docling-core 2.48.3__tar.gz → 2.49.0__tar.gz

{docling_core-2.48.3 → docling_core-2.49.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling-core
-Version: 2.48.3
+Version: 2.49.0
 Summary: A python library to define and validate data types in Docling.
 Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>
@@ -15,12 +15,17 @@ Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Database
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -29,7 +34,7 @@ Requires-Dist: pydantic!=2.10.0,!=2.10.1,!=2.10.2,<3.0.0,>=2.6.0
 Requires-Dist: jsonref<2.0.0,>=1.1.0
 Requires-Dist: tabulate<0.10.0,>=0.9.0
 Requires-Dist: pandas<3.0.0,>=2.1.4
-Requires-Dist: pillow<12.0.0,>=10.0.0
+Requires-Dist: pillow<13.0.0,>=10.0.0
 Requires-Dist: pyyaml<7.0.0,>=5.1
 Requires-Dist: typing-extensions<5.0.0,>=4.12.2
 Requires-Dist: typer<0.20.0,>=0.12.5
@@ -39,7 +44,7 @@ Requires-Dist: semchunk<3.0.0,>=2.2.0; extra == "chunking"
 Requires-Dist: transformers<5.0.0,>=4.34.0; extra == "chunking"
 Provides-Extra: chunking-openai
 Requires-Dist: semchunk; extra == "chunking-openai"
-Requires-Dist: tiktoken<0.10.0,>=0.9.0; extra == "chunking-openai"
+Requires-Dist: tiktoken<0.13.0,>=0.9.0; extra == "chunking-openai"
 Dynamic: license-file
 
 # Docling Core

{docling_core-2.48.3 → docling_core-2.49.0}/docling_core/transforms/serializer/markdown.py

@@ -40,6 +40,7 @@ from docling_core.types.doc.document import (
     ContentLayer,
     DescriptionAnnotation,
     DocItem,
+    DocItemLabel,
     DoclingDocument,
     FloatingItem,
     Formatting,
@@ -140,6 +141,10 @@ class MarkdownTextSerializer(BaseModel, BaseTextSerializer):
             text = item.text
             processing_pending = True
 
+        if item.label == DocItemLabel.CHECKBOX_SELECTED:
+            text = f"- [x] {text}"
+        if item.label == DocItemLabel.CHECKBOX_UNSELECTED:
+            text = f"- [ ] {text}"
         if isinstance(item, (ListItem, TitleItem, SectionHeaderItem)):
             if not has_inline_repr:
                 # case where processing/formatting should be applied first (in inner scope)

{docling_core-2.48.3 → docling_core-2.49.0}/docling_core/types/doc/document.py

@@ -2267,7 +2267,7 @@ class DoclingDocument(BaseModel):
             if not success:
                 del to_be_deleted_items[stack_]
             else:
-                _logger.info(f"deleted item in tree at stack: {stack_} => {ref_}")
+                _logger.debug(f"deleted item in tree at stack: {stack_} => {ref_}")
 
         # Create a new lookup of the orphans:
         # dict of item_label (`texts`, `tables`, ...) to a
@@ -4354,7 +4354,7 @@ class DoclingDocument(BaseModel):
         if isinstance(filename, str):
             filename = Path(filename)
         with open(filename, encoding="utf-8") as f:
-            data = yaml.load(f, Loader=yaml.FullLoader)
+            data = yaml.load(f, Loader=yaml.SafeLoader)
         return DoclingDocument.model_validate(data)
 
     def export_to_dict(

{docling_core-2.48.3 → docling_core-2.49.0}/docling_core.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling-core
-Version: 2.48.3
+Version: 2.49.0
 Summary: A python library to define and validate data types in Docling.
 Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>
@@ -15,12 +15,17 @@ Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Database
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -29,7 +34,7 @@ Requires-Dist: pydantic!=2.10.0,!=2.10.1,!=2.10.2,<3.0.0,>=2.6.0
 Requires-Dist: jsonref<2.0.0,>=1.1.0
 Requires-Dist: tabulate<0.10.0,>=0.9.0
 Requires-Dist: pandas<3.0.0,>=2.1.4
-Requires-Dist: pillow<12.0.0,>=10.0.0
+Requires-Dist: pillow<13.0.0,>=10.0.0
 Requires-Dist: pyyaml<7.0.0,>=5.1
 Requires-Dist: typing-extensions<5.0.0,>=4.12.2
 Requires-Dist: typer<0.20.0,>=0.12.5
@@ -39,7 +44,7 @@ Requires-Dist: semchunk<3.0.0,>=2.2.0; extra == "chunking"
 Requires-Dist: transformers<5.0.0,>=4.34.0; extra == "chunking"
 Provides-Extra: chunking-openai
 Requires-Dist: semchunk; extra == "chunking-openai"
-Requires-Dist: tiktoken<0.10.0,>=0.9.0; extra == "chunking-openai"
+Requires-Dist: tiktoken<0.13.0,>=0.9.0; extra == "chunking-openai"
 Dynamic: license-file
 
