docling-core 2.32.0__tar.gz → 2.51.1__tar.gz

docling_core-2.51.1/PKG-INFO

@@ -0,0 +1,160 @@
+Metadata-Version: 2.4
+Name: docling-core
+Version: 2.51.1
+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>
+License-Expression: MIT
+Project-URL: homepage, https://github.com/docling-project
+Project-URL: repository, https://github.com/docling-project/docling-core
+Project-URL: issues, https://github.com/docling-project/docling-core/issues
+Project-URL: changelog, https://github.com/docling-project/docling-core/blob/main/CHANGELOG.md
+Keywords: docling,discovery,etl,information retrieval,analytics,database,database schema,schema,JSON
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+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
+Requires-Dist: jsonschema<5.0.0,>=4.16.0
+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<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
+Requires-Dist: latex2mathml<4.0.0,>=3.77.0
+Provides-Extra: chunking
+Requires-Dist: semchunk<3.0.0,>=2.2.0; extra == "chunking"
+Requires-Dist: tree-sitter<1.0.0,>=0.23.2; extra == "chunking"
+Requires-Dist: tree-sitter-python<1.0.0,>=0.23.6; extra == "chunking"
+Requires-Dist: tree-sitter-c<1.0.0,>=0.23.4; extra == "chunking"
+Requires-Dist: tree-sitter-java<1.0.0,>=0.23.5; extra == "chunking"
+Requires-Dist: tree-sitter-javascript<1.0.0,>=0.23.1; extra == "chunking"
+Requires-Dist: tree-sitter-typescript<1.0.0,>=0.23.2; extra == "chunking"
+Requires-Dist: transformers<5.0.0,>=4.34.0; extra == "chunking"
+Provides-Extra: chunking-openai
+Requires-Dist: semchunk<3.0.0,>=2.2.0; extra == "chunking-openai"
+Requires-Dist: tree-sitter<1.0.0,>=0.23.2; extra == "chunking-openai"
+Requires-Dist: tree-sitter-python<1.0.0,>=0.23.6; extra == "chunking-openai"
+Requires-Dist: tree-sitter-c<1.0.0,>=0.23.4; extra == "chunking-openai"
+Requires-Dist: tree-sitter-java<1.0.0,>=0.23.5; extra == "chunking-openai"
+Requires-Dist: tree-sitter-javascript<1.0.0,>=0.23.1; extra == "chunking-openai"
+Requires-Dist: tree-sitter-typescript<1.0.0,>=0.23.2; extra == "chunking-openai"
+Requires-Dist: tiktoken<0.13.0,>=0.9.0; extra == "chunking-openai"
+Dynamic: license-file
+
+# Docling Core
+
+[![PyPI version](https://img.shields.io/pypi/v/docling-core)](https://pypi.org/project/docling-core/)
+![Python](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%20%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
+[![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/docling-project/docling-core)](https://opensource.org/licenses/MIT)
+
+Docling Core is a library that defines core data types and transformations in [Docling](https://github.com/docling-project/docling).
+
+## Installation
+
+To use Docling Core, simply install `docling-core` from your package manager, e.g. pip:
+```bash
+pip install docling-core
+```
+
+### Development setup
+
+To develop for Docling Core, you need Python 3.9 through 3.14 and the `uv` package. You can then install it from your local clone's root directory:
+```bash
+uv sync --all-extras
+```
+
+To run the pytest suite, execute:
+```
+uv run pytest -s test
+```
+
+## Main features
+
+Docling Core provides the foundational DoclingDocument data model and API, as well as
+additional APIs for tasks like serialization and chunking, which are key to developing
+generative AI applications using Docling.
+
+### DoclingDocument
+
+Docling Core defines the DoclingDocument as a Pydantic model, allowing for advanced
+data model control, customizability, and interoperability.
+
+In addition to specifying the schema, it provides a handy API for building documents,
+as well as for basic operations, e.g. exporting to various formats, like Markdown, HTML,
+and others.
+
+👉 More details:
+- [Architecture docs](https://docling-project.github.io/docling/concepts/architecture/)
+- [DoclingDocument docs](https://docling-project.github.io/docling/concepts/docling_document/)
+
+### Serialization
+
+Different users can have varying requirements when it comes to serialization.
+To address this, the Serialization API introduces a design that allows easy extension,
+while providing feature-rich built-in implementations (on which the respective
+DoclingDocument helpers are actually based).
+
+👉 More details:
+- [Serialization docs](https://docling-project.github.io/docling/concepts/serialization/)
+- [Serialization example](https://docling-project.github.io/docling/examples/serialization/)
+
+### Chunking
+
+Similarly to above, the Chunking API provides built-in chunking capabilities as well as
+a design that enables easy extension, this way tackling customization requirements of
+different use cases.
+
+👉 More details:
+- [Chunking docs](https://docling-project.github.io/docling/concepts/chunking/)
+- [Hybrid chunking example](https://docling-project.github.io/docling/examples/hybrid_chunking/)
+- [Advanced chunking and serialization](https://docling-project.github.io/docling/examples/advanced_chunking_and_serialization/)
+
+## Contributing
+
+Please read [Contributing to Docling Core](./CONTRIBUTING.md) for details.
+
+## References
+
+If you use Docling Core in your projects, please consider citing the following:
+
+```bib
+@techreport{Docling,
+  author = "Deep Search Team",
+  month = 8,
+  title = "Docling Technical Report",
+  url = "https://arxiv.org/abs/2408.09869",
+  eprint = "2408.09869",
+  doi = "10.48550/arXiv.2408.09869",
+  version = "1.0.0",
+  year = 2024
+}
+```
+
+## License
+
+The Docling Core codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.

