def api_segment(string):
'''分词,返回大数组,单个数据又是(词,词性,idf)组成的数组
**example**:
@startcode
for c in api_segment("我们是好朋友"):
print c[0],":",c[1],":",c[2]
@endcode
**result**:
@startcode
我们 : r : 4.42000007629
是 : v : 0.0
好朋友 : nz : 7.96999979019
@endcode
'''
try:
return {"code":200,"data":_scws.get_res(string)}
except:
return {"code":510,"msg":"scws internal error"}
# coding:utf8
import _scws
print "hello"
_scws.scws_new()
_scws.scws_set_charset("UTF8")
_scws.scws_set_xdb("/etc/scws/dict.utf8.xdb")
_scws.scws_set_rule("/etc/scws/rules.utf8.ini")
# print s[0]
print "hid"
print "hi"
d = _scws.get_res("我们是很好很好的好朋友啊,列宁说")
for c in d:
print c[0]
print c[1]
print c[2]
print "exit..."
print d
def segment(string):
'''分词,返回大数组,单个数据又是(词,词性,idf)组成的数组'''
return _scws.get_res(string)
def cnseg(string):
"""分词,返回用空格分开的词语组"""
d=_scws.get_res(string)
return " ".join([c[0] for c in d])
def get_text_fc(self,text): ret = _scws.get_res(text) return ret
def get_text_fc(self, text):
ret = _scws.get_res(text)
return ret