added overrides for fallbacks of legacy codes

Change-Id: I62be84904b3f0f4beeda35e78906604090eefa86

3 files changed, 479 insertions, 432 deletions

diff --git a/i18nlangtag/qa/cppunit/test_languagetag.cxx b/i18nlangtag/qa/cppunit/test_languagetag.cxx
index 5ddc9b8d6e7b..f3cea3a4ccfd 100644
--- a/i18nlangtag/qa/cppunit/test_languagetag.cxx
+++ b/i18nlangtag/qa/cppunit/test_languagetag.cxx
@@ -194,6 +194,29 @@ void TestLanguageTag::testAllTags()
     }
 
     {
+        OUString s_ca_XV( "ca-XV" );
+        LanguageTag ca_XV( s_ca_XV, true );
+        lang::Locale aLocale = ca_XV.getLocale();
+        CPPUNIT_ASSERT( ca_XV.getBcp47() == s_ca_XV );
+        CPPUNIT_ASSERT( aLocale.Language == "ca" );
+        CPPUNIT_ASSERT( aLocale.Country == "XV" );
+        CPPUNIT_ASSERT( aLocale.Variant == "" );
+        CPPUNIT_ASSERT( ca_XV.getLanguageType() == LANGUAGE_CATALAN_VALENCIAN );
+        CPPUNIT_ASSERT( ca_XV.isValidBcp47() == true );
+        CPPUNIT_ASSERT( ca_XV.isIsoLocale() == true );
+        CPPUNIT_ASSERT( ca_XV.isIsoODF() == true );
+        CPPUNIT_ASSERT( ca_XV.getLanguage() == "ca" );
+        CPPUNIT_ASSERT( ca_XV.getCountry() == "XV" );
+        CPPUNIT_ASSERT( ca_XV.getScript() == "" );
+        CPPUNIT_ASSERT( ca_XV.getLanguageAndScript() == "ca" );
+        ::std::vector< OUString > ca_XV_Fallbacks( ca_XV.getFallbackStrings( true));
+        CPPUNIT_ASSERT( ca_XV_Fallbacks.size() == 2);
+        CPPUNIT_ASSERT( ca_XV_Fallbacks[0] == "ca-XV");
+        CPPUNIT_ASSERT( ca_XV_Fallbacks[1] == "ca");
+        CPPUNIT_ASSERT( ca_XV.makeFallback().getBcp47() == "ca-ES-valencia");
+    }
+
+    {
         OUString s_de_DE( "de-DE" );
         LanguageTag de_DE( s_de_DE, true );
         lang::Locale aLocale = de_DE.getLocale();
diff --git a/i18nlangtag/source/isolang/isolang.cxx b/i18nlangtag/source/isolang/isolang.cxx
index 4e9a343ce7b5..74eb73790ebf 100644
--- a/i18nlangtag/source/isolang/isolang.cxx
+++ b/i18nlangtag/source/isolang/isolang.cxx
@@ -34,6 +34,9 @@ struct IsoLanguageCountryEntry
     LanguageType  mnLang;
     sal_Char      maLanguage[4];
     sal_Char      maCountry[3];
+    /** If TRUE, a higher (! else infinite recursion occurs!) level override
+        with the same mnLang (!) exists that should be used instead. */
+    bool          mbOverrideExists;
 
