/* Unused by core; should be deprecated */
#define Ctl(ch) ((ch) & 037)
+#if defined(PERL_CORE) || defined(PERL_EXT)
+# ifndef MIN
+# define MIN(a,b) ((a) < (b) ? (a) : (b))
+# endif
+# ifndef MAX
+# define MAX(a,b) ((a) > (b) ? (a) : (b))
+# endif
+#endif
+
/* This is a helper macro to avoid preprocessor issues, replaced by nothing
* unless under DEBUGGING, where it expands to an assert of its argument,
* followed by a comma (hence the comma operator). If we just used a straight
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) \
- : HV_FETCH_JUST_SV, NULL, 0))
-#define hv_stores(hv,key,val) \
- ((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)
=cut
*/
+
#define strNE(s1,s2) (strcmp(s1,s2))
#define strEQ(s1,s2) (!strcmp(s1,s2))
#define strLT(s1,s2) (strcmp(s1,s2) < 0)
#define strLE(s1,s2) (strcmp(s1,s2) <= 0)
#define strGT(s1,s2) (strcmp(s1,s2) > 0)
#define strGE(s1,s2) (strcmp(s1,s2) >= 0)
+
#define strnNE(s1,s2,l) (strncmp(s1,s2,l))
#define strnEQ(s1,s2,l) (!strncmp(s1,s2,l))
+#define strNEs(s1,s2) (strncmp(s1,"" s2 "", sizeof(s2)-1))
+#define strEQs(s1,s2) (!strncmp(s1,"" s2 "", sizeof(s2)-1))
+
#ifdef HAS_MEMCMP
# define memNE(s1,s2,l) (memcmp(s1,s2,l))
# define memEQ(s1,s2,l) (!memcmp(s1,s2,l))
# define memEQ(s1,s2,l) (!bcmp(s1,s2,l))
#endif
+/* memEQ and memNE where second comparand is a string constant */
#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)
+/* memEQ and memNE where second comparand is a string constant
+ * and we can assume the length of s1 is at least that of the string */
+#define _memEQs(s1, s2) \
+ (memEQ((s1), ("" s2 ""), (sizeof(s2)-1)))
+#define _memNEs(s1, s2) (memNE((s1),("" s2 ""),(sizeof(s2)-1)))
+
+#define memLT(s1,s2,l) (memcmp(s1,s2,l) < 0)
+#define memLE(s1,s2,l) (memcmp(s1,s2,l) <= 0)
+#define memGT(s1,s2,l) (memcmp(s1,s2,l) > 0)
+#define memGE(s1,s2,l) (memcmp(s1,s2,l) >= 0)
+
/*
* Character classes.
*
ASCII character in the named class based on platform, Unicode, and Perl rules.
If the input is a number that doesn't fit in an octet, FALSE is returned.
-Variant C<isFOO_A> (e.g., C<isALPHA_A()>) is identical to the base function
-with no suffix C<"_A">.
+Variant C<isI<FOO>_A> (e.g., C<isALPHA_A()>) is identical to the base function
+with no suffix C<"_A">. This variant is used to emphasize by its name that
+only ASCII-range characters can return TRUE.
-Variant C<isFOO_L1> imposes the Latin-1 (or EBCDIC equivlalent) character set
+Variant C<isI<FOO>_L1> imposes the Latin-1 (or EBCDIC equivlalent) 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<isWORDCHAR_L1()> will return
true when called with the code point 0xDF, which is a word character in both
ASCII and EBCDIC (though it represents different characters in each).
-Variant C<isFOO_uvchr> is like the C<isFOO_L1> variant, but accepts any UV code
+Variant C<isI<FOO>_uvchr> is like the C<isI<FOO>_L1> variant, but accepts any UV code
point as input. If the code point is larger than 255, Unicode rules are used
to determine if it is in the character class. For example,
C<isWORDCHAR_uvchr(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
WITH MACRON in Unicode, and is a word character.
-Variant C<isFOO_utf8> is like C<isFOO_uvchr>, but the input is a pointer to a
-(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
-possibly containing embedded C<NUL> characters). The classification of just
-the first (possibly multi-byte) character in the string is tested.
-
-Variant C<isFOO_LC> is like the C<isFOO_A> and C<isFOO_L1> variants, but the
+Variant C<isI<FOO>_utf8_safe> is like C<isI<FOO>_uvchr>, but is used for UTF-8
+encoded strings. Each call classifies one character, even if the string
+contains many. This variant takes two parameters. The first, C<p>, is a
+pointer to the first byte of the character to be classified. (Recall that it
+may take more than one byte to represent a character in UTF-8 strings.) The
+second parameter, C<e>, points to anywhere in the string beyond the first
+character, up to one byte past the end of the entire string. The suffix
+C<_safe> in the function's name indicates that it will not attempt to read
+beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
+is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
+character is malformed in some way, the program may croak, or the function may
+return FALSE, at the discretion of the implementation, and subject to change in
+future releases.
