docling 2.14.0__tar.gz → 2.15.0__tar.gz

{docling-2.14.0 → docling-2.15.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.14.0
+Version: 2.15.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -26,7 +26,7 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.12.1,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.13.1,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.1.0,<4.0.0)
 Requires-Dist: docling-parse (>=3.0.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)

{docling-2.14.0 → docling-2.15.0}/docling/backend/html_backend.py

@@ -37,10 +37,10 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         try:
             if isinstance(self.path_or_stream, BytesIO):
-                text_stream = self.path_or_stream.getvalue().decode("utf-8")
+                text_stream = self.path_or_stream.getvalue()
                 self.soup = BeautifulSoup(text_stream, "html.parser")
             if isinstance(self.path_or_stream, Path):
-                with open(self.path_or_stream, "r", encoding="utf-8") as f:
+                with open(self.path_or_stream, "rb") as f:
                     html_content = f.read()
                     self.soup = BeautifulSoup(html_content, "html.parser")
         except Exception as e:

{docling-2.14.0 → docling-2.15.0}/docling/backend/mspowerpoint_backend.py

@@ -16,7 +16,7 @@ from docling_core.types.doc import (
     TableCell,
     TableData,
 )
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
 
@@ -120,6 +120,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
         bullet_type = "None"
         list_text = ""
         list_label = GroupLabel.LIST
+        doc_label = DocItemLabel.LIST_ITEM
         prov = self.generate_prov(shape, slide_ind, shape.text.strip())
 
         # Identify if shape contains lists
@@ -276,16 +277,19 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
         im_dpi, _ = image.dpi
 
         # Open it with PIL
-        pil_image = Image.open(BytesIO(image_bytes))
-
-        # shape has picture
-        prov = self.generate_prov(shape, slide_ind, "")
-        doc.add_picture(
-            parent=parent_slide,
-            image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
-            caption=None,
-            prov=prov,
-        )
+        try:
+            pil_image = Image.open(BytesIO(image_bytes))
+
+            # shape has picture
+            prov = self.generate_prov(shape, slide_ind, "")
+            doc.add_picture(
+                parent=parent_slide,
+                image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
+                caption=None,
+                prov=prov,
+            )
+        except (UnidentifiedImageError, OSError) as e:
+            _log.warning(f"Warning: image cannot be loaded by Pillow: {e}")
         return
 
     def handle_tables(self, shape, parent_slide, slide_ind, doc):

{docling-2.14.0 → docling-2.15.0}/docling/cli/main.py

@@ -164,6 +164,11 @@ def convert(
     to_formats: List[OutputFormat] = typer.Option(
         None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
+    headers: str = typer.Option(
+        None,
+        "--headers",
+        help="Specify http request headers used when fetching url input sources in the form of a JSON string",
+    ),
     image_export_mode: Annotated[
         ImageRefMode,
         typer.Option(
@@ -279,12 +284,19 @@ def convert(
     if from_formats is None:
         from_formats = [e for e in InputFormat]
 
+    parsed_headers: Optional[Dict[str, str]] = None
+    if headers is not None:
+        headers_t = TypeAdapter(Dict[str, str])
+        parsed_headers = headers_t.validate_json(headers)
+
     with tempfile.TemporaryDirectory() as tempdir:
         input_doc_paths: List[Path] = []
         for src in input_sources:
             try:
                 # check if we can fetch some remote url
-                source = resolve_source_to_path(source=src, workdir=Path(tempdir))
+                source = resolve_source_to_path(
+                    source=src, headers=parsed_headers, workdir=Path(tempdir)
+                )
                 input_doc_paths.append(source)
             except FileNotFoundError:
                 err_console.print(
@@ -390,7 +402,7 @@ def convert(
         start_time = time.time()
 
         conv_results = doc_converter.convert_all(
-            input_doc_paths, raises_on_error=abort_on_error
+            input_doc_paths, headers=parsed_headers, raises_on_error=abort_on_error
         )
 
         output.mkdir(parents=True, exist_ok=True)

