From 73ccc0a14771ca64110aeea5303d134d94fadb42 Mon Sep 17 00:00:00 2001 From: Tatsuo Ishii Date: Sat, 2 May 2026 13:40:29 +0900 Subject: [PATCH v47 2/9] Row pattern recognition patch (parse/analysis). --- src/backend/nodes/copyfuncs.c | 27 ++ src/backend/nodes/equalfuncs.c | 35 ++ src/backend/nodes/outfuncs.c | 51 +++ src/backend/nodes/readfuncs.c | 85 +++++ src/backend/parser/Makefile | 1 + src/backend/parser/README | 1 + src/backend/parser/meson.build | 1 + src/backend/parser/parse_agg.c | 9 +- src/backend/parser/parse_clause.c | 12 +- src/backend/parser/parse_expr.c | 42 +++ src/backend/parser/parse_func.c | 86 ++++- src/backend/parser/parse_rpr.c | 594 ++++++++++++++++++++++++++++++ src/include/nodes/primnodes.h | 54 +++ src/include/parser/parse_clause.h | 3 + src/include/parser/parse_rpr.h | 22 ++ 15 files changed, 1017 insertions(+), 6 deletions(-) create mode 100644 src/backend/parser/parse_rpr.c create mode 100644 src/include/parser/parse_rpr.h diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c index ff22a04abe5..e67ad39bdb8 100644 --- a/src/backend/nodes/copyfuncs.c +++ b/src/backend/nodes/copyfuncs.c @@ -16,6 +16,7 @@ #include "postgres.h" #include "miscadmin.h" +#include "nodes/plannodes.h" #include "utils/datum.h" @@ -166,6 +167,32 @@ _copyBitmapset(const Bitmapset *from) return bms_copy(from); } +static RPRPattern * +_copyRPRPattern(const RPRPattern *from) +{ + RPRPattern *newnode = makeNode(RPRPattern); + + COPY_SCALAR_FIELD(numVars); + COPY_SCALAR_FIELD(maxDepth); + COPY_SCALAR_FIELD(numElements); + + /* Deep copy the varNames array (DEFINE clause is required) */ + Assert(from->numVars > 0); + newnode->varNames = palloc0(from->numVars * sizeof(char *)); + for (int i = 0; i < from->numVars; i++) + newnode->varNames[i] = pstrdup(from->varNames[i]); + + /* Deep copy the elements array (always has at least one element + FIN) */ + Assert(from->numElements >= 2); + newnode->elements = palloc(from->numElements * sizeof(RPRPatternElement)); + memcpy(newnode->elements, from->elements, + from->numElements * sizeof(RPRPatternElement)); + + COPY_SCALAR_FIELD(isAbsorbable); + + return newnode; +} + /* * copyObjectImpl -- implementation of copyObject(); see nodes/nodes.h diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c index 3d1a1adf86e..328199918b8 100644 --- a/src/backend/nodes/equalfuncs.c +++ b/src/backend/nodes/equalfuncs.c @@ -20,6 +20,7 @@ #include "postgres.h" #include "miscadmin.h" +#include "nodes/plannodes.h" #include "utils/datum.h" @@ -149,6 +150,40 @@ _equalBitmapset(const Bitmapset *a, const Bitmapset *b) return bms_equal(a, b); } +static bool +_equalRPRPattern(const RPRPattern *a, const RPRPattern *b) +{ + COMPARE_SCALAR_FIELD(numVars); + COMPARE_SCALAR_FIELD(maxDepth); + COMPARE_SCALAR_FIELD(numElements); + + /* Compare varNames array */ + if (a->numVars > 0) + { + if (a->varNames == NULL || b->varNames == NULL) + return false; + for (int i = 0; i < a->numVars; i++) + { + if (strcmp(a->varNames[i], b->varNames[i]) != 0) + return false; + } + } + + /* Compare elements array */ + if (a->numElements > 0) + { + if (a->elements == NULL || b->elements == NULL) + return false; + if (memcmp(a->elements, b->elements, + a->numElements * sizeof(RPRPatternElement)) != 0) + return false; + } + + COMPARE_SCALAR_FIELD(isAbsorbable); + + return true; +} + /* * Lists are handled specially */ diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c index 953c5797c5d..e6ea9ce22d9 100644 --- a/src/backend/nodes/outfuncs.c +++ b/src/backend/nodes/outfuncs.c @@ -23,6 +23,7 @@ #include "nodes/bitmapset.h" #include "nodes/nodes.h" #include "nodes/pg_list.h" +#include "nodes/plannodes.h" #include "utils/datum.h" /* State flag that determines how nodeToStringInternal() should treat location fields */ @@ -727,6 +728,56 @@ _outA_Const(StringInfo str, const A_Const *node) WRITE_LOCATION_FIELD(location); } +static void +_outRPRPattern(StringInfo str, const RPRPattern *node) +{ + WRITE_NODE_TYPE("RPRPATTERN"); + + WRITE_INT_FIELD(numVars); + WRITE_INT_FIELD(maxDepth); + WRITE_INT_FIELD(numElements); + + /* Write varNames array as list of strings */ + appendStringInfoString(str, " :varNames"); + if (node->numVars > 0 && node->varNames != NULL) + { + appendStringInfoString(str, " ("); + for (int i = 0; i < node->numVars; i++) + { + if (i > 0) + appendStringInfoChar(str, ' '); + outToken(str, node->varNames[i]); + } + appendStringInfoChar(str, ')'); + } + else + appendStringInfoString(str, " <>"); + + /* Write elements array */ + appendStringInfoString(str, " :elements"); + if (node->numElements > 0 && node->elements != NULL) + { + appendStringInfoChar(str, ' '); + for (int i = 0; i < node->numElements; i++) + { + const RPRPatternElement *elem = &node->elements[i]; + + appendStringInfo(str, "(%d %d %u %d %d %d %d)", + (int) elem->varId, + (int) elem->depth, + (unsigned) elem->flags, + (int) elem->min, + (int) elem->max, + (int) elem->next, + (int) elem->jump); + } + } + else + appendStringInfoString(str, " <>"); + + WRITE_BOOL_FIELD(isAbsorbable); +} + /* * outNode - diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c index b6b2ce6c792..5bbde5bcad2 100644 --- a/src/backend/nodes/readfuncs.c +++ b/src/backend/nodes/readfuncs.c @@ -28,6 +28,7 @@ #include "miscadmin.h" #include "nodes/bitmapset.h" +#include "nodes/plannodes.h" #include "nodes/readfuncs.h" @@ -567,6 +568,90 @@ _readExtensibleNode(void) READ_DONE(); } +static RPRPattern * +_readRPRPattern(void) +{ + READ_LOCALS(RPRPattern); + + READ_INT_FIELD(numVars); + READ_INT_FIELD(maxDepth); + READ_INT_FIELD(numElements); + + /* Read varNames array */ + token = pg_strtok(&length); /* skip :varNames */ + token = pg_strtok(&length); /* get '(' or '<>' */ + if (local_node->numVars > 0 && token[0] == '(') + { + local_node->varNames = palloc(local_node->numVars * sizeof(char *)); + for (int i = 0; i < local_node->numVars; i++) + { + token = pg_strtok(&length); + local_node->varNames[i] = debackslash(token, length); + } + token = pg_strtok(&length); /* skip ')' */ + } + else + { + local_node->varNames = NULL; + } + + /* Read elements array */ + token = pg_strtok(&length); /* skip :elements */ + token = pg_strtok(&length); /* get '(' or '<>' */ + if (local_node->numElements > 0 && token[0] == '(') + { + local_node->elements = palloc0(local_node->numElements * sizeof(RPRPatternElement)); + for (int i = 0; i < local_node->numElements; i++) + { + RPRPatternElement *elem = &local_node->elements[i]; + int varId, + flags, + depth, + min, + max, + next, + jump; + + /* Parse "(varId depth flags min max next jump)" */ + token = pg_strtok(&length); + varId = atoi(token); + token = pg_strtok(&length); + depth = atoi(token); + token = pg_strtok(&length); + flags = atoi(token); + token = pg_strtok(&length); + min = atoi(token); + token = pg_strtok(&length); + max = atoi(token); + token = pg_strtok(&length); + next = atoi(token); + token = pg_strtok(&length); + jump = atoi(token); + token = pg_strtok(&length); /* skip ')' */ + + elem->varId = (RPRVarId) varId; + elem->flags = (RPRElemFlags) flags; + elem->depth = (RPRDepth) depth; + elem->min = (RPRQuantity) min; + elem->max = (RPRQuantity) max; + elem->next = (RPRElemIdx) next; + elem->jump = (RPRElemIdx) jump; + + /* Read next element's '(' or end */ + if (i < local_node->numElements - 1) + token = pg_strtok(&length); /* get '(' */ + } + } + else + { + local_node->elements = NULL; + } + + READ_BOOL_FIELD(isAbsorbable); + + READ_DONE(); +} + /* * parseNodeString diff --git a/src/backend/parser/Makefile b/src/backend/parser/Makefile index 8b5a4af6bf2..51e6b1adfb8 100644 --- a/src/backend/parser/Makefile +++ b/src/backend/parser/Makefile @@ -30,6 +30,7 @@ OBJS = \ parse_oper.o \ parse_param.o \ parse_relation.o \ + parse_rpr.o \ parse_target.o \ parse_type.o \ parse_utilcmd.o \ diff --git a/src/backend/parser/README b/src/backend/parser/README index e26eb437a9f..22a5e91c8cf 100644 --- a/src/backend/parser/README +++ b/src/backend/parser/README @@ -26,6 +26,7 @@ parse_node.c create nodes for various structures parse_oper.c handle operators in expressions parse_param.c handle Params (for the cases used in the core backend) parse_relation.c support routines for tables and column handling +parse_rpr.c handle Row Pattern Recognition parse_target.c handle the result list of the query parse_type.c support routines for data type handling parse_utilcmd.c parse analysis for utility commands (done at execution time) diff --git a/src/backend/parser/meson.build b/src/backend/parser/meson.build index 86c09b29ec2..82fe86e10db 100644 --- a/src/backend/parser/meson.build +++ b/src/backend/parser/meson.build @@ -17,6 +17,7 @@ backend_sources += files( 'parse_oper.c', 'parse_param.c', 'parse_relation.c', + 'parse_rpr.c', 'parse_target.c', 'parse_type.c', 'parse_utilcmd.c', diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c index acb933392de..b16e54d6e31 100644 --- a/src/backend/parser/parse_agg.c +++ b/src/backend/parser/parse_agg.c @@ -597,7 +597,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr) err = _("aggregate functions are not allowed in property definition expressions"); else err = _("grouping operations are not allowed in property definition expressions"); + break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; break; /* @@ -1045,6 +1048,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, case EXPR_KIND_FOR_PORTION: err = _("window functions are not allowed in FOR PORTION OF expressions"); break; + case EXPR_KIND_RPR_DEFINE: + errkind = true; + break; /* * There is intentionally no default: case here, so that the @@ -1125,7 +1131,8 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, equal(refwin->orderClause, windef->orderClause) && refwin->frameOptions == windef->frameOptions && equal(refwin->startOffset, windef->startOffset) && - equal(refwin->endOffset, windef->endOffset)) + equal(refwin->endOffset, windef->endOffset) && + equal(refwin->rpCommonSyntax, windef->rpCommonSyntax)) { /* found