spaCy/spacy/lang/hi/lex_attrs.py

59 lines
2.8 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from ..norm_exceptions import BASE_NORMS
from ...attrs import NORM
from ...attrs import LIKE_NUM
from ...util import add_lookups
_stem_suffixes = [
["","","","","","ि",""],
["कर","ाओ","िए","ाई","ाए","ने","नी","ना","ते","ीं","ती","ता","ाँ","ां","ों","ें"],
["ाकर","ाइए","ाईं","ाया","ेगी","ेगा","ोगी","ोगे","ाने","ाना","ाते","ाती","ाता","तीं","ाओं","ाएं","ुओं","ुएं","ुआं"],
["ाएगी","ाएगा","ाओगी","ाओगे","एंगी","ेंगी","एंगे","ेंगे","ूंगी","ूंगा","ातीं","नाओं","नाएं","ताओं","ताएं","ियाँ","ियों","ियां"],
["ाएंगी","ाएंगे","ाऊंगी","ाऊंगा","ाइयाँ","ाइयों","ाइयां"]
]
#reference 1:https://en.wikipedia.org/wiki/Indian_numbering_system
#reference 2: https://blogs.transparent.com/hindi/hindi-numbers-1-100/
_num_words = ['शून्य', 'एक', 'दो', 'तीन', 'चार', 'पांच', 'छह', 'सात', 'आठ', 'नौ', 'दस',
'ग्यारह', 'बारह', 'तेरह', 'चौदह', 'पंद्रह', 'सोलह', 'सत्रह', 'अठारह', 'उन्नीस',
'बीस', 'तीस', 'चालीस', 'पचास', 'साठ', 'सत्तर', 'अस्सी', 'नब्बे', 'सौ', 'हज़ार',
'लाख', 'करोड़', 'अरब', 'खरब']
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:
# http://computing.open.ac.uk/Sites/EACLSouthAsia/Papers/p6-Ramanathan.pdf
# http://research.variancia.com/hindi_stemmer/
# https://github.com/taranjeet/hindi-tokenizer/blob/master/HindiTokenizer.py#L142
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):
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
}