/* IMPORTANT NOTE: Everything whose name begins with an underscore is for
* internal core Perl use only. */
-#ifndef HANDY_H /* Guard against nested #inclusion */
-#define HANDY_H
-
-#if !defined(__STDC__)
-#ifdef NULL
-#undef NULL
-#endif
-# define NULL 0
-#endif
+#ifndef PERL_HANDY_H_ /* Guard against nested #inclusion */
+#define PERL_HANDY_H_
#ifndef PERL_CORE
# define Null(type) ((type)NULL)
* 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). */
+# define FUNCTION__ ""
#else
-# if (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). */
-# define FUNCTION__ ""
-# else
-# define FUNCTION__ __FUNCTION__ /* Common extension. */
-# endif
+# define FUNCTION__ __FUNCTION__ /* Common extension. */
#endif
/* XXX A note on the perl source internal type system. The
typedef U16TYPE U16;
typedef I32TYPE I32;
typedef U32TYPE U32;
-#ifdef PERL_CORE
-# ifdef HAS_QUAD
+
+#ifdef HAS_QUAD
typedef I64TYPE I64;
typedef U64TYPE U64;
-# endif
-#endif /* PERL_CORE */
+#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
# define PeRl_UINT64_C(c) CAT2(c,UI64)
# endif
# ifndef PeRl_INT64_C
-# define PeRl_INT64_C(c) ((I64TYPE)(c)) /* last resort */
-# define PeRl_UINT64_C(c) ((U64TYPE)(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
/* Unused by core; should be deprecated */
#define Ctl(ch) ((ch) & 037)
+#if defined(PERL_CORE) || defined(PERL_EXT)
+# ifndef MIN
+# define MIN(a,b) ((a) < (b) ? (a) : (b))
+# endif
+# ifndef MAX
+# define MAX(a,b) ((a) > (b) ? (a) : (b))
+# endif
+#endif
+
/* This is a helper macro to avoid preprocessor issues, replaced by nothing
* unless under DEBUGGING, where it expands to an assert of its argument,
* followed by a comma (hence the comma operator). If we just used a straight
- * assert(), we would get a comma with nothing before it when not DEBUGGING */
-#ifdef DEBUGGING
+ * 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. */
+
+#if defined(DEBUGGING) && !defined(__COVERITY__)
# define __ASSERT_(statement) assert(statement),
#else
# define __ASSERT_(statement)
=head1 SV-Body Allocation
=for apidoc Ama|SV*|newSVpvs|const char* s
-Like C<newSVpvn>, but takes a literal C<NUL>-terminated string instead of a
+Like C<newSVpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|SV*|newSVpvs_flags|const char* s|U32 flags
-Like C<newSVpvn_flags>, but takes a literal C<NUL>-terminated string instead of
+Like C<newSVpvn_flags>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=for apidoc Ama|SV*|newSVpvs_share|const char* s
-Like C<newSVpvn_share>, but takes a literal C<NUL>-terminated string instead of
+Like C<newSVpvn_share>, but takes a C<NUL>-terminated literal string instead of
a string/length pair and omits the hash parameter.
=for apidoc Am|void|sv_catpvs_flags|SV* sv|const char* s|I32 flags
-Like C<sv_catpvn_flags>, but takes a literal C<NUL>-terminated string instead
+Like C<sv_catpvn_flags>, but takes a C<NUL>-terminated literal string instead
of a string/length pair.
=for apidoc Am|void|sv_catpvs_nomg|SV* sv|const char* s
-Like C<sv_catpvn_nomg>, but takes a literal string instead of a
-string/length pair.
+Like C<sv_catpvn_nomg>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=for apidoc Am|void|sv_catpvs|SV* sv|const char* s
-Like C<sv_catpvn>, but takes a literal string instead of a string/length pair.
+Like C<sv_catpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|void|sv_catpvs_mg|SV* sv|const char* s
-Like C<sv_catpvn_mg>, but takes a literal string instead of a
+Like C<sv_catpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|void|sv_setpvs|SV* sv|const char* s
-Like C<sv_setpvn>, but takes a literal string instead of a string/length pair.
+Like C<sv_setpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|void|sv_setpvs_mg|SV* sv|const char* s
-Like C<sv_setpvn_mg>, but takes a literal string instead of a
+Like C<sv_setpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|SV *|sv_setref_pvs|const char* s
-Like C<sv_setref_pvn>, but takes a literal string instead of a
-string/length pair.
+Like C<sv_setref_pvn>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=head1 Memory Management
=for apidoc Ama|char*|savepvs|const char* s
-Like C<savepvn>, but takes a literal C<NUL>-terminated string instead of a
+Like C<savepvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|char*|savesharedpvs|const char* s
=head1 GV Functions
=for apidoc Am|HV*|gv_stashpvs|const char* name|I32 create
-Like C<gv_stashpvn>, but takes a literal string instead of a string/length pair.
+Like C<gv_stashpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=head1 Hash Manipulation Functions
=for apidoc Am|SV**|hv_fetchs|HV* tb|const char* key|I32 lval
-Like C<hv_fetch>, but takes a literal string instead of a string/length pair.
+Like C<hv_fetch>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|SV**|hv_stores|HV* tb|const char* key|NULLOK SV* val
-Like C<hv_store>, but takes a literal string instead of a string/length pair
+Like C<hv_store>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair
and omits the hash parameter.
=head1 Lexer interface
=for apidoc Amx|void|lex_stuff_pvs|const char *pv|U32 flags
-Like L</lex_stuff_pvn>, but takes a literal string instead of a
-string/length pair.
+Like L</lex_stuff_pvn>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=cut
*/
Perl_gv_fetchpvn_flags(aTHX_ namebeg, len, add, sv_type)
#define sv_catxmlpvs(dsv, str, utf8) \
Perl_sv_catxmlpvn(aTHX_ dsv, STR_WITH_LEN(str), utf8)
-#define hv_fetchs(hv,key,lval) \
- ((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
- (lval) ? (HV_FETCH_JUST_SV | HV_FETCH_LVALUE) \
- : HV_FETCH_JUST_SV, NULL, 0))
-#define hv_stores(hv,key,val) \
- ((SV **)Perl_hv_common(aTHX_ (hv), NULL, STR_WITH_LEN(key), 0, \
- (HV_FETCH_ISSTORE|HV_FETCH_JUST_SV), (val), 0))
#define lex_stuff_pvs(pv,flags) Perl_lex_stuff_pvn(aTHX_ STR_WITH_LEN(pv), flags)
=head1 Miscellaneous Functions
=for apidoc Am|bool|strNE|char* s1|char* s2
-Test two strings to see if they are different. Returns true or
-false.
+Test two C<NUL>-terminated strings to see if they are different. Returns true
+or false.
=for apidoc Am|bool|strEQ|char* s1|char* s2
-Test two strings to see if they are equal. Returns true or false.
+Test two C<NUL>-terminated strings to see if they are equal. Returns true or
+false.
=for apidoc Am|bool|strLT|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is less than the second,
-C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than the
+second, C<s2>. Returns true or false.
=for apidoc Am|bool|strLE|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is less than or equal to the
-second, C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than or
+equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGT|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is greater than the second,
-C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
+the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGE|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is greater than or equal to
-the second, C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
+or equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strnNE|char* s1|char* s2|STRLEN len
-Test two strings to see if they are different. The C<len> parameter
-indicates the number of bytes to compare. Returns true or false. (A
+Test two C<NUL>-terminated strings to see if they are different. The C<len>
+parameter indicates the number of bytes to compare. Returns true or false. (A
wrapper for C<strncmp>).
=for apidoc Am|bool|strnEQ|char* s1|char* s2|STRLEN len
-Test two strings to see if they are equal. The C<len> parameter indicates
-the number of bytes to compare. Returns true or false. (A wrapper for
-C<strncmp>).
+Test two C<NUL>-terminated strings to see if they are equal. The C<len>
+parameter indicates the number of bytes to compare. Returns true or false. (A
+wrapper for C<strncmp>).
+
+=for apidoc Am|bool|memEQ|char* s1|char* s2|STRLEN len
+Test two buffers (which may contain embedded C<NUL> characters, to see if they
+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|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.
=cut
*/
-#define strNE(s1,s2) (strcmp(s1,s2))
-#define strEQ(s1,s2) (!strcmp(s1,s2))
+
+#define strNE(s1,s2) (strcmp(s1,s2) != 0)
+#define strEQ(s1,s2) (strcmp(s1,s2) == 0)
#define strLT(s1,s2) (strcmp(s1,s2) < 0)
#define strLE(s1,s2) (strcmp(s1,s2) <= 0)
#define strGT(s1,s2) (strcmp(s1,s2) > 0)
#define strGE(s1,s2) (strcmp(s1,s2) >= 0)
-#define strnNE(s1,s2,l) (strncmp(s1,s2,l))
-#define strnEQ(s1,s2,l) (!strncmp(s1,s2,l))
-#ifdef HAS_MEMCMP
-# define memNE(s1,s2,l) (memcmp(s1,s2,l))
-# define memEQ(s1,s2,l) (!memcmp(s1,s2,l))
-#else
-# define memNE(s1,s2,l) (bcmp(s1,s2,l))
-# define memEQ(s1,s2,l) (!bcmp(s1,s2,l))
-#endif
+#define strnNE(s1,s2,l) (strncmp(s1,s2,l) != 0)
+#define strnEQ(s1,s2,l) (strncmp(s1,s2,l) == 0)
+#define strBEGINs(s1,s2) (strncmp(s1,"" s2 "", sizeof(s2)-1) == 0)
+
+#define memNE(s1,s2,l) (memcmp(s1,s2,l) != 0)
+#define memEQ(s1,s2,l) (memcmp(s1,s2,l) == 0)
+
+/* memEQ and memNE where second comparand is a string constant */
#define memEQs(s1, l, s2) \
- (sizeof(s2)-1 == l && memEQ(s1, ("" s2 ""), (sizeof(s2)-1)))
-#define memNEs(s1, l, s2) !memEQs(s1, l, s2)
+ (((sizeof(s2)-1) == (l)) && memEQ((s1), ("" s2 ""), (sizeof(s2)-1)))
+#define memNEs(s1, l, s2) (! memEQs(s1, l, s2))
+
+#define memBEGINs(s1, l, s2) \
+ ( (l) >= sizeof(s2) - 1 \
+ && memEQ(s1, "" s2 "", sizeof(s2)-1))
+#define memBEGINPs(s1, l, s2) \
+ ( (l) > sizeof(s2) - 1 \
+ && memEQ(s1, "" s2 "", sizeof(s2)-1))
+#define memENDs(s1, l, s2) \
+ ( (l) >= sizeof(s2) - 1 \
+ && memEQ(s1 + (l) - (sizeof(s2) - 1), "" s2 "", sizeof(s2)-1))
+#define memENDPs(s1, l, s2) \
+ ( (l) > sizeof(s2) \
+ && memEQ(s1 + (l) - (sizeof(s2) - 1), "" s2 "", sizeof(s2)-1))
+
+#define memLT(s1,s2,l) (memcmp(s1,s2,l) < 0)
+#define memLE(s1,s2,l) (memcmp(s1,s2,l) <= 0)
+#define memGT(s1,s2,l) (memcmp(s1,s2,l) > 0)
+#define memGE(s1,s2,l) (memcmp(s1,s2,l) >= 0)
/*
* Character classes.
ASCII character in the named class based on platform, Unicode, and Perl rules.
If the input is a number that doesn't fit in an octet, FALSE is returned.
