public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v15 2/8] Row pattern recognition patch (parse/analysis).
3+ messages / 2 participants
[nested] [flat]

* [PATCH v15 2/8] Row pattern recognition patch (parse/analysis).
@ 2024-03-28 10:30 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 3+ messages in thread

From: Tatsuo Ishii @ 2024-03-28 10:30 UTC (permalink / raw)

---
 src/backend/parser/parse_agg.c    |   7 +
 src/backend/parser/parse_clause.c | 296 +++++++++++++++++++++++++++++-
 src/backend/parser/parse_expr.c   |   4 +
 src/backend/parser/parse_func.c   |   3 +
 4 files changed, 309 insertions(+), 1 deletion(-)

diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c
index bee7d8346a..9bc22a836a 100644
--- a/src/backend/parser/parse_agg.c
+++ b/src/backend/parser/parse_agg.c
@@ -577,6 +577,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr)
 			errkind = true;
 			break;
 
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
+
 			/*
 			 * There is intentionally no default: case here, so that the
 			 * compiler will warn if we add a new ParseExprKind without
@@ -967,6 +971,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc,
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c
index d2ac86777c..de2e5791e3 100644
--- a/src/backend/parser/parse_clause.c
+++ b/src/backend/parser/parse_clause.c
@@ -98,7 +98,14 @@ static WindowClause *findWindowClause(List *wclist, const char *name);
 static Node *transformFrameOffset(ParseState *pstate, int frameOptions,
 								  Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc,
 								  Node *clause);
-
+static void transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+						 List **targetlist);
+static List *transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+								   List **targetlist);
+static void transformPatternClause(ParseState *pstate, WindowClause *wc,
+								   WindowDef *windef);
+static List *transformMeasureClause(ParseState *pstate, WindowClause *wc,
+									WindowDef *windef);
 
 /*
  * transformFromClause -
@@ -2948,6 +2955,10 @@ transformWindowDefinitions(ParseState *pstate,
 											 rangeopfamily, rangeopcintype,
 											 &wc->endInRangeFunc,
 											 windef->endOffset);
+
+		/* Process Row Pattern Recognition related clauses */
+		transformRPR(pstate, wc, windef, targetlist);
+
 		wc->runCondition = NIL;
 		wc->winref = winref;
 
@@ -3813,3 +3824,286 @@ transformFrameOffset(ParseState *pstate, int frameOptions,
 
