Add WITH [NO] DATA clause to CREATE TABLE AS, per SQL.

Also, since WITH is now a reserved word, simplify the token merging code to
only deal with WITH_TIME.

by Tom Lane and myself

6 files changed, 44 insertions, 60 deletions

diff --git a/doc/src/sgml/ref/create_table_as.sgml b/doc/src/sgml/ref/create_table_as.sgml
index d26f947fb7..b67c6edc12 100644
--- a/doc/src/sgml/ref/create_table_as.sgml
+++ b/doc/src/sgml/ref/create_table_as.sgml
@@ -26,6 +26,7 @@ CREATE [ [ GLOBAL | LOCAL ] { TEMPORARY | TEMP } ] TABLE <replaceable>table_name
     [ ON COMMIT { PRESERVE ROWS | DELETE ROWS | DROP } ]
     [ TABLESPACE <replaceable class="PARAMETER">tablespace</replaceable> ]
     AS <replaceable>query</replaceable>
+    [ WITH [ NO ] DATA ]
 </synopsis>
  </refsynopsisdiv>
   
@@ -201,6 +202,18 @@ CREATE [ [ GLOBAL | LOCAL ] { TEMPORARY | TEMP } ] TABLE <replaceable>table_name
      </para>
     </listitem>
    </varlistentry>
+
+   <varlistentry>
+    <term><literal>WITH [ NO ] DATA</></term>
+    <listitem>
+     <para>
+      This clause specifies whether or not the data produced by the query
+      should be copied into the new table.  If not, only the table structure
+      is copied.  The default is to copy the data.
+     </para>
+    </listitem>
+   </varlistentry>
+
   </variablelist>
  </refsect1>
 
@@ -265,7 +278,7 @@ CREATE TEMP TABLE films_recent WITH (OIDS) ON COMMIT DROP AS
 
   <para>
    <command>CREATE TABLE AS</command> conforms to the <acronym>SQL</acronym>
-   standard, with the following exceptions:
+   standard.  The following are nonstandard extensions:
 
    <itemizedlist spacing="compact">
     <listitem>
@@ -278,12 +291,8 @@ CREATE TEMP TABLE films_recent WITH (OIDS) ON COMMIT DROP AS
 
     <listitem>
      <para>
-      The standard defines a <literal>WITH [ NO ] DATA</literal> clause;
-      this is not currently implemented by <productname>PostgreSQL</>.
-      The behavior provided by <productname>PostgreSQL</> is equivalent
-      to the standard's <literal>WITH DATA</literal> case.
-      <literal>WITH NO DATA</literal> can be simulated by appending
-      <literal>LIMIT 0</> to the query.
+      In the standard, the <literal>WITH [ NO ] DATA</literal> clause
+      is required; in PostgreSQL it is optional.
      </para>
     </listitem>
 
diff --git a/src/backend/catalog/sql_features.txt b/src/backend/catalog/sql_features.txt
index be9974af27..b795a70f3c 100644
--- a/src/backend/catalog/sql_features.txt
+++ b/src/backend/catalog/sql_features.txt
@@ -408,7 +408,7 @@ T141	SIMILAR predicate			YES
 T151	DISTINCT predicate			YES	
 T152	DISTINCT predicate with negation			YES	
 T171	LIKE clause in table definition			YES	
-T172	AS subquery clause in table definition			NO	
+T172	AS subquery clause in table definition			YES	
 T173	Extended LIKE clause in table definition			YES	
 T174	Identity columns			NO	
 T175	Generated columns			NO	
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index ec13e56ed7..70ea60a15a 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -216,7 +216,7 @@ static TypeName *TableFuncTypeName(List *columns);
 %type <ival>	opt_lock lock_type cast_context
 %type <boolean>	opt_force opt_or_replace
 				opt_grant_grant_option opt_grant_admin_option
-				opt_nowait opt_if_exists
+				opt_nowait opt_if_exists opt_with_data
 
