path: root/src/backend/commands/indexcmds.c

/*-------------------------------------------------------------------------
 *
 * indexcmds.c
 *	  POSTGRES define and remove index code.
 *
 * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/commands/indexcmds.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include "access/htup_details.h"
#include "access/reloptions.h"
#include "access/xact.h"
#include "catalog/catalog.h"
#include "catalog/index.h"
#include "catalog/indexing.h"
#include "catalog/pg_opclass.h"
#include "catalog/pg_opfamily.h"
#include "catalog/pg_tablespace.h"
#include "catalog/pg_type.h"
#include "commands/comment.h"
#include "commands/dbcommands.h"
#include "commands/defrem.h"
#include "commands/tablecmds.h"
#include "commands/tablespace.h"
#include "mb/pg_wchar.h"
#include "miscadmin.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/planner.h"
#include "parser/parse_coerce.h"
#include "parser/parse_func.h"
#include "parser/parse_oper.h"
#include "storage/lmgr.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/fmgroids.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/snapmgr.h"
#include "utils/syscache.h"
#include "utils/tqual.h"


/* non-export function prototypes */
static void CheckPredicate(Expr *predicate);
static void ComputeIndexAttrs(IndexInfo *indexInfo,
				  Oid *typeOidP,
				  Oid *collationOidP,
				  Oid *classOidP,
				  int16 *colOptionP,
				  List *attList,
				  List *exclusionOpNames,
				  Oid relId,
				  char *accessMethodName, Oid accessMethodId,
				  bool amcanorder,
				  bool isconstraint);
static Oid GetIndexOpClass(List *opclass, Oid attrType,
				char *accessMethodName, Oid accessMethodId);
static char *ChooseIndexName(const char *tabname, Oid namespaceId,
				List *colnames, List *exclusionOpNames,
				bool primary, bool isconstraint);
static char *ChooseIndexNameAddition(List *colnames);
static List *ChooseIndexColumnNames(List *indexElems);
static void RangeVarCallbackForReindexIndex(const RangeVar *relation,
								Oid relId, Oid oldRelId, void *arg);

/*
 * CheckIndexCompatible
 *		Determine whether an existing index definition is compatible with a
 *		prospective index definition, such that the existing index storage
 *		could become the storage of the new index, avoiding a rebuild.
 *
 * 'heapRelation': the relation the index would apply to.
 * 'accessMethodName': name of the AM to use.
 * 'attributeList': a list of IndexElem specifying columns and expressions
 *		to index on.
 * 'exclusionOpNames': list of names of exclusion-constraint operators,
 *		or NIL if not an exclusion constraint.
 *
 * This is tailored to the needs of ALTER TABLE ALTER TYPE, which recreates
 * any indexes that depended on a changing column from their pg_get_indexdef
 * or pg_get_constraintdef definitions.  We omit some of the sanity checks of
 * DefineIndex.  We assume that the old and new indexes have the same number
 * of columns and that if one has an expression column or predicate, both do.
 * Errors arising from the attribute list still apply.
 *
 * Most column type changes that can skip a table rewrite do not invalidate
 * indexes.  We ackowledge this when all operator classes, collations and
 * exclusion operators match.  Though we could further permit intra-opfamily
 * changes for btree and hash indexes, that adds subtle complexity with no
 * concrete benefit for core types.

 * When a comparison or exclusion operator has a polymorphic input type, the
 * actual input types must also match.	This defends against the possibility
 * that operators could vary behavior in response to get_fn_expr_argtype().
 * At present, this hazard is theoretical: check_exclusion_constraint() and
 * all core index access methods decline to set fn_expr for such calls.
 *
 * We do not yet implement a test to verify compatibility of expression
 * columns or predicates, so assume any such index is incompatible.
 */
bool
CheckIndexCompatible(Oid oldId,
					 RangeVar *heapRelation,
					 char *accessMethodName,
					 List *attributeList,
					 List *exclusionOpNames)
{
	bool		isconstraint;
	Oid		   *typeObjectId;
	Oid		   *collationObjectId;
	Oid		   *classObjectId;
	Oid			accessMethodId;
	Oid			relationId;
	HeapTuple	tuple;
	Form_pg_index indexForm;
	Form_pg_am	accessMethodForm;
	bool		amcanorder;
	int16	   *coloptions;
	IndexInfo  *indexInfo;
	int			numberOfAttributes;
	int			old_natts;
	bool		isnull;
	bool		ret = true;
	oidvector  *old_indclass;
	oidvector  *old_indcollation;
	Relation	irel;
	int			i;
	Datum		d;

	/* Caller should already have the relation locked in some way. */
	relationId = RangeVarGetRelid(heapRelation, NoLock, false);

	/*
	 * We can pretend isconstraint = false unconditionally.  It only serves to
	 * decide the text of an error message that should never happen for us.
	 */
	isconstraint = false;

	numberOfAttributes = list_length(attributeList);
	Assert(numberOfAttributes > 0);
	Assert(numberOfAttributes <= INDEX_MAX_KEYS);

	/* look up the access method */
	tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
	if (!HeapTupleIsValid(tuple))
		ereport(ERROR,
				(errcode(ERRCODE_UNDEFINED_OBJECT),
				 errmsg("access method \"%s\" does not exist",
						accessMethodName)));
	accessMethodId = HeapTupleGetOid(tuple);
	accessMethodForm = (Form_pg_am) GETSTRUCT(tuple);
	amcanorder = accessMethodForm->amcanorder;
	ReleaseSysCache(tuple);

	/*
	 * Compute the operator classes, collations, and exclusion operators for
	 * the new index, so we can test whether it's compatible with the existing
	 * one.  Note that ComputeIndexAttrs might fail here, but that's OK:
	 * DefineIndex would have called this function with the same arguments
	 * later on, and it would have failed then anyway.
	 */
	indexInfo = makeNode(IndexInfo);
	indexInfo->ii_Expressions = NIL;
	indexInfo->ii_ExpressionsState = NIL;
	indexInfo->ii_PredicateState = NIL;
	indexInfo->ii_ExclusionOps = NULL;
	indexInfo->ii_ExclusionProcs = NULL;
	indexInfo->ii_ExclusionStrats = NULL;
	typeObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	collationObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	classObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	coloptions = (int16 *) palloc(numberOfAttributes * sizeof(int16));
	ComputeIndexAttrs(indexInfo,
					  typeObjectId, collationObjectId, classObjectId,
					  coloptions, attributeList,
					  exclusionOpNames, relationId,
					  accessMethodName, accessMethodId,
					  amcanorder, isconstraint);


	/* Get the soon-obsolete pg_index tuple. */
	tuple = SearchSysCache1(INDEXRELID, ObjectIdGetDatum(oldId));
	if (!HeapTupleIsValid(tuple))
		elog(ERROR, "cache lookup failed for index %u", oldId);
	indexForm = (Form_pg_index) GETSTRUCT(tuple);

	/*
	 * We don't assess expressions or predicates; assume incompatibility.
	 * Also, if the index is invalid for any reason, treat it as incompatible.
	 */
	if (!(heap_attisnull(tuple, Anum_pg_index_indpred) &&
		  heap_attisnull(tuple, Anum_pg_index_indexprs) &&
		  IndexIsValid(indexForm)))
	{
		ReleaseSysCache(tuple);
		return false;
	}

	/* Any change in operator class or collation breaks compatibility. */
	old_natts = indexForm->indnatts;
	Assert(old_natts == numberOfAttributes);

	d = SysCacheGetAttr(INDEXRELID, tuple, Anum_pg_index_indcollation, &isnull);
	Assert(!isnull);
	old_indcollation = (oidvector *) DatumGetPointer(d);

	d = SysCacheGetAttr(INDEXRELID, tuple, Anum_pg_index_indclass, &isnull);
	Assert(!isnull);
	old_indclass = (oidvector *) DatumGetPointer(d);

	ret = (memcmp(old_indclass->values, classObjectId,
				  old_natts * sizeof(Oid)) == 0 &&
		   memcmp(old_indcollation->values, collationObjectId,
				  old_natts * sizeof(Oid)) == 0);

