public inbox for [email protected]help / color / mirror / Atom feed
[PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions 2+ messages / 2 participants [nested] [flat]
* [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions @ 2021-03-02 18:27 Tomas Vondra <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Tomas Vondra @ 2021-03-02 18:27 UTC (permalink / raw) The handling of IS [NOT] NULL clauses is independent of an opclass, and most of the code was exactly the same in both minmax and inclusion. So instead move the code from support procedures to the AM methods etc. This simplifies the code quite a bit - especially the support procedures quite a bit, as they don't need to care about NULL values and flags at all. It also means the IS [NOT] NULL clauses can be evaluated without invoking the support procedure at all. Author: Tomas Vondra <[email protected]> Author: Nikita Glukhov <[email protected]> Reviewed-by: Alvaro Herrera <[email protected]> Reviewed-by: Mark Dilger <[email protected]> Reviewed-by: Alexander Korotkov <[email protected]> Reviewed-by: Masahiko Sawada <[email protected]> Reviewed-by: John Naylor <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/access/brin/brin.c | 293 +++++++++++++++++------ src/backend/access/brin/brin_inclusion.c | 96 +------- src/backend/access/brin/brin_minmax.c | 93 +------ src/include/access/brin_internal.h | 3 + 4 files changed, 244 insertions(+), 241 deletions(-) diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c index 963b7079cf..9f2656b8d9 100644 --- a/src/backend/access/brin/brin.c +++ b/src/backend/access/brin/brin.c @@ -35,6 +35,7 @@ #include "storage/freespace.h" #include "utils/acl.h" #include "utils/builtins.h" +#include "utils/datum.h" #include "utils/index_selfuncs.h" #include "utils/memutils.h" #include "utils/rel.h" @@ -77,7 +78,9 @@ static void form_and_insert_tuple(BrinBuildState *state); static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b); static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy); - +static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc, + BrinMemTuple *dtup, Datum *values, bool *nulls); +static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys); /* * BRIN handler function: return IndexAmRoutine with access method parameters @@ -179,7 +182,6 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, OffsetNumber off; BrinTuple *brtup; BrinMemTuple *dtup; - int keyno; CHECK_FOR_INTERRUPTS(); @@ -243,31 +245,7 @@ brininsert(Relation idxRel, Datum *values, bool *nulls, dtup = brin_deform_tuple(bdesc, brtup, NULL); - /* - * Compare the key values of the new tuple to the stored index values; - * our deformed tuple will get updated if the new tuple doesn't fit - * the original range (note this means we can't break out of the loop - * early). Make a note of whether this happens, so that we know to - * insert the modified tuple later. - */ - for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) - { - Datum result; - BrinValues *bval; - FmgrInfo *addValue; - - bval = &dtup->bt_columns[keyno]; - addValue = index_getprocinfo(idxRel, keyno + 1, - BRIN_PROCNUM_ADDVALUE); - result = FunctionCall4Coll(addValue, - idxRel->rd_indcollation[keyno], - PointerGetDatum(bdesc), - PointerGetDatum(bval), - values[keyno], - nulls[keyno]); - /* if that returned true, we need to insert the updated tuple */ - need_insert |= DatumGetBool(result); - } + need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls); if (!need_insert) { @@ -390,8 +368,10 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinMemTuple *dtup; BrinTuple *btup = NULL; Size btupsz = 0; - ScanKey **keys; - int *nkeys; + ScanKey **keys, + **nullkeys; + int *nkeys, + *nnullkeys; int keyno; opaque = (BrinOpaque *) scan->opaque; @@ -419,13 +399,18 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) * consistent support procedure. We allocate space for all attributes, so * that we don't have to bother determining which attributes are used. * + * We keep null and regular keys separate, so that we can pass just the + * regular keys to the consistent function easily. + * * XXX The widest table can have ~1600 attributes, so this may allocate a * couple kilobytes of memory). We could invent a more compact approach * (with just space for used attributes) but that would make the matching * more complicated, so it may not be a win. */ keys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); + nullkeys = palloc0(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts); nkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); + nnullkeys = palloc0(sizeof(int) * bdesc->bd_tupdesc->natts); /* * Preprocess the scan keys - split them into per-attribute arrays. @@ -445,23 +430,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) TupleDescAttr(bdesc->bd_tupdesc, keyattno - 1)->attcollation)); - /* First time we see this index attribute, so init as needed. */ - if (!keys[keyattno - 1]) + /* + * First time we see this index attribute, so init as needed. + * + * This is a bit of an overkill - we don't know how many scan keys are + * there for a given attribute, so we simply allocate the largest + * number possible (as if all scan keys belonged to the same + * attribute). This may waste a bit of memory, but we only expect + * small number of scan keys in general, so this should be negligible, + * and it's probably cheaper than having to repalloc repeatedly. + */ + if (consistentFn[keyattno - 1].fn_oid == InvalidOid) { FmgrInfo *tmp; - /* - * This is a bit of an overkill - we don't know how many scan keys - * are there for this attribute, so we simply allocate the largest - * number possible. This may waste a bit of memory, but we only - * expect small number of scan keys in general, so this should be - * negligible, and it's cheaper than having to repalloc - * repeatedly. - */ - keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); - - /* First time this column, so look up consistent function */ - Assert(consistentFn[keyattno - 1].fn_oid == InvalidOid); + /* No key/null arrays for this attribute. */ + Assert((keys[keyattno - 1] == NULL) && (nkeys[keyattno - 1] == 0)); + Assert((nullkeys[keyattno - 1] == NULL) && (nnullkeys[keyattno - 1] == 0)); tmp = index_getprocinfo(idxRel, keyattno, BRIN_PROCNUM_CONSISTENT); @@ -469,9 +454,23 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) CurrentMemoryContext); } - /* Add key to the per-attribute array. */ - keys[keyattno - 1][nkeys[keyattno - 1]] = key; - nkeys[keyattno - 1]++; + /* Add key to the proper per-attribute array. */ + if (key->sk_flags & SK_ISNULL) + { + if (!nullkeys[keyattno - 1]) + nullkeys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key; + nnullkeys[keyattno - 1]++; + } + else + { + if (!keys[keyattno - 1]) + keys[keyattno - 1] = palloc0(sizeof(ScanKey) * scan->numberOfKeys); + + keys[keyattno - 1][nkeys[keyattno - 1]] = key; + nkeys[keyattno - 1]++; + } } /* allocate an initial in-memory tuple, out of the per-range memcxt */ @@ -549,15 +548,58 @@ bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm) BrinValues *bval; Datum add; - /* skip attributes without any san keys */ - if (nkeys[attno - 1] == 0) + /* + * skip attributes without any scan keys (both regular and + * IS [NOT] NULL) + */ + if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0) continue; bval = &dtup->bt_columns[attno - 1]; + /* + * First check if there are any IS [NOT] NULL scan keys, + * and if we're violating them. In that case we can + * terminate early, without invoking the support function. + * + * As there may be more keys, we can only detemine + * mismatch within this loop. + */ + if (bdesc->bd_info[attno - 1]->oi_regular_nulls && + !check_null_keys(bval, nullkeys[attno - 1], + nnullkeys[attno - 1])) + { + /* + * If any of the IS [NOT] NULL keys failed, the page + * range as a whole can't pass. So terminate the loop. + */ + addrange = false; + break; + } + + /* + * So either there are no IS [NOT] NULL keys, or all + * passed. If there are no regular scan keys, we're done - + * the page range matches. If there are regular keys, but + * the page range is marked as 'all nulls' it can't + * possibly pass (we're assuming the operators are + * strict). + */ + + /* No regular scan keys - page range as a whole passes. */ + if (!nkeys[attno - 1]) + continue; + Assert((nkeys[attno - 1] > 0) && (nkeys[attno - 1] <= scan->numberOfKeys)); + /* If it is all nulls, it cannot possibly be consistent. */ + if (bval->bv_allnulls) + { + addrange = false; + break; + } + /* * Check whether the scan key is consistent with the page * range values; if so, have the pages in the range added @@ -703,7 +745,6 @@ brinbuildCallback(Relation index, { BrinBuildState *state = (BrinBuildState *) brstate; BlockNumber thisblock; - int i; thisblock = ItemPointerGetBlockNumber(tid); @@ -732,25 +773,8 @@ brinbuildCallback(Relation index, } /* Accumulate the current tuple into the running state */ - for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++) - { - FmgrInfo *addValue; - BrinValues *col; - Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i); - - col = &state->bs_dtuple->bt_columns[i]; - addValue = index_getprocinfo(index, i + 1, - BRIN_PROCNUM_ADDVALUE); - - /* - * Update dtuple state, if and as necessary. - */ - FunctionCall4Coll(addValue, - attr->attcollation, - PointerGetDatum(state->bs_bdesc), - PointerGetDatum(col), - values[i], isnull[i]); - } + (void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple, + values, isnull); } /* @@ -1529,6 +1553,39 @@ union_tuples(BrinDesc *bdesc, BrinMemTuple *a, BrinTuple *b) FmgrInfo *unionFn; BrinValues *col_a = &a->bt_columns[keyno]; BrinValues *col_b = &db->bt_columns[keyno]; + BrinOpcInfo *opcinfo = bdesc->bd_info[keyno]; + + if (opcinfo->oi_regular_nulls) + { + /* Adjust "hasnulls". */ + if (!col_a->bv_hasnulls && col_b->bv_hasnulls) + col_a->bv_hasnulls = true; + + /* If there are no values in B, there's nothing left to do. */ + if (col_b->bv_allnulls) + continue; + + /* + * Adjust "allnulls". If A doesn't have values, just copy the + * values from B into A, and we're done. We cannot run the + * operators in this case, because values in A might contain + * garbage. Note we already established that B contains values. + */ + if (col_a->bv_allnulls) + { + int i; + + col_a->bv_allnulls = false; + + for (i = 0; i < opcinfo->oi_nstored; i++) + col_a->bv_values[i] = + datumCopy(col_b->bv_values[i], + opcinfo->oi_typcache[i]->typbyval, + opcinfo->oi_typcache[i]->typlen); + + continue; + } + } unionFn = index_getprocinfo(bdesc->bd_index, keyno + 1, BRIN_PROCNUM_UNION); @@ -1582,3 +1639,103 @@ brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy) */ FreeSpaceMapVacuum(idxrel); } + +static bool +add_values_to_range(Relation idxRel, BrinDesc *bdesc, BrinMemTuple *dtup, + Datum *values, bool *nulls) +{ + int keyno; + bool modified = false; + + /* + * Compare the key values of the new tuple to the stored index values; our + * deformed tuple will get updated if the new tuple doesn't fit the + * original range (note this means we can't break out of the loop early). + * Make a note of whether this happens, so that we know to insert the + * modified tuple later. + */ + for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++) + { + Datum result; + BrinValues *bval; + FmgrInfo *addValue; + + bval = &dtup->bt_columns[keyno]; + + if (bdesc->bd_info[keyno]->oi_regular_nulls && nulls[keyno]) + { + /* + * If the new value is null, we record that we saw it if it's the + * first one; otherwise, there's nothing to do. + */ + if (!bval->bv_hasnulls) + { + bval->bv_hasnulls = true; + modified = true; + } + + continue; + } + + addValue = index_getprocinfo(idxRel, keyno + 1, + BRIN_PROCNUM_ADDVALUE); + result = FunctionCall4Coll(addValue, + idxRel->rd_indcollation[keyno], + PointerGetDatum(bdesc), + PointerGetDatum(bval), + values[keyno], + nulls[keyno]); + /* if that returned true, we need to insert the updated tuple */ + modified |= DatumGetBool(result); + } + + return modified; +} + +static bool +check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys) +{ + int keyno; + + /* + * First check if there are any IS [NOT] NULL scan keys, and if we're + * violating them. + */ + for (keyno = 0; keyno < nnullkeys; keyno++) + { + ScanKey key = nullkeys[keyno]; + + Assert(key->sk_attno == bval->bv_attno); + + /* Handle only IS NULL/IS NOT NULL tests */ + if (!(key->sk_flags & SK_ISNULL)) + continue; + + if (key->sk_flags & SK_SEARCHNULL) + { + /* IS NULL scan key, but range has no NULLs */ + if (!bval->bv_allnulls && !bval->bv_hasnulls) + return false; + } + else if (key->sk_flags & SK_SEARCHNOTNULL) + { + /* + * For IS NOT NULL, we can only skip ranges that are known to have + * only nulls. + */ + if (bval->bv_allnulls) + return false; + } + else + { + /* + * Neither IS NULL nor IS NOT NULL was used; assume all indexable + * operators are strict and thus return false with NULL value in + * the scan key. + */ + return false; + } + } + + return true; +} diff --git a/src/backend/access/brin/brin_inclusion.c b/src/backend/access/brin/brin_inclusion.c index a260074c91..b17077703c 100644 --- a/src/backend/access/brin/brin_inclusion.c +++ b/src/backend/access/brin/brin_inclusion.c @@ -110,6 +110,7 @@ brin_inclusion_opcinfo(PG_FUNCTION_ARGS) */ result = palloc0(MAXALIGN(SizeofBrinOpcInfo(3)) + sizeof(InclusionOpaque)); result->oi_nstored = 3; + result->oi_regular_nulls = true; result->oi_opaque = (InclusionOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(3)); @@ -141,7 +142,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_BOOL(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_BOOL(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *finfo; Datum result; @@ -149,18 +150,7 @@ brin_inclusion_add_value(PG_FUNCTION_ARGS) AttrNumber attno; Form_pg_attribute attr; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -268,52 +258,9 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* Handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -331,9 +278,8 @@ brin_inclusion_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* Skip IS NULL/IS NOT NULL keys (already handled above). */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -574,37 +520,11 @@ brin_inclusion_union(PG_FUNCTION_ARGS) Datum result; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls". */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do. */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[INCLUSION_UNION] = - datumCopy(col_b->bv_values[INCLUSION_UNION], - attr->attbyval, attr->attlen); - col_a->bv_values[INCLUSION_UNMERGEABLE] = - col_b->bv_values[INCLUSION_UNMERGEABLE]; - col_a->bv_values[INCLUSION_CONTAINS_EMPTY] = - col_b->bv_values[INCLUSION_CONTAINS_EMPTY]; - PG_RETURN_VOID(); - } - /* If B includes empty elements, mark A similarly, if needed. */ if (!DatumGetBool(col_a->bv_values[INCLUSION_CONTAINS_EMPTY]) && DatumGetBool(col_b->bv_values[INCLUSION_CONTAINS_EMPTY])) diff --git a/src/backend/access/brin/brin_minmax.c b/src/backend/access/brin/brin_minmax.c index e116084a02..330bed0487 100644 --- a/src/backend/access/brin/brin_minmax.c +++ b/src/backend/access/brin/brin_minmax.c @@ -48,6 +48,7 @@ brin_minmax_opcinfo(PG_FUNCTION_ARGS) result = palloc0(MAXALIGN(SizeofBrinOpcInfo(2)) + sizeof(MinmaxOpaque)); result->oi_nstored = 2; + result->oi_regular_nulls = true; result->oi_opaque = (MinmaxOpaque *) MAXALIGN((char *) result + SizeofBrinOpcInfo(2)); result->oi_typcache[0] = result->oi_typcache[1] = @@ -69,7 +70,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) BrinDesc *bdesc = (BrinDesc *) PG_GETARG_POINTER(0); BrinValues *column = (BrinValues *) PG_GETARG_POINTER(1); Datum newval = PG_GETARG_DATUM(2); - bool isnull = PG_GETARG_DATUM(3); + bool isnull PG_USED_FOR_ASSERTS_ONLY = PG_GETARG_DATUM(3); Oid colloid = PG_GET_COLLATION(); FmgrInfo *cmpFn; Datum compar; @@ -77,18 +78,7 @@ brin_minmax_add_value(PG_FUNCTION_ARGS) Form_pg_attribute attr; AttrNumber attno; - /* - * If the new value is null, we record that we saw it if it's the first - * one; otherwise, there's nothing to do. - */ - if (isnull) - { - if (column->bv_hasnulls) - PG_RETURN_BOOL(false); - - column->bv_hasnulls = true; - PG_RETURN_BOOL(true); - } + Assert(!isnull); attno = column->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); @@ -156,52 +146,9 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) int nkeys = PG_GETARG_INT32(3); Oid colloid = PG_GET_COLLATION(); int keyno; - bool has_regular_keys = false; - - /* handle IS NULL/IS NOT NULL tests */ - for (keyno = 0; keyno < nkeys; keyno++) - { - ScanKey key = keys[keyno]; - - Assert(key->sk_attno == column->bv_attno); - - /* Skip regular scan keys (and remember that we have some). */ - if ((!key->sk_flags & SK_ISNULL)) - { - has_regular_keys = true; - continue; - } - if (key->sk_flags & SK_SEARCHNULL) - { - if (column->bv_allnulls || column->bv_hasnulls) - continue; /* this key is fine, continue */ - - PG_RETURN_BOOL(false); - } - - /* - * For IS NOT NULL, we can only skip ranges that are known to have - * only nulls. - */ - if (key->sk_flags & SK_SEARCHNOTNULL) - { - if (column->bv_allnulls) - PG_RETURN_BOOL(false); - - continue; - } - - /* - * Neither IS NULL nor IS NOT NULL was used; assume all indexable - * operators are strict and return false. - */ - PG_RETURN_BOOL(false); - } - - /* If there are no regular keys, the page range is considered consistent. */ - if (!has_regular_keys) - PG_RETURN_BOOL(true); + /* make sure we got some scan keys */ + Assert((nkeys > 0) && (keys != NULL)); /* * If is all nulls, it cannot possibly be consistent (at this point we @@ -215,9 +162,8 @@ brin_minmax_consistent(PG_FUNCTION_ARGS) { ScanKey key = keys[keyno]; - /* ignore IS NULL/IS NOT NULL tests handled above */ - if (key->sk_flags & SK_ISNULL) - continue; + /* NULL keys are handled and filtered-out in bringetbitmap */ + Assert(!