 %type <list>	OptRoleList
 %type <defelt>	OptRoleElem
@@ -485,7 +485,7 @@ static TypeName *TableFuncTypeName(List *columns);
  * list and so can never be entered directly.  The filter in parser.c
  * creates these tokens when required.
  */
-%token			NULLS_FIRST NULLS_LAST WITH_CASCADED WITH_LOCAL WITH_CHECK
+%token			NULLS_FIRST NULLS_LAST WITH_TIME
 
 /* Special token types, not actually keywords - see the "lex" file */
 %token <str>	IDENT FCONST SCONST BCONST XCONST Op
@@ -2416,7 +2416,7 @@ OptConsTableSpace:   USING INDEX TABLESPACE name	{ $$ = $4; }
  */
 
 CreateAsStmt:
-		CREATE OptTemp TABLE create_as_target AS SelectStmt
+		CREATE OptTemp TABLE create_as_target AS SelectStmt opt_with_data
 				{
 					/*
 					 * When the SelectStmt is a set-operation tree, we must
@@ -2433,6 +2433,9 @@ CreateAsStmt:
 								 scanner_errposition(exprLocation((Node *) n->intoClause))));
 					$4->rel->istemp = $2;
 					n->intoClause = $4;
+					/* Implement WITH NO DATA by forcing top-level LIMIT 0 */
+					if (!$7)
+						((SelectStmt *) $6)->limitCount = makeIntConst(0, -1);
 					$$ = $6;
 				}
 		;
@@ -2475,6 +2478,12 @@ CreateAsElement:
 				}
 		;
 
+opt_with_data:
+			WITH DATA_P								{ $$ = TRUE; }
+			| WITH NO DATA_P						{ $$ = FALSE; }
+			| /*EMPTY*/								{ $$ = TRUE; }
+		;
+
 
 /*****************************************************************************
  *
@@ -5387,24 +5396,20 @@ ViewStmt: CREATE OptTemp VIEW qualified_name opt_column_list
 				}
 		;
 
-/*
- * We use merged tokens here to avoid creating shift/reduce conflicts against
- * a whole lot of other uses of WITH.
- */
 opt_check_option:
-		WITH_CHECK OPTION
+		WITH CHECK OPTION
 				{
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 							 errmsg("WITH CHECK OPTION is not implemented")));
 				}
-		| WITH_CASCADED CHECK OPTION
+		| WITH CASCADED CHECK OPTION
 				{
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 							 errmsg("WITH CHECK OPTION is not implemented")));
 				}
-		| WITH_LOCAL CHECK OPTION
+		| WITH LOCAL CHECK OPTION
 				{
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -7509,7 +7514,7 @@ ConstInterval:
 		;
 
 opt_timezone:
-			WITH TIME ZONE							{ $$ = TRUE; }
+			WITH_TIME ZONE							{ $$ = TRUE; }
 			| WITHOUT TIME ZONE						{ $$ = FALSE; }
 			| /*EMPTY*/								{ $$ = FALSE; }
 		;
diff --git a/src/backend/parser/parser.c b/src/backend/parser/parser.c
index bd2689a8fe..459a0867b1 100644
--- a/src/backend/parser/parser.c
+++ b/src/backend/parser/parser.c
@@ -129,28 +129,15 @@ filtered_base_yylex(void)
 		case WITH:
 
 			/*
-			 * WITH CASCADED, LOCAL, or CHECK must be reduced to one token
-			 *
-			 * XXX an alternative way is to recognize just WITH_TIME and put
-			 * the ugliness into the datetime datatype productions instead of
-			 * WITH CHECK OPTION.  However that requires promoting WITH to a
-			 * fully reserved word.  If we ever have to do that anyway
-			 * (perhaps for SQL99 recursive queries), come back and simplify
-			 * this code.
+			 * WITH TIME must be reduced to one token
 			 */
 			cur_yylval = base_yylval;
 			cur_yylloc = base_yylloc;
 			next_token = base_yylex();
 			switch (next_token)
 			{
-				case CASCADED:
-					cur_token = WITH_CASCADED;
-					break;
-				case LOCAL:
-					cur_token = WITH_LOCAL;
-					break;
-				case CHECK:
-					cur_token = WITH_CHECK;
+				case TIME:
+					cur_token = WITH_TIME;
 					break;
 				default:
 					/* save the lookahead token for next time */
diff --git a/src/interfaces/ecpg/preproc/parser.c b/src/interfaces/ecpg/preproc/parser.c
index 9e7357ec67..38262f90f4 100644
--- a/src/interfaces/ecpg/preproc/parser.c
+++ b/src/interfaces/ecpg/preproc/parser.c
@@ -98,28 +98,15 @@ filtered_base_yylex(void)
 		case WITH:
 
