ICU-21408 Prohibit alpha4 as language inside tlang.

unicode-org · Nov 24, 2020 · 0ab995e · 0ab995e
1 parent 275d59a
commit 0ab995e
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 2 deletions.
diff --git a/icu4c/source/common/uloc_tag.cpp b/icu4c/source/common/uloc_tag.cpp
@@ -670,9 +670,13 @@ _isTransformedExtensionSubtag(int32_t& state, const char* s, int32_t len)
     const int32_t kGotTKey = -1;    // Got tkey, wait for tvalue. ERROR if stop here.
     const int32_t kGotTValue = 6;   // Got tvalue, wait for tkey, tvalue or end
 
+
+    if (len < 0) {
+        len = (int32_t)uprv_strlen(s);
+    }
     switch (state) {
         case kStart:
-            if (ultag_isLanguageSubtag(s, len)) {
+            if (ultag_isLanguageSubtag(s, len) && len != 4) {
                 state = kGotLanguage;
                 return TRUE;
             }

diff --git a/icu4c/source/test/intltest/localebuildertest.cpp b/icu4c/source/test/intltest/localebuildertest.cpp
@@ -1375,7 +1375,7 @@ void LocaleBuilderTest::TestSetExtensionValidateTIllFormed() {
         "9-",
         "-9",
         "-z",
-        // "Latn", // Per 2019-01-23 ICUTC, still accept 4alpha. See ICU-20321
+        "Latn",
         "Latn-",
         "en-",
         "nob-",
@@ -1400,6 +1400,8 @@ void LocaleBuilderTest::TestSetExtensionValidateTIllFormed() {
         "gab-Thai-TH-0bde-z9-abcde123-a1-",
         "gab-Thai-TH-0bde-z9-abcde123-a1-a",
         "gab-Thai-TH-0bde-z9-abcde123-a1-ab",
+        // ICU-21408
+        "root",
     };
     for (const char* ill : illFormed) {
         UErrorCode status = U_ZERO_ERROR;