGIN block contains a verbatim copy of -# Ned Konz' Algorithm::Diff package version 1.15 except -# that subroutine _longestCommonSubsequence has been replace by -# a routine which internally uses the UNIX diff command for -# the differencing rather than the Perl routines if the -# length of the sequences exceeds some threshold. -# Also, all POD documentation has been stripped out. -# -# (the distribution on which this modification is based is available -# from http://search.cpan.org/~nedkonz/Algorithm-Diff-1.15 -# the most recent version can be found via http://search.cpan.org/search?module=Algorithm::Diff ) -# Please note that the LICENCSE for Algorithm::Diff : -# "Copyright (c) 2000-2002 Ned Konz. All rights reserved. -# This program is free software; -# you can redistribute it and/or modify it under the same terms -# as Perl itself." -# The fast-differencing version of latexdiff is provided as a convenience -# for latex users under Unix-like systems which have a 'diff' command. -# If you believe -# the inlining of Algorithm::Diff violates its license please contact -# me and I will modify the latexdiff distribution accordingly. -# Frederik Tilmann (tilmann@esc.cam.ac.uk) -# Jonathan Paisley is acknowledged for the idea of using the system diff -# command to achieve shorter running times -BEGIN { -package Algorithm::Diff; -use strict; -use vars qw($VERSION @EXPORT_OK @ISA @EXPORT); -use integer; # see below in _replaceNextLargerWith() for mod to make - # if you don't use this -require Exporter; -@ISA = qw(Exporter); -@EXPORT = qw(); -@EXPORT_OK = qw(LCS diff traverse_sequences traverse_balanced sdiff); -$VERSION = sprintf('%d.%02d fast', (q$Revision: 1.15 $ =~ /\d+/g)); - -# Global parameters - -use File::Temp qw/tempfile/; -# if larger number of elements in longestCommonSubsequence smaller than -# this number, then use internal algorithm, otherwise use UNIX diff -use constant THRESHOLD => 100 ; -# Detect whether diff --minimal option is available -# if yes we use it -use constant MINIMAL => ( system('diff','--minimal','/dev/null','/dev/null') >> 8 ==0 ? "--minimal" : "" ) ; - - - -# McIlroy-Hunt diff algorithm -# Adapted from the Smalltalk code of Mario I. Wolczko, -# by Ned Konz, perl@bike-nomad.com - - -# Create a hash that maps each element of $aCollection to the set of positions -# it occupies in $aCollection, restricted to the elements within the range of -# indexes specified by $start and $end. -# The fourth parameter is a subroutine reference that will be called to -# generate a string to use as a key. -# Additional parameters, if any, will be passed to this subroutine. -# -# my $hashRef = _withPositionsOfInInterval( \@array, $start, $end, $keyGen ); - -sub _withPositionsOfInInterval -{ - my $aCollection = shift; # array ref - my $start = shift; - my $end = shift; - my $keyGen = shift; - my %d; - my $index; - for ( $index = $start ; $index <= $end ; $index++ ) - { - my $element = $aCollection->[$index]; - my $key = &$keyGen( $element, @_ ); - if ( exists( $d{$key} ) ) - { - unshift ( @{ $d{$key} }, $index ); - } - else - { - $d{$key} = [$index]; - } - } - return wantarray ? %d : \%d; -} - -# Find the place at which aValue would normally be inserted into the array. If -# that place is already occupied by aValue, do nothing, and return undef. If -# the place does not exist (i.e., it is off the end of the array), add it to -# the end, otherwise replace the element at that point with aValue. -# It is assumed that the array's values are numeric. -# This is where the bulk (75%) of the time is spent in this module, so try to -# make it fast! - -sub _replaceNextLargerWith -{ - my ( $array, $aValue, $high ) = @_; - $high ||= $#$array; - - # off the end? - if ( $high == -1 || $aValue > $array->[-1] ) - { - push ( @$array, $aValue ); - return $high + 1; - } - - # binary search for insertion point... - my $low = 0; - my $index; - my $found; - while ( $low <= $high ) - { - $index = ( $high + $low ) / 2; - - # $index = int(( $high + $low ) / 2); # without 'use integer' - $found = $array->[$index]; - - if ( $aValue == $found ) - { - return undef; - } - elsif ( $aValue > $found ) - { - $low = $index + 1; - } - else - { - $high = $index - 1; - } - } - - # now insertion point is in $low. - $array->[$low] = $aValue; # overwrite next larger - return $low; -} - -# This method computes the longest common subsequence in $a and $b. - -# Result is array or ref, whose contents is such that -# $a->[ $i ] == $b->[ $result[ $i ] ] -# foreach $i in ( 0 .. $#result ) if $result[ $i ] is defined. - -# An additional argument may be passed; this is a hash or key generating -# function that should return a string that uniquely identifies the given -# element. It should be the case that if the key is the same, the elements -# will compare the same. If this parameter is undef or missing, the key -# will be the element as a string. - -# By default, comparisons will use "eq" and elements will be turned into keys -# using the default stringizing operator '""'. - -# Additional parameters, if any, will be passed to the key generation routine. - -sub _longestCommonSubsequence -{ - my $a = shift; # array ref - my $b = shift; # array ref - my $keyGen = shift; # code ref - my $compare; # code ref - - # set up code refs - # Note that these are optimized. - if ( !defined($keyGen) ) # optimize for strings - { - $keyGen = sub { $_[0] }; - $compare = sub { my ( $a, $b ) = @_; $a eq $b }; - } - else - { - $compare = sub { - my $a = shift; - my $b = shift; - &$keyGen( $a, @_ ) eq &$keyGen( $b, @_ ); - }; - } - - my ( $aStart, $aFinish, $bStart, $bFinish, $matchVector ) = - ( 0, $#$a, 0, $#$b, [] ); - - # Check whether to use internal routine (small number of elements) - # or use it as a wrapper for UNIX diff - if ( ( $#$a > $#$b ? $#$a : $#$b) < THRESHOLD ) { - ### print STDERR "DEBUG: regular longestCommonSubsequence\n"; - # First we prune off any common elements at the beginning - while ( $aStart <= $aFinish - and $bStart <= $bFinish - and &$compare( $a->[$aStart], $b->[$bStart], @_ ) ) - { - $matchVector->[ $aStart++ ] = $bStart++; - } - - # now the end - while ( $aStart <= $aFinish - and $bStart <= $bFinish - and &$compare( $a->[$aFinish], $b->[$bFinish], @_ ) ) - { - $matchVector->[ $aFinish-- ] = $bFinish--; - } - - # Now compute the equivalence classes of positions of elements - my $bMatches = - _withPositionsOfInInterval( $b, $bStart, $bFinish, $keyGen, @_ ); - my $thresh = []; - my $links = []; - - my ( $i, $ai, $j, $k ); - for ( $i = $aStart ; $i <= $aFinish ; $i++ ) - { - $ai = &$keyGen( $a->[$i], @_ ); - if ( exists( $bMatches->{$ai} ) ) - { - $k = 0; - for $j ( @{ $bMatches->{$ai} } ) - { - - # optimization: most of the time this will be true - if ( $k and $thresh->[$k] > $j and $thresh->[ $k - 1 ] < $j ) - { - $thresh->[$k] = $j; - } - else - { - $k = _replaceNextLargerWith( $thresh, $j, $k ); - } - - # oddly, it's faster to always test this (CPU cache?). - if ( defined($k) ) - { - $links->[$k] = - [ ( $k ? $links->[ $k - 1 ] : undef ), $i, $j ]; - } - } - } - } - - if (@$thresh) - { - for ( my $link = $links->[$#$thresh] ; $link ; $link = $link->[0] ) - { - $matchVector->[ $link->[1] ] = $link->[2]; - } - } - } - else { - my ($fha,$fhb,$fna,$fnb,$ele,$key); - my ($alines,$blines,$alb,$alf,$blb,$blf); - my ($minimal)=MINIMAL; - # large number of elements, use system diff - ### print STDERR "DEBUG: fast (diff) longestCommonSubsequence\n"; - - ($fha,$fna)=tempfile("DiffA-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence A"; - ($fhb,$fnb)=tempfile("DiffB-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence B"; - # prepare sequence A - foreach $ele ( @$a ) { - $key=&$keyGen( $ele, @_ ); - $key =~ s/\\/\\\\/g ; - $key =~ s/\n/\\n/sg ; - print $fha "$key\n" ; - } - close($fha); - # prepare sequence B - foreach $ele ( @$b ) { - $key=&$keyGen( $ele, @_ ); - $key =~ s/\\/\\\\/g ; - $key =~ s/\n/\\n/sg ; - print $fhb "$key\n" ; - } - close($fhb); - - open(DIFFPIPE, "diff $minimal $fna $fnb |") or die "_longestCommonSubsequence: Cannot launch diff process. $!" ; - # The diff line numbering begins with 1, but Perl subscripts start with 0 - # We follow the diff numbering but substract 1 when assigning to matchVector - $aStart++; $bStart++ ; $aFinish++ ; $bFinish++ ; - while( ) { - if ( ($alines,$blines) = ( m/^(\d*(?:,\d*)?)?c(\d*(?:,\d*)?)?$/ ) ) { - ($alb,$alf)=split(/,/,$alines); - ($blb,$blf)=split(/,/,$blines); - $alf=$alb unless defined($alf); - $blf=$blb unless defined($blf); - while($aStart < $alb ) { - $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; - } - # check for consistency - $bStart==$blb or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in changed sequence"; - $aStart=$alf+1; - $bStart=$blf+1; - } - elsif ( ($alb,$blines) = ( m/^(\d*)a(\d*(?:,\d*)?)$/ ) ) { - ($blb,$blf)=split(/,/,$blines); - $blf=$blb unless defined($blf); - while ( $bStart < $blb ) { - $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; - } - $aStart==$alb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in appended sequence near elements $aStart and $bStart"; - $bStart=$blf+1; - } - elsif ( ($alines,$blb) = ( m/^(\d*(?:,\d*)?)d(\d*)$/ ) ) { - ($alb,$alf)=split(/,/,$alines); - $alf=$alb unless defined($alf); - while ( $aStart < $alb ) { - $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; - } - $bStart==$blb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in deleted sequence near elements $aStart and $bStart"; - $aStart=$alf+1; - } - elsif ( m/^Binary files/ ) { - # if diff reports it is a binary file force --text mode. I do not like - # to always use this option because it is probably only available in GNU diff - open(DIFFPIPE, "diff --text $fna $fnb |") or die "Cannot launch diff process. $!" ; - } - # Default: just skip line - } - while ($aStart <= $aFinish ) { - $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; - } - $bStart==$bFinish+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency at end"; - close DIFFPIPE; - # check whether a system error has occurred or return status is greater than or equal to 5 - if ( $! || ($? >> 8) > 5) { - print STDERR "diff process failed with exit code ", ($? >> 8), " $!\n"; - die; - } - unlink $fna,$fnb ; - } - return wantarray ? @$matchVector : $matchVector; -} - -sub traverse_sequences -{ - my $a = shift; # array ref - my $b = shift; # array ref - my $callbacks = shift || {}; - my $keyGen = shift; - my $matchCallback = $callbacks->{'MATCH'} || sub { }; - my $discardACallback = $callbacks->{'DISCARD_A'} || sub { }; - my $finishedACallback = $callbacks->{'A_FINISHED'}; - my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { }; - my $finishedBCallback = $callbacks->{'B_FINISHED'}; - my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ ); - - # Process all the lines in @$matchVector - my $lastA = $#$a; - my $lastB = $#$b; - my $bi = 0; - my $ai; - - for ( $ai = 0 ; $ai <= $#$matchVector ; $ai++ ) - { - my $bLine = $matchVector->[$ai]; - if ( defined($bLine) ) # matched - { - &$discardBCallback( $ai, $bi++, @_ ) while $bi < $bLine; - &$matchCallback( $ai, $bi++, @_ ); - } - else - { - &$discardACallback( $ai, $bi, @_ ); - } - } - - # The last entry (if any) processed was a match. - # $ai and $bi point just past the last matching lines in their sequences. - - while ( $ai <= $lastA or $bi <= $lastB ) - { - - # last A? - if ( $ai == $lastA + 1 and $bi <= $lastB ) - { - if ( defined($finishedACallback) ) - { - &$finishedACallback( $lastA, @_ ); - $finishedACallback = undef; - } - else - { - &$discardBCallback( $ai, $bi++, @_ ) while $bi <= $lastB; - } - } - - # last B? - if ( $bi == $lastB + 1 and $ai <= $lastA ) - { - if ( defined($finishedBCallback) ) - { - &$finishedBCallback( $lastB, @_ ); - $finishedBCallback = undef; - } - else - { - &$discardACallback( $ai++, $bi, @_ ) while $ai <= $lastA; - } - } - - &$discardACallback( $ai++, $bi, @_ ) if $ai <= $lastA; - &$discardBCallback( $ai, $bi++, @_ ) if $bi <= $lastB; - } - - return 1; -} - -sub traverse_balanced -{ - my $a = shift; # array ref - my $b = shift; # array ref - my $callbacks = shift || {}; - my $keyGen = shift; - my $matchCallback = $callbacks->{'MATCH'} || sub { }; - my $discardACallback = $callbacks->{'DISCARD_A'} || sub { }; - my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { }; - my $changeCallback = $callbacks->{'CHANGE'}; - my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ ); - - # Process all the lines in match vector - my $lastA = $#$a; - my $lastB = $#$b; - my $bi = 0; - my $ai = 0; - my $ma = -1; - my $mb; - - while (1) - { - - # Find next match indices $ma and $mb - do { $ma++ } while ( $ma <= $#$matchVector && !defined $matchVector->[$ma] ); - - last if $ma > $#$matchVector; # end of matchVector? - $mb = $matchVector->[$ma]; - - # Proceed with discard a/b or change events until - # next match - while ( $ai < $ma || $bi < $mb ) - { - - if ( $ai < $ma && $bi < $mb ) - { - - # Change - if ( defined $changeCallback ) - { - &$changeCallback( $ai++, $bi++, @_ ); - } - else - { - &$discardACallback( $ai++, $bi, @_ ); - &$discardBCallback( $ai, $bi++, @_ ); - } - } - elsif ( $ai < $ma ) - { - &$discardACallback( $ai++, $bi, @_ ); - } - else - { - - # $bi < $mb - &$discardBCallback( $ai, $bi++, @_ ); - } - } - - # Match - &$matchCallback( $ai++, $bi++, @_ ); - } - - while ( $ai <= $lastA || $bi <= $lastB ) - { - if ( $ai <= $lastA && $bi <= $lastB ) - { - - # Change - if ( defined $changeCallback ) - { - &$changeCallback( $ai++, $bi++, @_ ); - } - else - { - &$discardACallback( $ai++, $bi, @_ ); - &$discardBCallback( $ai, $bi++, @_ ); - } - } - elsif ( $ai <= $lastA ) - { - &$discardACallback( $ai++, $bi, @_ ); - } - else - { - - # $bi <= $lastB - &$discardBCallback( $ai, $bi++, @_ ); - } - } - - return 1; -} - -sub LCS -{ - my $a = shift; # array ref - my $matchVector = _longestCommonSubsequence( $a, @_ ); - my @retval; - my $i; - for ( $i = 0 ; $i <= $#$matchVector ; $i++ ) - { - if ( defined( $matchVector->[$i] ) ) - { - push ( @retval, $a->[$i] ); - } - } - return wantarray ? @retval : \@retval; -} - -sub diff -{ - my $a = shift; # array ref - my $b = shift; # array ref - my $retval = []; - my $hunk = []; - my $discard = sub { push ( @$hunk, [ '-', $_[0], $a->[ $_[0] ] ] ) }; - my $add = sub { push ( @$hunk, [ '+', $_[1], $b->[ $_[1] ] ] ) }; - my $match = sub { push ( @$retval, $hunk ) if scalar(@$hunk); $hunk = [] }; - traverse_sequences( $a, $b, - { MATCH => $match, DISCARD_A => $discard, DISCARD_B => $add }, @_ ); - &$match(); - return wantarray ? @$retval : $retval; -} - -sub sdiff -{ - my $a = shift; # array ref - my $b = shift; # array ref - my $retval = []; - my $discard = sub { push ( @$retval, [ '-', $a->[ $_[0] ], "" ] ) }; - my $add = sub { push ( @$retval, [ '+', "", $b->[ $_[1] ] ] ) }; - my $change = sub { - push ( @$retval, [ 'c', $a->[ $_[0] ], $b->[ $_[1] ] ] ); - }; - my $match = sub { - push ( @$retval, [ 'u', $a->[ $_[0] ], $b->[ $_[1] ] ] ); - }; - traverse_balanced( - $a, - $b, - { - MATCH => $match, - DISCARD_A => $discard, - DISCARD_B => $add, - CHANGE => $change, - }, - @_ - ); - return wantarray ? @$retval : $retval; -} - -1; -} -import Algorithm::Diff qw(traverse_sequences); -# End of inserted block for stand-alone version - - -use Getopt::Long ; -use strict ; -use utf8 ; - -my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); - - -my ($versionstring)=< \$type, - 'subtype|s=s' => \$subtype, - 'floattype|f=s' => \$floattype, - 'config|c=s' => \@configlist, - 'preamble|p=s' => \$preamblefile, - 'encoding|e=s' => \$encoding, - 'exclude-safecmd|A=s' => \@excludesafelist, - 'replace-safecmd=s' => \$replacesafe, - 'append-safecmd|a=s' => \@appendsafelist, - 'exclude-textcmd|X=s' => \@excludetextlist, - 'replace-textcmd=s' => \$replacetext, - 'append-textcmd|x=s' => \@appendtextlist, - 'replace-context1cmd=s' => \$replacecontext1, - 'append-context1cmd=s' => \@appendcontext1list, - 'replace-context2cmd=s' => \$replacecontext2, - 'append-context2cmd=s' => \@appendcontext2list, - 'show-preamble' => \$showpreamble, - 'show-safecmd' => \$showsafe, - 'show-textcmd' => \$showtext, - 'show-config' => \$showconfig, - 'show-all' => \$showall, - 'packages=s' => \@packagelist, - 'verbose|V' => \$verbose, - 'ignore-warnings' => \$ignorewarnings, - 'allow-spaces' => \$allowspaces, - 'flatten' => \$flatten, - 'version' => \$version, - 'help|h|H' => \$help); - -if ( $help ) { - usage() ; -} - - -if ( $version ) { - die $versionstring ; -} - -print STDERR $versionstring if $verbose; - -if (defined($showall)){ - $showpreamble=$showsafe=$showtext=$showconfig=1; -} - -# setting extra preamble commands -if (defined($preamblefile)) { - $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); -} else { - $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); -} - -# setting up @SAFECMDLIST and @SAFECMDEXCL -if (defined($replacesafe)) { - init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); -} else { - init_regex_arr_data(\@SAFECMDLIST, "SAFE COMMANDS"); -} -foreach $appendsafe ( @appendsafelist ) { - init_regex_arr_ext(\@SAFECMDLIST, $appendsafe); -} -foreach $excludesafe ( @excludesafelist ) { - init_regex_arr_ext(\@SAFECMDEXCL, $excludesafe); -} - -# Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode -# (there is a conflict between citation and ulem package, see -# package documentation) -if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { - push (@SAFECMDLIST, qr/^cite.*$/); -} - -# setting up @TEXTCMDLIST and @TEXTCMDEXCL -if (defined($replacetext)) { - init_regex_arr_ext(\@TEXTCMDLIST,$replacetext); -} else { - init_regex_arr_data(\@TEXTCMDLIST, "TEXT COMMANDS"); -} -foreach $appendtext ( @appendtextlist ) { - init_regex_arr_ext(\@TEXTCMDLIST, $appendtext); -} -foreach $excludetext ( @excludetextlist ) { - init_regex_arr_ext(\@TEXTCMDEXCL, $excludetext); -} - - -# setting up @CONTEXT1CMDLIST ( @CONTEXT1CMDEXCL exist but is always empty ) -if (defined($replacecontext1)) { - init_regex_arr_ext(\@CONTEXT1CMDLIST,$replacecontext1); -} else { - init_regex_arr_data(\@CONTEXT1CMDLIST, "CONTEXT1 COMMANDS"); -} -foreach $appendcontext1 ( @appendcontext1list ) { - init_regex_arr_ext(\@CONTEXT1CMDLIST, $appendcontext1); -} - - -# setting up @CONTEXT2CMDLIST ( @CONTEXT2CMDEXCL exist but is always empty ) -if (defined($replacecontext2)) { - init_regex_arr_ext(\@CONTEXT2CMDLIST,$replacecontext2); -} else { - init_regex_arr_data(\@CONTEXT2CMDLIST, "CONTEXT2 COMMANDS"); -} -foreach $appendcontext2 ( @appendcontext2list ) { - init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); -} - - - - -# setting configuration variables -@config=(); -foreach $config ( @configlist ) { - if (-f $config ) { - open(FILE,$config) or die ("Couldn't open configuration file $config: $!"); - while () { - chomp; - next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; - push (@config,$_); - } - close(FILE); - } - else { -# foreach ( split(",",$config) ) { -# push @config,$_; -# } - push @config,split(",",$config) - } -} -foreach $assign ( @config ) { - $assign=~ m/\s*(\w*)\s*=\s*(\S*)\s*$/ or die "Illegal assignment $assign in configuration list (must be variable=value)"; - if ( $1 eq "MINWORDSBLOCK" ) { $MINWORDSBLOCK = $2; } - elsif ( $1 eq "FLOATENV" ) { $FLOATENV = $2 ; } - elsif ( $1 eq "PICTUREENV" ) { $PICTUREENV = $2 ; } - elsif ( $1 eq "MATHENV" ) { $MATHENV = $2 ; } - elsif ( $1 eq "MATHREPL" ) { $MATHREPL = $2 ; } - elsif ( $1 eq "MATHARRENV" ) { $MATHARRENV = $2 ; } - elsif ( $1 eq "MATHARRREPL" ) { $MATHARRREPL = $2 ; } - elsif ( $1 eq "ARRENV" ) { $ARRENV = $2 ; } - elsif ( $1 eq "COUNTERCMD" ) { $COUNTERCMD = $2 ; } - else { die "Unknown variable $1 in assignment.";} -} - - -foreach $pkg ( @packagelist ) { - map { $packages{$_}="" } split(/,/,$pkg) ; -} - -if ($showpreamble) { - print "\nPreamble commands:\n"; - print $latexdiffpreamble ; -} - -if ($showsafe) { - print "\nCommands safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE (unless excluded):\n"; - print_regex_arr(@SAFECMDLIST); - print "\nCommands not safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE :\n"; - print_regex_arr(@SAFECMDEXCL); -} - -if ($showtext) { - print "\nCommands with last argument textual (unless excluded) and safe in every context:\n"; - print_regex_arr(@TEXTCMDLIST); - print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; - print_regex_arr(@CONTEXT1CMDLIST); - print "\nContext2 commands (last argument textual, command ant its argument will be disabled in deleted passages):\n"; - print_regex_arr(@CONTEXT2CMDLIST); - print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; - print_regex_arr(@TEXTCMDEXCL); -} - -if ($showconfig) { - print "Configuration variables:\n"; - print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; - print "FLOATENV=$FLOATENV\n"; - print "PICTUREENV=$PICTUREENV\n"; - print "MATHENV=$MATHENV\n"; - print "MATHREPL=$MATHREPL\n"; - print "MATHARRENV=$MATHARRENV\n"; - print "MATHARRREPL=$MATHARRREPL\n"; - print "ARRENV=$ARRENV\n"; - print "COUNTERCMD=$COUNTERCMD\n"; -} -if ($showconfig || $showtext || $showsafe || $showpreamble) { - exit 0; } -if ( @ARGV != 2 ) { - print STDERR "2 and only 2 non-option arguments required. Write latexdiff -h to get help\n"; - exit(2); -} - -# Are extra spaces between command arguments permissible? -my $extraspace; -if ($allowspaces) { - $extraspace='\s*'; -} else { - $extraspace=''; -} - -# append context lists to text lists (as text property is implied) -push @TEXTCMDLIST, @CONTEXT1CMDLIST; -push @TEXTCMDLIST, @CONTEXT2CMDLIST; - - -# Patterns. These are used by some of the subroutines, too -# I can only define them down here because value of extraspace depends on an option - my $pat0 = '(?:[^{}]|\\\{|\\\})*'; - my $pat1 = '(?:[^{}]|\\\{|\\\}|\{'.$pat0.'\})*'; - my $pat2 = '(?:[^{}]|\\\{|\\\}|\{'.$pat1.'\})*'; # - my $pat3 = '(?:[^{}]|\\\{|\\\}|\{'.$pat2.'\})*'; - my $pat4 = '(?:[^{}]|\\\{|\\\}|\{'.$pat3.'\})*'; - my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; - - my $quotemarks = '(?:\'\')|(?:\`\`)'; - my $punct='[0.,\/\'\`:;\"\?\(\)\[\]!~\p{IsNonAsciiPunct}\p{IsNonAsciiS}]'; - my $number='-?\d*\.\d*'; - my $mathpunct='[+=<>\-\|]'; - my $and = '&'; - my $coords= '[\-.,\s\d]*'; -# word: sequence of letters or accents followed by letter - my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; - my $cmdleftright='\\\\(?:left|right)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; - - my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat4 . '\}|\(' . $coords .'\))'.$extraspace.')*'; - my $oneletcmd='\\\\.(?:\['.$brat0.'\]|\{'. $pat4 . '\})*'; - my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; -# my $math='\$(?:[^$]|\\\$)*\$'; - my $comment='%.*?\n'; - my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; - - - -# now we are done setting up and can start working -my ($oldfile, $newfile) = @ARGV; - -$encoding=guess_encoding($newfile) unless defined($encoding); - -$encoding = "utf8" if $encoding =~ m/^utf8/i ; -if (lc($encoding) eq "utf8" ) { - binmode(STDOUT, ":utf8"); - binmode(STDERR, ":utf8"); -} - -$old=read_file_with_encoding($oldfile,$encoding); -$new=read_file_with_encoding($newfile,$encoding); - - - - -# reset time -exetime(1); -($oldpreamble,$oldbody,$oldpost)=splitdoc($old,'\\\\begin\{document\}','\\\\end\{document\}'); - - -($newpreamble,$newbody,$newpost)=splitdoc($new,'\\\\begin\{document\}','\\\\end\{document\}'); - - -if ($flatten) { - $oldbody=flatten($oldbody,$oldpreamble,$oldfile,$encoding); - $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); -} - -if ( length $oldpreamble && length $newpreamble ) { - @oldpreamble = split /\n/, $oldpreamble; - @newpreamble = split /\n/, $newpreamble; - - %packages=list_packages(@newpreamble) unless %packages; - if (defined $packages{"hyperref"} ) { - print STDERR "hyperref package detected.\n" if $verbose ; - $latexdiffpreamble =~ s/\{\\DIFadd\}/{\\DIFaddtex}/g; - $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; - $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); - } - # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct - unshift @newpreamble,''; - unshift @oldpreamble,''; - print STDERR "Differencing preamble.\n" if $verbose; - @diffpreamble = linediff(\@oldpreamble, \@newpreamble); - # remove dummy line again - shift @diffpreamble; - push @diffpreamble,$latexdiffpreamble; - push @diffpreamble,'\begin{document}'; -} -elsif ( !length $oldpreamble && !length $newpreamble ) { - @diffpreamble=(); -} else { - print STDERR "Either both texts must have preamble or neither text must have the preamble.\n"; - exit(2); -} - -if (defined $packages{"amsmath"} ) { - print STDERR "amsmath package detected.\n" if $verbose ; - $MATHARRREPL='align*'; -} - -print STDERR "Preprocessing body. " if $verbose; -my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); - - -# run difference algorithm -@diffbody=bodydiff($oldbody, $newbody); -$diffbo=join("",@diffbody); -print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; -postprocess($diffbo); -$diffall =join("\n",@diffpreamble) ; -$diffall .= "$newleadin$diffbo" ; -$diffall .= "\\end{document}$newpost" if length $newpreamble ; -if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { - print STDERR "Encoding output file to $encoding\n" if $verbose; - $diffall=Encode::encode($encoding,$diffall); - binmode STDOUT; -} -print $diffall; - - -print STDERR "(",exetime()," s)\n","Done.\n" if $verbose; - - - -## guess_encoding(filename) -## reads the first 20 lines of filename and looks for call of inputenc package -## if found, return the option of this package (encoding), otherwise return ascii -sub guess_encoding { - my ($filename)=@_; - my ($i,$enc); - open (FH, $filename) or die("Couldn't open $filename: $!"); - $i=0; - while () { - next if /^\s*%/; # skip comment lines - if (m/\\usepackage\[(\w*?)\]\{inputenc\}/) { - close(FH); - return($1); - } - last if (++$i > 20 ); # scan at most 20 non-comment lines - } - close(FH); - return("ascii"); -} - - -sub read_file_with_encoding { - my ($output); - my ($filename, $encoding) = @_; - - if (lc($encoding) eq "utf8" ) { - open (FILE, "<:utf8",$filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - } elsif ( lc($encoding) eq "ascii") { - open (FILE, $filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - } else { - require Encode; - open (FILE, "<",$filename) or die("Couldn't open $filename: $!"); - local $/ ; # locally set record operator to undefined, ie. enable whole-file mode - $output=; - print STDERR "Converting $filename from $encoding to utf8\n" if $verbose; - $output=Encode::decode($encoding,$output); - } - close FILE; - return $output; -} - -# %packages=list_packages(@preamble) -# scans the arguments for \documentclass and \usepackage statements and constructs a hash -# whose keys are the included packages, and whose values are the associated optional arguments -sub list_packages { - my (@preamble)=@_; - my %packages=(); - foreach $line ( @preamble ) { - # get rid of comments - $line=~s/(?catfile($dirname,$fname), "\n"; - # content of file becomes replacement value, add \newpage if the command was include - $replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die - "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; - $newpage=(defined($2)? " \\newpage " : "") ; - "$newpage$replacement$newpage"; - }/exg; - - return($text); -} - - -# print_regex_arr(@arr) -# prints regex array without x-ism expansion put in by pearl to stdout -sub print_regex_arr { - my $dumstring; - $dumstring = join(" ",@_); # PERL generates string (?-xism:^ref$) for quoted refex ^ref$ - $dumstring =~ s/\(\?-xism:\^(.*?)\$\)/$1/g; # remove string and ^,$ marks before output - print $dumstring,"\n"; -} - - -# @lines=extrapream($type) -# reads line from appendix (end of file after __END__ token) -sub extrapream { - my $type; - my @retval=("%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; - my ($copy); - - while (@_) { - $copy=0; - $type=shift ; - if ( -f $type ) { - open (FILE,$type) or die "Cannot open preamble file $type: $!"; - print STDERR "Reading preamble file $type\n" if $verbose ; - while () { - chomp ; - if ( $_ =~ m/%DIF PREAMBLE/ ) { - push (@retval,"$_"); - } else { - push (@retval,"$_ %DIF PREAMBLE"); - } - } - } - else { # not (-f $type) - $type=uc($type); # upcase argument - print STDERR "Preamble Internal Type $type\n" if $verbose; - while () { - if ( m/^%DIF $type/ ) { - $copy=1; } - elsif ( m/^%DIF END $type/ ) { - last; } - chomp; - push (@retval,"$_ %DIF PREAMBLE") if $copy; - } - if ( $copy == 0 ) { - print STDERR "\nPreamble style $type not implemented.\n"; - print STDERR "Write latexdiff -h to get help with available styles\n"; - exit(2); - } - seek DATA,0,0; # rewind DATA handle to file begin - } - } - push (@retval,"%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; - return @retval; -} - - -# ($part1,$part2,$part3)=splitdoc($text,$word1,$word2) -# splits $text into 3 parts at $word1 and $word2. -# if neither $word1 nor $word2 exist, $part1 and $part3 are empty, $part2 is $text -# If only $word1 or $word2 exist but not the other, output an error message. - -# NB this version avoids $` and $' for performance reason although it only makes a tiny difference -# (in one test gain a tenth of a second for a 30s run) -sub splitdoc { - my ($text,$word1,$word2)=@_; - my ($part1,$part2,$part3)=("","",""); - my ($rest,$pos); - - if ( $text =~ m/(^[^%]*)($word1)/mg ) { - $pos=pos $text; - $part1=substr($text,0,$pos-length($2)); - $rest=substr($text,$pos); - if ( $rest =~ m/(^[^%]*)($word2)/mg ) { - $pos=pos $rest; - $part2=substr($rest,0,$pos-length($2)); - $part3=substr($rest,$pos); - } - else { - die "$word1 and $word2 not in the correct order or not present as a pair." ; - } - } else { - $part2=$text; - die "$word2 present but not $word1." if ( $text =~ m/(^[^%]*)$word2/ms ); - } - return ($part1,$part2,$part3); -} - - - - - -# bodydiff($old,$new) -sub bodydiff { - my ($oldwords, $newwords) = @_; - my @retwords; - - print STDERR "(",exetime()," s)\n","Splitting into latex tokens \n" if $verbose; - print STDERR "Parsing $oldfile \n" if $verbose; - my @oldwords = splitlatex($oldwords); - print STDERR "Parsing $newfile \n" if $verbose; - my @newwords = splitlatex($newwords); - my $token; - - print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; - pass1(\@oldwords, \@newwords); - - - print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; - - @retwords=pass2(\@oldwords, \@newwords); - - return(@retwords); -} - - - - -# @words=splitlatex($string) -# split string according to latex rules -# Each element of words is either -# a word (including trailing spaces and punctuation) -# a latex command -sub splitlatex { - my ($string) = @_ ; - my @retval=($string =~ m/$pat/osg); - - if (length($string) != length(join("",@retval))) { - print STDERR "\nWARNING: Inconsistency in length of input string and parsed string:\n This often indicates faulty or non-standard latex code.\n In many cases you can ignore this and the following warning messages.\n Note that character numbers in the following are counted beginning after \\begin{document} and are only approximate." unless $ignorewarnings; - print STDERR "DEBUG Original length ",length($string)," Parsed length ",length(join("",@retval)),"\n" if $debug; - print STDERR "DEBUG Input string: |$string|\n" if (length($string)<500) && $debug; - print STDERR "DEBUG Token parsing: |",join("+",@retval),"|\n" if (length($string)<500) && $debug ; - @retval=(); - # slow way only do this if other m//sg method fails - my $last = 0; - while ( $string =~ m/$pat/osg ) { - my $match=$&; - if ($last + length $& != pos $string ) { - my $pos=pos($string); - my $offset=30<$last ? 30 : $last; - my $dum=substr($string,$last-$offset,$pos-$last+2*$offset); - my $dum1=$dum; - my $cnt=$#retval; - my $i; - $dum1 =~ s/\n/ /g; - unless ($ignorewarnings) { - print STDERR "\n$dum1\n"; - print STDERR " " x 30,"^" x ($pos-$last)," " x 30,"\n"; - print STDERR "Missing characters near word " . (scalar @retval) . " character index: " . $last . "-" . pos($string) . " Length: " . length($match) . " Match: |$match| (expected match marked above).\n"; - } - # put in missing characters `by hand' - push (@retval, substr($dum,$offset,$pos-$last-length($match))); -# Note: there seems to be a bug in substr with utf8 that made the following line output substr which were too long, -# using dum instead appears to work -# push (@retval, substr($string,$last, pos($string)-$last-length($match))); - } - push (@retval, $match); - $last=pos $string; - } - - } - return @retval; -} - - -# pass1( \@seq1,\@seq2) -# Look for differences between seq1 and seq2. -# Where an common-subsequence block is flanked by deleted or appended blocks, -# and is shorter than $MINWORDSBLOCK words it is appended -# to the last deleted or appended word. If the block contains tokens other than words -# or punctuation it is not merged. -# Deleted or appended block consisting of words and safe commands only are -# also merged, to prevent break-up in pass2 (after previous isolated words have been removed) -# If there are commands with textual arguments (e.g. \caption) both in corresponding -# appended and deleted blocks split them such that the command and opening bracket -# are one token, then the rest is split up following standard rules, and the closing -# bracket is a separate token, ie. turn -# "\caption{This is a textual argument}" into -# ("\caption{","This ","is ","a ","textual ","argument","}") -# No return value. Destructively changes sequences -sub pass1 { - my $seq1 = shift ; - my $seq2 = shift ; - - my $len1 = scalar @$seq1; - my $len2 = scalar @$seq2; - my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' - - my ($last1,$last2)=(-1,-1) ; - my $cnt=0; - my $block=[]; - my $addblock=[]; - my $delblock=[]; - my $todo=[]; - my $instruction=[]; - my $i; - my (@delmid,@addmid,@dummy); - - my ($addcmds,$delcmds,$matchindex); - my ($addtextblocks,$deltextblocks); - my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); - my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); - - my $adddiscard = sub { - if ($cnt > 0 ) { - $matblkcnt++; - # just after an unchanged block -# print STDERR "Unchanged block $cnt, $last1,$last2 \n"; - if ($cnt < $MINWORDSBLOCK - && $cnt==scalar ( - grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat4\})*)/o - && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) - && scalar(@dummy=split(" ",$2))<3 ) } - @$block) ) { - # merge identical blocks shorter than $MINWORDSBLOCK - # and only containing ordinary words - # with preceding different word - # We cannot carry out this merging immediately as this - # would change the index numbers of seq1 and seq2 and confuse - # the algorithm, instead we store in @$todo where we have to merge - push(@$todo, [ $last1,$last2,$cnt,@$block ]); - } - $block = []; - $cnt=0; $last1=-1; $last2=-1; - } - }; - my $discard=sub { $deltokcnt++; - &$adddiscard; #($_[0],$_[1]); - push(@$delblock,[ $seq1->[$_[0]],$_[0] ]); - $last1=$_[0] }; - - my $add = sub { $addtokcnt++; - &$adddiscard; #($_[0],$_[1]); - push(@$addblock,[ $seq2->[$_[1]],$_[1] ]); - $last2=$_[1] }; - - my $match = sub { $mattokcnt++; - if ($cnt==0) { # first word of matching sequence after changed sequence or at beginning of word sequence - $deltextblocks = extracttextblocks($delblock); - $delblkcnt++ if scalar @$delblock; - $addtextblocks = extracttextblocks($addblock); - $addblkcnt++ if scalar @$addblock; - - $delcmds = extractcommands($delblock); - $addcmds = extractcommands($addblock); - # keygen(third argument of _longestCommonSubsequence) implies to sort on command (0th elements of $addcmd elements) - # the calling format for longestCommonSubsequence has changed between versions of - # Algorithm::Diff so we need to check which one we are using - if ( $algodiffversion > 1.15 ) { - ### Algorithm::Diff 1.19 - $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, 0, sub { $_[0]->[0] } ); - } else { - ### Algorithm::Diff 1.15 - $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, sub { $_[0]->[0] } ); - } - - for ($i=0 ; $i<=$#$matchindex ; $i++) { - if (defined($matchindex->[$i])){ - $j=$matchindex->[$i]; - @delmid=splitlatex($delcmds->[$i][3]); - @addmid=splitlatex($addcmds->[$j][3]); - while (scalar(@$deltextblocks) && $deltextblocks->[0][0]<$delcmds->[$i][1]) { - my ($index,$block,$cnt)=@{ shift(@$deltextblocks) }; - push(@$todo, [$index,-1,$cnt,@$block]); - } - push(@$todo, [ $delcmds->[$i][1],-1,-1,$delcmds->[$i][2],@delmid,$delcmds->[$i][4]]); - - while (scalar(@$addtextblocks) && $addtextblocks->[0][0]<$addcmds->[$j][1]) { - my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; - push(@$todo, [-1,$index,$cnt,@$block]); - } - push(@$todo, [ -1,$addcmds->[$j][1],-1,$addcmds->[$j][2],@addmid,$addcmds->[$j][4]]); - } - } - # mop up remaining textblocks - while (scalar(@$deltextblocks)) { - my ($index,$block,$cnt)=@{ shift(@$deltextblocks) } ; - push(@$todo, [$index,-1,$cnt,@$block]); - } - while (scalar(@$addtextblocks)) { - my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; - push(@$todo, [-1,$index,$cnt,@$block]); - } - - $addblock=[]; - $delblock=[]; - } - push(@$block,$seq2->[$_[1]]); - $cnt++ }; - - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - - - # now carry out the merging/splitting. Refer to elements relative from - # the end (with negative indices) as these offsets don't change before the instruction is executed - # cnt>0: merged small unchanged groups with previous changed blocks - # cnt==-1: split textual commands into components - foreach $instruction ( @$todo) { - ($last1,$last2,$cnt,@$block)=@$instruction ; - if ($cnt>=0) { - splice(@$seq1,$last1-$len1,1+$cnt,join("",$seq1->[$last1-$len1],@$block)) if $last1>=0; - splice(@$seq2,$last2-$len2,1+$cnt,join("",$seq2->[$last2-$len2],@$block)) if $last2>=0; - } else { - splice(@$seq1,$last1-$len1,1,@$block) if $last1>=0; - splice(@$seq2,$last2-$len2,1,@$block) if $last2>=0; - } - } - - if ($verbose) { - print STDERR "\n"; - print STDERR " $mattokcnt matching tokens in $matblkcnt blocks.\n"; - print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; - print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; - } -} - - -# extracttextblocks(\@blockindex) -# $blockindex has the following format -# [ [ token1, index1 ], [token2, index2],.. ] -# where index refers to the index in the original old or new word sequence -# Returns: reference to an array of the form -# [[ $index, $textblock, $cnt ], .. -# where $index index of block to be merged -# $textblock contains all the words to be merged with the word at $index (but does not contain this word) -# $cnt is length of block -# -# requires: iscmd -# -sub extracttextblocks { - my $block=shift; - my ($i,$token,$index); - my $textblock=[]; - my $last=-1; - my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' - my $retval=[]; - - for ($i=0;$i< scalar @$block;$i++) { - ($token,$index)=@{ $block->[$i] }; - # store pure text blocks - if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*)/o - && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) - && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { - # we have text or a command which can be treated as text - if ($last<0) { - # new pure-text block - $last=$index; - } else { - # add to pure-text block - push(@$textblock, $token); - } - } else { - # it is not text - if (scalar(@$textblock)) { - push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); - } - $textblock=[]; - $last=-1; - } - } - # finish processing a possibly unfinished block before returning - if (scalar(@$textblock)) { - push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); - } - return($retval) -} - - - -# extractcommands( \@blockindex ) -# $blockindex has the following format -# [ [ token1, index1 ], [token2, index2],.. ] -# where index refers to the index in the original old or new word sequence -# Returns: reference to an array of the form -# [ [ "\cmd1", index, "\cmd1[optarg]{arg1}{", "arg2" ,"} " ],.. -# where index is just taken from input array -# command must have a textual argument as last argument -# -# requires: iscmd -# -sub extractcommands { - my $block=shift; - my ($i,$token,$index,$cmd,$open,$mid,$closing); - my $retval=[]; - - for ($i=0;$i< scalar @$block;$i++) { - ($token,$index)=@{ $block->[$i] }; - # check if token is an alphanumeric command sequence with at least one non-optional argument - # \cmd[...]{...}{last argument} - # Capturing in the following results in these associations - # $1: \cmd[...]{...}{ - # $2: \cmd - # $3: last argument - # $4: } + trailing spaces - if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { - # push(@$retval,[ $2,$index,$1,$3,$4 ]); - ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; - $closing =~ s/\}/\\RIGHTBRACE/ ; - push(@$retval,[ $cmd,$index,$open,$mid,$closing ]); - } - } - return $retval; -} - -# iscmd($cmd,\@regexarray,\@regexexcl) checks -# return 1 if $cmd matches any of the patterns in the -# array $@regexarray, and none of the patterns in \@regexexcl, otherwise return 0 -sub iscmd { - my ($cmd,$regexar,$regexexcl)=@_; - my ($ret)=0; - foreach $pat ( @$regexar ) { - if ( $cmd =~ m/^${pat}$/ ) { - $ret=1 ; - last; - } - } - return 0 unless $ret; - foreach $pat ( @$regexexcl ) { - return 0 if ( $cmd =~ m/^${pat}$/ ); - } - return 1; -} - - -# pass2( \@seq1,\@seq2) -# Look for differences between seq1 and seq2. -# Mark begin and end of deleted and appended sequences with tags $DELOPEN and $DELCLOSE -# and $ADDOPEN and $ADDCLOSE, respectively, however exclude { } & and all comands, unless -# they match an element of the whitelist (SAFECMD) -# For words in TEXTCMD but not in SAFECMD, enclose interior with $ADDOPEN and $ADDCLOSE brackets -# Deleted comment lines are marked with %DIF < -# Added comment lines are marked with %DIF > -sub pass2 { - my $seq1 = shift ; - my $seq2 = shift ; - - my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); - my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); - - my $retval = []; - my $delhunk = []; - my $addhunk = []; - - my $discard = sub { $deltokcnt++; - push ( @$delhunk, $seq1->[$_[0]]) }; - - my $add = sub { $addtokcnt++; - push ( @$addhunk, $seq2->[$_[1]]) }; - - my $match = sub { $mattokcnt++; - if ( scalar @$delhunk ) { - $delblkcnt++; - # mark up changes, but comment out commands - push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk); - $delhunk = []; - } - if ( scalar @$addhunk ) { - $addblkcnt++; - # we mark up changes, but simply quote commands - push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk); - $addhunk = []; - } - push(@$retval,$seq2->[$_[1]]) }; - - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - # clear up unprocessed hunks - push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk) if scalar @$delhunk; - push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk) if scalar @$addhunk; - - - if ($verbose) { - print STDERR "\n"; - print STDERR " $mattokcnt matching tokens. \n"; - print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; - print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; - } - - return(@$retval); -} - -# marktags($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,\@block) -# returns ($openmark,$open,$block,$close,$closemark) if @block only contains no commands (except white-listed ones), -# braces, ampersands, or comments -# mark comments with $comment -# exclude all other exceptions from scope of open, close like this -# ($openmark, $open,...,$close, $opencomd,command, command,$closecmd, $open, ..., $close, $closemark) -# If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block -sub marktags { - my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; - my $word; - my (@argtext); - my $retval=[]; - my $noncomment=0; - my $cmd=-1; # -1 at beginning 0: last token written is a ordinary word - # 1: last token written is a command - # for keeping track whether we are just in a command sequence or in a word sequence - my $cmdcomment= ($opencmd =~ m/^%/); # Flag to indicate whether opencmd is a comment (i.e. if we intend to simply comment out changed commands) - my ($command,$commandword,$closingbracket) ; # temporary variables needed below to remember sub-pattern matches - -# split this block to flatten out sequences joined in pass1 - @$block=splitlatex(join "",@$block); - foreach (@$block) { - $word=$_; - if ( $word =~ s/^%/%$comment/ ) { - # a comment - if ($cmd==1) { - push (@$retval,$closecmd) ; - $cmd=-1; - } - push (@$retval,$word); - next; - } - if (! $noncomment) { - push (@$retval,$openmark); - $noncomment=1; - } - # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns - if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()([\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { - # word is a command or other significant token (not in SAFECMDLIST) - ## same conditions as in subroutine extractcommand: - # check if token is an alphanumeric command sequence with at least one non-optional argument - # \cmd[...]{...}{last argument} - # Capturing in the following results in these associations - # $1: \cmd[...]{...}{ - # $2: \cmd - # $3: last argument - # $4: } + trailing spaces - ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat4\})*\{)($pat4)(\}\s*)$/so ) - if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { - # word is a text command - we mark up the interior of the word. But if we are in a deleted block ($cmdcomment=1) and - # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) - # Because we do not want to disable this command - # here we do not use $opencmd and $closecmd($opencmd is empty) - if ($cmd==1) { - push (@$retval,$closecmd) ; - } elsif ($cmd==0) { - push (@$retval,$close) ; - } - $command=$1; $commandword=$2; $closingbracket=$4; - @argtext=splitlatex($3); # split textual argument into tokens - # and mark it up (but we do not need openmark and closemark) - # insert command with initial arguments, marked-up final argument, and closing bracket - if ( $cmdcomment && iscmd($commandword,\@CONTEXT1CMDLIST, \@CONTEXT1CMDEXCL) ) { - # context1cmd in a deleted environment; delete command itself but keep last argument, marked up - push (@$retval,$opencmd); - $command =~ s/\n/\n${opencmd}/sg ; # repeat opencmd at the beginning of each line - # argument, note that the additional comment character is included - # to suppress linebreak after opening parentheses, which is important - # for latexrevise - push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } else { - # normal textcmd or context1cmd in an added block - push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } - push (@$retval,$AUXCMD,"\n") if $cmdcomment ; - $cmd=-1 ; - } else { - # ordinary command - push (@$retval,$opencmd) if $cmd==-1 ; - push (@$retval,$close,$opencmd) if $cmd==0 ; - $word =~ s/\n/\n${opencmd}/sg if $cmdcomment ; # if opencmd is a comment, repeat this at the beginning of every line - push (@$retval,$word); - $cmd=1; - } - } else { - # just an ordinary word or word in SAFECMD - push (@$retval,$open) if $cmd==-1 ; - push (@$retval,$closecmd,$open) if $cmd==1 ; - push (@$retval,$word); - $cmd=0; - } - } - push (@$retval,$close) if $cmd==0; - push (@$retval,$closecmd) if $cmd==1; - - push (@$retval,$closemark) if ($noncomment); - return @$retval; -} - -# preprocess($string, ..) -# carry out the following pre-processing steps for all arguments: -# 1. Remove leading white-space -# 2. mark all first empty line (in block of several) with \PAR tokens -# 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier -# 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) -# into \verb{hash} -# 5. Convert \begin{verbatim} some verbatim text \end{verbatim} into \verbatim{hash} -# 6. Convert _n into \SUBSCRIPTNB{n} and _{nnn} into \SUBSCRIPT{nn} -# 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} -# 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} -# b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} - -# 9. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. -# -# NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file -# names or labels but it does not matter because they are converted back in the postprocessing step -# Returns: leading white space removed in step 1 -sub preprocess { - my @leadin=() ; - for (@_) { - s/^(\s*)//s; - push(@leadin,$1); - s/\n(\s*?)\n((?:\s*\n)*)/\n$1\\PAR\n$2/g ; - s/(?{$hstr}) && $string ne $hash->{$hstr}) { - warn "Repeated hash value for verbatim mode in spite of different content."; - $hstr="-$hstr"; - } - $hash->{$hstr}=$string; - return($hstr); -} - -#string=fromhash(\%hash,$fromstring) -# restores string value stored in hash -#string=fromhash(\%hash,$fromstring,$prependstring) -# additionally begins each line with prependstring -sub fromhash { - my ($hash,$hstr)=($_[0],$_[1]); - my $retstr=$hash->{$hstr}; - if ( $#_ >= 2) { - $retstr =~ s/^/$_[2]/mg; - } - return $retstr; -} - - -# postprocess($string, ..) -# carry out the following post-processing steps for all arguments: -# * Remove STOP token from the end -# * Replace \RIGHTBRACE by } -# 1. Check all deleted blocks: -# a.where a deleted block contains a matching \begin and -# \end environment (these will be disabled by a %DIFDELCMD statements), for selected environment enable enable -# these commands again (such that for example displayed math in a deleted equation -# is properly within math mode. For math mode environments replace numbered equation -# environments with their display only variety (so that equation numbers in new file and -# diff file are identical). Where the correct type of math environment cannot be determined -# use a place holder MATHMODE -# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement -# subtracting one from the respective counter to keep numbering consistent with new file -# Replace all MATHMODE environment commands by the correct environment to achieve matching -# pairs -# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es -# 2. Remove DIFadd, DIFdel, DIFFaddbegin , ... from picture environments -# 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties -# within floats (currently recognised float environments: plate,table,figure -# plus starred varieties). -# 4. Remove empty %DIFDELCMD < lines -# 4. Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \] -# Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$ -# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn} -# 6. Convert \SUBSCRIPTNB{n} into _n and \SUBCRIPT{nn} into _{nnn} -# 7. Expand hashes of verb and verbatim environments -# 8. Convert '\PERCENTAGE ' back into '\%' -# 9.. remove all \PAR tokens -# 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always -# on a line by themselves, similarly for table environment -# 4, undo renaming of the \begin and \end in comments - -# -# Note have to manually synchronize substitution commands below and -# DIF.. command names in the header -sub postprocess { - my ($begin,$len,$cnt,$float,$delblock,$addblock); - # second level blocks - my ($begin2,$cnt2,$len2,$eqarrayblock,$mathblock); - - for (@_) { - - # change $'s in comments to something harmless - 1 while s/(%.*)\$/$1DOLLARDIF/mg ; - - # Remove final STOP token - s/ STOP$//; - # Replace \RIGHTBRACE by } - s/\\RIGHTBRACE/}/g; - # Check all deleted blocks: where a deleted block contains a matching \begin and - # \end environment (these will be disabled by a %DIFDELCMD statements), enable - # these commands again (such that for example displayed math in a deleted equation - # is properly within math mode. For math mode environments replace numbered equation - # environments with their display only variety (so that equation numbers in new file and - # diff file are identical - while ( m/\\DIFdelbegin.*?\\DIFdelend/sg ) { - $cnt=0; - $len=length($&); - $begin=pos($_) - $len; - $delblock=$&; - - - ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in - ### an error - # displayed math environments - $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; - # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above - $delblock=~ s/(?[$_[0]]) }; - my $add = sub { if (! scalar @$block) { - @begin=('a',$_[0],$_[1]) ;} - elsif ( $begin[0] eq 'd' ) { - $begin[0]='c'; $begin[2]=$_[1]; - push(@$block, "%DIF -------") } - push(@$block, $seq2->[$_[1]] . " %DIF > " ) }; - my $match = sub { if ( scalar @$block ) { - if ( $begin[0] eq 'd' && $begin[1]!=$_[0]-1) { - $instring = sprintf "%%DIF %d-%dd%d",$begin[1],$_[0]-1,$begin[2]; } - elsif ( $begin[0] eq 'a' && $begin[2]!=$_[1]-1) { - $instring = sprintf "%%DIF %da%d-%d",$begin[1],$begin[2],$_[1]-1; } - elsif ( $begin[0] eq 'c' ) { - $instring = sprintf "%%DIF %sc%s", - ($begin[1]==$_[0]-1) ? "$begin[1]" : $begin[1]."