Update CLDR to v27

+ A bunch of fixes in the locale data
+ New scripts from Unicode 7.0
+ New locales
- Some locales disappeared (aa_DJ, aa_ER, st_LS, ss_SZ, swc_CD, tn_BW)
- Some locales lost their contents (i.e. en_Dsrt_US)

[ChangeLog][QtCore] QLocale data updated to CLDR v.27

Change-Id: Iba8c7884f8087e577cbb25a8fc106dd7bd3ebb5d
Reviewed-by: Lars Knoll <lars.knoll@digia.com>

2 files changed, 84 insertions, 39 deletions

diff --git a/util/local_database/cldr2qlocalexml.py b/util/local_database/cldr2qlocalexml.py
index 697a2b6f71..400b7a51f8 100755
--- a/util/local_database/cldr2qlocalexml.py
+++ b/util/local_database/cldr2qlocalexml.py
@@ -803,42 +803,42 @@ for key in locale_keys:
     print "            <minus>"    + fixOrdStrMinus(l['minus'])   + "</minus>"
     print "            <plus>"     + fixOrdStrPlus(l['plus'])   + "</plus>"
     print "            <exp>"      + fixOrdStrExp(l['exp'])     + "</exp>"
-    print "            <quotationStart>" + l['quotationStart'].encode('utf-8') + "</quotationStart>"
-    print "            <quotationEnd>" + l['quotationEnd'].encode('utf-8')   + "</quotationEnd>"
-    print "            <alternateQuotationStart>" + l['alternateQuotationStart'].encode('utf-8') + "</alternateQuotationStart>"
-    print "            <alternateQuotationEnd>" + l['alternateQuotationEnd'].encode('utf-8')   + "</alternateQuotationEnd>"
-    print "            <listPatternPartStart>" + l['listPatternPartStart'].encode('utf-8')   + "</listPatternPartStart>"
-    print "            <listPatternPartMiddle>" + l['listPatternPartMiddle'].encode('utf-8')   + "</listPatternPartMiddle>"
-    print "            <listPatternPartEnd>" + l['listPatternPartEnd'].encode('utf-8')   + "</listPatternPartEnd>"
-    print "            <listPatternPartTwo>" + l['listPatternPartTwo'].encode('utf-8')   + "</listPatternPartTwo>"
-    print "            <am>"       + l['am'].encode('utf-8') + "</am>"
-    print "            <pm>"       + l['pm'].encode('utf-8') + "</pm>"
-    print "            <firstDayOfWeek>"  + l['firstDayOfWeek'].encode('utf-8') + "</firstDayOfWeek>"
-    print "            <weekendStart>"  + l['weekendStart'].encode('utf-8') + "</weekendStart>"
-    print "            <weekendEnd>"  + l['weekendEnd'].encode('utf-8') + "</weekendEnd>"
-    print "            <longDateFormat>"  + l['longDateFormat'].encode('utf-8')  + "</longDateFormat>"
-    print "            <shortDateFormat>" + l['shortDateFormat'].encode('utf-8') + "</shortDateFormat>"
-    print "            <longTimeFormat>"  + l['longTimeFormat'].encode('utf-8')  + "</longTimeFormat>"
-    print "            <shortTimeFormat>" + l['shortTimeFormat'].encode('utf-8') + "</shortTimeFormat>"
-    print "            <standaloneLongMonths>" + l['standaloneLongMonths'].encode('utf-8')      + "</standaloneLongMonths>"
-    print "            <standaloneShortMonths>"+ l['standaloneShortMonths'].encode('utf-8')      + "</standaloneShortMonths>"
-    print "            <standaloneNarrowMonths>"+ l['standaloneNarrowMonths'].encode('utf-8')      + "</standaloneNarrowMonths>"
-    print "            <longMonths>"      + l['longMonths'].encode('utf-8')      + "</longMonths>"
-    print "            <shortMonths>"     + l['shortMonths'].encode('utf-8')     + "</shortMonths>"
-    print "            <narrowMonths>"     + l['narrowMonths'].encode('utf-8')     + "</narrowMonths>"
-    print "            <longDays>"        + l['longDays'].encode('utf-8')        + "</longDays>"
-    print "            <shortDays>"       + l['shortDays'].encode('utf-8')       + "</shortDays>"
-    print "            <narrowDays>"       + l['narrowDays'].encode('utf-8')       + "</narrowDays>"
-    print "            <standaloneLongDays>" + l['standaloneLongDays'].encode('utf-8')        + "</standaloneLongDays>"
-    print "            <standaloneShortDays>" + l['standaloneShortDays'].encode('utf-8')       + "</standaloneShortDays>"
-    print "            <standaloneNarrowDays>" + l['standaloneNarrowDays'].encode('utf-8')       + "</standaloneNarrowDays>"
-    print "            <currencyIsoCode>" + l['currencyIsoCode'].encode('utf-8') + "</currencyIsoCode>"
-    print "            <currencySymbol>" + l['currencySymbol'].encode('utf-8') + "</currencySymbol>"
-    print "            <currencyDisplayName>" + l['currencyDisplayName'].encode('utf-8') + "</currencyDisplayName>"
+    print "            <quotationStart>" + escape(l['quotationStart']).encode('utf-8') + "</quotationStart>"
+    print "            <quotationEnd>" + escape(l['quotationEnd']).encode('utf-8')   + "</quotationEnd>"
+    print "            <alternateQuotationStart>" + escape(l['alternateQuotationStart']).encode('utf-8') + "</alternateQuotationStart>"
+    print "            <alternateQuotationEnd>" + escape(l['alternateQuotationEnd']).encode('utf-8')   + "</alternateQuotationEnd>"
+    print "            <listPatternPartStart>" + escape(l['listPatternPartStart']).encode('utf-8')   + "</listPatternPartStart>"
+    print "            <listPatternPartMiddle>" + escape(l['listPatternPartMiddle']).encode('utf-8')   + "</listPatternPartMiddle>"
+    print "            <listPatternPartEnd>" + escape(l['listPatternPartEnd']).encode('utf-8')   + "</listPatternPartEnd>"
