# define Null(type) ((type)NULL)
/*
-=head1 Handy Values
-
-=for apidoc AmU||Nullch
+=for apidoc_section $string
+=for apidoc AmnU||Nullch
Null character pointer. (No longer available when C<PERL_CORE> is
defined.)
-=for apidoc AmU||Nullsv
+=for apidoc_section $SV
+=for apidoc AmnU||Nullsv
Null SV pointer. (No longer available when C<PERL_CORE> is defined.)
=cut
+
+Below are signatures of functions from config.h which can't easily be gleaned
+from it, and are very unlikely to change
+
+=for apidoc_section $signals
+=for apidoc Am|int|Sigsetjmp|jmp_buf env|int savesigs
+=for apidoc Am|void|Siglongjmp|jmp_buf env|int val
+
+=for apidoc_section $filesystem
+=for apidoc Am|void *|FILE_ptr|FILE * f
+=for apidoc Am|Size_t|FILE_cnt|FILE * f
+=for apidoc Am|void *|FILE_base|FILE * f
+=for apidoc Am|Size_t|FILE_bufsiz|FILE *f
+
+=for apidoc_section $string
+=for apidoc Amu|token|CAT2|token x|token y
+=for apidoc Amu|string|STRINGIFY|token x
+
+=for apidoc_section $numeric
+=for apidoc Am|double|Drand01
+=for apidoc Am|void|seedDrand01|Rand_seed_t x
+=for apidoc Am|char *|Gconvert|double x|Size_t n|bool t|char * b
+
+=cut
*/
# define Nullch Null(char*)
#define TRUE (1)
#define FALSE (0)
-/* The MUTABLE_*() macros cast pointers to the types shown, in such a way
- * (compiler permitting) that casting away const-ness will give a warning;
- * e.g.:
- *
- * const SV *sv = ...;
- * AV *av1 = (AV*)sv; <== BAD: the const has been silently cast away
- * AV *av2 = MUTABLE_AV(sv); <== GOOD: it may warn
+/*
+=for apidoc_section $SV
+=for apidoc Am|void *|MUTABLE_PTR|void * p
+=for apidoc_item |AV *|MUTABLE_AV|AV * p
+=for apidoc_item |CV *|MUTABLE_CV|CV * p
+=for apidoc_item |GV *|MUTABLE_GV|GV * p
+=for apidoc_item |HV *|MUTABLE_HV|HV * p
+=for apidoc_item |IO *|MUTABLE_IO|IO * p
+=for apidoc_item |SV *|MUTABLE_SV|SV * p
+
+The C<MUTABLE_I<*>>() macros cast pointers to the types shown, in such a way
+(compiler permitting) that casting away const-ness will give a warning;
+e.g.:
+
+ const SV *sv = ...;
+ AV *av1 = (AV*)sv; <== BAD: the const has been silently
+ cast away
+ AV *av2 = MUTABLE_AV(sv); <== GOOD: it may warn
+
+C<MUTABLE_PTR> is the base macro used to derive new casts. The other
+already-built-in ones return pointers to what their names indicate.
+
+=cut
*/
-#if defined(__GNUC__) && !defined(PERL_GCC_BRACE_GROUPS_FORBIDDEN)
-# define MUTABLE_PTR(p) ({ void *_p = (p); _p; })
+#if defined(PERL_USE_GCC_BRACE_GROUPS)
+# define MUTABLE_PTR(p) ({ void *p_ = (p); p_; })
#else
# define MUTABLE_PTR(p) ((void *) (p))
#endif
# define HAS_BOOL 1
#endif
-/* 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 */
+/*
+=for apidoc_section $casting
+=for apidoc Am|bool|cBOOL|bool expr
+
+Cast-to-bool. A simple S<C<(bool) I<expr>>> cast may not do the right thing:
+if C<bool> is defined as C<char>, for example, then the cast from C<int> is
+implementation-defined.
+
+C<(bool)!!(cbool)> in a ternary triggers a bug in xlc on AIX
+
+=cut
+*/
#define cBOOL(cbool) ((cbool) ? (bool)1 : (bool)0)
/* Try to figure out __func__ or __FUNCTION__ equivalent, if any.
* XXX Similarly, a Configure probe for __FILE__ and __LINE__ is needed. */
#if (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L) || (defined(__SUNPRO_C)) /* C99 or close enough. */
# define FUNCTION__ __func__
-#elif (defined(USING_MSVC6)) || /* MSVC6 has neither __func__ nor __FUNCTION and no good workarounds, either. */ \
- (defined(__DECC_VER)) /* Tru64 or VMS, and strict C89 being used, but not modern enough cc (in Tur64, -c99 not known, only -std1). */
+#elif (defined(__DECC_VER)) /* Tru64 or VMS, and strict C89 being used, but not modern enough cc (in Tur64, -c99 not known, only -std1). */
# define FUNCTION__ ""
#else
# define FUNCTION__ __FUNCTION__ /* Common extension. */
typedef I32TYPE I32;
typedef U32TYPE U32;
-#ifdef HAS_QUAD
+#ifdef QUADKIND
typedef I64TYPE I64;
typedef U64TYPE U64;
#endif
-/* INT64_C/UINT64_C are C99 from <stdint.h> (so they will not be
- * available in strict C89 mode), but they are nice, so let's define
- * them if necessary. */
-#if defined(HAS_QUAD)
-# undef PeRl_INT64_C
-# undef PeRl_UINT64_C
-/* Prefer the native integer types (int and long) over long long
- * (which is not C89) and Win32-specific __int64. */
-# if QUADKIND == QUAD_IS_INT && INTSIZE == 8
-# define PeRl_INT64_C(c) (c)
-# define PeRl_UINT64_C(c) CAT2(c,U)
-# endif
-# if QUADKIND == QUAD_IS_LONG && LONGSIZE == 8
-# define PeRl_INT64_C(c) CAT2(c,L)
-# define PeRl_UINT64_C(c) CAT2(c,UL)
-# endif
-# if QUADKIND == QUAD_IS_LONG_LONG && defined(HAS_LONG_LONG)
-# define PeRl_INT64_C(c) CAT2(c,LL)
-# define PeRl_UINT64_C(c) CAT2(c,ULL)
-# endif
-# if QUADKIND == QUAD_IS___INT64
-# define PeRl_INT64_C(c) CAT2(c,I64)
-# define PeRl_UINT64_C(c) CAT2(c,UI64)
-# endif
-# ifndef PeRl_INT64_C
-# define PeRl_INT64_C(c) ((I64)(c)) /* last resort */
-# define PeRl_UINT64_C(c) ((U64)(c))
-# endif
-/* In OS X the INT64_C/UINT64_C are defined with LL/ULL, which will
- * not fly with C89-pedantic gcc, so let's undefine them first so that
- * we can redefine them with our native integer preferring versions. */
-# if defined(PERL_DARWIN) && defined(PERL_GCC_PEDANTIC)
-# undef INT64_C
-# undef UINT64_C
-# endif
-# ifndef INT64_C
-# define INT64_C(c) PeRl_INT64_C(c)
-# endif
-# ifndef UINT64_C
-# define UINT64_C(c) PeRl_UINT64_C(c)
-# endif
-#endif
-
-#if defined(UINT8_MAX) && defined(INT16_MAX) && defined(INT32_MAX)
-
/* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type.
Please search CHAR_MAX in perl.h for further details. */
-#define U8_MAX UINT8_MAX
-#define U8_MIN UINT8_MIN
-
-#define I16_MAX INT16_MAX
-#define I16_MIN INT16_MIN
-#define U16_MAX UINT16_MAX
-#define U16_MIN UINT16_MIN
-
-#define I32_MAX INT32_MAX
-#define I32_MIN INT32_MIN
-#ifndef UINT32_MAX_BROKEN /* e.g. HP-UX with gcc messes this up */
-# define U32_MAX UINT32_MAX
+#ifdef UINT8_MAX
+# define U8_MAX UINT8_MAX
#else
-# define U32_MAX 4294967295U
+# define U8_MAX PERL_UCHAR_MAX
#endif
-#define U32_MIN UINT32_MIN
-
+#ifdef UINT8_MIN
+# define U8_MIN UINT8_MIN
#else
+# define U8_MIN PERL_UCHAR_MIN
+#endif
-/* I8_MAX and I8_MIN constants are not defined, as I8 is an ambiguous type.
- Please search CHAR_MAX in perl.h for further details. */
-#define U8_MAX PERL_UCHAR_MAX
-#define U8_MIN PERL_UCHAR_MIN
-
-#define I16_MAX PERL_SHORT_MAX
-#define I16_MIN PERL_SHORT_MIN
-#define U16_MAX PERL_USHORT_MAX
-#define U16_MIN PERL_USHORT_MIN
-
-#if LONGSIZE > 4
-# define I32_MAX PERL_INT_MAX
-# define I32_MIN PERL_INT_MIN
-# define U32_MAX PERL_UINT_MAX
-# define U32_MIN PERL_UINT_MIN
+#ifdef INT16_MAX
+# define I16_MAX INT16_MAX
#else
-# define I32_MAX PERL_LONG_MAX
-# define I32_MIN PERL_LONG_MIN
-# define U32_MAX PERL_ULONG_MAX
-# define U32_MIN PERL_ULONG_MIN
+# define I16_MAX PERL_SHORT_MAX
+#endif
+#ifdef INT16_MIN
+# define I16_MIN INT16_MIN
+#else
+# define I16_MIN PERL_SHORT_MIN
+#endif
+#ifdef UINT16_MAX
+# define U16_MAX UINT16_MAX
+#else
+# define U16_MAX PERL_USHORT_MAX
+#endif
+#ifdef UINT16_MIN
+# define U16_MIN UINT16_MIN
+#else
+# define U16_MIN PERL_USHORT_MIN
#endif
+#ifdef INT32_MAX
+# define I32_MAX INT32_MAX
+#elif LONGSIZE > 4
+# define I32_MAX PERL_INT_MAX
+#else
+# define I32_MAX PERL_LONG_MAX
#endif
+#ifdef INT32_MIN
+# define I32_MIN INT32_MIN
+#elif LONGSIZE > 4
+# define I32_MIN PERL_INT_MIN
+#else
+# define I32_MIN PERL_LONG_MIN
+#endif
+#ifdef UINT32_MAX
+# ifndef UINT32_MAX_BROKEN /* e.g. HP-UX with gcc messes this up */
+# define U32_MAX UINT_MAX
+# else
+# define U32_MAX 4294967295U
+# endif
+#elif LONGSIZE > 4
+# define U32_MAX PERL_UINT_MAX
+#else
+# define U32_MAX PERL_ULONG_MAX
+#endif
+#ifdef UINT32_MIN
+# define U32_MIN UINT32_MIN
+#elif LONGSIZE > 4
+# define U32_MIN PERL_UINT_MIN
+#else
+# define U32_MIN PERL_ULONG_MIN
+#endif
+
+/*
+=for apidoc_section $integer
+=for apidoc Ay|| PERL_INT_FAST8_T
+=for apidoc_item PERL_INT_FAST16_T
+=for apidoc_item PERL_UINT_FAST8_T
+=for apidoc_item PERL_UINT_FAST16_T
+
+These are equivalent to the correspondingly-named C99 typedefs on platforms
+that have those; they evaluate to C<int> and C<unsigned int> on platforms that
+don't, so that you can portably take advantage of this C99 feature.
+
+=cut
+*/
+# ifdef I_STDINT
+ typedef int_fast8_t PERL_INT_FAST8_T;
+ typedef uint_fast8_t PERL_UINT_FAST8_T;
+ typedef int_fast16_t PERL_INT_FAST16_T;
+ typedef uint_fast16_t PERL_UINT_FAST16_T;
+# else
+ typedef int PERL_INT_FAST8_T;
+ typedef unsigned int PERL_UINT_FAST8_T;
+ typedef int PERL_INT_FAST16_T;
+ typedef unsigned int PERL_UINT_FAST16_T;
+# endif
/* log(2) (i.e., log base 10 of 2) is pretty close to 0.30103, just in case
- * anyone is grepping for it */
+ * anyone is grepping for it. So BIT_DIGITS gives the number of decimal digits
+ * required to represent any possible unsigned number containing N bits.
+ * TYPE_DIGITS gives the number of decimal digits required to represent any
+ * possible unsigned number of type T. */
#define BIT_DIGITS(N) (((N)*146)/485 + 1) /* log10(2) =~ 146/485 */
#define TYPE_DIGITS(T) BIT_DIGITS(sizeof(T) * 8)
#define TYPE_CHARS(T) (TYPE_DIGITS(T) + 2) /* sign, NUL */
# endif
#endif
-/* This is a helper macro to avoid preprocessor issues, replaced by nothing
- * unless under DEBUGGING, where it expands to an assert of its argument,
- * followed by a comma (hence the comma operator). If we just used a straight
- * assert(), we would get a comma with nothing before it when not DEBUGGING.
- *
- * We also use empty definition under Coverity since the __ASSERT__
- * checks often check for things that Really Cannot Happen, and Coverity
- * detects that and gets all excited. */
+/* Returns a boolean as to whether the input unsigned number is a power of 2
+ * (2**0, 2**1, etc). In other words if it has just a single bit set.
+ * If not, subtracting 1 would leave the uppermost bit set, so the & would
+ * yield non-zero */
+#if defined(PERL_CORE) || defined(PERL_EXT)
+# define isPOWER_OF_2(n) ((n) && ((n) & ((n)-1)) == 0)
+#endif
+
+/* Returns a mask with the lowest n bits set */
+#define nBIT_MASK(n) ((UINTMAX_C(1) << (n)) - 1)
+
+/* The largest unsigned number that will fit into n bits */
+#define nBIT_UMAX(n) nBIT_MASK(n)
+
+/*
+=for apidoc_section $directives
+=for apidoc Am||__ASSERT_|bool expr
+
+This is a helper macro to avoid preprocessor issues, replaced by nothing
+unless under DEBUGGING, where it expands to an assert of its argument,
+followed by a comma (hence the comma operator). If we just used a straight
+assert(), we would get a comma with nothing before it when not DEBUGGING.
