spaCy/spacy/lang/ne/lex_attrs.py

99 lines
3.3 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from ..norm_exceptions import BASE_NORMS
from ...attrs import NORM, LIKE_NUM
# fmt: off
_stem_suffixes = [
["", "ि", "", "", "", "", "", "", "", ""],
["", "", "", ""],
["लाई", "ले", "बाट", "को", "मा", "हरू"],
["हरूलाई", "हरूले", "हरूबाट", "हरूको", "हरूमा"],
["इलो", "िलो", "नु", "ाउनु", "", "इन", "इन्", "इनन्"],
["एँ", "इँन्", "इस्", "इनस्", "यो", "एन", "यौं", "एनौं", "", "एनन्"],
["छु", "छौँ", "छस्", "छौ", "", "छन्", "छेस्", "छे", "छ्यौ", "छिन्", "हुन्छ"],
["दै", "दिन", "दिँन", "दैनस्", "दैन", "दैनौँ", "दैनौं", "दैनन्"],
["हुन्न", "न्न", "न्न्स्", "न्नौं", "न्नौ", "न्न्न्", "िई"],
["", "", "", "अरी", "साथ", "वित्तिकै", "पूर्वक"],
["याइ", "ाइ", "बार", "वार", "चाँहि"],
["ने", "ेको", "ेकी", "ेका", "ेर", "दै", "तै", "िकन", "", "", "नन्"]
]
# fmt: on
# reference 1: https://en.wikipedia.org/wiki/Numbers_in_Nepali_language
# reference 2: https://www.imnepal.com/nepali-numbers/
_num_words = [
"शुन्य",
"एक",
"दुई",
"तीन",
"चार",
"पाँच",
"",
"सात",
"आठ",
"नौ",
"दश",
"एघार",
"बाह्र",
"तेह्र",
"चौध",
"पन्ध्र",
"सोह्र",
"सोह्र",
"सत्र",
"अठार",
"उन्नाइस",
"बीस",
"तीस",
"चालीस",
"पचास",
"साठी",
"सत्तरी",
"असी",
"नब्बे",
"सय",
"हजार",
"लाख",
"करोड",
"अर्ब",
"खर्ब",
]
def norm(string):
# normalise base exceptions, e.g. punctuation or currency symbols
if string in BASE_NORMS:
return BASE_NORMS[string]
# set stem word as norm, if available, adapted from:
# https://github.com/explosion/spaCy/blob/master/spacy/lang/hi/lex_attrs.py
# https://www.researchgate.net/publication/237261579_Structure_of_Nepali_Grammar
for suffix_group in reversed(_stem_suffixes):
length = len(suffix_group[0])
if len(string) <= length:
break
for suffix in suffix_group:
if string.endswith(suffix):
return string[:-length]
return string
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 = {NORM: norm, LIKE_NUM: like_num}