Address more review comments on commit 2d819a0.

Based on comments from Peter Eisentraut.

 * Document CREATE DATABASE ... BUILTIN_LOCALE.
 * Determine required encoding based on locale name for CREATE
   COLLATION. Use -1 for "C" (requires catversion bump).
 * initdb output fixups.
 * Make ctype_is_c a constant true for now.
 * Fixups to ICU 010_create_database.pl test.

Discussion: https://postgr.es/m/4135cf11-206d-40ed-96c0-9363c1232379@eisentraut.org

Author: jeff-davis

doc/src/sgml/ref/create_database.sgml

@@ -29,6 +29,7 @@ CREATE DATABASE <replaceable class="parameter">name</replaceable>
            [ LOCALE [=] <replaceable class="parameter">locale</replaceable> ]
            [ LC_COLLATE [=] <replaceable class="parameter">lc_collate</replaceable> ]
            [ LC_CTYPE [=] <replaceable class="parameter">lc_ctype</replaceable> ]
+           [ BUILTIN_LOCALE [=] <replaceable class="parameter">builtin_locale</replaceable> ]
            [ ICU_LOCALE [=] <replaceable class="parameter">icu_locale</replaceable> ]
            [ ICU_RULES [=] <replaceable class="parameter">icu_rules</replaceable> ]
            [ LOCALE_PROVIDER [=] <replaceable class="parameter">locale_provider</replaceable> ]
@@ -216,6 +217,23 @@ CREATE DATABASE <replaceable class="parameter">name</replaceable>
       </listitem>
      </varlistentry>
 
+     <varlistentry id="create-database-builtin-locale">
+      <term><replaceable class="parameter">builtin_locale</replaceable></term>
+      <listitem>
+       <para>
+        Specifies the builtin provider locale for the database default
+        collation order and character classification, overriding the setting
+        <xref linkend="create-database-locale"/>.  The <link
+        linkend="create-database-locale-provider">locale provider</link> must
+        be <literal>builtin</literal>.  The default is the setting of <xref
+        linkend="create-database-locale"/> if specified; otherwise the same
+        setting as the template database.  Currently, the only available
+        locale for the <literal>builtin</literal> provider is
+        <literal>C</literal>.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="create-database-icu-locale">
       <term><replaceable class="parameter">icu_locale</replaceable></term>
       <listitem>

src/backend/commands/collationcmds.c

@@ -318,7 +318,7 @@ DefineCollation(ParseState *pstate, List *names, List *parameters, bool if_not_e
 
 		if (collprovider == COLLPROVIDER_BUILTIN)
 		{
-			collencoding = GetDatabaseEncoding();
+			collencoding = builtin_locale_encoding(colllocale);
 		}
 		else if (collprovider == COLLPROVIDER_ICU)
 		{

src/backend/utils/adt/pg_locale.c

@@ -1270,14 +1270,8 @@ lookup_collation_cache(Oid collation, bool set_flags)
 
 		if (collform->collprovider == COLLPROVIDER_BUILTIN)
 		{
-			Datum		datum;
-			const char *colllocale;
-
-			datum = SysCacheGetAttrNotNull(COLLOID, tp, Anum_pg_collation_colllocale);
-			colllocale = TextDatumGetCString(datum);
-
 			cache_entry->collate_is_c = true;
-			cache_entry->ctype_is_c = (strcmp(colllocale, "C") == 0);
+			cache_entry->ctype_is_c = true;
 		}
 		else if (collform->collprovider == COLLPROVIDER_LIBC)
 		{
@@ -2501,6 +2495,26 @@ pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
 	return result;
 }
 
+/*
+ * Return required encoding ID for the given locale, or -1 if any encoding is
+ * valid for the locale.
+ *
+ * The only supported locale for the builtin provider is "C", and it's
+ * available for any encoding.
+ */
+int
+builtin_locale_encoding(const char *locale)
+{
+	if (strcmp(locale, "C") == 0)
+		return -1;
+	else
+		ereport(ERROR,
+				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
+				 errmsg("invalid locale name \"%s\" for builtin provider",
+						locale)));
+}
+
+
 /*
  * Validate the locale and encoding combination, and return the canonical form
  * of the locale name.

