Add COLLATION FOR expression

reviewed by Jaime Casanova

Author: petere

doc/src/sgml/func.sgml

@@ -13698,6 +13698,10 @@ SELECT pg_type_is_visible('myschema.widget'::regtype);
     <primary>pg_typeof</primary>
    </indexterm>
 
+   <indexterm>
+    <primary>collation for</primary>
+   </indexterm>
+
   <para>
    <xref linkend="functions-info-catalog-table"> lists functions that
    extract information from the system catalogs.
@@ -13859,6 +13863,11 @@ SELECT pg_type_is_visible('myschema.widget'::regtype);
        <entry><type>regtype</type></entry>
        <entry>get the data type of any value</entry>
       </row>
+      <row>
+       <entry><literal><function>collation for (<parameter>any</parameter>)</function></literal></entry>
+       <entry><type>text</type></entry>
+       <entry>get the collation of the argument</entry>
+      </row>
      </tbody>
     </tgroup>
    </table>
@@ -13983,6 +13992,27 @@ SELECT typlen FROM pg_type WHERE oid = pg_typeof(33);
       4
 (1 row)
 </programlisting>
+  </para>
+
+  <para>
+   The expression <literal>collation for</literal> returns the collation of the
+   value that is passed to it.  Example:
+<programlisting>
+SELECT collation for (description) FROM pg_description LIMIT 1;
+ pg_collation_for 
+------------------
+ "default"
+(1 row)
+
+SELECT collation for ('foo' COLLATE "de_DE");
+ pg_collation_for 
+------------------
+ "de_DE"
+(1 row)
+</programlisting>
+  The value might be quoted and schema-qualified.  If no collation is derived
+  for the argument expression, then a null value is returned.  If the argument
+  is not of a collatable data type, then an error is raised.
   </para>
 
    <indexterm>

src/backend/parser/gram.y

@@ -10701,6 +10701,19 @@ func_expr:	func_name '(' ')' over_clause
 					n->location = @1;
 					$$ = (Node *)n;
 				}
+			| COLLATION FOR '(' a_expr ')'
+				{
+					FuncCall *n = makeNode(FuncCall);
+					n->funcname = SystemFuncName("pg_collation_for");
+					n->args = list_make1($4);
+					n->agg_order = NIL;
+					n->agg_star = FALSE;
+					n->agg_distinct = FALSE;
+					n->func_variadic = FALSE;
+					n->over = NULL;
+					n->location = @1;
+					$$ = (Node *)n;
+				}
 			| CURRENT_DATE
 				{
 					/*
@@ -12152,7 +12165,6 @@ unreserved_keyword:
 			| CLASS
 			| CLOSE
 			| CLUSTER
-			| COLLATION
 			| COMMENT
 			| COMMENTS
 			| COMMIT
@@ -12491,6 +12503,7 @@ reserved_keyword:
 			| CAST
 			| CHECK
 			| COLLATE
+			| COLLATION
 			| COLUMN
 			| CONSTRAINT
 			| CREATE

src/backend/utils/adt/misc.c

@@ -32,6 +32,7 @@
 #include "storage/pmsignal.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
+#include "utils/lsyscache.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
 #include "utils/timestamp.h"
@@ -492,3 +493,29 @@ pg_typeof(PG_FUNCTION_ARGS)
 {
 	PG_RETURN_OID(get_fn_expr_argtype(fcinfo->flinfo, 0));
 }
+
+
+/*
+ * Implementation of the COLLATE FOR expression; returns the collation
+ * of the argument.
+ */
+Datum
+pg_collation_for(PG_FUNCTION_ARGS)
+{
+	Oid typeid;
+	Oid collid;
+
+	typeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
+	if (!typeid)
+		PG_RETURN_NULL();
+	if (!type_is_collatable(typeid) && typeid != UNKNOWNOID)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATATYPE_MISMATCH),
+				 errmsg("collations are not supported by type %s",
+						format_type_be(typeid))));
+
+	collid = PG_GET_COLLATION();
+	if (!collid)
+		PG_RETURN_NULL();
+	PG_RETURN_TEXT_P(cstring_to_text(generate_collation_name(collid)));
+}

src/include/catalog/catversion.h

@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	201203011
+#define CATALOG_VERSION_NO	201203021
 
