# -*- encoding: iso-8859-1 -*-

"""suchte alle Wortlemmata, die folgende nicht-alphanumerische Zeichen 
enthalten: $ \ * # § % & = ? < > [ ] { }  
"""

import re, sys
sys.path.append("../")
import classEntry02


def printNonAlphas(entryList):
	p = classEntry02.Entry(entryList)
	f = open("../../../res/teilergebnisse/02wlNonAlphas.txt", "a")
	if re.search("[$\[\]\\*#§%&=?<>}{]", " ".join(p.getWl1())):
#	if re.search("[<>]", " ".join(p.getWl1())):
#	if re.search("[\[\]]", " ".join(p.getWl1())):
#	if re.search("[\"']]", " ".join(p.getWl1())):
		f.write("WL1: "+ " ".join(p.getWl1()) + "\n")
		f.write("WL2: "+ " ".join(p.getWl2()) + "\n")		
		f.write("\n")
	elif re.search("[$\[\]\\*#§%&=?<>}{]", " ".join(p.getWl2())):
#	elif re.search("[<>]", " ".join(p.getWl2())):
#	elif re.search("[\[\]]", " ".join(p.getWl2())):
#	elif re.search("[\"']]", " ".join(p.getWl2())):
		f.write("WL1: "+ " ".join(p.getWl1()) + "\n")
		f.write("WL2: "+ " ".join(p.getWl2()) + "\n")		
		f.write("\n")		


if __name__ == "__main__":
	lexicon = open("../../../res/01WAT.txt")
	wholeEntry = []
	countEntry = 0
	line = lexicon.readline()
	while line:
		line = line.strip()
		if re.search("ID:", line):
			if wholeEntry and wholeEntry[0] is not "":
				countEntry += 1
				printNonAlphas(wholeEntry)
			wholeEntry = []
		wholeEntry.append(line)
		line = lexicon.readline()
	printNonAlphas(wholeEntry)
	print "Anzahl der Einträge: ", countEntry