postgresql/src/backend/rewrite/rewriteHandler.c

1232 lines
34 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* rewriteHandler.c
* Primary module of query rewriter.
*
2002-06-20 22:29:54 +02:00
* Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* $Header: /cvsroot/pgsql/src/backend/rewrite/rewriteHandler.c,v 1.114 2002/12/12 15:49:40 tgl Exp $
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
1999-07-16 07:00:38 +02:00
#include "access/heapam.h"
#include "catalog/pg_operator.h"
#include "catalog/pg_type.h"
1999-07-16 07:00:38 +02:00
#include "miscadmin.h"
#include "nodes/makefuncs.h"
1999-07-16 07:00:38 +02:00
#include "optimizer/clauses.h"
#include "optimizer/prep.h"
#include "optimizer/var.h"
1999-07-16 07:00:38 +02:00
#include "parser/analyze.h"
#include "parser/parse_coerce.h"
#include "parser/parse_expr.h"
#include "parser/parse_oper.h"
2000-06-15 05:33:12 +02:00
#include "parser/parse_type.h"
#include "parser/parsetree.h"
#include "rewrite/rewriteHandler.h"
1999-07-16 07:00:38 +02:00
#include "rewrite/rewriteManip.h"
#include "utils/builtins.h"
1999-07-16 07:00:38 +02:00
#include "utils/lsyscache.h"
static Query *rewriteRuleAction(Query *parsetree,
Query *rule_action,
Node *rule_qual,
int rt_index,
CmdType event);
static List *adjustJoinTreeList(Query *parsetree, bool removert, int rt_index);
static void rewriteTargetList(Query *parsetree, Relation target_relation);
static TargetEntry *process_matched_tle(TargetEntry *src_tle,
2002-09-04 22:31:48 +02:00
TargetEntry *prior_tle);
static void markQueryForUpdate(Query *qry, bool skipOldNew);
static List *matchLocks(CmdType event, RuleLock *rulelocks,
2001-03-22 05:01:46 +01:00
int varno, Query *parsetree);
static Query *fireRIRrules(Query *parsetree);
/*
* rewriteRuleAction -
* Rewrite the rule action with appropriate qualifiers (taken from
* the triggering query).
*/
static Query *
rewriteRuleAction(Query *parsetree,
Query *rule_action,
Node *rule_qual,
int rt_index,
CmdType event)
{
int current_varno,
new_varno;
int rt_length;
Query *sub_action;
Query **sub_action_ptr;
/*
* Make modifiable copies of rule action and qual (what we're passed
* are the stored versions in the relcache; don't touch 'em!).
*/
rule_action = (Query *) copyObject(rule_action);
rule_qual = (Node *) copyObject(rule_qual);
current_varno = rt_index;
rt_length = length(parsetree->rtable);
new_varno = PRS2_NEW_VARNO + rt_length;
/*
* Adjust rule action and qual to offset its varnos, so that we can
* merge its rtable with the main parsetree's rtable.
*
2001-03-22 05:01:46 +01:00
* If the rule action is an INSERT...SELECT, the OLD/NEW rtable entries
* will be in the SELECT part, and we have to modify that rather than
* the top-level INSERT (kluge!).
*/
sub_action = getInsertSelectQuery(rule_action, &sub_action_ptr);
OffsetVarNodes((Node *) sub_action, rt_length, 0);
OffsetVarNodes(rule_qual, rt_length, 0);
/* but references to *OLD* should point at original rt_index */
ChangeVarNodes((Node *) sub_action,
PRS2_OLD_VARNO + rt_length, rt_index, 0);
ChangeVarNodes(rule_qual,
PRS2_OLD_VARNO + rt_length, rt_index, 0);
/*
* Generate expanded rtable consisting of main parsetree's rtable plus
* rule action's rtable; this becomes the complete rtable for the rule
* action. Some of the entries may be unused after we finish
* rewriting, but if we tried to clean those out we'd have a much
* harder job to adjust RT indexes in the query's Vars. It's OK to
* have unused RT entries, since planner will ignore them.
*
* NOTE: because planner will destructively alter rtable, we must ensure
* that rule action's rtable is separate and shares no substructure
* with the main rtable. Hence do a deep copy here.
*/
sub_action->rtable = nconc((List *) copyObject(parsetree->rtable),
sub_action->rtable);
/*
* Each rule action's jointree should be the main parsetree's jointree
2001-03-22 05:01:46 +01:00
* plus that rule's jointree, but usually *without* the original
* rtindex that we're replacing (if present, which it won't be for
* INSERT). Note that if the rule action refers to OLD, its jointree
* will add a reference to rt_index. If the rule action doesn't refer
* to OLD, but either the rule_qual or the user query quals do, then
* we need to keep the original rtindex in the jointree to provide
* data for the quals. We don't want the original rtindex to be
* joined twice, however, so avoid keeping it if the rule action
* mentions it.
*
* As above, the action's jointree must not share substructure with the
* main parsetree's.
*/
if (sub_action->jointree != NULL)
{
2001-03-22 05:01:46 +01:00
bool keeporig;
List *newjointree;
2001-03-22 05:01:46 +01:00
keeporig = (!rangeTableEntry_used((Node *) sub_action->jointree,
rt_index, 0)) &&
(rangeTableEntry_used(rule_qual, rt_index, 0) ||
rangeTableEntry_used(parsetree->jointree->quals, rt_index, 0));
newjointree = adjustJoinTreeList(parsetree, !keeporig, rt_index);
sub_action->jointree->fromlist =
nconc(newjointree, sub_action->jointree->fromlist);
}
/*
* We copy the qualifications of the parsetree to the action and vice
* versa. So force hasSubLinks if one of them has it. If this is not
* right, the flag will get cleared later, but we mustn't risk having
* it not set when it needs to be. (XXX this should probably be
* handled by AddQual and friends, not here...)
*/
if (parsetree->hasSubLinks)
sub_action->hasSubLinks = TRUE;
else if (sub_action->hasSubLinks)
parsetree->hasSubLinks = TRUE;
/*
2001-03-22 05:01:46 +01:00
* Event Qualification forces copying of parsetree and splitting into
* two queries one w/rule_qual, one w/NOT rule_qual. Also add user
* query qual onto rule action
*/
AddQual(sub_action, rule_qual);
AddQual(sub_action, parsetree->jointree->quals);
/*
2001-03-22 05:01:46 +01:00
* Rewrite new.attribute w/ right hand side of target-list entry for
* appropriate field name in insert/update.
*
* KLUGE ALERT: since ResolveNew returns a mutated copy, we can't just
* apply it to sub_action; we have to remember to update the sublink
* inside rule_action, too.
*/
if (event == CMD_INSERT || event == CMD_UPDATE)
{
sub_action = (Query *) ResolveNew((Node *) sub_action,
new_varno,
0,
parsetree->targetList,
event,
current_varno);
if (sub_action_ptr)
*sub_action_ptr = sub_action;
else
rule_action = sub_action;
}
return rule_action;
}
/*
* Copy the query's jointree list, and optionally attempt to remove any
* occurrence of the given rt_index as a top-level join item (we do not look
* for it within join items; this is OK because we are only expecting to find
* it as an UPDATE or DELETE target relation, which will be at the top level
* of the join). Returns modified jointree list --- this is a separate copy
* sharing no nodes with the original.
*/
static List *
adjustJoinTreeList(Query *parsetree, bool removert, int rt_index)
{
List *newjointree = copyObject(parsetree->jointree->fromlist);
List *jjt;
if (removert)
1999-05-25 18:15:34 +02:00
{
foreach(jjt, newjointree)
{
RangeTblRef *rtr = lfirst(jjt);
2001-03-22 05:01:46 +01:00
if (IsA(rtr, RangeTblRef) &&rtr->rtindex == rt_index)
{
newjointree = lremove(rtr, newjointree);
break;
}
}
}
return newjointree;
}
This is the final state of the rule system for 6.4 after the patch is applied: Rewrite rules on relation level work fine now. Event qualifications on insert/update/delete rules work fine now. I added the new keyword OLD to reference the CURRENT tuple. CURRENT will be removed in 6.5. Update rules can reference NEW and OLD in the rule qualification and the actions. Insert/update/delete rules on views can be established to let them behave like real tables. For insert/update/delete rules multiple actions are supported now. The actions can also be surrounded by parantheses to make psql happy. Multiple actions are required if update to a view requires updates to multiple tables. Regular users are permitted to create/drop rules on tables they have RULE permissions for (DefineQueryRewrite() is now able to get around the access restrictions on pg_rewrite). This enables view creation for regular users too. This required an extra boolean parameter to pg_parse_and_plan() that tells to set skipAcl on all rangetable entries of the resulting queries. There is a new function pg_exec_query_acl_override() that could be used by backend utilities to use this facility. All rule actions (not only views) inherit the permissions of the event relations owner. Sample: User A creates tables T1 and T2, creates rules that log INSERT/UPDATE/DELETE on T1 in T2 (like in the regression tests for rules I created) and grants ALL but RULE on T1 to user B. User B can now fully access T1 and the logging happens in T2. But user B cannot access T2 at all, only the rule actions can. And due to missing RULE permissions on T1, user B cannot disable logging. Rules on the attribute level are disabled (they don't work properly and since regular users are now permitted to create rules I decided to disable them). Rules on select must have exactly one action that is a select (so select rules must be a view definition). UPDATE NEW/OLD rules are disabled (still broken, but triggers can do it). There are two new system views (pg_rule and pg_view) that show the definition of the rules or views so the db admin can see what the users do. They use two new functions pg_get_ruledef() and pg_get_viewdef() that are builtins. The functions pg_get_ruledef() and pg_get_viewdef() could be used to implement rule and view support in pg_dump. PostgreSQL is now the only database system I know, that has rewrite rules on the query level. All others (where I found a rule statement at all) use stored database procedures or the like (triggers as we call them) for active rules (as some call them). Future of the rule system: The now disabled parts of the rule system (attribute level, multiple actions on select and update new stuff) require a complete new rewrite handler from scratch. The old one is too badly wired up. After 6.4 I'll start to work on a new rewrite handler, that fully supports the attribute level rules, multiple actions on select and update new. This will be available for 6.5 so we get full rewrite rule capabilities. Jan
1998-08-24 03:38:11 +02:00
/*
* rewriteTargetList - rewrite INSERT/UPDATE targetlist into standard form
*
* This has the following responsibilities:
*
* 1. For an INSERT, add tlist entries to compute default values for any
* attributes that have defaults and are not assigned to in the given tlist.
* (We do not insert anything for default-less attributes, however. The
* planner will later insert NULLs for them, but there's no reason to slow
* down rewriter processing with extra tlist nodes.)
