mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
60 lines
988 B
Python
60 lines
988 B
Python
from ...attrs import LIKE_NUM
|
|
|
|
|
|
_num_words = [
|
|
"zero",
|
|
"one",
|
|
"two",
|
|
"three",
|
|
"four",
|
|
"five",
|
|
"six",
|
|
"seven",
|
|
"eight",
|
|
"nine",
|
|
"ten",
|
|
"eleven",
|
|
"twelve",
|
|
"thirteen",
|
|
"fourteen",
|
|
"fifteen",
|
|
"sixteen",
|
|
"seventeen",
|
|
"eighteen",
|
|
"nineteen",
|
|
"twenty",
|
|
"thirty",
|
|
"forty",
|
|
"fifty",
|
|
"sixty",
|
|
"seventy",
|
|
"eighty",
|
|
"ninety",
|
|
"hundred",
|
|
"thousand",
|
|
"million",
|
|
"billion",
|
|
"trillion",
|
|
"quadrillion",
|
|
"gajillion",
|
|
"bazillion",
|
|
]
|
|
|
|
|
|
def like_num(text):
|
|
if text.startswith(("+", "-", "±", "~")):
|
|
text = text[1:]
|
|
text = text.replace(",", "").replace(".", "")
|
|
if text.isdigit():
|
|
return True
|
|
if text.count("/") == 1:
|
|
num, denom = text.split("/")
|
|
if num.isdigit() and denom.isdigit():
|
|
return True
|
|
if text.lower() in _num_words:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|