#endif
AbnpdD |STRLEN |is_utf8_char |NN const U8 *s
Abmnpd |STRLEN |is_utf8_char_buf|NN const U8 *buf|NN const U8 *buf_end
+AnidR |Size_t |isUTF8_CHAR|NN const U8 * const s0 \
+ |NN const U8 * const e
AnmdpR |bool |is_utf8_string |NN const U8 *s|STRLEN len
AnidR |bool |is_utf8_string_flags \
|NN const U8 *s|STRLEN len|const U32 flags
#define init_stacks() Perl_init_stacks(aTHX)
#define init_tm(a) Perl_init_tm(aTHX_ a)
#define intro_my() Perl_intro_my(aTHX)
+#define isUTF8_CHAR S_isUTF8_CHAR
#define is_c9strict_utf8_string_loclen S_is_c9strict_utf8_string_loclen
#define is_lvalue_sub() Perl_is_lvalue_sub(aTHX)
#define is_safe_syscall(a,b,c,d) S_is_safe_syscall(aTHX_ a,b,c,d)
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
*
+ * This file contains tables and code adapted from
+ * http://bjoern.hoehrmann.de/utf-8/decoder/dfa/, which requires this
+ * copyright notice:
+
+Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+of the Software, and to permit persons to whom the Software is furnished to do
+so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+ *
* This file is a home for static inline functions that cannot go in other
* header files, because they depend on proto.h (included after most other
* headers) or struct definitions.
/*
+=for apidoc Am|STRLEN|isUTF8_CHAR|const U8 *s|const U8 *e
+
+Evaluates to non-zero if the first few bytes of the string starting at C<s> and
+looking no further than S<C<e - 1>> are well-formed UTF-8, as extended by Perl,
+that represents some code point; otherwise it evaluates to 0. If non-zero, the
+value gives how many bytes starting at C<s> comprise the code point's
+representation. Any bytes remaining before C<e>, but beyond the ones needed to
+form the first code point in C<s>, are not examined.
+
+The code point can be any that will fit in a UV on this machine, using Perl's
+extension to official UTF-8 to represent those higher than the Unicode maximum
+of 0x10FFFF. That means that this macro is used to efficiently decide if the
+next few bytes in C<s> is legal UTF-8 for a single character.
+
+Use C<L</isSTRICT_UTF8_CHAR>> to restrict the acceptable code points to those
+defined by Unicode to be fully interchangeable across applications;
+C<L</isC9_STRICT_UTF8_CHAR>> to use the L<Unicode Corrigendum
+#9|http://www.unicode.org/versions/corrigendum9.html> definition of allowable
+code points; and C<L</isUTF8_CHAR_flags>> for a more customized definition.
+
+Use C<L</is_utf8_string>>, C<L</is_utf8_string_loc>>, and
+C<L</is_utf8_string_loclen>> to check entire strings.
+
+Note that it is deprecated to use code points higher than what will fit in an
+IV. This macro does not raise any warnings for such code points, treating them
+as valid.
+
+Note also that a UTF-8 INVARIANT character (i.e. ASCII on non-EBCDIC machines)
+is a valid UTF-8 character.
+
+=cut
+
+This uses an adaptation of the table and algorithm given in
+http://bjoern.hoehrmann.de/utf-8/decoder/dfa/, which provides comprehensive
+documentation of the original version. A copyright notice for the original
+version is given at the beginning of this file. The Perl adapation is
+documented at the definition of perl_extended_utf8_dfa_tab[].
