summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/CORE/handy.h
diff options
context:
space:
mode:
Diffstat (limited to 'Master/tlpkg/tlperl/lib/CORE/handy.h')
-rw-r--r--Master/tlpkg/tlperl/lib/CORE/handy.h463
1 files changed, 364 insertions, 99 deletions
diff --git a/Master/tlpkg/tlperl/lib/CORE/handy.h b/Master/tlpkg/tlperl/lib/CORE/handy.h
index d12972d5297..6541c95c357 100644
--- a/Master/tlpkg/tlperl/lib/CORE/handy.h
+++ b/Master/tlpkg/tlperl/lib/CORE/handy.h
@@ -110,6 +110,12 @@ Null SV pointer. (No longer available when C<PERL_CORE> is defined.)
# define HAS_BOOL 1
#endif
+/* a simple (bool) cast may not do the right thing: if bool is defined
+ * as char for example, then the cast from int is implementation-defined
+ */
+
+#define cBOOL(cbool) ((bool)!!(cbool))
+
/* Try to figure out __func__ or __FUNCTION__ equivalent, if any.
* XXX Should really be a Configure probe, with HAS__FUNCTION__
* and FUNCTION__ as results.
@@ -202,19 +208,6 @@ typedef U64TYPE U64;
# endif
#endif
-/* HMB H.Merijn Brand - a placeholder for preparing Configure patches:
- *
- * USE_DTRACE HAS_PSEUDOFORK HAS_TIMEGM LOCALTIME_R_NEEDS_TZSET
- * GMTIME_MAX GMTIME_MIN LOCALTIME_MAX LOCALTIME_MIN
- * HAS_CTIME64 HAS_LOCALTIME64 HAS_GMTIME64 HAS_DIFFTIME64
- * HAS_MKTIME64 HAS_ASCTIME64 HAS_GETADDRINFO HAS_GETNAMEINFO
- * HAS_INETNTOP HAS_INETPTON CHARBITS
- * Not (yet) used at top level, but mention them for metaconfig
- */
-
-/* Mention I8SIZE, U8SIZE, I16SIZE, U16SIZE, I32SIZE, U32SIZE,
- I64SIZE, and U64SIZE here so that metaconfig pulls them in. */
-
#if defined(UINT8_MAX) && defined(INT16_MAX) && defined(INT32_MAX)
/* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type.
@@ -283,17 +276,41 @@ pair.
Like C<newSVpvn_share>, but takes a literal string instead of a string/length
pair and omits the hash parameter.
+=for apidoc Am|void|sv_catpvs_flags|SV* sv|const char* s|I32 flags
+Like C<sv_catpvn_flags>, but takes a literal string instead of a
+string/length pair.
+
+=for apidoc Am|void|sv_catpvs_nomg|SV* sv|const char* s
+Like C<sv_catpvn_nomg>, but takes a literal string instead of a
+string/length pair.
+
=for apidoc Am|void|sv_catpvs|SV* sv|const char* s
Like C<sv_catpvn>, but takes a literal string instead of a string/length pair.
+=for apidoc Am|void|sv_catpvs_mg|SV* sv|const char* s
+Like C<sv_catpvn_mg>, but takes a literal string instead of a
+string/length pair.
+
=for apidoc Am|void|sv_setpvs|SV* sv|const char* s
Like C<sv_setpvn>, but takes a literal string instead of a string/length pair.
+=for apidoc Am|void|sv_setpvs_mg|SV* sv|const char* s
+Like C<sv_setpvn_mg>, but takes a literal string instead of a
+string/length pair.
+
+=for apidoc Am|SV *|sv_setref_pvs|const char* s
+Like C<sv_setref_pvn>, but takes a literal string instead of a
+string/length pair.
+
=head1 Memory Management
=for apidoc Ama|char*|savepvs|const char* s
Like C<savepvn>, but takes a literal string instead of a string/length pair.
+=for apidoc Ama|char*|savesharedpvs|const char* s
+A version of C<savepvs()> which allocates the duplicate string in memory
+which is shared between threads.
