-
-Tests if the first C<len> bytes of string C<s> form a valid UTF-8
-character. Note that an INVARIANT (i.e. ASCII on non-EBCDIC) character is a
-valid UTF-8 character. The number of bytes in the UTF-8 character
-will be returned if it is valid, otherwise 0.
-
-This is the "slow" version as opposed to the "fast" version which is
-the "unrolled" IS_UTF8_CHAR(). E.g. for t/uni/class.t the speed
-difference is a factor of 2 to 3. For lengths (UTF8SKIP(s)) of four
-or less you should use the IS_UTF8_CHAR(), for lengths of five or more
-you should use the _slow(). In practice this means that the _slow()
-will be used very rarely, since the maximum Unicode code point (as of
-Unicode 4.1) is U+10FFFF, which encodes in UTF-8 to four bytes. Only
-the "Perl extended UTF-8" (e.g, the infamous 'v-strings') will encode into
-five bytes or more.
-
-=cut */
-PERL_STATIC_INLINE STRLEN
-S_is_utf8_char_slow(const U8 *s, const STRLEN len)
-{
- dTHX; /* The function called below requires thread context */
-
- STRLEN actual_len;
-
- PERL_ARGS_ASSERT_IS_UTF8_CHAR_SLOW;
-
- utf8n_to_uvchr(s, len, &actual_len, UTF8_CHECK_ONLY);
-
- return (actual_len == (STRLEN) -1) ? 0 : actual_len;
-}
-
-/*
-=for apidoc is_utf8_char_buf
-
-Returns the number of bytes that comprise the first UTF-8 encoded character in
-buffer C<buf>. C<buf_end> should point to one position beyond the end of the
-buffer. 0 is returned if C<buf> does not point to a complete, valid UTF-8
-encoded character.
-
-Note that an INVARIANT character (i.e. ASCII on non-EBCDIC
-machines) is a valid UTF-8 character.
-
-=cut */
-
-STRLEN
-Perl_is_utf8_char_buf(const U8 *buf, const U8* buf_end)
-{
-
- STRLEN len;
-
- PERL_ARGS_ASSERT_IS_UTF8_CHAR_BUF;
-
- if (buf_end <= buf) {
- return 0;
- }
-
- len = buf_end - buf;
- if (len > UTF8SKIP(buf)) {
- len = UTF8SKIP(buf);
- }
-
- if (IS_UTF8_CHAR_FAST(len))
- return IS_UTF8_CHAR(buf, len) ? len : 0;
- return is_utf8_char_slow(buf, len);
-}
-
-/*
-=for apidoc is_utf8_char
-
-Tests if some arbitrary number of bytes begins in a valid UTF-8
-character. Note that an INVARIANT (i.e. ASCII on non-EBCDIC machines)
-character is a valid UTF-8 character. The actual number of bytes in the UTF-8
-character will be returned if it is valid, otherwise 0.
-
-This function is deprecated due to the possibility that malformed input could
-cause reading beyond the end of the input buffer. Use L</is_utf8_char_buf>
-instead.
-
-=cut */
-
-STRLEN
-Perl_is_utf8_char(const U8 *s)
-{
- PERL_ARGS_ASSERT_IS_UTF8_CHAR;
-
- /* Assumes we have enough space, which is why this is deprecated */
- return is_utf8_char_buf(s, s + UTF8SKIP(s));
-}
-
-
-/*
https://perl5.git.perl.org / perl5.git / blobdiff