Lines Matching refs:utf
134 BOOL utf = md->utf;
149 the length passed is zero. Note that in caseless UTF-8 mode, the number of
171 BOOL utf = md->utf;
192 /* Separate the caseless case for speed. In UTF-8 mode we can only do this
199 if (utf)
202 data units matched may differ, because in UTF-8 there are some characters
204 For example, U+023A (2 bytes in UTF-8) is the upper case version of U+2C65
205 (3 bytes in UTF-8); a sequence of 3 of the former uses 6 bytes, as does a
233 /* The same code works when not in UTF-8 mode and in UTF-8 mode when there
250 are in UTF-8 mode. */
490 the md structure (e.g. utf, end_subject) into individual variables to improve
524 register BOOL utf; /* Local copy of UTF flag for speed */
716 utf = md->utf; /* Local copy of the flag */
718 utf = FALSE;
1667 move back, this match function fails. When working with UTF-8 we move
1672 if (utf)
1685 /* No UTF-8 support, or not in UTF-8 mode: count is byte count */
2182 It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to
2187 if (utf)
2238 /* Not in UTF-8 mode, but we may still have PCRE_UCP set, and for
2322 if (utf) ACROSSCHAR(eptr < md->end_subject, *eptr, eptr++);
2327 /* Match a single byte, even in UTF-8 mode. This opcode really does match
2661 if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
2860 0-127 when UTF-8 processing is enabled. The only difference between
2915 if (utf)
2935 /* Not UTF mode */
2967 if (utf)
2990 /* Not UTF mode */
3023 if (utf)
3055 /* Not UTF mode */
3094 encountered only when UTF-8 mode mode is supported. In the 16-bit and
3096 UTF is not supported. */
3149 if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
3173 if (!PRIV(xclass)(c, data, utf)) RRETURN(MATCH_NOMATCH);
3196 if (!PRIV(xclass)(c, data, utf)) break;
3208 if (utf) BACKCHAR(eptr);
3222 if (utf)
3236 /* Not UTF mode */
3259 if (utf)
3303 /* Not UTF mode */
3391 The various UTF/non-UTF and caseful/caseless cases are handled separately,
3396 if (utf)
3493 /* If the length of a UTF-8 character is 1, we fall through here, and
3494 obey the code as for non-UTF-8 characters below, though in this case the
3499 /* When not in UTF-8 mode, load a single-byte character. */
3503 or may not be in UTF mode. The code is duplicated for the caseless and
3517 /* fc must be < 128 if UTF is enabled. */
3522 if (utf && fc > 127)
3525 if (utf && fc > 127)
3661 if (utf)
3791 if (utf && fc > 127)
3794 if (utf && fc > 127)
3802 if (utf)
3818 /* Not UTF mode */
3837 if (utf)
3856 /* Not UTF mode */
3882 if (utf)
3909 /* Not UTF mode */
3939 if (utf)
3955 /* Not UTF mode */
3973 if (utf)
3992 /* Not UTF mode */
4017 if (utf)
4044 /* Not UTF mode */
4129 in UTF-8 mode, '.' matches a character of any length, but for the other
4147 (i.e. keep it out of the loop). Separate the UTF-8 code completely as that
4148 is tidier. Also separate the UCP code, which can be the same for both UTF-8
4357 if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
4371 /* Handle all other cases when the coding is UTF-8 */
4374 if (utf) switch(ctype)
4624 /* Code for the non-UTF-8 case for minimum matching of operators other
4875 subsequent match. Again, separate the UTF-8 case for speed, and also
5118 if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
5132 if (utf)
5257 /* Not UTF mode */
5395 UTF-8 and UCP stuff separate. */
5610 if (utf) BACKCHAR(eptr);
5634 if (!utf) c = *eptr; else { GETCHARLEN(c, eptr, len); }
5662 if (!utf) c = *eptr; else
5673 if (!utf) c = *fptr; else
5690 if (utf)
5733 eptr = md->end_subject; /* Unlimited UTF-8 repeat */
5932 /* Not UTF mode */
6356 BOOL utf;
6415 /* These two settings are used in the code for checking a UTF-8 string that
6421 utf = md->utf = (re->options & PCRE_UTF8) != 0;
6425 /* Check a UTF-8 string if required. Pass back the character offset and error
6429 if (utf && (options & PCRE_NO_UTF8_CHECK) == 0)
6451 /* Check that a start_offset points to the start of a UTF character. */
6695 if (utf && first_char > 127)
6717 if (utf && req_char > 127)
6744 if (utf)
6788 if (utf)
6964 if (utf)