docling_core-2.51.1/README.md

@@ -0,0 +1,99 @@
+# Docling Core
+
+[![PyPI version](https://img.shields.io/pypi/v/docling-core)](https://pypi.org/project/docling-core/)
+![Python](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%20%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
+[![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/docling-project/docling-core)](https://opensource.org/licenses/MIT)
+
+Docling Core is a library that defines core data types and transformations in [Docling](https://github.com/docling-project/docling).
+
+## Installation
+
+To use Docling Core, simply install `docling-core` from your package manager, e.g. pip:
+```bash
+pip install docling-core
+```
+
+### Development setup
+
+To develop for Docling Core, you need Python 3.9 through 3.14 and the `uv` package. You can then install it from your local clone's root directory:
+```bash
+uv sync --all-extras
+```
+
+To run the pytest suite, execute:
+```
+uv run pytest -s test
+```
+
+## Main features
+
+Docling Core provides the foundational DoclingDocument data model and API, as well as
+additional APIs for tasks like serialization and chunking, which are key to developing
+generative AI applications using Docling.
+
+### DoclingDocument
+
+Docling Core defines the DoclingDocument as a Pydantic model, allowing for advanced
+data model control, customizability, and interoperability.
+
+In addition to specifying the schema, it provides a handy API for building documents,
+as well as for basic operations, e.g. exporting to various formats, like Markdown, HTML,
+and others.
+
+👉 More details:
+- [Architecture docs](https://docling-project.github.io/docling/concepts/architecture/)
+- [DoclingDocument docs](https://docling-project.github.io/docling/concepts/docling_document/)
+
+### Serialization
+
+Different users can have varying requirements when it comes to serialization.
+To address this, the Serialization API introduces a design that allows easy extension,
+while providing feature-rich built-in implementations (on which the respective
+DoclingDocument helpers are actually based).
+
+👉 More details:
+- [Serialization docs](https://docling-project.github.io/docling/concepts/serialization/)
+- [Serialization example](https://docling-project.github.io/docling/examples/serialization/)
+
+### Chunking
+
+Similarly to above, the Chunking API provides built-in chunking capabilities as well as
+a design that enables easy extension, this way tackling customization requirements of
+different use cases.
+
+👉 More details:
+- [Chunking docs](https://docling-project.github.io/docling/concepts/chunking/)
+- [Hybrid chunking example](https://docling-project.github.io/docling/examples/hybrid_chunking/)
+- [Advanced chunking and serialization](https://docling-project.github.io/docling/examples/advanced_chunking_and_serialization/)
+
+## Contributing
+
+Please read [Contributing to Docling Core](./CONTRIBUTING.md) for details.
+
+## References
+
+If you use Docling Core in your projects, please consider citing the following:
+
+```bib
+@techreport{Docling,
+  author = "Deep Search Team",
+  month = 8,
+  title = "Docling Technical Report",
+  url = "https://arxiv.org/abs/2408.09869",
+  eprint = "2408.09869",
+  doi = "10.48550/arXiv.2408.09869",
+  version = "1.0.0",
+  year = 2024
+}
+```
+
+## License
+
+The Docling Core codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.