-".($_[0]-1) , - ($begin[2]==$_[1]-1) ? "$begin[2]" : $begin[2]."-".($_[1]-1) ; } - else { - $instring = sprintf "%%DIF %d%s%d",$begin[1],$begin[0],$begin[2]; } - push @$retseq, $instring,@$block, "%DIF -------" ; - $block = []; - } - push @$retseq, $seq2->[$_[1]] - }; - # key function: remove multiple spaces (such that insertion or deletion of redundant white space is not reported) - my $keyfunc = sub { join(" ",split(" ",shift())) }; - - traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); - push @$retseq, @$block if scalar @$block; - - return wantarray ? @$retseq : $retseq ; -} - - - -# init_regex_arr_data(\@array,"TOKEN INIT") -# scans DATA file handel for line "%% TOKEN INIT" line -# then appends each line not beginning with % into array (as a quoted regex) -sub init_regex_arr_data { - my ($arr,$token)=@_; - my ($copy); - while () { - if ( m/^%%BEGIN $token\s*$/ ) { - $copy=1; } - elsif ( m/^%%END $token\s*/ ) { - last; } - chomp; - push (@$arr,qr/^$_$/) if ( $copy && !/^%/ ) ; - } - seek DATA,0,0; # rewind DATA handle to file begin -} - - -# init_regex_arr_ext(\@array,$arg) -# fills array with regular expressions. -# if arg is a file name, then read in list of regular expressions from that file -# (one expression per line) -# Otherwise treat arg as a comma separated list of regular expressions -sub init_regex_arr_ext { - my ($arr,$arg)=@_; - my $regex; - if ( -f $ arg ) { - open(FILE,"$arg") or die ("Couldn't open $arg: $!"); - while () { - chomp; - next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; - push (@$arr,qr/^$_$/); - } - close(FILE); - } - else { - # assume it is a comma-separated list of reg-ex - foreach $regex (split(qr/(?=1) { - $reset=shift; - } - if ($reset) { - $lasttime=times(); - } - else { - $retval=times()-$lasttime; - $lasttime=$lasttime+$retval; - return($retval); - } -} - - -sub usage { - die <<"EOF"; -Usage: $0 [options] old.tex new.tex > diff.tex - -Compares two latex files and writes tex code to stdout, which has the same -format as new.tex but has all changes relative to old.tex marked up or commented. - ---type=markupstyle --t markupstyle Add code to preamble for selected markup style - Available styles: UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE - CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR - [ Default: UNDERLINE ] - ---subtype=markstyle --s markstyle Add code to preamble for selected style for bracketing - commands (e.g. to mark changes in margin) - Available styles: SAFE MARGINAL DVIPSCOL - [ Default: SAFE ] - ---floattype=markstyle --f markstyle Add code to preamble for selected style which - replace standard marking and markup commands within floats - (e.g., marginal remarks cause an error within floats - so marginal marking can be disabled thus) - Available styles: FLOATSAFE IDENTICAL - [ Default: FLOATSAFE ] - ---encoding=enc --e enc Specify encoding of old.tex and new.tex. Typical encodings are - ascii, utf8, latin1, latin9. A list of available encodings can be - obtained by executing - perl -MEncode -e 'print join ("\\n",Encode->encodings( ":all" )) ;' - [Default encoding is utf8 unless the first few lines of the preamble contain - an invocation "\\usepackage[..]{inputenc} in which case the - encoding chosen by this command is asssumed. Note that ASCII (standard - latex) is a subset of utf8] - ---preamble=file --p file Insert file at end of preamble instead of auto-generating - preamble. The preamble must define the following commands - \\DIFaddbegin,\\DIFaddend,\\DIFadd{..}, - \\DIFdelbegin,\\DIFdelend,\\DIFdel{..}, - and varieties for use within floats - \\DIFaddbeginFL,\\DIFaddendFL,\\DIFaddFL{..}, - \\DIFdelbeginFL,\\DIFdelendFL,\\DIFdelFL{..} - (If this option is set -t, -s, and -f options - are ignored.) - ---exclude-safecmd=exclude-file ---exclude-safecmd="cmd1,cmd2,..." --A exclude-file ---replace-safecmd=replace-file ---append-safecmd=append-file ---append-safecmd="cmd1,cmd2,..." --a append-file Exclude from, replace or append to the list of regex - matching commands which are safe to use within the - scope of a \\DIFadd or \\DIFdel command. The file must contain - one Perl-RegEx per line (Comment lines beginning with # or % are - ignored). A literal comma within the comma-separated list must be - escaped thus "\\,", Note that the RegEx needs to match the whole of - the token, i.e., /^regex\$/ is implied and that the initial - "\\" of the command is not included. The --exclude-safecmd - and --append-safecmd options can be combined with the --replace-safecmd - option and can be used repeatedly to add cumulatively to the lists. - ---exclude-textcmd=exclude-file ---exclude-textcmd="cmd1,cmd2,..." --X exclude-file ---replace-textcmd=replace-file ---append-textcmd=append-file ---append-textcmd="cmd1,cmd2,..." --x append-file Exclude from, replace or append to the list of regex - matching commands whose last argument is text. See - entry for --exclude-safecmd directly above for further details. - ---replace-context1cmd=replace-file ---append-context1cmd=append-file ---append-context1cmd="cmd1,cmd2,..." - Replace or append to the list of regex matching commands - whose last argument is text but which require a particular - context to work, e.g. \\caption will only work within a figure - or table. These commands behave like text commands, except when - they occur in a deleted section, when they are disabled, but their - argument is shown as deleted text. - ---replace-context2cmd=replace-file ---append-context2cmd=append-file ---append-context2cmd="cmd1,cmd2,..." - As corresponding commands for context1. The only difference is that - context2 commands are completely disabled in deleted sections, including - their arguments. - - ---config var1=val1,var2=val2,... --c var1=val1,.. Set configuration variables. --c configfile Available variables: - MINWORDSBLOCK (integer) - FLOATENV (RegEx) - PICTUREENV (RegEx) - MATHENV (RegEx) - MATHREPL (String) - MATHARRENV (RegEx) - MATHARRREPL (String) - ARRENV (RegEx) - COUNTERCMD (RegEx) - This option can be repeated. - - ---packages=pkg1,pkg2,.. - Tell latexdiff that .tex file is processed with the packages in list - loaded. This is normally not necessary if the .tex file includes the - preamble, as the preamble is automatically scanned for \\usepackage commands. - Use of the --packages option disables automatic scanning, so if for any - reason package specific parsing needs to be switched off, use --packages=none. - The following packages trigger special behaviour: - endfloat hyperref amsmath - [ Default: scan the preamble for \\usepackage commands to determine - loaded packages.] - ---show-preamble Print generated or included preamble commands to stdout. - ---show-safecmd Print list of regex matching and excluding safe commands. - ---show-textcmd Print list of regex matching and excluding commands with text argument. - ---show-config Show values of configuration variables - ---show-all Show all of the above - - NB For all --show commands, no old.tex or new.tex file needs to be given, and no - differencing takes place. - ---allow-spaces Allow spaces between bracketed or braced arguments to commands - [Default requires arguments to directly follow each other without - intervening spaces] - ---flatten Replace \\input and \\include commands within body by the content - of the files in their argument. If \\includeonly is present in the - preamble, only those files are expanded into the document. However, - no recursion is done, i.e. \\input and \\include commands within - included sections are not expanded. The included files are assumed to - be located in the same directories as the old and new master files, - respectively, making it possible to organise files into old and new directories. - ---help --h Show this help text. - ---ignore-warnings Suppress warnings about inconsistencies in length between input - and parsed strings and missing characters. - ---verbose --V Output various status information to stderr during processing. - Default is to work silently. - ---version Show version number. -EOF -} - -=head1 NAME - -latexdiff - determine and markup differences between two latex files - -=head1 SYNOPSIS - -B [ B ] F F > F - -=head1 DESCRIPTION - -Briefly, I is a utility program to aid in the management of -revisions of latex documents. It compares two valid latex files, here -called C and C, finds significant differences -between them (i.e., ignoring the number of white spaces and position -of line breaks), and adds special commands to highlight the -differences. Where visual highlighting is not possible, e.g. for changes -in the formatting, the differences are -nevertheless marked up in the source. - -The program treats the preamble differently from the main document. -Differences between the preambles are found using line-based -differencing (similarly to the Unix diff command, but ignoring white -spaces). A comment, "S>>" is appended to each added line, i.e. a -line present in C but not in C. Discarded lines - are deactivated by prepending "S>>". Changed blocks are preceded by -comment lines giving information about line numbers in the original files. Where there are insignificant -differences, the resulting file C will be similar to -C. At the end of the preamble, the definitions for I markup commands are inserted. -In differencing the main body of the text, I attempts to -satisfy the following guidelines (in order of priority): - -=over 3 - -=item 1 - -If both C and C are valid LaTeX, then the resulting -C should also be valid LateX. (NB If a few plain TeX commands -are used within C or C then C is not -guaranteed to work but usually will). - -=item 2 - -Significant differences are determined on the level of -individual words. All significant differences, including differences -between comments should be clearly marked in the resulting source code -C. - -=item 3 - -If a changed passage contains text or text-producing commands, then -running C through LateX should produce output where added -and discarded passages are highlighted. - -=item 4 - -Where there are insignificant differences, e.g. in the positioning of -line breaks, C should follow the formatting of C - -=back - -For differencing the same algorithm as I is used but words -instead of lines are compared. An attempt is made to recognize -blocks which are completely changed such that they can be marked up as a unit. -Comments are differenced line by line -but the number of spaces within comments is ignored. Commands including -all their arguments are generally compared as one unit, i.e., no mark-up -is inserted into the arguments of commands. However, for a selected -number of commands (for example, C<\caption> and all sectioning -commands) the last argument is known to be text. This text is -split into words and differenced just as ordinary text (use options to -show and change the list of text commands, see below). As the -algorithm has no detailed knowledge of LaTeX, it assumes all pairs of -curly braces immediately following a command (i.e. a sequence of -letters beginning with a backslash) are arguments for that command. -As a restriction to condition 1 above it is thus necessary to surround -all arguments with curly braces, and to not insert -extraneous spaces. For example, write - - \section{\textem{This is an emphasized section title}} - -and not - - \section {\textem{This is an emphasized section title}} - -or - - \section\textem{This is an emphasized section title} - -even though all varieties are the same to LaTeX (but see -B<--allow-spaces> option which allows the second variety). - -For environments whose content does not conform to standard LaTeX or -where graphical markup does not make sense all markup commands can be -removed by setting the PICTUREENV configuration variable, set by -default to C and C environments; see B<--config> -option). The latter environment (C) can be used to -protect parts of the latex file where the markup results in illegal -markup. You have to surround the offending passage in both the old and -new file by C<\begin{DIFnomarkup}> and C<\end{DIFnomarkup}>. You must -define the environment in the preambles of both old and new -documents. I prefer to define it as a null-environment, - -C<\newenvironment{DIFnomarkup}{}{}> - -but the choice is yours. Any markup within the environment will be -removed, and generally everything within the environment will just be -taken from the new file. - -It is also possible to difference files which do not have a preamble. - In this case, the file is processed in the main document -mode, but the definitions of the markup commands are not inserted. - -All markup commands inserted by I begin with "C<\DIF>". Added -blocks containing words, commands or comments which are in C -but not in C are marked by C<\DIFaddbegin> and C<\DIFaddend>. -Discarded blocks are marked by C<\DIFdelbegin> and C<\DIFdelend>. -Within added blocks all text is highlighted with C<\DIFadd> like this: -C<\DIFadd{Added text block}> -Selected `safe' commands can be contained in these text blocks as well -(use options to show and change the list of safe commands, see below). -All other commands as well as braces "{" and "}" are never put within -the scope of C<\DIFadd>. Added comments are marked by prepending -"S >>". - -Within deleted blocks text is highlighted with C<\DIFdel>. Deleted -comments are marked by prepending "S >>". Non-safe command -and curly braces within deleted blocks are commented out with -"S >>". - - - -=head1 OPTIONS - -=head2 Preamble - -The following options determine the visual markup style by adding the appropriate -command definitions to the preamble. See the end of this section for a description of -available styles. - -=over 4 - -=item B<--type=markupstyle> or -B<-t markupstyle> - -Add code to preamble for selected markup style. This option defines -C<\DIFadd> and C<\DIFdel> commands. -Available styles: - -C - -[ Default: C ] - -=item B<--subtype=markstyle> or -B<-s markstyle> - -Add code to preamble for selected style for bracketing -commands (e.g. to mark changes in margin). This option defines -C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. -Available styles: C - -[ Default: C ] - -=item B<--floattype=markstyle> or -B<-f markstyle> - -Add code to preamble for selected style which -replace standard marking and markup commands within floats -(e.g., marginal remarks cause an error within floats -so marginal marking can be disabled thus). This option defines all -C<\DIF...FL> commands. -Available styles: C - -[ Default: C ] - -=item B<--encoding=enc> or -B<-e enc> - -Specify encoding of old.tex and new.tex. Typical encodings are -C, C, C, C. A list of available encodings can be -obtained by executing - -Cencodings( ":all" )) ;' > - -[Default encoding is utf8 unless the first few lines of the preamble contain -an invocation C<\usepackage[..]{inputenc}> in which case the -encoding chosen by this command is asssumed. Note that ASCII (standard -latex) is a subset of utf8] - -=item B<--preamble=file> or -B<-p file> - -Insert file at end of preamble instead of generating -preamble. The preamble must define the following commands -C<\DIFaddbegin, \DIFaddend, \DIFadd{..}, -\DIFdelbegin,\DIFdelend,\DIFdel{..},> -and varieties for use within floats -C<\DIFaddbeginFL, \DIFaddendFL, \DIFaddFL{..}, -\DIFdelbeginFL, \DIFdelendFL, \DIFdelFL{..}> -(If this option is set B<-t>, B<-s>, and B<-f> options -are ignored.) - -=item B<--packages=pkg1,pkg2,..> - -Tell latexdiff that .tex file is processed with the packages in list -loaded. This is normally not necessary if the .tex file includes the -preamble, as the preamble is automatically scanned for C<\usepackage> commands. -Use of the B<--packages> option disables automatic scanning, so if for any -reason package specific parsing needs to be switched off, use B<--packages=none>. -The following packages trigger special behaviour: - -=over 8 - -=item C - -Configuration variable amsmath is set to C (Default: C) - -=item C - -Ensure that C<\begin{figure}> and C<\end{figure}> always appear by themselves on a line. - -=item C - -Change name of C<\DIFadd> and C<\DIFdel> commands to C<\DIFaddtex> and C<\DIFdeltex> and -define new C<\DIFadd> and C<\DIFdel> commands, which provide a wrapper for these commands, -using them for the text but not for the link defining command (where any markup would cause -errors). - -=back - -[ Default: scan the preamble for C<\\usepackage> commands to determine - loaded packages.] - - - -=item B<--show-preamble> - -Print generated or included preamble commands to stdout. - -=back - -=head2 Configuration - -=over 4 - -=item B<--exclude-safecmd=exclude-file> or -B<-A exclude-file> or B<--exclude-safecmd="cmd1,cmd2,..."> - -=item B<--replace-safecmd=replace-file> - -=item B<--append-safecmd=append-file> or -B<-a append-file> or B<--append-safecmd="cmd1,cmd2,..."> - -Exclude from, replace or append to the list of regular expressions (RegEx) -matching commands which are safe to use within the -scope of a C<\DIFadd> or C<\DIFdel> command. The file must contain -one Perl-RegEx per line (Comment lines beginning with # or % are -ignored). Note that the RegEx needs to match the whole of -the token, i.e., /^regex$/ is implied and that the initial -"\" of the command is not included. -The B<--exclude-safecmd> and B<--append-safecmd> options can be combined with the -B<--replace-safecmd> -option and can be used repeatedly to add cumulatively to the lists. - B<--exclude-safecmd> -and B<--append-safecmd> can also take a comma separated list as input. If a -comma for one of the regex is required, escape it thus "\,". In most cases it -will be necessary to protect the comma-separated list from the shell by putting -it in quotation marks. - -=item B<--exclude-textcmd=exclude-file> or -B<-X exclude-file> or B<--exclude-textcmd="cmd1,cmd2,..."> - -=item B<--replace-textcmd=replace-file> - -=item B<--append-textcmd=append-file> or -B<-x append-file> or B<--append-textcmd="cmd1,cmd2,..."> - -Exclude from, replace or append to the list of regular expressions -matching commands whose last argument is text. See -entry for B<--exclude-safecmd> directly above for further details. - - -=item B<--replace-context1cmd=replace-file> - -=item B<--append-context1cmd=append-file> or -=item B<--append-context1cmd="cmd1,cmd2,..."> - -Replace or append to the list of regex matching commands -whose last argument is text but which require a particular -context to work, e.g. \caption will only work within a figure -or table. These commands behave like text commands, except when -they occur in a deleted section, when they are disabled, but their -argument is shown as deleted text. - -=item B<--replace-context1cmd=replace-file> - -=item B<--append-context2cmd=append-file> or -=item B<--append-context2cmd="cmd1,cmd2,..."> -As corresponding commands for context1. The only difference is that -context2 commands are completely disabled in deleted sections, including -their arguments. - - - -=item B<--config var1=val1,var2=val2,...> or B<-c var1=val1,..> - -=item B<-c configfile> - -Set configuration variables. The option can be repeated to set different -variables (as an alternative to the comma-separated list). -Available variables (see below for further explanations): - -C (integer) - -C (RegEx) - -C (RegEx) - -C (RegEx) - -C (String) - -C (RegEx) - -C (String) - -C (RegEx) - -C (RegEx) - -=item B<--show-safecmd> - -Print list of RegEx matching and excluding safe commands. - -=item B<--show-textcmd> - -Print list of RegEx matching and excluding commands with text argument. - -=item B<--show-config> - -Show values of configuration variables. - -=item B<--show-all> - -Combine all --show commands. - -NB For all --show commands, no C or C file needs to be specified, and no -differencing takes place. - - -=back - -=head2 Miscellaneous - -=over 4 - -=item B<--verbose> or B<-V> - -Output various status information to stderr during processing. -Default is to work silently. - -=item B<--ignore-warnings> - -Suppress warnings about inconsistencies in length between input and -parsed strings and missing characters. These warning messages are -often related to non-standard latex or latex constructions with a -syntax unknown to C but the resulting difference argument -is often fully functional anyway, particularly if the non-standard -latex only occurs in parts of the text which have not changed. - -=item B<--allow-spaces> - -Allow spaces between bracketed or braced arguments to commands. Note -that this option might have undesirable side effects (unrelated scope -might get lumpeded with preceding commands) so should only be used if the -default produces erroneous results. (Default requires arguments to -directly follow each other without intervening spaces). - -=item B<--flatten> - -Replace C<\input> and C<\include> commands within body by the content -of the files in their argument. If C<\includeonly> is present in the -preamble, only those files are expanded into the document. However, -no recursion is done, i.e. C<\input> and C<\include> commands within -included sections are not expanded. The included files are assumed to - be located in the same directories as the old and new master files, -respectively, making it possible to organise files into old and new directories. - -Use of this option is not recommended -primarily the processing time for the large documents is prohibitive, and -the resulting difference document no longer reflects the structure of the -input documents. - -=item B<--help> or -B<-h> - -Show help text - -=item B<--version> - -Show version number - -=back - -=head2 Predefined styles - -=head2 Major types - -The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands C<\DIFadd{...}> and C<\DIFdel{...}> . - -=over 10 - -=item C - -Added text is wavy-underlined and blue, discarded text is struck out and red -(Requires color and ulem packages). Overstriking does not work in displayed math equations such that deleted parts of equation are underlined, not struck out (this is a shortcoming inherent to the ulem package). - -=item C - -Added text is blue and set in sans-serif, and a red footnote is created for each discarded -piece of text. (Requires color package) - -=item C - -Like C but without the use of color. - -=item C - -Added text is blue and set in sans-serif, and discarded text is red and very small size. - -=item C - -Added tex is set in sans-serif, discarded text small and struck out - -=item C - -Added text is blue, and discarded text is red. Additionally, the changed text is marked with a bar in the margin (Requires color and changebar packages). - -=item C - -Like C but with additional changebars (Requires color and changebar packages). - -=item C - -Like C but with additional changebars (Requires color, ulem and changebar packages). - -=item C - -No mark up of text, but mark margins with changebars (Requires changebar package). - -=item C - -No visible markup (but generic markup commands will still be inserted. - -=back - -=head2 Subtypes - -The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: C<\DIFaddbegin, \DIFaddend, \DIFdelbegin, \DIFdelend>) - -=over 10 - -=item C - -No additional markup (Recommended choice) - -=item C - -Mark beginning and end of changed blocks with symbols in the margin nearby (using -the standard C<\marginpar> command - note that this sometimes moves somewhat -from the intended position. - -=item C - -An alternative way of marking added passages in blue, and deleted ones in red. Note -that C only works with the dvips converter, e.g. not pdflatex. -(it is recommeneded to use instead the main types to effect colored markup, -although in some cases coloring with dvipscol can be more complete). - -=back - -=head2 Float Types - -Some of the markup used in the main text might cause problems when used within -floats (e.g. figures or tables). For this reason alternative versions of all -markup commands are used within floats. The float type defines these alternative commands. - -=over 10 - -=item C - -Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is C as C<\marginpar> does not work properly within floats. - -=item C - -Mark additions the same way as in the main text. Deleted environments are marked by angular brackets \[ and \] and the deleted text is set in scriptscript size. This float type should always be used with the C and C markup types as the \footnote command does not work properly in floating environments. - -=item C - -Make no difference between the main text and floats. - -=back - - -=head2 Configuration Variables - -=over 10 - -=item C - -Minimum number of tokens required to form an independent block. This value is -used in the algorithm to detect changes of complete blocks by merging identical text parts of less than C to the preceding added and discarded parts. - -[ Default: 3 ] - -=item C - -Environments whose name matches the regular expression in C are -considered floats. Within these environments, the I markup commands -are replaced by their FL variaties. - -[ Default: S >] - -=item C - -Within environments whose name matches the regular expression in C -all latexdiff markup is removed (in pathologic cases this might lead to - inconsistent markup but this situation should be rare). - -[ Default: S >] - -=item C,C - -If both \begin and \end for a math environment (environment name matching C -or \[ and \]) -are within the same deleted block, they are replaced by a \begin and \end commands for C -rather than being commented out. - -[ Default: C=S >, C=S >] - -=item C,C - -as C,C but for equation arrays - -[ Default: C=S >, C=S >] - -=item C - -If a match to C is found within an inline math environment within a deleted or added block, then the inlined math -is surrounded by C<\mbox{>...C<}>. This is necessary as underlining does not work within inlined array environments. - -[ Default: C=S > - -=item C - -If a command in a deleted block which is also in the textcmd list matches C then an -additional command C<\addtocounter{>FC<}{-1}>, where F is the matching command, is appended in the diff file such that the numbering in the diff file remains synchronized with the -numbering in the new file. - -[ Default: C=C<(?:footnote|part|section|subsection> ... - -C<|subsubsection|paragraph|subparagraph)> ] - -=back - -=head1 BUGS - -UTF-8 support requires a relatively new version of perl (5.8.0 is sufficient -but 5.6.2 up would work OK, too). - -Option allow-spaces not implemented entirely consistently. It breaks -the rules that number and type of white space does not matter, as -different numbers of inter-argument spaces are treated as significant. - -Please send bug reports -to I. Include the serial number of I -(from comments at the top of the source or use B<--version>). If you come across latex -files that are error-free and conform to the specifications set out -above, and whose differencing still does not result in error-free -latex, please send me those files, ideally edited to only contain the -offending passage as long as that still reproduces the problem. - -=head1 SEE ALSO - -L - -=head1 PORTABILITY - -I does not make use of external commands and thus should run -on any platform supporting Perl 5.6 or higher. If files with encodings -other than ASCII or UTF-8 are processed, Perl 5.8 or higher is required. - -The standard version of I requires installation of the Perl package -C (available from I - -I) but a stand-alone -version, I, which has this package inlined, is available, too. -I requires the I command to be present. - -=head1 AUTHOR - -Copyright (C) 2004-2007 Frederik Tilmann - -This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 - -Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner -Thanks to everyone who send in bug reports. - -=cut - -__END__ -%%BEGIN SAFE COMMANDS -% Regex matching commands which can safely be in the -% argument of a \DIFadd or \DIFdel command (leave out the \) -arabic -dashbox -emph -fbox -framebox -hspace -math.* -makebox -mbox -pageref -ref -symbol -raisebox -rule -text.* -shortstack -usebox -dag -ddag -copyright -pounds -S -P -oe -OE -ae -AE -aa -AA -o -O -l -L -frac -ss -sqrt -ldots -cdots -vdots -ddots -alpha -beta -gamma -delta -epsilon -varepsilon -zeta -eta -theta -vartheta -iota -kappa -lambda -mu -nu -xi -pi -varpi -rho -varrho -sigma -varsigma -tau -upsilon -phi -varphi -chi -psi -omega -Gamma -Delta -Theta -Lambda -Xi -Pi -Sigma -Upsilon -Phi -Psi -Omega -ps -mp -times -div -ast -star -circ -bullet -cdot -cap -cup -uplus -sqcap -vee -wedge -setminus -wr -diamond -(?:big)?triangle.* -lhd -rhd -unlhd -unrhd -oplus -ominus -otimes -oslash -odot -bigcirc -d?dagger -amalg -leq -prec -preceq -ll -(?:sq)?su[bp]set(?:eq)? -in -vdash -geq -succ(?:eq)? -gg -ni -dashv -equiv -sim(?:eq)? -asymp -approx -cong -neq -doteq -propto -models -perp -mid -parallel -bowtie -Join -smile -frown -.*arrow -(?:long)?mapsto -.*harpoon.* -leadsto -aleph -hbar -imath -jmath -ell -wp -Re -Im -mho -prime -emptyset -nabla -surd -top -bot -angle -forall -exists -neg -flat -natural -sharp -backslash -partial -infty -Box -Diamond -triangle -clubsuit -diamondsuit -heartsuit -spadesuit -sum -prod -coprod -int -oint -big(?:sq)?c[au]p -bigvee -bigwedge -bigodot -bigotimes -bigoplus -biguplus -(?:arc)?(?:cos|sin|tan|cot)h? -csc -arg -deg -det -dim -exp -gcd -hom -inf -ker -lg -lim -liminf -limsup -ln -log -max -min -Pr -sec -sup -(SUPER|SUB)SCRIPTNB -(SUPER|SUB)SCRIPT -%%END SAFE COMMANDS - -%%BEGIN TEXT COMMANDS -% Regex matching commands with a text argument (leave out the \) -addcontents.* -cc -closing -chapter -dashbox -emph -encl -fbox -framebox -footnote -footnotetext -framebox -part -(sub){0,2}section\*? -(sub)?paragraph\*? -makebox -mbox -opening -parbox -raisebox -savebox -sbox -shortstack -signature -text.* -value -underline -sqrt -(SUPER|SUB)SCRIPT -%%END TEXT COMMANDS - -%%BEGIN CONTEXT1 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text -caption -%%END CONTEXT1 COMMANDS - -%%BEGIN CONTEXT2 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text -title -author -%%END CONTEXT2 COMMANDS - - -%% TYPES (Commands for highlighting changed blocks) - -%DIF UNDERLINE PREAMBLE -\RequirePackage[normalem]{ulem} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}} -\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}} -%DIF END UNDERLINE PREAMBLE - -%DIF CTRADITIONAL PREAMBLE -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\RequirePackage[stable]{footmisc} -\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} -\providecommand{\DIFdel}[1]{{\protect\color{red} [..\footnote{removed: #1} ]}} -%DIF END CTRADITIONAL PREAMBLE - -%DIF TRADITIONAL PREAMBLE -\RequirePackage[stable]{footmisc} -\providecommand{\DIFadd}[1]{{\sf #1}} -\providecommand{\DIFdel}[1]{{[..\footnote{removed: #1} ]}} -%DIF END TRADITIONAL PREAMBLE - -%DIF CFONT PREAMBLE -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} -\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}} -%DIF END CFONT PREAMBLE - -%DIF FONTSTRIKE PREAMBLE -\RequirePackage[normalem]{ulem} -\providecommand{\DIFadd}[1]{{\sf #1}} -\providecommand{\DIFdel}[1]{{\footnotesize \sout{#1}}} -%DIF END FONTSTRIKE PREAMBLE - -%DIF CCHANGEBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}#1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}#1}\protect\cbdelete} -%DIF END CCHANGEBAR PREAMBLE - -%DIF CFONTCHBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\sf #1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\scriptsize #1}\protect\cbdelete} -%DIF END CFONTCHBAR PREAMBLE - -%DIF CULINECHBAR PREAMBLE -\RequirePackage[normalem]{ulem} -\RequirePackage[dvips]{changebar} -\RequirePackage{color} -\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\uwave{#1}}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\sout{#1}}\protect\cbdelete} -%DIF END CULINECHBAR PREAMBLE - -%DIF CHANGEBAR PREAMBLE -\RequirePackage[dvips]{changebar} -\providecommand{\DIFadd}[1]{\protect\cbstart{#1}\protect\cbend} -\providecommand{\DIFdel}[1]{\protect\cbdelete} -%DIF END CHANGEBAR PREAMBLE - -%DIF INVISIBLE PREAMBLE -\providecommand{\DIFadd}[1]{#1} -\providecommand{\DIFdel}[1]{} -%DIF END INVISIBLE PREAMBLE - - -%% SUBTYPES (Markers for beginning and end of changed blocks) - -%DIF SAFE PREAMBLE -\providecommand{\DIFaddbegin}{} -\providecommand{\DIFaddend}{} -\providecommand{\DIFdelbegin}{} -\providecommand{\DIFdelend}{} -%DIF END SAFE PREAMBLE - -%DIF MARGIN PREAMBLE -\providecommand{\DIFaddbegin}{\protect\marginpar{a[}} -\providecommand{\DIFaddend}{\protect\marginpar{]}} -\providecommand{\DIFdelbegin}{\protect\marginpar{d[}} -\providecommand{\DIFdelend}{\protect\marginpar{]}} -%DIF END BRACKET PREAMBLE - -%DIF DVIPSCOL PREAMBLE -%Note: only works with dvips converter -\RequirePackage{color} -\RequirePackage{dvipscol} -\providecommand{\DIFaddbegin}{\protect\nogroupcolor{blue}} -\providecommand{\DIFaddend}{\protect\nogroupcolor{black}} -\providecommand{\DIFdelbegin}{\protect\nogroupcolor{red}} -\providecommand{\DIFdelend}{\protect\nogroupcolor{black}} -%DIF END DVIPSCOL PREAMBLE - - -%% FLOAT TYPES - -%DIF FLOATSAFE PREAMBLE -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} -\providecommand{\DIFaddbeginFL}{} -\providecommand{\DIFaddendFL}{} -\providecommand{\DIFdelbeginFL}{} -\providecommand{\DIFdelendFL}{} -%DIF END FLOATSAFE PREAMBLE - -%DIF IDENTICAL PREAMBLE -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} -\providecommand{\DIFaddbeginFL}{\DIFaddbegin} -\providecommand{\DIFaddendFL}{\DIFaddend} -\providecommand{\DIFdelbeginFL}{\DIFdelbegin} -\providecommand{\DIFdelendFL}{\DIFdelend} -%DIF END IDENTICAL PREAMBLE - -%DIF TRADITIONALSAFE PREAMBLE -% procidecommand color to make this work for TRADITIONAL and CTRADITIONAL -\providecommand{\color}[1]{} -\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} -\providecommand{\DIFdel}[1]{{\protect\color{red}[..{\scriptsize {removed: #1}} ]}} -\providecommand{\DIFaddbeginFL}{} -\providecommand{\DIFaddendFL}{} -\providecommand{\DIFdelbeginFL}{} -\providecommand{\DIFdelendFL}{} -%DIF END FLOATSAFE PREAMBLE - -%% SPECIAL PACKAGE PREAMBLE COMMANDS - -% Standard \DIFadd and \DIFdel are redefined as \DIFaddtex and \DIFdeltex -% when hyperref package is included. -%DIF HYPERREF PREAMBLE -\providecommand{\DIFadd}[1]{\texorpdfstring{\DIFaddtex{#1}}{#1}} -\providecommand{\DIFdel}[1]{\texorpdfstring{\DIFdeltex{#1}}{}} -%DIF END HYPERREF PACKAGE diff --git a/Master/texmf-dist/doc/latex/latexdiff/latexdiff-man.pdf b/Master/texmf-dist/doc/latex/latexdiff/latexdiff-man.pdf deleted file mode 100644 index 09493af5fe7..00000000000 Binary files a/Master/texmf-dist/doc/latex/latexdiff/latexdiff-man.pdf and /dev/null differ diff --git a/Master/texmf-dist/doc/support/latexdiff/COPYING b/Master/texmf-dist/doc/support/latexdiff/COPYING new file mode 100644 index 00000000000..d6fa9152e8d --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/COPYING @@ -0,0 +1,623 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. 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 +them 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 prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. 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. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey 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; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If 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 convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU 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 that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + 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. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +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. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + diff --git a/Master/texmf-dist/doc/support/latexdiff/README b/Master/texmf-dist/doc/support/latexdiff/README new file mode 100644 index 00000000000..7c7ff86766b --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/README @@ -0,0 +1,107 @@ +INTRODUCTION + +latexdiff is a Perl script, which compares two latex files and marks +up significant differences between them (i.e. a diff for latex files). + Various options are available for visual markup using standard latex +packages such as "color.sty". Changes not directly affecting visible +text, for example in formatting commands, are still marked in +the latex source. + +A rudimentary revision facilility is provided by another Perl script, +latexrevise, which accepts or rejects all changes. Manual +editing of the difference file can be used to override this default +behaviour and accept or reject selected changes only. + +The author is F Tilmann (ftilmann@users.berlios.de). + +Project webpage: http://latexdiff.berlios.de/ +CTAN page: http://www.ctan.org/tex-archive/support/latexdiff + + +REQUIREMENTS + +Perl 5.8 or higher must be installed. + The latexdiff script makes use of the Perl package Algorithm::Diff (available +from www.cpan.org, current version 1.19). You can either install this package, or +use the standalone version of latexdiff, latexdiff-so, which has version 1.15 of +this package inlined and does not require external installation of +the package. Because latexdiff uses internal functions of Algorithm:Diff whose +calling format or availability can change without notice, the preferred method is +now to use the standalone version. + +As an alternative, latexdiff-fast has a modified version of Algorithm::Diff inlined, +which internally uses the UNIX diff command. This version is much faster but is dependent +on an external "diff" command. Subtle differences in the algorithm of Algorithm::Diff and +UNIX-diff mean that the resulting set of differences will generally not be the same as +for the standard latexdiff. In most practical cases, these differences are minor, though. + +INSTALLATION UNIX/LINUX + +The basic installation procedure is almost trivial: + +1. Copy latexdiff, latexrevise and latexdiff-vc into a directory which + is in the search path and make them executable. If the Algorithm::Diff + package is not installed, use latexdiff-so instead of latexdiff. + +2. Copy latexdiff.1 and latexrevise.1 into the correct man directory + +3. Optionally create soft links latexdiff-cvs latexdiff-rcs, and + latexdiff-svn for latexdiff-vc. + +The attached Makefile contains example commands to carry out above +steps as root for a typical UNIX installation. Type + + make install (for the stand alone version) +or + make install-ext (for the version using the external Algorithm::Diff) +or + make install-fast (for the version using the UNIX 'diff' function for fast differencing) + +to get it rolling. You can type + + make test +or + make test-ext +or + make test-fast + +to test the respective versions on a brief example before installation + + +DOCUMENTATION: + +Usage instructions are in the manual latexdiff-man.pdf as well as the +man pages. + +CHANGELOGS: + +Check out the comment lines at the beginning of the perl scripts (latexdiff, latexdiff-vc, latexrevise) + +CONTRIBUTIONS + +The directory contrib contains code written by others relating to latexdiff. +Currently this directory contains: + +latexdiff-wrap (Author: V. Kuhlmann) An alternative wrapper script which can be used + instead of latexdiff-vc. Its main use is as a template for customised wrapper scripts. + +latexdiff.spec (Author: T. Doerges) spec file for RPM generation + +latexchanges (Author: Jan-Ake Larsson) Wrapper script for applying latexdiff with numbered documen version +(see contrib/README.latexchanges for a more detailed description) + +Cntributions by the following authors were incorporated into the latexdiff code, or inspired me to +extend latexdiff in a similar way: J. Paisley, N. Becker, K. Huebner + +LICENSE (also see file COPYING) + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License Version 3 as published by +the Free Software Foundation. + +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 (file LICENSE in the +distribution). + diff --git a/Master/texmf-dist/doc/support/latexdiff/contrib/README.latexchanges b/Master/texmf-dist/doc/support/latexdiff/contrib/README.latexchanges new file mode 100644 index 00000000000..4a027658444 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/contrib/README.latexchanges @@ -0,0 +1,13 @@ +latexchanges.py (Jan-Ake Larsson): +Here's a wrapper I wrote for latexdiff, intended as a drop-in +replacement for latex, when you have several numbered (or dated) +versions of a manuscript. My coauthors don't as a rule know what CVS or +SVN is, they simply use a number or date for the different versions. + +latexchanges replaces the current DVI with one that includes a +latexdiff to the last version. The last version is selected as the +TEX file in the same directory with the same prefix (up to a number +or a dot), that has an mtime immediately preceding the given TEX +file. + + diff --git a/Master/texmf-dist/doc/support/latexdiff/contrib/latexchanges.py b/Master/texmf-dist/doc/support/latexdiff/contrib/latexchanges.py new file mode 100644 index 00000000000..de7acbe8258 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/contrib/latexchanges.py @@ -0,0 +1,67 @@ +#! /bin/env python +# latexchanges +# +# Wrapper for latexdiff, intended as a drop-in replacement for latex, +# when you have several numbered (or dated) versions of a manuscript. +# My coauthors don't as a rule know what CVS or SVN is, they simply +# use a number or date for the different versions. +# +# latexchanges replaces the current DVI with one that includes a +# latexdiff to the last version. The last version is selected as the +# TEX file in the same directory with the same prefix (up to a number +# or a dot), that has an mtime immediately preceding the given TEX +# file. +# +# (I should probably add CVS version numbering too, at some point.) +# +# Copyright (C) 2009 by Jan-\AA{}ke Larsson +# Released under the terms of the GNU General Public License (GPL) +# Version 2. See http://www.gnu.org/ for details. +# +# Please do provide patches and bug reports, but remember: if it +# breaks, you get to keep the pieces. +# +# Jan-\AA{}ke Larsson +# Sept 16 2009 + +from os import listdir,system,stat +from sys import argv +from re import split + +name="" +newarg=[] + +# Find filename argument +for i in range(1,len(argv)): + if argv[i][-4:]==".tex": + basename=split('[0-9.]',argv[i])[0] + name=argv[i][:-4] + newarg.append(name+".changes.tex") + else: + newarg.append(argv[i]) + +if name: + print "Filename",name+".tex" + print "Prefix is",basename + # Find last archived version + mtime=stat(name+".tex").st_mtime + old_mtime=0 + ls=listdir(".") + for j in ls: + if j.startswith(basename) and j.endswith(".tex")\ + and not j.endswith(".changes.tex"): + tmptime=stat(j).st_mtime + if mtime>tmptime and old_mtime0: + print "Comparing with",oldname + system ("/bin/cp "+name+".aux "+name+".changes.aux") + system ("/bin/cp "+name+".bbl "+name+".changes.bbl") + system ("latexdiff "+oldname+" "+name+".tex > "+name+".changes.tex") + system ("latex "+" ".join(newarg)) + system ("cp "+name+".changes.dvi "+name+".dvi") + else: + system ("latex "+" ".join(argv[1:])) diff --git a/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff-wrap b/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff-wrap new file mode 100755 index 00000000000..894b424de36 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff-wrap @@ -0,0 +1,192 @@ +#!/bin/bash +# +# latexdiff-wrap +# +# Wrapper for latexdiff, to +# * provide support for documents consiting of more than 1 latex file +# * provide my common arguments +# +# Copyright (C) by Volker Kuhlmann +# Released under the terms of the GNU General Public License (GPL) Version 2. +# See http://www.gnu.org/ for details. +# +# Volker Kuhlmann +# 5, 6, 7, 12, 16, 17 Oct 2005 +# 31 Jan; 5, 7, 13, 15 Feb 2006 +# + +VERSION="0.6, 15 Feb 2006" +AUTHOR="Volker Kuhlmann " +COPYRIGHT="Copyright (C) 2005-2006" + + +#### +#### Constants and initialised variables +# +diffcmd="latexdiff" +diffrc="$HOME/texmf/latexdiff" +#diffargs="-e latin1 --ignore-warnings -p latexdiff-preamble.sty" +diffargs="-e latin1 --ignore-warnings" +diffargs="$diffargs --append-safecmd $diffrc/safe-cmds" +diffargs="$diffargs --append-textcmd $diffrc/text-cmds" +# Note: Can't use multiple --append-safecmd +# show current command lists: +#diffcmd="$diffcmd --show-safecmd --show-textcmd --show-config" + + +#### +#### Version, Usage, Help +# +show_version() { + echo "${0##*/} version $VERSION +$COPYRIGHT by $AUTHOR" +} + +show_usage() { + echo " +Usage: ${0##*/} OLDDIR NEWDIR DIFFDIR [DIFFARGS --] FILE.tex [...] + ${0##*/} --show [DIFFARGS] +Version $VERSION +$COPYRIGHT by $AUTHOR +" +} + +show_help() { + show_usage + echo "\ +For each FILE.tex, build a new file DIFFDIR/FILE.tex with markup of the changes +which were made from OLDDIR/FILE.tex to NEWDIR/FILE.tex. +Any path given with FILE.tex is stripped off. +Any DIFFARGS are added to the latexdiff call, if present (remember to follow +them with a double-hyphen on its own before the FILE arguments). + +With --show, shows the settings latexdiff would be running with, including the +changes applied by the user. +" +} + +# For scripts not using function library only: +Version() { show_version; exitwith ErrVersion; } +Usage() { show_help; exitwith ErrUsage; } +Help() { test "$1" && exitwith ErrHelp show_help; show_help; exitwith ErrOK; } + + +#### +#### Error/Exit codes +# +exitwith() { + exec 1>&2 # write stdout on stderr instead + case "$1" in + ErrOK) + exit 0;; + ErrVersion|ErrUsage|ErrHelp) + # Output generated by function (program) $2, if given + test -n "$2" && "$2" + exit 1;; + # more codes in here + # more codes in here + ErrBadoption) + echo "Bad option '$2'." + echo "Call with -h for help." + exit 9;; + ErrMissingParameter) + echo "A required parameter for option $2 is missing." + echo "Call with -h for help." + exit 9;; + *) + echo "Internal error: exitwith() called with illegal error code '$1'." + exit 19;; + esac +} + + +#### +#### Parse command line parameters +# + +# If the next arg starts with a "-", collect additional argument for latexdiff +# until "--". +scanextraargs() { + addargs=() + case "$1" in -*) + while [ $# -gt 0 -a "$1" != "--" ]; do + addargs=( "${addargs[@]}" "$1" ) + shift + done + test "$1" == "--" && shift + ;; esac + fileargs=( "$@" ) +} + +case "$1" in + --version) Version;; + --usage) Usage;; + --help|-h|-help) Help;; + --show) + shift + scanextraargs "$@" + (set -x + $diffcmd $diffargs "${addargs[@]}" \ + --show-safecmd --show-textcmd --show-config + ) | fmt + exit $? ;; +esac + +olddir="${1%/}" +newdir="${2%/}" +diffdir="${3%/}" + +if ! [ -d "$olddir" -a -d "$newdir" -a -d "$diffdir" ]; then + Help 1>&2 err +fi + +shift 3 + +scanextraargs "$@" +set -- "${fileargs[@]}" + + + +#### +#### Functions +# +#set -x +Log() { echo 1>&2 "+ $@"; "$@"; } + + +#### +#### Main +# + +# Create output directory, just in case. +(set -x +mkdir -p "$diffdir" +) +while [ $# -gt 0 ]; do + file="${1##*/}" + echo Examining: "$file" + # No point running latexdiff if both files are identical, + # but run latexdiff on top-level LaTeX file in any case. + if cmp --quiet "$olddir/$file" "$newdir/$file" \ + && ! grep -lq '\\begin.*{document}' "$newdir/$file"; then + (set -x + cp -p "$olddir/$file" "$diffdir" + ) + else + # Delete file, to make sure it's not clobbered by redirecting stdout + # in case it's a symlink to te original. + test -f "$diffdir/$file" && (set -x + rm "$diffdir/$file" + ) + # Run latexdiff if both input files are present. + run=1 + test -f "$olddir/$file" || { echo 1>&2 "No file: $olddir/$file"; run=; } + test -f "$newdir/$file" || { echo 1>&2 "No file: $newdir/$file"; run=; } + test -n "$run" && \ + (set -x + $diffcmd $diffargs "${addargs[@]}" \ + "$olddir/$file" "$newdir/$file" > "$diffdir/$file" + ) + fi + shift +done diff --git a/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff.spec b/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff.spec new file mode 100644 index 00000000000..9255a69fea9 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/contrib/latexdiff.spec @@ -0,0 +1,58 @@ +Summary: Diff for LaTeX files +Name: latexdiff +Version: 0.5 +Release: 1 +License: GPL +Group: Productivity/Publishing/TeX/Utilities +URL: http://www.tug.org/tex-archive/help/Catalogue/entries/latexdiff.html +Source0: %{name}.zip +BuildArch: noarch +BuildRoot: %{_tmppath}/%{name}-%{version}-%{release}-root +# only required for 'make install-ext' +# Requires: perl-Algorithm-Diff + + +%description +latexdiff is a Perl script, which compares two latex files and marks +up significant differences between them (i.e. a diff for latex files). + Various options are available for visual markup using standard latex +packages such as "color.sty". Changes not directly affecting visible +text, for example in formatting commands, are still marked in +the latex source. + +(C) 2004 Frederik Tilmann + + +%prep +%setup -n %{name} + + +%build +# quick had to adapt the Makefile +%{__mv} Makefile Makefile.old +%{__sed} \ + -e "s;INSTALLPATH = /usr/local;INSTALLPATH = \${DESTDIR}%{_prefix};" \ + -e "s;INSTALLMANPATH = \$(INSTALLPATH)/man;INSTALLMANPATH = \${DESTDIR}%{_mandir};" \ + Makefile.old > Makefile + + +%install +%{__mkdir_p} $RPM_BUILD_ROOT%{_bindir} +%{__mkdir_p} $RPM_BUILD_ROOT%{_mandir}/man1 + +%makeinstall + + +%clean +[ "${RPM_BUILD_ROOT}" != "/" ] && [ -d "${RPM_BUILD_ROOT}" ] && %{__rm} -rf "${RPM_BUILD_ROOT}" + + +%files +%defattr(-,root,root) +%doc example CHANGES LICENSE README +%{_bindir}/* +%{_mandir}/man*/* + +%changelog +* Thu Jan 4 2007 Till Dörges - 0.5-1 +- Initial build. diff --git a/Master/texmf-dist/doc/support/latexdiff/doc/example-diff.tex b/Master/texmf-dist/doc/support/latexdiff/doc/example-diff.tex new file mode 100644 index 00000000000..149588d2110 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/doc/example-diff.tex @@ -0,0 +1,89 @@ +\documentclass[12pt,a4paper]{article} +%DIF LATEXDIFF DIFFERENCE FILE +%DIF DEL example-draft.tex Sat Nov 17 00:45:22 2012 +%DIF ADD example-rev.tex Sat Nov 17 00:45:22 2012 + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +%DIF 7c7 +%DIF < \setlength{\textwidth}{6.5in} +%DIF ------- +\setlength{\textwidth}{6in} %DIF > +%DIF ------- + +\title{latexdiff Example - \DIFdelbegin \DIFdel{Draft }\DIFdelend \DIFaddbegin \DIFadd{Revised }\DIFaddend version} +\author{F Tilmann} +% Note how in the preamble visual markup is never used (even %DIF > +% if some preamble might eventually end up as visible text.) %DIF > +%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF +%DIF UNDERLINE PREAMBLE %DIF PREAMBLE +\RequirePackage[normalem]{ulem} %DIF PREAMBLE +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} %DIF PREAMBLE +\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}} %DIF PREAMBLE +\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}} %DIF PREAMBLE +%DIF SAFE PREAMBLE %DIF PREAMBLE +\providecommand{\DIFaddbegin}{} %DIF PREAMBLE +\providecommand{\DIFaddend}{} %DIF PREAMBLE +\providecommand{\DIFdelbegin}{} %DIF PREAMBLE +\providecommand{\DIFdelend}{} %DIF PREAMBLE +%DIF FLOATSAFE PREAMBLE %DIF PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} %DIF PREAMBLE +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} %DIF PREAMBLE +\providecommand{\DIFaddbeginFL}{} %DIF PREAMBLE +\providecommand{\DIFaddendFL}{} %DIF PREAMBLE +\providecommand{\DIFdelbeginFL}{} %DIF PREAMBLE +\providecommand{\DIFdelendFL}{} %DIF PREAMBLE +%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of \DIFaddbegin \DIFadd{the }\DIFaddend latexdiff features. +Type +\begin{verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{verbatim} +or +\begin{verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{verbatim} +to display the markup. + +\section*{\DIFdelbegin \DIFdel{Another }\DIFdelend \DIFaddbegin \DIFadd{Yet another }\DIFaddend section title} + + \DIFdelbegin \DIFdel{A paragraph with a line only in the draft document. }\DIFdelend More things could be said were it not for the constraints of time and space. + +\DIFaddbegin \DIFadd{A paragraph with a line only in the revised document. }\DIFaddend More things could be +said were it not for the constraints of time and space. + +And here is a \DIFdelbegin \DIFdel{tipo}\DIFdelend \DIFaddbegin \DIFadd{typo}\DIFaddend . + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & \DIFdelbegin \DIFdel{Grey }\DIFdelend \DIFaddbegin \DIFadd{White }\DIFaddend \\ +Saruman & \DIFdelbegin \DIFdel{White +}\DIFdelend \DIFaddbegin \DIFadd{Evil +}\DIFaddend \end{tabular} + +And \DIFdelbegin \DIFdel{sometimes a whole paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical}\DIFdelend \DIFaddbegin \DIFadd{now for something completely different, with not a paragraph in sight}\DIFaddend . +No change, +no markup! +\end{document} + + diff --git a/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.pdf b/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.pdf new file mode 100644 index 00000000000..a6b5a33aacd Binary files /dev/null and b/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.pdf differ diff --git a/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.tex b/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.tex new file mode 100644 index 00000000000..b6bb37effe6 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/doc/latexdiff-man.tex @@ -0,0 +1,355 @@ +\documentclass[a4]{article} +\usepackage{graphicx} +%\def\C++{{\rm C\kern-.05em\raise.3ex\hbox{\footnotesize ++}}} +%\def\underscore{\leavevmode\kern.04em\vbox{\hrule width 0.4em height 0.3pt}} +\setlength{\parindent}{0pt} +%\setlength{\textwidth}{6.5in} +%\setlength{\oddsidemargin}{0.0in} +\title{Marking up differences between latex files with {\em latexdiff}} +\author{F.J. Tilmann\thanks{tilmann@gfz-potsdam.de,ftilmann@users.berlios.de}} +\date{\today} + +\begin{document} +\maketitle + +\section*{Preamble} + +{\em latexdiff} is a Perl script, which compares two +latex files and marks up significant differences between them. Various options are available for visual markup using standard +latex packages such as {\em color.sty}. Changes not directly affecting visible +text, for example in formatting commands, are still marked in the +latex source. + +A rudimentary revision facilility is provided by another Perl script, +{\em latexrevise}, which accepts or rejects all changes. Manual editing +of the difference file can be used to override this default behaviour +and accept or reject selected changes only. + +There is no explicit support for annotations as these are trivial to implement. +For example, I include the following command definition in the preamble +\begin{verbatim} +\newcommand{\remark}[1]{{ \bf [ \footnotesize #1 ]}} +\end{verbatim} +and mark up annotations as follows +\begin{verbatim} +... The roadrunner is the fastest running bird \remark{Check this +again with a zoologist!