[Python-checkins] [3.6] bpo-20087: Update locale alias mapping with glibc 2.27 supported locales. (GH-6708) (GH-6714)
Serhiy Storchaka
webhook-mailer at python.org
Sun May 6 03:20:44 EDT 2018
https://github.com/python/cpython/commit/b1c70d0ffbb235def1deab62a744ffd9b5253924
commit: b1c70d0ffbb235def1deab62a744ffd9b5253924
branch: 3.6
author: Miss Islington (bot) <31488909+miss-islington at users.noreply.github.com>
committer: Serhiy Storchaka <storchaka at gmail.com>
date: 2018-05-06T10:20:42+03:00
summary:
[3.6] bpo-20087: Update locale alias mapping with glibc 2.27 supported locales. (GH-6708) (GH-6714)
(cherry picked from commit cedc9b74202d8c1ae39bca261cbb45d42ed54d45)
Co-authored-by: Serhiy Storchaka <storchaka at gmail.com>
files:
A Misc/NEWS.d/next/Library/2018-05-05-18-02-24.bpo-20087.lJrvXL.rst
M Lib/locale.py
M Lib/test/test_locale.py
diff --git a/Lib/locale.py b/Lib/locale.py
index 4de0090ed9dd..e85f34ea1996 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -828,6 +828,16 @@ def getpreferredencoding(do_setlocale = True):
#
# SS 2014-10-01:
# Updated alias mapping with glibc 2.19 supported locales.
+#
+# SS 2018-05-05:
+# Updated alias mapping with glibc 2.27 supported locales.
+#
+# These are the differences compared to the old mapping (Python 3.6.5
+# and older):
+#
+# updated 'ca_es at valencia' -> 'ca_ES.ISO8859-15 at valencia' to 'ca_ES.UTF-8 at valencia'
+# updated 'kk_kz' -> 'kk_KZ.RK1048' to 'kk_KZ.ptcp154'
+# updated 'russian' -> 'ru_RU.ISO8859-5' to 'ru_RU.KOI8-R'
locale_alias = {
'a3': 'az_AZ.KOI8-C',
@@ -838,10 +848,13 @@ def getpreferredencoding(do_setlocale = True):
'aa_et': 'aa_ET.UTF-8',
'af': 'af_ZA.ISO8859-1',
'af_za': 'af_ZA.ISO8859-1',
+ 'agr_pe': 'agr_PE.UTF-8',
+ 'ak_gh': 'ak_GH.UTF-8',
'am': 'am_ET.UTF-8',
'am_et': 'am_ET.UTF-8',
'american': 'en_US.ISO8859-1',
'an_es': 'an_ES.ISO8859-15',
+ 'anp_in': 'anp_IN.UTF-8',
'ar': 'ar_AA.ISO8859-6',
'ar_aa': 'ar_AA.ISO8859-6',
'ar_ae': 'ar_AE.ISO8859-6',
@@ -859,6 +872,7 @@ def getpreferredencoding(do_setlocale = True):
'ar_qa': 'ar_QA.ISO8859-6',
'ar_sa': 'ar_SA.ISO8859-6',
'ar_sd': 'ar_SD.ISO8859-6',
+ 'ar_ss': 'ar_SS.UTF-8',
'ar_sy': 'ar_SY.ISO8859-6',
'ar_tn': 'ar_TN.ISO8859-6',
'ar_ye': 'ar_YE.ISO8859-6',
@@ -870,6 +884,7 @@ def getpreferredencoding(do_setlocale = True):
'az': 'az_AZ.ISO8859-9E',
'az_az': 'az_AZ.ISO8859-9E',
'az_az.iso88599e': 'az_AZ.ISO8859-9E',
+ 'az_ir': 'az_IR.UTF-8',
'be': 'be_BY.CP1251',
'be at latin': 'be_BY.UTF-8 at latin',
'be_bg.utf8': 'bg_BG.UTF-8',