-Variant C<isFOO_A> (e.g., C<isALPHA_A()>) is identical to the base function
-with no suffix C<"_A">.
+Variant C<isI<FOO>_A> (e.g., C<isALPHA_A()>) is identical to the base function
+with no suffix C<"_A">. This variant is used to emphasize by its name that
+only ASCII-range characters can return TRUE.
-Variant C<isFOO_L1> imposes the Latin-1 (or EBCDIC equivlalent) character set
+Variant C<isI<FOO>_L1> imposes the Latin-1 (or EBCDIC equivalent) character set
onto the platform. That is, the code points that are ASCII are unaffected,
since ASCII is a subset of Latin-1. But the non-ASCII code points are treated
as if they are Latin-1 characters. For example, C<isWORDCHAR_L1()> will return
true when called with the code point 0xDF, which is a word character in both
ASCII and EBCDIC (though it represents different characters in each).
-Variant C<isFOO_uni> is like the C<isFOO_L1> variant, but accepts any UV code
+Variant C<isI<FOO>_uvchr> is like the C<isI<FOO>_L1> variant, but accepts any UV code
point as input. If the code point is larger than 255, Unicode rules are used
to determine if it is in the character class. For example,
-C<isWORDCHAR_uni(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
+C<isWORDCHAR_uvchr(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
WITH MACRON in Unicode, and is a word character.
-Variant C<isFOO_utf8> is like C<isFOO_uni>, but the input is a pointer to a
-(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
-classification of just the first (possibly multi-byte) character in the string
-is tested.
-
-Variant C<isFOO_LC> is like the C<isFOO_A> and C<isFOO_L1> variants, but the
+Variant C<isI<FOO>_utf8_safe> is like C<isI<FOO>_uvchr>, but is used for UTF-8
+encoded strings. Each call classifies one character, even if the string
+contains many. This variant takes two parameters. The first, C<p>, is a
+pointer to the first byte of the character to be classified. (Recall that it
+may take more than one byte to represent a character in UTF-8 strings.) The
+second parameter, C<e>, points to anywhere in the string beyond the first
+character, up to one byte past the end of the entire string. The suffix
+C<_safe> in the function's name indicates that it will not attempt to read
+beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
+is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
+character is malformed in some way, the program may croak, or the function may
+return FALSE, at the discretion of the implementation, and subject to change in
+future releases.
+
+Variant C<isI<FOO>_utf8> is like C<isI<FOO>_utf8_safe>, but takes just a single
+parameter, C<p>, which has the same meaning as the corresponding parameter does
+in C<isI<FOO>_utf8_safe>. The function therefore can't check if it is reading
+beyond the end of the string. Starting in Perl v5.30, it will take a second
+parameter, becoming a synonym for C<isI<FOO>_utf8_safe>. At that time every
+program that uses it will have to be changed to successfully compile. In the
+meantime, the first runtime call to C<isI<FOO>_utf8> from each call point in the
+program will raise a deprecation warning, enabled by default. You can convert
+your program now to use C<isI<FOO>_utf8_safe>, and avoid the warnings, and get an
+extra measure of protection, or you can wait until v5.30, when you'll be forced
+to add the C<e> parameter.
+
+Variant C<isI<FOO>_LC> is like the C<isI<FOO>_A> and C<isI<FOO>_L1> variants, but the
result is based on the current locale, which is what C<LC> in the name stands
for. If Perl can determine that the current locale is a UTF-8 locale, it uses
the published Unicode rules; otherwise, it uses the C library function that
library function is known to be defective, Perl changes its result to follow
the POSIX standard's rules.
-Variant C<isFOO_LC_uvchr> is like C<isFOO_LC>, but is defined on any UV. It
-returns the same as C<isFOO_LC> for input code points less than 256, and
+Variant C<isI<FOO>_LC_uvchr> is like C<isI<FOO>_LC>, but is defined on any UV. It
+returns the same as C<isI<FOO>_LC> for input code points less than 256, and
returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
-Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer to a
-(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
-classification of just the first (possibly multi-byte) character in the string
-is tested.
+Variant C<isI<FOO>_LC_utf8_safe> is like C<isI<FOO>_LC_uvchr>, but is used for UTF-8
+encoded strings. Each call classifies one character, even if the string
+contains many. This variant takes two parameters. The first, C<p>, is a
+pointer to the first byte of the character to be classified. (Recall that it
+may take more than one byte to represent a character in UTF-8 strings.) The
+second parameter, C<e>, points to anywhere in the string beyond the first
+character, up to one byte past the end of the entire string. The suffix
+C<_safe> in the function's name indicates that it will not attempt to read
+beyond S<C<e - 1>>, provided that the constraint S<C<s E<lt> e>> is true (this
+is asserted for in C<-DDEBUGGING> builds). If the UTF-8 for the input
+character is malformed in some way, the program may croak, or the function may
+return FALSE, at the discretion of the implementation, and subject to change in
+future releases.
+
+Variant C<isI<FOO>_LC_utf8> is like C<isI<FOO>_LC_utf8_safe>, but takes just a single
+parameter, C<p>, which has the same meaning as the corresponding parameter does
+in C<isI<FOO>_LC_utf8_safe>. The function therefore can't check if it is reading
+beyond the end of the string. Starting in Perl v5.30, it will take a second
+parameter, becoming a synonym for C<isI<FOO>_LC_utf8_safe>. At that time every
+program that uses it will have to be changed to successfully compile. In the
+meantime, the first runtime call to C<isI<FOO>_LC_utf8> from each call point in
+the program will raise a deprecation warning, enabled by default. You can
+convert your program now to use C<isI<FOO>_LC_utf8_safe>, and avoid the warnings,
+and get an extra measure of protection, or you can wait until v5.30, when
+you'll be forced to add the C<e> parameter.
=for apidoc Am|bool|isALPHA|char ch
Returns a boolean indicating whether the specified character is an
alphabetic character, analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uni>, C<isALPHA_utf8>, C<isALPHA_LC>,
-C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8>.
+C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8_safe>,
+C<isALPHA_LC>, C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8_safe>.
=for apidoc Am|bool|isALPHANUMERIC|char ch
Returns a boolean indicating whether the specified character is a either an
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_uni>,
-C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>, and
-C<isALPHANUMERIC_LC_utf8>.
+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>.
=for apidoc Am|bool|isASCII|char ch
Returns a boolean indicating whether the specified character is one of the 128
C<isASCII_L1()> are identical to C<isASCII()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isASCII_uni>, C<isASCII_utf8>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
-C<isASCII_LC_utf8>. Note, however, that some platforms do not have the C
+C<isASCII_uvchr>, C<isASCII_utf8_safe>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
+C<isASCII_LC_utf8_safe>. Note, however, that some platforms do not have the C
library routine C<isascii()>. In these cases, the variants whose names contain
C<LC> are the same as the corresponding ones without.
Also note, that because all ASCII characters are UTF-8 invariant (meaning they
have the exact same representation (always a single byte) whether encoded in
UTF-8 or not), C<isASCII> will give the correct results when called with any
-byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8> will
-work properly on any string encoded or not in UTF-8.
+byte in any string encoded or not in UTF-8. And similarly C<isASCII_utf8_safe>
+will work properly on any string encoded or not in UTF-8.
=for apidoc Am|bool|isBLANK|char ch
Returns a boolean indicating whether the specified character is a
character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uni>, C<isBLANK_utf8>, C<isBLANK_LC>,
-C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8>. Note, however, that some
-platforms do not have the C library routine C<isblank()>. In these cases, the
-variants whose names contain C<LC> are the same as the corresponding ones
-without.
+C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8_safe>,
+C<isBLANK_LC>, C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8_safe>. Note,
+however, that some platforms do not have the C library routine
+C<isblank()>. In these cases, the variants whose names contain C<LC> are
+the same as the corresponding ones without.
=for apidoc Am|bool|isCNTRL|char ch
Returns a boolean indicating whether the specified character is a
control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uni>, C<isCNTRL_utf8>, C<isCNTRL_LC>,
-C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8>
-On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
+C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8_safe>,
+C<isCNTRL_LC>, C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8_safe> On EBCDIC
+platforms, you almost always want to use the C<isCNTRL_L1> variant.
=for apidoc Am|bool|isDIGIT|char ch
Returns a boolean indicating whether the specified character is a
Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isDIGIT_uni>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
-C<isDIGIT_LC_utf8>.
+C<isDIGIT_uvchr>, C<isDIGIT_utf8_safe>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
+C<isDIGIT_LC_utf8_safe>.
=for apidoc Am|bool|isGRAPH|char ch
Returns a boolean indicating whether the specified character is a
graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uni>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
-C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8>.
+variants C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8_safe>,
+C<isGRAPH_LC>, C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8_safe>.
=for apidoc Am|bool|isLOWER|char ch
Returns a boolean indicating whether the specified character is a
lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uni>, C<isLOWER_utf8>, C<isLOWER_LC>,
-C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
+C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8_safe>,
+C<isLOWER_LC>, C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8_safe>.
=for apidoc Am|bool|isOCTAL|char ch
Returns a boolean indicating whether the specified character is an
straightforward as one might desire. See L<perlrecharclass/POSIX Character
Classes> for details.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uni>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
-C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
+variants C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8_safe>,
+C<isPUNCT_LC>, C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8_safe>.
=for apidoc Am|bool|isSPACE|char ch
Returns a boolean indicating whether the specified character is a
whitespace character. This is analogous
to what C<m/\s/> matches in a regular expression. Starting in Perl 5.18
-(experimentally), this also matches what C<m/[[:space:]]/> does.
-("Experimentally" means that this change may be backed out in 5.22 if
-field experience indicates that it was unwise.) Prior to 5.18, only the
+this also matches what C<m/[[:space:]]/> does. Prior to 5.18, only the
locale forms of this macro (the ones with C<LC> in their names) matched
precisely what C<m/[[:space:]]/> does. In those releases, the only difference,
in the non-locale variants, was that C<isSPACE()> did not match a vertical tab.
(See L</isPSXSPC> for a macro that matches a vertical tab in all releases.)
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uni>, C<isSPACE_utf8>, C<isSPACE_LC>,
-C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
+C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8_safe>,
+C<isSPACE_LC>, C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8_safe>.
=for apidoc Am|bool|isPSXSPC|char ch
(short for Posix Space)
-Starting in 5.18, this is identical (experimentally) in all its forms to the
-corresponding C<isSPACE()> macros. ("Experimentally" means that this change
-may be backed out in 5.22 if field experience indicates that it
-was unwise.)
+Starting in 5.18, this is identical in all its forms to the
+corresponding C<isSPACE()> macros.
The locale forms of this macro are identical to their corresponding
C<isSPACE()> forms in all Perl releases. In releases prior to 5.18, the
non-locale forms differ from their C<isSPACE()> forms only in that the
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_uni>, C<isPSXSPC_utf8>, C<isPSXSPC_LC>,
-C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
+variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8_safe>,
+C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8_safe>.
=for apidoc Am|bool|isUPPER|char ch
Returns a boolean indicating whether the specified character is an
uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uni>, C<isUPPER_utf8>, C<isUPPER_LC>,
-C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8>.
+variants C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8_safe>,
+C<isUPPER_LC>, C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8_safe>.
=for apidoc Am|bool|isPRINT|char ch
Returns a boolean indicating whether the specified character is a
printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uni>, C<isPRINT_utf8>, C<isPRINT_LC>,
-C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
+C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8_safe>,
+C<isPRINT_LC>, C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8_safe>.
=for apidoc Am|bool|isWORDCHAR|char ch
Returns a boolean indicating whether the specified character is a character
word character includes more than the standard C language meaning of
alphanumeric.
