explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #996 from beneyal/master (closes #995)

Browse Source 
Fix for issue 995
This commit is contained in:
Ines Montani 2017-04-20 12:16:02 +02:00 committed by GitHub
commit df64e8dbb3
5 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/fr/tokenizer_exceptions.py
View File

@ -13,7 +13,7 @@ from ..symbols import *
import os import os
import io import io
import re import regex as re
def get_exceptions(): def get_exceptions():

2
spacy/hu/tokenizer_exceptions.py
View File

@ -1,7 +1,7 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import regex as re
from spacy.language_data.punctuation import ALPHA_LOWER, CURRENCY from spacy.language_data.punctuation import ALPHA_LOWER, CURRENCY
from ..language_data.tokenizer_exceptions import _URL_PATTERN from ..language_data.tokenizer_exceptions import _URL_PATTERN

30
spacy/language_data/punctuation.py
View File

@ -1,21 +1,8 @@
# coding: utf8 # coding: utf8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import regex as re
re.DEFAULT_VERSION = re.VERSION1
_ALPHA_LOWER = """
a ä à á â ǎ æ ã å ā ă ą b c ç ć č ĉ ċ c̄ d ð ď e é è ê ë ė ȅ ȩ ẽ ę f g ĝ ğ h i ı
î ï í ī ì ȉ ǐ į ĩ j k ķ l ł ļ m n ñ ń ň ņ o ö ó ò ő ô õ œ ø ō ő ǒ ơ p q r ř ŗ s
ß ś š ş ŝ t ť u ú û ù ú ū ű ǔ ů ų ư v w ŵ x y ÿ ý ỳ ŷ ỹ z ź ž ż þ
"""
_ALPHA_UPPER = """
A Ä À Á Â Ǎ Æ Ã Å Ā Ă Ą B C Ç Ć Č Ĉ Ċ C̄ D Ð Ď E É È Ê Ë Ė Ȅ Ȩ Ẽ Ę F G Ĝ Ğ H I İ
Î Ï Í Ī Ì Ȉ Ǐ Į Ĩ J K Ķ L Ł Ļ M N Ñ Ń Ň Ņ O Ö Ó Ò Ő Ô Õ Œ Ø Ō Ő Ǒ Ơ P Q R Ř Ŗ S
Ś Š Ş Ŝ T Ť U Ú Û Ù Ú Ū Ű Ǔ Ů Ų Ư V W Ŵ X Y Ÿ Ý Ỳ Ŷ Ỹ Z Ź Ž Ż Þ
"""
_UNITS = """ _UNITS = """
@ -57,9 +44,16 @@ LIST_PUNCT = list(_PUNCT.strip().split())
LIST_HYPHENS = list(_HYPHENS.strip().split()) LIST_HYPHENS = list(_HYPHENS.strip().split())
ALPHA_LOWER = _ALPHA_LOWER.strip().replace(' ', '').replace('\n', '') BENGALI = r'[\p{L}&&\p{Bengali}]'
ALPHA_UPPER = _ALPHA_UPPER.strip().replace(' ', '').replace('\n', '') HEBREW = r'[\p{L}&&\p{Hebrew}]'
ALPHA = ALPHA_LOWER + ALPHA_UPPER LATIN_LOWER = r'[\p{Ll}&&\p{Latin}]'
LATIN_UPPER = r'[\p{Lu}&&\p{Latin}]'
LATIN = r'[[\p{Ll}||\p{Lu}]&&\p{Latin}]'
ALPHA_LOWER = '[{}]'.format('||'.join([BENGALI, HEBREW, LATIN_LOWER]))
ALPHA_UPPER = '[{}]'.format('||'.join([BENGALI, HEBREW, LATIN_UPPER]))
ALPHA = '[{}]'.format('||'.join([BENGALI, HEBREW, LATIN]))
QUOTES = _QUOTES.strip().replace(' ', '|') QUOTES = _QUOTES.strip().replace(' ', '|')

2
spacy/tests/he/test_tokenizer.py
View File

@ -13,7 +13,7 @@ def test_tokenizer_handles_abbreviation(he_tokenizer, text, expected_tokens):
@pytest.mark.parametrize('text,expected_tokens', [ @pytest.mark.parametrize('text,expected_tokens', [
pytest.mark.xfail(('עקבת אחריו בכל רחבי המדינה.', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '.'])), ('עקבת אחריו בכל רחבי המדינה.', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '.']),
('עקבת אחריו בכל רחבי המדינה?', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '?']), ('עקבת אחריו בכל רחבי המדינה?', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '?']),
('עקבת אחריו בכל רחבי המדינה!', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '!']), ('עקבת אחריו בכל רחבי המדינה!', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '!']),
('עקבת אחריו בכל רחבי המדינה..', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '..']), ('עקבת אחריו בכל רחבי המדינה..', ['עקבת', 'אחריו', 'בכל', 'רחבי', 'המדינה', '..']),

2
spacy/util.py
View File

@ -2,7 +2,7 @@
from __future__ import unicode_literals, print_function from __future__ import unicode_literals, print_function
import ujson import ujson
import re import regex as re
from pathlib import Path from pathlib import Path
import sys import sys
import textwrap import textwrap