From bd59aa0b3a629b16c3253e4270972f697d77bbc3 Mon Sep 17 00:00:00 2001 From: Tatsuo Ishii Date: Mon, 26 Jun 2023 17:05:35 +0900 Subject: [PATCH v2 4/7] Row pattern recognition patch (executor). --- src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++- src/backend/utils/adt/windowfuncs.c | 302 ++++++++++++++++++++++++++- src/include/catalog/pg_proc.dat | 9 + src/include/nodes/execnodes.h | 13 ++ src/include/windowapi.h | 9 + 5 files changed, 548 insertions(+), 10 deletions(-) diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c index 310ac23e3a..bef2bc62b2 100644 --- a/src/backend/executor/nodeWindowAgg.c +++ b/src/backend/executor/nodeWindowAgg.c @@ -48,6 +48,7 @@ #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 +160,14 @@ typedef struct WindowStatePerAggData bool restart; /* need to restart this agg in this cycle? */ } WindowStatePerAggData; +/* + * Map between Var attno in a target list and the parsed attno. + */ +typedef struct AttnoMap { + List *attno; /* att number in target list (list of AttNumber) */ + List *attnosyn; /* parsed att number (list of AttNumber) */ +} AttnoMap; + static void initialize_windowaggregate(WindowAggState *winstate, WindowStatePerFunc perfuncstate, WindowStatePerAgg peraggstate); @@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype); static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1, TupleTableSlot *slot2); -static bool window_gettupleslot(WindowObject winobj, int64 pos, - TupleTableSlot *slot); +static void attno_map(Node *node, AttnoMap *map); +static bool attno_map_walker(Node *node, void *context); /* * initialize_windowaggregate @@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) TupleDesc scanDesc; ListCell *l; + TargetEntry *te; + Expr *expr; + Var *var; + int nargs; + AttnoMap attnomap; + /* check for unsupported flags */ Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK))); @@ -2483,6 +2498,16 @@ 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 @@ -2667,6 +2692,71 @@ 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 */ + + /* + * Collect mapping between varattno and varattnosyn in the targetlist. + * XXX: For now we only check RPR's argument. Eventually we have to + * recurse the targetlist to find out all mappings in Var nodes. + */ + attnomap.attno = NIL; + attnomap.attnosyn = NIL; + + foreach (l, node->plan.targetlist) + { + te = lfirst(l); + if (IsA(te->expr, WindowFunc)) + { + WindowFunc *func = (WindowFunc *)te->expr; + if (func->winfnoid != F_RPR) + continue; + + /* sanity check */ + nargs = list_length(func->args); + if (list_length(func->args) != 1) + elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs); + + expr = (Expr *) lfirst(list_head(func->args)); + if (!IsA(expr, Var)) + elog(ERROR, "RPR's arg is not Var"); + + var = (Var *)expr; + elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d", + te->resname, var->varattno, var->varattnosyn); + attnomap.attno = lappend_int(attnomap.attno, var->varattno); + attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn); + } + } + + winstate->defineVariableList = NIL; + winstate->defineClauseList = NIL; + if (node->defineClause != NIL) + { + foreach(l, node->defineClause) + { + char *name; + ExprState *exps; + + te = lfirst(l); + name = te->resname; + expr = te->expr; + + elog(DEBUG1, "defineVariable name: %s", name); + winstate->defineVariableList = lappend(winstate->defineVariableList, + makeString(pstrdup(name))); + /* tweak expr so that it referes to outer slot */ + attno_map((Node *)expr, &attnomap); + exps = ExecInitExpr(expr, (PlanState *) winstate); + winstate->defineClauseList = lappend(winstate->defineClauseList, exps); + } + } + winstate->all_first = true; winstate->partition_spooled = false; winstate->more_partitions = false; @@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags) return winstate; } +/* + * Rewrite Var node's varattno to the varattno which is used in the target + * list using AttnoMap. We also rewrite varno so that it sees outer tuple + * (PREV) or inner tuple (NEXT). + */ +static void +attno_map(Node *node, AttnoMap *map) +{ + (void) expression_tree_walker(node, attno_map_walker, (void *) map); +} + +static bool +attno_map_walker(Node *node, void *context) +{ + FuncExpr *func; + int nargs; + Expr *expr; + Var *var; + AttnoMap *attnomap; + ListCell *lc1, *lc2; + + if (node == NULL) + return false; + + attnomap = (AttnoMap *) context; + + if (IsA(node, FuncExpr)) + { + func = (FuncExpr *)node; + + if (func->funcid == F_PREV || func->funcid == F_NEXT) + { + /* sanity check */ + 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); + + expr = (Expr *) lfirst(list_head(func->args)); + if (!IsA(expr, Var)) + elog(ERROR, "PREV/NEXT's arg is not Var"); /* XXX: is it possible that arg type is Const? */ + var = (Var *)expr; + + if (func->funcid == F_PREV) + var->varno = OUTER_VAR; + else + var->varno = INNER_VAR; + } + return expression_tree_walker(node, attno_map_walker, (void *) context); + } + else if (IsA(node, Var)) + { + var = (Var *)node; + + elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno); + + forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn) + { + int attno = lfirst_int(lc1); + int attnosyn = lfirst_int(lc2); + + if (var->varattno == attnosyn) + { + elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno); + var->varattno = attno; + } + } + } + return expression_tree_walker(node, attno_map_walker, (void *) context); +} + /* ----------------- * ExecEndWindowAgg * ----------------- @@ -2691,6 +2851,8 @@ ExecEndWindowAgg(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) @@ -2740,6 +2902,8 @@ 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) @@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1, * * Returns true if successful, false if no such row */ -static bool +bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot) { WindowAggState *winstate = winobj->winstate; @@ -3420,14 +3584,53 @@ 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) + */ +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; + + Assert(WindowObjectIsValid(winobj)); + winstate = winobj->winstate; + switch (seektype) { case WINDOW_SEEK_CURRENT: @@ -3583,15 +3786,13 @@ 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; } /* @@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull) return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno), econtext, isnull); } + +WindowAggState * +WinGetAggState(WindowObject winobj) +{ + return winobj->winstate; +} diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c index b87a624fb2..74ef11ce55 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/supportnodes.h" #include "utils/builtins.h" #include "windowapi.h" @@ -36,10 +39,21 @@ 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); - +static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos); +static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate, + int relpos, char *vname, char *quantifier, bool *result); /* * utility routine for *_rank functions. @@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS) PG_RETURN_DATUM(result); } + +/* + * rpr + * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in + * the target list. + * Usage: SELECT rpr(colname) OVER (..) + * where colname is defined in PATTERN clause. + */ +Datum +window_rpr(PG_FUNCTION_ARGS) +{ +#define MAX_PATTERNS 16 /* max variables in PATTERN clause */ + + WindowObject winobj = PG_WINDOW_OBJECT(); + WindowAggState *winstate = WinGetAggState(winobj); + Datum result; + bool expression_result; + bool isnull; + int relpos; + int64 curr_pos, markpos; + ListCell *lc, *lc1; + SkipContext *context = NULL; + + curr_pos = WinGetCurrentPosition(winobj); + elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos); + + if (winstate->rpSkipTo == ST_PAST_LAST_ROW) + { + context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext)); + if (curr_pos < context->pos) + { + elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT, + curr_pos, context->pos); + PG_RETURN_NULL(); + } + } + + /* + * Evaluate PATTERN until one of expressions is not true or out of frame. + */ + relpos = 0; + + forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList) + { + char *vname = strVal(lfirst(lc)); + char *quantifier = strVal(lfirst(lc1)); + + elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier); + + /* evaluate row pattern against current row */ + relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result); + + /* + * If the expression did not match, we are done. + */ + if (!expression_result) + break; + + /* out of frame? */ + if (relpos < 0) + break; + + /* count up relative row position */ + relpos++; + } + + elog(DEBUG1, "relpos: %d", relpos); + + /* + * If current row satified the pattern, return argument expression. + */ + if (expression_result) + { + result = WinGetFuncArgInFrame(winobj, 0, + 0, WINDOW_SEEK_HEAD, false, + &isnull, NULL); + } + + /* + * At this point we can set mark down to current pos -2. + */ + markpos = curr_pos -2; + elog(DEBUG1, "markpos: " INT64_FORMAT, markpos); + if (markpos >= 0) + WinSetMarkPosition(winobj, markpos); + + if (expression_result) + { + if (winstate->rpSkipTo == ST_PAST_LAST_ROW) + { + context->pos += relpos; + elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos); + } + PG_RETURN_DATUM(result); + } + + PG_RETURN_NULL(); +} + +/* + * Evaluate expression associated with PATTERN variable vname. + * relpos is relative row position in a frame (starting from 0). + * "quantifier" is the quatifier part of the PATTERN regular expression. + * Currently only '+' is allowed. + * result is out paramater representing the expression evaluation result + * is true of false. + * Return values are: + * >=0: the last match relative row position + * -1: current row is out of frame + */ +static +int evaluate_pattern(WindowObject winobj, WindowAggState *winstate, + int relpos, char *vname, char *quantifier, bool *result) +{ + ExprContext *econtext = winstate->ss.ps.ps_ExprContext; + ListCell *lc1, *lc2; + ExprState *pat; + Datum eval_result; + int sts; + bool out_of_frame = false; + bool isnull; + StringInfo encoded_str = makeStringInfo(); + char