libreoffice-haystack 1.0.0__tar.gz

libreoffice_haystack-1.0.0/.gitignore

@@ -0,0 +1,146 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+volumes/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode
+
+# Docs generation artifacts
+_readme_*.md
+.idea
+
+# macOS
+.DS_Store
+
+# http cache (requests-cache)
+**/http_cache.sqlite
+
+# ruff
+.ruff_cache

libreoffice_haystack-1.0.0/LICENSE.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2023-present deepset GmbH
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

libreoffice_haystack-1.0.0/PKG-INFO

@@ -0,0 +1,37 @@
+Metadata-Version: 2.4
+Name: libreoffice-haystack
+Version: 1.0.0
+Summary: LibreOffice integration for Haystack
+Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/libreoffice#readme
+Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
+Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/libreoffice
+Author: Max Swain
+Author-email: deepset GmbH <info@deepset.ai>
+License-Expression: Apache-2.0
+License-File: LICENSE.txt
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+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
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: haystack-ai
+Description-Content-Type: text/markdown
+
+# libreoffice-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/libreoffice-haystack.svg)](https://pypi.org/project/libreoffice-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/libreoffice-haystack.svg)](https://pypi.org/project/libreoffice-haystack)
+
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/libreoffice/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

libreoffice_haystack-1.0.0/README.md

@@ -0,0 +1,12 @@
+# libreoffice-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/libreoffice-haystack.svg)](https://pypi.org/project/libreoffice-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/libreoffice-haystack.svg)](https://pypi.org/project/libreoffice-haystack)
+
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/libreoffice/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

libreoffice_haystack-1.0.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,13 @@
+loaders:
+  - modules:
+      - haystack_integrations.components.converters.libreoffice.converter
+    search_path: [../src]
+processors:
+  - type: filter
+    documented_only: true
+    skip_empty_modules: true
+renderer:
+  description: LibreOffice integration for Haystack
+  id: integrations-libreoffice
+  filename: libreoffice.md
+  title: LibreOffice

libreoffice_haystack-1.0.0/pyproject.toml

@@ -0,0 +1,159 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "libreoffice-haystack"
+dynamic = ["version"]
+description = "LibreOffice integration for Haystack"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+keywords = []
+authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }, { name = "Max Swain" }]
+classifiers = [
+  "License :: OSI Approved :: Apache Software License",
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "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",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: Implementation :: PyPy",
+]
+dependencies = ["haystack-ai"]
+
+[project.urls]
+Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/libreoffice#readme"
+Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
+Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/libreoffice"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/haystack_integrations"]
+
+[tool.hatch.version]
+source = "vcs"
+tag-pattern = 'integrations\/libreoffice-v(?P<version>.*)'
+
+[tool.hatch.version.raw-options]
+root = "../.."
+git_describe_command = 'git describe --tags --match="integrations/libreoffice-v[0-9]*"'
+
+[tool.hatch.envs.default]
+installer = "uv"
+dependencies = ["haystack-pydoc-tools", "ruff"]
+
+[tool.hatch.envs.default.scripts]
+docs = ["haystack-pydoc pydoc/config_docusaurus.yml"]
+fmt = "ruff check --fix {args}; ruff format {args}"
+fmt-check = "ruff check {args} && ruff format --check {args}"
+
+[tool.hatch.envs.test]
+dependencies = [
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-rerunfailures",
+    "mypy",
+    "pip",
+]
+
+[tool.hatch.envs.test.scripts]
+unit = 'pytest -m "not integration" {args:tests}'
+integration = 'pytest -m "integration" {args:tests}'
+all = 'pytest {args:tests}'
+cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
+types = "mypy -p haystack_integrations.components.converters.libreoffice {args}"
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
+
+[tool.ruff]
+line-length = 120
+
+[tool.ruff.lint]
+select = [
+    "A",
+    "ANN",
+    "ARG",
+    "B",
+    "C",
+    "D102",   # Missing docstring in public method
+    "D103",   # Missing docstring in public function
+    "D205",   # 1 blank line required between summary line and description
+    "D209",   # Closing triple quotes go to new line
+    "D213",   # summary lines must be positioned on the second physical line of the docstring
+    "D417",   # Missing argument descriptions in the docstring
+    "D419",   # Docstring is empty
+    "DTZ",
+    "E",
+    "EM",
+    "F",
+    "I",
+    "ICN",
+    "ISC",
+    "N",
+    "PLC",
+    "PLE",
+    "PLR",
+    "PLW",
+    "Q",
+    "RUF",
+    "S",
+    "T",
+    "TID",
+    "UP",
+    "W",
+    "YTT",
+]
+ignore = [
+    # Allow non-abstract empty methods in abstract base classes
+    "B027",
+    # Allow function calls in argument defaults (common Haystack pattern for Secret.from_env_var)
+    "B008",
+    # Ignore checks for possible passwords
+    "S105",
+    "S106",
+    "S107",
+    # Ignore complexity
+    "C901",
+    "PLR0911",
+    "PLR0912",
+    "PLR0913",
+    "PLR0915",
+    # Allow `Any` type - used legitimately for dynamic types and SDK boundaries
+    "ANN401",
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["haystack_integrations"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "parents"
+
+[tool.ruff.lint.per-file-ignores]
+# Tests can use magic values, assertions, relative imports, and don't need type annotations
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
+
+[tool.coverage.run]
+source = ["haystack_integrations"]
+branch = true
+parallel = false
+
+[tool.coverage.report]
+omit = ["*/tests/*", "*/__init__.py"]
+show_missing = true
+exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
+
+[tool.pytest.ini_options]
+addopts = "--strict-markers"
+markers = [
+  "integration: integration tests",
+]
+log_cli = true
+asyncio_default_fixture_loop_scope = "function"

