# 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
=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
-to what C<m/\s/> and C<m/[[:space:]]/> match in a regular expression.
+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
+field experience indicates that it was unwise.) Prior to 5.18, only the
+locale forms of this macro (the ones with C<LC> in their names) matched
+precisely what C<m/[[:space:]]/> does. In those releases, the only difference,
+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
+(short for Posix Space)
+Starting in 5.18, this is identical (experimentally) in all its forms to the
+corresponding C<isSPACE()> macros. ("Experimentally" means that this change
+may be backed out in 5.20 or 5.22 if field experience indicates that it
+was unwise.)
+The locale forms of this macro are identical to their corresponding
+C<isSPACE()> forms in all Perl releases. In releases prior to 5.18, the
+non-locale forms differ from their C<isSPACE()> forms only in that the
+C<isSPACE()> forms don't match a Vertical Tab, and the C<isPSXSPC()> forms do.
+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_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.
+
+The first code point of the titlecased version is returned
+(but note, as explained just above, that there may be more.)
-=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 input character at C<p> is assumed to be well-formed.
=cut
-Still undocumented are , PSXSPC, VERTSPACE, and IDFIRST, 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
/* ASCII range only */
#ifdef H_PERL /* If have access to perl.h, lookup in its table */
-/* Character class numbers. For internal core Perl use only. These are used
- * in PL_charclass[] and the ones up through the one that corresponds to
- * <_HIGHEST_REGCOMP_DOT_H_SYNC> are used by regcomp.h. These use names used
- * in l1_char_class_tab.h but their actual definitions are here. If that file
- * has a name not used here, it won't compile.
+/* Character class numbers. For internal core Perl use only. The ones less
+ * than 32 are used in PL_charclass[] and the ones up through the one that
+ * corresponds to <_HIGHEST_REGCOMP_DOT_H_SYNC> are used by regcomp.h and
+ * related files. PL_charclass ones use names used in l1_char_class_tab.h but
+ * their actual definitions are here. If that file has a name not used here,
+ * it won't compile.
*
* The first group of these is ordered in what I (khw) estimate to be the
* frequency of their use. This gives a slight edge to exiting a loop earlier
# 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 _FIRST_NON_SWASH_CC 9
+#define _FIRST_NON_SWASH_CC 10
/* The character classes above are implemented with swashes. The second group
* (just below) contains the ones implemented without. These are also sorted
* in rough order of the frequency of their use, except that \v should be last,
* useful to group these which have no members that match above Latin1, (or
* above ASCII in the latter case) */
-# define _CC_SPACE 9 /* \s */
-# define _CC_BLANK 10 /* [:blank:] */
-# define _CC_XDIGIT 11 /* [:xdigit:] */
-# define _CC_PSXSPC 12 /* [:space:] */
-# define _CC_CNTRL 13 /* [:cntrl:] */
-# define _CC_ASCII 14 /* [:ascii:] */
-# define _CC_VERTSPACE 15 /* \v */
+# define _CC_SPACE 10 /* \s */
+# define _CC_BLANK 11 /* [:blank:] */
+# define _CC_XDIGIT 12 /* [:xdigit:] */
+# define _CC_PSXSPC 13 /* [:space:] */
+# define _CC_CNTRL 14 /* [:cntrl:] */
+# define _CC_ASCII 15 /* [:ascii:] */
