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

Commit 9556aa01c 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
index 299d8b5790dbc8a10d310a89ec0d8ab610789f62..1587b4ed02a2a61a90687b2d8ccdc31bdfff9424 100644 (file)
--- 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
index 486c00b3b3e4fe8fe11a1fa937b02497d1e87e51..54505d1cdaf470c265b5b4fc9a469115133d8d93 100644 (file)
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -1371,6 +1371,24 @@ 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
index 5744c9f8007ff2d090a02ba63559169fd10c36ed..6905b4d7c1a2c2c2ba765209a5f830470e73b88e 100644 (file)
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -479,6 +479,12 @@ 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
 --