Fast transliteration for Arabic Text with Python

Question

I always work on Arabic text files and to avoid problems with encoding I transliterate Arabic characters into English according to Buckwalter\'s scheme (http://www.qamus.org/tra

Answer 1

Extending @larapsodia's answer, here is the complete code with dictionary:

# -*- coding: utf-8 -*-

# Arabic Transliteration based on Buckwalter
# dictionary source is buckwalter2unicode.py http://www.redhat.com/archives/fedora-extras-commits/2007-June/msg03617.html 

buck2uni = {"'": u"\u0621", # hamza-on-the-line
            "|": u"\u0622", # madda
            ">": u"\u0623", # hamza-on-'alif
            "&": u"\u0624", # hamza-on-waaw
            "<": u"\u0625", # hamza-under-'alif
            "}": u"\u0626", # hamza-on-yaa'
            "A": u"\u0627", # bare 'alif
            "b": u"\u0628", # baa'
            "p": u"\u0629", # taa' marbuuTa
            "t": u"\u062A", # taa'
            "v": u"\u062B", # thaa'
            "j": u"\u062C", # jiim
            "H": u"\u062D", # Haa'
            "x": u"\u062E", # khaa'
            "d": u"\u062F", # daal
            "*": u"\u0630", # dhaal
            "r": u"\u0631", # raa'
            "z": u"\u0632", # zaay
            "s": u"\u0633", # siin
            "$": u"\u0634", # shiin
            "S": u"\u0635", # Saad
            "D": u"\u0636", # Daad
            "T": u"\u0637", # Taa'
            "Z": u"\u0638", # Zaa' (DHaa')
            "E": u"\u0639", # cayn
            "g": u"\u063A", # ghayn
            "_": u"\u0640", # taTwiil
            "f": u"\u0641", # faa'
            "q": u"\u0642", # qaaf
            "k": u"\u0643", # kaaf
            "l": u"\u0644", # laam
            "m": u"\u0645", # miim
            "n": u"\u0646", # nuun
            "h": u"\u0647", # haa'
            "w": u"\u0648", # waaw
            "Y": u"\u0649", # 'alif maqSuura
            "y": u"\u064A", # yaa'
            "F": u"\u064B", # fatHatayn
            "N": u"\u064C", # Dammatayn
            "K": u"\u064D", # kasratayn
            "a": u"\u064E", # fatHa
            "u": u"\u064F", # Damma
            "i": u"\u0650", # kasra
            "~": u"\u0651", # shaddah
            "o": u"\u0652", # sukuun
            "`": u"\u0670", # dagger 'alif
            "{": u"\u0671", # waSla
}

def transString(string, reverse=0):
    '''Given a Unicode string, transliterate into Buckwalter. To go from
    Buckwalter back to Unicode, set reverse=1'''

    for k, v in buck2uni.items():
      if not reverse:
            string = string.replace(v, k)
      else:
            string = string.replace(k, v)

    return string


>>> print(transString(u'مرحبا'))
mrHbA
>>> print(transString('mrHbA', 1))
مرحبا
>>>

This taken from http://www.redhat.com/archives/fedora-extras-commits/2007-June/msg03617.html which is licensed under the GPLv2 or later.