diff options
author | Alexander Korotkov <akorotkov@postgresql.org> | 2019-09-08 21:13:40 +0300 |
---|---|---|
committer | Alexander Korotkov <akorotkov@postgresql.org> | 2019-09-08 22:08:12 +0300 |
commit | 02f90879e75b3d4ccdba1ec7c3cad6af08dff77d (patch) | |
tree | 9fc6dd6fdc3aba51027f5e02db15a0a271471882 /src/backend/access/gist/gistscan.c | |
parent | e5d8f3596100da0d38a38513c69e803b7fe7041a (diff) | |
download | postgresql-02f90879e75b3d4ccdba1ec7c3cad6af08dff77d.tar.gz postgresql-02f90879e75b3d4ccdba1ec7c3cad6af08dff77d.zip |
Fix handling of NULL distances in KNN-GiST
In order to implement NULL LAST semantic GiST previously assumed distance to
the NULL value to be Inf. However, our distance functions can return Inf and
NaN for non-null values. In such cases, NULL LAST semantic appears to be
broken. This commit fixes that by introducing separate array of null flags for
distances.
Backpatch to all supported versions.
Discussion: https://postgr.es/m/CAPpHfdsNvNdA0DBS%2BwMpFrgwT6C3-q50sFVGLSiuWnV3FqOJuQ%40mail.gmail.com
Author: Alexander Korotkov
Backpatch-through: 9.4
Diffstat (limited to 'src/backend/access/gist/gistscan.c')
-rw-r--r-- | src/backend/access/gist/gistscan.c | 25 |
1 files changed, 21 insertions, 4 deletions
diff --git a/src/backend/access/gist/gistscan.c b/src/backend/access/gist/gistscan.c index 636aa62b680..e72bf08f952 100644 --- a/src/backend/access/gist/gistscan.c +++ b/src/backend/access/gist/gistscan.c @@ -33,14 +33,30 @@ pairingheap_GISTSearchItem_cmp(const pairingheap_node *a, const pairingheap_node const GISTSearchItem *sb = (const GISTSearchItem *) b; IndexScanDesc scan = (IndexScanDesc) arg; int i; + double *da = GISTSearchItemDistanceValues(sa, scan->numberOfOrderBys), + *db = GISTSearchItemDistanceValues(sb, scan->numberOfOrderBys); + bool *na = GISTSearchItemDistanceNulls(sa, scan->numberOfOrderBys), + *nb = GISTSearchItemDistanceNulls(sb, scan->numberOfOrderBys); /* Order according to distance comparison */ for (i = 0; i < scan->numberOfOrderBys; i++) { - int cmp = -float8_cmp_internal(sa->distances[i], sb->distances[i]); + if (na[i]) + { + if (!nb[i]) + return -1; + } + else if (nb[i]) + { + return 1; + } + else + { + int cmp = -float8_cmp_internal(da[i], db[i]); - if (cmp != 0) - return cmp; + if (cmp != 0) + return cmp; + } } /* Heap items go before inner pages, to ensure a depth-first search */ @@ -84,7 +100,8 @@ gistbeginscan(Relation r, int nkeys, int norderbys) so->queueCxt = giststate->scanCxt; /* see gistrescan */ /* workspaces with size dependent on numberOfOrderBys: */ - so->distances = palloc(sizeof(double) * scan->numberOfOrderBys); + so->distanceValues = palloc(sizeof(double) * scan->numberOfOrderBys); + so->distanceNulls = palloc(sizeof(bool) * scan->numberOfOrderBys); so->qual_ok = true; /* in case there are zero keys */ if (scan->numberOfOrderBys > 0) { |