+
+Variant C<isI<FOO>_utf8> is like C<isI<FOO>_utf8_safe>, but takes just a single
+parameter, C<p>, which has the same meaning as the corresponding parameter does
+in C<isI<FOO>_utf8_safe>. The function therefore can't check if it is reading
+beyond the end of the string. Starting in Perl v5.30, it will take a second
+parameter, becoming a synonym for C<isI<FOO>_utf8_safe>. At that time every
+program that uses it will have to be changed to successfully compile. In the
+meantime, the first runtime call to C<isI<FOO>_utf8> from each call point in the
+program will raise a deprecation warning, enabled by default. You can convert
+your program now to use C<isI<FOO>_utf8_safe>, and avoid the warnings, and get an
+extra measure of protection, or you can wait until v5.30, when you'll be forced
+to add the C<e> parameter.
+
+Variant C<isI<FOO>_LC> is like the C<isI<FOO>_A> and C<isI<FOO>_L1> variants, but the
result is based on the current locale, which is what C<LC> in the name stands
for. If Perl can determine that the current locale is a UTF-8 locale, it uses
the published Unicode rules; otherwise, it uses the C library function that
library function is known to be defective, Perl changes its result to follow
the POSIX standard's rules.
-Variant C<isFOO_LC_uvchr> is like C<isFOO_LC>, but is defined on any UV. It
-returns the same as C<isFOO_LC> for input code points less than 256, and
+Variant C<isI<FOO>_LC_uvchr> is like C<isI<FOO>_LC>, but is defined on any UV. It
+returns the same as C<isI<FOO>_LC> for input code points less than 256, and
returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
-Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer
-to a (known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
-possibly containing embedded C<NUL> characters). The classification of just
-the first (possibly multi-byte) character in the string is tested.
+Variant C<isI<FOO>_LC_utf8_safe> is like C<isI<FOO>_LC_uvchr>, but is used for UTF-8
+encoded strings. Each call classifies one character, even if the string
+contains many. This variant takes two parameters. The first, C<p>, is a
+pointer to the first byte of the character to be classified. (Recall that it
+may take more than one byte to represent a character in UTF-8 strings.) The
+second parameter, C<e>, points to anywhere in the string beyond the first
+character, up to one byte past the end of the entire string. The suffix
+C<_safe> in the function's name indicates that it will not attempt to read
+beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
+is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
+character is malformed in some way, the program may croak, or the function may
+return FALSE, at the discretion of the implementation, and subject to change in
+future releases.
+
+Variant C<isI<FOO>_LC_utf8> is like C<isI<FOO>_LC_utf8_safe>, but takes just a single
+parameter, C<p>, which has the same meaning as the corresponding parameter does
+in C<isI<FOO>_LC_utf8_safe>. The function therefore can't check if it is reading
+beyond the end of the string. Starting in Perl v5.30, it will take a second
+parameter, becoming a synonym for C<isI<FOO>_LC_utf8_safe>. At that time every
+program that uses it will have to be changed to successfully compile. In the
+meantime, the first runtime call to C<isI<FOO>_LC_utf8> from each call point in
+the program will raise a deprecation warning, enabled by default. You can
+convert your program now to use C<isI<FOO>_LC_utf8_safe>, and avoid the warnings,
+and get an extra measure of protection, or you can wait until v5.30, when
+you'll be forced to add the C<e> parameter.
=for apidoc Am|bool|isALPHA|char ch
Returns a boolean indicating whether the specified character is an
alphabetic character, analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8>, C<isALPHA_LC>,
-C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8>.
+C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8_safe>,
+C<isALPHA_LC>, C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8_safe>.
=for apidoc Am|bool|isALPHANUMERIC|char ch
Returns a boolean indicating whether the specified character is a either an
See the L<top of this section|/Character classification> for an explanation of
variants
C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uvchr>,
-C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>, and
-C<isALPHANUMERIC_LC_utf8>.
+C<isALPHANUMERIC_utf8_safe>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>,
+and C<isALPHANUMERIC_LC_utf8_safe>.
=for apidoc Am|bool|isASCII|char ch
Returns a boolean indicating whether the specified character is one of the 128
C<isASCII_L1()> are identical to C<isASCII()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isASCII_uvchr>, C<isASCII_utf8>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
-C<isASCII_LC_utf8>. Note, however, that some platforms do not have the C
+C<isASCII_uvchr>, C<isASCII_utf8_safe>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
+C<isASCII_LC_utf8_safe>. Note, however, that some platforms do not have the C
library routine C<isascii()>. In these cases, the variants whose names contain
C<LC> are the same as the corresponding ones without.
Also note, that because all ASCII characters are UTF-8 invariant (meaning they
have the exact same representation (always a single byte) whether encoded in
UTF-8 or not), C<isASCII> will give the correct results when called with any
-byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8> will
-work properly on any string encoded or not in UTF-8.
+byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8_safe>
+will work properly on any string encoded or not in UTF-8.
=for apidoc Am|bool|isBLANK|char ch
Returns a boolean indicating whether the specified character is a
character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8>, C<isBLANK_LC>,
-C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8>. Note, however, that some
-platforms do not have the C library routine C<isblank()>. In these cases, the
-variants whose names contain C<LC> are the same as the corresponding ones
-without.