	ReleaseSysCache(tuple);

	if (!ret)
		return false;

	/* For polymorphic opcintype, column type changes break compatibility. */
	irel = index_open(oldId, AccessShareLock);	/* caller probably has a lock */
	for (i = 0; i < old_natts; i++)
	{
		if (IsPolymorphicType(get_opclass_input_type(classObjectId[i])) &&
			irel->rd_att->attrs[i]->atttypid != typeObjectId[i])
		{
			ret = false;
			break;
		}
	}

	/* Any change in exclusion operator selections breaks compatibility. */
	if (ret && indexInfo->ii_ExclusionOps != NULL)
	{
		Oid		   *old_operators,
				   *old_procs;
		uint16	   *old_strats;

		RelationGetExclusionInfo(irel, &old_operators, &old_procs, &old_strats);
		ret = memcmp(old_operators, indexInfo->ii_ExclusionOps,
					 old_natts * sizeof(Oid)) == 0;

		/* Require an exact input type match for polymorphic operators. */
		if (ret)
		{
			for (i = 0; i < old_natts && ret; i++)
			{
				Oid			left,
							right;

				op_input_types(indexInfo->ii_ExclusionOps[i], &left, &right);
				if ((IsPolymorphicType(left) || IsPolymorphicType(right)) &&
					irel->rd_att->attrs[i]->atttypid != typeObjectId[i])
				{
					ret = false;
					break;
				}
			}
		}
	}

	index_close(irel, NoLock);
	return ret;
}

/*
 * DefineIndex
 *		Creates a new index.
 *
 * 'stmt': IndexStmt describing the properties of the new index.
 * 'indexRelationId': normally InvalidOid, but during bootstrap can be
 *		nonzero to specify a preselected OID for the index.
 * 'is_alter_table': this is due to an ALTER rather than a CREATE operation.
 * 'check_rights': check for CREATE rights in the namespace.  (This should
 *		be true except when ALTER is deleting/recreating an index.)
 * 'skip_build': make the catalog entries but leave the index file empty;
 *		it will be filled later.
 * 'quiet': suppress the NOTICE chatter ordinarily provided for constraints.
 *
 * Returns the OID of the created index.
 */
Oid
DefineIndex(IndexStmt *stmt,
			Oid indexRelationId,
			bool is_alter_table,
			bool check_rights,
			bool skip_build,
			bool quiet)
{
	char	   *indexRelationName;
	char	   *accessMethodName;
	Oid		   *typeObjectId;
	Oid		   *collationObjectId;
	Oid		   *classObjectId;
	Oid			accessMethodId;
	Oid			relationId;
	Oid			namespaceId;
	Oid			tablespaceId;
	List	   *indexColNames;
	Relation	rel;
	Relation	indexRelation;
	HeapTuple	tuple;
	Form_pg_am	accessMethodForm;
	bool		amcanorder;
	RegProcedure amoptions;
	Datum		reloptions;
	int16	   *coloptions;
	IndexInfo  *indexInfo;
	int			numberOfAttributes;
	VirtualTransactionId *old_lockholders;
	VirtualTransactionId *old_snapshots;
	int			n_old_snapshots;
	LockRelId	heaprelid;
	LOCKTAG		heaplocktag;
	Snapshot	snapshot;
	int			i;

	/*
	 * count attributes in index
	 */
	numberOfAttributes = list_length(stmt->indexParams);
	if (numberOfAttributes <= 0)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
				 errmsg("must specify at least one column")));
	if (numberOfAttributes > INDEX_MAX_KEYS)
		ereport(ERROR,
				(errcode(ERRCODE_TOO_MANY_COLUMNS),
				 errmsg("cannot use more than %d columns in an index",
						INDEX_MAX_KEYS)));

	/*
	 * Open heap relation, acquire a suitable lock on it, remember its OID
	 *
	 * Only SELECT ... FOR UPDATE/SHARE are allowed while doing a standard
	 * index build; but for concurrent builds we allow INSERT/UPDATE/DELETE
	 * (but not VACUUM).
	 */
	rel = heap_openrv(stmt->relation,
					  (stmt->concurrent ? ShareUpdateExclusiveLock : ShareLock));

	relationId = RelationGetRelid(rel);
	namespaceId = RelationGetNamespace(rel);

	if (rel->rd_rel->relkind != RELKIND_RELATION)
	{
		if (rel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)

			/*
			 * Custom error message for FOREIGN TABLE since the term is close
			 * to a regular table and can confuse the user.
			 */
			ereport(ERROR,
					(errcode(ERRCODE_WRONG_OBJECT_TYPE),
					 errmsg("cannot create index on foreign table \"%s\"",
							RelationGetRelationName(rel))));
		else
			ereport(ERROR,
					(errcode(ERRCODE_WRONG_OBJECT_TYPE),
					 errmsg("\"%s\" is not a table",
							RelationGetRelationName(rel))));
	}

	/*
	 * Don't try to CREATE INDEX on temp tables of other backends.
	 */
	if (RELATION_IS_OTHER_TEMP(rel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot create indexes on temporary tables of other sessions")));

	/*
	 * Verify we (still) have CREATE rights in the rel's namespace.
	 * (Presumably we did when the rel was created, but maybe not anymore.)
	 * Skip check if caller doesn't want it.  Also skip check if
	 * bootstrapping, since permissions machinery may not be working yet.
	 */
	if (check_rights && !IsBootstrapProcessingMode())
	{
		AclResult	aclresult;

		aclresult = pg_namespace_aclcheck(namespaceId, GetUserId(),
										  ACL_CREATE);
		if (aclresult != ACLCHECK_OK)
			aclcheck_error(aclresult, ACL_KIND_NAMESPACE,
						   get_namespace_name(namespaceId));
	}

	/*
	 * Select tablespace to use.  If not specified, use default tablespace
	 * (which may in turn default to database's default).
	 */
	if (stmt->tableSpace)
	{
		tablespaceId = get_tablespace_oid(stmt->tableSpace, false);
	}
	else
	{
		tablespaceId = GetDefaultTablespace(rel->rd_rel->relpersistence);
		/* note InvalidOid is OK in this case */
	}

	/* Check permissions except when using database's default */
	if (OidIsValid(tablespaceId) && tablespaceId != MyDatabaseTableSpace)
	{
		AclResult	aclresult;

		aclresult = pg_tablespace_aclcheck(tablespaceId, GetUserId(),
										   ACL_CREATE);
		if (aclresult != ACLCHECK_OK)
			aclcheck_error(aclresult, ACL_KIND_TABLESPACE,
						   get_tablespace_name(tablespaceId));
	}

	/*
	 * Force shared indexes into the pg_global tablespace.	This is a bit of a
	 * hack but seems simpler than marking them in the BKI commands.  On the
	 * other hand, if it's not shared, don't allow it to be placed there.
	 */
	if (rel->rd_rel->relisshared)
		tablespaceId = GLOBALTABLESPACE_OID;
	else if (tablespaceId == GLOBALTABLESPACE_OID)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("only shared relations can be placed in pg_global tablespace")));

	/*
	 * Choose the index column names.
	 */
	indexColNames = ChooseIndexColumnNames(stmt->indexParams);

	/*
	 * Select name for index if caller didn't specify
	 */
	indexRelationName = stmt->idxname;
	if (indexRelationName == NULL)
		indexRelationName = ChooseIndexName(RelationGetRelationName(rel),
											namespaceId,
											indexColNames,
											stmt->excludeOpNames,
											stmt->primary,
											stmt->isconstraint);

