diff options
| author | Cédric Bonhomme <kimble.mandel@gmail.com> | 2012-12-30 21:46:32 +0100 |
|---|---|---|
| committer | Cédric Bonhomme <kimble.mandel@gmail.com> | 2012-12-30 21:46:32 +0100 |
| commit | d73f2d6ae43a4bcafdbcc2cb24503001ef41769e (patch) | |
| tree | 706c80efb36aff0912aa5045dd596683badab46c /source | |
| parent | Removed useless print(). (diff) | |
| download | newspipe-d73f2d6ae43a4bcafdbcc2cb24503001ef41769e.tar.gz newspipe-d73f2d6ae43a4bcafdbcc2cb24503001ef41769e.tar.bz2 newspipe-d73f2d6ae43a4bcafdbcc2cb24503001ef41769e.zip | |
Removed strip_accents function.
Diffstat (limited to 'source')
| -rwxr-xr-x | source/utils.py | 14 |
1 files changed, 0 insertions, 14 deletions
diff --git a/source/utils.py b/source/utils.py index f6cd93d1..b37ecb8b 100755 --- a/source/utils.py +++ b/source/utils.py @@ -116,19 +116,6 @@ def unescape(text): return text # leave as is return re.sub("&#?\w+;", fixup, text) -def not_combining(char): - return unicodedata.category(char) != 'Mn' - -def strip_accents(text, encoding): - """ - Strip accents. - - >>> print strip_accents("déjà", "utf-8") - deja - """ - unicode_text= unicodedata.normalize('NFD', text) - return filter(not_combining, unicode_text) - def normalize_filename(name): """ Normalize a file name. @@ -137,7 +124,6 @@ def normalize_filename(name): file_name = re.sub("[\s.]", "_", file_name) file_name = file_name.strip('_') file_name = file_name.strip('.') - #file_name = strip_accents(file_name, "utf-8") return os.path.normpath(file_name) def load_stop_words(): |