src/bin/initdb/initdb.c

@@ -2455,7 +2455,8 @@ usage(const char *progname)
 			 "                            set default locale in the respective category for\n"
 			 "                            new databases (default taken from environment)\n"));
 	printf(_("      --no-locale           equivalent to --locale=C\n"));
-	printf(_("      --builtin-locale=LOCALE   set builtin locale name for new databases\n"));
+	printf(_("      --builtin-locale=LOCALE\n"
+			 "                            set builtin locale name for new databases\n"));
 	printf(_("      --locale-provider={builtin|libc|icu}\n"
 			 "                            set default locale provider for new databases\n"));
 	printf(_("      --pwfile=FILE         read password for the new superuser from file\n"));
@@ -2618,9 +2619,9 @@ setup_locale_encoding(void)
 	else
 	{
 		printf(_("The database cluster will be initialized with this locale configuration:\n"));
-		printf(_("  default collation provider:  %s\n"), collprovider_name(locale_provider));
+		printf(_("  locale provider:   %s\n"), collprovider_name(locale_provider));
 		if (locale_provider != COLLPROVIDER_LIBC)
-			printf(_("  default collation locale:    %s\n"), datlocale);
+			printf(_("  default collation: %s\n"), datlocale);
 		printf(_("  LC_COLLATE:  %s\n"
 				 "  LC_CTYPE:    %s\n"
 				 "  LC_MESSAGES: %s\n"

src/bin/initdb/t/001_initdb.pl

@@ -138,7 +138,7 @@
 			'--lc-monetary=C', '--lc-time=C',
 			"$tempdir/data4"
 		],
-		qr/^\s+default collation locale:\s+und\n/ms,
+		qr/^\s+default collation:\s+und\n/ms,
 		'options --locale-provider=icu --locale=und --lc-*=C');
 
 	command_fails_like(

src/include/catalog/catversion.h

@@ -57,6 +57,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202403172
+#define CATALOG_VERSION_NO	202403181
 
 #endif

src/include/utils/pg_locale.h

@@ -117,6 +117,7 @@ extern size_t pg_strxfrm_prefix(char *dest, const char *src, size_t destsize,
 extern size_t pg_strnxfrm_prefix(char *dest, size_t destsize, const char *src,
 								 size_t srclen, pg_locale_t locale);
 
+extern int	builtin_locale_encoding(const char *loc_str);
 extern const char *builtin_validate_locale(int encoding, const char *loc_str);
 extern void icu_validate_locale(const char *loc_str);
 extern char *icu_language_tag(const char *loc_str, int elevel);

src/test/icu/t/010_database.pl

@@ -62,8 +62,18 @@
 	0,
 	"C locale works for ICU");
 
+# Test that LOCALE works for ICU locales if LC_COLLATE and LC_CTYPE
+# are specified
+is( $node1->psql(
+		'postgres',
+		q{CREATE DATABASE dbicu2 LOCALE_PROVIDER icu LOCALE '@colStrength=primary'
+          LC_COLLATE='C' LC_CTYPE='C' TEMPLATE template0 ENCODING UTF8}
+	),
+	0,
+	"LOCALE works for ICU locales if LC_COLLATE and LC_CTYPE are specified");
+
 my ($ret, $stdout, $stderr) = $node1->psql('postgres',
-	q{CREATE DATABASE dbicu LOCALE_PROVIDER builtin LOCALE 'C' TEMPLATE dbicu}
+	q{CREATE DATABASE dbicu3 LOCALE_PROVIDER builtin LOCALE 'C' TEMPLATE dbicu}
 );
 isnt($ret, 0, "locale provider must match template: exit code not 0");
 like(