{docling-2.14.0 → docling-2.15.0}/docling/datamodel/document.py

@@ -227,13 +227,18 @@ class _DummyBackend(AbstractDocumentBackend):
 class _DocumentConversionInput(BaseModel):
 
     path_or_stream_iterator: Iterable[Union[Path, str, DocumentStream]]
+    headers: Optional[Dict[str, str]] = None
     limits: Optional[DocumentLimits] = DocumentLimits()
 
     def docs(
         self, format_options: Dict[InputFormat, "FormatOption"]
     ) -> Iterable[InputDocument]:
         for item in self.path_or_stream_iterator:
-            obj = resolve_source_to_stream(item) if isinstance(item, str) else item
+            obj = (
+                resolve_source_to_stream(item, self.headers)
+                if isinstance(item, str)
+                else item
+            )
             format = self._guess_format(obj)
             backend: Type[AbstractDocumentBackend]
             if format not in format_options.keys():

{docling-2.14.0 → docling-2.15.0}/docling/document_converter.py

@@ -176,6 +176,7 @@ class DocumentConverter:
     def convert(
         self,
         source: Union[Path, str, DocumentStream],  # TODO review naming
+        headers: Optional[Dict[str, str]] = None,
         raises_on_error: bool = True,
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -185,6 +186,7 @@ class DocumentConverter:
             raises_on_error=raises_on_error,
             max_num_pages=max_num_pages,
             max_file_size=max_file_size,
+            headers=headers,
         )
         return next(all_res)
 
@@ -192,6 +194,7 @@ class DocumentConverter:
     def convert_all(
         self,
         source: Iterable[Union[Path, str, DocumentStream]],  # TODO review naming
+        headers: Optional[Dict[str, str]] = None,
         raises_on_error: bool = True,  # True: raises on first conversion error; False: does not raise on conv error
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -201,8 +204,7 @@ class DocumentConverter:
             max_file_size=max_file_size,
         )
         conv_input = _DocumentConversionInput(
-            path_or_stream_iterator=source,
-            limits=limits,
+            path_or_stream_iterator=source, limits=limits, headers=headers
         )
         conv_res_iter = self._convert(conv_input, raises_on_error=raises_on_error)
 

{docling-2.14.0 → docling-2.15.0}/docling/models/base_ocr_model.py

@@ -138,18 +138,31 @@ class BaseOcrModel(BasePageModel):
 
     def draw_ocr_rects_and_cells(self, conv_res, page, ocr_rects, show: bool = False):
         image = copy.deepcopy(page.image)
+        scale_x = image.width / page.size.width
+        scale_y = image.height / page.size.height
+
         draw = ImageDraw.Draw(image, "RGBA")
 
         # Draw OCR rectangles as yellow filled rect
         for rect in ocr_rects:
             x0, y0, x1, y1 = rect.as_tuple()
+            y0 *= scale_x
+            y1 *= scale_y
+            x0 *= scale_x
+            x1 *= scale_x
+
             shade_color = (255, 255, 0, 40)  # transparent yellow
             draw.rectangle([(x0, y0), (x1, y1)], fill=shade_color, outline=None)
 
         # Draw OCR and programmatic cells
         for tc in page.cells:
             x0, y0, x1, y1 = tc.bbox.as_tuple()
-            color = "red"
+            y0 *= scale_x
+            y1 *= scale_y
+            x0 *= scale_x
+            x1 *= scale_x
+
+            color = "gray"
             if isinstance(tc, OcrCell):
                 color = "magenta"
             draw.rectangle([(x0, y0), (x1, y1)], outline=color)

