#8016: add the CP858 codec (approved by Benjamin). (Also add CP720 to the…

#8016: add the CP858 codec (approved by Benjamin).  (Also add CP720 to the tests, it was missing there.)

Doc/library/codecs.rst

@@ -925,6 +925,8 @@ particular, the following variants typically exist:
 +-----------------+--------------------------------+--------------------------------+
 | cp857           | 857, IBM857                    | Turkish                        |
 +-----------------+--------------------------------+--------------------------------+
+| cp858           | 858, IBM858                    | Western Europe                 |
++-----------------+--------------------------------+--------------------------------+
 | cp860           | 860, IBM860                    | Portuguese                     |
 +-----------------+--------------------------------+--------------------------------+
 | cp861           | 861, CP-IS, IBM861             | Icelandic                      |

Lib/encodings/aliases.py

@@ -146,6 +146,11 @@ aliases = {
     'csibm857'           : 'cp857',
     'ibm857'             : 'cp857',
 
+    # cp858 codec
+    '858'                : 'cp858',
+    'csibm858'           : 'cp858',
+    'ibm858'             : 'cp858',
+
     # cp860 codec
     '860'                : 'cp860',
     'csibm860'           : 'cp860',

Lib/test/test_codecs.py

@@ -1190,6 +1190,7 @@ all_unicode_encodings = [
     "cp424",
     "cp437",
     "cp500",
+    "cp720",
     "cp737",
     "cp775",
     "cp850",
@@ -1197,6 +1198,7 @@ all_unicode_encodings = [
     "cp855",
     "cp856",
     "cp857",
+    "cp858",
     "cp860",
     "cp861",
     "cp862",

Lib/test/test_unicode.py

@@ -700,8 +700,8 @@ class UnicodeTest(
         s = ''.join(map(chr, xrange(128)))
         for encoding in (
             'cp037', 'cp1026',
-            'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
-            'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
+            'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
+            'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
             'cp863', 'cp865', 'cp866',
             'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
             'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
@@ -728,8 +728,8 @@ class UnicodeTest(
         s = ''.join(map(chr, xrange(128, 256)))
         for encoding in (
             'cp037', 'cp1026',
-            'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
-            'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
+            'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
+            'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
             'cp863', 'cp865', 'cp866',
             'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
             'iso8859_2', 'iso8859_4', 'iso8859_5',

Misc/NEWS

@@ -29,6 +29,8 @@ C-API
 Library
 -------
 
+- Issue #8016: Add the CP858 codec.
+
 - Issue #3924: Ignore cookies with invalid "version" field in cookielib.
 
 - Issue #6268: Fix seek() method of codecs.open(), don't read or write the BOM