From ad8a1c3fb27aa3e240540888b6062597dce36fe8 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Tue, 12 May 2015 23:16:55 +0300 Subject: [PATCH] Issue #22682: Added support for the kz1048 encoding. --- Doc/library/codecs.rst | 4 ++++ Doc/whatsnew/3.5.rst | 3 +++ Lib/encodings/aliases.py | 5 +++++ Lib/locale.py | 1 + Lib/test/test_codecs.py | 1 + Lib/test/test_unicode.py | 4 ++-- Lib/test/test_xml_etree.py | 2 +- Misc/NEWS | 2 ++ 8 files changed, 19 insertions(+), 3 deletions(-) diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst index 0430cb92a44..b3bd6af5302 100644 --- a/Doc/library/codecs.rst +++ b/Doc/library/codecs.rst @@ -1162,6 +1162,10 @@ particular, the following variants typically exist: +-----------------+--------------------------------+--------------------------------+ | koi8_u | | Ukrainian | +-----------------+--------------------------------+--------------------------------+ +| kz1048 | kz_1048, strk1048_2002, rk1048 | Kazakh | +| | | | +| | | .. versionadded:: 3.5 | ++-----------------+--------------------------------+--------------------------------+ | mac_cyrillic | maccyrillic | Bulgarian, Byelorussian, | | | | Macedonian, Russian, Serbian | +-----------------+--------------------------------+--------------------------------+ diff --git a/Doc/whatsnew/3.5.rst b/Doc/whatsnew/3.5.rst index 90418119ab1..412d9b08a8e 100644 --- a/Doc/whatsnew/3.5.rst +++ b/Doc/whatsnew/3.5.rst @@ -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 :class:`int`. (Contributed by Serhiy Storchaka in :issue:`23681`) +* New Kazakh :ref:`codec ` ``kz1048``. (Contributed by + Serhiy Storchaka in :issue:`22682`.) + New Modules =========== diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py index 4cbaadea3ee..67c828d639e 100644 --- a/Lib/encodings/aliases.py +++ b/Lib/encodings/aliases.py @@ -412,6 +412,11 @@ aliases = { # koi8_r codec 'cskoi8r' : 'koi8_r', + # kz1048 codec + 'kz_1048' : 'kz1048', + 'rk1048' : 'kz1048', + 'strk1048_2002' : 'kz1048', + # latin_1 codec # # Note that the latin_1 codec is implemented internally in C and a diff --git a/Lib/locale.py b/Lib/locale.py index 6b9eb3a09bc..c24f73167eb 100644 --- a/Lib/locale.py +++ b/Lib/locale.py @@ -700,6 +700,7 @@ locale_encoding_alias = { 'utf_8': 'UTF-8', 'koi8_r': 'KOI8-R', 'koi8_u': 'KOI8-U', + 'kz1048': 'RK1048', 'cp1251': 'CP1251', 'cp1255': 'CP1255', 'cp1256': 'CP1256', diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index fb3db77a92e..e7e189d3a0c 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -1823,6 +1823,7 @@ all_unicode_encodings = [ "johab", "koi8_r", "koi8_u", + "kz1048", "latin_1", "mac_cyrillic", "mac_greek", diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 2773fe5373e..b1d453b4785 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -2081,7 +2081,7 @@ class UnicodeTest(string_tests.CommonTest, 'cp863', 'cp865', 'cp866', 'cp1125', 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15', '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', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', @@ -2116,7 +2116,7 @@ class UnicodeTest(string_tests.CommonTest, #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', #'cp1256', 'cp1257', 'cp1258', #'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', ### These fail the round-trip: diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py index d3c0da081d1..5e638894819 100644 --- a/Lib/test/test_xml_etree.py +++ b/Lib/test/test_xml_etree.py @@ -704,7 +704,7 @@ class ElementTreeTest(unittest.TestCase): 'mac-roman', 'mac-turkish', 'iso2022-jp', 'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004', 'iso2022-jp-3', 'iso2022-jp-ext', - 'koi8-r', 'koi8-u', + 'koi8-r', 'koi8-u', 'kz1048', 'hz', 'ptcp154', ] for encoding in supported_encodings: diff --git a/Misc/NEWS b/Misc/NEWS index 2aa61d0db6c..a46e80a926f 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -42,6 +42,8 @@ Core and Builtins Library ------- +- Issue #22682: Added support for the kz1048 encoding. + - Issue #23796: peak and read1 methods of BufferedReader now raise ValueError if they called on a closed object. Patch by John Hergenroeder.