Merge branch 'gawk-4.1-stable'

1 files changed, 12 insertions, 3 deletions

diff --git a/re.c b/re.c
index cf369a97..c522aeb9 100644
--- a/re.c
+++ b/re.c
@@ -268,17 +268,26 @@ research(Regexp *rp, char *str, int start,
 		rp->pat.not_bol = 1;
 
 	/*
-	 * Always do dfa search if can; if it fails, we won't bother
-	 * with the regex search.
+	 * Always do dfa search if can; if it fails, then even if
+	 * need_start is true, we won't bother with the regex search.
 	 *
 	 * The dfa matcher doesn't have a no_bol flag, so don't bother
 	 * trying it in that case.
 	 *
+	 * 7/2008: Skip the dfa matcher if need_start. The dfa matcher
+	 * has bugs in certain multibyte cases and it's too difficult
+	 * to try to special case things.
+	 * 7/2017: Apparently there are some cases where DFA gets
+	 * stuck, even in the C locale, so we use dfa only if not need_start.
+	 *
+	 * Should that issue ever get resolved, note this comment:
+	 *
 	 * 7/2016: The dfa matcher can't handle a case where searching
 	 * starts in the middle of a string, so don't bother trying it
 	 * in that case.
+	 *	if (rp->dfa && ! no_bol && start == 0) ...
 	 */
-	if (rp->dfareg != NULL && ! no_bol && start == 0) {
+	if (rp->dfareg != NULL && ! no_bol && ! need_start) {
 		struct dfa *superset = dfasuperset(rp->dfareg);
 		if (superset)
 			ret = dfaexec(superset, str+start, str+start+len,