+
+=cut
-#if defined(DEBUGGING) && !defined(__COVERITY__)
+We also use empty definition under Coverity since the __ASSERT__
+checks often check for things that Really Cannot Happen, and Coverity
+detects that and gets all excited. */
+
+#if defined(DEBUGGING) && !defined(__COVERITY__) \
+ && ! defined(PERL_SMALL_MACRO_BUFFER)
# define __ASSERT_(statement) assert(statement),
#else
# define __ASSERT_(statement)
#endif
/*
-=head1 SV-Body Allocation
+=for apidoc_section $SV
-=for apidoc Ama|SV*|newSVpvs|"literal string" s
+=for apidoc Ama|SV*|newSVpvs|"literal string"
Like C<newSVpvn>, but takes a literal string instead of a
string/length pair.
-=for apidoc Ama|SV*|newSVpvs_flags|"literal string" s|U32 flags
+=for apidoc Ama|SV*|newSVpvs_flags|"literal string"|U32 flags
Like C<newSVpvn_flags>, but takes a literal string instead of
a string/length pair.
-=for apidoc Ama|SV*|newSVpvs_share|"literal string" s
+=for apidoc Ama|SV*|newSVpvs_share|"literal string"
Like C<newSVpvn_share>, but takes a literal string instead of
a string/length pair and omits the hash parameter.
-=for apidoc Am|void|sv_catpvs_flags|SV* sv|"literal string" s|I32 flags
+=for apidoc Am|void|sv_catpvs_flags|SV* sv|"literal string"|I32 flags
Like C<sv_catpvn_flags>, but takes a literal string instead
of a string/length pair.
-=for apidoc Am|void|sv_catpvs_nomg|SV* sv|"literal string" s
+=for apidoc Am|void|sv_catpvs_nomg|SV* sv|"literal string"
Like C<sv_catpvn_nomg>, but takes a literal string instead of
a string/length pair.
-=for apidoc Am|void|sv_catpvs|SV* sv|"literal string" s
+=for apidoc Am|void|sv_catpvs|SV* sv|"literal string"
Like C<sv_catpvn>, but takes a literal string instead of a
string/length pair.
-=for apidoc Am|void|sv_catpvs_mg|SV* sv|"literal string" s
+=for apidoc Am|void|sv_catpvs_mg|SV* sv|"literal string"
Like C<sv_catpvn_mg>, but takes a literal string instead of a
string/length pair.
-=for apidoc Am|void|sv_setpvs|SV* sv|"literal string" s
+=for apidoc Am|void|sv_setpvs|SV* sv|"literal string"
Like C<sv_setpvn>, but takes a literal string instead of a
string/length pair.
-=for apidoc Am|void|sv_setpvs_mg|SV* sv|"literal string" s
+=for apidoc Am|void|sv_setpvs_mg|SV* sv|"literal string"
Like C<sv_setpvn_mg>, but takes a literal string instead of a
string/length pair.
-=for apidoc Am|SV *|sv_setref_pvs|"literal string" s
+=for apidoc Am|SV *|sv_setref_pvs|SV *const rv|const char *const classname|"literal string"
Like C<sv_setref_pvn>, but takes a literal string instead of
a string/length pair.
-=head1 Memory Management
+=for apidoc_section $string
-=for apidoc Ama|char*|savepvs|"literal string" s
+=for apidoc Ama|char*|savepvs|"literal string"
Like C<savepvn>, but takes a literal string instead of a
string/length pair.
-=for apidoc Ama|char*|savesharedpvs|"literal string" s
+=for apidoc Ama|char*|savesharedpvs|"literal string"
A version of C<savepvs()> which allocates the duplicate string in memory
which is shared between threads.
-=head1 GV Functions
+=for apidoc_section $GV
-=for apidoc Am|HV*|gv_stashpvs|"literal string" name|I32 create
+=for apidoc Am|HV*|gv_stashpvs|"name"|I32 create
Like C<gv_stashpvn>, but takes a literal string instead of a
string/length pair.
-=head1 Hash Manipulation Functions
+=for apidoc_section $HV
-=for apidoc Am|SV**|hv_fetchs|HV* tb|"literal string" key|I32 lval
+=for apidoc Am|SV**|hv_fetchs|HV* tb|"key"|I32 lval
Like C<hv_fetch>, but takes a literal string instead of a
string/length pair.
-=for apidoc Am|SV**|hv_stores|HV* tb|"literal string" key|NULLOK SV* val
+=for apidoc Am|SV**|hv_stores|HV* tb|"key"|SV* val
Like C<hv_store>, but takes a literal string instead of a
string/length pair
and omits the hash parameter.
-=head1 Lexer interface
+=for apidoc_section $lexer
-=for apidoc Amx|void|lex_stuff_pvs|"literal string" pv|U32 flags
+=for apidoc Amx|void|lex_stuff_pvs|"pv"|U32 flags
Like L</lex_stuff_pvn>, but takes a literal string instead of
a string/length pair.
=cut
*/
-/* concatenating with "" ensures that only literal strings are accepted as
- * argument */
-#define STR_WITH_LEN(s) ("" s ""), (sizeof(s)-1)
+/*
+=for apidoc_section $string
-/* note that STR_WITH_LEN() can't be used as argument to macros or functions
- * that under some configurations might be macros, which means that it requires
- * the full Perl_xxx(aTHX_ ...) form for any API calls where it's used.
- */
+=for apidoc Amu|pair|STR_WITH_LEN|"literal string"
+
+Returns two comma separated tokens of the input literal string, and its length.
+This is convenience macro which helps out in some API calls.
+Note that it can't be used as an argument to macros or functions that under
+some configurations might be macros, which means that it requires the full
+Perl_xxx(aTHX_ ...) form for any API calls where it's used.
+
+=cut
+*/
+
+#define STR_WITH_LEN(s) ("" s ""), (sizeof(s)-1)
/* STR_WITH_LEN() shortcuts */
#define newSVpvs(str) Perl_newSVpvn(aTHX_ STR_WITH_LEN(str))
#define savesharedpvs(str) Perl_savesharedpvn(aTHX_ STR_WITH_LEN(str))
#define gv_stashpvs(str, create) \
Perl_gv_stashpvn(aTHX_ STR_WITH_LEN(str), create)
-#define gv_fetchpvs(namebeg, add, sv_type) \
- Perl_gv_fetchpvn_flags(aTHX_ STR_WITH_LEN(namebeg), add, sv_type)
-#define gv_fetchpvn(namebeg, len, add, sv_type) \
- Perl_gv_fetchpvn_flags(aTHX_ namebeg, len, add, sv_type)
+
+#define gv_fetchpvs(namebeg, flags, sv_type) \
+ Perl_gv_fetchpvn_flags(aTHX_ STR_WITH_LEN(namebeg), flags, sv_type)
+#define gv_fetchpvn gv_fetchpvn_flags
#define sv_catxmlpvs(dsv, str, utf8) \
Perl_sv_catxmlpvn(aTHX_ dsv, STR_WITH_LEN(str), utf8)
#define get_cvs(str, flags) \
Perl_get_cvn_flags(aTHX_ STR_WITH_LEN(str), (flags))
+/* internal helpers */
+/* Transitional */
+#ifndef PERL_VERSION_MAJOR
+# define PERL_VERSION_MAJOR PERL_REVISION
+#else
+# undef PERL_REVISION /* We don't want code to be using these */
+#endif
+#ifndef PERL_VERSION_MINOR
+# define PERL_VERSION_MINOR PERL_VERSION
+#else
+# undef PERL_VERSION
+#endif
+#ifndef PERL_VERSION_PATCH
+# define PERL_VERSION_PATCH PERL_SUBVERSION
+#else
+# undef PERL_SUBVERSION
+#endif
+
+#define PERL_JNP_TO_DECIMAL_(maJor,miNor,Patch) \
+ /* '10*' leaves room for things like alpha, beta, releases */ \
+ (10 * ((maJor) * 1000000) + ((miNor) * 1000) + (Patch))
+#define PERL_DECIMAL_VERSION_ \
+ PERL_JNP_TO_DECIMAL_(PERL_VERSION_MAJOR, PERL_VERSION_MINOR, \
+ PERL_VERSION_PATCH)
+
/*
-=head1 Miscellaneous Functions
+=for apidoc_section $versioning
+=for apidoc AmR|bool|PERL_VERSION_EQ|const U8 major|const U8 minor|const U8 patch
+=for apidoc_item PERL_VERSION_NE
+=for apidoc_item PERL_VERSION_LT
+=for apidoc_item PERL_VERSION_LE
+=for apidoc_item PERL_VERSION_GT
+=for apidoc_item PERL_VERSION_GE
+
+Returns whether or not the perl currently being compiled has the specified
+relationship to the perl given by the parameters. For example,
+
+ #if PERL_VERSION_GT(5,24,2)
+ code that will only be compiled on perls after v5.24.2
+ #else
+ fallback code
+ #endif
+
+Note that this is usable in making compile-time decisions
+
+You may use the special value '*' for the final number to mean ALL possible
+values for it. Thus,
+
+ #if PERL_VERSION_EQ(5,31,'*')
+
+means all perls in the 5.31 series. And
+
+ #if PERL_VERSION_NE(5,24,'*')
+
+means all perls EXCEPT 5.24 ones. And
+
+ #if PERL_VERSION_LE(5,9,'*')
+
+is effectively
+
+ #if PERL_VERSION_LT(5,10,0)
+
+This means you don't have to think so much when converting from the existing
+deprecated C<PERL_VERSION> to using this macro:
+
+ #if PERL_VERSION <= 9
+
+becomes
+
+ #if PERL_VERSION_LE(5,9,'*')
+
+=cut
+*/
+
+/* N.B. These don't work if the patch version is 42 or 92, as those are what
+ * '*' is in ASCII and EBCDIC respectively */
+# define PERL_VERSION_EQ(j,n,p) \
+ (((p) == '*') \
+ ? ( (j) == PERL_VERSION_MAJOR \
+ && (n) == PERL_VERSION_MINOR) \
+ : (PERL_DECIMAL_VERSION_ == PERL_JNP_TO_DECIMAL_(j,n,p)))
+# define PERL_VERSION_NE(j,n,p) (! PERL_VERSION_EQ(j,n,p))
+
+# define PERL_VERSION_LT(j,n,p) /* < '*' effectively means < 0 */ \
+ (PERL_DECIMAL_VERSION_ < PERL_JNP_TO_DECIMAL_( (j), \
+ (n), \
+ (((p) == '*') ? 0 : p)))
+# define PERL_VERSION_GE(j,n,p) (! PERL_VERSION_LT(j,n,p))
+
+# define PERL_VERSION_LE(j,n,p) /* <= '*' effectively means < n+1 */ \
+ (PERL_DECIMAL_VERSION_ < PERL_JNP_TO_DECIMAL_( (j), \
+ (((p) == '*') ? ((n)+1) : (n)), \
+ (((p) == '*') ? 0 : p)))
+# define PERL_VERSION_GT(j,n,p) (! PERL_VERSION_LE(j,n,p))
+
+/*
+=for apidoc_section $string
=for apidoc Am|bool|strNE|char* s1|char* s2
Test two C<NUL>-terminated strings to see if they are different. Returns true
are equal. The C<len> parameter indicates the number of bytes to compare.
Returns zero if equal, or non-zero if non-equal.
+=for apidoc Am|bool|memEQs|char* s1|STRLEN l1|"s2"
+Like L</memEQ>, but the second string is a literal enclosed in double quotes,
+C<l1> gives the number of bytes in C<s1>.
+Returns zero if equal, or non-zero if non-equal.
+
=for apidoc Am|bool|memNE|char* s1|char* s2|STRLEN len
Test two buffers (which may contain embedded C<NUL> characters, to see if they
are not equal. The C<len> parameter indicates the number of bytes to compare.
Returns zero if non-equal, or non-zero if equal.
+=for apidoc Am|bool|memNEs|char* s1|STRLEN l1|"s2"
+Like L</memNE>, but the second string is a literal enclosed in double quotes,
+C<l1> gives the number of bytes in C<s1>.
+Returns zero if non-equal, or zero if non-equal.
+
+=for apidoc Am|bool|memCHRs|"list"|char c
+Returns the position of the first occurence of the byte C<c> in the literal
+string C<"list">, or NULL if C<c> doesn't appear in C<"list">. All bytes are
+treated as unsigned char. Thus this macro can be used to determine if C<c> is
+in a set of particular characters. Unlike L<strchr(3)>, it works even if C<c>
+is C<NUL> (and the set doesn't include C<NUL>).
+
=cut
New macros should use the following conventions for their names (which are
length may be unknown, but can be calculated by C<strlen()>, since it is
terminated by a NUL, which isn't included in its length.
- The optional 'n' following 'str' means that that there is a third parameter,
+ The optional 'n' following 'str' means that there is a third parameter,
giving the maximum number of bytes to look at in each string. Even if both
strings are longer than the length parameter, those extra bytes will be
unexamined.