+
=head1 GV Functions
=for apidoc Am|HV*|gv_stashpvs|const char* name|I32 create
@@ -308,6 +325,13 @@ Like C<hv_fetch>, but takes a literal string instead of a string/length pair.
Like C<hv_store>, but takes a literal string instead of a string/length pair
and omits the hash parameter.
+=head1 Lexer interface
+
+=for apidoc Amx|void|lex_stuff_pvs|const char *pv|U32 flags
+
+Like L</lex_stuff_pvn>, but takes a literal string instead of a
+string/length pair.
+
=cut
*/
@@ -324,11 +348,28 @@ and omits the hash parameter.
#define newSVpvs_flags(str,flags) \
Perl_newSVpvn_flags(aTHX_ STR_WITH_LEN(str), flags)
#define newSVpvs_share(str) Perl_newSVpvn_share(aTHX_ STR_WITH_LEN(str), 0)
-#define sv_catpvs(sv, str) Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), SV_GMAGIC)
+#define sv_catpvs_flags(sv, str, flags) \
+ Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), flags)
+#define sv_catpvs_nomg(sv, str) \
+ Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), 0)
+#define sv_catpvs(sv, str) \
+ Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), SV_GMAGIC)
+#define sv_catpvs_mg(sv, str) \
+ Perl_sv_catpvn_flags(aTHX_ sv, STR_WITH_LEN(str), SV_GMAGIC|SV_SMAGIC)
#define sv_setpvs(sv, str) Perl_sv_setpvn(aTHX_ sv, STR_WITH_LEN(str))
+#define sv_setpvs_mg(sv, str) Perl_sv_setpvn_mg(aTHX_ sv, STR_WITH_LEN(str))
+#define sv_setref_pvs(rv, classname, str) \
+ Perl_sv_setref_pvn(aTHX_ rv, classname, STR_WITH_LEN(str))
#define savepvs(str) Perl_savepvn(aTHX_ STR_WITH_LEN(str))
-#define gv_stashpvs(str, create) Perl_gv_stashpvn(aTHX_ STR_WITH_LEN(str), create)
-#define gv_fetchpvs(namebeg, add, sv_type) Perl_gv_fetchpvn_flags(aTHX_ STR_WITH_LEN(namebeg), add, sv_type)
+#define savesharedpvs(str) Perl_savesharedpvn(aTHX_ STR_WITH_LEN(str))
+#define gv_stashpvs(str, create) \
+ Perl_gv_stashpvn(aTHX_ STR_WITH_LEN(str), create)
+#define gv_fetchpvs(namebeg, add, sv_type) \
+ Perl_gv_fetchpvn_flags(aTHX_ STR_WITH_LEN(namebeg), add, sv_type)
+#define gv_fetchpvn(namebeg, len, add, sv_type) \
+ Perl_gv_fetchpvn_flags(aTHX_ namebeg, len, add, sv_type)
+#define sv_catxmlpvs(dsv, str, utf8) \
+ Perl_sv_catxmlpvn(aTHX_ dsv, STR_WITH_LEN(str), utf8)
#define hv_fetchs(hv,key,lval) \
((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
(lval) ? (HV_FETCH_JUST_SV | HV_FETCH_LVALUE) \
@@ -338,6 +379,8 @@ and omits the hash parameter.
((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
(HV_FETCH_ISSTORE|HV_FETCH_JUST_SV), (val), 0))
+#define lex_stuff_pvs(pv,flags) Perl_lex_stuff_pvn(aTHX_ STR_WITH_LEN(pv), flags)
+
#define get_cvs(str, flags) \
Perl_get_cvn_flags(aTHX_ STR_WITH_LEN(str), (flags))
@@ -398,7 +441,7 @@ C<strncmp>).
#endif
#define memEQs(s1, l, s2) \
- (sizeof(s2)-1 == l && memEQ(s1, (s2 ""), (sizeof(s2)-1)))
+ (sizeof(s2)-1 == l && memEQ(s1, ("" s2 ""), (sizeof(s2)-1)))
#define memNEs(s1, l, s2) !memEQs(s1, l, s2)
/*
@@ -423,100 +466,325 @@ C<strncmp>).
/*
=head1 Character classes
-
-=for apidoc Am|bool|isALNUM|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-alphanumeric character (including underscore) or digit.