 # Docling Core

{docling_core-2.48.3 → docling_core-2.49.0}/docling_core.egg-info/requires.txt

@@ -3,7 +3,7 @@ pydantic!=2.10.0,!=2.10.1,!=2.10.2,<3.0.0,>=2.6.0
 jsonref<2.0.0,>=1.1.0
 tabulate<0.10.0,>=0.9.0
 pandas<3.0.0,>=2.1.4
-pillow<12.0.0,>=10.0.0
+pillow<13.0.0,>=10.0.0
 pyyaml<7.0.0,>=5.1
 typing-extensions<5.0.0,>=4.12.2
 typer<0.20.0,>=0.12.5
@@ -15,4 +15,4 @@ transformers<5.0.0,>=4.34.0
 
 [chunking-openai]
 semchunk
-tiktoken<0.10.0,>=0.9.0
+tiktoken<0.13.0,>=0.9.0

{docling_core-2.48.3 → docling_core-2.49.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-core"
-version = "2.48.3"  # DO NOT EDIT, updated automatically
+version = "2.49.0"  # DO NOT EDIT, updated automatically
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 license-files = ["LICENSE"]
@@ -26,12 +26,17 @@ classifiers = [
     "Intended Audience :: Science/Research",
     "Natural Language :: English",
     "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3",
     "Topic :: Database",
     "Topic :: Scientific/Engineering :: Information Analysis",
     "Topic :: Software Development :: Libraries :: Python Modules",
     "Typing :: Typed",
     "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
 ]
 requires-python = '>=3.9,<4.0'
 dependencies = [
@@ -40,7 +45,7 @@ dependencies = [
     'jsonref (>=1.1.0,<2.0.0)',
     'tabulate (>=0.9.0,<0.10.0)',
     'pandas (>=2.1.4,<3.0.0)',
-    'pillow (>=10.0.0,<12.0.0)',
+    'pillow (>=10.0.0,<13.0.0)',
     'pyyaml (>=5.1,<7.0.0)',
     'typing-extensions (>=4.12.2,<5.0.0)',
     'typer (>=0.12.5,<0.20.0)',
@@ -61,7 +66,7 @@ docling-view = "docling_core.cli.view:app"
 
 [project.optional-dependencies]
 chunking = ['semchunk (>=2.2.0,<3.0.0)', 'transformers (>=4.34.0,<5.0.0)']
-chunking-openai = ['semchunk', 'tiktoken (>=0.9.0,<0.10.0)']
+chunking-openai = ['semchunk', 'tiktoken (>=0.9.0,<0.13.0)']
 
 [dependency-groups]
 dev = [

{docling_core-2.48.3 → docling_core-2.49.0}/test/test_docling_doc.py

@@ -1973,7 +1973,7 @@ def test_export_with_precision():
             yaml.dump(act_data, f, default_flow_style=False)
     else:
         with open(exp_file, "r", encoding="utf-8") as f:
-            exp_data = yaml.load(f, Loader=yaml.FullLoader)
+            exp_data = yaml.load(f, Loader=yaml.SafeLoader)
         assert act_data == exp_data
 
 

{docling_core-2.48.3 → docling_core-2.49.0}/test/test_serialization.py

@@ -113,6 +113,23 @@ def test_md_cross_page_list_page_break():
     verify(exp_file=src.with_suffix(".gt.md"), actual=actual)
 
 
+def test_md_checkboxes():
+    src = Path("./test/data/doc/checkboxes.json")
+    doc = DoclingDocument.load_from_json(src)
+
+    ser = MarkdownDocSerializer(
+        doc=doc,
+        params=MarkdownParams(
+            image_mode=ImageRefMode.PLACEHOLDER,
+            image_placeholder="<!-- image -->",
+            page_break_placeholder="<!-- page break -->",
+            labels=_DEFAULT_LABELS - {DocItemLabel.PICTURE},
+        ),
+    )
+    actual = ser.serialize().text
+    verify(exp_file=src.parent / f"{src.stem}.gt.md", actual=actual)
+
+
 def test_md_cross_page_list_page_break_none():
     src = Path("./test/data/doc/activities.json")
     doc = DoclingDocument.load_from_json(src)