diff options
| author | Peter Eisentraut | 2021-02-01 12:54:59 +0000 |
|---|---|---|
| committer | Peter Eisentraut | 2021-02-01 13:32:51 +0000 |
| commit | 3696a600e2292d43c00949ddf0352e4ebb487e5b (patch) | |
| tree | 11f19c8c9e5757c44b8da02d0e1f7b41f8ec5f13 | |
| parent | bb513b364b4fe31574574c8d0afbb2255268b321 (diff) | |
SEARCH and CYCLE clauses
This adds the SQL standard feature that adds the SEARCH and CYCLE
clauses to recursive queries to be able to do produce breadth- or
depth-first search orders and detect cycles. These clauses can be
rewritten into queries using existing syntax, and that is what this
patch does in the rewriter.
Reviewed-by: Vik Fearing <[email protected]>
Reviewed-by: Pavel Stehule <[email protected]>
Discussion: https://www.postgresql.org/message-id/flat/[email protected]
28 files changed, 2301 insertions, 33 deletions
diff --git a/doc/src/sgml/queries.sgml b/doc/src/sgml/queries.sgml index ca512048756..4741506eb56 100644 --- a/doc/src/sgml/queries.sgml +++ b/doc/src/sgml/queries.sgml @@ -2218,6 +2218,39 @@ SELECT * FROM search_tree <emphasis>ORDER BY depth</emphasis>; in any case. </para> </tip> + + <para> + There is built-in syntax to compute a depth- or breadth-first sort column. + For example: + +<programlisting> +WITH RECURSIVE search_tree(id, link, data) AS ( + SELECT t.id, t.link, t.data + FROM tree t + UNION ALL + SELECT t.id, t.link, t.data + FROM tree t, search_tree st + WHERE t.id = st.link +) <emphasis>SEARCH DEPTH FIRST BY id SET ordercol</emphasis> +SELECT * FROM search_tree ORDER BY ordercol; + +WITH RECURSIVE search_tree(id, link, data) AS ( + SELECT t.id, t.link, t.data + FROM tree t + UNION ALL + SELECT t.id, t.link, t.data + FROM tree t, search_tree st + WHERE t.id = st.link +) <emphasis>SEARCH BREADTH FIRST BY id SET ordercol</emphasis> +SELECT * FROM search_tree ORDER BY ordercol; +</programlisting> + This syntax is internally expanded to something similar to the above + hand-written forms. The <literal>SEARCH</literal> clause specifies whether + depth- or breadth first search is wanted, the list of columns to track for + sorting, and a column name that will contain the result data that can be + used for sorting. That column will implicitly be added to the output rows + of the CTE. + </para> </sect3> <sect3 id="queries-with-cycle"> @@ -2305,10 +2338,39 @@ SELECT * FROM search_graph; </para> </tip> + <para> + There is built-in syntax to simplify cycle detection. The above query can + also be written like this: +<programlisting> +WITH RECURSIVE search_graph(id, link, data, depth) AS ( + SELECT g.id, g.link, g.data, 1 + FROM graph g + UNION ALL + SELECT g.id, g.link, g.data, sg.depth + 1 + FROM graph g, search_graph sg + WHERE g.id = sg.link +) <emphasis>CYCLE id SET is_cycle TO true DEFAULT false USING path</emphasis> +SELECT * FROM search_graph; +</programlisting> + and it will be internally rewritten to the above form. The + <literal>CYCLE</literal> clause specifies first the list of columns to + track for cycle detection, then a column name that will show whether a + cycle has been detected, then two values to use in that column for the yes + and no cases, and finally the name of another column that will track the + path. The cycle and path columns will implicitly be added to the output + rows of the CTE. + </para> + <tip> <para> The cycle path column is computed in the same way as the depth-first - ordering column show in the previous section. + ordering column show in the previous section. A query can have both a + <literal>SEARCH</literal> and a <literal>CYCLE</literal> clause, but a + depth-first search specification and a cycle detection specification would + create redundant computations, so it's more efficient to just use the + <literal>CYCLE</literal> clause and order by the path column. If + breadth-first ordering is wanted, then specifying both + <literal>SEARCH</literal> and <literal>CYCLE</literal> can be useful. </para> </tip> diff --git a/doc/src/sgml/ref/select.sgml b/doc/src/sgml/ref/select.sgml index c48ff6bc7e8..eb8b5249518 100644 --- a/doc/src/sgml/ref/select.sgml +++ b/doc/src/sgml/ref/select.sgml @@ -73,6 +73,8 @@ SELECT [ ALL | DISTINCT [ ON ( <replaceable class="parameter">expression</replac <phrase>and <replaceable class="parameter">with_query</replaceable> is:</phrase> <replaceable class="parameter">with_query_name</replaceable> [ ( <replaceable class="parameter">column_name</replaceable> [, ...] ) ] AS [ [ NOT ] MATERIALIZED ] ( <replaceable class="parameter">select</replaceable> | <replaceable class="parameter">values</replaceable> | <replaceable class="parameter">insert</replaceable> | <replaceable class="parameter">update</replaceable> | <replaceable class="parameter">delete</replaceable> ) + [ SEARCH { BREADTH | DEPTH } FIRST BY <replaceable>column_name</replaceable> [, ...] SET <replaceable>search_seq_col_name</replaceable> ] + [ CYCLE <replaceable>column_name</replaceable> [, ...] SET <replaceable>cycle_mark_col_name</replaceable> TO <replaceable>cycle_mark_value</replaceable> DEFAULT <replaceable>cycle_mark_default</replaceable> USING <replaceable>cycle_path_col_name</replaceable> ] TABLE [ ONLY ] <replaceable class="parameter">table_name</replaceable> [ * ] </synopsis> @@ -277,6 +279,48 @@ TABLE [ ONLY ] <replaceable class="parameter">table_name</replaceable> [ * ] </para> <para> + The optional <literal>SEARCH</literal> clause computes a <firstterm>search + sequence column</firstterm> that can be used for ordering the results of a + recursive query in either breadth-first or depth-first order. The + supplied column name list specifies the row key that is to be used for + keeping track of visited rows. A column named + <replaceable>search_seq_col_name</replaceable> will be added to the result + column list of the <literal>WITH</literal> query. This column can be + ordered by in the outer query to achieve the respective ordering. See + <xref linkend="queries-with-search"/> for examples. + </para> + + <para> + The optional <literal>CYCLE</literal> clause is used to detect cycles in + recursive queries. The supplied column name list specifies the row key + that is to be used for keeping track of visited rows. A column named + <replaceable>cycle_mark_col_name</replaceable> will be added to the result + column list of the <literal>WITH</literal> query. This column will be set + to <replaceable>cycle_mark_value</replaceable> when a cycle has been + detected, else to <replaceable>cycle_mark_default</replaceable>. + Furthermore, processing of the recursive union will stop when a cycle has + been detected. <replaceable>cycle_mark_value</replaceable> and + <replaceable>cycle_mark_default</replaceable> must be constants and they + must be coercible to a common data type, and the data type must have an + inequality operator. (The SQL standard requires that they be character + strings, but PostgreSQL does not require that.) Furthermore, a column + named <replaceable>cycle_path_col_name</replaceable> will be added to the + result column list of the <literal>WITH</literal> query. This column is + used internally for tracking visited rows. See <xref + linkend="queries-with-cycle"/> for examples. + </para> + + <para> + Both the <literal>SEARCH</literal> and the <literal>CYCLE</literal> clause + are only valid for recursive <literal>WITH</literal> queries. The + <replaceable>with_query</replaceable> must be a <literal>UNION</literal> + (or <literal>UNION ALL</literal>) of two <literal>SELECT</literal> (or + equivalent) commands (no nested <literal>UNION</literal>s). If both + clauses are used, the column added by the <literal>SEARCH</literal> clause + appears before the columns added by the <literal>CYCLE</literal> clause. + </para> + + <para> The primary query and the <literal>WITH</literal> queries are all (notionally) executed at the same time. This implies that the effects of a data-modifying statement in <literal>WITH</literal> cannot be seen from diff --git a/src/backend/catalog/dependency.c b/src/backend/catalog/dependency.c index 2140151a6af..13257336249 100644 --- a/src/backend/catalog/dependency.c +++ b/src/backend/catalog/dependency.c @@ -2264,6 +2264,21 @@ find_expr_references_walker(Node *node, context->addrs); /* fall through to examine substructure */ } + else if (IsA(node, CTECycleClause)) + { + CTECycleClause *cc = (CTECycleClause *) node; + + if (OidIsValid(cc->cycle_mark_type)) + add_object_address(OCLASS_TYPE, cc->cycle_mark_type, 0, + context->addrs); + if (OidIsValid(cc->cycle_mark_collation)) + add_object_address(OCLASS_COLLATION, cc->cycle_mark_collation, 0, + context->addrs); + if (OidIsValid(cc->cycle_mark_neop)) + add_object_address(OCLASS_OPERATOR, cc->cycle_mark_neop, 0, + context->addrs); + /* fall through to examine substructure */ + } else if (IsA(node, Query)) { /* Recurse into RTE subquery or not-yet-planned sublink subquery */ diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c index 21e09c667a3..65bbc18ecba 100644 --- a/src/backend/nodes/copyfuncs.c +++ b/src/backend/nodes/copyfuncs.c @@ -2589,6 +2589,38 @@ _copyOnConflictClause(const OnConflictClause *from) return newnode; } +static CTESearchClause * +_copyCTESearchClause(const CTESearchClause *from) +{ + CTESearchClause *newnode = makeNode(CTESearchClause); + + COPY_NODE_FIELD(search_col_list); + COPY_SCALAR_FIELD(search_breadth_first); + COPY_STRING_FIELD(search_seq_column); + COPY_LOCATION_FIELD(location); + + return newnode; +} + +static CTECycleClause * +_copyCTECycleClause(const CTECycleClause *from) +{ + CTECycleClause *newnode = makeNode(CTECycleClause); + + COPY_NODE_FIELD(cycle_col_list); + COPY_STRING_FIELD(cycle_mark_column); + COPY_NODE_FIELD(cycle_mark_value); + COPY_NODE_FIELD(cycle_mark_default); + COPY_STRING_FIELD(cycle_path_column); + COPY_LOCATION_FIELD(location); + COPY_SCALAR_FIELD(cycle_mark_type); + COPY_SCALAR_FIELD(cycle_mark_typmod); + COPY_SCALAR_FIELD(cycle_mark_collation); + COPY_SCALAR_FIELD(cycle_mark_neop); + + return newnode; +} + static CommonTableExpr * _copyCommonTableExpr(const CommonTableExpr *from) { @@ -2598,6 +2630,8 @@ _copyCommonTableExpr(const CommonTableExpr *from) COPY_NODE_FIELD(aliascolnames); COPY_SCALAR_FIELD(ctematerialized); COPY_NODE_FIELD(ctequery); + COPY_NODE_FIELD(search_clause); + COPY_NODE_FIELD(cycle_clause); COPY_LOCATION_FIELD(location); COPY_SCALAR_FIELD(cterecursive); COPY_SCALAR_FIELD(cterefcount); @@ -5682,6 +5716,12 @@ copyObjectImpl(const void *from) case T_OnConflictClause: retval = _copyOnConflictClause(from); break; + case T_CTESearchClause: + retval = _copyCTESearchClause(from); + break; + case T_CTECycleClause: + retval = _copyCTECycleClause(from); + break; case T_CommonTableExpr: retval = _copyCommonTableExpr(from); break; diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c index 5a5237c6c30..c2d73626fcc 100644 --- a/src/backend/nodes/equalfuncs.c +++ b/src/backend/nodes/equalfuncs.c @@ -2842,12 +2842,42 @@ _equalOnConflictClause(const OnConflictClause *a, const OnConflictClause *b) } static bool +_equalCTESearchClause(const CTESearchClause *a, const CTESearchClause *b) +{ + COMPARE_NODE_FIELD(search_col_list); + COMPARE_SCALAR_FIELD(search_breadth_first); + COMPARE_STRING_FIELD(search_seq_column); + COMPARE_LOCATION_FIELD(location); + + return true; +} + +static bool +_equalCTECycleClause(const CTECycleClause *a, const CTECycleClause *b) +{ + COMPARE_NODE_FIELD(cycle_col_list); + COMPARE_STRING_FIELD(cycle_mark_column); + COMPARE_NODE_FIELD(cycle_mark_value); + COMPARE_NODE_FIELD(cycle_mark_default); + COMPARE_STRING_FIELD(cycle_path_column); + COMPARE_LOCATION_FIELD(location); + COMPARE_SCALAR_FIELD(cycle_mark_type); + COMPARE_SCALAR_FIELD(cycle_mark_typmod); + COMPARE_SCALAR_FIELD(cycle_mark_collation); + COMPARE_SCALAR_FIELD(cycle_mark_neop); + + return true; +} + +static bool _equalCommonTableExpr(const CommonTableExpr *a, const CommonTableExpr *b) { COMPARE_STRING_FIELD(ctename); COMPARE_NODE_FIELD(aliascolnames); COMPARE_SCALAR_FIELD(ctematerialized); COMPARE_NODE_FIELD(ctequery); + COMPARE_NODE_FIELD(search_clause); + COMPARE_NODE_FIELD(cycle_clause); COMPARE_LOCATION_FIELD(location); COMPARE_SCALAR_FIELD(cterecursive); COMPARE_SCALAR_FIELD(cterefcount); @@ -3735,6 +3765,12 @@ equal(const void *a, const void *b) case T_OnConflictClause: retval = _equalOnConflictClause(a, b); break; + case T_CTESearchClause: + retval = _equalCTESearchClause(a, b); + break; + case T_CTECycleClause: + retval = _equalCTECycleClause(a, b); + break; case T_CommonTableExpr: retval = _equalCommonTableExpr(a, b); break; diff --git a/src/backend/nodes/nodeFuncs.c b/src/backend/nodes/nodeFuncs.c index 6be19916fce..49357ac5c2d 100644 --- a/src/backend/nodes/nodeFuncs.c +++ b/src/backend/nodes/nodeFuncs.c @@ -1566,6 +1566,12 @@ exprLocation(const Node *expr) case T_OnConflictClause: loc = ((const OnConflictClause *) expr)->location; break; + case T_CTESearchClause: + loc = ((const CTESearchClause *) expr)->location; + break; + case T_CTECycleClause: + loc = ((const CTECycleClause *) expr)->location; + break; case T_CommonTableExpr: loc = ((const CommonTableExpr *) expr)->location; break; @@ -1909,6 +1915,7 @@ expression_tree_walker(Node *node, case T_NextValueExpr: case T_RangeTblRef: case T_SortGroupClause: + case T_CTESearchClause: /* primitive node types with no expression subnodes */ break; case T_WithCheckOption: @@ -2148,6 +2155,16 @@ expression_tree_walker(Node *node, return true; } break; + case T_CTECycleClause: + { + CTECycleClause *cc = (CTECycleClause *) node; + + if (walker(cc->cycle_mark_value, context)) + return true; + if (walker(cc->cycle_mark_default, context)) + return true; + } + break; case T_CommonTableExpr: { CommonTableExpr *cte = (CommonTableExpr *) node; @@ -2156,7 +2173,13 @@ expression_tree_walker(Node *node, * Invoke the walker on the CTE's Query node, so it can * recurse into the sub-query if it wants to. */ - return walker(cte->ctequery, context); + if (walker(cte->ctequery, context)) + return true; + + if (walker(cte->search_clause, context)) + return true; + if (walker(cte->cycle_clause, context)) + return true; } break; case T_List: @@ -2615,6 +2638,7 @@ expression_tree_mutator(Node *node, case T_NextValueExpr: case T_RangeTblRef: case T_SortGroupClause: + case T_CTESearchClause: return (Node *) copyObject(node); case T_WithCheckOption: { @@ -3019,6 +3043,17 @@ expression_tree_mutator(Node *node, return (Node *) newnode; } break; + case T_CTECycleClause: + { + CTECycleClause *cc = (CTECycleClause *) node; + CTECycleClause *newnode; + + FLATCOPY(newnode, cc, CTECycleClause); + MUTATE(newnode->cycle_mark_value, cc->cycle_mark_value, Node *); + MUTATE(newnode->cycle_mark_default, cc->cycle_mark_default, Node *); + return (Node *) newnode; + } + break; case T_CommonTableExpr: { CommonTableExpr *cte = (CommonTableExpr *) node; @@ -3031,6 +3066,10 @@ expression_tree_mutator(Node *node, * recurse into the sub-query if it wants to. */ MUTATE(newnode->ctequery, cte->ctequery, Node *); + + MUTATE(newnode->search_clause, cte->search_clause, CTESearchClause *); + MUTATE(newnode->cycle_clause, cte->cycle_clause, CTECycleClause *); + return (Node *) newnode; } break; @@ -3913,6 +3952,7 @@ raw_expression_tree_walker(Node *node, } break; case T_CommonTableExpr: + /* search_clause and cycle_clause are not interesting here */ return walker(((CommonTableExpr *) node)->ctequery, context); default: elog(ERROR, "unrecognized node type: %d", diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c index 8392be6d44a..fda732b4c2d 100644 --- a/src/backend/nodes/outfuncs.c +++ b/src/backend/nodes/outfuncs.c @@ -3078,6 +3078,34 @@ _outWithClause(StringInfo str, const WithClause *node) } static void +_outCTESearchClause(StringInfo str, const CTESearchClause *node) +{ + WRITE_NODE_TYPE("CTESEARCHCLAUSE"); + + WRITE_NODE_FIELD(search_col_list); + WRITE_BOOL_FIELD(search_breadth_first); + WRITE_STRING_FIELD(search_seq_column); + WRITE_LOCATION_FIELD(location); +} + +static void +_outCTECycleClause(StringInfo str, const CTECycleClause *node) +{ + WRITE_NODE_TYPE("CTECYCLECLAUSE"); + + WRITE_NODE_FIELD(cycle_col_list); + WRITE_STRING_FIELD(cycle_mark_column); + WRITE_NODE_FIELD(cycle_mark_value); + WRITE_NODE_FIELD(cycle_mark_default); + WRITE_STRING_FIELD(cycle_path_column); + WRITE_LOCATION_FIELD(location); + WRITE_OID_FIELD(cycle_mark_type); + WRITE_INT_FIELD(cycle_mark_typmod); + WRITE_OID_FIELD(cycle_mark_collation); + WRITE_OID_FIELD(cycle_mark_neop); +} + +static void _outCommonTableExpr(StringInfo str, const CommonTableExpr *node) { WRITE_NODE_TYPE("COMMONTABLEEXPR"); @@ -3086,6 +3114,8 @@ _outCommonTableExpr(StringInfo str, const CommonTableExpr *node) WRITE_NODE_FIELD(aliascolnames); WRITE_ENUM_FIELD(ctematerialized, CTEMaterialize); WRITE_NODE_FIELD(ctequery); + WRITE_NODE_FIELD(search_clause); + WRITE_NODE_FIELD(cycle_clause); WRITE_LOCATION_FIELD(location); WRITE_BOOL_FIELD(cterecursive); WRITE_INT_FIELD(cterefcount); @@ -4262,6 +4292,12 @@ outNode(StringInfo str, const void *obj) case T_WithClause: _outWithClause(str, obj); break; + case T_CTESearchClause: + _outCTESearchClause(str, obj); + break; + case T_CTECycleClause: + _outCTECycleClause(str, obj); + break; case T_CommonTableExpr: _outCommonTableExpr(str, obj); break; diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c index d2c8d58070b..4388aae71d2 100644 --- a/src/backend/nodes/readfuncs.c +++ b/src/backend/nodes/readfuncs.c @@ -410,6 +410,44 @@ _readRowMarkClause(void) } /* + * _readCTESearchClause + */ +static CTESearchClause * +_readCTESearchClause(void) +{ + READ_LOCALS(CTESearchClause); + + READ_NODE_FIELD(search_col_list); + READ_BOOL_FIELD(search_breadth_first); + READ_STRING_FIELD(search_seq_column); + READ_LOCATION_FIELD(location); + + READ_DONE(); +} + +/* + * _readCTECycleClause + */ +static CTECycleClause * +_readCTECycleClause(void) +{ + READ_LOCALS(CTECycleClause); + + READ_NODE_FIELD(cycle_col_list); + READ_STRING_FIELD(cycle_mark_column); + READ_NODE_FIELD(cycle_mark_value); + READ_NODE_FIELD(cycle_mark_default); + READ_STRING_FIELD(cycle_path_column); + READ_LOCATION_FIELD(location); + READ_OID_FIELD(cycle_mark_type); + READ_INT_FIELD(cycle_mark_typmod); + READ_OID_FIELD(cycle_mark_collation); + READ_OID_FIELD(cycle_mark_neop); + + READ_DONE(); +} + +/* * _readCommonTableExpr */ static CommonTableExpr * @@ -421,6 +459,8 @@ _readCommonTableExpr(void) READ_NODE_FIELD(aliascolnames); READ_ENUM_FIELD(ctematerialized, CTEMaterialize); READ_NODE_FIELD(ctequery); + READ_NODE_FIELD(search_clause); + READ_NODE_FIELD(cycle_clause); READ_LOCATION_FIELD(location); READ_BOOL_FIELD(cterecursive); READ_INT_FIELD(cterefcount); @@ -2653,6 +2693,10 @@ parseNodeString(void) return_value = _readWindowClause(); else if (MATCH("ROWMARKCLAUSE", 13)) return_value = _readRowMarkClause(); + else if (MATCH("CTESEARCHCLAUSE", 15)) + return_value = _readCTESearchClause(); + else if (MATCH("CTECYCLECLAUSE", 14)) + return_value = _readCTECycleClause(); else if (MATCH("COMMONTABLEEXPR", 15)) return_value = _readCommonTableExpr(); else if (MATCH("SETOPERATIONSTMT", 16)) diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c index 65483892252..0f3a70c49a8 100644 --- a/src/backend/parser/analyze.c +++ b/src/backend/parser/analyze.c @@ -1810,6 +1810,33 @@ transformSetOperationStmt(ParseState *pstate, SelectStmt *stmt) } /* + * Make a SortGroupClause node for a SetOperationStmt's groupClauses + */ +SortGroupClause * +makeSortGroupClauseForSetOp(Oid rescoltype) +{ + SortGroupClause *grpcl = makeNode(SortGroupClause); + Oid sortop; + Oid eqop; + bool hashable; + + /* determine the eqop and optional sortop */ + get_sort_group_operators(rescoltype, + false, true, false, + &sortop, &eqop, NULL, + &hashable); + + /* we don't have a tlist yet, so can't assign sortgrouprefs */ + grpcl->tleSortGroupRef = 0; + grpcl->eqop = eqop; + grpcl->sortop = sortop; + grpcl->nulls_first = false; /* OK with or without sortop */ + grpcl->hashable = hashable; + + return grpcl; +} + +/* * transformSetOperationTree * Recursively transform leaves and internal nodes of a set-op tree * @@ -2109,31 +2136,15 @@ transformSetOperationTree(ParseState *pstate, SelectStmt *stmt, */ if (op->op != SETOP_UNION || !op->all) { - SortGroupClause *grpcl = makeNode(SortGroupClause); - Oid sortop; - Oid eqop; - bool hashable; ParseCallbackState pcbstate; setup_parser_errposition_callback(&pcbstate, pstate, bestlocation); - /* determine the eqop and optional sortop */ - get_sort_group_operators(rescoltype, - false, true, false, - &sortop, &eqop, NULL, - &hashable); + op->groupClauses = lappend(op->groupClauses, + makeSortGroupClauseForSetOp(rescoltype)); cancel_parser_errposition_callback(&pcbstate); - - /* we don't have a tlist yet, so can't assign sortgrouprefs */ - grpcl->tleSortGroupRef = 0; - grpcl->eqop = eqop; - grpcl->sortop = sortop; - grpcl->nulls_first = false; /* OK with or without sortop */ - grpcl->hashable = hashable; - - op->groupClauses = lappend(op->groupClauses, grpcl); } /* diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index b2f447bf9a2..dd72a9fc3c4 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -494,6 +494,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); %type <list> row explicit_row implicit_row type_list array_expr_list %type <node> case_expr case_arg when_clause case_default %type <list> when_clause_list +%type <node> opt_search_clause opt_cycle_clause %type <ival> sub_type opt_materialized %type <value> NumericOnly %type <list> NumericOnly_list @@ -625,7 +626,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); ASSERTION ASSIGNMENT ASYMMETRIC AT ATTACH ATTRIBUTE AUTHORIZATION BACKWARD BEFORE BEGIN_P BETWEEN BIGINT BINARY BIT - BOOLEAN_P BOTH BY + BOOLEAN_P BOTH BREADTH BY CACHE CALL CALLED CASCADE CASCADED CASE CAST CATALOG_P CHAIN CHAR_P CHARACTER CHARACTERISTICS CHECK CHECKPOINT CLASS CLOSE @@ -637,7 +638,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE DATA_P DATABASE DAY_P DEALLOCATE DEC DECIMAL_P DECLARE DEFAULT DEFAULTS - DEFERRABLE DEFERRED DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DESC + DEFERRABLE DEFERRED DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC DETACH DICTIONARY DISABLE_P DISCARD DISTINCT DO DOCUMENT_P DOMAIN_P DOUBLE_P DROP @@ -11353,8 +11354,6 @@ simple_select: * WITH [ RECURSIVE ] <query name> [ (<column>,...) ] * AS (query) [ SEARCH or CYCLE clause ] * - * We don't currently support the SEARCH or CYCLE clause. - * * Recognizing WITH_LA here allows a CTE to be named TIME or ORDINALITY. */ with_clause: @@ -11386,13 +11385,15 @@ cte_list: | cte_list ',' common_table_expr { $$ = lappend($1, $3); } ; -common_table_expr: name opt_name_list AS opt_materialized '(' PreparableStmt ')' +common_table_expr: name opt_name_list AS opt_materialized '(' PreparableStmt ')' opt_search_clause opt_cycle_clause { CommonTableExpr *n = makeNode(CommonTableExpr); n->ctename = $1; n->aliascolnames = $2; n->ctematerialized = $4; n->ctequery = $6; + n->search_clause = castNode(CTESearchClause, $8); + n->cycle_clause = castNode(CTECycleClause, $9); n->location = @1; $$ = (Node *) n; } @@ -11404,6 +11405,49 @@ opt_materialized: | /*EMPTY*/ { $$ = CTEMaterializeDefault; } ; +opt_search_clause: + SEARCH DEPTH FIRST_P BY columnList SET ColId + { + CTESearchClause *n = makeNode(CTESearchClause); + n->search_col_list = $5; + n->search_breadth_first = false; + n->search_seq_column = $7; + n->location = @1; + $$ = (Node *) n; + } + | SEARCH BREADTH FIRST_P BY columnList SET ColId + { + CTESearchClause *n = makeNode(CTESearchClause); + n->search_col_list = $5; + n->search_breadth_first = true; + n->search_seq_column = $7; + n->location = @1; + $$ = (Node *) n; + } + | /*EMPTY*/ + { + $$ = NULL; + } + ; + +opt_cycle_clause: + CYCLE columnList SET ColId TO AexprConst DEFAULT AexprConst USING ColId + { + CTECycleClause *n = makeNode(CTECycleClause); + n->cycle_col_list = $2; + n->cycle_mark_column = $4; + n->cycle_mark_value = $6; + n->cycle_mark_default = $8; + n->cycle_path_column = $10; + n->location = @1; + $$ = (Node *) n; + } + | /*EMPTY*/ + { + $$ = NULL; + } + ; + opt_with_clause: with_clause { $$ = $1; } | /*EMPTY*/ { $$ = NULL; } @@ -15222,6 +15266,7 @@ unreserved_keyword: | BACKWARD | BEFORE | BEGIN_P + | BREADTH | BY | CACHE | CALL @@ -15266,6 +15311,7 @@ unreserved_keyword: | DELIMITER | DELIMITERS | DEPENDS + | DEPTH | DETACH | DICTIONARY | DISABLE_P @@ -15733,6 +15779,7 @@ bare_label_keyword: | BIT | BOOLEAN_P | BOTH + | BREADTH | BY | CACHE | CALL @@ -15797,6 +15844,7 @@ bare_label_keyword: | DELIMITER | DELIMITERS | DEPENDS + | DEPTH | DESC | DETACH | DICTIONARY diff --git a/src/backend/parser/parse_agg.c b/src/backend/parser/parse_agg.c index 588f005dd93..fd08b9eeff0 100644 --- a/src/backend/parser/parse_agg.c +++ b/src/backend/parser/parse_agg.c @@ -545,6 +545,10 @@ check_agglevels_and_constraints(ParseState *pstate, Node *expr) break; + case EXPR_KIND_CYCLE_MARK: + errkind = true; + break; + /* * There is intentionally no default: case here, so that the * compiler will warn if we add a new ParseExprKind without @@ -933,6 +937,9 @@ transformWindowFuncCall(ParseState *pstate, WindowFunc *wfunc, case EXPR_KIND_GENERATED_COLUMN: err = _("window functions are not allowed in column generation expressions"); break; + case EXPR_KIND_CYCLE_MARK: + errkind = true; + break; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_cte.c b/src/backend/parser/parse_cte.c index 4e0029c58c9..f4f7041ead0 100644 --- a/src/backend/parser/parse_cte.c +++ b/src/backend/parser/parse_cte.c @@ -18,9 +18,13 @@ #include "catalog/pg_type.h" #include "nodes/nodeFuncs.h" #include "parser/analyze.h" +#include "parser/parse_coerce.h" +#include "parser/parse_collate.h" #include "parser/parse_cte.h" +#include "parser/parse_expr.h" #include "utils/builtins.h" #include "utils/lsyscache.h" +#include "utils/typcache.h" /* Enumeration of contexts in which a self-reference is disallowed */ @@ -334,6 +338,195 @@ analyzeCTE(ParseState *pstate, CommonTableExpr *cte) if (lctyp != NULL || lctypmod != NULL || lccoll != NULL) /* shouldn't happen */ elog(ERROR, "wrong number of output columns in WITH"); } + + if (cte->search_clause || cte->cycle_clause) + { + Query *ctequery; + SetOperationStmt *sos; + + if (!cte->cterecursive) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("WITH query is not recursive"), + parser_errposition(pstate, cte->location))); + + /* + * SQL requires a WITH list element (CTE) to be "expandable" in order + * to allow a search or cycle clause. That is a stronger requirement + * than just being recursive. It basically means the query expression + * looks like + * + * non-recursive query UNION [ALL] recursive query + * + * and that the recursive query is not itself a set operation. + * + * As of this writing, most of these criteria are already satisfied by + * all recursive CTEs allowed by PostgreSQL. In the future, if + * further variants recursive CTEs are accepted, there might be + * further checks required here to determine what is "expandable". + */ + + ctequery = castNode(Query, cte->ctequery); + Assert(ctequery->setOperations); + sos = castNode(SetOperationStmt, ctequery->setOperations); + + /* + * This left side check is not required for expandability, but + * rewriteSearchAndCycle() doesn't currently have support for it, so + * we catch it here. + */ + if (!IsA(sos->larg, RangeTblRef)) + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("with a SEARCH or CYCLE clause, the left side of the UNION must be a SELECT"))); + + if (!IsA(sos->rarg, RangeTblRef)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("with a SEARCH or CYCLE clause, the right side of the UNION must be a SELECT"))); + } + + if (cte->search_clause) + { + ListCell *lc; + List *seen = NIL; + + foreach(lc, cte->search_clause->search_col_list) + { + Value *colname = lfirst(lc); + + if (!list_member(cte->ctecolnames, colname)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("search column \"%s\" not in WITH query column list", + strVal(colname)), + parser_errposition(pstate, cte->search_clause->location))); + + if (list_member(seen, colname)) + ereport(ERROR, + (errcode(ERRCODE_DUPLICATE_COLUMN), + errmsg("search column \"%s\" specified more than once", + strVal(colname)), + parser_errposition(pstate, cte->search_clause->location))); + seen = lappend(seen, colname); + } + + if (list_member(cte->ctecolnames, makeString(cte->search_clause->search_seq_column))) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("search sequence column name \"%s\" already used in WITH query column list", + cte->search_clause->search_seq_column), + parser_errposition(pstate, cte->search_clause->location)); + } + + if (cte->cycle_clause) + { + ListCell *lc; + List *seen = NIL; + TypeCacheEntry *typentry; + Oid op; + + foreach(lc, cte->cycle_clause->cycle_col_list) + { + Value *colname = lfirst(lc); + + if (!list_member(cte->ctecolnames, colname)) + ereport(ERROR, + (errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cycle column \"%s\" not in WITH query column list", + strVal(colname)), + parser_errposition(pstate, cte->cycle_clause->location))); + + if (list_member(seen, colname)) + ereport(ERROR, + (errcode(ERRCODE_DUPLICATE_COLUMN), + errmsg("cycle column \"%s\" specified more than once", + strVal(colname)), + parser_errposition(pstate, cte->cycle_clause->location))); + seen = lappend(seen, colname); + } + + if (list_member(cte->ctecolnames, makeString(cte->cycle_clause->cycle_mark_column))) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cycle mark column name \"%s\" already used in WITH query column list", + cte->cycle_clause->cycle_mark_column), + parser_errposition(pstate, cte->cycle_clause->location)); + + cte->cycle_clause->cycle_mark_value = transformExpr(pstate, cte->cycle_clause->cycle_mark_value, + EXPR_KIND_CYCLE_MARK); + cte->cycle_clause->cycle_mark_default = transformExpr(pstate, cte->cycle_clause->cycle_mark_default, + EXPR_KIND_CYCLE_MARK); + + if (list_member(cte->ctecolnames, makeString(cte->cycle_clause->cycle_path_column))) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cycle path column name \"%s\" already used in WITH query column list", + cte->cycle_clause->cycle_path_column), + parser_errposition(pstate, cte->cycle_clause->location)); + + if (strcmp(cte->cycle_clause->cycle_mark_column, + cte->cycle_clause->cycle_path_column) == 0) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("cycle mark column name and cycle path column name are the same"), + parser_errposition(pstate, cte->cycle_clause->location)); + + cte->cycle_clause->cycle_mark_type = select_common_type(pstate, + list_make2(cte->cycle_clause->cycle_mark_value, + cte->cycle_clause->cycle_mark_default), + "CYCLE", NULL); + cte->cycle_clause->cycle_mark_value = coerce_to_common_type(pstate, + cte->cycle_clause->cycle_mark_value, + cte->cycle_clause->cycle_mark_type, + "CYCLE/SET/TO"); + cte->cycle_clause->cycle_mark_default = coerce_to_common_type(pstate, + cte->cycle_clause->cycle_mark_default, + cte->cycle_clause->cycle_mark_type, + "CYCLE/SET/DEFAULT"); + + cte->cycle_clause->cycle_mark_typmod = select_common_typmod(pstate, + list_make2(cte->cycle_clause->cycle_mark_value, + cte->cycle_clause->cycle_mark_default), + cte->cycle_clause->cycle_mark_type); + + cte->cycle_clause->cycle_mark_collation = select_common_collation(pstate, + list_make2(cte->cycle_clause->cycle_mark_value, + cte->cycle_clause->cycle_mark_default), + true); + + typentry = lookup_type_cache(cte->cycle_clause->cycle_mark_type, TYPECACHE_EQ_OPR); + if (!typentry->eq_opr) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_FUNCTION), + errmsg("could not identify an equality operator for type %s", + format_type_be(cte->cycle_clause->cycle_mark_type))); + op = get_negator(typentry->eq_opr); + if (!op) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_FUNCTION), + errmsg("could not identify an inequality operator for type %s", + format_type_be(cte->cycle_clause->cycle_mark_type))); + + cte->cycle_clause->cycle_mark_neop = op; + } + + if (cte->search_clause && cte->cycle_clause) + { + if (strcmp(cte->search_clause->search_seq_column, + cte->cycle_clause->cycle_mark_column) == 0) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("search sequence column name and cycle mark column name are the same"), + parser_errposition(pstate, cte->search_clause->location)); + + if (strcmp(cte->search_clause->search_seq_column, + cte->cycle_clause->cycle_path_column) == 0) + ereport(ERROR, + errcode(ERRCODE_SYNTAX_ERROR), + errmsg("search_sequence