+
+*/
+
+PERL_STATIC_INLINE Size_t
+S_isUTF8_CHAR(const U8 * const s0, const U8 * const e)
+{
+ const U8 * s = s0;
+ UV state = 0;
+
+ PERL_ARGS_ASSERT_ISUTF8_CHAR;
+
+ /* This dfa is fast. If it accepts the input, it was for a well-formed,
+ * code point, which can be returned immediately. Otherwise, it is either
+ * malformed, or for the start byte FF which the dfa doesn't handle (except
+ * on 32-bit ASCII platforms where it trivially is an error). Call a
+ * helper function for the other platforms. */
+
+ while (s < e && LIKELY(state != 1)) {
+ state = perl_extended_utf8_dfa_tab[256
+ + state
+ + perl_extended_utf8_dfa_tab[*s]];
+ if (state != 0) {
+ s++;
+ continue;
+ }
+
+ return s - s0 + 1;
+ }
+
+#if defined(UV_IS_QUAD) || defined(EBCDIC)
+
+ if (NATIVE_UTF8_TO_I8(*s0) == 0xFF && e - s0 >= UTF8_MAXBYTES) {
+ return _is_utf8_char_helper(s0, e, 0);
+ }
+
+#endif
+
+ return 0;
+}
+
+/*
+
=for apidoc is_strict_utf8_string_loc
Like C<L</is_strict_utf8_string>> but stores the location of the failure (in the
PERL_CALLCONV bool Perl_io_close(pTHX_ IO* io, GV *gv, bool not_implicit, bool warn_on_fail);
#define PERL_ARGS_ASSERT_IO_CLOSE \
assert(io)
+#ifndef PERL_NO_INLINE_FUNCTIONS
+PERL_STATIC_INLINE Size_t S_isUTF8_CHAR(const U8 * const s0, const U8 * const e)
+ __attribute__warn_unused_result__;
+#define PERL_ARGS_ASSERT_ISUTF8_CHAR \
+ assert(s0); assert(e)
+#endif
+
/* PERL_CALLCONV bool Perl_is_ascii_string(const U8* const s, STRLEN len)
__attribute__warn_unused_result__
__attribute__pure__; */
* 6aaacc29ce24746bcb2bf82a920fcf90e07cf92d75325199c50f40754d39bb72 lib/unicore/mktables
* 21653d2744fdd071f9ef138c805393901bb9547cf3e777ebf50215a191f986ea lib/unicore/version
* 4bb677187a1a64e39d48f2e341b5ecb6c99857e49d7a79cf503bd8a3c709999b regen/charset_translations.pl
- * 9ea6338945a7d70e5ea4b31ac7856c0b521df96be002e94b4b3b7d31debbf3ab regen/regcharclass.pl
+ * 069232ed937edb5a8f6a2e0e6e2d56e76ecc8d4580804f4f1ee98c828905434c regen/regcharclass.pl
* 393f8d882713a3ba227351ad0f00ea4839fda74fcf77dcd1cdf31519925adba5 regen/regcharclass_multi_char_folds.pl
* ex: set ro: */
# that have that start byte. In other words, it is the natural stopping place
# that includes all Unicode code points.
#
-#UTF8_CHAR: Matches legal UTF-8 variant code points up through the 0x1FFFFFF
-#=> UTF8 :no_length_checks only_ascii_platform
-#0x80 - 0x1FFFFF
-
-#UTF8_CHAR: Matches legal UTF-EBCDIC variant code points up through 0x1FFFFFF
-#=> UTF8 :no_length_checks only_ebcdic_platform
-#0xA0 - 0x1FFFFF
-
#STRICT_UTF8_CHAR: Matches legal Unicode UTF-8 variant code points, no surrrogates nor non-character code points
-#=> UTF8 :no_length_checks only_ascii_platform
#0x0080 - 0xD7FF
#0xE000 - 0xFDCF
#0xFDF0 - 0xFFFD
#define isUTF8_POSSIBLY_PROBLEMATIC(c) (__ASSERT_(FITS_IN_8_BITS(c)) \
(U8) c >= 0xED)
-/* A helper macro for isUTF8_CHAR, so use that one instead of this. This was
- * generated by regen/regcharclass.pl, and then moved here. Then it was
- * hand-edited to add some LIKELY() calls, presuming that malformations are
- * unlikely. The lines that generated it were then commented out. This was
- * done because it takes on the order of 10 minutes to generate, and is never
- * going to change, unless the generated code is improved, and figuring out
- * the LIKELYs there would be hard.
- *
- UTF8_CHAR: Matches legal UTF-8 variant code points up through 0x1FFFFFF
-
- 0x80 - 0x1FFFFF
-*/
-/*** GENERATED CODE ***/
-#define is_UTF8_CHAR_utf8_no_length_checks(s) \
-( ( 0xC2 <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xDF ) ? \
- ( LIKELY( ( ((const U8*)s)[1] & 0xC0 ) == 0x80 ) ? 2 : 0 ) \
-: ( 0xE0 == ((const U8*)s)[0] ) ? \
- ( LIKELY( ( ( ((const U8*)s)[1] & 0xE0 ) == 0xA0 ) && ( ( ((const U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\
-: ( 0xE1 <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xEF ) ? \
- ( LIKELY( ( ( ((const U8*)s)[1] & 0xC0 ) == 0x80 ) && ( ( ((const U8*)s)[2] & 0xC0 ) == 0x80 ) ) ? 3 : 0 )\
-: ( 0xF0 == ((const U8*)s)[0] ) ? \
- ( LIKELY( ( ( 0x90 <= ((const U8*)s)[1] && ((const U8*)s)[1] <= 0xBF ) && ( ( ((const U8*)s)[2] & 0xC0 ) == 0x80 ) ) && ( ( ((const U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )\
-: ( ( ( ( 0xF1 <= ((const U8*)s)[0] && ((const U8*)s)[0] <= 0xF7 ) && LIKELY( ( ((const U8*)s)[1] & 0xC0 ) == 0x80 ) ) && LIKELY( ( ((const U8*)s)[2] & 0xC0 ) == 0x80 ) ) && LIKELY( ( ((const U8*)s)[3] & 0xC0 ) == 0x80 ) ) ? 4 : 0 )
-
-/* The above macro handles UTF-8 that has this start byte as the maximum */
-#define _IS_UTF8_CHAR_HIGHEST_START_BYTE 0xF7
-
/* A helper macro for isSTRICT_UTF8_CHAR, so use that one instead of this.
* Like is_UTF8_CHAR_utf8_no_length_checks(), this was moved here and LIKELYs
* added manually.
#define SHARP_S_SKIP 2
-/*
-
-=for apidoc Am|STRLEN|isUTF8_CHAR|const U8 *s|const U8 *e
-
-Evaluates to non-zero if the first few bytes of the string starting at C<s> and
-looking no further than S<C<e - 1>> are well-formed UTF-8, as extended by Perl,
-that represents some code point; otherwise it evaluates to 0. If non-zero, the
-value gives how many bytes starting at C<s> comprise the code point's
-representation. Any bytes remaining before C<e>, but beyond the ones needed to
-form the first code point in C<s>, are not examined.
-
-The code point can be any that will fit in a UV on this machine, using Perl's
-extension to official UTF-8 to represent those higher than the Unicode maximum
-of 0x10FFFF. That means that this macro is used to efficiently decide if the
-next few bytes in C<s> is legal UTF-8 for a single character.
-
-Use C<L</isSTRICT_UTF8_CHAR>> to restrict the acceptable code points to those
-defined by Unicode to be fully interchangeable across applications;
-C<L</isC9_STRICT_UTF8_CHAR>> to use the L<Unicode Corrigendum
-#9|http://www.unicode.org/versions/corrigendum9.html> definition of allowable
-code points; and C<L</isUTF8_CHAR_flags>> for a more customized definition.
-
-Use C<L</is_utf8_string>>, C<L</is_utf8_string_loc>>, and
-C<L</is_utf8_string_loclen>> to check entire strings.
-
-Note that it is deprecated to use code points higher than what will fit in an
-IV. This macro does not raise any warnings for such code points, treating them
-as valid.
-
-Note also that a UTF-8 INVARIANT character (i.e. ASCII on non-EBCDIC machines)
-is a valid UTF-8 character.
-
-=cut
-*/
-
-#define isUTF8_CHAR(s, e) \
- (UNLIKELY((e) <= (s)) \
- ? 0 \
- : (UTF8_IS_INVARIANT(*s)) \
- ? 1 \
- : UNLIKELY(((e) - (s)) < UTF8SKIP(s)) \
- ? 0 \
- : LIKELY(NATIVE_UTF8_TO_I8(*s) <= _IS_UTF8_CHAR_HIGHEST_START_BYTE) \
- ? is_UTF8_CHAR_utf8_no_length_checks(s) \
- : _is_utf8_char_helper(s, e, 0))
-
#define is_utf8_char_buf(buf, buf_end) isUTF8_CHAR(buf, buf_end)
#define bytes_from_utf8(s, lenp, is_utf8p) \
bytes_from_utf8_loc(s, lenp, is_utf8p, 0)