diff options
| author | Tomaz Solc <tomaz.solc@tablix.org> | 2013-12-11 18:00:10 +0100 |
|---|---|---|
| committer | Tomaz Solc <tomaz.solc@tablix.org> | 2013-12-24 10:19:24 +0100 |
| commit | a31f934d4ff8a9eb39c5926d932233603b894d6d (patch) | |
| tree | e141192825c648d2170c1b8dfbf9ad03ab201a4c /unidecode/x000.py | |
| parent | 6f047e2655bcedd9a5ba4975caf7645e7b37fe8f (diff) | |
| download | unidecode-a31f934d4ff8a9eb39c5926d932233603b894d6d.tar.gz | |
Add some comments for commonly requested changes.
Diffstat (limited to 'unidecode/x000.py')
| -rw-r--r-- | unidecode/x000.py | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/unidecode/x000.py b/unidecode/x000.py index a27148a..c3f8f51 100644 --- a/unidecode/x000.py +++ b/unidecode/x000.py @@ -45,7 +45,10 @@ data = ( ' ', # 0xa0 '!', # 0xa1 'C/', # 0xa2 + +# Not "GBP" - Pound Sign is used for more than just British Pounds. 'PS', # 0xa3 + '$?', # 0xa4 'Y=', # 0xa5 '|', # 0xa6 @@ -60,8 +63,11 @@ data = ( '-', # 0xaf 'deg', # 0xb0 '+-', # 0xb1 + +# These might be combined with other superscript digits (u+2070 - u+2079) '2', # 0xb2 '3', # 0xb3 + '\'', # 0xb4 'u', # 0xb5 'P', # 0xb6 @@ -78,7 +84,10 @@ data = ( 'A', # 0xc1 'A', # 0xc2 'A', # 0xc3 + +# Not "AE" - used in languages other than German 'A', # 0xc4 + 'A', # 0xc5 'AE', # 0xc6 'C', # 0xc7 @@ -96,13 +105,19 @@ data = ( 'O', # 0xd3 'O', # 0xd4 'O', # 0xd5 + +# Not "OE" - used in languages other than German 'O', # 0xd6 + 'x', # 0xd7 'O', # 0xd8 'U', # 0xd9 'U', # 0xda 'U', # 0xdb + +# Not "UE" - used in languages other than German 'U', # 0xdc + 'Y', # 0xdd 'Th', # 0xde 'ss', # 0xdf @@ -110,7 +125,10 @@ data = ( 'a', # 0xe1 'a', # 0xe2 'a', # 0xe3 + +# Not "ae" - used in languages other than German 'a', # 0xe4 + 'a', # 0xe5 'ae', # 0xe6 'c', # 0xe7 @@ -128,13 +146,19 @@ data = ( 'o', # 0xf3 'o', # 0xf4 'o', # 0xf5 + +# Not "oe" - used in languages other than German 'o', # 0xf6 + '/', # 0xf7 'o', # 0xf8 'u', # 0xf9 'u', # 0xfa 'u', # 0xfb + +# Not "ue" - used in languages other than German 'u', # 0xfc + 'y', # 0xfd 'th', # 0xfe 'y', # 0xff |
