docling 2.16.0__py3-none-any.whl → 2.18.0__py3-none-any.whl

docling/backend/html_backend.py

@@ -1,9 +1,9 @@
 import logging
 from io import BytesIO
 from pathlib import Path
-from typing import Set, Union
+from typing import Optional, Set, Union
 
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, Tag
 from docling_core.types.doc import (
     DocItemLabel,
     DoclingDocument,
@@ -24,7 +24,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
         _log.debug("About to init HTML backend...")
-        self.soup = None
+        self.soup: Optional[Tag] = None
         # HTML file:
         self.path_or_stream = path_or_stream
         # Initialise the parents for the hierarchy
@@ -78,17 +78,18 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         if self.is_valid():
             assert self.soup is not None
+            content = self.soup.body or self.soup
             # Replace <br> tags with newline characters
-            for br in self.soup.body.find_all("br"):
+            for br in content.find_all("br"):
                 br.replace_with("\n")
-            doc = self.walk(self.soup.body, doc)
+            doc = self.walk(content, doc)
         else:
             raise RuntimeError(
                 f"Cannot convert doc with {self.document_hash} because the backend failed to init."
             )
         return doc
 
-    def walk(self, element, doc):
+    def walk(self, element: Tag, doc: DoclingDocument):
         try:
             # Iterate over elements in the body of the document
             for idx, element in enumerate(element.children):
@@ -105,7 +106,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         return doc
 
-    def analyse_element(self, element, idx, doc):
+    def analyse_element(self, element: Tag, idx: int, doc: DoclingDocument):
         """
         if element.name!=None:
             _log.debug("\t"*self.level, idx, "\t", f"{element.name} ({self.level})")
@@ -135,7 +136,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         else:
             self.walk(element, doc)
 
-    def get_direct_text(self, item):
+    def get_direct_text(self, item: Tag):
         """Get the direct text of the <li> element (ignoring nested lists)."""
         text = item.find(string=True, recursive=False)
         if isinstance(text, str):
@@ -144,7 +145,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         return ""
 
     # Function to recursively extract text from all child nodes
-    def extract_text_recursively(self, item):
+    def extract_text_recursively(self, item: Tag):
         result = []
 
         if isinstance(item, str):
@@ -165,7 +166,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         return "".join(result) + " "
 
-    def handle_header(self, element, idx, doc):
+    def handle_header(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles header tags (h1, h2, etc.)."""
         hlevel = int(element.name.replace("h", ""))
         slevel = hlevel - 1
@@ -207,7 +208,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 level=hlevel,
             )
 
-    def handle_code(self, element, idx, doc):
+    def handle_code(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles monospace code snippets (pre)."""
         if element.text is None:
             return
@@ -215,9 +216,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         label = DocItemLabel.CODE
         if len(text) == 0:
             return
-        doc.add_code(parent=self.parents[self.level], label=label, text=text)
+        doc.add_code(parent=self.parents[self.level], text=text)
 
-    def handle_paragraph(self, element, idx, doc):
+    def handle_paragraph(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles paragraph tags (p)."""
         if element.text is None:
             return
@@ -227,7 +228,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             return
         doc.add_text(parent=self.parents[self.level], label=label, text=text)
 
-    def handle_list(self, element, idx, doc):
+    def handle_list(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles list tags (ul, ol) and their list items."""
 
         if element.name == "ul":
@@ -249,7 +250,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         self.parents[self.level + 1] = None
         self.level -= 1
 
-    def handle_listitem(self, element, idx, doc):
+    def handle_listitem(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles listitem tags (li)."""
         nested_lists = element.find(["ul", "ol"])
 
@@ -303,7 +304,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         else:
             _log.warn("list-item has no text: ", element)
 
-    def handle_table(self, element, idx, doc):
+    def handle_table(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles table tags."""
 
         nested_tables = element.find("table")
@@ -376,7 +377,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         doc.add_table(data=data, parent=self.parents[self.level])
 
-    def get_list_text(self, list_element, level=0):
+    def get_list_text(self, list_element: Tag, level=0):
         """Recursively extract text from <ul> or <ol> with proper indentation."""
         result = []
         bullet_char = "*"  # Default bullet character for unordered lists
@@ -402,7 +403,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         return result
 
-    def extract_table_cell_text(self, cell):
+    def extract_table_cell_text(self, cell: Tag):
         """Extract text from a table cell, including lists with indents."""
         contains_lists = cell.find(["ul", "ol"])
         if contains_lists is None:
@@ -413,7 +414,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             )
             return cell.text
 
-    def handle_figure(self, element, idx, doc):
+    def handle_figure(self, element: Tag, idx: int, doc: DoclingDocument):
         """Handles image tags (img)."""
 
