docling 1.7.0__py3-none-any.whl → 1.7.1__py3-none-any.whl

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.dist-info → docling-1.7.1.dist-info}/METADATA

@@ -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.dist-info → docling-1.7.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
 docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/abstract_backend.py,sha256=wvrywm1pPt79L5Dt_da5QGmf9dDzjBGj1rSaUQxqI8s,1432
-docling/backend/docling_parse_backend.py,sha256=E4JFpWBamiU8vRmHvgMZLU7lOxtUMq85TV5hMrGvWJI,7070
+docling/backend/docling_parse_backend.py,sha256=hXyF2VPPdLs7APWEXTlfz0wI86rUGYa67Q73zgTB-Ug,7438
 docling/backend/pypdfium2_backend.py,sha256=84AnFah8Ztk-j8_9MTHalPU3a9fClrEz7A_rfzWDkFc,8122
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=5VHit5h7OleKnbhvy-sWDxQLizEdNrGUBrypyzwHyAE,8604
@@ -21,7 +21,7 @@ docling/pipeline/standard_model_pipeline.py,sha256=UTjyaEXvz9htYZz-IMTkn11cZwNjg
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/layout_utils.py,sha256=FOFbL0hKzUoWXdZaeUvEtFqKv0IkPifIr4sdGW4suKs,31804
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-1.7.0.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling-1.7.0.dist-info/METADATA,sha256=yqKqPH3w2IxOhmdqHy0nJcYKDrJAufx6uF1Ti44pRs4,7229
-docling-1.7.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.7.0.dist-info/RECORD,,
+docling-1.7.1.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling-1.7.1.dist-info/METADATA,sha256=ADdVabYgc4VEIGKhM-tI6XBU_CG9tzKl_au69TZ9LbY,7229
+docling-1.7.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.7.1.dist-info/RECORD,,