explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-30 23:47:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Check if full string is found in lang classes first

Browse Source 
This allows users to set arbitrary strings. (Otherwise, custom lang
class "my_custom_class" would always load Burmese "my" tokenizer if one
was available.)
This commit is contained in:
ines 2017-04-16 22:14:38 +02:00
parent 13d30b6c01
commit 5c5f8c0a72
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/util.py
View File

@ -20,9 +20,11 @@ def set_lang_class(name, cls):
def get_lang_class(name): def get_lang_class(name):
if name in LANGUAGES:
return LANGUAGES[name]
lang = re.split('[^a-zA-Z0-9]', name, 1)[0] lang = re.split('[^a-zA-Z0-9]', name, 1)[0]
if lang not in LANGUAGES: if lang not in LANGUAGES:
raise RuntimeError('Language not supported: %s' % lang) raise RuntimeError('Language not supported: %s' % name)
return LANGUAGES[lang] return LANGUAGES[lang]