+There are three variants for all the functions in this section. The base ones
+operate using the character set of the platform Perl is running on. The ones
+with an C<_A> suffix operate on the ASCII character set, and the ones with an
+C<_L1> suffix operate on the full Latin1 character set. All are unaffected by
+locale
+
+For ASCII platforms, the base function with no suffix and the one with the
+C<_A> suffix are identical. The function with the C<_L1> suffix imposes the
+Latin-1 character set onto the platform. That is, the code points that are
+ASCII are unaffected, since ASCII is a subset of Latin-1. But the non-ASCII
+code points are treated as if they are Latin-1 characters. For example,
+C<isSPACE_L1()> will return true when called with the code point 0xA0, which is
+the Latin-1 NO-BREAK SPACE.
+
+For EBCDIC platforms, the base function with no suffix and the one with the
+C<_L1> suffix should be identical, since, as of this writing, the EBCDIC code
+pages that Perl knows about all are equivalent to Latin-1. The function that
+ends in an C<_A> suffix will not return true unless the specified character also
+has an ASCII equivalent.
=for apidoc Am|bool|isALPHA|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-alphabetic character.
+Returns a boolean indicating whether the specified character is an
+alphabetic character in the platform's native character set.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isALPHA_A> and C<isALPHA_L1>.
-=for apidoc Am|bool|isSPACE|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-whitespace.
+=for apidoc Am|bool|isASCII|char ch
+Returns a boolean indicating whether the specified character is one of the 128
+characters in the ASCII character set. On non-ASCII platforms, it is if this
+character corresponds to an ASCII character. Variants C<isASCII_A()> and
+C<isASCII_L1()> are identical to C<isASCII()>.
=for apidoc Am|bool|isDIGIT|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-digit.
-
-=for apidoc Am|bool|isUPPER|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-uppercase character.
+Returns a boolean indicating whether the specified character is a
+digit in the platform's native character set.
+Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
=for apidoc Am|bool|isLOWER|char ch
-Returns a boolean indicating whether the C C<char> is a US-ASCII (Basic Latin)
-lowercase character.
+Returns a boolean indicating whether the specified character is a
+lowercase character in the platform's native character set.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isLOWER_A> and C<isLOWER_L1>.
+
+=for apidoc Am|bool|isOCTAL|char ch
+Returns a boolean indicating whether the specified character is an
+octal digit, [0-7] in the platform's native character set.
+Variants C<isOCTAL_A> and C<isOCTAL_L1> are identical to C<isOCTAL>.
+
+=for apidoc Am|bool|isSPACE|char ch
+Returns a boolean indicating whether the specified character is a
+whitespace character in the platform's native character set. This is the same
+as what C<\s> matches in a regular expression.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isSPACE_A> and C<isSPACE_L1>.
+
+=for apidoc Am|bool|isUPPER|char ch
+Returns a boolean indicating whether the specified character is an
+uppercase character in the platform's native character set.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isUPPER_A> and C<isUPPER_L1>.
+
+=for apidoc Am|bool|isWORDCHAR|char ch
+Returns a boolean indicating whether the specified character is a
+character that is any of: alphabetic, numeric, or an underscore. This is the
+same as what C<\w> matches in a regular expression.
+C<isALNUM()> is a synonym provided for backward compatibility. Note that it
+does not have the standard C language meaning of alphanumeric, since it matches
+an underscore and the standard meaning does not.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isWORDCHAR_A> and C<isWORDCHAR_L1>.
+
+=for apidoc Am|bool|isXDIGIT|char ch
+Returns a boolean indicating whether the specified character is a hexadecimal
+digit, [0-9A-Fa-f]. Variants C<isXDIGIT_A()> and C<isXDIGIT_L1()> are
+identical to C<isXDIGIT()>.
+
+=head1 Character case changing
=for apidoc Am|char|toUPPER|char ch
-Converts the specified character to uppercase. Characters outside the
-US-ASCII (Basic Latin) range are viewed as not having any case.
+Converts the specified character to uppercase in the platform's native
+character set, if possible; otherwise returns the input character itself.
