Kaydet (Commit) ad8a1c3f authored tarafından Serhiy Storchaka's avatar Serhiy Storchaka

Issue #22682: Added support for the kz1048 encoding.

üst 0d4df752
...@@ -1162,6 +1162,10 @@ particular, the following variants typically exist: ...@@ -1162,6 +1162,10 @@ particular, the following variants typically exist:
+-----------------+--------------------------------+--------------------------------+ +-----------------+--------------------------------+--------------------------------+
| koi8_u | | Ukrainian | | koi8_u | | Ukrainian |
+-----------------+--------------------------------+--------------------------------+ +-----------------+--------------------------------+--------------------------------+
| kz1048 | kz_1048, strk1048_2002, rk1048 | Kazakh |
| | | |
| | | .. versionadded:: 3.5 |
+-----------------+--------------------------------+--------------------------------+
| mac_cyrillic | maccyrillic | Bulgarian, Byelorussian, | | mac_cyrillic | maccyrillic | Bulgarian, Byelorussian, |
| | | Macedonian, Russian, Serbian | | | | Macedonian, Russian, Serbian |
+-----------------+--------------------------------+--------------------------------+ +-----------------+--------------------------------+--------------------------------+
......
...@@ -231,6 +231,9 @@ Some smaller changes made to the core Python language are: ...@@ -231,6 +231,9 @@ Some smaller changes made to the core Python language are:
* The :option:`-b` option now affects comparisons of :class:`bytes` with * The :option:`-b` option now affects comparisons of :class:`bytes` with
:class:`int`. (Contributed by Serhiy Storchaka in :issue:`23681`) :class:`int`. (Contributed by Serhiy Storchaka in :issue:`23681`)
* New Kazakh :ref:`codec <standard-encodings>` ``kz1048``. (Contributed by
Serhiy Storchaka in :issue:`22682`.)
New Modules New Modules
=========== ===========
......
...@@ -412,6 +412,11 @@ aliases = { ...@@ -412,6 +412,11 @@ aliases = {
# koi8_r codec # koi8_r codec
'cskoi8r' : 'koi8_r', 'cskoi8r' : 'koi8_r',
# kz1048 codec
'kz_1048' : 'kz1048',
'rk1048' : 'kz1048',
'strk1048_2002' : 'kz1048',
# latin_1 codec # latin_1 codec
# #
# Note that the latin_1 codec is implemented internally in C and a # Note that the latin_1 codec is implemented internally in C and a
......
...@@ -700,6 +700,7 @@ locale_encoding_alias = { ...@@ -700,6 +700,7 @@ locale_encoding_alias = {
'utf_8': 'UTF-8', 'utf_8': 'UTF-8',
'koi8_r': 'KOI8-R', 'koi8_r': 'KOI8-R',
'koi8_u': 'KOI8-U', 'koi8_u': 'KOI8-U',
'kz1048': 'RK1048',
'cp1251': 'CP1251', 'cp1251': 'CP1251',
'cp1255': 'CP1255', 'cp1255': 'CP1255',
'cp1256': 'CP1256', 'cp1256': 'CP1256',
......
...@@ -1823,6 +1823,7 @@ all_unicode_encodings = [ ...@@ -1823,6 +1823,7 @@ all_unicode_encodings = [
"johab", "johab",
"koi8_r", "koi8_r",
"koi8_u", "koi8_u",
"kz1048",
"latin_1", "latin_1",
"mac_cyrillic", "mac_cyrillic",
"mac_greek", "mac_greek",
......
...@@ -2081,7 +2081,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -2081,7 +2081,7 @@ class UnicodeTest(string_tests.CommonTest,
'cp863', 'cp865', 'cp866', 'cp1125', 'cp863', 'cp865', 'cp866', 'cp1125',
'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15', 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6', 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1', 'iso8859_7', 'iso8859_9', 'koi8_r', 'kz1048', 'latin_1',
'mac_cyrillic', 'mac_latin2', 'mac_cyrillic', 'mac_latin2',
'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
...@@ -2116,7 +2116,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -2116,7 +2116,7 @@ class UnicodeTest(string_tests.CommonTest,
#'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
#'cp1256', 'cp1257', 'cp1258', #'cp1256', 'cp1257', 'cp1258',
#'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874', #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
#'iso8859_3', 'iso8859_6', 'iso8859_7', #'iso8859_3', 'iso8859_6', 'iso8859_7', 'kz1048',
#'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish', #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
### These fail the round-trip: ### These fail the round-trip:
......
...@@ -704,7 +704,7 @@ class ElementTreeTest(unittest.TestCase): ...@@ -704,7 +704,7 @@ class ElementTreeTest(unittest.TestCase):
'mac-roman', 'mac-turkish', 'mac-roman', 'mac-turkish',
'iso2022-jp', 'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004', 'iso2022-jp', 'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004',
'iso2022-jp-3', 'iso2022-jp-ext', 'iso2022-jp-3', 'iso2022-jp-ext',
'koi8-r', 'koi8-u', 'koi8-r', 'koi8-u', 'kz1048',
'hz', 'ptcp154', 'hz', 'ptcp154',
] ]
for encoding in supported_encodings: for encoding in supported_encodings:
......
...@@ -42,6 +42,8 @@ Core and Builtins ...@@ -42,6 +42,8 @@ Core and Builtins
Library Library
------- -------
- Issue #22682: Added support for the kz1048 encoding.
- Issue #23796: peak and read1 methods of BufferedReader now raise ValueError - Issue #23796: peak and read1 methods of BufferedReader now raise ValueError
if they called on a closed object. Patch by John Hergenroeder. if they called on a closed object. Patch by John Hergenroeder.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment