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_3.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_3.py')
| -rw-r--r-- | Lib/encodings/iso8859_3.py | 17 |
1 files changed, 12 insertions, 5 deletions
diff --git a/Lib/encodings/iso8859_3.py b/Lib/encodings/iso8859_3.py index f262767..c2820ad 100644 --- a/Lib/encodings/iso8859_3.py +++ b/Lib/encodings/iso8859_3.py @@ -1,9 +1,9 @@ -""" Python Character Mapping Codec generated from '8859-3.TXT'. - +""" Python Character Mapping Codec generated from '8859-3.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. """#" @@ -35,15 +35,17 @@ def getregentry(): ### Decoding Map -decoding_map = { - +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ 0x00a1: 0x0126, # LATIN CAPITAL LETTER H WITH STROKE 0x00a2: 0x02d8, # BREVE + 0x00a5: None, 0x00a6: 0x0124, # LATIN CAPITAL LETTER H WITH CIRCUMFLEX 0x00a9: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE 0x00aa: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA 0x00ab: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE 0x00ac: 0x0134, # LATIN CAPITAL LETTER J WITH CIRCUMFLEX + 0x00ae: None, 0x00af: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE 0x00b1: 0x0127, # LATIN SMALL LETTER H WITH STROKE 0x00b6: 0x0125, # LATIN SMALL LETTER H WITH CIRCUMFLEX @@ -51,21 +53,26 @@ decoding_map = { 0x00ba: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA 0x00bb: 0x011f, # LATIN SMALL LETTER G WITH BREVE 0x00bc: 0x0135, # LATIN SMALL LETTER J WITH CIRCUMFLEX + 0x00be: None, 0x00bf: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x00c3: None, 0x00c5: 0x010a, # LATIN CAPITAL LETTER C WITH DOT ABOVE 0x00c6: 0x0108, # LATIN CAPITAL LETTER C WITH CIRCUMFLEX + 0x00d0: None, 0x00d5: 0x0120, # LATIN CAPITAL LETTER G WITH DOT ABOVE 0x00d8: 0x011c, # LATIN CAPITAL LETTER G WITH CIRCUMFLEX 0x00dd: 0x016c, # LATIN CAPITAL LETTER U WITH BREVE 0x00de: 0x015c, # LATIN CAPITAL LETTER S WITH CIRCUMFLEX + 0x00e3: None, 0x00e5: 0x010b, # LATIN SMALL LETTER C WITH DOT ABOVE 0x00e6: 0x0109, # LATIN SMALL LETTER C WITH CIRCUMFLEX + 0x00f0: None, 0x00f5: 0x0121, # LATIN SMALL LETTER G WITH DOT ABOVE 0x00f8: 0x011d, # LATIN SMALL LETTER G WITH CIRCUMFLEX 0x00fd: 0x016d, # LATIN SMALL LETTER U WITH BREVE 0x00fe: 0x015d, # LATIN SMALL LETTER S WITH CIRCUMFLEX 0x00ff: 0x02d9, # DOT ABOVE -} +}) ### Encoding Map |