#define strnNE(s1,s2,l) (strncmp(s1,s2,l) != 0)
#define strnEQ(s1,s2,l) (strncmp(s1,s2,l) == 0)
-#define memNE(s1,s2,l) (memcmp(s1,s2,l) != 0)
-#define memEQ(s1,s2,l) (memcmp(s1,s2,l) == 0)
+#define memEQ(s1,s2,l) (memcmp(((const void *) (s1)), ((const void *) (s2)), l) == 0)
+#define memNE(s1,s2,l) (! memEQ(s1,s2,l))
/* memEQ and memNE where second comparand is a string constant */
#define memEQs(s1, l, s2) \
#define strBEGINs(s1,s2) (strncmp(s1,"" s2 "", sizeof(s2)-1) == 0)
#define memBEGINs(s1, l, s2) \
- ( (l) >= sizeof(s2) - 1 \
+ ( (Ptrdiff_t) (l) >= (Ptrdiff_t) sizeof(s2) - 1 \
&& memEQ(s1, "" s2 "", sizeof(s2)-1))
#define memBEGINPs(s1, l, s2) \
- ( (l) > sizeof(s2) - 1 \
+ ( (Ptrdiff_t) (l) > (Ptrdiff_t) sizeof(s2) - 1 \
&& memEQ(s1, "" s2 "", sizeof(s2)-1))
#define memENDs(s1, l, s2) \
- ( (l) >= sizeof(s2) - 1 \
+ ( (Ptrdiff_t) (l) >= (Ptrdiff_t) sizeof(s2) - 1 \
&& memEQ(s1 + (l) - (sizeof(s2) - 1), "" s2 "", sizeof(s2)-1))
#define memENDPs(s1, l, s2) \
- ( (l) > sizeof(s2) \
+ ( (Ptrdiff_t) (l) > (Ptrdiff_t) sizeof(s2) \
&& memEQ(s1 + (l) - (sizeof(s2) - 1), "" s2 "", sizeof(s2)-1))
#endif /* End of making macros private */
#define memGT(s1,s2,l) (memcmp(s1,s2,l) > 0)
#define memGE(s1,s2,l) (memcmp(s1,s2,l) >= 0)
+#define memCHRs(s1,c) ((const char *) memchr("" s1 "" , c, sizeof(s1)-1))
+
/*
* Character classes.
*
ones valid for it.) None are affected by C<use bytes>, and only the ones
with C<LC> in the name are affected by the current locale.
-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 (or on non-ASCII platforms, corresponds to) an
+The base function, e.g., C<isALPHA()>, takes any signed or unsigned value,
+treating it as a code point, and returns a boolean as to whether or not the
+character represented by it 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.
as if they are Latin-1 characters. For example, C<isWORDCHAR_L1()> will return
true when called with the code point 0xDF, which is a word character in both
ASCII and EBCDIC (though it represents different characters in each).
+If the input is a number that doesn't fit in an octet, FALSE is returned.
+(Perl's documentation uses a colloquial definition of Latin-1, to include all
+code points below 256.)
-Variant C<isI<FOO>_uvchr> is like the C<isI<FOO>_L1> variant, but accepts any UV code
-point as input. If the code point is larger than 255, Unicode rules are used
-to determine if it is in the character class. For example,
+Variant C<isI<FOO>_uvchr> is exactly like the C<isI<FOO>_L1> variant, for
+inputs below 256, but if the code point is larger than 255, Unicode rules are
+used to determine if it is in the character class. For example,
C<isWORDCHAR_uvchr(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
WITH MACRON in Unicode, and is a word character.
-Variant C<isI<FOO>_utf8_safe> is like C<isI<FOO>_uvchr>, but is used for UTF-8
-encoded strings. Each call classifies one character, even if the string
-contains many. This variant takes two parameters. The first, C<p>, is a
-pointer to the first byte of the character to be classified. (Recall that it
-may take more than one byte to represent a character in UTF-8 strings.) The
-second parameter, C<e>, points to anywhere in the string beyond the first
-character, up to one byte past the end of the entire string. The suffix
-C<_safe> in the function's name indicates that it will not attempt to read
-beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
-is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
-character is malformed in some way, the program may croak, or the function may
-return FALSE, at the discretion of the implementation, and subject to change in
-future releases.
-
-Variant C<isI<FOO>_utf8> is like C<isI<FOO>_utf8_safe>, but takes just a single
-parameter, C<p>, which has the same meaning as the corresponding parameter does
-in C<isI<FOO>_utf8_safe>. The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take a second
-parameter, becoming a synonym for C<isI<FOO>_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<isI<FOO>_utf8> from each call point in the
-program will raise a deprecation warning, enabled by default. You can convert
-your program now to use C<isI<FOO>_utf8_safe>, and avoid the warnings, and get an
-extra measure of protection, or you can wait until v5.30, when you'll be forced
-to add the C<e> parameter.
-
-Variant C<isI<FOO>_LC> is like the C<isI<FOO>_A> and C<isI<FOO>_L1> variants, but the
-result is based on the current locale, which is what C<LC> in the name stands
-for. If Perl can determine that the current locale is a UTF-8 locale, it uses
-the published Unicode rules; otherwise, it uses the C library function that
-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
+Variants C<isI<FOO>_utf8> and C<isI<FOO>_utf8_safe> are like C<isI<FOO>_uvchr>,
+but are used for UTF-8 encoded strings. The two forms are different names for
+the same thing. Each call to one of these classifies the first character of
+the string starting at C<p>. The second parameter, C<e>, points to anywhere in
+the string beyond the first character, up to one byte past the end of the
+entire string. Although both variants are identical, the suffix C<_safe> in
+one name emphasizes that it will not attempt to read beyond S<C<e - 1>>,
+provided that the constraint S<C<s E<lt> e>> is true (this is asserted for in
+C<-DDEBUGGING> builds). If the UTF-8 for the input character is malformed in
+some way, the program may croak, or the function may return FALSE, at the
+discretion of the implementation, and subject to change in future releases.
+
+Variant C<isI<FOO>_LC> is like the C<isI<FOO>_A> and C<isI<FOO>_L1> variants,
+but the result is based on the current locale, which is what C<LC> in the name
+stands for. If Perl can determine that the current locale is a UTF-8 locale,
+it uses the published Unicode rules; otherwise, it uses the C library function
+that 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. 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<isI<FOO>_LC_uvchr> is like C<isI<FOO>_LC>, but is defined on any UV. It
-returns the same as C<isI<FOO>_LC> for input code points less than 256, and
-returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
-
-Variant C<isI<FOO>_LC_utf8_safe> is like C<isI<FOO>_LC_uvchr>, but is used for UTF-8
-encoded strings. Each call classifies one character, even if the string
-contains many. This variant takes two parameters. The first, C<p>, is a
-pointer to the first byte of the character to be classified. (Recall that it
-may take more than one byte to represent a character in UTF-8 strings.) The
-second parameter, C<e>, points to anywhere in the string beyond the first
-character, up to one byte past the end of the entire string. The suffix
-C<_safe> in the function's name indicates that it will not attempt to read
+Variant C<isI<FOO>_LC_uvchr> acts exactly like C<isI<FOO>_LC> for inputs less
+than 256, but for larger ones it returns the Unicode classification of the code
+point.
+
+Variants C<isI<FOO>_LC_utf8> and C<isI<FOO>_LC_utf8_safe> are like
+C<isI<FOO>_LC_uvchr>, but are used for UTF-8 encoded strings. The two forms
+are different names for the same thing. Each call to one of these classifies
+the first character of the string starting at C<p>. The second parameter,
+C<e>, points to anywhere in the string beyond the first character, up to one
+byte past the end of the entire string. Although both variants are identical,
+the suffix C<_safe> in one name emphasizes that it will not attempt to read
beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
character is malformed in some way, the program may croak, or the function may
return FALSE, at the discretion of the implementation, and subject to change in
future releases.
-Variant C<isI<FOO>_LC_utf8> is like C<isI<FOO>_LC_utf8_safe>, but takes just a single
-parameter, C<p>, which has the same meaning as the corresponding parameter does
-in C<isI<FOO>_LC_utf8_safe>. The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take a second
-parameter, becoming a synonym for C<isI<FOO>_LC_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<isI<FOO>_LC_utf8> from each call point in
-the program will raise a deprecation warning, enabled by default. You can
-convert your program now to use C<isI<FOO>_LC_utf8_safe>, and avoid the warnings,
-and get an extra measure of protection, or you can wait until v5.30, when
-you'll be forced to add the C<e> parameter.
-
-=for apidoc Am|bool|isALPHA|char ch
-Returns a boolean indicating whether the specified character is an
-alphabetic character, analogous to C<m/[[:alpha:]]/>.
+=for apidoc Am|bool|isALPHA|UV ch
+=for apidoc_item ||isALPHA_A|UV ch
+=for apidoc_item ||isALPHA_L1|UV ch
+=for apidoc_item ||isALPHA_uvchr|UV ch
+=for apidoc_item ||isALPHA_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isALPHA_utf8|U8 * s|U8 * end
+=for apidoc_item ||isALPHA_LC|UV ch
+=for apidoc_item ||isALPHA_LC_uvchr|UV ch
+=for apidoc_item ||isALPHA_LC_utf8_safe|U8 * s| U8 *end
+Returns a boolean indicating whether the specified input is one of C<[A-Za-z]>,
+analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8_safe>,
-C<isALPHA_LC>, C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8_safe>.
+the variants.
-=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 classification> for an explanation of
-variants
-C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uvchr>,
-C<isALPHANUMERIC_utf8_safe>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>,
-and C<isALPHANUMERIC_LC_utf8_safe>.
+=cut
-=for apidoc Am|bool|isASCII|char ch
+Here and below, we add the prototypes of these macros for downstream programs
+that would be interested in them, such as Devel::PPPort
+
+=for apidoc Am|bool|isALPHANUMERIC|UV ch
+=for apidoc_item ||isALPHANUMERIC_A|UV ch
+=for apidoc_item ||isALPHANUMERIC_L1|UV ch
+=for apidoc_item ||isALPHANUMERIC_uvchr|UV ch
+=for apidoc_item ||isALPHANUMERIC_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isALPHANUMERIC_utf8|U8 * s|U8 * end
+=for apidoc_item ||isALPHANUMERIC_LC|UV ch
+=for apidoc_item ||isALPHANUMERIC_LC_uvchr|UV ch
+=for apidoc_item ||isALPHANUMERIC_LC_utf8_safe|U8 * s| U8 *end
+=for apidoc_item ||isALNUMC|UV ch
+=for apidoc_item ||isALNUMC_A|UV ch
+=for apidoc_item ||isALNUMC_L1|UV ch
+=for apidoc_item ||isALNUMC_LC|UV ch
+=for apidoc_item ||isALNUMC_LC_uvchr|UV ch
+Returns a boolean indicating whether the specified character is one of
+C<[A-Za-z0-9]>, analogous to C<m/[[:alnum:]]/>.
+See the L<top of this section|/Character classification> for an explanation of
+the variants.
+
+A (discouraged from use) synonym is C<isALNUMC> (where the C<C> suffix means
+this corresponds to the C language alphanumeric definition). Also
+there are the variants
+C<isALNUMC_A>, C<isALNUMC_L1>
+C<isALNUMC_LC>, and C<isALNUMC_LC_uvchr>.
+
+=for apidoc Am|bool|isASCII|UV ch
+=for apidoc_item ||isASCII_A|UV ch
+=for apidoc_item ||isASCII_L1|UV ch
+=for apidoc_item ||isASCII_uvchr|UV ch
+=for apidoc_item ||isASCII_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isASCII_utf8|U8 * s|U8 * end
+=for apidoc_item ||isASCII_LC|UV ch
+=for apidoc_item ||isASCII_LC_uvchr|UV ch
+=for apidoc_item ||isASCII_LC_utf8_safe|U8 * s| U8 *end
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 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 classification> for an explanation of
-variants
-C<isASCII_uvchr>, C<isASCII_utf8_safe>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
-C<isASCII_LC_utf8_safe>. Note, however, that some platforms do not have the C
-library routine C<isascii()>. In these cases, the variants whose names contain
-C<LC> are the same as the corresponding ones without.
+the variants.
+Note, however, that some platforms do not have the C library routine
+C<isascii()>. In these cases, the variants whose names contain C<LC> are the
+same as the corresponding ones without.
Also note, that because all ASCII characters are UTF-8 invariant (meaning they
have the exact same representation (always a single byte) whether encoded in
UTF-8 or not), C<isASCII> will give the correct results when called with any
-byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8_safe>
-will work properly on any string encoded or not in UTF-8.
-
-=for apidoc Am|bool|isBLANK|char ch
+byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8> and
+C<isASCII_utf8_safe> will work properly on any string encoded or not in UTF-8.
+
+=for apidoc Am|bool|isBLANK|UV ch
+=for apidoc_item ||isBLANK_A|UV ch
+=for apidoc_item ||isBLANK_L1|UV ch
+=for apidoc_item ||isBLANK_uvchr|UV ch
+=for apidoc_item ||isBLANK_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isBLANK_utf8|U8 * s|U8 * end
+=for apidoc_item ||isBLANK_LC|UV ch
+=for apidoc_item ||isBLANK_LC_uvchr|UV ch
+=for apidoc_item ||isBLANK_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8_safe>,
-C<isBLANK_LC>, C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8_safe>. Note,
+the variants.
+Note,
however, that some platforms do not have the C library routine
C<isblank()>. In these cases, the variants whose names contain C<LC> are
the same as the corresponding ones without.
-=for apidoc Am|bool|isCNTRL|char ch
+=for apidoc Am|bool|isCNTRL|UV ch
+=for apidoc_item ||isCNTRL_A|UV ch
+=for apidoc_item ||isCNTRL_L1|UV ch
+=for apidoc_item ||isCNTRL_uvchr|UV ch
+=for apidoc_item ||isCNTRL_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isCNTRL_utf8|U8 * s|U8 * end
+=for apidoc_item ||isCNTRL_LC|UV ch
+=for apidoc_item ||isCNTRL_LC_uvchr|UV ch
+=for apidoc_item ||isCNTRL_LC_utf8_safe|U8 * s| U8 *end
+
Returns a boolean indicating whether the specified character is a
control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8_safe>,
-C<isCNTRL_LC>, C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8_safe> On EBCDIC
-platforms, you almost always want to use the C<isCNTRL_L1> variant.
+the variants.
+On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
+
+=for apidoc Am|bool|isDIGIT|UV ch
+=for apidoc_item ||isDIGIT_A|UV ch
+=for apidoc_item ||isDIGIT_L1|UV ch
+=for apidoc_item ||isDIGIT_uvchr|UV ch
+=for apidoc_item ||isDIGIT_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isDIGIT_utf8|U8 * s|U8 * end
+=for apidoc_item ||isDIGIT_LC|UV ch
+=for apidoc_item ||isDIGIT_LC_uvchr|UV ch
+=for apidoc_item ||isDIGIT_LC_utf8_safe|U8 * s| U8 *end
-=for apidoc Am|bool|isDIGIT|char ch
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 classification> for an explanation of
-variants
-C<isDIGIT_uvchr>, C<isDIGIT_utf8_safe>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
-C<isDIGIT_LC_utf8_safe>.