+# define _CC_VERTSPACE 16 /* \v */
# define _HIGHEST_REGCOMP_DOT_H_SYNC _CC_VERTSPACE
/* The members of the third group below do not need to be coordinated with data
* structures in regcomp.[ch] and regexec.c */
-# define _CC_IDFIRST 16
-# define _CC_CHARNAME_CONT 17
-# define _CC_NONLATIN1_FOLD 18
-# define _CC_QUOTEMETA 19
-# define _CC_NON_FINAL_FOLD 20
-# define _CC_IS_IN_SOME_FOLD 21
-/* Unused: 22-31
+# define _CC_IDFIRST 17
+# define _CC_CHARNAME_CONT 18
+# define _CC_NONLATIN1_FOLD 19
+# define _CC_QUOTEMETA 20
+# define _CC_NON_FINAL_FOLD 21
+# define _CC_IS_IN_SOME_FOLD 22
+# 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
* is used only for optimization (as of this writing), and differs in the
* Latin1 range from the ALPHA bit only in two relatively unimportant
- * characters: the masculine and feminine ordinal indicators */
+ * characters: the masculine and feminine ordinal indicators, so removing it
+ * would just cause /i regexes which match them to run less efficiently */
#if defined(PERL_CORE) || defined(PERL_EXT)
/* An enum version of the character class numbers, to help compilers
* optimize */
typedef enum {
- _CC_ENUM_ALPHANUMERIC = _CC_ALPHANUMERIC,
_CC_ENUM_ALPHA = _CC_ALPHA,
+ _CC_ENUM_ALPHANUMERIC = _CC_ALPHANUMERIC,
+ _CC_ENUM_ASCII = _CC_ASCII,
+ _CC_ENUM_BLANK = _CC_BLANK,
+ _CC_ENUM_CASED = _CC_CASED,
+ _CC_ENUM_CNTRL = _CC_CNTRL,
_CC_ENUM_DIGIT = _CC_DIGIT,
_CC_ENUM_GRAPH = _CC_GRAPH,
_CC_ENUM_LOWER = _CC_LOWER,
_CC_ENUM_PRINT = _CC_PRINT,
+ _CC_ENUM_PSXSPC = _CC_PSXSPC,
_CC_ENUM_PUNCT = _CC_PUNCT,
+ _CC_ENUM_SPACE = _CC_SPACE,
_CC_ENUM_UPPER = _CC_UPPER,
+ _CC_ENUM_VERTSPACE = _CC_VERTSPACE,
_CC_ENUM_WORDCHAR = _CC_WORDCHAR,
- _CC_ENUM_SPACE = _CC_SPACE,
- _CC_ENUM_BLANK = _CC_BLANK,
- _CC_ENUM_XDIGIT = _CC_XDIGIT,
- _CC_ENUM_CNTRL = _CC_CNTRL,
- _CC_ENUM_PSXSPC = _CC_PSXSPC,
- _CC_ENUM_ASCII = _CC_ASCII,
- _CC_ENUM_VERTSPACE = _CC_VERTSPACE
+ _CC_ENUM_XDIGIT = _CC_XDIGIT
} _char_class_number;
#endif
#define POSIX_SWASH_COUNT _FIRST_NON_SWASH_CC
#define POSIX_CC_COUNT (_HIGHEST_REGCOMP_DOT_H_SYNC + 1)
-#if defined(PERL_IN_UTF8_C) || defined(PERL_IN_REGCOMP_C)
+#if defined(PERL_IN_UTF8_C) || defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_REGEXEC_C)
# if _CC_WORDCHAR != 0 || _CC_DIGIT != 1 || _CC_ALPHA != 2 || _CC_LOWER != 3 \
- || _CC_UPPER != 4 || _CC_PUNCT != 5 || _CC_PRINT != 6 \
- || _CC_ALPHANUMERIC != 7 || _CC_GRAPH != 8
+ || _CC_UPPER != 4 || _CC_PUNCT != 5 || _CC_PRINT != 6 \
+ || _CC_ALPHANUMERIC != 7 || _CC_GRAPH != 8 || _CC_CASED != 9
#error Need to adjust order of swash_property_names[]
# endif
"XPosixPunct",
"XPosixPrint",
"XPosixAlnum",
- "XPosixGraph"
+ "XPosixGraph",
+ "Cased"
};
#endif
-#define PL_utf8_alnum PL_utf8_swash_ptrs[_CC_WORDCHAR]
-#define PL_utf8_alnumc PL_utf8_swash_ptrs[_CC_ALPHANUMERIC]
-#define PL_utf8_alpha PL_utf8_swash_ptrs[_CC_ALPHA]
-#define PL_utf8_graph PL_utf8_swash_ptrs[_CC_GRAPH]
-#define PL_utf8_digit PL_utf8_swash_ptrs[_CC_DIGIT]
-#define PL_utf8_upper PL_utf8_swash_ptrs[_CC_UPPER]
-#define PL_utf8_lower PL_utf8_swash_ptrs[_CC_LOWER]
-#define PL_utf8_print PL_utf8_swash_ptrs[_CC_PRINT]
-#define PL_utf8_punct PL_utf8_swash_ptrs[_CC_PUNCT]
-
# ifdef DOINIT
EXTCONST U32 PL_charclass[] = {
# include "l1_char_class_tab.h"
# define toUPPER(c) (isLOWER(c) ? (c) - ('a' - 'A') : (c))
#endif
+/* 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) \
+ : UNI_TO_NATIVE(PL_latin1_lc[ \
+ NATIVE_TO_UNI( (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) \
