# 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
- * (bool)!!(cbool) in a ternary triggers a bug in xlc on AIX
- */
-
+/* cast-to-bool. 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 (bool)!!(cbool) in a ternary triggers a bug in xlc on
+ * AIX */
#define cBOOL(cbool) ((cbool) ? (bool)1 : (bool)0)
/* Try to figure out __func__ or __FUNCTION__ equivalent, if any.
The base function, e.g., C<isALPHA()>, takes an octet (either a C<char> or a
C<U8>) as input and returns a boolean as to whether or not the character
-represented by that octet is 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
-always returned.
-
-Variant C<isFOO_A> (e.g., C<isALPHA_A()>) will return TRUE only if the input is
-also in the ASCII character set. For ASCII platforms, the base function with
-no suffix and the one with the C<_A> suffix are identical. On EBCDIC
-platforms, the C<_A> suffix function will not return true unless the specified
-character also has an ASCII equivalent.
-
-Variant C<isFOO_L1> operates on the full Latin1 character set. For EBCDIC
-platforms, the base function with no suffix and the one with the C<_L1> suffix
-are identical. For ASCII platforms, 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.
+represented by that octet is (or on non-ASCII platforms, corresponds to) an
+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<isFOO_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 represent different characters in each).
Variant C<isFOO_uni> is like the C<isFOO_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(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A WITH
-MACRON in Unicode, and is a word character.
+C<isWORDCHAR_uni(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_uni>, but the input is a pointer to a
(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
-classification of just the first character in the string is tested.
+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 uses
the C library function that gives the named classification instead of
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*>). The
-classification of just the first character in the string is tested.
+classification of just the first (possibly multi-byte) character in the string
+is tested.
=for apidoc Am|bool|isALPHA|char ch
Returns a boolean indicating whether the specified character is an
-alphabetic character in the platform's native character set, analogous to
-C<m/[[:alpha:]]/>.
+alphabetic character, analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uni>, C<isALPHA_utf8>, C<isALPHA_LC>
+C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uni>, C<isALPHA_utf8>, C<isALPHA_LC>,
C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8>.
=for apidoc Am|bool|isALPHANUMERIC|char ch
Returns a boolean indicating whether the specified character is a either an
-alphabetic character or decimal digit in the platform's native character set,
-analogous to C<m/[[:alnum:]]/>.
+alphabetic character or decimal digit, analogous to C<m/[[:alnum:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uni>,
-C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC> C<isALPHANUMERIC_LC_uvchr>, and
+C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>, and
C<isALPHANUMERIC_LC_utf8>.
=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, analogous to C<m/[[:ascii:]]/>.
-On non-ASCII platforms, it is if this
+On non-ASCII platforms, it returns TRUE iff this
character corresponds to an ASCII character. Variants C<isASCII_A()> and
C<isASCII_L1()> are identical to C<isASCII()>.
See the L<top of this section|/Character classes> for an explanation of variants
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.
+
=for apidoc Am|bool|isBLANK|char ch
Returns a boolean indicating whether the specified character is a
-character considered to be a blank in the platform's native character set,
-analogous to C<m/[[:blank:]]/>.
+character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uni>, C<isBLANK_utf8>, C<isBLANK_LC>
+C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uni>, 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
=for apidoc Am|bool|isCNTRL|char ch
Returns a boolean indicating whether the specified character is a
-control character in the platform's native character set,
-analogous to C<m/[[:cntrl:]]/>.
+control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uni>, C<isCNTRL_utf8>, C<isCNTRL_LC>
-C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8>.
+C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uni>, 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.
=for apidoc Am|bool|isDIGIT|char ch
Returns a boolean indicating whether the specified character is a
-digit in the platform's native character set, analogous to C<m/[[:digit:]]/>.
+digit, analogous to C<m/[[:digit:]]/>.
Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isDIGIT_uni>, C<isDIGIT_utf8>, C<isDIGIT_LC> C<isDIGIT_LC_uvchr>, and
+C<isDIGIT_uni>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
C<isDIGIT_LC_utf8>.
=for apidoc Am|bool|isGRAPH|char ch
Returns a boolean indicating whether the specified character is a
-graphic character in the platform's native character set, analogous to
-C<m/[[:graph:]]/>.
+graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uni>, C<isGRAPH_utf8>, C<isGRAPH_LC>
+C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uni>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8>.
=for apidoc Am|bool|isLOWER|char ch
Returns a boolean indicating whether the specified character is a
-lowercase character in the platform's native character set, analogous to
-C<m/[[:lower:]]/>.
+lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uni>, C<isLOWER_utf8>, C<isLOWER_LC>
+C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uni>, C<isLOWER_utf8>, C<isLOWER_LC>,
C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
=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.
+octal digit, [0-7].
The only two variants are C<isOCTAL_A> and C<isOCTAL_L1>; each is identical to
C<isOCTAL>.
=for apidoc Am|bool|isPUNCT|char ch
Returns a boolean indicating whether the specified character is a
-punctuation character in the platform's native character set, analogous to
-C<m/[[:punct:]]/>. Note that the definition of what is punctuation isn't as
+punctuation character, analogous to C<m/[[:punct:]]/>.
+Note that the definition of what is punctuation isn't as
straightforward as one might desire. See L<perlrecharclass/POSIX Character
Classes> for details.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uni>, C<isPUNCT_utf8>, C<isPUNCT_LC>
+C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uni>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
=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 analogous
+whitespace character. This is analogous
to what C<m/\s/> matches in a regular expression. Starting in Perl 5.18
(experimentally), this also matches what C<m/[[:space:]]/> does.
("Experimentally" means that this change may be backed out in 5.20 or 5.22 if
in the non-locale variants, was that C<isSPACE()> did not match a vertical tab.
(See L</isPSXSPC> for a macro that matches a vertical tab in all releases.)
See the L<top of this section|/Character classes> for an explanation of variants
-C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uni>, C<isSPACE_utf8>, C<isSPACE_LC>
+C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uni>, C<isSPACE_utf8>, C<isSPACE_LC>,
C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
=for apidoc Am|bool|isPSXSPC|char ch
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 classes> for an explanation of variants
-C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uni>, C<isPSXSPC_utf8>, C<isPSXSPC_LC>
+C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uni>, C<isPSXSPC_utf8>, C<isPSXSPC_LC>,
C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
=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, analogous to
-C<m/[[:upper:]]/>.
+uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uni>, C<isUPPER_utf8>, C<isUPPER_LC>
+C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uni>, C<isUPPER_utf8>, C<isUPPER_LC>,
C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8>.
=for apidoc Am|bool|isPRINT|char ch
Returns a boolean indicating whether the specified character is a
-printable character in the platform's native character set, analogous to
-C<m/[[:print:]]/>.
+printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classes> for an explanation of variants
-C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uni>, C<isPRINT_utf8>, C<isPRINT_LC>
+C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uni>, C<isPRINT_utf8>, C<isPRINT_LC>,
C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
=for apidoc Am|bool|isWORDCHAR|char ch
C<isXDIGIT_uni>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
C<isXDIGIT_LC_utf8>.
+=for apidoc Am|bool|isIDFIRST|char ch
+Returns a boolean indicating whether the specified character can be the first
+character of an identifier. This is very close to, but not quite the same as
+the official Unicode property C<XID_Start>. The difference is that this
+returns true only if the input character also matches L</isWORDCHAR>.
+See the L<top of this section|/Character classes> for an explanation of variants
+C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uni>, C<isIDFIRST_utf8>,
+C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8>.
+
+=for apidoc Am|bool|isIDCONT|char ch
+Returns a boolean indicating whether the specified character can be the
+second or succeeding character of an identifier. This is very close to, but
+not quite the same as the official Unicode property C<XID_Continue>. The
+difference is that this returns true only if the input character also matches
+L</isWORDCHAR>. See the L<top of this section|/Character classes> for an
+explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uni>,
+C<isIDCONT_utf8>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
+C<isIDCONT_LC_utf8>.
+
=head1 Miscellaneous Functions
=for apidoc Am|U8|READ_XDIGIT|char str*
=head1 Character case changing
-=for apidoc Am|char|toUPPER|char ch
-Converts the specified character to uppercase in the platform's native
-character set, if possible; otherwise returns the input character itself.
+=for apidoc Am|U8|toUPPER|U8 ch
+Converts the specified character to uppercase. If the input is anything but an
+ASCII lowercase character, that input character itself is returned. Variant
+C<toUPPER_A> is equivalent.
+
+=for apidoc Am|UV|toUPPER_uni|UV cp|U8* s|STRLEN* lenp
+Converts the Unicode code point C<cp> to its uppercase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+=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
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+The input character at C<p> is assumed to be well-formed.
+
+=for apidoc Am|U8|toFOLD|U8 ch
+Converts the specified character to foldcase. If the input is anything but an
+ASCII uppercase character, that input character itself is returned. Variant
+C<toFOLD_A> is equivalent. (There is no equivalent C<to_FOLD_L1> for the full
+Latin1 range, as the full generality of L</toFOLD_uni> is needed there.)
