Add support for collation attributes on older ICU versions

Starting in ICU 54, collation customization attributes can be
specified in the locale string, for example
"@colStrength=primary;colCaseLevel=yes".  Add support for this for
older ICU versions as well, by adding some minimal parsing of the
attributes in the locale string and calling ucol_setAttribute() on
them.  This is essentially what never ICU versions do internally in
ucol_open().  This was we can offer this functionality in a consistent
way in all ICU versions supported by PostgreSQL.

Also add some tests for ICU collation customization.

Reported-by: Daniel Verite <[email protected]>
Discussion: https://www.postgresql.org/message-id/[email protected]

Author: petere

src/backend/utils/adt/pg_locale.c

@@ -58,6 +58,7 @@
 #include "catalog/pg_control.h"
 #include "mb/pg_wchar.h"
 #include "utils/builtins.h"
+#include "utils/formatting.h"
 #include "utils/hsearch.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -132,6 +133,9 @@ static HTAB *collation_cache = NULL;
 static char *IsoLocaleName(const char *);	/* MSVC specific */
 #endif
 
+#ifdef USE_ICU
+static void icu_set_collation_attributes(UCollator *collator, const char *loc);
+#endif
 
 /*
  * pg_perm_setlocale
@@ -1380,6 +1384,9 @@ pg_newlocale_from_collation(Oid collid)
 						(errmsg("could not open collator for locale \"%s\": %s",
 								collcollate, u_errorName(status))));
 
+			if (U_ICU_VERSION_MAJOR_NUM < 54)
+				icu_set_collation_attributes(collator, collcollate);
+
 			/* We will leak this string if we get an error below :-( */
 			result.info.icu.locale = MemoryContextStrdup(TopMemoryContext,
 														 collcollate);
@@ -1588,6 +1595,103 @@ icu_from_uchar(char **result, const UChar *buff_uchar, int32_t len_uchar)
 	return len_result;
 }
 
+/*
+ * Parse collation attributes and apply them to the open collator.  This takes
+ * a string like "und@colStrength=primary;colCaseLevel=yes" and parses and
+ * applies the key-value arguments.
+ *
+ * Starting with ICU version 54, the attributes are processed automatically by
+ * ucol_open(), so this is only necessary for emulating this behavior on older
+ * versions.
+ */
+pg_attribute_unused()
+static void
+icu_set_collation_attributes(UCollator *collator, const char *loc)
+{
+	char	   *str = asc_tolower(loc, strlen(loc));
+
+	str = strchr(str, '@');
+	if (!str)
+		return;
+	str++;
+
+	for (char *token = strtok(str, ";"); token; token = strtok(NULL, ";"))
+	{
+		char	   *e = strchr(token, '=');
+
+		if (e)
+		{
+			char	   *name;
+			char	   *value;
+			UColAttribute uattr = -1;
+			UColAttributeValue uvalue = -1;
+			UErrorCode	status;
+
+			status = U_ZERO_ERROR;
+
+			*e = '\0';
+			name = token;
+			value = e + 1;
+
+			/*
+			 * See attribute name and value lists in ICU i18n/coll.cpp
+			 */
+			if (strcmp(name, "colstrength") == 0)
+				uattr = UCOL_STRENGTH;
+			else if (strcmp(name, "colbackwards") == 0)
+				uattr = UCOL_FRENCH_COLLATION;
+			else if (strcmp(name, "colcaselevel") == 0)
+				uattr = UCOL_CASE_LEVEL;
+			else if (strcmp(name, "colcasefirst") == 0)
+				uattr = UCOL_CASE_FIRST;
+			else if (strcmp(name, "colalternate") == 0)
+				uattr = UCOL_ALTERNATE_HANDLING;
+			else if (strcmp(name, "colnormalization") == 0)
+				uattr = UCOL_NORMALIZATION_MODE;
+			else if (strcmp(name, "colnumeric") == 0)
+				uattr = UCOL_NUMERIC_COLLATION;
+			/* ignore if unknown */
+
+			if (strcmp(value, "primary") == 0)
+				uvalue = UCOL_PRIMARY;
+			else if (strcmp(value, "secondary") == 0)
+				uvalue = UCOL_SECONDARY;
+			else if (strcmp(value, "tertiary") == 0)
+				uvalue = UCOL_TERTIARY;
+			else if (strcmp(value, "quaternary") == 0)
+				uvalue = UCOL_QUATERNARY;
+			else if (strcmp(value, "identical") == 0)
+				uvalue = UCOL_IDENTICAL;
+			else if (strcmp(value, "no") == 0)
+				uvalue = UCOL_OFF;
+			else if (strcmp(value, "yes") == 0)
+				uvalue = UCOL_ON;
+			else if (strcmp(value, "shifted") == 0)
+				uvalue = UCOL_SHIFTED;
+			else if (strcmp(value, "non-ignorable") == 0)
+				uvalue = UCOL_NON_IGNORABLE;
+			else if (strcmp(value, "lower") == 0)
+				uvalue = UCOL_LOWER_FIRST;
+			else if (strcmp(value, "upper") == 0)
+				uvalue = UCOL_UPPER_FIRST;
+			else
+				status = U_ILLEGAL_ARGUMENT_ERROR;
+
+			if (uattr != -1 && uvalue != -1)
+				ucol_setAttribute(collator, uattr, uvalue, &status);
+
+			/*
+			 * Pretend the error came from ucol_open(), for consistent error
+			 * message across ICU versions.
+			 */
+			if (U_FAILURE(status))
+				ereport(ERROR,
+						(errmsg("could not open collator for locale \"%s\": %s",
+								loc, u_errorName(status))));
+		}
+	}
+}
+
 #endif							/* USE_ICU */
 