         # Extract the image URI from the <img> tag
@@ -436,6 +437,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 caption=fig_caption,
             )
 
-    def handle_image(self, element, idx, doc):
+    def handle_image(self, element: Tag, idx, doc: DoclingDocument):
         """Handles image tags (img)."""
         doc.add_picture(parent=self.parents[self.level], caption=None)

docling/backend/md_backend.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import List, Optional, Set, Union
 
 import marko
+import marko.element
 import marko.ext
 import marko.ext.gfm
 import marko.inline
@@ -23,11 +24,16 @@ from docling_core.types.doc import (
 from marko import Markdown
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.backend.html_backend import HTMLDocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 
+_MARKER_BODY = "DOCLING_DOC_MD_HTML_EXPORT"
+_START_MARKER = f"#_#_{_MARKER_BODY}_START_#_#"
+_STOP_MARKER = f"#_#_{_MARKER_BODY}_STOP_#_#"
+
 
 class MarkdownDocumentBackend(DeclarativeDocumentBackend):
     def shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
@@ -65,7 +71,8 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
 
         self.in_table = False
         self.md_table_buffer: list[str] = []
-        self.inline_text_buffer = ""
+        self.inline_texts: list[str] = []
+        self._html_blocks: int = 0
 
         try:
             if isinstance(self.path_or_stream, BytesIO):
@@ -152,26 +159,25 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
     def process_inline_text(
         self, parent_element: Optional[NodeItem], doc: DoclingDocument
     ):
-        # self.inline_text_buffer += str(text_in)
-        txt = self.inline_text_buffer.strip()
+        txt = " ".join(self.inline_texts)
         if len(txt) > 0:
             doc.add_text(
                 label=DocItemLabel.PARAGRAPH,
                 parent=parent_element,
                 text=txt,
             )
-        self.inline_text_buffer = ""
+        self.inline_texts = []
 
     def iterate_elements(
         self,
-        element: marko.block.Element,
+        element: marko.element.Element,
         depth: int,
         doc: DoclingDocument,
         parent_element: Optional[NodeItem] = None,
     ):
         # Iterates over all elements in the AST
         # Check for different element types and process relevant details
-        if isinstance(element, marko.block.Heading):
+        if isinstance(element, marko.block.Heading) and len(element.children) > 0:
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(
@@ -206,17 +212,22 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 )
 
         elif isinstance(element, marko.block.List):
+            has_non_empty_list_items = False
+            for child in element.children:
+                if isinstance(child, marko.block.ListItem) and len(child.children) > 0:
+                    has_non_empty_list_items = True
+                    break
+
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - List {'ordered' if element.ordered else 'unordered'}")
-            list_label = GroupLabel.LIST
-            if element.ordered:
-                list_label = GroupLabel.ORDERED_LIST
-            parent_element = doc.add_group(
-                label=list_label, name=f"list", parent=parent_element
-            )
+            if has_non_empty_list_items:
+                label = GroupLabel.ORDERED_LIST if element.ordered else GroupLabel.LIST
+                parent_element = doc.add_group(
+                    label=label, name=f"list", parent=parent_element
+                )
 
-        elif isinstance(element, marko.block.ListItem):
+        elif isinstance(element, marko.block.ListItem) and len(element.children) > 0:
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(" - List item")
@@ -246,29 +257,25 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
 
             doc.add_picture(parent=parent_element, caption=fig_caption)
 
-        elif isinstance(element, marko.block.Paragraph):
+        elif isinstance(element, marko.block.Paragraph) and len(element.children) > 0:
             self.process_inline_text(parent_element, doc)
 
         elif isinstance(element, marko.inline.RawText):
             _log.debug(f" - Paragraph (raw text): {element.children}")
-            snippet_text = str(element.children).strip()
+            snippet_text = element.children.strip()
             # Detect start of the table:
             if "|" in snippet_text:
                 # most likely part of the markdown table
                 self.in_table = True
                 if len(self.md_table_buffer) > 0:
-                    self.md_table_buffer[len(self.md_table_buffer) - 1] += str(
-                        snippet_text
-                    )
+                    self.md_table_buffer[len(self.md_table_buffer) - 1] += snippet_text
                 else:
                     self.md_table_buffer.append(snippet_text)
             else:
                 self.close_table(doc)
                 self.in_table = False
                 # most likely just inline text
-                self.inline_text_buffer += str(
-                    element.children
-                )  # do not strip an inline text, as it may contain important spaces
+                self.inline_texts.append(str(element.children))
 
         elif isinstance(element, marko.inline.CodeSpan):
             self.close_table(doc)
@@ -277,50 +284,55 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             snippet_text = str(element.children).strip()
             doc.add_code(parent=parent_element, text=snippet_text)
 
-        elif isinstance(element, marko.block.CodeBlock):
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
-            _log.debug(f" - Code Block: {element.children}")
-            snippet_text = str(element.children[0].children).strip()  # type: ignore
-            doc.add_code(parent=parent_element, text=snippet_text)
-
-        elif isinstance(element, marko.block.FencedCode):
+        elif (
+            isinstance(element, (marko.block.CodeBlock, marko.block.FencedCode))
+            and len(element.children) > 0
+            and isinstance((first_child := element.children[0]), marko.inline.RawText)
+            and len(snippet_text := (first_child.children.strip())) > 0
+        ):
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - Code Block: {element.children}")
-            snippet_text = str(element.children[0].children).strip()  # type: ignore
             doc.add_code(parent=parent_element, text=snippet_text)
 
         elif isinstance(element, marko.inline.LineBreak):
-            self.process_inline_text(parent_element, doc)
             if self.in_table:
                 _log.debug("Line break in a table")
                 self.md_table_buffer.append("")
 
         elif isinstance(element, marko.block.HTMLBlock):
+            self._html_blocks += 1
             self.process_inline_text(parent_element, doc)
             self.close_table(doc)
             _log.debug("HTML Block: {}".format(element))
             if (
-                len(element.children) > 0
+                len(element.body) > 0
             ):  # If Marko doesn't return any content for HTML block, skip it
-                snippet_text = str(element.children).strip()
-                doc.add_text(
-                    label=DocItemLabel.CODE, parent=parent_element, text=snippet_text
-                )
+                html_block = element.body.strip()
+
+                # wrap in markers to enable post-processing in convert()
+                text_to_add = f"{_START_MARKER}{html_block}{_STOP_MARKER}"
+                doc.add_code(parent=parent_element, text=text_to_add)
         else:
             if not isinstance(element, str):
                 self.close_table(doc)
                 _log.debug("Some other element: {}".format(element))
 
+        processed_block_types = (
+            marko.block.ListItem,
+            marko.block.Heading,
+            marko.block.CodeBlock,
+            marko.block.FencedCode,
+            # marko.block.Paragraph,
+            marko.inline.RawText,
+        )
+
         # Iterate through the element's children (if any)
-        if not isinstance(element, marko.block.ListItem):
-            if not isinstance(element, marko.block.Heading):
-                if not isinstance(element, marko.block.FencedCode):
-                    # if not isinstance(element, marko.block.Paragraph):
-                    if hasattr(element, "children"):
-                        for child in element.children:
-                            self.iterate_elements(child, depth + 1, doc, parent_element)
+        if hasattr(element, "children") and not isinstance(
+            element, processed_block_types
+        ):
+            for child in element.children:
+                self.iterate_elements(child, depth + 1, doc, parent_element)
 
     def is_valid(self) -> bool:
         return self.valid
@@ -356,6 +368,43 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             # Start iterating from the root of the AST
             self.iterate_elements(parsed_ast, 0, doc, None)
             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(
+                    in_doc=in_doc, path_or_stream=stream
+                )
+                doc = html_backend_obj.convert()
         else:
             raise RuntimeError(
                 f"Cannot convert md with {self.document_hash} because the backend failed to init."

docling/backend/mspowerpoint_backend.py

@@ -98,21 +98,28 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
 
         return doc
 
-    def generate_prov(self, shape, slide_ind, text=""):
-        left = shape.left
-        top = shape.top
-        width = shape.width
-        height = shape.height
+    def generate_prov(
+        self, shape, slide_ind, text="", slide_size=Size(width=1, height=1)
+    ):
+        if shape.left:
+            left = shape.left
+            top = shape.top
+            width = shape.width
+            height = shape.height
+        else:
+            left = 0
+            top = 0
+            width = slide_size.width
+            height = slide_size.height
         shape_bbox = [left, top, left + width, top + height]
         shape_bbox = BoundingBox.from_tuple(shape_bbox, origin=CoordOrigin.BOTTOMLEFT)
-        # prov = [{"bbox": shape_bbox, "page": parent_slide, "span": [0, len(text)]}]
         prov = ProvenanceItem(
             page_no=slide_ind + 1, charspan=[0, len(text)], bbox=shape_bbox
         )
 
