Created
May 23, 2020 15:37
-
-
Save malaikannan/21fda36bd0bec126dd598924af1ab482 to your computer and use it in GitHub Desktop.
Tamil Spell Checker
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 os | |
import traceback | |
from bloomfilter import BloomFilter | |
import jellyfish | |
edit_distance = 2 | |
tamil_unique_words_file_path = "tamilwordlist.txt" | |
bloom_filter_file_path = "tamil_bloom_filter.txt" | |
def read_tamil_words_listfile(tamil_unique_words_file_path): | |
ta_words_unique = [] | |
try: | |
tamil_word_file = open(tamil_unique_words_file_path, 'r') | |
for line in tamil_word_file: | |
ta_words_unique.append(line.strip()) | |
tamil_word_file.close() | |
except Exception as e: | |
track = traceback.format_exc() | |
print(track) | |
return ta_words_unique | |
def read_bloom_filter_tamil_file(bloom_filter_path): | |
falsepositive_probability = 0.001 | |
tamil_word_count = 2043478 | |
bloom_tamil = "" | |
try: | |
bloom_tamil = BloomFilter(tamil_word_count,falsepositive_probability,bloom_filter_file_path) | |
except Exception as e: | |
track = traceback.format_exc() | |
print(track) | |
return bloom_tamil | |
def tamil_correct_spelling(word,edit_distance,ta_words_unique,bloom_tamil): | |
suggested_words = [] | |
if not bloom_tamil.check(word): | |
for tamil_word in ta_words_unique: | |
if jellyfish.levenshtein_distance(tamil_word, word) < edit_distance: | |
suggested_words.append(tamil_word) | |
return suggested_words | |
ta_words_unique = read_tamil_words_listfile(tamil_unique_words_file_path) | |
bloom_tamil = read_bloom_filter_tamil_file(bloom_filter_file_path) | |
word = "மெலாம்" | |
tamil_correct_spelling(word,edit_distance,ta_words_unique,bloom_tamil) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment