#filter waste lines
if splitValues[0] == 'text' or len(splitValues) < 9:
#print splitValues
continue
if splitValues[0] in words:
word = words[splitValues[0]]
else:
word = Word(splitValues[0]) #create Word object
words[splitValues[0]] = word
tagComb = TagCombination(splitValues[1], splitValues[2], splitValues[3],
splitValues[4], splitValues[5], splitValues[6],
splitValues[7], splitValues[8])
word.add(tagComb) #create connection between word and tag combination
gs_long.close()
#Part 2: compare tagger output file with gs
tagger_output = codecs.open("dummy_compare.csv", "r", "utf-8")
allLines = tagger_output.readlines()
wordNotFoundCounter = 0
combinationFoundCounter = 0
combinationNotFoundCounter = 0
for line in allLines:
splitValues = line.split("\t")
#print splitValues
if splitValues[0] in words:
