spaCy/spacy/lang/id/tokenizer_exceptions.py

# coding: utf8
from __future__ import unicode_literals

from ._tokenizer_exceptions_list import FR_BASE_EXCEPTIONS

_exc = {}

for orth in FR_BASE_EXCEPTIONS + ["etc."]:
    _exc[orth] = [{ORTH: orth}]

TOKENIZER_EXCEPTIONS = dict(_exc)
added tokenizer_exceptions 2017-07-23 15:55:05 +00:00			`# coding: utf8`
			`from __future__ import unicode_literals`

enable tokenizer exceptions 2017-07-24 07:11:10 +00:00			`from ._tokenizer_exceptions_list import FR_BASE_EXCEPTIONS`

			`_exc = {}`

			`for orth in FR_BASE_EXCEPTIONS + ["etc."]:`
			`_exc[orth] = [{ORTH: orth}]`

			`TOKENIZER_EXCEPTIONS = dict(_exc)`