 #endif

src/include/catalog/pg_proc.h

@@ -1953,6 +1953,8 @@ DESCR("convert generic options array to name/value table");
 
 DATA(insert OID = 1619 (  pg_typeof				PGNSP PGUID 12 1 0 0 0 f f f f f f s 1 0 2206 "2276" _null_ _null_ _null_ _null_  pg_typeof _null_ _null_ _null_ ));
 DESCR("type of the argument");
+DATA(insert OID = 3162 (  pg_collation_for		PGNSP PGUID 12 1 0 0 0 f f f f f f s 1 0   25 "2276" _null_ _null_ _null_ _null_  pg_collation_for _null_ _null_ _null_ ));
+DESCR("collation of the argument; implementation of the COLLATION FOR expression");
 
 /* Deferrable unique constraint trigger */
 DATA(insert OID = 1250 (  unique_key_recheck	PGNSP PGUID 12 1 0 0 0 f f f f t f v 0 0 2279 "" _null_ _null_ _null_ _null_ unique_key_recheck _null_ _null_ _null_ ));

src/include/parser/kwlist.h

@@ -79,7 +79,7 @@ PG_KEYWORD("close", CLOSE, UNRESERVED_KEYWORD)
 PG_KEYWORD("cluster", CLUSTER, UNRESERVED_KEYWORD)
 PG_KEYWORD("coalesce", COALESCE, COL_NAME_KEYWORD)
 PG_KEYWORD("collate", COLLATE, RESERVED_KEYWORD)
-PG_KEYWORD("collation", COLLATION, UNRESERVED_KEYWORD)
+PG_KEYWORD("collation", COLLATION, RESERVED_KEYWORD)
 PG_KEYWORD("column", COLUMN, RESERVED_KEYWORD)
 PG_KEYWORD("comment", COMMENT, UNRESERVED_KEYWORD)
 PG_KEYWORD("comments", COMMENTS, UNRESERVED_KEYWORD)

src/include/utils/builtins.h

@@ -480,6 +480,7 @@ extern Datum pg_rotate_logfile(PG_FUNCTION_ARGS);
 extern Datum pg_sleep(PG_FUNCTION_ARGS);
 extern Datum pg_get_keywords(PG_FUNCTION_ARGS);
 extern Datum pg_typeof(PG_FUNCTION_ARGS);
+extern Datum pg_collation_for(PG_FUNCTION_ARGS);
 
 /* oid.c */
 extern Datum oidin(PG_FUNCTION_ARGS);

src/test/regress/expected/collate.out

@@ -577,6 +577,26 @@ RESET enable_nestloop;
 -- 9.1 bug with useless COLLATE in an expression subject to length coercion
 CREATE TEMP TABLE vctable (f1 varchar(25));
 INSERT INTO vctable VALUES ('foo' COLLATE "C");
+SELECT collation for ('foo'); -- unknown type - null
+ pg_collation_for 
+------------------
+ 
+(1 row)
+
+SELECT collation for ('foo'::text);
+ pg_collation_for 
+------------------
+ "default"
+(1 row)
+
+SELECT collation for ((SELECT a FROM collate_test1 LIMIT 1)); -- non-collatable type - error
+ERROR:  collations are not supported by type integer
+SELECT collation for ((SELECT b FROM collate_test1 LIMIT 1));
+ pg_collation_for 
+------------------
+ "C"
+(1 row)
+
 --
 -- Clean up.  Many of these table names will be re-used if the user is
 -- trying to run any platform-specific collation tests later, so we

src/test/regress/sql/collate.sql

@@ -219,6 +219,13 @@ RESET enable_nestloop;
 CREATE TEMP TABLE vctable (f1 varchar(25));
 INSERT INTO vctable VALUES ('foo' COLLATE "C");
 
+
+SELECT collation for ('foo'); -- unknown type - null
+SELECT collation for ('foo'::text);
+SELECT collation for ((SELECT a FROM collate_test1 LIMIT 1)); -- non-collatable type - error
+SELECT collation for ((SELECT b FROM collate_test1 LIMIT 1));
+
+
 --
 -- Clean up.  Many of these table names will be re-used if the user is
 -- trying to run any platform-specific collation tests later, so we