# endif
#endif
-/* The NeXT dynamic loader headers will not build with the bool macro
- So declare them now to clear confusion.
-*/
-#if defined(NeXT) || defined(__NeXT__)
-# undef FALSE
-# undef TRUE
- typedef enum bool { FALSE = 0, TRUE = 1 } bool;
-# define ENUM_BOOL 1
-# ifndef HAS_BOOL
-# define HAS_BOOL 1
-# endif /* !HAS_BOOL */
-#endif /* NeXT || __NeXT__ */
-
#ifndef HAS_BOOL
# ifdef bool
# undef bool
#define TYPE_DIGITS(T) BIT_DIGITS(sizeof(T) * 8)
#define TYPE_CHARS(T) (TYPE_DIGITS(T) + 2) /* sign, NUL */
+/* Unused by core; should be deprecated */
#define Ctl(ch) ((ch) & 037)
/* This is a helper macro to avoid preprocessor issues, replaced by nothing
/*
-=head1 Character classes
+=head1 Character classification
This section is about functions (really macros) that classify characters
into types, such as punctuation versus alphabetic, etc. Most of these are
analogous to regular expression character classes. (See
the published Unicode rules; otherwise, it uses the C library function that
gives the named classification. For example, C<isDIGIT_LC()> when not in a
UTF-8 locale returns the result of calling C<isdigit()>. FALSE is always
-returned if the input won't fit into an octet.
+returned if the input won't fit into an octet. On some platforms where the C
+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
=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 classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
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, analogous to C<m/[[:alnum:]]/>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> 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_LC_utf8>.
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
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isASCII_uni>, 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
library routine C<isascii()>. In these cases, the variants whose names contain
=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 classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
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
=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 classes> for an explanation of variants
+See the L<top of this section|/Character classification> 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>
On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
Returns a boolean indicating whether the specified character is a
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
+See the L<top of this section|/Character classification> for an explanation of
+variants
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, analogous to C<m/[[:graph:]]/>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
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, analogous to C<m/[[:lower:]]/>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uni>, C<isLOWER_utf8>, C<isLOWER_LC>,
C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
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
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uni>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
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
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uni>, C<isSPACE_utf8>, C<isSPACE_LC>,
C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
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
+See the L<top of this section|/Character classification> 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, analogous to C<m/[[:upper:]]/>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
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, analogous to C<m/[[:print:]]/>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uni>, C<isPRINT_utf8>, C<isPRINT_LC>,
C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
C<isALNUM()> is a synonym provided for backward compatibility, even though a
word character includes more than the standard C language meaning of
alphanumeric.
-See the L<top of this section|/Character classes> for an explanation of variants
-C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uni>, C<isWORDCHAR_utf8>,
-C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and C<isWORDCHAR_LC_utf8>.
+See the L<top of this section|/Character classification> for an explanation of
+variants
+C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uni>, 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.
=for apidoc Am|bool|isXDIGIT|char ch
Returns a boolean indicating whether the specified character is a hexadecimal
digit. In the ASCII range these are C<[0-9A-Fa-f]>. Variants C<isXDIGIT_A()>
and C<isXDIGIT_L1()> are identical to C<isXDIGIT()>.
-See the L<top of this section|/Character classes> for an explanation of variants
+See the L<top of this section|/Character classification> for an explanation of
+variants
C<isXDIGIT_uni>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
C<isXDIGIT_LC_utf8>.
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
+See the L<top of this section|/Character classification> 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>.
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
+L</isWORDCHAR>. See the L<top of this section|/Character classification> 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>.