     /** Obtain a language tag string with '-' separator. */
     OUString getTagString() const;
@@ -140,434 +143,434 @@ struct IsoLangOtherEntry
 static IsoLanguageCountryEntry const aImplIsoLangEntries[] =
 {
     // MS-LANGID codes               ISO639-1/2/3 ISO3166
-    { LANGUAGE_ENGLISH,                     "en", ""   },
-    { LANGUAGE_ENGLISH_US,                  "en", "US" },
-    { LANGUAGE_ENGLISH_UK,                  "en", "GB" },
-    { LANGUAGE_ENGLISH_AUS,                 "en", "AU" },
-    { LANGUAGE_ENGLISH_CAN,                 "en", "CA" },
-    { LANGUAGE_FRENCH,                      "fr", "FR" },
-    { LANGUAGE_GERMAN,                      "de", "DE" },
-    { LANGUAGE_ITALIAN,                     "it", "IT" },
-    { LANGUAGE_DUTCH,                       "nl", "NL" },
-    { LANGUAGE_SPANISH_MODERN,              "es", "ES" },
-    { LANGUAGE_SPANISH_DATED,               "es", "ES" },
-    { LANGUAGE_PORTUGUESE,                  "pt", "PT" },
-    { LANGUAGE_PORTUGUESE_BRAZILIAN,        "pt", "BR" },
-    { LANGUAGE_DANISH,                      "da", "DK" },
-    { LANGUAGE_GREEK,                       "el", "GR" },
-    { LANGUAGE_CHINESE_SIMPLIFIED,          "zh", "CN" },
-    { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY,   "zh", "CN" },
-    { LANGUAGE_CHINESE_TRADITIONAL,         "zh", "TW" },
-    { LANGUAGE_CHINESE_TRADITIONAL_LEGACY,  "zh", "TW" },
-    { LANGUAGE_CHINESE_HONGKONG,            "zh", "HK" },
-    { LANGUAGE_CHINESE_SINGAPORE,           "zh", "SG" },
-    { LANGUAGE_CHINESE_MACAU,               "zh", "MO" },
-    { LANGUAGE_ENGLISH_HONG_KONG_SAR,       "en", "HK" },
-    { LANGUAGE_JAPANESE,                    "ja", "JP" },
-    { LANGUAGE_KOREAN,                      "ko", "KR" },
-    { LANGUAGE_KOREAN_JOHAB,                "ko", "KR" },
-    { LANGUAGE_USER_KOREAN_NORTH,           "ko", "KP" },
-    { LANGUAGE_SWEDISH,                     "sv", "SE" },
-    { LANGUAGE_SWEDISH_FINLAND,             "sv", "FI" },
-    { LANGUAGE_FINNISH,                     "fi", "FI" },
-    { LANGUAGE_RUSSIAN,                     "ru", "RU" },
-    { LANGUAGE_TATAR,                       "tt", "RU" },
-    { LANGUAGE_ENGLISH_NZ,                  "en", "NZ" },
-    { LANGUAGE_ENGLISH_EIRE,                "en", "IE" },
-    { LANGUAGE_DUTCH_BELGIAN,               "nl", "BE" },
-    { LANGUAGE_FRENCH_BELGIAN,              "fr", "BE" },
-    { LANGUAGE_FRENCH_CANADIAN,             "fr", "CA" },
-    { LANGUAGE_FRENCH_SWISS,                "fr", "CH" },
-    { LANGUAGE_GERMAN_SWISS,                "de", "CH" },
-    { LANGUAGE_GERMAN_AUSTRIAN,             "de", "AT" },
-    { LANGUAGE_ITALIAN_SWISS,               "it", "CH" },
-    { LANGUAGE_ALBANIAN,                    "sq", "AL" },
-    { LANGUAGE_ARABIC_SAUDI_ARABIA,         "ar", "SA" },
-    { LANGUAGE_ARABIC_EGYPT,                "ar", "EG" },
-    { LANGUAGE_ARABIC_UAE,                  "ar", "AE" },
-    { LANGUAGE_ARABIC_IRAQ,                 "ar", "IQ" },
-    { LANGUAGE_ARABIC_LIBYA,                "ar", "LY" },
-    { LANGUAGE_ARABIC_ALGERIA,              "ar", "DZ" },
-    { LANGUAGE_ARABIC_MOROCCO,              "ar", "MA" },
-    { LANGUAGE_ARABIC_TUNISIA,              "ar", "TN" },
-    { LANGUAGE_ARABIC_OMAN,                 "ar", "OM" },
-    { LANGUAGE_ARABIC_YEMEN,                "ar", "YE" },
-    { LANGUAGE_ARABIC_SYRIA,                "ar", "SY" },
-    { LANGUAGE_ARABIC_JORDAN,               "ar", "JO" },
-    { LANGUAGE_ARABIC_LEBANON,              "ar", "LB" },
-    { LANGUAGE_ARABIC_KUWAIT,               "ar", "KW" },
-    { LANGUAGE_ARABIC_BAHRAIN,              "ar", "BH" },
-    { LANGUAGE_ARABIC_QATAR,                "ar", "QA" },
-    { LANGUAGE_USER_ARABIC_CHAD,            "ar", "TD" },
-    { LANGUAGE_USER_ARABIC_COMOROS,         "ar", "KM" },
-    { LANGUAGE_USER_ARABIC_DJIBOUTI,        "ar", "DJ" },
-    { LANGUAGE_USER_ARABIC_ERITREA,         "ar", "ER" },
-    { LANGUAGE_USER_ARABIC_ISRAEL,          "ar", "IL" },
-    { LANGUAGE_USER_ARABIC_MAURITANIA,      "ar", "MR" },
-    { LANGUAGE_USER_ARABIC_PALESTINE,       "ar", "PS" },
-    { LANGUAGE_USER_ARABIC_SOMALIA,         "ar", "SO" },
-    { LANGUAGE_USER_ARABIC_SUDAN,           "ar", "SD" },
-    { LANGUAGE_ARABIC_PRIMARY_ONLY,         "ar", ""   },
-    { LANGUAGE_BASQUE,                      "eu", ""   },
-    { LANGUAGE_BULGARIAN,                   "bg", "BG" },
-    { LANGUAGE_CZECH,                       "cs", "CZ" },
-    { LANGUAGE_CZECH,                       "cz", ""   },
-    { LANGUAGE_ENGLISH_JAMAICA,             "en", "JM" },
-    { LANGUAGE_ENGLISH_CARRIBEAN,           "en", "BS" },   // not 100%, because AG is Bahamas
-    { LANGUAGE_ENGLISH_BELIZE,              "en", "BZ" },
-    { LANGUAGE_ENGLISH_TRINIDAD,            "en", "TT" },
-    { LANGUAGE_ENGLISH_ZIMBABWE,            "en", "ZW" },
-    { LANGUAGE_ENGLISH_INDONESIA,           "en", "ID" },
-    { LANGUAGE_ESTONIAN,                    "et", "EE" },
-    { LANGUAGE_FAEROESE,                    "fo", "FO" },
-    { LANGUAGE_FARSI,                       "fa", "IR" },
-    { LANGUAGE_FRENCH_LUXEMBOURG,           "fr", "LU" },
-    { LANGUAGE_FRENCH_MONACO,               "fr", "MC" },
-    { LANGUAGE_GERMAN_LUXEMBOURG,           "de", "LU" },
-    { LANGUAGE_GERMAN_LIECHTENSTEIN,        "de", "LI" },
-    { LANGUAGE_HEBREW,                      "he", "IL" },   // new: old was "iw"
-    { LANGUAGE_HEBREW,                      "iw", "IL" },   // old: new is "he"
-    { LANGUAGE_HUNGARIAN,                   "hu", "HU" },
-    { LANGUAGE_ICELANDIC,                   "is", "IS" },
-    { LANGUAGE_INDONESIAN,                  "id", "ID" },   // new: old was "in"
-    { LANGUAGE_INDONESIAN,                  "in", "ID" },   // old: new is "id"
-    { LANGUAGE_NORWEGIAN,                   "no", "NO" },
-    { LANGUAGE_NORWEGIAN_BOKMAL,            "nb", "NO" },
-    { LANGUAGE_NORWEGIAN_NYNORSK,           "nn", "NO" },
-    { LANGUAGE_POLISH,                      "pl", "PL" },
-    { LANGUAGE_RHAETO_ROMAN,                "rm", "CH" },
-    { LANGUAGE_ROMANIAN,                    "ro", "RO" },
-    { LANGUAGE_ROMANIAN_MOLDOVA,            "ro", "MD" },
-    { LANGUAGE_SLOVAK,                      "sk", "SK" },
-    { LANGUAGE_SLOVENIAN,                   "sl", "SI" },
-    { LANGUAGE_SPANISH_MEXICAN,             "es", "MX" },
-    { LANGUAGE_SPANISH_GUATEMALA,           "es", "GT" },
-    { LANGUAGE_SPANISH_COSTARICA,           "es", "CR" },
-    { LANGUAGE_SPANISH_PANAMA,              "es", "PA" },
-    { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC,  "es", "DO" },
-    { LANGUAGE_SPANISH_VENEZUELA,           "es", "VE" },
-    { LANGUAGE_SPANISH_COLOMBIA,            "es", "CO" },
-    { LANGUAGE_SPANISH_PERU,                "es", "PE" },
-    { LANGUAGE_SPANISH_ARGENTINA,           "es", "AR" },
-    { LANGUAGE_SPANISH_ECUADOR,             "es", "EC" },
-    { LANGUAGE_SPANISH_CHILE,               "es", "CL" },
-    { LANGUAGE_SPANISH_URUGUAY,             "es", "UY" },
-    { LANGUAGE_SPANISH_PARAGUAY,            "es", "PY" },
-    { LANGUAGE_SPANISH_BOLIVIA,             "es", "BO" },
-    { LANGUAGE_SPANISH_EL_SALVADOR,         "es", "SV" },
-    { LANGUAGE_SPANISH_HONDURAS,            "es", "HN" },
-    { LANGUAGE_SPANISH_NICARAGUA,           "es", "NI" },
-    { LANGUAGE_SPANISH_PUERTO_RICO,         "es", "PR" },
-    { LANGUAGE_SPANISH_UNITED_STATES,       "es", "US" },
-    { LANGUAGE_SPANISH_LATIN_AMERICA,       "es", ""   },
-    { LANGUAGE_TURKISH,                     "tr", "TR" },
-    { LANGUAGE_UKRAINIAN,                   "uk", "UA" },
-    { LANGUAGE_VIETNAMESE,                  "vi", "VN" },
-    { LANGUAGE_LATVIAN,                     "lv", "LV" },
-    { LANGUAGE_MACEDONIAN,                  "mk", "MK" },
-    { LANGUAGE_MALAY_MALAYSIA,              "ms", "MY" },
-    { LANGUAGE_MALAY_BRUNEI_DARUSSALAM,     "ms", "BN" },
-    { LANGUAGE_ENGLISH_MALAYSIA,            "en", "MY" },
-    { LANGUAGE_THAI,                        "th", "TH" },
-    { LANGUAGE_LITHUANIAN,                  "lt", "LT" },
-    { LANGUAGE_LITHUANIAN_CLASSIC,          "lt", "LT" },
-    { LANGUAGE_CROATIAN,                    "hr", "HR" },   // Croatian in Croatia
-    { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA" },
-    { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA,        "bs", "BA" },
-//  { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_AND_HERZEGOVINA, "bs", "BA" },   // script codes not supported yet
-    { LANGUAGE_USER_SERBIAN_CYRILLIC_SERBIA,        "sr", "RS" },   // Serbian Cyrillic in Serbia
-    { LANGUAGE_SERBIAN_CYRILLIC,                    "sr", "YU" },   // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_CS instead, sr_CS not supported by ICU 2.6 (3.4 does)
-    { LANGUAGE_SERBIAN_CYRILLIC,                    "sr", "CS" },   // alias to be able to integrate localizations, rsc needs it
-    { LANGUAGE_USER_SERBIAN_CYRILLIC_MONTENEGRO,    "sr", "ME" },
-    { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA" },
-    { LANGUAGE_USER_SERBIAN_LATIN_SERBIA,           "sh", "RS" },   // Serbian Latin in Serbia; kludge, needed to be sr_Latn_RS instead, script codes not supported yet
-    { LANGUAGE_SERBIAN_LATIN,                       "sh", "YU" },   // legacy Serbian Latin in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_Latn_CS instead, script codes not supported yet
-    { LANGUAGE_SERBIAN_LATIN,                       "sh", "CS" },   // Serbian Latin in Serbia and Montenegro; kludge, needed to be sr_Latn_CS instead, script codes not supported yet
-    { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO,       "sh", "ME" },   // Serbian Latin in Montenegro; kludge, needed to be sr_Latn_ME instead, script codes not supported yet
-    { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA,    "sh", "BA" },
-    { LANGUAGE_SERBIAN_LATIN_NEUTRAL,               "sh", ""   },   // kludge, needed to be sr_Latn instead, script codes not supported yet
-    { LANGUAGE_ARMENIAN,                    "hy", "AM" },
-    { LANGUAGE_AZERI_LATIN,                 "az", "AZ" },
-//  { LANGUAGE_AZERI_CYRILLIC,              "az", "AZ" },   // script codes not supported yet
-    { LANGUAGE_UZBEK_LATIN,                 "uz", "UZ" },
-//  { LANGUAGE_UZBEK_CYRILLIC,              "uz", "UZ" },   // script codes not supported yet
-    { LANGUAGE_BENGALI_BANGLADESH,          "bn", "BD" },
-    { LANGUAGE_BENGALI,                     "bn", "IN" },
-    { LANGUAGE_BURMESE,                     "my", "MM" },
-    { LANGUAGE_KAZAKH,                      "kk", "KZ" },
-    { LANGUAGE_ENGLISH_INDIA,               "en", "IN" },
-    { LANGUAGE_URDU_INDIA,                  "ur", "IN" },
-    { LANGUAGE_URDU_PAKISTAN,               "ur", "PK" },
-    { LANGUAGE_HINDI,                       "hi", "IN" },
-    { LANGUAGE_GUJARATI,                    "gu", "IN" },
-    { LANGUAGE_KANNADA,                     "kn", "IN" },
-    { LANGUAGE_ASSAMESE,                    "as", "IN" },
-    { LANGUAGE_KASHMIRI_INDIA,              "ks", "IN" },
-    { LANGUAGE_KASHMIRI,                    "ks", ""   },   // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
-    { LANGUAGE_MALAYALAM,                   "ml", "IN" },
-    { LANGUAGE_MANIPURI,                   "mni", "IN" },
-    { LANGUAGE_MARATHI,                     "mr", "IN" },
-    { LANGUAGE_KONKANI,                    "kok", "IN" },
-    { LANGUAGE_NEPALI,                      "ne", "NP" },
-    { LANGUAGE_NEPALI_INDIA,                "ne", "IN" },
-    { LANGUAGE_ORIYA,                       "or", "IN" },
-    { LANGUAGE_PUNJABI,                     "pa", "IN" },
-    { LANGUAGE_SANSKRIT,                    "sa", "IN" },
-    { LANGUAGE_SINDHI,                      "sd", "IN" },
-    { LANGUAGE_TAMIL,                       "ta", "IN" },
-    { LANGUAGE_TELUGU,                      "te", "IN" },
-    { LANGUAGE_PUNJABI_PAKISTAN,           "lah", "PK" },   // preferring "lah" over "pa" for Western Punjabi, see http://www.ethnologue.com/show_language.asp?code=PNB
-    { LANGUAGE_PUNJABI_PAKISTAN,            "pa", "PK" },
