Merge pull request #29 from postgres/master

Sync Fork from Upstream Repo
sthagen · Jan 18, 2020 · 5c346f3 · 5c346f3
2 parents 2dde6f1 + 4b754d6
commit 5c346f3
Show file tree

Hide file tree

Showing 17 changed files with 734 additions and 147 deletions.
diff --git a/contrib/pg_trgm/expected/pg_trgm.out b/contrib/pg_trgm/expected/pg_trgm.out
@@ -3498,6 +3498,107 @@ select count(*) from test_trgm where t ~ '[qwerty]{2}-?[qwerty]{2}';
   1000
 (1 row)
 
+-- check handling of indexquals that generate no searchable conditions
+explain (costs off)
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+                                 QUERY PLAN                                  
+-----------------------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on test_trgm
+         Recheck Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qwerty%'::text))
+         ->  Bitmap Index Scan on trgm_idx
+               Index Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qwerty%'::text))
+(5 rows)
+
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+ count 
+-------
+    19
+(1 row)
+
+explain (costs off)
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+                               QUERY PLAN                                
+-------------------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on test_trgm
+         Recheck Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qw%'::text))
+         ->  Bitmap Index Scan on trgm_idx
+               Index Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qw%'::text))
+(5 rows)
+
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+ count 
+-------
+    19
+(1 row)
+
+-- ensure that pending-list items are handled correctly, too
+create temp table t_test_trgm(t text COLLATE "C");
+create index t_trgm_idx on t_test_trgm using gin (t gin_trgm_ops);
+insert into t_test_trgm values ('qwerty99'), ('qwerty01');
+explain (costs off)
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+                                 QUERY PLAN                                  
+-----------------------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on t_test_trgm
+         Recheck Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qwerty%'::text))
+         ->  Bitmap Index Scan on t_trgm_idx
+               Index Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qwerty%'::text))
+(5 rows)
+
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+ count 
+-------
+     1
+(1 row)
+
+explain (costs off)
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+                               QUERY PLAN                                
+-------------------------------------------------------------------------
+ Aggregate
+   ->  Bitmap Heap Scan on t_test_trgm
+         Recheck Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qw%'::text))
+         ->  Bitmap Index Scan on t_trgm_idx
+               Index Cond: ((t ~~ '%99%'::text) AND (t ~~ '%qw%'::text))
+(5 rows)
+
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+ count 
+-------
+     1
+(1 row)
+
+-- run the same queries with sequential scan to check the results
+set enable_bitmapscan=off;
+set enable_seqscan=on;
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+ count 
+-------
+    19
+(1 row)
+
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+ count 
+-------
+    19
+(1 row)
+
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+ count 
+-------
+     1
+(1 row)
+
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+ count 
+-------
+     1
+(1 row)
+
+reset enable_bitmapscan;
 create table test2(t text COLLATE "C");
 insert into test2 values ('abcdef');
 insert into test2 values ('quark');

diff --git a/contrib/pg_trgm/sql/pg_trgm.sql b/contrib/pg_trgm/sql/pg_trgm.sql
@@ -55,6 +55,33 @@ select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu098
 select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
 select count(*) from test_trgm where t ~ '[qwerty]{2}-?[qwerty]{2}';
 
+-- check handling of indexquals that generate no searchable conditions
+explain (costs off)
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+explain (costs off)
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+-- ensure that pending-list items are handled correctly, too
+create temp table t_test_trgm(t text COLLATE "C");
+create index t_trgm_idx on t_test_trgm using gin (t gin_trgm_ops);
+insert into t_test_trgm values ('qwerty99'), ('qwerty01');
+explain (costs off)
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+explain (costs off)
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+
+-- run the same queries with sequential scan to check the results
+set enable_bitmapscan=off;
+set enable_seqscan=on;
+select count(*) from test_trgm where t like '%99%' and t like '%qwerty%';
+select count(*) from test_trgm where t like '%99%' and t like '%qw%';
+select count(*) from t_test_trgm where t like '%99%' and t like '%qwerty%';
+select count(*) from t_test_trgm where t like '%99%' and t like '%qw%';
+reset enable_bitmapscan;
+
 create table test2(t text COLLATE "C");
 insert into test2 values ('abcdef');
 insert into test2 values ('quark');

diff --git a/src/backend/access/gin/ginget.c b/src/backend/access/gin/ginget.c
@@ -528,8 +528,20 @@ startScanKey(GinState *ginstate, GinScanOpaque so, GinScanKey key)
 	 * order, until the consistent function says that none of the remaining
 	 * entries can form a match, without any items from the required set. The
 	 * rest go to the additional set.
+	 *
+	 * Exclude-only scan keys are known to have no required entries.
 	 */
-	if (key->nentries > 1)
+	if (key->excludeOnly)
+	{
+		MemoryContextSwitchTo(so->keyCtx);
+
+		key->nrequired = 0;
+		key->nadditional = key->nentries;
+		key->additionalEntries = palloc(key->nadditional * sizeof(GinScanEntry));
+		for (i = 0; i < key->nadditional; i++)
+			key->additionalEntries[i] = key->scanEntry[i];
+	}
+	else if (key->nentries > 1)
 	{
 		MemoryContextSwitchTo(so->tempCtx);
 