+
+=for apidoc Am|UV|toFOLD_uni|UV cp|U8* s|STRLEN* lenp
+Converts the Unicode code point C<cp> to its foldcase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+=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
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+The input character at C<p> is assumed to be well-formed.
+
+=for apidoc Am|U8|toLOWER|U8 ch
+Converts the specified character to lowercase. If the input is anything but an
+ASCII uppercase character, that input character itself is returned. Variant
+C<toLOWER_A> is equivalent.
+
+=for apidoc Am|U8|toLOWER_L1|U8 ch
+Converts the specified Latin1 character to lowercase. The results are undefined if
+the input doesn't fit in a byte.
+
+=for apidoc Am|U8|toLOWER_LC|U8 ch
+Converts the specified character to lowercase using the current locale's rules,
+if possible; otherwise returns the input character itself.
+
+=for apidoc Am|UV|toLOWER_uni|UV cp|U8* s|STRLEN* lenp
+Converts the Unicode code point C<cp> to its lowercase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+=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
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+The input character at C<p> is assumed to be well-formed.
+
+=for apidoc Am|U8|toLOWER_LC|U8 ch
+Converts the specified character to lowercase using the current locale's rules,
+if possible; otherwise returns the input character itself.
+
+=for apidoc Am|U8|toTITLE|U8 ch
+Converts the specified character to titlecase. If the input is anything but an
+ASCII lowercase character, that input character itself is returned. Variant
+C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1 range,
+as the full generality of L</toTITLE_uni> is needed there. Titlecase is not a
+concept used in locale handling, so there is no functionality for that.)
+
+=for apidoc Am|UV|toTITLE_uni|UV cp|U8* s|STRLEN* lenp
+Converts the Unicode code point C<cp> to its titlecase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+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.)
+
+=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
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
+bytes since the titlecase version may be longer than the original character.
-=for apidoc Am|char|toLOWER|char ch
-Converts the specified character to lowercase in the platform's native
-character set, if possible; otherwise returns the input character itself.
+The first code point of the titlecased version is returned
+(but note, as explained just above, that there may be more.)
+
+The input character at C<p> is assumed to be well-formed.
=cut
-XXX Still undocumented are VERTSPACE, and IDFIRST IDCONT, and the
-other toUPPER etc functions
+XXX Still undocumented isVERTWS_uni and _utf8; it's unclear what their names
+really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change.
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 FITS_IN_8_BITS(c) ((sizeof(c) == 1) || !(((WIDEST_UTYPE)(c)) & ~0xFF))
#ifdef EBCDIC
-# define isASCII(c) (FITS_IN_8_BITS(c) && (NATIVE_TO_UNI((U8) (c)) < 128))
+# ifndef _ALL_SOURCE
+ /* This returns the wrong results on at least z/OS unless this is
+ * defined. */
+# error _ALL_SOURCE should probably be defined
+# endif
+
+ /* We could be called without perl.h, in which case NATIVE_TO_ASCII() is
+ * likely not defined, and so we use the native function */
+# define isASCII(c) isascii(c)
#else
# define isASCII(c) ((WIDEST_UTYPE)(c) < 128)
#endif
# define _CC_QUOTEMETA 20
# define _CC_NON_FINAL_FOLD 21
# define _CC_IS_IN_SOME_FOLD 22
-/* Unused: 23-31
+# define _CC_BACKSLASH_FOO_LBRACE_IS_META 31 /* temp, see mk_PL_charclass.pl */
+/* Unused: 23-30
* If more bits are needed, one could add a second word for non-64bit
* QUAD_IS_INT systems, using some #ifdefs to distinguish between having a 2nd
* word or not. The IS_IN_SOME_FOLD bit is the most easily expendable, as it
/* The 1U keeps Solaris from griping when shifting sets the uppermost bit */
# define _CC_mask(classnum) (1U << (classnum))
# define _generic_isCC(c, classnum) cBOOL(FITS_IN_8_BITS(c) \
- && (PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_mask(classnum)))