libreoffice_haystack-1.0.0/src/haystack_integrations/components/converters/libreoffice/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .converter import LibreOfficeFileConverter
+
+__all__ = ["LibreOfficeFileConverter"]

libreoffice_haystack-1.0.0/src/haystack_integrations/components/converters/libreoffice/converter.py

@@ -0,0 +1,344 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+import shutil
+import subprocess
+from asyncio import create_subprocess_exec
+from collections.abc import Iterable
+from pathlib import Path
+from tempfile import TemporaryDirectory
+from typing import Any, ClassVar, Literal, TypedDict, get_args
+
+from haystack import component, default_from_dict, default_to_dict
+from haystack.dataclasses import ByteStream
+from typing_extensions import Self
+
+OUTPUT_FILE_TYPE = Literal[
+    "pdf",
+    "doc",
+    "docx",
+    "odt",
+    "rtf",
+    "txt",
+    "html",
+    "xlsx",
+    "xls",
+    "ods",
+    "csv",
+    "pptx",
+    "ppt",
+    "odp",
+    "epub",
+    "png",
+    "jpg",
+]
+
+
+class LibreOfficeFileConverterOutput(TypedDict):
+    output: list[ByteStream]
+
+
+@component
+class LibreOfficeFileConverter:
+    """
+    Component that uses libreoffice's command line utility (soffice) to convert files into various formats.
+
+    ### Usage examples
+
+    **Simple conversion:**
+    ```python
+    from pathlib import Path
+
+    from haystack_integrations.components.converters.libreoffice import LibreOfficeFileConverter
+
+    # Convert documents
+    converter = LibreOfficeFileConverter()
+    results = converter.run(sources=[Path("sample.doc")], output_file_type="docx")
+    print(results["output"])  # [ByteStream(data=b'...', meta={}, mime_type=None)]
+    ```
+
+    **Conversion pipeline:**
+    ```python
+    from pathlib import Path
+
+    from haystack import Pipeline
+    from haystack.components.converters import DOCXToDocument
+
+    from haystack_integrations.components.converters.libreoffice import LibreOfficeFileConverter
+
+    # Create pipeline with components
+    pipeline = Pipeline()
+    pipeline.add_component("libreoffice_converter", LibreOfficeFileConverter())
+    pipeline.add_component("docx_converter", DOCXToDocument())
+
+    pipeline.connect("libreoffice_converter.output", "docx_converter.sources")
+
+    # Run pipeline and convert legacy documents into Haystack documents
+    results = pipeline.run(
+        {
+            "libreoffice_converter": {
+                "sources": [Path("sample_doc.doc")],
+                "output_file_type": "docx",
+            }
+        }
+    )
+    print(results["docx_converter"]["documents"])
+    ```
+    """
+
+    SUPPORTED_TYPES: ClassVar[dict[str, frozenset[str]]] = {
+        # Documents
+        "doc": frozenset(["pdf", "docx", "odt", "rtf", "txt", "html", "epub"]),
+        "docx": frozenset(["pdf", "doc", "odt", "rtf", "txt", "html", "epub"]),
+        "odt": frozenset(["pdf", "docx", "doc", "rtf", "txt", "html", "epub"]),
+        "rtf": frozenset(["pdf", "docx", "doc", "odt", "txt", "html"]),
+        "txt": frozenset(["pdf", "docx", "doc", "odt", "rtf", "html"]),
+        "html": frozenset(["pdf", "docx", "doc", "odt", "rtf", "txt"]),
+        # Spreadsheets
+        "xlsx": frozenset(["pdf", "xls", "ods", "csv", "html"]),
+        "xls": frozenset(["pdf", "xlsx", "ods", "csv", "html"]),
+        "ods": frozenset(["pdf", "xlsx", "xls", "csv", "html"]),
+        "csv": frozenset(["pdf", "xlsx", "xls", "ods"]),
+        # Presentations
+        "pptx": frozenset(["pdf", "ppt", "odp", "html", "png", "jpg"]),
+        "ppt": frozenset(["pdf", "pptx", "odp", "html", "png", "jpg"]),
