diff options
| author | Yves Orton <demerphq@gmail.com> | 2009-10-25 20:37:08 +0100 |
|---|---|---|
| committer | Yves Orton <demerphq@gmail.com> | 2009-10-25 20:37:08 +0100 |
| commit | 0abd0d78a73da1c4d13b1c700526b7e5d03b32d4 (patch) | |
| tree | fb805d77831ce30b7330a3a5956e1ea4123e43a2 /regexec.c | |
| parent | fe88edf0c4ada4230b84bdb5417029b8f766694a (diff) | |
| download | perl-0abd0d78a73da1c4d13b1c700526b7e5d03b32d4.tar.gz | |
disable non-unicode case insensitive trie matching
Also revert 8902bb05b18c9858efa90229ca1ee42b17277554 as it merely
masked one symptom of the deeper problems.
Also fixes RT #69973, which was a segfault which was exposed by
8902bb05, see the ticket for further details.
http://rt.perl.org/rt3//Public/Bug/Display.html?id=69973
At the code of this is the problem that in unicode matching a bunch
of code points have case folding rules beyond just A-Z/a-z. Since
the case folding rules are decided at runtime by the string, we cant
use the same TRIE tables for both unicode/non-unicode matching.
Until this is reconciled or some other solution is found case insensitive
matching only gets the TRIE optimisation when the pattern is uniocde.
From CaseFolding.txt:
00B5; C; 03BC; # MICRO SIGN
00C0; C; 00E0; # LATIN CAPITAL LETTER A WITH GRAVE
00C1; C; 00E1; # LATIN CAPITAL LETTER A WITH ACUTE
00C2; C; 00E2; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
00C3; C; 00E3; # LATIN CAPITAL LETTER A WITH TILDE
00C4; C; 00E4; # LATIN CAPITAL LETTER A WITH DIAERESIS
00C5; C; 00E5; # LATIN CAPITAL LETTER A WITH RING ABOVE
00C6; C; 00E6; # LATIN CAPITAL LETTER AE
00C7; C; 00E7; # LATIN CAPITAL LETTER C WITH CEDILLA
00C8; C; 00E8; # LATIN CAPITAL LETTER E WITH GRAVE
00C9; C; 00E9; # LATIN CAPITAL LETTER E WITH ACUTE
00CA; C; 00EA; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
00CB; C; 00EB; # LATIN CAPITAL LETTER E WITH DIAERESIS
00CC; C; 00EC; # LATIN CAPITAL LETTER I WITH GRAVE
00CD; C; 00ED; # LATIN CAPITAL LETTER I WITH ACUTE
00CE; C; 00EE; # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
00CF; C; 00EF; # LATIN CAPITAL LETTER I WITH DIAERESIS
00D0; C; 00F0; # LATIN CAPITAL LETTER ETH
00D1; C; 00F1; # LATIN CAPITAL LETTER N WITH TILDE
00D2; C; 00F2; # LATIN CAPITAL LETTER O WITH GRAVE
00D3; C; 00F3; # LATIN CAPITAL LETTER O WITH ACUTE
00D4; C; 00F4; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
00D5; C; 00F5; # LATIN CAPITAL LETTER O WITH TILDE
00D6; C; 00F6; # LATIN CAPITAL LETTER O WITH DIAERESIS
00D8; C; 00F8; # LATIN CAPITAL LETTER O WITH STROKE
00D9; C; 00F9; # LATIN CAPITAL LETTER U WITH GRAVE
00DA; C; 00FA; # LATIN CAPITAL LETTER U WITH ACUTE
00DB; C; 00FB; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
00DC; C; 00FC; # LATIN CAPITAL LETTER U WITH DIAERESIS
00DD; C; 00FD; # LATIN CAPITAL LETTER Y WITH ACUTE
00DE; C; 00FE; # LATIN CAPITAL LETTER THORN
00DF; F; 0073 0073; # LATIN SMALL LETTER SHARP S
Diffstat (limited to 'regexec.c')
| -rw-r--r-- | regexec.c | 9 |
1 files changed, 2 insertions, 7 deletions
@@ -1105,16 +1105,15 @@ Perl_re_intuit_start(pTHX_ REGEXP * const rx, SV *sv, char *strpos, #define REXEC_TRIE_READ_CHAR(trie_type, trie, widecharmap, uc, uscan, len, \ uvc, charid, foldlen, foldbuf, uniflags) STMT_START { \ - UV uvc_unfolded = 0; \ switch (trie_type) { \ case trie_utf8_fold: \ if ( foldlen>0 ) { \ - uvc_unfolded = uvc = utf8n_to_uvuni( uscan, UTF8_MAXLEN, &len, uniflags ); \ + uvc = utf8n_to_uvuni( uscan, UTF8_MAXLEN, &len, uniflags ); \ foldlen -= len; \ uscan += len; \ len=0; \ } else { \ - uvc_unfolded = uvc = utf8n_to_uvuni( (U8*)uc, UTF8_MAXLEN, &len, uniflags ); \ + uvc = utf8n_to_uvuni( (U8*)uc, UTF8_MAXLEN, &len, uniflags ); \ uvc = to_uni_fold( uvc, foldbuf, &foldlen ); \ foldlen -= UNISKIP( uvc ); \ uscan = foldbuf + UNISKIP( uvc ); \ @@ -1140,7 +1139,6 @@ uvc, charid, foldlen, foldbuf, uniflags) STMT_START { \ uvc = (UV)*uc; \ len = 1; \ } \ - \ if (uvc < 256) { \ charid = trie->charmap[ uvc ]; \ } \ @@ -1153,9 +1151,6 @@ uvc, charid, foldlen, foldbuf, uniflags) STMT_START { \ charid = (U16)SvIV(*svpp); \ } \ } \ - if (!charid && trie_type == trie_utf8_fold && !UTF) { \ - charid = trie->charmap[uvc_unfolded]; \ - } \ } STMT_END #define REXEC_FBC_EXACTISH_CHECK(CoNd) \ |