a duplicate window specification */ wfunc->winref = winref; diff --git a/src/backend/parser/parse_clause.c b/src/backend/parser/parse_clause.c index 4270c2382c4..6c443a31e79 100644 --- a/src/backend/parser/parse_clause.c +++ b/src/backend/parser/parse_clause.c @@ -39,6 +39,7 @@ #include "parser/parse_graphtable.h" #include "parser/parse_oper.h" #include "parser/parse_relation.h" +#include "parser/parse_rpr.h" #include "parser/parse_target.h" #include "parser/parse_type.h" #include "parser/parser.h" @@ -88,8 +89,6 @@ static void checkExprIsVarFree(ParseState *pstate, Node *n, const char *constructName); static TargetEntry *findTargetlistEntrySQL92(ParseState *pstate, Node *node, List **tlist, ParseExprKind exprKind); -static TargetEntry *findTargetlistEntrySQL99(ParseState *pstate, Node *node, - List **tlist, ParseExprKind exprKind); static int get_matching_location(int sortgroupref, List *sortgrouprefs, List *exprs); static List *resolve_unique_index_expr(ParseState *pstate, InferClause *infer, @@ -101,7 +100,6 @@ static Node *transformFrameOffset(ParseState *pstate, int frameOptions, Oid rangeopfamily, Oid rangeopcintype, Oid *inRangeFunc, Node *clause); - /* * transformFromClause - * Process the FROM clause and add items to the query's range table, @@ -2310,7 +2308,7 @@ findTargetlistEntrySQL92(ParseState *pstate, Node *node, List **tlist, * tlist the target list (passed by reference so we can append to it) * exprKind identifies clause type being processed */ -static TargetEntry * +TargetEntry * findTargetlistEntrySQL99(ParseState *pstate, Node *node, List **tlist, ParseExprKind exprKind) { @@ -3033,6 +3031,8 @@ transformWindowDefinitions(ParseState *pstate, * And prepare the new WindowClause. */ wc = makeNode(WindowClause); + wc->rpSkipTo = ST_NONE; /* ST_NONE marks this as a non-RPR window; + * overridden by transformRPR() if RPR is used */ wc->name = windef->name; wc->refname = windef->refname; @@ -3161,6 +3161,10 @@ transformWindowDefinitions(ParseState *pstate, rangeopfamily, rangeopcintype, &wc->endInRangeFunc, windef->endOffset); + + /* Process Row Pattern Recognition related clauses */ + transformRPR(pstate, wc, windef, targetlist); + wc->winref = winref; result = lappend(result, wc); diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c index c3c7aa29720..f145342e1fb 100644 --- a/src/backend/parser/parse_expr.c +++ b/src/backend/parser/parse_expr.c @@ -579,6 +579,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) case EXPR_KIND_GENERATED_COLUMN: case EXPR_KIND_CYCLE_MARK: case EXPR_KIND_PROPGRAPH_PROPERTY: + case EXPR_KIND_RPR_DEFINE: /* okay */ break; @@ -627,6 +628,42 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) if (node != NULL) return node; + /* + * Qualified column references in DEFINE are not supported. This covers + * both FROM-clause range variables (prohibited by §6.5) and pattern + * variable qualified names (e.g. UP.price), which are valid per §4.16 + * but not yet implemented. + */ + if (pstate->p_expr_kind == EXPR_KIND_RPR_DEFINE && + list_length(cref->fields) != 1) + { + char *qualifier = strVal(linitial(cref->fields)); + ListCell *lc; + bool is_pattern_var = false; + + foreach(lc, pstate->p_rpr_pattern_vars) + { + if (strcmp(strVal(lfirst(lc)), qualifier) == 0) + { + is_pattern_var = true; + break; + } + } + + if (is_pattern_var) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("pattern variable qualified column reference \"%s\" is not supported in DEFINE clause", + NameListToString(cref->fields)), + parser_errposition(pstate, cref->location))); + else + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("range variable qualified column reference \"%s\" is not allowed in DEFINE clause", + NameListToString(cref->fields)), + parser_errposition(pstate, cref->location))); + } + /*---------- * The allowed syntaxes are: * @@ -1892,6 +1929,9 @@ transformSubLink(ParseState *pstate, SubLink *sublink) case EXPR_KIND_FOR_PORTION: err = _("cannot use subquery in FOR PORTION OF expression"); break; + case EXPR_KIND_RPR_DEFINE: + err = _("cannot use subquery in DEFINE expression"); + break; /* * There is intentionally no default: case here, so that the @@ -3255,6 +3295,8 @@ ParseExprKindName(ParseExprKind exprKind) return "property definition expression"; case EXPR_KIND_FOR_PORTION: return "FOR PORTION OF"; + 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 35ff6427147..1eabcda02a1 100644 --- a/src/backend/parser/parse_func.c +++ b/src/backend/parser/parse_func.c @@ -31,6 +31,7 @@ #include "parser/parse_target.h" #include "parser/parse_type.h" #include "utils/builtins.h" +#include "utils/fmgroids.h" #include "utils/lsyscache.h" #include "utils/syscache.h" @@ -756,8 +757,88 @@ ParseFuncOrColumn(ParseState *pstate, List *funcname, List *fargs, if (retset) check_srf_call_placement(pstate, last_srf, location); + /* + * RPR navigation functions (PREV/NEXT/FIRST/LAST) are only meaningful + * inside a WINDOW DEFINE clause. + * + * Outside