diff options
| author | Tom Lane | 2013-02-13 19:07:26 +0000 |
|---|---|---|
| committer | Tom Lane | 2013-02-13 19:07:26 +0000 |
| commit | 697f5cadf5d81eeee3f3018d711ef33261dc7cd5 (patch) | |
| tree | 3c736f0a8e9eb1e8f4e707db6b7a9d5607003eb6 | |
| parent | 06af3f96568646e7f878622bfa6e73f9eaa5f3f0 (diff) | |
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.
| -rw-r--r-- | contrib/pg_trgm/expected/pg_trgm.out | 6 | ||||
| -rw-r--r-- | contrib/pg_trgm/sql/pg_trgm.sql | 2 | ||||
| -rw-r--r-- | 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 98385347295..641e8cecf6b 100644 --- a/contrib/pg_trgm/expected/pg_trgm.out +++ b/contrib/pg_trgm/expected/pg_trgm.out @@ -59,6 +59,12 @@ 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 13045827ac7..1bcf2c9146c 100644 --- a/contrib/pg_trgm/sql/pg_trgm.sql +++ b/contrib/pg_trgm/sql/pg_trgm.sql @@ -19,6 +19,8 @@ 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 19b6747d68b..30965f818cb 100644 --- a/contrib/pg_trgm/trgm_op.c +++ b/contrib/pg_trgm/trgm_op.c @@ -311,6 +311,10 @@ 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); @@ -328,9 +332,9 @@ 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 } |