=for apidoc Am|char|toLOWER|char ch
-Converts the specified character to lowercase. Characters outside the
-US-ASCII (Basic Latin) range are viewed as not having any case.
+Converts the specified character to lowercase in the platform's native
+character set, if possible; otherwise returns the input character itself.
=cut
+
+Note that these macros are repeated in Devel::PPPort, so should also be
+patched there. The file as of this writing is cpan/Devel-PPPort/parts/inc/misc
+
*/
-#define isALNUM(c) (isALPHA(c) || isDIGIT(c) || (c) == '_')
-#define isIDFIRST(c) (isALPHA(c) || (c) == '_')
-#define isALPHA(c) (isUPPER(c) || isLOWER(c))
-/* ALPHAU includes Unicode semantics for latin1 characters. It has an extra
- * >= AA test to speed up ASCII-only tests at the expense of the others */
-#define isALPHAU(c) (isALPHA(c) || (NATIVE_TO_UNI((U8) c) >= 0xAA \
- && ((NATIVE_TO_UNI((U8) c) >= 0xC0 \
- && NATIVE_TO_UNI((U8) c) != 0xD7 && NATIVE_TO_UNI((U8) c) != 0xF7) \
- || NATIVE_TO_UNI((U8) c) == 0xAA \
- || NATIVE_TO_UNI((U8) c) == 0xB5 \
- || NATIVE_TO_UNI((U8) c) == 0xBA)))
-#define isALNUMU(c) (isDIGIT(c) || isALPHAU(c) || (c) == '_')
-
-/* continuation character for legal NAME in \N{NAME} */
-#define isCHARNAME_CONT(c) (isALNUMU(c) || (c) == ' ' || (c) == '-' || (c) == '(' || (c) == ')' || (c) == ':' || NATIVE_TO_UNI((U8) c) == 0xA0)
-#define isSPACE(c) \
- ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f')
-#define isPSXSPC(c) (isSPACE(c) || (c) == '\v')
-#define isBLANK(c) ((c) == ' ' || (c) == '\t')
-#define isDIGIT(c) ((c) >= '0' && (c) <= '9')
+/* FITS_IN_8_BITS(c) returns true if c occupies no more than 8 bits. It is
+ * designed to be hopefully bomb-proof, making sure that no bits of
+ * information are lost even on a 64-bit machine, but to get the compiler to
+ * optimize it out if possible. This is because Configure makes sure that the
+ * machine has an 8-bit byte, so if c is stored in a byte, the sizeof()
+ * guarantees that this evaluates to a constant true at compile time. The use
+ * of the mask instead of '< 256' keeps gcc from complaining that it is alway
+ * true, when c's storage class is a byte. Use U64TYPE because U64 is known
+ * only in the perl core, and this macro can be called from outside that */
+#ifdef HAS_QUAD
+# define FITS_IN_8_BITS(c) ((sizeof(c) == 1) || (((U64TYPE)(c) & 0xFF) == (U64TYPE)(c)))
+#else
+# define FITS_IN_8_BITS(c) ((sizeof(c) == 1) || (((U32)(c) & 0xFF) == (U32)(c)))
+#endif
+
+#define isASCII(c) (FITS_IN_8_BITS(c) ? NATIVE_TO_UNI((U8) c) <= 127 : 0)
+#define isASCII_A(c) isASCII(c)
+
+/* ASCII range only */
+#ifdef H_PERL /* If have access to perl.h, lookup in its table */
+/* Bits for PL_charclass[] */
+# define _CC_ALNUMC_A (1<<0)
+# define _CC_ALNUMC_L1 (1<<1)
+# define _CC_ALPHA_A (1<<2)
+# define _CC_ALPHA_L1 (1<<3)
+# define _CC_BLANK_A (1<<4)
+# define _CC_BLANK_L1 (1<<5)
+# define _CC_CHARNAME_CONT (1<<6)
+# define _CC_CNTRL_A (1<<7)
+# define _CC_CNTRL_L1 (1<<8)
+# define _CC_DIGIT_A (1<<9)
+# define _CC_GRAPH_A (1<<10)
+# define _CC_GRAPH_L1 (1<<11)
+# define _CC_IDFIRST_A (1<<12)
+# define _CC_IDFIRST_L1 (1<<13)
+# define _CC_LOWER_A (1<<14)