See the L<top of this section|/Character classification> for an explanation of
-variants
-C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uni>, and C<isWORDCHAR_utf8>.
-C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and C<isWORDCHAR_LC_utf8> are also as
-described there, but additionally include the platform's native underscore.
+variants C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and
+C<isWORDCHAR_utf8_safe>. C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and
+C<isWORDCHAR_LC_utf8_safe> are also as described there, but additionally
+include the platform's native underscore.
=for apidoc Am|bool|isXDIGIT|char ch
Returns a boolean indicating whether the specified character is a hexadecimal
and C<isXDIGIT_L1()> are identical to C<isXDIGIT()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isXDIGIT_uni>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
-C<isXDIGIT_LC_utf8>.
+C<isXDIGIT_uvchr>, C<isXDIGIT_utf8_safe>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>,
+and C<isXDIGIT_LC_utf8_safe>.
=for apidoc Am|bool|isIDFIRST|char ch
Returns a boolean indicating whether the specified character can be the first
returns true only if the input character also matches L</isWORDCHAR>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uni>, C<isIDFIRST_utf8>,
-C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8>.
+C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8_safe>,
+C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8_safe>.
=for apidoc Am|bool|isIDCONT|char ch
Returns a boolean indicating whether the specified character can be the
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_uni>,
-C<isIDCONT_utf8>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
-C<isIDCONT_LC_utf8>.
+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>.
=head1 Miscellaneous Functions
Behaviour is only well defined when isXDIGIT(*str) is true.
=head1 Character case changing
+Perl uses "full" Unicode case mappings. This means that converting a single
+character to another case may result in a sequence of more than one character.
+For example, the uppercase of C<E<223>> (LATIN SMALL LETTER SHARP S) is the two
+character sequence C<SS>. This presents some complications The lowercase of
+all characters in the range 0..255 is a single character, and thus
+C<L</toLOWER_L1>> is furnished. But, C<toUPPER_L1> can't exist, as it couldn't
+return a valid result for all legal inputs. Instead C<L</toUPPER_uvchr>> has
+an API that does allow every possible legal result to be returned.) Likewise
+no other function that is crippled by not being able to give the correct
+results for the full range of possible inputs has been implemented here.
=for apidoc Am|U8|toUPPER|U8 ch
Converts the specified character to uppercase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
C<toUPPER_A> is equivalent.
-=for apidoc Am|UV|toUPPER_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its uppercase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toUPPER_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its uppercase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. 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 uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more.)
-=for apidoc Am|UV|toUPPER_utf8|U8* p|U8* s|STRLEN* lenp
-Converts the UTF-8 encoded character at C<p> to its uppercase version, and
+=for apidoc Am|UV|toUPPER_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 uppercase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the uppercase version may be longer than the original character.
The first code point of the uppercased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
-The input character at C<p> is assumed to be well-formed.
+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|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.
=for apidoc Am|U8|toFOLD|U8 ch
Converts the specified character to foldcase. If the input is anything but an
ASCII uppercase character, that input character itself is returned. Variant
C<toFOLD_A> is equivalent. (There is no equivalent C<to_FOLD_L1> for the full
-Latin1 range, as the full generality of L</toFOLD_uni> is needed there.)
+Latin1 range, as the full generality of L</toFOLD_uvchr> is needed there.)
-=for apidoc Am|UV|toFOLD_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its foldcase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toFOLD_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its foldcase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. 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 foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
-=for apidoc Am|UV|toFOLD_utf8|U8* p|U8* s|STRLEN* lenp
-Converts the UTF-8 encoded character at C<p> to its foldcase version, and
+=for apidoc Am|UV|toFOLD_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 foldcase version, and
stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the foldcase version may be longer than the original character.
The first code point of the foldcased version is returned
-(but note, as explained just above, that there may be more.)
+(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.
-The input character at C<p> is assumed to be well-formed.
+=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
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.
+Converts the specified Latin1 character to lowercase. The results are
+undefined if the input doesn't fit in a byte.
=for apidoc Am|U8|toLOWER_LC|U8 ch
Converts the specified character to lowercase using the current locale's rules,
if possible; otherwise returns the input character itself.
-=for apidoc Am|UV|toLOWER_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its lowercase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=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 just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
-=for apidoc Am|UV|toLOWER_utf8|U8* p|U8* s|STRLEN* lenp
-Converts the UTF-8 encoded character at C<p> to its lowercase version, and
+
+=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 just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
-The input character at C<p> is assumed to be well-formed.
+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|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.
=for apidoc Am|U8|toTITLE|U8 ch
Converts the specified character to titlecase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
-C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1 range,
-as the full generality of L</toTITLE_uni> is needed there. Titlecase is not a
-concept used in locale handling, so there is no functionality for that.)
-
-=for apidoc Am|UV|toTITLE_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its titlecase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1
+range, as the full generality of L</toTITLE_uvchr> is needed there. Titlecase is
+not a concept used in locale handling, so there is no functionality for that.)
+
+=for apidoc Am|UV|toTITLE_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its titlecase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. 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 titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
-=for apidoc Am|UV|toTITLE_utf8|U8* p|U8* s|STRLEN* lenp
-Converts the UTF-8 encoded character at C<p> to its titlecase version, and
+=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
+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>
bytes since the titlecase version may be longer than the original character.
The first code point of the titlecased version is returned
-(but note, as explained just above, that there may be more.)
+(but note, as explained at L<the top of this section|/Character case
+changing>, that there may be more).
+
+The 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.
-The input character at C<p> is assumed to be well-formed.
+=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.
=cut
-XXX Still undocumented isVERTWS_uni and _utf8; it's unclear what their names
-really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change.
+XXX Still undocumented isVERTWS_uvchr and _utf8; it's unclear what their names
+really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change,
+and aren't general purpose as they don't work on U+DF, and assert against that.
Note that these macros are repeated in Devel::PPPort, so should also be
patched there. The file as of this writing is cpan/Devel-PPPort/parts/inc/misc
* compiler to optimize it out if possible. This is because Configure makes
* sure that the machine has an 8-bit byte, so if c is stored in a byte, the
* sizeof() guarantees that this evaluates to a constant true at compile time.
+ *
+ * For Coverity, be always true, because otherwise Coverity thinks
+ * it finds several expressions that are always true, independent
+ * of operands. Well, they are, but that is kind of the point.
*/
-#define FITS_IN_8_BITS(c) ((sizeof(c) == 1) || !(((WIDEST_UTYPE)(c)) & ~0xFF))
+#ifndef __COVERITY__
+ /* The '| 0' part ensures a compiler error if c is not integer (like e.g., a
+ * pointer) */
+#define FITS_IN_8_BITS(c) ( (sizeof(c) == 1) \
+ || !(((WIDEST_UTYPE)((c) | 0)) & ~0xFF))
+#else
+#define FITS_IN_8_BITS(c) (1)
+#endif
#ifdef EBCDIC
# ifndef _ALL_SOURCE
#else
/* There is a simple definition of ASCII for ASCII platforms. But the
* EBCDIC one isn't so simple, so is defined using table look-up like the
- * other macros below */
-# define isASCII(c) ((WIDEST_UTYPE)(c) < 128)
+ * other macros below.
+ *
+ * The cast here is used instead of '(c) >= 0', because some compilers emit
+ * a warning that that test is always true when the parameter is an
+ * unsigned type. khw supposes that it could be written as
+ * && ((c) == '\0' || (c) > 0)
+ * to avoid the message, but the cast will likely avoid extra branches even
+ * with stupid compilers.
+ *
+ * The '| 0' part ensures a compiler error if c is not integer (like e.g.,
+ * a pointer) */
+# define isASCII(c) ((WIDEST_UTYPE)((c) | 0) < 128)
#endif
-/* The lower 3 bits in both the ASCII and EBCDIC representations of '0' are 0,
- * and the 8 possible permutations of those bits exactly comprise the 8 octal
- * digits */
-#define isOCTAL_A(c) cBOOL(FITS_IN_8_BITS(c) && (0xF8 & (c)) == '0')
+/* Take the eight possible bit patterns of the lower 3 bits and you get the
+ * lower 3 bits of the 8 octal digits, in both ASCII and EBCDIC, so those bits
+ * can be ignored. If the rest match '0', we have an octal */
+#define isOCTAL_A(c) (((WIDEST_UTYPE)((c) | 0) & ~7) == '0')
#ifdef H_PERL /* If have access to perl.h, lookup in its table */
# define _CC_PRINT 6 /* [:print:] */
# define _CC_ALPHANUMERIC 7 /* [:alnum:] */
# define _CC_GRAPH 8 /* [:graph:] */
-# define _CC_CASED 9 /* [:lower:] and [:upper:] under /i */
+# define _CC_CASED 9 /* [:lower:] or [:upper:] under /i */
#define _FIRST_NON_SWASH_CC 10
/* The character classes above are implemented with swashes. The second group
* useful to group these which have no members that match above Latin1, (or
* above ASCII in the latter case) */
-# define _CC_SPACE 10 /* \s */
+# 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_PSXSPC 13 /* [:space:] */
-# define _CC_CNTRL 14 /* [:cntrl:] */
-# define _CC_ASCII 15 /* [:ascii:] */
-# define _CC_VERTSPACE 16 /* \v */
+# define _CC_CNTRL 13 /* [:cntrl:] */
+# define _CC_ASCII 14 /* [:ascii:] */
+# define _CC_VERTSPACE 15 /* \v */
# define _HIGHEST_REGCOMP_DOT_H_SYNC _CC_VERTSPACE
/* The members of the third group below do not need to be coordinated with data
* structures in regcomp.[ch] and regexec.c. */
-# define _CC_IDFIRST 17
-# define _CC_CHARNAME_CONT 18
-# define _CC_NONLATIN1_FOLD 19
-# define _CC_NONLATIN1_SIMPLE_FOLD 20
-# define _CC_QUOTEMETA 21
-# define _CC_NON_FINAL_FOLD 22
-# define _CC_IS_IN_SOME_FOLD 23
-# define _CC_MNEMONIC_CNTRL 24
-/* Unused: 25-31
+# define _CC_IDFIRST 16
+# define _CC_CHARNAME_CONT 17
+# define _CC_NONLATIN1_FOLD 18
+# define _CC_NONLATIN1_SIMPLE_FOLD 19
+# 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 */
+
+/* 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
* If more bits are needed, one could add a second word for non-64bit
* QUAD_IS_INT systems, using some #ifdefs to distinguish between having a 2nd
* word or not. The IS_IN_SOME_FOLD bit is the most easily expendable, as it
* is used only for optimization (as of this writing), and differs in the
* Latin1 range from the ALPHA bit only in two relatively unimportant
* characters: the masculine and feminine ordinal indicators, so removing it
- * would just cause /i regexes which match them to run less efficiently */
+ * would just cause /i regexes which match them to run less efficiently.