*
* 2. Merge multiple entries for the same target attribute, or declare error
* if we can't. Presently, multiple entries are only allowed for UPDATE of
* an array field, for example "UPDATE table SET foo[2] = 42, foo[4] = 43".
* We can merge such operations into a single assignment op. Essentially,
* the expression we want to produce in this case is like
* foo = array_set(array_set(foo, 2, 42), 4, 43)
*
* 3. Sort the tlist into standard order: non-junk fields in order by resno,
* then junk fields (these in no particular order).
*
* We must do items 1 and 2 before firing rewrite rules, else rewritten
2002-09-04 22:31:48 +02:00
* references to NEW.foo will produce wrong or incomplete results. Item 3
* is not needed for rewriting, but will be needed by the planner, and we
* can do it essentially for free while handling items 1 and 2.
*/
static void
rewriteTargetList(Query *parsetree, Relation target_relation)
{
CmdType commandType = parsetree->commandType;
List *tlist = parsetree->targetList;
List *new_tlist = NIL;
int attrno,
numattrs;
List *temp;
/*
* Scan the tuple description in the relation's relcache entry to make
* sure we have all the user attributes in the right order.
*/
numattrs = RelationGetNumberOfAttributes(target_relation);
for (attrno = 1; attrno <= numattrs; attrno++)
{
2002-09-04 22:31:48 +02:00
Form_pg_attribute att_tup = target_relation->rd_att->attrs[attrno - 1];
TargetEntry *new_tle = NULL;
/* We can ignore deleted attributes */
if (att_tup->attisdropped)
continue;
/*
2002-09-04 22:31:48 +02:00
* Look for targetlist entries matching this attr. We match by
* resno, but the resname should match too.
*
* Junk attributes are not candidates to be matched.
*/
foreach(temp, tlist)
{
TargetEntry *old_tle = (TargetEntry *) lfirst(temp);
Resdom *resdom = old_tle->resdom;
if (!resdom->resjunk && resdom->resno == attrno)
{
Assert(strcmp(resdom->resname,
NameStr(att_tup->attname)) == 0);
new_tle = process_matched_tle(old_tle, new_tle);
/* keep scanning to detect multiple assignments to attr */
}
}
if (new_tle == NULL && commandType == CMD_INSERT)
{
/*
2002-09-04 22:31:48 +02:00
* Didn't find a matching tlist entry; if it's an INSERT, look
* for a default value, and add a tlist entry computing the
* default if we find one.
*/
Node *new_expr;
new_expr = build_column_default(target_relation, attrno);
if (new_expr)
new_tle = makeTargetEntry(makeResdom(attrno,
att_tup->atttypid,
att_tup->atttypmod,
2002-09-04 22:31:48 +02:00
pstrdup(NameStr(att_tup->attname)),
false),
(Expr *) new_expr);
}
if (new_tle)
new_tlist = lappend(new_tlist, new_tle);
}
/*
* Copy all resjunk tlist entries to the end of the new tlist, and
* assign them resnos above the last real resno.
*
* Typical junk entries include ORDER BY or GROUP BY expressions (are
* these actually possible in an INSERT or UPDATE?), system attribute
* references, etc.
*/
foreach(temp, tlist)
{
TargetEntry *old_tle = (TargetEntry *) lfirst(temp);
Resdom *resdom = old_tle->resdom;
if (resdom->resjunk)
{
/* Get the resno right, but don't copy unnecessarily */
if (resdom->resno != attrno)
{
resdom = (Resdom *) copyObject((Node *) resdom);
resdom->resno = attrno;
old_tle = makeTargetEntry(resdom, old_tle->expr);
}
new_tlist = lappend(new_tlist, old_tle);
attrno++;
}
else
{
/* Let's just make sure we processed all the non-junk items */
if (resdom->resno < 1 || resdom->resno > numattrs)
elog(ERROR, "rewriteTargetList: bogus resno %d in targetlist",
resdom->resno);
}
}
parsetree->targetList = new_tlist;
}
/*
* Convert a matched TLE from the original tlist into a correct new TLE.
*
* This routine detects and handles multiple assignments to the same target
* attribute.
*/
static TargetEntry *
process_matched_tle(TargetEntry *src_tle,
TargetEntry *prior_tle)
{
Resdom *resdom = src_tle->resdom;
Node *priorbottom;
ArrayRef *newexpr;
if (prior_tle == NULL)
{
/*
* Normal case where this is the first assignment to the
* attribute.
*/
return src_tle;
}
/*
* Multiple assignments to same attribute. Allow only if all are
* array-assign operators with same bottom array object.
*/
if (src_tle->expr == NULL || !IsA(src_tle->expr, ArrayRef) ||
((ArrayRef *) src_tle->expr)->refassgnexpr == NULL ||
prior_tle->expr == NULL || !IsA(prior_tle->expr, ArrayRef) ||
((ArrayRef *) prior_tle->expr)->refassgnexpr == NULL ||
((ArrayRef *) src_tle->expr)->refrestype !=
((ArrayRef *) prior_tle->expr)->refrestype)
elog(ERROR, "Multiple assignments to same attribute \"%s\"",
resdom->resname);
/*
* Prior TLE could be a nest of ArrayRefs if we do this more than
* once.
*/
priorbottom = (Node *) ((ArrayRef *) prior_tle->expr)->refexpr;
while (priorbottom != NULL && IsA(priorbottom, ArrayRef) &&
((ArrayRef *) priorbottom)->refassgnexpr != NULL)
priorbottom = (Node *) ((ArrayRef *) priorbottom)->refexpr;
if (!equal(priorbottom, ((ArrayRef *) src_tle->expr)->refexpr))
elog(ERROR, "Multiple assignments to same attribute \"%s\"",
resdom->resname);
/*
* Looks OK to nest 'em.