+# define _CC_LOWER_L1 (1<<15)
+# define _CC_OCTAL_A (1<<16)
+# define _CC_PRINT_A (1<<17)
+# define _CC_PRINT_L1 (1<<18)
+# define _CC_PSXSPC_A (1<<19)
+# define _CC_PSXSPC_L1 (1<<20)
+# define _CC_PUNCT_A (1<<21)
+# define _CC_PUNCT_L1 (1<<22)
+# define _CC_SPACE_A (1<<23)
+# define _CC_SPACE_L1 (1<<24)
+# define _CC_UPPER_A (1<<25)
+# define _CC_UPPER_L1 (1<<26)
+# define _CC_WORDCHAR_A (1<<27)
+# define _CC_WORDCHAR_L1 (1<<28)
+# define _CC_XDIGIT_A (1<<29)
+# define _CC_NONLATIN1_FOLD (1<<30)
+/* Unused
+ * (1<<31)
+ */
+
+# ifdef DOINIT
+EXTCONST U32 PL_charclass[] = {
+# include "l1_char_class_tab.h"
+};
+
+# else /* ! DOINIT */
+EXTCONST U32 PL_charclass[];
+# endif
+
+# define isALNUMC_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_ALNUMC_A))
+# define isALPHA_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_ALPHA_A))
+# define isBLANK_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_BLANK_A))
+# define isCNTRL_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_CNTRL_A))
+# define isDIGIT_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_DIGIT_A))
+# define isGRAPH_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_GRAPH_A))
+# define isIDFIRST_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_IDFIRST_A))
+# define isLOWER_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_LOWER_A))
+# define isOCTAL_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_OCTAL_A))
+# define isPRINT_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PRINT_A))
+# define isPSXSPC_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PSXSPC_A))
+# define isPUNCT_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PUNCT_A))
+# define isSPACE_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_SPACE_A))
+# define isUPPER_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_UPPER_A))
+# define isWORDCHAR_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_WORDCHAR_A))
+# define isXDIGIT_A(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_XDIGIT_A))
+ /* Either participates in a fold with a character above 255, or is a
+ * multi-char fold */
+# define _HAS_NONLATIN1_FOLD_CLOSURE_ONLY_FOR_USE_BY_REGCOMP_DOT_C_AND_REGEXEC_DOT_C(c) ((! cBOOL(FITS_IN_8_BITS(c))) || (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_NONLATIN1_FOLD))
+#else /* No perl.h. */
+# define isOCTAL_A(c) ((c) >= '0' && (c) <= '9')
+# ifdef EBCDIC
+# define isALNUMC_A(c) (isASCII(c) && isALNUMC(c))
+# define isALPHA_A(c) (isASCII(c) && isALPHA(c))
+# define isBLANK_A(c) (isASCII(c) && isBLANK(c))
+# define isCNTRL_A(c) (isASCII(c) && isCNTRL(c))
+# define isDIGIT_A(c) (isASCII(c) && isDIGIT(c))
+# define isGRAPH_A(c) (isASCII(c) && isGRAPH(c))
+# define isIDFIRST_A(c) (isASCII(c) && isIDFIRST(c))
+# define isLOWER_A(c) (isASCII(c) && isLOWER(c))
+# define isPRINT_A(c) (isASCII(c) && isPRINT(c))
+# define isPSXSPC_A(c) (isASCII(c) && isPSXSPC(c))
+# define isPUNCT_A(c) (isASCII(c) && isPUNCT(c))
+# define isSPACE_A(c) (isASCII(c) && isSPACE(c))
+# define isUPPER_A(c) (isASCII(c) && isUPPER(c))
+# define isWORDCHAR_A(c) (isASCII(c) && isWORDCHAR(c))
+# define isXDIGIT_A(c) (isASCII(c) && isXDIGIT(c))
