Adapt LCIDs and language tags to [MS-LCID] rev.15

See
https://docs.microsoft.com/en-us/openspecs/windows_protocols/ms-lcid/70feba9f-294e-491e-b6eb-56532684c37f
https://winprotocoldoc.blob.core.windows.net/productionwindowsarchives/MS-LCID/%5bMS-LCID%5d-210625.pdf

and

commit 402dab839b2e451dec81bfb83dadbe0d5a231db2
CommitDate: Wed Aug 4 21:21:51 2021 +0200

update list of [MS-LCID] from 6/25/2021 15.0 rev.

Change-Id: I44db2bfaf894ead119c7014e3770fc44be537148
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/120128
Reviewed-by: Eike Rathke <erack@redhat.com>
Tested-by: Jenkins

6 files changed, 52 insertions, 42 deletions

diff --git a/i18nlangtag/qa/cppunit/test_languagetag.cxx b/i18nlangtag/qa/cppunit/test_languagetag.cxx
index 4fcc05785f2e..c3dfb151e14e 100644
--- a/i18nlangtag/qa/cppunit/test_languagetag.cxx
+++ b/i18nlangtag/qa/cppunit/test_languagetag.cxx
@@ -683,7 +683,8 @@ void TestLanguageTag::testAllTags()
 
 bool checkMapping( std::u16string_view rStr1, std::u16string_view rStr2 )
 {
-    if (rStr1 == u"la-Latn"     ) return rStr2 == u"la";
+    if (rStr1 == u"la"          ) return rStr2 == u"la-VA";
+    if (rStr1 == u"la-Latn"     ) return rStr2 == u"la-VA";
     if (rStr1 == u"tzm-Latn-DZ" ) return rStr2 == u"kab-DZ";
     if (rStr1 == u"bs-Latn-BA"  ) return rStr2 == u"bs-BA";
     if (rStr1 == u"bs-Latn"     ) return rStr2 == u"bs";
@@ -705,7 +706,8 @@ bool checkMapping( std::u16string_view rStr1, std::u16string_view rStr2 )
     if (rStr1 == u"ven-ZA"      ) return rStr2 == u"ve-ZA";
     if (rStr1 == u"qu-EC"       ) return rStr2 == u"quz-EC";
     if (rStr1 == u"qu-PE"       ) return rStr2 == u"quz-PE";
-    if (rStr1 == u"ff-NG"       ) return rStr2 == u"fuv-NG";
+    if (rStr1 == u"ff-Latn-NG"  ) return rStr2 == u"ff-NG";
+    if (rStr1 == u"fuv-NG"      ) return rStr2 == u"ff-NG";
     if (rStr1 == u"ji-IL"       ) return rStr2 == u"yi-IL";
     if (rStr1 == u"iu-CA"       ) return rStr2 == u"iu-Latn-CA";
     if (rStr1 == u"iu"          ) return rStr2 == u"iu-Latn";
@@ -716,6 +718,7 @@ bool checkMapping( std::u16string_view rStr1, std::u16string_view rStr2 )
     if (rStr1 == u"mg-MG"       ) return rStr2 == u"plt-MG";
     if (rStr1 == u"pli"         ) return rStr2 == u"pi-Latn";
     if (rStr1 == u"ks"          ) return rStr2 == u"ks-Arab";
+    if (rStr1 == u"ks-IN"       ) return rStr2 == u"ks-Deva-IN";
     if (rStr1 == u"chr-US"      ) return rStr2 == u"chr-Cher-US";
     if (rStr1 == u"sd-PK"       ) return rStr2 == u"sd-Arab-PK";
     if (rStr1 == u"sr-Cyrl-RS"  ) return rStr2 == u"sr-RS";
@@ -760,8 +763,7 @@ void TestLanguageTag::testAllIsoLangEntries()
         LanguageTag aTagID( elem.mnLang);
         if (!checkMapping( elem.maBcp47, aTagString.getBcp47()))
         {
-            OString aMessage( OUStringToOString( elem.maBcp47, RTL_TEXTENCODING_ASCII_US) + " -> " + OUStringToOString( aTagString.getBcp47(), RTL_TEXTENCODING_ASCII_US) );
-            CPPUNIT_ASSERT_EQUAL_MESSAGE( aMessage.getStr(), aTagString.getBcp47(), elem.maBcp47 );
+            CPPUNIT_ASSERT_EQUAL_MESSAGE( "defined elem to tag", elem.maBcp47, aTagString.getBcp47() );
         }
         if (elem.maBcp47 != aTagID.getBcp47())
         {
diff --git a/i18nlangtag/source/isolang/isolang.cxx b/i18nlangtag/source/isolang/isolang.cxx
index 941a73b25766..cb1d5956d6ea 100644
--- a/i18nlangtag/source/isolang/isolang.cxx
+++ b/i18nlangtag/source/isolang/isolang.cxx
@@ -251,7 +251,7 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_ENGLISH_BELIZE,              "en", "BZ", k0    },
     { LANGUAGE_ENGLISH_TRINIDAD,            "en", "TT", k0    },