@@ -1008,37 +1020,52 @@ keyGetItem(GinState *ginstate, MemoryContext tempCtx, GinScanKey key,
 			minItem = entry->curItem;
 	}
 
-	if (allFinished)
+	if (allFinished && !key->excludeOnly)
 	{
 		/* all entries are finished */
 		key->isFinished = true;
 		return;
 	}
 
-	/*
-	 * Ok, we now know that there are no matches < minItem.
-	 *
-	 * If minItem is lossy, it means that there were no exact items on the
-	 * page among requiredEntries, because lossy pointers sort after exact
-	 * items. However, there might be exact items for the same page among
-	 * additionalEntries, so we mustn't advance past them.
-	 */
-	if (ItemPointerIsLossyPage(&minItem))
+	if (!key->excludeOnly)
 	{
-		if (GinItemPointerGetBlockNumber(&advancePast) <
-			GinItemPointerGetBlockNumber(&minItem))
+		/*
+		 * For a normal scan key, we now know there are no matches < minItem.
+		 *
+		 * If minItem is lossy, it means that there were no exact items on the
+		 * page among requiredEntries, because lossy pointers sort after exact
+		 * items. However, there might be exact items for the same page among
+		 * additionalEntries, so we mustn't advance past them.
+		 */
+		if (ItemPointerIsLossyPage(&minItem))
 		{
+			if (GinItemPointerGetBlockNumber(&advancePast) <
+				GinItemPointerGetBlockNumber(&minItem))
+			{
+				ItemPointerSet(&advancePast,
+							   GinItemPointerGetBlockNumber(&minItem),
+							   InvalidOffsetNumber);
+			}
+		}
+		else
+		{
+			Assert(GinItemPointerGetOffsetNumber(&minItem) > 0);
 			ItemPointerSet(&advancePast,
 						   GinItemPointerGetBlockNumber(&minItem),
-						   InvalidOffsetNumber);
+						   OffsetNumberPrev(GinItemPointerGetOffsetNumber(&minItem)));
 		}
 	}
 	else
 	{
-		Assert(GinItemPointerGetOffsetNumber(&minItem) > 0);
-		ItemPointerSet(&advancePast,
-					   GinItemPointerGetBlockNumber(&minItem),
-					   OffsetNumberPrev(GinItemPointerGetOffsetNumber(&minItem)));
+		/*
+		 * excludeOnly scan keys don't have any entries that are necessarily
+		 * present in matching items.  So, we consider the item just after
+		 * advancePast.
+		 */
+		Assert(key->nrequired == 0);
+		ItemPointerSet(&minItem,
+					   GinItemPointerGetBlockNumber(&advancePast),
+					   OffsetNumberNext(GinItemPointerGetOffsetNumber(&advancePast)));
 	}
 
 	/*
@@ -1266,6 +1293,20 @@ scanGetItem(IndexScanDesc scan, ItemPointerData advancePast,
 		{
 			GinScanKey	key = so->keys + i;
 
+			/*
+			 * If we're considering a lossy page, skip excludeOnly keys,  They
+			 * can't exclude the whole page anyway.
+			 */
+			if (ItemPointerIsLossyPage(item) && key->excludeOnly)
+			{
+				/*
+				 * ginNewScanKey() should never mark the first key as
+				 * excludeOnly.
+				 */
+				Assert(i > 0);
+				continue;
+			}
+
 			/* Fetch the next item for this key that is > advancePast. */
 			keyGetItem(&so->ginstate, so->tempCtx, key, advancePast,
 					   scan->xs_snapshot);
@@ -1736,11 +1777,14 @@ collectMatchesForHeapRow(IndexScanDesc scan, pendingPosition *pos)
 	}
 
 	/*
-	 * Now return "true" if all scan keys have at least one matching datum
+	 * All scan keys except excludeOnly require at least one entry to match.
+	 * excludeOnly keys are an exception, because their implied
+	 * GIN_CAT_EMPTY_QUERY scanEntry always matches.  So return "true" if all
+	 * non-excludeOnly scan keys have at least one match.
 	 */
 	for (i = 0; i < so->nkeys; i++)
 	{
-		if (pos->hasMatchKey[i] == false)
+		if (pos->hasMatchKey[i] == false && !so->keys[i].excludeOnly)
 			return false;
 	}