+C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8_safe>,
+C<isBLANK_LC>, C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8_safe>. Note,
+however, that some platforms do not have the C library routine
+C<isblank()>. In these cases, the variants whose names contain C<LC> are
+the same as the corresponding ones without.
=for apidoc Am|bool|isCNTRL|char ch
Returns a boolean indicating whether the specified character is a
control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8>, C<isCNTRL_LC>,
-C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8>
-On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
+C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8_safe>,
+C<isCNTRL_LC>, C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8_safe> On EBCDIC
+platforms, you almost always want to use the C<isCNTRL_L1> variant.
=for apidoc Am|bool|isDIGIT|char ch
Returns a boolean indicating whether the specified character is a
Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isDIGIT_uvchr>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
-C<isDIGIT_LC_utf8>.
+C<isDIGIT_uvchr>, C<isDIGIT_utf8_safe>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
+C<isDIGIT_LC_utf8_safe>.
=for apidoc Am|bool|isGRAPH|char ch
Returns a boolean indicating whether the specified character is a
graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
-C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8>.
+variants C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8_safe>,
+C<isGRAPH_LC>, C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8_safe>.
=for apidoc Am|bool|isLOWER|char ch
Returns a boolean indicating whether the specified character is a
lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8>, C<isLOWER_LC>,
-C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
+C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8_safe>,
+C<isLOWER_LC>, C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8_safe>.
=for apidoc Am|bool|isOCTAL|char ch
Returns a boolean indicating whether the specified character is an
straightforward as one might desire. See L<perlrecharclass/POSIX Character
Classes> for details.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
-C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
+variants C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8_safe>,
+C<isPUNCT_LC>, C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8_safe>.
=for apidoc Am|bool|isSPACE|char ch
Returns a boolean indicating whether the specified character is a
(See L</isPSXSPC> for a macro that matches a vertical tab in all releases.)
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8>, C<isSPACE_LC>,
-C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
+C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8_safe>,
+C<isSPACE_LC>, C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8_safe>.
=for apidoc Am|bool|isPSXSPC|char ch
(short for Posix Space)
Otherwise they are identical. Thus this macro is analogous to what
C<m/[[:space:]]/> matches in a regular expression.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8>,
-C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
+variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8_safe>,
+C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8_safe>.
=for apidoc Am|bool|isUPPER|char ch
Returns a boolean indicating whether the specified character is an
uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8>, C<isUPPER_LC>,
-C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8>.
+variants C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8_safe>,
+C<isUPPER_LC>, C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8_safe>.
=for apidoc Am|bool|isPRINT|char ch
Returns a boolean indicating whether the specified character is a
printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8>, C<isPRINT_LC>,
-C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
+C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8_safe>,
+C<isPRINT_LC>, C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8_safe>.
=for apidoc Am|bool|isWORDCHAR|char ch
Returns a boolean indicating whether the specified character is a character
word character includes more than the standard C language meaning of
alphanumeric.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and C<isWORDCHAR_utf8>.
-C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and C<isWORDCHAR_LC_utf8> are also as
-described there, but additionally include the platform's native underscore.
+variants C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and
+C<isWORDCHAR_utf8_safe>. C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and
+C<isWORDCHAR_LC_utf8_safe> are also as described there, but additionally
+include the platform's native underscore.
=for apidoc Am|bool|isXDIGIT|char ch
Returns a boolean indicating whether the specified character is a hexadecimal
and C<isXDIGIT_L1()> are identical to C<isXDIGIT()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isXDIGIT_uvchr>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
-C<isXDIGIT_LC_utf8>.
+C<isXDIGIT_uvchr>, C<isXDIGIT_utf8_safe>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>,
+and C<isXDIGIT_LC_utf8_safe>.
=for apidoc Am|bool|isIDFIRST|char ch
Returns a boolean indicating whether the specified character can be the first
returns true only if the input character also matches L</isWORDCHAR>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8>,
-C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8>.
+C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8_safe>,
+C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8_safe>.
=for apidoc Am|bool|isIDCONT|char ch
Returns a boolean indicating whether the specified character can be the
L</isWORDCHAR>. See the L<top of this section|/Character classification> for
an
explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uvchr>,
-C<isIDCONT_utf8>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
-C<isIDCONT_LC_utf8>.
+C<isIDCONT_utf8_safe>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
+C<isIDCONT_LC_utf8_safe>.
=head1 Miscellaneous Functions
Behaviour is only well defined when isXDIGIT(*str) is true.
=head1 Character case changing
+Perl uses "full" Unicode case mappings. This means that converting a single
+character to another case may result in a sequence of more than one character.
+For example, the uppercase of C<E<223>> (LATIN SMALL LETTER SHARP S) is the two
+character sequence C<SS>. This presents some complications The lowercase of
+all characters in the range 0..255 is a single character, and thus
+C<L</toLOWER_L1>> is furnished. But, C<toUPPER_L1> can't exist, as it couldn't
+return a valid result for all legal inputs. Instead C<L</toUPPER_uvchr>> has
+an API that does allow every possible legal result to be returned.) Likewise
+no other function that is crippled by not being able to give the correct
+results for the full range of possible inputs has been implemented here.