}. The most famous roadrunner ... +\end{verbatim} +Alternatively, instead of a command like \verb#\remark# in the example just given, an +equivalent annotation environment could be defined. +{\em latexrevise} can remove such comments or +environments from the text body. + +%It is planned that the revision capabilities of this system will be +%further expanded, dependent on the amount of feedback received. + +On the following pages you find the {\em man} pages for {\em + latexdiff} and {\em latexrevise} and a simple example. + +\include{latexdiff} +\setcounter{section}{0} + +\include{latexrevise} +\setcounter{section}{0} + +\include{latexdiff-vc} +\setcounter{section}{0} + +\section*{A simple example} + +We start with a draft text, \verb|example-draft.tex|, listed here in +full but also included in the distribution (except that the ``verbatim'' environment had +to be renamed to ``Verbatim'' for the listing). + +{\scriptsize +\begin{verbatim} +\documentclass[12pt,a4paper]{article} + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +\setlength{\textwidth}{6.5in} + +\title{latexdiff Example - Draft version} +\author{F Tilmann} + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of latexdiff features. +Type +\begin{Verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{Verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{Verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{Verbatim} +or +\begin{Verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{Verbatim} +to display the markup. Of course, instead of \verb|xpdf| you can use +\verb|okular, evince, acroread| or any other pdf or postscript viewer. + +\section*{Another section title} + +A paragraph with a line only in the draft document. More things +could be said were it not for the constraints of time and space. + +More things could be said were it not for the constraints of time and space. + +And here is a tipo. + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & Grey \\ +Saruman & White +\end{tabular} + +And sometimes a whole paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical. +No change, no markup! +\end{document} +\end{verbatim} +} + +We can now edit +this text as we would do with any other latex file to create +a new revision of the text, \verb|example-rev.tex|. We should run +\begin{verbatim} +latex example-rev.tex +\end{verbatim} +and look at the resulting \verb|.dvi| file to make sure that all +changes are valid. An example revision is listed here: + +{\scriptsize +\begin{verbatim} +\documentclass[12pt,a4paper]{article} + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +\setlength{\textwidth}{6in} + +\title{latexdiff Example - Revised version} +\author{F Tilmann} +% Note how in the preamble visual markup is never used (even +% if some preamble might eventually end up as visible text.) + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of the latexdiff features. +Type +\begin{Verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{Verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{Verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{Verbatim} +or +\begin{Verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{Verbatim} +to display the markup. + +\section*{Yet another section title} + + More things could be said were it not for the constraints of time and space. + +A paragraph with a line only in the revised document. +More things could be said were it not for the constraints of time and space. + +And here is a typo. + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & White \\ +Saruman & Evil +\end{tabular} + +And now for something completely different, with not a paragraph in sight. +No change, +no markup! +\end{document} +\end{verbatim} +} + +To compare both revisions, type +\begin{verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{verbatim} +This results in the following difference file (a few newlines have been +added in this listing for legibility reasosn): +{\scriptsize +\begin{verbatim} +\documentclass[12pt,a4paper]{article} + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +%DIF 7c7 +%DIF < \setlength{\textwidth}{6.5in} +%DIF ------- +\setlength{\textwidth}{6in} %DIF > +%DIF ------- + +%DIF 9c9 +%DIF < \title{latexdiff Example - Draft version} +%DIF ------- +\title{latexdiff Example - Revised version} %DIF > +%DIF ------- +\author{F Tilmann} +% Note how in the preamble visual markup is never used (even %DIF > +% if some preamble might eventually end up as visible text.) %DIF > +%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF +%DIF UNDERLINE PREAMBLE %DIF PREAMBLE +\RequirePackage[normalem]{ulem} %DIF PREAMBLE +\RequirePackage{color} %DIF PREAMBLE +\providecommand{\DIFadd}[1]{{\color{blue}\uline{#1}}} %DIF PREAMBLE +\providecommand{\DIFdel}[1]{{\color{red}\sout{#1}}} %DIF PREAMBLE +%DIF SAFE PREAMBLE %DIF PREAMBLE +\providecommand{\DIFaddbegin}{} %DIF PREAMBLE +\providecommand{\DIFaddend}{} %DIF PREAMBLE +\providecommand{\DIFdelbegin}{} %DIF PREAMBLE +\providecommand{\DIFdelend}{} %DIF PREAMBLE +%DIF FLOATSAFE PREAMBLE %DIF PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} %DIF PREAMBLE +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} %DIF PREAMBLE +\providecommand{\DIFaddbeginFL}{} %DIF PREAMBLE +\providecommand{\DIFaddendFL}{} %DIF PREAMBLE +\providecommand{\DIFdelbeginFL}{} %DIF PREAMBLE +\providecommand{\DIFdelendFL}{} %DIF PREAMBLE +%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of latexdiff features. +Type +\begin{Verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{Verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{Verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{Verbatim} +or +\begin{Verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{Verbatim} +to display the markup. + +\section*{\DIFaddbegin \DIFadd{Yet another }\DIFaddend \DIFdelbegin +\DIFdel{Another }\DIFdelend section title} + + \DIFdelbegin \DIFdel{A paragraph with a line only in the draft + document. }\DIFdelend More things could + be said were it not for the constraints of time and space. + +\DIFaddbegin \DIFadd{A paragraph with a line only in the revised + document. }\DIFaddend More things could be said +were it not for the constraints of time and space. + +And here is a \DIFaddbegin \DIFadd{typo}\DIFaddend \DIFdelbegin +\DIFdel{tipo}\DIFdelend . + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & \DIFaddbegin \DIFadd{White }\DIFaddend \DIFdelbegin +\DIFdel{Grey }\DIFdelend \\ +Saruman & \DIFaddbegin \DIFadd{Evil +}\DIFaddend \DIFdelbegin \DIFdel{White +}\DIFdelend \end{tabular} + +And \DIFaddbegin \DIFadd{now for something completely different, with not + a paragraph in sight}\DIFaddend \DIFdelbegin \DIFdel{sometimes a whole + paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical}\DIFdelend . +No change, +no markup! +\end{document} +\end{verbatim} +} +Type +\begin{verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{verbatim} +to make the markup visible. This is what it looks like: + +\vspace{1cm} +\framebox[\textwidth]{\includegraphics[width=\textwidth]{example-diff}} +\vspace{1cm} + +If you approve of all the changes in the revision, just continue with +\verb|example-rev.tex| for the next revision. If you like to adopt +most but not all changes you can use \verb|latexrevise| in the +following manner. Simply remove the \verb|\DIFdelbegin| and +\verb|\DIFdelend| tags around the text you would like to keep and +simply remove the text between \verb|\DIFaddbegin| and +\verb|\DIFaddend| tags, if you do not wish to keep them. Say you are happy with all proposed changes for the +example above except in +the last paragraph where you prefer the original draft. You have +to change + +{\scriptsize +\begin{verbatim} +... +And \DIFaddbegin \DIFadd{now for something completely different, with not + a paragraph in sight}\DIFaddend \DIFdelbegin \DIFdel{sometimes a whole + paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical}\DIFdelend . +... +\end{verbatim} +} +into +{\scriptsize +\begin{verbatim} +... +And \DIFdel{sometimes a whole + paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical}. +... +\end{verbatim} +} +and run +\begin{verbatim} +latexrevise -a example-rev.tex > example-final.tex +\end{verbatim} +\verb|example-final.tex| is then almost identical to +\verb|example-rev.tex| except for the last paragraph. +\end{document} diff --git a/Master/texmf-dist/doc/support/latexdiff/example/example-draft.tex b/Master/texmf-dist/doc/support/latexdiff/example/example-draft.tex new file mode 100644 index 00000000000..593a1707121 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/example/example-draft.tex @@ -0,0 +1,59 @@ +\documentclass[12pt,a4paper]{article} + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +\setlength{\textwidth}{6.5in} + +\title{latexdiff Example - Draft version} +\author{F Tilmann} + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of latexdiff features. +Type +\begin{verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{verbatim} +or +\begin{verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{verbatim} +to display the markup. + +\section*{Another section title} + +A paragraph with a line only in the draft document. More things could be said +were it not for the constraints of time and space. + +More things could be said were it not for the constraints of time and space. + +And here is a tipo. + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & Grey \\ +Saruman & White +\end{tabular} + +And sometimes a whole paragraph gets completely rewritten. In this +case latexdiff marks up the whole paragraph even if some words in it +are identical. +No change, no markup! +\end{document} + + diff --git a/Master/texmf-dist/doc/support/latexdiff/example/example-rev.tex b/Master/texmf-dist/doc/support/latexdiff/example/example-rev.tex new file mode 100644 index 00000000000..4bcaf156272 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/example/example-rev.tex @@ -0,0 +1,60 @@ +\documentclass[12pt,a4paper]{article} + +\setlength{\topmargin}{-0.2in} +\setlength{\textheight}{9.5in} +\setlength{\oddsidemargin}{0.0in} + +\setlength{\textwidth}{6in} + +\title{latexdiff Example - Revised version} +\author{F Tilmann} +% Note how in the preamble visual markup is never used (even +% if some preamble might eventually end up as visible text.) + +\begin{document} +\maketitle + +\section*{Introduction} + +This is an extremely simple document that showcases some of the latexdiff features. +Type +\begin{verbatim} +latexdiff -t UNDERLINE example-draft.tex example-rev.tex > example-diff.tex +\end{verbatim} +to create the difference file. You can inspect this file directly. Then run either +\begin{verbatim} +pdflatex example-diff.tex +xpdf example-diff.pdf +\end{verbatim} +or +\begin{verbatim} +latex example-diff.tex +dvips -o example-diff.ps example-diff.dvi +gv example-diff.ps +\end{verbatim} +to display the markup. + +\section*{Yet another section title} + + More things could be said were it not for the constraints of time and space. + +A paragraph with a line only in the revised document. More things could be +said were it not for the constraints of time and space. + +And here is a typo. + +Here is a table: + +\begin{tabular}{ll} +Name & Description \\ +\hline +Gandalf & White \\ +Saruman & Evil +\end{tabular} + +And now for something completely different, with not a paragraph in sight. +No change, +no markup! +\end{document} + + diff --git a/Master/texmf-dist/doc/support/latexdiff/latexdiff b/Master/texmf-dist/doc/support/latexdiff/latexdiff new file mode 100755 index 00000000000..7075561e119 --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/latexdiff @@ -0,0 +1,3400 @@ +#!/usr/bin/env perl +##!/usr/bin/perl -w +# latexdiff - differences two latex files on the word level +# and produces a latex file with the differences marked up. +# +# Copyright (C) 2004-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) +# +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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 . +# +# Detailed usage information at the end of the file +# +# Version 1.0.1 - treat \big,\bigg etc. equivalently to \left and +# \right - include starred version in MATHENV - apply +# - flatten recursively and --flatten expansion is now +# aware of comments (thanks to Tim Connors for patch) +# - Change to post-processing for more reliability for +# deleted math environments +# - On linux systems, recognise and remove DOS style newlines +# - Provide markup for some special preamble commands (\title, +# \author,\date, +# - configurable by setting context2cmd +# - for styles using ulem package, remove \emph and \text.. from list of +# safe commands in order to allow linebreaks within the +# highlighted sections. +# - for ulem style, now show citations by enclosing them in \mbox commands. +# This unfortunately implies linebreaks within citations no longer function, +# so this functionality can be turned off (Option --disable-citation-markup). +# With --enable-citation-markup, the mbox markup is forced for other styles) +# - new substyle COLOR. This is particularly useful for marking up citations +# and some special post-processing is implemented to retain cite +# commands in deleted blocks. +# - four different levels of math-markup +# - Option --driver for choosing driver for modes employing changebar package +# - accept \\* as valid command (and other commands of form \.*). Also accept +# \ (backslashed newline) +# - some typo fixes, include commands defined in preamble as safe commands +# (Sebastian Gouezel) +# - include compared filenames as comments as line 2 and 3 of +# the preamble (can be modified with option --label, and suppressed with +# --no-label), option --visible-label to show files in generated pdf or dvi +# at the beginning of main document +# +# Version 0.5 A number of minor improvements based on feedback +# Deleted blocks are now shown before added blocks +# Package specific processing +# +# Version 0.43 unreleased typo in list of styles at the end +# Add protect to all \cbstart, \cbend commands +# More robust substitution of deleted math commands +# +# Version 0.42 November 06 Bug fixes only +# +# Version 0.4 March 06 option for fast differencing using UNIX diff command, several minor bug fixes (\par bug, improved highlighting of textcmds) +# +# Version 0.3 August 05 improved parsing of displayed math, --allow-spaces +# option, several minor bug fixes +# +# Version 0.25 October 04 Fix bug with deleted equations, add math mode commands to safecmd, add | to allowed interpunctuation signs +# Version 0.2 September 04 extension to utf-8 and variable encodings +# Version 0.1 August 04 First public release + +use Algorithm::Diff qw(traverse_sequences); + +use Getopt::Long ; +use strict ; +use warnings; +use utf8 ; + +my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); + + +my ($versionstring)=< 0, + WHOLE => 1, + COARSE => 2, + FINE => 3 +}; + + +my (@configlist,@labels, + @appendsafelist,@excludesafelist, + @appendtextlist,@excludetextlist, + @appendcontext1list,@appendcontext2list, + @packagelist); +my ($assign,@config); +# Hash where keys corresponds to the names of all included packages (including the documentclass as another package +# the optional arguments to the package are the values of the hash elements +my ($pkg,%packages); +# Defaults +$type='UNDERLINE'; +$subtype='SAFE'; +$floattype='FLOATSAFE'; +$mathmarkup=COARSE; + +$verbose=0; +# output debug and intermediate files, set to 0 in final distribution +$debug=0; +# define character properties +sub IsNonAsciiPunct { return <<'END' # Unicode punctuation but excluding ASCII punctuation ++utf8::IsPunct +-utf8::IsASCII +END +} +sub IsNonAsciiS { return <<'END' # Unicode symbol but excluding ASCII ++utf8::IsS +-utf8::IsASCII +END +} + + +my %verbhash; + +Getopt::Long::Configure('bundling'); +GetOptions('type|t=s' => \$type, + 'subtype|s=s' => \$subtype, + 'floattype|f=s' => \$floattype, + 'config|c=s' => \@configlist, + 'preamble|p=s' => \$preamblefile, + 'encoding|e=s' => \$encoding, + 'label|L=s' => \@labels, + 'no-label' => \$nolabel, + 'visible-label' => \$visiblelabel, + 'exclude-safecmd|A=s' => \@excludesafelist, + 'replace-safecmd=s' => \$replacesafe, + 'append-safecmd|a=s' => \@appendsafelist, + 'exclude-textcmd|X=s' => \@excludetextlist, + 'replace-textcmd=s' => \$replacetext, + 'append-textcmd|x=s' => \@appendtextlist, + 'replace-context1cmd=s' => \$replacecontext1, + 'append-context1cmd=s' => \@appendcontext1list, + 'replace-context2cmd=s' => \$replacecontext2, + 'append-context2cmd=s' => \@appendcontext2list, + 'show-preamble' => \$showpreamble, + 'show-safecmd' => \$showsafe, + 'show-textcmd' => \$showtext, + 'show-config' => \$showconfig, + 'show-all' => \$showall, + 'packages=s' => \@packagelist, + 'allow-spaces' => \$allowspaces, + 'math-markup=s' => \$mathmarkup, + 'enable-citation-markup' => \$enablecitmark, + 'disable-citation-markup' => \$disablecitmark, + 'verbose|V' => \$verbose, + 'ignore-warnings' => \$ignorewarnings, + 'driver=s'=> \$driver, + 'flatten' => \$flatten, + 'version' => \$version, + 'help|h|H' => \$help); + +if ( $help ) { + usage() ; +} + + +if ( $version ) { + die $versionstring ; +} + +print STDERR $versionstring if $verbose; + +if (defined($showall)){ + $showpreamble=$showsafe=$showtext=$showconfig=1; +} + +if (defined($mathmarkup)) { + $mathmarkup=~tr/a-z/A-Z/; + if ( $mathmarkup eq 'OFF' ){ + $mathmarkup=OFF; + } elsif ( $mathmarkup eq 'WHOLE' ){ + $mathmarkup=WHOLE; + } elsif ( $mathmarkup eq 'COARSE' ){ + $mathmarkup=COARSE; + } elsif ( $mathmarkup eq 'FINE' ){ + $mathmarkup=FINE; + } elsif ( $mathmarkup !~ m/^[0123]$/ ) { + die "Illegal value: ($mathmarkup) for option--math-markup. Possible values: OFF,WHOLE,COARSE,FINE,0- "; + } + # else use numerical value +} + +# setting extra preamble commands +if (defined($preamblefile)) { + $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); +} else { + $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); +} + +if ( defined($driver) ) { + # for changebar only + $latexdiffpreamble=~s/\[dvips\]/[$driver]/sg; +} +# setting up @SAFECMDLIST and @SAFECMDEXCL +if (defined($replacesafe)) { + init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); +} else { + init_regex_arr_data(\@SAFECMDLIST, "SAFE COMMANDS"); +} +foreach $appendsafe ( @appendsafelist ) { + init_regex_arr_ext(\@SAFECMDLIST, $appendsafe); +} +foreach $excludesafe ( @excludesafelist ) { + init_regex_arr_ext(\@SAFECMDEXCL, $excludesafe); +} + +# Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode +# (there is a conflict between citation and ulem package, see +# package documentation) +# Use post-processing + +if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { + push (@SAFECMDLIST, qr/^cite.*$/); +} else { + ### Experimental: disable text and emph commands + push (@SAFECMDLIST, qr/^cite.*$/) unless $disablecitmark; + push(@SAFECMDEXCL, qr/^emph$/, qr/^text..$/); + # replace \cite{..} by \mbox{\cite{..}} in added or deleted blocks in post-processing + if ( uc($subtype) eq "COLOR" or uc($subtype) eq "DVIPSCOL" ) { + # remove \cite command again from list of safe commands + pop @SAFECMDLIST; + # deleted cite commands + $CITE2CMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite-type commands which should be reinstated in deleted blocks + } else { + $CITECMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite commands which need to be protected within an mbox in UNDERLINE and other modes using ulem + } +} +$CITECMD='(?:cite\w*|nocite)' if $enablecitmark ; # as above for explicit selection + +# setting up @TEXTCMDLIST and @TEXTCMDEXCL +if (defined($replacetext)) { + init_regex_arr_ext(\@TEXTCMDLIST,$replacetext); +} else { + init_regex_arr_data(\@TEXTCMDLIST, "TEXT COMMANDS"); +} +foreach $appendtext ( @appendtextlist ) { + init_regex_arr_ext(\@TEXTCMDLIST, $appendtext); +} +foreach $excludetext ( @excludetextlist ) { + init_regex_arr_ext(\@TEXTCMDEXCL, $excludetext); +} + + +# setting up @CONTEXT1CMDLIST ( @CONTEXT1CMDEXCL exist but is always empty ) +if (defined($replacecontext1)) { + init_regex_arr_ext(\@CONTEXT1CMDLIST,$replacecontext1); +} else { + init_regex_arr_data(\@CONTEXT1CMDLIST, "CONTEXT1 COMMANDS"); +} +foreach $appendcontext1 ( @appendcontext1list ) { + init_regex_arr_ext(\@CONTEXT1CMDLIST, $appendcontext1); +} + + +# setting up @CONTEXT2CMDLIST ( @CONTEXT2CMDEXCL exist but is always empty ) +if (defined($replacecontext2)) { + init_regex_arr_ext(\@CONTEXT2CMDLIST,$replacecontext2); +} else { + init_regex_arr_data(\@CONTEXT2CMDLIST, "CONTEXT2 COMMANDS"); +} +foreach $appendcontext2 ( @appendcontext2list ) { + init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); +} + +# setting configuration variables +@config=(); +foreach $config ( @configlist ) { + if (-f $config ) { + open(FILE,$config) or die ("Couldn't open configuration file $config: $!"); + while () { + chomp; + next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; + push (@config,$_); + } + close(FILE); + } + else { +# foreach ( split(",",$config) ) { +# push @config,$_; +# } + push @config,split(",",$config) + } +} +foreach $assign ( @config ) { + $assign=~ m/\s*(\w*)\s*=\s*(\S*)\s*$/ or die "Illegal assignment $assign in configuration list (must be variable=value)"; + if ( $1 eq "MINWORDSBLOCK" ) { $MINWORDSBLOCK = $2; } + elsif ( $1 eq "FLOATENV" ) { $FLOATENV = $2 ; } + elsif ( $1 eq "PICTUREENV" ) { $PICTUREENV = $2 ; } + elsif ( $1 eq "MATHENV" ) { $MATHENV = $2 ; } + elsif ( $1 eq "MATHREPL" ) { $MATHREPL = $2 ; } + elsif ( $1 eq "MATHARRENV" ) { $MATHARRENV = $2 ; } + elsif ( $1 eq "MATHARRREPL" ) { $MATHARRREPL = $2 ; } + elsif ( $1 eq "ARRENV" ) { $ARRENV = $2 ; } + elsif ( $1 eq "COUNTERCMD" ) { $COUNTERCMD = $2 ; } + else { die "Unknown variable $1 in assignment.";} +} + +if ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) { + push(@MATHTEXTCMDLIST,qr/^MATHBLOCK(?:$MATHENV|$MATHARRENV|SQUAREBRACKET)$/); +} + + + +foreach $pkg ( @packagelist ) { + map { $packages{$_}="" } split(/,/,$pkg) ; +} + +if ($showpreamble) { + print "\nPreamble commands:\n"; + print $latexdiffpreamble ; +} + +if ($showsafe) { + print "\nCommands safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE (unless excluded):\n"; + print_regex_arr(@SAFECMDLIST); + print "\nCommands not safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE :\n"; + print_regex_arr(@SAFECMDEXCL); +} + +if ($showtext) { + print "\nCommands with last argument textual (unless excluded) and safe in every context:\n"; + print_regex_arr(@TEXTCMDLIST); + print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; + print_regex_arr(@CONTEXT1CMDLIST); + print "\nContext2 commands (last argument textual, command and its argument will be disabled in deleted passages):\n"; + print_regex_arr(@CONTEXT2CMDLIST); + print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; + print_regex_arr(@TEXTCMDEXCL); +} + + +if ($showconfig) { + print "Configuration variables:\n"; + print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; + print "FLOATENV=$FLOATENV\n"; + print "PICTUREENV=$PICTUREENV\n"; + print "MATHENV=$MATHENV\n"; + print "MATHREPL=$MATHREPL\n"; + print "MATHARRENV=$MATHARRENV\n"; + print "MATHARRREPL=$MATHARRREPL\n"; + print "ARRENV=$ARRENV\n"; + print "COUNTERCMD=$COUNTERCMD\n"; +} +if ($showconfig || $showtext || $showsafe || $showpreamble) { + exit 0; } +if ( @ARGV != 2 ) { + print STDERR "2 and only 2 non-option arguments required. Write latexdiff -h to get help\n"; + exit(2); +} + +# Are extra spaces between command arguments permissible? +my $extraspace; +if ($allowspaces) { + $extraspace='\s*'; +} else { + $extraspace=''; +} + +# append context lists to text lists (as text property is implied) +push @TEXTCMDLIST, @CONTEXT1CMDLIST; +push @TEXTCMDLIST, @CONTEXT2CMDLIST; + +push @TEXTCMDLIST, @MATHTEXTCMDLIST if $mathmarkup==COARSE; + +# internal additions to SAFECMDLIST +push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/); + + +# Patterns. These are used by some of the subroutines, too +# I can only define them down here because value of extraspace depends on an option + my $pat0 = '(?:[^{}])*'; + my $pat1 = '(?:[^{}]|\{'.$pat0.'\})*'; + my $pat2 = '(?:[^{}]|\{'.$pat1.'\})*'; + my $pat3 = '(?:[^{}]|\{'.$pat2.'\})*'; + my $pat4 = '(?:[^{}]|\{'.$pat3.'\})*'; + my $pat5 = '(?:[^{}]|\{'.$pat4.'\})*'; + my $pat6 = '(?:[^{}]|\{'.$pat5.'\})*'; + my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; + + my $quotemarks = '(?:\'\')|(?:\`\`)'; + my $punct='[0.,\/\'\`:;\"\?\(\)\[\]!~\p{IsNonAsciiPunct}\p{IsNonAsciiS}]'; + my $number='-?\d*\.\d*'; + my $mathpunct='[+=<>\-\|]'; + my $and = '&'; + my $coords= '[\-.,\s\d]*'; +# word: sequence of letters or accents followed by letter + my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; + my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; + + my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat6 . '\}|\(' . $coords .'\))'.$extraspace.')*'; + my $backslashnl='\\\\\n'; + my $oneletcmd='\\\\.\*?(?:\['.$brat0.'\]|\{'. $pat6 . '\})*'; + my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; +## the current maths command cannot cope with newline within the math expression + + my $comment='%.*?\n'; + my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${backslashnl}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; + + + +# now we are done setting up and can start working +my ($oldfile, $newfile) = @ARGV; +# check for existence of input files +if ( ! -e $oldfile ) { + die "Input file $oldfile does not exist."; +} +if ( ! -e $newfile ) { + die "Input file $newfile does not exist."; +} + + +# set the labels to be included into the file +my ($oldtime,$newtime,$oldlabel,$newlabel); +if (defined($labels[0])) { + $oldlabel=$labels[0] ; +} else { + $oldtime=localtime((stat($oldfile))[9]); + $oldlabel="$oldfile " . " "x(length($newfile)-length($oldfile)) . $oldtime; +} +if (defined($labels[1])) { + $newlabel=$labels[1] ; +} else { + $newtime=localtime((stat($newfile))[9]); + $newlabel="$newfile " . " "x(length($oldfile)-length($newfile)) . $newtime; +} + +$encoding=guess_encoding($newfile) unless defined($encoding); + +$encoding = "utf8" if $encoding =~ m/^utf8/i ; +if (lc($encoding) eq "utf8" ) { + binmode(STDOUT, ":utf8"); + binmode(STDERR, ":utf8"); +} + +$old=read_file_with_encoding($oldfile,$encoding); +$new=read_file_with_encoding($newfile,$encoding); + + + + +# reset time +exetime(1); +($oldpreamble,$oldbody,$oldpost)=splitdoc($old,'\\\\begin\{document\}','\\\\end\{document\}'); + + +($newpreamble,$newbody,$newpost)=splitdoc($new,'\\\\begin\{document\}','\\\\end\{document\}'); + + +if ($flatten) { + $oldbody=flatten($oldbody,$oldpreamble,$oldfile,$encoding); + $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); +} + +my @auxlines; +if ( length $oldpreamble && length $newpreamble ) { + # pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands) + # and marking up content with latexdiff markup + @auxlines=preprocess_preamble($oldpreamble,$newpreamble); + + @oldpreamble = split /\n/, $oldpreamble; + @newpreamble = split /\n/, $newpreamble; + + # If a command is defined in the preamble of the new file, and only uses safe commands, then it can be considered to be safe) (contribution S. Gouezel) + # Base this assessment on the new preamble + add_safe_commands($newpreamble); + + %packages=list_packages(@newpreamble) unless %packages; + if (defined $packages{"hyperref"} ) { + print STDERR "hyperref package detected.\n" if $verbose ; + $latexdiffpreamble =~ s/\{\\DIFadd\}/{\\DIFaddtex}/g; + $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; + $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); + } + print STDERR "Differencing preamble.\n" if $verbose; + + # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct + unshift @newpreamble,''; + unshift @oldpreamble,''; + @diffpreamble = linediff(\@oldpreamble, \@newpreamble); + # remove dummy line again + shift @diffpreamble; + # add filenames, modification time and latexdiff mark + defined($nolabel) or splice @diffpreamble,1,0, + "%DIF LATEXDIFF DIFFERENCE FILE", + ,"%DIF DEL $oldlabel", + "%DIF ADD $newlabel"; + if ( @auxlines ) { + push @diffpreamble,"%DIF DELETED TITLE COMMANDS FOR MARKUP"; + push @diffpreamble,join("\n",@auxlines); + } + push @diffpreamble,$latexdiffpreamble; + push @diffpreamble,'\begin{document}'; +} +elsif ( !length $oldpreamble && !length $newpreamble ) { + @diffpreamble=(); +} else { + print STDERR "Either both texts must have preamble or neither text must have the preamble.\n"; + exit(2); +} + +if (defined $packages{"amsmath"} or defined $packages{"amsart"} or defined $packages{"amsbook"} ) { + print STDERR "amsmath package detected.\n" if $verbose ; + $MATHARRREPL='align*'; +} + +print STDERR "Preprocessing body. " if $verbose; +my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); + + +# run difference algorithm +@diffbody=bodydiff($oldbody, $newbody); +$diffbo=join("",@diffbody); +if ( $debug ) { + open(RAWDIFF,">","latexdiff.debug.bodydiff"); + print RAWDIFF $diffbo; + close(RAWDIFF); +} +print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; +postprocess($diffbo); +$diffall =join("\n",@diffpreamble) ; +# add visible labels +if (defined($visiblelabel)) { + # Give information right after \begin{document} (or at the beginning of the text for files without preamble + ### if \date command is used, add information to \date argument, otherwise give right after \begin{document} + ### $diffall=~s/(\\date$extraspace(?:\[$brat0\])?$extraspace)\{($pat6)\}/$1\{$2 \\ LATEXDIFF comparison \\ Old: $oldlabel \\ New: $newlabel \}/ or + $diffbo = "\\begin{verbatim}LATEXDIFF comparison\nOld: $oldlabel\nNew: $newlabel\\end{verbatim}\n$diffbo" ; +} + +$diffall .= "$newleadin$diffbo" ; +$diffall .= "\\end{document}$newpost" if length $newpreamble ; +if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { + print STDERR "Encoding output file to $encoding\n" if $verbose; + $diffall=Encode::encode($encoding,$diffall); + binmode STDOUT; +} +print $diffall; + + +print STDERR "(",exetime()," s)\n","Done.\n" if $verbose; + + + +## guess_encoding(filename) +## reads the first 20 lines of filename and looks for call of inputenc package +## if found, return the option of this package (encoding), otherwise return ascii +sub guess_encoding { + my ($filename)=@_; + my ($i,$enc); + open (FH, $filename) or die("Couldn't open $filename: $!"); + $i=0; + while () { + next if /^\s*%/; # skip comment lines + if (m/\\usepackage\[(\w*?)\]\{inputenc\}/) { + close(FH); + return($1); + } + last if (++$i > 20 ); # scan at most 20 non-comment lines + } + close(FH); + return("ascii"); +} + + +sub read_file_with_encoding { + my ($output); + my ($filename, $encoding) = @_; + + if (lc($encoding) eq "utf8" ) { + open (FILE, "<:utf8",$filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + } elsif ( lc($encoding) eq "ascii") { + open (FILE, $filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + } else { + require Encode; + open (FILE, "<",$filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + print STDERR "Converting $filename from $encoding to utf8\n" if $verbose; + $output=Encode::decode($encoding,$output); + } + close FILE; + if ($^O eq "linux" ) { + $output =~ s/\r\n/\n/g ; + } + return $output; +} + +# %packages=list_packages(@preamble) +# scans the arguments for \documentclass and \usepackage statements and constructs a hash +# whose keys are the included packages, and whose values are the associated optional arguments +sub list_packages { + my (@preamble)=@_; + my %packages=(); + foreach $line ( @preamble ) { + # get rid of comments + $line=~s/(?catfile($dirname,$fname), "\n" if $debug; + # content of file becomes replacement value (use recursion), add \newpage if the command was include + ###$replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + $replacement=flatten(read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding), $preamble,$filename,$encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + # \include always starts a new page; use explicit \newpage command to simulate this + $begline=(defined($1)? $1 : "") ; + $newpage=(defined($3)? " \\newpage " : "") ; + "$begline$newpage$replacement$newpage"; + }/exgm; + + return($text); +} + + +# print_regex_arr(@arr) +# prints regex array without x-ism expansion put in by pearl to stdout +sub print_regex_arr { + my $dumstring; + $dumstring = join(" ",@_); # PERL generates string (?-xism:^ref$) for quoted refex ^ref$ + $dumstring =~ s/\(\?-xism:\^(.*?)\$\)/$1/g; # remove string and ^,$ marks before output + print $dumstring,"\n"; +} + + +# @lines=extrapream($type) +# reads line from appendix (end of file after __END__ token) +sub extrapream { + my $type; + my @retval=("%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; + my ($copy); + + while (@_) { + $copy=0; + $type=shift ; + if ( -f $type ) { + open (FILE,$type) or die "Cannot open preamble file $type: $!"; + print STDERR "Reading preamble file $type\n" if $verbose ; + while () { + chomp ; + if ( $_ =~ m/%DIF PREAMBLE/ ) { + push (@retval,"$_"); + } else { + push (@retval,"$_ %DIF PREAMBLE"); + } + } + } + else { # not (-f $type) + $type=uc($type); # upcase argument + print STDERR "Preamble Internal Type $type\n" if $verbose; + while () { + if ( m/^%DIF $type/ ) { + $copy=1; } + elsif ( m/^%DIF END $type/ ) { + last; } + chomp; + push (@retval,"$_ %DIF PREAMBLE") if $copy; + } + if ( $copy == 0 ) { + print STDERR "\nPreamble style $type not implemented.\n"; + print STDERR "Write latexdiff -h to get help with available styles\n"; + exit(2); + } + seek DATA,0,0; # rewind DATA handle to file begin + } + } + push (@retval,"%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; + return @retval; +} + + +# ($part1,$part2,$part3)=splitdoc($text,$word1,$word2) +# splits $text into 3 parts at $word1 and $word2. +# if neither $word1 nor $word2 exist, $part1 and $part3 are empty, $part2 is $text +# If only $word1 or $word2 exist but not the other, output an error message. + +# NB this version avoids $` and $' for performance reason although it only makes a tiny difference +# (in one test gain a tenth of a second for a 30s run) +sub splitdoc { + my ($text,$word1,$word2)=@_; + my ($part1,$part2,$part3)=("","",""); + my ($rest,$pos); + + if ( $text =~ m/(^[^%]*)($word1)/mg ) { + $pos=pos $text; + $part1=substr($text,0,$pos-length($2)); + $rest=substr($text,$pos); + if ( $rest =~ m/(^[^%]*)($word2)/mg ) { + $pos=pos $rest; + $part2=substr($rest,0,$pos-length($2)); + $part3=substr($rest,$pos); + } + else { + die "$word1 and $word2 not in the correct order or not present as a pair." ; + } + } else { + $part2=$text; + die "$word2 present but not $word1." if ( $text =~ m/(^[^%]*)$word2/ms ); + } + return ($part1,$part2,$part3); +} + + + + + +# bodydiff($old,$new) +sub bodydiff { + my ($oldwords, $newwords) = @_; + my @retwords; + + print STDERR "(",exetime()," s)\n","Splitting into latex tokens \n" if $verbose; + print STDERR "Parsing $oldfile \n" if $verbose; + my @oldwords = splitlatex($oldwords); + print STDERR "Parsing $newfile \n" if $verbose; + my @newwords = splitlatex($newwords); + + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } + + print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; + pass1(\@oldwords, \@newwords); + + + print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold2.tex"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew2.tex"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } + + @retwords=pass2(\@oldwords, \@newwords); + + return(@retwords); +} + + + + +# @words=splitlatex($string) +# split string according to latex rules +# Each element of words is either +# a word (including trailing spaces and punctuation) +# a latex command +sub splitlatex { + my ($string) = @_ ; + # if input is empty, return empty list + length($string)>0 or return (); + + my @retval=($string =~ m/$pat/osg); + + if (length($string) != length(join("",@retval))) { + print STDERR "\nWARNING: Inconsistency in length of input string and parsed string:\n This often indicates faulty or non-standard latex code.\n In many cases you can ignore this and the following warning messages.\n Note that character numbers in the following are counted beginning after \\begin{document} and are only approximate." unless $ignorewarnings; + print STDERR "DEBUG Original length ",length($string)," Parsed length ",length(join("",@retval)),"\n" if $debug; + print STDERR "DEBUG Input string: |$string|\n" if (length($string)<500) && $debug; + print STDERR "DEBUG Token parsing: |",join("+",@retval),"|\n" if (length($string)<500) && $debug ; + @retval=(); + # slow way only do this if other m//sg method fails + my $last = 0; + while ( $string =~ m/$pat/osg ) { + my $match=$&; + if ($last + length $& != pos $string ) { + my $pos=pos($string); + my $offset=30<$last ? 30 : $last; + my $dum=substr($string,$last-$offset,$pos-$last+2*$offset); + my $dum1=$dum; + my $cnt=$#retval; + my $i; + $dum1 =~ s/\n/ /g; + unless ($ignorewarnings) { + print STDERR "\n$dum1\n"; + print STDERR " " x 30,"^" x ($pos-$last)," " x 30,"\n"; + print STDERR "Missing characters near word " . (scalar @retval) . " character index: " . $last . "-" . pos($string) . " Length: " . length($match) . " Match: |$match| (expected match marked above).\n"; + } + # put in missing characters `by hand' + push (@retval, substr($dum,$offset,$pos-$last-length($match))); +# Note: there seems to be a bug in substr with utf8 that made the following line output substr which were too long, +# using dum instead appears to work +# push (@retval, substr($string,$last, pos($string)-$last-length($match))); + } + push (@retval, $match); + $last=pos $string; + } + + } + return @retval; +} + + +# pass1( \@seq1,\@seq2) +# Look for differences between seq1 and seq2. +# Where an common-subsequence block is flanked by deleted or appended blocks, +# and is shorter than $MINWORDSBLOCK words it is appended +# to the last deleted or appended word. If the block contains tokens other than words +# or punctuation it is not merged. +# Deleted or appended block consisting of words and safe commands only are +# also merged, to prevent break-up in pass2 (after previous isolated words have been removed) +# If there are commands with textual arguments (e.g. \caption) both in corresponding +# appended and deleted blocks split them such that the command and opening bracket +# are one token, then the rest is split up following standard rules, and the closing +# bracket is a separate token, ie. turn +# "\caption{This is a textual argument}" into +# ("\caption{","This ","is ","a ","textual ","argument","}") +# No return value. Destructively changes sequences +sub pass1 { + my $seq1 = shift ; + my $seq2 = shift ; + + my $len1 = scalar @$seq1; + my $len2 = scalar @$seq2; + my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' + + my ($last1,$last2)=(-1,-1) ; + my $cnt=0; + my $block=[]; + my $addblock=[]; + my $delblock=[]; + my $todo=[]; + my $instruction=[]; + my $i; + my (@delmid,@addmid,@dummy); + + my ($addcmds,$delcmds,$matchindex); + my ($addtextblocks,$deltextblocks); + my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); + my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); + + my $adddiscard = sub { + if ($cnt > 0 ) { + $matblkcnt++; + # just after an unchanged block +# print STDERR "Unchanged block $cnt, $last1,$last2 \n"; + if ($cnt < $MINWORDSBLOCK + && $cnt==scalar ( + grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat6\})*)/o + && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) + && scalar(@dummy=split(" ",$2))<3 ) } + @$block) ) { + # merge identical blocks shorter than $MINWORDSBLOCK + # and only containing ordinary words + # with preceding different word + # We cannot carry out this merging immediately as this + # would change the index numbers of seq1 and seq2 and confuse + # the algorithm, instead we store in @$todo where we have to merge + push(@$todo, [ $last1,$last2,$cnt,@$block ]); + } + $block = []; + $cnt=0; $last1=-1; $last2=-1; + } + }; + my $discard=sub { $deltokcnt++; + &$adddiscard; #($_[0],$_[1]); + push(@$delblock,[ $seq1->[$_[0]],$_[0] ]); + $last1=$_[0] }; + + my $add = sub { $addtokcnt++; + &$adddiscard; #($_[0],$_[1]); + push(@$addblock,[ $seq2->[$_[1]],$_[1] ]); + $last2=$_[1] }; + + my $match = sub { $mattokcnt++; + if ($cnt==0) { # first word of matching sequence after changed sequence or at beginning of word sequence + $deltextblocks = extracttextblocks($delblock); + $delblkcnt++ if scalar @$delblock; + $addtextblocks = extracttextblocks($addblock); + $addblkcnt++ if scalar @$addblock; + + $delcmds = extractcommands($delblock); + $addcmds = extractcommands($addblock); + # keygen(third argument of _longestCommonSubsequence) implies to sort on command (0th elements of $addcmd elements) + # the calling format for longestCommonSubsequence has changed between versions of + # Algorithm::Diff so we need to check which one we are using + if ( $algodiffversion > 1.15 ) { + ### Algorithm::Diff 1.19 + $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, 0, sub { $_[0]->[0] } ); + } else { + ### Algorithm::Diff 1.15 + $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, sub { $_[0]->[0] } ); + } + + for ($i=0 ; $i<=$#$matchindex ; $i++) { + if (defined($matchindex->[$i])){ + $j=$matchindex->[$i]; + @delmid=splitlatex($delcmds->[$i][3]); + @addmid=splitlatex($addcmds->[$j][3]); + while (scalar(@$deltextblocks) && $deltextblocks->[0][0]<$delcmds->[$i][1]) { + my ($index,$block,$cnt)=@{ shift(@$deltextblocks) }; + push(@$todo, [$index,-1,$cnt,@$block]); + } + push(@$todo, [ $delcmds->[$i][1],-1,-1,$delcmds->[$i][2],@delmid,$delcmds->[$i][4]]); + + while (scalar(@$addtextblocks) && $addtextblocks->[0][0]<$addcmds->[$j][1]) { + my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; + push(@$todo, [-1,$index,$cnt,@$block]); + } + push(@$todo, [ -1,$addcmds->[$j][1],-1,$addcmds->[$j][2],@addmid,$addcmds->[$j][4]]); + } + } + # mop up remaining textblocks + while (scalar(@$deltextblocks)) { + my ($index,$block,$cnt)=@{ shift(@$deltextblocks) } ; + push(@$todo, [$index,-1,$cnt,@$block]); + } + while (scalar(@$addtextblocks)) { + my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; + push(@$todo, [-1,$index,$cnt,@$block]); + } + + $addblock=[]; + $delblock=[]; + } + push(@$block,$seq2->[$_[1]]); + $cnt++ }; + + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + + + # now carry out the merging/splitting. Refer to elements relative from + # the end (with negative indices) as these offsets don't change before the instruction is executed + # cnt>0: merged small unchanged groups with previous changed blocks + # cnt==-1: split textual commands into components + foreach $instruction ( @$todo) { + ($last1,$last2,$cnt,@$block)=@$instruction ; + if ($cnt>=0) { + splice(@$seq1,$last1-$len1,1+$cnt,join("",$seq1->[$last1-$len1],@$block)) if $last1>=0; + splice(@$seq2,$last2-$len2,1+$cnt,join("",$seq2->[$last2-$len2],@$block)) if $last2>=0; + } else { + splice(@$seq1,$last1-$len1,1,@$block) if $last1>=0; + splice(@$seq2,$last2-$len2,1,@$block) if $last2>=0; + } + } + + if ($verbose) { + print STDERR "\n"; + print STDERR " $mattokcnt matching tokens in $matblkcnt blocks.\n"; + print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; + print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; + } +} + + +# extracttextblocks(\@blockindex) +# $blockindex has the following format +# [ [ token1, index1 ], [token2, index2],.. ] +# where index refers to the index in the original old or new word sequence +# Returns: reference to an array of the form +# [[ $index, $textblock, $cnt ], .. +# where $index index of block to be merged +# $textblock contains all the words to be merged with the word at $index (but does not contain this word) +# $cnt is length of block +# +# requires: iscmd +# +sub extracttextblocks { + my $block=shift; + my ($i,$token,$index); + my $textblock=[]; + my $last=-1; + my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' + my $retval=[]; + + for ($i=0;$i< scalar @$block;$i++) { + ($token,$index)=@{ $block->[$i] }; + # store pure text blocks + if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*)/o + && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) + && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { + # we have text or a command which can be treated as text + if ($last<0) { + # new pure-text block + $last=$index; + } else { + # add to pure-text block + push(@$textblock, $token); + } + } else { + # it is not text + if (scalar(@$textblock)) { + push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); + } + $textblock=[]; + $last=-1; + } + } + # finish processing a possibly unfinished block before returning + if (scalar(@$textblock)) { + push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); + } + return($retval) +} + + + +# extractcommands( \@blockindex ) +# $blockindex has the following format +# [ [ token1, index1 ], [token2, index2],.. ] +# where index refers to the index in the original old or new word sequence +# Returns: reference to an array of the form +# [ [ "\cmd1", index, "\cmd1[optarg]{arg1}{", "arg2" ,"} " ],.. +# where index is just taken from input array +# command must have a textual argument as last argument +# +# requires: iscmd +# +sub extractcommands { + my $block=shift; + my ($i,$token,$index,$cmd,$open,$mid,$closing); + my $retval=[]; + + for ($i=0;$i< scalar @$block;$i++) { + ($token,$index)=@{ $block->[$i] }; + # check if token is an alphanumeric command sequence with at least one non-optional argument + # \cmd[...]{...}{last argument} + # Capturing in the following results in these associations + # $1: \cmd[...]{...}{ + # $2: \cmd + # $3: last argument + # $4: } + trailing spaces + if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { + # push(@$retval,[ $2,$index,$1,$3,$4 ]); + ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; + $closing =~ s/\}/\\RIGHTBRACE/ ; + push(@$retval,[ $cmd,$index,$open,$mid,$closing ]); + } + } + return $retval; +} + +# iscmd($cmd,\@regexarray,\@regexexcl) checks +# return 1 if $cmd matches any of the patterns in the +# array $@regexarray, and none of the patterns in \@regexexcl, otherwise return 0 +sub iscmd { + my ($cmd,$regexar,$regexexcl)=@_; + my ($ret)=0; + foreach $pat ( @$regexar ) { + if ( $cmd =~ m/^${pat}$/ ) { + $ret=1 ; + last; + } + } + return 0 unless $ret; + foreach $pat ( @$regexexcl ) { + return 0 if ( $cmd =~ m/^${pat}$/ ); + } + return 1; +} + + +# pass2( \@seq1,\@seq2) +# Look for differences between seq1 and seq2. +# Mark begin and end of deleted and appended sequences with tags $DELOPEN and $DELCLOSE +# and $ADDOPEN and $ADDCLOSE, respectively, however exclude { } & and all comands, unless +# they match an element of the whitelist (SAFECMD) +# For words in TEXTCMD but not in SAFECMD, enclose interior with $ADDOPEN and $ADDCLOSE brackets +# Deleted comment lines are marked with %DIF < +# Added comment lines are marked with %DIF > +sub pass2 { + my $seq1 = shift ; + my $seq2 = shift ; + + my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); + my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); + + my $retval = []; + my $delhunk = []; + my $addhunk = []; + + my $discard = sub { $deltokcnt++; + push ( @$delhunk, $seq1->[$_[0]]) }; + + my $add = sub { $addtokcnt++; + push ( @$addhunk, $seq2->[$_[1]]) }; + + my $match = sub { $mattokcnt++; + if ( scalar @$delhunk ) { + $delblkcnt++; + # mark up changes, but comment out commands + push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk); + $delhunk = []; + } + if ( scalar @$addhunk ) { + $addblkcnt++; + # we mark up changes, but simply quote commands + push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk); + $addhunk = []; + } + push(@$retval,$seq2->[$_[1]]) }; + + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + # clear up unprocessed hunks + push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk) if scalar @$delhunk; + push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk) if scalar @$addhunk; + + + if ($verbose) { + print STDERR "\n"; + print STDERR " $mattokcnt matching tokens. \n"; + print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; + print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; + } + + return(@$retval); +} + +# marktags($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,\@block) +# returns ($openmark,$open,$block,$close,$closemark) if @block only contains no commands (except white-listed ones), +# braces, ampersands, or comments +# mark comments with $comment +# exclude all other exceptions from scope of open, close like this +# ($openmark, $open,...,$close, $opencmd,command, command,$closecmd, $open, ..., $close, $closemark) +# If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block +sub marktags { + my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; + my $word; + my (@argtext); + my $retval=[]; + my $noncomment=0; + my $cmd=-1; # -1 at beginning 0: last token written is a ordinary word + # 1: last token written is a command + # for keeping track whether we are just in a command sequence or in a word sequence + my $cmdcomment= ($opencmd =~ m/^%/); # Flag to indicate whether opencmd is a comment (i.e. if we intend to simply comment out changed commands) + my ($command,$commandword,$closingbracket) ; # temporary variables needed below to remember sub-pattern matches + +# split this block to flatten out sequences joined in pass1 + @$block=splitlatex(join "",@$block); + foreach (@$block) { + $word=$_; + if ( $word =~ s/^%/%$comment/ ) { + # a comment + if ($cmd==1) { + push (@$retval,$closecmd) ; + $cmd=-1; + } + push (@$retval,$word); + next; + } + if (! $noncomment) { + push (@$retval,$openmark); + $noncomment=1; + } + # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns + # also note that second pattern will match \\ + # Note: the second pattern should really be $word =~ /^\\(?!\()(\\|[\w*@]+)/, ie * replaced by + + # and then all commands \" \' etc declared safe. But as I don't have a complete list of one letter + # commands, and nobody has complained so far, I will eave this as is + if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()(\\|[\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { + # word is a command or other significant token (not in SAFECMDLIST) + ## same conditions as in subroutine extractcommand: + # check if token is an alphanumeric command sequence with at least one non-optional argument + # \cmd[...]