mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
cf52510631
* Add Amharic to space * clean up * Add some PRON_LEMMA * add Tigrinya support * remove text_noun_chunks * Tigrinya Support * added some more details for ti * fix unit test * add amharic char range * changes from review * amharic and tigrinya share same unicode block * get rid of _amharic/_tigrinya in char_classes Co-authored-by: Josiah Solomon <jsolomon@meteorcomm.com>
105 lines
2.3 KiB
Python
105 lines
2.3 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...attrs import LIKE_NUM
|
|
|
|
_num_words = [
|
|
"ዜሮ",
|
|
"ሐደ",
|
|
"ክልተ",
|
|
"ሰለስተ",
|
|
"ኣርባዕተ",
|
|
"ሓሙሽተ",
|
|
"ሽድሽተ",
|
|
"ሸውዓተ",
|
|
"ሽሞንተ",
|
|
"ትሽዓተ",
|
|
"ኣሰርተ",
|
|
"ኣሰርተ ሐደ",
|
|
"ኣሰርተ ክልተ",
|
|
"ኣሰርተ ሰለስተ",
|
|
"ኣሰርተ ኣርባዕተ",
|
|
"ኣሰርተ ሓሙሽተ",
|
|
"ኣሰርተ ሽድሽተ",
|
|
"ኣሰርተ ሸውዓተ",
|
|
"ኣሰርተ ሽሞንተ",
|
|
"ኣሰርተ ትሽዓተ",
|
|
"ዕስራ",
|
|
"ሰላሳ",
|
|
"ኣርብዓ",
|
|
"ሃምሳ",
|
|
"ስልሳ",
|
|
"ሰብዓ",
|
|
"ሰማንያ",
|
|
"ተስዓ",
|
|
"ሚእቲ",
|
|
"ሺሕ",
|
|
"ሚልዮን",
|
|
"ቢልዮን",
|
|
"ትሪልዮን",
|
|
"ኳድሪልዮን",
|
|
"ገጅልዮን",
|
|
"ባዝልዮን"
|
|
]
|
|
|
|
_ordinal_words = [
|
|
"ቀዳማይ",
|
|
"ካልኣይ",
|
|
"ሳልሳይ",
|
|
"ራብኣይ",
|
|
"ሓምሻይ",
|
|
"ሻድሻይ",
|
|
"ሻውዓይ",
|
|
"ሻምናይ",
|
|
"ዘጠነኛ",
|
|
"አስረኛ",
|
|
"ኣሰርተ አንደኛ",
|
|
"ኣሰርተ ሁለተኛ",
|
|
"ኣሰርተ ሶስተኛ",
|
|
"ኣሰርተ አራተኛ",
|
|
"ኣሰርተ አምስተኛ",
|
|
"ኣሰርተ ስድስተኛ",
|
|
"ኣሰርተ ሰባተኛ",
|
|
"ኣሰርተ ስምንተኛ",
|
|
"ኣሰርተ ዘጠነኛ",
|
|
"ሃያኛ",
|
|
"ሰላሳኛ"
|
|
"አርባኛ",
|
|
"አምሳኛ",
|
|
"ስድሳኛ",
|
|
"ሰባኛ",
|
|
"ሰማንያኛ",
|
|
"ዘጠናኛ",
|
|
"መቶኛ",
|
|
"ሺኛ",
|
|
"ሚሊዮንኛ",
|
|
"ቢሊዮንኛ",
|
|
"ትሪሊዮንኛ"
|
|
]
|
|
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("ኛ"):
|
|
if text_lower[:-2].isdigit():
|
|
return True
|
|
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {LIKE_NUM: like_num}
|