From: Yves Orton Date: Sun, 25 Oct 2009 19:37:08 +0000 (+0100) Subject: disable non-unicode case insensitive trie matching X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=0abd0d78a73da1c4d13b1c700526b7e5d03b32d4;p=p5sagit%2Fp5-mst-13.2.git 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 --- diff --git a/ext/re/t/regop.t b/ext/re/t/regop.t index 9118bf6..46e6ec0 100644 --- a/ext/re/t/regop.t +++ b/ext/re/t/regop.t @@ -231,12 +231,12 @@ anchored "ABC" at 0 #Freeing REx: "(\\.COM|\\.EXE|\\.BAT|\\.CMD|\\.VBS|\\.VBE|\\.JS|\\.JSE|\\."...... %MATCHED% floating ""$ at 3..4 (checking floating) -1:1[1] 3:2[1] 5:2[64] 45:83[1] 47:84[1] 48:85[0] -stclass EXACTF <.> minlen 3 -Found floating substr ""$ at offset 30... -Does not contradict STCLASS... -Guessed: match at offset 26 -Matching stclass EXACTF <.> against ".exe" +#1:1[1] 3:2[1] 5:2[64] 45:83[1] 47:84[1] 48:85[0] +#stclass EXACTF <.> minlen 3 +#Found floating substr ""$ at offset 30... +#Does not contradict STCLASS... +#Guessed: match at offset 26 +#Matching stclass EXACTF <.> against ".exe" --- #Compiling REx "[q]" #size 12 nodes Got 100 bytes for offset annotations. diff --git a/regcomp.c b/regcomp.c index 6e9fa26..eb5f12f 100644 --- a/regcomp.c +++ b/regcomp.c @@ -2833,13 +2833,18 @@ S_study_chunk(pTHX_ RExC_state_t *pRExC_state, regnode **scanp, } } else { /* - Currently we assume that the trie can handle unicode and ascii - matches fold cased matches. If this proves true then the following - define will prevent tries in this situation. - - #define TRIE_TYPE_IS_SAFE (UTF || optype==EXACT) -*/ + Currently we do not believe that the trie logic can + handle case insensitive matching properly when the + pattern is not unicode (thus forcing unicode semantics). + + If/when this is fixed the following define can be swapped + in below to fully enable trie logic. + #define TRIE_TYPE_IS_SAFE 1 + +*/ +#define TRIE_TYPE_IS_SAFE (UTF || optype==EXACT) + if ( last && TRIE_TYPE_IS_SAFE ) { make_trie( pRExC_state, startbranch, first, cur, tail, count, diff --git a/regexec.c b/regexec.c index 402ede3..ec09c28 100644 --- a/regexec.c +++ b/regexec.c @@ -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) \