-    { LANGUAGE_SINDHI_PAKISTAN,             "sd", "PK" },
-    { LANGUAGE_BELARUSIAN,                  "be", "BY" },
-    { LANGUAGE_CATALAN,                     "ca", "ES" },   // Spain (default)
-    { LANGUAGE_CATALAN,                     "ca", "AD" },   // Andorra
+    { LANGUAGE_ENGLISH,                     "en", ""  , false },
+    { LANGUAGE_ENGLISH_US,                  "en", "US", false },
+    { LANGUAGE_ENGLISH_UK,                  "en", "GB", false },
+    { LANGUAGE_ENGLISH_AUS,                 "en", "AU", false },
+    { LANGUAGE_ENGLISH_CAN,                 "en", "CA", false },
+    { LANGUAGE_FRENCH,                      "fr", "FR", false },
+    { LANGUAGE_GERMAN,                      "de", "DE", false },
+    { LANGUAGE_ITALIAN,                     "it", "IT", false },
+    { LANGUAGE_DUTCH,                       "nl", "NL", false },
+    { LANGUAGE_SPANISH_MODERN,              "es", "ES", false },
+    { LANGUAGE_SPANISH_DATED,               "es", "ES", false },
+    { LANGUAGE_PORTUGUESE,                  "pt", "PT", false },
+    { LANGUAGE_PORTUGUESE_BRAZILIAN,        "pt", "BR", false },
+    { LANGUAGE_DANISH,                      "da", "DK", false },
+    { LANGUAGE_GREEK,                       "el", "GR", false },
+    { LANGUAGE_CHINESE_SIMPLIFIED,          "zh", "CN", false },
+    { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY,   "zh", "CN", false },
+    { LANGUAGE_CHINESE_TRADITIONAL,         "zh", "TW", false },
+    { LANGUAGE_CHINESE_TRADITIONAL_LEGACY,  "zh", "TW", false },
+    { LANGUAGE_CHINESE_HONGKONG,            "zh", "HK", false },
+    { LANGUAGE_CHINESE_SINGAPORE,           "zh", "SG", false },
+    { LANGUAGE_CHINESE_MACAU,               "zh", "MO", false },
+    { LANGUAGE_ENGLISH_HONG_KONG_SAR,       "en", "HK", false },
+    { LANGUAGE_JAPANESE,                    "ja", "JP", false },
+    { LANGUAGE_KOREAN,                      "ko", "KR", false },
+    { LANGUAGE_KOREAN_JOHAB,                "ko", "KR", false },
+    { LANGUAGE_USER_KOREAN_NORTH,           "ko", "KP", false },
+    { LANGUAGE_SWEDISH,                     "sv", "SE", false },
+    { LANGUAGE_SWEDISH_FINLAND,             "sv", "FI", false },
+    { LANGUAGE_FINNISH,                     "fi", "FI", false },
+    { LANGUAGE_RUSSIAN,                     "ru", "RU", false },
+    { LANGUAGE_TATAR,                       "tt", "RU", false },
+    { LANGUAGE_ENGLISH_NZ,                  "en", "NZ", false },
+    { LANGUAGE_ENGLISH_EIRE,                "en", "IE", false },
+    { LANGUAGE_DUTCH_BELGIAN,               "nl", "BE", false },
+    { LANGUAGE_FRENCH_BELGIAN,              "fr", "BE", false },
+    { LANGUAGE_FRENCH_CANADIAN,             "fr", "CA", false },
+    { LANGUAGE_FRENCH_SWISS,                "fr", "CH", false },
+    { LANGUAGE_GERMAN_SWISS,                "de", "CH", false },
+    { LANGUAGE_GERMAN_AUSTRIAN,             "de", "AT", false },
+    { LANGUAGE_ITALIAN_SWISS,               "it", "CH", false },
+    { LANGUAGE_ALBANIAN,                    "sq", "AL", false },
+    { LANGUAGE_ARABIC_SAUDI_ARABIA,         "ar", "SA", false },
+    { LANGUAGE_ARABIC_EGYPT,                "ar", "EG", false },
+    { LANGUAGE_ARABIC_UAE,                  "ar", "AE", false },
+    { LANGUAGE_ARABIC_IRAQ,                 "ar", "IQ", false },
+    { LANGUAGE_ARABIC_LIBYA,                "ar", "LY", false },
+    { LANGUAGE_ARABIC_ALGERIA,              "ar", "DZ", false },
+    { LANGUAGE_ARABIC_MOROCCO,              "ar", "MA", false },
+    { LANGUAGE_ARABIC_TUNISIA,              "ar", "TN", false },
+    { LANGUAGE_ARABIC_OMAN,                 "ar", "OM", false },
+    { LANGUAGE_ARABIC_YEMEN,                "ar", "YE", false },
+    { LANGUAGE_ARABIC_SYRIA,                "ar", "SY", false },
+    { LANGUAGE_ARABIC_JORDAN,               "ar", "JO", false },
+    { LANGUAGE_ARABIC_LEBANON,              "ar", "LB", false },
+    { LANGUAGE_ARABIC_KUWAIT,               "ar", "KW", false },
+    { LANGUAGE_ARABIC_BAHRAIN,              "ar", "BH", false },
+    { LANGUAGE_ARABIC_QATAR,                "ar", "QA", false },
+    { LANGUAGE_USER_ARABIC_CHAD,            "ar", "TD", false },
+    { LANGUAGE_USER_ARABIC_COMOROS,         "ar", "KM", false },
+    { LANGUAGE_USER_ARABIC_DJIBOUTI,        "ar", "DJ", false },
+    { LANGUAGE_USER_ARABIC_ERITREA,         "ar", "ER", false },
+    { LANGUAGE_USER_ARABIC_ISRAEL,          "ar", "IL", false },
+    { LANGUAGE_USER_ARABIC_MAURITANIA,      "ar", "MR", false },
+    { LANGUAGE_USER_ARABIC_PALESTINE,       "ar", "PS", false },
+    { LANGUAGE_USER_ARABIC_SOMALIA,         "ar", "SO", false },
+    { LANGUAGE_USER_ARABIC_SUDAN,           "ar", "SD", false },
+    { LANGUAGE_ARABIC_PRIMARY_ONLY,         "ar", ""  , false },
+    { LANGUAGE_BASQUE,                      "eu", ""  , false },
+    { LANGUAGE_BULGARIAN,                   "bg", "BG", false },
+    { LANGUAGE_CZECH,                       "cs", "CZ", false },
+    { LANGUAGE_CZECH,                       "cz", ""  , false },
+    { LANGUAGE_ENGLISH_JAMAICA,             "en", "JM", false },
+    { LANGUAGE_ENGLISH_CARRIBEAN,           "en", "BS", false },   // not 100%, because AG is Bahamas
+    { LANGUAGE_ENGLISH_BELIZE,              "en", "BZ", false },
+    { LANGUAGE_ENGLISH_TRINIDAD,            "en", "TT", false },
+    { LANGUAGE_ENGLISH_ZIMBABWE,            "en", "ZW", false },
+    { LANGUAGE_ENGLISH_INDONESIA,           "en", "ID", false },
+    { LANGUAGE_ESTONIAN,                    "et", "EE", false },
+    { LANGUAGE_FAEROESE,                    "fo", "FO", false },
+    { LANGUAGE_FARSI,                       "fa", "IR", false },
+    { LANGUAGE_FRENCH_LUXEMBOURG,           "fr", "LU", false },
+    { LANGUAGE_FRENCH_MONACO,               "fr", "MC", false },
+    { LANGUAGE_GERMAN_LUXEMBOURG,           "de", "LU", false },
+    { LANGUAGE_GERMAN_LIECHTENSTEIN,        "de", "LI", false },
+    { LANGUAGE_HEBREW,                      "he", "IL", false },   // new: old was "iw"
+    { LANGUAGE_HEBREW,                      "iw", "IL", false },   // old: new is "he"
+    { LANGUAGE_HUNGARIAN,                   "hu", "HU", false },
+    { LANGUAGE_ICELANDIC,                   "is", "IS", false },
+    { LANGUAGE_INDONESIAN,                  "id", "ID", false },   // new: old was "in"
+    { LANGUAGE_INDONESIAN,                  "in", "ID", false },   // old: new is "id"
+    { LANGUAGE_NORWEGIAN,                   "no", "NO", false },
+    { LANGUAGE_NORWEGIAN_BOKMAL,            "nb", "NO", false },
+    { LANGUAGE_NORWEGIAN_NYNORSK,           "nn", "NO", false },
+    { LANGUAGE_POLISH,                      "pl", "PL", false },
+    { LANGUAGE_RHAETO_ROMAN,                "rm", "CH", false },
+    { LANGUAGE_ROMANIAN,                    "ro", "RO", false },
+    { LANGUAGE_ROMANIAN_MOLDOVA,            "ro", "MD", false },
+    { LANGUAGE_SLOVAK,                      "sk", "SK", false },
+    { LANGUAGE_SLOVENIAN,                   "sl", "SI", false },
+    { LANGUAGE_SPANISH_MEXICAN,             "es", "MX", false },
+    { LANGUAGE_SPANISH_GUATEMALA,           "es", "GT", false },
+    { LANGUAGE_SPANISH_COSTARICA,           "es", "CR", false },
+    { LANGUAGE_SPANISH_PANAMA,              "es", "PA", false },
+    { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC,  "es", "DO", false },
+    { LANGUAGE_SPANISH_VENEZUELA,           "es", "VE", false },
+    { LANGUAGE_SPANISH_COLOMBIA,            "es", "CO", false },
+    { LANGUAGE_SPANISH_PERU,                "es", "PE", false },
+    { LANGUAGE_SPANISH_ARGENTINA,           "es", "AR", false },
+    { LANGUAGE_SPANISH_ECUADOR,             "es", "EC", false },
+    { LANGUAGE_SPANISH_CHILE,               "es", "CL", false },
+    { LANGUAGE_SPANISH_URUGUAY,             "es", "UY", false },
+    { LANGUAGE_SPANISH_PARAGUAY,            "es", "PY", false },
+    { LANGUAGE_SPANISH_BOLIVIA,             "es", "BO", false },
+    { LANGUAGE_SPANISH_EL_SALVADOR,         "es", "SV", false },
+    { LANGUAGE_SPANISH_HONDURAS,            "es", "HN", false },
+    { LANGUAGE_SPANISH_NICARAGUA,           "es", "NI", false },
+    { LANGUAGE_SPANISH_PUERTO_RICO,         "es", "PR", false },
+    { LANGUAGE_SPANISH_UNITED_STATES,       "es", "US", false },
+    { LANGUAGE_SPANISH_LATIN_AMERICA,       "es", ""  , false },
+    { LANGUAGE_TURKISH,                     "tr", "TR", false },
+    { LANGUAGE_UKRAINIAN,                   "uk", "UA", false },
+    { LANGUAGE_VIETNAMESE,                  "vi", "VN", false },
+    { LANGUAGE_LATVIAN,                     "lv", "LV", false },
+    { LANGUAGE_MACEDONIAN,                  "mk", "MK", false },
+    { LANGUAGE_MALAY_MALAYSIA,              "ms", "MY", false },
+    { LANGUAGE_MALAY_BRUNEI_DARUSSALAM,     "ms", "BN", false },
+    { LANGUAGE_ENGLISH_MALAYSIA,            "en", "MY", false },
+    { LANGUAGE_THAI,                        "th", "TH", false },
+    { LANGUAGE_LITHUANIAN,                  "lt", "LT", false },
+    { LANGUAGE_LITHUANIAN_CLASSIC,          "lt", "LT", false },
+    { LANGUAGE_CROATIAN,                    "hr", "HR", false },   // Croatian in Croatia
+    { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", false },
+    { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA,        "bs", "BA", false },
+//  { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_AND_HERZEGOVINA, "bs", "BA", false },   // script codes not supported yet
+    { LANGUAGE_USER_SERBIAN_CYRILLIC_SERBIA,        "sr", "RS", false },   // Serbian Cyrillic in Serbia
+    { LANGUAGE_SERBIAN_CYRILLIC,                    "sr", "YU", false },   // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_CS instead, sr_CS not supported by ICU 2.6 (3.4 does)
+    { LANGUAGE_SERBIAN_CYRILLIC,                    "sr", "CS", false },   // alias to be able to integrate localizations, rsc needs it
+    { LANGUAGE_USER_SERBIAN_CYRILLIC_MONTENEGRO,    "sr", "ME", false },
+    { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", false },
+    { LANGUAGE_USER_SERBIAN_LATIN_SERBIA,           "sh", "RS", false },   // Serbian Latin in Serbia; kludge, needed to be sr_Latn_RS instead, script codes not supported yet
+    { LANGUAGE_SERBIAN_LATIN,                       "sh", "YU", false },   // legacy Serbian Latin in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_Latn_CS instead, script codes not supported yet
+    { LANGUAGE_SERBIAN_LATIN,                       "sh", "CS", false },   // Serbian Latin in Serbia and Montenegro; kludge, needed to be sr_Latn_CS instead, script codes not supported yet
+    { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO,       "sh", "ME", false },   // Serbian Latin in Montenegro; kludge, needed to be sr_Latn_ME instead, script codes not supported yet
+    { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA,    "sh", "BA", false },
+    { LANGUAGE_SERBIAN_LATIN_NEUTRAL,               "sh", ""  , false },   // kludge, needed to be sr_Latn instead, script codes not supported yet
+    { LANGUAGE_ARMENIAN,                    "hy", "AM", false },
+    { LANGUAGE_AZERI_LATIN,                 "az", "AZ", false },
+//  { LANGUAGE_AZERI_CYRILLIC,              "az", "AZ", false },   // script codes not supported yet
+    { LANGUAGE_UZBEK_LATIN,                 "uz", "UZ", false },
+//  { LANGUAGE_UZBEK_CYRILLIC,              "uz", "UZ", false },   // script codes not supported yet
+    { LANGUAGE_BENGALI_BANGLADESH,          "bn", "BD", false },
+    { LANGUAGE_BENGALI,                     "bn", "IN", false },
+    { LANGUAGE_BURMESE,                     "my", "MM", false },
+    { LANGUAGE_KAZAKH,                      "kk", "KZ", false },
+    { LANGUAGE_ENGLISH_INDIA,               "en", "IN", false },
+    { LANGUAGE_URDU_INDIA,                  "ur", "IN", false },
+    { LANGUAGE_URDU_PAKISTAN,               "ur", "PK", false },
+    { LANGUAGE_HINDI,                       "hi", "IN", false },
+    { LANGUAGE_GUJARATI,                    "gu", "IN", false },
+    { LANGUAGE_KANNADA,                     "kn", "IN", false },
