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

Author: petere

config/c-library.m4

@@ -297,3 +297,32 @@ int main()
 ])dnl AC_CACHE_VAL
 AC_MSG_RESULT([$pgac_cv_printf_arg_control])
 ])# PGAC_FUNC_PRINTF_ARG_CONTROL
+
+
+# PGAC_TYPE_LOCALE_T
+# ------------------
+# Check for the locale_t type and find the right header file.  Mac OS
+# X needs xlocale.h; standard is locale.h, but glibc also has an
+# xlocale.h file that we should not use.
+#
+AC_DEFUN([PGAC_TYPE_LOCALE_T],
+[AC_CACHE_CHECK([for locale_t], pgac_cv_type_locale_t,
+[AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
+[#include <locale.h>
+locale_t x;],
+[])],
+[pgac_cv_type_locale_t=yes],
+[AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
+[#include <xlocale.h>
+locale_t x;],
+[])],
+[pgac_cv_type_locale_t='yes (in xlocale.h)'],
+[pgac_cv_type_locale_t=no])])])
+if test "$pgac_cv_type_locale_t" != no; then
+  AC_DEFINE(HAVE_LOCALE_T, 1,
+            [Define to 1 if the system has the type `locale_t'.])
+fi
+if test "$pgac_cv_type_locale_t" = 'yes (in xlocale.h)'; then
+  AC_DEFINE(LOCALE_T_IN_XLOCALE, 1,
+            [Define to 1 if `locale_t' requires <xlocale.h>.])
+fi])])# PGAC_HEADER_XLOCALE

configure

@@ -16830,6 +16830,114 @@ _ACEOF
   fi
 
 
+{ $as_echo "$as_me:$LINENO: checking for locale_t" >&5
+$as_echo_n "checking for locale_t... " >&6; }
+if test "${pgac_cv_type_locale_t+set}" = set; then
+  $as_echo_n "(cached) " >&6
+else
+  cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+#include <locale.h>
+locale_t x;
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+rm -f conftest.$ac_objext
+if { (ac_try="$ac_compile"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:$LINENO: $ac_try_echo\""
+$as_echo "$ac_try_echo") >&5
+  (eval "$ac_compile") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  $as_echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && {
+	 test -z "$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       } && test -s conftest.$ac_objext; then
+  pgac_cv_type_locale_t=yes
+else
+  $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+	cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+#include <xlocale.h>
+locale_t x;
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+rm -f conftest.$ac_objext
+if { (ac_try="$ac_compile"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval ac_try_echo="\"\$as_me:$LINENO: $ac_try_echo\""
+$as_echo "$ac_try_echo") >&5
+  (eval "$ac_compile") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  $as_echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && {
+	 test -z "$ac_c_werror_flag" ||
+	 test ! -s conftest.err
+       } && test -s conftest.$ac_objext; then
+  pgac_cv_type_locale_t='yes (in xlocale.h)'
+else
+  $as_echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+	pgac_cv_type_locale_t=no
+fi
+
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:$LINENO: result: $pgac_cv_type_locale_t" >&5
+$as_echo "$pgac_cv_type_locale_t" >&6; }
+if test "$pgac_cv_type_locale_t" != no; then
+
+cat >>confdefs.h <<\_ACEOF
+#define HAVE_LOCALE_T 1
+_ACEOF
+
+fi
+if test "$pgac_cv_type_locale_t" = 'yes (in xlocale.h)'; then
+
+cat >>confdefs.h <<\_ACEOF
+#define LOCALE_T_IN_XLOCALE 1
+_ACEOF
+
+fi
+
 { $as_echo "$as_me:$LINENO: checking for struct cmsgcred" >&5
 $as_echo_n "checking for struct cmsgcred... " >&6; }
 if test "${ac_cv_type_struct_cmsgcred+set}" = set; then

configure.in

@@ -1118,6 +1118,8 @@ AC_TYPE_INTPTR_T
 AC_TYPE_UINTPTR_T
 AC_TYPE_LONG_LONG_INT
 
+PGAC_TYPE_LOCALE_T
+
 AC_CHECK_TYPES([struct cmsgcred, struct fcred, struct sockcred], [], [],
 [#include <sys/param.h>
 #include <sys/types.h>

contrib/btree_gin/btree_gin.c

@@ -7,6 +7,7 @@
 
 #include "fmgr.h"
 #include "access/skey.h"
+#include "catalog/pg_collation.h"
 #include "utils/builtins.h"
 #include "utils/bytea.h"
 #include "utils/cash.h"
@@ -120,8 +121,9 @@ gin_compare_prefix_##type(PG_FUNCTION_ARGS)									\
 	int32		res,														\
 				cmp;														\
 																			\
-	cmp = DatumGetInt32(DirectFunctionCall2(								\
+	cmp = DatumGetInt32(DirectFunctionCall2WithCollation(					\
 				TypeInfo_##type.typecmp,									\
+				DEFAULT_COLLATION_OID,										\
 				(data->strategy == BTLessStrategyNumber ||					\
 				 data->strategy == BTLessEqualStrategyNumber)				\
 				 ? data->datum : a,											\

contrib/btree_gist/btree_text.c

@@ -3,6 +3,7 @@
  */
 #include "btree_gist.h"
 #include "btree_utils_var.h"
+#include "catalog/pg_collation.h"
 #include "utils/builtins.h"
 