 	return node;
 }
+
+/*
+ * transformRPR
+ *		Process Row Pattern Recognition related clauses
+ */
+static void
+transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+			 List **targetlist)
+{
+	/*
+	 * Window definition exists?
+	 */
+	if (windef == NULL)
+		return;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	/* Check Frame option. Frame must start at current row */
+	if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("FRAME must start at current row when row patttern recognition is used")));
+
+	/* Transform AFTER MACH SKIP TO clause */
+	wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo;
+
+	/* Transform AFTER MACH SKIP TO variable */
+	wc->rpSkipVariable = windef->rpCommonSyntax->rpSkipVariable;
+
+	/* Transform SEEK or INITIAL clause */
+	wc->initial = windef->rpCommonSyntax->initial;
+
+	/* Transform DEFINE clause into list of TargetEntry's */
+	wc->defineClause = transformDefineClause(pstate, wc, windef, targetlist);
+
+	/* Check PATTERN clause and copy to patternClause */
+	transformPatternClause(pstate, wc, windef);
+
+	/* Transform MEASURE clause */
+	transformMeasureClause(pstate, wc, windef);
+}
+
+/*
+ * transformDefineClause Process DEFINE clause and transform ResTarget into
+ *		list of TargetEntry.
+ *
+ * XXX we only support column reference in row pattern definition search
+ * condition, e.g. "price". <row pattern definition variable name>.<column
+ * reference> is not supported, e.g. "A.price".
+ */
+static List *
+transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef,
+					  List **targetlist)
+{
+	/* DEFINE variable name initials */
+	static char *defineVariableInitials = "abcdefghijklmnopqrstuvwxyz";
+
+	ListCell   *lc,
+			   *l;
+	ResTarget  *restarget,
+			   *r;
+	List	   *restargets;
+	List	   *defineClause;
+	char	   *name;
+	int			initialLen;
+	int			i;
+
+	/*
+	 * If Row Definition Common Syntax exists, DEFINE clause must exist. (the
+	 * raw parser should have already checked it.)
+	 */
+	Assert(windef->rpCommonSyntax->rpDefs != NULL);
+
+	/*
+	 * Check and add "A AS A IS TRUE" if pattern variable is missing in DEFINE
+	 * per the SQL standard.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	   *a;
+		bool		found = false;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *) lfirst(lc);
+		name = strVal(a->lexpr);
+
+		foreach(l, windef->rpCommonSyntax->rpDefs)
+		{
+			restarget = (ResTarget *) lfirst(l);
+
+			if (!strcmp(restarget->name, name))
+			{
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+		{
+			/*
+			 * "name" is missing. So create "name AS name IS TRUE" ResTarget
+			 * node and add it to the temporary list.
+			 */
+			A_Const    *n;
+
+			restarget = makeNode(ResTarget);
+			n = makeNode(A_Const);
+			n->val.boolval.type = T_Boolean;
+			n->val.boolval.boolval = true;
+			n->location = -1;
+			restarget->name = pstrdup(name);
+			restarget->indirection = NIL;
+			restarget->val = (Node *) n;
+			restarget->location = -1;
+			restargets = lappend((List *) restargets, restarget);
+		}
+	}
+
+	if (list_length(restargets) >= 1)
+	{
+		/* add missing DEFINEs */
+		windef->rpCommonSyntax->rpDefs =
+			list_concat(windef->rpCommonSyntax->rpDefs, restargets);
+		list_free(restargets);
+	}
+
+	/*
+	 * Check for duplicate row pattern definition variables.  The standard
+	 * requires that no two row pattern definition variable names shall be
+	 * equivalent.
+	 */
+	restargets = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		restarget = (ResTarget *) lfirst(lc);
+		name = restarget->name;
+
+		/*
+		 * Add DEFINE expression (Restarget->val) to the targetlist as a
+		 * TargetEntry if it does not exist yet. Planner will add the column
+		 * ref var node to the outer plan's target list later on. This makes
+		 * DEFINE expression could access the outer tuple while evaluating
+		 * PATTERN.
+		 *
+		 * XXX: adding whole expressions of DEFINE to the plan.targetlist is
+		 * not so good, because it's not necessary to evalute the expression
+		 * in the target list while running the plan. We should extract the
+		 * var nodes only then add them to the plan.targetlist.
+		 */
+		findTargetlistEntrySQL99(pstate, (Node *) restarget->val,
+								 targetlist, EXPR_KIND_RPR_DEFINE);
+
+		/*
+		 * Make sure that the row pattern definition search condition is a
+		 * boolean expression.
+		 */
+		transformWhereClause(pstate, restarget->val,
+							 EXPR_KIND_RPR_DEFINE, "DEFINE");
+
+		foreach(l, restargets)
+		{
+			char	   *n;
+
+			r = (ResTarget *) lfirst(l);
+			n = r->name;
+
+			if (!strcmp(n, name))
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("row pattern definition variable name \"%s\" appears more than once in DEFINE clause",
+								name),
+						 parser_errposition(pstate, exprLocation((Node *) r))));
+		}
+		restargets = lappend(restargets, restarget);
+	}
+	list_free(restargets);
+
+	/*
+	 * Create list of row pattern DEFINE variable name's initial. We assign
+	 * [a-z] to them (up to 26 variable names are allowed).
+	 */
+	restargets = NIL;
+	i = 0;
+	initialLen = strlen(defineVariableInitials);
+
+	foreach(lc, windef->rpCommonSyntax->rpDefs)
+	{
+		char		initial[2];
+
+		restarget = (ResTarget *) lfirst(lc);
+		name = restarget->name;
+
+		if (i >= initialLen)
+		{
+			ereport(ERROR,
+					(errcode(ERRCODE_SYNTAX_ERROR),
+					 errmsg("number of row pattern definition variable names exceeds %d",
+							initialLen),
+					 parser_errposition(pstate,
+										exprLocation((Node *) restarget))));
+		}
+		initial[0] = defineVariableInitials[i++];
+		initial[1] = '\0';
+		wc->defineInitial = lappend(wc->defineInitial,
+									makeString(pstrdup(initial)));
+	}
+
+	defineClause = transformTargetList(pstate, windef->rpCommonSyntax->rpDefs,
+									   EXPR_KIND_RPR_DEFINE);
+
+	/* mark column origins */
+	markTargetListOrigins(pstate, defineClause);
+
+	/* mark all nodes in the DEFINE clause tree with collation information */
+	assign_expr_collations(pstate, (Node *) defineClause);
+
+	return defineClause;
+}
+
+/*
+ * transformPatternClause
+ *		Process PATTERN clause and return PATTERN clause in the raw parse tree
+ */
+static void
+transformPatternClause(ParseState *pstate, WindowClause *wc,
+					   WindowDef *windef)
+{
+	ListCell   *lc;
+
+	/*
+	 * Row Pattern Common Syntax clause exists?
+	 */
+	if (windef->rpCommonSyntax == NULL)
+		return;
+
+	wc->patternVariable = NIL;
+	wc->patternRegexp = NIL;
+	foreach(lc, windef->rpCommonSyntax->rpPatterns)
+	{
+		A_Expr	   *a;
+		char	   *name;
+		char	   *regexp;
+
+		if (!IsA(lfirst(lc), A_Expr))
+			ereport(ERROR,
+					errmsg("node type is not A_Expr"));
+
+		a = (A_Expr *) lfirst(lc);
+		name = strVal(a->lexpr);
+
+		wc->patternVariable = lappend(wc->patternVariable, makeString(pstrdup(name)));
+		regexp = strVal(lfirst(list_head(a->name)));
+
+		wc->patternRegexp = lappend(wc->patternRegexp, makeString(pstrdup(regexp)));
+	}
+}
+
+/*
+ * transformMeasureClause
+ *		Process MEASURE clause
+ *	XXX MEASURE clause is not supported yet
+ */
+static List *
+transformMeasureClause(ParseState *pstate, WindowClause *wc,
+					   WindowDef *windef)
+{
+	if (windef->rowPatternMeasures == NIL)
+		return NIL;
+
+	ereport(ERROR,
+			(errcode(ERRCODE_SYNTAX_ERROR),
+			 errmsg("%s", "MEASURE clause is not supported yet"),
+			 parser_errposition(pstate, exprLocation((Node *) windef->rowPatternMeasures))));
+	return NIL;
+}
diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c
index 73c83cea4a..8b0cc608bc 100644
--- a/src/backend/parser/parse_expr.c
+++ b/src/backend/parser/parse_expr.c
@@ -578,6 +578,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref)
 		case EXPR_KIND_COPY_WHERE:
 		case EXPR_KIND_GENERATED_COLUMN:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 
@@ -1817,6 +1818,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink)
 		case EXPR_KIND_VALUES:
 		case EXPR_KIND_VALUES_SINGLE:
 		case EXPR_KIND_CYCLE_MARK:
+		case EXPR_KIND_RPR_DEFINE:
 			/* okay */
 			break;
 		case EXPR_KIND_CHECK_CONSTRAINT:
@@ -3197,6 +3199,8 @@ ParseExprKindName(ParseExprKind exprKind)
 			return "GENERATED AS";
 		case EXPR_KIND_CYCLE_MARK:
 			return "CYCLE";
+		case EXPR_KIND_RPR_DEFINE:
+			return "DEFINE";
 