+    { LANGUAGE_ASSAMESE,                    "as", "IN", false },
+    { LANGUAGE_KASHMIRI_INDIA,              "ks", "IN", false },
+    { LANGUAGE_KASHMIRI,                    "ks", ""  , false },   // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
+    { LANGUAGE_MALAYALAM,                   "ml", "IN", false },
+    { LANGUAGE_MANIPURI,                   "mni", "IN", false },
+    { LANGUAGE_MARATHI,                     "mr", "IN", false },
+    { LANGUAGE_KONKANI,                    "kok", "IN", false },
+    { LANGUAGE_NEPALI,                      "ne", "NP", false },
+    { LANGUAGE_NEPALI_INDIA,                "ne", "IN", false },
+    { LANGUAGE_ORIYA,                       "or", "IN", false },
+    { LANGUAGE_PUNJABI,                     "pa", "IN", false },
+    { LANGUAGE_SANSKRIT,                    "sa", "IN", false },
+    { LANGUAGE_SINDHI,                      "sd", "IN", false },
+    { LANGUAGE_TAMIL,                       "ta", "IN", false },
+    { LANGUAGE_TELUGU,                      "te", "IN", false },
+    { LANGUAGE_PUNJABI_PAKISTAN,           "lah", "PK", false },   // preferring "lah" over "pa" for Western Punjabi, see http://www.ethnologue.com/show_language.asp?code=PNB
+    { LANGUAGE_PUNJABI_PAKISTAN,            "pa", "PK", false },
+    { LANGUAGE_SINDHI_PAKISTAN,             "sd", "PK", false },
+    { LANGUAGE_BELARUSIAN,                  "be", "BY", false },
+    { LANGUAGE_CATALAN,                     "ca", "ES", false },   // Spain (default)
+    { LANGUAGE_CATALAN,                     "ca", "AD", false },   // Andorra
     //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence
-    { LANGUAGE_CATALAN_VALENCIAN,           "ca", "XV" },   // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content
-    { LANGUAGE_CATALAN_VALENCIAN,          "qcv", "ES" },   // qcv: ISO 639-3 reserved-for-local-use; old UI localization quirk only, in case it escaped to document content
-    { LANGUAGE_FRENCH_CAMEROON,             "fr", "CM" },
-    { LANGUAGE_FRENCH_COTE_D_IVOIRE,        "fr", "CI" },
-    { LANGUAGE_FRENCH_MALI,                 "fr", "ML" },
-    { LANGUAGE_FRENCH_SENEGAL,              "fr", "SN" },
-    { LANGUAGE_FRENCH_ZAIRE,                "fr", "CD" },   // Democratic Republic Of Congo
-    { LANGUAGE_FRENCH_MOROCCO,              "fr", "MA" },
-    { LANGUAGE_FRENCH_REUNION,              "fr", "RE" },
-    { LANGUAGE_FRENCH,                      "fr", ""   },   // needed as a catcher before other "fr" entries!
-    { LANGUAGE_FRENCH_NORTH_AFRICA,         "fr", ""   },
-    { LANGUAGE_FRENCH_WEST_INDIES,          "fr", ""   },   // unknown ISO country code
-    { LANGUAGE_FRISIAN_NETHERLANDS,         "fy", "NL" },
-    { LANGUAGE_GAELIC_IRELAND,              "ga", "IE" },
-    { LANGUAGE_GAELIC_SCOTLAND,             "gd", "GB" },
-    { LANGUAGE_GALICIAN,                    "gl", "ES" },
-    { LANGUAGE_GEORGIAN,                    "ka", "GE" },
-    { LANGUAGE_KHMER,                       "km", "KH" },
-    { LANGUAGE_KIRGHIZ,                     "ky", "KG" },
-    { LANGUAGE_LAO,                         "lo", "LA" },
-    { LANGUAGE_MALTESE,                     "mt", "MT" },
-    { LANGUAGE_MONGOLIAN,                   "mn", "MN" },   // Cyrillic script
-    { LANGUAGE_MONGOLIAN_MONGOLIAN,         "mn", "MN" },
-    { LANGUAGE_RUSSIAN_MOLDOVA,             "mo", "MD" },
-    { LANGUAGE_SWAHILI,                     "sw", "KE" },
-    { LANGUAGE_USER_SWAHILI_TANZANIA,       "sw", "TZ" },
-    { LANGUAGE_TAJIK,                       "tg", "TJ" },
-    { LANGUAGE_TIBETAN,                     "bo", "CN" },   // CN politically correct?
-    { LANGUAGE_USER_TIBETAN_INDIA,          "bo", "IN" },
-    { LANGUAGE_DZONGKHA,                    "dz", "BT" },
-    { LANGUAGE_TURKMEN,                     "tk", "TM" },
-    { LANGUAGE_WELSH,                       "cy", "GB" },
-    { LANGUAGE_SESOTHO,                     "st", "ZA" },
-    { LANGUAGE_SEPEDI,                     "nso", "ZA" },
-    { LANGUAGE_SEPEDI,                      "ns", "ZA" },   // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
-    { LANGUAGE_TSONGA,                      "ts", "ZA" },
-    { LANGUAGE_TSWANA,                      "tn", "ZA" },
-    { LANGUAGE_ENGLISH_SAFRICA,             "en", "ZA" },
-    { LANGUAGE_AFRIKAANS,                   "af", "ZA" },
-    { LANGUAGE_VENDA,                       "ve", "ZA" },   // default 639-1
-    { LANGUAGE_VENDA,                      "ven", "ZA" },   // 639-2 may have been used temporarily since 2004-07-23
-    { LANGUAGE_XHOSA,                       "xh", "ZA" },
-    { LANGUAGE_ZULU,                        "zu", "ZA" },
-    { LANGUAGE_QUECHUA_ECUADOR,             "qu", "EC" },
-    { LANGUAGE_QUECHUA_PERU,                "qu", "PE" },
-    { LANGUAGE_QUECHUA_BOLIVIA,             "qu", "BO" },   // macro: quh-BO, qul-BO
-    { LANGUAGE_PASHTO,                      "ps", "AF" },
-    { LANGUAGE_OROMO,                       "om", "ET" },
-    { LANGUAGE_DHIVEHI,                     "dv", "MV" },
-    { LANGUAGE_UIGHUR_CHINA,                "ug", "CN" },
-    { LANGUAGE_TIGRIGNA_ETHIOPIA,           "ti", "ET" },
-    { LANGUAGE_TIGRIGNA_ERITREA,            "ti", "ER" },
-    { LANGUAGE_AMHARIC_ETHIOPIA,            "am", "ET" },
-    { LANGUAGE_GUARANI_PARAGUAY,           "gug", "PY" },
-    { LANGUAGE_HAWAIIAN_UNITED_STATES,     "haw", "US" },
-    { LANGUAGE_EDO,                        "bin", "NG" },
-    { LANGUAGE_FULFULDE_NIGERIA,            "ff", "NG" },
-    { LANGUAGE_HAUSA_NIGERIA,               "ha", "NG" },
-    { LANGUAGE_USER_HAUSA_GHANA,            "ha", "GH" },
-    { LANGUAGE_IGBO_NIGERIA,                "ig", "NG" },
-    { LANGUAGE_KANURI_NIGERIA,              "kr", "NG" },
-    { LANGUAGE_YORUBA,                      "yo", "NG" },
-    { LANGUAGE_SOMALI,                      "so", "SO" },
-    { LANGUAGE_PAPIAMENTU,                 "pap", "AN" },
-    { LANGUAGE_USER_PAPIAMENTU_ARUBA,      "pap", "AW" },
-    { LANGUAGE_USER_PAPIAMENTU_CURACAO,    "pap", "CW" },
-    { LANGUAGE_USER_PAPIAMENTU_BONAIRE,    "pap", "BQ" },
-    { LANGUAGE_ENGLISH_SINGAPORE,           "en", "SG" },
-    { LANGUAGE_USER_YIDDISH_US,             "yi", "US" },
-    { LANGUAGE_YIDDISH,                     "yi", "IL" },   // new: old was "ji"
-    { LANGUAGE_YIDDISH,                     "ji", "IL" },   // old: new is "yi"
-    { LANGUAGE_SYRIAC,                     "syr", "TR" },   // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
-    { LANGUAGE_SINHALESE_SRI_LANKA,         "si", "LK" },
-    { LANGUAGE_CHEROKEE_UNITED_STATES,     "chr", "US" },
-    { LANGUAGE_INUKTITUT_LATIN_CANADA,      "iu", "CA" },
-//  { LANGUAGE_INUKTITUT_SYLLABICS_CANADA,  "iu", "CA" },   // script codes not supported yet
-    { LANGUAGE_SAMI_NORTHERN_NORWAY,        "se", "NO" },
-    { LANGUAGE_SAMI_INARI,                 "smn", "FI" },
-    { LANGUAGE_SAMI_LULE_NORWAY,           "smj", "NO" },
-    { LANGUAGE_SAMI_LULE_SWEDEN,           "smj", "SE" },
-    { LANGUAGE_SAMI_NORTHERN_FINLAND,       "se", "FI" },
-    { LANGUAGE_SAMI_NORTHERN_SWEDEN,        "se", "SE" },
-    { LANGUAGE_SAMI_SKOLT,                 "sms", "FI" },
-    { LANGUAGE_SAMI_SOUTHERN_NORWAY,       "sma", "NO" },
-    { LANGUAGE_SAMI_SOUTHERN_SWEDEN,       "sma", "SE" },
-    { LANGUAGE_USER_SAMI_KILDIN_RUSSIA,    "sjd", "RU" },
-    { LANGUAGE_MAPUDUNGUN_CHILE,           "arn", "CL" },
-    { LANGUAGE_CORSICAN_FRANCE,             "co", "FR" },
-    { LANGUAGE_ALSATIAN_FRANCE,            "gsw", "FR" },   // in fact 'gsw' is Schwyzerduetsch (Swiss German), which is a dialect of Alemannic German, as is Alsatian. They aren't distinct languages and share this code.
-    { LANGUAGE_YAKUT_RUSSIA,               "sah", "RU" },
-    { LANGUAGE_MOHAWK_CANADA,              "moh", "CA" },
-    { LANGUAGE_BASHKIR_RUSSIA,              "ba", "RU" },
-    { LANGUAGE_KICHE_GUATEMALA,            "qut", "GT" },
-    { LANGUAGE_DARI_AFGHANISTAN,           "gbz", "AF" },
-    { LANGUAGE_WOLOF_SENEGAL,               "wo", "SN" },
-    { LANGUAGE_FILIPINO,                   "fil", "PH" },
-    { LANGUAGE_USER_TAGALOG,                "tl", "PH" },
-    { LANGUAGE_ENGLISH_PHILIPPINES,         "en", "PH" },
-//  { LANGUAGE_IBIBIO_NIGERIA,             "nic", "NG" },   // ISO "nic" is only a collective language code
-    { LANGUAGE_YI,                          "ii", "CN" },
-    { LANGUAGE_TAMAZIGHT_LATIN,            "kab", "DZ" },   // In practice Kabyle is the language used for this
-    { LANGUAGE_OBSOLETE_USER_KABYLE,       "kab", "DZ" },
-    { LANGUAGE_TAMAZIGHT_LATIN,            "ber", "DZ" },   // In practice Algeria has standardized on Kabyle as the member of the "ber" collective which gets used there.
-    { LANGUAGE_TAMAZIGHT_TIFINAGH,         "ber", "MA" },   // Morocco is officially using Tifinagh for its Berber languages so store it to distinguish explicitly from LANGUAGE_TAMAZIGHT_LATIN, even though as a collective language its not of much use
-//  { LANGUAGE_TAMAZIGHT_ARABIC,           "ber", ""   },   // ISO "ber" only collective!
-    { LANGUAGE_LATIN,                       "la", "VA" },
-    { LANGUAGE_OBSOLETE_USER_LATIN,         "la", "VA" },
-    { LANGUAGE_USER_ESPERANTO,              "eo", ""   },
-    { LANGUAGE_USER_INTERLINGUA,            "ia", ""   },
-    { LANGUAGE_MAORI_NEW_ZEALAND,           "mi", "NZ" },
-    { LANGUAGE_OBSOLETE_USER_MAORI,         "mi", "NZ" },
-    { LANGUAGE_KINYARWANDA_RWANDA,          "rw", "RW" },
-    { LANGUAGE_OBSOLETE_USER_KINYARWANDA,   "rw", "RW" },
-    { LANGUAGE_UPPER_SORBIAN_GERMANY,      "hsb", "DE" },   // MS maps this to 'wen-DE', which is nonsense. 'wen' is a collective language code, 'WEN' is a SIL code, see http://www.ethnologue.com/14/show_iso639.asp?code=wen and http://www.ethnologue.com/14/show_language.asp?code=WEN
-    { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE" },
-    { LANGUAGE_LOWER_SORBIAN_GERMANY,      "dsb", "DE" },   // MS maps this to 'wee-DE', which is nonsense. 'WEE' is a SIL code, see http://www.ethnologue.com/14/show_language.asp?code=WEE
-    { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE" },
-    { LANGUAGE_OCCITAN_FRANCE,              "oc", "FR" },
-    { LANGUAGE_OBSOLETE_USER_OCCITAN,       "oc", "FR" },
-    { LANGUAGE_USER_KURDISH_TURKEY,         "ku", "TR" },
-    { LANGUAGE_USER_KURDISH_SYRIA,          "ku", "SY" },
-    { LANGUAGE_USER_KURDISH_IRAQ,           "ku", "IQ" },
-    { LANGUAGE_USER_KURDISH_IRAN,           "ku", "IR" },
-    { LANGUAGE_USER_SARDINIAN,              "sc", "IT" },   // macrolanguage code
-    { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT" },
-    { LANGUAGE_USER_SARDINIAN_GALLURESE,   "sdn", "IT" },
-    { LANGUAGE_USER_SARDINIAN_LOGUDORESE,  "src", "IT" },
-    { LANGUAGE_USER_SARDINIAN_SASSARESE,   "sdc", "IT" },
-    { LANGUAGE_BRETON_FRANCE,               "br", "FR" },
-    { LANGUAGE_OBSOLETE_USER_BRETON,        "br", "FR" },
-    { LANGUAGE_KALAALLISUT_GREENLAND,       "kl", "GL" },
-    { LANGUAGE_OBSOLETE_USER_KALAALLISUT,   "kl", "GL" },
-    { LANGUAGE_USER_SWAZI,                  "ss", "ZA" },
-    { LANGUAGE_USER_NDEBELE_SOUTH,          "nr", "ZA" },
-    { LANGUAGE_USER_TSWANA_BOTSWANA,        "tn", "BW" },
-    { LANGUAGE_USER_MOORE,                 "mos", "BF" },
-    { LANGUAGE_USER_BAMBARA,                "bm", "ML" },
-    { LANGUAGE_USER_AKAN,                   "ak", "GH" },
-    { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG,    "lb", "LU" },
-    { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU" },
-    { LANGUAGE_USER_FRIULIAN,              "fur", "IT" },
-    { LANGUAGE_USER_FIJIAN,                 "fj", "FJ" },
-    { LANGUAGE_USER_AFRIKAANS_NAMIBIA,      "af", "NA" },
-    { LANGUAGE_USER_ENGLISH_NAMIBIA,        "en", "NA" },
-    { LANGUAGE_USER_WALLOON,                "wa", "BE" },
-    { LANGUAGE_USER_COPTIC,                "cop", "EG" },
-    { LANGUAGE_USER_GASCON,                "gsc", "FR" },
-    { LANGUAGE_USER_GERMAN_BELGIUM,         "de", "BE" },
-    { LANGUAGE_USER_CHUVASH,                "cv", "RU" },