*/
newexpr = makeNode(ArrayRef);
memcpy(newexpr, src_tle->expr, sizeof(ArrayRef));
newexpr->refexpr = prior_tle->expr;
return makeTargetEntry(resdom, (Expr *) newexpr);
}
/*
* Make an expression tree for the default value for a column.
*
* If there is no default, return a NULL instead.
*/
Node *
build_column_default(Relation rel, int attrno)
{
TupleDesc rd_att = rel->rd_att;
Form_pg_attribute att_tup = rd_att->attrs[attrno - 1];
Oid atttype = att_tup->atttypid;
int32 atttypmod = att_tup->atttypmod;
Node *expr = NULL;
Oid exprtype;
/*
* Scan to see if relation has a default for this column.
*/
if (rd_att->constr && rd_att->constr->num_defval > 0)
{
AttrDefault *defval = rd_att->constr->defval;
int ndef = rd_att->constr->num_defval;
while (--ndef >= 0)
{
if (attrno == defval[ndef].adnum)
{
/*
* Found it, convert string representation to node tree.
*/
expr = stringToNode(defval[ndef].adbin);
break;
}
}
}
if (expr == NULL)
{
/*
2002-09-04 22:31:48 +02:00
* No per-column default, so look for a default for the type
* itself.
*/
if (att_tup->attisset)
{
/*
2002-09-04 22:31:48 +02:00
* Set attributes are represented as OIDs no matter what the
* set element type is, and the element type's default is
* irrelevant too.
*/
}
else
expr = get_typdefault(atttype);
}
if (expr == NULL)
return NULL; /* No default anywhere */
/*
2002-09-04 22:31:48 +02:00
* Make sure the value is coerced to the target column type (might not
* be right type yet if it's not a constant!) This should match the
* parser's processing of non-defaulted expressions --- see
* updateTargetListEntry().
*/
exprtype = exprType(expr);
expr = coerce_to_target_type(expr, exprtype,
atttype, atttypmod,
COERCION_ASSIGNMENT,
COERCE_IMPLICIT_CAST);
/*
* This really shouldn't fail; should have checked the default's
* type when it was created ...
*/
if (expr == NULL)
elog(ERROR, "Column \"%s\" is of type %s"
" but default expression is of type %s"
"\n\tYou will need to rewrite or cast the expression",
NameStr(att_tup->attname),
format_type_be(atttype),
format_type_be(exprtype));
return expr;
}
/*
* matchLocks -
* match the list of locks and returns the matching rules
*/
static List *
matchLocks(CmdType event,
RuleLock *rulelocks,
int varno,
Query *parsetree)
{
List *matching_locks = NIL;
int nlocks;
int i;
Assert(rulelocks != NULL); /* we get called iff there is some lock */
Assert(parsetree != NULL);
if (parsetree->commandType != CMD_SELECT)
{
if (parsetree->resultRelation != varno)
return NIL;
}
nlocks = rulelocks->numLocks;
for (i = 0; i < nlocks; i++)
1999-05-25 18:15:34 +02:00
{
RewriteRule *oneLock = rulelocks->rules[i];
if (oneLock->event == event)
{
if (parsetree->commandType != CMD_SELECT ||
(oneLock->attrno == -1 ?
rangeTableEntry_used((Node *) parsetree, varno, 0) :
attribute_used((Node *) parsetree,
varno, oneLock->attrno, 0)))
matching_locks = lappend(matching_locks, oneLock);
}
}
return matching_locks;
}
static Query *
ApplyRetrieveRule(Query *parsetree,
RewriteRule *rule,
int rt_index,
bool relation_level,
Relation relation,
bool relIsUsed)
{
Query *rule_action;
RangeTblEntry *rte,
*subrte;
if (length(rule->actions) != 1)
elog(ERROR, "ApplyRetrieveRule: expected just one rule action");
if (rule->qual != NULL)
elog(ERROR, "ApplyRetrieveRule: can't handle qualified ON SELECT rule");
2001-03-22 05:01:46 +01:00
if (!relation_level)
elog(ERROR, "ApplyRetrieveRule: can't handle per-attribute ON SELECT rule");
/*
* Make a modifiable copy of the view query, and recursively expand
* any view references inside it.
*/
rule_action = copyObject(lfirst(rule->actions));
rule_action = fireRIRrules(rule_action);
/*
2001-03-22 05:01:46 +01:00
* VIEWs are really easy --- just plug the view query in as a
* subselect, replacing the relation's original RTE.
*/
rte = rt_fetch(rt_index, parsetree->rtable);
rte->rtekind = RTE_SUBQUERY;
rte->relid = InvalidOid;
rte->subquery = rule_action;
rte->inh = false; /* must not be set for a subquery */
/*
* We move the view's permission check data down to its rangetable.
* The checks will actually be done against the *OLD* entry therein.
*/
subrte = rt_fetch(PRS2_OLD_VARNO, rule_action->rtable);
Assert(subrte->relid == relation->rd_id);
subrte->checkForRead = rte->checkForRead;
subrte->checkForWrite = rte->checkForWrite;
subrte->checkAsUser = rte->checkAsUser;
rte->checkForRead = false; /* no permission check on subquery itself */
rte->checkForWrite = false;
rte->checkAsUser = InvalidOid;
/*
* FOR UPDATE of view?