+# else /* ASCII platform, no perl.h */
+# define isALNUMC_A(c) (isALPHA_A(c) || isDIGIT_A(c))
+# define isALPHA_A(c) (isUPPER_A(c) || isLOWER_A(c))
+# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
+# define isCNTRL_A(c) (FITS_IN_8_BITS(c) ? ((U8) (c) < ' ' || (c) == 127) : 0)
+# define isDIGIT_A(c) ((c) >= '0' && (c) <= '9')
+# define isGRAPH_A(c) (isWORDCHAR_A(c) || isPUNCT_A(c))
+# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
+# define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z')
+# define isPRINT_A(c) (((c) >= 32 && (c) < 127))
+# define isPSXSPC_A(c) (isSPACE_A(c) || (c) == '\v')
+# define isPUNCT_A(c) (((c) >= 33 && (c) <= 47) || ((c) >= 58 && (c) <= 64) || ((c) >= 91 && (c) <= 96) || ((c) >= 123 && (c) <= 126))
+# define isSPACE_A(c) ((c) == ' ' || (c) == '\t' || (c) == '\n' || (c) =='\r' || (c) == '\f')
+# define isUPPER_A(c) ((c) >= 'A' && (c) <= 'Z')
+# define isWORDCHAR_A(c) (isALPHA_A(c) || isDIGIT_A(c) || (c) == '_')
+# define isXDIGIT_A(c) (isDIGIT_A(c) || ((c) >= 'a' && (c) <= 'f') || ((c) >= 'A' && (c) <= 'F'))
+# endif
+#endif /* ASCII range definitions */
+
+/* Latin1 definitions */
+#ifdef H_PERL
+# define isALNUMC_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_ALNUMC_L1))
+# define isALPHA_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_ALPHA_L1))
+# define isBLANK_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_BLANK_L1))
+/* continuation character for legal NAME in \N{NAME} */
+# define isCHARNAME_CONT(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_CHARNAME_CONT))
+# define isCNTRL_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_CNTRL_L1))
+# define isGRAPH_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_GRAPH_L1))
+# define isIDFIRST_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_IDFIRST_L1))
+# define isLOWER_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_LOWER_L1))
+# define isPRINT_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PRINT_L1))
+# define isPSXSPC_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PSXSPC_L1))
+# define isPUNCT_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_PUNCT_L1))
+# define isSPACE_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_SPACE_L1))
+# define isUPPER_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_UPPER_L1))
+# define isWORDCHAR_L1(c) cBOOL(FITS_IN_8_BITS(c) && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_WORDCHAR_L1))
+#else /* No access to perl.h. Only a few provided here, just in case needed
+ * for backwards compatibility */
+ /* ALPHAU includes Unicode semantics for latin1 characters. It has an extra
+ * >= AA test to speed up ASCII-only tests at the expense of the others */
+# define isALPHA_L1(c) (isALPHA(c) || (NATIVE_TO_UNI((U8) c) >= 0xAA \
+ && ((NATIVE_TO_UNI((U8) c) >= 0xC0 \
+ && NATIVE_TO_UNI((U8) c) != 0xD7 && NATIVE_TO_UNI((U8) c) != 0xF7) \
+ || NATIVE_TO_UNI((U8) c) == 0xAA \
+ || NATIVE_TO_UNI((U8) c) == 0xB5 \
+ || NATIVE_TO_UNI((U8) c) == 0xBA)))
+# define isCHARNAME_CONT(c) (isALNUM_L1(c) || (c) == ' ' || (c) == '-' || (c) == '(' || (c) == ')' || (c) == ':' || NATIVE_TO_UNI((U8) c) == 0xA0)
+#endif
+