+ * Similarly the EBCDIC-only bits are used just for speed, and could be
+ * replaced by other means */
#if defined(PERL_CORE) || defined(PERL_EXT)
/* An enum version of the character class numbers, to help compilers
_CC_ENUM_GRAPH = _CC_GRAPH,
_CC_ENUM_LOWER = _CC_LOWER,
_CC_ENUM_PRINT = _CC_PRINT,
- _CC_ENUM_PSXSPC = _CC_PSXSPC,
_CC_ENUM_PUNCT = _CC_PUNCT,
_CC_ENUM_SPACE = _CC_SPACE,
_CC_ENUM_UPPER = _CC_UPPER,
#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 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
};
#endif
+START_EXTERN_C
# ifdef DOINIT
EXTCONST U32 PL_charclass[] = {
# include "l1_char_class_tab.h"
# else /* ! DOINIT */
EXTCONST U32 PL_charclass[];
# endif
+END_EXTERN_C
/* The 1U keeps Solaris from griping when shifting sets the uppermost bit */
# define _CC_mask(classnum) (1U << (classnum))
/* For internal core Perl use only: the base macro for defining macros like
* isALPHA_A. The foo_A version makes sure that both the desired bit and
* the ASCII bit are present */
-# define _generic_isCC_A(c, classnum) (FITS_IN_8_BITS(c) \
- && ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
- == _CC_mask_A(classnum)))
+# define _generic_isCC_A(c, classnum) (FITS_IN_8_BITS(c) \
+ && ((PL_charclass[(U8) (c)] & _CC_mask_A(classnum)) \
+ == _CC_mask_A(classnum)))
# define isALPHA_A(c) _generic_isCC_A(c, _CC_ALPHA)
# define isALPHANUMERIC_A(c) _generic_isCC_A(c, _CC_ALPHANUMERIC)
# 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 isPSXSPC_A(c) _generic_isCC_A(c, _CC_PSXSPC)
# 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 */
+# define isXDIGIT_A(c) _generic_isCC(c, _CC_XDIGIT) /* No non-ASCII xdigits
+ */
# define isIDFIRST_A(c) _generic_isCC_A(c, _CC_IDFIRST)
# define isALPHA_L1(c) _generic_isCC(c, _CC_ALPHA)
# define isALPHANUMERIC_L1(c) _generic_isCC(c, _CC_ALPHANUMERIC)
# define isGRAPH_L1(c) _generic_isCC(c, _CC_GRAPH)
# define isLOWER_L1(c) _generic_isCC(c, _CC_LOWER)
# define isPRINT_L1(c) _generic_isCC(c, _CC_PRINT)
-# define isPSXSPC_L1(c) _generic_isCC(c, _CC_PSXSPC)
+# define isPSXSPC_L1(c) isSPACE_L1(c)
# define isPUNCT_L1(c) _generic_isCC(c, _CC_PUNCT)
# define isSPACE_L1(c) _generic_isCC(c, _CC_SPACE)
# define isUPPER_L1(c) _generic_isCC(c, _CC_UPPER)
# 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)
+ _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)
+ _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)
#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 principals. First some ones common
- * to both ASCII and EBCDIC */
+ * to it. Most are coded based on first principles. These are written to
+ * avoid EBCDIC vs. ASCII #ifdef's as much as possible. */
# define isDIGIT_A(c) ((c) <= '9' && (c) >= '0')
# define isBLANK_A(c) ((c) == ' ' || (c) == '\t')
-# define isSPACE_A(c) (isBLANK_A(c) \
- || (c) == '\n' \
- || (c) == '\r' \
- || (c) == '\v' \
+# define isSPACE_A(c) (isBLANK_A(c) \
+ || (c) == '\n' \
+ || (c) == '\r' \
+ || (c) == '\v' \
|| (c) == '\f')
-# ifdef EBCDIC /* There are gaps between 'i' and 'j'; 'r' and 's'. Same
- for uppercase. This is ordered to exclude most things
- early */
-# define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z' \
- && ((c) <= 'i' \
- || ((c) >= 'j' && (c) <= 'r') \
- || (c) >= 's'))
-# define isUPPER_A(c) ((c) >= 'A' && (c) <= 'Z' \
- && ((c) <= 'I' \
- || ((c) >= 'J' && (c) <= 'R') \
- || (c) >= 'S'))
-# else /* ASCII platform. */
-# define isLOWER_A(c) ((c) >= 'a' && (c) <= 'z')
-# define isUPPER_A(c) ((c) <= 'Z' && (c) >= 'A')
-# endif
-
- /* Some more ASCII, non-ASCII common definitions */
+ /* On EBCDIC, there are gaps between 'i' and 'j'; 'r' and 's'. Same for
+ * 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 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') \
+# define isXDIGIT_A(c) (isDIGIT_A(c) \
+ || ((c) >= 'a' && (c) <= 'f') \
|| ((c) <= 'F' && (c) >= 'A'))
+# define isPUNCT_A(c) ((c) == '-' || (c) == '!' || (c) == '"' \
+ || (c) == '#' || (c) == '$' || (c) == '%' \
+ || (c) == '&' || (c) == '\'' || (c) == '(' \
+ || (c) == ')' || (c) == '*' || (c) == '+' \
+ || (c) == ',' || (c) == '.' || (c) == '/' \
+ || (c) == ':' || (c) == ';' || (c) == '<' \
+ || (c) == '=' || (c) == '>' || (c) == '?' \
+ || (c) == '@' || (c) == '[' || (c) == '\\' \
+ || (c) == ']' || (c) == '^' || (c) == '_' \
+ || (c) == '`' || (c) == '{' || (c) == '|' \
+ || (c) == '}' || (c) == '~')
+# define isGRAPH_A(c) (isALPHANUMERIC_A(c) || isPUNCT_A(c))
+# define isPRINT_A(c) (isGRAPH_A(c) || (c) == ' ')
# ifdef EBCDIC
-# define isPUNCT_A(c) ((c) == '-' || (c) == '!' || (c) == '"' \
- || (c) == '#' || (c) == '$' || (c) == '%' \
- || (c) == '&' || (c) == '\'' || (c) == '(' \
- || (c) == ')' || (c) == '*' || (c) == '+' \
- || (c) == ',' || (c) == '.' || (c) == '/' \
- || (c) == ':' || (c) == ';' || (c) == '<' \
- || (c) == '=' || (c) == '>' || (c) == '?' \
- || (c) == '@' || (c) == '[' || (c) == '\\' \
- || (c) == ']' || (c) == '^' || (c) == '_' \
- || (c) == '`' || (c) == '{' || (c) == '|' \
- || (c) == '}' || (c) == '~')
-# define isGRAPH_A(c) (isALPHANUMERIC_A(c) || isPUNCT_A(c))
-# define isPRINT_A(c) (isGRAPH_A(c) || (c) == ' ')
-
-# ifdef QUESTION_MARK_CTRL
-# define _isQMC(c) ((c) == QUESTION_MARK_CTRL)
-# else
-# define _isQMC(c) 0
-# endif
-
- /* I (khw) can't think of a way to define all the ASCII controls
- * without resorting to a libc (locale-sensitive) call. But we know
- * that all controls but the question-mark one are in the range 0-0x3f.
- * This makes sure that all the controls that have names are included,
- * and all controls that are also considered ASCII in the locale. This
- * may include more or fewer than what it actually should, but the
- * wrong ones are less-important controls, so likely won't impact
- * things (keep in mind that this is compiled only if perl.h isn't
- * available). The question mark control is included if available */
-# define isCNTRL_A(c) (((c) < 0x40 && isascii(c)) \
- || (c) == '\0' || (c) == '\a' || (c) == '\b' \
- || (c) == '\f' || (c) == '\n' || (c) == '\r' \
- || (c) == '\t' || (c) == '\v' || _isQMC(c))
-
+ /* The below is accurate for the 3 EBCDIC code pages traditionally
+ * supported by perl. The only difference between them in the controls
+ * is the position of \n, and that is represented symbolically below */
+# 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] */ \
+ || (c) == 0x18 /* U+18 CAN */ \
+ || (c) == 0x19 /* U+19 EOM */ \
+ || ((c) <= 0x1F && (c) >= 0x1C) /* [FGRU]S */ \
+ || (c) == 0x26 /* U+17 ETB */ \
+ || (c) == 0x27 /* U+1B ESC */ \
+ || (c) == 0x2D /* U+05 ENQ */ \
+ || (c) == 0x2E /* U+06 ACK */ \
+ || (c) == 0x32 /* U+16 SYN */ \
+ || (c) == 0x37 /* U+04 EOT */ \
+ || (c) == 0x3C /* U+14 DC4 */ \
+ || (c) == 0x3D /* U+15 NAK */ \
+ || (c) == 0x3F)/* U+1A SUB */
# define isASCII(c) (isCNTRL_A(c) || isPRINT_A(c))
-# else /* ASCII platform; things are simpler, and isASCII has already
- been defined */
-# define isGRAPH_A(c) (((c) > ' ' && (c) < 127))
-# define isPRINT_A(c) (isGRAPH_A(c) || (c) == ' ')
-# define isPUNCT_A(c) (isGRAPH_A(c) && (! isALPHANUMERIC_A(c)))
-# define isCNTRL_A(c) (isASCII(c) && (! isPRINT_A(c)))
+# else /* isASCII is already defined for ASCII platforms, so can use that to
+ define isCNTRL */
+# define isCNTRL_A(c) (isASCII(c) && ! isPRINT_A(c))
# endif
/* The _L1 macros may be unnecessary for the utilities; I (khw) added them
# if ! defined(EBCDIC) && ! defined(NATIVE_TO_LATIN1)
# define NATIVE_TO_LATIN1(ch) (ch)
# endif
-# define isPSXSPC_A(c) isSPACE_A(c) /* XXX Assumes SPACE matches '\v' */
# define isALPHA_L1(c) (isUPPER_L1(c) || isLOWER_L1(c))
# define isALPHANUMERIC_L1(c) (isALPHA_L1(c) || isDIGIT_A(c))
# define isBLANK_L1(c) (isBLANK_A(c) \
# define isGRAPH_L1(c) (isPRINT_L1(c) && (! isBLANK_L1(c)))
# define isLOWER_L1(c) (isLOWER_A(c) \
|| (FITS_IN_8_BITS(c) \
- && ((NATIVE_TO_LATIN1((U8) c) >= 0xDF \
+ && (( NATIVE_TO_LATIN1((U8) c) >= 0xDF \
&& NATIVE_TO_LATIN1((U8) c) != 0xF7) \
|| NATIVE_TO_LATIN1((U8) c) == 0xAA \
|| NATIVE_TO_LATIN1((U8) c) == 0xBA \
# define isPRINT_L1(c) (isPRINT_A(c) \
|| (FITS_IN_8_BITS(c) \
&& NATIVE_TO_LATIN1((U8) c) >= 0xA0))
-# define isPSXSPC_L1(c) isSPACE_L1(c)
# define isPUNCT_L1(c) (isPUNCT_A(c) \
|| (FITS_IN_8_BITS(c) \
- && (NATIVE_TO_LATIN1((U8) c) == 0xA1 \
+ && ( NATIVE_TO_LATIN1((U8) c) == 0xA1 \
|| NATIVE_TO_LATIN1((U8) c) == 0xA7 \
|| NATIVE_TO_LATIN1((U8) c) == 0xAB \
|| NATIVE_TO_LATIN1((U8) c) == 0xB6 \
|| NATIVE_TO_LATIN1((U8) c) == 0xBF)))
# define isSPACE_L1(c) (isSPACE_A(c) \
|| (FITS_IN_8_BITS(c) \
- && (NATIVE_TO_LATIN1((U8) c) == 0x85 \
+ && ( NATIVE_TO_LATIN1((U8) c) == 0x85 \
|| 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) >= 0xC0 \
&& NATIVE_TO_LATIN1((U8) c) <= 0xDE \
&& NATIVE_TO_LATIN1((U8) c) != 0xD7)))