 /*
@@ -32,37 +33,37 @@ Datum		gbt_text_same(PG_FUNCTION_ARGS);
 static bool
 gbt_textgt(const void *a, const void *b)
 {
-	return (DatumGetBool(DirectFunctionCall2(text_gt, PointerGetDatum(a), PointerGetDatum(b))));
+	return (DatumGetBool(DirectFunctionCall2WithCollation(text_gt, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b))));
 }
 
 static bool
 gbt_textge(const void *a, const void *b)
 {
-	return (DatumGetBool(DirectFunctionCall2(text_ge, PointerGetDatum(a), PointerGetDatum(b))));
+	return (DatumGetBool(DirectFunctionCall2WithCollation(text_ge, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b))));
 }
 
 static bool
 gbt_texteq(const void *a, const void *b)
 {
-	return (DatumGetBool(DirectFunctionCall2(texteq, PointerGetDatum(a), PointerGetDatum(b))));
+	return (DatumGetBool(DirectFunctionCall2WithCollation(texteq, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b))));
 }
 
 static bool
 gbt_textle(const void *a, const void *b)
 {
-	return (DatumGetBool(DirectFunctionCall2(text_le, PointerGetDatum(a), PointerGetDatum(b))));
+	return (DatumGetBool(DirectFunctionCall2WithCollation(text_le, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b))));
 }
 
 static bool
 gbt_textlt(const void *a, const void *b)
 {
-	return (DatumGetBool(DirectFunctionCall2(text_lt, PointerGetDatum(a), PointerGetDatum(b))));
+	return (DatumGetBool(DirectFunctionCall2WithCollation(text_lt, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b))));
 }
 
 static int32
 gbt_textcmp(const bytea *a, const bytea *b)
 {
-	return DatumGetInt32(DirectFunctionCall2(bttextcmp, PointerGetDatum(a), PointerGetDatum(b)));
+	return DatumGetInt32(DirectFunctionCall2WithCollation(bttextcmp, DEFAULT_COLLATION_OID, PointerGetDatum(a), PointerGetDatum(b)));
 }
 
 static gbtree_vinfo tinfo =

contrib/btree_gist/btree_utils_var.c

@@ -8,6 +8,7 @@
 #include <float.h>
 
 #include "btree_utils_var.h"
+#include "catalog/pg_collation.h"
 #include "utils/pg_locale.h"
 #include "utils/builtins.h"
 #include "utils/rel.h"
@@ -156,7 +157,7 @@ gbt_bytea_pf_match(const bytea *pf, const bytea *query, const gbtree_vinfo *tinf
 
 		if (tinfo->eml > 1)
 		{
-			out = (varstr_cmp(q, nlen, n, nlen) == 0);
+			out = (varstr_cmp(q, nlen, n, nlen, DEFAULT_COLLATION_OID) == 0);
 		}
 		else
 		{

contrib/citext/citext.c

@@ -18,7 +18,7 @@ PG_MODULE_MAGIC;
  *		====================
  */
 
-static int32 citextcmp(text *left, text *right);
+static int32 citextcmp(text *left, text *right, Oid collid);
 extern Datum citext_cmp(PG_FUNCTION_ARGS);
 extern Datum citext_hash(PG_FUNCTION_ARGS);
 extern Datum citext_eq(PG_FUNCTION_ARGS);
@@ -42,17 +42,18 @@ extern Datum citext_larger(PG_FUNCTION_ARGS);
  * Returns int32 negative, zero, or positive.
  */
 static int32
-citextcmp(text *left, text *right)
+citextcmp(text *left, text *right, Oid collid)
 {
 	char	   *lcstr,
 			   *rcstr;
 	int32		result;
 
-	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left));
-	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right));
+	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), collid);
+	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), collid);
 
 	result = varstr_cmp(lcstr, strlen(lcstr),
-						rcstr, strlen(rcstr));
+						rcstr, strlen(rcstr),
+						collid);
 
 	pfree(lcstr);
 	pfree(rcstr);
@@ -75,7 +76,7 @@ citext_cmp(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	int32		result;
 
