Merge branch 'main' into feat-support-google-ocr

DS4SD · Jan 8, 2025 · e571e31 · e571e31
2 parents aae5167 + ead396a
commit e571e31
Show file tree

Hide file tree

Showing 126 changed files with 88,667 additions and 2,245 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,22 @@
+## [v2.14.0](https://github.com/DS4SD/docling/releases/tag/v2.14.0) - 2024-12-18
+
+### Feature
+
+* Create a backend to transform PubMed XML files to DoclingDocument ([#557](https://github.com/DS4SD/docling/issues/557)) ([`fd03480`](https://github.com/DS4SD/docling/commit/fd034802b65a0e567531b8ecc9a283aaf030e050))
+
+## [v2.13.0](https://github.com/DS4SD/docling/releases/tag/v2.13.0) - 2024-12-17
+
+### Feature
+
+* Updated Layout processing with forms and key-value areas ([#530](https://github.com/DS4SD/docling/issues/530)) ([`60dc852`](https://github.com/DS4SD/docling/commit/60dc852f16dc1adbb5e9284c81a146043a301ec1))
+* Create a backend to parse USPTO patents into DoclingDocument ([#606](https://github.com/DS4SD/docling/issues/606)) ([`4e08750`](https://github.com/DS4SD/docling/commit/4e087504cc4b04210574e69f616badcddfa1f8e5))
+* Add Easyocr parameter recog_network ([#613](https://github.com/DS4SD/docling/issues/613)) ([`3b53bd3`](https://github.com/DS4SD/docling/commit/3b53bd38c8efcc5ba54421fbfa90d047f1a61f82))
+
+### Documentation
+
+* Add Haystack RAG example ([#615](https://github.com/DS4SD/docling/issues/615)) ([`3e599c7`](https://github.com/DS4SD/docling/commit/3e599c7bbeef211dc346e9bc1d3a249113fcc4e4))
+* Fix the path to the run_with_accelerator.py example ([#608](https://github.com/DS4SD/docling/issues/608)) ([`3bb3bf5`](https://github.com/DS4SD/docling/commit/3bb3bf57150c9705a055982e6fb0cc8d1408f161))
+
 ## [v2.12.0](https://github.com/DS4SD/docling/releases/tag/v2.12.0) - 2024-12-13
 
 ### Feature

diff --git a/docling/backend/html_backend.py b/docling/backend/html_backend.py
@@ -37,10 +37,10 @@ def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]
 
         try:
             if isinstance(self.path_or_stream, BytesIO):
-                text_stream = self.path_or_stream.getvalue().decode("utf-8")
+                text_stream = self.path_or_stream.getvalue()
                 self.soup = BeautifulSoup(text_stream, "html.parser")
             if isinstance(self.path_or_stream, Path):
-                with open(self.path_or_stream, "r", encoding="utf-8") as f:
+                with open(self.path_or_stream, "rb") as f:
                     html_content = f.read()
                     self.soup = BeautifulSoup(html_content, "html.parser")
         except Exception as e:

diff --git a/docling/backend/mspowerpoint_backend.py b/docling/backend/mspowerpoint_backend.py
@@ -16,7 +16,7 @@
     TableCell,
     TableData,
 )
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 from pptx import Presentation
 from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
 
@@ -120,6 +120,7 @@ def handle_text_elements(self, shape, parent_slide, slide_ind, doc):
         bullet_type = "None"
         list_text = ""
         list_label = GroupLabel.LIST
+        doc_label = DocItemLabel.LIST_ITEM
         prov = self.generate_prov(shape, slide_ind, shape.text.strip())
 
         # Identify if shape contains lists
@@ -276,16 +277,19 @@ def handle_pictures(self, shape, parent_slide, slide_ind, doc):
         im_dpi, _ = image.dpi
 
         # Open it with PIL
-        pil_image = Image.open(BytesIO(image_bytes))
-
-        # shape has picture
-        prov = self.generate_prov(shape, slide_ind, "")
-        doc.add_picture(
-            parent=parent_slide,
-            image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
-            caption=None,
-            prov=prov,
-        )
+        try:
+            pil_image = Image.open(BytesIO(image_bytes))
+
+            # shape has picture
+            prov = self.generate_prov(shape, slide_ind, "")
+            doc.add_picture(
+                parent=parent_slide,
+                image=ImageRef.from_pil(image=pil_image, dpi=im_dpi),
+                caption=None,
+                prov=prov,
+            )
+        except (UnidentifiedImageError, OSError) as e:
+            _log.warning(f"Warning: image cannot be loaded by Pillow: {e}")
         return
 
     def handle_tables(self, shape, parent_slide, slide_ind, doc):

diff --git a/docling/backend/xml/__init__.py b/docling/backend/xml/__init__.py