# define isWORDCHAR_L1(c) (isIDFIRST_L1(c) || isDIGIT_A(c))
#define isIDFIRST(c) isIDFIRST_A(c)
#define isLOWER(c) isLOWER_A(c)
#define isPRINT(c) isPRINT_A(c)
+#define isPSXSPC_A(c) isSPACE_A(c)
#define isPSXSPC(c) isPSXSPC_A(c)
+#define isPSXSPC_L1(c) isSPACE_L1(c)
#define isPUNCT(c) isPUNCT_A(c)
#define isSPACE(c) isSPACE_A(c)
#define isUPPER(c) isUPPER_A(c)
(! FITS_IN_8_BITS(c) \
? (c) \
: ((! IN_UTF8_CTYPE_LOCALE) \
- ? (cast)function((cast)(c)) \
+ ? (cast)function((cast)(c)) \
: ((((U8)(c)) == MICRO_SIGN) \
? GREEK_CAPITAL_LETTER_MU \
: ((((U8)(c)) == LATIN_SMALL_LETTER_Y_WITH_DIAERESIS) \
* Not all possible weirdnesses are checked for, just the ones that were
* detected on actual Microsoft code pages */
-# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
-# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
-
-# define isALPHA_LC(c) (_generic_LC(c, _CC_ALPHA, isalpha) && isALPHANUMERIC_LC(c))
-# define isALPHANUMERIC_LC(c) (_generic_LC(c, _CC_ALPHANUMERIC, isalnum) && ! isPUNCT_LC(c))
-# define isDIGIT_LC(c) (_generic_LC(c, _CC_DIGIT, isdigit) && isALPHANUMERIC_LC(c))
-# define isGRAPH_LC(c) (_generic_LC(c, _CC_GRAPH, isgraph) && isPRINT_LC(c))
-# define isIDFIRST_LC(c) (((c) == '_') || (_generic_LC(c, _CC_IDFIRST, isalpha) && ! isPUNCT_LC(c)))
-# define isLOWER_LC(c) (_generic_LC(c, _CC_LOWER, islower) && isALPHA_LC(c))
-# define isPRINT_LC(c) (_generic_LC(c, _CC_PRINT, isprint) && ! isCNTRL_LC(c))
-# define isPUNCT_LC(c) (_generic_LC(c, _CC_PUNCT, ispunct) && ! isCNTRL_LC(c))
-# define isUPPER_LC(c) (_generic_LC(c, _CC_UPPER, isupper) && isALPHA_LC(c))
+# define isCNTRL_LC(c) _generic_LC(c, _CC_CNTRL, iscntrl)
+# define isSPACE_LC(c) _generic_LC(c, _CC_SPACE, isspace)
+
+# define isALPHA_LC(c) (_generic_LC(c, _CC_ALPHA, isalpha) \
+ && isALPHANUMERIC_LC(c))
+# define isALPHANUMERIC_LC(c) (_generic_LC(c, _CC_ALPHANUMERIC, isalnum) && \
+ ! isPUNCT_LC(c))
+# define isDIGIT_LC(c) (_generic_LC(c, _CC_DIGIT, isdigit) && \
+ isALPHANUMERIC_LC(c))
+# define isGRAPH_LC(c) (_generic_LC(c, _CC_GRAPH, isgraph) && isPRINT_LC(c))
+# define isIDFIRST_LC(c) (((c) == '_') \
+ || (_generic_LC(c, _CC_IDFIRST, isalpha) && ! isPUNCT_LC(c)))
+# define isLOWER_LC(c) (_generic_LC(c, _CC_LOWER, islower) && isALPHA_LC(c))
+# define isPRINT_LC(c) (_generic_LC(c, _CC_PRINT, isprint) && ! isCNTRL_LC(c))
+# define isPUNCT_LC(c) (_generic_LC(c, _CC_PUNCT, ispunct) && ! isCNTRL_LC(c))
+# define isUPPER_LC(c) (_generic_LC(c, _CC_UPPER, isupper) && isALPHA_LC(c))
# define isWORDCHAR_LC(c) (((c) == '_') || isALPHANUMERIC_LC(c))
-# define isXDIGIT_LC(c) (_generic_LC(c, _CC_XDIGIT, isxdigit) && isALPHANUMERIC_LC(c))
+# define isXDIGIT_LC(c) (_generic_LC(c, _CC_XDIGIT, isxdigit) \
+ && isALPHANUMERIC_LC(c))
# define toLOWER_LC(c) _generic_toLOWER_LC((c), tolower, U8)
# define toUPPER_LC(c) _generic_toUPPER_LC((c), toupper, U8)
#else /* The final fallback position */
-# define isALPHA_LC(c) (isascii(c) && isalpha(c))
-# define isALPHANUMERIC_LC(c) (isascii(c) && isalnum(c))
-# define isCNTRL_LC(c) (isascii(c) && iscntrl(c))
-# define isDIGIT_LC(c) (isascii(c) && isdigit(c))
-# define isGRAPH_LC(c) (isascii(c) && isgraph(c))
+# define isALPHA_LC(c) (isascii(c) && isalpha(c))
+# define isALPHANUMERIC_LC(c) (isascii(c) && isalnum(c))
+# define isCNTRL_LC(c) (isascii(c) && iscntrl(c))
+# define isDIGIT_LC(c) (isascii(c) && isdigit(c))
+# define isGRAPH_LC(c) (isascii(c) && isgraph(c))
# define isIDFIRST_LC(c) (isascii(c) && (isalpha(c) || (c) == '_'))
-# define isLOWER_LC(c) (isascii(c) && islower(c))
-# define isPRINT_LC(c) (isascii(c) && isprint(c))
-# define isPUNCT_LC(c) (isascii(c) && ispunct(c))
-# define isSPACE_LC(c) (isascii(c) && isspace(c))
-# define isUPPER_LC(c) (isascii(c) && isupper(c))
+# define isLOWER_LC(c) (isascii(c) && islower(c))
+# define isPRINT_LC(c) (isascii(c) && isprint(c))
+# define isPUNCT_LC(c) (isascii(c) && ispunct(c))
+# define isSPACE_LC(c) (isascii(c) && isspace(c))
+# define isUPPER_LC(c) (isascii(c) && isupper(c))
# define isWORDCHAR_LC(c) (isascii(c) && (isalnum(c) || (c) == '_'))
-# define isXDIGIT_LC(c) (isascii(c) && isxdigit(c))
+# define isXDIGIT_LC(c) (isascii(c) && isxdigit(c))
# define toLOWER_LC(c) (isascii(c) ? tolower(c) : (c))
# define toUPPER_LC(c) (isascii(c) ? toupper(c) : (c))
#define isPSXSPC_LC(c) isSPACE_LC(c)
/* For internal core Perl use only: the base macros for defining macros like
- * isALPHA_uni. 'c' is the code point to check. 'classnum' is the POSIX class
- * number defined earlier in this file. _generic_uni() is used for POSIX
+ * isALPHA_uvchr. 'c' is the code point to check. 'classnum' is the POSIX class
+ * 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_uni() can be used
+ * lookup or inversion list binary search. _generic_swash_uvchr() can be used
* for classes where that overhead is faster than a direct lookup.
- * _generic_uni() won't compile if 'c' isn't unsigned, as it won't match the
+ * _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
* have duplicate checks here, so could create versions of the macros that
* don't, but experiments show that gcc optimizes them out anyway. */
/* Note that all ignore 'use bytes' */
-#define _generic_uni(classnum, above_latin1, c) ((c) < 256 \
- ? _generic_isCC(c, classnum) \
+#define _generic_uvchr(classnum, above_latin1, c) ((c) < 256 \
+ ? _generic_isCC(c, classnum) \
: above_latin1(c))
-#define _generic_swash_uni(classnum, c) ((c) < 256 \
- ? _generic_isCC(c, classnum) \
+#define _generic_swash_uvchr(classnum, c) ((c) < 256 \
+ ? _generic_isCC(c, classnum) \
: _is_uni_FOO(classnum, c))
-#define isALPHA_uni(c) _generic_swash_uni(_CC_ALPHA, c)
-#define isALPHANUMERIC_uni(c) _generic_swash_uni(_CC_ALPHANUMERIC, c)
-#define isASCII_uni(c) isASCII(c)
-#define isBLANK_uni(c) _generic_uni(_CC_BLANK, is_HORIZWS_cp_high, c)
-#define isCNTRL_uni(c) isCNTRL_L1(c) /* All controls are in Latin1 */
-#define isDIGIT_uni(c) _generic_swash_uni(_CC_DIGIT, c)
-#define isGRAPH_uni(c) _generic_swash_uni(_CC_GRAPH, c)
-#define isIDCONT_uni(c) _generic_uni(_CC_WORDCHAR, _is_uni_perl_idcont, c)
-#define isIDFIRST_uni(c) _generic_uni(_CC_IDFIRST, _is_uni_perl_idstart, c)
-#define isLOWER_uni(c) _generic_swash_uni(_CC_LOWER, c)
-#define isPRINT_uni(c) _generic_swash_uni(_CC_PRINT, c)
-
-/* Posix and regular space are identical above Latin1 */
-#define isPSXSPC_uni(c) _generic_uni(_CC_PSXSPC, is_XPERLSPACE_cp_high, c)
-
-#define isPUNCT_uni(c) _generic_swash_uni(_CC_PUNCT, c)
-#define isSPACE_uni(c) _generic_uni(_CC_SPACE, is_XPERLSPACE_cp_high, c)
-#define isUPPER_uni(c) _generic_swash_uni(_CC_UPPER, c)
-#define isVERTWS_uni(c) _generic_uni(_CC_VERTSPACE, is_VERTWS_cp_high, c)
-#define isWORDCHAR_uni(c) _generic_swash_uni(_CC_WORDCHAR, c)
-#define isXDIGIT_uni(c) _generic_uni(_CC_XDIGIT, is_XDIGIT_cp_high, c)
-
-#define toFOLD_uni(c,s,l) to_uni_fold(c,s,l)
-#define toLOWER_uni(c,s,l) to_uni_lower(c,s,l)
-#define toTITLE_uni(c,s,l) to_uni_title(c,s,l)
-#define toUPPER_uni(c,s,l) to_uni_upper(c,s,l)
+#define isALPHA_uvchr(c) _generic_swash_uvchr(_CC_ALPHA, c)
+#define isALPHANUMERIC_uvchr(c) _generic_swash_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 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 isPUNCT_uvchr(c) _generic_swash_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 isVERTWS_uvchr(c) _generic_uvchr(_CC_VERTSPACE, is_VERTWS_cp_high, c)
+#define isWORDCHAR_uvchr(c) _generic_swash_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)
+#define toLOWER_uvchr(c,s,l) to_uni_lower(c,s,l)
+#define toTITLE_uvchr(c,s,l) to_uni_title(c,s,l)
+#define toUPPER_uvchr(c,s,l) to_uni_upper(c,s,l)
+
+/* For backwards compatibility, even though '_uni' should mean official Unicode
+ * code points, in Perl it means native for those below 256 */
+#define isALPHA_uni(c) isALPHA_uvchr(c)
+#define isALPHANUMERIC_uni(c) isALPHANUMERIC_uvchr(c)
+#define isASCII_uni(c) isASCII_uvchr(c)
+#define isBLANK_uni(c) isBLANK_uvchr(c)
+#define isCNTRL_uni(c) isCNTRL_uvchr(c)
+#define isDIGIT_uni(c) isDIGIT_uvchr(c)
+#define isGRAPH_uni(c) isGRAPH_uvchr(c)
+#define isIDCONT_uni(c) isIDCONT_uvchr(c)
+#define isIDFIRST_uni(c) isIDFIRST_uvchr(c)
+#define isLOWER_uni(c) isLOWER_uvchr(c)
+#define isPRINT_uni(c) isPRINT_uvchr(c)
+#define isPUNCT_uni(c) isPUNCT_uvchr(c)
+#define isSPACE_uni(c) isSPACE_uvchr(c)
+#define isPSXSPC_uni(c) isPSXSPC_uvchr(c)
+#define isUPPER_uni(c) isUPPER_uvchr(c)
+#define isVERTWS_uni(c) isVERTWS_uvchr(c)
+#define isWORDCHAR_uni(c) isWORDCHAR_uvchr(c)
+#define isXDIGIT_uni(c) isXDIGIT_uvchr(c)
+#define toFOLD_uni(c,s,l) toFOLD_uvchr(c,s,l)
+#define toLOWER_uni(c,s,l) toLOWER_uvchr(c,s,l)
+#define toTITLE_uni(c,s,l) toTITLE_uvchr(c,s,l)
+#define toUPPER_uni(c,s,l) toUPPER_uvchr(c,s,l)
