explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add link for Finnish model

Browse Source
This commit is contained in:
Matthew Honnibal 2015-08-27 10:26:02 +02:00
parent 0af139e183
commit b6b1e1aa12
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
bin/init_model.py
View File

@ -38,6 +38,7 @@ from spacy.parts_of_speech import NOUN, VERB, ADJ
import spacy.en
import spacy.de
import spacy.fi
@ -184,7 +185,8 @@ def setup_vocab(get_lex_attr, src_dir, dst_dir):
def main(lang_id, lang_data_dir, corpora_dir, model_dir):
languages = {
'en': spacy.en.English.default_lex_attrs(),
'de': spacy.de.Deutsch.default_lex_attrs()
'de': spacy.de.Deutsch.default_lex_attrs(),
'fi': spacy.fi.Finnish.default_lex_attrs()
}
model_dir = Path(model_dir)
@ -203,6 +205,11 @@ def main(lang_id, lang_data_dir, corpora_dir, model_dir):
if (lang_data_dir / 'gazetteer.json').exists():
copyfile(str(lang_data_dir / 'gazetteer.json'),
str(model_dir / 'vocab' / 'gazetteer.json'))
if (lang_data_dir / 'lemma_rules.json').exists():
copyfile(str(lang_data_dir / 'lemma_rules.json'),
str(model_dir / 'vocab' / 'lemma_rules.json'))
if not (model_dir / 'wordnet').exists() and (corpora_dir / 'wordnet').exists():
copytree(str(corpora_dir / 'wordnet' / 'dict'), str(model_dir / 'wordnet'))