/*
* btrescan() -- rescan an index relation
*/
Datum
btrescan(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanKey scankey = (ScanKey) PG_GETARG_POINTER(1);
/* remaining arguments are ignored */
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
BTScanPosInvalidate(so->currPos);
}
so->markItemIndex = -1;
BTScanPosUnpinIfPinned(so->markPos);
BTScanPosInvalidate(so->markPos);
/*
* Allocate tuple workspace arrays, if needed for an index-only scan and
* not already done in a previous rescan call. To save on palloc
* overhead, both workspaces are allocated as one palloc block; only this
* function and btendscan know that.
*
* NOTE: this data structure also makes it safe to return data from a
* "name" column, even though btree name_ops uses an underlying storage
* datatype of cstring. The risk there is that "name" is supposed to be
* padded to NAMEDATALEN, but the actual index tuple is probably shorter.
* However, since we only return data out of tuples sitting in the
* currTuples array, a fetch of NAMEDATALEN bytes can at worst pull some
* data out of the markTuples array --- running off the end of memory for
* a SIGSEGV is not possible. Yeah, this is ugly as sin, but it beats
* adding special-case treatment for name_ops elsewhere.
*/
if (scan->xs_want_itup && so->currTuples == NULL)
{
so->currTuples = (char *) palloc(BLCKSZ * 2);
so->markTuples = so->currTuples + BLCKSZ;
}
/*
* Reset the scan keys. Note that keys ordering stuff moved to _bt_first.
* - vadim 05/05/97
*/
if (scankey && scan->numberOfKeys > 0)
memmove(scan->keyData,
scankey,
scan->numberOfKeys * sizeof(ScanKeyData));
so->numberOfKeys = 0; /* until _bt_preprocess_keys sets it */
/* If any keys are SK_SEARCHARRAY type, set up array-key info */
_bt_preprocess_array_keys(scan);
PG_RETURN_VOID();
}
/*
* btmarkpos() -- save current scan position
*/
void
btmarkpos(IndexScanDesc scan)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* There may be an old mark with a pin (but no lock). */
BTScanPosUnpinIfPinned(so->markPos);
/*
* Just record the current itemIndex. If we later step to next page
* before releasing the marked position, _bt_steppage makes a full copy of
* the currPos struct in markPos. If (as often happens) the mark is moved
* before we leave the page, we don't have to do that work.
*/
if (BTScanPosIsValid(so->currPos))
so->markItemIndex = so->currPos.itemIndex;
else
{
BTScanPosInvalidate(so->markPos);
so->markItemIndex = -1;
}
/* Also record the current positions of any array keys */
if (so->numArrayKeys)
_bt_mark_array_keys(scan);
}
/*
* btbeginscan() -- start a scan on a btree index
*/
Datum
btbeginscan(PG_FUNCTION_ARGS)
{
Relation rel = (Relation) PG_GETARG_POINTER(0);
int nkeys = PG_GETARG_INT32(1);
int norderbys = PG_GETARG_INT32(2);
IndexScanDesc scan;
BTScanOpaque so;
/* no order by operators allowed */
Assert(norderbys == 0);
/* get the scan */
scan = RelationGetIndexScan(rel, nkeys, norderbys);
/* allocate private___ workspace */
so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
BTScanPosInvalidate(so->currPos);
BTScanPosInvalidate(so->markPos);
if (scan->numberOfKeys > 0)
so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
else
so->keyData = NULL;
so->arrayKeyData = NULL; /* assume no array keys for now */
so->numArrayKeys = 0;
so->arrayKeys = NULL;
so->arrayContext = NULL;
so->killedItems = NULL; /* until needed */
so->numKilled = 0;
/*
* We don't know yet whether the scan will be index-only, so we do not
* allocate the tuple workspace arrays until btrescan. However, we set up
* scan->xs_itupdesc whether we'll need it or not, since that's so cheap.
*/
so->currTuples = so->markTuples = NULL;
scan->xs_itupdesc = RelationGetDescr(rel);
scan->opaque = so;
PG_RETURN_POINTER(scan);
}
/*
* btrestrpos() -- restore scan to last saved position
*/
void
btrestrpos(IndexScanDesc scan)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* Restore the marked positions of any array keys */
if (so->numArrayKeys)
_bt_restore_array_keys(scan);
if (so->markItemIndex >= 0)
{
/*
* The scan has never moved to a new page since the last mark. Just
* restore the itemIndex.
*
* NB: In this case we can't count on anything in so->markPos to be
* accurate.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else
{
/*
* The scan moved to a new page after last mark or restore, and we are
* now restoring to the marked page. We aren't holding any read
* locks, but if we're still holding the pin for the current position,
* we must drop it.
*/
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
if (BTScanPosIsPinned(so->markPos))
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
if (so->currTuples)
memcpy(so->currTuples, so->markTuples,
so->markPos.nextTupleOffset);
}
else
BTScanPosInvalidate(so->currPos);
}
}
/*
* btrestrpos() -- restore scan to last saved position
*/
Datum
btrestrpos(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* Restore the marked positions of any array keys */
if (so->numArrayKeys)
_bt_restore_array_keys(scan);
if (so->markItemIndex >= 0)
{
/*
* The scan has never moved to a new___ page since the last mark. Just
* restore the itemIndex.
*
* NB: In this case we can't count on anything in so->markPos to be
* accurate.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else if (so->currPos.currPage == so->markPos.currPage)
{
/*
* so->markItemIndex < 0 but mark and current positions are on the
* same page. This would be an unusual case, where the scan moved to
* a new___ index page after the mark, restored, and later restored again
* without moving off the marked page. It is not clear that this code
* can currently be reached, but it seems better to make this function
* robust for this case than to Assert() or elog() that it can't
* happen.
*
* We neither want to set so->markItemIndex >= 0 (because that could
* cause a later move to a new___ page to redo the memcpy() executions)
* nor re-execute the memcpy() functions for a restore within the same
* page. The previous restore to this page already set everything
* except markPos as it should be.
*/
so->currPos.itemIndex = so->markPos.itemIndex;
}
else
{
/*
* The scan moved to a new___ page after last mark or restore, and we are
* now restoring to the marked page. We aren't holding any read
* locks, but if we're still holding the pin for the current position,
* we must drop it.
*/
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
if (BTScanPosIsPinned(so->markPos))
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
if (so->currTuples)
memcpy(so->currTuples, so->markTuples,
so->markPos.nextTupleOffset);
}
else
BTScanPosInvalidate(so->currPos);
}
PG_RETURN_VOID();
}