+    print "            <listPatternPartTwo>" + escape(l['listPatternPartTwo']).encode('utf-8')   + "</listPatternPartTwo>"
+    print "            <am>"       + escape(l['am']).encode('utf-8') + "</am>"
+    print "            <pm>"       + escape(l['pm']).encode('utf-8') + "</pm>"
+    print "            <firstDayOfWeek>"  + escape(l['firstDayOfWeek']).encode('utf-8') + "</firstDayOfWeek>"
+    print "            <weekendStart>"  + escape(l['weekendStart']).encode('utf-8') + "</weekendStart>"
+    print "            <weekendEnd>"  + escape(l['weekendEnd']).encode('utf-8') + "</weekendEnd>"
+    print "            <longDateFormat>"  + escape(l['longDateFormat']).encode('utf-8')  + "</longDateFormat>"
+    print "            <shortDateFormat>" + escape(l['shortDateFormat']).encode('utf-8') + "</shortDateFormat>"
+    print "            <longTimeFormat>"  + escape(l['longTimeFormat']).encode('utf-8')  + "</longTimeFormat>"
+    print "            <shortTimeFormat>" + escape(l['shortTimeFormat']).encode('utf-8') + "</shortTimeFormat>"
+    print "            <standaloneLongMonths>" + escape(l['standaloneLongMonths']).encode('utf-8')      + "</standaloneLongMonths>"
+    print "            <standaloneShortMonths>"+ escape(l['standaloneShortMonths']).encode('utf-8')      + "</standaloneShortMonths>"
+    print "            <standaloneNarrowMonths>"+ escape(l['standaloneNarrowMonths']).encode('utf-8')      + "</standaloneNarrowMonths>"
+    print "            <longMonths>"      + escape(l['longMonths']).encode('utf-8')      + "</longMonths>"
+    print "            <shortMonths>"     + escape(l['shortMonths']).encode('utf-8')     + "</shortMonths>"
+    print "            <narrowMonths>"     + escape(l['narrowMonths']).encode('utf-8')     + "</narrowMonths>"
+    print "            <longDays>"        + escape(l['longDays']).encode('utf-8')        + "</longDays>"
+    print "            <shortDays>"       + escape(l['shortDays']).encode('utf-8')       + "</shortDays>"
+    print "            <narrowDays>"       + escape(l['narrowDays']).encode('utf-8')       + "</narrowDays>"
+    print "            <standaloneLongDays>" + escape(l['standaloneLongDays']).encode('utf-8')        + "</standaloneLongDays>"
+    print "            <standaloneShortDays>" + escape(l['standaloneShortDays']).encode('utf-8')       + "</standaloneShortDays>"
+    print "            <standaloneNarrowDays>" + escape(l['standaloneNarrowDays']).encode('utf-8')       + "</standaloneNarrowDays>"
+    print "            <currencyIsoCode>" + escape(l['currencyIsoCode']).encode('utf-8') + "</currencyIsoCode>"
+    print "            <currencySymbol>" + escape(l['currencySymbol']).encode('utf-8') + "</currencySymbol>"
+    print "            <currencyDisplayName>" + escape(l['currencyDisplayName']).encode('utf-8') + "</currencyDisplayName>"
     print "            <currencyDigits>" + str(l['currencyDigits']) + "</currencyDigits>"
     print "            <currencyRounding>" + str(l['currencyRounding']) + "</currencyRounding>"
-    print "            <currencyFormat>" + l['currencyFormat'].encode('utf-8') + "</currencyFormat>"
-    print "            <currencyNegativeFormat>" + l['currencyNegativeFormat'].encode('utf-8') + "</currencyNegativeFormat>"
+    print "            <currencyFormat>" + escape(l['currencyFormat']).encode('utf-8') + "</currencyFormat>"
+    print "            <currencyNegativeFormat>" + escape(l['currencyNegativeFormat']).encode('utf-8') + "</currencyNegativeFormat>"
     print "        </locale>"
 print "    </localeList>"
 print "</localeDatabase>"
diff --git a/util/local_database/enumdata.py b/util/local_database/enumdata.py
index b9f8077a59..fbeadfb610 100644
--- a/util/local_database/enumdata.py
+++ b/util/local_database/enumdata.py
@@ -351,7 +351,32 @@ language_list = {
     311 : [ "Ugaritic",           "uga" ],
     312 : [ "Akoose",             "bss" ],
     313 : [ "Lakota",             "lkt" ],
-    314 : [ "Standard Moroccan Tamazight", "zgh" ]
+    314 : [ "Standard Moroccan Tamazight", "zgh" ],
+    315 : [ "Mapuche",            "arn" ],
+    316 : [ "Central Kurdish",    "ckb" ],
+    317 : [ "LowerSorbian",       "dsb" ],
+    318 : [ "UpperSorbian",       "hsb" ],
+    319 : [ "Kenyang",            "ken" ],
+    320 : [ "Mohawk",             "moh" ],
+    321 : [ "Nko",                "nqo" ],
+    322 : [ "Prussian",           "prg" ],
+    323 : [ "Kiche",              "quc" ],
+    324 : [ "Southern Sami",      "sma" ],
+    325 : [ "Lule Sami",          "smj" ],
+    326 : [ "Inari Sami",         "smn" ],
+    327 : [ "Skolt Sami",         "sms" ],
+    328 : [ "Warlpiri",           "wbp" ],
+    329 : [ "Manichaean Middle Persian", "xmn" ],
+    330 : [ "Mende",              "men" ],
+    331 : [ "Ancient North Arabian", "xna" ],
+    332 : [ "Linear A",           "lab" ],
+    333 : [ "Hmong Njua",         "hnj" ],
+    334 : [ "Ho",                 "hoc" ],
+    335 : [ "Lezghian",           "lez" ],
+    336 : [ "Bassa",              "bsq" ],
+    337 : [ "Mono",               "mru" ],
+    338 : [ "Tedim Chin",         "ctd" ],
+    339 : [ "Maithili",           "mai" ]
 }
 
