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[].
+documented at the definition of PL_extended_utf8_dfa_tab[].
*/
* helper function for the other platforms. */
while (s < e && LIKELY(state != 1)) {
- state = perl_extended_utf8_dfa_tab[256
+ state = PL_extended_utf8_dfa_tab[256
+ state
- + perl_extended_utf8_dfa_tab[*s]];
+ + PL_extended_utf8_dfa_tab[*s]];
if (state != 0) {
s++;
continue;
/*
+=for apidoc isSTRICT_UTF8_CHAR
+
+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 that represents some
+Unicode code point completely acceptable for open interchange between all
+applications; 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 largest acceptable code point is the Unicode maximum 0x10FFFF, and must not
+be a surrogate nor a non-character code point. Thus this excludes any code
+point from Perl's extended UTF-8.
+
+This is used to efficiently decide if the next few bytes in C<s> is
+legal Unicode-acceptable UTF-8 for a single character.
+
+Use 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; C<L</isUTF8_CHAR>> to check for Perl's extended UTF-8;
+and C<L</isUTF8_CHAR_flags>> for a more customized definition.
+
+Use C<L</is_strict_utf8_string>>, C<L</is_strict_utf8_string_loc>>, and
+C<L</is_strict_utf8_string_loclen>> to check entire strings.
+
+=cut
+
+This uses an adaptation of the tables 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 strict_extended_utf8_dfa_tab[].
+
+*/
+
+PERL_STATIC_INLINE Size_t
+S_isSTRICT_UTF8_CHAR(const U8 * const s0, const U8 * const e)
+{
+ const U8 * s = s0;
+ UV state = 0;
+
+ PERL_ARGS_ASSERT_ISSTRICT_UTF8_CHAR;
+
+ while (s < e && LIKELY(state != 1)) {
+ state = PL_strict_utf8_dfa_tab[256 + state + PL_strict_utf8_dfa_tab[*s]];
+
+ if (state != 0) {
+ s++;
+ continue;
+ }
+
+ return s - s0 + 1;
+ }
+
+#ifndef EBCDIC
+
+ /* The dfa above drops out for certain Hanguls; handle them specially */
+ if (is_HANGUL_ED_utf8_safe(s0, e)) {
+ return 3;
+ }
+
+#endif
+
+ return 0;
+}
+
+/*
+
+=for apidoc Am|STRLEN|isC9_STRICT_UTF8_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 that represents some
+Unicode non-surrogate 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 largest acceptable code point is the Unicode maximum 0x10FFFF. This
+differs from C<L</isSTRICT_UTF8_CHAR>> only in that it accepts non-character
+code points. This corresponds to
+L<Unicode Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>.
+which said that non-character code points are merely discouraged rather than
+completely forbidden in open interchange. See
+L<perlunicode/Noncharacter code points>.
+
+Use C<L</isUTF8_CHAR>> to check for Perl's extended UTF-8; and
+C<L</isUTF8_CHAR_flags>> for a more customized definition.
+
+Use C<L</is_c9strict_utf8_string>>, C<L</is_c9strict_utf8_string_loc>>, and
+C<L</is_c9strict_utf8_string_loclen>> to check entire strings.
+
+=cut
+
+This uses an adaptation of the tables 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 PL_c9_utf8_dfa_tab[].
+
+*/
+
+PERL_STATIC_INLINE Size_t
+S_isC9_STRICT_UTF8_CHAR(const U8 * const s0, const U8 * const e)
+{
+ const U8 * s = s0;
+ UV state = 0;
+
+ PERL_ARGS_ASSERT_ISC9_STRICT_UTF8_CHAR;
+
+ while (s < e && LIKELY(state != 1)) {
+ state = PL_c9_utf8_dfa_tab[256 + state + PL_c9_utf8_dfa_tab[*s]];
+
+ if (state != 0) {
+ s++;
+ continue;
+ }
+
+ return s - s0 + 1;
+ }
+
+ 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
assert(off <= 0);
while (off++ && s > start) {
- s--;
- while (UTF8_IS_CONTINUATION(*s) && s > start)
+ do {
s--;
+ } while (UTF8_IS_CONTINUATION(*s) && s > start);
}
GCC_DIAG_IGNORE(-Wcast-qual)
* 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 strict_utf8_dfa_tab[].
+ * Perl adapation is documented at the definition of PL_strict_utf8_dfa_tab[].
*/
const U8 * const s0 = s;
const U8 * send = s0 + curlen;
- UV uv;
+ UV uv = 0; /* The 0 silences some stupid compilers */
UV state = 0;
PERL_ARGS_ASSERT_UTF8N_TO_UVCHR_MSGS;
* cases. */
while (s < send && LIKELY(state != 1)) {
- UV type = strict_utf8_dfa_tab[*s];
+ UV type = PL_strict_utf8_dfa_tab[*s];
uv = (state == 0)
? ((0xff >> type) & NATIVE_UTF8_TO_I8(*s))
: UTF8_ACCUMULATE(uv, *s);
- state = strict_utf8_dfa_tab[256 + state + type];
+ state = PL_strict_utf8_dfa_tab[256 + state + type];
if (state != 0) {
s++;
https://perl5.git.perl.org / perl5.git / blobdiff