summaryrefslogtreecommitdiff
path: root/contrib/pg_trgm/trgm_gist.c
diff options
context:
space:
mode:
authorNoah Misch <noah@leadboat.com>2017-03-12 19:35:34 -0400
committerNoah Misch <noah@leadboat.com>2017-03-12 19:35:34 -0400
commit3a0d473192b2045cbaf997df8437e7762d34f3ba (patch)
tree8bdf7e5e8f6a69041ff3fd4b2114cb9e8cbd69d4 /contrib/pg_trgm/trgm_gist.c
parent9d7726c2ba06b932f791f2d0cc5acf73cc0b4dca (diff)
Use wrappers of PG_DETOAST_DATUM_PACKED() more.
This makes almost all core code follow the policy introduced in the previous commit. Specific decisions: - Text search support functions with char* and length arguments, such as prsstart and lexize, may receive unaligned strings. I doubt maintainers of non-core text search code will notice. - Use plain VARDATA() on values detoasted or synthesized earlier in the same function. Use VARDATA_ANY() on varlenas sourced outside the function, even if they happen to always have four-byte headers. As an exception, retain the universal practice of using VARDATA() on return values of SendFunctionCall(). - Retain PG_GETARG_BYTEA_P() in pageinspect. (Page images are too large for a one-byte header, so this misses no optimization.) Sites that do not call get_page_from_raw() typically need the four-byte alignment. - For now, do not change btree_gist. Its use of four-byte headers in memory is partly entangled with storage of 4-byte headers inside GBT_VARKEY, on disk. - For now, do not change gtrgm_consistent() or gtrgm_distance(). They incorporate the varlena header into a cache, and there are multiple credible implementation strategies to consider.
Diffstat (limited to 'contrib/pg_trgm/trgm_gist.c')
-rw-r--r--contrib/pg_trgm/trgm_gist.c17
1 files changed, 9 insertions, 8 deletions
diff --git a/contrib/pg_trgm/trgm_gist.c b/contrib/pg_trgm/trgm_gist.c
index f52867df324..ed02af875ca 100644
--- a/contrib/pg_trgm/trgm_gist.c
+++ b/contrib/pg_trgm/trgm_gist.c
@@ -100,9 +100,9 @@ gtrgm_compress(PG_FUNCTION_ARGS)
if (entry->leafkey)
{ /* trgm */
TRGM *res;
- text *val = DatumGetTextP(entry->key);
+ text *val = DatumGetTextPP(entry->key);
- res = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+ res = generate_trgm(VARDATA_ANY(val), VARSIZE_ANY_EXHDR(val));
retval = (GISTENTRY *) palloc(sizeof(GISTENTRY));
gistentryinit(*retval, PointerGetDatum(res),
entry->rel, entry->page,
@@ -142,7 +142,7 @@ gtrgm_decompress(PG_FUNCTION_ARGS)
GISTENTRY *retval;
text *key;
- key = DatumGetTextP(entry->key);
+ key = DatumGetTextPP(entry->key);
if (key != (text *) DatumGetPointer(entry->key))
{
@@ -200,11 +200,12 @@ gtrgm_consistent(PG_FUNCTION_ARGS)
* depends on strategy.
*
* The cached structure is a single palloc chunk containing the
- * gtrgm_consistent_cache header, then the input query (starting at a
- * MAXALIGN boundary), then the TRGM value (also starting at a MAXALIGN
- * boundary). However we don't try to include the regex graph (if any) in
- * that struct. (XXX currently, this approach can leak regex graphs
- * across index rescans. Not clear if that's worth fixing.)
+ * gtrgm_consistent_cache header, then the input query (4-byte length
+ * word, uncompressed, starting at a MAXALIGN boundary), then the TRGM
+ * value (also starting at a MAXALIGN boundary). However we don't try to
+ * include the regex graph (if any) in that struct. (XXX currently, this
+ * approach can leak regex graphs across index rescans. Not clear if
+ * that's worth fixing.)
*/
cache = (gtrgm_consistent_cache *) fcinfo->flinfo->fn_extra;
if (cache == NULL ||