+ : UNI_TO_NATIVE(PL_mod_latin1_uc[ \
+ NATIVE_TO_UNI( (U8) (c)) ]))
#ifdef USE_NEXT_CTYPE
# endif
#endif /* USE_NEXT_CTYPE */
+#define isIDCONT(c) isWORDCHAR(c)
+#define isIDCONT_A(c) isWORDCHAR_A(c)
+#define isIDCONT_L1(c) isWORDCHAR_L1(c)
+#define isIDCONT_LC(c) isWORDCHAR_LC(c)
#define isPSXSPC_LC(c) isSPACE_LC(c)
/* For internal core Perl use only. If the input is Latin1, use the Latin1
- * macro; otherwise use the function. Won't compile if 'c' isn't unsigned, as
- * won't match function prototype. The macros do bounds checking, so have
+ * macro; otherwise use the function 'above_latin1'. Won't compile if 'c' isn't unsigned, as
+ * won't match above_latin1 prototype. The macros do bounds checking, so have
* duplicate checks here, so could create versions of the macros that don't,
* but experiments show that gcc optimizes them out anyway. */
#define isCNTRL_uni(c) isCNTRL_L1(c) /* All controls are in Latin1 */
#define isDIGIT_uni(c) _generic_swash_uni(_CC_DIGIT, c)
#define isGRAPH_uni(c) _generic_swash_uni(_CC_GRAPH, c)
+#define isIDCONT_uni(c) _generic_uni(_CC_WORDCHAR, _is_uni_perl_idcont, c)
#define isIDFIRST_uni(c) _generic_uni(_CC_IDFIRST, _is_uni_perl_idstart, c)
#define isLOWER_uni(c) _generic_swash_uni(_CC_LOWER, c)
#define isPRINT_uni(c) _generic_swash_uni(_CC_PRINT, c)
#define isCNTRL_LC_uvchr(c) (c < 256 ? isCNTRL_LC(c) : 0)
#define isDIGIT_LC_uvchr(c) _generic_LC_swash_uvchr(isDIGIT_LC, _CC_DIGIT, c)
#define isGRAPH_LC_uvchr(c) _generic_LC_swash_uvchr(isGRAPH_LC, _CC_GRAPH, c)
+#define isIDCONT_LC_uvchr(c) _generic_LC_uvchr(isIDCONT_LC, \
+ _is_uni_perl_idcont, c)
#define isIDFIRST_LC_uvchr(c) _generic_LC_uvchr(isIDFIRST_LC, \
_is_uni_perl_idstart, c)
#define isLOWER_LC_uvchr(c) _generic_LC_swash_uvchr(isLOWER_LC, _CC_LOWER, c)
#define isBLANK_LC_uni(c) isBLANK_LC_uvchr(UNI_TO_NATIVE(c))
-/* For internal core Perl use only. If the input is in the Latin1 range, use
+/* Everything whose name begins with an underscore is for internal core Perl
+ * use only. */
+
+/* If the input is in the Latin1 range, use
* the Latin1 macro 'classnum' on 'p' which is a pointer to a UTF-8 string.
* Otherwise use the value given by the 'utf8' parameter. This relies on the
* fact that ASCII characters have the same representation whether utf8 or not.
#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_xidcont, p)
+#define isIDCONT_utf8(p) _generic_func_utf8(_CC_WORDCHAR, \
+ _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)
#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)
* (U16)n > (size_t)~0/sizeof(U16) always being false. */
#ifdef PERL_MALLOC_WRAP
#define MEM_WRAP_CHECK(n,t) \
- (void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (croak_memory_wrap(),0))
+ (void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (Perl_croak_memory_wrap(),0))
#define MEM_WRAP_CHECK_1(n,t,a) \
(void)(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t) && (Perl_croak_nocontext("%s",(a)),0))
#define MEM_WRAP_CHECK_(n,t) MEM_WRAP_CHECK(n,t),
-#define PERL_STRLEN_ROUNDUP(n) ((void)(((n) > MEM_SIZE_MAX - 2 * PERL_STRLEN_ROUNDUP_QUANTUM) ? (croak_memory_wrap(),0):0),((n-1+PERL_STRLEN_ROUNDUP_QUANTUM)&~((MEM_SIZE)PERL_STRLEN_ROUNDUP_QUANTUM-1)))
+#define PERL_STRLEN_ROUNDUP(n) ((void)(((n) > MEM_SIZE_MAX - 2 * PERL_STRLEN_ROUNDUP_QUANTUM) ? (Perl_croak_memory_wrap(),0):0),((n-1+PERL_STRLEN_ROUNDUP_QUANTUM)&~((MEM_SIZE)PERL_STRLEN_ROUNDUP_QUANTUM-1)))
#else
#define MEM_WRAP_CHECK(n,t)
https://perl5.git.perl.org / perl5.git / blobdiff