+ && (PL_charclass[(U8) (c)] & _CC_mask(classnum)))
/* The mask for the _A versions of the macros; it just adds in the bit for
* ASCII. */
/* The _A version makes sure that both the desired bit and the ASCII bit
* are present */
# define _generic_isCC_A(c, classnum) (FITS_IN_8_BITS(c) \
- && ((PL_charclass[(U8) NATIVE_TO_UNI(c)] & _CC_mask_A(classnum)) \
+ && ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
== _CC_mask_A(classnum)))
# define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA)
/* 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_mask(_CC_NONLATIN1_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) (c)] & _CC_mask(_CC_NONLATIN1_FOLD)))
# define _isQUOTEMETA(c) _generic_isCC(c, _CC_QUOTEMETA)
# define _IS_NON_FINAL_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
# define _IS_IN_SOME_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
_generic_isCC(c, _CC_IS_IN_SOME_FOLD)
#else /* No perl.h. */
+# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
+# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
+# define isWORDCHAR_A(c) (isALPHANUMERIC_A(c) || (c) == '_')
+# define isPSXSPC_A(c) (isSPACE_A(c) || (c) == '\v')
# ifdef EBCDIC
-# define isALPHA_A(c) (isASCII(c) && isALPHA(c))
-# define isALPHANUMERIC_A(c) (isASCII(c) && isALPHANUMERIC(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))
+ /* We could be called without perl.h, so the native functions are the
+ * easiest to code these in. They likely will return false for all
+ * non-ASCII values, but this makes sure */
+# define isALPHA_A(c) (isASCII(c) && isalpha(c))
+# define isALPHANUMERIC_A(c) (isASCII(c) && isalnum(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 isLOWER_A(c) (isASCII(c) && islower(c))
+# define isPRINT_A(c) (isASCII(c) && isprint(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 isXDIGIT_A(c) (isASCII(c) && isxdigit(c))
# else /* ASCII platform, no perl.h */
# define isALPHA_A(c) (isUPPER_A(c) || isLOWER_A(c))
# define isALPHANUMERIC_A(c) (isALPHA_A(c) || isDIGIT_A(c))
-# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
-# define isCNTRL_A(c) (FITS_IN_8_BITS(c) && ((U8) (c) < ' ' || (c) == 127))
+# define isCNTRL_A(c) (isASCII(c) && ! isPRINT_A(c))
# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
-# define isGRAPH_A(c) (isWORDCHAR_A(c) || isPUNCT_A(c))
-# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
+# define isGRAPH_A(c) (isPRINT_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 isPUNCT_A(c) (isGRAPH_A(c) && ! isALPHANUMERIC(c))
# define isSPACE_A(c) ((c) == ' ' \
|| (c) == '\t' \
|| (c) == '\n' \
|| (c) =='\r' \
|| (c) == '\f')
# define isUPPER_A(c) ((c) <= 'Z' && (c) >= 'A')
-# define isWORDCHAR_A(c) (isALPHA_A(c) || isDIGIT_A(c) || (c) == '_')
# define isXDIGIT_A(c) (isDIGIT_A(c) \
|| ((c) >= 'a' && (c) <= 'f') \
|| ((c) <= 'F' && (c) >= 'A'))
* 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 isALPHA_L1(c) (isALPHA(c) || (NATIVE_TO_LATIN1((U8) c) >= 0xAA \
+ && ((NATIVE_TO_LATIN1((U8) c) >= 0xC0 \
+ && NATIVE_TO_LATIN1((U8) c) != 0xD7 && NATIVE_TO_LATIN1((U8) c) != 0xF7) \
+ || NATIVE_TO_LATIN1((U8) c) == 0xAA \
+ || NATIVE_TO_LATIN1((U8) c) == 0xB5 \
+ || NATIVE_TO_LATIN1((U8) c) == 0xBA)))
# define isCHARNAME_CONT(c) (isWORDCHAR_L1(c) \
|| (c) == ' ' \
|| (c) == '-' \
|| (c) == '(' \
|| (c) == ')' \
|| (c) == ':' \
- || NATIVE_TO_UNI((U8) c) == 0xA0)
-#endif
-
-/* 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
-# define isALPHA(c) isalpha(c)
-# define isALPHANUMERIC(c) isalnum(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' (Experimentally making
- these macros identical) */)
-# define isUPPER(c) isupper(c)
-# define isXDIGIT(c) isxdigit(c)
-# define isWORDCHAR(c) (isalnum(c) || (c) == '_')
-# define toLOWER(c) tolower(c)
-# define toUPPER(c) toupper(c)
-#else /* Not EBCDIC: ASCII-only matching */
-# define isALPHANUMERIC(c) isALPHANUMERIC_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))
+ || NATIVE_TO_LATIN1((U8) c) == 0xA0)
#endif
+#define isALPHANUMERIC(c) isALPHANUMERIC_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))
+
+/* In the ASCII range, these are equivalent to what they're here defined to be.