column name and cycle path column name are the same"), + parser_errposition(pstate, cte->search_clause->location)); + } } /* diff --git a/src/backend/parser/parse_expr.c b/src/backend/parser/parse_expr.c index 379355f9bff..6c87783b2c7 100644 --- a/src/backend/parser/parse_expr.c +++ b/src/backend/parser/parse_expr.c @@ -507,6 +507,7 @@ transformColumnRef(ParseState *pstate, ColumnRef *cref) case EXPR_KIND_CALL_ARGUMENT: case EXPR_KIND_COPY_WHERE: case EXPR_KIND_GENERATED_COLUMN: + case EXPR_KIND_CYCLE_MARK: /* okay */ break; @@ -1723,6 +1724,7 @@ transformSubLink(ParseState *pstate, SubLink *sublink) case EXPR_KIND_RETURNING: case EXPR_KIND_VALUES: case EXPR_KIND_VALUES_SINGLE: + case EXPR_KIND_CYCLE_MARK: /* okay */ break; case EXPR_KIND_CHECK_CONSTRAINT: @@ -3044,6 +3046,8 @@ ParseExprKindName(ParseExprKind exprKind) return "WHERE"; case EXPR_KIND_GENERATED_COLUMN: return "GENERATED AS"; + case EXPR_KIND_CYCLE_MARK: + return "CYCLE"; /* * 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 07d0013e84b..37cebc7d829 100644 --- a/src/backend/parser/parse_func.c +++ b/src/backend/parser/parse_func.c @@ -2527,6 +2527,9 @@ check_srf_call_placement(ParseState *pstate, Node *last_srf, int location) case EXPR_KIND_GENERATED_COLUMN: err = _("set-returning functions are not allowed in column generation expressions"); break; + case EXPR_KIND_CYCLE_MARK: + errkind = true; + break; /* * There is intentionally no default: case here, so that the diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c index e490043cf55..43db4e9af8b 100644 --- a/src/backend/parser/parse_relation.c +++ b/src/backend/parser/parse_relation.c @@ -2235,6 +2235,8 @@ addRangeTableEntryForCTE(ParseState *pstate, int numaliases; int varattno; ListCell *lc; + int n_dontexpand_columns = 0; + ParseNamespaceItem *psi; Assert(pstate != NULL); @@ -2267,9 +2269,9 @@ addRangeTableEntryForCTE(ParseState *pstate, parser_errposition(pstate, rv->location))); } - rte->coltypes = cte->ctecoltypes; - rte->coltypmods = cte->ctecoltypmods; - rte->colcollations = cte->ctecolcollations; + rte->coltypes = list_copy(cte->ctecoltypes); + rte->coltypmods = list_copy(cte->ctecoltypmods); + rte->colcollations = list_copy(cte->ctecolcollations); rte->alias = alias; if (alias) @@ -2294,6 +2296,34 @@ addRangeTableEntryForCTE(ParseState *pstate, rte->eref = eref; + if (cte->search_clause) + { + rte->eref->colnames = lappend(rte->eref->colnames, makeString(cte->search_clause->search_seq_column)); + if (cte->search_clause->search_breadth_first) + rte->coltypes = lappend_oid(rte->coltypes, RECORDOID); + else + rte->coltypes = lappend_oid(rte->coltypes, RECORDARRAYOID); + rte->coltypmods = lappend_int(rte->coltypmods, -1); + rte->colcollations = lappend_oid(rte->colcollations, InvalidOid); + + n_dontexpand_columns += 1; + } + + if (cte->cycle_clause) + { + rte->eref->colnames = lappend(rte->eref->colnames, makeString(cte->cycle_clause->cycle_mark_column)); + rte->coltypes = lappend_oid(rte->coltypes, cte->cycle_clause->cycle_mark_type); + rte->coltypmods = lappend_int(rte->coltypmods, cte->cycle_clause->cycle_mark_typmod); + rte->colcollations = lappend_oid(rte->colcollations, cte->cycle_clause->cycle_mark_collation); + + rte->eref->colnames = lappend(rte->eref->colnames, makeString(cte->cycle_clause->cycle_path_column)); + rte->coltypes = lappend_oid(rte->coltypes, RECORDARRAYOID); + rte->coltypmods = lappend_int(rte->coltypmods, -1); + rte->colcollations = lappend_oid(rte->colcollations, InvalidOid); + + n_dontexpand_columns += 2; + } + /* * Set flags and access permissions. * @@ -2321,9 +2351,19 @@ addRangeTableEntryForCTE(ParseState *pstate, * Build a ParseNamespaceItem, but don't add it to the pstate's namespace * list --- caller must do that if appropriate. */ - return buildNSItemFromLists(rte, list_length(pstate->p_rtable), + psi = buildNSItemFromLists(rte, list_length(pstate->p_rtable), rte->coltypes, rte->coltypmods, rte->colcollations); + + /* + * The columns added by search and cycle clauses are not included in star + * expansion in queries contained in the CTE. + */ + if (rte->ctelevelsup > 0) + for (int i = 0; i < n_dontexpand_columns; i++) + psi->p_nscolumns[list_length(psi->p_rte->eref->colnames) - 1 - i].p_dontexpand = true; + + return psi; } /* @@ -3008,7 +3048,11 @@ expandNSItemVars(ParseNamespaceItem *nsitem, const char *colname = strVal(colnameval); ParseNamespaceColumn *nscol = nsitem->p_nscolumns + colindex; - if (colname[0]) + if (nscol->p_dontexpand) + { + /* skip */ + } + else if (colname[0]) { Var *var; diff --git a/src/backend/parser/parse_target.c b/src/backend/parser/parse_target.c index 7eaa076771a..51ecc16c42e 100644 --- a/src/backend/parser/parse_target.c +++ b/src/backend/parser/parse_target.c @@ -399,8 +399,23 @@ markTargetListOrigin(ParseState *pstate, TargetEntry *tle, { CommonTableExpr *cte = GetCTEForRTE(pstate, rte, netlevelsup); TargetEntry *ste; + List *tl = GetCTETargetList(cte); + int extra_cols = 0; + + /* + * RTE for CTE will already have the search and cycle columns + * added, but the subquery won't, so skip looking those up. + */ + if (cte->search_clause) + extra_cols += 1; + if (cte->cycle_clause) + extra_cols += 2; + if (extra_cols && + attnum > list_length(tl) && + attnum <= list_length(tl) + extra_cols) + break; - ste = get_tle_by_resno(GetCTETargetList(cte), attnum); + ste = get_tle_by_resno(tl, attnum); if (ste == NULL || ste->resjunk) elog(ERROR, "CTE %s does not have attribute %d", rte->eref->aliasname, attnum); diff --git a/src/backend/rewrite/Makefile b/src/backend/rewrite/Makefile index b435b3e985c..4680752e6a7 100644 --- a/src/backend/rewrite/Makefile +++ b/src/backend/rewrite/Makefile @@ -17,6 +17,7 @@ OBJS = \ rewriteHandler.o \ rewriteManip.o \ rewriteRemove.o \ + rewriteSearchCycle.o \ rewriteSupport.o \ rowsecurity.o diff --git a/src/backend/rewrite/rewriteHandler.c b/src/backend/rewrite/rewriteHandler.c index 0c7508a0d8b..0672f497c6b 100644 --- a/src/backend/rewrite/rewriteHandler.c +++ b/src/backend/rewrite/rewriteHandler.c @@ -38,6 +38,7 @@ #include "rewrite/rewriteDefine.h" #include "rewrite/rewriteHandler.h" #include "rewrite/rewriteManip.h" +#include "rewrite/rewriteSearchCycle.h" #include "rewrite/rowsecurity.h" #include "utils/builtins.h" #include "utils/lsyscache.h" @@ -2080,6 +2081,23 @@ fireRIRrules(Query *parsetree, List *activeRIRs) ListCell *lc; /* + * Expand SEARCH and CYCLE clauses in CTEs. + * + * This is just a convenient place to do this, since we are already + * looking at each Query. + */ + foreach(lc, parsetree->cteList) + { + CommonTableExpr *cte = lfirst_node(CommonTableExpr, lc); + + if (cte->search_clause || cte->cycle_clause) + { + cte = rewriteSearchAndCycle(cte); + lfirst(lc) = cte; + } + } + + /* * don't try to convert this into a foreach loop, because rtable list can * get changed each time through... */ diff --git a/src/backend/rewrite/rewriteSearchCycle.c b/src/backend/rewrite/rewriteSearchCycle.c new file mode 100644 index 00000000000..1a7d66fa6f9 --- /dev/null +++ b/src/backend/rewrite/rewriteSearchCycle.c @@ -0,0 +1,668 @@ +/*------------------------------------------------------------------------- + * + * rewriteSearchCycle.c + * Support for rewriting SEARCH and CYCLE clauses. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/rewrite/rewriteSearchCycle.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "catalog/pg_operator_d.h" +#include "catalog/pg_type_d.h" +#include "nodes/makefuncs.h" +#include "nodes/pg_list.h" +#include "nodes/parsenodes.h" +#include "nodes/primnodes.h" +#include "parser/analyze.h" +#include "parser/parsetree.h" +#include "rewrite/rewriteManip.h" +#include "rewrite/rewriteSearchCycle.h" +#include "utils/fmgroids.h" + + +/*---------- + * Rewrite a CTE with SEARCH or CYCLE clause + * + * Consider a CTE like + * + * WITH RECURSIVE ctename (col1, col2, col3) AS ( + * query1 + * UNION [ALL] + * SELECT trosl FROM ctename + * ) + * + * With a search clause + * + * SEARCH BREADTH FIRST BY col1, col2 SET sqc + * + * the CTE is rewritten to + * + * WITH RECURSIVE ctename (col1, col2, col3, sqc) AS ( + * SELECT col1, col2, col3, -- original WITH column list + * ROW(0, col1, col2) -- initial row of search columns + * FROM (query1) "*TLOCRN*" (col1, col2, col3) + * UNION [ALL] + * SELECT col1, col2, col3, -- same as above + * ROW(sqc.depth + 1, col1, col2) -- count depth + * FROM (SELECT trosl, ctename.sqc FROM ctename) "*TROCRN*" (col1, col2, col3, sqc) + * ) + * + * (This isn't quite legal SQL: sqc.depth is meant to refer to the first + * column of sqc, which has a row type, but the field names are not defined + * here. Representing this properly in SQL would be more complicated (and the + * SQL standard actually does it in that more complicated way), but the + * internal representation allows us to construct it this way.) + * + * With a search caluse + * + * SEARCH DEPTH FIRST BY col1, col2 SET sqc + * + * the CTE is rewritten to + * + * WITH RECURSIVE ctename (col1, col2, col3, sqc) AS ( + * SELECT col1, col2, col3, -- original WITH column list + * ARRAY[ROW(col1, col2)] -- initial row of search columns + * FROM (query1) "*TLOCRN*" (col1, col2, col3) + * UNION [ALL] + * SELECT col1, col2, col3, -- same as above + * sqc || ARRAY[ROW(col1, col2)] -- record rows seen + * FROM (SELECT trosl, ctename.sqc FROM ctename) "*TROCRN*" (col1, col2, col3, sqc) + * ) + * + * With a cycle clause + * + * CYCLE col1, col2 SET cmc TO 'Y' DEFAULT 'N' USING cpa + * + * (cmc = cycle mark column, cpa = cycle path) the CTE is rewritten to + * + * WITH RECURSIVE ctename (col1, col2, col3, cmc, cpa) AS ( + * SELECT col1, col2, col3, -- original WITH column list + * 'N', -- cycle mark default + * ARRAY[ROW(col1, col2)] -- initial row of cycle columns + * FROM (query1) "*TLOCRN*" (col1, col2, col3) + * UNION [ALL] + * SELECT col1, col2, col3, -- same as above + * CASE WHEN ROW(col1, col2) = ANY (ARRAY[cpa]) THEN 'Y' ELSE 'N' END, -- compute cycle mark column + * cpa || ARRAY[ROW(col1, col2)] -- record rows seen + * FROM (SELECT trosl, ctename.cmc, ctename.cpa FROM ctename) "*TROCRN*" (col1, col2, col3, cmc, cpa) + * WHERE cmc <> 'Y' + * ) + * + * The expression to compute the cycle mark column in the right-hand query is + * written as + * + * CASE WHEN ROW(col1, col2) IN (SELECT p.