{docling_core-2.32.0 → docling_core-2.51.1}/docling_core/cli/view.py

@@ -39,9 +39,17 @@ def view(
         typer.Argument(
             ...,
             metavar="source",
-            help="Docling JSON file to view.",
+            help="Docling JSON or YAML file to view.",
         ),
     ],
+    split_view: Annotated[
+        bool,
+        typer.Option(
+            "--split-view",
+            "-s",
+            help="Split view of the document.",
+        ),
+    ] = False,
     version: Annotated[
         Optional[bool],
         typer.Option(
@@ -52,11 +60,19 @@ def view(
         ),
     ] = None,
 ):
-    """Display a Docling JSON file on the default browser."""
+    """Display a DoclingDocument file on the default browser."""
     path = resolve_source_to_path(source=source)
-    doc = DoclingDocument.load_from_json(filename=path)
-    target_path = Path(tempfile.mkdtemp()) / "out.html"
-    html_output = doc.export_to_html(image_mode=ImageRefMode.EMBEDDED)
+    if path.suffix == ".json":
+        doc = DoclingDocument.load_from_json(filename=path)
+    elif path.suffix in [".yaml", ".yml"]:
+        doc = DoclingDocument.load_from_yaml(filename=path)
+    else:
+        raise ValueError(f"Unsupported file type: {path.suffix}")
+    target_path = Path(tempfile.mkdtemp()) / f"{path.stem}.html"
+    html_output = doc.export_to_html(
+        image_mode=ImageRefMode.EMBEDDED,
+        split_page_view=split_view,
+    )
     with open(target_path, "w", encoding="utf-8") as f:
         f.write(html_output)
     webbrowser.open(url=f"file://{target_path.absolute().resolve()}")

docling_core-2.51.1/docling_core/transforms/chunker/__init__.py

@@ -0,0 +1,24 @@
+#
+# Copyright IBM Corp. 2024 - 2024
+# SPDX-License-Identifier: MIT
+#
+
+"""Define the chunker types."""
+
+from docling_core.transforms.chunker.base import BaseChunk, BaseChunker, BaseMeta
+from docling_core.transforms.chunker.code_chunking.base_code_chunking_strategy import (
+    BaseCodeChunkingStrategy,
+)
+from docling_core.transforms.chunker.code_chunking.code_chunk import (
+    CodeChunk,
+    CodeChunkType,
+    CodeDocMeta,
+)
+from docling_core.transforms.chunker.code_chunking.standard_code_chunking_strategy import (
+    StandardCodeChunkingStrategy,
+)
+from docling_core.transforms.chunker.doc_chunk import DocChunk, DocMeta
+from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
+from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
+from docling_core.transforms.chunker.page_chunker import PageChunker
+from docling_core.types.doc.labels import CodeLanguageLabel

docling_core-2.51.1/docling_core/transforms/chunker/code_chunking/__init__.py

@@ -0,0 +1 @@
+"""Code chunking package."""