docling 2.25.1__tar.gz → 2.25.2__tar.gz

{docling-2.25.1 → docling-2.25.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.25.1
+Version: 2.25.2
 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
@@ -185,7 +185,7 @@ For individual model usage, please refer to the model licenses found in the orig
 
 Docling has been brought to you by IBM.
 
-[supported_formats]: https://ds4sd.github.io/docling/supported_formats/
+[supported_formats]: https://ds4sd.github.io/docling/usage/supported_formats/
 [docling_document]: https://ds4sd.github.io/docling/concepts/docling_document/
 [integrations]: https://ds4sd.github.io/docling/integrations/
 

{docling-2.25.1 → docling-2.25.2}/README.md

@@ -123,6 +123,6 @@ For individual model usage, please refer to the model licenses found in the orig
 
 Docling has been brought to you by IBM.
 
-[supported_formats]: https://ds4sd.github.io/docling/supported_formats/
+[supported_formats]: https://ds4sd.github.io/docling/usage/supported_formats/
 [docling_document]: https://ds4sd.github.io/docling/concepts/docling_document/
 [integrations]: https://ds4sd.github.io/docling/integrations/

{docling-2.25.1 → docling-2.25.2}/docling/utils/layout_postprocessor.py

@@ -203,6 +203,7 @@ class LayoutPostprocessor:
         """Initialize processor with cells and spatial indices."""
         self.cells = cells
         self.page_size = page_size
+        self.all_clusters = clusters
         self.regular_clusters = [
             c for c in clusters if c.label not in self.SPECIAL_TYPES
         ]
@@ -267,7 +268,7 @@ class LayoutPostprocessor:
         # Handle orphaned cells
         unassigned = self._find_unassigned_cells(clusters)
         if unassigned:
-            next_id = max((c.id for c in clusters), default=0) + 1
+            next_id = max((c.id for c in self.all_clusters), default=0) + 1
             orphan_clusters = []
             for i, cell in enumerate(unassigned):
                 conf = 1.0

{docling-2.25.1 → docling-2.25.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.25.1"  # DO NOT EDIT, updated automatically
+version = "2.25.2"  # 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"