 			/*
 			 * There is intentionally no default: case here, so that the
diff --git a/src/backend/parser/parse_func.c b/src/backend/parser/parse_func.c
index 0cbc950c95..ad982a7c17 100644
--- a/src/backend/parser/parse_func.c
+++ b/src/backend/parser/parse_func.c
@@ -2657,6 +2657,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location)
 		case EXPR_KIND_CYCLE_MARK:
 			errkind = true;
 			break;
+		case EXPR_KIND_RPR_DEFINE:
+			errkind = true;
+			break;
 
 			/*
 			 * There is intentionally no default: case here, so that the
-- 
2.25.1


----Next_Part(Thu_Mar_28_19_59_25_2024_076)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v15-0003-Row-pattern-recognition-patch-rewriter.patch"



^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands.
@ 2024-07-02 20:10 Joel Jacobson <[email protected]>
  2024-07-02 20:13 ` Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands. Joel Jacobson <[email protected]>
  0 siblings, 1 reply; 3+ messages in thread

From: Joel Jacobson @ 2024-07-02 20:10 UTC (permalink / raw)
  To: Dean Rasheed <[email protected]>; +Cc: Dagfinn Ilmari MannsÃ¥ker <[email protected]>; pgsql-hackers

On Tue, Jul 2, 2024, at 21:55, Joel Jacobson wrote:
> On Tue, Jul 2, 2024, at 20:53, Joel Jacobson wrote:
>> Trying to wrap my head around what could cause this.

