diff options
author | Tom Lane <tgl@sss.pgh.pa.us> | 2010-10-30 21:55:20 -0400 |
---|---|---|
committer | Tom Lane <tgl@sss.pgh.pa.us> | 2010-10-30 21:56:11 -0400 |
commit | 186cbbda8f8dc5e42f68fc7892f206a76d56a20f (patch) | |
tree | 2c909d8365726683a61515b639c02a9ac00682f4 /src/backend/optimizer/plan/subselect.c | |
parent | bd1ff9713369c2f54391112b92e0c22ab5c99180 (diff) | |
download | postgresql-186cbbda8f8dc5e42f68fc7892f206a76d56a20f.tar.gz postgresql-186cbbda8f8dc5e42f68fc7892f206a76d56a20f.zip |
Provide hashing support for arrays.
The core of this patch is hash_array() and associated typcache
infrastructure, which works just about exactly like the existing support
for array comparison.
In addition I did some work to ensure that the planner won't think that an
array type is hashable unless its element type is hashable, and similarly
for sorting. This includes adding a datatype parameter to op_hashjoinable
and op_mergejoinable, and adding an explicit "hashable" flag to
SortGroupClause. The lack of a cross-check on the element type was a
pre-existing bug in mergejoin support --- but it didn't matter so much
before, because if you couldn't sort the element type there wasn't any good
alternative to failing anyhow. Now that we have the alternative of hashing
the array type, there are cases where we can avoid a failure by being picky
at the planner stage, so it's time to be picky.
The issue of exactly how to combine the per-element hash values to produce
an array hash is still open for discussion, but the rest of this is pretty
solid, so I'll commit it as-is.
Diffstat (limited to 'src/backend/optimizer/plan/subselect.c')
-rw-r--r-- | src/backend/optimizer/plan/subselect.c | 39 |
1 files changed, 28 insertions, 11 deletions
diff --git a/src/backend/optimizer/plan/subselect.c b/src/backend/optimizer/plan/subselect.c index 137e2ce0491..754753cc12d 100644 --- a/src/backend/optimizer/plan/subselect.c +++ b/src/backend/optimizer/plan/subselect.c @@ -861,28 +861,45 @@ testexpr_is_hashable(Node *testexpr) return false; } +/* + * Check expression is hashable + strict + * + * We could use op_hashjoinable() and op_strict(), but do it like this to + * avoid a redundant cache lookup. + */ static bool hash_ok_operator(OpExpr *expr) { Oid opid = expr->opno; - HeapTuple tup; - Form_pg_operator optup; /* quick out if not a binary operator */ if (list_length(expr->args) != 2) return false; - /* else must look up the operator properties */ - tup = SearchSysCache1(OPEROID, ObjectIdGetDatum(opid)); - if (!HeapTupleIsValid(tup)) - elog(ERROR, "cache lookup failed for operator %u", opid); - optup = (Form_pg_operator) GETSTRUCT(tup); - if (!optup->oprcanhash || !func_strict(optup->oprcode)) + if (opid == ARRAY_EQ_OP) + { + /* array_eq is strict, but must check input type to ensure hashable */ + Node *leftarg = linitial(expr->args); + + return op_hashjoinable(opid, exprType(leftarg)); + } + else { + /* else must look up the operator properties */ + HeapTuple tup; + Form_pg_operator optup; + + tup = SearchSysCache1(OPEROID, ObjectIdGetDatum(opid)); + if (!HeapTupleIsValid(tup)) + elog(ERROR, "cache lookup failed for operator %u", opid); + optup = (Form_pg_operator) GETSTRUCT(tup); + if (!optup->oprcanhash || !func_strict(optup->oprcode)) + { + ReleaseSysCache(tup); + return false; + } ReleaseSysCache(tup); - return false; + return true; } - ReleaseSysCache(tup); - return true; } |