postgresql/contrib/bloom/blvalidate.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

226 lines
6.6 KiB
C
Raw Permalink Normal View History

/*-------------------------------------------------------------------------
*
* blvalidate.c
* Opclass validator for bloom.
*
* Copyright (c) 2016-2024, PostgreSQL Global Development Group
*
* IDENTIFICATION
* contrib/bloom/blvalidate.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/amvalidate.h"
#include "access/htup_details.h"
#include "bloom.h"
#include "catalog/pg_amop.h"
#include "catalog/pg_amproc.h"
#include "catalog/pg_opclass.h"
#include "catalog/pg_opfamily.h"
#include "catalog/pg_type.h"
#include "utils/builtins.h"
#include "utils/lsyscache.h"
#include "utils/regproc.h"
#include "utils/syscache.h"
/*
* Validator for a bloom opclass.
*/
bool
blvalidate(Oid opclassoid)
{
bool result = true;
HeapTuple classtup;
Form_pg_opclass classform;
Oid opfamilyoid;
Oid opcintype;
Oid opckeytype;
char *opclassname;
HeapTuple familytup;
Form_pg_opfamily familyform;
char *opfamilyname;
CatCList *proclist,
*oprlist;
List *grouplist;
OpFamilyOpFuncGroup *opclassgroup;
int i;
ListCell *lc;
/* Fetch opclass information */
classtup = SearchSysCache1(CLAOID, ObjectIdGetDatum(opclassoid));
if (!HeapTupleIsValid(classtup))
elog(ERROR, "cache lookup failed for operator class %u", opclassoid);
classform = (Form_pg_opclass) GETSTRUCT(classtup);
opfamilyoid = classform->opcfamily;
opcintype = classform->opcintype;
opckeytype = classform->opckeytype;
if (!OidIsValid(opckeytype))
opckeytype = opcintype;
opclassname = NameStr(classform->opcname);
/* Fetch opfamily information */
familytup = SearchSysCache1(OPFAMILYOID, ObjectIdGetDatum(opfamilyoid));
if (!HeapTupleIsValid(familytup))
elog(ERROR, "cache lookup failed for operator family %u", opfamilyoid);
familyform = (Form_pg_opfamily) GETSTRUCT(familytup);
opfamilyname = NameStr(familyform->opfname);
/* Fetch all operators and support functions of the opfamily */
oprlist = SearchSysCacheList1(AMOPSTRATEGY, ObjectIdGetDatum(opfamilyoid));
proclist = SearchSysCacheList1(AMPROCNUM, ObjectIdGetDatum(opfamilyoid));
/* Check individual support functions */
for (i = 0; i < proclist->n_members; i++)
{
HeapTuple proctup = &proclist->members[i]->tuple;
Form_pg_amproc procform = (Form_pg_amproc) GETSTRUCT(proctup);
bool ok;
/*
* All bloom support functions should be registered with matching
* left/right types
*/
if (procform->amproclefttype != procform->amprocrighttype)
{
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opfamily %s contains support procedure %s with cross-type registration",
opfamilyname,
format_procedure(procform->amproc))));
result = false;
}
/*
* We can't check signatures except within the specific opclass, since
* we need to know the associated opckeytype in many cases.
*/
if (procform->amproclefttype != opcintype)
continue;
/* Check procedure numbers and function signatures */
switch (procform->amprocnum)
{
case BLOOM_HASH_PROC:
ok = check_amproc_signature(procform->amproc, INT4OID, false,
1, 1, opckeytype);
break;
Implement operator class parameters PostgreSQL provides set of template index access methods, where opclasses have much freedom in the semantics of indexing. These index AMs are GiST, GIN, SP-GiST and BRIN. There opclasses define representation of keys, operations on them and supported search strategies. So, it's natural that opclasses may be faced some tradeoffs, which require user-side decision. This commit implements opclass parameters allowing users to set some values, which tell opclass how to index the particular dataset. This commit doesn't introduce new storage in system catalog. Instead it uses pg_attribute.attoptions, which is used for table column storage options but unused for index attributes. In order to evade changing signature of each opclass support function, we implement unified way to pass options to opclass support functions. Options are set to fn_expr as the constant bytea expression. It's possible due to the fact that opclass support functions are executed outside of expressions, so fn_expr is unused for them. This commit comes with some examples of opclass options usage. We parametrize signature length in GiST. That applies to multiple opclasses: tsvector_ops, gist__intbig_ops, gist_ltree_ops, gist__ltree_ops, gist_trgm_ops and gist_hstore_ops. Also we parametrize maximum number of integer ranges for gist__int_ops. However, the main future usage of this feature is expected to be json, where users would be able to specify which way to index particular json parts. Catversion is bumped. Discussion: https://postgr.es/m/d22c3a18-31c7-1879-fc11-4c1ce2f5e5af%40postgrespro.ru Author: Nikita Glukhov, revised by me Reviwed-by: Nikolay Shaplov, Robert Haas, Tom Lane, Tomas Vondra, Alvaro Herrera
2020-03-30 18:17:11 +02:00
case BLOOM_OPTIONS_PROC:
ok = check_amoptsproc_signature(procform->amproc);
break;
default:
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opfamily %s contains function %s with invalid support number %d",
opfamilyname,
format_procedure(procform->amproc),
procform->amprocnum)));
result = false;
continue; /* don't want additional message */
}
if (!ok)
{
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("gist opfamily %s contains function %s with wrong signature for support number %d",
opfamilyname,
format_procedure(procform->amproc),
procform->amprocnum)));
result = false;
}
}
/* Check individual operators */
for (i = 0; i < oprlist->n_members; i++)
{
HeapTuple oprtup = &oprlist->members[i]->tuple;
Form_pg_amop oprform = (Form_pg_amop) GETSTRUCT(oprtup);
/* Check it's allowed strategy for bloom */
if (oprform->amopstrategy < 1 ||
oprform->amopstrategy > BLOOM_NSTRATEGIES)
{
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opfamily %s contains operator %s with invalid strategy number %d",
opfamilyname,
format_operator(oprform->amopopr),
oprform->amopstrategy)));
result = false;
}
/* bloom doesn't support ORDER BY operators */
if (oprform->amoppurpose != AMOP_SEARCH ||
OidIsValid(oprform->amopsortfamily))
{
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opfamily %s contains invalid ORDER BY specification for operator %s",
opfamilyname,
format_operator(oprform->amopopr))));
result = false;
}
/* Check operator signature --- same for all bloom strategies */
if (!check_amop_signature(oprform->amopopr, BOOLOID,
oprform->amoplefttype,
oprform->amoprighttype))
{
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opfamily %s contains operator %s with wrong signature",
opfamilyname,
format_operator(oprform->amopopr))));
result = false;
}
}
/* Now check for inconsistent groups of operators/functions */
grouplist = identify_opfamily_groups(oprlist, proclist);
opclassgroup = NULL;
foreach(lc, grouplist)
{
OpFamilyOpFuncGroup *thisgroup = (OpFamilyOpFuncGroup *) lfirst(lc);
/* Remember the group exactly matching the test opclass */
if (thisgroup->lefttype == opcintype &&
thisgroup->righttype == opcintype)
opclassgroup = thisgroup;
/*
* There is not a lot we can do to check the operator sets, since each
* bloom opclass is more or less a law unto itself, and some contain
* only operators that are binary-compatible with the opclass datatype
* (meaning that empty operator sets can be OK). That case also means
* that we shouldn't insist on nonempty function sets except for the
* opclass's own group.
*/
}
/* Check that the originally-named opclass is complete */
for (i = 1; i <= BLOOM_NPROC; i++)
{
if (opclassgroup &&
(opclassgroup->functionset & (((uint64) 1) << i)) != 0)
continue; /* got it */
Implement operator class parameters PostgreSQL provides set of template index access methods, where opclasses have much freedom in the semantics of indexing. These index AMs are GiST, GIN, SP-GiST and BRIN. There opclasses define representation of keys, operations on them and supported search strategies. So, it's natural that opclasses may be faced some tradeoffs, which require user-side decision. This commit implements opclass parameters allowing users to set some values, which tell opclass how to index the particular dataset. This commit doesn't introduce new storage in system catalog. Instead it uses pg_attribute.attoptions, which is used for table column storage options but unused for index attributes. In order to evade changing signature of each opclass support function, we implement unified way to pass options to opclass support functions. Options are set to fn_expr as the constant bytea expression. It's possible due to the fact that opclass support functions are executed outside of expressions, so fn_expr is unused for them. This commit comes with some examples of opclass options usage. We parametrize signature length in GiST. That applies to multiple opclasses: tsvector_ops, gist__intbig_ops, gist_ltree_ops, gist__ltree_ops, gist_trgm_ops and gist_hstore_ops. Also we parametrize maximum number of integer ranges for gist__int_ops. However, the main future usage of this feature is expected to be json, where users would be able to specify which way to index particular json parts. Catversion is bumped. Discussion: https://postgr.es/m/d22c3a18-31c7-1879-fc11-4c1ce2f5e5af%40postgrespro.ru Author: Nikita Glukhov, revised by me Reviwed-by: Nikolay Shaplov, Robert Haas, Tom Lane, Tomas Vondra, Alvaro Herrera
2020-03-30 18:17:11 +02:00
if (i == BLOOM_OPTIONS_PROC)
continue; /* optional method */
ereport(INFO,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("bloom opclass %s is missing support function %d",
opclassname, i)));
result = false;
}
ReleaseCatCacheList(proclist);
ReleaseCatCacheList(oprlist);
ReleaseSysCache(familytup);
ReleaseSysCache(classtup);
return result;
}