	/*
	 * look up the access method, verify it can handle the requested features
	 */
	accessMethodName = stmt->accessMethod;
	tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
	if (!HeapTupleIsValid(tuple))
	{
		/*
		 * Hack to provide more-or-less-transparent updating of old RTREE
		 * indexes to GiST: if RTREE is requested and not found, use GIST.
		 */
		if (strcmp(accessMethodName, "rtree") == 0)
		{
			ereport(NOTICE,
					(errmsg("substituting access method \"gist\" for obsolete method \"rtree\"")));
			accessMethodName = "gist";
			tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
		}

		if (!HeapTupleIsValid(tuple))
			ereport(ERROR,
					(errcode(ERRCODE_UNDEFINED_OBJECT),
					 errmsg("access method \"%s\" does not exist",
							accessMethodName)));
	}
	accessMethodId = HeapTupleGetOid(tuple);
	accessMethodForm = (Form_pg_am) GETSTRUCT(tuple);

	if (stmt->unique && !accessMethodForm->amcanunique)
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
			   errmsg("access method \"%s\" does not support unique indexes",
					  accessMethodName)));
	if (numberOfAttributes > 1 && !accessMethodForm->amcanmulticol)
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
		  errmsg("access method \"%s\" does not support multicolumn indexes",
				 accessMethodName)));
	if (stmt->excludeOpNames && !OidIsValid(accessMethodForm->amgettuple))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
		errmsg("access method \"%s\" does not support exclusion constraints",
			   accessMethodName)));

	amcanorder = accessMethodForm->amcanorder;
	amoptions = accessMethodForm->amoptions;

	ReleaseSysCache(tuple);

	/*
	 * Validate predicate, if given
	 */
	if (stmt->whereClause)
		CheckPredicate((Expr *) stmt->whereClause);

	/*
	 * Parse AM-specific options, convert to text array form, validate.
	 */
	reloptions = transformRelOptions((Datum) 0, stmt->options,
									 NULL, NULL, false, false);

	(void) index_reloptions(amoptions, reloptions, true);

	/*
	 * Prepare arguments for index_create, primarily an IndexInfo structure.
	 * Note that ii_Predicate must be in implicit-AND format.
	 */
	indexInfo = makeNode(IndexInfo);
	indexInfo->ii_NumIndexAttrs = numberOfAttributes;
	indexInfo->ii_Expressions = NIL;	/* for now */
	indexInfo->ii_ExpressionsState = NIL;
	indexInfo->ii_Predicate = make_ands_implicit((Expr *) stmt->whereClause);
	indexInfo->ii_PredicateState = NIL;
	indexInfo->ii_ExclusionOps = NULL;
	indexInfo->ii_ExclusionProcs = NULL;
	indexInfo->ii_ExclusionStrats = NULL;
	indexInfo->ii_Unique = stmt->unique;
	/* In a concurrent build, mark it not-ready-for-inserts */
	indexInfo->ii_ReadyForInserts = !stmt->concurrent;
	indexInfo->ii_Concurrent = stmt->concurrent;
	indexInfo->ii_BrokenHotChain = false;

	typeObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	collationObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	classObjectId = (Oid *) palloc(numberOfAttributes * sizeof(Oid));
	coloptions = (int16 *) palloc(numberOfAttributes * sizeof(int16));
	ComputeIndexAttrs(indexInfo,
					  typeObjectId, collationObjectId, classObjectId,
					  coloptions, stmt->indexParams,
					  stmt->excludeOpNames, relationId,
					  accessMethodName, accessMethodId,
					  amcanorder, stmt->isconstraint);

	/*
	 * Extra checks when creating a PRIMARY KEY index.
	 */
	if (stmt->primary)
		index_check_primary_key(rel, indexInfo, is_alter_table);

	/*
	 * Report index creation if appropriate (delay this till after most of the
	 * error checks)
	 */
	if (stmt->isconstraint && !quiet)
	{
		const char *constraint_type;

		if (stmt->primary)
			constraint_type = "PRIMARY KEY";
		else if (stmt->unique)
			constraint_type = "UNIQUE";
		else if (stmt->excludeOpNames != NIL)
			constraint_type = "EXCLUDE";
		else
		{
			elog(ERROR, "unknown constraint type");
			constraint_type = NULL;		/* keep compiler quiet */
		}

		ereport(DEBUG1,
		  (errmsg("%s %s will create implicit index \"%s\" for table \"%s\"",
				  is_alter_table ? "ALTER TABLE / ADD" : "CREATE TABLE /",
				  constraint_type,
				  indexRelationName, RelationGetRelationName(rel))));
	}

	/*
	 * A valid stmt->oldNode implies that we already have a built form of the
	 * index.  The caller should also decline any index build.
	 */
	Assert(!OidIsValid(stmt->oldNode) || (skip_build && !stmt->concurrent));

	/*
	 * Make the catalog entries for the index, including constraints. Then, if
	 * not skip_build || concurrent, actually build the index.
	 */
	indexRelationId =
		index_create(rel, indexRelationName, indexRelationId, stmt->oldNode,
					 indexInfo, indexColNames,
					 accessMethodId, tablespaceId,
					 collationObjectId, classObjectId,
					 coloptions, reloptions, stmt->primary,
					 stmt->isconstraint, stmt->deferrable, stmt->initdeferred,
					 allowSystemTableMods,
					 skip_build || stmt->concurrent,
					 stmt->concurrent, !check_rights);

	/* Add any requested comment */
	if (stmt->idxcomment != NULL)
		CreateComments(indexRelationId, RelationRelationId, 0,
					   stmt->idxcomment);

	if (!stmt->concurrent)
	{
		/* Close the heap and we're done, in the non-concurrent case */
		heap_close(rel, NoLock);
		return indexRelationId;
	}

	/* save lockrelid and locktag for below, then close rel */
	heaprelid = rel->rd_lockInfo.lockRelId;
	SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId);
	heap_close(rel, NoLock);

	/*
	 * For a concurrent build, it's important to make the catalog entries
	 * visible to other transactions before we start to build the index. That
	 * will prevent them from making incompatible HOT updates.	The new index
	 * will be marked not indisready and not indisvalid, so that no one else
	 * tries to either insert into it or use it for queries.
	 *
	 * We must commit our current transaction so that the index becomes
	 * visible; then start another.  Note that all the data structures we just
	 * built are lost in the commit.  The only data we keep past here are the
	 * relation IDs.
	 *
	 * Before committing, get a session-level lock on the table, to ensure
	 * that neither it nor the index can be dropped before we finish. This
	 * cannot block, even if someone else is waiting for access, because we
	 * already have the same lock within our transaction.
	 *
	 * Note: we don't currently bother with a session lock on the index,
	 * because there are no operations that could change its state while we
	 * hold lock on the parent table.  This might need to change later.
	 */
	LockRelationIdForSession(&heaprelid, ShareUpdateExclusiveLock);

	PopActiveSnapshot();
	CommitTransactionCommand();
	StartTransactionCommand();

	/*
	 * Phase 2 of concurrent index build (see comments for validate_index()
	 * for an overview of how this works)
	 *
	 * Now we must wait until no running transaction could have the table open
	 * with the old list of indexes.  To do this, inquire which xacts
	 * currently would conflict with ShareLock on the table -- ie, which ones
	 * have a lock that permits writing the table.	Then wait for each of
	 * these xacts to commit or abort.	Note we do not need to worry about
	 * xacts that open the table for writing after this point; they will see
	 * the new index when they open it.
	 *
	 * Note: the reason we use actual lock acquisition here, rather than just
	 * checking the ProcArray and sleeping, is that deadlock is possible if
	 * one of the transactions in question is blocked trying to acquire an
	 * exclusive lock on our table.  The lock code will detect deadlock and
	 * error out properly.
	 *
	 * Note: GetLockConflicts() never reports our own xid, hence we need not
	 * check for that.	Also, prepared xacts are not reported, which is fine
	 * since they certainly aren't going to do anything more.
	 */
	old_lockholders = GetLockConflicts(&heaplocktag, ShareLock);

	while (VirtualTransactionIdIsValid(*old_lockholders))
	{
		VirtualXactLock(*old_lockholders, true);
		old_lockholders++;
	}