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
#ifdef EBCDIC
# ifndef _ALL_SOURCE
- /* This returns the wrong results on at least z/OS unless this is
- * defined. */
+ /* The native libc isascii() et.al. functions return 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) cBOOL(isascii(c))
#else
+ /* There is a simple definition of ASCII for ASCII platforms. But the
+ * EBCDIC one isn't so simple, so is defined using table look-up like the
+ * other macros below */
# define isASCII(c) ((WIDEST_UTYPE)(c) < 128)
#endif
-#define isASCII_A(c) isASCII(c)
-#define isASCII_L1(c) isASCII(c)
-
/* 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')
-/* 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. The ones less
/* 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 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
+# define _CC_IDFIRST 17
+# define _CC_CHARNAME_CONT 18
+# define _CC_NONLATIN1_FOLD 19
+# define _CC_NONLATIN1_SIMPLE_FOLD 20
+# define _CC_QUOTEMETA 21
+# define _CC_NON_FINAL_FOLD 22
+# define _CC_IS_IN_SOME_FOLD 23
+# define _CC_MNEMONIC_CNTRL 24
+/* Unused: 25-31
* 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
# define isALPHANUMERIC_A(c) _generic_isCC_A(c, _CC_ALPHANUMERIC)
# define isBLANK_A(c) _generic_isCC_A(c, _CC_BLANK)
# define isCNTRL_A(c) _generic_isCC_A(c, _CC_CNTRL)
-# define isDIGIT_A(c) _generic_isCC(c, _CC_DIGIT)
+# define isDIGIT_A(c) _generic_isCC(c, _CC_DIGIT) /* No non-ASCII digits */
# define isGRAPH_A(c) _generic_isCC_A(c, _CC_GRAPH)
# define isLOWER_A(c) _generic_isCC_A(c, _CC_LOWER)
# define isPRINT_A(c) _generic_isCC_A(c, _CC_PRINT)
# define isSPACE_A(c) _generic_isCC_A(c, _CC_SPACE)
# define isUPPER_A(c) _generic_isCC_A(c, _CC_UPPER)
# define isWORDCHAR_A(c) _generic_isCC_A(c, _CC_WORDCHAR)
-# define isXDIGIT_A(c) _generic_isCC(c, _CC_XDIGIT)
+# define isXDIGIT_A(c) _generic_isCC(c, _CC_XDIGIT) /* No non-ASCII xdigits */
# define isIDFIRST_A(c) _generic_isCC_A(c, _CC_IDFIRST)
# define isALPHA_L1(c) _generic_isCC(c, _CC_ALPHA)
# define isALPHANUMERIC_L1(c) _generic_isCC(c, _CC_ALPHANUMERIC)
# define isWORDCHAR_L1(c) _generic_isCC(c, _CC_WORDCHAR)
# define isIDFIRST_L1(c) _generic_isCC(c, _CC_IDFIRST)
- /* Either participates in a fold with a character above 255, or is a
- * multi-char fold */
+# ifdef EBCDIC
+# define isASCII(c) _generic_isCC(c, _CC_ASCII)
+# endif
+
+ /* Participates in a single-character fold with a character above 255 */
+# define _HAS_NONLATIN1_SIMPLE_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_SIMPLE_FOLD)))
+
+ /* Like the above, but also can be part of 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) (c)] & _CC_mask(_CC_NONLATIN1_FOLD)))
# define _isQUOTEMETA(c) _generic_isCC(c, _CC_QUOTEMETA)
_generic_isCC(c, _CC_NON_FINAL_FOLD)
# define _IS_IN_SOME_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
_generic_isCC(c, _CC_IS_IN_SOME_FOLD)
-#else /* else we don't have perl.h */
+# define _IS_MNEMONIC_CNTRL_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
+ _generic_isCC(c, _CC_MNEMONIC_CNTRL)
+#else /* else we don't have perl.h H_PERL */
/* 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. */
-# ifdef EBCDIC
- /* Use the native functions. They likely will return false for all
- * non-ASCII values, but this makes sure */
