Issue #19668: Added support for the cp1125 encoding.

2024-10-16 12:18:50 +00:00 · 2013-11-23 18:52:23 +02:00 · 2013-11-23 18:52:23 +02:00 · be0c3250b1
parent e50240c504
commit be0c3250b1
7 changed files with 44 additions and 31 deletions
--- a/Doc/library/codecs.rst
+++ b/Doc/library/codecs.rst
@ -1027,6 +1027,10 @@ particular, the following variants typically exist:
 +-----------------+--------------------------------+--------------------------------+
 | cp1026          | ibm1026                        | Turkish                        |
 +-----------------+--------------------------------+--------------------------------+
+| cp1125          | 1125, ibm1125, cp866u, ruscii  | Ukrainian                      |
+|                 |                                |                                |
+|                 |                                | .. versionadded:: 3.4          |
+-----------------+--------------------------------+--------------------------------+
 | cp1140          | ibm1140                        | Western Europe                 |
 +-----------------+--------------------------------+--------------------------------+
 | cp1250          | windows-1250                   | Central and Eastern Europe     |
--- a/Lib/encodings/aliases.py
+++ b/Lib/encodings/aliases.py
@ -63,6 +63,12 @@
    'csibm1026'          : 'cp1026',
    'ibm1026'            : 'cp1026',

+    # cp1125 codec
+    '1125'                : 'cp1125',
+    'ibm1125'             : 'cp1125',
+    'cp866u'              : 'cp1125',
+    'ruscii'              : 'cp1125',
+
    # cp1140 codec
    '1140'               : 'cp1140',
    'ibm1140'            : 'cp1140',
--- a/Lib/encodings/cp866.py
+++ b/Lib/encodings/cp866.py
@ -1,4 +1,4 @@
-""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP866.TXT' with gencodec.py.
+""" Python Character Mapping Codec for CP1125

 """#"

@ -32,7 +32,7 @@ class StreamReader(Codec,codecs.StreamReader):

