From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Fri, 19 Jul 2013 01:22:37 +0000 (-0400)
Subject: Fix regex match failures for backrefs combined with non-greedy quantifiers.
X-Git-Tag: REL9_4_BETA1~1302
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=e2bd904955e2221eddf01110b1f25002de2aaa83;p=postgresql

Fix regex match failures for backrefs combined with non-greedy quantifiers.

An ancient logic error in cfindloop() could cause the regex engine to fail
to find matches that begin later than the start of the string.  This
function is only used when the regex pattern contains a back reference,
and so far as we can tell the error is only reachable if the pattern is
non-greedy (i.e. its first quantifier uses the ? modifier).  Furthermore,
the actual match must begin after some potential match that satisfies the
DFA but then fails the back-reference's match test.

Reported and fixed by Jeevan Chalke, with cosmetic adjustments by me.
---

diff --git a/src/backend/regex/regexec.c b/src/backend/regex/regexec.c
index 3748a9c171..78ebdee39e 100644
--- a/src/backend/regex/regexec.c
+++ b/src/backend/regex/regexec.c
@@ -487,19 +487,21 @@ cfindloop(struct vars * v,
 					*coldp = cold;
 					return er;
 				}
-				if ((shorter) ? end == estop : end == begin)
-				{
-					/* no point in trying again */
-					*coldp = cold;
-					return REG_NOMATCH;
-				}
-				/* go around and try again */
+				/* try next shorter/longer match with same begin point */
 				if (shorter)
+				{
+					if (end == estop)
+						break;	/* NOTE BREAK OUT */
 					estart = end + 1;
+				}
 				else
+				{
+					if (end == begin)
+						break;	/* NOTE BREAK OUT */
 					estop = end - 1;
-			}
-		}
+				}
+			}					/* end loop over endpoint positions */
+		}						/* end loop over beginning positions */
 	} while (close < v->stop);
 
 	*coldp = cold;
diff --git a/src/test/regress/expected/regex.out b/src/test/regress/expected/regex.out
index 757f2a4028..df39ef937d 100644
--- a/src/test/regress/expected/regex.out
+++ b/src/test/regress/expected/regex.out
@@ -173,3 +173,18 @@ select 'a' ~ '((((((a+|)+|)+|)+|)+|)+|)';
  t
 (1 row)
 
+-- Test backref in combination with non-greedy quantifier
+-- https://core.tcl.tk/tcl/tktview/6585b21ca8fa6f3678d442b97241fdd43dba2ec0
+select 'Programmer' ~ '(\w).*?\1' as t;
+ t 
+---
+ t
+(1 row)
+
+select regexp_matches('Programmer', '(\w)(.*?\1)', 'g');
+ regexp_matches 
+----------------
+ {r,ogr}
+ {m,m}
+(2 rows)
+
diff --git a/src/test/regress/sql/regex.sql b/src/test/regress/sql/regex.sql
index 1426562119..e5f690263b 100644
--- a/src/test/regress/sql/regex.sql
+++ b/src/test/regress/sql/regex.sql
@@ -41,3 +41,8 @@ select 'a' ~ '($|^)*';
 -- Test for infinite loop in fixempties() (Tcl bugs 3604074, 3606683)
 select 'a' ~ '((((((a)*)*)*)*)*)*';
 select 'a' ~ '((((((a+|)+|)+|)+|)+|)+|)';
+
+-- Test backref in combination with non-greedy quantifier
+-- https://core.tcl.tk/tcl/tktview/6585b21ca8fa6f3678d442b97241fdd43dba2ec0
+select 'Programmer' ~ '(\w).*?\1' as t;
+select regexp_matches('Programmer', '(\w)(.*?\1)', 'g');