Expand set of predefined ICU locales

Install language+region combinations even if they are not distinct from
the language's base locale.  This gives better long-term stability of
the set of predefined locales and makes the predefined locales less
implementation-dependent and more practical for users.

Reviewed-by: Peter Geoghegan <pg@bowt.ie>

2 files changed, 18 insertions, 10 deletions

diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml
index 48ecfc5f48e..f2a4acc1150 100644
--- a/doc/src/sgml/charset.sgml
+++ b/doc/src/sgml/charset.sgml
@@ -653,9 +653,8 @@ SELECT a COLLATE "C" < b COLLATE "POSIX" FROM test1;
     string will be accepted as a locale name.)
     See <ulink url="http://userguide.icu-project.org/locale"></ulink> for
     information on ICU locale naming.  <command>initdb</command> uses the ICU
-    APIs to extract a set of locales with distinct collation rules to populate
-    the initial set of collations.  Here are some example collations that
-    might be created:
+    APIs to extract a set of distinct locales to populate the initial set of
+    collations.  Here are some example collations that might be created:
 
     <variablelist>
      <varlistentry>
@@ -677,9 +676,9 @@ SELECT a COLLATE "C" &lt; b COLLATE "POSIX" FROM test1;
       <listitem>
        <para>German collation for Austria, default variant</para>
        <para>
-        (As of this writing, there is no,
-        say, <literal>de-DE-x-icu</literal> or <literal>de-CH-x-icu</literal>,
-        because those are equivalent to <literal>de-x-icu</literal>.)
+        (There are also, say, <literal>de-DE-x-icu</literal>
+        or <literal>de-CH-x-icu</literal>, but as of this writing, they are
+        equivalent to <literal>de-x-icu</literal>.)
        </para>
       </listitem>
      </varlistentry>
@@ -690,6 +689,7 @@ SELECT a COLLATE "C" &lt; b COLLATE "POSIX" FROM test1;
        <para>German collation for Austria, phone book variant</para>
       </listitem>
      </varlistentry>
+
      <varlistentry>
       <term><literal>und-x-icu</literal> (for <quote>undefined</quote>)</term>
       <listitem>
@@ -724,7 +724,6 @@ SELECT a COLLATE "C" &lt; b COLLATE "POSIX" FROM test1;
 <programlisting>
 CREATE COLLATION german FROM "de_DE";
 CREATE COLLATION french FROM "fr-x-icu";
-CREATE COLLATION "de-DE-x-icu" FROM "de-x-icu";
 </programlisting>
    </para>
 
diff --git a/src/backend/commands/collationcmds.c b/src/backend/commands/collationcmds.c
index 8572b2dedc4..d36ce535604 100644
--- a/src/backend/commands/collationcmds.c
+++ b/src/backend/commands/collationcmds.c
@@ -667,7 +667,16 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 	}
 #endif							/* READ_LOCALE_A_OUTPUT */
 
-	/* Load collations known to ICU */
+	/*
+	 * Load collations known to ICU
+	 *
+	 * We use uloc_countAvailable()/uloc_getAvailable() rather than
+	 * ucol_countAvailable()/ucol_getAvailable().  The former returns a full
+	 * set of language+region combinations, whereas the latter only returns
+	 * language+region combinations of they are distinct from the language's
+	 * base collation.  So there might not be a de-DE or en-GB, which would be
+	 * confusing.
+	 */
 #ifdef USE_ICU
 	{
 		int			i;
@@ -676,7 +685,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 		 * Start the loop at -1 to sneak in the root locale without too much
 		 * code duplication.
 		 */
-		for (i = -1; i < ucol_countAvailable(); i++)
+		for (i = -1; i < uloc_countAvailable(); i++)
 		{
 			/*
 			 * In ICU 4.2, ucol_getKeywordValuesForLocale() sometimes returns
@@ -706,7 +715,7 @@ pg_import_system_collations(PG_FUNCTION_ARGS)
 			if (i == -1)
 				name = "";		/* ICU root locale */
 			else
-				name = ucol_getAvailable(i);
+				name = uloc_getAvailable(i);
 
 			langtag = get_icu_language_tag(name);
 			collcollate = U_ICU_VERSION_MAJOR_NUM >= 54 ? langtag : name;