Per-column collation support

This adds collation support for columns and domains, a COLLATE clause
to override it per expression, and B-tree index support.

Peter Eisentraut
reviewed by Pavel Stehule, Itagaki Takahiro, Robert Haas, Noah Misch

src/backend/utils/cache/lsyscache.c

@@ -20,6 +20,7 @@
 #include "bootstrap/bootstrap.h"
 #include "catalog/pg_amop.h"
 #include "catalog/pg_amproc.h"
+#include "catalog/pg_collation.h"
 #include "catalog/pg_constraint.h"
 #include "catalog/pg_namespace.h"
 #include "catalog/pg_opclass.h"
@@ -902,6 +903,33 @@ get_atttypmod(Oid relid, AttrNumber attnum)
 		return -1;
 }
 
+/*
+ * get_attcollation
+ *
+ *		Given the relation id and the attribute number,
+ *		return the "attcollation" field from the attribute relation.
+ */
+Oid
+get_attcollation(Oid relid, AttrNumber attnum)
+{
+	HeapTuple	tp;
+
+	tp = SearchSysCache2(ATTNUM,
+						 ObjectIdGetDatum(relid),
+						 Int16GetDatum(attnum));
+	if (HeapTupleIsValid(tp))
+	{
+		Form_pg_attribute att_tup = (Form_pg_attribute) GETSTRUCT(tp);
+		Oid		result;
+
+		result = att_tup->attcollation;
+		ReleaseSysCache(tp);
+		return result;
+	}
+	else
+		return InvalidOid;
+}
+
 /*
  * get_atttypetypmod
  *
@@ -931,6 +959,36 @@ get_atttypetypmod(Oid relid, AttrNumber attnum,
 	ReleaseSysCache(tp);
 }
 
+/*				---------- COLLATION CACHE ----------					 */
+
+/*
+ * get_collation_name
+ *		Returns the name of a given pg_collation entry.
+ *
+ * Returns a palloc'd copy of the string, or NULL if no such constraint.
+ *
+ * NOTE: since collation name is not unique, be wary of code that uses this
+ * for anything except preparing error messages.
+ */
+char *
+get_collation_name(Oid colloid)
+{
+	HeapTuple	tp;
+
+	tp = SearchSysCache1(COLLOID, ObjectIdGetDatum(colloid));
+	if (HeapTupleIsValid(tp))
+	{
+		Form_pg_collation colltup = (Form_pg_collation) GETSTRUCT(tp);
+		char	   *result;
+
+		result = pstrdup(NameStr(colltup->collname));
+		ReleaseSysCache(tp);
+		return result;
+	}
+	else
+		return NULL;
+}
+
 /*				---------- CONSTRAINT CACHE ----------					 */
 
 /*
@@ -2523,6 +2581,42 @@ get_typmodout(Oid typid)
 }
 #endif   /* NOT_USED */
 
+/*
+ * get_typcollation
+ *
+ *		Given the type OID, return the type's typcollation attribute.
+ */
+Oid
+get_typcollation(Oid typid)
+{
+	HeapTuple	tp;
+
+	tp = SearchSysCache1(TYPEOID, ObjectIdGetDatum(typid));
+	if (HeapTupleIsValid(tp))
+	{
+		Form_pg_type typtup = (Form_pg_type) GETSTRUCT(tp);
+		Oid			result;
+
+		result = typtup->typcollation;
+		ReleaseSysCache(tp);
+		return result;
+	}
+	else
+		return InvalidOid;
+}
+
+
+/*
+ * type_is_collatable
+ *
+ *		Return whether the type cares about collations
+ */
+bool
+type_is_collatable(Oid typid)
+{
+	return OidIsValid(get_typcollation(typid));
+}
+
 
 /*				---------- STATISTICS CACHE ----------					 */
 

src/backend/utils/cache/relcache.c

@@ -976,9 +976,11 @@ RelationInitIndexAccessInfo(Relation relation)
 {
 	HeapTuple	tuple;
 	Form_pg_am	aform;
+	Datum		indcollDatum;
 	Datum		indclassDatum;
 	Datum		indoptionDatum;
 	bool		isnull;
+	oidvector  *indcoll;
 	oidvector  *indclass;
 	int2vector *indoption;
 	MemoryContext indexcxt;
@@ -1061,9 +1063,25 @@ RelationInitIndexAccessInfo(Relation relation)
 		relation->rd_supportinfo = NULL;
 	}
 