* FROM TABLE(cpa) p) THEN cmv ELSE cmd END + * + * in the SQL standard, but in PostgreSQL we can use the scalar-array operator + * expression shown above. + * + * Also, in some of the cases where operators are shown above we actually + * directly produce the underlying function call. + * + * If both a search clause and a cycle clause is specified, then the search + * clause column is added before the cycle clause columns. + */ + +/* + * Make a RowExpr from the specified column names, which have to be among the + * output columns of the CTE. + */ +static RowExpr * +make_path_rowexpr(const CommonTableExpr *cte, const List *col_list) +{ + RowExpr *rowexpr; + ListCell *lc; + + rowexpr = makeNode(RowExpr); + rowexpr->row_typeid = RECORDOID; + rowexpr->row_format = COERCE_IMPLICIT_CAST; + rowexpr->location = -1; + + foreach(lc, col_list) + { + char *colname = strVal(lfirst(lc)); + + for (int i = 0; i < list_length(cte->ctecolnames); i++) + { + char *colname2 = strVal(list_nth(cte->ctecolnames, i)); + + if (strcmp(colname, colname2) == 0) + { + Var *var; + + var = makeVar(1, i + 1, + list_nth_oid(cte->ctecoltypes, i), + list_nth_int(cte->ctecoltypmods, i), + list_nth_oid(cte->ctecolcollations, i), + 0); + rowexpr->args = lappend(rowexpr->args, var); + rowexpr->colnames = lappend(rowexpr->colnames, makeString(colname)); + break; + } + } + } + + return rowexpr; +} + +/* + * Wrap a RowExpr in an ArrayExpr, for the initial search depth first or cycle + * row. + */ +static Expr * +make_path_initial_array(RowExpr *rowexpr) +{ + ArrayExpr *arr; + + arr = makeNode(ArrayExpr); + arr->array_typeid = RECORDARRAYOID; + arr->element_typeid = RECORDOID; + arr->location = -1; + arr->elements = list_make1(rowexpr); + + return (Expr *) arr; +} + +/* + * Make an array catenation expression like + * + * cpa || ARRAY[ROW(cols)] + * + * where the varattno of cpa is provided as path_varattno. + */ +static Expr * +make_path_cat_expr(RowExpr *rowexpr, AttrNumber path_varattno) +{ + ArrayExpr *arr; + FuncExpr *fexpr; + + arr = makeNode(ArrayExpr); + arr->array_typeid = RECORDARRAYOID; + arr->element_typeid = RECORDOID; + arr->location = -1; + arr->elements = list_make1(rowexpr); + + fexpr = makeFuncExpr(F_ARRAY_CAT, RECORDARRAYOID, + list_make2(makeVar(1, path_varattno, RECORDARRAYOID, -1, 0, 0), + arr), + InvalidOid, InvalidOid, COERCE_EXPLICIT_CALL); + + return (Expr *) fexpr; +} + +/* + * The real work happens here. + */ +CommonTableExpr * +rewriteSearchAndCycle(CommonTableExpr *cte) +{ + Query *ctequery; + SetOperationStmt *sos; + int rti1, + rti2; + RangeTblEntry *rte1, + *rte2, + *newrte; + Query *newq1, + *newq2; + Query *newsubquery; + RangeTblRef *rtr; + Oid search_seq_type = InvalidOid; + AttrNumber sqc_attno = InvalidAttrNumber; + AttrNumber cmc_attno = InvalidAttrNumber; + AttrNumber cpa_attno = InvalidAttrNumber; + TargetEntry *tle; + RowExpr *cycle_col_rowexpr = NULL; + RowExpr *search_col_rowexpr = NULL; + List *ewcl; + int cte_rtindex = -1; + + Assert(cte->search_clause || cte->cycle_clause); + + cte = copyObject(cte); + + ctequery = castNode(Query, cte->ctequery); + + /* + * The top level of the CTE's query should be a UNION. Find the two + * subqueries. + */ + Assert(ctequery->setOperations); + sos = castNode(SetOperationStmt, ctequery->setOperations); + Assert(sos->op == SETOP_UNION); + + rti1 = castNode(RangeTblRef, sos->larg)->rtindex; + rti2 = castNode(RangeTblRef, sos->rarg)->rtindex; + + rte1 = rt_fetch(rti1, ctequery->rtable); + rte2 = rt_fetch(rti2, ctequery->rtable); + + Assert(rte1->rtekind == RTE_SUBQUERY); + Assert(rte2->rtekind == RTE_SUBQUERY); + + /* + * We'll need this a few times later. + */ + if (cte->search_clause) + { + if (cte->search_clause->search_breadth_first) + search_seq_type = RECORDOID; + else + search_seq_type = RECORDARRAYOID; + } + + /* + * Attribute numbers of the added columns in the CTE's column list + */ + if (cte->search_clause) + sqc_attno = list_length(cte->ctecolnames) + 1; + if (cte->cycle_clause) + { + cmc_attno = list_length(cte->ctecolnames) + 1; + cpa_attno = list_length(cte->ctecolnames) + 2; + if (cte->search_clause) + { + cmc_attno++; + cpa_attno++; + } + } + + /* + * Make new left subquery + */ + newq1 = makeNode(Query); + newq1->commandType = CMD_SELECT; + newq1->canSetTag = true; + + newrte = makeNode(RangeTblEntry); + newrte->rtekind = RTE_SUBQUERY; + newrte->alias = makeAlias("*TLOCRN*", cte->ctecolnames); + newrte->eref = newrte->alias; + newsubquery = copyObject(rte1->subquery); + IncrementVarSublevelsUp((Node *) newsubquery, 1, 1); + newrte->subquery = newsubquery; + newrte->inFromCl = true; + newq1->rtable = list_make1(newrte); + + rtr = makeNode(RangeTblRef); + rtr->rtindex = 1; + newq1->jointree = makeFromExpr(list_make1(rtr), NULL); + + /* + * Make target list + */ + for (int i = 0; i < list_length(cte->ctecolnames); i++) + { + Var *var; + + var = makeVar(1, i + 1, + list_nth_oid(cte->ctecoltypes, i), + list_nth_int(cte->ctecoltypmods, i), + list_nth_oid(cte->ctecolcollations, i), + 0); + tle = makeTargetEntry((Expr *) var, i + 1, strVal(list_nth(cte->ctecolnames, i)), false); + tle->resorigtbl = castNode(TargetEntry, list_nth(rte1->subquery->targetList, i))->resorigtbl; + tle->resorigcol = castNode(TargetEntry, list_nth(rte1->subquery->targetList, i))->resorigcol; + newq1->targetList = lappend(newq1->targetList, tle); + } + + if (cte->search_clause) + { + Expr *texpr; + + search_col_rowexpr = make_path_rowexpr(cte, cte->search_clause->search_col_list); + if (cte->search_clause->search_breadth_first) + { + search_col_rowexpr->args = lcons(makeConst(INT8OID, -1, InvalidOid, sizeof(int64), + Int64GetDatum(0), false, FLOAT8PASSBYVAL), + search_col_rowexpr->args); + search_col_rowexpr->colnames = lcons(makeString("*DEPTH*"), search_col_rowexpr->colnames); + texpr = (Expr *) search_col_rowexpr; + } + else + texpr = make_path_initial_array(search_col_rowexpr); + tle = makeTargetEntry(texpr, + list_length(newq1->targetList) + 1, + cte->search_clause->search_seq_column, + false); + newq1->targetList = lappend(newq1->targetList, tle); + } + if (cte->cycle_clause) + { + tle = makeTargetEntry((Expr *) cte->cycle_clause->cycle_mark_default, + list_length(newq1->targetList) + 1, + cte->cycle_clause->cycle_mark_column, + false); + newq1->targetList = lappend(newq1->targetList, tle); + cycle_col_rowexpr = make_path_rowexpr(cte, cte->cycle_clause->cycle_col_list); + tle = makeTargetEntry(make_path_initial_array(cycle_col_rowexpr), + list_length(newq1->targetList) + 1, + cte->cycle_clause->cycle_path_column, + false); + newq1->targetList = lappend(newq1->targetList, tle); + } + + rte1->subquery = newq1; + + if (cte->search_clause) + { + rte1->eref->colnames = lappend(rte1->eref->colnames, makeString(cte->search_clause->search_seq_column)); + } + if (cte->cycle_clause) + { + rte1->eref->colnames = lappend(rte1->eref->colnames, makeString(cte->cycle_clause->cycle_mark_column)); + rte1->eref->colnames = lappend(rte1->eref->colnames, makeString(cte->cycle_clause->cycle_path_column)); + } + + /* + * Make new right subquery + */ + newq2 = makeNode(Query); + newq2->commandType = CMD_SELECT; + newq2->canSetTag = true; + + newrte = makeNode(RangeTblEntry); + newrte->rtekind = RTE_SUBQUERY; + ewcl = copyObject(cte->ctecolnames); + if (cte->search_clause) + { + ewcl = lappend(ewcl, makeString(cte->search_clause->search_seq_column)); + } + if (cte->cycle_clause) + { + ewcl = lappend(ewcl, makeString(cte->cycle_clause->cycle_mark_column)); + ewcl = lappend(ewcl, makeString(cte->cycle_clause->cycle_path_column)); + } + newrte->alias = makeAlias("*TROCRN*", ewcl); + newrte->eref = newrte->alias; + + /* + * Find the reference to our CTE in the range table + */ + for (int rti = 1; rti <= list_length(rte2->subquery->rtable); rti++) + { + RangeTblEntry *e = rt_fetch(rti, rte2->subquery->rtable); + + if (e->rtekind == RTE_CTE && strcmp(cte->ctename, e->ctename) == 0) + { + cte_rtindex = rti; + break; + } + } + Assert(cte_rtindex > 0); + + newsubquery = copyObject(rte2->subquery); + IncrementVarSublevelsUp((Node *) newsubquery, 1, 1); + + /* + * Add extra columns to target list of subquery of right subquery + */ + if (cte->search_clause) + { + Var *var; + + /* ctename.sqc */ + var = makeVar(cte_rtindex, sqc_attno, + search_seq_type, -1, InvalidOid, 0); + tle = makeTargetEntry((Expr *) var, + list_length(newsubquery->targetList) + 1, + cte->search_clause->search_seq_column, + false); + newsubquery->targetList = lappend(newsubquery->targetList, tle); + } + if (cte->cycle_clause) + { + Var *var; + + /* ctename.cmc */ + var = makeVar(cte_rtindex, cmc_attno, + cte->cycle_clause->cycle_mark_type, + cte->cycle_clause->cycle_mark_typmod, + cte->cycle_clause->cycle_mark_collation, 0); + tle = makeTargetEntry((Expr *) var, + list_length(newsubquery->targetList) + 1, + cte->cycle_clause->cycle_mark_column, + false); + newsubquery->targetList = lappend(newsubquery->targetList, tle); + + /* ctename.cpa */ + var = makeVar(cte_rtindex, cpa_attno, + RECORDARRAYOID, -1, InvalidOid, 0); + tle = makeTargetEntry((Expr *) var, + list_length(newsubquery->targetList) + 1, + cte->cycle_clause->cycle_path_column, + false); + newsubquery->targetList = lappend(newsubquery->targetList, tle); + } + + newrte->subquery = newsubquery; + newrte->inFromCl = true; + newq2->rtable = list_make1(newrte); + + rtr = makeNode(RangeTblRef); + rtr->rtindex = 1; + + if (cte->cycle_clause) + { + Expr *expr; + + /* + * Add cmc <> cmv condition + */ + expr = make_opclause(cte->cycle_clause->cycle_mark_neop, BOOLOID, false, + (Expr *) makeVar(1, cmc_attno, + cte->cycle_clause->cycle_mark_type, + cte->cycle_clause->cycle_mark_typmod, + cte->cycle_clause->cycle_mark_collation, 0), + (Expr *) cte->cycle_clause->cycle_mark_value, + InvalidOid, + cte->cycle_clause->cycle_mark_collation); + + newq2->jointree = makeFromExpr(list_make1(rtr), (Node *) expr); + } + else + newq2->jointree = makeFromExpr(list_make1(rtr), NULL); + + /* + * Make target list + */ + for (int i = 0; i < list_length(cte->ctecolnames); i++) + { + Var *var; + + var = makeVar(1, i + 1, + list_nth_oid(cte->ctecoltypes, i), + list_nth_int(cte->ctecoltypmods, i), + list_nth_oid(cte->ctecolcollations, i), + 0); + tle = makeTargetEntry((Expr *) var, i + 1, strVal(list_nth(cte->ctecolnames, i)), false); + tle->resorigtbl = castNode(TargetEntry, list_nth(rte2->subquery->targetList, i))->resorigtbl; + tle->resorigcol = castNode(TargetEntry, list_nth(rte2->subquery->targetList, i))->resorigcol; + newq2->targetList = lappend(newq2->targetList, tle); + } + + if (cte->search_clause) + { + Expr *texpr; + + if (cte->search_clause->search_breadth_first) + { + FieldSelect *fs; + FuncExpr *fexpr; + + /* + * ROW(sqc.depth + 1, cols) + */ + + search_col_rowexpr = copyObject(search_col_rowexpr); + + fs = makeNode(FieldSelect); + fs->arg = (Expr *) makeVar(1, sqc_attno, RECORDOID, -1, 0, 0); + fs->fieldnum = 1; + fs->resulttype = INT8OID; + fs->resulttypmod = -1; + + fexpr = makeFuncExpr(F_INT8INC, INT8OID, list_make1(fs), InvalidOid, InvalidOid, COERCE_EXPLICIT_CALL); + + lfirst(list_head(search_col_rowexpr->args)) = fexpr; + + texpr = (Expr *) search_col_rowexpr; + } + else + { + /* + * sqc || ARRAY[ROW(cols)] + */ + texpr = make_path_cat_expr(search_col_rowexpr, sqc_attno); + } + tle = makeTargetEntry(texpr, + list_length(newq2->targetList) + 1, + cte->search_clause->search_seq_column, + false); + newq2->targetList = lappend(newq2->targetList, tle); + } + + if (cte->cycle_clause) + { + ScalarArrayOpExpr *saoe; + CaseExpr *caseexpr; + CaseWhen *casewhen; + + /* + * CASE WHEN ROW(cols) = ANY (ARRAY[cpa]) THEN cmv ELSE cmd END + */ + + saoe = makeNode(ScalarArrayOpExpr); + saoe->location = -1; + saoe->opno = RECORD_EQ_OP; + saoe->useOr = true; + saoe->args = list_make2(cycle_col_rowexpr, + makeVar(1, cpa_attno, RECORDARRAYOID, -1, 0, 0)); + + caseexpr = makeNode(CaseExpr); + caseexpr->location = -1; + caseexpr->casetype = cte->cycle_clause->cycle_mark_type; + caseexpr->casecollid = cte->cycle_clause->cycle_mark_collation; + casewhen = makeNode(CaseWhen); + casewhen->location = -1; + casewhen->expr = (Expr *) saoe; + casewhen->result = (Expr *) cte->cycle_clause->cycle_mark_value; + caseexpr->args = list_make1(casewhen); + caseexpr->defresult = (Expr *) cte->cycle_clause->cycle_mark_default; + + tle = makeTargetEntry((Expr *) caseexpr, + list_length(newq2->targetList) + 1, + cte->cycle_clause->cycle_mark_column, + false); + newq2->targetList = lappend(newq2->targetList, tle); + + /* + * cpa || ARRAY[ROW(cols)] + */ + tle = makeTargetEntry(make_path_cat_expr(cycle_col_rowexpr, cpa_attno), + list_length(newq2->targetList) + 1, + cte->cycle_clause->cycle_path_column, + false); + newq2->targetList = lappend(newq2->targetList, tle); + } + + rte2->subquery = newq2; + + if (cte->search_clause) + { + rte2->eref->colnames = lappend(rte2->eref->colnames, makeString(cte->search_clause->search_seq_column)); + } + if (cte->cycle_clause) + { + rte2->eref->colnames = lappend(rte2->eref->colnames, makeString(cte->cycle_clause->cycle_mark_column)); + rte2->eref->colnames = lappend(rte2->eref->colnames, makeString(cte->cycle_clause->cycle_path_column)); + } + + /* + * Add the additional columns to the SetOperationStmt + */ + if (cte->search_clause) + { + sos->colTypes = lappend_oid(sos->colTypes, search_seq_type); + sos->colTypmods = lappend_int(sos->colTypmods, -1); + sos->colCollations = lappend_oid(sos->colCollations, InvalidOid); + if (!sos->all) + sos->groupClauses = lappend(sos->groupClauses, + makeSortGroupClauseForSetOp(search_seq_type)); + } + if (cte->cycle_clause) + { + sos->colTypes = lappend_oid(sos->colTypes, cte->cycle_clause->cycle_mark_type); + sos->colTypmods = lappend_int(sos->colTypmods, cte->cycle_clause->cycle_mark_typmod); + sos->colCollations = lappend_oid(sos->colCollations, cte->cycle_clause->cycle_mark_collation); + if (!sos->all) + sos->groupClauses = lappend(sos->groupClauses, + makeSortGroupClauseForSetOp(cte->cycle_clause->cycle_mark_type)); + + sos->colTypes = lappend_oid(sos->colTypes, RECORDARRAYOID); + sos->colTypmods = lappend_int(sos->colTypmods, -1); + sos->colCollations = lappend_oid(sos->colCollations, InvalidOid); + if (!sos->all) + sos->groupClauses = lappend(sos->groupClauses, + makeSortGroupClauseForSetOp(RECORDARRAYOID)); + } + + /* + * Add the additional columns to the CTE query's target list + */ + if (cte->search_clause) + { + ctequery->targetList = lappend(ctequery->targetList, + makeTargetEntry((Expr *) makeVar(1, sqc_attno, + search_seq_type, -1, InvalidOid, 0), + list_length(ctequery->targetList) + 1, + cte->search_clause->search_seq_column, + false)); + } + if (cte->cycle_clause) + { + ctequery->targetList = lappend(ctequery->targetList, + makeTargetEntry((Expr *) makeVar(1, cmc_attno, + cte->cycle_clause->cycle_mark_type, + cte->cycle_clause->cycle_mark_typmod, + cte->cycle_clause->cycle_mark_collation, 0), + list_length(ctequery->targetList) + 1, + cte->cycle_clause->cycle_mark_column, + false)); + ctequery->targetList = lappend(ctequery->targetList, + makeTargetEntry((Expr *) makeVar(1, cpa_attno, + RECORDARRAYOID, -1, InvalidOid, 0), + list_length(ctequery->targetList) + 1, + cte->cycle_clause->cycle_path_column, + false)); + } + + /* + * Add the additional columns to the CTE's output columns + */ + cte->ctecolnames = ewcl; + if (cte->search_clause) + { + cte->ctecoltypes = lappend_oid(cte->ctecoltypes, search_seq_type); + cte->ctecoltypmods = lappend_int(cte->ctecoltypmods, -1); + cte->ctecolcollations = lappend_oid(cte->ctecolcollations, InvalidOid); + } + if (cte->cycle_clause) + { + cte->ctecoltypes = lappend_oid(cte->ctecoltypes, cte->cycle_clause->cycle_mark_type); + cte->ctecoltypmods = lappend_int(cte->ctecoltypmods, cte->cycle_clause->cycle_mark_typmod); + cte->ctecolcollations = lappend_oid(cte->ctecolcollations, cte->cycle_clause->cycle_mark_collation); + + cte->ctecoltypes = lappend_oid(cte->ctecoltypes, RECORDARRAYOID); + cte->ctecoltypmods = lappend_int(cte->ctecoltypmods, -1); + cte->ctecolcollations = lappend_oid(cte->ctecolcollations, InvalidOid); + } + + return cte; +} diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c index 1a844bc4613..4a9244f4f66 100644 --- a/src/backend/utils/adt/ruleutils.c +++ b/src/backend/utils/adt/ruleutils.c @@ -5168,6 +5168,53 @@ get_with_clause(Query *query, deparse_context *context) if (PRETTY_INDENT(context)) appendContextKeyword(context, "", 0, 0, 0); appendStringInfoChar(buf, ')'); + + if (cte->search_clause) + { + bool first = true; + ListCell *lc; + + appendStringInfo(buf, " SEARCH %s FIRST BY ", + cte->search_clause->search_breadth_first ? "BREADTH" : "DEPTH"); + + foreach(lc, cte->search_clause->search_col_list) + { + if (first) + first = false; + else + appendStringInfoString(buf, ", "); + appendStringInfoString(buf, + quote_identifier(strVal(lfirst(lc)))); + } + + appendStringInfo(buf, " SET %s", quote_identifier(cte->search_clause->search_seq_column)); + } + + if (cte->cycle_clause) + { + bool first = true; + ListCell *lc; + + appendStringInfoString(buf, " CYCLE "); + + foreach(lc, cte->cycle_clause->cycle_col_list) + { + if (first) + first = false; + else + appendStringInfoString(buf, ", "); + appendStringInfoString(buf, + quote_identifier(strVal(lfirst(lc)))); + } + + appendStringInfo(buf, " SET %s", quote_identifier(cte->cycle_clause->cycle_mark_column)); + appendStringInfoString(buf, " TO "); + get_rule_expr(cte->cycle_clause->cycle_mark_value, context, false); + appendStringInfoString(buf, " DEFAULT "); + get_rule_expr(cte->cycle_clause->cycle_mark_default, context, false); + appendStringInfo(buf, " USING %s", quote_identifier(cte->cycle_clause->cycle_path_column)); + } + sep = ", "; } diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h index caed683ba92..40ae489c235 100644 --- a/src/include/nodes/nodes.h +++ b/src/include/nodes/nodes.h @@ -471,6 +471,8 @@ typedef enum NodeTag T_WithClause, T_InferClause, T_OnConflictClause, + T_CTESearchClause, + T_CTECycleClause, T_CommonTableExpr, T_RoleSpec, T_TriggerTransition, diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index 068c6ec4401..236832a2ca7 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -1439,9 +1439,8 @@ typedef struct OnConflictClause /* * CommonTableExpr - * representation of WITH list element - * - * We don't currently support the SEARCH or CYCLE clause. */ + typedef enum CTEMaterialize { CTEMaterializeDefault, /* no option specified */ @@ -1449,6 +1448,31 @@ typedef enum CTEMaterialize CTEMaterializeNever /* NOT MATERIALIZED */ } CTEMaterialize; +typedef struct CTESearchClause +{ + NodeTag type; + List *search_col_list; + bool search_breadth_first; + char *search_seq_column; + int location; +} CTESearchClause; + +typedef struct CTECycleClause +{ + NodeTag type; + List *cycle_col_list; + char *cycle_mark_column; + Node *cycle_mark_value; + Node *cycle_mark_default; + char *cycle_path_column; + int location; + /* These fields are set during parse analysis: */ + Oid cycle_mark_type; /* common type of _value and _default */ + int cycle_mark_typmod; + Oid cycle_mark_collation; + Oid cycle_mark_neop; /* <> operator for type */ +} CTECycleClause; + typedef struct CommonTableExpr { NodeTag type; @@ -1457,6 +1481,8 @@ typedef struct CommonTableExpr CTEMaterialize ctematerialized; /* is this an optimization fence? */ /* SelectStmt/InsertStmt/etc before parse analysis, Query afterwards: */ Node *ctequery; /* the CTE's subquery */ + CTESearchClause *search_clause; + CTECycleClause *cycle_clause; int location; /* token location, or -1 if unknown */ /* These fields are set during parse analysis: */ bool cterecursive; /* is this CTE actually recursive? */ diff --git a/src/include/parser/analyze.h b/src/include/parser/analyze.h index fede4be820a..4a3c9686f90 100644 --- a/src/include/parser/analyze.h +++ b/src/include/parser/analyze.h @@ -46,4 +46,6 @@ extern void applyLockingClause(Query *qry, Index rtindex, extern List *BuildOnConflictExcludedTargetlist(Relation targetrel, Index exclRelIndex); +extern SortGroupClause *makeSortGroupClauseForSetOp(Oid rescoltype); + #endif /* ANALYZE_H */ diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h index 8c554e1f690..28083aaac9d 100644 --- a/src/include/parser/kwlist.h +++ b/src/include/parser/kwlist.h @@ -60,6 +60,7 @@ PG_KEYWORD("binary", BINARY, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL) PG_KEYWORD("bit", BIT, COL_NAME_KEYWORD, BARE_LABEL) PG_KEYWORD("boolean", BOOLEAN_P, COL_NAME_KEYWORD, BARE_LABEL) PG_KEYWORD("both", BOTH, RESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("breadth", BREADTH, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("by", BY, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("cache", CACHE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("call", CALL, UNRESERVED_KEYWORD, BARE_LABEL) @@ -128,6 +129,7 @@ PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("delimiters", DELIMITERS, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("depends", DEPENDS, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("depth", DEPTH, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("desc", DESC, RESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("detach", DETACH, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("dictionary", DICTIONARY, UNRESERVED_KEYWORD, BARE_LABEL) diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h index dfc214b06fb..176b9f37c1f 100644 --- a/src/include/parser/parse_node.h +++ b/src/include/parser/parse_node.h @@ -78,6 +78,7 @@ typedef enum ParseExprKind EXPR_KIND_CALL_ARGUMENT, /* procedure argument in CALL */ EXPR_KIND_COPY_WHERE, /* WHERE condition in COPY FROM */ EXPR_KIND_GENERATED_COLUMN, /* generation expression for a column */ + EXPR_KIND_CYCLE_MARK, /* cycle mark value */ } ParseExprKind; @@ -294,6 +295,7 @@ struct ParseNamespaceColumn Oid p_varcollid; /* OID of collation, or InvalidOid */ Index p_varnosyn; /* rangetable index of syntactic referent */ AttrNumber p_varattnosyn; /* attribute number of syntactic referent */ + bool p_dontexpand; /* not included in star expansion */ }; /* Support for parser_errposition_callback function */ diff --git a/src/include/rewrite/rewriteSearchCycle.h b/src/include/rewrite/rewriteSearchCycle.h