=for apidoc Am|U8|toUPPER|U8 ch
Converts the specified character to uppercase. If the input is anything but an
bytes since the uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more.)
=for apidoc Am|UV|toUPPER_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its uppercase version, and
bytes since the uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
The input character at C<p> is assumed to be well-formed.
bytes since the foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
=for apidoc Am|UV|toFOLD_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its foldcase version, and
bytes since the foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
The input character at C<p> is assumed to be well-formed.
bytes since the lowercase version may be longer than the original character.
The first code point of the lowercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
=for apidoc Am|UV|toLOWER_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its lowercase version, and
bytes since the lowercase version may be longer than the original character.
The first code point of the lowercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
The input character at C<p> is assumed to be well-formed.
bytes since the titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
=for apidoc Am|UV|toTITLE_utf8|U8* p|U8* s|STRLEN* lenp
Converts the UTF-8 encoded character at C<p> to its titlecase version, and
bytes since the titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
The input character at C<p> is assumed to be well-formed.
=cut
XXX Still undocumented isVERTWS_uvchr and _utf8; it's unclear what their names
-really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change.
+really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change,
+and aren't general purpose as they don't work on U+DF, and assert against that.
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
/* The '| 0' part ensures a compiler error if c is not integer (like e.g., a
* pointer) */
#define FITS_IN_8_BITS(c) ( (sizeof(c) == 1) \
- || !(((WIDEST_UTYPE)(c | 0)) & ~0xFF))
+ || !(((WIDEST_UTYPE)((c) | 0)) & ~0xFF))
#else
#define FITS_IN_8_BITS(c) (1)
#endif
# define isASCII(c) ((WIDEST_UTYPE)((c) | 0) < 128)
#endif
-/* The lower 3 bits in both the ASCII and EBCDIC representations of '0' are 0,
- * and the 8 possible permutations of those bits exactly comprise the 8 octal
- * digits */
-#define isOCTAL_A(c) cBOOL(FITS_IN_8_BITS(c) && (0xF8 & (c)) == '0')
+/* Take the eight possible bit patterns of the lower 3 bits and you get the
+ * lower 3 bits of the 8 octal digits, in both ASCII and EBCDIC, so those bits
+ * can be ignored. If the rest match '0', we have an octal */
+#define isOCTAL_A(c) (((WIDEST_UTYPE)((c) | 0) & ~7) == '0')
#ifdef H_PERL /* If have access to perl.h, lookup in its table */
# define _CC_PRINT 6 /* [:print:] */
# define _CC_ALPHANUMERIC 7 /* [:alnum:] */
# define _CC_GRAPH 8 /* [:graph:] */
-# define _CC_CASED 9 /* [:lower:] and [:upper:] under /i */
+# define _CC_CASED 9 /* [:lower:] or [:upper:] under /i */
#define _FIRST_NON_SWASH_CC 10
/* The character classes above are implemented with swashes. The second group
* above ASCII in the latter case) */
# define _CC_SPACE 10 /* \s, [:space:] */
+# define _CC_PSXSPC _CC_SPACE /* XXX Temporary, can be removed
+ when the deprecated isFOO_utf8()
+ functions are removed */
# define _CC_BLANK 11 /* [:blank:] */
# define _CC_XDIGIT 12 /* [:xdigit:] */
# define _CC_CNTRL 13 /* [:cntrl:] */
# define _CC_IS_IN_SOME_FOLD 22
# define _CC_MNEMONIC_CNTRL 23
+# define _CC_IDCONT 24 /* XXX Temporary, can be removed when the deprecated
+ isFOO_utf8() functions are removed */
+
/* This next group is only used on EBCDIC platforms, so theoretically could be
* shared with something entirely different that's only on ASCII platforms */
# define _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE 28
/* If we don't have perl.h, we are compiling a utility program. Below we
* hard-code various macro definitions that wouldn't otherwise be available
- * to it. Most are coded based on first principals. These are written to
+ * to it. Most are coded based on first principles. These are written to
* avoid EBCDIC vs. ASCII #ifdef's as much as possible. */
# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
* don't, but experiments show that gcc optimizes them out anyway. */
/* Note that all ignore 'use bytes' */
-#define _generic_uvchr(classnum, above_latin1, c) ((c) < 256 \
- ? _generic_isCC(c, classnum) \
+#define _generic_uvchr(classnum, above_latin1, c) ((c) < 256 \
