diff options
| author | Marc-André Lemburg <mal@egenix.com> | 2001-01-03 21:29:14 (GMT) |
|---|---|---|
| committer | Marc-André Lemburg <mal@egenix.com> | 2001-01-03 21:29:14 (GMT) |
| commit | a866df806dd0ffd439bbba873ab9f3da7080e0a0 (patch) | |
| tree | dd4b4b62a54e1eb7da6c33e4c578f5b7d78a43f9 /Lib/encodings/iso8859_8.py | |
| parent | b55b7bb3ab1cb0259e3ba2d9acaebbbd1cb78099 (diff) | |
| download | cpython-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_8.py')
| -rw-r--r-- | Lib/encodings/iso8859_8.py | 49 |
1 files changed, 43 insertions, 6 deletions
diff --git a/Lib/encodings/iso8859_8.py b/Lib/encodings/iso8859_8.py index 72b783b..a19aa67 100644 --- a/Lib/encodings/iso8859_8.py +++ b/Lib/encodings/iso8859_8.py @@ -1,9 +1,9 @@ -""" Python Character Mapping Codec generated from '8859-8.TXT'. - +""" Python Character Mapping Codec generated from '8859-8.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. """#" @@ -35,11 +35,43 @@ def getregentry(): ### Decoding Map -decoding_map = { - +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x00a1: None, 0x00aa: 0x00d7, # MULTIPLICATION SIGN - 0x00af: 0x203e, # OVERLINE 0x00ba: 0x00f7, # DIVISION SIGN + 0x00bf: None, + 0x00c0: None, + 0x00c1: None, + 0x00c2: None, + 0x00c3: None, + 0x00c4: None, + 0x00c5: None, + 0x00c6: None, + 0x00c7: None, + 0x00c8: None, + 0x00c9: None, + 0x00ca: None, + 0x00cb: None, + 0x00cc: None, + 0x00cd: None, + 0x00ce: None, + 0x00cf: None, + 0x00d0: None, + 0x00d1: None, + 0x00d2: None, + 0x00d3: None, + 0x00d4: None, + 0x00d5: None, + 0x00d6: None, + 0x00d7: None, + 0x00d8: None, + 0x00d9: None, + 0x00da: None, + 0x00db: None, + 0x00dc: None, + 0x00dd: None, + 0x00de: None, 0x00df: 0x2017, # DOUBLE LOW LINE 0x00e0: 0x05d0, # HEBREW LETTER ALEF 0x00e1: 0x05d1, # HEBREW LETTER BET @@ -68,7 +100,12 @@ decoding_map = { 0x00f8: 0x05e8, # HEBREW LETTER RESH 0x00f9: 0x05e9, # HEBREW LETTER SHIN 0x00fa: 0x05ea, # HEBREW LETTER TAV -} + 0x00fb: None, + 0x00fc: None, + 0x00fd: 0x200e, # LEFT-TO-RIGHT MARK + 0x00fe: 0x200f, # RIGHT-TO-LEFT MARK + 0x00ff: None, +}) ### Encoding Map |