 country_list = {
@@ -720,13 +745,33 @@ script_list = {
     101 : [ "Takri",                  "Takr" ],
     102 : [ "Ugaritic",               "Ugar" ],
     103 : [ "Braille",                "Brai" ],
-    104 : [ "Hiragana",               "Hira" ]
+    104 : [ "Hiragana",               "Hira" ],
+    105 : [ "Caucasian Albanian",     "Aghb" ],
+    106 : [ "Bassa Vah",              "Bass" ],
+    107 : [ "Duployan",               "Dupl" ],
+    108 : [ "Elbasan",                "Elba" ],
+    109 : [ "Grantha",                "Gran" ],
+    110 : [ "Pahawh Hmong",           "Hmng" ],
+    111 : [ "Khojki",                 "Khoj" ],
+    112 : [ "Linear A",               "Lina" ],
+    113 : [ "Mahajani",               "Mahj" ],
+    114 : [ "Manichaean",             "Mani" ],
+    115 : [ "Mende Kikakui",          "Mend" ],
+    116 : [ "Modi",                   "Modi" ],
+    117 : [ "Mro",                    "Mroo" ],
+    118 : [ "Old North Arabian",      "Narb" ],
+    119 : [ "Nabataean",              "Nbat" ],
+    120 : [ "Palmyrene",              "Palm" ],
+    121 : [ "Pau Cin Hau",            "Pauc" ],
+    122 : [ "Old Permic",             "Perm" ],
+    123 : [ "Psalter Pahlavi",        "Phlp" ],
+    124 : [ "Siddham",                "Sidd" ],
+    125 : [ "Khudawadi",              "Sind" ],
+    126 : [ "Tirhuta",                "Tirh" ],
+    127 : [ "Varang Kshiti",          "Wara" ]
 
 #    ### : [ "Blissymbols",            "Blis" ],
-#    ### : [ "Linear A",               "Lina" ],
 #    ### : [ "Naxi Geba",              "Nkgb" ],
-#    ### : [ "Pahawh Hmong",           "Hmng" ],
-#    ### : [ "Varang Kshiti",          "Wara" ],
 }
 
 def countryCodeToId(code):