	/*
	 * At this moment we are sure that there are no transactions with the
	 * table open for write that don't have this new index in their list of
	 * indexes.  We have waited out all the existing transactions and any new
	 * transaction will have the new index in its list, but the index is still
	 * marked as "not-ready-for-inserts".  The index is consulted while
	 * deciding HOT-safety though.	This arrangement ensures that no new HOT
	 * chains can be created where the new tuple and the old tuple in the
	 * chain have different index keys.
	 *
	 * We now take a new snapshot, and build the index using all tuples that
	 * are visible in this snapshot.  We can be sure that any HOT updates to
	 * these tuples will be compatible with the index, since any updates made
	 * by transactions that didn't know about the index are now committed or
	 * rolled back.  Thus, each visible tuple is either the end of its
	 * HOT-chain or the extension of the chain is HOT-safe for this index.
	 */

	/* Open and lock the parent heap relation */
	rel = heap_openrv(stmt->relation, ShareUpdateExclusiveLock);

	/* And the target index relation */
	indexRelation = index_open(indexRelationId, RowExclusiveLock);

	/* Set ActiveSnapshot since functions in the indexes may need it */
	PushActiveSnapshot(GetTransactionSnapshot());

	/* We have to re-build the IndexInfo struct, since it was lost in commit */
	indexInfo = BuildIndexInfo(indexRelation);
	Assert(!indexInfo->ii_ReadyForInserts);
	indexInfo->ii_Concurrent = true;
	indexInfo->ii_BrokenHotChain = false;

	/* Now build the index */
	index_build(rel, indexRelation, indexInfo, stmt->primary, false);

	/* Close both the relations, but keep the locks */
	heap_close(rel, NoLock);
	index_close(indexRelation, NoLock);

	/*
	 * Update the pg_index row to mark the index as ready for inserts. Once we
	 * commit this transaction, any new transactions that open the table must
	 * insert new entries into the index for insertions and non-HOT updates.
	 */
	index_set_state_flags(indexRelationId, INDEX_CREATE_SET_READY);

	/* we can do away with our snapshot */
	PopActiveSnapshot();

	/*
	 * Commit this transaction to make the indisready update visible.
	 */
	CommitTransactionCommand();
	StartTransactionCommand();

	/*
	 * Phase 3 of concurrent index build
	 *
	 * We once again wait until no transaction can have the table open with
	 * the index marked as read-only for updates.
	 */
	old_lockholders = GetLockConflicts(&heaplocktag, ShareLock);

	while (VirtualTransactionIdIsValid(*old_lockholders))
	{
		VirtualXactLock(*old_lockholders, true);
		old_lockholders++;
	}

	/*
	 * Now take the "reference snapshot" that will be used by validate_index()
	 * to filter candidate tuples.	Beware!  There might still be snapshots in
	 * use that treat some transaction as in-progress that our reference
	 * snapshot treats as committed.  If such a recently-committed transaction
	 * deleted tuples in the table, we will not include them in the index; yet
	 * those transactions which see the deleting one as still-in-progress will
	 * expect such tuples to be there once we mark the index as valid.
	 *
	 * We solve this by waiting for all endangered transactions to exit before
	 * we mark the index as valid.
	 *
	 * We also set ActiveSnapshot to this snap, since functions in indexes may
	 * need a snapshot.
	 */
	snapshot = RegisterSnapshot(GetTransactionSnapshot());
	PushActiveSnapshot(snapshot);

	/*
	 * Scan the index and the heap, insert any missing index entries.
	 */
	validate_index(relationId, indexRelationId, snapshot);

	/*
	 * The index is now valid in the sense that it contains all currently
	 * interesting tuples.	But since it might not contain tuples deleted just
	 * before the reference snap was taken, we have to wait out any
	 * transactions that might have older snapshots.  Obtain a list of VXIDs
	 * of such transactions, and wait for them individually.
	 *
	 * We can exclude any running transactions that have xmin > the xmin of
	 * our reference snapshot; their oldest snapshot must be newer than ours.
	 * We can also exclude any transactions that have xmin = zero, since they
	 * evidently have no live snapshot at all (and any one they might be in
	 * process of taking is certainly newer than ours).  Transactions in other
	 * DBs can be ignored too, since they'll never even be able to see this
	 * index.
	 *
	 * We can also exclude autovacuum processes and processes running manual
	 * lazy VACUUMs, because they won't be fazed by missing index entries
	 * either.	(Manual ANALYZEs, however, can't be excluded because they
	 * might be within transactions that are going to do arbitrary operations
	 * later.)
	 *
	 * Also, GetCurrentVirtualXIDs never reports our own vxid, so we need not
	 * check for that.
	 *
	 * If a process goes idle-in-transaction with xmin zero, we do not need to
	 * wait for it anymore, per the above argument.  We do not have the
	 * infrastructure right now to stop waiting if that happens, but we can at
	 * least avoid the folly of waiting when it is idle at the time we would
	 * begin to wait.  We do this by repeatedly rechecking the output of
	 * GetCurrentVirtualXIDs.  If, during any iteration, a particular vxid
	 * doesn't show up in the output, we know we can forget about it.
	 */
	old_snapshots = GetCurrentVirtualXIDs(snapshot->xmin, true, false,
										  PROC_IS_AUTOVACUUM | PROC_IN_VACUUM,
										  &n_old_snapshots);

	for (i = 0; i < n_old_snapshots; i++)
	{
		if (!VirtualTransactionIdIsValid(old_snapshots[i]))
			continue;			/* found uninteresting in previous cycle */

		if (i > 0)
		{
			/* see if anything's changed ... */
			VirtualTransactionId *newer_snapshots;
			int			n_newer_snapshots;
			int			j;
			int			k;

			newer_snapshots = GetCurrentVirtualXIDs(snapshot->xmin,
													true, false,
										 PROC_IS_AUTOVACUUM | PROC_IN_VACUUM,
													&n_newer_snapshots);
			for (j = i; j < n_old_snapshots; j++)
			{
				if (!VirtualTransactionIdIsValid(old_snapshots[j]))
					continue;	/* found uninteresting in previous cycle */
				for (k = 0; k < n_newer_snapshots; k++)
				{
					if (VirtualTransactionIdEquals(old_snapshots[j],
												   newer_snapshots[k]))
						break;
				}
				if (k >= n_newer_snapshots)		/* not there anymore */
					SetInvalidVirtualTransactionId(old_snapshots[j]);
			}
			pfree(newer_snapshots);
		}

		if (VirtualTransactionIdIsValid(old_snapshots[i]))
			VirtualXactLock(old_snapshots[i], true);
	}

	/*
	 * Index can now be marked valid -- update its pg_index entry
	 */
	index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID);

	/*
	 * The pg_index update will cause backends (including this one) to update
	 * relcache entries for the index itself, but we should also send a
	 * relcache inval on the parent table to force replanning of cached plans.
	 * Otherwise existing sessions might fail to use the new index where it
	 * would be useful.  (Note that our earlier commits did not create reasons
	 * to replan; so relcache flush on the index itself was sufficient.)
	 */
	CacheInvalidateRelcacheByRelid(heaprelid.relId);

	/* we can now do away with our active snapshot */
	PopActiveSnapshot();

	/* And we can remove the validating snapshot too */
	UnregisterSnapshot(snapshot);

	/*
	 * Last thing to do is release the session-level lock on the parent table.
	 */
	UnlockRelationIdForSession(&heaprelid, ShareUpdateExclusiveLock);

	return indexRelationId;
}


/*
 * CheckMutability
 *		Test whether given expression is mutable
 */
static bool
CheckMutability(Expr *expr)
{
	/*
	 * First run the expression through the planner.  This has a couple of
	 * important consequences.	First, function default arguments will get
	 * inserted, which may affect volatility (consider "default now()").
	 * Second, inline-able functions will get inlined, which may allow us to
	 * conclude that the function is really less volatile than it's marked. As
	 * an example, polymorphic functions must be marked with the most volatile
	 * behavior that they have for any input type, but once we inline the
	 * function we may be able to conclude that it's not so volatile for the
	 * particular input type we're dealing with.
	 *
	 * We assume here that expression_planner() won't scribble on its input.
	 */
	expr = expression_planner(expr);

