explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Rename _URL_PATTERN to URL_PATTERN

Browse Source
This commit is contained in:
ines 2017-05-09 00:00:00 +02:00
parent 604f299cf6
commit a91278cb32
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/lang/fr/tokenizer_exceptions.py
View File

@ -144,7 +144,7 @@ _regular_exp += ["^{prefix}[{hyphen}][{alpha}][{alpha}{elision}{other_hyphen}\-]
_regular_exp += ["^{prefix}[{elision}][{alpha}][{alpha}{elision}{hyphen}\-]*$".format(
prefix=p, elision=HYPHENS, hyphen=_other_hyphens, alpha=ALPHA_LOWER)
for p in _elision_prefix]
_regular_exp.append(_URL_PATTERN)
_regular_exp.append(URL_PATTERN)
TOKENIZER_EXCEPTIONS = dict(_exc)

2
spacy/lang/hu/tokenizer_exceptions.py
View File

@ -96,4 +96,4 @@ _nums = "(({ne})|({t})|({on})|({c}))({s})?".format(
TOKENIZER_EXCEPTIONS = dict(_exc)
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=_URL_PATTERN, n=_nums)).match
TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=URL_PATTERN, n=_nums)).match

4
spacy/lang/tokenizer_exceptions.py
View File

@ -10,7 +10,7 @@ from ..symbols import ORTH, POS, LEMMA, SPACE, PUNCT
# URL validation regex courtesy of: https://mathiasbynens.be/demo/url-regex
# A few minor mods to this regex to account for use cases represented in test_urls
_URL_PATTERN = (
URL_PATTERN = (
r"^"
# in order to support the prefix tokenization (see prefix test cases in test_urls).
r"(?=[\w])"
@ -53,7 +53,7 @@ _URL_PATTERN = (
r"$"
).strip()
TOKEN_MATCH = regex.compile(_URL_PATTERN, regex.UNICODE).match
TOKEN_MATCH = regex.compile(URL_PATTERN, regex.UNICODE).match