     { LANGUAGE_ENGLISH_ZIMBABWE,            "en", "ZW", k0    },
-    { LANGUAGE_ENGLISH_INDONESIA,           "en", "ID", k0    },
+    { LANGUAGE_ENGLISH_INDONESIA,           "en", "ID", k0    },    // MS reserved
     { LANGUAGE_ESTONIAN,                    "et", "EE", k0    },
     { LANGUAGE_FAEROESE,                    "fo", "FO", k0    },
     { LANGUAGE_FARSI,                       "fa", "IR", k0    },
@@ -344,10 +344,10 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_GUJARATI,                    "gu", "IN", k0    },
     { LANGUAGE_KANNADA,                     "kn", "IN", k0    },
     { LANGUAGE_ASSAMESE,                    "as", "IN", k0    },
-    { LANGUAGE_KASHMIRI_INDIA,              "ks", "IN", k0    },
+    { LANGUAGE_KASHMIRI_INDIA,              "ks", "IN", kSAME },
     { LANGUAGE_KASHMIRI,                    "ks", ""  , kSAME },    // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
     { LANGUAGE_MALAYALAM,                   "ml", "IN", k0    },
-    { LANGUAGE_MANIPURI,                   "mni", "IN", k0    },
+    { LANGUAGE_MANIPURI,                   "mni", "IN", k0    },    // MS reserved
     { LANGUAGE_MARATHI,                     "mr", "IN", k0    },
     { LANGUAGE_KONKANI,                    "kok", "IN", k0    },
     { LANGUAGE_NEPALI,                      "ne", "NP", k0    },
@@ -378,8 +378,6 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_FRENCH_MOROCCO,              "fr", "MA", k0    },
     { LANGUAGE_FRENCH_REUNION,              "fr", "RE", k0    },
     { LANGUAGE_FRENCH,                      "fr", ""  , k0    },    // needed as a catcher before other "fr" entries!
-    { LANGUAGE_FRENCH_NORTH_AFRICA,         "fr", ""  , k0    },    // MS reserved, "fr-015"
-    { LANGUAGE_FRENCH_WEST_INDIES,          "fr", ""  , k0    },    // no ISO country code; MS "Neither defined nor reserved"
     { LANGUAGE_FRISIAN_NETHERLANDS,         "fy", "NL", k0    },
     { LANGUAGE_GAELIC_IRELAND,              "ga", "IE", k0    },
     { LANGUAGE_GAELIC_SCOTLAND,             "gd", "GB", k0    },
@@ -433,14 +431,14 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_AMHARIC_ETHIOPIA,            "am", "ET", k0    },
     { LANGUAGE_GUARANI_PARAGUAY,           "gug", "PY", k0    },
     { LANGUAGE_HAWAIIAN_UNITED_STATES,     "haw", "US", k0    },
-    { LANGUAGE_EDO,                        "bin", "NG", k0    },
-    { LANGUAGE_FULFULDE_NIGERIA,           "fuv", "NG", k0    },
-    { LANGUAGE_FULFULDE_NIGERIA,            "ff", "NG", kSAME },    // macrolanguage code
+    { LANGUAGE_EDO,                        "bin", "NG", k0    },    // MS reserved
+    { LANGUAGE_FULFULDE_NIGERIA,            "ff", "NG", k0    },    // macrolanguage code; MS since rev.15
+    { LANGUAGE_FULFULDE_NIGERIA,           "fuv", "NG", kSAME },    // MS reserved until rev.15, since rev.15 "ff-NG" and "ff-Latn-NG"
     { LANGUAGE_FULFULDE_SENEGAL,            "ff", "SN", k0    },    // macrolanguage code
     { LANGUAGE_HAUSA_NIGERIA,               "ha", "NG", kSAME },
     { LANGUAGE_USER_HAUSA_GHANA,            "ha", "GH", kSAME },
     { LANGUAGE_IGBO_NIGERIA,                "ig", "NG", k0    },
-    { LANGUAGE_KANURI_NIGERIA,              "kr", "NG", k0    },
+    { LANGUAGE_KANURI_NIGERIA,              "kr", "NG", k0    },    // macrolanguage code; MS reserved until rev.15
     { LANGUAGE_YORUBA,                      "yo", "NG", k0    },
     { LANGUAGE_SOMALI,                      "so", "SO", k0    },
     { LANGUAGE_PAPIAMENTU,                 "pap", "AN", k0    },
@@ -449,8 +447,8 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_USER_PAPIAMENTU_BONAIRE,    "pap", "BQ", k0    },