 def getregentry():
    return codecs.CodecInfo(
-        name='cp866',
+        name='cp1125',
        encode=Codec().encode,
        decode=Codec().decode,
        incrementalencoder=IncrementalEncoder,
@ -159,14 +159,14 @@ def getregentry():
    0x00ef: 0x044f,     #  CYRILLIC SMALL LETTER YA
    0x00f0: 0x0401,     #  CYRILLIC CAPITAL LETTER IO
    0x00f1: 0x0451,     #  CYRILLIC SMALL LETTER IO
-    0x00f2: 0x0404,     #  CYRILLIC CAPITAL LETTER UKRAINIAN IE
-    0x00f3: 0x0454,     #  CYRILLIC SMALL LETTER UKRAINIAN IE
-    0x00f4: 0x0407,     #  CYRILLIC CAPITAL LETTER YI
-    0x00f5: 0x0457,     #  CYRILLIC SMALL LETTER YI
-    0x00f6: 0x040e,     #  CYRILLIC CAPITAL LETTER SHORT U
-    0x00f7: 0x045e,     #  CYRILLIC SMALL LETTER SHORT U
-    0x00f8: 0x00b0,     #  DEGREE SIGN
-    0x00f9: 0x2219,     #  BULLET OPERATOR
+    0x00f2: 0x0490,     #  CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+    0x00f3: 0x0491,     #  CYRILLIC SMALL LETTER GHE WITH UPTURN
+    0x00f4: 0x0404,     #  CYRILLIC CAPITAL LETTER UKRAINIAN IE
+    0x00f5: 0x0454,     #  CYRILLIC SMALL LETTER UKRAINIAN IE
+    0x00f6: 0x0406,     #  CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+    0x00f7: 0x0456,     #  CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+    0x00f8: 0x0407,     #  CYRILLIC CAPITAL LETTER YI
+    0x00f9: 0x0457,     #  CYRILLIC SMALL LETTER YI
    0x00fa: 0x00b7,     #  MIDDLE DOT
    0x00fb: 0x221a,     #  SQUARE ROOT
    0x00fc: 0x2116,     #  NUMERO SIGN
@ -420,14 +420,14 @@ def getregentry():
    '\u044f'   #  0x00ef -> CYRILLIC SMALL LETTER YA
    '\u0401'   #  0x00f0 -> CYRILLIC CAPITAL LETTER IO
    '\u0451'   #  0x00f1 -> CYRILLIC SMALL LETTER IO
-    '\u0404'   #  0x00f2 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
-    '\u0454'   #  0x00f3 -> CYRILLIC SMALL LETTER UKRAINIAN IE
-    '\u0407'   #  0x00f4 -> CYRILLIC CAPITAL LETTER YI
-    '\u0457'   #  0x00f5 -> CYRILLIC SMALL LETTER YI
-    '\u040e'   #  0x00f6 -> CYRILLIC CAPITAL LETTER SHORT U
-    '\u045e'   #  0x00f7 -> CYRILLIC SMALL LETTER SHORT U
-    '\xb0'     #  0x00f8 -> DEGREE SIGN
-    '\u2219'   #  0x00f9 -> BULLET OPERATOR
+    '\u0490'   #  0x00f2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+    '\u0491'   #  0x00f3 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
+    '\u0404'   #  0x00f4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
+    '\u0454'   #  0x00f5 -> CYRILLIC SMALL LETTER UKRAINIAN IE
+    '\u0406'   #  0x00f6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+    '\u0456'   #  0x00f7 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+    '\u0407'   #  0x00f8 -> CYRILLIC CAPITAL LETTER YI
+    '\u0457'   #  0x00f9 -> CYRILLIC SMALL LETTER YI
    '\xb7'     #  0x00fa -> MIDDLE DOT
    '\u221a'   #  0x00fb -> SQUARE ROOT
    '\u2116'   #  0x00fc -> NUMERO SIGN
@ -569,12 +569,11 @@ def getregentry():
    0x007f: 0x007f,     #  DELETE
    0x00a0: 0x00ff,     #  NO-BREAK SPACE
    0x00a4: 0x00fd,     #  CURRENCY SIGN
-    0x00b0: 0x00f8,     #  DEGREE SIGN
    0x00b7: 0x00fa,     #  MIDDLE DOT
    0x0401: 0x00f0,     #  CYRILLIC CAPITAL LETTER IO
-    0x0404: 0x00f2,     #  CYRILLIC CAPITAL LETTER UKRAINIAN IE
-    0x0407: 0x00f4,     #  CYRILLIC CAPITAL LETTER YI
-    0x040e: 0x00f6,     #  CYRILLIC CAPITAL LETTER SHORT U
+    0x0404: 0x00f4,     #  CYRILLIC CAPITAL LETTER UKRAINIAN IE
+    0x0406: 0x00f6,     #  CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
+    0x0407: 0x00f8,     #  CYRILLIC CAPITAL LETTER YI
    0x0410: 0x0080,     #  CYRILLIC CAPITAL LETTER A
    0x0411: 0x0081,     #  CYRILLIC CAPITAL LETTER BE
    0x0412: 0x0082,     #  CYRILLIC CAPITAL LETTER VE
@ -640,11 +639,12 @@ def getregentry():
    0x044e: 0x00ee,     #  CYRILLIC SMALL LETTER YU
    0x044f: 0x00ef,     #  CYRILLIC SMALL LETTER YA
    0x0451: 0x00f1,     #  CYRILLIC SMALL LETTER IO
-    0x0454: 0x00f3,     #  CYRILLIC SMALL LETTER UKRAINIAN IE
-    0x0457: 0x00f5,     #  CYRILLIC SMALL LETTER YI
-    0x045e: 0x00f7,     #  CYRILLIC SMALL LETTER SHORT U
+    0x0454: 0x00f5,     #  CYRILLIC SMALL LETTER UKRAINIAN IE
+    0x0456: 0x00f7,     #  CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
+    0x0457: 0x00f9,     #  CYRILLIC SMALL LETTER YI
+    0x0490: 0x00f2,     #  CYRILLIC CAPITAL LETTER GHE WITH UPTURN
+    0x0491: 0x00f3,     #  CYRILLIC SMALL LETTER GHE WITH UPTURN
    0x2116: 0x00fc,     #  NUMERO SIGN
-    0x2219: 0x00f9,     #  BULLET OPERATOR
    0x221a: 0x00fb,     #  SQUARE ROOT
    0x2500: 0x00c4,     #  BOX DRAWINGS LIGHT HORIZONTAL
    0x2502: 0x00b3,     #  BOX DRAWINGS LIGHT VERTICAL
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@ -1602,6 +1602,7 @@ def test_basic(self):
    "cp037",
    "cp1006",
    "cp1026",
+    "cp1125",
    "cp1140",
    "cp1250",
    "cp1251",
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@ -1834,7 +1834,7 @@ def test_codecs_charmap(self):
            'cp037', 'cp1026', 'cp273',
            'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
            'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
-            'cp863', 'cp865', 'cp866',
+            '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',
@ -1862,7 +1862,7 @@ def test_codecs_charmap(self):
            'cp037', 'cp1026', 'cp273',
            'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
            'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
-            'cp863', 'cp865', 'cp866',
+            'cp863', 'cp865', 'cp866', 'cp1125',
            'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
            'iso8859_2', 'iso8859_4', 'iso8859_5',
            'iso8859_9', 'koi8_r', 'latin_1',
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@ -692,9 +692,9 @@ def bxml(encoding):
            'iso8859-13', 'iso8859-14', 'iso8859-15', 'iso8859-16',
            'cp437', 'cp720', 'cp737', 'cp775', 'cp850', 'cp852',
            'cp855', 'cp856', 'cp857', 'cp858', 'cp860', 'cp861', 'cp862',
-            'cp863', 'cp865', 'cp866', 'cp869', 'cp874', 'cp1006', 'cp1250',
-            'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', 'cp1256',
-            'cp1257', 'cp1258',
+            'cp863', 'cp865', 'cp866', 'cp869', 'cp874', 'cp1006', 'cp1125',
+            'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
+            'cp1256', 'cp1257', 'cp1258',
            'mac-cyrillic', 'mac-greek', 'mac-iceland', 'mac-latin2',
            'mac-roman', 'mac-turkish',
            'iso2022-jp', 'iso2022-jp-1', 'iso2022-jp-2', 'iso2022-jp-2004',
--- a/Misc/NEWS
+++ b/Misc/NEWS
@ -68,6 +68,8 @@ Core and Builtins
 Library
 -------

+- Issue #19668: Added support for the cp1125 encoding.
+
 - Issue #19689: Add ssl.create_default_context() factory function. It creates
  a new SSLContext object with secure default settings.