docling 2.7.0__tar.gz → 2.7.1__tar.gz

{docling-2.7.0 → docling-2.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.7.0
+Version: 2.7.1
 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
@@ -31,12 +31,13 @@ Requires-Dist: docling-parse (>=2.0.5,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
+Requires-Dist: lxml (>=4.0.0,<6.0.0)
 Requires-Dist: marko (>=2.1.2,<3.0.0)
 Requires-Dist: ocrmac (>=1.0.0,<2.0.0) ; (sys_platform == "darwin") and (extra == "ocrmac")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
-Requires-Dist: pydantic (>=2.0.0,<3.0.0)
+Requires-Dist: pydantic (>=2.0.0,<2.10)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
 Requires-Dist: python-docx (>=1.1.2,<2.0.0)
@@ -71,12 +72,13 @@ Description-Content-Type: text/markdown
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/DS4SD/docling)](https://opensource.org/licenses/MIT)
+[![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
 
 Docling parses documents and exports them to the desired format with ease and speed.
 
 ## Features
 
-* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to Markdown and JSON
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 🤖 Easy integration with LlamaIndex 🦙 & LangChain 🦜🔗 for powerful RAG / QA applications

{docling-2.7.0 → docling-2.7.1}/README.md

@@ -20,12 +20,13 @@
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/DS4SD/docling)](https://opensource.org/licenses/MIT)
+[![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
 
 Docling parses documents and exports them to the desired format with ease and speed.
 
 ## Features
 
-* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON
+* 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to Markdown and JSON
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
 * 🤖 Easy integration with LlamaIndex 🦙 & LangChain 🦜🔗 for powerful RAG / QA applications

{docling-2.7.0 → docling-2.7.1}/docling/backend/msword_backend.py

@@ -14,7 +14,8 @@ from docling_core.types.doc import (
     TableData,
 )
 from lxml import etree
-from PIL import Image
+from lxml.etree import XPath
+from PIL import Image, UnidentifiedImageError
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
 from docling.datamodel.base_models import InputFormat
@@ -132,8 +133,14 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
     def walk_linear(self, body, docx_obj, doc) -> DoclingDocument:
         for element in body:
             tag_name = etree.QName(element).localname
+
             # Check for Inline Images (blip elements)
-            drawing_blip = element.xpath(".//a:blip")
+            namespaces = {
+                "a": "http://schemas.openxmlformats.org/drawingml/2006/main",
+                "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
+            }
+            xpath_expr = XPath(".//a:blip", namespaces=namespaces)
+            drawing_blip = xpath_expr(element)
 
             # Check for Tables
             if element.tag.endswith("tbl"):
@@ -210,7 +217,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         paragraph = docx.text.paragraph.Paragraph(element, docx_obj)
 
         if paragraph.text is None:
-            # _log.warn(f"paragraph has text==None")
             return
         text = paragraph.text.strip()
         # if len(text)==0 # keep empty paragraphs, they seperate adjacent lists!
@@ -502,10 +508,17 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         image_data = get_docx_image(element, drawing_blip)
         image_bytes = BytesIO(image_data)
         # Open the BytesIO object with PIL to create an Image
-        pil_image = Image.open(image_bytes)
-        doc.add_picture(
-            parent=self.parents[self.level],
-            image=ImageRef.from_pil(image=pil_image, dpi=72),
-            caption=None,
-        )
+        try:
+            pil_image = Image.open(image_bytes)
+            doc.add_picture(
+                parent=self.parents[self.level],
+                image=ImageRef.from_pil(image=pil_image, dpi=72),
+                caption=None,
+            )
+        except (UnidentifiedImageError, OSError) as e:
+            _log.warning("Warning: image cannot be loaded by Pillow")
+            doc.add_picture(
+                parent=self.parents[self.level],
+                caption=None,
+            )
         return

{docling-2.7.0 → docling-2.7.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.7.0"  # DO NOT EDIT, updated automatically
+version = "2.7.1"  # 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"
@@ -25,7 +25,7 @@ packages = [{include = "docling"}]
 # actual dependencies:
 ######################
 python = "^3.9"
-pydantic = "^2.0.0"
+pydantic = ">=2.0.0,<2.10"
 docling-core = "^2.4.0"
 docling-ibm-models = "^2.0.6"
 deepsearch-glm = "^0.26.1"
@@ -48,6 +48,7 @@ beautifulsoup4 = "^4.12.3"
 pandas = "^2.1.4"
 marko = "^2.1.2"
 openpyxl = "^3.1.5"
+lxml = ">=4.0.0,<6.0.0"
 ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
 
 [tool.poetry.group.dev.dependencies]