     { LANGUAGE_ENGLISH_SINGAPORE,           "en", "SG", k0    },
     { LANGUAGE_USER_YIDDISH_US,             "yi", "US", k0    },
-    { LANGUAGE_YIDDISH,                     "yi", "IL", k0    },    // new: old was "ji"
-    { LANGUAGE_YIDDISH,                     "ji", "IL", kSAME },    // old: new is "yi"
+    { LANGUAGE_USER_YIDDISH_ISRAEL,         "yi", "IL", k0    },    // new: old was "ji"
+    { LANGUAGE_USER_YIDDISH_ISRAEL,         "ji", "IL", kSAME },    // old: new is "yi"
     { LANGUAGE_SYRIAC,                     "syr", "TR", k0    },    // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
     { LANGUAGE_SINHALESE_SRI_LANKA,         "si", "LK", k0    },
     { LANGUAGE_CHEROKEE_UNITED_STATES,     "chr", "US", kSAME },
@@ -476,14 +474,14 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_YAKUT_RUSSIA,               "sah", "RU", k0    },
     { LANGUAGE_MOHAWK_CANADA,              "moh", "CA", k0    },
     { LANGUAGE_BASHKIR_RUSSIA,              "ba", "RU", k0    },
-    { LANGUAGE_KICHE_GUATEMALA,            "qut", "GT", k0    },
+    { LANGUAGE_KICHE_GUATEMALA,            "qut", "GT", k0    },    // MS reserved since rev.15
     { LANGUAGE_DARI_AFGHANISTAN,           "prs", "AF", k0    },
     { LANGUAGE_DARI_AFGHANISTAN,           "gbz", "AF", kSAME },    // was an error
     { LANGUAGE_WOLOF_SENEGAL,               "wo", "SN", k0    },
     { LANGUAGE_FILIPINO,                   "fil", "PH", k0    },
     { LANGUAGE_USER_TAGALOG,                "tl", "PH", k0    },
     { LANGUAGE_ENGLISH_PHILIPPINES,         "en", "PH", k0    },
-    { LANGUAGE_IBIBIO_NIGERIA,             "ibb", "NG", k0    },
+    { LANGUAGE_IBIBIO_NIGERIA,             "ibb", "NG", k0    },    // MS reserved
     { LANGUAGE_YI,                          "ii", "CN", k0    },
     { LANGUAGE_ENGLISH_ARAB_EMIRATES,       "en", "AE", k0    },
     { LANGUAGE_ENGLISH_BAHRAIN,             "en", "BH", k0    },    // MS reserved
@@ -498,9 +496,10 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME },
     { LANGUAGE_TAMAZIGHT_MOROCCO,          "tmz", "MA", k0    },    // MS reserved
     { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "ber", "MA", kSAME },    // Morocco is officially using Tifinagh for its Berber languages, old kludge to distinguish from LANGUAGE_TAMAZIGHT_LATIN_ALGERIA
-    { LANGUAGE_USER_LATIN_VATICAN,          "la", "VA", k0    },
-    { LANGUAGE_OBSOLETE_USER_LATIN,         "la", "VA", k0    },
-    { LANGUAGE_LATIN_LSO,                   "la", ""  , k0    },
+    { LANGUAGE_LATIN,                       "la", "VA", k0    },
+    { LANGUAGE_OBSOLETE_USER_LATIN_VATICAN, "la", "VA", LANGUAGE_LATIN },
+    { LANGUAGE_OBSOLETE_USER_LATIN,         "la", "VA", LANGUAGE_LATIN },
+    { LANGUAGE_LATIN,                       "la", ""  , kSAME },
     { LANGUAGE_USER_ESPERANTO,              "eo", ""  , k0    },
     { LANGUAGE_USER_INTERLINGUA,            "ia", ""  , k0    },
     { LANGUAGE_USER_INTERLINGUE,            "ie", ""  , k0    },
@@ -583,7 +582,7 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_USER_MAORE,                 "swb", "YT", k0    },
     { LANGUAGE_USER_BUSHI,                 "buc", "YT", k0    },
     { LANGUAGE_USER_TAHITIAN,               "ty", "PF", k0    },
-    { LANGUAGE_MALAGASY_PLATEAU,           "plt", "MG", k0    },
+    { LANGUAGE_MALAGASY_PLATEAU,           "plt", "MG", k0    },    // MS reserved
     { LANGUAGE_MALAGASY_PLATEAU,            "mg", "MG", kSAME },
     { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", k0 },
     { LANGUAGE_USER_BAFIA,                 "ksf", "CM", k0    },