+ ? _generic_isCC(c, classnum) \
: above_latin1(c))
-#define _generic_swash_uvchr(classnum, c) ((c) < 256 \
- ? _generic_isCC(c, classnum) \
+#define _generic_swash_uvchr(classnum, c) ((c) < 256 \
+ ? _generic_isCC(c, classnum) \
: _is_uni_FOO(classnum, c))
#define isALPHA_uvchr(c) _generic_swash_uvchr(_CC_ALPHA, c)
#define isALPHANUMERIC_uvchr(c) _generic_swash_uvchr(_CC_ALPHANUMERIC, c)
#define isCNTRL_uvchr(c) isCNTRL_L1(c) /* All controls are in Latin1 */
#define isDIGIT_uvchr(c) _generic_swash_uvchr(_CC_DIGIT, c)
#define isGRAPH_uvchr(c) _generic_swash_uvchr(_CC_GRAPH, c)
-#define isIDCONT_uvchr(c) _generic_uvchr(_CC_WORDCHAR, _is_uni_perl_idcont, c)
-#define isIDFIRST_uvchr(c) _generic_uvchr(_CC_IDFIRST, _is_uni_perl_idstart, c)
+#define isIDCONT_uvchr(c) \
+ _generic_uvchr(_CC_WORDCHAR, _is_uni_perl_idcont, c)
+#define isIDFIRST_uvchr(c) \
+ _generic_uvchr(_CC_IDFIRST, _is_uni_perl_idstart, c)
#define isLOWER_uvchr(c) _generic_swash_uvchr(_CC_LOWER, c)
#define isPRINT_uvchr(c) _generic_swash_uvchr(_CC_PRINT, c)
* 'utf8' parameter. This relies on the fact that ASCII characters have the
* same representation whether utf8 or not. Note that it assumes that the utf8
* has been validated, and ignores 'use bytes' */
-#define _generic_utf8(classnum, p, utf8) (UTF8_IS_INVARIANT(*(p)) \
- ? _generic_isCC(*(p), classnum) \
- : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
- ? _generic_isCC( \
- EIGHT_BIT_UTF8_TO_NATIVE(*(p), \
- *((p)+1 )), \
- classnum) \
- : utf8)
+#define _base_generic_utf8(enum_name, name, p, use_locale ) \
+ _is_utf8_FOO(CAT2(_CC_, enum_name), \
+ (const U8 *) p, \
+ "is" STRINGIFY(name) "_utf8", \
+ "is" STRINGIFY(name) "_utf8_safe", \
+ 1, use_locale, __FILE__,__LINE__)
+
+#define _generic_utf8(name, p) _base_generic_utf8(name, name, p, 0)
+
+/* The "_safe" macros make sure that we don't attempt to read beyond 'e', but
+ * they don't otherwise go out of their way to look for malformed UTF-8. If
+ * they can return accurate results without knowing if the input is otherwise
+ * malformed, they do so. For example isASCII is accurate in spite of any
+ * non-length malformations because it looks only at a single byte. Likewise
+ * isDIGIT looks just at the first byte for code points 0-255, as all UTF-8
+ * variant ones return FALSE. But, if the input has to be well-formed in order
+ * for the results to be accurate, the macros will test and if malformed will
+ * call a routine to die
+ *
+ * Except for toke.c, the macros do assume that e > p, asserting that on
+ * DEBUGGING builds. Much code that calls these depends on this being true,
+ * for other reasons. toke.c is treated specially as using the regular
+ * assertion breaks it in many ways. All strings that these operate on there
+ * are supposed to have an extra NUL character at the end, so that *e = \0. A
+ * bunch of code in toke.c assumes that this is true, so the assertion allows
+ * for that */
+#ifdef PERL_IN_TOKE_C
+# define _utf8_safe_assert(p,e) ((e) > (p) || ((e) == (p) && *(p) == '\0'))
+#else
+# define _utf8_safe_assert(p,e) ((e) > (p))
+#endif
+
+#define _generic_utf8_safe(classnum, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? _generic_isCC(*(p), classnum) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p)) \
+ ? ((LIKELY((e) - (p) > 1 && UTF8_IS_CONTINUATION(*((p)+1)))) \
+ ? _generic_isCC(EIGHT_BIT_UTF8_TO_NATIVE(*(p), *((p)+1 )), \
+ classnum) \
+ : (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0)) \
+ : above_latin1))
/* Like the above, but calls 'above_latin1(p)' to get the utf8 value.
* 'above_latin1' can be a macro */
-#define _generic_func_utf8(classnum, above_latin1, p) \
- _generic_utf8(classnum, p, above_latin1(p))
+#define _generic_func_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_utf8_safe(classnum, p, e, above_latin1(p, e))
+#define _generic_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_utf8_safe(classnum, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : above_latin1(p)))
/* Like the above, but passes classnum to _isFOO_utf8(), instead of having an
* 'above_latin1' parameter */
-#define _generic_swash_utf8(classnum, p) \
- _generic_utf8(classnum, p, _is_utf8_FOO(classnum, p))
+#define _generic_swash_utf8_safe(classnum, p, e) \
+_generic_utf8_safe(classnum, p, e, _is_utf8_FOO_with_len(classnum, p, e))
/* Like the above, but should be used only when it is known that there are no
* characters in the upper-Latin1 range (128-255 on ASCII platforms) which the
* class is TRUE for. Hence it can skip the tests for this range.