-    { LANGUAGE_USER_EWE_GHANA,              "ee", "GH" },
-    { LANGUAGE_USER_ENGLISH_GHANA,          "en", "GH" },
-    { LANGUAGE_USER_SANGO,                  "sg", "CF" },
-    { LANGUAGE_USER_GANDA,                  "lg", "UG" },
-    { LANGUAGE_USER_LINGALA_DRCONGO,        "ln", "CD" },
-    { LANGUAGE_USER_LOW_GERMAN,            "nds", "DE" },
-    { LANGUAGE_USER_HILIGAYNON,            "hil", "PH" },
-    { LANGUAGE_USER_ENGLISH_MALAWI,         "en", "MW" },   /* en default for MW */
-    { LANGUAGE_USER_NYANJA,                 "ny", "MW" },
-    { LANGUAGE_USER_KASHUBIAN,             "csb", "PL" },
-    { LANGUAGE_USER_SPANISH_CUBA,           "es", "CU" },
-    { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO" },
-    { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO" },
-    { LANGUAGE_USER_BODO_INDIA,            "brx", "IN" },
-    { LANGUAGE_USER_DOGRI_INDIA,           "dgo", "IN" },
-    { LANGUAGE_USER_MAITHILI_INDIA,        "mai", "IN" },
-    { LANGUAGE_USER_SANTALI_INDIA,         "sat", "IN" },
-    { LANGUAGE_USER_TETUN,                 "tet", "ID" },
-    { LANGUAGE_USER_TETUN_TIMOR_LESTE,     "tet", "TL" },
-    { LANGUAGE_USER_TOK_PISIN,             "tpi", "PG" },
-    { LANGUAGE_USER_SHUSWAP,               "shs", "CA" },
-    { LANGUAGE_USER_ANCIENT_GREEK,         "grc", "GR" },
-    { LANGUAGE_USER_ASTURIAN,              "ast", "ES" },
-    { LANGUAGE_USER_LATGALIAN,             "ltg", "LV" },
-    { LANGUAGE_USER_MAORE,                 "swb", "YT" },
-    { LANGUAGE_USER_BUSHI,                 "buc", "YT" },
-    { LANGUAGE_USER_TAHITIAN,               "ty", "PF" },
-    { LANGUAGE_USER_MALAGASY_PLATEAU,      "plt", "MG" },
-    { LANGUAGE_USER_MALAGASY_PLATEAU,       "mg", "MG" },
-    { LANGUAGE_USER_BAFIA,                 "ksf", "CM" },
-    { LANGUAGE_USER_GIKUYU,                 "ki", "KE" },
-    { LANGUAGE_USER_RUSYN_UKRAINE,         "rue", "UA" },
-    { LANGUAGE_USER_RUSYN_SLOVAKIA,        "rue", "SK" },
-    { LANGUAGE_USER_LIMBU,                 "lif", "NP" },
-    { LANGUAGE_USER_LOJBAN,                "jbo", ""   },
-    { LANGUAGE_USER_HAITIAN,                "ht", "HT" },
-    { LANGUAGE_FRENCH_HAITI,                "fr", "HT" },
-    { LANGUAGE_USER_BEEMBE,                "beq", "CG" },
-    { LANGUAGE_USER_BEKWEL,                "bkw", "CG" },
-    { LANGUAGE_USER_KITUBA,                "mkw", "CG" },
-    { LANGUAGE_USER_LARI,                  "ldi", "CG" },
-    { LANGUAGE_USER_MBOCHI,                "mdw", "CG" },
-    { LANGUAGE_USER_TEKE_EBOO,             "ebo", "CG" },
-    { LANGUAGE_USER_TEKE_IBALI,            "tek", "CG" },
-    { LANGUAGE_USER_TEKE_TYEE,             "tyx", "CG" },
-    { LANGUAGE_USER_VILI,                  "vif", "CG" },
-    { LANGUAGE_USER_PORTUGUESE_ANGOLA,      "pt", "AO" },
-    { LANGUAGE_USER_MANX,                   "gv", "GB" },
-    { LANGUAGE_USER_ARAGONESE,              "an", "ES" },
-    { LANGUAGE_USER_KEYID,                 "qtz", ""   },   // key id pseudolanguage used for UI testing
-    { LANGUAGE_USER_PALI_LATIN,             "pi", ""   },   // Pali with Latin script, ISO 639-1
-    { LANGUAGE_USER_PALI_LATIN,            "pli", ""   },   // Pali with Latin script, ISO 639-3 (sigh..) back-compat
-    { LANGUAGE_USER_KYRGYZ_CHINA,           "ky", "CN" },
-    { LANGUAGE_USER_KOMI_ZYRIAN,           "kpv", "RU" },
-    { LANGUAGE_USER_KOMI_PERMYAK,          "koi", "RU" },
-    { LANGUAGE_USER_PITJANTJATJARA,        "pjt", "AU" },
-    { LANGUAGE_USER_ERZYA,                 "myv", "RU" },
-    { LANGUAGE_USER_MARI_MEADOW,           "mhr", "RU" },
-    { LANGUAGE_USER_KHANTY,                "kca", "RU" },
-    { LANGUAGE_USER_LIVONIAN,              "liv", "RU" },
-    { LANGUAGE_USER_MOKSHA,                "mdf", "RU" },
-    { LANGUAGE_USER_MARI_HILL,             "mrj", "RU" },
-    { LANGUAGE_USER_NGANASAN,              "nio", "RU" },
-    { LANGUAGE_USER_OLONETS,               "olo", "RU" },
-    { LANGUAGE_USER_VEPS,                  "vep", "RU" },
-    { LANGUAGE_USER_VORO,                  "vro", "EE" },
-    { LANGUAGE_USER_NENETS,                "yrk", "RU" },
-    { LANGUAGE_USER_AKA,                   "axk", "CF" },
-    { LANGUAGE_USER_AKA_CONGO,             "axk", "CG" },
-    { LANGUAGE_USER_DIBOLE,                "bvx", "CG" },
-    { LANGUAGE_USER_DOONDO,                "dde", "CG" },
-    { LANGUAGE_USER_KAAMBA,                "xku", "CG" },
-    { LANGUAGE_USER_KOONGO,                "kng", "CD" },
-    { LANGUAGE_USER_KOONGO_CONGO,          "kng", "CG" },
-    { LANGUAGE_USER_KUNYI,                 "njx", "CG" },
-    { LANGUAGE_USER_NGUNGWEL,              "ngz", "CG" },
-    { LANGUAGE_USER_NJYEM,                 "njy", "CM" },
-    { LANGUAGE_USER_NJYEM_CONGO,           "njy", "CG" },
-    { LANGUAGE_USER_PUNU,                  "puu", "GA" },
-    { LANGUAGE_USER_PUNU_CONGO,            "puu", "CG" },
-    { LANGUAGE_USER_SUUNDI,                "sdj", "CG" },
-    { LANGUAGE_USER_TEKE_KUKUYA,           "kkw", "CG" },
-    { LANGUAGE_USER_TSAANGI,               "tsa", "CG" },
-    { LANGUAGE_USER_YAKA,                  "iyx", "CG" },
-    { LANGUAGE_USER_YOMBE,                 "yom", "CD" },
-    { LANGUAGE_USER_YOMBE_CONGO,           "yom", "CG" },
-    { LANGUAGE_USER_SIDAMA,                "sid", "ET" },
-    { LANGUAGE_USER_NKO,                   "nqo", "GN" },
-    { LANGUAGE_USER_UDMURT,                "udm", "RU" },
-    { LANGUAGE_USER_CORNISH,               "kw",  "UK" },
-    { LANGUAGE_USER_SAMI_PITE_SWEDEN,      "sje", "SE" },
-    { LANGUAGE_USER_NGAEBERE,              "gym", "PA" },
-    { LANGUAGE_MULTIPLE,                   "mul", ""   },   // multiple languages, many languages are used
-    { LANGUAGE_UNDETERMINED,               "und", ""   },   // undetermined language, language cannot be identified
-    { LANGUAGE_NONE,                       "zxx", ""   },   // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
-    { LANGUAGE_DONTKNOW,                    "",   ""   }    // marks end of table
+    { LANGUAGE_CATALAN_VALENCIAN,           "ca", "XV", true  },   // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content
+    { LANGUAGE_CATALAN_VALENCIAN,          "qcv", "ES", true  },   // qcv: ISO 639-3 reserved-for-local-use; old UI localization quirk only, in case it escaped to document content
+    { LANGUAGE_FRENCH_CAMEROON,             "fr", "CM", false },
+    { LANGUAGE_FRENCH_COTE_D_IVOIRE,        "fr", "CI", false },
+    { LANGUAGE_FRENCH_MALI,                 "fr", "ML", false },
+    { LANGUAGE_FRENCH_SENEGAL,              "fr", "SN", false },
+    { LANGUAGE_FRENCH_ZAIRE,                "fr", "CD", false },   // Democratic Republic Of Congo
+    { LANGUAGE_FRENCH_MOROCCO,              "fr", "MA", false },
+    { LANGUAGE_FRENCH_REUNION,              "fr", "RE", false },
+    { LANGUAGE_FRENCH,                      "fr", ""  , false },   // needed as a catcher before other "fr" entries!
+    { LANGUAGE_FRENCH_NORTH_AFRICA,         "fr", ""  , false },
+    { LANGUAGE_FRENCH_WEST_INDIES,          "fr", ""  , false },   // unknown ISO country code
+    { LANGUAGE_FRISIAN_NETHERLANDS,         "fy", "NL", false },
+    { LANGUAGE_GAELIC_IRELAND,              "ga", "IE", false },
+    { LANGUAGE_GAELIC_SCOTLAND,             "gd", "GB", false },
+    { LANGUAGE_GALICIAN,                    "gl", "ES", false },
+    { LANGUAGE_GEORGIAN,                    "ka", "GE", false },
+    { LANGUAGE_KHMER,                       "km", "KH", false },
+    { LANGUAGE_KIRGHIZ,                     "ky", "KG", false },
+    { LANGUAGE_LAO,                         "lo", "LA", false },
+    { LANGUAGE_MALTESE,                     "mt", "MT", false },
+    { LANGUAGE_MONGOLIAN,                   "mn", "MN", false },   // Cyrillic script
+    { LANGUAGE_MONGOLIAN_MONGOLIAN,         "mn", "MN", false },
+    { LANGUAGE_RUSSIAN_MOLDOVA,             "mo", "MD", false },
+    { LANGUAGE_SWAHILI,                     "sw", "KE", false },
+    { LANGUAGE_USER_SWAHILI_TANZANIA,       "sw", "TZ", false },
+    { LANGUAGE_TAJIK,                       "tg", "TJ", false },
+    { LANGUAGE_TIBETAN,                     "bo", "CN", false },   // CN politically correct?
+    { LANGUAGE_USER_TIBETAN_INDIA,          "bo", "IN", false },
+    { LANGUAGE_DZONGKHA,                    "dz", "BT", false },
+    { LANGUAGE_TURKMEN,                     "tk", "TM", false },
+    { LANGUAGE_WELSH,                       "cy", "GB", false },
+    { LANGUAGE_SESOTHO,                     "st", "ZA", false },
+    { LANGUAGE_SEPEDI,                     "nso", "ZA", false },
+    { LANGUAGE_SEPEDI,                      "ns", "ZA", false },   // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
+    { LANGUAGE_TSONGA,                      "ts", "ZA", false },
+    { LANGUAGE_TSWANA,                      "tn", "ZA", false },
+    { LANGUAGE_ENGLISH_SAFRICA,             "en", "ZA", false },
+    { LANGUAGE_AFRIKAANS,                   "af", "ZA", false },
+    { LANGUAGE_VENDA,                       "ve", "ZA", false },   // default 639-1
+    { LANGUAGE_VENDA,                      "ven", "ZA", false },   // 639-2 may have been used temporarily since 2004-07-23
+    { LANGUAGE_XHOSA,                       "xh", "ZA", false },
+    { LANGUAGE_ZULU,                        "zu", "ZA", false },
+    { LANGUAGE_QUECHUA_ECUADOR,             "qu", "EC", false },
+    { LANGUAGE_QUECHUA_PERU,                "qu", "PE", false },
+    { LANGUAGE_QUECHUA_BOLIVIA,             "qu", "BO", false },   // macro: quh-BO, qul-BO
+    { LANGUAGE_PASHTO,                      "ps", "AF", false },
+    { LANGUAGE_OROMO,                       "om", "ET", false },
+    { LANGUAGE_DHIVEHI,                     "dv", "MV", false },
+    { LANGUAGE_UIGHUR_CHINA,                "ug", "CN", false },
+    { LANGUAGE_TIGRIGNA_ETHIOPIA,           "ti", "ET", false },
+    { LANGUAGE_TIGRIGNA_ERITREA,            "ti", "ER", false },
+    { LANGUAGE_AMHARIC_ETHIOPIA,            "am", "ET", false },
+    { LANGUAGE_GUARANI_PARAGUAY,           "gug", "PY", false },
+    { LANGUAGE_HAWAIIAN_UNITED_STATES,     "haw", "US", false },
+    { LANGUAGE_EDO,                        "bin", "NG", false },
+    { LANGUAGE_FULFULDE_NIGERIA,            "ff", "NG", false },
+    { LANGUAGE_HAUSA_NIGERIA,               "ha", "NG", false },
+    { LANGUAGE_USER_HAUSA_GHANA,            "ha", "GH", false },
+    { LANGUAGE_IGBO_NIGERIA,                "ig", "NG", false },
+    { LANGUAGE_KANURI_NIGERIA,              "kr", "NG", false },
+    { LANGUAGE_YORUBA,                      "yo", "NG", false },
+    { LANGUAGE_SOMALI,                      "so", "SO", false },
+    { LANGUAGE_PAPIAMENTU,                 "pap", "AN", false },
+    { LANGUAGE_USER_PAPIAMENTU_ARUBA,      "pap", "AW", false },
+    { LANGUAGE_USER_PAPIAMENTU_CURACAO,    "pap", "CW", false },
+    { LANGUAGE_USER_PAPIAMENTU_BONAIRE,    "pap", "BQ", false },
+    { LANGUAGE_ENGLISH_SINGAPORE,           "en", "SG", false },
+    { LANGUAGE_USER_YIDDISH_US,             "yi", "US", false },
+    { LANGUAGE_YIDDISH,                     "yi", "IL", false },   // new: old was "ji"
+    { LANGUAGE_YIDDISH,                     "ji", "IL", false },   // old: new is "yi"
+    { LANGUAGE_SYRIAC,                     "syr", "TR", false },   // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
+    { LANGUAGE_SINHALESE_SRI_LANKA,         "si", "LK", false },
+    { LANGUAGE_CHEROKEE_UNITED_STATES,     "chr", "US", false },
+    { LANGUAGE_INUKTITUT_LATIN_CANADA,      "iu", "CA", false },
+//  { LANGUAGE_INUKTITUT_SYLLABICS_CANADA,  "iu", "CA", false },   // script codes not supported yet
+    { LANGUAGE_SAMI_NORTHERN_NORWAY,        "se", "NO", false },
+    { LANGUAGE_SAMI_INARI,                 "smn", "FI", false },
+    { LANGUAGE_SAMI_LULE_NORWAY,           "smj", "NO", false },
+    { LANGUAGE_SAMI_LULE_SWEDEN,           "smj", "SE", false },
+    { LANGUAGE_SAMI_NORTHERN_FINLAND,       "se", "FI", false },
+    { LANGUAGE_SAMI_NORTHERN_SWEDEN,        "se", "SE", false },
+    { LANGUAGE_SAMI_SKOLT,                 "sms", "FI", false },