@@ -719,14 +718,14 @@ IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
     { LANGUAGE_SERBIAN_CYRILLIC_LSO,                "sr-Cyrl", ""  , kSAME },   // MS
     { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", k0    },
     { LANGUAGE_BOSNIAN_CYRILLIC_LSO,                "bs-Cyrl", ""  , k0    },
-    { LANGUAGE_AZERI_CYRILLIC,                      "az-Cyrl", "AZ", k0    },   // macrolanguage code
+    { LANGUAGE_AZERI_CYRILLIC,                      "az-Cyrl", "AZ", k0    },   // macrolanguage code; MS reserved since rev.15
     { LANGUAGE_AZERI_CYRILLIC_LSO,                  "az-Cyrl", ""  , k0    },   // macrolanguage code
-    { LANGUAGE_UZBEK_CYRILLIC,                      "uz-Cyrl", "UZ", k0    },   // macrolanguage code
+    { LANGUAGE_UZBEK_CYRILLIC,                      "uz-Cyrl", "UZ", k0    },   // macrolanguage code; MS reserved since rev.15
     { LANGUAGE_UZBEK_CYRILLIC_LSO,                  "uz-Cyrl", ""  , k0    },   // macrolanguage code
     { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA,         "mn-Cyrl", "MN", k0    },   // macrolanguage code; should be khk-MN or khk-Cyrl-MN
     { LANGUAGE_MONGOLIAN_CYRILLIC_LSO,              "mn-Cyrl", ""  , k0    },   // macrolanguage code; MS, should be khk or khk-Cyrl
     { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA,        "mn-Mong", "MN", k0    },   // macrolanguage code; MS, should be khk-Mong-MN
-    { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA,           "mn-Mong", "CN", k0    },   // macrolanguage code; MS, should actually be mvf-CN
+    { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA,           "mn-Mong", "CN", k0    },   // macrolanguage code; MS reserved since rev.15; should actually be mvf-CN
     { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO,             "mn-Mong", ""  , k0    },   // macrolanguage code
     { LANGUAGE_USER_PALI_LATIN,                     "pi-Latn", ""  , k0    },
     { LANGUAGE_USER_PALI_THAI,                      "pi-Thai", ""  , k0    },
@@ -736,10 +735,10 @@ IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
     { LANGUAGE_AZERI_LATIN,                         "az-Latn", "AZ", k0    },   // macrolanguage code; MS
     { LANGUAGE_AZERI_LATIN_LSO,                     "az-Latn", ""  , k0    },   // macrolanguage code; MS
     { LANGUAGE_USER_YIDDISH_US,                     "yi-Hebr", "US", kSAME },   // macrolanguage code; MS, Hebr is suppress-script
-    { LANGUAGE_YIDDISH,                             "yi-Hebr", "IL", kSAME },   // macrolanguage code; MS, Hebr is suppress-script
+    { LANGUAGE_USER_YIDDISH_ISRAEL,                 "yi-Hebr", "IL", kSAME },   // macrolanguage code; MS, Hebr is suppress-script
     { LANGUAGE_UZBEK_LATIN,                         "uz-Latn", "UZ", k0    },   // macrolanguage code
     { LANGUAGE_UZBEK_LATIN_LSO,                     "uz-Latn", ""  , k0    },
-    { LANGUAGE_SINDHI,                              "sd-Deva", "IN", k0    },   // MS
+    { LANGUAGE_SINDHI,                              "sd-Deva", "IN", k0    },   // MS reserved
     { LANGUAGE_SINDHI_PAKISTAN,                     "sd-Arab", "PK", k0    },   // MS
     { LANGUAGE_SINDHI_ARABIC_LSO,                   "sd-Arab", ""  , k0    },
     { LANGUAGE_CHEROKEE_UNITED_STATES,             "chr-Cher", "US", k0    },   // MS
@@ -750,12 +749,12 @@ IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
     { LANGUAGE_INUKTITUT_LATIN_LSO,                 "iu-Latn", ""  , k0    },   // macrolanguage code, MS
     { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO,         "tzm-Tfng", "MA", k0    },
     { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO,             "tzm-Tfng", ""  , k0    },
-    { LANGUAGE_KASHMIRI_INDIA,                      "ks-Deva", "IN", k0    },   // MS
+    { LANGUAGE_KASHMIRI_INDIA,                      "ks-Deva", "IN", k0    },   // MS since rev.15, earlier was "ks-Deva" reserved
     { LANGUAGE_KASHMIRI,                            "ks-Arab", ""  , k0    },   // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
     { LANGUAGE_HAUSA_NIGERIA,                       "ha-Latn", "NG", k0    },   // MS
     { LANGUAGE_USER_HAUSA_GHANA,                    "ha-Latn", "GH", k0    },
     { LANGUAGE_HAUSA_LATIN_LSO,                     "ha-Latn", ""  , k0    },
-    { LANGUAGE_LATIN_LSO,                           "la-Latn", ""  , kSAME },   // MS, though Latn is suppress-script
+    { LANGUAGE_LATIN,                               "la-Latn", ""  , kSAME },   // MS reserved until rev.15, though Latn is suppress-script, "la-VA" since rev.15
     { LANGUAGE_TAI_NUA_CHINA,                      "tdd-Tale", "CN", k0    },   // MS reserved
     { LANGUAGE_LU_CHINA,                           "khb-Talu", "CN", k0    },   // MS reserved
     { LANGUAGE_KURDISH_ARABIC_IRAQ,                 "ku-Arab", "IQ", kSAME },   // macrolanguage code, MS
@@ -768,6 +767,7 @@ IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
     { LANGUAGE_PUNJABI_ARABIC_LSO,                  "pa-Arab", ""  , k0    },   // MS, incorrect
     { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA,            "tzm-Latn", "DZ", kSAME },   // MS
     { LANGUAGE_TAMAZIGHT_LATIN_LSO,                "tzm-Latn", ""  , k0    },   // MS
+    { LANGUAGE_FULFULDE_NIGERIA,                    "ff-Latn", "NG", kSAME },   // macrolanguage code; MS since rev.15
     { LANGUAGE_FULFULDE_SENEGAL,                    "ff-Latn", "SN", k0    },   // macrolanguage code, MS
     { LANGUAGE_FULFULDE_LATIN_LSO,                  "ff-Latn", ""  , k0    },   // macrolanguage code
     { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA,    "bs-Latn", "BA", kSAME },   // MS, though Latn is suppress-script
@@ -781,9 +781,11 @@ IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
     { LANGUAGE_USER_HUNGARIAN_ROVAS,                "hu-Hung", "HU", k0    },
     { LANGUAGE_USER_MALAY_ARABIC_MALAYSIA,          "ms-Arab", "MY", k0    },
     { LANGUAGE_USER_MALAY_ARABIC_BRUNEI,            "ms-Arab", "BN", k0    },
-    { LANGUAGE_KAZAKH_LATIN,                        "kk-Latn", "KZ", k0    },   // MS reserved
+    { LANGUAGE_KAZAKH_LATIN,                        "kk-Latn", "KZ", k0    },
     { LANGUAGE_KAZAKH_LATIN_LSO,                    "kk-Latn", ""  , k0    },   // MS reserved
     { LANGUAGE_KAZAKH_CYRILLIC_LSO,                 "kk-Cyrl", ""  , k0    },   // MS reserved
+    { LANGUAGE_KANURI_NIGERIA,                      "kr-Latn", "NG", k0    },   // macrolanguage code; MS since rev.15
+    { LANGUAGE_TAMAZIGHT_ARABIC_MOROCCO,           "tzm-Arab", "MA", k0    },   // MS since rev.15, was reserved
     { LANGUAGE_DONTKNOW,                            "",        ""  , k0    }    // marks end of table
 };
 
@@ -797,6 +799,8 @@ Bcp47CountryEntry const aImplBcp47CountryEntries[] =
     { LANGUAGE_SPANISH_DATED,           "es-ES-u-co-trad", "ES", "es-u-co-trad", k0 },  // RFC6067/CLDR
     { LANGUAGE_SPANISH_DATED,              "es-ES_tradnl", "ES", "", kSAME },           // MS malformed
 //  { LANGUAGE_YUE_CHINESE_HONGKONG,         "zh-yue-HK", "HK", "", 0 },   // MS reserved, prefer yue-HK; do not add unless LanguageTag::simpleExtract() can handle it to not call liblangtag for rsc!