         return prov
 
-    def handle_text_elements(self, shape, parent_slide, slide_ind, doc):
+    def handle_text_elements(self, shape, parent_slide, slide_ind, doc, slide_size):
         is_a_list = False
         is_list_group_created = False
         enum_list_item_value = 0
@@ -121,7 +128,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
         list_text = ""
         list_label = GroupLabel.LIST
         doc_label = DocItemLabel.LIST_ITEM
-        prov = self.generate_prov(shape, slide_ind, shape.text.strip())
+        prov = self.generate_prov(shape, slide_ind, shape.text.strip(), slide_size)
 
         # Identify if shape contains lists
         for paragraph in shape.text_frame.paragraphs:
@@ -270,18 +277,17 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
                 )
         return
 
-    def handle_pictures(self, shape, parent_slide, slide_ind, doc):
-        # Get the image bytes
-        image = shape.image
-        image_bytes = image.blob
-        im_dpi, _ = image.dpi
-
+    def handle_pictures(self, shape, parent_slide, slide_ind, doc, slide_size):
         # Open it with PIL
         try:
+            # Get the image bytes
+            image = shape.image
+            image_bytes = image.blob
+            im_dpi, _ = image.dpi
             pil_image = Image.open(BytesIO(image_bytes))
 
             # shape has picture
-            prov = self.generate_prov(shape, slide_ind, "")
+            prov = self.generate_prov(shape, slide_ind, "", slide_size)
             doc.add_picture(
                 parent=parent_slide,
                 image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
@@ -292,13 +298,13 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
             _log.warning(f"Warning: image cannot be loaded by Pillow: {e}")
         return
 
-    def handle_tables(self, shape, parent_slide, slide_ind, doc):
+    def handle_tables(self, shape, parent_slide, slide_ind, doc, slide_size):
         # Handling tables, images, charts
         if shape.has_table:
             table = shape.table
             table_xml = shape._element
 
-            prov = self.generate_prov(shape, slide_ind, "")
+            prov = self.generate_prov(shape, slide_ind, "", slide_size)
 
             num_cols = 0
             num_rows = len(table.rows)
@@ -375,17 +381,19 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
                 name=f"slide-{slide_ind}", label=GroupLabel.CHAPTER, parent=parents[0]
             )
 
-            size = Size(width=slide_width, height=slide_height)
-            parent_page = doc.add_page(page_no=slide_ind + 1, size=size)
+            slide_size = Size(width=slide_width, height=slide_height)
+            parent_page = doc.add_page(page_no=slide_ind + 1, size=slide_size)
 
-            def handle_shapes(shape, parent_slide, slide_ind, doc):
-                handle_groups(shape, parent_slide, slide_ind, doc)
+            def handle_shapes(shape, parent_slide, slide_ind, doc, slide_size):
+                handle_groups(shape, parent_slide, slide_ind, doc, slide_size)
                 if shape.has_table:
                     # Handle Tables
-                    self.handle_tables(shape, parent_slide, slide_ind, doc)
+                    self.handle_tables(shape, parent_slide, slide_ind, doc, slide_size)
                 if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
                     # Handle Pictures
-                    self.handle_pictures(shape, parent_slide, slide_ind, doc)
+                    self.handle_pictures(
+                        shape, parent_slide, slide_ind, doc, slide_size
+                    )
                 # If shape doesn't have any text, move on to the next shape
                 if not hasattr(shape, "text"):
                     return
@@ -397,16 +405,20 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
                     _log.warning("Warning: shape has text but not text_frame")
                     return
                 # Handle other text elements, including lists (bullet lists, numbered lists)
-                self.handle_text_elements(shape, parent_slide, slide_ind, doc)
+                self.handle_text_elements(
+                    shape, parent_slide, slide_ind, doc, slide_size
+                )
                 return
 
-            def handle_groups(shape, parent_slide, slide_ind, doc):
+            def handle_groups(shape, parent_slide, slide_ind, doc, slide_size):
                 if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
                     for groupedshape in shape.shapes:
-                        handle_shapes(groupedshape, parent_slide, slide_ind, doc)
+                        handle_shapes(
+                            groupedshape, parent_slide, slide_ind, doc, slide_size
+                        )
 
             # Loop through each shape in the slide
             for shape in slide.shapes:
-                handle_shapes(shape, parent_slide, slide_ind, doc)
+                handle_shapes(shape, parent_slide, slide_ind, doc, slide_size)
 
         return doc