explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove time from German language data

Browse Source
This commit is contained in:
Ines Montani 2016-12-08 19:45:50 +01:00
parent e8ae588be9
commit 70b51ed7c8
2 changed files with 0 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/de/__init__.py
View File

@ -10,7 +10,6 @@ from ..util import update_exc
from ..language_data import EMOTICONS
from .language_data import ORTH_ONLY
from .language_data import strings_to_exc
from .language_data import get_time_exc
TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)
@ -23,7 +22,6 @@ STOP_WORDS = set(language_data.STOP_WORDS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(EMOTICONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, get_time_exc(range(1, 24 + 1)))
class German(Language):

11
spacy/de/language_data.py
View File

@ -9,17 +9,6 @@ def strings_to_exc(orths):
return {orth: [{ORTH: orth}] for orth in orths}
def get_time_exc(hours):
exc = {}
for hour in hours:
# currently only supporting formats like "10h", not "10 Uhr"
exc["%dh" % hour] = [
{ORTH: hour},
{ORTH: "h", LEMMA: "Uhr"}
]
return exc
PRON_LEMMA = "-PRON-"