	/* Now we can search for non-immutable functions */
	return contain_mutable_functions((Node *) expr);
}


/*
 * CheckPredicate
 *		Checks that the given partial-index predicate is valid.
 *
 * This used to also constrain the form of the predicate to forms that
 * indxpath.c could do something with.	However, that seems overly
 * restrictive.  One useful application of partial indexes is to apply
 * a UNIQUE constraint across a subset of a table, and in that scenario
 * any evaluatable predicate will work.  So accept any predicate here
 * (except ones requiring a plan), and let indxpath.c fend for itself.
 */
static void
CheckPredicate(Expr *predicate)
{
	/*
	 * transformExpr() should have already rejected subqueries, aggregates,
	 * and window functions, based on the EXPR_KIND_ for a predicate.
	 */

	/*
	 * A predicate using mutable functions is probably wrong, for the same
	 * reasons that we don't allow an index expression to use one.
	 */
	if (CheckMutability(predicate))
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
		   errmsg("functions in index predicate must be marked IMMUTABLE")));
}

/*
 * Compute per-index-column information, including indexed column numbers
 * or index expressions, opclasses, and indoptions.
 */
static void
ComputeIndexAttrs(IndexInfo *indexInfo,
				  Oid *typeOidP,
				  Oid *collationOidP,
				  Oid *classOidP,
				  int16 *colOptionP,
				  List *attList,	/* list of IndexElem's */
				  List *exclusionOpNames,
				  Oid relId,
				  char *accessMethodName,
				  Oid accessMethodId,
				  bool amcanorder,
				  bool isconstraint)
{
	ListCell   *nextExclOp;
	ListCell   *lc;
	int			attn;

	/* Allocate space for exclusion operator info, if needed */
	if (exclusionOpNames)
	{
		int			ncols = list_length(attList);

		Assert(list_length(exclusionOpNames) == ncols);
		indexInfo->ii_ExclusionOps = (Oid *) palloc(sizeof(Oid) * ncols);
		indexInfo->ii_ExclusionProcs = (Oid *) palloc(sizeof(Oid) * ncols);
		indexInfo->ii_ExclusionStrats = (uint16 *) palloc(sizeof(uint16) * ncols);
		nextExclOp = list_head(exclusionOpNames);
	}
	else
		nextExclOp = NULL;

	/*
	 * process attributeList
	 */
	attn = 0;
	foreach(lc, attList)
	{
		IndexElem  *attribute = (IndexElem *) lfirst(lc);
		Oid			atttype;
		Oid			attcollation;

		/*
		 * Process the column-or-expression to be indexed.
		 */
		if (attribute->name != NULL)
		{
			/* Simple index attribute */
			HeapTuple	atttuple;
			Form_pg_attribute attform;

			Assert(attribute->expr == NULL);
			atttuple = SearchSysCacheAttName(relId, attribute->name);
			if (!HeapTupleIsValid(atttuple))
			{
				/* difference in error message spellings is historical */
				if (isconstraint)
					ereport(ERROR,
							(errcode(ERRCODE_UNDEFINED_COLUMN),
						  errmsg("column \"%s\" named in key does not exist",
								 attribute->name)));
				else
					ereport(ERROR,
							(errcode(ERRCODE_UNDEFINED_COLUMN),
							 errmsg("column \"%s\" does not exist",
									attribute->name)));
			}
			attform = (Form_pg_attribute) GETSTRUCT(atttuple);
			indexInfo->ii_KeyAttrNumbers[attn] = attform->attnum;
			atttype = attform->atttypid;
			attcollation = attform->attcollation;
			ReleaseSysCache(atttuple);
		}
		else
		{
			/* Index expression */
			Node	   *expr = attribute->expr;

			Assert(expr != NULL);
			atttype = exprType(expr);
			attcollation = exprCollation(expr);

			/*
			 * Strip any top-level COLLATE clause.	This ensures that we treat
			 * "x COLLATE y" and "(x COLLATE y)" alike.
			 */
			while (IsA(expr, CollateExpr))
				expr = (Node *) ((CollateExpr *) expr)->arg;

			if (IsA(expr, Var) &&
				((Var *) expr)->varattno != InvalidAttrNumber)
			{
				/*
				 * User wrote "(column)" or "(column COLLATE something)".
				 * Treat it like simple attribute anyway.
				 */
				indexInfo->ii_KeyAttrNumbers[attn] = ((Var *) expr)->varattno;
			}
			else
			{
				indexInfo->ii_KeyAttrNumbers[attn] = 0; /* marks expression */
				indexInfo->ii_Expressions = lappend(indexInfo->ii_Expressions,
													expr);

				/*
				 * transformExpr() should have already rejected subqueries,
				 * aggregates, and window functions, based on the EXPR_KIND_
				 * for an index expression.
				 */

				/*
				 * A expression using mutable functions is probably wrong,
				 * since if you aren't going to get the same result for the
				 * same data every time, it's not clear what the index entries
				 * mean at all.
				 */
				if (CheckMutability((Expr *) expr))
					ereport(ERROR,
							(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
							 errmsg("functions in index expression must be marked IMMUTABLE")));
			}
		}

		typeOidP[attn] = atttype;

		/*
		 * Apply collation override if any
		 */
		if (attribute->collation)
			attcollation = get_collation_oid(attribute->collation, false);

		/*
		 * Check we have a collation iff it's a collatable type.  The only
		 * expected failures here are (1) COLLATE applied to a noncollatable
		 * type, or (2) index expression had an unresolved collation.  But we
		 * might as well code this to be a complete consistency check.
		 */
		if (type_is_collatable(atttype))
		{
			if (!OidIsValid(attcollation))
				ereport(ERROR,
						(errcode(ERRCODE_INDETERMINATE_COLLATION),
						 errmsg("could not determine which collation to use for index expression"),
						 errhint("Use the COLLATE clause to set the collation explicitly.")));
		}
		else
		{
			if (OidIsValid(attcollation))
				ereport(ERROR,
						(errcode(ERRCODE_DATATYPE_MISMATCH),
						 errmsg("collations are not supported by type %s",
								format_type_be(atttype))));
		}

		collationOidP[attn] = attcollation;

		/*
		 * Identify the opclass to use.
		 */
		classOidP[attn] = GetIndexOpClass(attribute->opclass,
										  atttype,
										  accessMethodName,
										  accessMethodId);

		/*
		 * Identify the exclusion operator, if any.
		 */
		if (nextExclOp)
		{
			List	   *opname = (List *) lfirst(nextExclOp);
			Oid			opid;
			Oid			opfamily;
			int			strat;

			/*
			 * Find the operator --- it must accept the column datatype
			 * without runtime coercion (but binary compatibility is OK)
			 */
			opid = compatible_oper_opid(opname, atttype, atttype, false);

			/*
			 * Only allow commutative operators to be used in exclusion
			 * constraints. If X conflicts with Y, but Y does not conflict
			 * with X, bad things will happen.
			 */
			if (get_commutator(opid) != opid)
				ereport(ERROR,
						(errcode(ERRCODE_WRONG_OBJECT_TYPE),
						 errmsg("operator %s is not commutative",
								format_operator(opid)),
						 errdetail("Only commutative operators can be used in exclusion constraints.")));

			/*
			 * Operator must be a member of the right opfamily, too
			 */
			opfamily = get_opclass_family(classOidP[attn]);
			strat = get_op_opfamily_strategy(opid, opfamily);
			if (strat == 0)
			{
				HeapTuple	opftuple;
				Form_pg_opfamily opfform;

