docling-core 2.3.2__tar.gz → 2.4.1__tar.gz

{docling_core-2.3.2 → docling_core-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.3.2
+Version: 2.4.1
 Summary: A python library to define and validate data types in Docling.
 Home-page: https://ds4sd.github.io/
 License: MIT
@@ -29,7 +29,7 @@ Requires-Dist: jsonref (>=1.1.0,<2.0.0)
 Requires-Dist: jsonschema (>=4.16.0,<5.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pillow (>=10.3.0,<11.0.0)
-Requires-Dist: pydantic (>=2.6.0,<3.0.0)
+Requires-Dist: pydantic (>=2.6.0,<2.10)
 Requires-Dist: tabulate (>=0.9.0,<0.10.0)
 Project-URL: Repository, https://github.com/DS4SD/docling-core
 Description-Content-Type: text/markdown

{docling_core-2.3.2 → docling_core-2.4.1}/docling_core/types/doc/document.py

@@ -551,6 +551,28 @@ class DocItem(
 
         return location
 
+    def get_image(self, doc: "DoclingDocument") -> Optional[PILImage.Image]:
+        """Returns the image of this DocItem.
+
+        The function returns None if this DocItem has no valid provenance or
+        if a valid image of the page containing this DocItem is not available
+        in doc.
+        """
+        if not len(self.prov):
+            return None
+
+        page = doc.pages.get(self.prov[0].page_no)
+        if page is None or page.size is None or page.image is None:
+            return None
+
+        page_image = page.image.pil_image
+        crop_bbox = (
+            self.prov[0]
+            .bbox.to_top_left_origin(page_height=page.size.height)
+            .scaled(scale=page_image.height / page.size.height)
+        )
+        return page_image.crop(crop_bbox.as_tuple())
+
 
 class TextItem(DocItem):
     """TextItem."""
@@ -633,6 +655,20 @@ class FloatingItem(DocItem):
             text += cap.resolve(doc).text
         return text
 
+    def get_image(self, doc: "DoclingDocument") -> Optional[PILImage.Image]:
+        """Returns the image corresponding to this FloatingItem.
+
+        This function returns the PIL image from self.image if one is available.
+        Otherwise, it uses DocItem.get_image to get an image of this FloatingItem.
+
+        In particular, when self.image is None, the function returns None if this
+        FloatingItem has no valid provenance or the doc does not contain a valid image
+        for the required page.
+        """
+        if self.image is not None:
+            return self.image.pil_image
+        return super().get_image(doc=doc)
+
 
 class PictureItem(FloatingItem):
     """PictureItem."""
@@ -1255,7 +1291,10 @@ class DoclingDocument(BaseModel):
                 # If the child is a NodeItem, recursively traverse it
                 if not isinstance(child, PictureItem) or traverse_pictures:
                     yield from self.iterate_items(
-                        child, _level=_level + 1, with_groups=with_groups
+                        child,
+                        _level=_level + 1,
+                        with_groups=with_groups,
+                        page_no=page_no,
                     )
 
     def print_element_tree(self):
@@ -1281,6 +1320,7 @@ class DoclingDocument(BaseModel):
         image_mode: ImageRefMode = ImageRefMode.PLACEHOLDER,
         indent: int = 4,
         text_width: int = -1,
+        page_no: Optional[int] = None,
     ) -> str:
         r"""Serialize to Markdown.
 
@@ -1317,7 +1357,7 @@ class DoclingDocument(BaseModel):
         in_list = False  # Track if we're currently processing list items
 
         for ix, (item, level) in enumerate(
-            self.iterate_items(self.body, with_groups=True)
+            self.iterate_items(self.body, with_groups=True, page_no=page_no)
         ):
             # If we've moved to a lower level, we're exiting one or more groups
             if level < previous_level:

{docling_core-2.3.2 → docling_core-2.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-core"
-version = "2.3.2"
+version = "2.4.1"
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 authors = [
@@ -48,7 +48,7 @@ generate_docs = "docling_core.utils.generate_docs:main"
 [tool.poetry.dependencies]
 python = "^3.9"
 jsonschema = "^4.16.0"
-pydantic = "^2.6.0"
+pydantic = ">=2.6.0,<2.10"
 jsonref = "^1.1.0"
 tabulate = "^0.9.0"
 pandas = "^2.1.4"