diff --git a/Lib/locale.py b/Lib/locale.py index 18079e73ad6..876d2eb1e12 100644 --- a/Lib/locale.py +++ b/Lib/locale.py @@ -846,6 +846,16 @@ for k, v in sorted(locale_encoding_alias.items()): # # 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@valencia' -> 'ca_ES.ISO8859-15@valencia' to 'ca_ES.UTF-8@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', @@ -856,10 +866,13 @@ locale_alias = { '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', @@ -877,6 +890,7 @@ locale_alias = { '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', @@ -888,6 +902,7 @@ locale_alias = { '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@latin': 'be_BY.UTF-8@latin', 'be_bg.utf8': 'bg_BG.UTF-8', @@ -898,13 +913,17 @@ locale_alias = { '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', 'bo_in': 'bo_IN.UTF-8', 'bokmal': 'nb_NO.ISO8859-1', 'bokm\xe5l': 'nb_NO.ISO8859-1', + 'bokm\xef\xbf\xbd': 'nb_NO.ISO8859-1', 'br': 'br_FR.ISO8859-1', 'br_fr': 'br_FR.ISO8859-1', 'brx_in': 'brx_IN.UTF-8', @@ -923,13 +942,17 @@ locale_alias = { 'ca': 'ca_ES.ISO8859-1', 'ca_ad': 'ca_AD.ISO8859-1', 'ca_es': 'ca_ES.ISO8859-1', - 'ca_es@valencia': 'ca_ES.ISO8859-15@valencia', + 'ca_es@valencia': 'ca_ES.UTF-8@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', @@ -951,6 +974,7 @@ locale_alias = { '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', @@ -977,10 +1001,12 @@ locale_alias = { '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', @@ -991,6 +1017,7 @@ locale_alias = { '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', @@ -1045,6 +1072,7 @@ locale_alias = { 'fr_fr': 'fr_FR.ISO8859-1', 'fr_lu': 'fr_LU.ISO8859-1', 'fran\xe7ais': 'fr_FR.ISO8859-1', + 'fran\xef\xbf\xbdis': 'fr_FR.ISO8859-1', 'fre_fr': 'fr_FR.ISO8859-1', 'french': 'fr_FR.ISO8859-1', 'french.iso88591': 'fr_CH.ISO8859-1', @@ -1071,12 +1099,14 @@ locale_alias = { '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', @@ -1131,7 +1161,8 @@ locale_alias = { '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', @@ -1157,6 +1188,7 @@ locale_alias = { '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', @@ -1166,13 +1198,18 @@ locale_alias = { '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', @@ -1186,7 +1223,7 @@ locale_alias = { 'mt': 'mt_MT.ISO8859-3', 'mt_mt': 'mt_MT.ISO8859-3', 'my_mm': 'my_MM.UTF-8', - 'nan_tw@latin': 'nan_TW.UTF-8@latin', + 'nan_tw': 'nan_TW.UTF-8', 'nb': 'nb_NO.ISO8859-1', 'nb_no': 'nb_NO.ISO8859-1', 'nds_de': 'nds_DE.UTF-8', @@ -1225,6 +1262,8 @@ locale_alias = { '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', @@ -1243,6 +1282,8 @@ locale_alias = { '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', @@ -1250,7 +1291,7 @@ locale_alias = { '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', @@ -1262,12 +1303,14 @@ locale_alias = { 'sd_pk': 'sd_PK.UTF-8', 'se_no': 'se_NO.UTF-8', 'serbocroatian': 'sr_RS.UTF-8@latin', + 'sgs_lt': 'sgs_LT.UTF-8', 'sh': 'sr_RS.UTF-8@latin', 'sh_ba.iso88592@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@latin', + 'shn_mm': 'shn_MM.UTF-8', 'shs_ca': 'shs_CA.UTF-8', 'si': 'si_LK.UTF-8', 'si_lk': 'si_LK.UTF-8', @@ -1281,6 +1324,7 @@ locale_alias = { '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', @@ -1327,6 +1371,7 @@ locale_alias = { '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', @@ -1336,6 +1381,7 @@ locale_alias = { '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', @@ -1344,6 +1390,8 @@ locale_alias = { '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', @@ -1386,6 +1434,7 @@ locale_alias = { '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 d93b3ad048b..e2c2178ae6c 100644 --- a/Lib/test/test_locale.py +++ b/Lib/test/test_locale.py @@ -441,7 +441,7 @@ class NormalizeTest(unittest.TestCase): def test_valencia_modifier(self): self.check('ca_ES.UTF-8@valencia', 'ca_ES.UTF-8@valencia') - self.check('ca_ES@valencia', 'ca_ES.ISO8859-15@valencia') + self.check('ca_ES@valencia', 'ca_ES.UTF-8@valencia') self.check('ca@valencia', 'ca_ES.ISO8859-1@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 00000000000..2342cb78192 --- /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.