				/*
				 * attribute->opclass might not explicitly name the opfamily,
				 * so fetch the name of the selected opfamily for use in the
				 * error message.
				 */
				opftuple = SearchSysCache1(OPFAMILYOID,
										   ObjectIdGetDatum(opfamily));
				if (!HeapTupleIsValid(opftuple))
					elog(ERROR, "cache lookup failed for opfamily %u",
						 opfamily);
				opfform = (Form_pg_opfamily) GETSTRUCT(opftuple);

				ereport(ERROR,
						(errcode(ERRCODE_WRONG_OBJECT_TYPE),
						 errmsg("operator %s is not a member of operator family \"%s\"",
								format_operator(opid),
								NameStr(opfform->opfname)),
						 errdetail("The exclusion operator must be related to the index operator class for the constraint.")));
			}

			indexInfo->ii_ExclusionOps[attn] = opid;
			indexInfo->ii_ExclusionProcs[attn] = get_opcode(opid);
			indexInfo->ii_ExclusionStrats[attn] = strat;
			nextExclOp = lnext(nextExclOp);
		}

		/*
		 * Set up the per-column options (indoption field).  For now, this is
		 * zero for any un-ordered index, while ordered indexes have DESC and
		 * NULLS FIRST/LAST options.
		 */
		colOptionP[attn] = 0;
		if (amcanorder)
		{
			/* default ordering is ASC */
			if (attribute->ordering == SORTBY_DESC)
				colOptionP[attn] |= INDOPTION_DESC;
			/* default null ordering is LAST for ASC, FIRST for DESC */
			if (attribute->nulls_ordering == SORTBY_NULLS_DEFAULT)
			{
				if (attribute->ordering == SORTBY_DESC)
					colOptionP[attn] |= INDOPTION_NULLS_FIRST;
			}
			else if (attribute->nulls_ordering == SORTBY_NULLS_FIRST)
				colOptionP[attn] |= INDOPTION_NULLS_FIRST;
		}
		else
		{
			/* index AM does not support ordering */
			if (attribute->ordering != SORTBY_DEFAULT)
				ereport(ERROR,
						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
						 errmsg("access method \"%s\" does not support ASC/DESC options",
								accessMethodName)));
			if (attribute->nulls_ordering != SORTBY_NULLS_DEFAULT)
				ereport(ERROR,
						(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
						 errmsg("access method \"%s\" does not support NULLS FIRST/LAST options",
								accessMethodName)));
		}

		attn++;
	}
}

/*
 * Resolve possibly-defaulted operator class specification
 */
static Oid
GetIndexOpClass(List *opclass, Oid attrType,
				char *accessMethodName, Oid accessMethodId)
{
	char	   *schemaname;
	char	   *opcname;
	HeapTuple	tuple;
	Oid			opClassId,
				opInputType;

	/*
	 * Release 7.0 removed network_ops, timespan_ops, and datetime_ops, so we
	 * ignore those opclass names so the default *_ops is used.  This can be
	 * removed in some later release.  bjm 2000/02/07
	 *
	 * Release 7.1 removes lztext_ops, so suppress that too for a while.  tgl
	 * 2000/07/30
	 *
	 * Release 7.2 renames timestamp_ops to timestamptz_ops, so suppress that
	 * too for awhile.	I'm starting to think we need a better approach. tgl
	 * 2000/10/01
	 *
	 * Release 8.0 removes bigbox_ops (which was dead code for a long while
	 * anyway).  tgl 2003/11/11
	 */
	if (list_length(opclass) == 1)
	{
		char	   *claname = strVal(linitial(opclass));

		if (strcmp(claname, "network_ops") == 0 ||
			strcmp(claname, "timespan_ops") == 0 ||
			strcmp(claname, "datetime_ops") == 0 ||
			strcmp(claname, "lztext_ops") == 0 ||
			strcmp(claname, "timestamp_ops") == 0 ||
			strcmp(claname, "bigbox_ops") == 0)
			opclass = NIL;
	}

	if (opclass == NIL)
	{
		/* no operator class specified, so find the default */
		opClassId = GetDefaultOpClass(attrType, accessMethodId);
		if (!OidIsValid(opClassId))
			ereport(ERROR,
					(errcode(ERRCODE_UNDEFINED_OBJECT),
					 errmsg("data type %s has no default operator class for access method \"%s\"",
							format_type_be(attrType), accessMethodName),
					 errhint("You must specify an operator class for the index or define a default operator class for the data type.")));
		return opClassId;
	}

	/*
	 * Specific opclass name given, so look up the opclass.
	 */

	/* deconstruct the name list */
	DeconstructQualifiedName(opclass, &schemaname, &opcname);

	if (schemaname)
	{
		/* Look in specific schema only */
		Oid			namespaceId;

		namespaceId = LookupExplicitNamespace(schemaname);
		tuple = SearchSysCache3(CLAAMNAMENSP,
								ObjectIdGetDatum(accessMethodId),
								PointerGetDatum(opcname),
								ObjectIdGetDatum(namespaceId));
	}
	else
	{
		/* Unqualified opclass name, so search the search path */
		opClassId = OpclassnameGetOpcid(accessMethodId, opcname);
		if (!OidIsValid(opClassId))
			ereport(ERROR,
					(errcode(ERRCODE_UNDEFINED_OBJECT),
					 errmsg("operator class \"%s\" does not exist for access method \"%s\"",
							opcname, accessMethodName)));
		tuple = SearchSysCache1(CLAOID, ObjectIdGetDatum(opClassId));
	}

	if (!HeapTupleIsValid(tuple))
		ereport(ERROR,
				(errcode(ERRCODE_UNDEFINED_OBJECT),
				 errmsg("operator class \"%s\" does not exist for access method \"%s\"",
						NameListToString(opclass), accessMethodName)));

	/*
	 * Verify that the index operator class accepts this datatype.	Note we
	 * will accept binary compatibility.
	 */
	opClassId = HeapTupleGetOid(tuple);
	opInputType = ((Form_pg_opclass) GETSTRUCT(tuple))->opcintype;

	if (!IsBinaryCoercible(attrType, opInputType))
		ereport(ERROR,
				(errcode(ERRCODE_DATATYPE_MISMATCH),
				 errmsg("operator class \"%s\" does not accept data type %s",
					  NameListToString(opclass), format_type_be(attrType))));

	ReleaseSysCache(tuple);

	return opClassId;
}

/*
 * GetDefaultOpClass
 *
 * Given the OIDs of a datatype and an access method, find the default
 * operator class, if any.	Returns InvalidOid if there is none.
 */
Oid
GetDefaultOpClass(Oid type_id, Oid am_id)
{
	Oid			result = InvalidOid;
	int			nexact = 0;
	int			ncompatible = 0;
	int			ncompatiblepreferred = 0;
	Relation	rel;
	ScanKeyData skey[1];
	SysScanDesc scan;
	HeapTuple	tup;
	TYPCATEGORY tcategory;

	/* If it's a domain, look at the base type instead */
	type_id = getBaseType(type_id);

	tcategory = TypeCategory(type_id);

	/*
	 * We scan through all the opclasses available for the access method,
	 * looking for one that is marked default and matches the target type
	 * (either exactly or binary-compatibly, but prefer an exact match).
	 *
	 * We could find more than one binary-compatible match.  If just one is
	 * for a preferred type, use that one; otherwise we fail, forcing the user
	 * to specify which one he wants.  (The preferred-type special case is a
	 * kluge for varchar: it's binary-compatible to both text and bpchar, so
	 * we need a tiebreaker.)  If we find more than one exact match, then
	 * someone put bogus entries in pg_opclass.
	 */
	rel = heap_open(OperatorClassRelationId, AccessShareLock);

	ScanKeyInit(&skey[0],
				Anum_pg_opclass_opcmethod,
				BTEqualStrategyNumber, F_OIDEQ,
				ObjectIdGetDatum(am_id));

	scan = systable_beginscan(rel, OpclassAmNameNspIndexId, true,
							  SnapshotNow, 1, skey);

	while (HeapTupleIsValid(tup = systable_getnext(scan)))
	{
		Form_pg_opclass opclass = (Form_pg_opclass) GETSTRUCT(tup);