+/* Macros for backwards compatibility and for completeness when the ASCII and
+ * Latin1 values are identical */
+#define isALNUM(c) isWORDCHAR(c)
+#define isALNUMU(c) isWORDCHAR_L1(c)
+#define isALPHAU(c) isALPHA_L1(c)
+#define isDIGIT_L1(c) isDIGIT_A(c)
+#define isOCTAL(c) isOCTAL_A(c)
+#define isOCTAL_L1(c) isOCTAL_A(c)
+#define isXDIGIT_L1(c) isXDIGIT_A(c)
+
+/* Macros that differ between EBCDIC and ASCII. Where C89 defines a function,
+ * that is used in the EBCDIC form, because in EBCDIC we do not do locales:
+ * therefore can use native functions. For those where C89 doesn't define a
+ * function, use our function, assuming that the EBCDIC code page is isomorphic
+ * with Latin1, which the three currently recognized by Perl are. Some libc's
+ * have an isblank(), but it's not guaranteed. */
#ifdef EBCDIC
- /* In EBCDIC we do not do locales: therefore() isupper() is fine. */
-# define isUPPER(c) isupper(c)
-# define isLOWER(c) islower(c)
# define isALNUMC(c) isalnum(c)
-# define isASCII(c) isascii(c)
+# define isALPHA(c) isalpha(c)
+# define isBLANK(c) ((c) == ' ' || (c) == '\t' || NATIVE_TO_UNI(c) == 0xA0)
# define isCNTRL(c) iscntrl(c)
+# define isDIGIT(c) isdigit(c)
# define isGRAPH(c) isgraph(c)
+# define isIDFIRST(c) (isALPHA(c) || (c) == '_')
+# define isLOWER(c) islower(c)
# define isPRINT(c) isprint(c)
+# define isPSXSPC(c) isspace(c)
# define isPUNCT(c) ispunct(c)
+# define isSPACE(c) (isPSXSPC(c) && (c) != '\v')
+# define isUPPER(c) isupper(c)
# define isXDIGIT(c) isxdigit(c)
-# define toUPPER(c) toupper(c)
-# define toUPPER_LATIN1_MOD(c) UNI_TO_NATIVE(PL_mod_latin1_uc[(U8) NATIVE_TO_UNI(c)])
+# define isWORDCHAR(c) (isalnum(c) || (c) == '_')
# define toLOWER(c) tolower(c)
-# define toLOWER_LATIN1(c) UNI_TO_NATIVE(PL_latin1_lc[(U8) NATIVE_TO_UNI(c)])
-#else
-# define isUPPER(c) ((c) >= 'A' && (c) <= 'Z')
-# define isLOWER(c) ((c) >= 'a' && (c) <= 'z')
-# define isALNUMC(c) (isALPHA(c) || isDIGIT(c))
-# define isASCII(c) ((c) <= 127)
-# define isCNTRL(c) ((c) < ' ' || (c) == 127)
-# define isGRAPH(c) (isALNUM(c) || isPUNCT(c))
-# define isPRINT(c) (((c) >= 32 && (c) < 127))
-# define isPUNCT(c) (((c) >= 33 && (c) <= 47) || ((c) >= 58 && (c) <= 64) || ((c) >= 91 && (c) <= 96) || ((c) >= 123 && (c) <= 126))
-# define isXDIGIT(c) (isDIGIT(c) || ((c) >= 'a' && (c) <= 'f') || ((c) >= 'A' && (c) <= 'F'))
-
-/* Use table lookup for speed */
-# define toLOWER_LATIN1(c) (PL_latin1_lc[(U8) c])
-
-/* Modified uc. Is correct uc except for three non-ascii chars which are
- * all mapped to one of them, and these need special handling */
-# define toUPPER_LATIN1_MOD(c) (PL_mod_latin1_uc[(U8) c])
-
-/* ASCII casing. */
-# define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c))
+# define toUPPER(c) toupper(c)
+#else /* Not EBCDIC: ASCII-only matching */
+# define isALNUMC(c) isALNUMC_A(c)
+# define isALPHA(c) isALPHA_A(c)
+# define isBLANK(c) isBLANK_A(c)
+# define isCNTRL(c) isCNTRL_A(c)
+# define isDIGIT(c) isDIGIT_A(c)
+# define isGRAPH(c) isGRAPH_A(c)
+# define isIDFIRST(c) isIDFIRST_A(c)
+# define isLOWER(c) isLOWER_A(c)
+# define isPRINT(c) isPRINT_A(c)
+# define isPSXSPC(c) isPSXSPC_A(c)
+# define isPUNCT(c) isPUNCT_A(c)