 /*

src/test/regress/expected/collate.icu.utf8.out

@@ -1100,6 +1100,45 @@ select textrange_en_us('A','Z') @> 'b'::text;
 
 drop type textrange_c;
 drop type textrange_en_us;
+-- test ICU collation customization
+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? 
+----------+----------
+ t        | t
+(1 row)
+
+CREATE COLLATION testcoll_backwards (provider = icu, locale = '@colBackwards=yes');
+SELECT 'coté' < 'côte' COLLATE "und-x-icu", 'coté' > 'côte' COLLATE testcoll_backwards;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
+CREATE COLLATION testcoll_lower_first (provider = icu, locale = '@colCaseFirst=lower');
+CREATE COLLATION testcoll_upper_first (provider = icu, locale = '@colCaseFirst=upper');
+SELECT 'aaa' < 'AAA' COLLATE testcoll_lower_first, 'aaa' > 'AAA' COLLATE testcoll_upper_first;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
+CREATE COLLATION testcoll_shifted (provider = icu, locale = '@colAlternate=shifted');
+SELECT 'de-luge' < 'deanza' COLLATE "und-x-icu", 'de-luge' > 'deanza' COLLATE testcoll_shifted;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
+CREATE COLLATION testcoll_numeric (provider = icu, locale = '@colNumeric=yes');
+SELECT 'A-21' > 'A-123' COLLATE "und-x-icu", 'A-21' < 'A-123' COLLATE testcoll_numeric;
+ ?column? | ?column? 
+----------+----------
+ t        | t
+(1 row)
+
+CREATE COLLATION testcoll_error1 (provider = icu, locale = '@colNumeric=lower');
+ERROR:  could not open collator for locale "@colNumeric=lower": U_ILLEGAL_ARGUMENT_ERROR
 -- cleanup
 SET client_min_messages TO warning;
 DROP SCHEMA collate_tests CASCADE;

src/test/regress/sql/collate.icu.utf8.sql

@@ -425,6 +425,27 @@ drop type textrange_c;
 drop type textrange_en_us;
 
 
+-- test ICU collation customization
+
+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;
+
+CREATE COLLATION testcoll_backwards (provider = icu, locale = '@colBackwards=yes');
+SELECT 'coté' < 'côte' COLLATE "und-x-icu", 'coté' > 'côte' COLLATE testcoll_backwards;
+
+CREATE COLLATION testcoll_lower_first (provider = icu, locale = '@colCaseFirst=lower');
+CREATE COLLATION testcoll_upper_first (provider = icu, locale = '@colCaseFirst=upper');
+SELECT 'aaa' < 'AAA' COLLATE testcoll_lower_first, 'aaa' > 'AAA' COLLATE testcoll_upper_first;
+
+CREATE COLLATION testcoll_shifted (provider = icu, locale = '@colAlternate=shifted');
+SELECT 'de-luge' < 'deanza' COLLATE "und-x-icu", 'de-luge' > 'deanza' COLLATE testcoll_shifted;
+
+CREATE COLLATION testcoll_numeric (provider = icu, locale = '@colNumeric=yes');
+SELECT 'A-21' > 'A-123' COLLATE "und-x-icu", 'A-21' < 'A-123' COLLATE testcoll_numeric;
+
+CREATE COLLATION testcoll_error1 (provider = icu, locale = '@colNumeric=lower');
+
+
 -- cleanup
 SET client_min_messages TO warning;
 DROP SCHEMA collate_tests CASCADE;