I found the bug in the case 3 code,
and it turns out the same type of bug also exists in the case 2 code:

			case 2:
				newdig = (int) var1digits[1] * var2digits[res_ndigits - 4];

The problem here is that res_ndigits could become less than 4,
if rscale is low enough,
and then we would try to access a negative array index in var2digits.

Fix:

			case 2:
				if (res_ndigits - 4 >= 0 && res_ndigits - 4 < var2ndigits)
					newdig = (int) var1digits[1] * var2digits[res_ndigits - 4];
				else
					newdig = 0;

Another problem in the case 2 code:

				if (res_ndigits - 3 < var2ndigits)
					newdig += (int) var1digits[0] * var2digits[res_ndigits - 3];

Fix:

				if (res_ndigits - 3 >= 0 && res_ndigits - 3 < var2ndigits)
					newdig += (int) var1digits[0] * var2digits[res_ndigits - 3];

New version attached that fixes both the case 2 and case 3 code.

Regards,
Joel

Attachments:

  [application/octet-stream] v4-optimize-numeric-mul_var-small-var1-arbitrary-var2.patch (4.3K, ../../[email protected]/2-v4-optimize-numeric-mul_var-small-var1-arbitrary-var2.patch)
  download | inline diff:
From a7d421d5fcd4f6b367f266c3b005c82abff03d7c Mon Sep 17 00:00:00 2001
From: Joel Jakobsson <[email protected]>
Date: Tue, 2 Jul 2024 17:54:25 +0200
Subject: [PATCH] numeric: Simplified fast-path computation for mul_var()

---
 src/backend/utils/adt/numeric.c | 106 ++++++++++++++++++++++++++++++++
 1 file changed, 106 insertions(+)

diff --git a/src/backend/utils/adt/numeric.c b/src/backend/utils/adt/numeric.c
index 5510a203b0..e3bc29b626 100644
--- a/src/backend/utils/adt/numeric.c
+++ b/src/backend/utils/adt/numeric.c
@@ -8747,6 +8747,112 @@ mul_var(const NumericVar *var1, const NumericVar *var2, NumericVar *result,
 		return;
 	}
 