+    { LANGUAGE_YIDDISH,                          "yi-001",   "", "", k0 },  // MS since rev.15, was "yi-Hebr" reserved, "001"="World"
+    { LANGUAGE_FRENCH_WEST_INDIES,               "fr-029",   "", "", k0 },  // MS since rev.15, was "Neither defined nor reserved", "029"="Caribbean"
     { LANGUAGE_DONTKNOW,                    "", "", "", k0 }    // marks end of table
 };
 
diff --git a/i18nlangtag/source/isolang/mslangid.cxx b/i18nlangtag/source/isolang/mslangid.cxx
index ae6cd6291672..9e6f2a7532ad 100644
--- a/i18nlangtag/source/isolang/mslangid.cxx
+++ b/i18nlangtag/source/isolang/mslangid.cxx
@@ -490,7 +490,9 @@ bool MsLangId::isLegacy( LanguageType nLang )
 LanguageType MsLangId::getReplacementForObsoleteLanguage( LanguageType nLang )
 {
     if (nLang == LANGUAGE_OBSOLETE_USER_LATIN)
-        nLang = LANGUAGE_USER_LATIN_VATICAN;
+        nLang = LANGUAGE_LATIN;
+    else if (nLang == LANGUAGE_OBSOLETE_USER_LATIN_VATICAN)
+        nLang = LANGUAGE_LATIN;
     else if (nLang == LANGUAGE_OBSOLETE_USER_MAORI)
         nLang = LANGUAGE_MAORI_NEW_ZEALAND;
     else if (nLang == LANGUAGE_OBSOLETE_USER_KINYARWANDA)
diff --git a/i18nlangtag/source/languagetag/languagetag.cxx b/i18nlangtag/source/languagetag/languagetag.cxx
index 41f23973020f..6175820bb546 100644
--- a/i18nlangtag/source/languagetag/languagetag.cxx
+++ b/i18nlangtag/source/languagetag/languagetag.cxx
@@ -3173,7 +3173,7 @@ LanguageTag makeLanguageTagFromAppleLanguageId(AppleLanguageId nLanguage)
             nLang = LANGUAGE_CATALAN;
             break;
         case AppleLanguageId::LATIN:
-            nLang = LANGUAGE_USER_LATIN;
+            nLang = LANGUAGE_LATIN;
             break;
         case AppleLanguageId::QUENCHUA:
             nLang = LANGUAGE_QUECHUA_BOLIVIA; //maybe
diff --git a/include/i18nlangtag/lang.h b/include/i18nlangtag/lang.h
index c319b068b215..4b28d9dc3ac6 100644
--- a/include/i18nlangtag/lang.h
+++ b/include/i18nlangtag/lang.h
@@ -193,7 +193,7 @@ namespace o3tl
 #define LANGUAGE_ENGLISH_BAHRAIN            LanguageType(0x5009)
 #define LANGUAGE_ENGLISH_BELIZE             LanguageType(0x2809)
 #define LANGUAGE_ENGLISH_CAN                LanguageType(0x1009)
-#define LANGUAGE_ENGLISH_CARIBBEAN          LanguageType(0x2409)
+#define LANGUAGE_ENGLISH_CARIBBEAN          LanguageType(0x2409)  /* MS reserved since rev.15, "en-029" */
 #define LANGUAGE_ENGLISH_EGYPT              LanguageType(0x5409)
 #define LANGUAGE_ENGLISH_EIRE               LanguageType(0x1809)
 #define LANGUAGE_ENGLISH_HONG_KONG_SAR      LanguageType(0x3C09)
@@ -229,11 +229,11 @@ namespace o3tl
 #define LANGUAGE_FRENCH_MALI                LanguageType(0x340C)
 #define LANGUAGE_FRENCH_MONACO              LanguageType(0x180C)
 #define LANGUAGE_FRENCH_MOROCCO             LanguageType(0x380C)
-#define LANGUAGE_FRENCH_NORTH_AFRICA        LanguageType(0xE40C)
+#define LANGUAGE_FRENCH_NORTH_AFRICA        LanguageType(0xE40C)  /* MS reserved, "fr-015", "015"="Northern Africa" */
 #define LANGUAGE_FRENCH_REUNION             LanguageType(0x200C)
 #define LANGUAGE_FRENCH_SENEGAL             LanguageType(0x280C)
 #define LANGUAGE_FRENCH_SWISS               LanguageType(0x100C)