DEFINE, these polymorphic placeholders can shadow column access + * via functional notation (e.g., last(f) meaning f.last). For the 1-arg + * form, try column projection first; if that succeeds, use it instead. + * Otherwise, report a clear parser error. + */ + if (fdresult == FUNCDETAIL_NORMAL && + pstate->p_expr_kind != EXPR_KIND_RPR_DEFINE && + (funcid == F_PREV_ANYELEMENT || funcid == F_NEXT_ANYELEMENT || + funcid == F_PREV_ANYELEMENT_INT8 || funcid == F_NEXT_ANYELEMENT_INT8 || + funcid == F_FIRST_ANYELEMENT || funcid == F_LAST_ANYELEMENT || + funcid == F_FIRST_ANYELEMENT_INT8 || funcid == F_LAST_ANYELEMENT_INT8)) + { + /* 1-arg form: try column projection before erroring out */ + if (nargs == 1 && !agg_star && !agg_distinct && over == NULL && + list_length(funcname) == 1) + { + Node *projection; + + projection = ParseComplexProjection(pstate, + strVal(linitial(funcname)), + linitial(fargs), + location); + if (projection) + return projection; + } + + /* Not a column projection -- report error */ + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cannot use %s outside a DEFINE clause", + NameListToString(funcname)), + parser_errposition(pstate, location))); + } + /* build the appropriate output structure */ - if (fdresult == FUNCDETAIL_NORMAL || fdresult == FUNCDETAIL_PROCEDURE) + if (fdresult == FUNCDETAIL_NORMAL && + pstate->p_expr_kind == EXPR_KIND_RPR_DEFINE && + (funcid == F_PREV_ANYELEMENT || funcid == F_NEXT_ANYELEMENT || + funcid == F_PREV_ANYELEMENT_INT8 || funcid == F_NEXT_ANYELEMENT_INT8 || + funcid == F_FIRST_ANYELEMENT || funcid == F_LAST_ANYELEMENT || + funcid == F_FIRST_ANYELEMENT_INT8 || funcid == F_LAST_ANYELEMENT_INT8)) + { + /* + * RPR navigation functions (PREV/NEXT/FIRST/LAST) are compiled into + * EEOP_RPR_NAV_SET / EEOP_RPR_NAV_RESTORE opcodes instead of a normal + * function call. Represent them as RPRNavExpr nodes so that later + * stages can identify them without relying on funcid comparisons. + */ + RPRNavKind kind; + bool has_offset; + RPRNavExpr *navexpr; + + if (funcid == F_PREV_ANYELEMENT || funcid == F_PREV_ANYELEMENT_INT8) + kind = RPR_NAV_PREV; + else if (funcid == F_NEXT_ANYELEMENT || funcid == F_NEXT_ANYELEMENT_INT8) + kind = RPR_NAV_NEXT; + else if (funcid == F_FIRST_ANYELEMENT || funcid == F_FIRST_ANYELEMENT_INT8) + kind = RPR_NAV_FIRST; + else + kind = RPR_NAV_LAST; + + has_offset = (funcid == F_PREV_ANYELEMENT_INT8 || + funcid == F_NEXT_ANYELEMENT_INT8 || + funcid == F_FIRST_ANYELEMENT_INT8 || + funcid == F_LAST_ANYELEMENT_INT8); + + navexpr = makeNode(RPRNavExpr); + + navexpr->kind = kind; + navexpr->arg = (Expr *) linitial(fargs); + navexpr->offset_arg = has_offset ? (Expr *) lsecond(fargs) : NULL; + navexpr->resulttype = rettype; + /* resultcollid will be set by parse_collate.c */ + navexpr->location = location; + + retval = (Node *) navexpr; + } + else if (fdresult == FUNCDETAIL_NORMAL || fdresult == FUNCDETAIL_PROCEDURE) { FuncExpr *funcexpr = makeNode(FuncExpr); @@ -2789,6 +2870,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location) case EXPR_KIND_FOR_PORTION: err = _("set-returning functions are not allowed in FOR PORTION OF expressions"); 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_rpr.c b/src/backend/parser/parse_rpr.c new file mode 100644 index 00000000000..f56b7db5bc8 --- /dev/null +++ b/src/backend/parser/parse_rpr.c @@ -0,0 +1,594 @@ +/*------------------------------------------------------------------------- + * + * parse_rpr.c + * Handle Row Pattern Recognition clauses in parser. + * + * This file transforms RPR-related clauses from raw parse tree to planner + * structures during query analysis: + * - Validates frame options (must start at CURRENT ROW, no EXCLUDE) + * - Validates PATTERN variable count (max RPR_VARID_MAX) + * - Transforms DEFINE clause into TargetEntry list + * - Stores PATTERN/SKIP TO/INITIAL clauses for planner + * + * Pattern optimization and compilation to NFA bytecode happens later + * in the planner (see optimizer/plan/rpr.c). + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/parser/parse_rpr.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "miscadmin.h" +#include "nodes/makefuncs.h" +#include "nodes/nodeFuncs.h" +#include "optimizer/optimizer.h" +#include "optimizer/rpr.h" +#include "parser/parse_coerce.h" +#include "parser/parse_collate.h" +#include "parser/parse_expr.h" +#include "parser/parse_rpr.h" +#include "parser/parse_target.h" + +/* Forward declarations */ +static void validateRPRPatternVarCount(ParseState *pstate, RPRPatternNode *node, + List *rpDefs, List **varNames); +static List *transformDefineClause(ParseState *pstate, WindowClause *wc, + WindowDef *windef, List **targetlist); +static void check_rpr_nav_expr(RPRNavExpr *nav, ParseState *pstate); +static bool check_rpr_nav_nesting_walker(Node *node, void *context); + +/* + * transformRPR + * Process Row Pattern Recognition related clauses. + * + * Validates and transforms RPR clauses from parse tree to