+        "odp": frozenset(["pdf", "pptx", "ppt", "html", "png", "jpg"]),
+    }
+    """A non-exhaustive mapping of supported conversion types by this component.
+    See https://help.libreoffice.org/latest/en-GB/text/shared/guide/convertfilters.html for more information."""
+
+    def __init__(
+        self,
+        output_file_type: OUTPUT_FILE_TYPE | None = None,
+    ) -> None:
+        """
+        Check whether soffice is installed.
+
+        :param output_file_type:
+            Target file format to convert to. Must be a valid conversion target for
+            each source's input type — see :attr:`SUPPORTED_TYPES` for the full mapping.
+        """
+        soffice_path = shutil.which("soffice")
+        if soffice_path is None:
+            msg = """LibreOffice (soffice) is required but not installed or not in PATH.
+
+- Install instructions: https://www.libreoffice.org/get-help/install-howto/"""
+            raise FileNotFoundError(msg)
+
+        self.soffice_path = soffice_path
+        self.output_file_type = output_file_type
+
+    def to_dict(self) -> dict[str, Any]:
+        """
+        Serializes the component to a dictionary.
+
+        :returns:
+            Dictionary with serialized data.
+        """
+        return default_to_dict(self)
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> Self:
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            The dictionary to deserialize from.
+        :returns:
+            The deserialized component.
+        """
+        return default_from_dict(cls, data)
+
+    def _get_conversion_args(
+        self, source: str | Path, output_directory: str | Path, output_file_type: str
+    ) -> tuple[Path, list[str]]:
+        """
+        Validate source file and return the soffice arguments for conversion.
+
+        :param source: Source file path.
+        :param output_directory: Output directory to save converted files to.
+        :param output_file_type: Target file format extension (e.g. `"pdf"`).
+        :returns: Tuple of `(output_path, soffice_args)` where `output_path` is the
+            expected path of the converted file and `soffice_args` is the list of
+            arguments to pass to `soffice`.
+        :raises FileNotFoundError: If `source` does not exist.
+        :raises OSError: If `output_directory` does not exist or is not writable.
+        """
+        source_path = Path(source)
+        output_path = Path(output_directory)
+
+        # Source file must exist
+        if not source_path.is_file():
+            msg = f"{source=} does not exist"
+            raise FileNotFoundError(msg)
+
+        # Output directory must exist and be writable
+        if not output_path.is_dir() or not os.access(output_path, os.W_OK):
+            msg = f"{output_directory=} must exist and be writable"
+            raise OSError(msg)
+
+        args = [
+            self.soffice_path,
+            "--headless",
+            "--convert-to",
+            output_file_type,
+            "--outdir",
+            str(output_directory),
+            str(source),
+        ]
+        return (output_path / source_path.name).with_suffix(f".{output_file_type}"), args
+
+    def _validate_args(self, output_file_type: str, input_file_type: str | None = None) -> None:
+        """
+        Validate that the input and output file types are supported.
+
+        :param output_file_type: Target file format extension to convert to.
+        :param input_file_type: Source file format extension. If provided, validates that