* 'above_latin1' should include its arguments */
-#define _generic_utf8_no_upper_latin1(classnum, p, above_latin1) \
- (UTF8_IS_INVARIANT(*(p)) \
- ? _generic_isCC(*(p), classnum) \
- : (UTF8_IS_ABOVE_LATIN1(*(p))) \
- ? above_latin1 \
- : 0)
+#define _generic_utf8_safe_no_upper_latin1(classnum, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? _generic_isCC(*(p), classnum) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
+ ? 0 /* Note that doesn't check validity for latin1 */ \
+ : above_latin1)
/* NOTE that some of these macros have very similar ones in regcharclass.h.
* For example, there is (at the time of this writing) an 'is_SPACE_utf8()'
* points; the regcharclass.h ones are implemented as a series of
* "if-else-if-else ..." */
-#define isALPHA_utf8(p) _generic_swash_utf8(_CC_ALPHA, p)
-#define isALPHANUMERIC_utf8(p) _generic_swash_utf8(_CC_ALPHANUMERIC, p)
-#define isASCII_utf8(p) isASCII(*p) /* Because ASCII is invariant under
- utf8, the non-utf8 macro works
- */
-#define isBLANK_utf8(p) _generic_func_utf8(_CC_BLANK, is_HORIZWS_high, p)
+#define isALPHA_utf8(p) _generic_utf8(ALPHA, p)
+#define isALPHANUMERIC_utf8(p) _generic_utf8(ALPHANUMERIC, p)
+#define isASCII_utf8(p) _generic_utf8(ASCII, p)
+#define isBLANK_utf8(p) _generic_utf8(BLANK, p)
+#define isCNTRL_utf8(p) _generic_utf8(CNTRL, p)
+#define isDIGIT_utf8(p) _generic_utf8(DIGIT, p)
+#define isGRAPH_utf8(p) _generic_utf8(GRAPH, p)
+#define isIDCONT_utf8(p) _generic_utf8(IDCONT, p)
+#define isIDFIRST_utf8(p) _generic_utf8(IDFIRST, p)
+#define isLOWER_utf8(p) _generic_utf8(LOWER, p)
+#define isPRINT_utf8(p) _generic_utf8(PRINT, p)
+#define isPSXSPC_utf8(p) _generic_utf8(PSXSPC, p)
+#define isPUNCT_utf8(p) _generic_utf8(PUNCT, p)
+#define isSPACE_utf8(p) _generic_utf8(SPACE, p)
+#define isUPPER_utf8(p) _generic_utf8(UPPER, p)
+#define isVERTWS_utf8(p) _generic_utf8(VERTSPACE, p)
+#define isWORDCHAR_utf8(p) _generic_utf8(WORDCHAR, p)
+#define isXDIGIT_utf8(p) _generic_utf8(XDIGIT, p)
+
+#define isALPHA_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_ALPHA, p, e)
+#define isALPHANUMERIC_utf8_safe(p, e) \
+ _generic_swash_utf8_safe(_CC_ALPHANUMERIC, p, e)
+#define isASCII_utf8_safe(p, e) \
+ /* Because ASCII is invariant under utf8, the non-utf8 macro \
+ * works */ \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isASCII(*(p)))
+#define isBLANK_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_BLANK, is_HORIZWS_high, p, e)
#ifdef EBCDIC
/* Because all controls are UTF-8 invariants in EBCDIC, we can use this
* more efficient macro instead of the more general one */
-# define isCNTRL_utf8(p) isCNTRL_L1(*(p))
+# define isCNTRL_utf8_safe(p, e) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isCNTRL_L1(*(p))
#else
-# define isCNTRL_utf8(p) _generic_utf8(_CC_CNTRL, p, 0)
+# define isCNTRL_utf8_safe(p, e) _generic_utf8_safe(_CC_CNTRL, p, e, 0)
#endif
-#define isDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_DIGIT, p, \
- _is_utf8_FOO(_CC_DIGIT, p))
-#define isGRAPH_utf8(p) _generic_swash_utf8(_CC_GRAPH, p)
-#define isIDCONT_utf8(p) _generic_func_utf8(_CC_WORDCHAR, \
- _is_utf8_perl_idcont, p)
+#define isDIGIT_utf8_safe(p, e) \
+ _generic_utf8_safe_no_upper_latin1(_CC_DIGIT, p, e, \
+ _is_utf8_FOO_with_len(_CC_DIGIT, p, e))
+#define isGRAPH_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_GRAPH, p, e)
+#define isIDCONT_utf8_safe(p, e) _generic_func_utf8_safe(_CC_WORDCHAR, \
+ _is_utf8_perl_idcont_with_len, p, e)
/* To prevent S_scan_word in toke.c from hanging, we have to make sure that
* IDFIRST is an alnum. See
* ever wanted to know about. (In the ASCII range, there isn't a difference.)
