pymmseg

用python写的分词程序,实现的是最大匹配方法,简单易用

#!/usr/bin/env python

import sys
import getopt
from os.path import dirname, join

sys.path.append(join(dirname(__file__), '..'))

import mmseg

def print_usage():
    print """\
mmseg  Segment Chinese text. Read from stdin and print to stdout.

Options:
  -h
  --help      Print this message

  -s
  --separator Select the separator of the segmented text. Default is
              space.
    """
    sys.exit(0)

separator = " "

optlst, args = getopt.getopt(sys.argv[1:], 'hs:')

for opt, val in optlst:
    if opt == '-h':
        print_usage()
    
    elif opt == '-s':
        separator = val


# load default dictionaries
mmseg.dict_load_defaults()

algor = mmseg.Algorithm(sys.stdin.read())
first = True
for tk in algor:
    if not first:
        sys.stdout.write(separator)
    first = False
    sys.stdout.write(tk.text)
print