+    { LANGUAGE_SAMI_SOUTHERN_NORWAY,       "sma", "NO", false },
+    { LANGUAGE_SAMI_SOUTHERN_SWEDEN,       "sma", "SE", false },
+    { LANGUAGE_USER_SAMI_KILDIN_RUSSIA,    "sjd", "RU", false },
+    { LANGUAGE_MAPUDUNGUN_CHILE,           "arn", "CL", false },
+    { LANGUAGE_CORSICAN_FRANCE,             "co", "FR", false },
+    { LANGUAGE_ALSATIAN_FRANCE,            "gsw", "FR", false },   // in fact 'gsw' is Schwyzerduetsch (Swiss German), which is a dialect of Alemannic German, as is Alsatian. They aren't distinct languages and share this code.
+    { LANGUAGE_YAKUT_RUSSIA,               "sah", "RU", false },
+    { LANGUAGE_MOHAWK_CANADA,              "moh", "CA", false },
+    { LANGUAGE_BASHKIR_RUSSIA,              "ba", "RU", false },
+    { LANGUAGE_KICHE_GUATEMALA,            "qut", "GT", false },
+    { LANGUAGE_DARI_AFGHANISTAN,           "gbz", "AF", false },
+    { LANGUAGE_WOLOF_SENEGAL,               "wo", "SN", false },
+    { LANGUAGE_FILIPINO,                   "fil", "PH", false },
+    { LANGUAGE_USER_TAGALOG,                "tl", "PH", false },
+    { LANGUAGE_ENGLISH_PHILIPPINES,         "en", "PH", false },
+//  { LANGUAGE_IBIBIO_NIGERIA,             "nic", "NG", false },   // ISO "nic" is only a collective language code
+    { LANGUAGE_YI,                          "ii", "CN", false },
+    { LANGUAGE_TAMAZIGHT_LATIN,            "kab", "DZ", false },   // In practice Kabyle is the language used for this
+    { LANGUAGE_OBSOLETE_USER_KABYLE,       "kab", "DZ", false },
+    { LANGUAGE_TAMAZIGHT_LATIN,            "ber", "DZ", false },   // In practice Algeria has standardized on Kabyle as the member of the "ber" collective which gets used there.
+    { LANGUAGE_TAMAZIGHT_TIFINAGH,         "ber", "MA", false },   // Morocco is officially using Tifinagh for its Berber languages so store it to distinguish explicitly from LANGUAGE_TAMAZIGHT_LATIN, even though as a collective language its not of much use
+//  { LANGUAGE_TAMAZIGHT_ARABIC,           "ber", ""  , false },   // ISO "ber" only collective!
+    { LANGUAGE_LATIN,                       "la", "VA", false },
+    { LANGUAGE_OBSOLETE_USER_LATIN,         "la", "VA", false },
+    { LANGUAGE_USER_ESPERANTO,              "eo", ""  , false },
+    { LANGUAGE_USER_INTERLINGUA,            "ia", ""  , false },
+    { LANGUAGE_MAORI_NEW_ZEALAND,           "mi", "NZ", false },
+    { LANGUAGE_OBSOLETE_USER_MAORI,         "mi", "NZ", false },
+    { LANGUAGE_KINYARWANDA_RWANDA,          "rw", "RW", false },
+    { LANGUAGE_OBSOLETE_USER_KINYARWANDA,   "rw", "RW", false },
+    { LANGUAGE_UPPER_SORBIAN_GERMANY,      "hsb", "DE", false },   // MS maps this to 'wen-DE', which is nonsense. 'wen' is a collective language code, 'WEN' is a SIL code, see http://www.ethnologue.com/14/show_iso639.asp?code=wen and http://www.ethnologue.com/14/show_language.asp?code=WEN
+    { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", false },
+    { LANGUAGE_LOWER_SORBIAN_GERMANY,      "dsb", "DE", false },   // MS maps this to 'wee-DE', which is nonsense. 'WEE' is a SIL code, see http://www.ethnologue.com/14/show_language.asp?code=WEE
+    { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", false },
+    { LANGUAGE_OCCITAN_FRANCE,              "oc", "FR", false },
+    { LANGUAGE_OBSOLETE_USER_OCCITAN,       "oc", "FR", false },
+    { LANGUAGE_USER_KURDISH_TURKEY,         "ku", "TR", false },
+    { LANGUAGE_USER_KURDISH_SYRIA,          "ku", "SY", false },
+    { LANGUAGE_USER_KURDISH_IRAQ,           "ku", "IQ", false },
+    { LANGUAGE_USER_KURDISH_IRAN,           "ku", "IR", false },
+    { LANGUAGE_USER_SARDINIAN,              "sc", "IT", false },   // macrolanguage code
+    { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", false },
+    { LANGUAGE_USER_SARDINIAN_GALLURESE,   "sdn", "IT", false },
+    { LANGUAGE_USER_SARDINIAN_LOGUDORESE,  "src", "IT", false },
+    { LANGUAGE_USER_SARDINIAN_SASSARESE,   "sdc", "IT", false },
+    { LANGUAGE_BRETON_FRANCE,               "br", "FR", false },
+    { LANGUAGE_OBSOLETE_USER_BRETON,        "br", "FR", false },
+    { LANGUAGE_KALAALLISUT_GREENLAND,       "kl", "GL", false },
+    { LANGUAGE_OBSOLETE_USER_KALAALLISUT,   "kl", "GL", false },
+    { LANGUAGE_USER_SWAZI,                  "ss", "ZA", false },
+    { LANGUAGE_USER_NDEBELE_SOUTH,          "nr", "ZA", false },
+    { LANGUAGE_USER_TSWANA_BOTSWANA,        "tn", "BW", false },
+    { LANGUAGE_USER_MOORE,                 "mos", "BF", false },
+    { LANGUAGE_USER_BAMBARA,                "bm", "ML", false },
+    { LANGUAGE_USER_AKAN,                   "ak", "GH", false },
+    { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG,    "lb", "LU", false },
+    { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", false },
+    { LANGUAGE_USER_FRIULIAN,              "fur", "IT", false },
+    { LANGUAGE_USER_FIJIAN,                 "fj", "FJ", false },
+    { LANGUAGE_USER_AFRIKAANS_NAMIBIA,      "af", "NA", false },
+    { LANGUAGE_USER_ENGLISH_NAMIBIA,        "en", "NA", false },
+    { LANGUAGE_USER_WALLOON,                "wa", "BE", false },
+    { LANGUAGE_USER_COPTIC,                "cop", "EG", false },
+    { LANGUAGE_USER_GASCON,                "gsc", "FR", false },
+    { LANGUAGE_USER_GERMAN_BELGIUM,         "de", "BE", false },
+    { LANGUAGE_USER_CHUVASH,                "cv", "RU", false },
+    { LANGUAGE_USER_EWE_GHANA,              "ee", "GH", false },
+    { LANGUAGE_USER_ENGLISH_GHANA,          "en", "GH", false },
+    { LANGUAGE_USER_SANGO,                  "sg", "CF", false },
+    { LANGUAGE_USER_GANDA,                  "lg", "UG", false },
+    { LANGUAGE_USER_LINGALA_DRCONGO,        "ln", "CD", false },
+    { LANGUAGE_USER_LOW_GERMAN,            "nds", "DE", false },
+    { LANGUAGE_USER_HILIGAYNON,            "hil", "PH", false },
+    { LANGUAGE_USER_ENGLISH_MALAWI,         "en", "MW", false },   /* en default for MW */
+    { LANGUAGE_USER_NYANJA,                 "ny", "MW", false },
+    { LANGUAGE_USER_KASHUBIAN,             "csb", "PL", false },
+    { LANGUAGE_USER_SPANISH_CUBA,           "es", "CU", false },
+    { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", false },
+    { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", false },
+    { LANGUAGE_USER_BODO_INDIA,            "brx", "IN", false },
+    { LANGUAGE_USER_DOGRI_INDIA,           "dgo", "IN", false },
+    { LANGUAGE_USER_MAITHILI_INDIA,        "mai", "IN", false },
+    { LANGUAGE_USER_SANTALI_INDIA,         "sat", "IN", false },
+    { LANGUAGE_USER_TETUN,                 "tet", "ID", false },
+    { LANGUAGE_USER_TETUN_TIMOR_LESTE,     "tet", "TL", false },
+    { LANGUAGE_USER_TOK_PISIN,             "tpi", "PG", false },
+    { LANGUAGE_USER_SHUSWAP,               "shs", "CA", false },
+    { LANGUAGE_USER_ANCIENT_GREEK,         "grc", "GR", false },
+    { LANGUAGE_USER_ASTURIAN,              "ast", "ES", false },
+    { LANGUAGE_USER_LATGALIAN,             "ltg", "LV", false },
+    { LANGUAGE_USER_MAORE,                 "swb", "YT", false },
+    { LANGUAGE_USER_BUSHI,                 "buc", "YT", false },
+    { LANGUAGE_USER_TAHITIAN,               "ty", "PF", false },
+    { LANGUAGE_USER_MALAGASY_PLATEAU,      "plt", "MG", false },
+    { LANGUAGE_USER_MALAGASY_PLATEAU,       "mg", "MG", false },
+    { LANGUAGE_USER_BAFIA,                 "ksf", "CM", false },
+    { LANGUAGE_USER_GIKUYU,                 "ki", "KE", false },
+    { LANGUAGE_USER_RUSYN_UKRAINE,         "rue", "UA", false },
+    { LANGUAGE_USER_RUSYN_SLOVAKIA,        "rue", "SK", false },
+    { LANGUAGE_USER_LIMBU,                 "lif", "NP", false },
+    { LANGUAGE_USER_LOJBAN,                "jbo", ""  , false },
+    { LANGUAGE_USER_HAITIAN,                "ht", "HT", false },
+    { LANGUAGE_FRENCH_HAITI,                "fr", "HT", false },
+    { LANGUAGE_USER_BEEMBE,                "beq", "CG", false },
+    { LANGUAGE_USER_BEKWEL,                "bkw", "CG", false },
+    { LANGUAGE_USER_KITUBA,                "mkw", "CG", false },
+    { LANGUAGE_USER_LARI,                  "ldi", "CG", false },
+    { LANGUAGE_USER_MBOCHI,                "mdw", "CG", false },
+    { LANGUAGE_USER_TEKE_EBOO,             "ebo", "CG", false },
+    { LANGUAGE_USER_TEKE_IBALI,            "tek", "CG", false },
+    { LANGUAGE_USER_TEKE_TYEE,             "tyx", "CG", false },
+    { LANGUAGE_USER_VILI,                  "vif", "CG", false },
+    { LANGUAGE_USER_PORTUGUESE_ANGOLA,      "pt", "AO", false },
+    { LANGUAGE_USER_MANX,                   "gv", "GB", false },
+    { LANGUAGE_USER_ARAGONESE,              "an", "ES", false },
+    { LANGUAGE_USER_KEYID,                 "qtz", ""  , false },   // key id pseudolanguage used for UI testing
+    { LANGUAGE_USER_PALI_LATIN,             "pi", ""  , false },   // Pali with Latin script, ISO 639-1
+    { LANGUAGE_USER_PALI_LATIN,            "pli", ""  , false },   // Pali with Latin script, ISO 639-3 (sigh..) back-compat
+    { LANGUAGE_USER_KYRGYZ_CHINA,           "ky", "CN", false },
+    { LANGUAGE_USER_KOMI_ZYRIAN,           "kpv", "RU", false },
+    { LANGUAGE_USER_KOMI_PERMYAK,          "koi", "RU", false },
+    { LANGUAGE_USER_PITJANTJATJARA,        "pjt", "AU", false },
+    { LANGUAGE_USER_ERZYA,                 "myv", "RU", false },
+    { LANGUAGE_USER_MARI_MEADOW,           "mhr", "RU", false },
+    { LANGUAGE_USER_KHANTY,                "kca", "RU", false },
+    { LANGUAGE_USER_LIVONIAN,              "liv", "RU", false },
+    { LANGUAGE_USER_MOKSHA,                "mdf", "RU", false },
+    { LANGUAGE_USER_MARI_HILL,             "mrj", "RU", false },
+    { LANGUAGE_USER_NGANASAN,              "nio", "RU", false },
+    { LANGUAGE_USER_OLONETS,               "olo", "RU", false },
+    { LANGUAGE_USER_VEPS,                  "vep", "RU", false },
+    { LANGUAGE_USER_VORO,                  "vro", "EE", false },
+    { LANGUAGE_USER_NENETS,                "yrk", "RU", false },
+    { LANGUAGE_USER_AKA,                   "axk", "CF", false },
+    { LANGUAGE_USER_AKA_CONGO,             "axk", "CG", false },
+    { LANGUAGE_USER_DIBOLE,                "bvx", "CG", false },
+    { LANGUAGE_USER_DOONDO,                "dde", "CG", false },
+    { LANGUAGE_USER_KAAMBA,                "xku", "CG", false },
+    { LANGUAGE_USER_KOONGO,                "kng", "CD", false },
+    { LANGUAGE_USER_KOONGO_CONGO,          "kng", "CG", false },
+    { LANGUAGE_USER_KUNYI,                 "njx", "CG", false },
+    { LANGUAGE_USER_NGUNGWEL,              "ngz", "CG", false },
+    { LANGUAGE_USER_NJYEM,                 "njy", "CM", false },
+    { LANGUAGE_USER_NJYEM_CONGO,           "njy", "CG", false },
+    { LANGUAGE_USER_PUNU,                  "puu", "GA", false },
+    { LANGUAGE_USER_PUNU_CONGO,            "puu", "CG", false },
+    { LANGUAGE_USER_SUUNDI,                "sdj", "CG", false },
+    { LANGUAGE_USER_TEKE_KUKUYA,           "kkw", "CG", false },
+    { LANGUAGE_USER_TSAANGI,               "tsa", "CG", false },
+    { LANGUAGE_USER_YAKA,                  "iyx", "CG", false },
+    { LANGUAGE_USER_YOMBE,                 "yom", "CD", false },
+    { LANGUAGE_USER_YOMBE_CONGO,           "yom", "CG", false },
+    { LANGUAGE_USER_SIDAMA,                "sid", "ET", false },
+    { LANGUAGE_USER_NKO,                   "nqo", "GN", false },
+    { LANGUAGE_USER_UDMURT,                "udm", "RU", false },
+    { LANGUAGE_USER_CORNISH,               "kw",  "UK", false },
+    { LANGUAGE_USER_SAMI_PITE_SWEDEN,      "sje", "SE", false },
+    { LANGUAGE_USER_NGAEBERE,              "gym", "PA", false },
+    { LANGUAGE_MULTIPLE,                   "mul", ""  , false },   // multiple languages, many languages are used
+    { LANGUAGE_UNDETERMINED,               "und", ""  , false },   // undetermined language, language cannot be identified
+    { LANGUAGE_NONE,                       "zxx", ""  , false },   // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
+    { LANGUAGE_DONTKNOW,                    "",   ""  , false }    // marks end of table
 };
 
