UDParser.py 文件源码

def fresh(self, s, tokenized=False):
        """UD-parse and POS-tag sentence `s`. Returns (UDParse, PTB-parse-string).

        Pass in `tokenized=True` if `s` has already been tokenized, otherwise we
        apply `nltk.tokenize.TreebankWordTokenizer`.

        """
        if self.process is None:
            self._start_subprocess()
        s = str(s.strip())
        if not tokenized:
            s = tokenize(s)
        s = s.strip()
        assert '\n' not in s, "No newline characters allowed %r" % s
        try:
            self.process.stdin.write(s.encode('utf-8'))
        except IOError as e:
            #if e.errno == 32:          # broken pipe
            #    self.process = None
            #    return self(s)  # retry will restart process
            raise e
        self.process.stdin.write(b'\n')
        self.process.stdin.flush()
        out = self.process.stdout.readline()
        if sys.version_info[0] == 3:
            out = out.decode()
        return self.to_ud(out)