i18nlangtag/source/isolang/isolang.cxx  |    3 ++-
 i18nlangtag/source/isolang/mslangid.cxx |    2 ++
 include/i18nlangtag/lang.h              |    3 ++-
 3 files changed, 6 insertions(+), 2 deletions(-)

New commits:
commit 375630ae76f46c096421dfadee8d37b406bc10c5
Author:     Eike Rathke <er...@redhat.com>
AuthorDate: Thu Jan 5 18:12:59 2023 +0100
Commit:     Eike Rathke <er...@redhat.com>
CommitDate: Thu Jan 5 21:35:29 2023 +0000

    Related: tdf#152781 Stab the 0xE40A {es} vs Latin America quirk
    
    First, the LANGUAGE_SPANISH_LATIN_AMERICA 0xE40A is not a MS
    system LCID, it is Spanish 0x00a with sublanguage 0x39 => user
    defined (in the range 0x20 to 0x3f). Meanwhile MS reserved 0x580A
    for {es-419}, so obsolete the legacy 0xE40A definition and replace
    with 0x580A when encountered.
    
    Second, due to the legacy plain {es} mapping being present, an
    encountered 'es' (from our bundled dictionary extension) got
    mapped to 0xE40A instead of 0xA and thus was added to the
    character language listbox (that otherwise suppresses LCIDs
    without sublanguage), resulting in a "Spanish {es}" entry.
    
    Besides, it's currently not clear how to actually proceed with
    such dictionary situation when, for example, both 'es-ES' and 'es'
    dictionaries are present and the 'es' dictionary apparently is
    meant as base and contains entries the 'es-ES' does not or 'es-ES'
    overrides entries. It might be it's handled half-way in
    linguistics, but maybe not even that, I didn't investigate.
    
    Change-Id: Id859731ba5efa65d4a6de429b7f52027aa69327c
    Reviewed-on: https://gerrit.libreoffice.org/c/core/+/145093
    Reviewed-by: Eike Rathke <er...@redhat.com>
    Tested-by: Jenkins

diff --git a/i18nlangtag/source/isolang/isolang.cxx 
b/i18nlangtag/source/isolang/isolang.cxx
index c5259a53886d..2bd6b5e5e229 100644
--- a/i18nlangtag/source/isolang/isolang.cxx
+++ b/i18nlangtag/source/isolang/isolang.cxx
@@ -273,7 +273,6 @@ IsoLanguageCountryEntry const aImplIsoLangEntries[] =
     { LANGUAGE_SPANISH_NICARAGUA,           "es", "NI", k0    },
     { LANGUAGE_SPANISH_PUERTO_RICO,         "es", "PR", k0    },
     { LANGUAGE_SPANISH_UNITED_STATES,       "es", "US", k0    },
-    { LANGUAGE_SPANISH_LATIN_AMERICA,       "es", ""  , k0    },
     { LANGUAGE_TURKISH,                     "tr", "TR", k0    },
     { LANGUAGE_UKRAINIAN,                   "uk", "UA", k0    },
     { LANGUAGE_VIETNAMESE,                  "vi", "VN", k0    },
@@ -791,6 +790,8 @@ Bcp47CountryEntry const aImplBcp47CountryEntries[] =
 //  { 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_SPANISH_LATIN_AMERICA,            "es-419",   "", "", k0 },  // 
MS reserved since rev.15, "419"="Latin America and the Caribbean"
+    { LANGUAGE_OBSOLETE_USER_SPANISH_LATIN_AMERICA, "es-419", "", "", 
LANGUAGE_SPANISH_LATIN_AMERICA },
     { LANGUAGE_USER_INTERSLAVIC_LATIN, "art-Latn-x-interslv", "", "", k0 },  
// see discussion in tdf#145853
     { LANGUAGE_USER_INTERSLAVIC_CYRILLIC, "art-Cyrl-x-interslv", "", "", k0 },
     { LANGUAGE_DONTKNOW,                    "", "", "", k0 }    // marks end 
of table
diff --git a/i18nlangtag/source/isolang/mslangid.cxx 
b/i18nlangtag/source/isolang/mslangid.cxx
index 4e446d568858..cac12347fc54 100644
--- a/i18nlangtag/source/isolang/mslangid.cxx
+++ b/i18nlangtag/source/isolang/mslangid.cxx
@@ -567,6 +567,8 @@ LanguageType MsLangId::getReplacementForObsoleteLanguage( 
LanguageType nLang )
         nLang = LANGUAGE_KURDISH_ARABIC_IRAQ;
     else if (nLang == LANGUAGE_OBSOLETE_USER_SPANISH_CUBA)
         nLang = LANGUAGE_SPANISH_CUBA;
+    else if (nLang == LANGUAGE_OBSOLETE_USER_SPANISH_LATIN_AMERICA)
+        nLang = LANGUAGE_SPANISH_LATIN_AMERICA;
 
     // The following are not strictly obsolete but should be mapped to a
     // replacement locale when encountered.
diff --git a/include/i18nlangtag/lang.h b/include/i18nlangtag/lang.h
index 158a7c7fe5be..59e20669cddd 100644
--- a/include/i18nlangtag/lang.h
+++ b/include/i18nlangtag/lang.h
@@ -389,7 +389,6 @@ namespace o3tl
 #define LANGUAGE_SPANISH_EL_SALVADOR        LanguageType(0x440A)
 #define LANGUAGE_SPANISH_GUATEMALA          LanguageType(0x100A)
 #define LANGUAGE_SPANISH_HONDURAS           LanguageType(0x480A)
-#define LANGUAGE_SPANISH_LATIN_AMERICA      LanguageType(0xE40A)  /* no locale 
possible */
 #define LANGUAGE_SPANISH_MEXICAN            LanguageType(0x080A)
 #define LANGUAGE_SPANISH_MODERN             LanguageType(0x0C0A)
 #define LANGUAGE_SPANISH_NICARAGUA          LanguageType(0x4C0A)
@@ -532,6 +531,8 @@ namespace o3tl
  * that such a mapping exists in i18nlangtag/source/isolang/isolang.cxx, but
  * mapping ISO back to LANGID will return the new value.
  */
+#define LANGUAGE_OBSOLETE_USER_SPANISH_LATIN_AMERICA LanguageType(0xE40A)  /* 
no locale possible, legacy for es-419, makeLangID( 0x39, getPrimaryLanguage( 
LANGUAGE_SPANISH)) */
+#define LANGUAGE_SPANISH_LATIN_AMERICA      LANGUAGE_es_419_reserved
 #define LANGUAGE_OBSOLETE_USER_LATIN        LanguageType(0x0610)
 #define LANGUAGE_USER_LATIN                 LANGUAGE_LATIN
 #define LANGUAGE_OBSOLETE_USER_LATIN_VATICAN LanguageType(0x8076)  /* 
makeLangID( 0x20, getPrimaryLanguage( LANGUAGE_LATIN)) */

Reply via email to