*/
if (intMember(rt_index, parsetree->rowMarks))
{
/*
* Remove the view from the list of rels that will actually be
* marked FOR UPDATE by the executor. It will still be access-
* checked for write access, though.
*/
parsetree->rowMarks = lremovei(rt_index, parsetree->rowMarks);
1999-05-25 18:15:34 +02:00
/*
* Set up the view's referenced tables as if FOR UPDATE.
1999-01-21 17:08:55 +01:00
*/
markQueryForUpdate(rule_action, true);
1999-01-21 17:08:55 +01:00
}
return parsetree;
}
/*
* Recursively mark all relations used by a view as FOR UPDATE.
*
* This may generate an invalid query, eg if some sub-query uses an
* aggregate. We leave it to the planner to detect that.
*
* NB: this must agree with the parser's transformForUpdate() routine.
*/
static void
markQueryForUpdate(Query *qry, bool skipOldNew)
{
Index rti = 0;
List *l;
foreach(l, qry->rtable)
{
RangeTblEntry *rte = (RangeTblEntry *) lfirst(l);
rti++;
/* Ignore OLD and NEW entries if we are at top level of view */
if (skipOldNew &&
(rti == PRS2_OLD_VARNO || rti == PRS2_NEW_VARNO))
continue;
if (rte->rtekind == RTE_RELATION)
{
if (!intMember(rti, qry->rowMarks))
qry->rowMarks = lappendi(qry->rowMarks, rti);
rte->checkForWrite = true;
}
else if (rte->rtekind == RTE_SUBQUERY)
{
/* FOR UPDATE of subquery is propagated to subquery's rels */
markQueryForUpdate(rte->subquery, false);
}
}
}
/*
* fireRIRonSubLink -
* Apply fireRIRrules() to each SubLink (subselect in expression) found
* in the given tree.
*
* NOTE: although this has the form of a walker, we cheat and modify the
* SubLink nodes in-place. It is caller's responsibility to ensure that
* no unwanted side-effects occur!
*
* This is unlike most of the other routines that recurse into subselects,
* because we must take control at the SubLink node in order to replace
* the SubLink's subselect link with the possibly-rewritten subquery.
*/
static bool
fireRIRonSubLink(Node *node, void *context)
{
if (node == NULL)
return false;
if (IsA(node, SubLink))
1999-05-25 18:15:34 +02:00
{
SubLink *sub = (SubLink *) node;
/* Do what we came for */
sub->subselect = (Node *) fireRIRrules((Query *) (sub->subselect));
/* Fall through to process lefthand args of SubLink */
}
2001-03-22 05:01:46 +01:00
/*
* Do NOT recurse into Query nodes, because fireRIRrules already
* processed subselects of subselects for us.
*/
return expression_tree_walker(node, fireRIRonSubLink,
(void *) context);
}
/*
* fireRIRrules -
* Apply all RIR rules on each rangetable entry in a query
*/
static Query *
fireRIRrules(Query *parsetree)
{
1999-05-25 18:15:34 +02:00
int rt_index;
/*
* don't try to convert this into a foreach loop, because rtable list
* can get changed each time through...
*/
rt_index = 0;
1999-05-25 18:15:34 +02:00
while (rt_index < length(parsetree->rtable))
{
RangeTblEntry *rte;
Relation rel;
List *locks;
RuleLock *rules;
RewriteRule *rule;
LOCKMODE lockmode;
bool relIsUsed;
int i;
List *l;
++rt_index;
rte = rt_fetch(rt_index, parsetree->rtable);
/*
* A subquery RTE can't have associated rules, so there's nothing
* to do to this level of the query, but we must recurse into the
* subquery to expand any rule references in it.
*/
if (rte->rtekind == RTE_SUBQUERY)
{
rte->subquery = fireRIRrules(rte->subquery);
continue;
}
/*
* Joins and other non-relation RTEs can be ignored completely.
*/
if (rte->rtekind != RTE_RELATION)
continue;
/*
* If the table is not referenced in the query, then we ignore it.
* This prevents infinite expansion loop due to new rtable entries
* inserted by expansion of a rule. A table is referenced if it is
* part of the join set (a source table), or is referenced by any
* Var nodes, or is the result table.
*/
relIsUsed = rangeTableEntry_used((Node *) parsetree, rt_index, 0);
if (!relIsUsed && rt_index != parsetree->resultRelation)
continue;
1999-05-25 18:15:34 +02:00
/*
2001-03-22 05:01:46 +01:00
* This may well be the first access to the relation during the
* current statement (it will be, if this Query was extracted from
* a rule or somehow got here other than via the parser).
* Therefore, grab the appropriate lock type for the relation, and
* do not release it until end of transaction. This protects the
* rewriter and planner against schema changes mid-query.
*
2001-03-22 05:01:46 +01:00
* If the relation is the query's result relation, then
* RewriteQuery() already got the right lock on it, so we need no
* additional lock. Otherwise, check to see if the relation is
* accessed FOR UPDATE or not.
