gh-102388: Add windows_31j to aliases for cp932 codec

moriyama · moriyama · commit 80c8f245ffde · 2023-03-03T07:32:17.000Z
The charset name "Windows-31J" is registered in the IANA Charset Registry[1] and is implemented in Python as the cp932 codec. This commit adds windows_31j to the aliases of cp932. [1] https://www.iana.org/assignments/charset-reg/windows-31J Signed-off-by: Masayuki Moriyama <masayuki.moriyama@miraclelinux.com>
diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst
@@ -1126,7 +1126,8 @@ particular, the following variants typically exist:
 +-----------------+--------------------------------+--------------------------------+
 | cp875           |                                | Greek                          |
 +-----------------+--------------------------------+--------------------------------+
-| cp932           | 932, ms932, mskanji, ms-kanji  | Japanese                       |
+| cp932           | 932, ms932, mskanji, ms-kanji, | Japanese                       |
+|                 | windows_31j                    |                                |
 +-----------------+--------------------------------+--------------------------------+
 | cp949           | 949, ms949, uhc                | Korean                         |
 +-----------------+--------------------------------+--------------------------------+
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
@@ -209,6 +209,7 @@
     'ms932'              : 'cp932',
     'mskanji'            : 'cp932',
     'ms_kanji'           : 'cp932',
+    'windows_31j'        : 'cp932',
 
     # cp949 codec
     '949'                : 'cp949',