-	result = citextcmp(left, right);
+	result = citextcmp(left, right, PG_GET_COLLATION());
 
 	PG_FREE_IF_COPY(left, 0);
 	PG_FREE_IF_COPY(right, 1);
@@ -92,7 +93,7 @@ citext_hash(PG_FUNCTION_ARGS)
 	char	   *str;
 	Datum		result;
 
-	str = str_tolower(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt));
+	str = str_tolower(VARDATA_ANY(txt), VARSIZE_ANY_EXHDR(txt), PG_GET_COLLATION());
 	result = hash_any((unsigned char *) str, strlen(str));
 	pfree(str);
 
@@ -121,8 +122,8 @@ citext_eq(PG_FUNCTION_ARGS)
 
 	/* We can't compare lengths in advance of downcasing ... */
 
-	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left));
-	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right));
+	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), PG_GET_COLLATION());
+	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), PG_GET_COLLATION());
 
 	/*
 	 * Since we only care about equality or not-equality, we can avoid all the
@@ -151,8 +152,8 @@ citext_ne(PG_FUNCTION_ARGS)
 
 	/* We can't compare lengths in advance of downcasing ... */
 
-	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left));
-	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right));
+	lcstr = str_tolower(VARDATA_ANY(left), VARSIZE_ANY_EXHDR(left), PG_GET_COLLATION());
+	rcstr = str_tolower(VARDATA_ANY(right), VARSIZE_ANY_EXHDR(right), PG_GET_COLLATION());
 
 	/*
 	 * Since we only care about equality or not-equality, we can avoid all the
@@ -177,7 +178,7 @@ citext_lt(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	bool		result;
 
-	result = citextcmp(left, right) < 0;
+	result = citextcmp(left, right, PG_GET_COLLATION()) < 0;
 
 	PG_FREE_IF_COPY(left, 0);
 	PG_FREE_IF_COPY(right, 1);
@@ -194,7 +195,7 @@ citext_le(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	bool		result;
 
-	result = citextcmp(left, right) <= 0;
+	result = citextcmp(left, right, PG_GET_COLLATION()) <= 0;
 
 	PG_FREE_IF_COPY(left, 0);
 	PG_FREE_IF_COPY(right, 1);
@@ -211,7 +212,7 @@ citext_gt(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	bool		result;
 
-	result = citextcmp(left, right) > 0;
+	result = citextcmp(left, right, PG_GET_COLLATION()) > 0;
 
 	PG_FREE_IF_COPY(left, 0);
 	PG_FREE_IF_COPY(right, 1);
@@ -228,7 +229,7 @@ citext_ge(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	bool		result;
 
-	result = citextcmp(left, right) >= 0;
+	result = citextcmp(left, right, PG_GET_COLLATION()) >= 0;
 
 	PG_FREE_IF_COPY(left, 0);
 	PG_FREE_IF_COPY(right, 1);
@@ -251,7 +252,7 @@ citext_smaller(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	text	   *result;
 
-	result = citextcmp(left, right) < 0 ? left : right;
+	result = citextcmp(left, right, PG_GET_COLLATION()) < 0 ? left : right;
 	PG_RETURN_TEXT_P(result);
 }
 
@@ -264,6 +265,6 @@ citext_larger(PG_FUNCTION_ARGS)
 	text	   *right = PG_GETARG_TEXT_PP(1);
 	text	   *result;
 
-	result = citextcmp(left, right) > 0 ? left : right;
+	result = citextcmp(left, right, PG_GET_COLLATION()) > 0 ? left : right;
 	PG_RETURN_TEXT_P(result);
 }

contrib/citext/citext.sql.in

@@ -52,7 +52,8 @@ CREATE TYPE citext (
     STORAGE        = extended,
     -- make it a non-preferred member of string type category
     CATEGORY       = 'S',
-    PREFERRED      = false
+    PREFERRED      = false,
+    COLLATABLE     = true
 );
 
 --

contrib/ltree/lquery_op.c

@@ -7,6 +7,7 @@
 
 #include <ctype.h>
 
+#include "catalog/pg_collation.h"
 #include "utils/array.h"
 #include "utils/formatting.h"
 #include "ltree.h"
@@ -90,8 +91,8 @@ bool
 int
 ltree_strncasecmp(const char *a, const char *b, size_t s)
 {
-	char	   *al = str_tolower(a, s);
-	char	   *bl = str_tolower(b, s);
+	char	   *al = str_tolower(a, s, DEFAULT_COLLATION_OID);
+	char	   *bl = str_tolower(b, s, DEFAULT_COLLATION_OID);
 	int			res;
 
 	res = strncmp(al, bl, s);