A Chinese character code is converted into the python library Pinyin

Below is the code on a code segment to convert Chinese characters into pinyin of python library.
#! / usr / bin / env python

"""
Author:cleverdeng
E-mail:[email protected]
"""

__version__ = '0.9'
__all__ = ["PinYin"]

import os.path


class PinYin(object):
def __init__(self, dict_file='word.data'):
self.word_dict = {}
self.dict_file = dict_file


def load_word(self):
if not os.path.exists(self.dict_file):
raise IOError("NotFoundFile")

with file(self.dict_file) as f_obj:
for f_line in f_obj.readlines():
try:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]
except:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]


def hanzi2pinyin(self, string=""):
result = []
if not isinstance(string, unicode):
string = string.decode("utf-8")

for char in string:
key = '%X' % ord(char)
result.append(self.word_dict.get(key, char).split()[0][:-1].lower())

return result


def hanzi2pinyin_split(self, string="", split=""):
result = self.hanzi2pinyin(string=string)
if split == "":
return result
else:
return split.join(result)


if __name__ == "__main__":
test = PinYin()
test.load_word()
string = "钓鱼岛是中国的"
print "in: %s" % string
print "out: %s" % str(test.hanzi2pinyin(string=string))
print "out: %s" % test.hanzi2pinyin_split(string=string, split="-")



<H4> Annex: <a href="/uploadfiles/2013/06/20/13717130117510.zip"> Source Codes </a> </ h4>


 

Guess you like

Origin www.cnblogs.com/fulhns/p/11241287.html