+ * But by creating these definitions, other code doesn't have to be aware of
+ * this detail */
+#define toFOLD(c) toLOWER(c)
+#define toFOLD_LC(c) toLOWER_LC(c)
+#define toTITLE(c) toUPPER(c)
+
+#define toLOWER_A(c) toLOWER(c)
+#define toUPPER_A(c) toUPPER(c)
+#define toFOLD_A(c) toFOLD(c)
+#define toTITLE_A(c) toTITLE(c)
/* 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)
+#define toLOWER_LATIN1(c) ((! FITS_IN_8_BITS(c)) \
+ ? (c) \
+ : PL_latin1_lc[ (U8) (c) ])
+#define toLOWER_L1(c) toLOWER_LATIN1(c) /* Synonym for consistency */
+
/* 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)
-
+#define toUPPER_LATIN1_MOD(c) ((! FITS_IN_8_BITS(c)) \
+ ? (c) \
+ : PL_mod_latin1_uc[ (U8) (c) ])
#ifdef USE_NEXT_CTYPE
# define isALPHANUMERIC_LC(c) NXIsAlNum((unsigned int)(c))
? _generic_isCC(*(p), classnum) \
: (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
? _generic_isCC( \
- TWO_BYTE_UTF8_TO_UNI(*(p), \
+ TWO_BYTE_UTF8_TO_NATIVE(*(p), \
*((p)+1 )), \
- classnum) \
+ classnum) \
: utf8)
/* Like the above, but calls 'above_latin1(p)' to get the utf8 value. 'above_latin1'
* can be a macro */
_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_idstart, p)
+ _is_utf8_perl_idcont, p)
/* To prevent S_scan_word in toke.c from hanging, we have to make sure that
* IDFIRST is an alnum. See
#define isXDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_XDIGIT, p, \
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)
#define toTITLE_utf8(p,s,l) to_utf8_title(p,s,l)
#define toUPPER_utf8(p,s,l) to_utf8_upper(p,s,l)
* use the value given by the '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_LC_utf8(macro, p, utf8) \
- (UTF8_IS_INVARIANT(*(p)) \
- ? macro(*(p)) \
- : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
- ? macro(TWO_BYTE_UTF8_TO_UNI(*(p), *((p)+1))) \
+#define _generic_LC_utf8(macro, p, utf8) \
+ (UTF8_IS_INVARIANT(*(p)) \
+ ? macro(*(p)) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
+ ? macro(TWO_BYTE_UTF8_TO_NATIVE(*(p), *((p)+1))) \
: utf8)
#define _generic_LC_swash_utf8(macro, classnum, p) \
* CTRL-@ is 0, CTRL-A is 1, etc, just like on ASCII, except that they don't
* necessarily mean the same characters, e.g. CTRL-D is 4 on both systems, but
* that is EOT on ASCII; ST on EBCDIC */
-# define toCTRL(c) (toUPPER(NATIVE_TO_UNI(c)) ^ 64)
+# define toCTRL(c) (toUPPER(NATIVE_TO_LATIN1(c)) ^ 64)
/* Line numbers are unsigned, 32 bits. */
typedef U32 line_t;
# define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), "Use of " s " is deprecated")
#endif
+/* Internal macros to deal with gids and uids */
+#ifdef PERL_CORE
+
+# if Uid_t_size > IVSIZE
+# define sv_setuid(sv, uid) sv_setnv((sv), (NV)(uid))
+# define SvUID(sv) SvNV(sv)
+# else
+# if Uid_t_sign <= 0
+# define sv_setuid(sv, uid) sv_setiv((sv), (IV)(uid))
+# define SvUID(sv) SvIV(sv)
+# else
+# define sv_setuid(sv, uid) sv_setuv((sv), (UV)(uid))
+# define SvUID(sv) SvUV(sv)
+# endif
+# endif /* Uid_t_size */
+
+# if Gid_t_size > IVSIZE
+# define sv_setgid(sv, gid) sv_setnv((sv), (NV)(gid))
+# define SvGID(sv) SvNV(sv)
+# else
+# if Gid_t_sign <= 0
+# define sv_setgid(sv, gid) sv_setiv((sv), (IV)(gid))
+# define SvGID(sv) SvIV(sv)
+# else
+# define sv_setgid(sv, gid) sv_setuv((sv), (UV)(gid))
+# define SvGID(sv) SvUV(sv)
+# endif
+# endif /* Gid_t_size */
+
+#endif
+
#endif /* HANDY_H */
/*
https://perl5.git.perl.org / perl5.git / blobdiff