new file mode 100644 index 00000000000..257fb7cdab7 --- /dev/null +++ b/src/include/rewrite/rewriteSearchCycle.h @@ -0,0 +1,21 @@ +/*------------------------------------------------------------------------- + * + * rewriteSearchCycle.h + * Support for rewriting SEARCH and CYCLE clauses. + * + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/rewrite/rewriteSearchCycle.h + * + *------------------------------------------------------------------------- + */ +#ifndef REWRITESEARCHCYCLE_H +#define REWRITESEARCHCYCLE_H + +#include "nodes/parsenodes.h" + +extern CommonTableExpr *rewriteSearchAndCycle(CommonTableExpr *cte); + +#endif /* REWRITESEARCHCYCLE_H */ diff --git a/src/test/regress/expected/with.out b/src/test/regress/expected/with.out index 9429e9fd28f..c519a61c4fe 100644 --- a/src/test/regress/expected/with.out +++ b/src/test/regress/expected/with.out @@ -577,6 +577,190 @@ SELECT t1.id, t2.path, t2 FROM t AS t1 JOIN t AS t2 ON 16 | {3,7,11,16} | (16,"{3,7,11,16}") (16 rows) +-- SEARCH clause +create temp table graph0( f int, t int, label text ); +insert into graph0 values + (1, 2, 'arc 1 -> 2'), + (1, 3, 'arc 1 -> 3'), + (2, 3, 'arc 2 -> 3'), + (1, 4, 'arc 1 -> 4'), + (4, 5, 'arc 4 -> 5'); +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; + f | t | label | seq +---+---+------------+------------------- + 1 | 2 | arc 1 -> 2 | {"(1,2)"} + 2 | 3 | arc 2 -> 3 | {"(1,2)","(2,3)"} + 1 | 3 | arc 1 -> 3 | {"(1,3)"} + 1 | 4 | arc 1 -> 4 | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | {"(1,4)","(4,5)"} + 2 | 3 | arc 2 -> 3 | {"(2,3)"} + 4 | 5 | arc 4 -> 5 | {"(4,5)"} +(7 rows) + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union distinct + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; + f | t | label | seq +---+---+------------+------------------- + 1 | 2 | arc 1 -> 2 | {"(1,2)"} + 2 | 3 | arc 2 -> 3 | {"(1,2)","(2,3)"} + 1 | 3 | arc 1 -> 3 | {"(1,3)"} + 1 | 4 | arc 1 -> 4 | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | {"(1,4)","(4,5)"} + 2 | 3 | arc 2 -> 3 | {"(2,3)"} + 4 | 5 | arc 4 -> 5 | {"(4,5)"} +(7 rows) + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq +select * from search_graph order by seq; + f | t | label | seq +---+---+------------+--------- + 1 | 2 | arc 1 -> 2 | (0,1,2) + 1 | 3 | arc 1 -> 3 | (0,1,3) + 1 | 4 | arc 1 -> 4 | (0,1,4) + 2 | 3 | arc 2 -> 3 | (0,2,3) + 4 | 5 | arc 4 -> 5 | (0,4,5) + 2 | 3 | arc 2 -> 3 | (1,2,3) + 4 | 5 | arc 4 -> 5 | (1,4,5) +(7 rows) + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union distinct + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq +select * from search_graph order by seq; + f | t | label | seq +---+---+------------+--------- + 1 | 2 | arc 1 -> 2 | (0,1,2) + 1 | 3 | arc 1 -> 3 | (0,1,3) + 1 | 4 | arc 1 -> 4 | (0,1,4) + 2 | 3 | arc 2 -> 3 | (0,2,3) + 4 | 5 | arc 4 -> 5 | (0,4,5) + 2 | 3 | arc 2 -> 3 | (1,2,3) + 4 | 5 | arc 4 -> 5 | (1,4,5) +(7 rows) + +-- various syntax errors +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by foo, tar set seq +select * from search_graph; +ERROR: search column "foo" not in WITH query column list +LINE 7: ) search depth first by foo, tar set seq + ^ +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set label +select * from search_graph; +ERROR: search sequence column name "label" already used in WITH query column list +LINE 7: ) search depth first by f, t set label + ^ +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t, f set seq +select * from search_graph; +ERROR: search column "f" specified more than once +LINE 7: ) search depth first by f, t, f set seq + ^ +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; +ERROR: with a SEARCH or CYCLE clause, the left side of the UNION must be a SELECT +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + (select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t) +) search depth first by f, t set seq +select * from search_graph order by seq; +ERROR: with a SEARCH or CYCLE clause, the right side of the UNION must be a SELECT +-- test ruleutils and view expansion +create temp view v_search as +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select f, t, label from search_graph; +select pg_get_viewdef('v_search'); + pg_get_viewdef +------------------------------------------------ + WITH RECURSIVE search_graph(f, t, label) AS (+ + SELECT g.f, + + g.t, + + g.label + + FROM graph0 g + + UNION ALL + + SELECT g.f, + + g.t, + + g.label + + FROM graph0 g, + + search_graph sg + + WHERE (g.f = sg.t) + + ) SEARCH DEPTH FIRST BY f, t SET seq + + SELECT search_graph.f, + + search_graph.t, + + search_graph.label + + FROM search_graph; +(1 row) + +select * from v_search; + f | t | label +---+---+------------ + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 2 | 3 | arc 2 -> 3 + 1 | 4 | arc 1 -> 4 + 4 | 5 | arc 4 -> 5 + 2 | 3 | arc 2 -> 3 + 4 | 5 | arc 4 -> 5 +(7 rows) + -- -- test cycle detection -- @@ -701,6 +885,380 @@ select * from search_graph order by path; 5 | 1 | arc 5 -> 1 | t | {"(5,1)","(1,4)","(4,5)","(5,1)"} (25 rows) +-- CYCLE clause +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select * from search_graph; + f | t | label | is_cycle | path +---+---+------------+----------+------------------------------------------- + 1 | 2 | arc 1 -> 2 | f | {"(1,2)"} + 1 | 3 | arc 1 -> 3 | f | {"(1,3)"} + 2 | 3 | arc 2 -> 3 | f | {"(2,3)"} + 1 | 4 | arc 1 -> 4 | f | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | f | {"(4,5)"} + 5 | 1 | arc 5 -> 1 | f | {"(5,1)"} + 1 | 2 | arc 1 -> 2 | f | {"(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | f | {"(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | f | {"(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | f | {"(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | f | {"(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | f | {"(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | f | {"(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | f | {"(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | f | {"(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | f | {"(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | f | {"(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | f | {"(1,4)","(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | f | {"(1,4)","(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | f | {"(1,4)","(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | t | {"(1,4)","(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | f | {"(4,5)","(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | t | {"(4,5)","(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | t | {"(5,1)","(1,4)","(4,5)","(5,1)"} + 2 | 3 | arc 2 -> 3 | f | {"(1,4)","(4,5)","(5,1)","(1,2)","(2,3)"} +(25 rows) + +with recursive search_graph(f, t, label) as ( + select * from graph g + union distinct + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to 'Y' default 'N' using path +select * from search_graph; + f | t | label | is_cycle | path +---+---+------------+----------+------------------------------------------- + 1 | 2 | arc 1 -> 2 | N | {"(1,2)"} + 1 | 3 | arc 1 -> 3 | N | {"(1,3)"} + 2 | 3 | arc 2 -> 3 | N | {"(2,3)"} + 1 | 4 | arc 1 -> 4 | N | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | N | {"(4,5)"} + 5 | 1 | arc 5 -> 1 | N | {"(5,1)"} + 1 | 2 | arc 1 -> 2 | N | {"(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | N | {"(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | N | {"(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | N | {"(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | N | {"(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | N | {"(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | N | {"(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | N | {"(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | N | {"(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | N | {"(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | N | {"(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | N | {"(1,4)","(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | N | {"(1,4)","(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | N | {"(1,4)","(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | Y | {"(1,4)","(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | N | {"(4,5)","(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | Y | {"(4,5)","(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | Y | {"(5,1)","(1,4)","(4,5)","(5,1)"} + 2 | 3 | arc 2 -> 3 | N | {"(1,4)","(4,5)","(5,1)","(1,2)","(2,3)"} +(25 rows) + +-- multiple CTEs +with recursive +graph(f, t, label) as ( + values (1, 2, 'arc 1 -> 2'), + (1, 3, 'arc 1 -> 3'), + (2, 3, 'arc 2 -> 3'), + (1, 4, 'arc 1 -> 4'), + (4, 5, 'arc 4 -> 5'), + (5, 1, 'arc 5 -> 1') +), +search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select f, t, label from search_graph; + f | t | label +---+---+------------ + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 2 | 3 | arc 2 -> 3 + 1 | 4 | arc 1 -> 4 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 2 | 3 | arc 2 -> 3 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 1 | 4 | arc 1 -> 4 + 1 | 3 | arc 1 -> 3 + 1 | 2 | arc 1 -> 2 + 5 | 1 | arc 5 -> 1 + 1 | 4 | arc 1 -> 4 + 1 | 3 | arc 1 -> 3 + 1 | 2 | arc 1 -> 2 + 4 | 5 | arc 4 -> 5 + 2 | 3 | arc 2 -> 3 + 1 | 4 | arc 1 -> 4 + 1 | 3 | arc 1 -> 3 + 1 | 2 | arc 1 -> 2 + 4 | 5 | arc 4 -> 5 + 2 | 3 | arc 2 -> 3 + 5 | 1 | arc 5 -> 1 + 2 | 3 | arc 2 -> 3 +(25 rows) + +-- star expansion +with recursive a as ( + select 1 as b + union all + select * from a +) cycle b set c to true default false using p +select * from a; + b | c | p +---+---+----------- + 1 | f | {(1)} + 1 | t | {(1),(1)} +(2 rows) + +-- search+cycle +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq + cycle f, t set is_cycle to true default false using path +select * from search_graph; + f | t | label | seq | is_cycle | path +---+---+------------+-------------------------------------------+----------+------------------------------------------- + 1 | 2 | arc 1 -> 2 | {"(1,2)"} | f | {"(1,2)"} + 1 | 3 | arc 1 -> 3 | {"(1,3)"} | f | {"(1,3)"} + 2 | 3 | arc 2 -> 3 | {"(2,3)"} | f | {"(2,3)"} + 1 | 4 | arc 1 -> 4 | {"(1,4)"} | f | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | {"(4,5)"} | f | {"(4,5)"} + 5 | 1 | arc 5 -> 1 | {"(5,1)"} | f | {"(5,1)"} + 1 | 2 | arc 1 -> 2 | {"(5,1)","(1,2)"} | f | {"(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | {"(5,1)","(1,3)"} | f | {"(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | {"(5,1)","(1,4)"} | f | {"(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | {"(1,2)","(2,3)"} | f | {"(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | {"(1,4)","(4,5)"} | f | {"(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | {"(4,5)","(5,1)"} | f | {"(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | {"(4,5)","(5,1)","(1,2)"} | f | {"(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | {"(4,5)","(5,1)","(1,3)"} | f | {"(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | {"(4,5)","(5,1)","(1,4)"} | f | {"(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | {"(5,1)","(1,2)","(2,3)"} | f | {"(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | {"(5,1)","(1,4)","(4,5)"} | f | {"(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | {"(1,4)","(4,5)","(5,1)"} | f | {"(1,4)","(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | {"(1,4)","(4,5)","(5,1)","(1,2)"} | f | {"(1,4)","(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | {"(1,4)","(4,5)","(5,1)","(1,3)"} | f | {"(1,4)","(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | {"(1,4)","(4,5)","(5,1)","(1,4)"} | t | {"(1,4)","(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | {"(4,5)","(5,1)","(1,2)","(2,3)"} | f | {"(4,5)","(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | {"(4,5)","(5,1)","(1,4)","(4,5)"} | t | {"(4,5)","(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | {"(5,1)","(1,4)","(4,5)","(5,1)"} | t | {"(5,1)","(1,4)","(4,5)","(5,1)"} + 2 | 3 | arc 2 -> 3 | {"(1,4)","(4,5)","(5,1)","(1,2)","(2,3)"} | f | {"(1,4)","(4,5)","(5,1)","(1,2)","(2,3)"} +(25 rows) + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq + cycle f, t set is_cycle to true default false using path +select * from search_graph; + f | t | label | seq | is_cycle | path +---+---+------------+---------+----------+------------------------------------------- + 1 | 2 | arc 1 -> 2 | (0,1,2) | f | {"(1,2)"} + 1 | 3 | arc 1 -> 3 | (0,1,3) | f | {"(1,3)"} + 2 | 3 | arc 2 -> 3 | (0,2,3) | f | {"(2,3)"} + 1 | 4 | arc 1 -> 4 | (0,1,4) | f | {"(1,4)"} + 4 | 5 | arc 4 -> 5 | (0,4,5) | f | {"(4,5)"} + 5 | 1 | arc 5 -> 1 | (0,5,1) | f | {"(5,1)"} + 1 | 2 | arc 1 -> 2 | (1,1,2) | f | {"(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | (1,1,3) | f | {"(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | (1,1,4) | f | {"(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | (1,2,3) | f | {"(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | (1,4,5) | f | {"(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | (1,5,1) | f | {"(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | (2,1,2) | f | {"(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | (2,1,3) | f | {"(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | (2,1,4) | f | {"(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | (2,2,3) | f | {"(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | (2,4,5) | f | {"(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | (2,5,1) | f | {"(1,4)","(4,5)","(5,1)"} + 1 | 2 | arc 1 -> 2 | (3,1,2) | f | {"(1,4)","(4,5)","(5,1)","(1,2)"} + 1 | 3 | arc 1 -> 3 | (3,1,3) | f | {"(1,4)","(4,5)","(5,1)","(1,3)"} + 1 | 4 | arc 1 -> 4 | (3,1,4) | t | {"(1,4)","(4,5)","(5,1)","(1,4)"} + 2 | 3 | arc 2 -> 3 | (3,2,3) | f | {"(4,5)","(5,1)","(1,2)","(2,3)"} + 4 | 5 | arc 4 -> 5 | (3,4,5) | t | {"(4,5)","(5,1)","(1,4)","(4,5)"} + 5 | 1 | arc 5 -> 1 | (3,5,1) | t | {"(5,1)","(1,4)","(4,5)","(5,1)"} + 2 | 3 | arc 2 -> 3 | (4,2,3) | f | {"(1,4)","(4,5)","(5,1)","(1,2)","(2,3)"} +(25 rows) + +-- various syntax errors +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle foo, tar set is_cycle to true default false using path +select * from search_graph; +ERROR: cycle column "foo" not in WITH query column list +LINE 7: ) cycle foo, tar set is_cycle to true default false using pa... + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default 55 using path +select * from search_graph; +ERROR: CYCLE types boolean and integer cannot be matched +LINE 7: ) cycle f, t set is_cycle to true default 55 using path + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to point '(1,1)' default point '(0,0)' using path +select * from search_graph; +ERROR: could not identify an equality operator for type point +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set label to true default false using path +select * from search_graph; +ERROR: cycle mark column name "label" already used in WITH query column list +LINE 7: ) cycle f, t set label to true default false using path + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using label +select * from search_graph; +ERROR: cycle path column name "label" already used in WITH query column list +LINE 7: ) cycle f, t set is_cycle to true default false using label + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set foo to true default false using foo +select * from search_graph; +ERROR: cycle mark column name and cycle path column name are the same +LINE 7: ) cycle f, t set foo to true default false using foo + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t, f set is_cycle to true default false using path +select * from search_graph; +ERROR: cycle column "f" specified more than once +LINE 7: ) cycle f, t, f set is_cycle to true default false using pat... + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set foo + cycle f, t set foo to true default false using path +select * from search_graph; +ERROR: search sequence column name and cycle mark column name are the same +LINE 7: ) search depth first by f, t set foo + ^ +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set foo + cycle f, t set is_cycle to true default false using foo +select * from search_graph; +ERROR: search_sequence column name and cycle path column name are the same +LINE 7: ) search depth first by f, t set foo + ^ +-- test ruleutils and view expansion +create temp view v_cycle as +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select f, t, label from search_graph; +select pg_get_viewdef('v_cycle'); + pg_get_viewdef +-------------------------------------------------------------------- + WITH RECURSIVE search_graph(f, t, label) AS ( + + SELECT g.f, + + g.t, + + g.label + + FROM graph g + + UNION ALL + + SELECT g.f, + + g.t, + + g.label + + FROM graph g, + + search_graph sg + + WHERE (g.f = sg.t) + + ) CYCLE f, t SET is_cycle TO true DEFAULT false USING path+ + SELECT search_graph.f, + + search_graph.t, + + search_graph.label + + FROM search_graph; +(1 row) + +select * from v_cycle; + f | t | label +---+---+------------ + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 2 | 3 | arc 2 -> 3 + 1 | 4 | arc 1 -> 4 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 1 | 4 | arc 1 -> 4 + 2 | 3 | arc 2 -> 3 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 1 | 4 | arc 1 -> 4 + 2 | 3 | arc 2 -> 3 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 1 | 2 | arc 1 -> 2 + 1 | 3 | arc 1 -> 3 + 1 | 4 | arc 1 -> 4 + 2 | 3 | arc 2 -> 3 + 4 | 5 | arc 4 -> 5 + 5 | 1 | arc 5 -> 1 + 2 | 3 | arc 2 -> 3 +(25 rows) + -- -- test multiple WITH queries -- diff --git a/src/test/regress/sql/with.sql b/src/test/regress/sql/with.sql index ad976de5311..f4ba0d8e399 100644 --- a/src/test/regress/sql/with.sql +++ b/src/test/regress/sql/with.sql @@ -303,6 +303,118 @@ UNION ALL SELECT t1.id, t2.path, t2 FROM t AS t1 JOIN t AS t2 ON (t1.id=t2.id); +-- SEARCH clause + +create temp table graph0( f int, t int, label text ); + +insert into graph0 values + (1, 2, 'arc 1 -> 2'), + (1, 3, 'arc 1 -> 3'), + (2, 3, 'arc 2 -> 3'), + (1, 4, 'arc 1 -> 4'), + (4, 5, 'arc 4 -> 5'); + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union distinct + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq +select * from search_graph order by seq; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union distinct + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq +select * from search_graph order by seq; + +-- various syntax errors +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by foo, tar set seq +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set label +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t, f set seq +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select * from search_graph order by seq; + +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + (select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t) +) search depth first by f, t set seq +select * from search_graph order by seq; + +-- test ruleutils and view expansion +create temp view v_search as +with recursive search_graph(f, t, label) as ( + select * from graph0 g + union all + select g.* + from graph0 g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq +select f, t, label from search_graph; + +select pg_get_viewdef('v_search'); + +select * from v_search; + -- -- test cycle detection -- @@ -345,6 +457,173 @@ with recursive search_graph(f, t, label, is_cycle, path) as ( ) select * from search_graph order by path; +-- CYCLE clause + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union distinct + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to 'Y' default 'N' using path +select * from search_graph; + +-- multiple CTEs +with recursive +graph(f, t, label) as ( + values (1, 2, 'arc 1 -> 2'), + (1, 3, 'arc 1 -> 3'), + (2, 3, 'arc 2 -> 3'), + (1, 4, 'arc 1 -> 4'), + (4, 5, 'arc 4 -> 5'), + (5, 1, 'arc 5 -> 1') +), +search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select f, t, label from search_graph; + +-- star expansion +with recursive a as ( + select 1 as b + union all + select * from a +) cycle b set c to true default false using p +select * from a; + +-- search+cycle +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set seq + cycle f, t set is_cycle to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search breadth first by f, t set seq + cycle f, t set is_cycle to true default false using path +select * from search_graph; + +-- various syntax errors +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle foo, tar set is_cycle to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default 55 using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to point '(1,1)' default point '(0,0)' using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set label to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using label +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set foo to true default false using foo +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t, f set is_cycle to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set foo + cycle f, t set foo to true default false using path +select * from search_graph; + +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) search depth first by f, t set foo + cycle f, t set is_cycle to true default false using foo +select * from search_graph; + +-- test ruleutils and view expansion +create temp view v_cycle as +with recursive search_graph(f, t, label) as ( + select * from graph g + union all + select g.* + from graph g, search_graph sg + where g.f = sg.t +) cycle f, t set is_cycle to true default false using path +select f, t, label from search_graph; + +select pg_get_viewdef('v_cycle'); + +select * from v_cycle; + -- -- test multiple WITH queries -- |