fix: Upgrade docling-parse to 1.1.1, safety checks for failed parse o…

…n pages (#45) * Put safety-checks for failed parse of pages Signed-off-by: Christoph Auer <[email protected]> * Bump to docling-parse 1.1.1 Signed-off-by: Christoph Auer <[email protected]> --------- Signed-off-by: Christoph Auer <[email protected]>
DS4SD · Aug 23, 2024 · 7e84533 · 7e84533
1 parent 1930f08
commit 7e84533
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 28 deletions.
diff --git a/docling/backend/docling_parse_backend.py b/docling/backend/docling_parse_backend.py
@@ -23,9 +23,15 @@ def __init__(
         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]
 
     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 +66,9 @@ def get_text_cells(self) -> Iterable[Cell]:
         cells = []
         cell_counter = 0
 
+        if self.broken_page:
+            return cells
+
         page_size = self.get_size()
 
         parser_width = self._dpage["width"]

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -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"