-# define isLOWER_A(c) (isASCII(c) && islower(c))
-# define isPRINT_A(c) (isASCII(c) && isprint(c))
-# define isUPPER_A(c) (isASCII(c) && isupper(c))
-# else /* ASCII platform. These are coded based on first principals */
+ * to it. Most are coded based on first principals. First some ones common
+ * to both ASCII and EBCDIC */
+# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
+# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
+# define isSPACE_A(c) (isBLANK_A(c) \
+ || (c) == '\n' \
+ || (c) == '\r' \
+ || (c) == '\v' \
+ || (c) == '\f')
+# ifdef EBCDIC /* There are gaps between 'i' and 'j'; 'r' and 's'. Same
+ for uppercase. This is ordered to exclude most things
+ early */
+# define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z' \
+ && ((c) <= 'i' \
+ || ((c) >= 'j' && (c) <= 'r') \
+ || (c) >= 's'))
+# define isUPPER_A(c) ((c) >= 'A' && (c) <= 'Z' \
+ && ((c) <= 'I' \
+ || ((c) >= 'J' && (c) <= 'R') \
+ || (c) >= 'S'))
+# else /* ASCII platform. */
# define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z')
-# define isPRINT_A(c) (((c) >= 32 && (c) < 127))
# define isUPPER_A(c) ((c) <= 'Z' && (c) >= 'A')
-# endif /* Below are common definitions for ASCII and non-ASCII */
+# endif
+
+ /* Some more ASCII, non-ASCII common definitions */
# 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) (isASCII(c) && (! isPRINT_A(c)))
-# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
-# define isGRAPH_A(c) (isPRINT_A(c) && (c) != ' ')
-# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
-# define isPUNCT_A(c) (isGRAPH_A(c) && (! isALPHANUMERIC_A(c)))
-# define isSPACE_A(c) ((c) == ' ' \
- || (c) == '\t' \
- || (c) == '\n' \
- || (c) == '\r' \
- || (c) == '\v' \
- || (c) == '\f')
# define isWORDCHAR_A(c) (isALPHANUMERIC_A(c) || (c) == '_')
-# define isXDIGIT_A(c) (isDIGIT_A(c) \
- || ((c) >= 'a' && (c) <= 'f') \
+# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
+# define isXDIGIT_A(c) (isDIGIT_A(c) \
+ || ((c) >= 'a' && (c) <= 'f') \
|| ((c) <= 'F' && (c) >= 'A'))
+# ifdef EBCDIC
+# define isPUNCT_A(c) ((c) == '-' || (c) == '!' || (c) == '"' \
+ || (c) == '#' || (c) == '$' || (c) == '%' \
+ || (c) == '&' || (c) == '\'' || (c) == '(' \
+ || (c) == ')' || (c) == '*' || (c) == '+' \
+ || (c) == ',' || (c) == '.' || (c) == '/' \
+ || (c) == ':' || (c) == ';' || (c) == '<' \
+ || (c) == '=' || (c) == '>' || (c) == '?' \
+ || (c) == '@' || (c) == '[' || (c) == '\\' \
+ || (c) == ']' || (c) == '^' || (c) == '_' \
+ || (c) == '`' || (c) == '{' || (c) == '|' \
+ || (c) == '}' || (c) == '~')
+# define isGRAPH_A(c) (isALPHANUMERIC_A(c) || isPUNCT_A(c))
+# define isPRINT_A(c) (isGRAPH_A(c) || (c) == ' ')
+
+# ifdef QUESTION_MARK_CTRL
+# define _isQMC(c) ((c) == QUESTION_MARK_CTRL)
+# else
+# define _isQMC(c) 0
+# endif
+
+ /* I (khw) can't think of a way to define all the ASCII controls
+ * without resorting to a libc (locale-sensitive) call. But we know
+ * that all controls but the question-mark one are in the range 0-0x3f.
+ * This makes sure that all the controls that have names are included,
+ * and all controls that are also considered ASCII in the locale. This
+ * may include more or fewer than what it actually should, but the
+ * wrong ones are less-important controls, so likely won't impact
+ * things (keep in mind that this is compiled only if perl.h isn't