pattern_str[128]; + + forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList) + { + char *name = strVal(lfirst(lc1)); + bool second_try_match = false; + + if (strcmp(vname, name)) + continue; + + /* set expression to evaluate */ + pat = lfirst(lc2); + + for (;;) + { + if (!get_slots(winobj, winstate, relpos)) + { + out_of_frame = true; + break; /* current row is out of frame */ + } + + /* evaluate the expression */ + eval_result = ExecEvalExpr(pat, econtext, &isnull); + if (isnull) + { + /* expression is NULL */ + elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos); + break; + } + else + { + if (!DatumGetBool(eval_result)) + { + /* expression is false */ + elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos); + break; + } + else + { + /* expression is true */ + elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos); + appendStringInfoChar(encoded_str, vname[0]); + + /* If quantifier is "+", we need to look for more matching row */ + if (quantifier && !strcmp(quantifier, "+")) + { + /* remember that we want to try another row */ + second_try_match = true; + relpos++; + } + else + break; + } + } + } + if (second_try_match) + relpos--; + + if (out_of_frame) + { + *result = false; + return -1; + } + + /* build regular expression */ + snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier); + + /* + * Do regular expression matching against sequence of rows satisfying + * the expression using regexp_instr(). + */ + sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID, + PointerGetDatum(cstring_to_text(encoded_str->data)), + PointerGetDatum(cstring_to_text(pattern_str)))); + elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s", + sts, encoded_str->data, pattern_str); + *result = (sts > 0)? true : false; + } + return relpos; +} + +/* + * Get current, previous and next tuple. + * Returns true if still within frame. + */ +static bool +get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos) +{ + TupleTableSlot *slot; + bool isnull, isout; + int sts; + ExprContext *econtext; + + econtext = winstate->ss.ps.ps_ExprContext; + + /* for current row */ + slot = winstate->temp_slot_1; + sts = WinGetSlotInFrame(winobj, slot, + current_pos, WINDOW_SEEK_HEAD, false, + &isnull, &isout); + if (sts < 0) + { + elog(DEBUG1, "current row is out of frame"); + econtext->ecxt_scantuple = winstate->null_slot; + return false; + } + else + econtext->ecxt_scantuple = slot; + + /* for PREV */ + if (current_pos > 0) + { + slot = winstate->prev_slot; + sts = WinGetSlotInFrame(winobj, slot, + current_pos - 1, WINDOW_SEEK_HEAD, false, + &isnull, &isout); + if (sts < 0) + { + elog(DEBUG1, "previous row out of frame at: %d", current_pos); + econtext->ecxt_outertuple = winstate->null_slot; + } + econtext->ecxt_outertuple = slot; + } + else + econtext->ecxt_outertuple = winstate->null_slot; + + /* for NEXT */ + slot = winstate->next_slot; + sts = WinGetSlotInFrame(winobj, slot, + current_pos + 1, WINDOW_SEEK_HEAD, false, + &isnull, &isout); + if (sts < 0) + { + elog(DEBUG1, "next row out of frame at: %d", current_pos); + econtext->ecxt_innertuple = winstate->null_slot; + } + else + econtext->ecxt_innertuple = slot; + + return true; +} + +/* + * 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 6996073989..e3a9e0ffeb 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10397,6 +10397,15 @@ { oid => '3114', descr => 'fetch the Nth row value', proname => 'nth_value', prokind => 'w', prorettype => 'anyelement', proargtypes => 'anyelement int4', prosrc => 'window_nth_value' }, +{ oid => '6122', descr => 'row pattern recognition in window', + proname => 'rpr', prokind => 'w', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_rpr' }, +{ oid => '6123', descr => 'previous value', + proname => 'prev', provolatile => 's', prorettype => 'anyelement', + proargtypes => 'anyelement', prosrc => 'window_prev' }, +{ oid => '6124', 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 cb714f4a19..1643eaa6f1 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -2519,6 +2519,14 @@ 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 */ + MemoryContext partcontext; /* context for partition-lifespan data */ MemoryContext aggcontext; /* shared context for aggregate working data */ MemoryContext curaggcontext; /* current aggregate's working data */ @@ -2555,6 +2563,11 @@ 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 */ } WindowAggState; /* ---------------- diff --git a/src/include/windowapi.h b/src/include/windowapi.h index b8c2c565d1..a0facf38fe 100644 --- a/src/include/windowapi.h +++ b/src/include/windowapi.h @@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno, int relpos, int seektype, bool set_mark, bool *isnull, bool *isout); +extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot, + int relpos, int seektype, bool set_mark, + bool *isnull, bool *isout); + extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull); +extern WindowAggState *WinGetAggState(WindowObject winobj); + +extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot); + + #endif /* WINDOWAPI_H */ -- 2.25.1