convert_possible_tags_to_header() — langchain Function Reference

Source Code

libs/text-splitters/langchain_text_splitters/html.py lines 493–528

    def convert_possible_tags_to_header(self, html_content: str) -> str:
        """Convert specific HTML tags to headers using an XSLT transformation.

        This method uses an XSLT file to transform the HTML content, converting
        certain tags into headers for easier parsing. If no XSLT path is provided,
        the HTML content is returned unchanged.

        Args:
            html_content: The HTML content to be transformed.

        Returns:
            The transformed HTML content as a string.

        Raises:
            ImportError: If the `lxml` library is not installed.
        """
        if not _HAS_LXML:
            msg = "Unable to import lxml, please install with `pip install lxml`."
            raise ImportError(msg)
        # use lxml library to parse html document and return xml ElementTree
        # Create secure parsers to prevent XXE attacks
        html_parser = etree.HTMLParser(no_network=True)
        xslt_parser = etree.XMLParser(
            resolve_entities=False, no_network=True, load_dtd=False
        )

        # Apply XSLT access control to prevent file/network access
        # DENY_ALL is a predefined access control that blocks all file/network access
        # Type ignore needed due to incomplete lxml type stubs
        ac = etree.XSLTAccessControl.DENY_ALL  # type: ignore[attr-defined]

        tree = etree.parse(StringIO(html_content), html_parser)
        xslt_tree = etree.parse(self.xslt_path, xslt_parser)
        transform = etree.XSLT(xslt_tree, access_control=ac)
        result = transform(tree)
        return str(result)