 static IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
@@ -586,7 +589,7 @@ static Bcp47CountryEntry const aImplBcp47CountryEntries[] =
 };
 
 static IsoLanguageCountryEntry aLastResortFallbackEntry =
-{ LANGUAGE_ENGLISH_US, "en", "US" };
+{ LANGUAGE_ENGLISH_US, "en", "US", false };
 
 OUString IsoLanguageCountryEntry::getTagString() const
 {
@@ -812,6 +815,19 @@ void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
 // -----------------------------------------------------------------------
 
 // static
+com::sun::star::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageCountryEntry * pEntry )
+{
+    if (pEntry->mbOverrideExists)
+    {
+        lang::Locale aLocale;
+        convertLanguageToLocaleImpl( pEntry->mnLang, aLocale);
+        return aLocale;
+    }
+    else
+        return pEntry->getLocale();
+}
+
+// static
 ::com::sun::star::lang::Locale MsLangId::Conversion::lookupFallbackLocale(
         const ::com::sun::star::lang::Locale & rLocale )
 {
@@ -887,7 +903,7 @@ void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
             if (*pEntry->maCountry)
             {
                 if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
-                    return pEntry->getLocale();
+                    return getLocale( pEntry);  // may override
             }
             else
             {
@@ -900,7 +916,7 @@ void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
                     case LANGUAGE_USER_LOJBAN:
                     case LANGUAGE_KASHMIRI:
                     case LANGUAGE_USER_KEYID:
-                        return pEntry->getLocale();
+                        return getLocale( pEntry);  // may override
                     default:
                         ;   // nothing
                 }
@@ -921,7 +937,7 @@ void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
         if (aLowerLang.equalsAscii( pEntry->maLanguage))
         {
             if (*pEntry->maCountry)
-                return pEntry->getLocale();
+                return getLocale( pEntry);  // may override
         }
     }
 
