Validate ICU locales.

For ICU collations, ensure that the locale's language exists in ICU,
and that the locale can be opened.

Basic validation helps avoid minor mistakes and misspellings, which
often fall back to the root locale instead of the intended
locale. It's even more important to avoid such mistakes in ICU
versions 54 and earlier, where the same (misspelled) locale string
could fall back to different locales depending on the environment.

Discussion: https://postgr.es/m/11b1eeb7e7667fdd4178497aeb796c48d26e69b9.camel@j-davis.com
Discussion: https://postgr.es/m/df2efad0cae7c65180df8e5ebb709e5eb4f2a82b.camel@j-davis.com
Reviewed-by: Peter Eisentraut

2 files changed, 74 insertions, 2 deletions

diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c
index 6b20a962ecc..d5ac25904da 100644
--- a/src/bin/initdb/initdb.c
+++ b/src/bin/initdb/initdb.c
@@ -2243,6 +2243,58 @@ check_icu_locale_encoding(int user_enc)
 }
 
 /*
+ * Perform best-effort check that the locale is a valid one. Should be
+ * consistent with pg_locale.c, except that it doesn't need to open the
+ * collator (that will happen during post-bootstrap initialization).
+ */
+static void
+icu_validate_locale(const char *loc_str)
+{
+#ifdef USE_ICU
+	UErrorCode	 status;
+	char		 lang[ULOC_LANG_CAPACITY];
+	bool		 found	 = false;
+
+	/* validate that we can extract the language */
+	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;
+	}
+
+	/* 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)
+		found = true;
+
+	/* search for matching language within ICU */
+	for (int32_t i = 0; !found && i < uloc_countAvailable(); i++)
+	{
+		const char	*otherloc = uloc_getAvailable(i);
+		char		 otherlang[ULOC_LANG_CAPACITY];
+
+		status = U_ZERO_ERROR;
+		uloc_getLanguage(otherloc, otherlang, ULOC_LANG_CAPACITY, &status);
+		if (U_FAILURE(status))
+			continue;
+
+		if (strcmp(lang, otherlang) == 0)
+			found = true;
+	}
+
+	if (!found)
+		pg_fatal("locale \"%s\" has unknown language \"%s\"",
+				 loc_str, lang);
+#else
+	pg_fatal("ICU is not supported in this build");
+#endif
+}
+
+/*
  * Determine default ICU locale by opening the default collator and reading
  * its locale.
  *
@@ -2344,9 +2396,11 @@ setlocales(void)
 			printf(_("Using default ICU locale \"%s\".\n"), icu_locale);
 		}
 
+		icu_validate_locale(icu_locale);
+
 		/*
-		 * In supported builds, the ICU locale ID will be checked by the
-		 * backend during post-bootstrap initialization.
+		 * In supported builds, the ICU locale ID will be opened during
+		 * post-bootstrap initialization, which will perform extra checks.
 		 */
 #ifndef USE_ICU
 		pg_fatal("ICU is not supported in this build");
diff --git a/src/bin/initdb/t/001_initdb.pl b/src/bin/initdb/t/001_initdb.pl
index b97420f7e88..db7995fe28d 100644
--- a/src/bin/initdb/t/001_initdb.pl
+++ b/src/bin/initdb/t/001_initdb.pl
@@ -128,6 +128,24 @@ if ($ENV{with_icu} eq 'yes')
 		],
 		qr/error: encoding mismatch/,
 		'fails for encoding not supported by ICU');
+
+	command_fails_like(
+		[
+			'initdb',                '--no-sync',
+			'--locale-provider=icu',
+			'--icu-locale=nonsense-nowhere', "$tempdir/dataX"
+		],
+		qr/error: locale "nonsense-nowhere" has unknown language "nonsense"/,
+		'fails for nonsense language');
+
+	command_fails_like(
+		[
+			'initdb',                '--no-sync',
+			'--locale-provider=icu',
+			'--icu-locale=@colNumeric=lower', "$tempdir/dataX"
+		],
+		qr/could not open collator for locale "\@colNumeric=lower": U_ILLEGAL_ARGUMENT_ERROR/,
+		'fails for invalid collation argument');
 }
 else
 {