Add CJK codecs support as discussed on python-dev. (SF #873597)
Several style fixes are suggested by Martin v. Loewis and
Marc-Andre Lemburg. Thanks!
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
index b304f15..0594171 100644
--- a/Lib/encodings/aliases.py
+++ b/Lib/encodings/aliases.py
@@ -14,12 +14,6 @@
codecs. In addition to these, a few Python specific codec
aliases have also been added.
- About the CJK codec aliases:
-
- The codecs for these encodings are not distributed with the
- Python core, but are included here for reference, since the
- locale module relies on having these aliases available.
-
"""
aliases = {
@@ -41,6 +35,10 @@
'base64' : 'base64_codec',
'base_64' : 'base64_codec',
+ # big5 codec
+ 'big5_tw' : 'big5',
+ 'csbig5' : 'big5',
+
# bz2_codec codec
'bz2' : 'bz2_codec',
@@ -168,9 +166,91 @@
'csibm869' : 'cp869',
'ibm869' : 'cp869',
+ # cp932 codec
+ '932' : 'cp932',
+ 'ms932' : 'cp932',
+ 'mskanji' : 'cp932',
+ 'ms_kanji' : 'cp932',
+
+ # cp949 codec
+ '949' : 'cp949',
+ 'ms949' : 'cp949',
+ 'uhc' : 'cp949',
+
+ # cp950 codec
+ '950' : 'cp950',
+ 'ms950' : 'cp950',
+
+ # euc_jisx0213 codec
+ 'jisx0213' : 'euc_jisx0213',
+ 'eucjisx0213' : 'euc_jisx0213',
+
+ # euc_jp codec
+ 'eucjp' : 'euc_jp',
+ 'ujis' : 'euc_jp',
+ 'u_jis' : 'euc_jp',
+
+ # euc_kr codec
+ 'euckr' : 'euc_kr',
+ 'korean' : 'euc_kr',
+ 'ksc5601' : 'euc_kr',
+ 'ks_c_5601' : 'euc_kr',
+ 'ks_c_5601_1987' : 'euc_kr',
+ 'ksx1001' : 'euc_kr',
+ 'ks_x_1001' : 'euc_kr',
+
+ # gb18030 codec
+ 'gb18030_2000' : 'gb18030',
+
+ # gb2312 codec
+ 'chinese' : 'gb2312',
+ 'csiso58gb231280' : 'gb2312',
+ 'euc_cn' : 'gb2312',
+ 'euccn' : 'gb2312',
+ 'eucgb2312_cn' : 'gb2312',
+ 'gb2312_1980' : 'gb2312',
+ 'gb2312_80' : 'gb2312',
+ 'iso_ir_58' : 'gb2312',
+
+ # gbk codec
+ '936' : 'gbk',
+ 'cp936' : 'gbk',
+ 'ms936' : 'gbk',
+
# hex_codec codec
'hex' : 'hex_codec',
+ # hz codec
+ 'hzgb' : 'hz',
+ 'hz_gb' : 'hz',
+ 'hz_gb_2312' : 'hz',
+
+ # iso2022_jp codec
+ 'csiso2022jp' : 'iso2022_jp',
+ 'iso2022jp' : 'iso2022_jp',
+ 'iso_2022_jp' : 'iso2022_jp',
+
+ # iso2022_jp_1 codec
+ 'iso2022jp_1' : 'iso2022_jp_1',
+ 'iso_2022_jp_1' : 'iso2022_jp_1',
+
+ # iso2022_jp_2 codec
+ 'iso2022jp_2' : 'iso2022_jp_2',
+ 'iso_2022_jp_2' : 'iso2022_jp_2',
+
+ # iso_3022_jp_3 codec
+ 'iso2022jp_3' : 'iso2022_jp_3',
+ 'iso_2022_jp_3' : 'iso2022_jp_3',
+
+ # iso2022_jp_ext codec
+ 'iso2022jp_ext' : 'iso2022_jp_ext',
+ 'iso_2022_jp_ext' : 'iso2022_jp_ext',
+
+ # iso2022_kr codec
+ 'csiso2022kr' : 'iso2022_kr',
+ 'iso2022kr' : 'iso2022_kr',
+ 'iso_2022_kr' : 'iso2022_kr',
+
# iso8859_10 codec
'csisolatin6' : 'iso8859_10',
'iso_8859_10' : 'iso8859_10',
@@ -258,9 +338,9 @@
'l5' : 'iso8859_9',
'latin5' : 'iso8859_9',
- # jis_7 codec
- 'csiso2022jp' : 'jis_7',
- 'iso_2022_jp' : 'jis_7',
+ # johab codec
+ 'cp1361' : 'johab',
+ 'ms1361' : 'johab',
# koi8_r codec
'cskoi8r' : 'koi8_r',
@@ -308,6 +388,17 @@
# rot_13 codec
'rot13' : 'rot_13',
+ # shift_jis codec
+ 'csshiftjis' : 'shift_jis',
+ 'shiftjis' : 'shift_jis',
+ 'sjis' : 'shift_jis',
+ 's_jis' : 'shift_jis',
+
+ # shift_jisx0213 codec
+ 'shiftjisx0213' : 'shift_jisx0213',
+ 'sjisx0213' : 'shift_jisx0213',
+ 's_jisx0213' : 'shift_jisx0213',
+
# tactis codec
'tis260' : 'tactis',