		/* ignore altogether if not a default opclass */
		if (!opclass->opcdefault)
			continue;
		if (opclass->opcintype == type_id)
		{
			nexact++;
			result = HeapTupleGetOid(tup);
		}
		else if (nexact == 0 &&
				 IsBinaryCoercible(type_id, opclass->opcintype))
		{
			if (IsPreferredType(tcategory, opclass->opcintype))
			{
				ncompatiblepreferred++;
				result = HeapTupleGetOid(tup);
			}
			else if (ncompatiblepreferred == 0)
			{
				ncompatible++;
				result = HeapTupleGetOid(tup);
			}
		}
	}

	systable_endscan(scan);

	heap_close(rel, AccessShareLock);

	/* raise error if pg_opclass contains inconsistent data */
	if (nexact > 1)
		ereport(ERROR,
				(errcode(ERRCODE_DUPLICATE_OBJECT),
		errmsg("there are multiple default operator classes for data type %s",
			   format_type_be(type_id))));

	if (nexact == 1 ||
		ncompatiblepreferred == 1 ||
		(ncompatiblepreferred == 0 && ncompatible == 1))
		return result;

	return InvalidOid;
}

/*
 *	makeObjectName()
 *
 *	Create a name for an implicitly created index, sequence, constraint, etc.
 *
 *	The parameters are typically: the original table name, the original field
 *	name, and a "type" string (such as "seq" or "pkey").	The field name
 *	and/or type can be NULL if not relevant.
 *
 *	The result is a palloc'd string.
 *
 *	The basic result we want is "name1_name2_label", omitting "_name2" or
 *	"_label" when those parameters are NULL.  However, we must generate
 *	a name with less than NAMEDATALEN characters!  So, we truncate one or
 *	both names if necessary to make a short-enough string.	The label part
 *	is never truncated (so it had better be reasonably short).
 *
 *	The caller is responsible for checking uniqueness of the generated
 *	name and retrying as needed; retrying will be done by altering the
 *	"label" string (which is why we never truncate that part).
 */
char *
makeObjectName(const char *name1, const char *name2, const char *label)
{
	char	   *name;
	int			overhead = 0;	/* chars needed for label and underscores */
	int			availchars;		/* chars available for name(s) */
	int			name1chars;		/* chars allocated to name1 */
	int			name2chars;		/* chars allocated to name2 */
	int			ndx;

	name1chars = strlen(name1);
	if (name2)
	{
		name2chars = strlen(name2);
		overhead++;				/* allow for separating underscore */
	}
	else
		name2chars = 0;
	if (label)
		overhead += strlen(label) + 1;

	availchars = NAMEDATALEN - 1 - overhead;
	Assert(availchars > 0);		/* else caller chose a bad label */

	/*
	 * If we must truncate,  preferentially truncate the longer name. This
	 * logic could be expressed without a loop, but it's simple and obvious as
	 * a loop.
	 */
	while (name1chars + name2chars > availchars)
	{
		if (name1chars > name2chars)
			name1chars--;
		else
			name2chars--;
	}

	name1chars = pg_mbcliplen(name1, name1chars, name1chars);
	if (name2)
		name2chars = pg_mbcliplen(name2, name2chars, name2chars);

	/* Now construct the string using the chosen lengths */
	name = palloc(name1chars + name2chars + overhead + 1);
	memcpy(name, name1, name1chars);
	ndx = name1chars;
	if (name2)
	{
		name[ndx++] = '_';
		memcpy(name + ndx, name2, name2chars);
		ndx += name2chars;
	}
	if (label)
	{
		name[ndx++] = '_';
		strcpy(name + ndx, label);
	}
	else
		name[ndx] = '\0';

	return name;
}

/*
 * Select a nonconflicting name for a new relation.  This is ordinarily
 * used to choose index names (which is why it's here) but it can also
 * be used for sequences, or any autogenerated relation kind.
 *
 * name1, name2, and label are used the same way as for makeObjectName(),
 * except that the label can't be NULL; digits will be appended to the label
 * if needed to create a name that is unique within the specified namespace.
 *
 * Note: it is theoretically possible to get a collision anyway, if someone
 * else chooses the same name concurrently.  This is fairly unlikely to be
 * a problem in practice, especially if one is holding an exclusive lock on
 * the relation identified by name1.  However, if choosing multiple names
 * within a single command, you'd better create the new object and do
 * CommandCounterIncrement before choosing the next one!
 *
 * Returns a palloc'd string.
 */
char *
ChooseRelationName(const char *name1, const char *name2,
				   const char *label, Oid namespaceid)
{
	int			pass = 0;
	char	   *relname = NULL;
	char		modlabel[NAMEDATALEN];

	/* try the unmodified label first */
	StrNCpy(modlabel, label, sizeof(modlabel));

	for (;;)
	{
		relname = makeObjectName(name1, name2, modlabel);

		if (!OidIsValid(get_relname_relid(relname, namespaceid)))
			break;

		/* found a conflict, so try a new name component */
		pfree(relname);
		snprintf(modlabel, sizeof(modlabel), "%s%d", label, ++pass);
	}

	return relname;
}

/*
 * Select the name to be used for an index.
 *
 * The argument list is pretty ad-hoc :-(
 */
static char *
ChooseIndexName(const char *tabname, Oid namespaceId,
				List *colnames, List *exclusionOpNames,
				bool primary, bool isconstraint)
{
	char	   *indexname;

	if (primary)
	{
		/* the primary key's name does not depend on the specific column(s) */
		indexname = ChooseRelationName(tabname,
									   NULL,
									   "pkey",
									   namespaceId);
	}
	else if (exclusionOpNames != NIL)
	{
		indexname = ChooseRelationName(tabname,
									   ChooseIndexNameAddition(colnames),
									   "excl",
									   namespaceId);
	}
	else if (isconstraint)
	{
		indexname = ChooseRelationName(tabname,
									   ChooseIndexNameAddition(colnames),
									   "key",
									   namespaceId);
	}
	else
	{
		indexname = ChooseRelationName(tabname,
									   ChooseIndexNameAddition(colnames),
									   "idx",
									   namespaceId);
	}

	return indexname;
}

/*
 * Generate "name2" for a new index given the list of column names for it
 * (as produced by ChooseIndexColumnNames).  This will be passed to
 * ChooseRelationName along with the parent table name and a suitable label.
 *
 * We know that less than NAMEDATALEN characters will actually be used,
 * so we can truncate the result once we've generated that many.
 */
static char *
ChooseIndexNameAddition(List *colnames)
{
	char		buf[NAMEDATALEN * 2];
	int			buflen = 0;
	ListCell   *lc;

	buf[0] = '\0';
	foreach(lc, colnames)
	{
		const char *name = (const char *) lfirst(lc);

		if (buflen > 0)
			buf[buflen++] = '_';	/* insert _ between names */

		/*
		 * At this point we have buflen <= NAMEDATALEN.  name should be less
		 * than NAMEDATALEN already, but use strlcpy for paranoia.
		 */
		strlcpy(buf + buflen, name, NAMEDATALEN);
		buflen += strlen(buf + buflen);
		if (buflen >= NAMEDATALEN)
			break;
	}
	return pstrdup(buf);
}

/*
 * Select the actual names to be used for the columns of an index, given the
 * list of IndexElems for the columns.	This is mostly about ensuring the
 * names are unique so we don't get a conflicting-attribute-names error.
 *
 * Returns a List of plain strings (char *, not String nodes).
 */
static List *
ChooseIndexColumnNames(List *indexElems)
{
	List	   *result = NIL;
	ListCell   *lc;

	foreach(lc, indexElems)
	{
		IndexElem  *ielem = (IndexElem *) lfirst(lc);
		const char *origname;
		const char *curname;
		int			i;
		char		buf[NAMEDATALEN];

