From 9728eda7925b6d42621b38c48e91ef9ab8d90cbc Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Wed, 13 Feb 2013 14:07:06 -0500
Subject: [PATCH] Fix contrib/pg_trgm's similarity() function for trigram-free
strings.
Cases such as similarity('', '') produced a NaN result due to computing
0/0. Per discussion, make it return zero instead.
This appears to be the basic cause of bug #7867 from Michele Baravalle,
although it remains unclear why her installation doesn't think Cyrillic
letters are letters.
Back-patch to all active branches.
---
contrib/pg_trgm/expected/pg_trgm.out | 6 ++++++
contrib/pg_trgm/sql/pg_trgm.sql | 2 ++
contrib/pg_trgm/trgm_op.c | 8 ++++++--
3 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/contrib/pg_trgm/expected/pg_trgm.out b/contrib/pg_trgm/expected/pg_trgm.out
index 81d0ca80b20..ea4d5fab061 100644
--- a/contrib/pg_trgm/expected/pg_trgm.out
+++ b/contrib/pg_trgm/expected/pg_trgm.out
@@ -53,6 +53,12 @@ select similarity('wow',' WOW ');
1
(1 row)
+select similarity('---', '####---');
+ similarity
+------------
+ 0
+(1 row)
+
CREATE TABLE test_trgm(t text);
\copy test_trgm from 'data/trgm.data
select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu0988' order by sml desc, t;
diff --git a/contrib/pg_trgm/sql/pg_trgm.sql b/contrib/pg_trgm/sql/pg_trgm.sql
index 81ab1e79b17..b235ca73577 100644
--- a/contrib/pg_trgm/sql/pg_trgm.sql
+++ b/contrib/pg_trgm/sql/pg_trgm.sql
@@ -11,6 +11,8 @@ select show_trgm('a b C0*%^');
select similarity('wow','WOWa ');
select similarity('wow',' WOW ');
+select similarity('---', '####---');
+
CREATE TABLE test_trgm(t text);
\copy test_trgm from 'data/trgm.data
diff --git a/contrib/pg_trgm/trgm_op.c b/contrib/pg_trgm/trgm_op.c
index 87dffd1dd2c..9638dbdb701 100644
--- a/contrib/pg_trgm/trgm_op.c
+++ b/contrib/pg_trgm/trgm_op.c
@@ -553,6 +553,10 @@ cnt_sml(TRGM *trg1, TRGM *trg2)
len1 = ARRNELEM(trg1);
len2 = ARRNELEM(trg2);
+ /* explicit test is needed to avoid 0/0 division when both lengths are 0 */
+ if (len1 <= 0 || len2 <= 0)
+ return (float4) 0.0;
+
while (ptr1 - GETARR(trg1) < len1 && ptr2 - GETARR(trg2) < len2)
{
int res = CMPTRGM(ptr1, ptr2);
@@ -570,9 +574,9 @@ cnt_sml(TRGM *trg1, TRGM *trg2)
}
#ifdef DIVUNION
- return ((((float4) count) / ((float4) (len1 + len2 - count))));
+ return ((float4) count) / ((float4) (len1 + len2 - count));
#else
- return (((float) count) / ((float) ((len1 > len2) ? len1 : len2)));
+ return ((float4) count) / ((float4) ((len1 > len2) ? len1 : len2));
#endif
}
--
GitLab