Method convert

docling/backend/md_backend.py:363–428

(self)

        return {InputFormat.MD}

    def convert(self) -> DoclingDocument:
        _log.debug("converting Markdown...")

        origin = DocumentOrigin(
            filename=self.file.name or "file",
            mimetype="text/markdown",
            binary_hash=self.document_hash,
        )

        doc = DoclingDocument(name=self.file.stem or "file", origin=origin)

        if self.is_valid():
            # Parse the markdown into an abstract syntax tree (AST)
            marko_parser = Markdown()
            parsed_ast = marko_parser.parse(self.markdown)
            # Start iterating from the root of the AST
            self._iterate_elements(
                element=parsed_ast,
                depth=0,
                doc=doc,
                parent_item=None,
                visited=set(),
            )
            self._process_inline_text(None, doc)  # handle last hanging inline text
            self._close_table(doc=doc)  # handle any last hanging table

            # if HTML blocks were detected, export to HTML and delegate to HTML backend
            if self._html_blocks > 0:

                # export to HTML
                html_backend_cls = HTMLDocumentBackend
                html_str = doc.export_to_html()

                def _restore_original_html(txt, regex):
                    _txt, count = re.subn(regex, "", txt)
                    if count != self._html_blocks:
                        raise RuntimeError(
                            "An internal error has occurred during Markdown conversion."
                        )
                    return _txt

                # restore original HTML by removing previouly added markers
                for regex in [
                    rf"<pre>\s*<code>\s*{_START_MARKER}",
                    rf"{_STOP_MARKER}\s*</code>\s*</pre>",
                ]:
                    html_str = _restore_original_html(txt=html_str, regex=regex)
                self._html_blocks = 0

                # delegate to HTML backend
                stream = BytesIO(bytes(html_str, encoding="utf-8"))
                in_doc = InputDocument(
                    path_or_stream=stream,
                    format=InputFormat.HTML,
                    backend=html_backend_cls,
                    filename=self.file.name,
                )
                html_backend_obj = html_backend_cls(