+	relation->rd_indcollation = (Oid *)
+		MemoryContextAllocZero(indexcxt, natts * sizeof(Oid));
+
 	relation->rd_indoption = (int16 *)
 		MemoryContextAllocZero(indexcxt, natts * sizeof(int16));
 
+	/*
+	 * indcollation cannot be referenced directly through the C struct, because it
+	 * comes after the variable-width indkey field.  Must extract the datum
+	 * the hard way...
+	 */
+	indcollDatum = fastgetattr(relation->rd_indextuple,
+							   Anum_pg_index_indcollation,
+							   GetPgIndexDescriptor(),
+							   &isnull);
+	Assert(!isnull);
+	indcoll = (oidvector *) DatumGetPointer(indcollDatum);
+	memcpy(relation->rd_indcollation, indcoll->values, natts * sizeof(Oid));
+
 	/*
 	 * indclass cannot be referenced directly through the C struct, because it
 	 * comes after the variable-width indkey field.  Must extract the datum
@@ -3988,6 +4006,7 @@ load_relcache_init_file(bool shared)
 			RegProcedure *support;
 			int			nsupport;
 			int16	   *indoption;
+			Oid		   *indcollation;
 
 			/* Count nailed indexes to ensure we have 'em all */
 			if (rel->rd_isnailed)
@@ -4054,6 +4073,16 @@ load_relcache_init_file(bool shared)
 
 			rel->rd_support = support;
 
+			/* next, read the vector of collation OIDs */
+			if (fread(&len, 1, sizeof(len), fp) != sizeof(len))
+				goto read_failed;
+
+			indcollation = (Oid *) MemoryContextAlloc(indexcxt, len);
+			if (fread(indcollation, 1, len, fp) != len)
+				goto read_failed;
+
+			rel->rd_indcollation = indcollation;
+
 			/* finally, read the vector of indoption values */
 			if (fread(&len, 1, sizeof(len), fp) != sizeof(len))
 				goto read_failed;
@@ -4087,6 +4116,7 @@ load_relcache_init_file(bool shared)
 			Assert(rel->rd_support == NULL);
 			Assert(rel->rd_supportinfo == NULL);
 			Assert(rel->rd_indoption == NULL);
+			Assert(rel->rd_indcollation == NULL);
 		}
 
 		/*
@@ -4305,6 +4335,11 @@ write_relcache_init_file(bool shared)
 				  relform->relnatts * (am->amsupport * sizeof(RegProcedure)),
 					   fp);
 
+			/* next, write the vector of collation OIDs */
+			write_item(rel->rd_indcollation,
+					   relform->relnatts * sizeof(Oid),
+					   fp);
+
 			/* finally, write the vector of indoption values */
 			write_item(rel->rd_indoption,
 					   relform->relnatts * sizeof(int16),

src/backend/utils/cache/syscache.c

@@ -28,6 +28,7 @@
 #include "catalog/pg_auth_members.h"
 #include "catalog/pg_authid.h"
 #include "catalog/pg_cast.h"
+#include "catalog/pg_collation.h"
 #include "catalog/pg_constraint.h"
 #include "catalog/pg_conversion.h"
 #include "catalog/pg_database.h"
@@ -267,6 +268,28 @@ static const struct cachedesc cacheinfo[] = {
 		},
 		64
 	},
+	{CollationRelationId,		/* COLLNAMEENCNSP */
+		CollationNameEncNspIndexId,
+		3,
+		{
+			Anum_pg_collation_collname,
+			Anum_pg_collation_collencoding,
+			Anum_pg_collation_collnamespace,
+			0
+		},
+		256
+	},
+	{CollationRelationId,		/* COLLOID */
+		CollationOidIndexId,
+		1,
+		{
+			ObjectIdAttributeNumber,
+			0,
+			0,
+			0
+		},
+		256
+	},
 	{ConversionRelationId,		/* CONDEFAULT */
 		ConversionDefaultIndexId,
 		4,