{...}{last argument} + # Capturing in the following results in these associations + # $1: \cmd[...]{...}{ + # $2: cmd + # $3: last argument + # $4: } + trailing spaces + ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat6\})*\{)($pat6)(\}\s*)$/so ) + if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && (iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL)|| iscmd($2,\@MATHTEXTCMDLIST,\@MATHTEXTCMDEXCL)) + && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { + # Condition 1: word is a command? - if yes, $1,$2,.. will be set as above + # Condition 2: word is a text command - we mark up the interior of the word. There is a separate check for MATHTEXTCMDLIST + # because for $mathmarkup=WHOLE, the commands should not be split in pass1 (ie. math mode commands are not in + # TEXTCMDLIST, but the interior of MATHTEXT commands should be highlighted in both deleted and added blocks + # Condition 3: But if we are in a deleted block ($cmdcomment=1) and + # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) + # Because we do not want to disable this command + # here we do not use $opencmd and $closecmd($opencmd is empty) + if ($cmd==1) { + push (@$retval,$closecmd) ; + } elsif ($cmd==0) { + push (@$retval,$close) ; + } + $command=$1; $commandword=$2; $closingbracket=$4; + @argtext=splitlatex($3); # split textual argument into tokens + # and mark it up (but we do not need openmark and closemark) + # insert command with initial arguments, marked-up final argument, and closing bracket + if ( $cmdcomment && iscmd($commandword,\@CONTEXT1CMDLIST, \@CONTEXT1CMDEXCL) ) { + # context1cmd in a deleted environment; delete command itself but keep last argument, marked up + push (@$retval,$opencmd); + $command =~ s/\n/\n${opencmd}/sg ; # repeat opencmd at the beginning of each line + # argument, note that the additional comment character is included + # to suppress linebreak after opening parentheses, which is important + # for latexrevise + push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); + } elsif ( iscmd($commandword,,\@MATHTEXTCMDLIST, \@MATHTEXTCMDEXCL) ) { + # MATHBLOCK pseudo command: consider all commands safe, except & and \\ + # Keep these commands even in deleted blocks, hence set $opencmd and $closecmd (5th and 6th argument of marktags) to + # "" + local @SAFECMDLIST=(".*"); + local @SAFECMDEXCL=('\\','\\\\'); + push(@$retval,$command,marktags("","",$open,$close,"","",$comment,\@argtext)#@argtext + ,$closingbracket); + } else { + # normal textcmd or context1cmd in an added block + push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); + } + push (@$retval,$AUXCMD,"\n") if $cmdcomment ; + $cmd=-1 ; + } else { + # ordinary command + push (@$retval,$opencmd) if $cmd==-1 ; + push (@$retval,$close,$opencmd) if $cmd==0 ; + $word =~ s/\n/\n${opencmd}/sg if $cmdcomment ; # if opencmd is a comment, repeat this at the beginning of every line + push (@$retval,$word); + $cmd=1; + } + } else { + # just an ordinary word or word in SAFECMD + push (@$retval,$open) if $cmd==-1 ; + push (@$retval,$closecmd,$open) if $cmd==1 ; + push (@$retval,$word); + $cmd=0; + } + } + push (@$retval,$close) if $cmd==0; + push (@$retval,$closecmd) if $cmd==1; + + push (@$retval,$closemark) if ($noncomment); + return @$retval; +} + +# preprocess($string, ..) +# carry out the following pre-processing steps for all arguments: +# 1. Remove leading white-space +# Change \{ to \LEFTBRACE and \} to \RIGHTBRACE +# #. change begin and end commands within comments to BEGINDIF, ENDDIF +# so they don't disturb the pattern matching (if there are several \begin or \end in one line +# 2. mark all first empty line (in block of several) with \PAR tokens +# 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier +# 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) +# into \verb{hash} +# 5. Convert \begin{verbatim} some verbatim text \end{verbatim} into \verbatim{hash} +# 6. Convert _n into \SUBSCRIPTNB{n} and _{nnn} into \SUBSCRIPT{nn} +# 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} +# 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} +# b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} +# 9. Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv +# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH} +# into \MATHBLOCKmath{...} commands, where MATH/math is any valid math environment + +# 10. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. +# +# NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file +# names or labels but it does not matter because they are converted back in the postprocessing step +# Returns: leading white space removed in step 1 +sub preprocess { + my @leadin=() ; + for (@_) { + s/^(\s*)//s; + push(@leadin,$1); + # Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE + s/(?{$hstr}) && $string ne $hash->{$hstr}) { + warn "Repeated hash value for verbatim mode in spite of different content."; + $hstr="-$hstr"; + } + $hash->{$hstr}=$string; + return($hstr); +} + +#string=fromhash(\%hash,$fromstring) +# restores string value stored in hash +#string=fromhash(\%hash,$fromstring,$prependstring) +# additionally begins each line with prependstring +sub fromhash { + my ($hash,$hstr)=($_[0],$_[1]); + my $retstr=$hash->{$hstr}; + if ( $#_ >= 2) { + $retstr =~ s/^/$_[2]/mg; + } + return $retstr; +} + + +# postprocess($string, ..) +# carry out the following post-processing steps for all arguments: +# * Remove STOP token from the end +# * Replace \RIGHTBRACE by } +# * change citation commands within comments to protect from processing (using marker CITEDIF) +# 1. Check all deleted blocks: +# a.where a deleted block contains a matching \begin and +# \end environment (these will be disabled by a %DIFDELCMD statements), for selected environments enable +# these commands again (such that for example displayed math in a deleted equation +# is properly within math mode. For math mode environments replace numbered equation +# environments with their display only variety (so that equation numbers in new file and +# diff file are identical). Where the correct type of math environment cannot be determined +# use a place holder MATHMODE +# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement +# subtracting one from the respective counter to keep numbering consistent with new file +# Replace all MATHMODE environment commands by the correct environment to achieve matching +# pairs +# c. Convert MATHBLOCKmath commands to their uncounted numbers (e.g. convert equation -> displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL +# d. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# For added blocks: +# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# 2. If --block-math-markup option set: Convert \MATHBLOCKmath{..} commands back to environments +# +# Convert all PICTUREblock{..} commands back to the appropriate environments +# 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties +# within floats (currently recognised float environments: plate,table,figure +# plus starred varieties). +# 4. Remove empty %DIFDELCMD < lines +# 4. Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \] +# Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$ +# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn} +# 6. Convert \SUBSCRIPTNB{n} into _n and \SUBCRIPT{nn} into _{nnn} +# 7. Expand hashes of verb and verbatim environments +# 8. Convert '\PERCENTAGE ' back into '\%' +# 9.. remove all \PAR tokens +# 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always +# on a line by themselves, similarly for table environment +# 4, undo renaming of the \begin and \end in comments +# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\} +# +# Note have to manually synchronize substitution commands below and +# DIF.. command names in the header +sub postprocess { + my ($begin,$len,$cnt,$float,$delblock,$addblock); + # second level blocks + my ($begin2,$cnt2,$len2,$eqarrayblock,$mathblock); + + for (@_) { + + # change $'s in comments to something harmless + 1 while s/(%.*)\$/$1DOLLARDIF/mg ; + + # Remove final STOP token + s/ STOP$//; + # Replace \RIGHTBRACE by } + s/\\RIGHTBRACE/}/g; + + # change citation commands within comments to protect from processing + if ($CITECMD){ + 1 while s/(%.*)\\($CITECMD)/$1\\CITEDIF$2/m ; + } + # Check all deleted blocks: where a deleted block contains a matching \begin and + # \end environment (these will be disabled by a %DIFDELCMD statements), enable + # these commands again (such that for example displayed math in a deleted equation + # is properly within math mode. For math mode environments replace numbered equation + # environments with their display only variety (so that equation numbers in new file and + # diff file are identical + while ( m/\\DIFdelbegin.*?\\DIFdelend/sg ) { + $cnt=0; + $len=length($&); + $begin=pos($_) - $len; + $delblock=$&; + + + ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in + ### an error + # displayed math environments + if ($mathmarkup == FINE ) { + $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}.*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; + # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above + ### pre-0.42 obsolete version which did not work on eqnarray test $delblock=~ s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL + $delblock=~ s/\\MATHBLOCK($MATHENV)\{($pat6)\}/\\MATHBLOCK$MATHREPL\{$2\}/sg; + $delblock=~ s/\\MATHBLOCK($MATHARRENV)\{($pat6)\}/\\MATHBLOCK$MATHARRREPL\{$2\}/sg; + } + + +# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement +# subtracting one from the respective counter to keep numbering consistent with new file + $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + + +# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es + while ( $delblock =~ m/($math)(\s*)/sg ) { + $cnt2=0; + $len2=length($&); + $begin2=pos($delblock) - $len2; + $mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n"; + next unless $mathblock =~ m/\{$ARRENV\}/ ; + substr($delblock,$begin2,$len2)=$mathblock; + pos($delblock) = $begin2 + length($mathblock); + } + if ($CITE2CMD) { + $delblock=~s/($DELCMDOPEN\s*\\($CITE2CMD)(.*)$DELCMDCLOSE)/ + # Replacement code + {my ($aux,$all); + $aux=$all=$1; + $aux=~s#\n?($DELCMDOPEN|$DELCMDCLOSE)##g; + $all."$aux$AUXCMD\n";}/sge; + } + # or protect \cite commands with \mbox + if ($CITECMD) { + $delblock=~s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat6\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } +# splice in modified delblock + substr($_,$begin,$len)=$delblock; + pos = $begin + length($delblock); + } + # make the array modification in added blocks + while ( m/\\DIFaddbegin.*?\\DIFaddend/sg ) { + $cnt=0; + $len=length($&); + $begin=pos($_) - $len; + $addblock=$&; + while ( $addblock =~ m/($math)(\s*)/sg ) { + $cnt2=0; + $len2=length($&); + $begin2=pos($addblock) - $len2; + $mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n"; + next unless $mathblock =~ m/\{$ARRENV\}/ ; + substr($addblock,$begin2,$len2)=$mathblock; + pos($addblock) = $begin2 + length($mathblock); + } + if ($CITECMD) { + my $addblockbefore=$addblock; + $addblock=~ s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat2\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } +# splice in modified addblock + substr($_,$begin,$len)=$addblock; + pos = $begin + length($addblock); + } + + + ### old place for BEGINDIF, ENDDIF replacement + # change begin and end commands within comments such that they + # don't disturb the pattern matching (if there are several \begin or \end in one line + # this substitution is insufficient but that appears unlikely) + # This needs to be repeated here to also get rid of DIFdelcmd-protected environments + s/(%.*)\\begin\{(.*)$/$1\\BEGINDIF\{$2/mg ; + s/(%.*)\\end\{(.*)$/$1\\ENDDIF\{$2/mg ; + + # Replace MATHMODE environments from step 1a above by the correct Math environment + + # The next line is complicated. The negative look-ahead insertion makes sure that no \end{$MATHENV} (or other mathematical + # environments) are between the \begin{$MATHENV} and \end{MATHMODE} commands. This is necessary as the minimal matching + # is not globally minimal but only 'locally' (matching is beginning from the left side of the string) + if ( $mathmarkup == FINE ) { + 1 while s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}((?:.(?!(?:\\end{(?:(?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}|\\begin{MATHMODE})))*?)\\end{MATHMODE}/\\begin{$1}$2\\end{$1}/s; + 1 while s/\\begin{MATHMODE}((?:.(?!\\end{MATHMODE}))*?)\\end{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}/\\begin{$2}$1\\end{$2}/s; + # convert remaining \begin{MATHMODE} \end{MATHMODE} (and not containing & or \\ )into MATHREPL environments + s/\\begin{MATHMODE}((?:(.(?!(?[1])) { + $optargnew=$newhash{$cmd}->[1]; + } else { + $optargnew=""; + } + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + } else { + $optargold=""; + } + + if ( defined($oldhash{$cmd}) ) { + $argold=$oldhash{$cmd}->[2]; + } else { + $argold=""; + } + $argnew=$newhash{$cmd}->[2]; + $argdiff="{" . join("",bodydiff($argold,$argnew)) ."}"; + if ( length $optargnew ) { + $optargdiff="[".join("",bodydiff($optargold,$optargnew))."]" ; + $optargdiff =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g; + $optargdiff =~ s/\\DIFaddend /\\DIFaddendFL /g; + $optargdiff =~ s/\\DIFadd\{/\\DIFaddFL{/g; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + ### print STDERR "DEBUG s/\\Q$newhash{$cmd}->[0]\\E/\\$cmd$optargdiff$argdiff/s\n"; + # Note: \Q and \E force literal interpretation of what it between them but allow + # variable interpolation, such that e.g. \title matches just that and not TAB-itle + $$newpreambleref=~s/\Q$newhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s; + # replace this in old preamble if necessary + if ( defined($oldhash{$cmd}->[0])) { + $$oldpreambleref=~s/\Q$oldhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s ; + } + ### print STDERR "DEBUG NEW PRE ".$$newpreambleref."\n"; + } + + foreach $cmd ( keys %oldhash ) { + # if this has already been dealt with above can just skip + next if defined($newhash{$cmd}) ; + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + $optargdiff="[".join("",bodydiff($optargold,""))."]" ; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + $argdiff="{" . join("",bodydiff($argold,"")) ."}"; + $auxline = "\\$cmd$optargdiff$argdiff"; + $auxline =~s/$/$AUXCMD/sg; + push @auxlines,$auxline; + } + # add auxcmd comment to highlight added lines + return(@auxlines); +} + + + +# @diffs=linediff(\@seq1, \@seq2) +# mark up lines like this +#%DIF mm-mmdnn +#%< old deleted line(s) +#%DIF ------- +#%DIF mmann-nn +#new appended line %< +#%DIF ------- +# Future extension: mark change explicitly +# Assumes: traverse_sequence traverses deletions before insertions in changed sequences +# all line numbers relative to line 0 (first line of real file) +sub linediff { + my $seq1 = shift ; + my $seq2 = shift ; + + my $block = []; + my $retseq = []; + my @begin=('','',''); # dummy initialisation + my $instring ; + + my $discard = sub { @begin=('d',$_[0],$_[1]) unless scalar @$block ; + push(@$block, "%DIF < " . $seq1->[$_[0]]) }; + my $add = sub { if (! scalar @$block) { + @begin=('a',$_[0],$_[1]) ;} + elsif ( $begin[0] eq 'd' ) { + $begin[0]='c'; $begin[2]=$_[1]; + push(@$block, "%DIF -------") } + push(@$block, $seq2->[$_[1]] . " %DIF > " ) }; + my $match = sub { if ( scalar @$block ) { + if ( $begin[0] eq 'd' && $begin[1]!=$_[0]-1) { + $instring = sprintf "%%DIF %d-%dd%d",$begin[1],$_[0]-1,$begin[2]; } + elsif ( $begin[0] eq 'a' && $begin[2]!=$_[1]-1) { + $instring = sprintf "%%DIF %da%d-%d",$begin[1],$begin[2],$_[1]-1; } + elsif ( $begin[0] eq 'c' ) { + $instring = sprintf "%%DIF %sc%s", + ($begin[1]==$_[0]-1) ? "$begin[1]" : $begin[1]."-".($_[0]-1) , + ($begin[2]==$_[1]-1) ? "$begin[2]" : $begin[2]."-".($_[1]-1) ; } + else { + $instring = sprintf "%%DIF %d%s%d",$begin[1],$begin[0],$begin[2]; } + push @$retseq, $instring,@$block, "%DIF -------" ; + $block = []; + } + push @$retseq, $seq2->[$_[1]] + }; + # key function: remove multiple spaces (such that insertion or deletion of redundant white space is not reported) + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + push @$retseq, @$block if scalar @$block; + + return wantarray ? @$retseq : $retseq ; +} + + + +# init_regex_arr_data(\@array,"TOKEN INIT") +# scans DATA file handel for line "%% TOKEN INIT" line +# then appends each line not beginning with % into array (as a quoted regex) +sub init_regex_arr_data { + my ($arr,$token)=@_; + my ($copy); + while () { + if ( m/^%%BEGIN $token\s*$/ ) { + $copy=1; } + elsif ( m/^%%END $token\s*/ ) { + last; } + chomp; + push (@$arr,qr/^$_$/) if ( $copy && !/^%/ ) ; + } + seek DATA,0,0; # rewind DATA handle to file begin +} + + +# init_regex_arr_ext(\@array,$arg) +# fills array with regular expressions. +# if arg is a file name, then read in list of regular expressions from that file +# (one expression per line) +# Otherwise treat arg as a comma separated list of regular expressions +sub init_regex_arr_ext { + my ($arr,$arg)=@_; + my $regex; + if ( -f $ arg ) { + open(FILE,"$arg") or die ("Couldn't open $arg: $!"); + while () { + chomp; + next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; + push (@$arr,qr/^$_$/); + } + close(FILE); + } + else { + # assume it is a comma-separated list of reg-ex + foreach $regex (split(qr/(?=1) { + $reset=shift; + } + if ($reset) { + $lasttime=times(); + } + else { + $retval=times()-$lasttime; + $lasttime=$lasttime+$retval; + return($retval); + } +} + + +sub usage { + die <<"EOF"; +Usage: $0 [options] old.tex new.tex > diff.tex + +Compares two latex files and writes tex code to stdout, which has the same +format as new.tex but has all changes relative to old.tex marked up or commented. + +--type=markupstyle +-t markupstyle Add code to preamble for selected markup style + Available styles: UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE + CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR + [ Default: UNDERLINE ] + +--subtype=markstyle +-s markstyle Add code to preamble for selected style for bracketing + commands (e.g. to mark changes in margin) + Available styles: SAFE MARGINAL DVIPSCOL COLOR + [ Default: SAFE ] + +--floattype=markstyle +-f markstyle Add code to preamble for selected style which + replace standard marking and markup commands within floats + (e.g., marginal remarks cause an error within floats + so marginal marking can be disabled thus) + Available styles: FLOATSAFE IDENTICAL + [ Default: FLOATSAFE ] + +--encoding=enc +-e enc Specify encoding of old.tex and new.tex. Typical encodings are + ascii, utf8, latin1, latin9. A list of available encodings can be + obtained by executing + perl -MEncode -e 'print join ("\\n",Encode->encodings( ":all" )) ;' + [Default encoding is utf8 unless the first few lines of the preamble contain + an invocation "\\usepackage[..]{inputenc} in which case the + encoding chosen by this command is asssumed. Note that ASCII (standard + latex) is a subset of utf8] + +--preamble=file +-p file Insert file at end of preamble instead of auto-generating + preamble. The preamble must define the following commands + \\DIFaddbegin,\\DIFaddend,\\DIFadd{..}, + \\DIFdelbegin,\\DIFdelend,\\DIFdel{..}, + and varieties for use within floats + \\DIFaddbeginFL,\\DIFaddendFL,\\DIFaddFL{..}, + \\DIFdelbeginFL,\\DIFdelendFL,\\DIFdelFL{..} + (If this option is set -t, -s, and -f options + are ignored.) + +--exclude-safecmd=exclude-file +--exclude-safecmd="cmd1,cmd2,..." +-A exclude-file +--replace-safecmd=replace-file +--append-safecmd=append-file +--append-safecmd="cmd1,cmd2,..." +-a append-file Exclude from, replace or append to the list of regex + matching commands which are safe to use within the + scope of a \\DIFadd or \\DIFdel command. The file must contain + one Perl-RegEx per line (Comment lines beginning with # or % are + ignored). A literal comma within the comma-separated list must be + escaped thus "\\,", Note that the RegEx needs to match the whole of + the token, i.e., /^regex\$/ is implied and that the initial + "\\" of the command is not included. The --exclude-safecmd + and --append-safecmd options can be combined with the --replace-safecmd + option and can be used repeatedly to add cumulatively to the lists. + +--exclude-textcmd=exclude-file +--exclude-textcmd="cmd1,cmd2,..." +-X exclude-file +--replace-textcmd=replace-file +--append-textcmd=append-file +--append-textcmd="cmd1,cmd2,..." +-x append-file Exclude from, replace or append to the list of regex + matching commands whose last argument is text. See + entry for --exclude-safecmd directly above for further details. + +--replace-context1cmd=replace-file +--append-context1cmd=append-file +--append-context1cmd="cmd1,cmd2,..." + Replace or append to the list of regex matching commands + whose last argument is text but which require a particular + context to work, e.g. \\caption will only work within a figure + or table. These commands behave like text commands, except when + they occur in a deleted section, when they are disabled, but their + argument is shown as deleted text. + +--replace-context2cmd=replace-file +--append-context2cmd=append-file +--append-context2cmd="cmd1,cmd2,..." + As corresponding commands for context1. The only difference is that + context2 commands are completely disabled in deleted sections, including + their arguments. + + +--config var1=val1,var2=val2,... +-c var1=val1,.. Set configuration variables. +-c configfile Available variables: + MINWORDSBLOCK (integer) + FLOATENV (RegEx) + PICTUREENV (RegEx) + MATHENV (RegEx) + MATHREPL (String) + MATHARRENV (RegEx) + MATHARRREPL (String) + ARRENV (RegEx) + COUNTERCMD (RegEx) + This option can be repeated. + + +--packages=pkg1,pkg2,.. + Tell latexdiff that .tex file is processed with the packages in list + loaded. This is normally not necessary if the .tex file includes the + preamble, as the preamble is automatically scanned for \\usepackage commands. + Use of the --packages option disables automatic scanning, so if for any + reason package specific parsing needs to be switched off, use --packages=none. + The following packages trigger special behaviour: + endfloat hyperref amsmath + [ Default: scan the preamble for \\usepackage commands to determine + loaded packages.] + +--show-preamble Print generated or included preamble commands to stdout. + +--show-safecmd Print list of regex matching and excluding safe commands. + +--show-textcmd Print list of regex matching and excluding commands with text argument. + +--show-config Show values of configuration variables + +--show-all Show all of the above + + NB For all --show commands, no old.tex or new.tex file needs to be given, and no + differencing takes place. + +Other configuration options: + +--allow-spaces Allow spaces between bracketed or braced arguments to commands + [Default requires arguments to directly follow each other without + intervening spaces] + +--math-markup=level Determine granularity of markup in displayed math environments: + Possible values for level are (both numerical and text labels are acceptable): + off or 0: suppress markup for math environments. Deleted equations will not + appear in diff file. This mode can be used if all the other modes + cause invalid latex code. + whole or 1: Differencing on the level of whole equations. Even trivial changes + to equations cause the whole equation to be marked changed. This + mode can be used if processing in coarse or fine mode results in + invalid latex code. + coarse or 2: Detect changes within equations marked up with a coarse + granularity; changes in equation type (e.g.displaymath to equation) + appear as a change to the complete equation. This mode is recommended + for situations where the content and order of some equations are still + being changed. [Default] + fine or 3: Detect small change in equations and mark up and fine granularity. + This mode is most suitable, if only minor changes to equations are + expected, e.g. correction of typos. + +--disable-citation-markup Suppress citation markup in styles using ulem (UNDERLINE, + FONTSTRIKE, CULINECHBAR) +--enable-citation-markup Protect citation commands in changed sections with \\mbox command + [i.e. use default behaviour for ulem package for other packages] + +Miscelleneous options + +--label=label +-L label Sets the labels used to describe the old and new files. The first use + of this option sets the label describing the old file and the second + use of the option sets the label for the new file. + [Default: use the filename and modification dates for the label] + +--no-label Suppress inclusion of old and new file names as comment in output file + +--visble-label Include old and new filenames (or labels set with --label option) as + visible output + +--flatten Replace \\input and \\include commands within body by the content + of the files in their argument. If \\includeonly is present in the + preamble, only those files are expanded into the document. However, + no recursion is done, i.e. \\input and \\include commands within + included sections are not expanded. The included files are assumed to + be located in the same directories as the old and new master files, + respectively, making it possible to organise files into old and new directories. + --flatten is applied recursively, so inputted files can contain further + \\input statements. + +--help +-h Show this help text. + +--ignore-warnings Suppress warnings about inconsistencies in length between input + and parsed strings and missing characters. + +--verbose +-V Output various status information to stderr during processing. + Default is to work silently. + +--version Show version number. + +For further information, consult http://latexdiff.berlios.de +EOF +} + +=head1 NAME + +latexdiff - determine and markup differences between two latex files + +=head1 SYNOPSIS + +B [ B ] F F > F + +=head1 DESCRIPTION + +Briefly, I is a utility program to aid in the management of +revisions of latex documents. It compares two valid latex files, here +called C and C, finds significant differences +between them (i.e., ignoring the number of white spaces and position +of line breaks), and adds special commands to highlight the +differences. Where visual highlighting is not possible, e.g. for changes +in the formatting, the differences are +nevertheless marked up in the source. + +The program treats the preamble differently from the main document. +Differences between the preambles are found using line-based +differencing (similarly to the Unix diff command, but ignoring white +spaces). A comment, "S>>" is appended to each added line, i.e. a +line present in C but not in C. Discarded lines + are deactivated by prepending "S>>". Changed blocks are preceded by +comment lines giving information about line numbers in the original files. Where there are insignificant +differences, the resulting file C will be similar to +C. At the end of the preamble, the definitions for I markup commands are inserted. +In differencing the main body of the text, I attempts to +satisfy the following guidelines (in order of priority): + +=over 3 + +=item 1 + +If both C and C are valid LaTeX, then the resulting +C should also be valid LateX. (NB If a few plain TeX commands +are used within C or C then C is not +guaranteed to work but usually will). + +=item 2 + +Significant differences are determined on the level of +individual words. All significant differences, including differences +between comments should be clearly marked in the resulting source code +C. + +=item 3 + +If a changed passage contains text or text-producing commands, then +running C through LateX should produce output where added +and discarded passages are highlighted. + +=item 4 + +Where there are insignificant differences, e.g. in the positioning of +line breaks, C should follow the formatting of C + +=back + +For differencing the same algorithm as I is used but words +instead of lines are compared. An attempt is made to recognize +blocks which are completely changed such that they can be marked up as a unit. +Comments are differenced line by line +but the number of spaces within comments is ignored. Commands including +all their arguments are generally compared as one unit, i.e., no mark-up +is inserted into the arguments of commands. However, for a selected +number of commands (for example, C<\caption> and all sectioning +commands) the last argument is known to be text. This text is +split into words and differenced just as ordinary text (use options to +show and change the list of text commands, see below). As the +algorithm has no detailed knowledge of LaTeX, it assumes all pairs of +curly braces immediately following a command (i.e. a sequence of +letters beginning with a backslash) are arguments for that command. +As a restriction to condition 1 above it is thus necessary to surround +all arguments with curly braces, and to not insert +extraneous spaces. For example, write + + \section{\textem{This is an emphasized section title}} + +and not + + \section {\textem{This is an emphasized section title}} + +or + + \section\textem{This is an emphasized section title} + +even though all varieties are the same to LaTeX (but see +B<--allow-spaces> option which allows the second variety). + +For environments whose content does not conform to standard LaTeX or +where graphical markup does not make sense all markup commands can be +removed by setting the PICTUREENV configuration variable, set by +default to C and C environments; see B<--config> +option). The latter environment (C) can be used to +protect parts of the latex file where the markup results in illegal +markup. You have to surround the offending passage in both the old and +new file by C<\begin{DIFnomarkup}> and C<\end{DIFnomarkup}>. You must +define the environment in the preambles of both old and new +documents. I prefer to define it as a null-environment, + +C<\newenvironment{DIFnomarkup}{}{}> + +but the choice is yours. Any markup within the environment will be +removed, and generally everything within the environment will just be +taken from the new file. + +It is also possible to difference files which do not have a preamble. + In this case, the file is processed in the main document +mode, but the definitions of the markup commands are not inserted. + +All markup commands inserted by I begin with "C<\DIF>". Added +blocks containing words, commands or comments which are in C +but not in C are marked by C<\DIFaddbegin> and C<\DIFaddend>. +Discarded blocks are marked by C<\DIFdelbegin> and C<\DIFdelend>. +Within added blocks all text is highlighted with C<\DIFadd> like this: +C<\DIFadd{Added text block}> +Selected `safe' commands can be contained in these text blocks as well +(use options to show and change the list of safe commands, see below). +All other commands as well as braces "{" and "}" are never put within +the scope of C<\DIFadd>. Added comments are marked by prepending +"S >>". + +Within deleted blocks text is highlighted with C<\DIFdel>. Deleted +comments are marked by prepending "S >>". Non-safe command +and curly braces within deleted blocks are commented out with +"S >>". + + + +=head1 OPTIONS + +=head2 Preamble + +The following options determine the visual markup style by adding the appropriate +command definitions to the preamble. See the end of this section for a description of +available styles. + +=over 4 + +=item B<--type=markupstyle> or +B<-t markupstyle> + +Add code to preamble for selected markup style. This option defines +C<\DIFadd> and C<\DIFdel> commands. +Available styles: + +C + +[ Default: C ] + +=item B<--subtype=markstyle> or +B<-s markstyle> + +Add code to preamble for selected style for bracketing +commands (e.g. to mark changes in margin). This option defines +C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. +Available styles: C + +[ Default: C ] + +=item B<--floattype=markstyle> or +B<-f markstyle> + +Add code to preamble for selected style which +replace standard marking and markup commands within floats +(e.g., marginal remarks cause an error within floats +so marginal marking can be disabled thus). This option defines all +C<\DIF...FL> commands. +Available styles: C + +[ Default: C ] + +=item B<--encoding=enc> or +B<-e enc> + +Specify encoding of old.tex and new.tex. Typical encodings are +C, C, C, C. A list of available encodings can be +obtained by executing + +Cencodings( ":all" )) ;' > + +[Default encoding is utf8 unless the first few lines of the preamble contain +an invocation C<\usepackage[..]{inputenc}> in which case the +encoding chosen by this command is asssumed. Note that ASCII (standard +latex) is a subset of utf8] + +=item B<--preamble=file> or +B<-p file> + +Insert file at end of preamble instead of generating +preamble. The preamble must define the following commands +C<\DIFaddbegin, \DIFaddend, \DIFadd{..}, +\DIFdelbegin,\DIFdelend,\DIFdel{..},> +and varieties for use within floats +C<\DIFaddbeginFL, \DIFaddendFL, \DIFaddFL{..}, +\DIFdelbeginFL, \DIFdelendFL, \DIFdelFL{..}> +(If this option is set B<-t>, B<-s>, and B<-f> options +are ignored.) + +=item B<--packages=pkg1,pkg2,..> + +Tell latexdiff that .tex file is processed with the packages in list +loaded. This is normally not necessary if the .tex file includes the +preamble, as the preamble is automatically scanned for C<\usepackage> commands. +Use of the B<--packages> option disables automatic scanning, so if for any +reason package specific parsing needs to be switched off, use B<--packages=none>. +The following packages trigger special behaviour: + +=over 8 + +=item C + +Configuration variable amsmath is set to C (Default: C) + +=item C + +Ensure that C<\begin{figure}> and C<\end{figure}> always appear by themselves on a line. + +=item C + +Change name of C<\DIFadd> and C<\DIFdel> commands to C<\DIFaddtex> and C<\DIFdeltex> and +define new C<\DIFadd> and C<\DIFdel> commands, which provide a wrapper for these commands, +using them for the text but not for the link defining command (where any markup would cause +errors). + +=back + +[ Default: scan the preamble for C<\\usepackage> commands to determine + loaded packages.] + + + +=item B<--show-preamble> + +Print generated or included preamble commands to stdout. + +=back + +=head2 Configuration + +=over 4 + +=item B<--exclude-safecmd=exclude-file> or +B<-A exclude-file> or B<--exclude-safecmd="cmd1,cmd2,..."> + +=item B<--replace-safecmd=replace-file> + +=item B<--append-safecmd=append-file> or +B<-a append-file> or B<--append-safecmd="cmd1,cmd2,..."> + +Exclude from, replace or append to the list of regular expressions (RegEx) +matching commands which are safe to use within the +scope of a C<\DIFadd> or C<\DIFdel> command. The file must contain +one Perl-RegEx per line (Comment lines beginning with # or % are +ignored). Note that the RegEx needs to match the whole of +the token, i.e., /^regex$/ is implied and that the initial +"\" of the command is not included. +The B<--exclude-safecmd> and B<--append-safecmd> options can be combined with the -B<--replace-safecmd> +option and can be used repeatedly to add cumulatively to the lists. + B<--exclude-safecmd> +and B<--append-safecmd> can also take a comma separated list as input. If a +comma for one of the regex is required, escape it thus "\,". In most cases it +will be necessary to protect the comma-separated list from the shell by putting +it in quotation marks. + +=item B<--exclude-textcmd=exclude-file> or +B<-X exclude-file> or B<--exclude-textcmd="cmd1,cmd2,..."> + +=item B<--replace-textcmd=replace-file> + +=item B<--append-textcmd=append-file> or +B<-x append-file> or B<--append-textcmd="cmd1,cmd2,..."> + +Exclude from, replace or append to the list of regular expressions +matching commands whose last argument is text. See +entry for B<--exclude-safecmd> directly above for further details. + + +=item B<--replace-context1cmd=replace-file> + +=item B<--append-context1cmd=append-file> or +=item B<--append-context1cmd="cmd1,cmd2,..."> + +Replace or append to the list of regex matching commands +whose last argument is text but which require a particular +context to work, e.g. \caption will only work within a figure +or table. These commands behave like text commands, except when +they occur in a deleted section, when they are disabled, but their +argument is shown as deleted text. + +=item B<--replace-context2cmd=replace-file> + +=item B<--append-context2cmd=append-file> or +=item B<--append-context2cmd="cmd1,cmd2,..."> +As corresponding commands for context1. The only difference is that +context2 commands are completely disabled in deleted sections, including +their arguments. + + + +=item B<--config var1=val1,var2=val2,...> or B<-c var1=val1,..> + +=item B<-c configfile> + +Set configuration variables. The option can be repeated to set different +variables (as an alternative to the comma-separated list). +Available variables (see below for further explanations): + +C (integer) + +C (RegEx) + +C (RegEx) + +C (RegEx) + +C (String) + +C (RegEx) + +C (String) + +C (RegEx) + +C (RegEx) + +=item B<--show-safecmd> + +Print list of RegEx matching and excluding safe commands. + +=item B<--show-textcmd> + +Print list of RegEx matching and excluding commands with text argument. + +=item B<--show-config> + +Show values of configuration variables. + +=item B<--show-all> + +Combine all --show commands. + +NB For all --show commands, no C or C file needs to be specified, and no +differencing takes place. + +=back + +=head2 Other configuration options: + +=over 4 + +=item B<--allow-spaces> + +Allow spaces between bracketed or braced arguments to commands. Note +that this option might have undesirable side effects (unrelated scope +might get lumpeded with preceding commands) so should only be used if the +default produces erroneous results. (Default requires arguments to +directly follow each other without intervening spaces). + +=item B<--math-markup=level> + +Determine granularity of markup in displayed math environments: +Possible values for level are (both numerical and text labels are acceptable): + +C or C<0>: suppress markup for math environments. Deleted equations will not +appear in diff file. This mode can be used if all the other modes +cause invalid latex code. + +C or C<1>: Differencing on the level of whole equations. Even trivial changes +to equations cause the whole equation to be marked changed. This +mode can be used if processing in coarse or fine mode results in +invalid latex code. + +C or C<2>: Detect changes within equations marked up with a coarse +granularity; changes in equation type (e.g.displaymath to equation) +appear as a change to the complete equation. This mode is recommended +for situations where the content and order of some equations are still +being changed. [Default] + +C or C<3>: Detect small change in equations and mark up at fine granularity. +This mode is most suitable, if only minor changes to equations are +expected, e.g. correction of typos. + +=item B<--disable-citation-markup> + +Suppress citation markup in styles using ulem (UNDERLINE, +FONTSTRIKE, CULINECHBAR) + +=item B<--enable-citation-markup> + +Protect citation commands in changed sections with \\mbox command [i.e. use default behaviour for ulem package for other packages] + +=back + +=head2 Miscellaneous + +=over 4 +=item B<--verbose> or B<-V> + +Output various status information to stderr during processing. +Default is to work silently. + +=item B<--driver=type> + +Choose driver for changebar package (only relevant for styles using + changebar: CCHANGEBAR CFONTCHBAR CULINECHBAR CHANGEBAR). Possible +drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops + [Default: dvips] + +=item B<--ignore-warnings> + +Suppress warnings about inconsistencies in length between input and +parsed strings and missing characters. These warning messages are +often related to non-standard latex or latex constructions with a +syntax unknown to C but the resulting difference argument +is often fully functional anyway, particularly if the non-standard +latex only occurs in parts of the text which have not changed. + +=item B<--label=label> or +B<-L label> + +Sets the labels used to describe the old and new files. The first use +of this option sets the label describing the old file and the second +use of the option sets the label for the new file, i.e. set both +labels like this C<-L labelold -L labelnew>. +[Default: use the filename and modification dates for the label] + +=item B<--no-label> + +Suppress inclusion of old and new file names as comment in output file + +=item B<--visble-label> + +Include old and new filenames (or labels set with --label option) as +visible output. + +=item B<--flatten> + +Replace C<\input> and C<\include> commands within body by the content +of the files in their argument. If C<\includeonly> is present in the +preamble, only those files are expanded into the document. However, +no recursion is done, i.e. C<\input> and C<\include> commands within +included sections are not expanded. The included files are assumed to + be located in the same directories as the old and new master files, +respectively, making it possible to organise files into old and new directories. +--flatten is applied recursively, so inputted files can contain further +C<\input> statements. + +Use of this option might result in prohibitive processing times for +larger documents, and the resulting difference document +no longer reflects the structure of the input documents. + +=item B<--help> or +B<-h> + +Show help text + +=item B<--version> + +Show version number + +=back + + + +=head2 Predefined styles + +=head2 Major types + +The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands C<\DIFadd{...}> and C<\DIFdel{...}> . + +=over 10 + +=item C + +Added text is wavy-underlined and blue, discarded text is struck out and red +(Requires color and ulem packages). Overstriking does not work in displayed math equations such that deleted parts of equation are underlined, not struck out (this is a shortcoming inherent to the ulem package). + +=item C + +Added text is blue and set in sans-serif, and a red footnote is created for each discarded +piece of text. (Requires color package) + +=item C + +Like C but without the use of color. + +=item C + +Added text is blue and set in sans-serif, and discarded text is red and very small size. + +=item C + +Added tex is set in sans-serif, discarded text small and struck out + +=item C + +Added text is blue, and discarded text is red. Additionally, the changed text is marked with a bar in the margin (Requires color and changebar packages). + +=item C + +Like C but with additional changebars (Requires color and changebar packages). + +=item C + +Like C but with additional changebars (Requires color, ulem and changebar packages). + +=item C + +No mark up of text, but mark margins with changebars (Requires changebar package). + +=item C + +No visible markup (but generic markup commands will still be inserted. + +=back + +=head2 Subtypes + +The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: C<\DIFaddbegin, \DIFaddend, \DIFdelbegin, \DIFdelend>) + +=over 10 + +=item C + +No additional markup (Recommended choice) + +=item C + +Mark beginning and end of changed blocks with symbols in the margin nearby (using +the standard C<\marginpar> command - note that this sometimes moves somewhat +from the intended position. + +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. +(It is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete, for example +with citation commands). + +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. Note +that C only works with the dvips converter, e.g. not pdflatex. +(it is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete). + +=back + +=head2 Float Types + +Some of the markup used in the main text might cause problems when used within +floats (e.g. figures or tables). For this reason alternative versions of all +markup commands are used within floats. The float type defines these alternative commands. + +=over 10 + +=item C + +Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is C as C<\marginpar> does not work properly within floats. + +=item C + +Mark additions the same way as in the main text. Deleted environments are marked by angular brackets \[ and \] and the deleted text is set in scriptscript size. This float type should always be used with the C and C markup types as the \footnote command does not work properly in floating environments. + +=item C + +Make no difference between the main text and floats. + +=back + + +=head2 Configuration Variables + +=over 10 + +=item C + +Minimum number of tokens required to form an independent block. This value is +used in the algorithm to detect changes of complete blocks by merging identical text parts of less than C to the preceding added and discarded parts. + +[ Default: 3 ] + +=item C + +Environments whose name matches the regular expression in C are +considered floats. Within these environments, the I markup commands +are replaced by their FL variaties. + +[ Default: S >] + +=item C + +Within environments whose name matches the regular expression in C +all latexdiff markup is removed (in pathologic cases this might lead to + inconsistent markup but this situation should be rare). + +[ Default: S >] + +=item C,C + +If both \begin and \end for a math environment (environment name matching C +or \[ and \]) +are within the same deleted block, they are replaced by a \begin and \end commands for C +rather than being commented out. + +[ Default: C=S >, C=S >] + +=item C,C + +as C,C but for equation arrays + +[ Default: C=S >, C=S >] + +=item C + +If a match to C is found within an inline math environment within a deleted or added block, then the inlined math +is surrounded by C<\mbox{>...C<}>. This is necessary as underlining does not work within inlined array environments. + +[ Default: C=S > + +=item C + +If a command in a deleted block which is also in the textcmd list matches C then an +additional command C<\addtocounter{>FC<}{-1}>, where F is the matching command, is appended in the diff file such that the numbering in the diff file remains synchronized with the +numbering in the new file. + +[ Default: C=C<(?:footnote|part|section|subsection> ... + +C<|subsubsection|paragraph|subparagraph)> ] + +=back + +=head1 COMMON PROBLEMS + +=over 10 + +=item Citations result in overfull boxes + +There is an incompatibility between the C package, which C uses for underlining and striking out in the UNDERLINE style, +the default style. In order to be able to mark up citations properly, they are placed with an C<\mbox> command in post-processing. As mboxes +cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities: + +1. Use C or C subtype markup (option C<-s COLOR>): If this markup is chosen, then changed citations are no longer marked up +with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color. + +2. Choose option C<--disable-citation-markup> which turns off the marking up of citations: deleted citations are no longer shown, and +added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older) + +=item Changes in complicated mathematical equations result in latex processing errors + +Try options C<--math-markup=whole>. If even that fails, you can turn off mark up for equations with C<--math-markup=off>. + +=back + +=head1 BUGS + +Option allow-spaces not implemented entirely consistently. It breaks +the rules that number and type of white space does not matter, as +different numbers of inter-argument spaces are treated as significant. + +Please submit bug reports on the latexdiff project page I, +send them to user discussion list C (prior subscription +to list required, also on project webpage) +or send them to I. Include the serial number of I +(from comments at the top of the source or use B<--version>). If you come across latex +files that are error-free and conform to the specifications set out +above, and whose differencing still does not result in error-free +latex, please send me those files, ideally edited to only contain the +offending passage as long as that still reproduces the problem. If your +file relies on non-standard class files, you must include those. I will not +look at examples where I have trouble to latex the original files. + +=head1 SEE ALSO + +L, L + +=head1 PORTABILITY + +I does not make use of external commands and thus should run +on any platform supporting Perl 5.6 or higher. If files with encodings +other than ASCII or UTF-8 are processed, Perl 5.8 or higher is required. + +The standard version of I requires installation of the Perl package +C (available from I - +I) but a stand-alone +version, I, which has this package inlined, is available, too. +I requires the I command to be present. + +=head1 AUTHOR + +Version 1.0.2 +Copyright (C) 2004-2012 Frederik Tilmann + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License Version 3 + +Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner, +T. Connors, Sebastian Gouezel and many others. +Thanks to the many people who send in bug reports, feature suggestions, and other feedback. + +=cut + +__END__ +%%BEGIN SAFE COMMANDS +% Regex matching commands which can safely be in the +% argument of a \DIFadd or \DIFdel command (leave out the \) +arabic +dashbox +emph +fbox +framebox +hspace +math.* +makebox +mbox +pageref +ref +symbol +raisebox +rule +text.* +shortstack +usebox +dag +ddag +copyright +pounds +S +P +oe +OE +ae +AE +aa +AA +o +O +l +L +frac +ss +sqrt +ldots +cdots +vdots +ddots +alpha +beta +gamma +delta +epsilon +varepsilon +zeta +eta +theta +vartheta +iota +kappa +lambda +mu +nu +xi +pi +varpi +rho +varrho +sigma +varsigma +tau +upsilon +phi +varphi +chi +psi +omega +Gamma +Delta +Theta +Lambda +Xi +Pi +Sigma +Upsilon +Phi +Psi +Omega +ps +mp +times +div +ast +star +circ +bullet +cdot +cap +cup +uplus +sqcap +vee +wedge +setminus +wr +diamond +(?:big)?triangle.* +lhd +rhd +unlhd +unrhd +oplus +ominus +otimes +oslash +odot +bigcirc +d?dagger +amalg +leq +prec +preceq +ll +(?:sq)?su[bp]set(?:eq)? +in +vdash +geq +succ(?:eq)? +gg +ni +dashv +equiv +sim(?:eq)? +asymp +approx +cong +neq +doteq +propto +models +perp +mid +parallel +bowtie +Join +smile +frown +.*arrow +(?:long)?mapsto +.*harpoon.* +leadsto +aleph +hbar +imath +jmath +ell +wp +Re +Im +mho +prime +emptyset +nabla +surd +top +bot +angle +forall +exists +neg +flat +natural +sharp +backslash +partial +infty +Box +Diamond +triangle +clubsuit +diamondsuit +heartsuit +spadesuit +sum +prod +coprod +int +oint +big(?:sq)?c[au]p +bigvee +bigwedge +bigodot +bigotimes +bigoplus +biguplus +(?:arc)?(?:cos|sin|tan|cot)h? +csc +arg +deg +det +dim +exp +gcd +hom +inf +ker +lg +lim +liminf +limsup +ln +log +max +min +Pr +sec +sup +(SUPER|SUB)SCRIPTNB +(SUPER|SUB)SCRIPT +%%END SAFE COMMANDS + +%%BEGIN TEXT COMMANDS +% Regex matching commands with a text argument (leave out the \) +addcontents.* +cc +closing +chapter +dashbox +emph +encl +fbox +framebox +footnote +footnotetext +framebox +part +(sub){0,2}section\*? +(sub)?paragraph\*? +makebox +mbox +opening +parbox +raisebox +savebox +sbox +shortstack +signature +text.* +value +underline +sqrt +(SUPER|SUB)SCRIPT +%%END TEXT COMMANDS + +%%BEGIN CONTEXT1 COMMANDS +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text +caption +%%END CONTEXT1 COMMANDS + +%%BEGIN CONTEXT2 COMMANDS +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text +title +author +date +institute +%%END CONTEXT2 COMMANDS + + +%% TYPES (Commands for highlighting changed blocks) + +%DIF UNDERLINE PREAMBLE +\RequirePackage[normalem]{ulem} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}} +\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}} +%DIF END UNDERLINE PREAMBLE + +%DIF CTRADITIONAL PREAMBLE +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\RequirePackage[stable]{footmisc} +\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} +\providecommand{\DIFdel}[1]{{\protect\color{red} [..\footnote{removed: #1} ]}} +%DIF END CTRADITIONAL PREAMBLE + +%DIF TRADITIONAL PREAMBLE +\RequirePackage[stable]{footmisc} +\providecommand{\DIFadd}[1]{{\sf #1}} +\providecommand{\DIFdel}[1]{{[..\footnote{removed: #1} ]}} +%DIF END TRADITIONAL PREAMBLE + +%DIF CFONT PREAMBLE +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} +\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}} +%DIF END CFONT PREAMBLE + +%DIF FONTSTRIKE PREAMBLE +\RequirePackage[normalem]{ulem} +\providecommand{\DIFadd}[1]{{\sf #1}} +\providecommand{\DIFdel}[1]{{\footnotesize \sout{#1}}} +%DIF END FONTSTRIKE PREAMBLE + +%DIF CCHANGEBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}#1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}#1}\protect\cbdelete} +%DIF END CCHANGEBAR PREAMBLE + +%DIF CFONTCHBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\sf #1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\scriptsize #1}\protect\cbdelete} +%DIF END CFONTCHBAR PREAMBLE + +%DIF CULINECHBAR PREAMBLE +\RequirePackage[normalem]{ulem} +\RequirePackage[dvips]{changebar} +\RequirePackage{color} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\uwave{#1}}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\sout{#1}}\protect\cbdelete} +%DIF END CULINECHBAR PREAMBLE + +%DIF CHANGEBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\providecommand{\DIFadd}[1]{\protect\cbstart{#1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete} +%DIF END CHANGEBAR PREAMBLE + +%DIF INVISIBLE PREAMBLE +\providecommand{\DIFadd}[1]{#1} +\providecommand{\DIFdel}[1]{} +%DIF END INVISIBLE PREAMBLE + + +%% SUBTYPES (Markers for beginning and end of changed blocks) + +%DIF SAFE PREAMBLE +\providecommand{\DIFaddbegin}{} +\providecommand{\DIFaddend}{} +\providecommand{\DIFdelbegin}{} +\providecommand{\DIFdelend}{} +%DIF END SAFE PREAMBLE + +%DIF MARGIN PREAMBLE +\providecommand{\DIFaddbegin}{\protect\marginpar{a[}} +\providecommand{\DIFaddend}{\protect\marginpar{]}} +\providecommand{\DIFdelbegin}{\protect\marginpar{d[}} +\providecommand{\DIFdelend}{\protect\marginpar{]}} +%DIF END BRACKET PREAMBLE + +%DIF DVIPSCOL PREAMBLE +%Note: only works with dvips converter +\RequirePackage{color} +\RequirePackage{dvipscol} +\providecommand{\DIFaddbegin}{\protect\nogroupcolor{blue}} +\providecommand{\DIFaddend}{\protect\nogroupcolor{black}} +\providecommand{\DIFdelbegin}{\protect\nogroupcolor{red}} +\providecommand{\DIFdelend}{\protect\nogroupcolor{black}} +%DIF END DVIPSCOL PREAMBLE + +%DIF COLOR PREAMBLE +\RequirePackage{color} +\providecommand{\DIFaddbegin}{\protect\color{blue}} +\providecommand{\DIFaddend}{\protect\color{black}} +\providecommand{\DIFdelbegin}{\protect\color{red}} +\providecommand{\DIFdelend}{\protect\color{black}} +%DIF END COLOR PREAMBLE + + +%% FLOAT TYPES + +%DIF FLOATSAFE PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} +\providecommand{\DIFaddbeginFL}{} +\providecommand{\DIFaddendFL}{} +\providecommand{\DIFdelbeginFL}{} +\providecommand{\DIFdelendFL}{} +%DIF END FLOATSAFE PREAMBLE + +%DIF IDENTICAL PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} +\providecommand{\DIFaddbeginFL}{\DIFaddbegin} +\providecommand{\DIFaddendFL}{\DIFaddend} +\providecommand{\DIFdelbeginFL}{\DIFdelbegin} +\providecommand{\DIFdelendFL}{\DIFdelend} +%DIF END IDENTICAL PREAMBLE + +%DIF TRADITIONALSAFE PREAMBLE +% procidecommand color to make this work for TRADITIONAL and CTRADITIONAL +\providecommand{\color}[1]{} +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdel}[1]{{\protect\color{red}[..{\scriptsize {removed: #1}} ]}} +\providecommand{\DIFaddbeginFL}{} +\providecommand{\DIFaddendFL}{} +\providecommand{\DIFdelbeginFL}{} +\providecommand{\DIFdelendFL}{} +%DIF END FLOATSAFE PREAMBLE + +%% SPECIAL PACKAGE PREAMBLE COMMANDS + +% Standard \DIFadd and \DIFdel are redefined as \DIFaddtex and \DIFdeltex +% when hyperref package is included. +%DIF HYPERREF PREAMBLE +\providecommand{\DIFadd}[1]{\texorpdfstring{\DIFaddtex{#1}}{#1}} +\providecommand{\DIFdel}[1]{\texorpdfstring{\DIFdeltex{#1}}{}} +%DIF END HYPERREF PACKAGE diff --git a/Master/texmf-dist/doc/support/latexdiff/latexdiff-fast b/Master/texmf-dist/doc/support/latexdiff/latexdiff-fast new file mode 100755 index 00000000000..310ecc4daef --- /dev/null +++ b/Master/texmf-dist/doc/support/latexdiff/latexdiff-fast @@ -0,0 +1,3961 @@ +#!/usr/bin/env perl +##!/usr/bin/perl -w +# latexdiff - differences two latex files on the word level +# and produces a latex file with the differences marked up. +# +# Copyright (C) 2004-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) +# +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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 . +# +# Detailed usage information at the end of the file +# +# Version 1.0.1 - treat \big,\bigg etc. equivalently to \left and +# \right - include starred version in MATHENV - apply +# - flatten recursively and --flatten expansion is now +# aware of comments (thanks to Tim Connors for patch) +# - Change to post-processing for more reliability for +# deleted math environments +# - On linux systems, recognise and remove DOS style newlines +# - Provide markup for some special preamble commands (\title, +# \author,\date, +# - configurable by setting context2cmd +# - for styles using ulem package, remove \emph and \text.. from list of +# safe commands in order to allow linebreaks within the +# highlighted sections. +# - for ulem style, now show citations by enclosing them in \mbox commands. +# This unfortunately implies linebreaks within citations no longer function, +# so this functionality can be turned off (Option --disable-citation-markup). +# With --enable-citation-markup, the mbox markup is forced for other styles) +# - new substyle COLOR. This is particularly useful for marking up citations +# and some special post-processing is implemented to retain cite +# commands in deleted blocks. +# - four different levels of math-markup +# - Option --driver for choosing driver for modes employing changebar package +# - accept \\* as valid command (and other commands of form \.*). Also accept +# \ (backslashed newline) +# - some typo fixes, include commands defined in preamble as safe commands +# (Sebastian Gouezel) +# - include compared filenames as comments as line 2 and 3 of +# the preamble (can be modified with option --label, and suppressed with +# --no-label), option --visible-label to show files in generated pdf or dvi +# at the beginning of main document +# +# Version 0.5 A number of minor improvements based on feedback +# Deleted blocks are now shown before added blocks +# Package specific processing +# +# Version 0.43 unreleased typo in list of styles at the end +# Add protect to all \cbstart, \cbend commands +# More robust substitution of deleted math commands +# +# Version 0.42 November 06 Bug fixes only +# +# Version 0.4 March 06 option for fast differencing using UNIX diff command, several minor bug fixes (\par bug, improved highlighting of textcmds) +# +# Version 0.3 August 05 improved parsing of displayed math, --allow-spaces +# option, several minor bug fixes +# +# Version 0.25 October 04 Fix bug with deleted equations, add math mode commands to safecmd, add | to allowed interpunctuation signs +# Version 0.2 September 04 extension to utf-8 and variable encodings +# Version 0.1 August 04 First public release + +# Inserted block for differenceing +# use Algorithm::Diff qw(traverse_sequences); +# in standard version +# The following BEGIN block contains a verbatim copy of +# Ned Konz' Algorithm::Diff package version 1.15 except +# that subroutine _longestCommonSubsequence has been replace by +# a routine which internally uses the UNIX diff command for +# the differencing rather than the Perl routines if the +# length of the sequences exceeds some threshold. +# Also, all POD documentation has been stripped out. +# +# (the distribution on which this modification is based is available +# from http://search.cpan.org/~nedkonz/Algorithm-Diff-1.15 +# the most recent version can be found via http://search.cpan.org/search?module=Algorithm::Diff ) +# Please note that the LICENCSE for Algorithm::Diff : +# "Copyright (c) 2000-2002 Ned Konz. All rights reserved. +# This program is free software; +# you can redistribute it and/or modify it under the same terms +# as Perl itself." +# The fast-differencing version of latexdiff is provided as a convenience +# for latex users under Unix-like systems which have a 'diff' command. +# If you believe +# the inlining of Algorithm::Diff violates its license please contact +# me and I will modify the latexdiff distribution accordingly. +# Frederik Tilmann (tilmann@esc.cam.ac.uk) +# Jonathan Paisley is acknowledged for the idea of using the system diff +# command to achieve shorter running times +BEGIN { +package Algorithm::Diff; +use strict; +use vars qw($VERSION @EXPORT_OK @ISA @EXPORT); +use integer; # see below in _replaceNextLargerWith() for mod to make + # if you don't use this +require Exporter; +@ISA = qw(Exporter); +@EXPORT = qw(); +@EXPORT_OK = qw(LCS diff traverse_sequences traverse_balanced sdiff); +$VERSION = sprintf('%d.%02d fast', (q$Revision: 1.15 $ =~ /\d+/g)); + +# Global parameters + +use File::Temp qw/tempfile/; +# if larger number of elements in longestCommonSubsequence smaller than +# this number, then use internal algorithm, otherwise use UNIX diff +use constant THRESHOLD => 100 ; +# Detect whether diff --minimal option is available +# if yes we use it +use constant MINIMAL => ( system('diff','--minimal','/dev/null','/dev/null') >> 8 ==0 ? "--minimal" : "" ) ; + + + +# McIlroy-Hunt diff algorithm +# Adapted from the Smalltalk code of Mario I. Wolczko, +# by Ned Konz, perl@bike-nomad.com + + +# Create a hash that maps each element of $aCollection to the set of positions +# it occupies in $aCollection, restricted to the elements within the range of +# indexes specified by $start and $end. +# The fourth parameter is a subroutine reference that will be called to +# generate a string to use as a key. +# Additional parameters, if any, will be passed to this subroutine. +# +# my $hashRef = _withPositionsOfInInterval( \@array, $start, $end, $keyGen ); + +sub _withPositionsOfInInterval +{ + my $aCollection = shift; # array ref + my $start = shift; + my $end = shift; + my $keyGen = shift; + my %d; + my $index; + for ( $index = $start ; $index <= $end ; $index++ ) + { + my $element = $aCollection->[$index]; + my $key = &$keyGen( $element, @_ ); + if ( exists( $d{$key} ) ) + { + unshift ( @{ $d{$key} }, $index ); + } + else + { + $d{$key} = [$index]; + } + } + return wantarray ? %d : \%d; +} + +# Find the place at which aValue would normally be inserted into the array. If +# that place is already occupied by aValue, do nothing, and return undef. If +# the place does not exist (i.e., it is off the end of the array), add it to +# the end, otherwise replace the element at that point with aValue. +# It is assumed that the array's values are numeric. +# This is where the bulk (75%) of the time is spent in this module, so try to +# make it fast! + +sub _replaceNextLargerWith +{ + my ( $array, $aValue, $high ) = @_; + $high ||= $#$array; + + # off the end? + if ( $high == -1 || $aValue > $array->[-1] ) + { + push ( @$array, $aValue ); + return $high + 1; + } + + # binary search for insertion point... + my $low = 0; + my $index; + my $found; + while ( $low <= $high ) + { + $index = ( $high + $low ) / 2; + + # $index = int(( $high + $low ) / 2); # without 'use integer' + $found = $array->[$index]; + + if ( $aValue == $found ) + { + return undef; + } + elsif ( $aValue > $found ) + { + $low = $index + 1; + } + else + { + $high = $index - 1; + } + } + + # now insertion point is in $low. + $array->[$low] = $aValue; # overwrite next larger + return $low; +} + +# This method computes the longest common subsequence in $a and $b. + +# Result is array or ref, whose contents is such that +# $a->[ $i ] == $b->[ $result[ $i ] ] +# foreach $i in ( 0 .. $#result ) if $result[ $i ] is defined. + +# An additional argument may be passed; this is a hash or key generating +# function that should return a string that uniquely identifies the given +# element. It should be the case that if the key is the same, the elements +# will compare the same. If this parameter is undef or missing, the key +# will be the element as a string. + +# By default, comparisons will use "eq" and elements will be turned into keys +# using the default stringizing operator '""'. + +# Additional parameters, if any, will be passed to the key generation routine. + +sub _longestCommonSubsequence +{ + my $a = shift; # array ref + my $b = shift; # array ref + my $keyGen = shift; # code ref + my $compare; # code ref + + # set up code refs + # Note that these are optimized. + if ( !defined($keyGen) ) # optimize for strings + { + $keyGen = sub { $_[0] }; + $compare = sub { my ( $a, $b ) = @_; $a eq $b }; + } + else + { + $compare = sub { + my $a = shift; + my $b = shift; + &$keyGen( $a, @_ ) eq &$keyGen( $b, @_ ); + }; + } + + my ( $aStart, $aFinish, $bStart, $bFinish, $matchVector ) = + ( 0, $#$a, 0, $#$b, [] ); + + # Check whether to use internal routine (small number of elements) + # or use it as a wrapper for UNIX diff + if ( ( $#$a > $#$b ? $#$a : $#$b) < THRESHOLD ) { + ### print STDERR "DEBUG: regular longestCommonSubsequence\n"; + # First we prune off any common elements at the beginning + while ( $aStart <= $aFinish + and $bStart <= $bFinish + and &$compare( $a->[$aStart], $b->[$bStart], @_ ) ) + { + $matchVector->[ $aStart++ ] = $bStart++; + } + + # now the end + while ( $aStart <= $aFinish + and $bStart <= $bFinish + and &$compare( $a->[$aFinish], $b->[$bFinish], @_ ) ) + { + $matchVector->[ $aFinish-- ] = $bFinish--; + } + + # Now compute the equivalence classes of positions of elements + my $bMatches = + _withPositionsOfInInterval( $b, $bStart, $bFinish, $keyGen, @_ ); + my $thresh = []; + my $links = []; + + my ( $i, $ai, $j, $k ); + for ( $i = $aStart ; $i <= $aFinish ; $i++ ) + { + $ai = &$keyGen( $a->[$i], @_ ); + if ( exists( $bMatches->{$ai} ) ) + { + $k = 0; + for $j ( @{ $bMatches->{$ai} } ) + { + + # optimization: most of the time this will be true + if ( $k and $thresh->[$k] > $j and $thresh->[ $k - 1 ] < $j ) + { + $thresh->[$k] = $j; + } + else + { + $k = _replaceNextLargerWith( $thresh, $j, $k ); + } + + # oddly, it's faster to always test this (CPU cache?). + if ( defined($k) ) + { + $links->[$k] = + [ ( $k ? $links->[ $k - 1 ] : undef ), $i, $j ]; + } + } + } + } + + if (@$thresh) + { + for ( my $link = $links->[$#$thresh] ; $link ; $link = $link->[0] ) + { + $matchVector->[ $link->[1] ] = $link->[2]; + } + } + } + else { + my ($fha,$fhb,$fna,$fnb,$ele,$key); + my ($alines,$blines,$alb,$alf,$blb,$blf); + my ($minimal)=MINIMAL; + # large number of elements, use system diff + ### print STDERR "DEBUG: fast (diff) longestCommonSubsequence\n"; + + ($fha,$fna)=tempfile("DiffA-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence A"; + ($fhb,$fnb)=tempfile("DiffB-XXXX") or die "_longestCommonSubsequence: Cannot open tempfile for sequence B"; + # prepare sequence A + foreach $ele ( @$a ) { + $key=&$keyGen( $ele, @_ ); + $key =~ s/\\/\\\\/g ; + $key =~ s/\n/\\n/sg ; + print $fha "$key\n" ; + } + close($fha); + # prepare sequence B + foreach $ele ( @$b ) { + $key=&$keyGen( $ele, @_ ); + $key =~ s/\\/\\\\/g ; + $key =~ s/\n/\\n/sg ; + print $fhb "$key\n" ; + } + close($fhb); + + open(DIFFPIPE, "diff $minimal $fna $fnb |") or die "_longestCommonSubsequence: Cannot launch diff process. $!" ; + # The diff line numbering begins with 1, but Perl subscripts start with 0 + # We follow the diff numbering but substract 1 when assigning to matchVector + $aStart++; $bStart++ ; $aFinish++ ; $bFinish++ ; + while( ) { + if ( ($alines,$blines) = ( m/^(\d*(?:,\d*)?)?c(\d*(?:,\d*)?)?$/ ) ) { + ($alb,$alf)=split(/,/,$alines); + ($blb,$blf)=split(/,/,$blines); + $alf=$alb unless defined($alf); + $blf=$blb unless defined($blf); + while($aStart < $alb ) { + $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; + } + # check for consistency + $bStart==$blb or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in changed sequence"; + $aStart=$alf+1; + $bStart=$blf+1; + } + elsif ( ($alb,$blines) = ( m/^(\d*)a(\d*(?:,\d*)?)$/ ) ) { + ($blb,$blf)=split(/,/,$blines); + $blf=$blb unless defined($blf); + while ( $bStart < $blb ) { + $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; + } + $aStart==$alb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in appended sequence near elements $aStart and $bStart"; + $bStart=$blf+1; + } + elsif ( ($alines,$blb) = ( m/^(\d*(?:,\d*)?)d(\d*)$/ ) ) { + ($alb,$alf)=split(/,/,$alines); + $alf=$alb unless defined($alf); + while ( $aStart < $alb ) { + $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; + } + $bStart==$blb+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency in deleted sequence near elements $aStart and $bStart"; + $aStart=$alf+1; + } + elsif ( m/^Binary files/ ) { + # if diff reports it is a binary file force --text mode. I do not like + # to always use this option because it is probably only available in GNU diff + open(DIFFPIPE, "diff --text $fna $fnb |") or die "Cannot launch diff process. $!" ; + } + # Default: just skip line + } + while ($aStart <= $aFinish ) { + $matchVector->[ -1 + $aStart++ ] = -1 + $bStart++ ; + } + $bStart==$bFinish+1 or die "_longestCommonSubsequence: Fatal error in interpreting diff output: Inconsistency at end"; + close DIFFPIPE; + # check whether a system error has occurred or return status is greater than or equal to 5 + if ( $! || ($? >> 8) > 5) { + print STDERR "diff process failed with exit code ", ($? >> 8), " $!\n"; + die; + } + unlink $fna,$fnb ; + } + return wantarray ? @$matchVector : $matchVector; +} + +sub traverse_sequences +{ + my $a = shift; # array ref + my $b = shift; # array ref + my $callbacks = shift || {}; + my $keyGen = shift; + my $matchCallback = $callbacks->{'MATCH'} || sub { }; + my $discardACallback = $callbacks->{'DISCARD_A'} || sub { }; + my $finishedACallback = $callbacks->{'A_FINISHED'}; + my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { }; + my $finishedBCallback = $callbacks->{'B_FINISHED'}; + my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ ); + + # Process all the lines in @$matchVector + my $lastA = $#$a; + my $lastB = $#$b; + my $bi = 0; + my $ai; + + for ( $ai = 0 ; $ai <= $#$matchVector ; $ai++ ) + { + my $bLine = $matchVector->[$ai]; + if ( defined($bLine) ) # matched + { + &$discardBCallback( $ai, $bi++, @_ ) while $bi < $bLine; + &$matchCallback( $ai, $bi++, @_ ); + } + else + { + &$discardACallback( $ai, $bi, @_ ); + } + } + + # The last entry (if any) processed was a match. + # $ai and $bi point just past the last matching lines in their sequences. + + while ( $ai <= $lastA or $bi <= $lastB ) + { + + # last A? + if ( $ai == $lastA + 1 and $bi <= $lastB ) + { + if ( defined($finishedACallback) ) + { + &$finishedACallback( $lastA, @_ ); + $finishedACallback = undef; + } + else + { + &$discardBCallback( $ai, $bi++, @_ ) while $bi <= $lastB; + } + } + + # last B? + if ( $bi == $lastB + 1 and $ai <= $lastA ) + { + if ( defined($finishedBCallback) ) + { + &$finishedBCallback( $lastB, @_ ); + $finishedBCallback = undef; + } + else + { + &$discardACallback( $ai++, $bi, @_ ) while $ai <= $lastA; + } + } + + &$discardACallback( $ai++, $bi, @_ ) if $ai <= $lastA; + &$discardBCallback( $ai, $bi++, @_ ) if $bi <= $lastB; + } + + return 1; +} + +sub traverse_balanced +{ + my $a = shift; # array ref + my $b = shift; # array ref + my $callbacks = shift || {}; + my $keyGen = shift; + my $matchCallback = $callbacks->{'MATCH'} || sub { }; + my $discardACallback = $callbacks->{'DISCARD_A'} || sub { }; + my $discardBCallback = $callbacks->{'DISCARD_B'} || sub { }; + my $changeCallback = $callbacks->{'CHANGE'}; + my $matchVector = _longestCommonSubsequence( $a, $b, $keyGen, @_ ); + + # Process all the lines in match vector + my $lastA = $#$a; + my $lastB = $#$b; + my $bi = 0; + my $ai = 0; + my $ma = -1; + my $mb; + + while (1) + { + + # Find next match indices $ma and $mb + do { $ma++ } while ( $ma <= $#$matchVector && !defined $matchVector->[$ma] ); + + last if $ma > $#$matchVector; # end of matchVector? + $mb = $matchVector->[$ma]; + + # Proceed with discard a/b or change events until + # next match + while ( $ai < $ma || $bi < $mb ) + { + + if ( $ai < $ma && $bi < $mb ) + { + + # Change + if ( defined $changeCallback ) + { + &$changeCallback( $ai++, $bi++, @_ ); + } + else + { + &$discardACallback( $ai++, $bi, @_ ); + &$discardBCallback( $ai, $bi++, @_ ); + } + } + elsif ( $ai < $ma ) + { + &$discardACallback( $ai++, $bi, @_ ); + } + else + { + + # $bi < $mb + &$discardBCallback( $ai, $bi++, @_ ); + } + } + + # Match + &$matchCallback( $ai++, $bi++, @_ ); + } + + while ( $ai <= $lastA || $bi <= $lastB ) + { + if ( $ai <= $lastA && $bi <= $lastB ) + { + + # Change + if ( defined $changeCallback ) + { + &$changeCallback( $ai++, $bi++, @_ ); + } + else + { + &$discardACallback( $ai++, $bi, @_ ); + &$discardBCallback( $ai, $bi++, @_ ); + } + } + elsif ( $ai <= $lastA ) + { + &$discardACallback( $ai++, $bi, @_ ); + } + else + { + + # $bi <= $lastB + &$discardBCallback( $ai, $bi++, @_ ); + } + } + + return 1; +} + +sub LCS +{ + my $a = shift; # array ref + my $matchVector = _longestCommonSubsequence( $a, @_ ); + my @retval; + my $i; + for ( $i = 0 ; $i <= $#$matchVector ; $i++ ) + { + if ( defined( $matchVector->[$i] ) ) + { + push ( @retval, $a->[$i] ); + } + } + return wantarray ? @retval : \@retval; +} + +sub diff +{ + my $a = shift; # array ref + my $b = shift; # array ref + my $retval = []; + my $hunk = []; + my $discard = sub { push ( @$hunk, [ '-', $_[0], $a->[ $_[0] ] ] ) }; + my $add = sub { push ( @$hunk, [ '+', $_[1], $b->[ $_[1] ] ] ) }; + my $match = sub { push ( @$retval, $hunk ) if scalar(@$hunk); $hunk = [] }; + traverse_sequences( $a, $b, + { MATCH => $match, DISCARD_A => $discard, DISCARD_B => $add }, @_ ); + &$match(); + return wantarray ? @$retval : $retval; +} + +sub sdiff +{ + my $a = shift; # array ref + my $b = shift; # array ref + my $retval = []; + my $discard = sub { push ( @$retval, [ '-', $a->[ $_[0] ], "" ] ) }; + my $add = sub { push ( @$retval, [ '+', "", $b->[ $_[1] ] ] ) }; + my $change = sub { + push ( @$retval, [ 'c', $a->[ $_[0] ], $b->[ $_[1] ] ] ); + }; + my $match = sub { + push ( @$retval, [ 'u', $a->[ $_[0] ], $b->[ $_[1] ] ] ); + }; + traverse_balanced( + $a, + $b, + { + MATCH => $match, + DISCARD_A => $discard, + DISCARD_B => $add, + CHANGE => $change, + }, + @_ + ); + return wantarray ? @$retval : $retval; +} + +1; +} +import Algorithm::Diff qw(traverse_sequences); +# End of inserted block for stand-alone version + + +use Getopt::Long ; +use strict ; +use warnings; +use utf8 ; + +my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); + + +my ($versionstring)=< 0, + WHOLE => 1, + COARSE => 2, + FINE => 3 +}; + + +my (@configlist,@labels, + @appendsafelist,@excludesafelist, + @appendtextlist,@excludetextlist, + @appendcontext1list,@appendcontext2list, + @packagelist); +my ($assign,@config); +# Hash where keys corresponds to the names of all included packages (including the documentclass as another package +# the optional arguments to the package are the values of the hash elements +my ($pkg,%packages); +# Defaults +$type='UNDERLINE'; +$subtype='SAFE'; +$floattype='FLOATSAFE'; +$mathmarkup=COARSE; + +$verbose=0; +# output debug and intermediate files, set to 0 in final distribution +$debug=0; +# define character properties +sub IsNonAsciiPunct { return <<'END' # Unicode punctuation but excluding ASCII punctuation ++utf8::IsPunct +-utf8::IsASCII +END +} +sub IsNonAsciiS { return <<'END' # Unicode symbol but excluding ASCII ++utf8::IsS +-utf8::IsASCII +END +} + + +my %verbhash; + +Getopt::Long::Configure('bundling'); +GetOptions('type|t=s' => \$type, + 'subtype|s=s' => \$subtype, + 'floattype|f=s' => \$floattype, + 'config|c=s' => \@configlist, + 'preamble|p=s' => \$preamblefile, + 'encoding|e=s' => \$encoding, + 'label|L=s' => \@labels, + 'no-label' => \$nolabel, + 'visible-label' => \$visiblelabel, + 'exclude-safecmd|A=s' => \@excludesafelist, + 'replace-safecmd=s' => \$replacesafe, + 'append-safecmd|a=s' => \@appendsafelist, + 'exclude-textcmd|X=s' => \@excludetextlist, + 'replace-textcmd=s' => \$replacetext, + 'append-textcmd|x=s' => \@appendtextlist, + 'replace-context1cmd=s' => \$replacecontext1, + 'append-context1cmd=s' => \@appendcontext1list, + 'replace-context2cmd=s' => \$replacecontext2, + 'append-context2cmd=s' => \@appendcontext2list, + 'show-preamble' => \$showpreamble, + 'show-safecmd' => \$showsafe, + 'show-textcmd' => \$showtext, + 'show-config' => \$showconfig, + 'show-all' => \$showall, + 'packages=s' => \@packagelist, + 'allow-spaces' => \$allowspaces, + 'math-markup=s' => \$mathmarkup, + 'enable-citation-markup' => \$enablecitmark, + 'disable-citation-markup' => \$disablecitmark, + 'verbose|V' => \$verbose, + 'ignore-warnings' => \$ignorewarnings, + 'driver=s'=> \$driver, + 'flatten' => \$flatten, + 'version' => \$version, + 'help|h|H' => \$help); + +if ( $help ) { + usage() ; +} + + +if ( $version ) { + die $versionstring ; +} + +print STDERR $versionstring if $verbose; + +if (defined($showall)){ + $showpreamble=$showsafe=$showtext=$showconfig=1; +} + +if (defined($mathmarkup)) { + $mathmarkup=~tr/a-z/A-Z/; + if ( $mathmarkup eq 'OFF' ){ + $mathmarkup=OFF; + } elsif ( $mathmarkup eq 'WHOLE' ){ + $mathmarkup=WHOLE; + } elsif ( $mathmarkup eq 'COARSE' ){ + $mathmarkup=COARSE; + } elsif ( $mathmarkup eq 'FINE' ){ + $mathmarkup=FINE; + } elsif ( $mathmarkup !~ m/^[0123]$/ ) { + die "Illegal value: ($mathmarkup) for option--math-markup. Possible values: OFF,WHOLE,COARSE,FINE,0- "; + } + # else use numerical value +} + +# setting extra preamble commands +if (defined($preamblefile)) { + $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); +} else { + $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); +} + +if ( defined($driver) ) { + # for changebar only + $latexdiffpreamble=~s/\[dvips\]/[$driver]/sg; +} +# setting up @SAFECMDLIST and @SAFECMDEXCL +if (defined($replacesafe)) { + init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); +} else { + init_regex_arr_data(\@SAFECMDLIST, "SAFE COMMANDS"); +} +foreach $appendsafe ( @appendsafelist ) { + init_regex_arr_ext(\@SAFECMDLIST, $appendsafe); +} +foreach $excludesafe ( @excludesafelist ) { + init_regex_arr_ext(\@SAFECMDEXCL, $excludesafe); +} + +# Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode +# (there is a conflict between citation and ulem package, see +# package documentation) +# Use post-processing + +if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { + push (@SAFECMDLIST, qr/^cite.*$/); +} else { + ### Experimental: disable text and emph commands + push (@SAFECMDLIST, qr/^cite.*$/) unless $disablecitmark; + push(@SAFECMDEXCL, qr/^emph$/, qr/^text..$/); + # replace \cite{..} by \mbox{\cite{..}} in added or deleted blocks in post-processing + if ( uc($subtype) eq "COLOR" or uc($subtype) eq "DVIPSCOL" ) { + # remove \cite command again from list of safe commands + pop @SAFECMDLIST; + # deleted cite commands + $CITE2CMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite-type commands which should be reinstated in deleted blocks + } else { + $CITECMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite commands which need to be protected within an mbox in UNDERLINE and other modes using ulem + } +} +$CITECMD='(?:cite\w*|nocite)' if $enablecitmark ; # as above for explicit selection + +# setting up @TEXTCMDLIST and @TEXTCMDEXCL +if (defined($replacetext)) { + init_regex_arr_ext(\@TEXTCMDLIST,$replacetext); +} else { + init_regex_arr_data(\@TEXTCMDLIST, "TEXT COMMANDS"); +} +foreach $appendtext ( @appendtextlist ) { + init_regex_arr_ext(\@TEXTCMDLIST, $appendtext); +} +foreach $excludetext ( @excludetextlist ) { + init_regex_arr_ext(\@TEXTCMDEXCL, $excludetext); +} + + +# setting up @CONTEXT1CMDLIST ( @CONTEXT1CMDEXCL exist but is always empty ) +if (defined($replacecontext1)) { + init_regex_arr_ext(\@CONTEXT1CMDLIST,$replacecontext1); +} else { + init_regex_arr_data(\@CONTEXT1CMDLIST, "CONTEXT1 COMMANDS"); +} +foreach $appendcontext1 ( @appendcontext1list ) { + init_regex_arr_ext(\@CONTEXT1CMDLIST, $appendcontext1); +} + + +# setting up @CONTEXT2CMDLIST ( @CONTEXT2CMDEXCL exist but is always empty ) +if (defined($replacecontext2)) { + init_regex_arr_ext(\@CONTEXT2CMDLIST,$replacecontext2); +} else { + init_regex_arr_data(\@CONTEXT2CMDLIST, "CONTEXT2 COMMANDS"); +} +foreach $appendcontext2 ( @appendcontext2list ) { + init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); +} + +# setting configuration variables +@config=(); +foreach $config ( @configlist ) { + if (-f $config ) { + open(FILE,$config) or die ("Couldn't open configuration file $config: $!"); + while () { + chomp; + next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; + push (@config,$_); + } + close(FILE); + } + else { +# foreach ( split(",",$config) ) { +# push @config,$_; +# } + push @config,split(",",$config) + } +} +foreach $assign ( @config ) { + $assign=~ m/\s*(\w*)\s*=\s*(\S*)\s*$/ or die "Illegal assignment $assign in configuration list (must be variable=value)"; + if ( $1 eq "MINWORDSBLOCK" ) { $MINWORDSBLOCK = $2; } + elsif ( $1 eq "FLOATENV" ) { $FLOATENV = $2 ; } + elsif ( $1 eq "PICTUREENV" ) { $PICTUREENV = $2 ; } + elsif ( $1 eq "MATHENV" ) { $MATHENV = $2 ; } + elsif ( $1 eq "MATHREPL" ) { $MATHREPL = $2 ; } + elsif ( $1 eq "MATHARRENV" ) { $MATHARRENV = $2 ; } + elsif ( $1 eq "MATHARRREPL" ) { $MATHARRREPL = $2 ; } + elsif ( $1 eq "ARRENV" ) { $ARRENV = $2 ; } + elsif ( $1 eq "COUNTERCMD" ) { $COUNTERCMD = $2 ; } + else { die "Unknown variable $1 in assignment.";} +} + +if ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) { + push(@MATHTEXTCMDLIST,qr/^MATHBLOCK(?:$MATHENV|$MATHARRENV|SQUAREBRACKET)$/); +} + + + +foreach $pkg ( @packagelist ) { + map { $packages{$_}="" } split(/,/,$pkg) ; +} + +if ($showpreamble) { + print "\nPreamble commands:\n"; + print $latexdiffpreamble ; +} + +if ($showsafe) { + print "\nCommands safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE (unless excluded):\n"; + print_regex_arr(@SAFECMDLIST); + print "\nCommands not safe within scope of $ADDOPEN $ADDCLOSE and $DELOPEN $DELCLOSE :\n"; + print_regex_arr(@SAFECMDEXCL); +} + +if ($showtext) { + print "\nCommands with last argument textual (unless excluded) and safe in every context:\n"; + print_regex_arr(@TEXTCMDLIST); + print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; + print_regex_arr(@CONTEXT1CMDLIST); + print "\nContext2 commands (last argument textual, command and its argument will be disabled in deleted passages):\n"; + print_regex_arr(@CONTEXT2CMDLIST); + print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; + print_regex_arr(@TEXTCMDEXCL); +} + + +if ($showconfig) { + print "Configuration variables:\n"; + print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; + print "FLOATENV=$FLOATENV\n"; + print "PICTUREENV=$PICTUREENV\n"; + print "MATHENV=$MATHENV\n"; + print "MATHREPL=$MATHREPL\n"; + print "MATHARRENV=$MATHARRENV\n"; + print "MATHARRREPL=$MATHARRREPL\n"; + print "ARRENV=$ARRENV\n"; + print "COUNTERCMD=$COUNTERCMD\n"; +} +if ($showconfig || $showtext || $showsafe || $showpreamble) { + exit 0; } +if ( @ARGV != 2 ) { + print STDERR "2 and only 2 non-option arguments required. Write latexdiff -h to get help\n"; + exit(2); +} + +# Are extra spaces between command arguments permissible? +my $extraspace; +if ($allowspaces) { + $extraspace='\s*'; +} else { + $extraspace=''; +} + +# append context lists to text lists (as text property is implied) +push @TEXTCMDLIST, @CONTEXT1CMDLIST; +push @TEXTCMDLIST, @CONTEXT2CMDLIST; + +push @TEXTCMDLIST, @MATHTEXTCMDLIST if $mathmarkup==COARSE; + +# internal additions to SAFECMDLIST +push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/); + + +# Patterns. These are used by some of the subroutines, too +# I can only define them down here because value of extraspace depends on an option + my $pat0 = '(?:[^{}])*'; + my $pat1 = '(?:[^{}]|\{'.$pat0.'\})*'; + my $pat2 = '(?:[^{}]|\{'.$pat1.'\})*'; + my $pat3 = '(?:[^{}]|\{'.$pat2.'\})*'; + my $pat4 = '(?:[^{}]|\{'.$pat3.'\})*'; + my $pat5 = '(?:[^{}]|\{'.$pat4.'\})*'; + my $pat6 = '(?:[^{}]|\{'.$pat5.'\})*'; + my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; + + my $quotemarks = '(?:\'\')|(?:\`\`)'; + my $punct='[0.,\/\'\`:;\"\?\(\)\[\]!~\p{IsNonAsciiPunct}\p{IsNonAsciiS}]'; + my $number='-?\d*\.\d*'; + my $mathpunct='[+=<>\-\|]'; + my $and = '&'; + my $coords= '[\-.,\s\d]*'; +# word: sequence of letters or accents followed by letter + my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; + my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; + + my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat6 . '\}|\(' . $coords .'\))'.$extraspace.')*'; + my $backslashnl='\\\\\n'; + my $oneletcmd='\\\\.\*?(?:\['.$brat0.'\]|\{'. $pat6 . '\})*'; + my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; +## the current maths command cannot cope with newline within the math expression + + my $comment='%.*?\n'; + my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${backslashnl}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; + + + +# now we are done setting up and can start working +my ($oldfile, $newfile) = @ARGV; +# check for existence of input files +if ( ! -e $oldfile ) { + die "Input file $oldfile does not exist."; +} +if ( ! -e $newfile ) { + die "Input file $newfile does not exist."; +} + + +# set the labels to be included into the file +my ($oldtime,$newtime,$oldlabel,$newlabel); +if (defined($labels[0])) { + $oldlabel=$labels[0] ; +} else { + $oldtime=localtime((stat($oldfile))[9]); + $oldlabel="$oldfile " . " "x(length($newfile)-length($oldfile)) . $oldtime; +} +if (defined($labels[1])) { + $newlabel=$labels[1] ; +} else { + $newtime=localtime((stat($newfile))[9]); + $newlabel="$newfile " . " "x(length($oldfile)-length($newfile)) . $newtime; +} + +$encoding=guess_encoding($newfile) unless defined($encoding); + +$encoding = "utf8" if $encoding =~ m/^utf8/i ; +if (lc($encoding) eq "utf8" ) { + binmode(STDOUT, ":utf8"); + binmode(STDERR, ":utf8"); +} + +$old=read_file_with_encoding($oldfile,$encoding); +$new=read_file_with_encoding($newfile,$encoding); + + + + +# reset time +exetime(1); +($oldpreamble,$oldbody,$oldpost)=splitdoc($old,'\\\\begin\{document\}','\\\\end\{document\}'); + + +($newpreamble,$newbody,$newpost)=splitdoc($new,'\\\\begin\{document\}','\\\\end\{document\}'); + + +if ($flatten) { + $oldbody=flatten($oldbody,$oldpreamble,$oldfile,$encoding); + $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); +} + +my @auxlines; +if ( length $oldpreamble && length $newpreamble ) { + # pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands) + # and marking up content with latexdiff markup + @auxlines=preprocess_preamble($oldpreamble,$newpreamble); + + @oldpreamble = split /\n/, $oldpreamble; + @newpreamble = split /\n/, $newpreamble; + + # If a command is defined in the preamble of the new file, and only uses safe commands, then it can be considered to be safe) (contribution S. Gouezel) + # Base this assessment on the new preamble + add_safe_commands($newpreamble); + + %packages=list_packages(@newpreamble) unless %packages; + if (defined $packages{"hyperref"} ) { + print STDERR "hyperref package detected.\n" if $verbose ; + $latexdiffpreamble =~ s/\{\\DIFadd\}/{\\DIFaddtex}/g; + $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; + $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); + } + print STDERR "Differencing preamble.\n" if $verbose; + + # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct + unshift @newpreamble,''; + unshift @oldpreamble,''; + @diffpreamble = linediff(\@oldpreamble, \@newpreamble); + # remove dummy line again + shift @diffpreamble; + # add filenames, modification time and latexdiff mark + defined($nolabel) or splice @diffpreamble,1,0, + "%DIF LATEXDIFF DIFFERENCE FILE", + ,"%DIF DEL $oldlabel", + "%DIF ADD $newlabel"; + if ( @auxlines ) { + push @diffpreamble,"%DIF DELETED TITLE COMMANDS FOR MARKUP"; + push @diffpreamble,join("\n",@auxlines); + } + push @diffpreamble,$latexdiffpreamble; + push @diffpreamble,'\begin{document}'; +} +elsif ( !length $oldpreamble && !length $newpreamble ) { + @diffpreamble=(); +} else { + print STDERR "Either both texts must have preamble or neither text must have the preamble.\n"; + exit(2); +} + +if (defined $packages{"amsmath"} or defined $packages{"amsart"} or defined $packages{"amsbook"} ) { + print STDERR "amsmath package detected.\n" if $verbose ; + $MATHARRREPL='align*'; +} + +print STDERR "Preprocessing body. " if $verbose; +my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); + + +# run difference algorithm +@diffbody=bodydiff($oldbody, $newbody); +$diffbo=join("",@diffbody); +if ( $debug ) { + open(RAWDIFF,">","latexdiff.debug.bodydiff"); + print RAWDIFF $diffbo; + close(RAWDIFF); +} +print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; +postprocess($diffbo); +$diffall =join("\n",@diffpreamble) ; +# add visible labels +if (defined($visiblelabel)) { + # Give information right after \begin{document} (or at the beginning of the text for files without preamble + ### if \date command is used, add information to \date argument, otherwise give right after \begin{document} + ### $diffall=~s/(\\date$extraspace(?:\[$brat0\])?$extraspace)\{($pat6)\}/$1\{$2 \\ LATEXDIFF comparison \\ Old: $oldlabel \\ New: $newlabel \}/ or + $diffbo = "\\begin{verbatim}LATEXDIFF comparison\nOld: $oldlabel\nNew: $newlabel\\end{verbatim}\n$diffbo" ; +} + +$diffall .= "$newleadin$diffbo" ; +$diffall .= "\\end{document}$newpost" if length $newpreamble ; +if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { + print STDERR "Encoding output file to $encoding\n" if $verbose; + $diffall=Encode::encode($encoding,$diffall); + binmode STDOUT; +} +print $diffall; + + +print STDERR "(",exetime()," s)\n","Done.\n" if $verbose; + + + +## guess_encoding(filename) +## reads the first 20 lines of filename and looks for call of inputenc package +## if found, return the option of this package (encoding), otherwise return ascii +sub guess_encoding { + my ($filename)=@_; + my ($i,$enc); + open (FH, $filename) or die("Couldn't open $filename: $!"); + $i=0; + while () { + next if /^\s*%/; # skip comment lines + if (m/\\usepackage\[(\w*?)\]\{inputenc\}/) { + close(FH); + return($1); + } + last if (++$i > 20 ); # scan at most 20 non-comment lines + } + close(FH); + return("ascii"); +} + + +sub read_file_with_encoding { + my ($output); + my ($filename, $encoding) = @_; + + if (lc($encoding) eq "utf8" ) { + open (FILE, "<:utf8",$filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + } elsif ( lc($encoding) eq "ascii") { + open (FILE, $filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + } else { + require Encode; + open (FILE, "<",$filename) or die("Couldn't open $filename: $!"); + local $/ ; # locally set record operator to undefined, ie. enable whole-file mode + $output=; + print STDERR "Converting $filename from $encoding to utf8\n" if $verbose; + $output=Encode::decode($encoding,$output); + } + close FILE; + if ($^O eq "linux" ) { + $output =~ s/\r\n/\n/g ; + } + return $output; +} + +# %packages=list_packages(@preamble) +# scans the arguments for \documentclass and \usepackage statements and constructs a hash +# whose keys are the included packages, and whose values are the associated optional arguments +sub list_packages { + my (@preamble)=@_; + my %packages=(); + foreach $line ( @preamble ) { + # get rid of comments + $line=~s/(?catfile($dirname,$fname), "\n" if $debug; + # content of file becomes replacement value (use recursion), add \newpage if the command was include + ###$replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + $replacement=flatten(read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding), $preamble,$filename,$encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + # \include always starts a new page; use explicit \newpage command to simulate this + $begline=(defined($1)? $1 : "") ; + $newpage=(defined($3)? " \\newpage " : "") ; + "$begline$newpage$replacement$newpage"; + }/exgm; + + return($text); +} + + +# print_regex_arr(@arr) +# prints regex array without x-ism expansion put in by pearl to stdout +sub print_regex_arr { + my $dumstring; + $dumstring = join(" ",@_); # PERL generates string (?-xism:^ref$) for quoted refex ^ref$ + $dumstring =~ s/\(\?-xism:\^(.*?)\$\)/$1/g; # remove string and ^,$ marks before output + print $dumstring,"\n"; +} + + +# @lines=extrapream($type) +# reads line from appendix (end of file after __END__ token) +sub extrapream { + my $type; + my @retval=("%DIF PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; + my ($copy); + + while (@_) { + $copy=0; + $type=shift ; + if ( -f $type ) { + open (FILE,$type) or die "Cannot open preamble file $type: $!"; + print STDERR "Reading preamble file $type\n" if $verbose ; + while () { + chomp ; + if ( $_ =~ m/%DIF PREAMBLE/ ) { + push (@retval,"$_"); + } else { + push (@retval,"$_ %DIF PREAMBLE"); + } + } + } + else { # not (-f $type) + $type=uc($type); # upcase argument + print STDERR "Preamble Internal Type $type\n" if $verbose; + while () { + if ( m/^%DIF $type/ ) { + $copy=1; } + elsif ( m/^%DIF END $type/ ) { + last; } + chomp; + push (@retval,"$_ %DIF PREAMBLE") if $copy; + } + if ( $copy == 0 ) { + print STDERR "\nPreamble style $type not implemented.\n"; + print STDERR "Write latexdiff -h to get help with available styles\n"; + exit(2); + } + seek DATA,0,0; # rewind DATA handle to file begin + } + } + push (@retval,"%DIF END PREAMBLE EXTENSION ADDED BY LATEXDIFF") ; + return @retval; +} + + +# ($part1,$part2,$part3)=splitdoc($text,$word1,$word2) +# splits $text into 3 parts at $word1 and $word2. +# if neither $word1 nor $word2 exist, $part1 and $part3 are empty, $part2 is $text +# If only $word1 or $word2 exist but not the other, output an error message. + +# NB this version avoids $` and $' for performance reason although it only makes a tiny difference +# (in one test gain a tenth of a second for a 30s run) +sub splitdoc { + my ($text,$word1,$word2)=@_; + my ($part1,$part2,$part3)=("","",""); + my ($rest,$pos); + + if ( $text =~ m/(^[^%]*)($word1)/mg ) { + $pos=pos $text; + $part1=substr($text,0,$pos-length($2)); + $rest=substr($text,$pos); + if ( $rest =~ m/(^[^%]*)($word2)/mg ) { + $pos=pos $rest; + $part2=substr($rest,0,$pos-length($2)); + $part3=substr($rest,$pos); + } + else { + die "$word1 and $word2 not in the correct order or not present as a pair." ; + } + } else { + $part2=$text; + die "$word2 present but not $word1." if ( $text =~ m/(^[^%]*)$word2/ms ); + } + return ($part1,$part2,$part3); +} + + + + + +# bodydiff($old,$new) +sub bodydiff { + my ($oldwords, $newwords) = @_; + my @retwords; + + print STDERR "(",exetime()," s)\n","Splitting into latex tokens \n" if $verbose; + print STDERR "Parsing $oldfile \n" if $verbose; + my @oldwords = splitlatex($oldwords); + print STDERR "Parsing $newfile \n" if $verbose; + my @newwords = splitlatex($newwords); + + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } + + print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; + pass1(\@oldwords, \@newwords); + + + print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold2.tex"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew2.tex"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } + + @retwords=pass2(\@oldwords, \@newwords); + + return(@retwords); +} + + + + +# @words=splitlatex($string) +# split string according to latex rules +# Each element of words is either +# a word (including trailing spaces and punctuation) +# a latex command +sub splitlatex { + my ($string) = @_ ; + # if input is empty, return empty list + length($string)>0 or return (); + + my @retval=($string =~ m/$pat/osg); + + if (length($string) != length(join("",@retval))) { + print STDERR "\nWARNING: Inconsistency in length of input string and parsed string:\n This often indicates faulty or non-standard latex code.\n In many cases you can ignore this and the following warning messages.\n Note that character numbers in the following are counted beginning after \\begin{document} and are only approximate." unless $ignorewarnings; + print STDERR "DEBUG Original length ",length($string)," Parsed length ",length(join("",@retval)),"\n" if $debug; + print STDERR "DEBUG Input string: |$string|\n" if (length($string)<500) && $debug; + print STDERR "DEBUG Token parsing: |",join("+",@retval),"|\n" if (length($string)<500) && $debug ; + @retval=(); + # slow way only do this if other m//sg method fails + my $last = 0; + while ( $string =~ m/$pat/osg ) { + my $match=$&; + if ($last + length $& != pos $string ) { + my $pos=pos($string); + my $offset=30<$last ? 30 : $last; + my $dum=substr($string,$last-$offset,$pos-$last+2*$offset); + my $dum1=$dum; + my $cnt=$#retval; + my $i; + $dum1 =~ s/\n/ /g; + unless ($ignorewarnings) { + print STDERR "\n$dum1\n"; + print STDERR " " x 30,"^" x ($pos-$last)," " x 30,"\n"; + print STDERR "Missing characters near word " . (scalar @retval) . " character index: " . $last . "-" . pos($string) . " Length: " . length($match) . " Match: |$match| (expected match marked above).\n"; + } + # put in missing characters `by hand' + push (@retval, substr($dum,$offset,$pos-$last-length($match))); +# Note: there seems to be a bug in substr with utf8 that made the following line output substr which were too long, +# using dum instead appears to work +# push (@retval, substr($string,$last, pos($string)-$last-length($match))); + } + push (@retval, $match); + $last=pos $string; + } + + } + return @retval; +} + + +# pass1( \@seq1,\@seq2) +# Look for differences between seq1 and seq2. +# Where an common-subsequence block is flanked by deleted or appended blocks, +# and is shorter than $MINWORDSBLOCK words it is appended +# to the last deleted or appended word. If the block contains tokens other than words +# or punctuation it is not merged. +# Deleted or appended block consisting of words and safe commands only are +# also merged, to prevent break-up in pass2 (after previous isolated words have been removed) +# If there are commands with textual arguments (e.g. \caption) both in corresponding +# appended and deleted blocks split them such that the command and opening bracket +# are one token, then the rest is split up following standard rules, and the closing +# bracket is a separate token, ie. turn +# "\caption{This is a textual argument}" into +# ("\caption{","This ","is ","a ","textual ","argument","}") +# No return value. Destructively changes sequences +sub pass1 { + my $seq1 = shift ; + my $seq2 = shift ; + + my $len1 = scalar @$seq1; + my $len2 = scalar @$seq2; + my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' + + my ($last1,$last2)=(-1,-1) ; + my $cnt=0; + my $block=[]; + my $addblock=[]; + my $delblock=[]; + my $todo=[]; + my $instruction=[]; + my $i; + my (@delmid,@addmid,@dummy); + + my ($addcmds,$delcmds,$matchindex); + my ($addtextblocks,$deltextblocks); + my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); + my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); + + my $adddiscard = sub { + if ($cnt > 0 ) { + $matblkcnt++; + # just after an unchanged block +# print STDERR "Unchanged block $cnt, $last1,$last2 \n"; + if ($cnt < $MINWORDSBLOCK + && $cnt==scalar ( + grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat6\})*)/o + && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) + && scalar(@dummy=split(" ",$2))<3 ) } + @$block) ) { + # merge identical blocks shorter than $MINWORDSBLOCK + # and only containing ordinary words + # with preceding different word + # We cannot carry out this merging immediately as this + # would change the index numbers of seq1 and seq2 and confuse + # the algorithm, instead we store in @$todo where we have to merge + push(@$todo, [ $last1,$last2,$cnt,@$block ]); + } + $block = []; + $cnt=0; $last1=-1; $last2=-1; + } + }; + my $discard=sub { $deltokcnt++; + &$adddiscard; #($_[0],$_[1]); + push(@$delblock,[ $seq1->[$_[0]],$_[0] ]); + $last1=$_[0] }; + + my $add = sub { $addtokcnt++; + &$adddiscard; #($_[0],$_[1]); + push(@$addblock,[ $seq2->[$_[1]],$_[1] ]); + $last2=$_[1] }; + + my $match = sub { $mattokcnt++; + if ($cnt==0) { # first word of matching sequence after changed sequence or at beginning of word sequence + $deltextblocks = extracttextblocks($delblock); + $delblkcnt++ if scalar @$delblock; + $addtextblocks = extracttextblocks($addblock); + $addblkcnt++ if scalar @$addblock; + + $delcmds = extractcommands($delblock); + $addcmds = extractcommands($addblock); + # keygen(third argument of _longestCommonSubsequence) implies to sort on command (0th elements of $addcmd elements) + # the calling format for longestCommonSubsequence has changed between versions of + # Algorithm::Diff so we need to check which one we are using + if ( $algodiffversion > 1.15 ) { + ### Algorithm::Diff 1.19 + $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, 0, sub { $_[0]->[0] } ); + } else { + ### Algorithm::Diff 1.15 + $matchindex=Algorithm::Diff::_longestCommonSubsequence($delcmds,$addcmds, sub { $_[0]->[0] } ); + } + + for ($i=0 ; $i<=$#$matchindex ; $i++) { + if (defined($matchindex->[$i])){ + $j=$matchindex->[$i]; + @delmid=splitlatex($delcmds->[$i][3]); + @addmid=splitlatex($addcmds->[$j][3]); + while (scalar(@$deltextblocks) && $deltextblocks->[0][0]<$delcmds->[$i][1]) { + my ($index,$block,$cnt)=@{ shift(@$deltextblocks) }; + push(@$todo, [$index,-1,$cnt,@$block]); + } + push(@$todo, [ $delcmds->[$i][1],-1,-1,$delcmds->[$i][2],@delmid,$delcmds->[$i][4]]); + + while (scalar(@$addtextblocks) && $addtextblocks->[0][0]<$addcmds->[$j][1]) { + my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; + push(@$todo, [-1,$index,$cnt,@$block]); + } + push(@$todo, [ -1,$addcmds->[$j][1],-1,$addcmds->[$j][2],@addmid,$addcmds->[$j][4]]); + } + } + # mop up remaining textblocks + while (scalar(@$deltextblocks)) { + my ($index,$block,$cnt)=@{ shift(@$deltextblocks) } ; + push(@$todo, [$index,-1,$cnt,@$block]); + } + while (scalar(@$addtextblocks)) { + my ($index,$block,$cnt)=@{ shift(@$addtextblocks) }; + push(@$todo, [-1,$index,$cnt,@$block]); + } + + $addblock=[]; + $delblock=[]; + } + push(@$block,$seq2->[$_[1]]); + $cnt++ }; + + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + + + # now carry out the merging/splitting. Refer to elements relative from + # the end (with negative indices) as these offsets don't change before the instruction is executed + # cnt>0: merged small unchanged groups with previous changed blocks + # cnt==-1: split textual commands into components + foreach $instruction ( @$todo) { + ($last1,$last2,$cnt,@$block)=@$instruction ; + if ($cnt>=0) { + splice(@$seq1,$last1-$len1,1+$cnt,join("",$seq1->[$last1-$len1],@$block)) if $last1>=0; + splice(@$seq2,$last2-$len2,1+$cnt,join("",$seq2->[$last2-$len2],@$block)) if $last2>=0; + } else { + splice(@$seq1,$last1-$len1,1,@$block) if $last1>=0; + splice(@$seq2,$last2-$len2,1,@$block) if $last2>=0; + } + } + + if ($verbose) { + print STDERR "\n"; + print STDERR " $mattokcnt matching tokens in $matblkcnt blocks.\n"; + print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; + print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; + } +} + + +# extracttextblocks(\@blockindex) +# $blockindex has the following format +# [ [ token1, index1 ], [token2, index2],.. ] +# where index refers to the index in the original old or new word sequence +# Returns: reference to an array of the form +# [[ $index, $textblock, $cnt ], .. +# where $index index of block to be merged +# $textblock contains all the words to be merged with the word at $index (but does not contain this word) +# $cnt is length of block +# +# requires: iscmd +# +sub extracttextblocks { + my $block=shift; + my ($i,$token,$index); + my $textblock=[]; + my $last=-1; + my $wpat=qr/^(?:[a-zA-Z.,'`:;?()!]