docling 1.7.0__tar.gz → 1.7.1__tar.gz

{docling-1.7.0 → docling-1.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.7.0
+Version: 1.7.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -23,7 +23,7 @@ Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.1.2,<2.0.0)
-Requires-Dist: docling-parse (>=1.0.0,<2.0.0)
+Requires-Dist: docling-parse (>=1.1.1,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)

{docling-1.7.0 → docling-1.7.1}/docling/backend/docling_parse_backend.py

@@ -23,9 +23,19 @@ class DoclingParsePageBackend(PdfPageBackend):
         self._ppage = page_obj
 
         parsed_page = parser.parse_pdf_from_key_on_page(document_hash, page_no)
-        self._dpage = parsed_page["pages"][0]
+
+        self._dpage = None
+        self.broken_page = "pages" not in parsed_page
+        if not self.broken_page:
+            self._dpage = parsed_page["pages"][0]
+        else:
+            raise RuntimeError(
+                f"Page {page_no} of document {document_hash} could not be parsed."
+            )
 
     def get_text_in_rect(self, bbox: BoundingBox) -> str:
+        if self.broken_page:
+            return ""
         # Find intersecting cells on the page
         text_piece = ""
         page_size = self.get_size()
@@ -60,6 +70,9 @@ class DoclingParsePageBackend(PdfPageBackend):
         cells = []
         cell_counter = 0
 
+        if self.broken_page:
+            return cells
+
         page_size = self.get_size()
 
         parser_width = self._dpage["width"]

{docling-1.7.0 → docling-1.7.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.7.0"  # DO NOT EDIT, updated automatically
+version = "1.7.1"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 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>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -32,7 +32,7 @@ pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
-docling-parse = "^1.0.0"
+docling-parse = "^1.1.1"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
 scipy = "^1.14.1"