Fix bug in support for collation attributes on older ICU versions

petere · petere · commit 1f050c08f91d · 2019-03-19T09:37:46.000+01:00
Unrecognized attribute names are supposed to be ignored.  But the code
would error out on an unrecognized attribute value even if it did not
recognize the attribute name.  So unrecognized attributes wouldn't
really be ignored unless the value happened to be one that matched a
recognized value.  This would break some important cases where the
attribute would be processed by ucol_open() directly.  Fix that and
add a test case.

The restructured code should also avoid compiler warnings about
initializing a UColAttribute value to -1, because the type might be an
unsigned enum.  (reported by Andres Freund)
diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
@@ -1623,8 +1623,8 @@ icu_set_collation_attributes(UCollator *collator, const char *loc)
 		{
 			char	   *name;
 			char	   *value;
-			UColAttribute uattr = -1;
-			UColAttributeValue uvalue = -1;
+			UColAttribute uattr;
+			UColAttributeValue uvalue;
 			UErrorCode	status;
 
 			status = U_ZERO_ERROR;
@@ -1650,7 +1650,9 @@ icu_set_collation_attributes(UCollator *collator, const char *loc)
 				uattr = UCOL_NORMALIZATION_MODE;
 			else if (strcmp(name, "colnumeric") == 0)
 				uattr = UCOL_NUMERIC_COLLATION;
-			/* ignore if unknown */
+			else
+				/* ignore if unknown */
+				continue;
 
 			if (strcmp(value, "primary") == 0)
 				uvalue = UCOL_PRIMARY;
@@ -1677,7 +1679,7 @@ icu_set_collation_attributes(UCollator *collator, const char *loc)
 			else
 				status = U_ILLEGAL_ARGUMENT_ERROR;
 
-			if (uattr != -1 && uvalue != -1)
+			if (status == U_ZERO_ERROR)
 				ucol_setAttribute(collator, uattr, uvalue, &status);
 
 			/*
diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
@@ -1101,6 +1101,7 @@ select textrange_en_us('A','Z') @> 'b'::text;
 drop type textrange_c;
 drop type textrange_en_us;
 -- test ICU collation customization
+-- test the attributes handled by icu_set_collation_attributes()
 CREATE COLLATION testcoll_ignore_accents (provider = icu, locale = '@colStrength=primary;colCaseLevel=yes');
 SELECT 'aaá' > 'AAA' COLLATE "und-x-icu", 'aaá' < 'AAA' COLLATE testcoll_ignore_accents;
  ?column? | ?column? 
@@ -1139,6 +1140,15 @@ SELECT 'A-21' > 'A-123' COLLATE "und-x-icu", 'A-21' < 'A-123' COLLATE testcoll_n
 
 CREATE COLLATION testcoll_error1 (provider = icu, locale = '@colNumeric=lower');
 ERROR:  could not open collator for locale "@colNumeric=lower": U_ILLEGAL_ARGUMENT_ERROR
+-- test that attributes not handled by icu_set_collation_attributes()
+-- (handled by ucol_open() directly) also work
+CREATE COLLATION testcoll_de_phonebook (provider = icu, locale = 'de@collation=phonebook');
+SELECT 'Goldmann' < 'Götz' COLLATE "de-x-icu", 'Goldmann' > 'Götz' COLLATE testcoll_de_phonebook;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
 -- cleanup
 SET client_min_messages TO warning;
 DROP SCHEMA collate_tests CASCADE;
diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
@@ -427,6 +427,8 @@ drop type textrange_en_us;
 
 -- test ICU collation customization
 
+-- test the attributes handled by icu_set_collation_attributes()
+
 CREATE COLLATION testcoll_ignore_accents (provider = icu, locale = '@colStrength=primary;colCaseLevel=yes');
 SELECT 'aaá' > 'AAA' COLLATE "und-x-icu", 'aaá' < 'AAA' COLLATE testcoll_ignore_accents;
 
@@ -445,6 +447,11 @@ SELECT 'A-21' > 'A-123' COLLATE "und-x-icu", 'A-21' < 'A-123' COLLATE testcoll_n
 
 CREATE COLLATION testcoll_error1 (provider = icu, locale = '@colNumeric=lower');
 
+-- test that attributes not handled by icu_set_collation_attributes()
+-- (handled by ucol_open() directly) also work
+CREATE COLLATION testcoll_de_phonebook (provider = icu, locale = 'de@collation=phonebook');
+SELECT 'Goldmann' < 'Götz' COLLATE "de-x-icu", 'Goldmann' > 'Götz' COLLATE testcoll_de_phonebook;
+
 
 -- cleanup
 SET client_min_messages TO warning;
