From: Karl Williamson <khw@khw-desktop.(none)>
Date: Sat, 8 May 2010 20:06:10 +0000 (-0600)
Subject: PATCH [perl #74978] dot after } breaks \N{}
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=37820adc4aeb8cb209843cf0abf3b24c8e5b59e8;p=p5sagit%2Fp5-mst-13.2.git

PATCH [perl #74978] dot after } breaks \N{}

The problem is that a dot can come between the braces in \N{foo.bar},
but when searching for it, I didn't stop looking at the right brace, so
it generated an error inappropriately.

This is essentially a minimum patch; efficiency could be improved
slightly with a little more work.
---

diff --git a/regcomp.c b/regcomp.c
index f665f0b..be5acdb 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -6762,11 +6762,10 @@ S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep, I32 *flagp)
 	    | PERL_SCAN_DISALLOW_PREFIX
 	    | (SIZE_ONLY ? PERL_SCAN_SILENT_ILLDIGIT : 0);
     
-	char * endchar = strchr(RExC_parse, '.');
-	if (endchar) {
+	char * endchar = RExC_parse + strcspn(RExC_parse, ".}");
+	if (endchar < endbrace) {
 	    ckWARNreg(endchar, "Using just the first character returned by \\N{} in character class");
 	}
-	else endchar = endbrace;
 
 	length_of_hex = (STRLEN)(endchar - RExC_parse);
 	*valuep = grok_hex(RExC_parse, &length_of_hex, &flags, NULL);
@@ -6817,8 +6816,7 @@ S_reg_namedseq(pTHX_ RExC_state_t *pRExC_state, UV *valuep, I32 *flagp)
 
 	    /* Code points are separated by dots.  If none, there is only one
 	     * code point, and is terminated by the brace */
-	    endchar = strchr(RExC_parse, '.');
-	    if (! endchar) endchar = endbrace;
+	    endchar = RExC_parse + strcspn(RExC_parse, ".}");
 
 	    /* The values are Unicode even on EBCDIC machines */
 	    length_of_hex = (STRLEN)(endchar - RExC_parse);
diff --git a/t/re/pat.t b/t/re/pat.t
index 40ae52e..7b9594c 100644
--- a/t/re/pat.t
+++ b/t/re/pat.t
@@ -23,7 +23,7 @@ BEGIN {
 }
 
 
-plan tests => 297;  # Update this when adding/deleting tests.
+plan tests => 299;  # Update this when adding/deleting tests.
 
 run_tests() unless caller;
 
@@ -987,6 +987,12 @@ sub run_tests {
         ok "abbbbc" =~ m/\N{3,4}/ && $& eq "abbb", '"abbbbc" =~ m/\N{3,4}/ && $& eq "abbb"';
     }
 
+    {
+        use charnames ":full";
+        local $Message = '[perl #74982] Period coming after \N{}';
+        ok "\x{ff08}." =~ m/\N{FULLWIDTH LEFT PARENTHESIS}./ && $& eq "\x{ff08}.";
+        ok "\x{ff08}." =~ m/[\N{FULLWIDTH LEFT PARENTHESIS}]./ && $& eq "\x{ff08}.";
+    }
 
 } # End of sub run_tests