twitter.py 文件源码

def __init__(self, root, fileids=None,
                 word_tokenizer=TweetTokenizer(),
                 encoding='utf8'):
        """

        :param root: The root directory for this corpus.

        :param fileids: A list or regexp specifying the fileids in this corpus.

        :param word_tokenizer: Tokenizer for breaking the text of Tweets into
        smaller units, including but not limited to words.

        """
        CorpusReader.__init__(self, root, fileids, encoding)

        for path in self.abspaths(self._fileids):
            if isinstance(path, ZipFilePathPointer):
                pass
            elif os.path.getsize(path) == 0:
                raise ValueError("File {} is empty".format(path))
        """Check that all user-created corpus files are non-empty."""

        self._word_tokenizer = word_tokenizer