*/
if (rt_index == parsetree->resultRelation)
lockmode = NoLock;
else if (intMember(rt_index, parsetree->rowMarks))
lockmode = RowShareLock;
else
lockmode = AccessShareLock;
rel = heap_open(rte->relid, lockmode);
/*
* Collect the RIR rules that we must apply
*/
rules = rel->rd_rules;
if (rules == NULL)
1999-05-25 18:15:34 +02:00
{
heap_close(rel, NoLock);
continue;
}
locks = NIL;
1999-05-25 18:15:34 +02:00
for (i = 0; i < rules->numLocks; i++)
{
rule = rules->rules[i];
if (rule->event != CMD_SELECT)
continue;
1999-05-25 18:15:34 +02:00
if (rule->attrno > 0)
{
/* per-attr rule; do we need it? */
if (!attribute_used((Node *) parsetree, rt_index,
rule->attrno, 0))
continue;
}
locks = lappend(locks, rule);
}
/*
* Now apply them
*/
1999-05-25 18:15:34 +02:00
foreach(l, locks)
{
rule = lfirst(l);
parsetree = ApplyRetrieveRule(parsetree,
rule,
rt_index,
rule->attrno == -1,
rel,
relIsUsed);
}
heap_close(rel, NoLock);
}
/*
* Recurse into sublink subqueries, too. But we already did the ones
* in the rtable.
*/
if (parsetree->hasSubLinks)
query_tree_walker(parsetree, fireRIRonSubLink, NULL,
QTW_IGNORE_SUBQUERIES);
/*
2001-03-22 05:01:46 +01:00
* If the query was marked having aggregates, check if this is still
* true after rewriting. Ditto for sublinks. Note there should be no
* aggs in the qual at this point. (Does this code still do anything
* useful? The view-becomes-subselect-in-FROM approach doesn't look
* like it could remove aggs or sublinks...)
*/
if (parsetree->hasAggs)
{
parsetree->hasAggs = checkExprHasAggs((Node *) parsetree);
if (parsetree->hasAggs)
if (checkExprHasAggs((Node *) parsetree->jointree))
elog(ERROR, "fireRIRrules: failed to remove aggs from qual");
}
if (parsetree->hasSubLinks)
parsetree->hasSubLinks = checkExprHasSubLink((Node *) parsetree);
return parsetree;
}
/*
* Modify the given query by adding 'AND rule_qual IS NOT TRUE' to its
* qualification. This is used to generate suitable "else clauses" for
* conditional INSTEAD rules. (Unfortunately we must use "x IS NOT TRUE",
* not just "NOT x" which the planner is much smarter about, else we will
* do the wrong thing when the qual evaluates to NULL.)
*
2001-03-22 05:01:46 +01:00
* The rule_qual may contain references to OLD or NEW. OLD references are
* replaced by references to the specified rt_index (the relation that the
* rule applies to). NEW references are only possible for INSERT and UPDATE
* queries on the relation itself, and so they should be replaced by copies
* of the related entries in the query's own targetlist.
*/
static Query *
CopyAndAddInvertedQual(Query *parsetree,
Node *rule_qual,
int rt_index,
CmdType event)
{
Query *new_tree = (Query *) copyObject(parsetree);
Node *new_qual = (Node *) copyObject(rule_qual);
/* Fix references to OLD */
ChangeVarNodes(new_qual, PRS2_OLD_VARNO, rt_index, 0);
/* Fix references to NEW */
if (event == CMD_INSERT || event == CMD_UPDATE)
new_qual = ResolveNew(new_qual,
PRS2_NEW_VARNO,
0,
parsetree->targetList,
event,
rt_index);
/* And attach the fixed qual */
AddInvertedQual(new_tree, new_qual);
return new_tree;
}
/*
* fireRules -
* Iterate through rule locks applying rules.
*
* Input arguments:
* parsetree - original query
* rt_index - RT index of result relation in original query
* event - type of rule event
* locks - list of rules to fire
* Output arguments:
* *instead_flag - set TRUE if any unqualified INSTEAD rule is found
* (must be initialized to FALSE)
* *qual_product - filled with modified original query if any qualified
* INSTEAD rule is found (must be initialized to NULL)
* Return value:
* list of rule actions adjusted for use with this query
*
* Qualified INSTEAD rules generate their action with the qualification
* condition added. They also generate a modified version of the original
* query with the negated qualification added, so that it will run only for
* rows that the qualified action doesn't act on. (If there are multiple
* qualified INSTEAD rules, we AND all the negated quals onto a single
* modified original query.) We won't execute the original, unmodified
* query if we find either qualified or unqualified INSTEAD rules. If
* we find both, the modified original query is discarded too.
*/
static List *
fireRules(Query *parsetree,
int rt_index,
CmdType event,
List *locks,
bool *instead_flag,
Query **qual_product)
{
List *results = NIL;
List *i;
foreach(i, locks)
{
RewriteRule *rule_lock = (RewriteRule *) lfirst(i);
Node *event_qual = rule_lock->qual;
List *actions = rule_lock->actions;
QuerySource qsrc;
List *r;
/* Determine correct QuerySource value for actions */
if (rule_lock->isInstead)
{
if (event_qual != NULL)
qsrc = QSRC_QUAL_INSTEAD_RULE;
else
{
qsrc = QSRC_INSTEAD_RULE;
*instead_flag = true; /* report unqualified INSTEAD */
}
}
else
qsrc = QSRC_NON_INSTEAD_RULE;
if (qsrc == QSRC_QUAL_INSTEAD_RULE)
{
/*
* If there are INSTEAD rules with qualifications, the
* original query is still performed. But all the negated rule
* qualifications of the INSTEAD rules are added so it does
* its actions only in cases where the rule quals of all
* INSTEAD rules are false. Think of it as the default action
* in a case. We save this in *qual_product so
* deepRewriteQuery() can add it to the query list after we
* mangled it up enough.