-
-=for apidoc Am|bool|isGRAPH|char ch
+the variants.
+
+=for apidoc Am|bool|isGRAPH|UV ch
+=for apidoc_item ||isGRAPH_A|UV ch
+=for apidoc_item ||isGRAPH_L1|UV ch
+=for apidoc_item ||isGRAPH_uvchr|UV ch
+=for apidoc_item ||isGRAPH_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isGRAPH_utf8|U8 * s|U8 * end
+=for apidoc_item ||isGRAPH_LC|UV ch
+=for apidoc_item ||isGRAPH_LC_uvchr|UV ch
+=for apidoc_item ||isGRAPH_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8_safe>,
-C<isGRAPH_LC>, C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8_safe>.
-
-=for apidoc Am|bool|isLOWER|char ch
+the variants.
+
+=for apidoc Am|bool|isLOWER|UV ch
+=for apidoc_item ||isLOWER_A|UV ch
+=for apidoc_item ||isLOWER_L1|UV ch
+=for apidoc_item ||isLOWER_uvchr|UV ch
+=for apidoc_item ||isLOWER_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isLOWER_utf8|U8 * s|U8 * end
+=for apidoc_item ||isLOWER_LC|UV ch
+=for apidoc_item ||isLOWER_LC_uvchr|UV ch
+=for apidoc_item ||isLOWER_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8_safe>,
-C<isLOWER_LC>, C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8_safe>.
+the variants
-=for apidoc Am|bool|isOCTAL|char ch
+=for apidoc Am|bool|isOCTAL|UV ch
+=for apidoc_item ||isOCTAL_A|UV ch
+=for apidoc_item ||isOCTAL_L1|UV ch
Returns a boolean indicating whether the specified character is an
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
+=for apidoc Am|bool|isPUNCT|UV ch
+=for apidoc_item ||isPUNCT_A|UV ch
+=for apidoc_item ||isPUNCT_L1|UV ch
+=for apidoc_item ||isPUNCT_uvchr|UV ch
+=for apidoc_item ||isPUNCT_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isPUNCT_utf8|U8 * s|U8 * end
+=for apidoc_item ||isPUNCT_LC|UV ch
+=for apidoc_item ||isPUNCT_LC_uvchr|UV ch
+=for apidoc_item ||isPUNCT_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
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 classification> for an explanation of
-variants C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8_safe>,
-C<isPUNCT_LC>, C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8_safe>.
-
-=for apidoc Am|bool|isSPACE|char ch
+the variants.
+
+=for apidoc Am|bool|isSPACE|UV ch
+=for apidoc_item ||isSPACE_A|UV ch
+=for apidoc_item ||isSPACE_L1|UV ch
+=for apidoc_item ||isSPACE_uvchr|UV ch
+=for apidoc_item ||isSPACE_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isSPACE_utf8|U8 * s|U8 * end
+=for apidoc_item ||isSPACE_LC|UV ch
+=for apidoc_item ||isSPACE_LC_uvchr|UV ch
+=for apidoc_item ||isSPACE_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
whitespace character. This is analogous
to what C<m/\s/> matches in a regular expression. Starting in Perl 5.18
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 classification> for an explanation of
-variants
-C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8_safe>,
-C<isSPACE_LC>, C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8_safe>.
-
-=for apidoc Am|bool|isPSXSPC|char ch
+the variants.
+
+=for apidoc Am|bool|isPSXSPC|UV ch
+=for apidoc_item ||isPSXSPC_A|UV ch
+=for apidoc_item ||isPSXSPC_L1|UV ch
+=for apidoc_item ||isPSXSPC_uvchr|UV ch
+=for apidoc_item ||isPSXSPC_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isPSXSPC_utf8|U8 * s|U8 * end
+=for apidoc_item ||isPSXSPC_LC|UV ch
+=for apidoc_item ||isPSXSPC_LC_uvchr|UV ch
+=for apidoc_item ||isPSXSPC_LC_utf8_safe|U8 * s| U8 *end
(short for Posix Space)
Starting in 5.18, this is identical in all its forms to the
corresponding C<isSPACE()> macros.
Otherwise they are identical. Thus this macro is analogous to what
C<m/[[:space:]]/> matches in a regular expression.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8_safe>,
-C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8_safe>.
-
-=for apidoc Am|bool|isUPPER|char ch
+the variants.
+
+=for apidoc Am|bool|isUPPER|UV ch
+=for apidoc_item ||isUPPER_A|UV ch
+=for apidoc_item ||isUPPER_L1|UV ch
+=for apidoc_item ||isUPPER_uvchr|UV ch
+=for apidoc_item ||isUPPER_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isUPPER_utf8|U8 * s|U8 * end
+=for apidoc_item ||isUPPER_LC|UV ch
+=for apidoc_item ||isUPPER_LC_uvchr|UV ch
+=for apidoc_item ||isUPPER_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is an
uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8_safe>,
-C<isUPPER_LC>, C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8_safe>.
-
-=for apidoc Am|bool|isPRINT|char ch
+the variants.
+
+=for apidoc Am|bool|isPRINT|UV ch
+=for apidoc_item ||isPRINT_A|UV ch
+=for apidoc_item ||isPRINT_L1|UV ch
+=for apidoc_item ||isPRINT_uvchr|UV ch
+=for apidoc_item ||isPRINT_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isPRINT_utf8|U8 * s|U8 * end
+=for apidoc_item ||isPRINT_LC|UV ch
+=for apidoc_item ||isPRINT_LC_uvchr|UV ch
+=for apidoc_item ||isPRINT_LC_utf8_safe|U8 * s| U8 *end
Returns a boolean indicating whether the specified character is a
printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8_safe>,
-C<isPRINT_LC>, C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8_safe>.
-
-=for apidoc Am|bool|isWORDCHAR|char ch
+the variants.
+
+=for apidoc Am|bool|isWORDCHAR|UV ch
+=for apidoc_item ||isWORDCHAR_A|UV ch
+=for apidoc_item ||isWORDCHAR_L1|UV ch
+=for apidoc_item ||isWORDCHAR_uvchr|UV ch
+=for apidoc_item ||isWORDCHAR_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isWORDCHAR_utf8|U8 * s|U8 * end
+=for apidoc_item ||isWORDCHAR_LC|UV ch
+=for apidoc_item ||isWORDCHAR_LC_uvchr|UV ch
+=for apidoc_item ||isWORDCHAR_LC_utf8_safe|U8 * s| U8 *end
+=for apidoc_item ||isALNUM|UV ch
+=for apidoc_item ||isALNUM_A|UV ch
+=for apidoc_item ||isALNUM_LC|UV ch
+=for apidoc_item ||isALNUM_LC_uvchr|UV ch
Returns a boolean indicating whether the specified character is a character
that is a word character, analogous to what C<m/\w/> and C<m/[[:word:]]/> match
in a regular expression. A word character is an alphabetic character, a
word character includes more than the standard C language meaning of
alphanumeric.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and
-C<isWORDCHAR_utf8_safe>. C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and
+the variants.
+C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>,
+C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, C<isWORDCHAR_LC_utf8>, and
C<isWORDCHAR_LC_utf8_safe> are also as described there, but additionally
include the platform's native underscore.
-=for apidoc Am|bool|isXDIGIT|char ch
+=for apidoc Am|bool|isXDIGIT|UV ch
+=for apidoc_item ||isXDIGIT_A|UV ch
+=for apidoc_item ||isXDIGIT_L1|UV ch
+=for apidoc_item ||isXDIGIT_uvchr|UV ch
+=for apidoc_item ||isXDIGIT_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isXDIGIT_utf8|U8 * s|U8 * end
+=for apidoc_item ||isXDIGIT_LC|UV ch
+=for apidoc_item ||isXDIGIT_LC_uvchr|UV ch
+=for apidoc_item ||isXDIGIT_LC_utf8_safe|U8 * s| U8 *end
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 classification> for an explanation of
-variants
-C<isXDIGIT_uvchr>, C<isXDIGIT_utf8_safe>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>,
-and C<isXDIGIT_LC_utf8_safe>.
-
-=for apidoc Am|bool|isIDFIRST|char ch
+the variants.
+
+=for apidoc Am|bool|isIDFIRST|UV ch
+=for apidoc_item ||isIDFIRST_A|UV ch
+=for apidoc_item ||isIDFIRST_L1|UV ch
+=for apidoc_item ||isIDFIRST_uvchr|UV ch
+=for apidoc_item ||isIDFIRST_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isIDFIRST_utf8|U8 * s|U8 * end
+=for apidoc_item ||isIDFIRST_LC|UV ch
+=for apidoc_item ||isIDFIRST_LC_uvchr|UV ch
+=for apidoc_item ||isIDFIRST_LC_utf8_safe|U8 * s| U8 *end
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 classification> for an explanation of
-variants
-C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8_safe>,
-C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8_safe>.
-
-=for apidoc Am|bool|isIDCONT|char ch
+the variants.
+
+=for apidoc Am|bool|isIDCONT|UV ch
+=for apidoc_item ||isIDCONT_A|UV ch
+=for apidoc_item ||isIDCONT_L1|UV ch
+=for apidoc_item ||isIDCONT_uvchr|UV ch
+=for apidoc_item ||isIDCONT_utf8_safe|U8 * s|U8 * end
+=for apidoc_item ||isIDCONT_utf8|U8 * s|U8 * end
+=for apidoc_item ||isIDCONT_LC|UV ch
+=for apidoc_item ||isIDCONT_LC_uvchr|UV ch
+=for apidoc_item ||isIDCONT_LC_utf8_safe|U8 * s| U8 *end
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 classification> for
-an
-explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uvchr>,
-C<isIDCONT_utf8_safe>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
-C<isIDCONT_LC_utf8_safe>.
+an explanation of the variants.
-=head1 Miscellaneous Functions
+=for apidoc_section $numeric
=for apidoc Am|U8|READ_XDIGIT|char str*
Returns the value of an ASCII-range hex digit and advances the string pointer.
no other function that is crippled by not being able to give the correct
results for the full range of possible inputs has been implemented here.
-=for apidoc Am|U8|toUPPER|U8 ch
+=for apidoc Am|U8|toUPPER|int 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.
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more.)
-=for apidoc Am|UV|toUPPER_utf8_safe|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc Am|UV|toUPPER_utf8|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc_item toUPPER_utf8_safe
Converts the first UTF-8 encoded character in the sequence starting at C<p> and
extending no further than S<C<e - 1>> to its uppercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more).
-The suffix C<_safe> in the function's name indicates that it will not attempt
-to read beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is
-true (this is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the
-input character is malformed in some way, the program may croak, or the
-function may return the REPLACEMENT CHARACTER, at the discretion of the
-implementation, and subject to change in future releases.
+It will not attempt to read beyond S<C<e - 1>>, provided that the constraint
+S<C<s E<lt> e>> is true (this is asserted for in C<-DDEBUGGING> builds). If
+the UTF-8 for the input character is malformed in some way, the program may
+croak, or the function may return the REPLACEMENT CHARACTER, at the discretion
+of the implementation, and subject to change in future releases.
-=for apidoc Am|UV|toUPPER_utf8|U8* p|U8* s|STRLEN* lenp
-This is like C<L</toUPPER_utf8_safe>>, but doesn't have the C<e>
-parameter The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take the C<e>
-parameter, becoming a synonym for C<toUPPER_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<toUPPER_utf8> from each call point in the
-program will raise a deprecation warning, enabled by default. You can convert
-your program now to use C<toUPPER_utf8_safe>, and avoid the warnings, and get an
-extra measure of protection, or you can wait until v5.30, when you'll be forced
-to add the C<e> parameter.
+C<toUPPER_utf8_safe> is now just a different spelling of plain C<toUPPER_utf8>
=for apidoc Am|U8|toFOLD|U8 ch
Converts the specified character to foldcase. If the input is anything but an
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more).
-=for apidoc Am|UV|toFOLD_utf8_safe|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc Am|UV|toFOLD_utf8|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc_item toFOLD_utf8_safe
Converts the first UTF-8 encoded character in the sequence starting at C<p> and
extending no further than S<C<e - 1>> to its foldcase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more).
-The suffix C<_safe> in the function's name indicates that it will not attempt
-to read beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is
-true (this is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the
-input character is malformed in some way, the program may croak, or the
-function may return the REPLACEMENT CHARACTER, at the discretion of the
-implementation, and subject to change in future releases.
-
-=for apidoc Am|UV|toFOLD_utf8|U8* p|U8* s|STRLEN* lenp
-This is like C<L</toFOLD_utf8_safe>>, but doesn't have the C<e>
-parameter The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take the C<e>
-parameter, becoming a synonym for C<toFOLD_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<toFOLD_utf8> from each call point in the
-program will raise a deprecation warning, enabled by default. You can convert
-your program now to use C<toFOLD_utf8_safe>, and avoid the warnings, and get an
-extra measure of protection, or you can wait until v5.30, when you'll be forced
-to add the C<e> parameter.
-
-=for apidoc Am|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_uvchr|UV cp|U8* s|STRLEN* lenp
-Converts the 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>. The code
-point is interpreted as native if less than 256; otherwise as Unicode. 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 at L<the top of this section|/Character case
-changing>, that there may be more).
-
-
-=for apidoc Am|UV|toLOWER_utf8_safe|U8* p|U8* e|U8* s|STRLEN* lenp
-Converts the first UTF-8 encoded character in the sequence starting at C<p> and
-extending no further than S<C<e - 1>> 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 at L<the top of this section|/Character case
-changing>, that there may be more).
