Issue #20076: Added non derived UTF-8 aliases to locale aliases table.

serhiy-storchaka · serhiy-storchaka · commit c383ad8d9c3a · 2014-10-02T00:11:21.000+03:00
The makelocalealias.py script no longer ignores UTF-8 mapping.
diff --git a/Lib/locale.py b/Lib/locale.py
@@ -861,6 +861,7 @@ def getpreferredencoding(do_setlocale = True):
     'az_az.iso88599e':                      'az_AZ.ISO8859-9E',
     'be':                                   'be_BY.CP1251',
     'be@latin':                             'be_BY.UTF-8@latin',
+    'be_bg.utf8':                           'bg_BG.UTF-8',
     'be_by':                                'be_BY.CP1251',
     'be_by@latin':                          'be_BY.UTF-8@latin',
     'bem_zm':                               'bem_ZM.UTF-8',
@@ -887,6 +888,7 @@ def getpreferredencoding(do_setlocale = True):
     'c.ascii':                              'C',
     'c.en':                                 'C',
     'c.iso88591':                           'en_US.ISO8859-1',
+    'c.utf8':                               'en_US.UTF-8',
     'c_c':                                  'C',
     'c_c.c':                                'C',
     'ca':                                   'ca_ES.ISO8859-1',
@@ -940,6 +942,7 @@ def getpreferredencoding(do_setlocale = True):
     'en_bw':                                'en_BW.ISO8859-1',
     'en_ca':                                'en_CA.ISO8859-1',
     'en_dk':                                'en_DK.ISO8859-1',
+    'en_dl.utf8':                           'en_DL.UTF-8',
     'en_gb':                                'en_GB.ISO8859-1',
     'en_hk':                                'en_HK.ISO8859-1',
     'en_ie':                                'en_IE.ISO8859-1',
@@ -954,6 +957,7 @@ def getpreferredencoding(do_setlocale = True):
     'en_za':                                'en_ZA.ISO8859-1',
     'en_zm':                                'en_ZM.UTF-8',
     'en_zw':                                'en_ZW.ISO8859-1',
+    'en_zw.utf8':                           'en_ZS.UTF-8',
     'eng_gb':                               'en_GB.ISO8859-1',
     'english':                              'en_EN.ISO8859-1',
     'english_uk':                           'en_GB.ISO8859-1',
@@ -1106,6 +1110,7 @@ def getpreferredencoding(do_setlocale = True):
     'korean.euc':                           'ko_KR.eucKR',
     'ks':                                   'ks_IN.UTF-8',
     'ks_in':                                'ks_IN.UTF-8',
+    'ks_in@devanagari.utf8':                'ks_IN.UTF-8@devanagari',
     'ku_tr':                                'ku_TR.ISO8859-9',
     'kw':                                   'kw_GB.ISO8859-1',
     'kw_gb':                                'kw_GB.ISO8859-1',
@@ -1218,6 +1223,7 @@ def getpreferredencoding(do_setlocale = True):
     'sc_it':                                'sc_IT.UTF-8',
     'sd':                                   'sd_IN.UTF-8',
     'sd_in':                                'sd_IN.UTF-8',
+    'sd_in@devanagari.utf8':                'sd_IN.UTF-8@devanagari',
     'se_no':                                'se_NO.UTF-8',
     'serbocroatian':                        'sr_RS.UTF-8@latin',
     'sh':                                   'sr_RS.UTF-8@latin',
@@ -1258,6 +1264,7 @@ def getpreferredencoding(do_setlocale = True):
     'sr_cs@latn':                           'sr_CS.UTF-8@latin',
     'sr_me':                                'sr_ME.UTF-8',
     'sr_rs':                                'sr_RS.UTF-8',
+    'sr_rs.utf8@latn':                      'sr_RS.UTF-8@latin',
     'sr_rs@latn':                           'sr_RS.UTF-8@latin',
     'sr_sp':                                'sr_CS.ISO8859-2',
     'sr_yu':                                'sr_RS.UTF-8@latin',
@@ -1266,6 +1273,8 @@ def getpreferredencoding(do_setlocale = True):
     'sr_yu.iso88595':                       'sr_CS.ISO8859-5',
     'sr_yu.iso88595@cyrillic':              'sr_CS.ISO8859-5',
     'sr_yu.microsoftcp1251@cyrillic':       'sr_CS.CP1251',
+    'sr_yu.utf8':                           'sr_RS.UTF-8',
+    'sr_yu.utf8@cyrillic':                  'sr_RS.UTF-8',
     'sr_yu@cyrillic':                       'sr_RS.UTF-8',
     'ss':                                   'ss_ZA.ISO8859-1',
     'ss_za':                                'ss_ZA.ISO8859-1',
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -156,6 +156,8 @@ Core and Builtins
 Library
 -------
 
+- Issue #20076: Added non derived UTF-8 aliases to locale aliases table.
+
 - Issue #20079: Added locales supported in glibc 2.18 to locale alias table.
 
 - Issue #20218: Added convenience methods read_text/write_text and read_bytes/
@@ -1188,6 +1190,8 @@ Tests
 Tools/Demos
 -----------
 
+- Issue #20076: The makelocalealias.py script no longer ignores UTF-8 mapping.
+
 - Issue #20079: The makelocalealias.py script now can parse the SUPPORTED file
   from glibc sources and supports command line options for source paths.
 
diff --git a/Tools/i18n/makelocalealias.py b/Tools/i18n/makelocalealias.py
@@ -45,10 +45,6 @@ def parse(filename):
             encoding = encoding.replace('-', '')
             encoding = encoding.replace('_', '')
             locale = lang + '.' + encoding
-            if encoding.lower() == 'utf8':
-                # Ignore UTF-8 mappings - this encoding should be
-                # available for all locales
-                continue
         data[locale] = alias
     return data
 
