iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

remove Hangul fillers that confuse cld2

Browse Source 
Former-commit-id: 140ca6c050
This commit is contained in:
Robyn Speer 2015-08-24 17:10:01 -04:00
parent 3674d35501
commit 4ec128adae
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
wordfreq_builder/wordfreq_builder/ninja.py
View File

@ -123,7 +123,6 @@ def google_books_deps(dirname_in):
def twitter_deps(input_filename, slice_prefix, combined_prefix, slices, def twitter_deps(input_filename, slice_prefix, combined_prefix, slices,
languages): languages):
lines = [] lines = []
slice_files = ['{prefix}.part{num:0>2d}'.format(prefix=slice_prefix, slice_files = ['{prefix}.part{num:0>2d}'.format(prefix=slice_prefix,

5
wordfreq_builder/wordfreq_builder/tokenizers.py
View File

@ -11,7 +11,10 @@ CLD2_BAD_CHAR_RANGE = "[%s]" % "".join(
'\x0e-\x1f', '\x0e-\x1f',
'\x7f-\x9f', '\x7f-\x9f',
'\ud800-\udfff', '\ud800-\udfff',
'\ufdd0-\ufdef' '\ufdd0-\ufdef',
'\N{HANGUL FILLER}',
'\N{HANGUL CHOSEONG FILLER}',
'\N{HANGUL JUNGSEONG FILLER}'
] + ] +
[chr(65534+65536*x+y) for x in range(17) for y in range(2)] [chr(65534+65536*x+y) for x in range(17) for y in range(2)]
) )