/* For internal core Perl use only: the base macros for defining macros like
* isALPHA_LC_uvchr. These are like isALPHA_LC, but the input can be any code
- * point, not just 0-255. Like _generic_uni, there are two versions, one for
+ * point, not just 0-255. Like _generic_uvchr, there are two versions, one for
* simple class definitions; the other for more complex. These are like
- * _generic_uni, so see it for more info. */
+ * _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 isALPHA_LC_uvchr(c) _generic_LC_swash_uvchr(isALPHA_LC, _CC_ALPHA, c)
#define isALPHANUMERIC_LC_uvchr(c) _generic_LC_swash_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 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 isIDCONT_LC_uvchr(c) _generic_LC_uvchr(isIDCONT_LC, \
+#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, \
+#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 isPSXSPC_LC_uvchr(c) isSPACE_LC_uvchr(c) /* space is identical to posix
- space under locale */
+#define isPSXSPC_LC_uvchr(c) isSPACE_LC_uvchr(c)
#define isPUNCT_LC_uvchr(c) _generic_LC_swash_uvchr(isPUNCT_LC, _CC_PUNCT, c)
-#define isSPACE_LC_uvchr(c) _generic_LC_uvchr(isSPACE_LC, \
+#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 isWORDCHAR_LC_uvchr(c) _generic_LC_swash_uvchr(isWORDCHAR_LC, \
_CC_WORDCHAR, c)
-#define isXDIGIT_LC_uvchr(c) _generic_LC_uvchr(isXDIGIT_LC, is_XDIGIT_cp_high, 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))
+#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
* 'utf8' parameter. This relies on the fact that ASCII characters have the
* same representation whether utf8 or not. Note that it assumes that the utf8
* has been validated, and ignores 'use bytes' */
-#define _generic_utf8(classnum, p, utf8) (UTF8_IS_INVARIANT(*(p)) \
- ? _generic_isCC(*(p), classnum) \
- : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
- ? _generic_isCC( \
- TWO_BYTE_UTF8_TO_NATIVE(*(p), \
- *((p)+1 )), \
- classnum) \
- : utf8)
-/* Like the above, but calls 'above_latin1(p)' to get the utf8 value. 'above_latin1'
- * can be a macro */
-#define _generic_func_utf8(classnum, above_latin1, p) \
- _generic_utf8(classnum, p, above_latin1(p))
+#define _base_generic_utf8(enum_name, name, p, use_locale ) \
+ _is_utf8_FOO(CAT2(_CC_, enum_name), \
+ (const U8 *) p, \
+ "is" STRINGIFY(name) "_utf8", \
+ "is" STRINGIFY(name) "_utf8_safe", \
+ 1, use_locale, __FILE__,__LINE__)
+
+#define _generic_utf8(name, p) _base_generic_utf8(name, name, p, 0)
+
+/* The "_safe" macros make sure that we don't attempt to read beyond 'e', but
+ * they don't otherwise go out of their way to look for malformed UTF-8. If
+ * they can return accurate results without knowing if the input is otherwise
+ * malformed, they do so. For example isASCII is accurate in spite of any
+ * non-length malformations because it looks only at a single byte. Likewise
+ * isDIGIT looks just at the first byte for code points 0-255, as all UTF-8
+ * variant ones return FALSE. But, if the input has to be well-formed in order
+ * for the results to be accurate, the macros will test and if malformed will
+ * call a routine to die
+ *
+ * Except for toke.c, the macros do assume that e > p, asserting that on
+ * DEBUGGING builds. Much code that calls these depends on this being true,
+ * for other reasons. toke.c is treated specially as using the regular
+ * assertion breaks it in many ways. All strings that these operate on there
+ * are supposed to have an extra NUL character at the end, so that *e = \0. A
+ * bunch of code in toke.c assumes that this is true, so the assertion allows
+ * for that */
+#ifdef PERL_IN_TOKE_C
+# define _utf8_safe_assert(p,e) ((e) > (p) || ((e) == (p) && *(p) == '\0'))
+#else
+# define _utf8_safe_assert(p,e) ((e) > (p))
+#endif
+
+#define _generic_utf8_safe(classnum, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? _generic_isCC(*(p), classnum) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p)) \
+ ? ((LIKELY((e) - (p) > 1 && UTF8_IS_CONTINUATION(*((p)+1)))) \
+ ? _generic_isCC(EIGHT_BIT_UTF8_TO_NATIVE(*(p), *((p)+1 )), \
+ classnum) \
+ : (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0)) \
+ : above_latin1))
+/* Like the above, but calls 'above_latin1(p)' to get the utf8 value.
+ * 'above_latin1' can be a macro */
+#define _generic_func_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_utf8_safe(classnum, p, e, above_latin1(p, e))
+#define _generic_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_utf8_safe(classnum, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : above_latin1(p)))
/* Like the above, but passes classnum to _isFOO_utf8(), instead of having an
* 'above_latin1' parameter */
-#define _generic_swash_utf8(classnum, p) \
- _generic_utf8(classnum, p, _is_utf8_FOO(classnum, p))
+#define _generic_swash_utf8_safe(classnum, p, e) \
+_generic_utf8_safe(classnum, p, e, _is_utf8_FOO_with_len(classnum, p, e))
/* Like the above, but should be used only when it is known that there are no
* characters in the upper-Latin1 range (128-255 on ASCII platforms) which the
* class is TRUE for. Hence it can skip the tests for this range.
* 'above_latin1' should include its arguments */
-#define _generic_utf8_no_upper_latin1(classnum, p, above_latin1) \
- (UTF8_IS_INVARIANT(*(p)) \
- ? _generic_isCC(*(p), classnum) \
- : (UTF8_IS_ABOVE_LATIN1(*(p))) \
- ? above_latin1 \
- : 0)
+#define _generic_utf8_safe_no_upper_latin1(classnum, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? _generic_isCC(*(p), classnum) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
+ ? 0 /* Note that doesn't check validity for latin1 */ \
+ : above_latin1)
/* NOTE that some of these macros have very similar ones in regcharclass.h.
* For example, there is (at the time of this writing) an 'is_SPACE_utf8()'
* points; the regcharclass.h ones are implemented as a series of
* "if-else-if-else ..." */
-#define isALPHA_utf8(p) _generic_swash_utf8(_CC_ALPHA, p)
-#define isALPHANUMERIC_utf8(p) _generic_swash_utf8(_CC_ALPHANUMERIC, p)
-#define isASCII_utf8(p) isASCII(*p) /* Because ASCII is invariant under
- utf8, the non-utf8 macro works
- */
-#define isBLANK_utf8(p) _generic_func_utf8(_CC_BLANK, is_HORIZWS_high, p)
+#define isALPHA_utf8(p) _generic_utf8(ALPHA, p)
+#define isALPHANUMERIC_utf8(p) _generic_utf8(ALPHANUMERIC, p)
+#define isASCII_utf8(p) _generic_utf8(ASCII, p)
+#define isBLANK_utf8(p) _generic_utf8(BLANK, p)
+#define isCNTRL_utf8(p) _generic_utf8(CNTRL, p)
+#define isDIGIT_utf8(p) _generic_utf8(DIGIT, p)
+#define isGRAPH_utf8(p) _generic_utf8(GRAPH, p)
+#define isIDCONT_utf8(p) _generic_utf8(IDCONT, p)
+#define isIDFIRST_utf8(p) _generic_utf8(IDFIRST, p)
+#define isLOWER_utf8(p) _generic_utf8(LOWER, p)
+#define isPRINT_utf8(p) _generic_utf8(PRINT, p)
+#define isPSXSPC_utf8(p) _generic_utf8(PSXSPC, p)
+#define isPUNCT_utf8(p) _generic_utf8(PUNCT, p)
+#define isSPACE_utf8(p) _generic_utf8(SPACE, p)
+#define isUPPER_utf8(p) _generic_utf8(UPPER, p)
+#define isVERTWS_utf8(p) _generic_utf8(VERTSPACE, p)
+#define isWORDCHAR_utf8(p) _generic_utf8(WORDCHAR, p)
+#define isXDIGIT_utf8(p) _generic_utf8(XDIGIT, p)
+
+#define isALPHA_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_ALPHA, p, e)
+#define isALPHANUMERIC_utf8_safe(p, e) \
+ _generic_swash_utf8_safe(_CC_ALPHANUMERIC, p, e)
+#define isASCII_utf8_safe(p, e) \
+ /* Because ASCII is invariant under utf8, the non-utf8 macro \
+ * works */ \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isASCII(*(p)))
+#define isBLANK_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_BLANK, is_HORIZWS_high, p, e)
#ifdef EBCDIC
/* Because all controls are UTF-8 invariants in EBCDIC, we can use this
* more efficient macro instead of the more general one */
-# define isCNTRL_utf8(p) isCNTRL_L1(*(p))
+# define isCNTRL_utf8_safe(p, e) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isCNTRL_L1(*(p)))
#else
-# define isCNTRL_utf8(p) _generic_utf8(_CC_CNTRL, p, 0)
+# define isCNTRL_utf8_safe(p, e) _generic_utf8_safe(_CC_CNTRL, p, e, 0)
#endif
-#define isDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_DIGIT, p, \
- _is_utf8_FOO(_CC_DIGIT, p))
-#define isGRAPH_utf8(p) _generic_swash_utf8(_CC_GRAPH, p)
-#define isIDCONT_utf8(p) _generic_func_utf8(_CC_WORDCHAR, \
- _is_utf8_perl_idcont, p)
+#define isDIGIT_utf8_safe(p, e) \
+ _generic_utf8_safe_no_upper_latin1(_CC_DIGIT, p, e, \
+ _is_utf8_FOO_with_len(_CC_DIGIT, p, e))
+#define isGRAPH_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_GRAPH, p, e)
+#define isIDCONT_utf8_safe(p, e) _generic_func_utf8_safe(_CC_WORDCHAR, \
+ _is_utf8_perl_idcont_with_len, p, e)
/* To prevent S_scan_word in toke.c from hanging, we have to make sure that
* IDFIRST is an alnum. See
* ever wanted to know about. (In the ASCII range, there isn't a difference.)