@@ -880,7 +895,10 @@ def getpreferredencoding(do_setlocale = True):
'ber_ma': 'ber_MA.UTF-8',
'bg': 'bg_BG.CP1251',
'bg_bg': 'bg_BG.CP1251',
+ 'bhb_in.utf8': 'bhb_IN.UTF-8',
'bho_in': 'bho_IN.UTF-8',
+ 'bho_np': 'bho_NP.UTF-8',
+ 'bi_vu': 'bi_VU.UTF-8',
'bn_bd': 'bn_BD.UTF-8',
'bn_in': 'bn_IN.UTF-8',
'bo_cn': 'bo_CN.UTF-8',
@@ -905,13 +923,17 @@ def getpreferredencoding(do_setlocale = True):
'ca': 'ca_ES.ISO8859-1',
'ca_ad': 'ca_AD.ISO8859-1',
'ca_es': 'ca_ES.ISO8859-1',
- 'ca_es at valencia': 'ca_ES.ISO8859-15 at valencia',
+ 'ca_es at valencia': 'ca_ES.UTF-8 at valencia',
'ca_fr': 'ca_FR.ISO8859-1',
'ca_it': 'ca_IT.ISO8859-1',
'catalan': 'ca_ES.ISO8859-1',
+ 'ce_ru': 'ce_RU.UTF-8',
'cextend': 'en_US.ISO8859-1',
'chinese-s': 'zh_CN.eucCN',
'chinese-t': 'zh_TW.eucTW',
+ 'chr_us': 'chr_US.UTF-8',
+ 'ckb_iq': 'ckb_IQ.UTF-8',
+ 'cmn_tw': 'cmn_TW.UTF-8',
'crh_ua': 'crh_UA.UTF-8',
'croatian': 'hr_HR.ISO8859-2',
'cs': 'cs_CZ.ISO8859-2',
@@ -933,6 +955,7 @@ def getpreferredencoding(do_setlocale = True):
'de_be': 'de_BE.ISO8859-1',
'de_ch': 'de_CH.ISO8859-1',
'de_de': 'de_DE.ISO8859-1',
+ 'de_it': 'de_IT.ISO8859-1',
'de_li.utf8': 'de_LI.UTF-8',
'de_lu': 'de_LU.ISO8859-1',
'deutsch': 'de_DE.ISO8859-1',
@@ -959,10 +982,12 @@ def getpreferredencoding(do_setlocale = True):
'en_gb': 'en_GB.ISO8859-1',
'en_hk': 'en_HK.ISO8859-1',
'en_ie': 'en_IE.ISO8859-1',
+ 'en_il': 'en_IL.UTF-8',
'en_in': 'en_IN.ISO8859-1',
'en_ng': 'en_NG.UTF-8',
'en_nz': 'en_NZ.ISO8859-1',
'en_ph': 'en_PH.ISO8859-1',
+ 'en_sc.utf8': 'en_SC.UTF-8',
'en_sg': 'en_SG.ISO8859-1',
'en_uk': 'en_GB.ISO8859-1',
'en_us': 'en_US.ISO8859-1',
@@ -973,6 +998,7 @@ def getpreferredencoding(do_setlocale = True):
'en_zw.utf8': 'en_ZS.UTF-8',
'eng_gb': 'en_GB.ISO8859-1',
'english': 'en_EN.ISO8859-1',
+ 'english.iso88591': 'en_US.ISO8859-1',
'english_uk': 'en_GB.ISO8859-1',
'english_united-states': 'en_US.ISO8859-1',
'english_united-states.437': 'C',
@@ -1053,12 +1079,14 @@ def getpreferredencoding(do_setlocale = True):
'gv': 'gv_GB.ISO8859-1',
'gv_gb': 'gv_GB.ISO8859-1',
'ha_ng': 'ha_NG.UTF-8',
+ 'hak_tw': 'hak_TW.UTF-8',
'he': 'he_IL.ISO8859-8',
'he_il': 'he_IL.ISO8859-8',
'hebrew': 'he_IL.ISO8859-8',
'hi': 'hi_IN.ISCII-DEV',
'hi_in': 'hi_IN.ISCII-DEV',
'hi_in.isciidev': 'hi_IN.ISCII-DEV',
+ 'hif_fj': 'hif_FJ.UTF-8',
'hne': 'hne_IN.UTF-8',
'hne_in': 'hne_IN.UTF-8',
'hr': 'hr_HR.ISO8859-2',
@@ -1113,7 +1141,8 @@ def getpreferredencoding(do_setlocale = True):
'ka_ge.georgianacademy': 'ka_GE.GEORGIAN-ACADEMY',
