diff options
Diffstat (limited to 'src/regex.c')
| -rw-r--r-- | src/regex.c | 63 |
1 files changed, 55 insertions, 8 deletions
diff --git a/src/regex.c b/src/regex.c index 846c87041b1..ae80ad0cee8 100644 --- a/src/regex.c +++ b/src/regex.c @@ -2530,6 +2530,7 @@ regex_compile (pattern, size, syntax, bufp) bufp->syntax = syntax; bufp->fastmap_accurate = 0; bufp->not_bol = bufp->not_eol = 0; + bufp->used_syntax = 0; /* Set `used' to zero, so that if we return an error, the pattern printer (for debugging) will think there's no pattern. We reset it @@ -2942,6 +2943,14 @@ regex_compile (pattern, size, syntax, bufp) SET_LIST_BIT (translated); } + /* In most cases the matching rule for char classes + only uses the syntax table for multibyte chars, + so that the content of the syntax-table it is not + hardcoded in the range_table. SPACE and WORD are + the two exceptions. */ + if ((1 << cc) & ((1 << RECC_SPACE) | (1 << RECC_WORD))) + bufp->used_syntax = 1; + /* Repeat the loop. */ continue; } @@ -3877,11 +3886,13 @@ analyse_first (p, pend, fastmap, multibyte) if (fastmap) { int c = RE_STRING_CHAR (p + 1, pend - p); - + /* When fast-scanning, the fastmap can be indexed either with + a char (smaller than 256) or with the first byte of + a char's byte sequence. So we have to conservatively add + both to the table. */ if (SINGLE_BYTE_CHAR_P (c)) fastmap[c] = 1; - else - fastmap[p[1]] = 1; + fastmap[p[1]] = 1; } break; @@ -3899,6 +3910,10 @@ analyse_first (p, pend, fastmap, multibyte) So any that are not listed in the charset are possible matches, even in multibyte buffers. */ if (!fastmap) break; + /* We don't need to mark LEADING_CODE_8_BIT_CONTROL specially + because it will automatically be set when needed by virtue of + being larger than the highest char of its charset (0xbf) but + smaller than (1<<BYTEWIDTH). */ for (j = CHARSET_BITMAP_SIZE (&p[-1]) * BYTEWIDTH; j < (1 << BYTEWIDTH); j++) fastmap[j] = 1; @@ -3909,7 +3924,13 @@ analyse_first (p, pend, fastmap, multibyte) for (j = CHARSET_BITMAP_SIZE (&p[-1]) * BYTEWIDTH - 1, p++; j >= 0; j--) if (!!(p[j / BYTEWIDTH] & (1 << (j % BYTEWIDTH))) ^ not) - fastmap[j] = 1; + { + fastmap[j] = 1; +#ifdef emacs + if (j >= 0x80 && j < 0xa0) + fastmap[LEADING_CODE_8_BIT_CONTROL] = 1; +#endif + } if ((not && multibyte) /* Any character set can possibly contain a character @@ -4352,11 +4373,33 @@ re_search_2 (bufp, str1, size1, str2, size2, startpos, range, regs, stop) } } else - while (range > lim && !fastmap[*d]) + do { - d++; - range--; - } + re_char *d_start = d; + while (range > lim && !fastmap[*d]) + { + d++; + range--; + } +#ifdef emacs + if (multibyte && range > lim) + { + /* Check that we are at the beginning of a char. */ + int at_boundary; + AT_CHAR_BOUNDARY_P (at_boundary, d, d_start); + if (at_boundary) + break; + else + { /* We have matched an internal byte of a char + rather than the leading byte, so it's a false + positive: we should keep scanning. */ + d++; range--; + } + } + else +#endif + break; + } while (1); startpos += irange - range; } @@ -6197,6 +6240,10 @@ re_compile_pattern (pattern, length, bufp) { reg_errcode_t ret; +#ifdef emacs + gl_state.current_syntax_table = current_buffer->syntax_table; +#endif + /* GNU code is written to assume at least RE_NREGS registers will be set (and at least one extra will be -1). */ bufp->regs_allocated = REGS_UNALLOCATED; |