class Parser(object):
def __init__(self, encoding="utf8", mecab_option=default_option):
self.encoding = encoding
self.mecab_option = mecab_option
self.tagger = MeCab.Tagger(self.mecab_option)
self.normalizer = TextNormalizer()
def node(self, s):
try:
if type(s) == str:
s = s.decode(self.encoding)
s = self.normalizer.normalize(s)
s = s.encode(self.encoding)
except:
s = ""
return self.tagger.parseToNode(s)
def parse(self, s, to_unicode=False):
node = self.node(s)
ret = []
while node:
surface = node.surface
if surface != "":
if to_unicode:
surface = surface.decode(self.encoding)
ret.append(surface)
node = node.next
return ret
class Parser(object):
def __init__(self, encoding="utf8", mecab_option=default_option):
self.encoding = encoding
self.mecab_option = mecab_option
self.tagger = MeCab.Tagger(self.mecab_option)
self.normalizer = TextNormalizer()
def node(self, s):
try:
if type(s) == str:
s = s.decode(self.encoding)
s = self.normalizer.normalize(s)
s = s.encode(self.encoding)
except:
s = ""
return self.tagger.parseToNode(s)
def parse(self, s, to_unicode=False):
node = self.node(s)
ret = []
while node:
surface = node.surface
if surface != "":
if to_unicode:
surface = surface.decode(self.encoding)
ret.append(surface)
node = node.next
return ret
#!/usr/bin/python
#encoding: utf8
import sys
from NormalizeText import TextNormalizer
if __name__ == '__main__':
#print sys.argv
if len(sys.argv) < 2:
normalizer = TextNormalizer()
else:
normalizer = TextNormalizer(*sys.argv[1:])
#print normalizer.normalize_methods
while 1:
s = raw_input()
print normalizer.normalize(s.decode('utf8'))