'ka_ge.georgianps': 'ka_GE.GEORGIAN-PS',
'ka_ge.georgianrs': 'ka_GE.GEORGIAN-ACADEMY',
- 'kk_kz': 'kk_KZ.RK1048',
+ 'kab_dz': 'kab_DZ.UTF-8',
+ 'kk_kz': 'kk_KZ.ptcp154',
'kl': 'kl_GL.ISO8859-1',
'kl_gl': 'kl_GL.ISO8859-1',
'km_kh': 'km_KH.UTF-8',
@@ -1139,6 +1168,7 @@ def getpreferredencoding(do_setlocale = True):
'li_nl': 'li_NL.UTF-8',
'lij_it': 'lij_IT.UTF-8',
'lithuanian': 'lt_LT.ISO8859-13',
+ 'ln_cd': 'ln_CD.UTF-8',
'lo': 'lo_LA.MULELAO-1',
'lo_la': 'lo_LA.MULELAO-1',
'lo_la.cp1133': 'lo_LA.IBM-CP1133',
@@ -1148,13 +1178,18 @@ def getpreferredencoding(do_setlocale = True):
'lt_lt': 'lt_LT.ISO8859-13',
'lv': 'lv_LV.ISO8859-13',
'lv_lv': 'lv_LV.ISO8859-13',
+ 'lzh_tw': 'lzh_TW.UTF-8',
'mag_in': 'mag_IN.UTF-8',
'mai': 'mai_IN.UTF-8',
'mai_in': 'mai_IN.UTF-8',
+ 'mai_np': 'mai_NP.UTF-8',
+ 'mfe_mu': 'mfe_MU.UTF-8',
'mg_mg': 'mg_MG.ISO8859-15',
'mhr_ru': 'mhr_RU.UTF-8',
'mi': 'mi_NZ.ISO8859-1',
'mi_nz': 'mi_NZ.ISO8859-1',
+ 'miq_ni': 'miq_NI.UTF-8',
+ 'mjw_in': 'mjw_IN.UTF-8',
'mk': 'mk_MK.ISO8859-5',
'mk_mk': 'mk_MK.ISO8859-5',
'ml': 'ml_IN.UTF-8',
@@ -1168,7 +1203,7 @@ def getpreferredencoding(do_setlocale = True):
'mt': 'mt_MT.ISO8859-3',
'mt_mt': 'mt_MT.ISO8859-3',
'my_mm': 'my_MM.UTF-8',
- 'nan_tw at latin': 'nan_TW.UTF-8 at latin',
+ 'nan_tw': 'nan_TW.UTF-8',
'nb': 'nb_NO.ISO8859-1',
'nb_no': 'nb_NO.ISO8859-1',
'nds_de': 'nds_DE.UTF-8',
@@ -1207,6 +1242,8 @@ def getpreferredencoding(do_setlocale = True):
'pa_in': 'pa_IN.UTF-8',
'pa_pk': 'pa_PK.UTF-8',
'pap_an': 'pap_AN.UTF-8',
+ 'pap_aw': 'pap_AW.UTF-8',
+ 'pap_cw': 'pap_CW.UTF-8',
'pd': 'pd_US.ISO8859-1',
'pd_de': 'pd_DE.ISO8859-1',
'pd_us': 'pd_US.ISO8859-1',
@@ -1225,6 +1262,8 @@ def getpreferredencoding(do_setlocale = True):
'pt': 'pt_PT.ISO8859-1',
'pt_br': 'pt_BR.ISO8859-1',
'pt_pt': 'pt_PT.ISO8859-1',
+ 'quz_pe': 'quz_PE.UTF-8',
+ 'raj_in': 'raj_IN.UTF-8',
'ro': 'ro_RO.ISO8859-2',
'ro_ro': 'ro_RO.ISO8859-2',
'romanian': 'ro_RO.ISO8859-2',
@@ -1232,7 +1271,7 @@ def getpreferredencoding(do_setlocale = True):
'ru_ru': 'ru_RU.UTF-8',
'ru_ua': 'ru_UA.KOI8-U',
'rumanian': 'ro_RO.ISO8859-2',
- 'russian': 'ru_RU.ISO8859-5',
+ 'russian': 'ru_RU.KOI8-R',
'rw': 'rw_RW.ISO8859-1',
'rw_rw': 'rw_RW.ISO8859-1',
'sa_in': 'sa_IN.UTF-8',
@@ -1244,12 +1283,14 @@ def getpreferredencoding(do_setlocale = True):
'sd_pk': 'sd_PK.UTF-8',
'se_no': 'se_NO.UTF-8',
'serbocroatian': 'sr_RS.UTF-8 at latin',
+ 'sgs_lt': 'sgs_LT.UTF-8',
'sh': 'sr_RS.UTF-8 at latin',
'sh_ba.iso88592 at bosnia': 'sr_CS.ISO8859-2',