diff --git a/include/i18nlangtag/mslangid.hxx b/include/i18nlangtag/mslangid.hxx
index 6be7e66eed40..95adb9118ba6 100644
--- a/include/i18nlangtag/mslangid.hxx
+++ b/include/i18nlangtag/mslangid.hxx
@@ -27,6 +27,8 @@
 #include <com/sun/star/lang/Locale.hpp>
 #include <vector>
 
+struct IsoLanguageCountryEntry;
+
 /** Methods related to Microsoft language IDs. For details about MS-LANGIDs
     please see lang.h */
 class I18NLANGTAG_DLLPUBLIC MsLangId
@@ -230,6 +232,11 @@ public:
                 const OString& rLang, const OString& rCountry );
 
 
+        /** Used by lookupFallbackLocale(Locale) */
+        I18NLANGTAG_DLLPRIVATE static com::sun::star::lang::Locale getLocale(
+                const IsoLanguageCountryEntry * pEntry );
+
+
         /** Convert a LanguageType to a Locale.
 
             @param bResolveSystem
@@ -240,7 +247,8 @@ public:
         I18NLANGTAG_DLLPRIVATE static ::com::sun::star::lang::Locale convertLanguageToLocale(
                 LanguageType nLang, bool bResolveSystem );
 
-        /** Used by convertLanguageToLocale(LanguageType,bool)
+        /** Used by convertLanguageToLocale(LanguageType,bool) and
+            getLocale(IsoLanguageCountryEntry*)
 
             @return rLocale set to mapped values, unchanged if no mapping was
                     found. E.g. pass empty Locale to obtain empty SYSTEM locale