ICU: do not convert locale 'C' to 'en-US-u-va-posix'.

The conversion was intended to be for convenience, but it's more
likely to be confusing than useful.

The user can still directly specify 'en-US-u-va-posix' if desired.

Discussion: https://postgr.es/m/f83f089ee1e9acd5dbbbf3353294d24e1f196e95.camel@j-davis.com
Discussion: https://postgr.es/m/37520ec1ae9591f83132f82dbd625f3fc2d69c16.camel@j-davis.com

Author: jeff-davis

src/backend/utils/adt/pg_locale.c

@@ -2782,26 +2782,10 @@ icu_language_tag(const char *loc_str, int elevel)
 {
 #ifdef USE_ICU
 	UErrorCode	 status;
-	char		 lang[ULOC_LANG_CAPACITY];
 	char		*langtag;
 	size_t		 buflen = 32;	/* arbitrary starting buffer size */
 	const bool	 strict = true;
 
-	status = U_ZERO_ERROR;
-	uloc_getLanguage(loc_str, lang, ULOC_LANG_CAPACITY, &status);
-	if (U_FAILURE(status))
-	{
-		if (elevel > 0)
-			ereport(elevel,
-					(errmsg("could not get language from locale \"%s\": %s",
-							loc_str, u_errorName(status))));
-		return NULL;
-	}
-
-	/* C/POSIX locales aren't handled by uloc_getLanguageTag() */
-	if (strcmp(lang, "c") == 0 || strcmp(lang, "posix") == 0)
-		return pstrdup("en-US-u-va-posix");
-
 	/*
 	 * A BCP47 language tag doesn't have a clearly-defined upper limit
 	 * (cf. RFC5646 section 4.4). Additionally, in older ICU versions,
@@ -2889,8 +2873,7 @@ icu_validate_locale(const char *loc_str)
 
 	/* check for special language name */
 	if (strcmp(lang, "") == 0 ||
-		strcmp(lang, "root") == 0 || strcmp(lang, "und") == 0 ||
-		strcmp(lang, "c") == 0 || strcmp(lang, "posix") == 0)
+		strcmp(lang, "root") == 0 || strcmp(lang, "und") == 0)
 		found = true;
 
 	/* search for matching language within ICU */

src/bin/initdb/initdb.c

@@ -2238,24 +2238,10 @@ icu_language_tag(const char *loc_str)
 {
 #ifdef USE_ICU
 	UErrorCode	 status;
-	char		 lang[ULOC_LANG_CAPACITY];
 	char		*langtag;
 	size_t		 buflen = 32;	/* arbitrary starting buffer size */
 	const bool	 strict = true;
 
-	status = U_ZERO_ERROR;
-	uloc_getLanguage(loc_str, lang, ULOC_LANG_CAPACITY, &status);
-	if (U_FAILURE(status))
-	{
-		pg_fatal("could not get language from locale \"%s\": %s",
-				 loc_str, u_errorName(status));
-		return NULL;
-	}
-
-	/* C/POSIX locales aren't handled by uloc_getLanguageTag() */
-	if (strcmp(lang, "c") == 0 || strcmp(lang, "posix") == 0)
-		return pstrdup("en-US-u-va-posix");
-
 	/*
 	 * A BCP47 language tag doesn't have a clearly-defined upper limit
 	 * (cf. RFC5646 section 4.4). Additionally, in older ICU versions,
@@ -2327,8 +2313,7 @@ icu_validate_locale(const char *loc_str)
 
 	/* check for special language name */
 	if (strcmp(lang, "") == 0 ||
-		strcmp(lang, "root") == 0 || strcmp(lang, "und") == 0 ||
-		strcmp(lang, "c") == 0 || strcmp(lang, "posix") == 0)
+		strcmp(lang, "root") == 0 || strcmp(lang, "und") == 0)
 		found = true;
 
 	/* search for matching language within ICU */

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

@@ -1020,6 +1020,7 @@ CREATE ROLE regress_test_role;
 CREATE SCHEMA test_schema;
 -- We need to do this this way to cope with varying names for encodings:
 SET client_min_messages TO WARNING;
+SET icu_validation_level = disabled;
 do $$
 BEGIN
   EXECUTE 'CREATE COLLATION test0 (provider = icu, locale = ' ||
@@ -1034,17 +1035,24 @@ BEGIN
           quote_literal(current_setting('lc_collate')) || ');';
 END
 $$;
+RESET icu_validation_level;
 RESET client_min_messages;
 CREATE COLLATION test3 (provider = icu, lc_collate = 'en_US.utf8'); -- fail, needs "locale"
 ERROR:  parameter "locale" must be specified
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); -- fails
 ERROR:  ICU locale "nonsense-nowhere" has unknown language "nonsense"
 HINT:  To disable ICU locale validation, set parameter icu_validation_level to DISABLED.
+CREATE COLLATION testx (provider = icu, locale = 'C'); -- fails
+ERROR:  could not convert locale name "C" to language tag: U_ILLEGAL_ARGUMENT_ERROR
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); -- fails
 ERROR:  could not convert locale name "@colStrength=primary;nonsense=yes" to language tag: U_ILLEGAL_ARGUMENT_ERROR
 SET icu_validation_level = WARNING;
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); DROP COLLATION testx;
 WARNING:  could not convert locale name "@colStrength=primary;nonsense=yes" to language tag: U_ILLEGAL_ARGUMENT_ERROR
+CREATE COLLATION testx (provider = icu, locale = 'C'); DROP COLLATION testx;
+WARNING:  could not convert locale name "C" to language tag: U_ILLEGAL_ARGUMENT_ERROR
+WARNING:  ICU locale "C" has unknown language "c"
+HINT:  To disable ICU locale validation, set parameter icu_validation_level to DISABLED.
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); DROP COLLATION testx;
 WARNING:  ICU locale "nonsense-nowhere" has unknown language "nonsense"
 HINT:  To disable ICU locale validation, set parameter icu_validation_level to DISABLED.

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

@@ -358,6 +358,7 @@ CREATE SCHEMA test_schema;
 
 -- We need to do this this way to cope with varying names for encodings:
 SET client_min_messages TO WARNING;
+SET icu_validation_level = disabled;
 
 do $$
 BEGIN
@@ -373,13 +374,16 @@ BEGIN
 END
 $$;
 
+RESET icu_validation_level;
 RESET client_min_messages;
 
 CREATE COLLATION test3 (provider = icu, lc_collate = 'en_US.utf8'); -- fail, needs "locale"
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); -- fails
+CREATE COLLATION testx (provider = icu, locale = 'C'); -- fails
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); -- fails
 SET icu_validation_level = WARNING;
 CREATE COLLATION testx (provider = icu, locale = '@colStrength=primary;nonsense=yes'); DROP COLLATION testx;
+CREATE COLLATION testx (provider = icu, locale = 'C'); DROP COLLATION testx;
 CREATE COLLATION testx (provider = icu, locale = 'nonsense-nowhere'); DROP COLLATION testx;
 RESET icu_validation_level;