{docling-2.14.0 → docling-2.15.0}/docling/models/layout_model.py

@@ -67,29 +67,9 @@ class LayoutModel(BasePageModel):
         - Right: Clusters including FORM, KEY_VALUE_REGION, and PICTURE.
         Includes label names and confidence scores for each cluster.
         """
-        label_to_color = {
-            DocItemLabel.TEXT: (255, 255, 153),  # Light Yellow
-            DocItemLabel.CAPTION: (255, 204, 153),  # Light Orange
-            DocItemLabel.LIST_ITEM: (153, 153, 255),  # Light Purple
-            DocItemLabel.FORMULA: (192, 192, 192),  # Gray
-            DocItemLabel.TABLE: (255, 204, 204),  # Light Pink
-            DocItemLabel.PICTURE: (255, 204, 164),  # Light Beige
-            DocItemLabel.SECTION_HEADER: (255, 153, 153),  # Light Red
-            DocItemLabel.PAGE_HEADER: (204, 255, 204),  # Light Green
-            DocItemLabel.PAGE_FOOTER: (
-                204,
-                255,
-                204,
-            ),  # Light Green (same as Page-Header)
-            DocItemLabel.TITLE: (255, 153, 153),  # Light Red (same as Section-Header)
-            DocItemLabel.FOOTNOTE: (200, 200, 255),  # Light Blue
-            DocItemLabel.DOCUMENT_INDEX: (220, 220, 220),  # Light Gray
-            DocItemLabel.CODE: (125, 125, 125),  # Gray
-            DocItemLabel.CHECKBOX_SELECTED: (255, 182, 193),  # Pale Green
-            DocItemLabel.CHECKBOX_UNSELECTED: (255, 182, 193),  # Light Pink
-            DocItemLabel.FORM: (200, 255, 255),  # Light Cyan
-            DocItemLabel.KEY_VALUE_REGION: (183, 65, 14),  # Rusty orange
-        }
+        scale_x = page.image.width / page.size.width
+        scale_y = page.image.height / page.size.height
+
         # Filter clusters for left and right images
         exclude_labels = {
             DocItemLabel.FORM,
@@ -118,6 +98,11 @@ class LayoutModel(BasePageModel):
                     cell_color = (0, 0, 0, 40)  # Transparent black for cells
                     for tc in c.cells:
                         cx0, cy0, cx1, cy1 = tc.bbox.as_tuple()
+                        cx0 *= scale_x
+                        cx1 *= scale_x
+                        cy0 *= scale_x
+                        cy1 *= scale_y
+
                         draw.rectangle(
                             [(cx0, cy0), (cx1, cy1)],
                             outline=None,
@@ -125,8 +110,16 @@ class LayoutModel(BasePageModel):
                         )
                     # Draw cluster rectangle
                     x0, y0, x1, y1 = c.bbox.as_tuple()
-                    cluster_fill_color = (*list(label_to_color.get(c.label)), 70)
-                    cluster_outline_color = (*list(label_to_color.get(c.label)), 255)
+                    x0 *= scale_x
+                    x1 *= scale_x
+                    y0 *= scale_x
+                    y1 *= scale_y
+
+                    cluster_fill_color = (*list(DocItemLabel.get_color(c.label)), 70)
+                    cluster_outline_color = (
+                        *list(DocItemLabel.get_color(c.label)),
+                        255,
+                    )
                     draw.rectangle(
                         [(x0, y0), (x1, y1)],
                         outline=cluster_outline_color,

{docling-2.14.0 → docling-2.15.0}/docling/models/table_structure_model.py

@@ -66,23 +66,43 @@ class TableStructureModel(BasePageModel):
         show: bool = False,
     ):
         assert page._backend is not None
+        assert page.size is not None
 
         image = (
             page._backend.get_page_image()
         )  # make new image to avoid drawing on the saved ones
+
+        scale_x = image.width / page.size.width
+        scale_y = image.height / page.size.height
+
         draw = ImageDraw.Draw(image)
 
         for table_element in tbl_list:
             x0, y0, x1, y1 = table_element.cluster.bbox.as_tuple()
+            y0 *= scale_x
+            y1 *= scale_y
+            x0 *= scale_x
+            x1 *= scale_x
+
             draw.rectangle([(x0, y0), (x1, y1)], outline="red")
 
             for cell in table_element.cluster.cells:
                 x0, y0, x1, y1 = cell.bbox.as_tuple()
+                x0 *= scale_x
+                x1 *= scale_x
+                y0 *= scale_x
+                y1 *= scale_y
+
                 draw.rectangle([(x0, y0), (x1, y1)], outline="green")
 
             for tc in table_element.table_cells:
                 if tc.bbox is not None:
                     x0, y0, x1, y1 = tc.bbox.as_tuple()
+                    x0 *= scale_x
+                    x1 *= scale_x
+                    y0 *= scale_x
+                    y1 *= scale_y
+
                     if tc.column_header:
                         width = 3
                     else:

{docling-2.14.0 → docling-2.15.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.14.0"  # DO NOT EDIT, updated automatically
+version = "2.15.0"  # DO NOT EDIT, updated automatically
 description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Panos Vagenas <pva@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -25,7 +25,7 @@ packages = [{include = "docling"}]
 # actual dependencies:
 ######################
 python = "^3.9"
-docling-core = { version = "^2.12.1", extras = ["chunking"] }
+docling-core = { version = "^2.13.1", extras = ["chunking"] }
 pydantic = "^2.0.0"
 docling-ibm-models = "^3.1.0"
 deepsearch-glm = "^1.0.0"