+# define isSPACE(c) isSPACE_A(c)
+# define isUPPER(c) isUPPER_A(c)
+# define isWORDCHAR(c) isWORDCHAR_A(c)
+# define isXDIGIT(c) isXDIGIT_A(c)
+
+ /* ASCII casing. These could also be written as
+ #define toLOWER(c) (isASCII(c) ? toLOWER_LATIN1(c) : (c))
+ #define toUPPER(c) (isASCII(c) ? toUPPER_LATIN1_MOD(c) : (c))
+ which uses table lookup and mask instead of subtraction. (This would
+ work because the _MOD does not apply in the ASCII range) */
# define toLOWER(c) (isUPPER(c) ? (c) + ('a' - 'A') : (c))
+# define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c))
#endif
+
+/* Use table lookup for speed; return error character for input
+ * out-of-range */
+#define toLOWER_LATIN1(c) (FITS_IN_8_BITS(c) \
+ ? UNI_TO_NATIVE(PL_latin1_lc[ \
+ NATIVE_TO_UNI( (U8) (c)) ]) \
+ : UNICODE_REPLACEMENT)
+/* Modified uc. Is correct uc except for three non-ascii chars which are
+ * all mapped to one of them, and these need special handling; error
+ * character for input out-of-range */
+#define toUPPER_LATIN1_MOD(c) (FITS_IN_8_BITS(c) \
+ ? UNI_TO_NATIVE(PL_mod_latin1_uc[ \
+ NATIVE_TO_UNI( (U8) (c)) ]) \
+ : UNICODE_REPLACEMENT)
+
#ifdef USE_NEXT_CTYPE
# define isALNUM_LC(c) \
@@ -615,10 +883,13 @@ US-ASCII (Basic Latin) range are viewed as not having any case.
#define isBLANK_LC_uni(c) isBLANK(c) /* could be wrong */
#define isALNUM_utf8(p) is_utf8_alnum(p)
-/* The ID_Start of Unicode is quite limiting: it assumes a L-class
- * character (meaning that you cannot have, say, a CJK character).
- * Instead, let's allow ID_Continue but not digits. */
-#define isIDFIRST_utf8(p) (is_utf8_idcont(p) && !is_utf8_digit(p))
+/* To prevent S_scan_word in toke.c from hanging, we have to make sure that
+ * IDFIRST is an alnum. See
+ * http://rt.perl.org/rt3/Ticket/Display.html?id=74022
+ * for more detail than you ever wanted to know about. This used to be not the
+ * XID version, but we decided to go with the more modern Unicode definition */
+#define isIDFIRST_utf8(p) (is_utf8_xidfirst(p) && is_utf8_alnum(p))
+#define isIDCONT_utf8(p) is_utf8_xidcont(p)
#define isALPHA_utf8(p) is_utf8_alpha(p)
#define isSPACE_utf8(p) is_utf8_space(p)
#define isDIGIT_utf8(p) is_utf8_digit(p)
@@ -653,16 +924,9 @@ US-ASCII (Basic Latin) range are viewed as not having any case.
#define isPSXSPC_LC_utf8(c) (isSPACE_LC_utf8(c) ||(c) == '\f')
#define isBLANK_LC_utf8(c) isBLANK(c) /* could be wrong */
-#ifdef EBCDIC
-# ifdef PERL_IMPLICIT_CONTEXT
-# define toCTRL(c) Perl_ebcdic_control(aTHX_ c)
-# else
-# define toCTRL Perl_ebcdic_control
-# endif
-#else
- /* This conversion works both ways, strangely enough. */
-# define toCTRL(c) (toUPPER(c) ^ 64)
-#endif
+/* This conversion works both ways, strangely enough. On EBCDIC platforms,
+ * CTRL-@ is 0, CTRL-A is 1, etc, just like on ASCII */
+# define toCTRL(c) (toUPPER(NATIVE_TO_UNI(c)) ^ 64)
/* Line numbers are unsigned, 32 bits. */
typedef U32 line_t;
@@ -912,6 +1176,7 @@ void Perl_mem_log_del_sv(const SV *sv, const char *filename, const int linenumbe
#endif
#define C_ARRAY_LENGTH(a) (sizeof(a)/sizeof((a)[0]))
+#define C_ARRAY_END(a) (a) + (sizeof(a)/sizeof((a)[0]))
#ifdef NEED_VA_COPY
# ifdef va_copy