diff options
| -rw-r--r-- | mathoms.c | 30 | ||||
| -rw-r--r-- | utf8.c | 30 |
2 files changed, 30 insertions, 30 deletions
@@ -1693,36 +1693,6 @@ Perl_valid_utf8_to_uvuni(pTHX_ const U8 *s, STRLEN *retlen) } /* -=for apidoc utf8_to_uvchr - -Returns the native code point of the first character in the string C<s> -which is assumed to be in UTF-8 encoding; C<retlen> will be set to the -length, in bytes, of that character. - -Some, but not all, UTF-8 malformations are detected, and in fact, some -malformed input could cause reading beyond the end of the input buffer, which -is why this function is deprecated. Use L</utf8_to_uvchr_buf> instead. - -If C<s> points to one of the detected malformations, and UTF8 warnings are -enabled, zero is returned and C<*retlen> is set (if C<retlen> isn't -C<NULL>) to -1. If those warnings are off, the computed value if well-defined (or -the Unicode REPLACEMENT CHARACTER, if not) is silently returned, and C<*retlen> -is set (if C<retlen> isn't NULL) so that (S<C<s> + C<*retlen>>) is the -next possible position in C<s> that could begin a non-malformed character. -See L</utf8n_to_uvchr> for details on when the REPLACEMENT CHARACTER is returned. - -=cut -*/ - -UV -Perl_utf8_to_uvchr(pTHX_ const U8 *s, STRLEN *retlen) -{ - PERL_ARGS_ASSERT_UTF8_TO_UVCHR; - - return utf8_to_uvchr_buf(s, s + UTF8_MAXBYTES, retlen); -} - -/* =for apidoc utf8_to_uvuni Returns the Unicode code point of the first character in the string C<s> @@ -5851,5 +5851,35 @@ Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags) } /* +=for apidoc utf8_to_uvchr + +Returns the native code point of the first character in the string C<s> +which is assumed to be in UTF-8 encoding; C<retlen> will be set to the +length, in bytes, of that character. + +Some, but not all, UTF-8 malformations are detected, and in fact, some +malformed input could cause reading beyond the end of the input buffer, which +is why this function is deprecated. Use L</utf8_to_uvchr_buf> instead. + +If C<s> points to one of the detected malformations, and UTF8 warnings are +enabled, zero is returned and C<*retlen> is set (if C<retlen> isn't +C<NULL>) to -1. If those warnings are off, the computed value if well-defined (or +the Unicode REPLACEMENT CHARACTER, if not) is silently returned, and C<*retlen> +is set (if C<retlen> isn't NULL) so that (S<C<s> + C<*retlen>>) is the +next possible position in C<s> that could begin a non-malformed character. +See L</utf8n_to_uvchr> for details on when the REPLACEMENT CHARACTER is returned. + +=cut +*/ + +UV +Perl_utf8_to_uvchr(pTHX_ const U8 *s, STRLEN *retlen) +{ + PERL_ARGS_ASSERT_UTF8_TO_UVCHR; + + return utf8_to_uvchr_buf(s, s + UTF8_MAXBYTES, retlen); +} + +/* * ex: set ts=8 sts=4 sw=4 et: */ |