string.py 文件源码

def __init__(self, encoding='utf-8', normalize=True):
        # type: (Text, bool) -> None
        """
        :param encoding:
            Used to decode non-unicode values.

        :param normalize:
            Whether to normalize the resulting value:
                - Convert to NFC form.
                - Remove non-printable characters.
                - Convert all line endings to unix-style ('\n').
        """
        super(Unicode, self).__init__()

        self.encoding   = encoding
        self.normalize  = normalize

        if self.normalize:
            #
            # Compile the regex that we will use to remove non-
            # printables from the resulting unicode.
            # http://www.regular-expressions.info/unicode.html#category
            #
            # Note: using a double negative so that we can exclude
            # newlines, which are technically considered control chars.
            # http://stackoverflow.com/a/3469155
            #
            self.npr = regex.compile(r'[^\P{C}\s]+', regex.UNICODE)