*
* If we have already found an unqualified INSTEAD rule,
* then *qual_product won't be used, so don't bother building it.
*/
if (! *instead_flag)
{
if (*qual_product == NULL)
*qual_product = parsetree;
*qual_product = CopyAndAddInvertedQual(*qual_product,
event_qual,
rt_index,
event);
}
}
/* Now process the rule's actions and add them to the result list */
foreach(r, actions)
{
Query *rule_action = lfirst(r);
if (rule_action->commandType == CMD_NOTHING)
continue;
rule_action = rewriteRuleAction(parsetree, rule_action,
event_qual, rt_index, event);
rule_action->querySource = qsrc;
results = lappend(results, rule_action);
}
}
return results;
}
/*
* One pass of rewriting a single query.
*
* parsetree is the input query. Return value and output parameters
* are defined the same as for fireRules, above.
*/
static List *
RewriteQuery(Query *parsetree, bool *instead_flag, Query **qual_product)
{
CmdType event;
1999-05-25 18:15:34 +02:00
List *product_queries = NIL;
int result_relation;
1999-05-25 18:15:34 +02:00
RangeTblEntry *rt_entry;
Relation rt_entry_relation;
RuleLock *rt_entry_locks;
Assert(parsetree != NULL);
event = parsetree->commandType;
/*
1999-05-25 18:15:34 +02:00
* SELECT rules are handled later when we have all the queries that
* should get executed
*/
if (event == CMD_SELECT)
return NIL;
/*
* Utilities aren't rewritten at all - why is this here?
*/
if (event == CMD_UTILITY)
return NIL;
/*
1999-05-25 18:15:34 +02:00
* the statement is an update, insert or delete - fire rules on it.
*/
result_relation = parsetree->resultRelation;
Assert(result_relation != 0);
rt_entry = rt_fetch(result_relation, parsetree->rtable);
Assert(rt_entry->rtekind == RTE_RELATION);
/*
2001-03-22 05:01:46 +01:00
* This may well be the first access to the result relation during the
* current statement (it will be, if this Query was extracted from a
* rule or somehow got here other than via the parser). Therefore,
* grab the appropriate lock type for a result relation, and do not
* release it until end of transaction. This protects the rewriter
* and planner against schema changes mid-query.
*/
rt_entry_relation = heap_open(rt_entry->relid, RowExclusiveLock);
/*
* If it's an INSERT or UPDATE, rewrite the targetlist into standard
* form. This will be needed by the planner anyway, and doing it now
* ensures that any references to NEW.field will behave sanely.
*/
if (event == CMD_INSERT || event == CMD_UPDATE)
rewriteTargetList(parsetree, rt_entry_relation);
/*
* Collect and apply the appropriate rules.
*/
rt_entry_locks = rt_entry_relation->rd_rules;
if (rt_entry_locks != NULL)
{
List *locks = matchLocks(event, rt_entry_locks,
result_relation, parsetree);
product_queries = fireRules(parsetree,
1999-05-25 18:15:34 +02:00
result_relation,
event,
locks,
instead_flag,
qual_product);
}
2001-03-22 05:01:46 +01:00
heap_close(rt_entry_relation, NoLock); /* keep lock! */
return product_queries;
}
/*
* to avoid infinite recursion, we restrict the number of times a query
* can be rewritten. Detecting cycles is left for the reader as an exercise.
*/
#ifndef REWRITE_INVOKE_MAX
#define REWRITE_INVOKE_MAX 100
#endif
static int numQueryRewriteInvoked = 0;
/*
* deepRewriteQuery -
* rewrites the query and apply the rules again on the queries rewritten
*/
static List *
deepRewriteQuery(Query *parsetree)
{
List *rewritten = NIL;
List *result;
bool instead = false;
Query *qual_product = NULL;
List *n;
if (++numQueryRewriteInvoked > REWRITE_INVOKE_MAX)
elog(ERROR, "query rewritten %d times, may contain cycles",
numQueryRewriteInvoked - 1);
result = RewriteQuery(parsetree, &instead, &qual_product);
foreach(n, result)
{
Query *pt = lfirst(n);
List *newstuff;
newstuff = deepRewriteQuery(pt);
rewritten = nconc(rewritten, newstuff);
}
/*
* For INSERTs, the original query is done first; for UPDATE/DELETE,
* it is done last. This is needed because update and delete rule
* actions might not do anything if they are invoked after the update
* or delete is performed. The command counter increment between the
* query executions makes the deleted (and maybe the updated) tuples
* disappear so the scans for them in the rule actions cannot find
* them.
*
* If we found any unqualified INSTEAD, the original query is not
* done at all, in any form. Otherwise, we add the modified form
* if qualified INSTEADs were found, else the unmodified form.
*/
if (!instead)
{
if (parsetree->commandType == CMD_INSERT)
{
if (qual_product != NULL)
rewritten = lcons(qual_product, rewritten);
else
rewritten = lcons(parsetree, rewritten);
}
else
{
if (qual_product != NULL)
rewritten = lappend(rewritten, qual_product);
else
rewritten = lappend(rewritten, parsetree);
}
}
return rewritten;
}
/*
* QueryRewriteOne -
* rewrite one query
*/
static List *
QueryRewriteOne(Query *parsetree)
{
numQueryRewriteInvoked = 0;
/*
* take a deep breath and apply all the rewrite rules - ay
*/
return deepRewriteQuery(parsetree);
}
/*
* QueryRewrite -
* Primary entry point to the query rewriter.
