Dashka Rodionova roddar92
roddar92
/ Soundex.py
Created
May 15, 2019 14:21
Phonetic algorithm for Russian and English languages based on Soundex
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re | |
| from abc import ABC, abstractmethod | |
| import editdistance | |
| import pymorphy2 | |
| class Soundex(ABC): | |
| _vowels = '' | |
| _table = str.maketrans('', '') | |
| _reduce_regex = re.compile(r'(\w)(\1)+', re.IGNORECASE) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # -*- coding: utf-8 -*- | |
| import re | |
| import string | |
| from src.russian.NaiveTokenizer import NaiveTokenizer | |
| from src.russian.SpellChecker import StatisticalSpeller | |
| class Transliterator: |