planner structures: + * - Validates frame options (must start at CURRENT ROW, no EXCLUDE) + * - Stores AFTER MATCH SKIP TO clause + * - Stores SEEK/INITIAL clause + * - Transforms DEFINE clause into TargetEntry list + * - Stores PATTERN AST for deparsing (optimization happens in planner) + * + * Returns early if windef has no rpCommonSyntax (non-RPR window). + */ +void +transformRPR(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + /* Window definition must exist when called */ + Assert(windef != NULL); + + /* + * Row Pattern Common Syntax clause exists? + */ + if (windef->rpCommonSyntax == NULL) + return; + + /* Check Frame options */ + + /* Frame type must be "ROW" */ + if (wc->frameOptions & FRAMEOPTION_GROUPS) + ereport(ERROR, + (errcode(ERRCODE_WINDOWING_ERROR), + errmsg("cannot use FRAME option GROUPS with row pattern recognition"), + errhint("Use ROWS instead."), + parser_errposition(pstate, + windef->frameLocation >= 0 ? + windef->frameLocation : windef->location))); + if (wc->frameOptions & FRAMEOPTION_RANGE) + ereport(ERROR, + (errcode(ERRCODE_WINDOWING_ERROR), + errmsg("cannot use FRAME option RANGE with row pattern recognition"), + errhint("Use ROWS instead."), + parser_errposition(pstate, + windef->frameLocation >= 0 ? + windef->frameLocation : windef->location))); + + /* Frame must start at current row */ + if ((wc->frameOptions & FRAMEOPTION_START_CURRENT_ROW) == 0) + { + const char *frameType = "ROWS"; + const char *startBound = "unknown"; + + /* Determine current start bound */ + if (wc->frameOptions & FRAMEOPTION_START_UNBOUNDED_PRECEDING) + startBound = "UNBOUNDED PRECEDING"; + else if (wc->frameOptions & FRAMEOPTION_START_OFFSET_PRECEDING) + startBound = "offset PRECEDING"; + else if (wc->frameOptions & FRAMEOPTION_START_OFFSET_FOLLOWING) + startBound = "offset FOLLOWING"; + + /* At least one valid frame start option should be set */ + Assert((wc->frameOptions & FRAMEOPTION_START_UNBOUNDED_PRECEDING) || + (wc->frameOptions & FRAMEOPTION_START_OFFSET_PRECEDING) || + (wc->frameOptions & FRAMEOPTION_START_OFFSET_FOLLOWING)); + + ereport(ERROR, + (errcode(ERRCODE_WINDOWING_ERROR), + errmsg("FRAME must start at CURRENT ROW when using row pattern recognition"), + errdetail("Current frame starts with %s.", startBound), + errhint("Use: %s BETWEEN CURRENT ROW AND ...", frameType), + parser_errposition(pstate, windef->frameLocation >= 0 ? windef->frameLocation : windef->location))); + } + + /* EXCLUDE options are not permitted */ + if ((wc->frameOptions & FRAMEOPTION_EXCLUSION) != 0) + { + const char *excludeType = "EXCLUDE"; + + /* Determine which EXCLUDE option was used */ + if (wc->frameOptions & FRAMEOPTION_EXCLUDE_CURRENT_ROW) + excludeType = "EXCLUDE CURRENT ROW"; + else if (wc->frameOptions & FRAMEOPTION_EXCLUDE_GROUP) + excludeType = "EXCLUDE GROUP"; + else if (wc->frameOptions & FRAMEOPTION_EXCLUDE_TIES) + excludeType = "EXCLUDE TIES"; + + /* At least one valid exclude option should be set */ + Assert((wc->frameOptions & FRAMEOPTION_EXCLUDE_CURRENT_ROW) || + (wc->frameOptions & FRAMEOPTION_EXCLUDE_GROUP) || + (wc->frameOptions & FRAMEOPTION_EXCLUDE_TIES)); + + ereport(ERROR, + (errcode(ERRCODE_WINDOWING_ERROR), + errmsg("cannot use EXCLUDE options with row pattern recognition"), + errdetail("Frame definition includes %s.", excludeType), + errhint("Remove the EXCLUDE clause from the window definition."), + parser_errposition(pstate, windef->excludeLocation >= 0 ? windef->excludeLocation : windef->location))); + } + + /* Transform AFTER MATCH SKIP TO clause */ + wc->rpSkipTo = windef->rpCommonSyntax->rpSkipTo; + + /* 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); + + /* Store PATTERN AST for deparsing */ + wc->rpPattern = windef->rpCommonSyntax->rpPattern; +} + +/* + * validateRPRPatternVarCount + * Validate that PATTERN variables don't exceed RPR_VARID_MAX. + * + * Recursively traverses the pattern tree, collecting unique variable names. + * Throws an error if the number of unique variables exceeds RPR_VARID_MAX. + * + * If rpDefs is non-NULL, DEFINE variable names are also collected into + * varNames so that transformColumnRef can distinguish pattern variable + * qualifiers from FROM-clause range variables. + * + * varNames is both input and output: existing names are preserved, new ones added. + */ +static void +validateRPRPatternVarCount(ParseState *pstate, RPRPatternNode *node, + List *rpDefs, List **varNames) +{ + ListCell *lc; + + /* Pattern node must exist - parser always provides non-NULL root */ + Assert(node != NULL); + + check_stack_depth(); + + switch (node->nodeType) + { + case RPR_PATTERN_VAR: + /* Add variable name if not already in list */ + { + bool found = false; + + foreach(lc, *varNames) + { + if (strcmp(strVal(lfirst(lc)), node->varName) == 0) + { + found = true; + break; + } + } + if (!found) + { + /* Check against RPR_VARID_MAX before adding */ + if (list_length(*varNames) >= RPR_VARID_MAX) + ereport(ERROR, + (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED), + errmsg("too