* This used to be not the XID version, but we decided to go with the more
* modern Unicode definition */
-#define isIDFIRST_utf8(p) _generic_func_utf8(_CC_IDFIRST, \
- _is_utf8_perl_idstart, p)
-
-#define isLOWER_utf8(p) _generic_swash_utf8(_CC_LOWER, p)
-#define isPRINT_utf8(p) _generic_swash_utf8(_CC_PRINT, p)
-
-/* Posix and regular space are identical above Latin1 */
-#define isPSXSPC_utf8(p) _generic_func_utf8(_CC_PSXSPC, is_XPERLSPACE_high, p)
-
-#define isPUNCT_utf8(p) _generic_swash_utf8(_CC_PUNCT, p)
-#define isSPACE_utf8(p) _generic_func_utf8(_CC_SPACE, is_XPERLSPACE_high, p)
-#define isUPPER_utf8(p) _generic_swash_utf8(_CC_UPPER, p)
-#define isVERTWS_utf8(p) _generic_func_utf8(_CC_VERTSPACE, is_VERTWS_high, p)
-#define isWORDCHAR_utf8(p) _generic_swash_utf8(_CC_WORDCHAR, p)
-#define isXDIGIT_utf8(p) _generic_utf8_no_upper_latin1(_CC_XDIGIT, p, \
- is_XDIGIT_high(p))
+#define isIDFIRST_utf8_safe(p, e) \
+ _generic_func_utf8_safe(_CC_IDFIRST, \
+ _is_utf8_perl_idstart_with_len, (U8 *) (p), (U8 *) (e))
+
+#define isLOWER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_LOWER, p, e)
+#define isPRINT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PRINT, p, e)
+#define isPSXSPC_utf8_safe(p, e) isSPACE_utf8_safe(p, e)
+#define isPUNCT_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_PUNCT, p, e)
+#define isSPACE_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_SPACE, is_XPERLSPACE_high, p, e)
+#define isUPPER_utf8_safe(p, e) _generic_swash_utf8_safe(_CC_UPPER, p, e)
+#define isVERTWS_utf8_safe(p, e) \
+ _generic_non_swash_utf8_safe(_CC_VERTSPACE, is_VERTWS_high, p, e)
+#define isWORDCHAR_utf8_safe(p, e) \
+ _generic_swash_utf8_safe(_CC_WORDCHAR, p, e)
+#define isXDIGIT_utf8_safe(p, e) \
+ _generic_utf8_safe_no_upper_latin1(_CC_XDIGIT, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : is_XDIGIT_high(p)))
#define toFOLD_utf8(p,s,l) to_utf8_fold(p,s,l)
#define toLOWER_utf8(p,s,l) to_utf8_lower(p,s,l)
#define toTITLE_utf8(p,s,l) to_utf8_title(p,s,l)
#define toUPPER_utf8(p,s,l) to_utf8_upper(p,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_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(macro, p, utf8) \
- (UTF8_IS_INVARIANT(*(p)) \
- ? macro(*(p)) \
- : (UTF8_IS_DOWNGRADEABLE_START(*(p))) \
- ? macro(TWO_BYTE_UTF8_TO_NATIVE(*(p), *((p)+1))) \
- : utf8)
-
-#define _generic_LC_swash_utf8(macro, classnum, p) \
- _generic_LC_utf8(macro, p, _is_utf8_FOO(classnum, p))
-#define _generic_LC_func_utf8(macro, above_latin1, p) \
- _generic_LC_utf8(macro, p, above_latin1(p))
-
-#define isALPHANUMERIC_LC_utf8(p) _generic_LC_swash_utf8(isALPHANUMERIC_LC, \
- _CC_ALPHANUMERIC, p)
-#define isALPHA_LC_utf8(p) _generic_LC_swash_utf8(isALPHA_LC, _CC_ALPHA, p)
-#define isASCII_LC_utf8(p) isASCII_LC(*p)
-#define isBLANK_LC_utf8(p) _generic_LC_func_utf8(isBLANK_LC, is_HORIZWS_high, p)
-#define isCNTRL_LC_utf8(p) _generic_LC_utf8(isCNTRL_LC, p, 0)
-#define isDIGIT_LC_utf8(p) _generic_LC_swash_utf8(isDIGIT_LC, _CC_DIGIT, p)
-#define isGRAPH_LC_utf8(p) _generic_LC_swash_utf8(isGRAPH_LC, _CC_GRAPH, p)
-#define isIDCONT_LC_utf8(p) _generic_LC_func_utf8(isIDCONT_LC, _is_utf8_perl_idcont, p)
-#define isIDFIRST_LC_utf8(p) _generic_LC_func_utf8(isIDFIRST_LC, _is_utf8_perl_idstart, p)
-#define isLOWER_LC_utf8(p) _generic_LC_swash_utf8(isLOWER_LC, _CC_LOWER, p)
-#define isPRINT_LC_utf8(p) _generic_LC_swash_utf8(isPRINT_LC, _CC_PRINT, p)
-#define isPSXSPC_LC_utf8(p) isSPACE_LC_utf8(p) /* space is identical to posix
- space under locale */
-#define isPUNCT_LC_utf8(p) _generic_LC_swash_utf8(isPUNCT_LC, _CC_PUNCT, p)
-#define isSPACE_LC_utf8(p) _generic_LC_func_utf8(isSPACE_LC, is_XPERLSPACE_high, p)
-#define isUPPER_LC_utf8(p) _generic_LC_swash_utf8(isUPPER_LC, _CC_UPPER, p)
-#define isWORDCHAR_LC_utf8(p) _generic_LC_swash_utf8(isWORDCHAR_LC, \
- _CC_WORDCHAR, p)
-#define isXDIGIT_LC_utf8(p) _generic_LC_func_utf8(isXDIGIT_LC, is_XDIGIT_high, p)
+#define _generic_LC_utf8(name, p) _base_generic_utf8(name, name, p, 1)
+
+#define isALPHA_LC_utf8(p) _generic_LC_utf8(ALPHA, p)
+#define isALPHANUMERIC_LC_utf8(p) _generic_LC_utf8(ALPHANUMERIC, p)
+#define isASCII_LC_utf8(p) _generic_LC_utf8(ASCII, p)
+#define isBLANK_LC_utf8(p) _generic_LC_utf8(BLANK, p)
+#define isCNTRL_LC_utf8(p) _generic_LC_utf8(CNTRL, p)
+#define isDIGIT_LC_utf8(p) _generic_LC_utf8(DIGIT, p)
+#define isGRAPH_LC_utf8(p) _generic_LC_utf8(GRAPH, p)
+#define isIDCONT_LC_utf8(p) _generic_LC_utf8(IDCONT, p)
+#define isIDFIRST_LC_utf8(p) _generic_LC_utf8(IDFIRST, p)
+#define isLOWER_LC_utf8(p) _generic_LC_utf8(LOWER, p)
+#define isPRINT_LC_utf8(p) _generic_LC_utf8(PRINT, p)
+#define isPSXSPC_LC_utf8(p) _generic_LC_utf8(PSXSPC, p)
+#define isPUNCT_LC_utf8(p) _generic_LC_utf8(PUNCT, p)
+#define isSPACE_LC_utf8(p) _generic_LC_utf8(SPACE, p)
+#define isUPPER_LC_utf8(p) _generic_LC_utf8(UPPER, p)
+#define isWORDCHAR_LC_utf8(p) _generic_LC_utf8(WORDCHAR, p)
+#define isXDIGIT_LC_utf8(p) _generic_LC_utf8(XDIGIT, p)
+
+/* For internal core Perl use only: the base macros for defining macros like
+ * isALPHA_LC_utf8_safe. These are like _generic_utf8, but if the first code
+ * point in 'p' is within the 0-255 range, it uses locale rules from the
+ * passed-in 'macro' parameter */
+#define _generic_LC_utf8_safe(macro, p, e, above_latin1) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) \
+ (UTF8_IS_INVARIANT(*(p))) \
+ ? macro(*(p)) \
+ : (UTF8_IS_DOWNGRADEABLE_START(*(p)) \
+ ? ((LIKELY((e) - (p) > 1 && UTF8_IS_CONTINUATION(*((p)+1)))) \
+ ? macro(EIGHT_BIT_UTF8_TO_NATIVE(*(p), *((p)+1))) \
+ : (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0)) \
+ : above_latin1))
+
+#define _generic_LC_swash_utf8_safe(macro, classnum, p, e) \
+ _generic_LC_utf8_safe(macro, p, e, \
+ _is_utf8_FOO_with_len(classnum, p, e))
+
+#define _generic_LC_func_utf8_safe(macro, above_latin1, p, e) \
+ _generic_LC_utf8_safe(macro, p, e, above_latin1(p, e))
+
+#define _generic_LC_non_swash_utf8_safe(classnum, above_latin1, p, e) \
+ _generic_LC_utf8_safe(classnum, p, e, \
+ (UNLIKELY((e) - (p) < UTF8SKIP(p)) \
+ ? (_force_out_malformed_utf8_message( \
+ (U8 *) (p), (U8 *) (e), 0, 1), 0) \
+ : above_latin1(p)))
+
+#define isALPHANUMERIC_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isALPHANUMERIC_LC, \
+ _CC_ALPHANUMERIC, p, e)
+#define isALPHA_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isALPHA_LC, _CC_ALPHA, p, e)
+#define isASCII_LC_utf8_safe(p, e) \
+ (__ASSERT_(_utf8_safe_assert(p, e)) isASCII_LC(*(p)))
+#define isBLANK_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isBLANK_LC, is_HORIZWS_high, p, e)
+#define isCNTRL_LC_utf8_safe(p, e) \
+ _generic_LC_utf8_safe(isCNTRL_LC, p, e, 0)
+#define isDIGIT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isDIGIT_LC, _CC_DIGIT, p, e)
+#define isGRAPH_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isGRAPH_LC, _CC_GRAPH, p, e)
+#define isIDCONT_LC_utf8_safe(p, e) \
+ _generic_LC_func_utf8_safe(isIDCONT_LC, \
+ _is_utf8_perl_idcont_with_len, p, e)
+#define isIDFIRST_LC_utf8_safe(p, e) \
+ _generic_LC_func_utf8_safe(isIDFIRST_LC, \
+ _is_utf8_perl_idstart_with_len, p, e)
+#define isLOWER_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isLOWER_LC, _CC_LOWER, p, e)
+#define isPRINT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isPRINT_LC, _CC_PRINT, p, e)
+#define isPSXSPC_LC_utf8_safe(p, e) isSPACE_LC_utf8_safe(p, e)
+#define isPUNCT_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isPUNCT_LC, _CC_PUNCT, p, e)
+#define isSPACE_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isSPACE_LC, is_XPERLSPACE_high, p, e)
+#define isUPPER_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isUPPER_LC, _CC_UPPER, p, e)
+#define isWORDCHAR_LC_utf8_safe(p, e) \
+ _generic_LC_swash_utf8_safe(isWORDCHAR_LC, _CC_WORDCHAR, p, e)
+#define isXDIGIT_LC_utf8_safe(p, e) \
+ _generic_LC_non_swash_utf8_safe(isXDIGIT_LC, is_XDIGIT_high, p, e)
/* Macros for backwards compatibility and for completeness when the ASCII and
* Latin1 values are identical */
-#define isALPHAU(c) isALPHA_L1(c)
-#define isDIGIT_L1(c) isDIGIT_A(c)
-#define isOCTAL(c) isOCTAL_A(c)
-#define isOCTAL_L1(c) isOCTAL_A(c)
-#define isXDIGIT_L1(c) isXDIGIT_A(c)
-#define isALNUM(c) isWORDCHAR(c)
-#define isALNUMU(c) isWORDCHAR_L1(c)
-#define isALNUM_LC(c) isWORDCHAR_LC(c)
-#define isALNUM_uni(c) isWORDCHAR_uni(c)
+#define isALPHAU(c) isALPHA_L1(c)
+#define isDIGIT_L1(c) isDIGIT_A(c)
+#define isOCTAL(c) isOCTAL_A(c)
+#define isOCTAL_L1(c) isOCTAL_A(c)
+#define isXDIGIT_L1(c) isXDIGIT_A(c)
+#define isALNUM(c) isWORDCHAR(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 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 isALNUM_utf8(p) isWORDCHAR_utf8(p)
+#define isALNUM_LC_utf8(p) isWORDCHAR_LC_utf8(p)
+#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_utf8(p) isALPHANUMERIC_utf8(p)
#define isALNUMC_LC_utf8(p) isALPHANUMERIC_LC_utf8(p)
/* On EBCDIC platforms, CTRL-@ is 0, CTRL-A is 1, etc, just like on ASCII,
=for apidoc Am|void|Newx|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<malloc> function.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
In 5.9.3, Newx() and friends replace the older New() API, and drops
the first parameter, I<x>, a debug aid which allowed callers to identify
=for apidoc Am|void|Newxc|void* ptr|int nitems|type|cast
The XSUB-writer's interface to the C C<malloc> function, with
-cast. See also C<Newx>.