-
-The suffix C<_safe> in the function's name indicates that it will not attempt
+It will not attempt
to read beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is
true (this is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the
input character is malformed in some way, the program may croak, or the
function may return the REPLACEMENT CHARACTER, at the discretion of the
implementation, and subject to change in future releases.
-=for apidoc Am|UV|toLOWER_utf8|U8* p|U8* s|STRLEN* lenp
-This is like C<L</toLOWER_utf8_safe>>, but doesn't have the C<e>
-parameter The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take the C<e>
-parameter, becoming a synonym for C<toLOWER_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<toLOWER_utf8> from each call point in the
-program will raise a deprecation warning, enabled by default. You can convert
-your program now to use C<toLOWER_utf8_safe>, and avoid the warnings, and get an
-extra measure of protection, or you can wait until v5.30, when you'll be forced
-to add the C<e> parameter.
+C<toFOLD_utf8_safe> is now just a different spelling of plain C<toFOLD_utf8>
+
+=for apidoc Am|UV|toLOWER|UV cp
+=for apidoc_item |UV|toLOWER_A|UV cp
+=for apidoc_item |UV|toLOWER_L1|UV cp
+=for apidoc_item |UV|toLOWER_LATIN1|UV cp
+=for apidoc_item |UV|toLOWER_LC|UV cp
+=for apidoc_item |UV|toLOWER_uvchr|UV cp|U8* s|STRLEN* lenp
+=for apidoc_item |UV|toLOWER_utf8|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc_item |UV|toLOWER_utf8_safe|U8* p|U8* e|U8* s|STRLEN* lenp
+
+These all return the lowercase of a character. The differences are what domain
+they operate on, and whether the input is specified as a code point (those
+forms with a C<cp> parameter) or as a UTF-8 string (the others). In the latter
+case, the code point to use is the first one in the buffer of UTF-8 encoded
+code points, delineated by the arguments S<C<p .. e - 1>>.
+
+C<toLOWER> and C<toLOWER_A> are synonyms of each other. They return the
+lowercase of any uppercase ASCII-range code point. All other inputs are
+returned unchanged. Since these are macros, the input type may be any integral
+one, and the output will occupy the same number of bits as the input.
+
+C<toLOWER_L1> and C<toLOWER_LATIN1> are synonyms of each other. They behave
+identically as C<toLOWER> for ASCII-range input. But additionally will return
+the lowercase of any uppercase code point in the entire 0..255 range, assuming
+a Latin-1 encoding (or the EBCDIC equivalent on such platforms).
+
+C<toLOWER_LC> returns the lowercase of the input code point according to the
+rules of the current POSIX locale. Input code points outside the range 0..255
+are returned unchanged.
+
+C<toLOWER_uvchr> returns the lowercase of any Unicode code point. The return
+value is identical to that of C<toLOWER_L1> for input code points in the 0..255
+range. The lowercase of the vast majority of Unicode code points is the same
+as the code point itself. For these, and for code points above the legal
+Unicode maximum, this returns the input code point unchanged. It additionally
+stores the UTF-8 of the result into the buffer beginning at C<s>, and its
+length in bytes into C<*lenp>. The caller must have made C<s> large enough to
+contain at least C<UTF8_MAXBYTES_CASE+1> bytes to avoid possible overflow.
+
+NOTE: the lowercase of a code point may be more than one code point. The
+return value of this function is only the first of these. The entire lowercase
+is returned in C<s>. To determine if the result is more than a single code
+point, you can do something like this:
+
+ uc = toLOWER_uvchr(cp, s, &len);
+ if (len > UTF8SKIP(s)) { is multiple code points }
+ else { is a single code point }
+
+C<toLOWER_utf8> and C<toLOWER_utf8_safe> are synonyms of each other. The only
+difference between these and C<toLOWER_uvchr> is that the source for these is
+encoded in UTF-8, instead of being a code point. It is passed as a buffer
+starting at C<p>, with C<e> pointing to one byte beyond its end. The C<p>
+buffer may certainly contain more than one code point; but only the first one
+(up through S<C<e - 1>>) is examined. If the UTF-8 for the input character is
+malformed in some way, the program may croak, or the function may return the
+REPLACEMENT CHARACTER, at the discretion of the implementation, and subject to
+change in future releases.
=for apidoc Am|U8|toTITLE|U8 ch
Converts the specified character to titlecase. If the input is anything but an
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more).
-=for apidoc Am|UV|toTITLE_utf8_safe|U8* p|U8* e|U8* s|STRLEN* lenp
-Converts the first UTF-8 encoded character in the sequence starting at C<p> and
+=for apidoc Am|UV|toTITLE_utf8|U8* p|U8* e|U8* s|STRLEN* lenp
+=for apidoc_item toTITLE_utf8_safe
+Convert the first UTF-8 encoded character in the sequence starting at C<p> and
extending no further than S<C<e - 1>> 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>
(but note, as explained at L<the top of this section|/Character case
changing>, that there may be more).
-The suffix C<_safe> in the function's name indicates that it will not attempt
+It will not attempt
to read beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is
true (this is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the
input character is malformed in some way, the program may croak, or the
function may return the REPLACEMENT CHARACTER, at the discretion of the
implementation, and subject to change in future releases.
-=for apidoc Am|UV|toTITLE_utf8|U8* p|U8* s|STRLEN* lenp
-This is like C<L</toLOWER_utf8_safe>>, but doesn't have the C<e>
-parameter The function therefore can't check if it is reading
-beyond the end of the string. Starting in Perl v5.30, it will take the C<e>
-parameter, becoming a synonym for C<toTITLE_utf8_safe>. At that time every
-program that uses it will have to be changed to successfully compile. In the
-meantime, the first runtime call to C<toTITLE_utf8> from each call point in the
-program will raise a deprecation warning, enabled by default. You can convert
-your program now to use C<toTITLE_utf8_safe>, and avoid the warnings, and get an
-extra measure of protection, or you can wait until v5.30, when you'll be forced
-to add the C<e> parameter.
+C<toTITLE_utf8_safe> is now just a different spelling of plain C<toTITLE_utf8>
=cut
*/
-/* Specify the widest unsigned type on the platform. Use U64TYPE because U64
- * is known only in the perl core, and this macro can be called from outside
- * that */
-#ifdef HAS_QUAD
-# define WIDEST_UTYPE U64TYPE
+/*
+ void below because that's the best fit, and works for Devel::PPPort
+=for apidoc_section $integer
+=for apidoc AyT||WIDEST_UTYPE
+
+Yields the widest unsigned integer type on the platform, currently either
+C<U32> or C<U64>. This can be used in declarations such as
+
+ WIDEST_UTYPE my_uv;
+
+or casts
+
+ my_uv = (WIDEST_UTYPE) val;
+
+=cut
+
+*/
+#ifdef QUADKIND
+# define WIDEST_UTYPE U64
#else
# define WIDEST_UTYPE U32
#endif
#define FITS_IN_8_BITS(c) (1)
#endif
+/* Returns true if l <= c <= (l + n), where 'l' and 'n' are non-negative
+ * Written this way so that after optimization, only one conditional test is
+ * needed. (The NV casts stop any warnings about comparison always being true
+ * if called with an unsigned. The cast preserves the sign, which is all we
+ * care about.) */
+#define withinCOUNT(c, l, n) (__ASSERT_((NV) (l) >= 0) \
+ __ASSERT_((NV) (n) >= 0) \
+ (((WIDEST_UTYPE) (((c)) - ((l) | 0))) <= (((WIDEST_UTYPE) ((n) | 0)))))
+
+/* Returns true if c is in the range l..u, where 'l' is non-negative
+ * Written this way so that after optimization, only one conditional test is
+ * needed. */
+#define inRANGE(c, l, u) (__ASSERT_((u) >= (l)) \
+ ( (sizeof(c) == sizeof(U8)) ? withinCOUNT(((U8) (c)), (l), ((u) - (l))) \
+ : (sizeof(c) == sizeof(U32)) ? withinCOUNT(((U32) (c)), (l), ((u) - (l))) \
+ : (__ASSERT_(sizeof(c) == sizeof(WIDEST_UTYPE)) \
+ withinCOUNT(((WIDEST_UTYPE) (c)), (l), ((u) - (l))))))
+
#ifdef EBCDIC
# ifndef _ALL_SOURCE
/* The native libc isascii() et.al. functions return the wrong results
*
* 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
- * (in reginclass() in regexec.c) */
+ * (in reginclass() in regexec.c). Except \v should be last, as it isn't a
+ * real Posix character class, and some (small) inefficiencies in regular
+ * expression handling would be introduced by putting it in the middle of those
+ * that are. Also, cntrl and ascii come after the others as it may be useful
+ * to group these which have no members that match above Latin1, (or above
+ * ASCII in the latter case) */
+
# define _CC_WORDCHAR 0 /* \w and [:word:] */
# define _CC_DIGIT 1 /* \d and [:digit:] */
# define _CC_ALPHA 2 /* [:alpha:] */
# define _CC_ALPHANUMERIC 7 /* [:alnum:] */
# define _CC_GRAPH 8 /* [:graph:] */
# define _CC_CASED 9 /* [:lower:] or [:upper:] under /i */
-
-#define _FIRST_NON_SWASH_CC 10
-/* The character classes above are implemented with swashes. The second group
- * (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,
- * as it isn't a real Posix character class, and some (small) inefficiencies in
- * regular expression handling would be introduced by putting it in the middle
- * of those that are. Also, cntrl and ascii come after the others as it may be
- * useful to group these which have no members that match above Latin1, (or
- * above ASCII in the latter case) */
-
# define _CC_SPACE 10 /* \s, [:space:] */
-# define _CC_PSXSPC _CC_SPACE /* XXX Temporary, can be removed
- when the deprecated isFOO_utf8()
- functions are removed */
# define _CC_BLANK 11 /* [:blank:] */
# define _CC_XDIGIT 12 /* [:xdigit:] */
# define _CC_CNTRL 13 /* [:cntrl:] */
# define _CC_QUOTEMETA 20
# define _CC_NON_FINAL_FOLD 21
# define _CC_IS_IN_SOME_FOLD 22
-# define _CC_MNEMONIC_CNTRL 23
-
-# define _CC_IDCONT 24 /* XXX Temporary, can be removed when the deprecated
- isFOO_utf8() functions are removed */
+# define _CC_BINDIGIT 23
+# define _CC_OCTDIGIT 24
+# define _CC_MNEMONIC_CNTRL 25
/* This next group is only used on EBCDIC platforms, so theoretically could be
* shared with something entirely different that's only on ASCII platforms */
-# define _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE 28
-# define _CC_UTF8_IS_START 29
-# define _CC_UTF8_IS_DOWNGRADEABLE_START 30
-# define _CC_UTF8_IS_CONTINUATION 31
-/* Unused: 24-27
+# define _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE 31
+/* Unused: 26-30
* 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
} _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) \
- || 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_CASED != 9
- #error Need to adjust order of swash_property_names[]
-# endif
-
-/* This is declared static in each of the few files that this is #defined for
- * to keep them from being publicly accessible. Hence there is a small amount
- * of wasted space */
-
-static const char* const swash_property_names[] = {
- "XPosixWord",
- "XPosixDigit",
- "XPosixAlpha",
- "XPosixLower",
- "XPosixUpper",
- "XPosixPunct",
- "XPosixPrint",
- "XPosixAlnum",
- "XPosixGraph",
- "Cased"
-};
-#endif
-
START_EXTERN_C
# ifdef DOINIT
EXTCONST U32 PL_charclass[] = {
&& ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
== _CC_mask_A(classnum)))
-# define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA)
+/* On ASCII platforms certain classes form a single range. It's faster to
+ * special case these. isDIGIT is a single range on all platforms */
+# ifdef EBCDIC
+# define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA)
+# 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 isUPPER_A(c) _generic_isCC_A(c, _CC_UPPER)
+# else
+ /* By folding the upper and lowercase, we can use a single range */
+# define isALPHA_A(c) inRANGE((~('A' ^ 'a') & (c)), 'A', 'Z')
+# define isGRAPH_A(c) inRANGE(c, ' ' + 1, 0x7e)
+# define isLOWER_A(c) inRANGE(c, 'a', 'z')
+# define isPRINT_A(c) inRANGE(c, ' ', 0x7e)
+# define isUPPER_A(c) inRANGE(c, 'A', 'Z')
+# endif
# 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) /* 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 isDIGIT_A(c) inRANGE(c, '0', '9')
# define isPUNCT_A(c) _generic_isCC_A(c, _CC_PUNCT)
# 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) /* No non-ASCII xdigits
*/
# 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)))
+# if defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_REGEXEC_C)
+# define HAS_NONLATIN1_SIMPLE_FOLD_CLOSURE(c) \
+ (( ! cBOOL(FITS_IN_8_BITS(c))) \
+ || (PL_charclass[(U8) (c)] & _CC_mask(_CC_NONLATIN1_SIMPLE_FOLD)))
+
+# define IS_NON_FINAL_FOLD(c) _generic_isCC(c, _CC_NON_FINAL_FOLD)
+# define IS_IN_SOME_FOLD_L1(c) _generic_isCC(c, _CC_IS_IN_SOME_FOLD)
+# endif
/* 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 HAS_NONLATIN1_FOLD_CLOSURE(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) \
- _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)
-# define _IS_MNEMONIC_CNTRL_ONLY_FOR_USE_BY_REGCOMP_DOT_C(c) \
- _generic_isCC(c, _CC_MNEMONIC_CNTRL)
+
+/* is c a control character for which we have a mnemonic? */
+# if defined(PERL_CORE) || defined(PERL_EXT)
+# define isMNEMONIC_CNTRL(c) _generic_isCC(c, _CC_MNEMONIC_CNTRL)
+# endif
#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. Most are coded based on first principles. These are written to
* avoid EBCDIC vs. ASCII #ifdef's as much as possible. */
-# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
+# define isDIGIT_A(c) inRANGE(c, '0', '9')
# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
# define isSPACE_A(c) (isBLANK_A(c) \
|| (c) == '\n' \
* uppercase. The tests for those aren't necessary on ASCII, but hurt only
* performance (if optimization isn't on), and allow the same code to be
* used for both platform types */
-# 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'))
+# define isLOWER_A(c) inRANGE((c), 'a', 'i') \
+ || inRANGE((c), 'j', 'r') \
+ || inRANGE((c), 's', 'z')
+# define isUPPER_A(c) inRANGE((c), 'A', 'I') \
+ || inRANGE((c), 'J', 'R') \
+ || inRANGE((c), 'S', 'Z')
# define isALPHA_A(c) (isUPPER_A(c) || isLOWER_A(c))
# define isALPHANUMERIC_A(c) (isALPHA_A(c) || isDIGIT_A(c))
# define isWORDCHAR_A(c) (isALPHANUMERIC_A(c) || (c) == '_')
# define isIDFIRST_A(c) (isALPHA_A(c) || (c) == '_')
-# define isXDIGIT_A(c) (isDIGIT_A(c) \
- || ((c) >= 'a' && (c) <= 'f') \
- || ((c) <= 'F' && (c) >= 'A'))
+# define isXDIGIT_A(c) ( isDIGIT_A(c) \
+ || inRANGE((c), 'a', 'f') \
+ || inRANGE((c), 'A', 'F')
# define isPUNCT_A(c) ((c) == '-' || (c) == '!' || (c) == '"' \
|| (c) == '#' || (c) == '$' || (c) == '%' \
|| (c) == '&' || (c) == '\'' || (c) == '(' \
# define isCNTRL_A(c) ((c) == '\0' || (c) == '\a' || (c) == '\b' \
|| (c) == '\f' || (c) == '\n' || (c) == '\r' \
|| (c) == '\t' || (c) == '\v' \
- || ((c) <= 3 && (c) >= 1) /* SOH, STX, ETX */ \
- || (c) == 7 /* U+7F DEL */ \
- || ((c) <= 0x13 && (c) >= 0x0E) /* SO, SI */ \
- /* DLE, DC[1-3] */ \
+ || inRANGE((c), 1, 3) /* SOH, STX, ETX */ \
+ || (c) == 7F /* U+7F DEL */ \
+ || inRANGE((c), 0x0E, 0x13) /* SO SI DLE \
+ DC[1-3] */ \
|| (c) == 0x18 /* U+18 CAN */ \
|| (c) == 0x19 /* U+19 EOM */ \
- || ((c) <= 0x1F && (c) >= 0x1C) /* [FGRU]S */ \
+ || inRANGE((c), 0x1C, 0x1F) /* [FGRU]S */ \
|| (c) == 0x26 /* U+17 ETB */ \
|| (c) == 0x27 /* U+1B ESC */ \
|| (c) == 0x2D /* U+05 ENQ */ \
|| NATIVE_TO_LATIN1((U8) c) == 0xA0)))
# define isUPPER_L1(c) (isUPPER_A(c) \
|| (FITS_IN_8_BITS(c) \
- && ( NATIVE_TO_LATIN1((U8) c) >= 0xC0 \
- && NATIVE_TO_LATIN1((U8) c) <= 0xDE \
+ && ( IN_RANGE(NATIVE_TO_LATIN1((U8) c), \
+ 0xC0, 0xDE) \
&& NATIVE_TO_LATIN1((U8) c) != 0xD7)))
# define isWORDCHAR_L1(c) (isIDFIRST_L1(c) || isDIGIT_A(c))
# define isIDFIRST_L1(c) (isALPHA_L1(c) || NATIVE_TO_LATIN1(c) == '_')
#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) */
+ work because the _MOD does not apply in the ASCII range).