many pattern variables"), + errdetail("Maximum is %d.", RPR_VARID_MAX), + parser_errposition(pstate, + exprLocation((Node *) node)))); + + *varNames = lappend(*varNames, makeString(pstrdup(node->varName))); + } + } + break; + + case RPR_PATTERN_SEQ: + case RPR_PATTERN_ALT: + case RPR_PATTERN_GROUP: + /* Recurse into children */ + foreach(lc, node->children) + { + validateRPRPatternVarCount(pstate, (RPRPatternNode *) lfirst(lc), + NULL, varNames); + } + break; + } + + /* + * After the top-level call, also collect DEFINE variable names that are + * not already in the list. This is only done once at the outermost + * recursion level, detected by rpDefs being non-NULL (recursive calls + * pass NULL). + */ + if (rpDefs) + { + foreach(lc, rpDefs) + { + ResTarget *rt = (ResTarget *) lfirst(lc); + ListCell *lc2; + bool found = false; + + foreach(lc2, *varNames) + { + if (strcmp(strVal(lfirst(lc2)), rt->name) == 0) + { + found = true; + break; + } + } + if (!found) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("DEFINE variable \"%s\" is not used in PATTERN", + rt->name), + parser_errposition(pstate, rt->location))); + } + } +} + +/* + * transformDefineClause + * Process DEFINE clause and transform ResTarget into list of TargetEntry. + * + * First: + * 1. Validates PATTERN variable count and collects RPR variable names + * + * Then for each DEFINE variable: + * 2. Checks for duplicate variable names in DEFINE clause + * 3. Transforms expression via transformExpr() and ensures referenced + * Var nodes are present in the query targetlist (via pull_var_clause) + * 4. Creates defineClause entry with proper resname (pattern variable name) + * 5. Coerces expressions to boolean type + * 6. Marks column origins and assigns collation information + * + * Note: Variables not in DEFINE are evaluated as TRUE by the executor. + * Variables in DEFINE but not in PATTERN are rejected as an error. + * + * XXX Pattern variable qualified column references in DEFINE (e.g. + * "A.price") are not yet supported. Currently rejected by + * transformColumnRef in parse_expr.c via the p_rpr_pattern_vars check. + */ +static List * +transformDefineClause(ParseState *pstate, WindowClause *wc, WindowDef *windef, + List **targetlist) +{ + ListCell *lc, + *l; + ResTarget *restarget, + *r; + List *restargets; + List *defineClause = NIL; + char *name; + List *patternVarNames = NIL; + + /* + * If Row Definition Common Syntax exists, DEFINE clause must exist. (the + * raw parser should have already checked it.) + */ + Assert(windef->rpCommonSyntax->rpDefs != NULL); + + /* + * Validate PATTERN variable count and collect all RPR variable names + * (PATTERN + DEFINE) for use in transformColumnRef. + */ + validateRPRPatternVarCount(pstate, windef->rpCommonSyntax->rpPattern, + windef->rpCommonSyntax->rpDefs, + &patternVarNames); + pstate->p_rpr_pattern_vars = patternVarNames; + + /* + * 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) + { + TargetEntry *teDefine; + + restarget = (ResTarget *) lfirst(lc); + name = restarget->name; + + foreach(l, restargets) + { + char *n; + + r = (ResTarget *) lfirst(l); + n = r->name; + + if (!strcmp(n, name)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("DEFINE variable \"%s\" appears more than once", + name), + parser_errposition(pstate, exprLocation((Node *) r)))); + } + + restargets = lappend(restargets, restarget); + + /* + * Transform the DEFINE expression. We must NOT add the whole + * expression to the query targetlist, because it may contain + * RPRNavExpr nodes (PREV/NEXT/FIRST/LAST) that can only be evaluated + * inside the owning WindowAgg. + * + * Instead, we transform the expression directly and only ensure that + * the individual Var nodes it references are present in the + * targetlist, so the planner can propagate the referenced columns. + */ + { + Node *expr; + List *vars; + ListCell *lc2; + + expr = transformExpr(pstate, restarget->val, + EXPR_KIND_RPR_DEFINE); + + /* + * Pull out Var nodes from the transformed expression and ensure + * each one is present in the targetlist. This is needed so the + * planner propagates the referenced columns through the plan + * tree, making them available to the WindowAgg's DEFINE + * evaluation. + */ + vars = pull_var_clause(expr, 0); + foreach(lc2, vars) + { + Var *var = (Var *) lfirst(lc2); + bool found = false; + ListCell *tl; + + foreach(tl, *targetlist) + { + TargetEntry *tle = (TargetEntry *) lfirst(tl); + + if (IsA(tle->expr, Var) && + ((Var *) tle->expr)->varno == var->varno && + ((Var *) tle->expr)->varattno == var->varattno) + { + found = true; + break; + } + } + if (!found) + { + TargetEntry *newtle; + + newtle = makeTargetEntry((Expr *) copyObject(var), + list_length(*targetlist) + 1, + NULL, + true); + *targetlist = lappend(*targetlist, newtle); + } + } + list_free(vars); + + /* Build the defineClause entry directly from the transformed expr */ + teDefine = makeTargetEntry((Expr *) expr, + list_length(defineClause) + 1, + pstrdup(name), + true); + } + + /* build transformed DEFINE clause (list of TargetEntry) */ + defineClause = lappend(defineClause, teDefine); + } + list_free(restargets); + pstate->p_rpr_pattern_vars = NIL; + + /* + * Make sure that the row pattern definition search condition is a boolean + * expression. + */ + foreach_ptr(TargetEntry, te, defineClause) + te->expr = (Expr *) coerce_to_boolean(pstate, (Node *) te->expr, "DEFINE"); + + /* check for nested PREV/NEXT and missing column references */ + foreach_ptr(TargetEntry, te, defineClause) + (void) check_rpr_nav_nesting_walker((Node *) te->expr, pstate); + + /* 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; +} + +/* + * check_rpr_nav_expr + * Validate a single RPRNavExpr node by walking its arg and offset_arg + * subtrees in a single pass each. Check for illegal nesting, missing + * column references, and non-constant offset expressions. + * + * Nesting rules (SQL standard 5.6.4): + * - PREV/NEXT wrapping FIRST/LAST: allowed (compound navigation) + * - FIRST/LAST wrapping PREV/NEXT: prohibited + * - Same-category nesting (PREV inside PREV, FIRST inside FIRST, etc.): + * prohibited + */ +typedef struct +{ + int nav_count; /* number of RPRNavExpr nodes found */ + bool has_column_ref; /* Var found */ + RPRNavKind inner_kind; /* kind of first (outermost) nested RPRNavExpr */ +} NavCheckResult; + +static bool +nav_check_walker(Node *node, void *context) +{ + NavCheckResult *result = (NavCheckResult *) context; + + if (node == NULL) + return false; + if (IsA(node, RPRNavExpr)) + { + if (result->nav_count == 0) + result->inner_kind = ((RPRNavExpr *) node)->kind; + result->nav_count++; + } + if (IsA(node, Var)) + result->has_column_ref = true; + + return expression_tree_walker(node, nav_check_walker, context); +} + +static void +check_rpr_nav_expr(RPRNavExpr *nav, ParseState *pstate) +{ + NavCheckResult result; + bool outer_is_physical = (nav->kind == RPR_NAV_PREV || + nav->kind == RPR_NAV_NEXT); + + /* Check arg subtree: nesting + column reference in one walk */ + memset(&result, 0, sizeof(result)); + (void) nav_check_walker((Node *) nav->arg, &result); + + if (result.nav_count > 0) + { + bool inner_is_physical = (result.inner_kind == RPR_NAV_PREV || + result.inner_kind == RPR_NAV_NEXT); + + if (outer_is_physical && !inner_is_physical) + { + /* + * PREV/NEXT wrapping FIRST/LAST: compound navigation per SQL + * standard 5.6.4. Flatten the nested RPRNavExpr into a single + * compound node. The inner RPRNavExpr must be the direct arg of + * the outer; expressions like PREV(val + FIRST(v)) are not valid + * compound navigation. + */ + RPRNavExpr *inner; + + /* Reject triple-or-deeper nesting (e.g. PREV(FIRST(PREV(x)))) */ + if (result.nav_count > 1) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cannot nest row pattern navigation more than two levels deep"), + errhint("Only PREV(FIRST()), PREV(LAST()), NEXT(FIRST()), and NEXT(LAST()) compound forms are allowed."), + parser_errposition(pstate, nav->location))); + + if (!IsA(nav->arg, RPRNavExpr)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("row pattern navigation operation must be a direct argument of the outer navigation"), + errhint("Only PREV(FIRST()), PREV(LAST()), NEXT(FIRST()), and NEXT(LAST()) compound forms are allowed."), + parser_errposition(pstate, nav->location))); + inner = (RPRNavExpr *) nav->arg; + + /* Determine compound kind */ + if (nav->kind == RPR_NAV_PREV && inner->kind == RPR_NAV_FIRST) + nav->kind = RPR_NAV_PREV_FIRST; + else if (nav->kind == RPR_NAV_PREV && inner->kind == RPR_NAV_LAST) + nav->kind = RPR_NAV_PREV_LAST; + else if (nav->kind == RPR_NAV_NEXT && inner->kind == RPR_NAV_FIRST) + nav->kind = RPR_NAV_NEXT_FIRST; + else if (nav->kind == RPR_NAV_NEXT && inner->kind == RPR_NAV_LAST) + nav->kind = RPR_NAV_NEXT_LAST; + + /* Move outer offset to compound_offset_arg */ + nav->compound_offset_arg = nav->offset_arg; + + /* Move inner offset and arg up */ + nav->offset_arg = inner->offset_arg; + nav->arg = inner->arg; + + /* No further nesting check needed - already validated */ + return; + } + else if (!outer_is_physical && inner_is_physical) + { + /* FIRST/LAST wrapping PREV/NEXT: prohibited by standard */ + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("FIRST and LAST cannot contain PREV or NEXT"), + errhint("Only PREV(FIRST()), PREV(LAST()), NEXT(FIRST()), and NEXT(LAST()) compound forms are allowed."), + parser_errposition(pstate, nav->location))); + } + else if (outer_is_physical && inner_is_physical) + { + /* PREV/NEXT wrapping PREV/NEXT: prohibited */ + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("PREV and NEXT cannot contain PREV or NEXT"), + errhint("Only PREV(FIRST()), PREV(LAST()), NEXT(FIRST()), and NEXT(LAST()) compound forms are allowed."), + parser_errposition(pstate, nav->location))); + } + else + { + /* FIRST/LAST wrapping FIRST/LAST: prohibited */ + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("FIRST and LAST cannot contain FIRST or LAST"), + errhint("Only PREV(FIRST()), PREV(LAST()), NEXT(FIRST()), and NEXT(LAST()) compound forms are allowed."), + parser_errposition(pstate, nav->location))); + } + } + if (!result.has_column_ref) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("argument of row pattern navigation operation must include at least one column reference"), + parser_errposition(pstate, nav->location))); + + /* Check offset_arg: column ref + volatile in one walk */ + if (nav->offset_arg != NULL) + { + memset(&result, 0, sizeof(result)); + (void) nav_check_walker((Node *) nav->offset_arg, &result); + + if (result.has_column_ref || + contain_volatile_functions((Node *) nav->offset_arg)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("row pattern navigation offset must be a run-time constant"), + parser_errposition(pstate, nav->location))); + } +} + +/* + * check_rpr_nav_nesting_walker + * Walk the DEFINE clause expression tree and validate each RPRNavExpr. + */ +static bool +check_rpr_nav_nesting_walker(Node *node, void *context) +{ + if (node == NULL) + return false; + if (IsA(node, RPRNavExpr)) + { + check_rpr_nav_expr((RPRNavExpr *) node, (ParseState *) context); + /* don't recurse into arg; nesting already checked above */ + return false; + } + return expression_tree_walker(node, check_rpr_nav_nesting_walker, context); +} diff --git a/src/include/nodes/primnodes.h b/src/include/nodes/primnodes.h index 7977ee24783..656c552b0a8 100644 --- a/src/include/nodes/primnodes.h +++ b/src/include/nodes/primnodes.h @@ -648,6 +648,60 @@ typedef struct WindowFuncRunCondition Expr *arg; } WindowFuncRunCondition; +/* + * RPRNavExpr + * + * Represents a PREV/NEXT/FIRST/LAST navigation call in an RPR DEFINE clause. + * At expression compile time this is translated into EEOP_RPR_NAV_SET / + * EEOP_RPR_NAV_RESTORE opcodes rather than a normal function call. + * + * Simple navigation (PREV/NEXT/FIRST/LAST): + * kind: RPR_NAV_PREV, RPR_NAV_NEXT, RPR_NAV_FIRST, or RPR_NAV_LAST + * arg: the expression to evaluate against the target row + * offset_arg: optional explicit offset expression (2-arg form); NULL for + * the 1-arg form (implicit offset: 1 for PREV/NEXT, 0 for + * FIRST/LAST) + * + * Compound navigation (PREV/NEXT wrapping FIRST/LAST): + * kind: RPR_NAV_PREV_FIRST, PREV_LAST, NEXT_FIRST, NEXT_LAST + * arg: the expression to evaluate against the final target row + * offset_arg: inner offset (FIRST/LAST), NULL = implicit default + * compound_offset_arg: outer offset (PREV/NEXT), NULL = implicit default + * + * Compound target computation: + * PREV_FIRST: (match_start + inner) - outer + * NEXT_FIRST: (match_start + inner) + outer + * PREV_LAST: (currentpos - inner) - outer + * NEXT_LAST: (currentpos - inner) + outer + */ +typedef enum RPRNavKind +{ + RPR_NAV_PREV, + RPR_NAV_NEXT, + RPR_NAV_FIRST, + RPR_NAV_LAST, + /* compound: outer(inner(arg)) */ + RPR_NAV_PREV_FIRST, + RPR_NAV_PREV_LAST, + RPR_NAV_NEXT_FIRST, + RPR_NAV_NEXT_LAST +} RPRNavKind; + +typedef struct RPRNavExpr +{ + Expr xpr; + RPRNavKind kind; /* navigation kind */ + Expr *arg; /* argument expression */ + Expr *offset_arg; /* offset expression, or NULL for default */ + Expr *compound_offset_arg; /* outer offset for compound nav, or + * NULL if simple */ + Oid resulttype; /* result type (same as arg's type) */ + /* OID of collation of result */ + Oid resultcollid pg_node_attr(query_jumble_ignore); + /* token location, or -1 if unknown */ + ParseLoc location; +} RPRNavExpr; + /* * MergeSupportFunc * diff --git a/src/include/parser/parse_clause.h b/src/include/parser/parse_clause.h index fe234611007..8aaac881f2b 100644 --- a/src/include/parser/parse_clause.h +++ b/src/include/parser/parse_clause.h @@ -52,6 +52,9 @@ extern List *addTargetToSortList(ParseState *pstate, TargetEntry *tle, extern Index assignSortGroupRef(TargetEntry *tle, List *tlist); extern bool targetIsInSortList(TargetEntry *tle, Oid sortop, List *sortList); +extern TargetEntry *findTargetlistEntrySQL99(ParseState *pstate, Node *node, + List **tlist, ParseExprKind exprKind); + /* functions in parse_jsontable.c */ extern ParseNamespaceItem *transformJsonTable(ParseState *pstate, JsonTable *jt); diff --git a/src/include/parser/parse_rpr.h b/src/include/parser/parse_rpr.h new file mode 100644 index 00000000000..7fab6f292aa --- /dev/null +++ b/src/include/parser/parse_rpr.h @@ -0,0 +1,22 @@ +/*------------------------------------------------------------------------- + * + * parse_rpr.h + * handle Row Pattern Recognition in parser + * + * + * Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/parser/parse_rpr.h + * + *------------------------------------------------------------------------- + */ +#ifndef PARSE_RPR_H +#define PARSE_RPR_H + +#include "parser/parse_node.h" + +extern void transformRPR(ParseState *pstate, WindowClause *wc, + WindowDef *windef, List **targetlist); + +#endif /* PARSE_RPR_H */ -- 2.43.0