Fix contrib/pg_trgm's similarity() function for trigram-free strings.

tglsfdc · tglsfdc · commit 9728eda7925b · 2013-02-13T14:07:06.000-05:00
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.
diff --git 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
@@ -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
@@ -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
 
 }

Original file line number	Diff line number	Diff line change
`@@ -553,6 +553,10 @@ cnt_sml(TRGM trg1, TRGM trg2)`
`553`	`553`	`len1 = ARRNELEM(trg1);`
`554`	`554`	`len2 = ARRNELEM(trg2);`
`555`	`555`
	`556`	`+ /* explicit test is needed to avoid 0/0 division when both lengths are 0 */`
	`557`	`+ if (len1 <= 0 \|\| len2 <= 0)`
	`558`	`+ return (float4) 0.0;`
	`559`	`+`
`556`	`560`	`while (ptr1 - GETARR(trg1) < len1 && ptr2 - GETARR(trg2) < len2)`
`557`	`561`	`{`
`558`	`562`	`int res = CMPTRGM(ptr1, ptr2);`
`@@ -570,9 +574,9 @@ cnt_sml(TRGM trg1, TRGM trg2)`
`570`	`574`	`}`
`571`	`575`
`572`	`576`	`#ifdef DIVUNION`
`573`		`- return ((((float4) count) / ((float4) (len1 + len2 - count))));`
	`577`	`+ return ((float4) count) / ((float4) (len1 + len2 - count));`
`574`	`578`	`#else`
`575`		`- return (((float) count) / ((float) ((len1 > len2) ? len1 : len2)));`
	`579`	`+ return ((float4) count) / ((float4) ((len1 > len2) ? len1 : len2));`
`576`	`580`	`#endif`
`577`	`581`
`578`	`582`	`}`