(key->sk_flags & SK_ISNULL)); /* * When there are multiple scan keys, failure to meet the criteria for @@ -307,34 +253,11 @@ brin_minmax_union(PG_FUNCTION_ARGS) bool needsadj; Assert(col_a->bv_attno == col_b->bv_attno); - - /* Adjust "hasnulls" */ - if (!col_a->bv_hasnulls && col_b->bv_hasnulls) - col_a->bv_hasnulls = true; - - /* If there are no values in B, there's nothing left to do */ - if (col_b->bv_allnulls) - PG_RETURN_VOID(); + Assert(!col_a->bv_allnulls && !col_b->bv_allnulls); attno = col_a->bv_attno; attr = TupleDescAttr(bdesc->bd_tupdesc, attno - 1); - /* - * Adjust "allnulls". If A doesn't have values, just copy the values from - * B into A, and we're done. We cannot run the operators in this case, - * because values in A might contain garbage. Note we already established - * that B contains values. - */ - if (col_a->bv_allnulls) - { - col_a->bv_allnulls = false; - col_a->bv_values[0] = datumCopy(col_b->bv_values[0], - attr->attbyval, attr->attlen); - col_a->bv_values[1] = datumCopy(col_b->bv_values[1], - attr->attbyval, attr->attlen); - PG_RETURN_VOID(); - } - /* Adjust minimum, if B's min is less than A's min */ finfo = minmax_get_strategy_procinfo(bdesc, attno, attr->atttypid, BTLessStrategyNumber); diff --git a/src/include/access/brin_internal.h b/src/include/access/brin_internal.h index 78c89a6961..79440ebe7b 100644 --- a/src/include/access/brin_internal.h +++ b/src/include/access/brin_internal.h @@ -27,6 +27,9 @@ typedef struct BrinOpcInfo /* Number of columns stored in an index column of this opclass */ uint16 oi_nstored; + /* Regular processing of NULLs in BrinValues? */ + bool oi_regular_nulls; + /* Opaque pointer for the opclass' private use */ void *oi_opaque; -- 2.26.2 --------------6A37408A2C42B5B56C3B3D49 Content-Type: text/x-patch; charset=UTF-8; name="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-Optimize-allocations-in-bringetbitmap-20210303.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
* [PATCH v23 5/8] Row pattern recognition patch (executor). @ 2024-10-25 03:56 Tatsuo Ishii <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Tatsuo Ishii @ 2024-10-25 03:56 UTC (permalink / raw) --- src/backend/executor/nodeWindowAgg.c | 1676 +++++++++++++++++++++++++- src/backend/utils/adt/windowfuncs.c | 37 +- src/include/catalog/pg_proc.dat | 6 + src/include/nodes/execnodes.h | 30 + 4 files changed, 1738 insertions(+), 11 deletions(-) diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c index 51a6708a39..e6f4fc1a7a 100644 --- a/src/backend/executor/nodeWindowAgg.c +++ b/src/backend/executor/nodeWindowAgg.c @@ -36,6 +36,7 @@ #include "access/htup_details.h" #include "catalog/objectaccess.h" #include "catalog/pg_aggregate.h" +#include "catalog/pg_collation_d.h" #include "catalog/pg_proc.h" #include "executor/executor.h" #include "executor/nodeWindowAgg.h" @@ -48,6 +49,7 @@ #include "utils/acl.h" #include "utils/builtins.h" #include "utils/datum.h" +#include "utils/fmgroids.h" #include "utils/expandeddatum.h" #include "utils/lsyscache.h" #include "utils/memutils.h" @@ -159,6 +161,53 @@ typedef struct WindowStatePerAggData bool restart; /* need to restart this agg in this cycle? */ } WindowStatePerAggData; +/* + * Set of StringInfo. Used in RPR. + */ +typedef struct StringSet +{ + StringInfo *str_set; + Size set_size; /* current array allocation size in number of + * items */ + int set_index; /* current used size */ +} StringSet; + +/* + * Allowed subsequent PATTERN variables positions. + * Used in RPR. + * + * pos represents the pattern variable defined order in DEFINE caluase. For + * example. "DEFINE START..., UP..., DOWN ..." and "PATTERN START UP DOWN UP" + * will create: + * VariablePos[0].pos[0] = 0; START + * VariablePos[1].pos[0] = 1; UP + * VariablePos[1].pos[1] = 3; UP + * VariablePos[2].pos[0] = 2; DOWN + * + * Note that UP has two pos because UP appears in PATTERN twice. + * + * By using this strucrture, we can know which pattern variable can be followed + * by which pattern variable(s). For example, START can be followed by UP and + * DOWN since START's pos is 0, and UP's pos is 1 or 3, DOWN's pos is 2. + * DOWN can be followed by UP since UP's pos is either 1 or 3. + * + */ + +/* + * Structure used by check_rpr_navigation() and rpr_navigation_walker(). + */ +typedef struct NavigationInfo +{ + bool is_prev; /* true if PREV */ + int num_vars; /* number of var nodes */ +} NavigationInfo; + +#define NUM_ALPHABETS 26 /* we allow [a-z] variable initials */ +typedef struct VariablePos +{ + int pos[NUM_ALPHABETS]; /* postion(s) in PATTERN */ +} VariablePos; + static void initialize_windowaggregate(WindowAggState *winstate, WindowStatePerFunc perfuncstate, WindowStatePerAgg peraggstate); @@ -184,6 +233,7 @@ static void release_partition(WindowAggState *winstate); static int row_is_in_frame(WindowAggState *winstate, int64 pos, TupleTableSlot *slot); + static void update_frameheadpos(WindowAggState *winstate); static void update_frametailpos(WindowAggState *winstate); static void update_grouptailpos(WindowAggState *winstate); @@ -195,9 +245,51 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype); static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1, TupleTableSlot *slot2); + +static int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout); static bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot); +static void attno_map(Node *node); +static bool attno_map_walker(Node *node, void *context); +static int row_is_in_reduced_frame(WindowObject winobj, int64 pos); +static bool rpr_is_defined(WindowAggState *winstate); + +static void create_reduced_frame_map(WindowAggState *winstate); +static int get_reduced_frame_map(WindowAggState *winstate, int64 pos); +static void register_reduced_frame_map(WindowAggState *winstate, int64 pos, + int val); +static void clear_reduced_frame_map(WindowAggState *winstate); +static void update_reduced_frame(WindowObject winobj, int64 pos); + +static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result); + +static bool get_slots(WindowObject winobj, int64 current_pos); + +static int search_str_set(char *pattern, StringSet * str_set, + VariablePos * variable_pos); +static char pattern_initial(WindowAggState *winstate, char *vname); +static int do_pattern_match(char *pattern, char *encoded_str); + +static StringSet * string_set_init(void); +static void string_set_add(StringSet * string_set, StringInfo str); +static StringInfo string_set_get(StringSet * string_set, int index); +static int string_set_get_size(StringSet * string_set); +static void string_set_discard(StringSet * string_set); +static VariablePos * variable_pos_init(void); +static void variable_pos_register(VariablePos * variable_pos, char initial, + int pos); +static bool variable_pos_compare(VariablePos * variable_pos, + char initial1, char initial2); +static int variable_pos_fetch(VariablePos * variable_pos, char initial, + int index); +static void variable_pos_discard(VariablePos * variable_pos); + +static void check_rpr_navigation(Node *node, bool is_prev); +static bool rpr_navigation_walker(Node *node, void *context); /* * initialize_windowaggregate @@ -774,10 +866,12 @@ eval_windowaggregates(WindowAggState *winstate) * transition function, or * - we have an EXCLUSION clause, or * - if the new frame doesn't overlap the old one + * - if RPR is enabled * * Note that we don't strictly need to restart in the last case, but if * we're going to remove all rows from the aggregation anyway, a restart * surely is faster. + * we restart aggregation too. *---------- */ numaggs_restart = 0; @@ -788,7 +882,8 @@ eval_windowaggregates(WindowAggState *winstate) (winstate->aggregatedbase != winstate->frameheadpos && !OidIsValid(peraggstate->invtransfn_oid)) || (winstate->frameOptions & FRAMEOPTION_EXCLUSION) || - winstate->aggregatedupto <= winstate->frameheadpos) + winstate->aggregatedupto <= winstate->frameheadpos || + rpr_is_defined(winstate)) { peraggstate->restart = true; numaggs_restart++; @@ -862,7 +957,22 @@ eval_windowaggregates(WindowAggState *winstate) * head, so that tuplestore can discard unnecessary rows. */ if (agg_winobj->markptr >= 0) - WinSetMarkPosition(agg_winobj, winstate->frameheadpos); + { + int64 markpos = winstate->frameheadpos; + + if (rpr_is_defined(winstate)) + { + /* + * If RPR is used, it is possible PREV wants to look at the + * previous row. So the mark pos should be frameheadpos - 1 + * unless it is below 0. + */ + markpos -= 1; + if (markpos < 0) + markpos = 0; + } + WinSetMarkPosition(agg_winobj, markpos); + } /* * Now restart the aggregates that require it. @@ -917,6 +1027,14 @@ eval_windowaggregates(WindowAggState *winstate) { winstate->aggregatedupto = winstate->frameheadpos; ExecClearTuple(agg_row_slot); + + /* + * If RPR is defined, we do not use aggregatedupto_nonrestarted. To + * avoid assertion failure below, we reset aggregatedupto_nonrestarted + * to frameheadpos. + */ + if (rpr_is_defined(winstate)) + aggregatedupto_nonrestarted = winstate->frameheadpos; } /* @@ -930,6 +1048,12 @@ eval_windowaggregates(WindowAggState *winstate) { int ret; +#ifdef RPR_DEBUG + elog(DEBUG1, "===== loop in frame starts: aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + /* Fetch next row if we didn't already */ if (TupIsNull(agg_row_slot)) { @@ -945,9 +1069,53 @@ eval_windowaggregates(WindowAggState *winstate) ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot); if (ret < 0) break; + if (ret == 0) goto next_tuple; + if (rpr_is_defined(winstate)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "reduced_frame_map: %d aggregatedupto: " INT64_FORMAT " aggregatedbase: " INT64_FORMAT, + get_reduced_frame_map(winstate, + winstate->aggregatedupto), + winstate->aggregatedupto, + winstate->aggregatedbase); +#endif + + /* + * If the row status at currentpos is already decided and current + * row status is not decided yet, it means we passed the last + * reduced frame. Time to break the loop. + */ + if (get_reduced_frame_map(winstate, + winstate->currentpos) != RF_NOT_DETERMINED && + get_reduced_frame_map(winstate, + winstate->aggregatedupto) == RF_NOT_DETERMINED) + break; + + /* + * Otherwise we need to calculate the reduced frame. + */ + ret = row_is_in_reduced_frame(winstate->agg_winobj, + winstate->aggregatedupto); + if (ret == -1) /* unmatched row */ + break; + + /* + * Check if current row needs to be skipped due to no match. + */ + if (get_reduced_frame_map(winstate, + winstate->aggregatedupto) == RF_SKIPPED && + winstate->aggregatedupto == winstate->aggregatedbase) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "skip current row for aggregation"); +#endif + break; + } + } + /* Set tuple context for evaluation of aggregate arguments */ winstate->tmpcontext->ecxt_outertuple = agg_row_slot; @@ -976,6 +1144,7 @@ next_tuple: ExecClearTuple(agg_row_slot); } + /* The frame's end is not supposed to move backwards, ever */ Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto); @@ -1199,6 +1368,7 @@ begin_partition(WindowAggState *winstate) winstate->framehead_valid = false; winstate->frametail_valid = false; winstate->grouptail_valid = false; + create_reduced_frame_map(winstate); winstate->spooled_rows = 0; winstate->currentpos = 0; winstate->frameheadpos = 0; @@ -2170,6 +2340,11 @@ ExecWindowAgg(PlanState *pstate) CHECK_FOR_INTERRUPTS(); +#ifdef RPR_DEBUG + elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT, + winstate->currentpos); +#endif + if (winstate->status == WINDOWAGG_DONE) return NULL; @@ -2278,6 +2453,17 @@ ExecWindowAgg(PlanState *pstate) /* don't evaluate the window functions when we're in pass-through mode */ if (winstate->status == WINDOWAGG_RUN) { + /* + * If RPR is defined and skip mode is next row, we need to clear + * existing reduced frame info so that we newly calculate the info + * starting from current row. + */ + if (rpr_is_defined(winstate)) + { + if (winstate->rpSkipTo == ST_NEXT_ROW) + clear_reduced_frame_map(winstate); + } + /* * Evaluate true window functions */ @@ -2445,6 +2631,9 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) TupleDesc scanDesc; ListCell *l; + TargetEntry *te; + Expr *expr; + /* check for unsupported flags */ Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK))); @@ -2543,6 +2732,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc, &TTSOpsMinimalTuple); + winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + + winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc, + &TTSOpsMinimalTuple); + winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot); + /* * create frame head and tail slots only if needed (must create slots in * exactly the same cases that update_frameheadpos and update_frametailpos @@ -2724,6 +2923,43 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) winstate->inRangeAsc = node->inRangeAsc; winstate->inRangeNullsFirst = node->inRangeNullsFirst; + /* Set up SKIP TO type */ + winstate->rpSkipTo = node->rpSkipTo; + /* Set up row pattern recognition PATTERN clause */ + winstate->patternVariableList = node->patternVariable; + winstate->patternRegexpList = node->patternRegexp; + + /* Set up row pattern recognition DEFINE clause */ + winstate->defineInitial = node->defineInitial; + winstate->defineVariableList = NIL; + winstate->defineClauseList = NIL; + if (node->defineClause != NIL) + { + /* + * Tweak arg var of PREV/NEXT so that it refers to scan/inner slot. + */ + foreach(l, node->defineClause) + { + char *name; + ExprState *exps; + + te = lfirst(l); + name = te->resname; + expr = te->expr; + +#ifdef RPR_DEBUG + elog(DEBUG1, "defineVariable name: %s", name); +#endif + winstate->defineVariableList = + lappend(winstate->defineVariableList, + makeString(pstrdup(name))); + attno_map((Node *) expr); + exps = ExecInitExpr(expr, (PlanState *) winstate); + winstate->defineClauseList = + lappend(winstate->defineClauseList, exps); + } + } + winstate->all_first = true; winstate->partition_spooled = false; winstate->more_partitions = false; @@ -2732,6 +2968,111 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) return winstate; } +/* + * Rewrite varno of Var nodes that are the argument of PREV/NET so that they + * see scan tuple (PREV) or inner tuple (NEXT). Also we check the arguments + * of PREV/NEXT include at least 1 column reference. This is required by the + * SQL standard. + */ +static void +attno_map(Node *node) +{ + (void) expression_tree_walker(node, attno_map_walker, NULL); +} + +static bool +attno_map_walker(Node *node, void *context) +{ + FuncExpr *func; + int nargs; + bool is_prev; + + if (node == NULL) + return false; + + if (IsA(node, FuncExpr)) + { + func = (FuncExpr *) node; + + if (func->funcid == F_PREV || func->funcid == F_NEXT) + { + /* + * The SQL standard allows to have two more arguments form of + * PREV/NEXT. But currently we allow only 1 argument form. + */ + nargs = list_length(func->args); + if (list_length(func->args) != 1) + elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", + func->funcid, nargs); + + /* + * Check expr of PREV/NEXT aruguments and replace varno. + */ + is_prev = (func->funcid == F_PREV) ? true : false; + check_rpr_navigation(node, is_prev); + } + } + return expression_tree_walker(node, attno_map_walker, NULL); +} + +/* + * Rewrite varno of Var of RPR navigation operations (PREV/NEXT). + * If is_prev is true, we take care PREV, otherwise NEXT. + */ +static void +check_rpr_navigation(Node *node, bool is_prev) +{ + NavigationInfo context; + + context.is_prev = is_prev; + context.num_vars = 0; + (void) expression_tree_walker(node, rpr_navigation_walker, &context); + if (context.num_vars < 1) + ereport(ERROR, + errmsg("row pattern navigation operation's argument must include at least one column reference")); +} + +static bool +rpr_navigation_walker(Node *node, void *context) +{ + NavigationInfo *nav = (NavigationInfo *) context; + + if (node == NULL) + return false; + + switch (nodeTag(node)) + { + case T_Var: + { + Var *var = (Var *) node; + + nav->num_vars++; + + if (nav->is_prev) + { + /* + * Rewrite varno from OUTER_VAR to regular var no so that + * the var references scan tuple. + */ + var->varno = var->varnosyn; + } + else + var->varno = INNER_VAR; + } + break; + case T_Const: + case T_FuncExpr: + case T_OpExpr: + break; + + default: + ereport(ERROR, + errmsg("row pattern navigation operation's argument includes unsupported expression")); + } + return expression_tree_walker(node, rpr_navigation_walker, context); +} + + /* ----------------- * ExecEndWindowAgg * ----------------- @@ -2789,6 +3130,8 @@ ExecReScanWindowAgg(WindowAggState *node) ExecClearTuple(node->agg_row_slot); ExecClearTuple(node->temp_slot_1); ExecClearTuple(node->temp_slot_2); + ExecClearTuple(node->prev_slot); + ExecClearTuple(node->next_slot); if (node->framehead_slot) ExecClearTuple(node->framehead_slot); if (node->frametail_slot) @@ -3149,7 +3492,8 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot) return false; if (pos < winobj->markpos) - elog(ERROR, "cannot fetch row before WindowObject's mark position"); + elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT, + pos, winobj->markpos); oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory); @@ -3469,14 +3813,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, WindowAggState *winstate; ExprContext *econtext; TupleTableSlot *slot; - int64 abs_pos; - int64 mark_pos; Assert(WindowObjectIsValid(winobj)); winstate = winobj->winstate; econtext = winstate->ss.ps.ps_ExprContext; slot = winstate->temp_slot_1; + if (WinGetSlotInFrame(winobj, slot, + relpos, seektype, set_mark, + isnull, isout) == 0) + { + econtext->ecxt_outertuple = slot; + return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), + econtext, isnull); + } + + if (isout) + *isout = true; + *isnull = true; + return (Datum) 0; +} + +/* + * WinGetSlotInFrame + * slot: TupleTableSlot to store the result + * relpos: signed rowcount offset from the seek position + * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL + * set_mark: If the row is found/in frame and set_mark is true, the mark is + * moved to the row as a side-effect. + * isnull: output argument, receives isnull status of result + * isout: output argument, set to indicate whether target row position + * is out of frame (can pass NULL if caller doesn't care about this) + * + * Returns 0 if we successfullt got the slot. false if out of frame. + * (also isout is set) + */ +static int +WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout) +{ + WindowAggState *winstate; + int64 abs_pos; + int64 mark_pos; + int num_reduced_frame; + + Assert(WindowObjectIsValid(winobj)); + winstate = winobj->winstate; + switch (seektype) { case WINDOW_SEEK_CURRENT: @@ -3543,11 +3927,25 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, winstate->frameOptions); break; } + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + if (relpos >= num_reduced_frame) + goto out_of_frame; break; case WINDOW_SEEK_TAIL: /* rejecting relpos > 0 is easy and simplifies code below */ if (relpos > 0) goto out_of_frame; + + /* + * RPR cares about frame head pos. Need to call + * update_frameheadpos + */ + update_frameheadpos(winstate); + update_frametailpos(winstate); abs_pos = winstate->frametailpos - 1 + relpos; @@ -3614,6 +4012,14 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, mark_pos = 0; /* keep compiler quiet */ break; } + + num_reduced_frame = row_is_in_reduced_frame(winobj, + winstate->frameheadpos + relpos); + if (num_reduced_frame < 0) + goto out_of_frame; + else if (num_reduced_frame > 0) + abs_pos = winstate->frameheadpos + relpos + + num_reduced_frame - 1; break; default: elog(ERROR, "unrecognized window seek type: %d", seektype); @@ -3632,15 +4038,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno, *isout = false; if (set_mark) WinSetMarkPosition(winobj, mark_pos); - econtext->ecxt_outertuple = slot; - return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), - econtext, isnull); + return 0; out_of_frame: if (isout) *isout = true; *isnull = true; - return (Datum) 0; + return -1; } /* @@ -3671,3 +4075,1257 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull) return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), econtext, isnull); } + +/* + * rpr_is_defined + * return true if Row pattern recognition is defined. + */ +static +bool +rpr_is_defined(WindowAggState *winstate) +{ + return winstate->patternVariableList != NIL; +} + +/* + * ----------------- + * row_is_in_reduced_frame + * Determine whether a row is in the current row's reduced window frame + * according to row pattern matching + * + * The row must has been already determined that it is in a full window frame + * and fetched it into slot. + * + * Returns: + * = 0, RPR is not defined. + * >0, if the row is the first in the reduced frame. Return the number of rows + * in the reduced frame. + * -1, if the row is unmatched row + * -2, if the row is in the reduced frame but needed to be skipped because of + * AFTER MATCH SKIP PAST LAST ROW + * ----------------- + */ +static +int +row_is_in_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + int state; + int rtn; + + if (!rpr_is_defined(winstate)) + { + /* + * RPR is not defined. Assume that we are always in the the reduced + * window frame. + */ + rtn = 0; +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; + } + + state = get_reduced_frame_map(winstate, pos); + + if (state == RF_NOT_DETERMINED) + { + update_frameheadpos(winstate); + update_reduced_frame(winobj, pos); + } + + state = get_reduced_frame_map(winstate, pos); + + switch (state) + { + int64 i; + int num_reduced_rows; + + case RF_FRAME_HEAD: + num_reduced_rows = 1; + for (i = pos + 1; + get_reduced_frame_map(winstate, i) == RF_SKIPPED; i++) + num_reduced_rows++; + rtn = num_reduced_rows; + break; + + case RF_SKIPPED: + rtn = -2; + break; + + case RF_UNMATCHED: + rtn = -1; + break; + + default: + elog(ERROR, "Unrecognized state: %d at: " INT64_FORMAT, + state, pos); + break; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "row_is_in_reduced_frame returns %d: pos: " INT64_FORMAT, + rtn, pos); +#endif + return rtn; +} + +#define REDUCED_FRAME_MAP_INIT_SIZE 1024L + +/* + * create_reduced_frame_map + * Create reduced frame map + */ +static +void +create_reduced_frame_map(WindowAggState *winstate) +{ + winstate->reduced_frame_map = + MemoryContextAlloc(winstate->partcontext, + REDUCED_FRAME_MAP_INIT_SIZE); + winstate->alloc_sz = REDUCED_FRAME_MAP_INIT_SIZE; + clear_reduced_frame_map(winstate); +} + +/* + * clear_reduced_frame_map + * Clear reduced frame map + */ +static +void +clear_reduced_frame_map(WindowAggState *winstate) +{ + Assert(winstate->reduced_frame_map != NULL); + MemSet(winstate->reduced_frame_map, RF_NOT_DETERMINED, + winstate->alloc_sz); +} + +/* + * get_reduced_frame_map + * Get reduced frame map specified by pos + */ +static +int +get_reduced_frame_map(WindowAggState *winstate, int64 pos) +{ + Assert(winstate->reduced_frame_map != NULL); + Assert(pos >= 0); + + /* + * If pos is not in the reduced frame map, it means that any info + * regarding the pos has not been registered yet. So we return + * RF_NOT_DETERMINED. + */ + if (pos >= winstate->alloc_sz) + return RF_NOT_DETERMINED; + + return winstate->reduced_frame_map[pos]; +} + +/* + * register_reduced_frame_map + * Add/replace reduced frame map member at pos. + * If there's no enough space, expand the map. + */ +static +void +register_reduced_frame_map(WindowAggState *winstate, int64 pos, int val) +{ + int64 realloc_sz; + + Assert(winstate->reduced_frame_map != NULL); + + if (pos < 0) + elog(ERROR, "wrong pos: " INT64_FORMAT, pos); + + if (pos > winstate->alloc_sz - 1) + { + realloc_sz = winstate->alloc_sz * 2; + + winstate->reduced_frame_map = + repalloc(winstate->reduced_frame_map, realloc_sz); + + MemSet(winstate->reduced_frame_map + winstate->alloc_sz, + RF_NOT_DETERMINED, realloc_sz - winstate->alloc_sz); + + winstate->alloc_sz = realloc_sz; + } + + winstate->reduced_frame_map[pos] = val; +} + +/* + * update_reduced_frame + * Update reduced frame info. + */ +static +void +update_reduced_frame(WindowObject winobj, int64 pos) +{ + WindowAggState *winstate = winobj->winstate; + ListCell *lc1, + *lc2; + bool expression_result; + int num_matched_rows; + int64 original_pos; + bool anymatch; + StringInfo encoded_str; + StringInfo pattern_str = makeStringInfo(); + StringSet *str_set; + int initial_index; + VariablePos *variable_pos; + bool greedy = false; + int64 result_pos, + i; + + /* + * Set of pattern variables evaluated to true. Each character corresponds + * to pattern variable. Example: str_set[0] = "AB"; str_set[1] = "AC"; In + * this case at row 0 A and B are true, and A and C are true in row 1. + */ + + /* initialize pattern variables set */ + str_set = string_set_init(); + + /* save original pos */ + original_pos = pos; + + /* + * Check if the pattern does not include any greedy quantifier. If it does + * not, we can just apply the pattern to each row. If it succeeds, we are + * done. + */ + foreach(lc1, winstate->patternRegexpList) + { + char *quantifier = strVal(lfirst(lc1)); + + if (*quantifier == '+' || *quantifier == '*') + { + greedy = true; + break; + } + } + + /* + * Non greedy case + */ + if (!greedy) + { + num_matched_rows = 0; + + foreach(lc1, winstate->patternVariableList) + { + char *vname = strVal(lfirst(lc1)); + + encoded_str = makeStringInfo(); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s", + pos, vname); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + if (!expression_result || result_pos < 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is false or out of frame"); +#endif + register_reduced_frame_map(winstate, original_pos, + RF_UNMATCHED); + return; + } + /* move to next row */ + pos++; + num_matched_rows++; + } +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern matched"); +#endif + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + return; + } + + /* + * Greedy quantifiers included. Loop over until none of pattern matches or + * encounters end of frame. + */ + for (;;) + { + result_pos = -1; + + /* + * Loop over each PATTERN variable. + */ + anymatch = false; + encoded_str = makeStringInfo(); + + forboth(lc1, winstate->patternVariableList, lc2, + winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); +#ifdef RPR_DEBUG + char *quantifier = strVal(lfirst(lc2)); + + elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", + pos, vname, quantifier); +#endif + expression_result = false; + + /* evaluate row pattern against current row */ + result_pos = evaluate_pattern(winobj, pos, vname, + encoded_str, &expression_result); + if (expression_result) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "expression result is true"); +#endif + anymatch = true; + } + + /* + * If out of frame, we are done. + */ + if (result_pos < 0) + break; + } + + if (!anymatch) + { + /* none of patterns matched. */ + break; + } + + string_set_add(str_set, encoded_str); + +#ifdef RPR_DEBUG + elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", + encoded_str->data); +#endif + + /* move to next row */ + pos++; + + if (result_pos < 0) + { + /* out of frame */ + break; + } + } + + if (string_set_get_size(str_set) == 0) + { + /* no match found in the first row */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + return; + } + +#ifdef RPR_DEBUG + elog(DEBUG2, "pos: " INT64_FORMAT " encoded_str: %s", + pos, encoded_str->data); +#endif + + /* build regular expression */ + pattern_str = makeStringInfo(); + appendStringInfoChar(pattern_str, '^'); + initial_index = 0; + + variable_pos = variable_pos_init(); + + forboth(lc1, winstate->patternVariableList, + lc2, winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc1)); + char *quantifier = strVal(lfirst(lc2)); + char initial; + + initial = pattern_initial(winstate, vname); + Assert(initial != 0); + appendStringInfoChar(pattern_str, initial); + if (quantifier[0]) + appendStringInfoChar(pattern_str, quantifier[0]); + + /* + * Register the initial at initial_index. If the initial appears more + * than once, all of it's initial_index will be recorded. This could + * happen if a pattern variable appears in the PATTERN clause more + * than once like "UP DOWN UP" "UP UP UP". + */ + variable_pos_register(variable_pos, initial, initial_index); + + initial_index++; + } + +#ifdef RPR_DEBUG + elog(DEBUG2, "pos: " INT64_FORMAT " pattern: %s", + pos, pattern_str->data); +#endif + + /* look for matching pattern variable sequence */ +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set started"); +#endif + num_matched_rows = search_str_set(pattern_str->data, + str_set, variable_pos); +#ifdef RPR_DEBUG + elog(DEBUG1, "search_str_set returns: %d", num_matched_rows); +#endif + variable_pos_discard(variable_pos); + string_set_discard(str_set); + + /* + * We are at the first row in the reduced frame. Save the number of + * matched rows as the number of rows in the reduced frame. + */ + if (num_matched_rows <= 0) + { + /* no match */ + register_reduced_frame_map(winstate, original_pos, RF_UNMATCHED); + } + else + { + register_reduced_frame_map(winstate, original_pos, RF_FRAME_HEAD); + + for (i = original_pos + 1; i < original_pos + num_matched_rows; i++) + { + register_reduced_frame_map(winstate, i, RF_SKIPPED); + } + } + + return; +} + +/* + * search_str_set + * Perform pattern matching using "pattern" against str_set. pattern is a + * regular expression derived from PATTERN clause. Note that the regular + * expression string is prefixed by '^' and followed by initials represented + * in a same way as str_set. str_set is a set of StringInfo. Each StringInfo + * has a string comprising initials of pattern variable strings being true in + * a row. The initials are one of [a-y], parallel to the order of variable + * names in DEFINE clause. Suppose DEFINE has variables START, UP and DOWN. If + * PATTERN has START, UP+ and DOWN, then the initials in PATTERN will be 'a', + * 'b' and 'c'. The "pattern" will be "^ab+c". + * + * variable_pos is an array representing the order of pattern variable string + * initials in PATTERN clause. For example initial 'a' potion is in + * variable_pos[0].pos[0] = 0. Note that if the pattern is "START UP DOWN UP" + * (UP appears twice), then "UP" (initial is 'b') has two position 1 and + * 3. Thus variable_pos for b is variable_pos[1].pos[0] = 1 and + * variable_pos[1].pos[1] = 3. + * + * Returns the longest number of the matching rows (greedy matching) if + * quatifier '+' or '*' is included in "pattern". + */ +static +int +search_str_set(char *pattern, StringSet * str_set, VariablePos * variable_pos) +{ +#define MAX_CANDIDATE_NUM 10000 /* max pattern match candidate size */ +#define FREEZED_CHAR 'Z' /* a pattern is freezed if it ends with the + * char */ +#define DISCARD_CHAR 'z' /* a pattern is not need to keep */ + + int set_size; /* number of rows in the set */ + int resultlen; + int index; + StringSet *old_str_set, + *new_str_set; + int new_str_size; + int len; + + set_size = string_set_get_size(str_set); + new_str_set = string_set_init(); + len = 0; + resultlen = 0; + + /* + * Generate all possible pattern variable name initials as a set of + * StringInfo named "new_str_set". For example, if we have two rows + * having "ab" (row 0) and "ac" (row 1) in the input str_set, new_str_set + * will have set of StringInfo "aa", "ac", "ba" and "bc" in the end. + */ +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern: %s set_size: %d", pattern, set_size); +#endif + for (index = 0; index < set_size; index++) + { + StringInfo str; /* search target row */ + char *p; + int old_set_size; + int i; + +#ifdef RPR_DEBUG + elog(DEBUG1, "index: %d", index); +#endif + if (index == 0) + { + /* copy variables in row 0 */ + str = string_set_get(str_set, index); + p = str->data; + + /* + * Loop over each new pattern variable char. + */ + while (*p) + { + StringInfo new = makeStringInfo(); + + /* add pattern variable char */ + appendStringInfoChar(new, *p); + /* add new one to string set */ + string_set_add(new_str_set, new); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: NULL new_str: %s", new->data); +#endif + p++; /* next pattern variable */ + } + } + else /* index != 0 */ + { + old_str_set = new_str_set; + new_str_set = string_set_init(); + str = string_set_get(str_set, index); + old_set_size = string_set_get_size(old_str_set); + + /* + * Loop over each rows in the previous result set. + */ + for (i = 0; i < old_set_size; i++) + { + StringInfo new; + char last_old_char; + int old_str_len; + StringInfo old = string_set_get(old_str_set, i); + + p = old->data; + old_str_len = strlen(p); + if (old_str_len > 0) + last_old_char = p[old_str_len - 1]; + else + last_old_char = '\0'; + + /* Is this old set freezed? */ + if (last_old_char == FREEZED_CHAR) + { + /* if shorter match. we can discard it */ + if ((old_str_len - 1) < resultlen) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this old set because shorter match: %s", + old->data); +#endif + continue; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "keep this old set: %s", old->data); +#endif + + /* move the old set to new_str_set */ + string_set_add(new_str_set, old); + old_str_set->str_set[i] = NULL; + continue; + } + /* Can this old set be discarded? */ + else if (last_old_char == DISCARD_CHAR) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this old set: %s", old->data); +#endif + continue; + } + +#ifdef RPR_DEBUG + elog(DEBUG1, "str->data: %s", str->data); +#endif + + /* + * loop over each pattern variable initial char in the input + * set. + */ + for (p = str->data; *p; p++) + { + /* + * Optimization. Check if the row's pattern variable + * initial character position is greater than or equal to + * the old set's last pattern variable initial character + * position. For example, if the old set's last pattern + * variable initials are "ab", then the new pattern + * variable initial can be "b" or "c" but can not be "a", + * if the initials in PATTERN is something like "a b c" or + * "a b+ c+" etc. This optimization is possible when we + * only allow "+" quantifier. + */ + if (variable_pos_compare(variable_pos, last_old_char, *p)) + { + /* copy source string */ + new = makeStringInfo(); + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + /* add pattern variable char */ + appendStringInfoChar(new, *p); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: %s new_str: %s", + old->data, new->data); +#endif + + /* + * Adhoc optimization. If the first letter in the + * input string is the first and second position one + * and there's no associated quatifier '+', then we + * can dicard the input because there's no chace to + * expand the string further. + * + * For example, pattern "abc" cannot match "aa". + */ +#ifdef RPR_DEBUG + elog(DEBUG1, "pattern[1]:%c pattern[2]:%c new[0]:%c new[1]:%c", + pattern[1], pattern[2], new->data[0], new->data[1]); +#endif + if (pattern[1] == new->data[0] && + pattern[1] == new->data[1] && + pattern[2] != '+' && + pattern[1] != pattern[2]) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "discard this new data: %s", + new->data); +#endif + pfree(new->data); + pfree(new); + continue; + } + + /* add new one to string set */ + string_set_add(new_str_set, new); + } + else + { + /* + * We are freezing this pattern string. Since there's + * no chance to expand the string further, we perform + * pattern matching against the string. If it does not + * match, we can discard it. + */ + len = do_pattern_match(pattern, old->data); + + if (len <= 0) + { + /* no match. we can discard it */ + continue; + } + + else if (len <= resultlen) + { + /* shorter match. we can discard it */ + continue; + } + else + { + /* match length is the longest so far */ + + int new_index; + + /* remember the longest match */ + resultlen = len; + + /* freeze the pattern string */ + new = makeStringInfo(); + enlargeStringInfo(new, old->len + 1); + appendStringInfoString(new, old->data); + /* add freezed mark */ + appendStringInfoChar(new, FREEZED_CHAR); +#ifdef RPR_DEBUG + elog(DEBUG1, "old_str: %s new_str: %s", old->data, new->data); +#endif + string_set_add(new_str_set, new); + + /* + * Search new_str_set to find out freezed entries + * that have shorter match length. Mark them as + * "discard" so that they are discarded in the + * next round. + */ + + /* new_index_size should be the one before */ + new_str_size = + string_set_get_size(new_str_set) - 1; + + /* loop over new_str_set */ + for (new_index = 0; new_index < new_str_size; + new_index++) + { + char new_last_char; + int new_str_len; + + new = string_set_get(new_str_set, new_index); + new_str_len = strlen(new->data); + if (new_str_len > 0) + { + new_last_char = + new->data[new_str_len - 1]; + if (new_last_char == FREEZED_CHAR && + (new_str_len - 1) <= len) + { + /* + * mark this set to discard in the + * next round + */ + appendStringInfoChar(new, DISCARD_CHAR); +#ifdef RPR_DEBUG + elog(DEBUG1, "add discard char: %s", new->data); +#endif + } + } + } + } + } + } + } + /* we no longer need old string set */ + string_set_discard(old_str_set); + } + } + + /* + * Perform pattern matching to find out the longest match. + */ + new_str_size = string_set_get_size(new_str_set); +#ifdef RPR_DEBUG + elog(DEBUG1, "new_str_size: %d", new_str_size); +#endif + len = 0; + resultlen = 0; + + for (index = 0; index < new_str_size; index++) + { + StringInfo s; + + s = string_set_get(new_str_set, index); + if (s == NULL) + continue; /* no data */ + +#ifdef RPR_DEBUG + elog(DEBUG1, "target string: %s", s->data); +#endif + len = do_pattern_match(pattern, s->data); + if (len > resultlen) + { + /* remember the longest match */ + resultlen = len; + + /* + * If the size of result set is equal to the number of rows in the + * set, we are done because it's not possible that the number of + * matching rows exceeds the number of rows in the set. + */ + if (resultlen >= set_size) + break; + } + } + + /* we no longer need new string set */ + string_set_discard(new_str_set); + + return resultlen; +} + +/* + * do_pattern_match + * perform pattern match using pattern against encoded_str. + * returns matching number of rows if matching is succeeded. + * Otherwise returns 0. + */ +static +int +do_pattern_match(char *pattern, char *encoded_str) +{ + Datum d; + text *res; + char *substr; + int len = 0; + text *pattern_text, + *encoded_str_text; + + pattern_text = cstring_to_text(pattern); + encoded_str_text = cstring_to_text(encoded_str); + + /* + * We first perform pattern matching using regexp_instr, then call + * textregexsubstr to get matched substring to know how long the matched + * string is. That is the number of rows in the reduced window frame. The + * reason why we can't call textregexsubstr in the first place is, it + * errors out if pattern does not match. + */ + if (DatumGetInt32(DirectFunctionCall2Coll( + regexp_instr, DEFAULT_COLLATION_OID, + PointerGetDatum(encoded_str_text), + PointerGetDatum(pattern_text)))) + { + d = DirectFunctionCall2Coll(textregexsubstr, + DEFAULT_COLLATION_OID, + PointerGetDatum(encoded_str_text), + PointerGetDatum(pattern_text)); + if (d != 0) + { + res = DatumGetTextPP(d); + substr = text_to_cstring(res); + len = strlen(substr); + pfree(substr); + } + } + pfree(encoded_str_text); + pfree(pattern_text); + + return len; +} + +/* + * evaluate_pattern + * Evaluate expression associated with PATTERN variable vname. current_pos is + * relative row position in a frame (starting from 0). If vname is evaluated + * to true, initial letters associated with vname is appended to + * encode_str. result is out paramater representing the expression evaluation + * result is true of false. + *--------- + * Return values are: + * >=0: the last match absolute row position + * otherwise out of frame. + *--------- + */ +static +int64 +evaluate_pattern(WindowObject winobj, int64 current_pos, + char *vname, StringInfo encoded_str, bool *result) +{ + WindowAggState *winstate = winobj->winstate; + ExprContext *econtext = winstate->ss.ps.ps_ExprContext; + ListCell *lc1, + *lc2, + *lc3; + ExprState *pat; + Datum eval_result; + bool out_of_frame = false; + bool isnull; + TupleTableSlot *slot; + + forthree(lc1, winstate->defineVariableList, + lc2, winstate->defineClauseList, + lc3, winstate->defineInitial) + { + char initial; /* initial letter associated with vname */ + char *name = strVal(lfirst(lc1)); + + if (strcmp(vname, name)) + continue; + + initial = *(strVal(lfirst(lc3))); + + /* set expression to evaluate */ + pat = lfirst(lc2); + + /* get current, previous and next tuples */ + if (!get_slots(winobj, current_pos)) + { + out_of_frame = true; + } + else + { + /* evaluate the expression */ + eval_result = ExecEvalExpr(pat, econtext, &isnull); + if (isnull) + { + /* expression is NULL */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + if (!DatumGetBool(eval_result)) + { + /* expression is false */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, + vname, current_pos); +#endif + *result = false; + } + else + { + /* expression is true */ +#ifdef RPR_DEBUG + elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, + vname, current_pos); +#endif + appendStringInfoChar(encoded_str, initial); + *result = true; + } + } + + slot = winstate->temp_slot_1; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->prev_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + slot = winstate->next_slot; + if (slot != winstate->null_slot) + ExecClearTuple(slot); + + break; + } + + if (out_of_frame) + { + *result = false; + return -1; + } + } + return current_pos; +} + +/* + * get_slots + * Get current, previous and next tuples. + * Returns false if current row is out of partition/full frame. + */ +static +bool +get_slots(WindowObject winobj, int64 current_pos) +{ + WindowAggState *winstate = winobj->winstate; + TupleTableSlot *slot; + int ret; + ExprContext *econtext; + + econtext = winstate->ss.ps.ps_ExprContext; + + /* set up current row tuple slot */ + slot = winstate->temp_slot_1; + if (!window_gettupleslot(winobj, current_pos, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, + current_pos); +#endif + return false; + } + ret = row_is_in_frame(winstate, current_pos, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, + current_pos); +#endif + ExecClearTuple(slot); + return false; + } + econtext->ecxt_outertuple = slot; + + /* for PREV */ + if (current_pos > 0) + { + slot = winstate->prev_slot; + if (!window_gettupleslot(winobj, current_pos - 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, + current_pos - 1); +#endif + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos - 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, + current_pos - 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_scantuple = winstate->null_slot; + } + else + { + econtext->ecxt_scantuple = slot; + } + } + } + else + econtext->ecxt_scantuple = winstate->null_slot; + + /* for NEXT */ + slot = winstate->next_slot; + if (!window_gettupleslot(winobj, current_pos + 1, slot)) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, + current_pos + 1); +#endif + econtext->ecxt_innertuple = winstate->null_slot; + } + else + { + ret = row_is_in_frame(winstate, current_pos + 1, slot); + if (ret <= 0) + { +#ifdef RPR_DEBUG + elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, + current_pos + 1); +#endif + ExecClearTuple(slot); + econtext->ecxt_innertuple = winstate->null_slot; + } + else + econtext->ecxt_innertuple = slot; + } + return true; +} + +/* + * pattern_initial + * Return pattern variable initial character + * matching with pattern variable name vname. + * If not found, return 0. + */ +static +char +pattern_initial(WindowAggState *winstate, char *vname) +{ + char initial; + char *name; + ListCell *lc1, + *lc2; + + forboth(lc1, winstate->defineVariableList, + lc2, winstate->defineInitial) + { + name = strVal(lfirst(lc1)); /* DEFINE variable name */ + initial = *(strVal(lfirst(lc2))); /* DEFINE variable initial */ + + + if (!strcmp(name, vname)) + return initial; /* found */ + } + return 0; +} + +/* + * string_set_init + * Create dynamic set of StringInfo. + */ +static +StringSet * string_set_init(void) +{ +/* Initial allocation size of str_set */ +#define STRING_SET_ALLOC_SIZE 1024 + + StringSet *string_set; + Size set_size; + + string_set = palloc0(sizeof(StringSet)); + string_set->set_index = 0; + set_size = STRING_SET_ALLOC_SIZE; + string_set->str_set = palloc(set_size * sizeof(StringInfo)); + string_set->set_size = set_size; + + return string_set; +} + +/* + * string_set_add + * Add StringInfo str to StringSet string_set. + */ +static +void +string_set_add(StringSet * string_set, StringInfo str) +{ + Size set_size; + + set_size = string_set->set_size; + if (string_set->set_index >= set_size) + { + set_size *= 2; + string_set->str_set = repalloc(string_set->str_set, + set_size * sizeof(StringInfo)); + string_set->set_size = set_size; + } + + string_set->str_set[string_set->set_index++] = str; + + return; +} + +/* + * string_set_get + * Returns StringInfo specified by index. + * If there's no data yet, returns NULL. + */ +static +StringInfo +string_set_get(StringSet * string_set, int index) +{ + /* no data? */ + if (index == 0 && string_set->set_index == 0) + return NULL; + + if (index < 0 || index >= string_set->set_index) + elog(ERROR, "invalid index: %d", index); + + return string_set->str_set[index]; +} + +/* + * string_set_get_size + * Returns the size of StringSet. + */ +static +int +string_set_get_size(StringSet * string_set) +{ + return string_set->set_index; +} + +/* + * string_set_discard + * Discard StringSet. + * All memory including StringSet itself is freed. + */ +static +void +string_set_discard(StringSet * string_set) +{ + int i; + + for (i = 0; i < string_set->set_index; i++) + { + StringInfo str = string_set->str_set[i]; + + if (str) + { + pfree(str->data); + pfree(str); + } + } + pfree(string_set->str_set); + pfree(string_set); +} + +/* + * variable_pos_init + * Create and initialize variable postion structure + */ +static +VariablePos * variable_pos_init(void) +{ + VariablePos *variable_pos; + + variable_pos = palloc(sizeof(VariablePos) * NUM_ALPHABETS); + MemSet(variable_pos, -1, sizeof(VariablePos) * NUM_ALPHABETS); + return variable_pos; +} + +/* + * variable_pos_register + * Register pattern variable whose initial is initial into postion index. + * pos is position of initial. + * If pos is already registered, register it at next empty slot. + */ +static +void +variable_pos_register(VariablePos * variable_pos, char initial, int pos) +{ + int index = initial - 'a'; + int slot; + int i; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + for (i = 0; i < NUM_ALPHABETS; i++) + { + slot = variable_pos[index].pos[i]; + if (slot < 0) + { + /* empty slot found */ + variable_pos[index].pos[i] = pos; + return; + } + } + elog(ERROR, "no empty slot for initial: %c", initial); +} + +/* + * variable_pos_compare + * Returns true if initial1 can be followed by initial2 + */ +static +bool +variable_pos_compare(VariablePos * variable_pos, char initial1, char initial2) +{ + int index1, + index2; + int pos1, + pos2; + + for (index1 = 0;; index1++) + { + pos1 = variable_pos_fetch(variable_pos, initial1, index1); + if (pos1 < 0) + break; + + for (index2 = 0;; index2++) + { + pos2 = variable_pos_fetch(variable_pos, initial2, index2); + if (pos2 < 0) + break; + if (pos1 <= pos2) + return true; + } + } + return false; +} + +/* + * variable_pos_fetch + * Fetch position of pattern variable whose initial is initial, and whose index + * is index. If no postion was registered by initial, index, returns -1. + */ +static +int +variable_pos_fetch(VariablePos * variable_pos, char initial, int index) +{ + int pos = initial - 'a'; + + if (pos < 0 || pos > NUM_ALPHABETS) + elog(ERROR, "initial is not valid char: %c", initial); + + if (index < 0 || index > NUM_ALPHABETS) + elog(ERROR, "index is not valid: %d", index); + + return variable_pos[pos].pos[index]; +} + +/* + * variable_pos_discard + * Discard VariablePos + */ +static +void +variable_pos_discard(VariablePos * variable_pos) +{ + pfree(variable_pos); +} diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c index 473c61569f..92c528d38c 100644 --- a/src/backend/utils/adt/windowfuncs.c +++ b/src/backend/utils/adt/windowfuncs.c @@ -13,6 +13,9 @@ */ #include "postgres.h" +#include "catalog/pg_collation_d.h" +#include "executor/executor.h" +#include "nodes/execnodes.h" #include "nodes/parsenodes.h" #include "nodes/supportnodes.h" #include "utils/fmgrprotos.h" @@ -37,11 +40,19 @@ typedef struct int64 remainder; /* (total rows) % (bucket num) */ } ntile_context; +/* + * rpr process information. + * Used for AFTER MATCH SKIP PAST LAST ROW + */ +typedef struct SkipContext +{ + int64 pos; /* last row absolute position */ +} SkipContext; + static bool rank_up(WindowObject winobj); static Datum leadlag_common(FunctionCallInfo fcinfo, bool forward, bool withoffset, bool withdefault); - /* * utility routine for *_rank functions. */ @@ -674,7 +685,7 @@ window_last_value(PG_FUNCTION_ARGS) bool isnull; result = WinGetFuncArgInFrame(winobj, 0, - 0, WINDOW_SEEK_TAIL, true, + 0, WINDOW_SEEK_TAIL, false, &isnull, NULL); if (isnull) PG_RETURN_NULL(); @@ -714,3 +725,25 @@ window_nth_value(PG_FUNCTION_ARGS) PG_RETURN_DATUM(result); } + +/* + * prev + * Dummy function to invoke RPR's navigation operator "PREV". + * This is *not* a window function. + */ +Datum +window_prev(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} + +/* + * next + * Dummy function to invoke RPR's navigation operation "NEXT". + * This is *not* a window function. + */ +Datum +window_next(PG_FUNCTION_ARGS) +{ + PG_RETURN_DATUM(PG_GETARG_DATUM(0)); +} diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 1ec0d6f6b5..754e855552 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10635,6 +10635,12 @@ { oid => '3114', descr => 'fetch the Nth row value', proname => 'nth_value', prokind => 'w', prorettype => 'anyelement', proargtypes => 'anyelement int4', prosrc => 'window_nth_value' }, +{ oid => '8126', descr => 'previous value', + proname => 'prev', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_prev' }, +{ oid => '8127', descr => 'next value', + proname => 'next', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_next' }, # functions for range types { oid => '3832', descr => 'I/O', diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index e4698a28c4..9a2f8254d1 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -2589,6 +2589,11 @@ typedef enum WindowAggStatus * tuples during spool */ } WindowAggStatus; +#define RF_NOT_DETERMINED 0 +#define RF_FRAME_HEAD 1 +#define RF_SKIPPED 2 +#define RF_UNMATCHED 3 + typedef struct WindowAggState { ScanState ss; /* its first field is NodeTag */ @@ -2648,6 +2653,19 @@ typedef struct WindowAggState int64 groupheadpos; /* current row's peer group head position */ int64 grouptailpos; /* " " " " tail position (group end+1) */ + /* these fields are used in Row pattern recognition: */ + RPSkipTo rpSkipTo; /* Row Pattern Skip To type */ + List *patternVariableList; /* list of row pattern variables names + * (list of String) */ + List *patternRegexpList; /* list of row pattern regular expressions + * ('+' or ''. list of String) */ + List *defineVariableList; /* list of row pattern definition + * variables (list of String) */ + List *defineClauseList; /* expression for row pattern definition + * search conditions ExprState list */ + List *defineInitial; /* list of row pattern definition variable + * initials (list of String) */ + MemoryContext partcontext; /* context for partition-lifespan data */ MemoryContext aggcontext; /* shared context for aggregate working data */ MemoryContext curaggcontext; /* current aggregate's working data */ @@ -2675,6 +2693,18 @@ typedef struct WindowAggState TupleTableSlot *agg_row_slot; TupleTableSlot *temp_slot_1; TupleTableSlot *temp_slot_2; + + /* temporary slots for RPR */ + TupleTableSlot *prev_slot; /* PREV row navigation operator */ + TupleTableSlot *next_slot; /* NEXT row navigation operator */ + TupleTableSlot *null_slot; /* all NULL slot */ + + /* + * Each byte corresponds to a row positioned at absolute its pos in + * partition. See above definition for RF_* + */ + char *reduced_frame_map; + int64 alloc_sz; /* size of the map */ } WindowAggState; /* ---------------- -- 2.25.1 ----Next_Part(Fri_Oct_25_13_04_53_2024_648)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v23-0006-Row-pattern-recognition-patch-docs.patch" ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2024-10-25 03:56 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2021-03-02 18:27 [PATCH 2/6] Move IS [NOT] NULL handling from BRIN support functions Tomas Vondra <[email protected]> 2024-10-25 03:56 [PATCH v23 5/8] Row pattern recognition patch (executor). Tatsuo Ishii <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox