xmldocs.py 文件源码

def words(self, fileid=None):
        """
        Returns all of the words and punctuation symbols in the specified file
        that were in text nodes -- ie, tags are ignored. Like the xml() method,
        fileid can only specify one file.

        :return: the given file's text nodes as a list of words and punctuation symbols
        :rtype: list(str)
        """

        elt = self.xml(fileid)
        encoding = self.encoding(fileid)
        word_tokenizer=WordPunctTokenizer()
        iterator = elt.getiterator()
        out = []

        for node in iterator:
            text = node.text
            if text is not None:
                if isinstance(text, bytes):
                    text = text.decode(encoding)
                toks = word_tokenizer.tokenize(text)
                out.extend(toks)
        return out