mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
5610fdcc06
Makes sure spaCy fails early if no tokenizer exists, and allows printing better error message.
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from . import util
|
|
from .deprecated import resolve_model_name
|
|
from .cli import info
|
|
|
|
from . import en, de, zh, es, it, hu, fr, pt, nl, sv, fi, bn, he
|
|
|
|
|
|
_languages = (en.English, de.German, es.Spanish, pt.Portuguese, fr.French,
|
|
it.Italian, hu.Hungarian, zh.Chinese, nl.Dutch, sv.Swedish,
|
|
fi.Finnish, bn.Bengali, he.Hebrew)
|
|
|
|
|
|
for _lang in _languages:
|
|
util.set_lang_class(_lang.lang, _lang)
|
|
|
|
|
|
def load(name, **overrides):
|
|
if overrides.get('path') in (None, False, True):
|
|
data_path = util.get_data_path()
|
|
model_name = resolve_model_name(name)
|
|
model_path = data_path / model_name
|
|
if not model_path.exists():
|
|
lang_name = util.get_lang_class(name).lang
|
|
model_path = None
|
|
util.print_msg(
|
|
"Only loading the '{}' tokenizer.".format(lang_name),
|
|
title="Warning: no model found for '{}'".format(name))
|
|
else:
|
|
model_path = util.ensure_path(overrides['path'])
|
|
data_path = model_path.parent
|
|
model_name = ''
|
|
meta = util.parse_package_meta(data_path, model_name, require=False)
|
|
lang = meta['lang'] if meta and 'lang' in meta else name
|
|
cls = util.get_lang_class(lang)
|
|
overrides['meta'] = meta
|
|
overrides['path'] = model_path
|
|
return cls(**overrides)
|