Script to parse ZWNJ/ZWJ/ZWSP from http://dumps.wikimedia.org/tawiki/20120526/tawiki-20120526-all-titles-in-ns0.gz

ListZWNJ.py

# -*- coding: utf-8  -*-
# Script to parse ZWNJ/ZWJ/ZWSP from http://dumps.wikimedia.org/tawiki/20120526/tawiki-20120526-all-titles-in-ns0.gz
# Srikanth Logic
import sys
def main():
	srcPath = sys.argv[1]
	destPath = sys.argv[2]
	sourceFile = open(srcPath,'r')
	outputFile = open(destPath,'a')
	outputFile.write("ZWNJ =====================\n")
	for line in sourceFile:
		line = line.splitlines()[0]
		if ( line.find('\xe2\x80\x8c') != -1):
			outputFile.write( "* [[" + line + "]], [[" + line.replace('\xe2\x80\x8c','') + "]]\n")
	outputFile.write("ZWJ =====================\n")
	for line in sourceFile:
		line = line.splitlines()[0]
		if ( line.find('\xe2\x80\x8d') != -1):
			outputFile.write( "* [[" + line + "]], [[" + line.replace('\xe2\x80\x8d','') + "]]\n")
	outputFile.write("ZWSP =====================\n")
	for line in sourceFile:
		line = line.splitlines()[0]
		if ( line.find('\xe2\x80\x8b') != -1):
			outputFile.write( "* [[" + line + "]], [[" + line.replace('\xe2\x80\x8b','') + "]]\n")

if __name__ == "__main__":
	main()