Created
December 15, 2022 21:34
-
-
Save linuxscout/bb1eff5f553c2167fc6e6bbf15a48b9a to your computer and use it in GitHub Desktop.
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
#!/usr/bin/python | |
# -*- coding=utf-8 -*- | |
""" | |
Example on arabic text cleaning using PyArbic Library | |
Requirements: pip install pyarabic | |
Data: csv text file contains (tweet, emotion) separated by a ',' | |
Ouput: text file ( cleaned) | |
""" | |
import sys | |
import pyarabic.araby as araby | |
SEPARATOR = "," | |
def clean_file(file_name, outfile_name): | |
# open file with unicode | |
try: | |
myfile = open(file_name, encoding="utf8") | |
except: | |
print("Can't open file ", file_name) | |
print("Exit from program ", file_name) | |
sys.exit() | |
# read lines from file: | |
lines = myfile.readlines() | |
cleaned_lines = [] | |
# for each line, we do treatment to clean text | |
for text_line in lines: | |
# select fields to treats | |
fields = text_line.split(",") | |
if len(fields) >=2: | |
tweet = fields[0] | |
emotion = fields[1] | |
# conditions to make on text, keep only arabic letters and text | |
conditions = [araby.is_arabicrange,] | |
# actions to do on texts, | |
# remove tashkeel | |
# remove all kind of diacrtics like small alif, or other marks koranics for example | |
# remove tatweel | |
morphs = [araby.strip_tashkeel, araby.strip_diacritics, araby.strip_tatweel] | |
tokens = araby.tokenize(tweet,conditions= conditions, morphs= morphs) | |
# tokens is a list, join them to be a cleaned text line | |
cleaned_tweet = " ".join(tokens) | |
cleaned_one_line = SEPARATOR.join([tweet, cleaned_tweet, emotion, "\n"]) | |
# append line into a list of cleaned lines | |
cleaned_lines.append(cleaned_one_line) | |
# after treatments, write into files | |
# open destination file | |
try: | |
myoutfile = open(outfile_name, "a+", encoding="utf8",) | |
except: | |
print("Can't open file to write outputs", outfile_name) | |
print("Exit from program ", outfile_name) | |
sys.exit() | |
# write lines into file | |
myoutfile.writelines(cleaned_lines) | |
myoutfile.flush() | |
# close file | |
myoutfile.close() | |
# Main function | |
if __name__ == '__main__': | |
file_name = 'text_file.txt' | |
outfile_name = "output.txt" | |
clean_file(file_name,outfile_name) | |
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
أذكر مشكلة كهذه اعترضتني في مشروع تعريب رسمي، وأظن عندي فكرة عن السبب لذلك يمكن أن أعلق بخصوص الموضوع., True | |
ايش بدهم من الأطفال؟ شركة ملابس عالمية فارهة تعمل حملات إعلانية تتضمن إيحاءات جنسية وتقديم قرابين من الأطفال للشيطان, True | |
ستُغلق خدمة Revue، وهي خدمة النشرات البريدية التي استحوذ عليها تويتر ودمجها في منصته، ولن يعود بالإمكان استخدامها.,Postive | |
يبدو أن إيلون ماسك يركّز على أمور محددة فقط بعد استحواذه على تويتر ولا يريد أن يتابع كل شيء كما كان في السابق., negative | |
https://getrevue.co, positive | |
في هذه الحروف فعل رباعي جميع حروفه أصلية.. ما هو؟, negative |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment