summaryrefslogtreecommitdiffstats
path: root/Lib/encodings/iso8859_7.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/iso8859_7.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/iso8859_7.py')
-rw-r--r--Lib/encodings/iso8859_7.py16
1 files changed, 11 insertions, 5 deletions
diff --git a/Lib/encodings/iso8859_7.py b/Lib/encodings/iso8859_7.py
index c847610..48f1bd5 100644
--- a/Lib/encodings/iso8859_7.py
+++ b/Lib/encodings/iso8859_7.py
@@ -1,9 +1,9 @@
-""" Python Character Mapping Codec generated from '8859-7.TXT'.
-
+""" Python Character Mapping Codec generated from '8859-7.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.
"""#"
@@ -35,10 +35,14 @@ def getregentry():
### Decoding Map
-decoding_map = {
-
+decoding_map = codecs.make_identity_dict(range(256))
+decoding_map.update({
0x00a1: 0x2018, # LEFT SINGLE QUOTATION MARK
0x00a2: 0x2019, # RIGHT SINGLE QUOTATION MARK
+ 0x00a4: None,
+ 0x00a5: None,
+ 0x00aa: None,
+ 0x00ae: None,
0x00af: 0x2015, # HORIZONTAL BAR
0x00b4: 0x0384, # GREEK TONOS
0x00b5: 0x0385, # GREEK DIALYTIKA TONOS
@@ -67,6 +71,7 @@ decoding_map = {
0x00cf: 0x039f, # GREEK CAPITAL LETTER OMICRON
0x00d0: 0x03a0, # GREEK CAPITAL LETTER PI
0x00d1: 0x03a1, # GREEK CAPITAL LETTER RHO
+ 0x00d2: None,
0x00d3: 0x03a3, # GREEK CAPITAL LETTER SIGMA
0x00d4: 0x03a4, # GREEK CAPITAL LETTER TAU
0x00d5: 0x03a5, # GREEK CAPITAL LETTER UPSILON
@@ -111,7 +116,8 @@ decoding_map = {
0x00fc: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
0x00fd: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
0x00fe: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
-}
+ 0x00ff: None,
+})
### Encoding Map