def start(raw):
print "[INFO] Analyze Korean"
print "[INFO] raw data"
print raw
print "[INFO] raw data -Done-"
tokens = Tokenizer.space_tokenizer(Tokenizer.symbol_escaper(raw))
print "[INFO] escape symbol"
print os.linesep.join(tokens)
print "[INFO] escape symbol -Done-"
j_dic = Dictionary("./dic/josa.dic")
for t in tokens:
what = Tokenizer.check_token(t)
if what == "korean":
stemm, josa = josa_analyzer(t, j_dic)
print "%s:\t%s %s" % (t, stemm, josa)
else:
print "%s: %s" % (t, what)
print "[INFO] Analyze Korean -Done-"