*)[\s~]*$/; #' + my $retval=[]; + + for ($i=0;$i< scalar @$block;$i++) { + ($token,$index)=@{ $block->[$i] }; + # store pure text blocks + if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*)/o + && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) + && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { + # we have text or a command which can be treated as text + if ($last<0) { + # new pure-text block + $last=$index; + } else { + # add to pure-text block + push(@$textblock, $token); + } + } else { + # it is not text + if (scalar(@$textblock)) { + push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); + } + $textblock=[]; + $last=-1; + } + } + # finish processing a possibly unfinished block before returning + if (scalar(@$textblock)) { + push(@$retval,[ $last, $textblock, scalar(@$textblock) ]); + } + return($retval) +} + + + +# extractcommands( \@blockindex ) +# $blockindex has the following format +# [ [ token1, index1 ], [token2, index2],.. ] +# where index refers to the index in the original old or new word sequence +# Returns: reference to an array of the form +# [ [ "\cmd1", index, "\cmd1[optarg]{arg1}{", "arg2" ,"} " ],.. +# where index is just taken from input array +# command must have a textual argument as last argument +# +# requires: iscmd +# +sub extractcommands { + my $block=shift; + my ($i,$token,$index,$cmd,$open,$mid,$closing); + my $retval=[]; + + for ($i=0;$i< scalar @$block;$i++) { + ($token,$index)=@{ $block->[$i] }; + # check if token is an alphanumeric command sequence with at least one non-optional argument + # \cmd[...]{...}{last argument} + # Capturing in the following results in these associations + # $1: \cmd[...]{...}{ + # $2: \cmd + # $3: last argument + # $4: } + trailing spaces + if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { + # push(@$retval,[ $2,$index,$1,$3,$4 ]); + ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; + $closing =~ s/\}/\\RIGHTBRACE/ ; + push(@$retval,[ $cmd,$index,$open,$mid,$closing ]); + } + } + return $retval; +} + +# iscmd($cmd,\@regexarray,\@regexexcl) checks +# return 1 if $cmd matches any of the patterns in the +# array $@regexarray, and none of the patterns in \@regexexcl, otherwise return 0 +sub iscmd { + my ($cmd,$regexar,$regexexcl)=@_; + my ($ret)=0; + foreach $pat ( @$regexar ) { + if ( $cmd =~ m/^${pat}$/ ) { + $ret=1 ; + last; + } + } + return 0 unless $ret; + foreach $pat ( @$regexexcl ) { + return 0 if ( $cmd =~ m/^${pat}$/ ); + } + return 1; +} + + +# pass2( \@seq1,\@seq2) +# Look for differences between seq1 and seq2. +# Mark begin and end of deleted and appended sequences with tags $DELOPEN and $DELCLOSE +# and $ADDOPEN and $ADDCLOSE, respectively, however exclude { } & and all comands, unless +# they match an element of the whitelist (SAFECMD) +# For words in TEXTCMD but not in SAFECMD, enclose interior with $ADDOPEN and $ADDCLOSE brackets +# Deleted comment lines are marked with %DIF < +# Added comment lines are marked with %DIF > +sub pass2 { + my $seq1 = shift ; + my $seq2 = shift ; + + my ($addtokcnt,$deltokcnt,$mattokcnt)=(0,0,0); + my ($addblkcnt,$delblkcnt,$matblkcnt)=(0,0,0); + + my $retval = []; + my $delhunk = []; + my $addhunk = []; + + my $discard = sub { $deltokcnt++; + push ( @$delhunk, $seq1->[$_[0]]) }; + + my $add = sub { $addtokcnt++; + push ( @$addhunk, $seq2->[$_[1]]) }; + + my $match = sub { $mattokcnt++; + if ( scalar @$delhunk ) { + $delblkcnt++; + # mark up changes, but comment out commands + push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk); + $delhunk = []; + } + if ( scalar @$addhunk ) { + $addblkcnt++; + # we mark up changes, but simply quote commands + push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk); + $addhunk = []; + } + push(@$retval,$seq2->[$_[1]]) }; + + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + # clear up unprocessed hunks + push @$retval,marktags($DELMARKOPEN,$DELMARKCLOSE,$DELOPEN,$DELCLOSE,$DELCMDOPEN,$DELCMDCLOSE,$DELCOMMENT,$delhunk) if scalar @$delhunk; + push @$retval,marktags($ADDMARKOPEN,$ADDMARKCLOSE,$ADDOPEN,$ADDCLOSE,"","",$ADDCOMMENT,$addhunk) if scalar @$addhunk; + + + if ($verbose) { + print STDERR "\n"; + print STDERR " $mattokcnt matching tokens. \n"; + print STDERR " $deltokcnt discarded tokens in $delblkcnt blocks.\n"; + print STDERR " $addtokcnt appended tokens in $addblkcnt blocks.\n"; + } + + return(@$retval); +} + +# marktags($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,\@block) +# returns ($openmark,$open,$block,$close,$closemark) if @block only contains no commands (except white-listed ones), +# braces, ampersands, or comments +# mark comments with $comment +# exclude all other exceptions from scope of open, close like this +# ($openmark, $open,...,$close, $opencmd,command, command,$closecmd, $open, ..., $close, $closemark) +# If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block +sub marktags { + my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; + my $word; + my (@argtext); + my $retval=[]; + my $noncomment=0; + my $cmd=-1; # -1 at beginning 0: last token written is a ordinary word + # 1: last token written is a command + # for keeping track whether we are just in a command sequence or in a word sequence + my $cmdcomment= ($opencmd =~ m/^%/); # Flag to indicate whether opencmd is a comment (i.e. if we intend to simply comment out changed commands) + my ($command,$commandword,$closingbracket) ; # temporary variables needed below to remember sub-pattern matches + +# split this block to flatten out sequences joined in pass1 + @$block=splitlatex(join "",@$block); + foreach (@$block) { + $word=$_; + if ( $word =~ s/^%/%$comment/ ) { + # a comment + if ($cmd==1) { + push (@$retval,$closecmd) ; + $cmd=-1; + } + push (@$retval,$word); + next; + } + if (! $noncomment) { + push (@$retval,$openmark); + $noncomment=1; + } + # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns + # also note that second pattern will match \\ + # Note: the second pattern should really be $word =~ /^\\(?!\()(\\|[\w*@]+)/, ie * replaced by + + # and then all commands \" \' etc declared safe. But as I don't have a complete list of one letter + # commands, and nobody has complained so far, I will eave this as is + if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()(\\|[\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { + # word is a command or other significant token (not in SAFECMDLIST) + ## same conditions as in subroutine extractcommand: + # check if token is an alphanumeric command sequence with at least one non-optional argument + # \cmd[...]{...}{last argument} + # Capturing in the following results in these associations + # $1: \cmd[...]{...}{ + # $2: cmd + # $3: last argument + # $4: } + trailing spaces + ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat6\})*\{)($pat6)(\}\s*)$/so ) + if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && (iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL)|| iscmd($2,\@MATHTEXTCMDLIST,\@MATHTEXTCMDEXCL)) + && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { + # Condition 1: word is a command? - if yes, $1,$2,.. will be set as above + # Condition 2: word is a text command - we mark up the interior of the word. There is a separate check for MATHTEXTCMDLIST + # because for $mathmarkup=WHOLE, the commands should not be split in pass1 (ie. math mode commands are not in + # TEXTCMDLIST, but the interior of MATHTEXT commands should be highlighted in both deleted and added blocks + # Condition 3: But if we are in a deleted block ($cmdcomment=1) and + # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) + # Because we do not want to disable this command + # here we do not use $opencmd and $closecmd($opencmd is empty) + if ($cmd==1) { + push (@$retval,$closecmd) ; + } elsif ($cmd==0) { + push (@$retval,$close) ; + } + $command=$1; $commandword=$2; $closingbracket=$4; + @argtext=splitlatex($3); # split textual argument into tokens + # and mark it up (but we do not need openmark and closemark) + # insert command with initial arguments, marked-up final argument, and closing bracket + if ( $cmdcomment && iscmd($commandword,\@CONTEXT1CMDLIST, \@CONTEXT1CMDEXCL) ) { + # context1cmd in a deleted environment; delete command itself but keep last argument, marked up + push (@$retval,$opencmd); + $command =~ s/\n/\n${opencmd}/sg ; # repeat opencmd at the beginning of each line + # argument, note that the additional comment character is included + # to suppress linebreak after opening parentheses, which is important + # for latexrevise + push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); + } elsif ( iscmd($commandword,,\@MATHTEXTCMDLIST, \@MATHTEXTCMDEXCL) ) { + # MATHBLOCK pseudo command: consider all commands safe, except & and \\ + # Keep these commands even in deleted blocks, hence set $opencmd and $closecmd (5th and 6th argument of marktags) to + # "" + local @SAFECMDLIST=(".*"); + local @SAFECMDEXCL=('\\','\\\\'); + push(@$retval,$command,marktags("","",$open,$close,"","",$comment,\@argtext)#@argtext + ,$closingbracket); + } else { + # normal textcmd or context1cmd in an added block + push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); + } + push (@$retval,$AUXCMD,"\n") if $cmdcomment ; + $cmd=-1 ; + } else { + # ordinary command + push (@$retval,$opencmd) if $cmd==-1 ; + push (@$retval,$close,$opencmd) if $cmd==0 ; + $word =~ s/\n/\n${opencmd}/sg if $cmdcomment ; # if opencmd is a comment, repeat this at the beginning of every line + push (@$retval,$word); + $cmd=1; + } + } else { + # just an ordinary word or word in SAFECMD + push (@$retval,$open) if $cmd==-1 ; + push (@$retval,$closecmd,$open) if $cmd==1 ; + push (@$retval,$word); + $cmd=0; + } + } + push (@$retval,$close) if $cmd==0; + push (@$retval,$closecmd) if $cmd==1; + + push (@$retval,$closemark) if ($noncomment); + return @$retval; +} + +# preprocess($string, ..) +# carry out the following pre-processing steps for all arguments: +# 1. Remove leading white-space +# Change \{ to \LEFTBRACE and \} to \RIGHTBRACE +# #. change begin and end commands within comments to BEGINDIF, ENDDIF +# so they don't disturb the pattern matching (if there are several \begin or \end in one line +# 2. mark all first empty line (in block of several) with \PAR tokens +# 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier +# 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) +# into \verb{hash} +# 5. Convert \begin{verbatim} some verbatim text \end{verbatim} into \verbatim{hash} +# 6. Convert _n into \SUBSCRIPTNB{n} and _{nnn} into \SUBSCRIPT{nn} +# 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} +# 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} +# b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} +# 9. Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv +# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH} +# into \MATHBLOCKmath{...} commands, where MATH/math is any valid math environment + +# 10. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. +# +# NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file +# names or labels but it does not matter because they are converted back in the postprocessing step +# Returns: leading white space removed in step 1 +sub preprocess { + my @leadin=() ; + for (@_) { + s/^(\s*)//s; + push(@leadin,$1); + # Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE + s/(?{$hstr}) && $string ne $hash->{$hstr}) { + warn "Repeated hash value for verbatim mode in spite of different content."; + $hstr="-$hstr"; + } + $hash->{$hstr}=$string; + return($hstr); +} + +#string=fromhash(\%hash,$fromstring) +# restores string value stored in hash +#string=fromhash(\%hash,$fromstring,$prependstring) +# additionally begins each line with prependstring +sub fromhash { + my ($hash,$hstr)=($_[0],$_[1]); + my $retstr=$hash->{$hstr}; + if ( $#_ >= 2) { + $retstr =~ s/^/$_[2]/mg; + } + return $retstr; +} + + +# postprocess($string, ..) +# carry out the following post-processing steps for all arguments: +# * Remove STOP token from the end +# * Replace \RIGHTBRACE by } +# * change citation commands within comments to protect from processing (using marker CITEDIF) +# 1. Check all deleted blocks: +# a.where a deleted block contains a matching \begin and +# \end environment (these will be disabled by a %DIFDELCMD statements), for selected environments enable +# these commands again (such that for example displayed math in a deleted equation +# is properly within math mode. For math mode environments replace numbered equation +# environments with their display only variety (so that equation numbers in new file and +# diff file are identical). Where the correct type of math environment cannot be determined +# use a place holder MATHMODE +# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement +# subtracting one from the respective counter to keep numbering consistent with new file +# Replace all MATHMODE environment commands by the correct environment to achieve matching +# pairs +# c. Convert MATHBLOCKmath commands to their uncounted numbers (e.g. convert equation -> displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL +# d. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# For added blocks: +# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# 2. If --block-math-markup option set: Convert \MATHBLOCKmath{..} commands back to environments +# +# Convert all PICTUREblock{..} commands back to the appropriate environments +# 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties +# within floats (currently recognised float environments: plate,table,figure +# plus starred varieties). +# 4. Remove empty %DIFDELCMD < lines +# 4. Convert \begin{SQUAREBRACKET} \end{SQUAREBRACKET} into \[ \] +# Convert \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} into $$ $$ +# 5. Convert \SUPERSCRIPTNB{n} into ^n and \SUPERSCRIPT{nn} into ^{nnn} +# 6. Convert \SUBSCRIPTNB{n} into _n and \SUBCRIPT{nn} into _{nnn} +# 7. Expand hashes of verb and verbatim environments +# 8. Convert '\PERCENTAGE ' back into '\%' +# 9.. remove all \PAR tokens +# 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always +# on a line by themselves, similarly for table environment +# 4, undo renaming of the \begin and \end in comments +# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\} +# +# Note have to manually synchronize substitution commands below and +# DIF.. command names in the header +sub postprocess { + my ($begin,$len,$cnt,$float,$delblock,$addblock); + # second level blocks + my ($begin2,$cnt2,$len2,$eqarrayblock,$mathblock); + + for (@_) { + + # change $'s in comments to something harmless + 1 while s/(%.*)\$/$1DOLLARDIF/mg ; + + # Remove final STOP token + s/ STOP$//; + # Replace \RIGHTBRACE by } + s/\\RIGHTBRACE/}/g; + + # change citation commands within comments to protect from processing + if ($CITECMD){ + 1 while s/(%.*)\\($CITECMD)/$1\\CITEDIF$2/m ; + } + # Check all deleted blocks: where a deleted block contains a matching \begin and + # \end environment (these will be disabled by a %DIFDELCMD statements), enable + # these commands again (such that for example displayed math in a deleted equation + # is properly within math mode. For math mode environments replace numbered equation + # environments with their display only variety (so that equation numbers in new file and + # diff file are identical + while ( m/\\DIFdelbegin.*?\\DIFdelend/sg ) { + $cnt=0; + $len=length($&); + $begin=pos($_) - $len; + $delblock=$&; + + + ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in + ### an error + # displayed math environments + if ($mathmarkup == FINE ) { + $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}.*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; + # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above + ### pre-0.42 obsolete version which did not work on eqnarray test $delblock=~ s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL + $delblock=~ s/\\MATHBLOCK($MATHENV)\{($pat6)\}/\\MATHBLOCK$MATHREPL\{$2\}/sg; + $delblock=~ s/\\MATHBLOCK($MATHARRENV)\{($pat6)\}/\\MATHBLOCK$MATHARRREPL\{$2\}/sg; + } + + +# b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement +# subtracting one from the respective counter to keep numbering consistent with new file + $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + + +# c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es + while ( $delblock =~ m/($math)(\s*)/sg ) { + $cnt2=0; + $len2=length($&); + $begin2=pos($delblock) - $len2; + $mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n"; + next unless $mathblock =~ m/\{$ARRENV\}/ ; + substr($delblock,$begin2,$len2)=$mathblock; + pos($delblock) = $begin2 + length($mathblock); + } + if ($CITE2CMD) { + $delblock=~s/($DELCMDOPEN\s*\\($CITE2CMD)(.*)$DELCMDCLOSE)/ + # Replacement code + {my ($aux,$all); + $aux=$all=$1; + $aux=~s#\n?($DELCMDOPEN|$DELCMDCLOSE)##g; + $all."$aux$AUXCMD\n";}/sge; + } + # or protect \cite commands with \mbox + if ($CITECMD) { + $delblock=~s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat6\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } +# splice in modified delblock + substr($_,$begin,$len)=$delblock; + pos = $begin + length($delblock); + } + # make the array modification in added blocks + while ( m/\\DIFaddbegin.*?\\DIFaddend/sg ) { + $cnt=0; + $len=length($&); + $begin=pos($_) - $len; + $addblock=$&; + while ( $addblock =~ m/($math)(\s*)/sg ) { + $cnt2=0; + $len2=length($&); + $begin2=pos($addblock) - $len2; + $mathblock="%\n\\mbox{$AUXCMD\n$1\n}$AUXCMD\n"; + next unless $mathblock =~ m/\{$ARRENV\}/ ; + substr($addblock,$begin2,$len2)=$mathblock; + pos($addblock) = $begin2 + length($mathblock); + } + if ($CITECMD) { + my $addblockbefore=$addblock; + $addblock=~ s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat2\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } +# splice in modified addblock + substr($_,$begin,$len)=$addblock; + pos = $begin + length($addblock); + } + + + ### old place for BEGINDIF, ENDDIF replacement + # change begin and end commands within comments such that they + # don't disturb the pattern matching (if there are several \begin or \end in one line + # this substitution is insufficient but that appears unlikely) + # This needs to be repeated here to also get rid of DIFdelcmd-protected environments + s/(%.*)\\begin\{(.*)$/$1\\BEGINDIF\{$2/mg ; + s/(%.*)\\end\{(.*)$/$1\\ENDDIF\{$2/mg ; + + # Replace MATHMODE environments from step 1a above by the correct Math environment + + # The next line is complicated. The negative look-ahead insertion makes sure that no \end{$MATHENV} (or other mathematical + # environments) are between the \begin{$MATHENV} and \end{MATHMODE} commands. This is necessary as the minimal matching + # is not globally minimal but only 'locally' (matching is beginning from the left side of the string) + if ( $mathmarkup == FINE ) { + 1 while s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}((?:.(?!(?:\\end{(?:(?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}|\\begin{MATHMODE})))*?)\\end{MATHMODE}/\\begin{$1}$2\\end{$1}/s; + 1 while s/\\begin{MATHMODE}((?:.(?!\\end{MATHMODE}))*?)\\end{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}/\\begin{$2}$1\\end{$2}/s; + # convert remaining \begin{MATHMODE} \end{MATHMODE} (and not containing & or \\ )into MATHREPL environments + s/\\begin{MATHMODE}((?:(.(?!(?[1])) { + $optargnew=$newhash{$cmd}->[1]; + } else { + $optargnew=""; + } + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + } else { + $optargold=""; + } + + if ( defined($oldhash{$cmd}) ) { + $argold=$oldhash{$cmd}->[2]; + } else { + $argold=""; + } + $argnew=$newhash{$cmd}->[2]; + $argdiff="{" . join("",bodydiff($argold,$argnew)) ."}"; + if ( length $optargnew ) { + $optargdiff="[".join("",bodydiff($optargold,$optargnew))."]" ; + $optargdiff =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g; + $optargdiff =~ s/\\DIFaddend /\\DIFaddendFL /g; + $optargdiff =~ s/\\DIFadd\{/\\DIFaddFL{/g; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + ### print STDERR "DEBUG s/\\Q$newhash{$cmd}->[0]\\E/\\$cmd$optargdiff$argdiff/s\n"; + # Note: \Q and \E force literal interpretation of what it between them but allow + # variable interpolation, such that e.g. \title matches just that and not TAB-itle + $$newpreambleref=~s/\Q$newhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s; + # replace this in old preamble if necessary + if ( defined($oldhash{$cmd}->[0])) { + $$oldpreambleref=~s/\Q$oldhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s ; + } + ### print STDERR "DEBUG NEW PRE ".$$newpreambleref."\n"; + } + + foreach $cmd ( keys %oldhash ) { + # if this has already been dealt with above can just skip + next if defined($newhash{$cmd}) ; + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + $optargdiff="[".join("",bodydiff($optargold,""))."]" ; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + $argdiff="{" . join("",bodydiff($argold,"")) ."}"; + $auxline = "\\$cmd$optargdiff$argdiff"; + $auxline =~s/$/$AUXCMD/sg; + push @auxlines,$auxline; + } + # add auxcmd comment to highlight added lines + return(@auxlines); +} + + + +# @diffs=linediff(\@seq1, \@seq2) +# mark up lines like this +#%DIF mm-mmdnn +#%< old deleted line(s) +#%DIF ------- +#%DIF mmann-nn +#new appended line %< +#%DIF ------- +# Future extension: mark change explicitly +# Assumes: traverse_sequence traverses deletions before insertions in changed sequences +# all line numbers relative to line 0 (first line of real file) +sub linediff { + my $seq1 = shift ; + my $seq2 = shift ; + + my $block = []; + my $retseq = []; + my @begin=('','',''); # dummy initialisation + my $instring ; + + my $discard = sub { @begin=('d',$_[0],$_[1]) unless scalar @$block ; + push(@$block, "%DIF < " . $seq1->[$_[0]]) }; + my $add = sub { if (! scalar @$block) { + @begin=('a',$_[0],$_[1]) ;} + elsif ( $begin[0] eq 'd' ) { + $begin[0]='c'; $begin[2]=$_[1]; + push(@$block, "%DIF -------") } + push(@$block, $seq2->[$_[1]] . " %DIF > " ) }; + my $match = sub { if ( scalar @$block ) { + if ( $begin[0] eq 'd' && $begin[1]!=$_[0]-1) { + $instring = sprintf "%%DIF %d-%dd%d",$begin[1],$_[0]-1,$begin[2]; } + elsif ( $begin[0] eq 'a' && $begin[2]!=$_[1]-1) { + $instring = sprintf "%%DIF %da%d-%d",$begin[1],$begin[2],$_[1]-1; } + elsif ( $begin[0] eq 'c' ) { + $instring = sprintf "%%DIF %sc%s", + ($begin[1]==$_[0]-1) ? "$begin[1]" : $begin[1]."-".($_[0]-1) , + ($begin[2]==$_[1]-1) ? "$begin[2]" : $begin[2]."-".($_[1]-1) ; } + else { + $instring = sprintf "%%DIF %d%s%d",$begin[1],$begin[0],$begin[2]; } + push @$retseq, $instring,@$block, "%DIF -------" ; + $block = []; + } + push @$retseq, $seq2->[$_[1]] + }; + # key function: remove multiple spaces (such that insertion or deletion of redundant white space is not reported) + my $keyfunc = sub { join(" ",split(" ",shift())) }; + + traverse_sequences($seq1,$seq2, { MATCH=>$match, DISCARD_A=>$discard, DISCARD_B=>$add }, $keyfunc ); + push @$retseq, @$block if scalar @$block; + + return wantarray ? @$retseq : $retseq ; +} + + + +# init_regex_arr_data(\@array,"TOKEN INIT") +# scans DATA file handel for line "%% TOKEN INIT" line +# then appends each line not beginning with % into array (as a quoted regex) +sub init_regex_arr_data { + my ($arr,$token)=@_; + my ($copy); + while () { + if ( m/^%%BEGIN $token\s*$/ ) { + $copy=1; } + elsif ( m/^%%END $token\s*/ ) { + last; } + chomp; + push (@$arr,qr/^$_$/) if ( $copy && !/^%/ ) ; + } + seek DATA,0,0; # rewind DATA handle to file begin +} + + +# init_regex_arr_ext(\@array,$arg) +# fills array with regular expressions. +# if arg is a file name, then read in list of regular expressions from that file +# (one expression per line) +# Otherwise treat arg as a comma separated list of regular expressions +sub init_regex_arr_ext { + my ($arr,$arg)=@_; + my $regex; + if ( -f $ arg ) { + open(FILE,"$arg") or die ("Couldn't open $arg: $!"); + while () { + chomp; + next if /^\s*#/ || /^\s*%/ || /^\s*$/ ; + push (@$arr,qr/^$_$/); + } + close(FILE); + } + else { + # assume it is a comma-separated list of reg-ex + foreach $regex (split(qr/(?=1) { + $reset=shift; + } + if ($reset) { + $lasttime=times(); + } + else { + $retval=times()-$lasttime; + $lasttime=$lasttime+$retval; + return($retval); + } +} + + +sub usage { + die <<"EOF"; +Usage: $0 [options] old.tex new.tex > diff.tex + +Compares two latex files and writes tex code to stdout, which has the same +format as new.tex but has all changes relative to old.tex marked up or commented. + +--type=markupstyle +-t markupstyle Add code to preamble for selected markup style + Available styles: UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE + CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR + [ Default: UNDERLINE ] + +--subtype=markstyle +-s markstyle Add code to preamble for selected style for bracketing + commands (e.g. to mark changes in margin) + Available styles: SAFE MARGINAL DVIPSCOL COLOR + [ Default: SAFE ] + +--floattype=markstyle +-f markstyle Add code to preamble for selected style which + replace standard marking and markup commands within floats + (e.g., marginal remarks cause an error within floats + so marginal marking can be disabled thus) + Available styles: FLOATSAFE IDENTICAL + [ Default: FLOATSAFE ] + +--encoding=enc +-e enc Specify encoding of old.tex and new.tex. Typical encodings are + ascii, utf8, latin1, latin9. A list of available encodings can be + obtained by executing + perl -MEncode -e 'print join ("\\n",Encode->encodings( ":all" )) ;' + [Default encoding is utf8 unless the first few lines of the preamble contain + an invocation "\\usepackage[..]{inputenc} in which case the + encoding chosen by this command is asssumed. Note that ASCII (standard + latex) is a subset of utf8] + +--preamble=file +-p file Insert file at end of preamble instead of auto-generating + preamble. The preamble must define the following commands + \\DIFaddbegin,\\DIFaddend,\\DIFadd{..}, + \\DIFdelbegin,\\DIFdelend,\\DIFdel{..}, + and varieties for use within floats + \\DIFaddbeginFL,\\DIFaddendFL,\\DIFaddFL{..}, + \\DIFdelbeginFL,\\DIFdelendFL,\\DIFdelFL{..} + (If this option is set -t, -s, and -f options + are ignored.) + +--exclude-safecmd=exclude-file +--exclude-safecmd="cmd1,cmd2,..." +-A exclude-file +--replace-safecmd=replace-file +--append-safecmd=append-file +--append-safecmd="cmd1,cmd2,..." +-a append-file Exclude from, replace or append to the list of regex + matching commands which are safe to use within the + scope of a \\DIFadd or \\DIFdel command. The file must contain + one Perl-RegEx per line (Comment lines beginning with # or % are + ignored). A literal comma within the comma-separated list must be + escaped thus "\\,", Note that the RegEx needs to match the whole of + the token, i.e., /^regex\$/ is implied and that the initial + "\\" of the command is not included. The --exclude-safecmd + and --append-safecmd options can be combined with the --replace-safecmd + option and can be used repeatedly to add cumulatively to the lists. + +--exclude-textcmd=exclude-file +--exclude-textcmd="cmd1,cmd2,..." +-X exclude-file +--replace-textcmd=replace-file +--append-textcmd=append-file +--append-textcmd="cmd1,cmd2,..." +-x append-file Exclude from, replace or append to the list of regex + matching commands whose last argument is text. See + entry for --exclude-safecmd directly above for further details. + +--replace-context1cmd=replace-file +--append-context1cmd=append-file +--append-context1cmd="cmd1,cmd2,..." + Replace or append to the list of regex matching commands + whose last argument is text but which require a particular + context to work, e.g. \\caption will only work within a figure + or table. These commands behave like text commands, except when + they occur in a deleted section, when they are disabled, but their + argument is shown as deleted text. + +--replace-context2cmd=replace-file +--append-context2cmd=append-file +--append-context2cmd="cmd1,cmd2,..." + As corresponding commands for context1. The only difference is that + context2 commands are completely disabled in deleted sections, including + their arguments. + + +--config var1=val1,var2=val2,... +-c var1=val1,.. Set configuration variables. +-c configfile Available variables: + MINWORDSBLOCK (integer) + FLOATENV (RegEx) + PICTUREENV (RegEx) + MATHENV (RegEx) + MATHREPL (String) + MATHARRENV (RegEx) + MATHARRREPL (String) + ARRENV (RegEx) + COUNTERCMD (RegEx) + This option can be repeated. + + +--packages=pkg1,pkg2,.. + Tell latexdiff that .tex file is processed with the packages in list + loaded. This is normally not necessary if the .tex file includes the + preamble, as the preamble is automatically scanned for \\usepackage commands. + Use of the --packages option disables automatic scanning, so if for any + reason package specific parsing needs to be switched off, use --packages=none. + The following packages trigger special behaviour: + endfloat hyperref amsmath + [ Default: scan the preamble for \\usepackage commands to determine + loaded packages.] + +--show-preamble Print generated or included preamble commands to stdout. + +--show-safecmd Print list of regex matching and excluding safe commands. + +--show-textcmd Print list of regex matching and excluding commands with text argument. + +--show-config Show values of configuration variables + +--show-all Show all of the above + + NB For all --show commands, no old.tex or new.tex file needs to be given, and no + differencing takes place. + +Other configuration options: + +--allow-spaces Allow spaces between bracketed or braced arguments to commands + [Default requires arguments to directly follow each other without + intervening spaces] + +--math-markup=level Determine granularity of markup in displayed math environments: + Possible values for level are (both numerical and text labels are acceptable): + off or 0: suppress markup for math environments. Deleted equations will not + appear in diff file. This mode can be used if all the other modes + cause invalid latex code. + whole or 1: Differencing on the level of whole equations. Even trivial changes + to equations cause the whole equation to be marked changed. This + mode can be used if processing in coarse or fine mode results in + invalid latex code. + coarse or 2: Detect changes within equations marked up with a coarse + granularity; changes in equation type (e.g.displaymath to equation) + appear as a change to the complete equation. This mode is recommended + for situations where the content and order of some equations are still + being changed. [Default] + fine or 3: Detect small change in equations and mark up and fine granularity. + This mode is most suitable, if only minor changes to equations are + expected, e.g. correction of typos. + +--disable-citation-markup Suppress citation markup in styles using ulem (UNDERLINE, + FONTSTRIKE, CULINECHBAR) +--enable-citation-markup Protect citation commands in changed sections with \\mbox command + [i.e. use default behaviour for ulem package for other packages] + +Miscelleneous options + +--label=label +-L label Sets the labels used to describe the old and new files. The first use + of this option sets the label describing the old file and the second + use of the option sets the label for the new file. + [Default: use the filename and modification dates for the label] + +--no-label Suppress inclusion of old and new file names as comment in output file + +--visble-label Include old and new filenames (or labels set with --label option) as + visible output + +--flatten Replace \\input and \\include commands within body by the content + of the files in their argument. If \\includeonly is present in the + preamble, only those files are expanded into the document. However, + no recursion is done, i.e. \\input and \\include commands within + included sections are not expanded. The included files are assumed to + be located in the same directories as the old and new master files, + respectively, making it possible to organise files into old and new directories. + --flatten is applied recursively, so inputted files can contain further + \\input statements. + +--help +-h Show this help text. + +--ignore-warnings Suppress warnings about inconsistencies in length between input + and parsed strings and missing characters. + +--verbose +-V Output various status information to stderr during processing. + Default is to work silently. + +--version Show version number. + +For further information, consult http://latexdiff.berlios.de +EOF +} + +=head1 NAME + +latexdiff - determine and markup differences between two latex files + +=head1 SYNOPSIS + +B [ B ] F F > F + +=head1 DESCRIPTION + +Briefly, I is a utility program to aid in the management of +revisions of latex documents. It compares two valid latex files, here +called C and C, finds significant differences +between them (i.e., ignoring the number of white spaces and position +of line breaks), and adds special commands to highlight the +differences. Where visual highlighting is not possible, e.g. for changes +in the formatting, the differences are +nevertheless marked up in the source. + +The program treats the preamble differently from the main document. +Differences between the preambles are found using line-based +differencing (similarly to the Unix diff command, but ignoring white +spaces). A comment, "S>>" is appended to each added line, i.e. a +line present in C but not in C. Discarded lines + are deactivated by prepending "S>>". Changed blocks are preceded by +comment lines giving information about line numbers in the original files. Where there are insignificant +differences, the resulting file C will be similar to +C. At the end of the preamble, the definitions for I markup commands are inserted. +In differencing the main body of the text, I attempts to +satisfy the following guidelines (in order of priority): + +=over 3 + +=item 1 + +If both C and C are valid LaTeX, then the resulting +C should also be valid LateX. (NB If a few plain TeX commands +are used within C or C then C is not +guaranteed to work but usually will). + +=item 2 + +Significant differences are determined on the level of +individual words. All significant differences, including differences +between comments should be clearly marked in the resulting source code +C. + +=item 3 + +If a changed passage contains text or text-producing commands, then +running C through LateX should produce output where added +and discarded passages are highlighted. + +=item 4 + +Where there are insignificant differences, e.g. in the positioning of +line breaks, C should follow the formatting of C + +=back + +For differencing the same algorithm as I is used but words +instead of lines are compared. An attempt is made to recognize +blocks which are completely changed such that they can be marked up as a unit. +Comments are differenced line by line +but the number of spaces within comments is ignored. Commands including +all their arguments are generally compared as one unit, i.e., no mark-up +is inserted into the arguments of commands. However, for a selected +number of commands (for example, C<\caption> and all sectioning +commands) the last argument is known to be text. This text is +split into words and differenced just as ordinary text (use options to +show and change the list of text commands, see below). As the +algorithm has no detailed knowledge of LaTeX, it assumes all pairs of +curly braces immediately following a command (i.e. a sequence of +letters beginning with a backslash) are arguments for that command. +As a restriction to condition 1 above it is thus necessary to surround +all arguments with curly braces, and to not insert +extraneous spaces. For example, write + + \section{\textem{This is an emphasized section title}} + +and not + + \section {\textem{This is an emphasized section title}} + +or + + \section\textem{This is an emphasized section title} + +even though all varieties are the same to LaTeX (but see +B<--allow-spaces> option which allows the second variety). + +For environments whose content does not conform to standard LaTeX or +where graphical markup does not make sense all markup commands can be +removed by setting the PICTUREENV configuration variable, set by +default to C and C environments; see B<--config> +option). The latter environment (C) can be used to +protect parts of the latex file where the markup results in illegal +markup. You have to surround the offending passage in both the old and +new file by C<\begin{DIFnomarkup}> and C<\end{DIFnomarkup}>. You must +define the environment in the preambles of both old and new +documents. I prefer to define it as a null-environment, + +C<\newenvironment{DIFnomarkup}{}{}> + +but the choice is yours. Any markup within the environment will be +removed, and generally everything within the environment will just be +taken from the new file. + +It is also possible to difference files which do not have a preamble. + In this case, the file is processed in the main document +mode, but the definitions of the markup commands are not inserted. + +All markup commands inserted by I begin with "C<\DIF>". Added +blocks containing words, commands or comments which are in C +but not in C are marked by C<\DIFaddbegin> and C<\DIFaddend>. +Discarded blocks are marked by C<\DIFdelbegin> and C<\DIFdelend>. +Within added blocks all text is highlighted with C<\DIFadd> like this: +C<\DIFadd{Added text block}> +Selected `safe' commands can be contained in these text blocks as well +(use options to show and change the list of safe commands, see below). +All other commands as well as braces "{" and "}" are never put within +the scope of C<\DIFadd>. Added comments are marked by prepending +"S >>". + +Within deleted blocks text is highlighted with C<\DIFdel>. Deleted +comments are marked by prepending "S >>". Non-safe command +and curly braces within deleted blocks are commented out with +"S >>". + + + +=head1 OPTIONS + +=head2 Preamble + +The following options determine the visual markup style by adding the appropriate +command definitions to the preamble. See the end of this section for a description of +available styles. + +=over 4 + +=item B<--type=markupstyle> or +B<-t markupstyle> + +Add code to preamble for selected markup style. This option defines +C<\DIFadd> and C<\DIFdel> commands. +Available styles: + +C + +[ Default: C ] + +=item B<--subtype=markstyle> or +B<-s markstyle> + +Add code to preamble for selected style for bracketing +commands (e.g. to mark changes in margin). This option defines +C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. +Available styles: C + +[ Default: C ] + +=item B<--floattype=markstyle> or +B<-f markstyle> + +Add code to preamble for selected style which +replace standard marking and markup commands within floats +(e.g., marginal remarks cause an error within floats +so marginal marking can be disabled thus). This option defines all +C<\DIF...FL> commands. +Available styles: C + +[ Default: C ] + +=item B<--encoding=enc> or +B<-e enc> + +Specify encoding of old.tex and new.tex. Typical encodings are +C, C, C, C. A list of available encodings can be +obtained by executing + +Cencodings( ":all" )) ;' > + +[Default encoding is utf8 unless the first few lines of the preamble contain +an invocation C<\usepackage[..]{inputenc}> in which case the +encoding chosen by this command is asssumed. Note that ASCII (standard +latex) is a subset of utf8] + +=item B<--preamble=file> or +B<-p file> + +Insert file at end of preamble instead of generating +preamble. The preamble must define the following commands +C<\DIFaddbegin, \DIFaddend, \DIFadd{..}, +\DIFdelbegin,\DIFdelend,\DIFdel{..},> +and varieties for use within floats +C<\DIFaddbeginFL, \DIFaddendFL, \DIFaddFL{..}, +\DIFdelbeginFL, \DIFdelendFL, \DIFdelFL{..}> +(If this option is set B<-t>, B<-s>, and B<-f> options +are ignored.) + +=item B<--packages=pkg1,pkg2,..> + +Tell latexdiff that .tex file is processed with the packages in list +loaded. This is normally not necessary if the .tex file includes the +preamble, as the preamble is automatically scanned for C<\usepackage> commands. +Use of the B<--packages> option disables automatic scanning, so if for any +reason package specific parsing needs to be switched off, use B<--packages=none>. +The following packages trigger special behaviour: + +=over 8 + +=item C + +Configuration variable amsmath is set to C (Default: C) + +=item C + +Ensure that C<\begin{figure}> and C<\end{figure}> always appear by themselves on a line. + +=item C + +Change name of C<\DIFadd> and C<\DIFdel> commands to C<\DIFaddtex> and C<\DIFdeltex> and +define new C<\DIFadd> and C<\DIFdel> commands, which provide a wrapper for these commands, +using them for the text but not for the link defining command (where any markup would cause +errors). + +=back + +[ Default: scan the preamble for C<\\usepackage> commands to determine + loaded packages.] + + + +=item B<--show-preamble> + +Print generated or included preamble commands to stdout. + +=back + +=head2 Configuration + +=over 4 + +=item B<--exclude-safecmd=exclude-file> or +B<-A exclude-file> or B<--exclude-safecmd="cmd1,cmd2,..."> + +=item B<--replace-safecmd=replace-file> + +=item B<--append-safecmd=append-file> or +B<-a append-file> or B<--append-safecmd="cmd1,cmd2,..."> + +Exclude from, replace or append to the list of regular expressions (RegEx) +matching commands which are safe to use within the +scope of a C<\DIFadd> or C<\DIFdel> command. The file must contain +one Perl-RegEx per line (Comment lines beginning with # or % are +ignored). Note that the RegEx needs to match the whole of +the token, i.e., /^regex$/ is implied and that the initial +"\" of the command is not included. +The B<--exclude-safecmd> and B<--append-safecmd> options can be combined with the -B<--replace-safecmd> +option and can be used repeatedly to add cumulatively to the lists. + B<--exclude-safecmd> +and B<--append-safecmd> can also take a comma separated list as input. If a +comma for one of the regex is required, escape it thus "\,". In most cases it +will be necessary to protect the comma-separated list from the shell by putting +it in quotation marks. + +=item B<--exclude-textcmd=exclude-file> or +B<-X exclude-file> or B<--exclude-textcmd="cmd1,cmd2,..."> + +=item B<--replace-textcmd=replace-file> + +=item B<--append-textcmd=append-file> or +B<-x append-file> or B<--append-textcmd="cmd1,cmd2,..."> + +Exclude from, replace or append to the list of regular expressions +matching commands whose last argument is text. See +entry for B<--exclude-safecmd> directly above for further details. + + +=item B<--replace-context1cmd=replace-file> + +=item B<--append-context1cmd=append-file> or +=item B<--append-context1cmd="cmd1,cmd2,..."> + +Replace or append to the list of regex matching commands +whose last argument is text but which require a particular +context to work, e.g. \caption will only work within a figure +or table. These commands behave like text commands, except when +they occur in a deleted section, when they are disabled, but their +argument is shown as deleted text. + +=item B<--replace-context2cmd=replace-file> + +=item B<--append-context2cmd=append-file> or +=item B<--append-context2cmd="cmd1,cmd2,..."> +As corresponding commands for context1. The only difference is that +context2 commands are completely disabled in deleted sections, including +their arguments. + + + +=item B<--config var1=val1,var2=val2,...> or B<-c var1=val1,..> + +=item B<-c configfile> + +Set configuration variables. The option can be repeated to set different +variables (as an alternative to the comma-separated list). +Available variables (see below for further explanations): + +C (integer) + +C (RegEx) + +C (RegEx) + +C (RegEx) + +C (String) + +C (RegEx) + +C (String) + +C (RegEx) + +C (RegEx) + +=item B<--show-safecmd> + +Print list of RegEx matching and excluding safe commands. + +=item B<--show-textcmd> + +Print list of RegEx matching and excluding commands with text argument. + +=item B<--show-config> + +Show values of configuration variables. + +=item B<--show-all> + +Combine all --show commands. + +NB For all --show commands, no C or C file needs to be specified, and no +differencing takes place. + +=back + +=head2 Other configuration options: + +=over 4 + +=item B<--allow-spaces> + +Allow spaces between bracketed or braced arguments to commands. Note +that this option might have undesirable side effects (unrelated scope +might get lumpeded with preceding commands) so should only be used if the +default produces erroneous results. (Default requires arguments to +directly follow each other without intervening spaces). + +=item B<--math-markup=level> + +Determine granularity of markup in displayed math environments: +Possible values for level are (both numerical and text labels are acceptable): + +C or C<0>: suppress markup for math environments. Deleted equations will not +appear in diff file. This mode can be used if all the other modes +cause invalid latex code. + +C or C<1>: Differencing on the level of whole equations. Even trivial changes +to equations cause the whole equation to be marked changed. This +mode can be used if processing in coarse or fine mode results in +invalid latex code. + +C or C<2>: Detect changes within equations marked up with a coarse +granularity; changes in equation type (e.g.displaymath to equation) +appear as a change to the complete equation. This mode is recommended +for situations where the content and order of some equations are still +being changed. [Default] + +C or C<3>: Detect small change in equations and mark up at fine granularity. +This mode is most suitable, if only minor changes to equations are +expected, e.g. correction of typos. + +=item B<--disable-citation-markup> + +Suppress citation markup in styles using ulem (UNDERLINE, +FONTSTRIKE, CULINECHBAR) + +=item B<--enable-citation-markup> + +Protect citation commands in changed sections with \\mbox command [i.e. use default behaviour for ulem package for other packages] + +=back + +=head2 Miscellaneous + +=over 4 +=item B<--verbose> or B<-V> + +Output various status information to stderr during processing. +Default is to work silently. + +=item B<--driver=type> + +Choose driver for changebar package (only relevant for styles using + changebar: CCHANGEBAR CFONTCHBAR CULINECHBAR CHANGEBAR). Possible +drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops + [Default: dvips] + +=item B<--ignore-warnings> + +Suppress warnings about inconsistencies in length between input and +parsed strings and missing characters. These warning messages are +often related to non-standard latex or latex constructions with a +syntax unknown to C but the resulting difference argument +is often fully functional anyway, particularly if the non-standard +latex only occurs in parts of the text which have not changed. + +=item B<--label=label> or +B<-L label> + +Sets the labels used to describe the old and new files. The first use +of this option sets the label describing the old file and the second +use of the option sets the label for the new file, i.e. set both +labels like this C<-L labelold -L labelnew>. +[Default: use the filename and modification dates for the label] + +=item B<--no-label> + +Suppress inclusion of old and new file names as comment in output file + +=item B<--visble-label> + +Include old and new filenames (or labels set with --label option) as +visible output. + +=item B<--flatten> + +Replace C<\input> and C<\include> commands within body by the content +of the files in their argument. If C<\includeonly> is present in the +preamble, only those files are expanded into the document. However, +no recursion is done, i.e. C<\input> and C<\include> commands within +included sections are not expanded. The included files are assumed to + be located in the same directories as the old and new master files, +respectively, making it possible to organise files into old and new directories. +--flatten is applied recursively, so inputted files can contain further +C<\input> statements. + +Use of this option might result in prohibitive processing times for +larger documents, and the resulting difference document +no longer reflects the structure of the input documents. + +=item B<--help> or +B<-h> + +Show help text + +=item B<--version> + +Show version number + +=back + + + +=head2 Predefined styles + +=head2 Major types + +The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands C<\DIFadd{...}> and C<\DIFdel{...}> . + +=over 10 + +=item C + +Added text is wavy-underlined and blue, discarded text is struck out and red +(Requires color and ulem packages). Overstriking does not work in displayed math equations such that deleted parts of equation are underlined, not struck out (this is a shortcoming inherent to the ulem package). + +=item C + +Added text is blue and set in sans-serif, and a red footnote is created for each discarded +piece of text. (Requires color package) + +=item C + +Like C but without the use of color. + +=item C + +Added text is blue and set in sans-serif, and discarded text is red and very small size. + +=item C + +Added tex is set in sans-serif, discarded text small and struck out + +=item C + +Added text is blue, and discarded text is red. Additionally, the changed text is marked with a bar in the margin (Requires color and changebar packages). + +=item C + +Like C but with additional changebars (Requires color and changebar packages). + +=item C + +Like C but with additional changebars (Requires color, ulem and changebar packages). + +=item C + +No mark up of text, but mark margins with changebars (Requires changebar package). + +=item C + +No visible markup (but generic markup commands will still be inserted. + +=back + +=head2 Subtypes + +The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: C<\DIFaddbegin, \DIFaddend, \DIFdelbegin, \DIFdelend>) + +=over 10 + +=item C + +No additional markup (Recommended choice) + +=item C + +Mark beginning and end of changed blocks with symbols in the margin nearby (using +the standard C<\marginpar> command - note that this sometimes moves somewhat +from the intended position. + +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. +(It is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete, for example +with citation commands). + +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. Note +that C only works with the dvips converter, e.g. not pdflatex. +(it is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete). + +=back + +=head2 Float Types + +Some of the markup used in the main text might cause problems when used within +floats (e.g. figures or tables). For this reason alternative versions of all +markup commands are used within floats. The float type defines these alternative commands. + +=over 10 + +=item C + +Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is C as C<\marginpar> does not work properly within floats. + +=item C + +Mark additions the same way as in the main text. Deleted environments are marked by angular brackets \[ and \] and the deleted text is set in scriptscript size. This float type should always be used with the C and C markup types as the \footnote command does not work properly in floating environments. + +=item C + +Make no difference between the main text and floats. + +=back + + +=head2 Configuration Variables + +=over 10 + +=item C + +Minimum number of tokens required to form an independent block. This value is +used in the algorithm to detect changes of complete blocks by merging identical text parts of less than C to the preceding added and discarded parts. + +[ Default: 3 ] + +=item C + +Environments whose name matches the regular expression in C are +considered floats. Within these environments, the I markup commands +are replaced by their FL variaties. + +[ Default: S >] + +=item C + +Within environments whose name matches the regular expression in C +all latexdiff markup is removed (in pathologic cases this might lead to + inconsistent markup but this situation should be rare). + +[ Default: S >] + +=item C,C + +If both \begin and \end for a math environment (environment name matching C +or \[ and \]) +are within the same deleted block, they are replaced by a \begin and \end commands for C +rather than being commented out. + +[ Default: C=S >, C=S >] + +=item C,C + +as C,C but for equation arrays + +[ Default: C=S >, C=S >] + +=item C + +If a match to C is found within an inline math environment within a deleted or added block, then the inlined math +is surrounded by C<\mbox{>...C<}>. This is necessary as underlining does not work within inlined array environments. + +[ Default: C=S > + +=item C + +If a command in a deleted block which is also in the textcmd list matches C then an +additional command C<\addtocounter{>FC<}{-1}>, where F is the matching command, is appended in the diff file such that the numbering in the diff file remains synchronized with the +numbering in the new file. + +[ Default: C=C<(?:footnote|part|section|subsection> ... + +C<|subsubsection|paragraph|subparagraph)> ] + +=back + +=head1 COMMON PROBLEMS + +=over 10 + +=item Citations result in overfull boxes + +There is an incompatibility between the C package, which C uses for underlining and striking out in the UNDERLINE style, +the default style. In order to be able to mark up citations properly, they are placed with an C<\mbox> command in post-processing. As mboxes +cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities: + +1. Use C or C subtype markup (option C<-s COLOR>): If this markup is chosen, then changed citations are no longer marked up +with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color. + +2. Choose option C<--disable-citation-markup> which turns off the marking up of citations: deleted citations are no longer shown, and +added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older) + +=item Changes in complicated mathematical equations result in latex processing errors + +Try options C<--math-markup=whole>. If even that fails, you can turn off mark up for equations with C<--math-markup=off>. + +=back + +=head1 BUGS + +Option allow-spaces not implemented entirely consistently. It breaks +the rules that number and type of white space does not matter, as +different numbers of inter-argument spaces are treated as significant. + +Please submit bug reports on the latexdiff project page I, +send them to user discussion list C (prior subscription +to list required, also on project webpage) +or send them to I. Include the serial number of I +(from comments at the top of the source or use B<--version>). If you come across latex +files that are error-free and conform to the specifications set out +above, and whose differencing still does not result in error-free +latex, please send me those files, ideally edited to only contain the +offending passage as long as that still reproduces the problem. If your +file relies on non-standard class files, you must include those. I will not +look at examples where I have trouble to latex the original files. + +=head1 SEE ALSO + +L, L + +=head1 PORTABILITY + +I does not make use of external commands and thus should run +on any platform supporting Perl 5.6 or higher. If files with encodings +other than ASCII or UTF-8 are processed, Perl 5.8 or higher is required. + +The standard version of I requires installation of the Perl package +C (available from I - +I) but a stand-alone +version, I, which has this package inlined, is available, too. +I requires the I command to be present. + +=head1 AUTHOR + +Version 1.0.2 +Copyright (C) 2004-2012 Frederik Tilmann + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License Version 3 + +Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner, +T. Connors, Sebastian Gouezel and many others. +Thanks to the many people who send in bug reports, feature suggestions, and other feedback. + +=cut + +__END__ +%%BEGIN SAFE COMMANDS +% Regex matching commands which can safely be in the +% argument of a \DIFadd or \DIFdel command (leave out the \) +arabic +dashbox +emph +fbox +framebox +hspace +math.* +makebox +mbox +pageref +ref +symbol +raisebox +rule +text.* +shortstack +usebox +dag +ddag +copyright +pounds +S +P +oe +OE +ae +AE +aa +AA +o +O +l +L +frac +ss +sqrt +ldots +cdots +vdots +ddots +alpha +beta +gamma +delta +epsilon +varepsilon +zeta +eta +theta +vartheta +iota +kappa +lambda +mu +nu +xi +pi +varpi +rho +varrho +sigma +varsigma +tau +upsilon +phi +varphi +chi +psi +omega +Gamma +Delta +Theta +Lambda +Xi +Pi +Sigma +Upsilon +Phi +Psi +Omega +ps +mp +times +div +ast +star +circ +bullet +cdot +cap +cup +uplus +sqcap +vee +wedge +setminus +wr +diamond +(?:big)?triangle.* +lhd +rhd +unlhd +unrhd +oplus +ominus +otimes +oslash +odot +bigcirc +d?dagger +amalg +leq +prec +preceq +ll +(?:sq)?su[bp]set(?:eq)? +in +vdash +geq +succ(?:eq)? +gg +ni +dashv +equiv +sim(?:eq)? +asymp +approx +cong +neq +doteq +propto +models +perp +mid +parallel +bowtie +Join +smile +frown +.*arrow +(?:long)?mapsto +.*harpoon.* +leadsto +aleph +hbar +imath +jmath +ell +wp +Re +Im +mho +prime +emptyset +nabla +surd +top +bot +angle +forall +exists +neg +flat +natural +sharp +backslash +partial +infty +Box +Diamond +triangle +clubsuit +diamondsuit +heartsuit +spadesuit +sum +prod +coprod +int +oint +big(?:sq)?c[au]p +bigvee +bigwedge +bigodot +bigotimes +bigoplus +biguplus +(?:arc)?(?:cos|sin|tan|cot)h? +csc +arg +deg +det +dim +exp +gcd +hom +inf +ker +lg +lim +liminf +limsup +ln +log +max +min +Pr +sec +sup +(SUPER|SUB)SCRIPTNB +(SUPER|SUB)SCRIPT +%%END SAFE COMMANDS + +%%BEGIN TEXT COMMANDS +% Regex matching commands with a text argument (leave out the \) +addcontents.* +cc +closing +chapter +dashbox +emph +encl +fbox +framebox +footnote +footnotetext +framebox +part +(sub){0,2}section\*? +(sub)?paragraph\*? +makebox +mbox +opening +parbox +raisebox +savebox +sbox +shortstack +signature +text.* +value +underline +sqrt +(SUPER|SUB)SCRIPT +%%END TEXT COMMANDS + +%%BEGIN CONTEXT1 COMMANDS +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text +caption +%%END CONTEXT1 COMMANDS + +%%BEGIN CONTEXT2 COMMANDS +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text +title +author +date +institute +%%END CONTEXT2 COMMANDS + + +%% TYPES (Commands for highlighting changed blocks) + +%DIF UNDERLINE PREAMBLE +\RequirePackage[normalem]{ulem} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{{\protect\color{blue}\uwave{#1}}} +\providecommand{\DIFdel}[1]{{\protect\color{red}\sout{#1}}} +%DIF END UNDERLINE PREAMBLE + +%DIF CTRADITIONAL PREAMBLE +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\RequirePackage[stable]{footmisc} +\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} +\providecommand{\DIFdel}[1]{{\protect\color{red} [..\footnote{removed: #1} ]}} +%DIF END CTRADITIONAL PREAMBLE + +%DIF TRADITIONAL PREAMBLE +\RequirePackage[stable]{footmisc} +\providecommand{\DIFadd}[1]{{\sf #1}} +\providecommand{\DIFdel}[1]{{[..\footnote{removed: #1} ]}} +%DIF END TRADITIONAL PREAMBLE + +%DIF CFONT PREAMBLE +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{{\protect\color{blue} \sf #1}} +\providecommand{\DIFdel}[1]{{\protect\color{red} \scriptsize #1}} +%DIF END CFONT PREAMBLE + +%DIF FONTSTRIKE PREAMBLE +\RequirePackage[normalem]{ulem} +\providecommand{\DIFadd}[1]{{\sf #1}} +\providecommand{\DIFdel}[1]{{\footnotesize \sout{#1}}} +%DIF END FONTSTRIKE PREAMBLE + +%DIF CCHANGEBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}#1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}#1}\protect\cbdelete} +%DIF END CCHANGEBAR PREAMBLE + +%DIF CFONTCHBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\RequirePackage{color}\definecolor{RED}{rgb}{1,0,0}\definecolor{BLUE}{rgb}{0,0,1} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\sf #1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\scriptsize #1}\protect\cbdelete} +%DIF END CFONTCHBAR PREAMBLE + +%DIF CULINECHBAR PREAMBLE +\RequirePackage[normalem]{ulem} +\RequirePackage[dvips]{changebar} +\RequirePackage{color} +\providecommand{\DIFadd}[1]{\protect\cbstart{\protect\color{blue}\uwave{#1}}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete{\protect\color{red}\sout{#1}}\protect\cbdelete} +%DIF END CULINECHBAR PREAMBLE + +%DIF CHANGEBAR PREAMBLE +\RequirePackage[dvips]{changebar} +\providecommand{\DIFadd}[1]{\protect\cbstart{#1}\protect\cbend} +\providecommand{\DIFdel}[1]{\protect\cbdelete} +%DIF END CHANGEBAR PREAMBLE + +%DIF INVISIBLE PREAMBLE +\providecommand{\DIFadd}[1]{#1} +\providecommand{\DIFdel}[1]{} +%DIF END INVISIBLE PREAMBLE + + +%% SUBTYPES (Markers for beginning and end of changed blocks) + +%DIF SAFE PREAMBLE +\providecommand{\DIFaddbegin}{} +\providecommand{\DIFaddend}{} +\providecommand{\DIFdelbegin}{} +\providecommand{\DIFdelend}{} +%DIF END SAFE PREAMBLE + +%DIF MARGIN PREAMBLE +\providecommand{\DIFaddbegin}{\protect\marginpar{a[}} +\providecommand{\DIFaddend}{\protect\marginpar{]}} +\providecommand{\DIFdelbegin}{\protect\marginpar{d[}} +\providecommand{\DIFdelend}{\protect\marginpar{]}} +%DIF END BRACKET PREAMBLE + +%DIF DVIPSCOL PREAMBLE +%Note: only works with dvips converter +\RequirePackage{color} +\RequirePackage{dvipscol} +\providecommand{\DIFaddbegin}{\protect\nogroupcolor{blue}} +\providecommand{\DIFaddend}{\protect\nogroupcolor{black}} +\providecommand{\DIFdelbegin}{\protect\nogroupcolor{red}} +\providecommand{\DIFdelend}{\protect\nogroupcolor{black}} +%DIF END DVIPSCOL PREAMBLE + +%DIF COLOR PREAMBLE +\RequirePackage{color} +\providecommand{\DIFaddbegin}{\protect\color{blue}} +\providecommand{\DIFaddend}{\protect\color{black}} +\providecommand{\DIFdelbegin}{\protect\color{red}} +\providecommand{\DIFdelend}{\protect\color{black}} +%DIF END COLOR PREAMBLE + + +%% FLOAT TYPES + +%DIF FLOATSAFE PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} +\providecommand{\DIFaddbeginFL}{} +\providecommand{\DIFaddendFL}{} +\providecommand{\DIFdelbeginFL}{} +\providecommand{\DIFdelendFL}{} +%DIF END FLOATSAFE PREAMBLE + +%DIF IDENTICAL PREAMBLE +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdelFL}[1]{\DIFdel{#1}} +\providecommand{\DIFaddbeginFL}{\DIFaddbegin} +\providecommand{\DIFaddendFL}{\DIFaddend} +\providecommand{\DIFdelbeginFL}{\DIFdelbegin} +\providecommand{\DIFdelendFL}{\DIFdelend} +%DIF END IDENTICAL PREAMBLE + +%DIF TRADITIONALSAFE PREAMBLE +% procidecommand color to make this work for TRADITIONAL and CTRADITIONAL +\providecommand{\color}[1]{} +\providecommand{\DIFaddFL}[1]{\DIFadd{#1}} +\providecommand{\DIFdel}[1]{{\protect\color{red}[..{\scriptsize {removed: #1}} ]}} +\providecommand{\DIFaddbeginFL}{} +\providecommand{\DIFaddendFL}{} +\providecommand{\DIFdelbeginFL}{} +\providecommand{\DIFdelendFL}{} +%DIF END FLOATSAFE PREAMBLE + +%% SPECIAL PACKAGE PREAMBLE COMMANDS + +% Standard \DIFadd and \DIFdel are redefined as \DIFaddtex and \DIFdeltex +% when hyperref package is included. +%DIF HYPERREF PREAMBLE +\providecommand{\DIFadd}[1]{\texorpdfstring{\DIFaddtex{#1}}{#1}} +\providecommand{\DIFdel}[1]{\texorpdfstring{\DIFdeltex{#1}}{}} +%DIF END HYPERREF PACKAGE diff --git a/Master/texmf-dist/scripts/latexdiff/latexdiff-vc.pl b/Master/texmf-dist/scripts/latexdiff/latexdiff-vc.pl index 3e9a3f246de..16b0dea5e7d 100755 --- a/Master/texmf-dist/scripts/latexdiff/latexdiff-vc.pl +++ b/Master/texmf-dist/scripts/latexdiff/latexdiff-vc.pl @@ -1,41 +1,54 @@ -#!/usr/bin/perl -w -# Place the following 2 lines at beginning to make script independent of location of perl -#eval 'exec perl -w -S $0 ${1+"$@"}' -# if 0; # not running under some shell +#!/usr/bin/env perl # # latexdiff-vc - wrapper script for applying latexdiff to rcs managed files # and for automatised creation of postscript or pdf from difference file # -# Copyright (C) 2005 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2005-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) +# +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# # # Contributors: S Utcke, H Bruyninckx # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file # +# version 1.0.2: - option --so to use latexdiff-so +# version 1.0.1 (change version numbering to match that of latexdiff) +# - Option --fast to use latexdiff-fast, +# - git support (thanks to Bjørn Magnus Mathisen, Santi Béjar, Pietro Battiston and Stefan Alfredson for patches) - UNTESTED # version 0.25: # - bbl is allowed as alternative extension (instead of .tex) -# +# version 0.26a +# - Bug fix: it copes now correctly with the possibility that there are no changes between current +# and archived version use Getopt::Long ; use Pod::Usage qw/pod2usage/ ; use File::Temp qw/tempdir/ ; use File::Basename qw/dirname/; use strict ; +use warnings ; + +my $versionstring=< 1); my ($file1,$file2,$diff,$diffbase,$answer,$options,$infile,$append,$dirname,$cwd); my (@files,@ldoptions,@tmpfiles,@ptmpfiles,@difffiles); # , - Getopt::Long::Configure('pass_through','bundling'); GetOptions('revision|r:s' => \@revs, 'cvs' => \$cvs, 'rcs' => \$rcs, 'svn' => \$svn, + 'git' => \$git, 'dir|d:s' => \$dir, + 'fast' => \$fast, + 'so' => \$so, 'postscript|ps' => \$postscript, 'pdf' => \$pdf, 'force' => \$force, @@ -63,32 +78,47 @@ if ( $help ) { } if ( $version ) { - die "This is LATEXDIFF-VC 0.25\n" ; + die $versionstring ; +} + +if ( $so ) { + $latexdiff='latexdiff-so'; +} +if ( $fast ) { + die "Cannot specify more than one of --fast or --so " if ($so); + $latexdiff='latexdiff-fast'; } if ( $cvs ) { $vc="CVS"; } if ( $rcs ) { - die "Cannot specify more than one of --cvs, --rcs or --svn." if ($vc); + die "Cannot specify more than one of --cvs, --rcs --svn or --git." if ($vc); $vc="RCS"; } if ( $svn ) { - die "Cannot specify more than one of --cvs, --rcs or --svn." if ($vc); + die "Cannot specify more than one of --cvs, --rcs --svn or --git." if ($vc); $vc="SVN"; } +if ( $git ) { + die "Cannot specify more than one of --cvs, --rcs, --svn or --git." if ($vc); + $vc="GIT"; +} + -# check whether the first file name got misinterpreted as an option to an empty -r option -if ( @revs && -f $revs[$#revs] ) { +# check whether the first file name or first passed-through option for latexdiff got misinterpreted as an option to an empty -r option +if ( @revs && ( -f $revs[$#revs] || $revs[$#revs] =~ /^-/ ) ) { unshift @ARGV,$revs[$#revs]; $revs[$#revs]=""; } -# check whether the first file name got misinterpreted as an option to an empty -d option -if ( defined($dir) && -f $dir ) { +# check whether the first file name or first passed-through option for latexdiff got misinterpreted as an option to an empty -d option +if ( defined($dir) && ( -f $dir || $dir =~ /^-/ ) ) { unshift @ARGV,$dir; $dir=""; } +#print "DEBUG: latexdiff-vc command line: ", join(" ",@ARGV), "\n"; + $file2=pop @ARGV; ( defined($file2) && $file2 =~ /\.(tex|bbl)$/ ) or pod2usage("Must specify at least one tex or bbl file"); @@ -101,6 +131,8 @@ if (! $vc && scalar(@revs)>0 ) { $vc="RCS"; } elsif ( $0 =~ /-svn$/ ) { $vc="SVN"; + } elsif ( $0 =~ /-git$/ ) { + $vc="GIT"; } elsif ( -e "CVSROOT" || defined($ENV{"CVSROOT"}) ) { print STDERR "Guess you are using CVS ...\n"; $vc="CVS"; @@ -110,6 +142,9 @@ if (! $vc && scalar(@revs)>0 ) { } elsif ( -d ".svn" ) { print STDERR "Guess you are using SVN ...\n"; $vc="SVN"; + } elsif ( -d ".git" ) { + print STDERR "Guess you are using GIT ...\n"; + $vc="GIT"; } else { print STDERR "Cannot figure out version control system, so I default to CVS\n"; $vc="CVS"; @@ -117,7 +152,7 @@ if (! $vc && scalar(@revs)>0 ) { } if (defined($dir) && $dir=~/^\.\/?/ ) { - print STDERR "You wrote selected -dir=. but you do not really like to do that, do you ?\n"; + print STDERR "You wrote -dir=. but you do not really like to do that, do you ?\n"; exit 10 } @@ -131,6 +166,12 @@ if ( scalar(@revs)>0 ) { } elsif ( $vc eq "SVN" ) { $diffcmd = "svn diff -r "; $patchcmd = "patch -R -p0"; + } elsif ( $vc eq "GIT" ) { + $diffcmd = "git diff -r --relative --no-prefix "; + $patchcmd = "patch -R -p0"; + # alternatively: + # $diffcmd = "git diff "; + # $patchcmd = "patch -R -p1"; } else { print STDERR "Unknown versioning system $vc \n"; exit 10; @@ -189,13 +230,22 @@ while ( $infile=$file2=shift @files ) { ($file1=$infile) =~ s/\.(tex|bbl)/-oldtmp-$$.$1/ ; push @tmpfiles,$file1; # compare file with previous version ($revs[0]="") or specified version - system("$diffcmd$revs[0] $infile| $patchcmd -o$file1") ; + ### system("$diffcmd$revs[0] $infile| $patchcmd -o$file1") ; + if (system("$diffcmd$revs[0] $infile | $patchcmd -o$file1")==0 and -z $file1 ) { + # no differences detected, i.e. file is equal to current version + system("\cp $infile $file1"); + } } elsif ( scalar(@revs) == 2 ) { ($file1=$infile) =~ s/\.(tex|bbl)/-oldtmp-$$.$1/ ; $file2 =~ s/\.(tex|bbl)/-newtmp-$$.$1/ ; push @tmpfiles,$file2; - system("$diffcmd$revs[1] $infile | $patchcmd -o$file2") ; - system("$diffcmd$revs[0] $infile | $patchcmd -o$file1") ; + ; + if (system("$diffcmd$revs[1] $infile | $patchcmd -o$file2")==0 and -z $file2 ) { + system("\cp $infile $file2"); + } + if (system("$diffcmd$revs[0] $infile | $patchcmd -o$file1")==0 and -z $file1 ) { + system("\cp $infile $file1"); + }; } if ( -z $file1 || -z $file2) { @@ -315,7 +365,7 @@ B [ F ] [ F ][ B<--posts =head1 DESCRIPTION I is a wrapper script that applies I to a -file, or multiple files under version control (CVS or RCS), and optionally runs the +file, or multiple files under version control (CVS, RCS or SVN), and optionally runs the sequence of C and C or C commands necessary to produce pdf or postscript output of the difference tex file(s). It can also be applied to a pair of files to automatise the generation of difference @@ -325,7 +375,7 @@ file in postscript or pdf format. =over 4 -=item B<--rcs>, B<--svn>, or B<--cvs> +=item B<--rcs>, B<--svn>, B<--cvs>, or B<--git> Set the version system. If no version system is specified, latexdiff-vc will venture a guess. @@ -335,8 +385,8 @@ the respective versioning system. However, this default can still be overridden =item B<-r>, B<-r> F or B<--revision>, B<--revision=>F -Choose revision (under RCS, CVS or SVN). One or two B<-r> options can be -specified, and the resulting in different behaviour: +Choose revision (under RCS, CVS, SVN or GIT). One or two B<-r> options can be +specified, and they result in different behaviour: =over 4 @@ -372,6 +422,10 @@ to the original filename, creating the directory and subdirectories should they not exist already. This is particularly useful in order to clone a complete directory hierarchy. Optionally, a pathname F can be specified, which is prepended instead of C. +=item B<--fast> or B<--so> + +Use C or C, respectively (instead of C). + =item B<--ps> or B<--postscript> Generate postscript output from difference file. This will run the @@ -417,13 +471,19 @@ limited to Unix-like systems. It also requires the RCS version control system and latex to be installed on the system. Modules from Perl 5.8 or higher are required. +=head1 BUG REPORTING + Please submit bug reports through +the latexdiff project page I or send +to I. Include the serial number of I +(option C<--version>) +. =head1 AUTHOR -Copyright (C) 2005 Frederik Tilmann +Copyright (C) 2005,2012 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 Contributors: S Utcke, H Bruyninckx =cut diff --git a/Master/texmf-dist/scripts/latexdiff/latexdiff.pl b/Master/texmf-dist/scripts/latexdiff/latexdiff.pl index 03c70c3ac4e..865fc4853b1 100755 --- a/Master/texmf-dist/scripts/latexdiff/latexdiff.pl +++ b/Master/texmf-dist/scripts/latexdiff/latexdiff.pl @@ -1,24 +1,58 @@ -#!/usr/bin/perl -w +#!/usr/bin/env perl +##!/usr/bin/perl -w # latexdiff - differences two latex files on the word level # and produces a latex file with the differences marked up. # -# Copyright (C) 2004-2007 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2004-12 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file # +# Version 1.0.1 - treat \big,\bigg etc. equivalently to \left and +# \right - include starred version in MATHENV - apply +# - flatten recursively and --flatten expansion is now +# aware of comments (thanks to Tim Connors for patch) +# - Change to post-processing for more reliability for +# deleted math environments +# - On linux systems, recognise and remove DOS style newlines +# - Provide markup for some special preamble commands (\title, +# \author,\date, +# - configurable by setting context2cmd +# - for styles using ulem package, remove \emph and \text.. from list of +# safe commands in order to allow linebreaks within the +# highlighted sections. +# - for ulem style, now show citations by enclosing them in \mbox commands. +# This unfortunately implies linebreaks within citations no longer function, +# so this functionality can be turned off (Option --disable-citation-markup). +# With --enable-citation-markup, the mbox markup is forced for other styles) +# - new substyle COLOR. This is particularly useful for marking up citations +# and some special post-processing is implemented to retain cite +# commands in deleted blocks. +# - four different levels of math-markup +# - Option --driver for choosing driver for modes employing changebar package +# - accept \\* as valid command (and other commands of form \.*). Also accept +# \ (backslashed newline) +# - some typo fixes, include commands defined in preamble as safe commands +# (Sebastian Gouezel) +# - include compared filenames as comments as line 2 and 3 of +# the preamble (can be modified with option --label, and suppressed with +# --no-label), option --visible-label to show files in generated pdf or dvi +# at the beginning of main document +# # Version 0.5 A number of minor improvements based on feedback # Deleted blocks are now shown before added blocks # Package specific processing @@ -499,14 +533,15 @@ import Algorithm::Diff qw(traverse_sequences); use Getopt::Long ; use strict ; +use warnings; use utf8 ; my ($algodiffversion)=split(/ /,$Algorithm::Diff::VERSION); my ($versionstring)=< 0, + WHOLE => 1, + COARSE => 2, + FINE => 3 +}; + + +my (@configlist,@labels, @appendsafelist,@excludesafelist, @appendtextlist,@excludetextlist, @appendcontext1list,@appendcontext2list, @@ -592,9 +648,11 @@ my ($pkg,%packages); $type='UNDERLINE'; $subtype='SAFE'; $floattype='FLOATSAFE'; +$mathmarkup=COARSE; $verbose=0; -$debug=1; +# output debug and intermediate files, set to 0 in final distribution +$debug=0; # define character properties sub IsNonAsciiPunct { return <<'END' # Unicode punctuation but excluding ASCII punctuation +utf8::IsPunct @@ -608,8 +666,7 @@ END } - - my %verbhash; +my %verbhash; Getopt::Long::Configure('bundling'); GetOptions('type|t=s' => \$type, @@ -618,6 +675,9 @@ GetOptions('type|t=s' => \$type, 'config|c=s' => \@configlist, 'preamble|p=s' => \$preamblefile, 'encoding|e=s' => \$encoding, + 'label|L=s' => \@labels, + 'no-label' => \$nolabel, + 'visible-label' => \$visiblelabel, 'exclude-safecmd|A=s' => \@excludesafelist, 'replace-safecmd=s' => \$replacesafe, 'append-safecmd|a=s' => \@appendsafelist, @@ -634,9 +694,13 @@ GetOptions('type|t=s' => \$type, 'show-config' => \$showconfig, 'show-all' => \$showall, 'packages=s' => \@packagelist, + 'allow-spaces' => \$allowspaces, + 'math-markup=s' => \$mathmarkup, + 'enable-citation-markup' => \$enablecitmark, + 'disable-citation-markup' => \$disablecitmark, 'verbose|V' => \$verbose, 'ignore-warnings' => \$ignorewarnings, - 'allow-spaces' => \$allowspaces, + 'driver=s'=> \$driver, 'flatten' => \$flatten, 'version' => \$version, 'help|h|H' => \$help); @@ -656,6 +720,22 @@ if (defined($showall)){ $showpreamble=$showsafe=$showtext=$showconfig=1; } +if (defined($mathmarkup)) { + $mathmarkup=~tr/a-z/A-Z/; + if ( $mathmarkup eq 'OFF' ){ + $mathmarkup=OFF; + } elsif ( $mathmarkup eq 'WHOLE' ){ + $mathmarkup=WHOLE; + } elsif ( $mathmarkup eq 'COARSE' ){ + $mathmarkup=COARSE; + } elsif ( $mathmarkup eq 'FINE' ){ + $mathmarkup=FINE; + } elsif ( $mathmarkup !~ m/^[0123]$/ ) { + die "Illegal value: ($mathmarkup) for option--math-markup. Possible values: OFF,WHOLE,COARSE,FINE,0- "; + } + # else use numerical value +} + # setting extra preamble commands if (defined($preamblefile)) { $latexdiffpreamble=join "\n",(extrapream($preamblefile),""); @@ -663,6 +743,10 @@ if (defined($preamblefile)) { $latexdiffpreamble=join "\n",(extrapream($type,$subtype,$floattype),""); } +if ( defined($driver) ) { + # for changebar only + $latexdiffpreamble=~s/\[dvips\]/[$driver]/sg; +} # setting up @SAFECMDLIST and @SAFECMDEXCL if (defined($replacesafe)) { init_regex_arr_ext(\@SAFECMDLIST,$replacesafe); @@ -679,9 +763,25 @@ foreach $excludesafe ( @excludesafelist ) { # Special: treat all cite commands as safe except in UNDERLINE and FONTSTRIKE mode # (there is a conflict between citation and ulem package, see # package documentation) +# Use post-processing + if ( uc($type) ne "UNDERLINE" && uc($type) ne "FONTSTRIKE" && uc($type) ne "CULINECHBAR" ) { push (@SAFECMDLIST, qr/^cite.*$/); +} else { + ### Experimental: disable text and emph commands + push (@SAFECMDLIST, qr/^cite.*$/) unless $disablecitmark; + push(@SAFECMDEXCL, qr/^emph$/, qr/^text..$/); + # replace \cite{..} by \mbox{\cite{..}} in added or deleted blocks in post-processing + if ( uc($subtype) eq "COLOR" or uc($subtype) eq "DVIPSCOL" ) { + # remove \cite command again from list of safe commands + pop @SAFECMDLIST; + # deleted cite commands + $CITE2CMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite-type commands which should be reinstated in deleted blocks + } else { + $CITECMD='(?:cite\w*|nocite)' unless $disablecitmark ; # \cite commands which need to be protected within an mbox in UNDERLINE and other modes using ulem + } } +$CITECMD='(?:cite\w*|nocite)' if $enablecitmark ; # as above for explicit selection # setting up @TEXTCMDLIST and @TEXTCMDEXCL if (defined($replacetext)) { @@ -718,9 +818,6 @@ foreach $appendcontext2 ( @appendcontext2list ) { init_regex_arr_ext(\@CONTEXT2CMDLIST, $appendcontext2); } - - - # setting configuration variables @config=(); foreach $config ( @configlist ) { @@ -754,6 +851,11 @@ foreach $assign ( @config ) { else { die "Unknown variable $1 in assignment.";} } +if ( $mathmarkup == COARSE || $mathmarkup == WHOLE ) { + push(@MATHTEXTCMDLIST,qr/^MATHBLOCK(?:$MATHENV|$MATHARRENV|SQUAREBRACKET)$/); +} + + foreach $pkg ( @packagelist ) { map { $packages{$_}="" } split(/,/,$pkg) ; @@ -776,12 +878,13 @@ if ($showtext) { print_regex_arr(@TEXTCMDLIST); print "\nContext1 commands (last argument textual, command will be disabled in deleted passages, last argument will be shown as plain text):\n"; print_regex_arr(@CONTEXT1CMDLIST); - print "\nContext2 commands (last argument textual, command ant its argument will be disabled in deleted passages):\n"; + print "\nContext2 commands (last argument textual, command and its argument will be disabled in deleted passages):\n"; print_regex_arr(@CONTEXT2CMDLIST); print "\nExclude list of Commands with last argument not textual (overrides patterns above):\n"; print_regex_arr(@TEXTCMDEXCL); } + if ($showconfig) { print "Configuration variables:\n"; print "MINWORDSBLOCK=$MINWORDSBLOCK\n"; @@ -813,14 +916,21 @@ if ($allowspaces) { push @TEXTCMDLIST, @CONTEXT1CMDLIST; push @TEXTCMDLIST, @CONTEXT2CMDLIST; +push @TEXTCMDLIST, @MATHTEXTCMDLIST if $mathmarkup==COARSE; + +# internal additions to SAFECMDLIST +push(@SAFECMDLIST, qr/^QLEFTBRACE$/, qr/^QRIGHTBRACE$/); + # Patterns. These are used by some of the subroutines, too # I can only define them down here because value of extraspace depends on an option - my $pat0 = '(?:[^{}]|\\\{|\\\})*'; - my $pat1 = '(?:[^{}]|\\\{|\\\}|\{'.$pat0.'\})*'; - my $pat2 = '(?:[^{}]|\\\{|\\\}|\{'.$pat1.'\})*'; # - my $pat3 = '(?:[^{}]|\\\{|\\\}|\{'.$pat2.'\})*'; - my $pat4 = '(?:[^{}]|\\\{|\\\}|\{'.$pat3.'\})*'; + my $pat0 = '(?:[^{}])*'; + my $pat1 = '(?:[^{}]|\{'.$pat0.'\})*'; + my $pat2 = '(?:[^{}]|\{'.$pat1.'\})*'; + my $pat3 = '(?:[^{}]|\{'.$pat2.'\})*'; + my $pat4 = '(?:[^{}]|\{'.$pat3.'\})*'; + my $pat5 = '(?:[^{}]|\{'.$pat4.'\})*'; + my $pat6 = '(?:[^{}]|\{'.$pat5.'\})*'; my $brat0 = '(?:[^\[\]]|\\\[|\\\])*'; my $quotemarks = '(?:\'\')|(?:\`\`)'; @@ -831,19 +941,44 @@ push @TEXTCMDLIST, @CONTEXT2CMDLIST; my $coords= '[\-.,\s\d]*'; # word: sequence of letters or accents followed by letter my $word='(?:[-\w\d*]|\\\\[\"\'\`~^][A-Za-z\*])+'; - my $cmdleftright='\\\\(?:left|right)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; + my $cmdleftright='\\\\(?:left|right|[Bb]igg?[lrm]?|middle)\s*(?:[()\[\]|]|\\\\(?:[|{}]|\w+))'; - my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat4 . '\}|\(' . $coords .'\))'.$extraspace.')*'; - my $oneletcmd='\\\\.(?:\['.$brat0.'\]|\{'. $pat4 . '\})*'; + my $cmdoptseq='\\\\[\w\d\*]+'.$extraspace.'(?:(?:\['.$brat0.'\]|\{'. $pat6 . '\}|\(' . $coords .'\))'.$extraspace.')*'; + my $backslashnl='\\\\\n'; + my $oneletcmd='\\\\.\*?(?:\['.$brat0.'\]|\{'. $pat6 . '\})*'; my $math='\$(?:[^$]|\\\$)*?\$|\\\\[(].*?\\\\[)]'; -# my $math='\$(?:[^$]|\\\$)*\$'; +## the current maths command cannot cope with newline within the math expression + my $comment='%.*?\n'; - my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; + my $pat=qr/(?:\A\s*)?(?:${and}|${quotemarks}|${number}|${word}|$cmdleftright|${cmdoptseq}|${math}|${backslashnl}|${oneletcmd}|${comment}|${punct}|${mathpunct}|\{|\})\s*/ ; # now we are done setting up and can start working my ($oldfile, $newfile) = @ARGV; +# check for existence of input files +if ( ! -e $oldfile ) { + die "Input file $oldfile does not exist."; +} +if ( ! -e $newfile ) { + die "Input file $newfile does not exist."; +} + + +# set the labels to be included into the file +my ($oldtime,$newtime,$oldlabel,$newlabel); +if (defined($labels[0])) { + $oldlabel=$labels[0] ; +} else { + $oldtime=localtime((stat($oldfile))[9]); + $oldlabel="$oldfile " . " "x(length($newfile)-length($oldfile)) . $oldtime; +} +if (defined($labels[1])) { + $newlabel=$labels[1] ; +} else { + $newtime=localtime((stat($newfile))[9]); + $newlabel="$newfile " . " "x(length($oldfile)-length($newfile)) . $newtime; +} $encoding=guess_encoding($newfile) unless defined($encoding); @@ -872,10 +1007,19 @@ if ($flatten) { $newbody=flatten($newbody,$newpreamble,$newfile,$encoding); } +my @auxlines; if ( length $oldpreamble && length $newpreamble ) { + # pre-process preamble by looking for commands used in \maketitle (title, author, date etc commands) + # and marking up content with latexdiff markup + @auxlines=preprocess_preamble($oldpreamble,$newpreamble); + @oldpreamble = split /\n/, $oldpreamble; @newpreamble = split /\n/, $newpreamble; - + + # If a command is defined in the preamble of the new file, and only uses safe commands, then it can be considered to be safe) (contribution S. Gouezel) + # Base this assessment on the new preamble + add_safe_commands($newpreamble); + %packages=list_packages(@newpreamble) unless %packages; if (defined $packages{"hyperref"} ) { print STDERR "hyperref package detected.\n" if $verbose ; @@ -883,13 +1027,23 @@ if ( length $oldpreamble && length $newpreamble ) { $latexdiffpreamble =~ s/\{\\DIFdel\}/{\\DIFdeltex}/g; $latexdiffpreamble .= join "\n",(extrapream("HYPERREF"),""); } + print STDERR "Differencing preamble.\n" if $verbose; + # insert dummy first line such that line count begins with line 1 (rather than perl's line 0) - just so that line numbers inserted by linediff are correct unshift @newpreamble,''; unshift @oldpreamble,''; - print STDERR "Differencing preamble.\n" if $verbose; @diffpreamble = linediff(\@oldpreamble, \@newpreamble); # remove dummy line again shift @diffpreamble; + # add filenames, modification time and latexdiff mark + defined($nolabel) or splice @diffpreamble,1,0, + "%DIF LATEXDIFF DIFFERENCE FILE", + ,"%DIF DEL $oldlabel", + "%DIF ADD $newlabel"; + if ( @auxlines ) { + push @diffpreamble,"%DIF DELETED TITLE COMMANDS FOR MARKUP"; + push @diffpreamble,join("\n",@auxlines); + } push @diffpreamble,$latexdiffpreamble; push @diffpreamble,'\begin{document}'; } @@ -900,7 +1054,7 @@ elsif ( !length $oldpreamble && !length $newpreamble ) { exit(2); } -if (defined $packages{"amsmath"} ) { +if (defined $packages{"amsmath"} or defined $packages{"amsart"} or defined $packages{"amsbook"} ) { print STDERR "amsmath package detected.\n" if $verbose ; $MATHARRREPL='align*'; } @@ -912,9 +1066,22 @@ my ($oldleadin,$newleadin)=preprocess($oldbody,$newbody); # run difference algorithm @diffbody=bodydiff($oldbody, $newbody); $diffbo=join("",@diffbody); +if ( $debug ) { + open(RAWDIFF,">","latexdiff.debug.bodydiff"); + print RAWDIFF $diffbo; + close(RAWDIFF); +} print STDERR "(",exetime()," s)\n","Postprocessing body. \n " if $verbose; postprocess($diffbo); $diffall =join("\n",@diffpreamble) ; +# add visible labels +if (defined($visiblelabel)) { + # Give information right after \begin{document} (or at the beginning of the text for files without preamble + ### if \date command is used, add information to \date argument, otherwise give right after \begin{document} + ### $diffall=~s/(\\date$extraspace(?:\[$brat0\])?$extraspace)\{($pat6)\}/$1\{$2 \\ LATEXDIFF comparison \\ Old: $oldlabel \\ New: $newlabel \}/ or + $diffbo = "\\begin{verbatim}LATEXDIFF comparison\nOld: $oldlabel\nNew: $newlabel\\end{verbatim}\n$diffbo" ; +} + $diffall .= "$newleadin$diffbo" ; $diffall .= "\\end{document}$newpost" if length $newpreamble ; if ( lc($encoding) ne "utf8" && lc($encoding) ne "ascii" ) { @@ -971,6 +1138,9 @@ sub read_file_with_encoding { $output=Encode::decode($encoding,$output); } close FILE; + if ($^O eq "linux" ) { + $output =~ s/\r\n/\n/g ; + } return $output; } @@ -995,13 +1165,66 @@ sub list_packages { return (%packages); } +# Subroutine add_safe_commands modified from version provided by S. Gouezel +# add_safe_commands($preamble) +# scans the argument for \newcommand and \DeclareMathOperator, +# and adds the created commands which are clearly safe to @SAFECMDLIST +sub add_safe_commands { + my ($preamble)=@_; + my $added_command = 1; + + $preamble=~s/(?catfile($dirname,$fname), "\n"; - # content of file becomes replacement value, add \newpage if the command was include - $replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die - "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; - $newpage=(defined($2)? " \\newpage " : "") ; - "$newpage$replacement$newpage"; - }/exg; + print STDERR "DEBUG looking for file ",File::Spec->catfile($dirname,$fname), "\n" if $debug; + # content of file becomes replacement value (use recursion), add \newpage if the command was include + ###$replacement=read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + $replacement=flatten(read_file_with_encoding(File::Spec->catfile($dirname,$fname), $encoding), $preamble,$filename,$encoding) or die "Couldn't find file ",File::Spec->catfile($dirname,$fname),": $!"; + # \include always starts a new page; use explicit \newpage command to simulate this + $begline=(defined($1)? $1 : "") ; + $newpage=(defined($3)? " \\newpage " : "") ; + "$begline$newpage$replacement$newpage"; + }/exgm; return($text); } @@ -1133,13 +1359,29 @@ sub bodydiff { my @oldwords = splitlatex($oldwords); print STDERR "Parsing $newfile \n" if $verbose; my @newwords = splitlatex($newwords); - my $token; + + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } print STDERR "(",exetime()," s)\n","Pass 1: Expanding text commands and merging isolated identities with changed blocks " if $verbose; pass1(\@oldwords, \@newwords); print STDERR "(",exetime()," s)\n","Pass 2: inserting DIF tokens and mark up. " if $verbose; + if ( $debug ) { + open(TOKENOLD,">","latexdiff.debug.tokenold2.tex"); + print TOKENOLD join("***\n",@oldwords); + close(TOKENOLD); + open(TOKENNEW,">","latexdiff.debug.tokennew2.tex"); + print TOKENNEW join("***\n",@newwords); + close(TOKENNEW); + } @retwords=pass2(\@oldwords, \@newwords); @@ -1156,6 +1398,9 @@ sub bodydiff { # a latex command sub splitlatex { my ($string) = @_ ; + # if input is empty, return empty list + length($string)>0 or return (); + my @retval=($string =~ m/$pat/osg); if (length($string) != length(join("",@retval))) { @@ -1241,7 +1486,7 @@ sub pass1 { # print STDERR "Unchanged block $cnt, $last1,$last2 \n"; if ($cnt < $MINWORDSBLOCK && $cnt==scalar ( - grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat4\})*)/o + grep { /^$wpat/ || ( /^\\([\w\d\*]+)((?:\[$brat0\]|\{$pat6\})*)/o && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) && scalar(@dummy=split(" ",$2))<3 ) } @$block) ) { @@ -1373,7 +1618,7 @@ sub extracttextblocks { for ($i=0;$i< scalar @$block;$i++) { ($token,$index)=@{ $block->[$i] }; # store pure text blocks - if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*)/o + if ($token =~ /$wpat/ || ( $token =~/^\\([\w\d\*]+)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*)/o && iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL) && !iscmd($1,\@TEXTCMDLIST,\@TEXTCMDEXCL))) { # we have text or a command which can be treated as text @@ -1427,7 +1672,7 @@ sub extractcommands { # $2: \cmd # $3: last argument # $4: } + trailing spaces - if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) + if ( ( $token =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) ) { # push(@$retval,[ $2,$index,$1,$3,$4 ]); ($cmd,$open,$mid,$closing) = ($2,$1,$3,$4) ; @@ -1521,7 +1766,7 @@ sub pass2 { # braces, ampersands, or comments # mark comments with $comment # exclude all other exceptions from scope of open, close like this -# ($openmark, $open,...,$close, $opencomd,command, command,$closecmd, $open, ..., $close, $closemark) +# ($openmark, $open,...,$close, $opencmd,command, command,$closecmd, $open, ..., $close, $closemark) # If $opencmd begins with "%" marktags assumes it is operating on a deleted block, otherwise on an added block sub marktags { my ($openmark,$closemark,$open,$close,$opencmd,$closecmd,$comment,$block)=@_; @@ -1553,21 +1798,30 @@ sub marktags { $noncomment=1; } # negative lookahead pattern (?!) in second clause is put in to avoid mathcing \( .. \) patterns - if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()([\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { + # also note that second pattern will match \\ + # Note: the second pattern should really be $word =~ /^\\(?!\()(\\|[\w*@]+)/, ie * replaced by + + # and then all commands \" \' etc declared safe. But as I don't have a complete list of one letter + # commands, and nobody has complained so far, I will eave this as is + if ( $word =~ /^[&{}\[\]]/ || ( $word =~ /^\\(?!\()(\\|[\w*@]*)/ && !iscmd($1,\@SAFECMDLIST,\@SAFECMDEXCL)) ) { # word is a command or other significant token (not in SAFECMDLIST) ## same conditions as in subroutine extractcommand: # check if token is an alphanumeric command sequence with at least one non-optional argument # \cmd[...]{...}{last argument} # Capturing in the following results in these associations # $1: \cmd[...]{...}{ - # $2: \cmd + # $2: cmd # $3: last argument # $4: } + trailing spaces - ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat4\})*\{)($pat4)(\}\s*)$/so ) - if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat4\})*${extraspace}\{)($pat4)(\}\s*)$/so ) - && iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL) && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { - # word is a text command - we mark up the interior of the word. But if we are in a deleted block ($cmdcomment=1) and - # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) + ### pre-0.3 if ( ( $token =~ m/^(\\([\w\d\*]+)(?:\[$brat0\]|\{$pat6\})*\{)($pat6)(\}\s*)$/so ) + if ( ( $word =~ m/^(\\([\w\d\*]+)(?:${extraspace}\[$brat0\]|${extraspace}\{$pat6\})*${extraspace}\{)($pat6)(\}\s*)$/so ) + && (iscmd($2,\@TEXTCMDLIST,\@TEXTCMDEXCL)|| iscmd($2,\@MATHTEXTCMDLIST,\@MATHTEXTCMDEXCL)) + && ( !$cmdcomment || !iscmd($2,\@CONTEXT2CMDLIST, \@CONTEXT2CMDEXCL) ) ) { + # Condition 1: word is a command? - if yes, $1,$2,.. will be set as above + # Condition 2: word is a text command - we mark up the interior of the word. There is a separate check for MATHTEXTCMDLIST + # because for $mathmarkup=WHOLE, the commands should not be split in pass1 (ie. math mode commands are not in + # TEXTCMDLIST, but the interior of MATHTEXT commands should be highlighted in both deleted and added blocks + # Condition 3: But if we are in a deleted block ($cmdcomment=1) and + # $2 (the command) is in context2, just treat it as an ordinary command (i.e. comment it open with $opencmd) # Because we do not want to disable this command # here we do not use $opencmd and $closecmd($opencmd is empty) if ($cmd==1) { @@ -1587,7 +1841,15 @@ sub marktags { # to suppress linebreak after opening parentheses, which is important # for latexrevise push (@$retval,$command,"%\n{$AUXCMD\n",marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); - } else { + } elsif ( iscmd($commandword,,\@MATHTEXTCMDLIST, \@MATHTEXTCMDEXCL) ) { + # MATHBLOCK pseudo command: consider all commands safe, except & and \\ + # Keep these commands even in deleted blocks, hence set $opencmd and $closecmd (5th and 6th argument of marktags) to + # "" + local @SAFECMDLIST=(".*"); + local @SAFECMDEXCL=('\\','\\\\'); + push(@$retval,$command,marktags("","",$open,$close,"","",$comment,\@argtext)#@argtext + ,$closingbracket); + } else { # normal textcmd or context1cmd in an added block push (@$retval,$command,marktags("","",$open,$close,$opencmd,$closecmd,$comment,\@argtext),$closingbracket); } @@ -1619,6 +1881,9 @@ sub marktags { # preprocess($string, ..) # carry out the following pre-processing steps for all arguments: # 1. Remove leading white-space +# Change \{ to \LEFTBRACE and \} to \RIGHTBRACE +# #. change begin and end commands within comments to BEGINDIF, ENDDIF +# so they don't disturb the pattern matching (if there are several \begin or \end in one line # 2. mark all first empty line (in block of several) with \PAR tokens # 3. Convert all '\%' into '\PERCENTAGE ' to make parsing regular expressions easier # 4. Convert all \verb|some verbatim text| commands (where | can be an arbitrary character) @@ -1628,8 +1893,11 @@ sub marktags { # 7. Convert ^n into \SUPERSCRIPTNB{n} and ^{nnn} into \SUPERSCRIPT{nn} # 8. a. Convert $$ $$ into \begin{DOLLARDOLLAR} \end{DOLLARDOLLAR} # b. Convert \[ \] into \begin{SQUAREBRACKET} \end{SQUAREBRACKET} +# 9. Convert all picture environmentent (\begin{PICTUREENV} .. \end{PICTUREENV} \PICTUREBLOCKenv +# For --block-math-markup option -convert all \begin{MATH} .. \end{MATH} +# into \MATHBLOCKmath{...} commands, where MATH/math is any valid math environment -# 9. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. +# 10. Add final token STOP to the very end. This is put in because the algorithm works better if the last token is identical. This is removed again in postprocessing. # # NB: step 6 and 7 is likely to convert some "_" inappropriately, e.g. in file # names or labels but it does not matter because they are converted back in the postprocessing step @@ -1639,21 +1907,39 @@ sub preprocess { for (@_) { s/^(\s*)//s; push(@leadin,$1); + # Change \{ to \QLEFTBRACE and \} to \QRIGHTBRACE + s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL +# d. If in-line math mode contains array environment, enclose the whole environment in \mbox'es +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# For added blocks: # c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es -# 2. Remove DIFadd, DIFdel, DIFFaddbegin , ... from picture environments +# d. place \cite commands in mbox'es (for UNDERLINE style) +# +# 2. If --block-math-markup option set: Convert \MATHBLOCKmath{..} commands back to environments +# +# Convert all PICTUREblock{..} commands back to the appropriate environments # 3. Convert DIFadd, DIFdel, DIFFaddbegin , ... into FL varieties # within floats (currently recognised float environments: plate,table,figure # plus starred varieties). @@ -1729,7 +2027,7 @@ sub fromhash { # 10. package specific processing: endfloat: make sure \begin{figure} and \end{figure} are always # on a line by themselves, similarly for table environment # 4, undo renaming of the \begin and \end in comments - +# Change \QLEFTBRACE, \QRIGHTBRACE to \{,\} # # Note have to manually synchronize substitution commands below and # DIF.. command names in the header @@ -1747,6 +2045,11 @@ sub postprocess { s/ STOP$//; # Replace \RIGHTBRACE by } s/\\RIGHTBRACE/}/g; + + # change citation commands within comments to protect from processing + if ($CITECMD){ + 1 while s/(%.*)\\($CITECMD)/$1\\CITEDIF$2/m ; + } # Check all deleted blocks: where a deleted block contains a matching \begin and # \end environment (these will be disabled by a %DIFDELCMD statements), enable # these commands again (such that for example displayed math in a deleted equation @@ -1763,55 +2066,72 @@ sub postprocess { ### (.*?[^\n]?)\n? construct is necessary to avoid empty lines in math mode, which result in ### an error # displayed math environments - $delblock=~ s/(\%DIFDELCMD < \s*\\begin\{((?:$MATHENV)|SQUAREBRACKET)\}\s*?(?:$DELCMDCLOSE|\n))(.*?[^\n]?)\n?(\%DIFDELCMD < \s*\\end\{\2\})/\\begin{$MATHREPL}$AUXCMD\n$1$3\n\\end{$MATHREPL}$AUXCMD\n$4/sg; - # also transform the opposite pair \end{displaymath} .. \begin{displaymath} but we have to be careful not to interfere with the results of the transformation in the line directly above - $delblock=~ s/(? displaymath +# (environments defined in $MATHENV will be replaced by $MATHREPL, and environments in $MATHARRENV +# will be replaced by $MATHARRREPL + $delblock=~ s/\\MATHBLOCK($MATHENV)\{($pat6)\}/\\MATHBLOCK$MATHREPL\{$2\}/sg; + $delblock=~ s/\\MATHBLOCK($MATHARRENV)\{($pat6)\}/\\MATHBLOCK$MATHARRREPL\{$2\}/sg; } - # b.where one of the commands matching $COUNTERCMD is used as a DIFAUXCMD, add a statement # subtracting one from the respective counter to keep numbering consistent with new file - $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat4\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + $delblock=~ s/\\($COUNTERCMD)((?:${extraspace}\[$brat0\]${extraspace}|${extraspace}\{$pat6\})*\s*${AUXCMD}\n)/\\$1$2\\addtocounter{$1}{-1}${AUXCMD}\n/sg ; + + # c. If in-line math mode contains array environment, enclose the whole environment in \mbox'es while ( $delblock =~ m/($math)(\s*)/sg ) { $cnt2=0; @@ -1822,7 +2142,18 @@ sub postprocess { substr($delblock,$begin2,$len2)=$mathblock; pos($delblock) = $begin2 + length($mathblock); } - + if ($CITE2CMD) { + $delblock=~s/($DELCMDOPEN\s*\\($CITE2CMD)(.*)$DELCMDCLOSE)/ + # Replacement code + {my ($aux,$all); + $aux=$all=$1; + $aux=~s#\n?($DELCMDOPEN|$DELCMDCLOSE)##g; + $all."$aux$AUXCMD\n";}/sge; + } + # or protect \cite commands with \mbox + if ($CITECMD) { + $delblock=~s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat6\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } # splice in modified delblock substr($_,$begin,$len)=$delblock; pos = $begin + length($delblock); @@ -1842,7 +2173,10 @@ sub postprocess { substr($addblock,$begin2,$len2)=$mathblock; pos($addblock) = $begin2 + length($mathblock); } - + if ($CITECMD) { + my $addblockbefore=$addblock; + $addblock=~ s/(\\($CITECMD)${extraspace}(?:\[$brat0\]${extraspace}){0,2}\{$pat2\})(\s*)/\\mbox{$AUXCMD\n$1\n}$AUXCMD\n/msg ; + } # splice in modified addblock substr($_,$begin,$len)=$addblock; pos = $begin + length($addblock); @@ -1853,6 +2187,7 @@ sub postprocess { # change begin and end commands within comments such that they # don't disturb the pattern matching (if there are several \begin or \end in one line # this substitution is insufficient but that appears unlikely) + # This needs to be repeated here to also get rid of DIFdelcmd-protected environments s/(%.*)\\begin\{(.*)$/$1\\BEGINDIF\{$2/mg ; s/(%.*)\\end\{(.*)$/$1\\ENDDIF\{$2/mg ; @@ -1861,32 +2196,40 @@ sub postprocess { # The next line is complicated. The negative look-ahead insertion makes sure that no \end{$MATHENV} (or other mathematical # environments) are between the \begin{$MATHENV} and \end{MATHMODE} commands. This is necessary as the minimal matching # is not globally minimal but only 'locally' (matching is beginning from the left side of the string) - 1 while s/\\begin{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}((?:.(?!(?:\\end{(?:(?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}|\\begin{MATHMODE})))*?)\\end{MATHMODE}/\\begin{$1}$2\\end{$1}/s; - 1 while s/\\begin{MATHMODE}((?:.(?!\\end{MATHMODE}))*?)\\end{((?:$MATHENV)|(?:$MATHARRENV)|SQUAREBRACKET)}/\\begin{$2}$1\\end{$2}/s; - # convert remaining \begin{MATHMODE} \end{MATHMODE} (and not containing & or \\ )into MATHREPL environments - s/\\begin{MATHMODE}((?:(.(?!(?[1])) { + $optargnew=$newhash{$cmd}->[1]; + } else { + $optargnew=""; + } + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + } else { + $optargold=""; + } + + if ( defined($oldhash{$cmd}) ) { + $argold=$oldhash{$cmd}->[2]; + } else { + $argold=""; + } + $argnew=$newhash{$cmd}->[2]; + $argdiff="{" . join("",bodydiff($argold,$argnew)) ."}"; + if ( length $optargnew ) { + $optargdiff="[".join("",bodydiff($optargold,$optargnew))."]" ; + $optargdiff =~ s/\\DIFaddbegin /\\DIFaddbeginFL /g; + $optargdiff =~ s/\\DIFaddend /\\DIFaddendFL /g; + $optargdiff =~ s/\\DIFadd\{/\\DIFaddFL{/g; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + ### print STDERR "DEBUG s/\\Q$newhash{$cmd}->[0]\\E/\\$cmd$optargdiff$argdiff/s\n"; + # Note: \Q and \E force literal interpretation of what it between them but allow + # variable interpolation, such that e.g. \title matches just that and not TAB-itle + $$newpreambleref=~s/\Q$newhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s; + # replace this in old preamble if necessary + if ( defined($oldhash{$cmd}->[0])) { + $$oldpreambleref=~s/\Q$oldhash{$cmd}->[0]\E/\\$cmd$optargdiff$argdiff/s ; + } + ### print STDERR "DEBUG NEW PRE ".$$newpreambleref."\n"; + } + + foreach $cmd ( keys %oldhash ) { + # if this has already been dealt with above can just skip + next if defined($newhash{$cmd}) ; + if ( defined($oldhash{$cmd}->[1])) { + $optargold=$oldhash{$cmd}->[1]; + $optargdiff="[".join("",bodydiff($optargold,""))."]" ; + $optargdiff =~ s/\\DIFdelbegin /\\DIFdelbeginFL /g; + $optargdiff =~ s/\\DIFdelend /\\DIFdelendFL /g; + $optargdiff =~ s/\\DIFdel\{/\\DIFdelFL{/g; + } else { + $optargdiff=""; + } + $argdiff="{" . join("",bodydiff($argold,"")) ."}"; + $auxline = "\\$cmd$optargdiff$argdiff"; + $auxline =~s/$/$AUXCMD/sg; + push @auxlines,$auxline; + } + # add auxcmd comment to highlight added lines + return(@auxlines); +} + + + # @diffs=linediff(\@seq1, \@seq2) # mark up lines like this #%DIF mm-mmdnn @@ -2091,7 +2559,7 @@ format as new.tex but has all changes relative to old.tex marked up or commented --subtype=markstyle -s markstyle Add code to preamble for selected style for bracketing commands (e.g. to mark changes in margin) - Available styles: SAFE MARGINAL DVIPSCOL + Available styles: SAFE MARGINAL DVIPSCOL COLOR [ Default: SAFE ] --floattype=markstyle @@ -2207,10 +2675,48 @@ format as new.tex but has all changes relative to old.tex marked up or commented NB For all --show commands, no old.tex or new.tex file needs to be given, and no differencing takes place. +Other configuration options: + --allow-spaces Allow spaces between bracketed or braced arguments to commands [Default requires arguments to directly follow each other without intervening spaces] +--math-markup=level Determine granularity of markup in displayed math environments: + Possible values for level are (both numerical and text labels are acceptable): + off or 0: suppress markup for math environments. Deleted equations will not + appear in diff file. This mode can be used if all the other modes + cause invalid latex code. + whole or 1: Differencing on the level of whole equations. Even trivial changes + to equations cause the whole equation to be marked changed. This + mode can be used if processing in coarse or fine mode results in + invalid latex code. + coarse or 2: Detect changes within equations marked up with a coarse + granularity; changes in equation type (e.g.displaymath to equation) + appear as a change to the complete equation. This mode is recommended + for situations where the content and order of some equations are still + being changed. [Default] + fine or 3: Detect small change in equations and mark up and fine granularity. + This mode is most suitable, if only minor changes to equations are + expected, e.g. correction of typos. + +--disable-citation-markup Suppress citation markup in styles using ulem (UNDERLINE, + FONTSTRIKE, CULINECHBAR) +--enable-citation-markup Protect citation commands in changed sections with \\mbox command + [i.e. use default behaviour for ulem package for other packages] + +Miscelleneous options + +--label=label +-L label Sets the labels used to describe the old and new files. The first use + of this option sets the label describing the old file and the second + use of the option sets the label for the new file. + [Default: use the filename and modification dates for the label] + +--no-label Suppress inclusion of old and new file names as comment in output file + +--visble-label Include old and new filenames (or labels set with --label option) as + visible output + --flatten Replace \\input and \\include commands within body by the content of the files in their argument. If \\includeonly is present in the preamble, only those files are expanded into the document. However, @@ -2218,6 +2724,8 @@ format as new.tex but has all changes relative to old.tex marked up or commented included sections are not expanded. The included files are assumed to be located in the same directories as the old and new master files, respectively, making it possible to organise files into old and new directories. + --flatten is applied recursively, so inputted files can contain further + \\input statements. --help -h Show this help text. @@ -2230,6 +2738,8 @@ format as new.tex but has all changes relative to old.tex marked up or commented Default is to work silently. --version Show version number. + +For further information, consult http://latexdiff.berlios.de EOF } @@ -2392,7 +2902,7 @@ B<-s markstyle> Add code to preamble for selected style for bracketing commands (e.g. to mark changes in margin). This option defines C<\DIFaddbegin>, C<\DIFaddend>, C<\DIFdelbegin> and C<\DIFdelend> commands. -Available styles: C +Available styles: C [ Default: C ] @@ -2526,7 +3036,7 @@ or table. These commands behave like text commands, except when they occur in a deleted section, when they are disabled, but their argument is shown as deleted text. -=item B<--replace-context1cmd=replace-file> +=item B<--replace-context2cmd=replace-file> =item B<--append-context2cmd=append-file> or =item B<--append-context2cmd="cmd1,cmd2,..."> @@ -2581,18 +3091,70 @@ Combine all --show commands. NB For all --show commands, no C or C file needs to be specified, and no differencing takes place. +=back + +=head2 Other configuration options: + +=over 4 + +=item B<--allow-spaces> + +Allow spaces between bracketed or braced arguments to commands. Note +that this option might have undesirable side effects (unrelated scope +might get lumpeded with preceding commands) so should only be used if the +default produces erroneous results. (Default requires arguments to +directly follow each other without intervening spaces). + +=item B<--math-markup=level> + +Determine granularity of markup in displayed math environments: +Possible values for level are (both numerical and text labels are acceptable): + +C or C<0>: suppress markup for math environments. Deleted equations will not +appear in diff file. This mode can be used if all the other modes +cause invalid latex code. + +C or C<1>: Differencing on the level of whole equations. Even trivial changes +to equations cause the whole equation to be marked changed. This +mode can be used if processing in coarse or fine mode results in +invalid latex code. + +C or C<2>: Detect changes within equations marked up with a coarse +granularity; changes in equation type (e.g.displaymath to equation) +appear as a change to the complete equation. This mode is recommended +for situations where the content and order of some equations are still +being changed. [Default] + +C or C<3>: Detect small change in equations and mark up at fine granularity. +This mode is most suitable, if only minor changes to equations are +expected, e.g. correction of typos. + +=item B<--disable-citation-markup> + +Suppress citation markup in styles using ulem (UNDERLINE, +FONTSTRIKE, CULINECHBAR) + +=item B<--enable-citation-markup> + +Protect citation commands in changed sections with \\mbox command [i.e. use default behaviour for ulem package for other packages] =back =head2 Miscellaneous =over 4 - =item B<--verbose> or B<-V> Output various status information to stderr during processing. Default is to work silently. +=item B<--driver=type> + +Choose driver for changebar package (only relevant for styles using + changebar: CCHANGEBAR CFONTCHBAR CULINECHBAR CHANGEBAR). Possible +drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops + [Default: dvips] + =item B<--ignore-warnings> Suppress warnings about inconsistencies in length between input and @@ -2602,13 +3164,23 @@ syntax unknown to C but the resulting difference argument is often fully functional anyway, particularly if the non-standard latex only occurs in parts of the text which have not changed. -=item B<--allow-spaces> +=item B<--label=label> or +B<-L label> -Allow spaces between bracketed or braced arguments to commands. Note -that this option might have undesirable side effects (unrelated scope -might get lumpeded with preceding commands) so should only be used if the -default produces erroneous results. (Default requires arguments to -directly follow each other without intervening spaces). +Sets the labels used to describe the old and new files. The first use +of this option sets the label describing the old file and the second +use of the option sets the label for the new file, i.e. set both +labels like this C<-L labelold -L labelnew>. +[Default: use the filename and modification dates for the label] + +=item B<--no-label> + +Suppress inclusion of old and new file names as comment in output file + +=item B<--visble-label> + +Include old and new filenames (or labels set with --label option) as +visible output. =item B<--flatten> @@ -2619,11 +3191,12 @@ no recursion is done, i.e. C<\input> and C<\include> commands within included sections are not expanded. The included files are assumed to be located in the same directories as the old and new master files, respectively, making it possible to organise files into old and new directories. +--flatten is applied recursively, so inputted files can contain further +C<\input> statements. -Use of this option is not recommended -primarily the processing time for the large documents is prohibitive, and -the resulting difference document no longer reflects the structure of the -input documents. +Use of this option might result in prohibitive processing times for +larger documents, and the resulting difference document +no longer reflects the structure of the input documents. =item B<--help> or B<-h> @@ -2636,6 +3209,8 @@ Show version number =back + + =head2 Predefined styles =head2 Major types @@ -2704,6 +3279,13 @@ Mark beginning and end of changed blocks with symbols in the margin nearby (usin the standard C<\marginpar> command - note that this sometimes moves somewhat from the intended position. +=item C + +An alternative way of marking added passages in blue, and deleted ones in red. +(It is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete, for example +with citation commands). + =item C An alternative way of marking added passages in blue, and deleted ones in red. Note @@ -2797,26 +3379,49 @@ C<|subsubsection|paragraph|subparagraph)> ] =back -=head1 BUGS +=head1 COMMON PROBLEMS + +=over 10 -UTF-8 support requires a relatively new version of perl (5.8.0 is sufficient -but 5.6.2 up would work OK, too). +=item Citations result in overfull boxes + +There is an incompatibility between the C package, which C uses for underlining and striking out in the UNDERLINE style, +the default style. In order to be able to mark up citations properly, they are placed with an C<\mbox> command in post-processing. As mboxes +cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities: + +1. Use C or C subtype markup (option C<-s COLOR>): If this markup is chosen, then changed citations are no longer marked up +with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color. + +2. Choose option C<--disable-citation-markup> which turns off the marking up of citations: deleted citations are no longer shown, and +added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older) + +=item Changes in complicated mathematical equations result in latex processing errors + +Try options C<--math-markup=whole>. If even that fails, you can turn off mark up for equations with C<--math-markup=off>. + +=back + +=head1 BUGS Option allow-spaces not implemented entirely consistently. It breaks the rules that number and type of white space does not matter, as different numbers of inter-argument spaces are treated as significant. -Please send bug reports -to I. Include the serial number of I +Please submit bug reports on the latexdiff project page I, +send them to user discussion list C (prior subscription +to list required, also on project webpage) +or send them to I. Include the serial number of I (from comments at the top of the source or use B<--version>). If you come across latex files that are error-free and conform to the specifications set out above, and whose differencing still does not result in error-free latex, please send me those files, ideally edited to only contain the -offending passage as long as that still reproduces the problem. +offending passage as long as that still reproduces the problem. If your +file relies on non-standard class files, you must include those. I will not +look at examples where I have trouble to latex the original files. =head1 SEE ALSO -L +L, L =head1 PORTABILITY @@ -2832,13 +3437,15 @@ I requires the I command to be present. =head1 AUTHOR -Copyright (C) 2004-2007 Frederik Tilmann +Version 1.0.2 +Copyright (C) 2004-2012 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 -Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner -Thanks to everyone who send in bug reports. +Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner, +T. Connors, Sebastian Gouezel and many others. +Thanks to the many people who send in bug reports, feature suggestions, and other feedback. =cut @@ -3093,14 +3700,16 @@ sqrt %%END TEXT COMMANDS %%BEGIN CONTEXT1 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text caption %%END CONTEXT1 COMMANDS %%BEGIN CONTEXT2 COMMANDS -% Regex matching commands with a text argument (leave out the \), which will fail out of context, but who's arguemtn should be printed as plain text +% Regex matching commands with a text argument (leave out the \), which will fail out of context, but whose argument should be printed as plain text title author +date +institute %%END CONTEXT2 COMMANDS @@ -3198,6 +3807,14 @@ author \providecommand{\DIFdelend}{\protect\nogroupcolor{black}} %DIF END DVIPSCOL PREAMBLE +%DIF COLOR PREAMBLE +\RequirePackage{color} +\providecommand{\DIFaddbegin}{\protect\color{blue}} +\providecommand{\DIFaddend}{\protect\color{black}} +\providecommand{\DIFdelbegin}{\protect\color{red}} +\providecommand{\DIFdelend}{\protect\color{black}} +%DIF END COLOR PREAMBLE + %% FLOAT TYPES diff --git a/Master/texmf-dist/scripts/latexdiff/latexrevise.pl b/Master/texmf-dist/scripts/latexdiff/latexrevise.pl index 279dac1fc6a..0f333fbb994 100755 --- a/Master/texmf-dist/scripts/latexdiff/latexrevise.pl +++ b/Master/texmf-dist/scripts/latexdiff/latexrevise.pl @@ -1,30 +1,39 @@ -#!/usr/bin/perl -w +#!/usr/bin/env perl # latexrevise - takes output file of latexdiff and removes either discarded # or appended passages, then deletes all other latexdiff markup # -# Copyright (C) 2004 F J Tilmann (tilmann@esc.cam.ac.uk) +# Copyright (C) 2004 F J Tilmann (tilmann@gfz-potsdam.de, ftilmann@users.berlios.de) # -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License Version 2 as published by -# the Free Software Foundation. +# Project webpages: http://latexdiff.berlios.de/ +# CTAN page: http://www.ctan.org/tex-archive/support/latexdiff +# +# 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 3 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# along with this program. If not, see . # # Detailed usage information at the end of the file -# -# Version 0.1 First public release +# Note: version number now keeping up with latexdiff +# Version 1.0.2 Option --version +# Version 1.0.1 no changes to latexrevise # Version 0.3 Updated for compatibility with latexdiff 0.3 output (DIFAUXCMD removal) -# +# Version 0.1 First public release use Getopt::Long ; use strict; +use warnings; + +my $versionstring=< \$accept, 'markup|m=s' => \$markup, 'markup-environment|n=s' => \$markenv, 'no-warnings|q' => \$verbose, + 'version' => \$version, 'verbose|V' => \$verbose, 'help|h|H' => \$help); @@ -87,6 +97,11 @@ if ( $help ) { usage() ; } +if ( $version ) { + die $versionstring ; +} + + if ( ($accept && $decline) || ($accept && $simplify) || ($decline && $simplify) ) { die '-a,-d and -s options are mutually axclusive. Type latexrevise -h to get more help.'; } @@ -493,15 +508,16 @@ which should have been removed already. =head1 BUGS The current version is a beta version which has not yet been -extensively tested, but worked fine locally. Please send bug reports -to I. Include the serial number of I +extensively tested, but worked fine locally. Please submit bug reports through +the latexdiff project page I or send +to I. Include the serial number of I (from comments at the top of the source). If you come across latexdiff output which is not processed correctly by I please include the problem file as well as the old and new files on which it is based, ideally edited to only contain the offending passage as long as that still reproduces the problem. -I gets confused by commented C<\begin{document}> or +Note that I gets confused by commented C<\begin{document}> or C<\end{document}> statements =head1 SEE ALSO @@ -518,6 +534,6 @@ on any platform supporting PERL v5 or higher. Copyright (C) 2004 Frederik Tilmann This program is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License Version 2 +it under the terms of the GNU General Public License Version 3 =cut diff --git a/Master/texmf/doc/man/man1/latexdiff-vc.1 b/Master/texmf/doc/man/man1/latexdiff-vc.1 index 1c5946d6fdf..497b8fed20b 100644 --- a/Master/texmf/doc/man/man1/latexdiff-vc.1 +++ b/Master/texmf/doc/man/man1/latexdiff-vc.1 @@ -1,15 +1,7 @@ -.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.14 +.\" Automatically generated by Pod::Man 2.23 (Pod::Simple 3.14) .\" .\" Standard preamble: .\" ======================================================================== -.de Sh \" Subsection heading -.br -.if t .Sp -.ne 5 -.PP -\fB\\$1\fR -.PP -.. .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp @@ -25,11 +17,11 @@ .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left -.\" double quote, and \*(R" will give a right double quote. | will give a -.\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to -.\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' -.\" expand to `' in nroff, nothing in troff, for use with C<>. -.tr \(*W-|\(bv\*(Tr +.\" double quote, and \*(R" will give a right double quote. \*(C+ will +.\" give a nicer C++. Capital omega is used to do unbreakable dashes and +.\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, +.\" nothing in troff, for use with C<>. +.tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- @@ -48,22 +40,25 @@ . ds R" '' 'br\} .\" +.\" Escape single quotes in literal strings from groff's Unicode transform. +.ie \n(.g .ds Aq \(aq +.el .ds Aq ' +.\" .\" If the F register is turned on, we'll generate index entries on stderr for -.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index +.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. -.if \nF \{\ +.ie \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} -.\" -.\" For nroff, turn off justification. Always turn off hyphenation; it makes -.\" way too many mistakes in technical documents. -.hy 0 -.if n .na +.el \{\ +. de IX +.. +.\} .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. @@ -129,7 +124,11 @@ .\" ======================================================================== .\" .IX Title "LATEXDIFF-VC 1" -.TH LATEXDIFF-VC 1 "2007-07-24" "perl v5.8.5" " " +.TH LATEXDIFF-VC 1 "2012-12-16" "perl v5.12.4" " " +.\" For nroff, turn off justification. Always turn off hyphenation; it makes +.\" way too many mistakes in technical documents. +.if n .ad l +.nh .SH "NAME" latexdiff\-vc \- wrapper script that calls latexdiff for different versions of a file under version management (CVS, RCS or SVN) .SH "SYNOPSIS" @@ -144,15 +143,15 @@ latexdiff\-vc \- wrapper script that calls latexdiff for different versions of a .SH "DESCRIPTION" .IX Header "DESCRIPTION" \&\fIlatexdiff-vc\fR is a wrapper script that applies \fIlatexdiff\fR to a -file, or multiple files under version control (\s-1CVS\s0 or \s-1RCS\s0), and optionally runs the +file, or multiple files under version control (\s-1CVS\s0, \s-1RCS\s0 or \s-1SVN\s0), and optionally runs the sequence of \f(CW\*(C`latex\*(C'\fR and \f(CW\*(C`dvips\*(C'\fR or \f(CW\*(C`pdflatex\*(C'\fR commands necessary to produce pdf or postscript output of the difference tex file(s). It can also be applied to a pair of files to automatise the generation of difference file in postscript or pdf format. .SH "OPTIONS" .IX Header "OPTIONS" -.IP "\fB\-\-rcs\fR, \fB\-\-svn\fR, or \fB\-\-cvs\fR" 4 -.IX Item "--rcs, --svn, or --cvs" +.IP "\fB\-\-rcs\fR, \fB\-\-svn\fR, \fB\-\-cvs\fR, or \fB\-\-git\fR" 4 +.IX Item "--rcs, --svn, --cvs, or --git" Set the version system. If no version system is specified, latexdiff-vc will venture a guess. .Sp @@ -160,8 +159,8 @@ latexdiff-cvs and latexdiff-rcs are variants of latexdiff-vc which default to the respective versioning system. However, this default can still be overridden using the options above. .IP "\fB\-r\fR, \fB\-r\fR \fIrev\fR or \fB\-\-revision\fR, \fB\-\-revision=\fR\fIrev\fR" 4 .IX Item "-r, -r rev or --revision, --revision=rev" -Choose revision (under \s-1RCS\s0, \s-1CVS\s0 or \s-1SVN\s0). One or two \fB\-r\fR options can be -specified, and the resulting in different behaviour: +Choose revision (under \s-1RCS\s0, \s-1CVS\s0, \s-1SVN\s0 or \s-1GIT\s0). One or two \fB\-r\fR options can be +specified, and they result in different behaviour: .RS 4 .IP "\fBlatexdiff-vc\fR \-r \fIfile.tex\fR ..." 4 .IX Item "latexdiff-vc -r file.tex ..." @@ -187,10 +186,13 @@ reported to stdout. .IP "\fB\-d\fR or \fB\-\-dir\fR \fB\-d\fR \fIpath\fR or \fB\-\-dir=\fR\fIpath\fR" 4 .IX Item "-d or --dir -d path or --dir=path" Rather than appending the string \f(CW\*(C`diff\*(C'\fR and optionally the version -numbers given to the output\-file, this will prepend a directory name \f(CW\*(C`diff\*(C'\fR +numbers given to the output-file, this will prepend a directory name \f(CW\*(C`diff\*(C'\fR to the original filename, creating the directory and subdirectories should they not exist already. This is particularly useful in order to clone a complete directory hierarchy. Optionally, a pathname \fIpath\fR can be specified, which is prepended instead of \f(CW\*(C`diff\*(C'\fR. +.IP "\fB\-\-fast\fR or \fB\-\-so\fR" 4 +.IX Item "--fast or --so" +Use \f(CW\*(C`latexdiff\-fast\*(C'\fR or \f(CW\*(C`latexdiff\-so\*(C'\fR, respectively (instead of \f(CW\*(C`latexdiff\*(C'\fR). .IP "\fB\-\-ps\fR or \fB\-\-postscript\fR" 4 .IX Item "--ps or --postscript" Generate postscript output from difference file. This will run the @@ -226,10 +228,19 @@ latexdiff limited to Unix-like systems. It also requires the \s-1RCS\s0 version control system and latex to be installed on the system. Modules from Perl 5.8 or higher are required. -.SH "AUTHOR" -.IX Header "AUTHOR" -Copyright (C) 2005 Frederik Tilmann +.SH "BUG REPORTING" +.IX Header "BUG REPORTING" +.Vb 6 +\& Please submit bug reports through +\&the latexdiff project page I or send +\&to I. Include the serial number of I +\&(option C<\-\-version>) +\&. +\&=head1 AUTHOR +.Ve +.PP +Copyright (C) 2005,2012 Frederik Tilmann .PP This program is free software; you can redistribute it and/or modify -it under the terms of the \s-1GNU\s0 General Public License Version 2 +it under the terms of the \s-1GNU\s0 General Public License Version 3 Contributors: S Utcke, H Bruyninckx diff --git a/Master/texmf/doc/man/man1/latexdiff-vc.man1.pdf b/Master/texmf/doc/man/man1/latexdiff-vc.man1.pdf index 4006570e376..779eaa29e23 100644 Binary files a/Master/texmf/doc/man/man1/latexdiff-vc.man1.pdf and b/Master/texmf/doc/man/man1/latexdiff-vc.man1.pdf differ diff --git a/Master/texmf/doc/man/man1/latexdiff.1 b/Master/texmf/doc/man/man1/latexdiff.1 index 7b6653fca4e..2f075daa0a9 100644 --- a/Master/texmf/doc/man/man1/latexdiff.1 +++ b/Master/texmf/doc/man/man1/latexdiff.1 @@ -1,15 +1,7 @@ -.\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 +.\" Automatically generated by Pod::Man 2.23 (Pod::Simple 3.14) .\" .\" Standard preamble: .\" ======================================================================== -.de Sh \" Subsection heading -.br -.if t .Sp -.ne 5 -.PP -\fB\\$1\fR -.PP -.. .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp @@ -25,11 +17,11 @@ .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left -.\" double quote, and \*(R" will give a right double quote. | will give a -.\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to -.\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' -.\" expand to `' in nroff, nothing in troff, for use with C<>. -.tr \(*W-|\(bv\*(Tr +.\" double quote, and \*(R" will give a right double quote. \*(C+ will +.\" give a nicer C++. Capital omega is used to do unbreakable dashes and +.\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, +.\" nothing in troff, for use with C<>. +.tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- @@ -48,22 +40,25 @@ . ds R" '' 'br\} .\" +.\" Escape single quotes in literal strings from groff's Unicode transform. +.ie \n(.g .ds Aq \(aq +.el .ds Aq ' +.\" .\" If the F register is turned on, we'll generate index entries on stderr for -.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index +.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. -.if \nF \{\ +.ie \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} -.\" -.\" For nroff, turn off justification. Always turn off hyphenation; it makes -.\" way too many mistakes in technical documents. -.hy 0 -.if n .na +.el \{\ +. de IX +.. +.\} .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. @@ -129,7 +124,11 @@ .\" ======================================================================== .\" .IX Title "LATEXDIFF 1" -.TH LATEXDIFF 1 "2007-10-19" "perl v5.8.0" " " +.TH LATEXDIFF 1 "2012-12-16" "perl v5.12.4" " " +.\" For nroff, turn off justification. Always turn off hyphenation; it makes +.\" way too many mistakes in technical documents. +.if n .ad l +.nh .SH "NAME" latexdiff \- determine and markup differences between two latex files .SH "SYNOPSIS" @@ -157,25 +156,21 @@ differences, the resulting file \f(CW\*(C`diff.tex\*(C'\fR will be similar to \&\f(CW\*(C`new.tex\*(C'\fR. At the end of the preamble, the definitions for \fIlatexdiff\fR markup commands are inserted. In differencing the main body of the text, \fIlatexdiff\fR attempts to satisfy the following guidelines (in order of priority): -.IP "1" 3 -.IX Item "1" +.IP "1." 3 If both \f(CW\*(C`old.tex\*(C'\fR and \f(CW\*(C`new.tex\*(C'\fR are valid LaTeX, then the resulting \&\f(CW\*(C`diff.tex\*(C'\fR should also be valid LateX. (\s-1NB\s0 If a few plain TeX commands are used within \f(CW\*(C`old.tex\*(C'\fR or \f(CW\*(C`new.tex\*(C'\fR then \f(CW\*(C`diff.tex\*(C'\fR is not guaranteed to work but usually will). -.IP "2" 3 -.IX Item "2" +.IP "2." 3 Significant differences are determined on the level of individual words. All significant differences, including differences between comments should be clearly marked in the resulting source code \&\f(CW\*(C`diff.tex\*(C'\fR. -.IP "3" 3 -.IX Item "3" +.IP "3." 3 If a changed passage contains text or text-producing commands, then running \f(CW\*(C`diff.tex\*(C'\fR through LateX should produce output where added and discarded passages are highlighted. -.IP "4" 3 -.IX Item "4" +.IP "4." 3 Where there are insignificant differences, e.g. in the positioning of line breaks, \f(CW\*(C`diff.tex\*(C'\fR should follow the formatting of \f(CW\*(C`new.tex\*(C'\fR .PP @@ -195,7 +190,7 @@ curly braces immediately following a command (i.e. a sequence of letters beginning with a backslash) are arguments for that command. As a restriction to condition 1 above it is thus necessary to surround all arguments with curly braces, and to not insert -extraneous spaces. For example, write +extraneous spaces. For example, write .PP .Vb 1 \& \esection{\etextem{This is an emphasized section title}} @@ -225,7 +220,7 @@ protect parts of the latex file where the markup results in illegal markup. You have to surround the offending passage in both the old and new file by \f(CW\*(C`\ebegin{DIFnomarkup}\*(C'\fR and \f(CW\*(C`\eend{DIFnomarkup}\*(C'\fR. You must define the environment in the preambles of both old and new -documents. I prefer to define it as a null\-environment, +documents. I prefer to define it as a null-environment, .PP \&\f(CW\*(C`\enewenvironment{DIFnomarkup}{}{}\*(C'\fR .PP @@ -255,7 +250,7 @@ and curly braces within deleted blocks are commented out with \&\*(R"\f(CW\*(C`%DIFDELCMD\ <\ \*(C'\fR". .SH "OPTIONS" .IX Header "OPTIONS" -.Sh "Preamble" +.SS "Preamble" .IX Subsection "Preamble" The following options determine the visual markup style by adding the appropriate command definitions to the preamble. See the end of this section for a description of @@ -264,7 +259,7 @@ available styles. .IX Item "--type=markupstyle or -t markupstyle" Add code to preamble for selected markup style. This option defines \&\f(CW\*(C`\eDIFadd\*(C'\fR and \f(CW\*(C`\eDIFdel\*(C'\fR commands. -Available styles: +Available styles: .Sp \&\f(CW\*(C`UNDERLINE CTRADITIONAL TRADITIONAL CFONT FONTSTRIKE INVISIBLE CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR\*(C'\fR @@ -275,7 +270,7 @@ CHANGEBAR CCHANGEBAR CULINECHBAR CFONTCBHBAR\*(C'\fR Add code to preamble for selected style for bracketing commands (e.g. to mark changes in margin). This option defines \&\f(CW\*(C`\eDIFaddbegin\*(C'\fR, \f(CW\*(C`\eDIFaddend\*(C'\fR, \f(CW\*(C`\eDIFdelbegin\*(C'\fR and \f(CW\*(C`\eDIFdelend\*(C'\fR commands. -Available styles: \f(CW\*(C`SAFE MARGINAL DVIPSCOL\*(C'\fR +Available styles: \f(CW\*(C`SAFE MARGINAL COLOR DVIPSCOL\*(C'\fR .Sp [ Default: \f(CW\*(C`SAFE\*(C'\fR ] .IP "\fB\-\-floattype=markstyle\fR or \fB\-f markstyle\fR" 4 @@ -292,9 +287,9 @@ Available styles: \f(CW\*(C`FLOATSAFE TRADITIONALSAFE IDENTICAL\*(C'\fR .IX Item "--encoding=enc or -e enc" Specify encoding of old.tex and new.tex. Typical encodings are \&\f(CW\*(C`ascii\*(C'\fR, \f(CW\*(C`utf8\*(C'\fR, \f(CW\*(C`latin1\*(C'\fR, \f(CW\*(C`latin9\*(C'\fR. A list of available encodings can be -obtained by executing +obtained by executing .Sp -\&\f(CW\*(C`perl \-MEncode \-e 'print join ("\en",Encode\-\*(C'\fRencodings( \*(L":all\*(R" )) ;' > +\&\f(CW\*(C`perl \-MEncode \-e \*(Aqprint join ("\en",Encode\-\*(C'\fRencodings( \*(L":all\*(R" )) ;' > .Sp [Default encoding is utf8 unless the first few lines of the preamble contain an invocation \f(CW\*(C`\eusepackage[..]{inputenc}\*(C'\fR in which case the @@ -344,7 +339,7 @@ errors). .IP "\fB\-\-show\-preamble\fR" 4 .IX Item "--show-preamble" Print generated or included preamble commands to stdout. -.Sh "Configuration" +.SS "Configuration" .IX Subsection "Configuration" .ie n .IP "\fB\-\-exclude\-safecmd=exclude\-file\fR or \fB\-A exclude-file\fR or \fB\-\-exclude\-safecmd=""cmd1,cmd2,...""\fR" 4 .el .IP "\fB\-\-exclude\-safecmd=exclude\-file\fR or \fB\-A exclude-file\fR or \fB\-\-exclude\-safecmd=``cmd1,cmd2,...''\fR" 4 @@ -396,8 +391,8 @@ context to work, e.g. \ecaption will only work within a figure or table. These commands behave like text commands, except when they occur in a deleted section, when they are disabled, but their argument is shown as deleted text. -.IP "\fB\-\-replace\-context1cmd=replace\-file\fR" 4 -.IX Item "--replace-context1cmd=replace-file" +.IP "\fB\-\-replace\-context2cmd=replace\-file\fR" 4 +.IX Item "--replace-context2cmd=replace-file" .PD 0 .ie n .IP "\fB\-\-append\-context2cmd=append\-file\fR or =item \fB\-\-append\-context2cmd=""cmd1,cmd2,...""\fR As corresponding commands for context1. The only difference is that context2 commands are completely disabled in deleted sections, including their arguments." 4 .el .IP "\fB\-\-append\-context2cmd=append\-file\fR or =item \fB\-\-append\-context2cmd=``cmd1,cmd2,...''\fR As corresponding commands for context1. The only difference is that context2 commands are completely disabled in deleted sections, including their arguments." 4 @@ -409,7 +404,7 @@ argument is shown as deleted text. .PD Set configuration variables. The option can be repeated to set different variables (as an alternative to the comma-separated list). -Available variables (see below for further explanations): +Available variables (see below for further explanations): .Sp \&\f(CW\*(C`MINWORDSBLOCK\*(C'\fR (integer) .Sp @@ -443,29 +438,87 @@ Combine all \-\-show commands. .Sp \&\s-1NB\s0 For all \-\-show commands, no \f(CW\*(C`old.tex\*(C'\fR or \f(CW\*(C`new.tex\*(C'\fR file needs to be specified, and no differencing takes place. -.Sh "Miscellaneous" +.SS "Other configuration options:" +.IX Subsection "Other configuration options:" +.IP "\fB\-\-allow\-spaces\fR" 4 +.IX Item "--allow-spaces" +Allow spaces between bracketed or braced arguments to commands. Note +that this option might have undesirable side effects (unrelated scope +might get lumpeded with preceding commands) so should only be used if the +default produces erroneous results. (Default requires arguments to +directly follow each other without intervening spaces). +.IP "\fB\-\-math\-markup=level\fR" 4 +.IX Item "--math-markup=level" +Determine granularity of markup in displayed math environments: +Possible values for level are (both numerical and text labels are acceptable): +.Sp +\&\f(CW\*(C`off\*(C'\fR or \f(CW0\fR: suppress markup for math environments. Deleted equations will not +appear in diff file. This mode can be used if all the other modes +cause invalid latex code. +.Sp +\&\f(CW\*(C`whole\*(C'\fR or \f(CW1\fR: Differencing on the level of whole equations. Even trivial changes +to equations cause the whole equation to be marked changed. This +mode can be used if processing in coarse or fine mode results in +invalid latex code. +.Sp +\&\f(CW\*(C`coarse\*(C'\fR or \f(CW2\fR: Detect changes within equations marked up with a coarse +granularity; changes in equation type (e.g.displaymath to equation) +appear as a change to the complete equation. This mode is recommended +for situations where the content and order of some equations are still +being changed. [Default] +.Sp +\&\f(CW\*(C`fine\*(C'\fR or \f(CW3\fR: Detect small change in equations and mark up at fine granularity. +This mode is most suitable, if only minor changes to equations are +expected, e.g. correction of typos. +.IP "\fB\-\-disable\-citation\-markup\fR" 4 +.IX Item "--disable-citation-markup" +Suppress citation markup in styles using ulem (\s-1UNDERLINE\s0, +\&\s-1FONTSTRIKE\s0, \s-1CULINECHBAR\s0) +.IP "\fB\-\-enable\-citation\-markup\fR" 4 +.IX Item "--enable-citation-markup" +Protect citation commands in changed sections with \e\embox command [i.e. use default behaviour for ulem package for other packages] +.SS "Miscellaneous" .IX Subsection "Miscellaneous" -.IP "\fB\-\-verbose\fR or \fB\-V\fR" 4 -.IX Item "--verbose or -V" +.RS 4 Output various status information to stderr during processing. Default is to work silently. -.IP "\fB\-\-ignore\-warnings\fR" 4 -.IX Item "--ignore-warnings" +.Sp +\&\fB\-\-driver=type\fR +.Sp +Choose driver for changebar package (only relevant for styles using + changebar: \s-1CCHANGEBAR\s0 \s-1CFONTCHBAR\s0 \s-1CULINECHBAR\s0 \s-1CHANGEBAR\s0). Possible +drivers are listed in changebar manual, e.g. pdftex,dvips,dvitops + [Default: dvips] +.Sp +\&\fB\-\-ignore\-warnings\fR +.Sp Suppress warnings about inconsistencies in length between input and parsed strings and missing characters. These warning messages are often related to non-standard latex or latex constructions with a syntax unknown to \f(CW\*(C`latexdiff\*(C'\fR but the resulting difference argument is often fully functional anyway, particularly if the non-standard latex only occurs in parts of the text which have not changed. -.IP "\fB\-\-allow\-spaces\fR" 4 -.IX Item "--allow-spaces" -Allow spaces between bracketed or braced arguments to commands. Note -that this option might have undesirable side effects (unrelated scope -might get lumpeded with preceding commands) so should only be used if the -default produces erroneous results. (Default requires arguments to -directly follow each other without intervening spaces). -.IP "\fB\-\-flatten\fR" 4 -.IX Item "--flatten" +.Sp +\&\fB\-\-label=label\fR or +\&\fB\-L label\fR +.Sp +Sets the labels used to describe the old and new files. The first use +of this option sets the label describing the old file and the second +use of the option sets the label for the new file, i.e. set both +labels like this \f(CW\*(C`\-L labelold \-L labelnew\*(C'\fR. +[Default: use the filename and modification dates for the label] +.Sp +\&\fB\-\-no\-label\fR +.Sp +Suppress inclusion of old and new file names as comment in output file +.Sp +\&\fB\-\-visble\-label\fR +.Sp +Include old and new filenames (or labels set with \-\-label option) as +visible output. +.Sp +\&\fB\-\-flatten\fR +.Sp Replace \f(CW\*(C`\einput\*(C'\fR and \f(CW\*(C`\einclude\*(C'\fR commands within body by the content of the files in their argument. If \f(CW\*(C`\eincludeonly\*(C'\fR is present in the preamble, only those files are expanded into the document. However, @@ -473,20 +526,25 @@ no recursion is done, i.e. \f(CW\*(C`\einput\*(C'\fR and \f(CW\*(C`\einclude\*(C included sections are not expanded. The included files are assumed to be located in the same directories as the old and new master files, respectively, making it possible to organise files into old and new directories. +\&\-\-flatten is applied recursively, so inputted files can contain further +\&\f(CW\*(C`\einput\*(C'\fR statements. +.Sp +Use of this option might result in prohibitive processing times for +larger documents, and the resulting difference document +no longer reflects the structure of the input documents. +.Sp +\&\fB\-\-help\fR or +\&\fB\-h\fR .Sp -Use of this option is not recommended -primarily the processing time for the large documents is prohibitive, and -the resulting difference document no longer reflects the structure of the -input documents. -.IP "\fB\-\-help\fR or \fB\-h\fR" 4 -.IX Item "--help or -h" Show help text -.IP "\fB\-\-version\fR" 4 -.IX Item "--version" +.Sp +\&\fB\-\-version\fR +.Sp Show version number -.Sh "Predefined styles" +.RE +.SS "Predefined styles" .IX Subsection "Predefined styles" -.Sh "Major types" +.SS "Major types" .IX Subsection "Major types" The major type determine the markup of plain text and some selected latex commands outside floats by defining the markup commands \f(CW\*(C`\eDIFadd{...}\*(C'\fR and \f(CW\*(C`\eDIFdel{...}\*(C'\fR . .ie n .IP """UNDERLINE""" 10 @@ -497,7 +555,7 @@ Added text is wavy-underlined and blue, discarded text is struck out and red .ie n .IP """CTRADITIONAL""" 10 .el .IP "\f(CWCTRADITIONAL\fR" 10 .IX Item "CTRADITIONAL" -Added text is blue and set in sans\-serif, and a red footnote is created for each discarded +Added text is blue and set in sans-serif, and a red footnote is created for each discarded piece of text. (Requires color package) .ie n .IP """TRADITIONAL""" 10 .el .IP "\f(CWTRADITIONAL\fR" 10 @@ -506,11 +564,11 @@ Like \f(CW\*(C`CTRADITIONAL\*(C'\fR but without the use of color. .ie n .IP """CFONT""" 10 .el .IP "\f(CWCFONT\fR" 10 .IX Item "CFONT" -Added text is blue and set in sans\-serif, and discarded text is red and very small size. +Added text is blue and set in sans-serif, and discarded text is red and very small size. .ie n .IP """FONTSTRIKE""" 10 .el .IP "\f(CWFONTSTRIKE\fR" 10 .IX Item "FONTSTRIKE" -Added tex is set in sans\-serif, discarded text small and struck out +Added tex is set in sans-serif, discarded text small and struck out .ie n .IP """CCHANGEBAR""" 10 .el .IP "\f(CWCCHANGEBAR\fR" 10 .IX Item "CCHANGEBAR" @@ -531,9 +589,9 @@ No mark up of text, but mark margins with changebars (Requires changebar package .el .IP "\f(CWINVISIBLE\fR" 10 .IX Item "INVISIBLE" No visible markup (but generic markup commands will still be inserted. -.Sh "Subtypes" +.SS "Subtypes" .IX Subsection "Subtypes" -The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: \f(CW\*(C`\eDIFaddbegin, \eDIFaddend, \eDIFdelbegin, \eDIFdelend\*(C'\fR) +The subtype defines the commands that are inserted at the begin and end of added or discarded blocks, irrespectively of whether these blocks contain text or commands (Defined commands: \f(CW\*(C`\eDIFaddbegin, \eDIFaddend, \eDIFdelbegin, \eDIFdelend\*(C'\fR) .ie n .IP """SAFE""" 10 .el .IP "\f(CWSAFE\fR" 10 .IX Item "SAFE" @@ -544,6 +602,13 @@ No additional markup (Recommended choice) Mark beginning and end of changed blocks with symbols in the margin nearby (using the standard \f(CW\*(C`\emarginpar\*(C'\fR command \- note that this sometimes moves somewhat from the intended position. +.ie n .IP """COLOR""" 10 +.el .IP "\f(CWCOLOR\fR" 10 +.IX Item "COLOR" +An alternative way of marking added passages in blue, and deleted ones in red. +(It is recommeneded to use instead the main types to effect colored markup, +although in some cases coloring with dvipscol can be more complete, for example +with citation commands). .ie n .IP """DVIPSCOL""" 10 .el .IP "\f(CWDVIPSCOL\fR" 10 .IX Item "DVIPSCOL" @@ -551,7 +616,7 @@ An alternative way of marking added passages in blue, and deleted ones in red. N that \f(CW\*(C`DVIPSCOL\*(C'\fR only works with the dvips converter, e.g. not pdflatex. (it is recommeneded to use instead the main types to effect colored markup, although in some cases coloring with dvipscol can be more complete). -.Sh "Float Types" +.SS "Float Types" .IX Subsection "Float Types" Some of the markup used in the main text might cause problems when used within floats (e.g. figures or tables). For this reason alternative versions of all @@ -559,7 +624,7 @@ markup commands are used within floats. The float type defines these alternative .ie n .IP """FLOATSAFE""" 10 .el .IP "\f(CWFLOATSAFE\fR" 10 .IX Item "FLOATSAFE" -Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null\-commands. You have to choose this float type if your subtype is \f(CW\*(C`MARGIN\*(C'\fR as \f(CW\*(C`\emarginpar\*(C'\fR does not work properly within floats. +Use identical markup for text as in the main body, but set all commands marking the begin and end of changed blocks to null-commands. You have to choose this float type if your subtype is \f(CW\*(C`MARGIN\*(C'\fR as \f(CW\*(C`\emarginpar\*(C'\fR does not work properly within floats. .ie n .IP """TRADITIONALSAFE""" 10 .el .IP "\f(CWTRADITIONALSAFE\fR" 10 .IX Item "TRADITIONALSAFE" @@ -568,7 +633,7 @@ Mark additions the same way as in the main text. Deleted environments are marke .el .IP "\f(CWIDENTICAL\fR" 10 .IX Item "IDENTICAL" Make no difference between the main text and floats. -.Sh "Configuration Variables" +.SS "Configuration Variables" .IX Subsection "Configuration Variables" .ie n .IP """MINWORDSBLOCK""" 10 .el .IP "\f(CWMINWORDSBLOCK\fR" 10 @@ -593,7 +658,7 @@ all latexdiff markup is removed (in pathologic cases this might lead to inconsistent markup but this situation should be rare). .Sp [ Default: \f(CW\*(C`(?:picture|DIFnomarkup)[\ew\ed*@]*\*(C'\fR\ ] -.ie n .IP """MATHENV""\fR,\f(CW""MATHREPL""" 10 +.ie n .IP """MATHENV"",""MATHREPL""" 10 .el .IP "\f(CWMATHENV\fR,\f(CWMATHREPL\fR" 10 .IX Item "MATHENV,MATHREPL" If both \ebegin and \eend for a math environment (environment name matching \f(CW\*(C`MATHENV\*(C'\fR @@ -602,7 +667,7 @@ are within the same deleted block, they are replaced by a \ebegin and \eend comm rather than being commented out. .Sp [ Default: \f(CW\*(C`MATHENV\*(C'\fR=\f(CW\*(C`(?:displaymath|equation)\*(C'\fR\ , \f(CW\*(C`MATHREPL\*(C'\fR=\f(CW\*(C`displaymath\*(C'\fR\ ] -.ie n .IP """MATHARRENV""\fR,\f(CW""MATHARRREPL""" 10 +.ie n .IP """MATHARRENV"",""MATHARRREPL""" 10 .el .IP "\f(CWMATHARRENV\fR,\f(CWMATHARRREPL\fR" 10 .IX Item "MATHARRENV,MATHARRREPL" as \f(CW\*(C`MATHENV\*(C'\fR,\f(CW\*(C`MATHREPL\*(C'\fR but for equation arrays @@ -614,7 +679,7 @@ as \f(CW\*(C`MATHENV\*(C'\fR,\f(CW\*(C`MATHREPL\*(C'\fR but for equation arrays If a match to \f(CW\*(C`ARRENV\*(C'\fR is found within an inline math environment within a deleted or added block, then the inlined math is surrounded by \f(CW\*(C`\embox{\*(C'\fR...\f(CW\*(C`}\*(C'\fR. This is necessary as underlining does not work within inlined array environments. .Sp -[ Default: \f(CW\*(C`ARRENV\*(C'\fR=\f(CW\*(C`(?:array|[pbvBV]matrix)\*(C'\fR\ +[ Default: \f(CW\*(C`ARRENV\*(C'\fR=\f(CW\*(C`(?:array|[pbvBV]matrix)\*(C'\fR\ .ie n .IP """COUNTERCMD""" 10 .el .IP "\f(CWCOUNTERCMD\fR" 10 .IX Item "COUNTERCMD" @@ -625,25 +690,42 @@ numbering in the new file. [ Default: \f(CW\*(C`COUNTERCMD\*(C'\fR=\f(CW\*(C`(?:footnote|part|section|subsection\*(C'\fR ... .Sp \&\f(CW\*(C`|subsubsection|paragraph|subparagraph)\*(C'\fR ] +.SH "COMMON PROBLEMS" +.IX Header "COMMON PROBLEMS" +.IP "Citations result in overfull boxes" 10 +.IX Item "Citations result in overfull boxes" +There is an incompatibility between the \f(CW\*(C`ulem\*(C'\fR package, which \f(CW\*(C`latexdiff\*(C'\fR uses for underlining and striking out in the \s-1UNDERLINE\s0 style, +the default style. In order to be able to mark up citations properly, they are placed with an \f(CW\*(C`\embox\*(C'\fR command in post-processing. As mboxes +cannot be broken across lines, this procedure frequently results in overfull boxes, possibly obscuring the content as it extends beyond the right margin. If this is a problem, you have two possibilities: +.Sp +1. Use \f(CW\*(C`COLOR\*(C'\fR or \f(CW\*(C`DVIPSCOL\*(C'\fR subtype markup (option \f(CW\*(C`\-s COLOR\*(C'\fR): If this markup is chosen, then changed citations are no longer marked up +with the wavy line (additions) or struck out (deletions), but are still highlighted in the appropriate color. +.Sp +2. Choose option \f(CW\*(C`\-\-disable\-citation\-markup\*(C'\fR which turns off the marking up of citations: deleted citations are no longer shown, and +added ctations are shown without markup. (This was the default behaviour of latexdiff at versions 0.6 and older) +.IP "Changes in complicated mathematical equations result in latex processing errors" 10 +.IX Item "Changes in complicated mathematical equations result in latex processing errors" +Try options \f(CW\*(C`\-\-math\-markup=whole\*(C'\fR. If even that fails, you can turn off mark up for equations with \f(CW\*(C`\-\-math\-markup=off\*(C'\fR. .SH "BUGS" .IX Header "BUGS" -\&\s-1UTF\-8\s0 support requires a relatively new version of perl (5.8.0 is sufficient -but 5.6.2 up would work \s-1OK\s0, too). -.PP Option allow-spaces not implemented entirely consistently. It breaks the rules that number and type of white space does not matter, as different numbers of inter-argument spaces are treated as significant. .PP -Please send bug reports -to \fItilmann@esc.cam.ac.uk\fR. Include the serial number of \fIlatexdiff\fR +Please submit bug reports on the latexdiff project page \fIhttp://latexdiff.berlios.de\fR, +send them to user discussion list \f(CW\*(C`latexdiff\-users@lists.berlios,de\*(C'\fR (prior subscription +to list required, also on project webpage) +or send them to \fItilmann@gfz\-potsdam.de\fR. Include the serial number of \fIlatexdiff\fR (from comments at the top of the source or use \fB\-\-version\fR). If you come across latex files that are error-free and conform to the specifications set out above, and whose differencing still does not result in error-free latex, please send me those files, ideally edited to only contain the -offending passage as long as that still reproduces the problem. +offending passage as long as that still reproduces the problem. If your +file relies on non-standard class files, you must include those. I will not +look at examples where I have trouble to latex the original files. .SH "SEE ALSO" .IX Header "SEE ALSO" -latexrevise +latexrevise, latexdiff-vc .SH "PORTABILITY" .IX Header "PORTABILITY" \&\fIlatexdiff\fR does not make use of external commands and thus should run @@ -657,10 +739,20 @@ version, \fIlatexdiff-so\fR, which has this package inlined, is available, too. \&\fIlatexdiff-fast\fR requires the \fIdiff\fR command to be present. .SH "AUTHOR" .IX Header "AUTHOR" -Copyright (C) 2004\-2007 Frederik Tilmann +Version 1.0.2 +Copyright (C) 2004\-2012 Frederik Tilmann .PP This program is free software; you can redistribute it and/or modify -it under the terms of the \s-1GNU\s0 General Public License Version 2 +it under the terms of the \s-1GNU\s0 General Public License Version 3 .PP -Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner -Thanks to everyone who send in bug reports. +Contributors of fixes and additions: V. Kuhlmann, J. Paisley, N. Becker, T. Doerges, K. Huebner, +T. Connors, Sebastian Gouezel and many others. +Thanks to the many people who send in bug reports, feature suggestions, and other feedback. +.SH "POD ERRORS" +.IX Header "POD ERRORS" +Hey! \fBThe above document had some coding errors, which are explained below:\fR +.IP "Around line 2942:" 4 +.IX Item "Around line 2942:" +=over should be: '=over' or '=over positive_number' +.Sp +You can't have =items (as at line 2948) unless the first thing after the =over is an =item diff --git a/Master/texmf/doc/man/man1/latexdiff.man1.pdf b/Master/texmf/doc/man/man1/latexdiff.man1.pdf index e3ab33271c6..efa57b96109 100644 Binary files a/Master/texmf/doc/man/man1/latexdiff.man1.pdf and b/Master/texmf/doc/man/man1/latexdiff.man1.pdf differ diff --git a/Master/texmf/doc/man/man1/latexrevise.1 b/Master/texmf/doc/man/man1/latexrevise.1 index 283c614677b..b8d0d2da807 100644 --- a/Master/texmf/doc/man/man1/latexrevise.1 +++ b/Master/texmf/doc/man/man1/latexrevise.1 @@ -1,15 +1,7 @@ -.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.14 +.\" Automatically generated by Pod::Man 2.23 (Pod::Simple 3.14) .\" .\" Standard preamble: .\" ======================================================================== -.de Sh \" Subsection heading -.br -.if t .Sp -.ne 5 -.PP -\fB\\$1\fR -.PP -.. .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp @@ -25,11 +17,11 @@ .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left -.\" double quote, and \*(R" will give a right double quote. | will give a -.\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to -.\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' -.\" expand to `' in nroff, nothing in troff, for use with C<>. -.tr \(*W-|\(bv\*(Tr +.\" double quote, and \*(R" will give a right double quote. \*(C+ will +.\" give a nicer C++. Capital omega is used to do unbreakable dashes and +.\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, +.\" nothing in troff, for use with C<>. +.tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- @@ -48,22 +40,25 @@ . ds R" '' 'br\} .\" +.\" Escape single quotes in literal strings from groff's Unicode transform. +.ie \n(.g .ds Aq \(aq +.el .ds Aq ' +.\" .\" If the F register is turned on, we'll generate index entries on stderr for -.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index +.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. -.if \nF \{\ +.ie \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} -.\" -.\" For nroff, turn off justification. Always turn off hyphenation; it makes -.\" way too many mistakes in technical documents. -.hy 0 -.if n .na +.el \{\ +. de IX +.. +.\} .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. @@ -129,7 +124,11 @@ .\" ======================================================================== .\" .IX Title "LATEXREVISE 1" -.TH LATEXREVISE 1 "2007-09-07" "perl v5.8.5" " " +.TH LATEXREVISE 1 "2012-12-16" "perl v5.12.4" " " +.\" For nroff, turn off justification. Always turn off hyphenation; it makes +.\" way too many mistakes in technical documents. +.if n .ad l +.nh .SH "NAME" latexrevise \- selectively remove markup and text from latexdiff output .SH "SYNOPSIS" @@ -171,7 +170,7 @@ and \f(CW\*(C`\eDIFaddend\*(C'\fR). .IX Item "-s or --simplify" Run in \fI\s-1SIMPLIFY\s0\fR mode (Keep all \f(CW\*(C`\eDIFaddbegin\*(C'\fR, \f(CW\*(C`\eDIFaddend\*(C'\fR, \&\f(CW\*(C`\eDIFdelbegin\*(C'\fR, \f(CW\*(C`\eDIFdelend\*(C'\fR tokens, but remove all other latexdiff -markup from body). +markup from body). .PP Note that the three mode options are mutually exclusive. If no mode option is given, \&\fIlatexrevise\fR simply removes user annotations and markup according to the following four @@ -195,7 +194,7 @@ blocks. .IP "\fB\-m cmd\fR or \fB\-\-markup=cmd\fR" 4 .IX Item "-m cmd or --markup=cmd" Remove the markup command \f(CW\*(C`\ecmd\*(C'\fR but leave its argument, i.e. -turn \f(CW\*(C`\ecmd{abc}\*(C'\fR into \f(CW\*(C`abc\*(C'\fR. +turn \f(CW\*(C`\ecmd{abc}\*(C'\fR into \f(CW\*(C`abc\*(C'\fR. .IP "\fB\-n envir\fR or \fB\-\-markup\-environment=envir\fR" 4 .IX Item "-n envir or --markup-environment=envir" Similarly, remove \f(CW\*(C`\ebegin{envir}\*(C'\fR and \f(CW\*(C`\eend{envir}\*(C'\fR commands but @@ -210,15 +209,16 @@ which should have been removed already. .SH "BUGS" .IX Header "BUGS" The current version is a beta version which has not yet been -extensively tested, but worked fine locally. Please send bug reports -to \fItilmann@esc.cam.ac.uk\fR. Include the serial number of \fIlatexrevise\fR +extensively tested, but worked fine locally. Please submit bug reports through +the latexdiff project page \fIhttp://developer.berlios.de/projects/latexdiff/\fR or send +to \fItilmann@gfz\-potsdam.de\fR. Include the serial number of \fIlatexrevise\fR (from comments at the top of the source). If you come across latexdiff output which is not processed correctly by \fIlatexrevise\fR please include the problem file as well as the old and new files on which it is based, ideally edited to only contain the offending passage as long as that still reproduces the problem. .PP -\&\fIlatexrevise\fR gets confused by commented \f(CW\*(C`\ebegin{document}\*(C'\fR or +Note that \fIlatexrevise\fR gets confused by commented \f(CW\*(C`\ebegin{document}\*(C'\fR or \&\f(CW\*(C`\eend{document}\*(C'\fR statements .SH "SEE ALSO" .IX Header "SEE ALSO" @@ -226,10 +226,10 @@ latexdiff .SH "PORTABILITY" .IX Header "PORTABILITY" \&\fIlatexrevise\fR does not make use of external commands and thus should run -on any platform supporting \s-1PERL\s0 v5 or higher. +on any platform supporting \s-1PERL\s0 v5 or higher. .SH "AUTHOR" .IX Header "AUTHOR" Copyright (C) 2004 Frederik Tilmann .PP This program is free software; you can redistribute it and/or modify -it under the terms of the \s-1GNU\s0 General Public License Version 2 +it under the terms of the \s-1GNU\s0 General Public License Version 3 diff --git a/Master/texmf/doc/man/man1/latexrevise.man1.pdf b/Master/texmf/doc/man/man1/latexrevise.man1.pdf index a2e788c29dc..623a87d27af 100644 Binary files a/Master/texmf/doc/man/man1/latexrevise.man1.pdf and b/Master/texmf/doc/man/man1/latexrevise.man1.pdf differ diff --git a/Master/tlpkg/libexec/ctan2tds b/Master/tlpkg/libexec/ctan2tds index c815fade73b..b1231301cef 100755 --- a/Master/tlpkg/libexec/ctan2tds +++ b/Master/tlpkg/libexec/ctan2tds @@ -1062,6 +1062,7 @@ chomp ($Build = `cd $Master/../Build/source && pwd`); 'fontools' => '&PREHOOK_fontools', 'ibygrk' => '&PREHOOK_ibygrk', 'ktv-texdata' => '&PREHOOK_ktv_texdata', + 'latexdiff' => '&PREHOOK_latexdiff', 'mathspic' => '&PREHOOK_mathspic', 'movie15' => '&PREHOOK_flatten1', 'musixtex' => '&PREHOOK_musixtex', @@ -1107,7 +1108,6 @@ chomp ($Build = `cd $Master/../Build/source && pwd`); 'knitting' => '&POSTknitting', 'knuth' => '&POSTknuth', 'koma-script' => '&POST_rmsymlink', - 'latexdiff' => '&POSTlatexdiff', 'latex2e-help-texinfo' => '&POSTlatex2ehelptexinfo', 'listbib' => '&POSTlistbib', 'lithuanian' => '&POSTlithuanian', @@ -2283,7 +2283,7 @@ $standardxmt='\.xmt'; 'installfont' => 'installfont-tl', 'jfontmaps' => 'updmap-setup-kanji\.pl|updmap-setup-kanji-sys.sh', 'latex2man' => 'latex2man$', - 'latexdiff' => 'latex(diff-so|diff-vc|revise)$', + 'latexdiff' => 'latex(diff|diff-vc|revise)\.pl$', 'latexmk' => '\.pl$', 'latexfileversion' => 'latexfileversion$', 'latexpand' => 'latexpand$', @@ -3025,7 +3025,6 @@ sub doscripts { } } - # info files. We put these in texmf/doc/info, which is where we keep # the info files for the programs, too. Having an info dir in @@ -4673,6 +4672,14 @@ sub PREHOOK_ktv_texdata { &SYSTEM ("$RM -rf latex"); } +sub PREHOOK_latexdiff { + print "PREHOOK_$package - rename $package-so to $package.pl, etc.\n"; + # Consistently use *.pl to avoid special case in w32 wrapper + &SYSTEM ("$MV latexdiff-so latexdiff.pl"); + &SYSTEM ("$MV latexrevise latexrevise.pl"); + &SYSTEM ("$MV latexdiff-vc latexdiff-vc.pl"); +} + sub PREHOOK_mathspic { print "PREHOOK_$package - eliminate version from mathspicNNN.pl\n"; # the w32 wrapper can only find foo.pl from foo, not fooNNN.pl. @@ -5080,15 +5087,6 @@ sub POSTlatex2html { &SYSTEM ("$MV $DEST/scripts/latex2html/styles/$package.perl $dest"); } -sub POSTlatexdiff { - print "POST$package - rename $package-so to $package.pl\n"; - # to avoid special case in w32 wrapper - my $dir = "$DEST/scripts/$package"; - &SYSTEM ("$MV $dir/latexdiff-so $dir/latexdiff.pl"); - &SYSTEM ("$MV $dir/latexrevise $dir/latexrevise.pl"); - &SYSTEM ("$MV $dir/latexdiff-vc $dir/latexdiff-vc.pl"); -} - sub POSTlatex2ehelptexinfo { print "\t POST$package - remove translation subdir\n"; &SYSTEM ("$RM -rf spanish"); -- cgit v1.2.3