Handle empty-string edge cases correctly in strpos().

tglsfdc · tglsfdc · commit bd1ef5799b04 · 2019-10-28T12:21:13.000-04:00
Commit 9556aa0 rearranged the innards of text_position() in a way that would make it not work for empty search strings. Which is fine, because all callers of that code special-case an empty pattern in some way. However, the primary use-case (text_position itself) got special-cased incorrectly: historically it's returned 1 not 0 for an empty search string. Restore the historical behavior. Per complaint from Austin Drenski (via Shay Rojansky). Back-patch to v12 where it got broken. Discussion: https://postgr.es/m/CADT4RqAz7oN4vkPir86Kg1_mQBmBxCp-L_=9vRpgSNPJf0KRkw@mail.gmail.com
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
@@ -1118,7 +1118,12 @@ text_position(text *t1, text *t2, Oid collid)
 	TextPositionState state;
 	int			result;
 
-	if (VARSIZE_ANY_EXHDR(t1) < 1 || VARSIZE_ANY_EXHDR(t2) < 1)
+	/* Empty needle always matches at position 1 */
+	if (VARSIZE_ANY_EXHDR(t2) < 1)
+		return 1;
+
+	/* Otherwise, can't match if haystack is shorter than needle */
+	if (VARSIZE_ANY_EXHDR(t1) < VARSIZE_ANY_EXHDR(t2))
 		return 0;
 
 	text_position_setup(t1, t2, collid, &state);
@@ -1272,6 +1277,9 @@ text_position_setup(text *t1, text *t2, Oid collid, TextPositionState *state)
  * Advance to the next match, starting from the end of the previous match
  * (or the beginning of the string, on first call).  Returns true if a match
  * is found.
+ *
+ * Note that this refuses to match an empty-string needle.  Most callers
+ * will have handled that case specially and we'll never see it here.
  */
 static bool
 text_position_next(TextPositionState *state)
diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
@@ -1420,6 +1420,24 @@ SELECT strpos('abcdef', 'xy') AS "pos_0";
      0
 (1 row)
 
+SELECT strpos('abcdef', '') AS "pos_1";
+ pos_1 
+-------
+     1
+(1 row)
+
+SELECT strpos('', 'xy') AS "pos_0";
+ pos_0 
+-------
+     0
+(1 row)
+
+SELECT strpos('', '') AS "pos_1";
+ pos_1 
+-------
+     1
+(1 row)
+
 --
 -- test replace
 --
diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
@@ -492,6 +492,12 @@ SELECT strpos('abcdef', 'cd') AS "pos_3";
 
 SELECT strpos('abcdef', 'xy') AS "pos_0";
 
+SELECT strpos('abcdef', '') AS "pos_1";
+
+SELECT strpos('', 'xy') AS "pos_0";
+
+SELECT strpos('', '') AS "pos_1";
+
 --
 -- test replace
 --