* This used to be not the XID version, but we decided to go with the more
* modern Unicode definition */
-#define isIDFIRST_utf8(p) _generic_func_utf8(_CC_IDFIRST, \
- _is_utf8_perl_idstart, p)
-
-#define isLOWER_utf8(p) _generic_swash_utf8(_CC_LOWER, p)
-#define isPRINT_utf8(p) _generic_swash_utf8(_CC_PRINT, p)
-#define isPSXSPC_utf8(p) isSPACE_utf8(p)
-#define isPUNCT_utf8(p) _generic_swash_utf8(_CC_PUNCT, p)
-#define isSPACE_utf8(p) _generic_func_utf8(_CC_SPACE, is_XPERLSPACE_high, p)
-#define isUPPER_utf8(p) _generic_swash_utf8(_CC_UPPER, p)
-#define isVERTWS_utf8(p) _generic_func_utf8(_CC_VERTSPACE, is_VERTWS_high, p)
-#define isWORDCHAR_utf8(p) _generic_swash_utf8(_CC_WORDCHAR, p)
-#define isXDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_XDIGIT, p, \
- is_XDIGIT_high(p))
+#define isIDFIRST_utf8_safe(p, e) \
+ _generic_func_utf8_safe(_CC_IDFIRST, \
+ _is_utf8_perl_idstart_with_len, (U8 *) (p), (U8 *) (e))
+
+#define isLOWER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_LOWER, p, e)
+#define isPRINT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PRINT, p, e)
+#define isPSXSPC_utf8_safe(p, e) isSPACE_utf8_safe(p, e)
+#define isPUNCT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PUNCT, p, e)
+#define isSPACE_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_SPACE, is_XPERLSPACE_high, p, e)
+#define isUPPER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_UPPER, p, e)
+#define isVERTWS_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_VERTSPACE, is_VERTWS_high, p, e)
+#define isWORDCHAR_utf8_safe(p, e) \
+ _generic_swash_utf8_safe(_CC_WORDCHAR, p, e)
+#define isXDIGIT_utf8_safe(p, e) \
+ _generic_utf8_safe_no_upper_latin1(_CC_XDIGIT, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : is_XDIGIT_high(p)))
#define toFOLD_utf8(p,s,l) to_utf8_fold(p,s,l)
#define toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l)
* isALPHA_LC_utf8. These are like _generic_utf8, but if the first code point
* in 'p' is within the 0-255 range, it uses locale rules from the passed-in
* 'macro' parameter */
-#define _generic_LC_utf8(macro, p, utf8) \
- (UTF8_IS_INVARIANT(*(p)) \
- ? macro(*(p)) \
- : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
- ? macro(EIGHT_BIT_UTF8_TO_NATIVE(*(p), *((p)+1)))\
- : utf8)
-
-#define _generic_LC_swash_utf8(macro, classnum, p) \
- _generic_LC_utf8(macro, p, _is_utf8_FOO(classnum, p))
-#define _generic_LC_func_utf8(macro, above_latin1, p) \
- _generic_LC_utf8(macro, p, above_latin1(p))
-
-#define isALPHANUMERIC_LC_utf8(p) _generic_LC_swash_utf8(isALPHANUMERIC_LC, \
- _CC_ALPHANUMERIC, p)
-#define isALPHA_LC_utf8(p) _generic_LC_swash_utf8(isALPHA_LC, _CC_ALPHA, p)
-#define isASCII_LC_utf8(p) isASCII_LC(*p)
-#define isBLANK_LC_utf8(p) _generic_LC_func_utf8(isBLANK_LC, \
- is_HORIZWS_high, p)
-#define isCNTRL_LC_utf8(p) _generic_LC_utf8(isCNTRL_LC, p, 0)
-#define isDIGIT_LC_utf8(p) _generic_LC_swash_utf8(isDIGIT_LC, _CC_DIGIT, p)
-#define isGRAPH_LC_utf8(p) _generic_LC_swash_utf8(isGRAPH_LC, _CC_GRAPH, p)
-#define isIDCONT_LC_utf8(p) _generic_LC_func_utf8(isIDCONT_LC, \
- _is_utf8_perl_idcont, p)
-#define isIDFIRST_LC_utf8(p) _generic_LC_func_utf8(isIDFIRST_LC, \
- _is_utf8_perl_idstart, p)
-#define isLOWER_LC_utf8(p) _generic_LC_swash_utf8(isLOWER_LC, _CC_LOWER, p)
-#define isPRINT_LC_utf8(p) _generic_LC_swash_utf8(isPRINT_LC, _CC_PRINT, p)
-#define isPSXSPC_LC_utf8(p) isSPACE_LC_utf8(p)
-#define isPUNCT_LC_utf8(p) _generic_LC_swash_utf8(isPUNCT_LC, _CC_PUNCT, p)
-#define isSPACE_LC_utf8(p) _generic_LC_func_utf8(isSPACE_LC, \
- is_XPERLSPACE_high, p)
-#define isUPPER_LC_utf8(p) _generic_LC_swash_utf8(isUPPER_LC, _CC_UPPER, p)
-#define isWORDCHAR_LC_utf8(p) _generic_LC_swash_utf8(isWORDCHAR_LC, \
- _CC_WORDCHAR, p)
-#define isXDIGIT_LC_utf8(p) _generic_LC_func_utf8(isXDIGIT_LC, \
- is_XDIGIT_high, p)
+#define _generic_LC_utf8(name, p) _base_generic_utf8(name, name, p, 1)
+