-#define LANGUAGE_FRENCH_WEST_INDIES         LanguageType(0x1C0C)  /* MS in its MS-LCID.pdf now says "Neither defined nor reserved" */
+#define LANGUAGE_FRENCH_WEST_INDIES         LanguageType(0x1C0C)  /* MS-LCID.pdf in between said "Neither defined nor reserved" but since rev.15 it's "fr-029" */
 #define LANGUAGE_FRENCH_ZAIRE               LanguageType(0x240C)
 #define LANGUAGE_FRISIAN_NETHERLANDS        LanguageType(0x0462)
 #define LANGUAGE_FULFULDE_LATIN_LSO         LanguageType(0x7C67)
@@ -279,7 +279,7 @@ namespace o3tl
 #define LANGUAGE_KAZAKH_CYRILLIC_LSO        LanguageType(0x783F)
 #define LANGUAGE_KAZAKH_LATIN_LSO           LanguageType(0x7C3F)
 #define LANGUAGE_KHMER                      LanguageType(0x0453)
-#define LANGUAGE_KICHE_GUATEMALA            LanguageType(0x0486)  /* AKA K'iche', West Central Quiche,  */
+#define LANGUAGE_KICHE_GUATEMALA            LanguageType(0x0486)  /* AKA K'iche', West Central Quiche */
 #define LANGUAGE_KINYARWANDA_RWANDA         LanguageType(0x0487)  /* obsoletes LANGUAGE_USER_KINYARWANDA 0x0621 */
 #define LANGUAGE_KIRGHIZ                    LanguageType(0x0440)  /* AKA Kyrgyz */
 #define LANGUAGE_KONKANI                    LanguageType(0x0457)
@@ -288,7 +288,7 @@ namespace o3tl
 #define LANGUAGE_KURDISH_ARABIC_IRAQ        LanguageType(0x0492)  /* obsoletes LANGUAGE_USER_KURDISH_IRAQ 0x0E26 */
 #define LANGUAGE_KURDISH_ARABIC_LSO         LanguageType(0x7C92)
 #define LANGUAGE_LAO                        LanguageType(0x0454)
-#define LANGUAGE_LATIN_LSO                  LanguageType(0x0476)  /* obsoletes LANGUAGE_USER_LATIN 0x0610 */
+#define LANGUAGE_LATIN                      LanguageType(0x0476)  /* obsoletes LANGUAGE_USER_LATIN 0x0610 and LANGUAGE_USER_LATIN_VATICAN 0x8076 */
 #define LANGUAGE_LATVIAN                    LanguageType(0x0426)
 #define LANGUAGE_LITHUANIAN                 LanguageType(0x0427)
 #define LANGUAGE_LITHUANIAN_CLASSIC         LanguageType(0x0827)  /* MS in its MS-LCID.pdf now says "Neither defined nor reserved" */
@@ -455,9 +455,9 @@ namespace o3tl
 
 #define LANGUAGE_ar_Ploc_SA_reserved        LanguageType(0x4401)  /* 'ar-Ploc-SA', 'Ploc'?? */
 #define LANGUAGE_ja_Ploc_JP_reserved        LanguageType(0x0811)  /* 'ja-Ploc-JP', 'Ploc'?? */
-#define LANGUAGE_pap_029_reserved           LanguageType(0x0479)  /* 'pap-029' */
-#define LANGUAGE_ar_145_reserved            LanguageType(0x4801)  /* 'ar-145' */
-#define LANGUAGE_es_419                     LanguageType(0x580A)  /* 'es-419', not reserved, used? */
+#define LANGUAGE_pap_029_reserved           LanguageType(0x0479)  /* "pap-029", "029"="Caribbean" */
+#define LANGUAGE_ar_145_reserved            LanguageType(0x4801)  /* "ar-145", "145"="Western Asia" */
+#define LANGUAGE_es_419_reserved            LanguageType(0x580A)  /* MS reserved since rev.15, "es-419", "419"="Latin America and the Caribbean" */
 
 /* Seems these values were used or reserved at one point of time ... */
 #define LANGUAGE_Neither_defined_nor_reserved_0x007B LanguageType(0x007B)
@@ -533,8 +533,9 @@ namespace o3tl
  * mapping ISO back to LANGID will return the new value.
