mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 22:27:12 +03:00
b10c7bc56e
* Update stop_words.py Hebrew STOP WORDS * Update stop_words.py * contributor * contributor * add some common domain extentions support human number 1K/1M.... * support human number 1K/1M.... * hebrew number tokenize 1K/1M implement in EN * test human tokenize fix * test * heb like num revert human number change * heb like num
110 lines
1.8 KiB
Python
110 lines
1.8 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
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",
|
|
]
|
|
|
|
|
|
_ordinal_words = [
|
|
"first",
|
|
"second",
|
|
"third",
|
|
"fourth",
|
|
"fifth",
|
|
"sixth",
|
|
"seventh",
|
|
"eighth",
|
|
"ninth",
|
|
"tenth",
|
|
"eleventh",
|
|
"twelfth",
|
|
"thirteenth",
|
|
"fourteenth",
|
|
"fifteenth",
|
|
"sixteenth",
|
|
"seventeenth",
|
|
"eighteenth",
|
|
"nineteenth",
|
|
"twentieth",
|
|
"thirtieth",
|
|
"fortieth",
|
|
"fiftieth",
|
|
"sixtieth",
|
|
"seventieth",
|
|
"eightieth",
|
|
"ninetieth",
|
|
"hundredth",
|
|
"thousandth",
|
|
"millionth",
|
|
"billionth",
|
|
"trillionth",
|
|
"quadrillionth",
|
|
"gajillionth",
|
|
"bazillionth",
|
|
]
|
|
|
|
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
|
|
|
|
text_lower = text.lower()
|
|
if text_lower in _num_words:
|
|
return True
|
|
|
|
# CHeck ordinal number
|
|
if text_lower in _ordinal_words:
|
|
return True
|
|
if text_lower.endswith("th"):
|
|
if text_lower[:-2].isdigit():
|
|
return True
|
|
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|