 			/*
-			 * WITH CASCADED, LOCAL, or CHECK must be reduced to one token
-			 *
-			 * XXX an alternative way is to recognize just WITH_TIME and put
-			 * the ugliness into the datetime datatype productions instead of
-			 * WITH CHECK OPTION.  However that requires promoting WITH to a
-			 * fully reserved word.  If we ever have to do that anyway
-			 * (perhaps for SQL99 recursive queries), come back and simplify
-			 * this code.
+			 * WITH TIME must be reduced to one token
 			 */
 			cur_yylval = base_yylval;
 			cur_yylloc = base_yylloc;
 			next_token = base_yylex();
 			switch (next_token)
 			{
-				case CASCADED:
-					cur_token = WITH_CASCADED;
-					break;
-				case LOCAL:
-					cur_token = WITH_LOCAL;
-					break;
-				case CHECK:
-					cur_token = WITH_CHECK;
+				case TIME:
+					cur_token = WITH_TIME;
 					break;
 				default:
 					/* save the lookahead token for next time */
diff --git a/src/interfaces/ecpg/preproc/preproc.y b/src/interfaces/ecpg/preproc/preproc.y
index 4f0319ee3e..70c7588c51 100644
--- a/src/interfaces/ecpg/preproc/preproc.y
+++ b/src/interfaces/ecpg/preproc/preproc.y
@@ -505,7 +505,7 @@ add_typedef(char *name, char * dimension, char * length, enum ECPGttype type_enu
  * list and so can never be entered directly.  The filter in parser.c
  * creates these tokens when required.
  */
-%token           NULLS_FIRST NULLS_LAST WITH_CASCADED WITH_LOCAL WITH_CHECK
+%token           NULLS_FIRST NULLS_LAST WITH_TIME
 
 /* Special token types, not actually keywords - see the "lex" file */
 %token <str>	IDENT SCONST Op CSTRING CVARIABLE CPP_LINE IP BCONST
@@ -3100,22 +3100,18 @@ ViewStmt:  CREATE OptTemp VIEW qualified_name opt_column_list AS SelectStmt opt_
 			{ $$ = cat_str(8, make_str("create or replace"), $4, make_str("view"), $6, $7, make_str("as"), $9, $10); }
 		;
 
-/*
- * We use merged tokens here to avoid creating shift/reduce conflicts against
- * a whole lot of other uses of WITH.
- */
 opt_check_option:
-                   WITH_CHECK OPTION
+                   WITH CHECK OPTION
 		   { 
 		   	mmerror(PARSE_ERROR, ET_ERROR, "WITH CHECK OPTION not implemented");
 			$$ = EMPTY;
 		   }
-                   | WITH_CASCADED CHECK OPTION
+                   | WITH CASCADED CHECK OPTION
 		   { 
 		   	mmerror(PARSE_ERROR, ET_ERROR, "WITH CHECK OPTION not implemented");
 			$$ = EMPTY;
 		   }
-		   | WITH_LOCAL CHECK OPTION
+		   | WITH LOCAL CHECK OPTION
 		   {
 		   	mmerror(PARSE_ERROR, ET_ERROR, "WITH CHECK OPTION not implemented");
 			$$ = EMPTY;
@@ -4155,7 +4151,7 @@ ConstInterval:	INTERVAL
 			{ $$ = make_str("interval"); }
 		;
 
-opt_timezone:  WITH TIME ZONE
+opt_timezone:  WITH_TIME ZONE
 			{ $$ = make_str("with time zone"); }
 		| WITHOUT TIME ZONE
 			{ $$ = make_str("without time zone"); }