  */
 #define LANGUAGE_OBSOLETE_USER_LATIN        LanguageType(0x0610)
-#define LANGUAGE_USER_LATIN                 LANGUAGE_LATIN_LSO
-#define LANGUAGE_USER_LATIN_VATICAN         LanguageType(0x8076)  /* makeLangID( 0x20, getPrimaryLanguage( LANGUAGE_LATIN_LSO)) */
+#define LANGUAGE_USER_LATIN                 LANGUAGE_LATIN
+#define LANGUAGE_OBSOLETE_USER_LATIN_VATICAN LanguageType(0x8076)  /* makeLangID( 0x20, getPrimaryLanguage( LANGUAGE_LATIN)) */
+#define LANGUAGE_USER_LATIN_VATICAN         LANGUAGE_LATIN
 #define LANGUAGE_USER_ESPERANTO             LanguageType(0x0611)  /* no locale possible */
 #define LANGUAGE_USER_INTERLINGUA           LanguageType(0x0612)  /* no locale, but conventions */
 #define LANGUAGE_OBSOLETE_USER_MAORI        LanguageType(0x0620)
@@ -767,6 +768,7 @@ namespace o3tl
 #define LANGUAGE_USER_BRIBRI                LanguageType(0x06AB)
 #define LANGUAGE_USER_ENGLISH_DENMARK       LanguageType(0xB009)  /* makeLangID( 0x2C, getPrimaryLanguage( LANGUAGE_ENGLISH_UK)) */
 #define LANGUAGE_USER_SESOTHO_LESOTHO       LanguageType(0x8030)  /* makeLangID( 0x20, getPrimaryLanguage( LANGUAGE_SESOTHO)) */
+#define LANGUAGE_USER_YIDDISH_ISRAEL        LanguageType(0x843D)  /* makeLangID( 0x21, getPrimaryLanguage( LANGUAGE_YIDDISH)) */
 
 
 /* XXX Add new user defined LCIDs ^^^ there.
diff --git a/svtools/inc/langtab.hrc b/svtools/inc/langtab.hrc
index d44b38294f5a..155be7b45358 100644
--- a/svtools/inc/langtab.hrc
+++ b/svtools/inc/langtab.hrc
@@ -293,7 +293,7 @@ const std::pair<TranslateId, LanguageType> STR_ARR_SVT_LANGUAGE_TABLE[] =
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Shuswap") , LANGUAGE_USER_SHUSWAP },
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Oromo") , LANGUAGE_OROMO },
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Greek, Ancient") , LANGUAGE_USER_ANCIENT_GREEK },
-    { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Yiddish (Israel)") , LANGUAGE_YIDDISH },
+    { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Yiddish (Israel)") , LANGUAGE_USER_YIDDISH_ISRAEL },
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Quechua (Ecuador)") , LANGUAGE_QUECHUA_ECUADOR },
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Uyghur") , LANGUAGE_UIGHUR_CHINA },
     { NC_("STR_ARR_SVT_LANGUAGE_TABLE", "Asturian") , LANGUAGE_USER_ASTURIAN },