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

update comments in wordfreq_builder.config; remove unused 'version'

Browse Source
This commit is contained in:
Rob Speer 2015-09-08 16:15:08 -04:00
parent 0ab23f8a28
commit bc323eccaf
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
wordfreq_builder/wordfreq_builder/config.py
View File

@ -1,19 +1,17 @@
import os
CONFIG = {
'version': '1.0b',
# data_dir is a relative or absolute path to where the wordlist data
# is stored
'data_dir': 'data',
'sources': {
# A list of language codes (possibly un-standardized) that we'll
# look up in filenames for these various data sources.
# A list of language codes that we'll look up in filenames for these
# various data sources.
#
# Consider adding:
# 'th' when we get tokenization for it
# 'hi' when we stop messing up its tokenization
# 'tl' with one more data source
# 'sv' because its data sources are ready
'twitter': [
'ar', 'de', 'el', 'en', 'es', 'fr', 'id', 'it', 'ja', 'ko', 'ms', 'nl',
'pl', 'pt', 'ru', 'sv', 'tr'