mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 09:56:28 +03:00
1a00bff06d
* Hindi: Adds tests for lexical attributes (norm and like_num) * Signs and sdds the contributor agreement * Add ordinal numbers to be tagged as like_num * Adds alternate pronunciation for 31 and 39
192 lines
5.8 KiB
Python
192 lines
5.8 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...attrs import NORM, LIKE_NUM
|
|
|
|
|
|
# fmt: off
|
|
_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/
|
|
# reference 3: https://www.mindurhindi.com/basic-words-and-phrases-in-hindi/
|
|
|
|
_one_to_ten = [
|
|
"शून्य",
|
|
"एक",
|
|
"दो",
|
|
"तीन",
|
|
"चार",
|
|
"पांच", "पाँच",
|
|
"छह",
|
|
"सात",
|
|
"आठ",
|
|
"नौ",
|
|
"दस",
|
|
]
|
|
|
|
_eleven_to_beyond = [
|
|
"ग्यारह",
|
|
"बारह",
|
|
"तेरह",
|
|
"चौदह",
|
|
"पंद्रह",
|
|
"सोलह",
|
|
"सत्रह",
|
|
"अठारह",
|
|
"उन्नीस",
|
|
"बीस",
|
|
"इकीस", "इक्कीस",
|
|
"बाईस",
|
|
"तेइस",
|
|
"चौबीस",
|
|
"पच्चीस",
|
|
"छब्बीस",
|
|
"सताइस", "सत्ताइस",
|
|
"अट्ठाइस",
|
|
"उनतीस",
|
|
"तीस",
|
|
"इकतीस", "इकत्तीस",
|
|
"बतीस", "बत्तीस",
|
|
"तैंतीस",
|
|
"चौंतीस",
|
|
"पैंतीस",
|
|
"छतीस", "छत्तीस",
|
|
"सैंतीस",
|
|
"अड़तीस",
|
|
"उनतालीस", "उनत्तीस",
|
|
"चालीस",
|
|
"इकतालीस",
|
|
"बयालीस",
|
|
"तैतालीस",
|
|
"चवालीस",
|
|
"पैंतालीस",
|
|
"छयालिस",
|
|
"सैंतालीस",
|
|
"अड़तालीस",
|
|
"उनचास",
|
|
"पचास",
|
|
"इक्यावन",
|
|
"बावन",
|
|
"तिरपन", "तिरेपन",
|
|
"चौवन", "चउवन",
|
|
"पचपन",
|
|
"छप्पन",
|
|
"सतावन", "सत्तावन",
|
|
"अठावन",
|
|
"उनसठ",
|
|
"साठ",
|
|
"इकसठ",
|
|
"बासठ",
|
|
"तिरसठ", "तिरेसठ",
|
|
"चौंसठ",
|
|
"पैंसठ",
|
|
"छियासठ",
|
|
"सड़सठ",
|
|
"अड़सठ",
|
|
"उनहत्तर",
|
|
"सत्तर",
|
|
"इकहत्तर"
|
|
"बहत्तर",
|
|
"तिहत्तर",
|
|
"चौहत्तर",
|
|
"पचहत्तर",
|
|
"छिहत्तर",
|
|
"सतहत्तर",
|
|
"अठहत्तर",
|
|
"उन्नासी", "उन्यासी"
|
|
"अस्सी",
|
|
"इक्यासी",
|
|
"बयासी",
|
|
"तिरासी",
|
|
"चौरासी",
|
|
"पचासी",
|
|
"छियासी",
|
|
"सतासी",
|
|
"अट्ठासी",
|
|
"नवासी",
|
|
"नब्बे",
|
|
"इक्यानवे",
|
|
"बानवे",
|
|
"तिरानवे",
|
|
"चौरानवे",
|
|
"पचानवे",
|
|
"छियानवे",
|
|
"सतानवे",
|
|
"अट्ठानवे",
|
|
"निन्यानवे",
|
|
"सौ",
|
|
"हज़ार",
|
|
"लाख",
|
|
"करोड़",
|
|
"अरब",
|
|
"खरब",
|
|
]
|
|
|
|
_num_words = _one_to_ten + _eleven_to_beyond
|
|
|
|
_ordinal_words_one_to_ten = [
|
|
"प्रथम", "पहला",
|
|
"द्वितीय", "दूसरा",
|
|
"तृतीय", "तीसरा",
|
|
"चौथा",
|
|
"पांचवाँ",
|
|
"छठा",
|
|
"सातवाँ",
|
|
"आठवाँ",
|
|
"नौवाँ",
|
|
"दसवाँ",
|
|
]
|
|
_ordinal_suffix = "वाँ"
|
|
# fmt: on
|
|
|
|
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:
|
|
continue
|
|
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
|
|
|
|
# check ordinal numbers
|
|
# reference: http://www.englishkitab.com/Vocabulary/Numbers.html
|
|
if text in _ordinal_words_one_to_ten:
|
|
return True
|
|
if text.endswith(_ordinal_suffix):
|
|
if text[:-len(_ordinal_suffix)] in _eleven_to_beyond:
|
|
return True
|
|
return False
|
|
|
|
|
|
LEX_ATTRS = {NORM: norm, LIKE_NUM: like_num}
|