+ * available). The question mark control is included if available */
+# define isCNTRL_A(c) (((c) < 0x40 && isascii(c)) \
+ || (c) == '\0' || (c) == '\a' || (c) == '\b' \
+ || (c) == '\f' || (c) == '\n' || (c) == '\r' \
+ || (c) == '\t' || (c) == '\v' || _isQMC(c))
+
+# define isASCII(c) (isCNTRL_A(c) || isPRINT_A(c))
+# else /* ASCII platform; things are simpler, and isASCII has already
+ been defined */
+# define isGRAPH_A(c) (((c) > ' ' && (c) < 127))
+# define isPRINT_A(c) (isGRAPH_A(c) || (c) == ' ')
+# define isPUNCT_A(c) (isGRAPH_A(c) && (! isALPHANUMERIC_A(c)))
+# define isCNTRL_A(c) (isASCII(c) && (! isPRINT_A(c)))
+# endif
+
/* The _L1 macros may be unnecessary for the utilities; I (khw) added them
- * during debugging, and it seems best to keep them. */
+ * during debugging, and it seems best to keep them. We may be called
+ * without NATIVE_TO_LATIN1 being defined. On ASCII platforms, it doesn't
+ * do anything anyway, so make it not a problem */
+# if ! defined(EBCDIC) && ! defined(NATIVE_TO_LATIN1)
+# define NATIVE_TO_LATIN1(ch) (ch)
+# endif
# define isPSXSPC_A(c) isSPACE_A(c) /* XXX Assumes SPACE matches '\v' */
# define isALPHA_L1(c) (isUPPER_L1(c) || isLOWER_L1(c))
# define isALPHANUMERIC_L1(c) (isALPHA_L1(c) || isDIGIT_A(c))
/* And these aren't accurate at all. They are useful only for above
* Latin1, which utilities and bootstrapping don't deal with */
# define _IS_NON_FINAL_FOLD_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) 0
+# define _HAS_NONLATIN1_SIMPLE_FOLD_CLOSURE_ONLY_FOR_USE_BY_REGCOMP_DOT_C_AND_REGEXEC_DOT_C(c) 0
# define _HAS_NONLATIN1_FOLD_CLOSURE_ONLY_FOR_USE_BY_REGCOMP_DOT_C_AND_REGEXEC_DOT_C(c) 0
/* Many of the macros later in this file are defined in terms of these. By
(FITS_IN_8_BITS(c) && S_bootstrap_ctype((U8) (c), (classnum), TRUE))
# define _generic_isCC_A(c, classnum) \
(FITS_IN_8_BITS(c) && S_bootstrap_ctype((U8) (c), (classnum), FALSE))
-#endif /* End of no perl.h */
+#endif /* End of no perl.h H_PERL */
#define isALPHANUMERIC(c) isALPHANUMERIC_A(c)
#define isALPHA(c) isALPHA_A(c)
+#define isASCII_A(c) isASCII(c)
+#define isASCII_L1(c) isASCII(c)
#define isBLANK(c) isBLANK_A(c)
#define isCNTRL(c) isCNTRL_A(c)
#define isDIGIT(c) isDIGIT_A(c)
? (c) \
: (IN_UTF8_CTYPE_LOCALE) \
? PL_latin1_lc[ (U8) (c) ] \
- : function((cast)(c)))
+ : (cast)function((cast)(c)))
/* Note that the result can be larger than a byte in a UTF-8 locale. It
* returns a single value, so can't adequately return the upper case of LATIN
(! FITS_IN_8_BITS(c) \
? (c) \
: ((! IN_UTF8_CTYPE_LOCALE) \
- ? function((cast)(c)) \
+ ? (cast)function((cast)(c)) \
: ((((U8)(c)) == MICRO_SIGN) \
? GREEK_CAPITAL_LETTER_MU \
: ((((U8)(c)) == LATIN_SMALL_LETTER_Y_WITH_DIAERESIS) \
_generic_toLOWER_LC(c, function, cast)))
/* Use the libc versions for these if available. */
-#if defined(HAS_ISASCII) && ! defined(USE_NEXT_CTYPE)
+#if defined(HAS_ISASCII)
# define isASCII_LC(c) (FITS_IN_8_BITS(c) && isascii( (U8) (c)))
#else
# define isASCII_LC(c) isASCII(c)
#endif
-#if defined(HAS_ISBLANK) && ! defined(USE_NEXT_CTYPE)
+#if defined(HAS_ISBLANK)
# define isBLANK_LC(c) _generic_LC(c, _CC_BLANK, isblank)
#else /* Unlike isASCII, varies if in a UTF-8 locale */
-# define isBLANK_LC(c) (IN_UTF8_CTYPE_LOCALE) ? isBLANK_L1(c) : isBLANK(c)
