iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-26 02:28:50 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #6 from LuminosoInsight/code-review-leftovers

Browse Source 
Code review leftovers
This commit is contained in:
Andrew Lin 2015-07-07 19:39:44 -04:00
commit 30de0ff17f
1 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
wordfreq_builder/wordfreq_builder/config.py
View File

@ -50,10 +50,17 @@ CONFIG = {
def data_filename(filename): def data_filename(filename):
"""
Convert a relative filename to a path inside the configured data_dir.
"""
return os.path.join(CONFIG['data_dir'], filename) return os.path.join(CONFIG['data_dir'], filename)
def wordlist_filename(source, language, extension='txt'): def wordlist_filename(source, language, extension='txt'):
"""
Get the path where a particular built wordlist should go, parameterized by
its language and its file extension.
"""
path = CONFIG['wordlist_paths'][source].format( path = CONFIG['wordlist_paths'][source].format(
lang=language, ext=extension lang=language, ext=extension
) )
@ -64,11 +71,15 @@ def source_names(language):
""" """
Get the names of data sources that supply data for the given language. Get the names of data sources that supply data for the given language.
""" """
return sorted([key for key in CONFIG['sources'] return sorted(key for key in CONFIG['sources']
if language in CONFIG['sources'][key]]) if language in CONFIG['sources'][key])
def all_languages(): def all_languages():
"""
Get all languages that should have their data built, which is those that
are supported by at least `min_sources` sources.
"""
languages = set() languages = set()
for langlist in CONFIG['sources'].values(): for langlist in CONFIG['sources'].values():
languages |= set(langlist) languages |= set(langlist)