diff options
| author | karl williamson <public@khwilliamson.com> | 2008-11-05 11:42:16 -0700 |
|---|---|---|
| committer | David Mitchell <davem@iabyn.com> | 2009-01-05 20:59:43 +0000 |
| commit | 223f428994e176e66ea910f6fc1c59be58c44497 (patch) | |
| tree | e441370b48f6606bab2097650980daabc27af893 /regcomp.c | |
| parent | e2e39fcceab23a76ef1286d497aae405e36e4efc (diff) | |
| download | perl-223f428994e176e66ea910f6fc1c59be58c44497.tar.gz | |
Reolve perlbug #59328: In re's, \N{U+...} doesn't match for ... > 256
Subject: PATCH [perl #59328] In re's, \N{U+...} doesn't match for ... > 256
Message-ID: <49124B78.2000907@khwilliamson.com>
Date: Wed, 05 Nov 2008 18:42:16 -0700
p4raw-id: //depot/perl@34747
(cherry picked from commit a4893424bce3ee5da2b2e8e1c256b806c74bfb50)
Diffstat (limited to 'regcomp.c')
| -rw-r--r-- | regcomp.c | 22 |
1 files changed, 16 insertions, 6 deletions
@@ -6529,20 +6529,30 @@ S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep) | PERL_SCAN_DISALLOW_PREFIX | (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0); UV cp; - char string; len = (STRLEN)(endbrace - name - 2); cp = grok_hex(name + 2, &len, &fl, NULL); if ( len != (STRLEN)(endbrace - name - 2) ) { cp = 0xFFFD; } - if (cp > 0xff) - RExC_utf8 = 1; if ( valuep ) { + if (cp > 0xff) RExC_utf8 = 1; *valuep = cp; return NULL; } - string = (char)cp; - sv_str= newSVpvn(&string, 1); + + /* Need to convert to utf8 if either: won't fit into a byte, or the re + * is going to be in utf8 and the representation changes under utf8. */ + if (cp > 0xff || (RExC_utf8 && ! UNI_IS_INVARIANT(cp))) { + U8 string[UTF8_MAXBYTES+1]; + U8 *tmps; + RExC_utf8 = 1; + tmps = uvuni_to_utf8(string, cp); + sv_str = newSVpvn_utf8((char*)string, tmps - string, TRUE); + } else { /* Otherwise, no need for utf8, can skip that step */ + char string; + string = (char)cp; + sv_str= newSVpvn(&string, 1); + } } else { /* fetch the charnames handler for this scope */ HV * const table = GvHV(PL_hintgv); @@ -6721,7 +6731,7 @@ S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep) Set_Node_Cur_Length(ret); /* MJD */ RExC_parse--; nextchar(pRExC_state); - } else { + } else { /* zero length */ ret = reg_node(pRExC_state,NOTHING); } if (!cached) { |