+	/*
+	 * Simplified fast-path computation, if var1 has just one or two digits.
+	 * This is significantly faster, since it avoids allocating a separate
+	 * digit array, making multiple passes over var2, and having separate
+	 * carry-propagation passes.
+	 */
+	if (var1ndigits <= 3)
+	{
+		NumericDigit *res_buf;
+
+		/* Allocate result digit array */
+		res_buf = digitbuf_alloc(res_ndigits);
+		res_buf[0] = 0;				/* spare digit for later rounding */
+		res_digits = res_buf + 1;
+
+		/*
+		 * Compute the result digits directly, in one pass, propagating the
+		 * carry up as we go.
+		 */
+		switch (var1ndigits)
+		{
+			case 1:
+				carry = 0;
+				for (i = res_ndigits - 3; i >= 0; i--)
+				{
+					newdig = (int) var1digits[0] * var2digits[i] + carry;
+					res_digits[i + 1] = (NumericDigit) (newdig % NBASE);
+					carry = newdig / NBASE;
+				}
+				res_digits[0] = (NumericDigit) carry;
+				break;
+
+			case 2:
+				if (res_ndigits - 4 >= 0 && res_ndigits - 4 < var2ndigits)
+					newdig = (int) var1digits[1] * var2digits[res_ndigits - 4];
+				else
+					newdig = 0;
+				if (res_ndigits - 3 >= 0 && res_ndigits - 3 < var2ndigits)
+					newdig += (int) var1digits[0] * var2digits[res_ndigits - 3];
+				res_digits[res_ndigits - 2] = (NumericDigit) (newdig % NBASE);
+				carry = newdig / NBASE;
+				for (i = res_ndigits - 4; i >= 1; i--)
+				{
+					newdig = (int) var1digits[0] * var2digits[i] +
+						(int) var1digits[1] * var2digits[i - 1] + carry;
+					res_digits[i + 1] = (NumericDigit) (newdig % NBASE);
+					carry = newdig / NBASE;
+				}
+				newdig = (int) var1digits[0] * var2digits[0] + carry;
+				res_digits[1] = (NumericDigit) (newdig % NBASE);
+				res_digits[0] = (NumericDigit) (newdig / NBASE);
+				break;
+
+			case 3:
+				if (res_ndigits - 5 >= 0 && res_ndigits - 5 < var2ndigits)
+					newdig = (int) var1digits[2] * var2digits[res_ndigits - 5];
+				else
+					newdig = 0;
+				if (res_ndigits - 4 >= 0 && res_ndigits - 4 < var2ndigits)
+					newdig += (int) var1digits[1] * var2digits[res_ndigits - 4];
+				if (res_ndigits - 3 >= 0 && res_ndigits - 3 < var2ndigits)
+					newdig += (int) var1digits[0] * var2digits[res_ndigits - 3];
+				res_digits[res_ndigits - 2] = (NumericDigit) (newdig % NBASE);
+				carry = newdig / NBASE;
+				for (i = res_ndigits - 4; i >= 2; i--)
+				{
+					newdig = carry;
+					if (i < var2ndigits)
+						newdig += (int) var1digits[0] * var2digits[i];
+					if (i - 1 >= 0 && i - 1 < var2ndigits)
+						newdig += (int) var1digits[1] * var2digits[i - 1];
+					if (i - 2 >= 0 && i - 2 < var2ndigits)
+						newdig += (int) var1digits[2] * var2digits[i - 2];
+					res_digits[i + 1] = (NumericDigit) (newdig % NBASE);
+					carry = newdig / NBASE;
+				}
+				newdig = carry;
+				if (var2ndigits > 1)
+					newdig += (int) var1digits[0] * var2digits[1];
+				if (var2ndigits > 0)
+					newdig += (int) var1digits[1] * var2digits[0];
+				res_digits[2] = (NumericDigit) (newdig % NBASE);
+				carry = newdig / NBASE;
+				newdig = (int) var1digits[0] * var2digits[0] + carry;
+				res_digits[1] = (NumericDigit) (newdig % NBASE);
+				res_digits[0] = (NumericDigit) (newdig / NBASE);
+				break;
+		}
+
+		/* Store the product in result (minus extra rounding digit) */
+		digitbuf_free(result->buf);
+		result->ndigits = res_ndigits - 1;
+		result->buf = res_buf;
+		result->digits = res_digits;
+		result->weight = res_weight - 1;
+		result->sign = res_sign;
+
+		/* Round to target rscale (and set result->dscale) */
+		round_var(result, rscale);
+
+		/* Strip leading and trailing zeroes */
+		strip_var(result);
+
+		return;
+	}
+
 	/*
 	 * We do the arithmetic in an array "dig[]" of signed int's.  Since
 	 * INT_MAX is noticeably larger than NBASE*NBASE, this gives us headroom
-- 
2.45.1



^ permalink  raw  reply  [nested|flat] 3+ messages in thread

* Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands.
  2024-07-02 20:10 Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands. Joel Jacobson <[email protected]>
@ 2024-07-02 20:13 ` Joel Jacobson <[email protected]>
  0 siblings, 0 replies; 3+ messages in thread

From: Joel Jacobson @ 2024-07-02 20:13 UTC (permalink / raw)
  To: Dean Rasheed <[email protected]>; +Cc: Dagfinn Ilmari MannsÃ¥ker <[email protected]>; pgsql-hackers

On Tue, Jul 2, 2024, at 22:10, Joel Jacobson wrote:
> * v4-optimize-numeric-mul_var-small-var1-arbitrary-var2.patch

Instead of these boundary checks, maybe it would be cleaner to just
skip this optimization if there are too few res_ndigits?

/Joel






^ permalink  raw  reply  [nested|flat] 3+ messages in thread


end of thread, other threads:[~2024-07-02 20:13 UTC | newest]

Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2024-03-28 10:30 [PATCH v15 2/8] Row pattern recognition patch (parse/analysis). Tatsuo Ishii <[email protected]>
2024-07-02 20:10 Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands. Joel Jacobson <[email protected]>
2024-07-02 20:13 ` Re: Optimize numeric multiplication for one and two base-NBASE digit multiplicands. Joel Jacobson <[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