+
+ These actually are UTF-8 invariant casing, not just ASCII, as any non-ASCII
+ UTF-8 invariants are neither upper nor lower. (Only on EBCDIC platforms are
+ there non-ASCII invariants, and all of them are controls.) */
#define toLOWER(c) (isUPPER(c) ? (U8)((c) + ('a' - 'A')) : (c))
#define toUPPER(c) (isLOWER(c) ? (U8)((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 */
+ * this detail. Actually this works for all UTF-8 invariants, not just the
+ * ASCII range. (EBCDIC platforms can have non-ASCII invariants.) */
#define toFOLD(c) toLOWER(c)
#define toTITLE(c) toUPPER(c)
|| (char)(c) == '_'))
/* These next three are also for internal core Perl use only: case-change
- * helper macros */
+ * helper macros. The reason for using the PL_latin arrays is in case the
+ * system function is defective; it ensures uniform results that conform to the
+ * Unicod standard. It does not handle the anomalies in UTF-8 Turkic locales */
#define _generic_toLOWER_LC(c, function, cast) (! FITS_IN_8_BITS(c) \
? (c) \
: (IN_UTF8_CTYPE_LOCALE) \
? PL_latin1_lc[ (U8) (c) ] \
- : (cast)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
* SMALL LETTER SHARP S in a UTF-8 locale (which should be a string of two
* values "SS"); instead it asserts against that under DEBUGGING, and
- * otherwise returns its input */
+ * otherwise returns its input. It does not handle the anomalies in UTF-8
+ * Turkic locales. */
#define _generic_toUPPER_LC(c, function, cast) \
(! FITS_IN_8_BITS(c) \
? (c) \
* returns a single value, so can't adequately return the fold case of LATIN
* SMALL LETTER SHARP S in a UTF-8 locale (which should be a string of two
* values "ss"); instead it asserts against that under DEBUGGING, and
- * otherwise returns its input */
+ * otherwise returns its input. It does not handle the anomalies in UTF-8
+ * Turkic locales */
#define _generic_toFOLD_LC(c, function, cast) \
((UNLIKELY((c) == MICRO_SIGN) && IN_UTF8_CTYPE_LOCALE) \
? GREEK_SMALL_LETTER_MU \
* number defined earlier in this file. _generic_uvchr() is used for POSIX
* classes where there is a macro or function 'above_latin1' that takes the
* single argument 'c' and returns the desired value. These exist for those
- * classes which have simple definitions, avoiding the overhead of a hash
- * lookup or inversion list binary search. _generic_swash_uvchr() can be used
+ * classes which have simple definitions, avoiding the overhead of an inversion
+ * list binary search. _generic_invlist_uvchr() can be used
* for classes where that overhead is faster than a direct lookup.
* _generic_uvchr() won't compile if 'c' isn't unsigned, as it won't match the
* 'above_latin1' prototype. _generic_isCC() macro does bounds checking, so
#define _generic_uvchr(classnum, above_latin1, c) ((c) < 256 \
? _generic_isCC(c, classnum) \
: above_latin1(c))
-#define _generic_swash_uvchr(classnum, c) ((c) < 256 \
+#define _generic_invlist_uvchr(classnum, c) ((c) < 256 \
? _generic_isCC(c, classnum) \
: _is_uni_FOO(classnum, c))
-#define isALPHA_uvchr(c) _generic_swash_uvchr(_CC_ALPHA, c)
-#define isALPHANUMERIC_uvchr(c) _generic_swash_uvchr(_CC_ALPHANUMERIC, c)
+#define isALPHA_uvchr(c) _generic_invlist_uvchr(_CC_ALPHA, c)
+#define isALPHANUMERIC_uvchr(c) _generic_invlist_uvchr(_CC_ALPHANUMERIC, c)
#define isASCII_uvchr(c) isASCII(c)
#define isBLANK_uvchr(c) _generic_uvchr(_CC_BLANK, is_HORIZWS_cp_high, c)
#define isCNTRL_uvchr(c) isCNTRL_L1(c) /* All controls are in Latin1 */
-#define isDIGIT_uvchr(c) _generic_swash_uvchr(_CC_DIGIT, c)
-#define isGRAPH_uvchr(c) _generic_swash_uvchr(_CC_GRAPH, c)
+#define isDIGIT_uvchr(c) _generic_invlist_uvchr(_CC_DIGIT, c)
+#define isGRAPH_uvchr(c) _generic_invlist_uvchr(_CC_GRAPH, c)
#define isIDCONT_uvchr(c) \
_generic_uvchr(_CC_WORDCHAR, _is_uni_perl_idcont, c)
#define isIDFIRST_uvchr(c) \
_generic_uvchr(_CC_IDFIRST, _is_uni_perl_idstart, c)
-#define isLOWER_uvchr(c) _generic_swash_uvchr(_CC_LOWER, c)
-#define isPRINT_uvchr(c) _generic_swash_uvchr(_CC_PRINT, c)
+#define isLOWER_uvchr(c) _generic_invlist_uvchr(_CC_LOWER, c)
+#define isPRINT_uvchr(c) _generic_invlist_uvchr(_CC_PRINT, c)
-#define isPUNCT_uvchr(c) _generic_swash_uvchr(_CC_PUNCT, c)
+#define isPUNCT_uvchr(c) _generic_invlist_uvchr(_CC_PUNCT, c)
#define isSPACE_uvchr(c) _generic_uvchr(_CC_SPACE, is_XPERLSPACE_cp_high, c)
#define isPSXSPC_uvchr(c) isSPACE_uvchr(c)
-#define isUPPER_uvchr(c) _generic_swash_uvchr(_CC_UPPER, c)
+#define isUPPER_uvchr(c) _generic_invlist_uvchr(_CC_UPPER, c)
#define isVERTWS_uvchr(c) _generic_uvchr(_CC_VERTSPACE, is_VERTWS_cp_high, c)
-#define isWORDCHAR_uvchr(c) _generic_swash_uvchr(_CC_WORDCHAR, c)
+#define isWORDCHAR_uvchr(c) _generic_invlist_uvchr(_CC_WORDCHAR, c)
#define isXDIGIT_uvchr(c) _generic_uvchr(_CC_XDIGIT, is_XDIGIT_cp_high, c)
#define toFOLD_uvchr(c,s,l) to_uni_fold(c,s,l)
* _generic_uvchr, so see it for more info. */
#define _generic_LC_uvchr(latin1, above_latin1, c) \
(c < 256 ? latin1(c) : above_latin1(c))
-#define _generic_LC_swash_uvchr(latin1, classnum, c) \
+#define _generic_LC_invlist_uvchr(latin1, classnum, c) \
(c < 256 ? latin1(c) : _is_uni_FOO(classnum, c))
-#define isALPHA_LC_uvchr(c) _generic_LC_swash_uvchr(isALPHA_LC, _CC_ALPHA, c)
-#define isALPHANUMERIC_LC_uvchr(c) _generic_LC_swash_uvchr(isALPHANUMERIC_LC, \
+#define isALPHA_LC_uvchr(c) _generic_LC_invlist_uvchr(isALPHA_LC, _CC_ALPHA, c)
+#define isALPHANUMERIC_LC_uvchr(c) _generic_LC_invlist_uvchr(isALPHANUMERIC_LC, \
_CC_ALPHANUMERIC, c)
#define isASCII_LC_uvchr(c) isASCII_LC(c)
#define isBLANK_LC_uvchr(c) _generic_LC_uvchr(isBLANK_LC, \
is_HORIZWS_cp_high, 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 isDIGIT_LC_uvchr(c) _generic_LC_invlist_uvchr(isDIGIT_LC, _CC_DIGIT, c)
+#define isGRAPH_LC_uvchr(c) _generic_LC_invlist_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 isPRINT_LC_uvchr(c) _generic_LC_swash_uvchr(isPRINT_LC, _CC_PRINT, c)
+#define isLOWER_LC_uvchr(c) _generic_LC_invlist_uvchr(isLOWER_LC, _CC_LOWER, c)
+#define isPRINT_LC_uvchr(c) _generic_LC_invlist_uvchr(isPRINT_LC, _CC_PRINT, c)
#define isPSXSPC_LC_uvchr(c) isSPACE_LC_uvchr(c)
-#define isPUNCT_LC_uvchr(c) _generic_LC_swash_uvchr(isPUNCT_LC, _CC_PUNCT, c)
+#define isPUNCT_LC_uvchr(c) _generic_LC_invlist_uvchr(isPUNCT_LC, _CC_PUNCT, c)
#define isSPACE_LC_uvchr(c) _generic_LC_uvchr(isSPACE_LC, \
is_XPERLSPACE_cp_high, c)
-#define isUPPER_LC_uvchr(c) _generic_LC_swash_uvchr(isUPPER_LC, _CC_UPPER, c)
-#define isWORDCHAR_LC_uvchr(c) _generic_LC_swash_uvchr(isWORDCHAR_LC, \
+#define isUPPER_LC_uvchr(c) _generic_LC_invlist_uvchr(isUPPER_LC, _CC_UPPER, c)
+#define isWORDCHAR_LC_uvchr(c) _generic_LC_invlist_uvchr(isWORDCHAR_LC, \
_CC_WORDCHAR, c)
#define isXDIGIT_LC_uvchr(c) _generic_LC_uvchr(isXDIGIT_LC, \
is_XDIGIT_cp_high, c)
#define isBLANK_LC_uni(c) isBLANK_LC_uvchr(UNI_TO_NATIVE(c))
-/* For internal core Perl use only: the base macros for defining macros like
- * isALPHA_utf8. These are like the earlier defined macros, but take an input
- * UTF-8 encoded string 'p'. If the input is in the Latin1 range, use
- * the Latin1 macro 'classnum' on 'p'. 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. Note that it assumes that the utf8
- * has been validated, and ignores 'use bytes' */
-#define _base_generic_utf8(enum_name, name, p, use_locale ) \
- _is_utf8_FOO(CAT2(_CC_, enum_name), \
- (const U8 *) p, \
- "is" STRINGIFY(name) "_utf8", \
- "is" STRINGIFY(name) "_utf8_safe", \
- 1, use_locale, __FILE__,__LINE__)
-
-#define _generic_utf8(name, p) _base_generic_utf8(name, name, p, 0)
-
/* The "_safe" macros make sure that we don't attempt to read beyond 'e', but
* they don't otherwise go out of their way to look for malformed UTF-8. If
* they can return accurate results without knowing if the input is otherwise
#endif
#define _generic_utf8_safe(classnum, p, e, above_latin1) \
- (__ASSERT_(_utf8_safe_assert(p, e)) \
- (UTF8_IS_INVARIANT(*(p))) \
+ ((! _utf8_safe_assert(p, e)) \
+ ? (_force_out_malformed_utf8_message((U8 *) (p), (U8 *) (e), 0, 1), 0)\
+ : (UTF8_IS_INVARIANT(*(p))) \
? _generic_isCC(*(p), classnum) \
: (UTF8_IS_DOWNGRADEABLE_START(*(p)) \
? ((LIKELY((e) - (p) > 1 && UTF8_IS_CONTINUATION(*((p)+1)))) \
* 'above_latin1' can be a macro */
#define _generic_func_utf8_safe(classnum, above_latin1, p, e) \
_generic_utf8_safe(classnum, p, e, above_latin1(p, e))
-#define _generic_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+#define _generic_non_invlist_utf8_safe(classnum, above_latin1, p, e) \
_generic_utf8_safe(classnum, p, e, \
(UNLIKELY((e) - (p) < UTF8SKIP(p)) \
? (_force_out_malformed_utf8_message( \
: above_latin1(p)))
/* Like the above, but passes classnum to _isFOO_utf8(), instead of having an
* 'above_latin1' parameter */
-#define _generic_swash_utf8_safe(classnum, p, e) \
-_generic_utf8_safe(classnum, p, e, _is_utf8_FOO_with_len(classnum, p, e))
+#define _generic_invlist_utf8_safe(classnum, p, e) \
+ _generic_utf8_safe(classnum, p, e, _is_utf8_FOO(classnum, p, e))
/* Like the above, but should be used only when it is known that there are no
* characters in the upper-Latin1 range (128-255 on ASCII platforms) which the
? 0 /* Note that doesn't check validity for latin1 */ \
: above_latin1)
-/* NOTE that some of these macros have very similar ones in regcharclass.h.
- * For example, there is (at the time of this writing) an 'is_SPACE_utf8()'
- * there, differing in name only by an underscore from the one here
- * 'isSPACE_utf8(). The difference is that the ones here are probably more
- * efficient and smaller, using an O(1) array lookup for Latin1-range code
- * points; the regcharclass.h ones are implemented as a series of
- * "if-else-if-else ..." */
-
-#define isALPHA_utf8(p) _generic_utf8(ALPHA, p)
-#define isALPHANUMERIC_utf8(p) _generic_utf8(ALPHANUMERIC, p)
-#define isASCII_utf8(p) _generic_utf8(ASCII, p)
-#define isBLANK_utf8(p) _generic_utf8(BLANK, p)
-#define isCNTRL_utf8(p) _generic_utf8(CNTRL, p)
-#define isDIGIT_utf8(p) _generic_utf8(DIGIT, p)
-#define isGRAPH_utf8(p) _generic_utf8(GRAPH, p)
-#define isIDCONT_utf8(p) _generic_utf8(IDCONT, p)
-#define isIDFIRST_utf8(p) _generic_utf8(IDFIRST, p)
-#define isLOWER_utf8(p) _generic_utf8(LOWER, p)
-#define isPRINT_utf8(p) _generic_utf8(PRINT, p)
-#define isPSXSPC_utf8(p) _generic_utf8(PSXSPC, p)
-#define isPUNCT_utf8(p) _generic_utf8(PUNCT, p)
-#define isSPACE_utf8(p) _generic_utf8(SPACE, p)
-#define isUPPER_utf8(p) _generic_utf8(UPPER, p)
-#define isVERTWS_utf8(p) _generic_utf8(VERTSPACE, p)
-#define isWORDCHAR_utf8(p) _generic_utf8(WORDCHAR, p)
-#define isXDIGIT_utf8(p) _generic_utf8(XDIGIT, p)
-
-#define isALPHA_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_ALPHA, p, e)
+
+#define isALPHA_utf8(p, e) isALPHA_utf8_safe(p, e)
+#define isALPHANUMERIC_utf8(p, e) isALPHANUMERIC_utf8_safe(p, e)
+#define isASCII_utf8(p, e) isASCII_utf8_safe(p, e)
+#define isBLANK_utf8(p, e) isBLANK_utf8_safe(p, e)
+#define isCNTRL_utf8(p, e) isCNTRL_utf8_safe(p, e)
+#define isDIGIT_utf8(p, e) isDIGIT_utf8_safe(p, e)
+#define isGRAPH_utf8(p, e) isGRAPH_utf8_safe(p, e)
+#define isIDCONT_utf8(p, e) isIDCONT_utf8_safe(p, e)
+#define isIDFIRST_utf8(p, e) isIDFIRST_utf8_safe(p, e)
+#define isLOWER_utf8(p, e) isLOWER_utf8_safe(p, e)
+#define isPRINT_utf8(p, e) isPRINT_utf8_safe(p, e)
+#define isPSXSPC_utf8(p, e) isPSXSPC_utf8_safe(p, e)
+#define isPUNCT_utf8(p, e) isPUNCT_utf8_safe(p, e)
+#define isSPACE_utf8(p, e) isSPACE_utf8_safe(p, e)
+#define isUPPER_utf8(p, e) isUPPER_utf8_safe(p, e)
+#define isVERTWS_utf8(p, e) isVERTWS_utf8_safe(p, e)
+#define isWORDCHAR_utf8(p, e) isWORDCHAR_utf8_safe(p, e)
+#define isXDIGIT_utf8(p, e) isXDIGIT_utf8_safe(p, e)
+
+#define isALPHA_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_ALPHA, p, e)
#define isALPHANUMERIC_utf8_safe(p, e) \
- _generic_swash_utf8_safe(_CC_ALPHANUMERIC, p, e)
+ _generic_invlist_utf8_safe(_CC_ALPHANUMERIC, p, e)
#define isASCII_utf8_safe(p, e) \
/* Because ASCII is invariant under utf8, the non-utf8 macro \
* works */ \
(__ASSERT_(_utf8_safe_assert(p, e)) isASCII(*(p)))
#define isBLANK_utf8_safe(p, e) \
- _generic_non_swash_utf8_safe(_CC_BLANK, is_HORIZWS_high, p, e)
+ _generic_non_invlist_utf8_safe(_CC_BLANK, is_HORIZWS_high, p, e)
#ifdef EBCDIC
/* Because all controls are UTF-8 invariants in EBCDIC, we can use this
#define isDIGIT_utf8_safe(p, e) \
_generic_utf8_safe_no_upper_latin1(_CC_DIGIT, p, e, \
- _is_utf8_FOO_with_len(_CC_DIGIT, p, e))
-#define isGRAPH_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_GRAPH, p, e)
+ _is_utf8_FOO(_CC_DIGIT, p, e))
+#define isGRAPH_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_GRAPH, p, e)
#define isIDCONT_utf8_safe(p, e) _generic_func_utf8_safe(_CC_WORDCHAR, \
- _is_utf8_perl_idcont_with_len, p, e)
+ _is_utf8_perl_idcont, p, e)
/* To prevent S_scan_word in toke.c from hanging, we have to make sure that
* IDFIRST is an alnum. See
- * http://rt.perl.org/rt3/Ticket/Display.html?id=74022 for more detail than you
+ * https://github.com/Perl/perl5/issues/10275 for more detail than you
* ever wanted to know about. (In the ASCII range, there isn't a difference.)
* This used to be not the XID version, but we decided to go with the more
* modern Unicode definition */
#define isIDFIRST_utf8_safe(p, e) \
_generic_func_utf8_safe(_CC_IDFIRST, \
- _is_utf8_perl_idstart_with_len, (U8 *) (p), (U8 *) (e))
+ _is_utf8_perl_idstart, (U8 *) (p), (U8 *) (e))
-#define isLOWER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_LOWER, p, e)
-#define isPRINT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PRINT, p, e)
+#define isLOWER_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_LOWER, p, e)
+#define isPRINT_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_PRINT, p, e)
#define isPSXSPC_utf8_safe(p, e) isSPACE_utf8_safe(p, e)
-#define isPUNCT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PUNCT, p, e)
+#define isPUNCT_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_PUNCT, p, e)
#define isSPACE_utf8_safe(p, e) \
- _generic_non_swash_utf8_safe(_CC_SPACE, is_XPERLSPACE_high, p, e)
-#define isUPPER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_UPPER, p, e)
+ _generic_non_invlist_utf8_safe(_CC_SPACE, is_XPERLSPACE_high, p, e)
+#define isUPPER_utf8_safe(p, e) _generic_invlist_utf8_safe(_CC_UPPER, p, e)
#define isVERTWS_utf8_safe(p, e) \
- _generic_non_swash_utf8_safe(_CC_VERTSPACE, is_VERTWS_high, p, e)
+ _generic_non_invlist_utf8_safe(_CC_VERTSPACE, is_VERTWS_high, p, e)
#define isWORDCHAR_utf8_safe(p, e) \
- _generic_swash_utf8_safe(_CC_WORDCHAR, p, e)
+ _generic_invlist_utf8_safe(_CC_WORDCHAR, p, e)
#define isXDIGIT_utf8_safe(p, e) \
_generic_utf8_safe_no_upper_latin1(_CC_XDIGIT, p, e, \
(UNLIKELY((e) - (p) < UTF8SKIP(p)) \
(U8 *) (p), (U8 *) (e), 0, 1), 0) \
: is_XDIGIT_high(p)))
-#define toFOLD_utf8(p,s,l) to_utf8_fold(p,s,l)
-#define toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l)
-#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 toFOLD_utf8(p,e,s,l) toFOLD_utf8_safe(p,e,s,l)
+#define toLOWER_utf8(p,e,s,l) toLOWER_utf8_safe(p,e,s,l)
+#define toTITLE_utf8(p,e,s,l) toTITLE_utf8_safe(p,e,s,l)
+#define toUPPER_utf8(p,e,s,l) toUPPER_utf8_safe(p,e,s,l)
/* For internal core use only, subject to change */
-#define _toFOLD_utf8_flags(p,e,s,l,f) _to_utf8_fold_flags (p,e,s,l,f, "", 0)
-#define _toLOWER_utf8_flags(p,e,s,l,f) _to_utf8_lower_flags(p,e,s,l,f, "", 0)
-#define _toTITLE_utf8_flags(p,e,s,l,f) _to_utf8_title_flags(p,e,s,l,f, "", 0)
-#define _toUPPER_utf8_flags(p,e,s,l,f) _to_utf8_upper_flags(p,e,s,l,f, "", 0)
+#define _toFOLD_utf8_flags(p,e,s,l,f) _to_utf8_fold_flags (p,e,s,l,f)
+#define _toLOWER_utf8_flags(p,e,s,l,f) _to_utf8_lower_flags(p,e,s,l,f)
+#define _toTITLE_utf8_flags(p,e,s,l,f) _to_utf8_title_flags(p,e,s,l,f)
+#define _toUPPER_utf8_flags(p,e,s,l,f) _to_utf8_upper_flags(p,e,s,l,f)
#define toFOLD_utf8_safe(p,e,s,l) _toFOLD_utf8_flags(p,e,s,l, FOLD_FLAGS_FULL)
#define toLOWER_utf8_safe(p,e,s,l) _toLOWER_utf8_flags(p,e,s,l, 0)
#define toTITLE_utf8_safe(p,e,s,l) _toTITLE_utf8_flags(p,e,s,l, 0)
#define toUPPER_utf8_safe(p,e,s,l) _toUPPER_utf8_flags(p,e,s,l, 0)
-/* For internal core Perl use only: the base macros for defining macros like
- * isALPHA_LC_utf8. These are like _generic_utf8, but if the first code point
- * in 'p' is within the 0-255 range, it uses locale rules from the passed-in
- * 'macro' parameter */
-#define _generic_LC_utf8(name, p) _base_generic_utf8(name, name, p, 1)
-
-#define isALPHA_LC_utf8(p) _generic_LC_utf8(ALPHA, p)
-#define isALPHANUMERIC_LC_utf8(p) _generic_LC_utf8(ALPHANUMERIC, p)
-#define isASCII_LC_utf8(p) _generic_LC_utf8(ASCII, p)
-#define isBLANK_LC_utf8(p) _generic_LC_utf8(BLANK, p)
-#define isCNTRL_LC_utf8(p) _generic_LC_utf8(CNTRL, p)
-#define isDIGIT_LC_utf8(p) _generic_LC_utf8(DIGIT, p)
-#define isGRAPH_LC_utf8(p) _generic_LC_utf8(GRAPH, p)
-#define isIDCONT_LC_utf8(p) _generic_LC_utf8(IDCONT, p)
-#define isIDFIRST_LC_utf8(p) _generic_LC_utf8(IDFIRST, p)
-#define isLOWER_LC_utf8(p) _generic_LC_utf8(LOWER, p)
-#define isPRINT_LC_utf8(p) _generic_LC_utf8(PRINT, p)
-#define isPSXSPC_LC_utf8(p) _generic_LC_utf8(PSXSPC, p)
-#define isPUNCT_LC_utf8(p) _generic_LC_utf8(PUNCT, p)
-#define isSPACE_LC_utf8(p) _generic_LC_utf8(SPACE, p)
-#define isUPPER_LC_utf8(p) _generic_LC_utf8(UPPER, p)
-#define isWORDCHAR_LC_utf8(p) _generic_LC_utf8(WORDCHAR, p)
-#define isXDIGIT_LC_utf8(p) _generic_LC_utf8(XDIGIT, p)
+#define isALPHA_LC_utf8(p, e) isALPHA_LC_utf8_safe(p, e)
+#define isALPHANUMERIC_LC_utf8(p, e) isALPHANUMERIC_LC_utf8_safe(p, e)
+#define isASCII_LC_utf8(p, e) isASCII_LC_utf8_safe(p, e)
+#define isBLANK_LC_utf8(p, e) isBLANK_LC_utf8_safe(p, e)
+#define isCNTRL_LC_utf8(p, e) isCNTRL_LC_utf8_safe(p, e)
+#define isDIGIT_LC_utf8(p, e) isDIGIT_LC_utf8_safe(p, e)
+#define isGRAPH_LC_utf8(p, e) isGRAPH_LC_utf8_safe(p, e)
+#define isIDCONT_LC_utf8(p, e) isIDCONT_LC_utf8_safe(p, e)
+#define isIDFIRST_LC_utf8(p, e) isIDFIRST_LC_utf8_safe(p, e)
+#define isLOWER_LC_utf8(p, e) isLOWER_LC_utf8_safe(p, e)
+#define isPRINT_LC_utf8(p, e) isPRINT_LC_utf8_safe(p, e)
+#define isPSXSPC_LC_utf8(p, e) isPSXSPC_LC_utf8_safe(p, e)
+#define isPUNCT_LC_utf8(p, e) isPUNCT_LC_utf8_safe(p, e)
+#define isSPACE_LC_utf8(p, e) isSPACE_LC_utf8_safe(p, e)
+#define isUPPER_LC_utf8(p, e) isUPPER_LC_utf8_safe(p, e)
+#define isWORDCHAR_LC_utf8(p, e) isWORDCHAR_LC_utf8_safe(p, e)
+#define isXDIGIT_LC_utf8(p, e) isXDIGIT_LC_utf8_safe(p, e)
/* For internal core Perl use only: the base macros for defining macros like
* isALPHA_LC_utf8_safe. These are like _generic_utf8, but if the first code
(U8 *) (p), (U8 *) (e), 0, 1), 0)) \
: above_latin1))
-#define _generic_LC_swash_utf8_safe(macro, classnum, p, e) \
+#define _generic_LC_invlist_utf8_safe(macro, classnum, p, e) \
_generic_LC_utf8_safe(macro, p, e, \
- _is_utf8_FOO_with_len(classnum, p, e))
+ _is_utf8_FOO(classnum, p, e))
#define _generic_LC_func_utf8_safe(macro, above_latin1, p, e) \
_generic_LC_utf8_safe(macro, p, e, above_latin1(p, e))
-#define _generic_LC_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+#define _generic_LC_non_invlist_utf8_safe(classnum, above_latin1, p, e) \
_generic_LC_utf8_safe(classnum, p, e, \
(UNLIKELY((e) - (p) < UTF8SKIP(p)) \
? (_force_out_malformed_utf8_message( \
: above_latin1(p)))
#define isALPHANUMERIC_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isALPHANUMERIC_LC, \
+ _generic_LC_invlist_utf8_safe(isALPHANUMERIC_LC, \
_CC_ALPHANUMERIC, p, e)
#define isALPHA_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isALPHA_LC, _CC_ALPHA, p, e)
+ _generic_LC_invlist_utf8_safe(isALPHA_LC, _CC_ALPHA, p, e)
#define isASCII_LC_utf8_safe(p, e) \
(__ASSERT_(_utf8_safe_assert(p, e)) isASCII_LC(*(p)))
#define isBLANK_LC_utf8_safe(p, e) \
- _generic_LC_non_swash_utf8_safe(isBLANK_LC, is_HORIZWS_high, p, e)
+ _generic_LC_non_invlist_utf8_safe(isBLANK_LC, is_HORIZWS_high, p, e)
#define isCNTRL_LC_utf8_safe(p, e) \
_generic_LC_utf8_safe(isCNTRL_LC, p, e, 0)
#define isDIGIT_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isDIGIT_LC, _CC_DIGIT, p, e)
+ _generic_LC_invlist_utf8_safe(isDIGIT_LC, _CC_DIGIT, p, e)
#define isGRAPH_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isGRAPH_LC, _CC_GRAPH, p, e)
+ _generic_LC_invlist_utf8_safe(isGRAPH_LC, _CC_GRAPH, p, e)
#define isIDCONT_LC_utf8_safe(p, e) \
_generic_LC_func_utf8_safe(isIDCONT_LC, \
- _is_utf8_perl_idcont_with_len, p, e)
+ _is_utf8_perl_idcont, p, e)
#define isIDFIRST_LC_utf8_safe(p, e) \
_generic_LC_func_utf8_safe(isIDFIRST_LC, \
- _is_utf8_perl_idstart_with_len, p, e)
+ _is_utf8_perl_idstart, p, e)
#define isLOWER_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isLOWER_LC, _CC_LOWER, p, e)
+ _generic_LC_invlist_utf8_safe(isLOWER_LC, _CC_LOWER, p, e)
#define isPRINT_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isPRINT_LC, _CC_PRINT, p, e)
+ _generic_LC_invlist_utf8_safe(isPRINT_LC, _CC_PRINT, p, e)
#define isPSXSPC_LC_utf8_safe(p, e) isSPACE_LC_utf8_safe(p, e)
#define isPUNCT_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isPUNCT_LC, _CC_PUNCT, p, e)
+ _generic_LC_invlist_utf8_safe(isPUNCT_LC, _CC_PUNCT, p, e)
#define isSPACE_LC_utf8_safe(p, e) \
- _generic_LC_non_swash_utf8_safe(isSPACE_LC, is_XPERLSPACE_high, p, e)
+ _generic_LC_non_invlist_utf8_safe(isSPACE_LC, is_XPERLSPACE_high, p, e)
#define isUPPER_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isUPPER_LC, _CC_UPPER, p, e)
+ _generic_LC_invlist_utf8_safe(isUPPER_LC, _CC_UPPER, p, e)
#define isWORDCHAR_LC_utf8_safe(p, e) \
- _generic_LC_swash_utf8_safe(isWORDCHAR_LC, _CC_WORDCHAR, p, e)
+ _generic_LC_invlist_utf8_safe(isWORDCHAR_LC, _CC_WORDCHAR, p, e)
#define isXDIGIT_LC_utf8_safe(p, e) \
- _generic_LC_non_swash_utf8_safe(isXDIGIT_LC, is_XDIGIT_high, p, e)
+ _generic_LC_non_invlist_utf8_safe(isXDIGIT_LC, is_XDIGIT_high, p, e)
/* Macros for backwards compatibility and for completeness when the ASCII and
* Latin1 values are identical */
#define isOCTAL_L1(c) isOCTAL_A(c)
#define isXDIGIT_L1(c) isXDIGIT_A(c)
#define isALNUM(c) isWORDCHAR(c)
+#define isALNUM_A(c) isALNUM(c)
#define isALNUMU(c) isWORDCHAR_L1(c)
#define isALNUM_LC(c) isWORDCHAR_LC(c)
#define isALNUM_uni(c) isWORDCHAR_uni(c)
#define isALNUM_LC_uvchr(c) isWORDCHAR_LC_uvchr(c)
-#define isALNUM_utf8(p) isWORDCHAR_utf8(p)
-#define isALNUM_LC_utf8(p) isWORDCHAR_LC_utf8(p)
+#define isALNUM_utf8(p,e) isWORDCHAR_utf8(p,e)
+#define isALNUM_utf8_safe(p,e) isWORDCHAR_utf8_safe(p,e)
+#define isALNUM_LC_utf8(p,e)isWORDCHAR_LC_utf8(p,e)
+#define isALNUM_LC_utf8_safe(p,e)isWORDCHAR_LC_utf8_safe(p,e)
#define isALNUMC_A(c) isALPHANUMERIC_A(c) /* Mnemonic: "C's alnum" */
#define isALNUMC_L1(c) isALPHANUMERIC_L1(c)
#define isALNUMC(c) isALPHANUMERIC(c)
#define isALNUMC_LC(c) isALPHANUMERIC_LC(c)
#define isALNUMC_uni(c) isALPHANUMERIC_uni(c)
#define isALNUMC_LC_uvchr(c) isALPHANUMERIC_LC_uvchr(c)
-#define isALNUMC_utf8(p) isALPHANUMERIC_utf8(p)
-#define isALNUMC_LC_utf8(p) isALPHANUMERIC_LC_utf8(p)
+#define isALNUMC_utf8(p,e) isALPHANUMERIC_utf8(p,e)
+#define isALNUMC_utf8_safe(p,e) isALPHANUMERIC_utf8_safe(p,e)
+#define isALNUMC_LC_utf8_safe(p,e) isALPHANUMERIC_LC_utf8_safe(p,e)
/* On EBCDIC platforms, 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
} \
return a;
-/* Converts a character known to represent a hexadecimal digit (0-9, A-F, or
- * a-f) to its numeric value. READ_XDIGIT's argument is a string pointer,
- * which is advanced. The input is validated only by an assert() in DEBUGGING
- * builds. In both ASCII and EBCDIC the last 4 bits of the digits are 0-9; and
- * the last 4 bits of A-F and a-f are 1-6, so adding 9 yields 10-15 */
-#define XDIGIT_VALUE(c) (__ASSERT_(isXDIGIT(c)) (0xf & (isDIGIT(c) \
- ? (c) \
- : ((c) + 9))))
-#define READ_XDIGIT(s) (__ASSERT_(isXDIGIT(*s)) (0xf & (isDIGIT(*(s)) \
- ? (*(s)++) \
- : (*(s)++ + 9))))
+/* Converts a character KNOWN to represent a hexadecimal digit (0-9, A-F, or
+ * a-f) to its numeric value without using any branches. The input is
+ * validated only by an assert() in DEBUGGING builds.
+ *
+ * It works by right shifting and isolating the bit that is 0 for the digits,
+ * and 1 for at least the alphas A-F, a-f. The bit is shifted to the ones
+ * position, and then to the eights position. Both are added together to form
+ * 0 if the input is '0'-'9' and to form 9 if alpha. This is added to the
+ * final four bits of the input to form the correct value. */
+#define XDIGIT_VALUE(c) (__ASSERT_(isXDIGIT(c)) \
+ ((NATIVE_TO_LATIN1(c) >> 6) & 1) /* 1 if alpha; 0 if not */ \
+ + ((NATIVE_TO_LATIN1(c) >> 3) & 8) /* 8 if alpha; 0 if not */ \
+ + ((c) & 0xF)) /* 0-9 if input valid hex digit */
+
+/* The argument is a string pointer, which is advanced. */
+#define READ_XDIGIT(s) ((s)++, XDIGIT_VALUE(*((s) - 1)))
/* Converts a character known to represent an octal digit (0-7) to its numeric
* value. The input is validated only by an assert() in DEBUGGING builds. In
#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];
+ * case-insensitively. 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.
#define isALPHA_FOLD_NE(c1, c2) (! isALPHA_FOLD_EQ((c1), (c2)))
/*
-=head1 Memory Management
+=for apidoc_section $memory
=for apidoc Am|void|Newx|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<malloc> function.
This should B<ONLY> be used on memory obtained using L</"Newx"> and friends.
+=for apidoc_section $string
=for apidoc Am|void|Move|void* src|void* dest|int nitems|type
The XSUB-writer's interface to the C C<memmove> function. The C<src> is the
source, C<dest> is the destination, C<nitems> is the number of items, and
for encouraging compilers to tail-call
optimise.
-=for apidoc Am|void|StructCopy|type *src|type *dest|type
+=for apidoc_section $utility
+=for apidoc Amu|void|StructCopy|type *src|type *dest|type
This is an architecture-independent macro to copy one structure to another.
=for apidoc Am|void|PoisonWith|void* dest|int nitems|type|U8 byte
(void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,t)) \
&& (Perl_croak_nocontext("%s",(a)),0))
+/* "a" arg must be a string literal */
+# define MEM_WRAP_CHECK_s(n,t,a) \
+ (void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,t)) \
+ && (Perl_croak_nocontext("" 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), _PERL_STRLEN_ROUNDUP_UNCHECKED(n))
#define MEM_WRAP_CHECK(n,t)
#define MEM_WRAP_CHECK_1(n,t,a)
-#define MEM_WRAP_CHECK_2(n,t,a,b)
+#define MEM_WRAP_CHECK_s(n,t,a)
#define MEM_WRAP_CHECK_(n,t)
#define PERL_STRLEN_ROUNDUP(n) _PERL_STRLEN_ROUNDUP_UNCHECKED(n)
#define Safefree(d) safefree(MEM_LOG_FREE((Malloc_t)(d)))
#endif
+/* assert that a valid ptr has been supplied - use this instead of assert(ptr) *
+ * as it handles cases like constant string arguments without throwing warnings *
+ * the cast is required, as is the inequality check, to avoid warnings */
#define perl_assert_ptr(p) assert( ((void*)(p)) != 0 )
#define Copy(s,d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), perl_assert_ptr(s), (void)memcpy((char*)(d),(const char*)(s), (n) * sizeof(t)))
#define Zero(d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), (void)memzero((char*)(d), (n) * sizeof(t)))
+/* Like above, but returns a pointer to 'd' */
#define MoveD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), perl_assert_ptr(s), memmove((char*)(d),(const char*)(s), (n) * sizeof(t)))
#define CopyD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), perl_assert_ptr(s), memcpy((char*)(d),(const char*)(s), (n) * sizeof(t)))
#define ZeroD(d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), memzero((char*)(d), (n) * sizeof(t)))
#define StructCopy(s,d,t) (*((t*)(d)) = *((t*)(s)))
-/* C_ARRAY_LENGTH is the number of elements in the C array (so you
- * want your zero-based indices to be less than but not equal to).
- *
- * C_ARRAY_END is one past the last: half-open/half-closed range,
- * not last-inclusive range. */
+/*
+=for apidoc_section $utility
+
+=for apidoc Am|STRLEN|C_ARRAY_LENGTH|void *a
+
+Returns the number of elements in the input C array (so you want your
+zero-based indices to be less than but not equal to).
+
+=for apidoc Am|void *|C_ARRAY_END|void *a
+
+Returns a pointer to one element past the final element of the input C array.
+
+=cut
+
+C_ARRAY_END is one past the last: half-open/half-closed range, not
+last-inclusive range.
+*/
#define C_ARRAY_LENGTH(a) (sizeof(a)/sizeof((a)[0]))
#define C_ARRAY_END(a) ((a) + C_ARRAY_LENGTH(a))
https://perl5.git.perl.org / perl5.git / blobdiff