explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

updated regexp

Browse Source
This commit is contained in:
Jim Geovedi 2017-07-29 17:44:57 +07:00
parent 7d96d477ea
commit 4d04898dea
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/lang/id/tokenizer_exceptions.py
View File

@ -44,10 +44,11 @@ ke-annya di-kan di-kannya de-isasi ber-an berke-an""".split()
_hyphen_suffix = """el""" _hyphen_suffix = """el"""
_regular_exp = ['^{p}-*$'.format(p=prefix) for prefix in _hyphen_prefix] _regular_exp = ['^{p}-.*$'.format(p=prefix) for prefix in _hyphen_prefix]
_regular_exp = ['^{p}-*$'.format(p=prefix.title()) for prefix in _hyphen_prefix] _regular_exp += ['^{p}-.*$'.format(p=prefix.title()) for prefix in _hyphen_prefix]
_regular_exp += ['^{0}-*-{1}$'.format(*infix.title().split('-')) for infix in _hyphen_infix] _regular_exp += ['^{p}-.*$'.format(p=prefix.upper()) for prefix in _hyphen_prefix]
_regular_exp = ['^*-{s}$'.format(s=suffix) for suffix in _hyphen_suffix] _regular_exp += ['^{0}-.*-{1}$'.format(*infix.title().split('-')) for infix in _hyphen_infix]
_regular_exp += ['^.*-{s}$'.format(s=suffix) for suffix in _hyphen_suffix]
_regular_exp.append(URL_PATTERN) _regular_exp.append(URL_PATTERN)