From 5db48808c4d5c3641b76d442ba7e7d8916adadf4 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Thu, 7 May 2020 15:59:52 -0400
Subject: [PATCH] Fix YA text phrase search bug.

checkcondition_str() failed to report multiple matches for a prefix
pattern correctly: it would dutifully merge the match positions, but
then after exiting that loop, if the last prefix-matching word had
had no suitable positions, it would report there were no matches.
The upshot would be failing to recognize a match that the query
should match.

It looks like you need all of these conditions to see the bug:
* a phrase search (else we don't ask for match position details)
* a prefix search item (else we don't get to this code)
* a weight restriction (else checkclass_str won't fail)

Noted while investigating a problem report from Pavel Borisov,
though this is distinct from the issue he was on about.

Back-patch to 9.6 where phrase search was added.
---
 src/backend/utils/adt/tsvector_op.c   |  8 +++++++-
 src/test/regress/expected/tstypes.out | 18 ++++++++++++++++++
 src/test/regress/sql/tstypes.sql      |  3 +++
 3 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/src/backend/utils/adt/tsvector_op.c b/src/backend/utils/adt/tsvector_op.c
index 3cd1dfbb6c..4e4119af2c 100644
--- a/src/backend/utils/adt/tsvector_op.c
+++ b/src/backend/utils/adt/tsvector_op.c
@@ -1327,12 +1327,13 @@ checkcondition_str(void *checkval, QueryOperand *val, ExecPhraseData *data)
 	WordEntry  *StopLow = chkval->arrb;
 	WordEntry  *StopHigh = chkval->arre;
 	WordEntry  *StopMiddle = StopHigh;
-	int			difference = -1;
 	bool		res = false;
 
 	/* Loop invariant: StopLow <= val < StopHigh */
 	while (StopLow < StopHigh)
 	{
+		int			difference;
+
 		StopMiddle = StopLow + (StopHigh - StopLow) / 2;
 		difference = tsCompareString(chkval->operand + val->distance,
 									 val->length,
@@ -1398,6 +1399,11 @@ checkcondition_str(void *checkval, QueryOperand *val, ExecPhraseData *data)
 					memcpy(allpos + npos, data->pos, sizeof(WordEntryPos) * data->npos);
 					npos += data->npos;
 				}
+				else
+				{
+					/* at loop exit, res must be true if we found matches */
+					res = (npos > 0);
+				}
 			}
 			else
 			{
diff --git a/src/test/regress/expected/tstypes.out b/src/test/regress/expected/tstypes.out
index 8ff0d0496e..fa829d61e4 100644
--- a/src/test/regress/expected/tstypes.out
+++ b/src/test/regress/expected/tstypes.out
@@ -531,6 +531,24 @@ SELECT 'a b:89  ca:23A,64c cb:80b d:34c'::tsvector @@ 'd:AC & c:*B' as "true";
  t
 (1 row)
 
+SELECT 'wa:1D wb:2A'::tsvector @@ 'w:*D & w:*A'::tsquery as "true";
+ true 
+------
+ t
+(1 row)
+
+SELECT 'wa:1D wb:2A'::tsvector @@ 'w:*D <-> w:*A'::tsquery as "true";
+ true 
+------
+ t
+(1 row)
+
+SELECT 'wa:1A wb:2D'::tsvector @@ 'w:*D <-> w:*A'::tsquery as "false";
+ false 
+-------
+ f
+(1 row)
+
 SELECT 'supernova'::tsvector @@ 'super'::tsquery AS "false";
  false 
 -------
diff --git a/src/test/regress/sql/tstypes.sql b/src/test/regress/sql/tstypes.sql
index 4c60f602e5..55710f1c04 100644
--- a/src/test/regress/sql/tstypes.sql
+++ b/src/test/regress/sql/tstypes.sql
@@ -98,6 +98,9 @@ SELECT 'a b:89  ca:23A,64b d:34c'::tsvector @@ 'd:AC & c:*CB' as "true";
 SELECT 'a b:89  ca:23A,64b cb:80c d:34c'::tsvector @@ 'd:AC & c:*C' as "true";
 SELECT 'a b:89  ca:23A,64c cb:80b d:34c'::tsvector @@ 'd:AC & c:*C' as "true";
 SELECT 'a b:89  ca:23A,64c cb:80b d:34c'::tsvector @@ 'd:AC & c:*B' as "true";
+SELECT 'wa:1D wb:2A'::tsvector @@ 'w:*D & w:*A'::tsquery as "true";
+SELECT 'wa:1D wb:2A'::tsvector @@ 'w:*D <-> w:*A'::tsquery as "true";
+SELECT 'wa:1A wb:2D'::tsvector @@ 'w:*D <-> w:*A'::tsquery as "false";
 
 SELECT 'supernova'::tsvector @@ 'super'::tsquery AS "false";
 SELECT 'supeanova supernova'::tsvector @@ 'super'::tsquery AS "false";