+#define isALPHA_LC_utf8(p) _generic_LC_utf8(ALPHA, p)
+#define isALPHANUMERIC_LC_utf8(p) _generic_LC_utf8(ALPHANUMERIC, p)
+#define isASCII_LC_utf8(p) _generic_LC_utf8(ASCII, p)
+#define isBLANK_LC_utf8(p) _generic_LC_utf8(BLANK, p)
+#define isCNTRL_LC_utf8(p) _generic_LC_utf8(CNTRL, p)
+#define isDIGIT_LC_utf8(p) _generic_LC_utf8(DIGIT, p)
+#define isGRAPH_LC_utf8(p) _generic_LC_utf8(GRAPH, p)
+#define isIDCONT_LC_utf8(p) _generic_LC_utf8(IDCONT, p)
+#define isIDFIRST_LC_utf8(p) _generic_LC_utf8(IDFIRST, p)
+#define isLOWER_LC_utf8(p) _generic_LC_utf8(LOWER, p)
+#define isPRINT_LC_utf8(p) _generic_LC_utf8(PRINT, p)
+#define isPSXSPC_LC_utf8(p) _generic_LC_utf8(PSXSPC, p)
+#define isPUNCT_LC_utf8(p) _generic_LC_utf8(PUNCT, p)
+#define isSPACE_LC_utf8(p) _generic_LC_utf8(SPACE, p)
+#define isUPPER_LC_utf8(p) _generic_LC_utf8(UPPER, p)
+#define isWORDCHAR_LC_utf8(p) _generic_LC_utf8(WORDCHAR, p)
+#define isXDIGIT_LC_utf8(p) _generic_LC_utf8(XDIGIT, p)
+
+/* For internal core Perl use only: the base macros for defining macros like
+ * isALPHA_LC_utf8_safe. These are like _generic_utf8, but if the first code
+ * point in 'p' is within the 0-255 range, it uses locale rules from the
+ * passed-in 'macro' parameter */
+#define _generic_LC_utf8_safe(macro, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? macro(*(p)) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p)) \
+ ? ((LIKELY((e) - (p) > 1 && UTF8_IS_CONTINUATION(*((p)+1)))) \
+ ? macro(EIGHT_BIT_UTF8_TO_NATIVE(*(p), *((p)+1))) \
+ : (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0)) \
+ : above_latin1))
+
+#define _generic_LC_swash_utf8_safe(macro, classnum, p, e) \
+ _generic_LC_utf8_safe(macro, p, e, \
+ _is_utf8_FOO_with_len(classnum, p, e))
+
+#define _generic_LC_func_utf8_safe(macro, above_latin1, p, e) \
+ _generic_LC_utf8_safe(macro, p, e, above_latin1(p, e))
+
+#define _generic_LC_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_LC_utf8_safe(classnum, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : above_latin1(p)))
+
+#define isALPHANUMERIC_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isALPHANUMERIC_LC, \
+ _CC_ALPHANUMERIC, p, e)
+#define isALPHA_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isALPHA_LC, _CC_ALPHA, p, e)
+#define isASCII_LC_utf8_safe(p, e) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isASCII_LC(*(p)))
+#define isBLANK_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isBLANK_LC, is_HORIZWS_high, p, e)
+#define isCNTRL_LC_utf8_safe(p, e) \
+ _generic_LC_utf8_safe(isCNTRL_LC, p, e, 0)
+#define isDIGIT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isDIGIT_LC, _CC_DIGIT, p, e)
+#define isGRAPH_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isGRAPH_LC, _CC_GRAPH, p, e)
+#define isIDCONT_LC_utf8_safe(p, e) \
+ _generic_LC_func_utf8_safe(isIDCONT_LC, \
+ _is_utf8_perl_idcont_with_len, p, e)
+#define isIDFIRST_LC_utf8_safe(p, e) \
+ _generic_LC_func_utf8_safe(isIDFIRST_LC, \
+ _is_utf8_perl_idstart_with_len, p, e)
+#define isLOWER_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isLOWER_LC, _CC_LOWER, p, e)
+#define isPRINT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isPRINT_LC, _CC_PRINT, p, e)
+#define isPSXSPC_LC_utf8_safe(p, e) isSPACE_LC_utf8_safe(p, e)
+#define isPUNCT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isPUNCT_LC, _CC_PUNCT, p, e)
+#define isSPACE_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isSPACE_LC, is_XPERLSPACE_high, p, e)
+#define isUPPER_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isUPPER_LC, _CC_UPPER, p, e)
+#define isWORDCHAR_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isWORDCHAR_LC, _CC_WORDCHAR, p, e)
+#define isXDIGIT_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isXDIGIT_LC, is_XDIGIT_high, p, e)
/* Macros for backwards compatibility and for completeness when the ASCII and
* Latin1 values are identical */
https://perl5.git.perl.org / perl5.git / blobdiff