'sh_hr': 'sh_HR.ISO8859-2',
'sh_hr.iso88592': 'hr_HR.ISO8859-2',
'sh_sp': 'sr_CS.ISO8859-2',
'sh_yu': 'sr_RS.UTF-8 at latin',
+ 'shn_mm': 'shn_MM.UTF-8',
'shs_ca': 'shs_CA.UTF-8',
'si': 'si_LK.UTF-8',
'si_lk': 'si_LK.UTF-8',
@@ -1263,6 +1304,7 @@ def getpreferredencoding(do_setlocale = True):
'slovak': 'sk_SK.ISO8859-2',
'slovene': 'sl_SI.ISO8859-2',
'slovenian': 'sl_SI.ISO8859-2',
+ 'sm_ws': 'sm_WS.UTF-8',
'so_dj': 'so_DJ.ISO8859-1',
'so_et': 'so_ET.UTF-8',
'so_ke': 'so_KE.ISO8859-1',
@@ -1309,6 +1351,7 @@ def getpreferredencoding(do_setlocale = True):
'ta_in.tscii': 'ta_IN.TSCII-0',
'ta_in.tscii0': 'ta_IN.TSCII-0',
'ta_lk': 'ta_LK.UTF-8',
+ 'tcy_in.utf8': 'tcy_IN.UTF-8',
'te': 'te_IN.UTF-8',
'te_in': 'te_IN.UTF-8',
'tg': 'tg_TJ.KOI8-C',
@@ -1318,6 +1361,7 @@ def getpreferredencoding(do_setlocale = True):
'th_th.tactis': 'th_TH.TIS620',
'th_th.tis620': 'th_TH.TIS620',
'thai': 'th_TH.ISO8859-11',
+ 'the_np': 'the_NP.UTF-8',
'ti_er': 'ti_ER.UTF-8',
'ti_et': 'ti_ET.UTF-8',
'tig_er': 'tig_ER.UTF-8',
@@ -1326,6 +1370,8 @@ def getpreferredencoding(do_setlocale = True):
'tl_ph': 'tl_PH.ISO8859-1',
'tn': 'tn_ZA.ISO8859-15',
'tn_za': 'tn_ZA.ISO8859-15',
+ 'to_to': 'to_TO.UTF-8',
+ 'tpi_pg': 'tpi_PG.UTF-8',
'tr': 'tr_TR.ISO8859-9',
'tr_cy': 'tr_CY.ISO8859-9',
'tr_tr': 'tr_TR.ISO8859-9',
@@ -1368,6 +1414,7 @@ def getpreferredencoding(do_setlocale = True):
'yi_us': 'yi_US.CP1255',
'yo_ng': 'yo_NG.UTF-8',
'yue_hk': 'yue_HK.UTF-8',
+ 'yuw_pg': 'yuw_PG.UTF-8',
'zh': 'zh_CN.eucCN',
'zh_cn': 'zh_CN.gb2312',
'zh_cn.big5': 'zh_TW.big5',
diff --git a/Lib/test/test_locale.py b/Lib/test/test_locale.py
index 650d7373d8e1..a5ec2c51c55d 100644
--- a/Lib/test/test_locale.py
+++ b/Lib/test/test_locale.py
@@ -430,7 +430,7 @@ def test_latin_modifier(self):
def test_valencia_modifier(self):
self.check('ca_ES.UTF-8 at valencia', 'ca_ES.UTF-8 at valencia')
- self.check('ca_ES at valencia', 'ca_ES.ISO8859-15 at valencia')
+ self.check('ca_ES at valencia', 'ca_ES.UTF-8 at valencia')
self.check('ca at valencia', 'ca_ES.ISO8859-1 at valencia')
def test_devanagari_modifier(self):
diff --git a/Misc/NEWS.d/next/Library/2018-05-05-18-02-24.bpo-20087.lJrvXL.rst b/Misc/NEWS.d/next/Library/2018-05-05-18-02-24.bpo-20087.lJrvXL.rst
new file mode 100644
index 000000000000..2342cb781926
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2018-05-05-18-02-24.bpo-20087.lJrvXL.rst
@@ -0,0 +1 @@
+Updated alias mapping with glibc 2.27 supported locales.
More information about the Python-checkins
mailing list