def wordsplit(s):
'返回一个由 分割开的自符'
str=''
#print s
ictclas.import_dict('./user.txt')
ictclas.ict_init("./")
li = ictclas.process_str_ret_list(s)
for i in li:
#print i.start, i.length, i.word_id, s[i.start:(i.start+i.length)]
# print s[i.start:(i.start+i.length)],hash(s[i.start:(i.start+i.length)])
str=str+s[i.start:(i.start+i.length)]+' '
ictclas.ict_exit()
return str
def __init__(self,basepath='./'):
ictclas.ict_init(basepath)
def filesplit(f,n,tag):
ictclas.import_dict('./user.txt')
ictclas.ict_init("./")
li=ictclas.process_file(f,n,tag)
ictclas.ict_exit()
def __init__(self,basepath='/home/chunwei/swin2/_parser/ICTCLAS50'):
ictclas.ict_init(basepath)
def __init__(self, basepath='./'):
ictclas.ict_init(basepath)
#!/usr/bin/env python
#-*- coding:utf8 -*-
import ictclas
print ictclas.ict_init("./",0)
s = "我们都是好孩子，异想天开的孩子。written by 爱思客"
count = ictclas.process_str_ret_word_count(s.decode("utf8").encode("gb2312"))
print "Count:%s"%(count)
li = ictclas.process_str_ret_list(s)
print "-"*8
for i in li:
print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
print "-"*8
kw = ictclas.keyword(len(li))
for i in kw:
print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
print "-"*8
print "set pos map:%s"%(ictclas.POSMAP.ICT_SECOND)
print "after add user word"
ictclas.add_user_word("爱思客 n")
ictclas.set_pos_map(ictclas.POSMAP.ICT_SECOND)
li = ictclas.process_str_ret_list(s)
fingerprint = ictclas.fingerprint()
print "fingerprint:%s"%(fingerprint)
kw = ictclas.keyword(len(li))
for i in kw:
print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
print ictclas.ict_exit()
#!/usr/bin/env python
#-*- coding:gb2312 -*-
import ictclas
print ictclas.ict_init(".")
s = "我们都是好孩子，异想天开的孩子。written by 爱思客"
print s
count = ictclas.process_str_ret_word_count(s)
print "Count:%s"%(count)
#li = ictclas.process_str_ret_list(s)
#print "-"*8
#for i in li:
# print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
#print "-"*8
#kw = ictclas.keyword(len(li))
#for i in kw:
# print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
#
#print "-"*8
#print "set pos map:%s"%(ictclas.POSMAP.ICT_SECOND)
#print "after add user word"
#ictclas.add_user_word("爱思客 n")
#ictclas.set_pos_map(ictclas.POSMAP.ICT_SECOND)
#li = ictclas.process_str_ret_list(s)
#fingerprint = ictclas.fingerprint()
#print "fingerprint:%s"%(fingerprint)
#kw = ictclas.keyword(len(li))
#for i in kw:
# print i.start, i.length, i.ipos, i.spos, i.word_id, i.word_type, i.weight, s[i.start:(i.start+i.length)]
#
#print ictclas.ict_exit()
#
def ict_init():
import os
path = os.path.join(os.getcwd(), __file__)
path = os.path.abspath(path[:path.rfind("/")])
return ictclas.ict_init(path)