+cast. See also C<L</Newx>>.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Newxz|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<malloc> function. The allocated
-memory is zeroed with C<memzero>. See also C<Newx>.
+memory is zeroed with C<memzero>. See also C<L</Newx>>.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Renew|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<realloc> function.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Renewc|void* ptr|int nitems|type|cast
The XSUB-writer's interface to the C C<realloc> function, with
cast.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Safefree|void* ptr
The XSUB-writer's interface to the C C<free> function.
-This should B<ONLY> be used on memory obtained using L<"Newx"> and friends.
+This should B<ONLY> be used on memory obtained using L</"Newx"> and friends.
=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
-C<type> is the type. Can do overlapping moves. See also C<Copy>.
+C<type> is the type. Can do overlapping moves. See also C<L</Copy>>.
=for apidoc Am|void *|MoveD|void* src|void* dest|int nitems|type
-Like C<Move> but returns dest. Useful
+Like C<Move> but returns C<dest>. Useful
for encouraging compilers to tail-call
optimise.
=for apidoc Am|void|Copy|void* src|void* dest|int nitems|type
The XSUB-writer's interface to the C C<memcpy> function. The C<src> is the
source, C<dest> is the destination, C<nitems> is the number of items, and
-C<type> is the type. May fail on overlapping copies. See also C<Move>.
+C<type> is the type. May fail on overlapping copies. See also C<L</Move>>.
=for apidoc Am|void *|CopyD|void* src|void* dest|int nitems|type
-Like C<Copy> but returns dest. Useful
+Like C<Copy> but returns C<dest>. Useful
for encouraging compilers to tail-call
optimise.
#define MEM_SIZE_MAX ((MEM_SIZE)~0)
-/* The +0.0 in MEM_WRAP_CHECK_ is an attempt to foil
- * overly eager compilers that will bleat about e.g.
- * (U16)n > (size_t)~0/sizeof(U16) always being false. */
+
#ifdef PERL_MALLOC_WRAP
-#define MEM_WRAP_CHECK(n,t) \
- (void)(UNLIKELY(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t)) && (croak_memory_wrap(),0))
-#define MEM_WRAP_CHECK_1(n,t,a) \
- (void)(UNLIKELY(sizeof(t) > 1 && ((MEM_SIZE)(n)+0.0) > MEM_SIZE_MAX/sizeof(t)) && (Perl_croak_nocontext("%s",(a)),0))
+
+/* This expression will be constant-folded at compile time. It checks
+ * whether or not the type of the count n is so small (e.g. U8 or U16, or
+ * U32 on 64-bit systems) that there's no way a wrap-around could occur.
+ * As well as avoiding the need for a run-time check in some cases, it's
+ * designed to avoid compiler warnings like:
+ * comparison is always false due to limited range of data type
+ * It's mathematically equivalent to
+ * max(n) * sizeof(t) > MEM_SIZE_MAX
+ */
+
+# define _MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) \
+ (8 * sizeof(n) + sizeof(t) > sizeof(MEM_SIZE))
+
+/* This is written in a slightly odd way to avoid various spurious
+ * compiler warnings. We *want* to write the expression as
+ * _MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) && (n > C)
+ * (for some compile-time constant C), but even when the LHS
+ * constant-folds to false at compile-time, g++ insists on emitting
+ * warnings about the RHS (e.g. "comparison is always false"), so instead
+ * we write it as
+ *
+ * (cond ? n : X) > C
+ *
+ * where X is a constant with X > C always false. Choosing a value for X
+ * is tricky. If 0, some compilers will complain about 0 > C always being
+ * false; if 1, Coverity complains when n happens to be the constant value
+ * '1', that cond ? 1 : 1 has the same value on both branches; so use C
+ * for X and hope that nothing else whines.
+ */
+
+# define _MEM_WRAP_WILL_WRAP(n,t) \
+ ((_MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) ? (MEM_SIZE)(n) : \
+ MEM_SIZE_MAX/sizeof(t)) > MEM_SIZE_MAX/sizeof(t))
+
+# define MEM_WRAP_CHECK(n,t) \
+ (void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,t)) \
+ && (croak_memory_wrap(),0))
+
+# define MEM_WRAP_CHECK_1(n,t,a) \
+ (void)(UNLIKELY(_MEM_WRAP_WILL_WRAP(n,t)) \
+ && (Perl_croak_nocontext("%s",(a)),0))
+
#define MEM_WRAP_CHECK_(n,t) MEM_WRAP_CHECK(n,t),
#define PERL_STRLEN_ROUNDUP(n) ((void)(((n) > MEM_SIZE_MAX - 2 * PERL_STRLEN_ROUNDUP_QUANTUM) ? (croak_memory_wrap(),0):0),((n-1+PERL_STRLEN_ROUNDUP_QUANTUM)&~((MEM_SIZE)PERL_STRLEN_ROUNDUP_QUANTUM-1)))
* - lots of ENV reads
*/
-PERL_EXPORT_C Malloc_t Perl_mem_log_alloc(const UV n, const UV typesize, const char *type_name, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-
-PERL_EXPORT_C Malloc_t Perl_mem_log_realloc(const UV n, const UV typesize, const char *type_name, Malloc_t oldalloc, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-
-PERL_EXPORT_C Malloc_t Perl_mem_log_free(Malloc_t oldalloc, const char *filename, const int linenumber, const char *funcname);
-
# ifdef PERL_CORE
# ifndef PERL_MEM_LOG_NOIMPL
enum mem_log_type {
#define Safefree(d) safefree(MEM_LOG_FREE((Malloc_t)(d)))
#endif
-#define Move(s,d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memmove((char*)(d),(const char*)(s), (n) * sizeof(t)))
-#define Copy(s,d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memcpy((char*)(d),(const char*)(s), (n) * sizeof(t)))
-#define Zero(d,n,t) (MEM_WRAP_CHECK_(n,t) (void)memzero((char*)(d), (n) * sizeof(t)))
+#define perl_assert_ptr(p) assert( ((void*)(p)) != 0 )
-#define MoveD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) memmove((char*)(d),(const char*)(s), (n) * sizeof(t)))
-#define CopyD(s,d,n,t) (MEM_WRAP_CHECK_(n,t) memcpy((char*)(d),(const char*)(s), (n) * sizeof(t)))
-#ifdef HAS_MEMSET
-#define ZeroD(d,n,t) (MEM_WRAP_CHECK_(n,t) memzero((char*)(d), (n) * sizeof(t)))
-#else
-/* Using bzero(), which returns void. */
-#define ZeroD(d,n,t) (MEM_WRAP_CHECK_(n,t) memzero((char*)(d), (n) * sizeof(t)),d)
-#endif
+
+#define Move(s,d,n,t) (MEM_WRAP_CHECK_(n,t) perl_assert_ptr(d), perl_assert_ptr(s), (void)memmove((char*)(d),(const char*)(s), (n) * sizeof(t)))
+#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)))
+
+#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 PoisonWith(d,n,t,b) (MEM_WRAP_CHECK_(n,t) (void)memset((char*)(d), (U8)(b), (n) * sizeof(t)))
#define PoisonNew(d,n,t) PoisonWith(d,n,t,0xAB)
# define PERL_POISON_EXPR(x)
#endif
-#ifdef USE_STRUCT_COPY
#define StructCopy(s,d,t) (*((t*)(d)) = *((t*)(s)))
-#else
-#define StructCopy(s,d,t) Copy(s,d,1,t)
-#endif
/* 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).
#ifdef NEED_VA_COPY
# ifdef va_copy
# define Perl_va_copy(s, d) va_copy(d, s)
+# elif defined(__va_copy)
+# define Perl_va_copy(s, d) __va_copy(d, s)
# else
-# if defined(__va_copy)
-# define Perl_va_copy(s, d) __va_copy(d, s)
-# else
-# define Perl_va_copy(s, d) Copy(s, d, 1, va_list)
-# endif
+# define Perl_va_copy(s, d) Copy(s, d, 1, va_list)
# endif
#endif
shortcut macro defined without -DPERL_CORE. Neither codesearch.google.com nor
CPAN::Unpack show any users outside the core. */
#ifdef PERL_CORE
-# define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), "Use of " s " is deprecated")
+# define deprecate(s) Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), \
+ "Use of " s " is deprecated")
+# define deprecate_disappears_in(when,message) \
+ Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), \
+ message ", and will disappear in Perl " when)
+# define deprecate_fatal_in(when,message) \
+ Perl_ck_warner_d(aTHX_ packWARN(WARN_DEPRECATED), \
+ message ". Its use will be fatal in Perl " when)
#endif
/* Internal macros to deal with gids and uids */
# if Uid_t_size > IVSIZE
# define sv_setuid(sv, uid) sv_setnv((sv), (NV)(uid))
# define SvUID(sv) SvNV(sv)
+# elif Uid_t_sign <= 0
+# define sv_setuid(sv, uid) sv_setiv((sv), (IV)(uid))
+# define SvUID(sv) SvIV(sv)
# else
-# if Uid_t_sign <= 0
-# define sv_setuid(sv, uid) sv_setiv((sv), (IV)(uid))
-# define SvUID(sv) SvIV(sv)
-# else
-# define sv_setuid(sv, uid) sv_setuv((sv), (UV)(uid))
-# define SvUID(sv) SvUV(sv)
-# endif
+# define sv_setuid(sv, uid) sv_setuv((sv), (UV)(uid))
+# define SvUID(sv) SvUV(sv)
# endif /* Uid_t_size */
# if Gid_t_size > IVSIZE
# define sv_setgid(sv, gid) sv_setnv((sv), (NV)(gid))
# define SvGID(sv) SvNV(sv)
+# elif Gid_t_sign <= 0
+# define sv_setgid(sv, gid) sv_setiv((sv), (IV)(gid))
+# define SvGID(sv) SvIV(sv)
# else
-# if Gid_t_sign <= 0
-# define sv_setgid(sv, gid) sv_setiv((sv), (IV)(gid))
-# define SvGID(sv) SvIV(sv)
-# else
-# define sv_setgid(sv, gid) sv_setuv((sv), (UV)(gid))
-# define SvGID(sv) SvUV(sv)
-# endif
+# define sv_setgid(sv, gid) sv_setuv((sv), (UV)(gid))
+# define SvGID(sv) SvUV(sv)
# endif /* Gid_t_size */
#endif
-#endif /* HANDY_H */
+#endif /* PERL_HANDY_H_ */
/*
- * Local variables:
- * c-indentation-style: bsd
- * c-basic-offset: 4
- * indent-tabs-mode: nil
- * End:
- *
* ex: set ts=8 sts=4 sw=4 et:
*/
https://perl5.git.perl.org / perl5.git / blobdiff