summaryrefslogtreecommitdiffstats
path: root/Lib/encodings/cp855.py
diff options
context:
space:
mode:
authorMarc-André Lemburg <mal@egenix.com>2001-01-03 21:29:14 (GMT)
committerMarc-André Lemburg <mal@egenix.com>2001-01-03 21:29:14 (GMT)
commita866df806dd0ffd439bbba873ab9f3da7080e0a0 (patch)
treedd4b4b62a54e1eb7da6c33e4c578f5b7d78a43f9 /Lib/encodings/cp855.py
parentb55b7bb3ab1cb0259e3ba2d9acaebbbd1cb78099 (diff)
downloadcpython-a866df806dd0ffd439bbba873ab9f3da7080e0a0.zip
cpython-a866df806dd0ffd439bbba873ab9f3da7080e0a0.tar.gz
cpython-a866df806dd0ffd439bbba873ab9f3da7080e0a0.tar.bz2
This patch changes the default behaviour of the builtin charmap
codec to not apply Latin-1 mappings for keys which are not found in the mapping dictionaries, but instead treat them as undefined mappings. The patch was originally written by Martin v. Loewis with some additional (cosmetic) changes and an updated test script by Marc-Andre Lemburg. The standard codecs were recreated from the most current files available at the Unicode.org site using the Tools/scripts/gencodec.py tool. This patch closes the bugs #116285 and #119960.
Diffstat (limited to 'Lib/encodings/cp855.py')
-rw-r--r--Lib/encodings/cp855.py10
1 files changed, 5 insertions, 5 deletions
diff --git a/Lib/encodings/cp855.py b/Lib/encodings/cp855.py
index c967bcf..c9e7168 100644
--- a/Lib/encodings/cp855.py
+++ b/Lib/encodings/cp855.py
@@ -1,9 +1,9 @@
-""" Python Character Mapping Codec generated from 'CP855.TXT'.
-
+""" Python Character Mapping Codec generated from 'CP855.TXT' with gencodec.py.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
+(c) Copyright 2000 Guido van Rossum.
"""#"
@@ -35,8 +35,8 @@ def getregentry():
### Decoding Map
-decoding_map = {
-
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE
0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE
0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE
@@ -165,7 +165,7 @@ decoding_map = {
0x00fd: 0x00a7, # SECTION SIGN
0x00fe: 0x25a0, # BLACK SQUARE
0x00ff: 0x00a0, # NO-BREAK SPACE
-}
+})
### Encoding Map