+# define isBLANK_LC(c) ((IN_UTF8_CTYPE_LOCALE) ? isBLANK_L1(c) : isBLANK(c))
#endif
-#ifdef USE_NEXT_CTYPE /* NeXT computers */
-
-# define _LC_CAST unsigned int /* Needed by _generic_LC. NeXT functions
- use this as their input type */
-
-# define isALPHA_LC(c) _generic_LC(c, _CC_ALPHA, NXIsAlpha)
-# define isALPHANUMERIC_LC(c) _generic_LC(c, _CC_ALPHANUMERIC, NXIsAlNum)
-# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, NXIsCntrl)
-# define isDIGIT_LC(c) _generic_LC(c, _CC_DIGIT, NXIsDigit)
-# define isGRAPH_LC(c) _generic_LC(c, _CC_GRAPH, NXIsGraph)
-# define isIDFIRST_LC(c) _generic_LC_underscore(c, _CC_IDFIRST, NXIsAlpha)
-# define isLOWER_LC(c) _generic_LC(c, _CC_LOWER, NXIsLower)
-# define isPRINT_LC(c) _generic_LC(c, _CC_PRINT, NXIsPrint)
-# define isPUNCT_LC(c) _generic_LC(c, _CC_PUNCT, NXIsPunct)
-# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, NXIsSpace)
-# define isUPPER_LC(c) _generic_LC(c, _CC_UPPER, NXIsUpper)
-# define isWORDCHAR_LC(c) _generic_LC_underscore(c, _CC_WORDCHAR, NXIsAlNum)
-# define isXDIGIT_LC(c) _generic_LC(c, _CC_XDIGIT, NXIsXdigit)
-
-# define toLOWER_LC(c) _generic_toLOWER_LC((c), NXToLower, unsigned int)
-# define toUPPER_LC(c) _generic_toUPPER_LC((c), NXToUpper, unsigned int)
-# define toFOLD_LC(c) _generic_toFOLD_LC((c), NXToLower, unsigned int)
-
-#else /* !USE_NEXT_CTYPE */
-
-# define _LC_CAST U8
-
-# if defined(CTYPE256) || (!defined(isascii) && !defined(HAS_ISASCII))
+#define _LC_CAST U8
+
+#ifdef WIN32
+ /* The Windows functions don't bother to follow the POSIX standard, which
+ * for example says that something can't both be a printable and a control.
+ * But Windows treats the \t control as a printable, and does such things
+ * as making superscripts into both digits and punctuation. This tames
+ * these flaws by assuming that the definitions of both controls and space
+ * are correct, and then making sure that other definitions don't have
+ * weirdnesses, by making sure that isalnum() isn't also ispunct(), etc.
+ * Not all possible weirdnesses are checked for, just the ones that were
+ * detected on actual Microsoft code pages */
+
+# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
+# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
+
+# define isALPHA_LC(c) (_generic_LC(c, _CC_ALPHA, isalpha) && isALPHANUMERIC_LC(c))
+# define isALPHANUMERIC_LC(c) (_generic_LC(c, _CC_ALPHANUMERIC, isalnum) && ! isPUNCT_LC(c))
+# define isDIGIT_LC(c) (_generic_LC(c, _CC_DIGIT, isdigit) && isALPHANUMERIC_LC(c))
+# define isGRAPH_LC(c) (_generic_LC(c, _CC_GRAPH, isgraph) && isPRINT_LC(c))
+# define isIDFIRST_LC(c) (((c) == '_') || (_generic_LC(c, _CC_IDFIRST, isalpha) && ! isPUNCT_LC(c)))
+# define isLOWER_LC(c) (_generic_LC(c, _CC_LOWER, islower) && isALPHA_LC(c))
+# define isPRINT_LC(c) (_generic_LC(c, _CC_PRINT, isprint) && ! isCNTRL_LC(c))
+# define isPUNCT_LC(c) (_generic_LC(c, _CC_PUNCT, ispunct) && ! isCNTRL_LC(c))
+# define isUPPER_LC(c) (_generic_LC(c, _CC_UPPER, isupper) && isALPHA_LC(c))
+# define isWORDCHAR_LC(c) (((c) == '_') || isALPHANUMERIC_LC(c))
+# define isXDIGIT_LC(c) (_generic_LC(c, _CC_XDIGIT, isxdigit) && isALPHANUMERIC_LC(c))
+
+# define toLOWER_LC(c) _generic_toLOWER_LC((c), tolower, U8)
+# define toUPPER_LC(c) _generic_toUPPER_LC((c), toupper, U8)
+# define toFOLD_LC(c) _generic_toFOLD_LC((c), tolower, U8)
+
+#elif defined(CTYPE256) || (!defined(isascii) && !defined(HAS_ISASCII))
/* For most other platforms */
-# define isALPHA_LC(c) _generic_LC(c, _CC_ALPHA, isalpha)
-# define isALPHANUMERIC_LC(c) _generic_LC(c, _CC_ALPHANUMERIC, isalnum)
-# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
-# define isDIGIT_LC(c) _generic_LC(c, _CC_DIGIT, isdigit)
-# define isGRAPH_LC(c) _generic_LC(c, _CC_GRAPH, isgraph)
-# define isIDFIRST_LC(c) _generic_LC_underscore(c, _CC_IDFIRST, isalpha)
-# define isLOWER_LC(c) _generic_LC(c, _CC_LOWER, islower)
-# define isPRINT_LC(c) _generic_LC(c, _CC_PRINT, isprint)
-# define isPUNCT_LC(c) _generic_LC(c, _CC_PUNCT, ispunct)
-# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
-# define isUPPER_LC(c) _generic_LC(c, _CC_UPPER, isupper)
-# define isWORDCHAR_LC(c) _generic_LC_underscore(c, _CC_WORDCHAR, isalnum)
-# define isXDIGIT_LC(c) _generic_LC(c, _CC_XDIGIT, isxdigit)
-
-
-# define toLOWER_LC(c) _generic_toLOWER_LC((c), tolower, U8)
-# define toUPPER_LC(c) _generic_toUPPER_LC((c), toupper, U8)
-# define toFOLD_LC(c) _generic_toFOLD_LC((c), tolower, U8)
-
-# else /* The final fallback position */
-
-# define isALPHA_LC(c) (isascii(c) && isalpha(c))
-# define isALPHANUMERIC_LC(c) (isascii(c) && isalnum(c))
-# define isCNTRL_LC(c) (isascii(c) && iscntrl(c))
-# define isDIGIT_LC(c) (isascii(c) && isdigit(c))
-# define isGRAPH_LC(c) (isascii(c) && isgraph(c))
-# define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_'))
-# define isLOWER_LC(c) (isascii(c) && islower(c))
-# define isPRINT_LC(c) (isascii(c) && isprint(c))
-# define isPUNCT_LC(c) (isascii(c) && ispunct(c))
-# define isSPACE_LC(c) (isascii(c) && isspace(c))
-# define isUPPER_LC(c) (isascii(c) && isupper(c))
-# define isWORDCHAR_LC(c) (isascii(c) && (isalnum(c) || (c) == '_'))
-# define isXDIGIT_LC(c) (isascii(c) && isxdigit(c))
-
-# define toLOWER_LC(c) (isascii(c) ? tolower(c) : (c))
-# define toUPPER_LC(c) (isascii(c) ? toupper(c) : (c))
-# define toFOLD_LC(c) (isascii(c) ? tolower(c) : (c))
+# define isALPHA_LC(c) _generic_LC(c, _CC_ALPHA, isalpha)
+# define isALPHANUMERIC_LC(c) _generic_LC(c, _CC_ALPHANUMERIC, isalnum)
+# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
+# define isDIGIT_LC(c) _generic_LC(c, _CC_DIGIT, isdigit)
+# define isGRAPH_LC(c) _generic_LC(c, _CC_GRAPH, isgraph)
+# define isIDFIRST_LC(c) _generic_LC_underscore(c, _CC_IDFIRST, isalpha)
+# define isLOWER_LC(c) _generic_LC(c, _CC_LOWER, islower)
+# define isPRINT_LC(c) _generic_LC(c, _CC_PRINT, isprint)
+# define isPUNCT_LC(c) _generic_LC(c, _CC_PUNCT, ispunct)
+# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
+# define isUPPER_LC(c) _generic_LC(c, _CC_UPPER, isupper)
+# define isWORDCHAR_LC(c) _generic_LC_underscore(c, _CC_WORDCHAR, isalnum)
+# define isXDIGIT_LC(c) _generic_LC(c, _CC_XDIGIT, isxdigit)
+
+
+# define toLOWER_LC(c) _generic_toLOWER_LC((c), tolower, U8)
+# define toUPPER_LC(c) _generic_toUPPER_LC((c), toupper, U8)
+# define toFOLD_LC(c) _generic_toFOLD_LC((c), tolower, U8)
+
+#else /* The final fallback position */
+
+# define isALPHA_LC(c) (isascii(c) && isalpha(c))
+# define isALPHANUMERIC_LC(c) (isascii(c) && isalnum(c))
+# define isCNTRL_LC(c) (isascii(c) && iscntrl(c))
+# define isDIGIT_LC(c) (isascii(c) && isdigit(c))
+# define isGRAPH_LC(c) (isascii(c) && isgraph(c))
+# define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_'))
+# define isLOWER_LC(c) (isascii(c) && islower(c))
+# define isPRINT_LC(c) (isascii(c) && isprint(c))
+# define isPUNCT_LC(c) (isascii(c) && ispunct(c))
+# define isSPACE_LC(c) (isascii(c) && isspace(c))
+# define isUPPER_LC(c) (isascii(c) && isupper(c))
+# define isWORDCHAR_LC(c) (isascii(c) && (isalnum(c) || (c) == '_'))
+# define isXDIGIT_LC(c) (isascii(c) && isxdigit(c))
+
+# define toLOWER_LC(c) (isascii(c) ? tolower(c) : (c))
+# define toUPPER_LC(c) (isascii(c) ? toupper(c) : (c))
+# define toFOLD_LC(c) (isascii(c) ? tolower(c) : (c))
-# endif
-#endif /* USE_NEXT_CTYPE */
+#endif
#define isIDCONT(c) isWORDCHAR(c)
#define isIDCONT_A(c) isWORDCHAR_A(c)
#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(p) isCNTRL_L1(*(p))
#else
# define isCNTRL_utf8(p) _generic_utf8(_CC_CNTRL, p, 0)
#endif
* the outlier from the block that contains the other controls, just like
* toCTRL('?') on ASCII yields DEL, the control that is the outlier from the C0
* block. If it weren't special cased, it would yield a non-control.
- * The conversion works both ways, so CTRL('D') is 4, and CTRL(4) is D, etc. */
+ * The conversion works both ways, so toCTRL('D') is 4, and toCTRL(4) is D,
+ * etc. */
#ifndef EBCDIC
-# define toCTRL(c) (toUPPER(c) ^ 64)
+# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) toUPPER(c) ^ 64)
#else
-# define toCTRL(c) ((isPRINT_A(c)) \
- ? UNLIKELY((c) == '?') \
- ? QUESTION_MARK_CTRL \
- : (NATIVE_TO_LATIN1(toUPPER(c)) ^ 64) \
- : UNLIKELY((c) == QUESTION_MARK_CTRL) \
- ? ((c) == '?') \
- : (LATIN1_TO_NATIVE((c) ^ 64)))
+# define toCTRL(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
+ ((isPRINT_A(c)) \
+ ? (UNLIKELY((c) == '?') \
+ ? QUESTION_MARK_CTRL \
+ : (NATIVE_TO_LATIN1(toUPPER(c)) ^ 64)) \
+ : (UNLIKELY((c) == QUESTION_MARK_CTRL) \
+ ? '?' \
+ : (LATIN1_TO_NATIVE((c) ^ 64)))))
#endif
/* Line numbers are unsigned, 32 bits. */
* both ASCII and EBCDIC the last 3 bits of the octal digits range from 0-7. */
#define OCTAL_VALUE(c) (__ASSERT_(isOCTAL(c)) (7 & (c)))
+/* Efficiently returns a boolean as to if two native characters are equivalent
+ * case-insenstively. At least one of the characters must be one of [A-Za-z];
+ * the ALPHA in the name is to remind you of that. This is asserted() in
+ * DEBUGGING builds. Because [A-Za-z] are invariant under UTF-8, this macro
+ * works (on valid input) for both non- and UTF-8-encoded bytes.
+ *
+ * When one of the inputs is a compile-time constant and gets folded by the
+ * compiler, this reduces to an AND and a TEST. On both EBCDIC and ASCII
+ * machines, 'A' and 'a' differ by a single bit; the same with the upper and
+ * lower case of all other ASCII-range alphabetics. On ASCII platforms, they
+ * are 32 apart; on EBCDIC, they are 64. At compile time, this uses an
+ * exclusive 'or' to find that bit and then inverts it to form a mask, with
+ * just a single 0, in the bit position where the upper- and lowercase differ.
+ * */
+#define isALPHA_FOLD_EQ(c1, c2) \
+ (__ASSERT_(isALPHA_A(c1) || isALPHA_A(c2)) \
+ ((c1) & ~('A' ^ 'a')) == ((c2) & ~('A' ^ 'a')))
+#define isALPHA_FOLD_NE(c1, c2) (! isALPHA_FOLD_EQ((c1), (c2)))
+
/*
=head1 Memory Management
https://perl5.git.perl.org / perl5.git / blobdiff