Fix planner's test for case-foldable characters in ILIKE with ICU.

tglsfdc · tglsfdc · commit 03c811a483b2 · 2019-08-12T13:15:47.000-04:00
As coded, the ICU-collation path in pattern_char_isalpha() failed to consider regular ASCII letters to be case-varying. This led to like_fixed_prefix treating too much of an ILIKE pattern as being a fixed prefix, so that indexscans derived from an ILIKE clause might miss entries that they should find. Per bug #15892 from James Inform. This is an oversight in the original ICU patch (commit eccfef8), so back-patch to v10 where that came in. Discussion: https://postgr.es/m/15892-e5d2bea3e8a04a1b@postgresql.org
diff --git a/src/backend/utils/adt/like_support.c b/src/backend/utils/adt/like_support.c
@@ -1437,8 +1437,9 @@ regex_selectivity(const char *patt, int pattlen, bool case_insensitive,
  * Check whether char is a letter (and, hence, subject to case-folding)
  *
  * In multibyte character sets or with ICU, we can't use isalpha, and it does
- * not seem worth trying to convert to wchar_t to use iswalpha.  Instead, just
- * assume any multibyte char is potentially case-varying.
+ * not seem worth trying to convert to wchar_t to use iswalpha or u_isalpha.
+ * Instead, just assume any non-ASCII char is potentially case-varying, and
+ * hard-wire knowledge of which ASCII chars are letters.
  */
 static int
 pattern_char_isalpha(char c, bool is_multibyte,
@@ -1449,7 +1450,8 @@ pattern_char_isalpha(char c, bool is_multibyte,
 	else if (is_multibyte && IS_HIGHBIT_SET(c))
 		return true;
 	else if (locale && locale->provider == COLLPROVIDER_ICU)
-		return IS_HIGHBIT_SET(c) ? true : false;
+		return IS_HIGHBIT_SET(c) ||
+			(c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
 #ifdef HAVE_LOCALE_T
 	else if (locale && locale->provider == COLLPROVIDER_LIBC)
 		return isalpha_l((unsigned char) c, locale->info.lt);
diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
@@ -983,6 +983,38 @@ SELECT relname, pg_get_indexdef(oid) FROM pg_class WHERE relname LIKE 'collate_t
  collate_test1_idx4 | CREATE INDEX collate_test1_idx4 ON collate_tests.collate_test1 USING btree (((b || 'foo'::text)) COLLATE "POSIX")
 (4 rows)
 
+set enable_seqscan = off;
+explain (costs off)
+select * from collate_test1 where b ilike 'abc';
+          QUERY PLAN           
+-------------------------------
+ Seq Scan on collate_test1
+   Filter: (b ~~* 'abc'::text)
+(2 rows)
+
+select * from collate_test1 where b ilike 'abc';
+ a |  b  
+---+-----
+ 1 | abc
+ 4 | ABC
+(2 rows)
+
+explain (costs off)
+select * from collate_test1 where b ilike 'ABC';
+          QUERY PLAN           
+-------------------------------
+ Seq Scan on collate_test1
+   Filter: (b ~~* 'ABC'::text)
+(2 rows)
+
+select * from collate_test1 where b ilike 'ABC';
+ a |  b  
+---+-----
+ 1 | abc
+ 4 | ABC
+(2 rows)
+
+reset enable_seqscan;
 -- schema manipulation commands
 CREATE ROLE regress_test_role;
 CREATE SCHEMA test_schema;
@@ -1867,8 +1899,9 @@ SELECT (SELECT count(*) FROM test33_0) <> (SELECT count(*) FROM test33_1);
 (1 row)
 
 -- cleanup
+RESET search_path;
 SET client_min_messages TO warning;
 DROP SCHEMA collate_tests CASCADE;
-RESET search_path;
+RESET client_min_messages;
 -- leave a collation for pg_upgrade test
 CREATE COLLATION coll_icu_upgrade FROM "und-x-icu";
diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
@@ -341,6 +341,15 @@ CREATE INDEX collate_test1_idx6 ON collate_test1 ((a COLLATE "C")); -- fail
 
 SELECT relname, pg_get_indexdef(oid) FROM pg_class WHERE relname LIKE 'collate_test%_idx%' ORDER BY 1;
 
+set enable_seqscan = off;
+explain (costs off)
+select * from collate_test1 where b ilike 'abc';
+select * from collate_test1 where b ilike 'abc';
+explain (costs off)
+select * from collate_test1 where b ilike 'ABC';
+select * from collate_test1 where b ilike 'ABC';
+reset enable_seqscan;
+
 
 -- schema manipulation commands
 
@@ -712,9 +721,10 @@ SELECT (SELECT count(*) FROM test33_0) <> (SELECT count(*) FROM test33_1);
 
 
 -- cleanup
+RESET search_path;
 SET client_min_messages TO warning;
 DROP SCHEMA collate_tests CASCADE;
-RESET search_path;
+RESET client_min_messages;
 
 -- leave a collation for pg_upgrade test
 CREATE COLLATION coll_icu_upgrade FROM "und-x-icu";