		/* Get the preliminary name from the IndexElem */
		if (ielem->indexcolname)
			origname = ielem->indexcolname;		/* caller-specified name */
		else if (ielem->name)
			origname = ielem->name;		/* simple column reference */
		else
			origname = "expr";	/* default name for expression */

		/* If it conflicts with any previous column, tweak it */
		curname = origname;
		for (i = 1;; i++)
		{
			ListCell   *lc2;
			char		nbuf[32];
			int			nlen;

			foreach(lc2, result)
			{
				if (strcmp(curname, (char *) lfirst(lc2)) == 0)
					break;
			}
			if (lc2 == NULL)
				break;			/* found nonconflicting name */

			sprintf(nbuf, "%d", i);

			/* Ensure generated names are shorter than NAMEDATALEN */
			nlen = pg_mbcliplen(origname, strlen(origname),
								NAMEDATALEN - 1 - strlen(nbuf));
			memcpy(buf, origname, nlen);
			strcpy(buf + nlen, nbuf);
			curname = buf;
		}

		/* And attach to the result list */
		result = lappend(result, pstrdup(curname));
	}
	return result;
}

/*
 * ReindexIndex
 *		Recreate a specific index.
 */
Oid
ReindexIndex(RangeVar *indexRelation)
{
	Oid			indOid;
	Oid			heapOid = InvalidOid;

	/* lock level used here should match index lock reindex_index() */
	indOid = RangeVarGetRelidExtended(indexRelation, AccessExclusiveLock,
									  false, false,
									  RangeVarCallbackForReindexIndex,
									  (void *) &heapOid);

	reindex_index(indOid, false);

	return indOid;
}

/*
 * Check permissions on table before acquiring relation lock; also lock
 * the heap before the RangeVarGetRelidExtended takes the index lock, to avoid
 * deadlocks.
 */
static void
RangeVarCallbackForReindexIndex(const RangeVar *relation,
								Oid relId, Oid oldRelId, void *arg)
{
	char		relkind;
	Oid		   *heapOid = (Oid *) arg;

	/*
	 * If we previously locked some other index's heap, and the name we're
	 * looking up no longer refers to that relation, release the now-useless
	 * lock.
	 */
	if (relId != oldRelId && OidIsValid(oldRelId))
	{
		/* lock level here should match reindex_index() heap lock */
		UnlockRelationOid(*heapOid, ShareLock);
		*heapOid = InvalidOid;
	}

	/* If the relation does not exist, there's nothing more to do. */
	if (!OidIsValid(relId))
		return;

	/*
	 * If the relation does exist, check whether it's an index.  But note that
	 * the relation might have been dropped between the time we did the name
	 * lookup and now.	In that case, there's nothing to do.
	 */
	relkind = get_rel_relkind(relId);
	if (!relkind)
		return;
	if (relkind != RELKIND_INDEX)
		ereport(ERROR,
				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
				 errmsg("\"%s\" is not an index", relation->relname)));

	/* Check permissions */
	if (!pg_class_ownercheck(relId, GetUserId()))
		aclcheck_error(ACLCHECK_NOT_OWNER, ACL_KIND_CLASS, relation->relname);

	/* Lock heap before index to avoid deadlock. */
	if (relId != oldRelId)
	{
		/*
		 * Lock level here should match reindex_index() heap lock. If the OID
		 * isn't valid, it means the index as concurrently dropped, which is
		 * not a problem for us; just return normally.
		 */
		*heapOid = IndexGetRelation(relId, true);
		if (OidIsValid(*heapOid))
			LockRelationOid(*heapOid, ShareLock);
	}
}

/*
 * ReindexTable
 *		Recreate all indexes of a table (and of its toast table, if any)
 */
Oid
ReindexTable(RangeVar *relation)
{
	Oid			heapOid;

	/* The lock level used here should match reindex_relation(). */
	heapOid = RangeVarGetRelidExtended(relation, ShareLock, false, false,
									   RangeVarCallbackOwnsTable, NULL);

	if (!reindex_relation(heapOid, REINDEX_REL_PROCESS_TOAST))
		ereport(NOTICE,
				(errmsg("table \"%s\" has no indexes",
						relation->relname)));

	return heapOid;
}

/*
 * ReindexDatabase
 *		Recreate indexes of a database.
 *
 * To reduce the probability of deadlocks, each table is reindexed in a
 * separate transaction, so we can release the lock on it right away.
 * That means this must not be called within a user transaction block!
 */
Oid
ReindexDatabase(const char *databaseName, bool do_system, bool do_user)
{
	Relation	relationRelation;
	HeapScanDesc scan;
	HeapTuple	tuple;
	MemoryContext private_context;
	MemoryContext old;
	List	   *relids = NIL;
	ListCell   *l;

	AssertArg(databaseName);

	if (strcmp(databaseName, get_database_name(MyDatabaseId)) != 0)
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("can only reindex the currently open database")));

	if (!pg_database_ownercheck(MyDatabaseId, GetUserId()))
		aclcheck_error(ACLCHECK_NOT_OWNER, ACL_KIND_DATABASE,
					   databaseName);

	/*
	 * Create a memory context that will survive forced transaction commits we
	 * do below.  Since it is a child of PortalContext, it will go away
	 * eventually even if we suffer an error; there's no need for special
	 * abort cleanup logic.
	 */
	private_context = AllocSetContextCreate(PortalContext,
											"ReindexDatabase",
											ALLOCSET_DEFAULT_MINSIZE,
											ALLOCSET_DEFAULT_INITSIZE,
											ALLOCSET_DEFAULT_MAXSIZE);

	/*
	 * We always want to reindex pg_class first.  This ensures that if there
	 * is any corruption in pg_class' indexes, they will be fixed before we
	 * process any other tables.  This is critical because reindexing itself
	 * will try to update pg_class.
	 */
	if (do_system)
	{
		old = MemoryContextSwitchTo(private_context);
		relids = lappend_oid(relids, RelationRelationId);
		MemoryContextSwitchTo(old);
	}

	/*
	 * Scan pg_class to build a list of the relations we need to reindex.
	 *
	 * We only consider plain relations here (toast rels will be processed
	 * indirectly by reindex_relation).
	 */
	relationRelation = heap_open(RelationRelationId, AccessShareLock);
	scan = heap_beginscan(relationRelation, SnapshotNow, 0, NULL);
	while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
	{
		Form_pg_class classtuple = (Form_pg_class) GETSTRUCT(tuple);

		if (classtuple->relkind != RELKIND_RELATION)
			continue;

		/* Skip temp tables of other backends; we can't reindex them at all */
		if (classtuple->relpersistence == RELPERSISTENCE_TEMP &&
			!isTempNamespace(classtuple->relnamespace))
			continue;

		/* Check user/system classification, and optionally skip */
		if (IsSystemClass(classtuple))
		{
			if (!do_system)
				continue;
		}
		else
		{
			if (!do_user)
				continue;
		}

		if (HeapTupleGetOid(tuple) == RelationRelationId)
			continue;			/* got it already */

		old = MemoryContextSwitchTo(private_context);
		relids = lappend_oid(relids, HeapTupleGetOid(tuple));
		MemoryContextSwitchTo(old);
	}
	heap_endscan(scan);
	heap_close(relationRelation, AccessShareLock);

	/* Now reindex each rel in a separate transaction */
	PopActiveSnapshot();
	CommitTransactionCommand();
	foreach(l, relids)
	{
		Oid			relid = lfirst_oid(l);

		StartTransactionCommand();
		/* functions in indexes may want a snapshot set */
		PushActiveSnapshot(GetTransactionSnapshot());
		if (reindex_relation(relid, REINDEX_REL_PROCESS_TOAST))
			ereport(NOTICE,
					(errmsg("table \"%s.%s\" was reindexed",
							get_namespace_name(get_rel_namespace(relid)),
							get_rel_name(relid))));
		PopActiveSnapshot();
		CommitTransactionCommand();
	}
	StartTransactionCommand();

	MemoryContextDelete(private_context);

	return MyDatabaseId;
}