* Rewrite one query via query rewrite system, possibly returning 0
* or many queries.
*
* NOTE: The code in QueryRewrite was formerly in pg_parse_and_plan(), and was
* moved here so that it would be invoked during EXPLAIN.
*/
List *
QueryRewrite(Query *parsetree)
{
1999-05-25 18:15:34 +02:00
List *querylist;
List *results = NIL;
List *l;
/*
* Step 1
*
* Apply all non-SELECT rules possibly getting 0 or many queries
*/
querylist = QueryRewriteOne(parsetree);
/*
* Step 2
*
* Apply all the RIR rules on each query
*/
1999-05-25 18:15:34 +02:00
foreach(l, querylist)
{
2001-03-22 05:01:46 +01:00
Query *query = (Query *) lfirst(l);
1999-05-25 18:15:34 +02:00
query = fireRIRrules(query);
1999-05-25 18:15:34 +02:00
/*
* If the query target was rewritten as a view, complain.
1999-05-25 18:15:34 +02:00
*/
if (query->resultRelation)
1999-05-25 18:15:34 +02:00
{
RangeTblEntry *rte = rt_fetch(query->resultRelation,
query->rtable);
1999-05-25 18:15:34 +02:00
if (rte->rtekind == RTE_SUBQUERY)
1999-05-25 18:15:34 +02:00
{
switch (query->commandType)
{
case CMD_INSERT:
elog(ERROR, "Cannot insert into a view"
"\n\tYou need an unconditional ON INSERT DO INSTEAD rule");
break;
case CMD_UPDATE:
elog(ERROR, "Cannot update a view"
"\n\tYou need an unconditional ON UPDATE DO INSTEAD rule");
break;
case CMD_DELETE:
elog(ERROR, "Cannot delete from a view"
"\n\tYou need an unconditional ON DELETE DO INSTEAD rule");
break;
default:
elog(ERROR, "QueryRewrite: unexpected commandType %d",
(int) query->commandType);
break;
}
1999-05-25 18:15:34 +02:00
}
}
results = lappend(results, query);
1999-05-25 18:15:34 +02:00
}
return results;
Hi! INTERSECT and EXCEPT is available for postgresql-v6.4! The patch against v6.4 is included at the end of the current text (in uuencoded form!) I also included the text of my Master's Thesis. (a postscript version). I hope that you find something of it useful and would be happy if parts of it find their way into the PostgreSQL documentation project (If so, tell me, then I send the sources of the document!) The contents of the document are: -) The first chapter might be of less interest as it gives only an overview on SQL. -) The second chapter gives a description on much of PostgreSQL's features (like user defined types etc. and how to use these features) -) The third chapter starts with an overview of PostgreSQL's internal structure with focus on the stages a query has to pass (i.e. parser, planner/optimizer, executor). Then a detailed description of the implementation of the Having clause and the Intersect/Except logic is given. Originally I worked on v6.3.2 but never found time enough to prepare and post a patch. Now I applied the changes to v6.4 to get Intersect and Except working with the new version. Chapter 3 of my documentation deals with the changes against v6.3.2, so keep that in mind when comparing the parts of the code printed there with the patched sources of v6.4. Here are some remarks on the patch. There are some things that have still to be done but at the moment I don't have time to do them myself. (I'm doing my military service at the moment) Sorry for that :-( -) I used a rewrite technique for the implementation of the Except/Intersect logic which rewrites the query to a semantically equivalent query before it is handed to the rewrite system (for views, rules etc.), planner, executor etc. -) In v6.3.2 the types of the attributes of two select statements connected by the UNION keyword had to match 100%. In v6.4 the types only need to be familiar (i.e. int and float can be mixed). Since this feature did not exist when I worked on Intersect/Except it does not work correctly for Except/Intersect queries WHEN USED IN COMBINATION WITH UNIONS! (i.e. sometimes the wrong type is used for the resulting table. This is because until now the types of the attributes of the first select statement have been used for the resulting table. When Intersects and/or Excepts are used in combination with Unions it might happen, that the first select statement of the original query appears at another position in the query which will be executed. The reason for this is the technique used for the implementation of Except/Intersect which does a query rewrite!) NOTE: It is NOT broken for pure UNION queries and pure INTERSECT/EXCEPT queries!!! -) I had to add the field intersect_clause to some data structures but did not find time to implement printfuncs for the new field. This does NOT break the debug modes but when an Except/Intersect is used the query debug output will be the already rewritten query. -) Massive changes to the grammar rules for SELECT and INSERT statements have been necessary (see comments in gram.y and documentation for deatails) in order to be able to use mixed queries like (SELECT ... UNION (SELECT ... EXCEPT SELECT)) INTERSECT SELECT...; -) When using UNION/EXCEPT/INTERSECT you will get: NOTICE: equal: "Don't know if nodes of type xxx are equal". I did not have time to add comparsion support for all the needed nodes, but the default behaviour of the function equal met my requirements. I did not dare to supress this message! That's the reason why the regression test for union will fail: These messages are also included in the union.out file! -) Somebody of you changed the union_planner() function for v6.4 (I copied the targetlist to new_tlist and that was removed and replaced by a cleanup of the original targetlist). These chnages violated some having queries executed against views so I changed it back again. I did not have time to examine the differences between the two versions but now it works :-) If you want to find out, try the file queries/view_having.sql on both versions and compare the results . Two queries won't produce a correct result with your version. regards Stefan
1999-01-18 01:10:17 +01:00
}