explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add regular expressions for English multi-word expressions

Browse Source
This commit is contained in:
Matthew Honnibal 2015-04-07 03:45:18 +02:00
parent 5a075ea3fc
commit 2fee67cfa3
1 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
spacy/en/regexes.py Normal file
View File

@ -0,0 +1,35 @@
import re
_mw_prepositions = [
'close to',
'down by',
'on the way to',
'on my way',
'on his way',
'on her way',
'on your way',
'on our way',
'on their way',
]
MW_PREPOSITIONS_RE = re.compile('|'.join(_mw_prepositions), flags=re.IGNORECASE)
TIME_RE = re.compile(
'{colon_digits}|{colon_digits} ?{am_pm}?|{one_two_digits} ?({am_pm})'.format(
colon_digits=r'[0-2]?[0-9]:[0-5][0-9](?::[0-5][0-9])?',
one_two_digits=r'[0-2]?[0-9]',
am_pm=r'[ap]\.?m\.?'))
MONEY_RE = re.compile('\$\d+(?:\.\d+)?|\d+ dollars(?: \d+ cents)?')
DAYS_RE = re.compile('Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday')
REGEXES = [('IN', 'O', MW_PREPOSITIONS_RE), ('CD', 'TIME', TIME_RE),
('NNP', 'DATE', DAYS_RE), ('CD', 'MONEY', MONEY_RE)]