+            it is a supported input type and that `output_file_type` is a valid conversion
+            target for it.
+        :raises ValueError: If `input_file_type` is not in :attr:`SUPPORTED_TYPES`, or if
+            `output_file_type` is not a valid conversion target for the given `input_file_type`.
+        """
+        # Validate specified output type is one of allow output file types
+        supported_output_types = get_args(OUTPUT_FILE_TYPE)
+        if output_file_type not in supported_output_types:
+            supported_types = ", ".join(supported_output_types)
+            msg = f"{output_file_type=} is not supported and must be one of type {supported_types}"
+            raise ValueError(msg)
+
+        # Cannot further validate conversion types if input conversions is not known - i.e., source is `ByteStream`
+        if input_file_type is None:
+            return
+
+        if input_file_type not in self.SUPPORTED_TYPES:
+            supported_types = ", ".join(self.SUPPORTED_TYPES)
+            msg = f"{input_file_type=} is not supported and must be one of type {supported_types}"
+            raise ValueError(msg)
+
+        if output_file_type not in (output_types := self.SUPPORTED_TYPES[input_file_type]):
+            supported_types = ", ".join(output_types)
+            msg = (
+                f"{output_file_type=} is not supported for {input_file_type=} and must be one of type {supported_types}"
+            )
+            raise ValueError(msg)
+
+    @component.output_types(output=list[ByteStream])
+    def run(
+        self,
+        sources: Iterable[str | Path | ByteStream],
+        output_file_type: OUTPUT_FILE_TYPE | None = None,
+    ) -> LibreOfficeFileConverterOutput:
+        """
+        Convert office files to the specified output format using LibreOffice.
+
+        :param sources:
+            List of sources to convert. Each source can be a file path (`str` or
+            `Path`) or a `ByteStream`. For `ByteStream` sources, the input file
+            type cannot be inferred from the filename, so only `output_file_type` is
+            validated (not the source type).
+        :param output_file_type:
+            Target file format to convert to. Must be a valid conversion target for
+            each source's input type — see :attr:`SUPPORTED_TYPES` for the full mapping.
+            If set, it will override the `output_file_type` parameter provided during initialization.
+        :returns:
+            A dictionary with the following key:
+            - `output`: List of `ByteStream` objects containing the converted file
+              data, in the same order as `sources`.
+        :raises FileNotFoundError: If a source file path does not exist.
+        :raises OSError: If the internal temporary output directory is not writable.
+        :raises ValueError: If a source's file type is not in :attr:`SUPPORTED_TYPES`,
+            or if `output_file_type` is not a valid conversion target for it,
+            or if `output_file_type` has not been provided anywhere.
+        """
+        resolved_output_file_type = output_file_type or self.output_file_type
+        if resolved_output_file_type is None:
+            msg = "output_file_type must be provided either during initialization or for this method"
+            raise ValueError(msg)
+
+        outputs: list[ByteStream] = []
+        with TemporaryDirectory() as tmpdir:
+            for source in sources:
+                # Handle case where source is a `ByteStream` using tempfile
+                if isinstance(source, ByteStream):
+                    tmp_path = Path(tmpdir) / "input"
+                    tmp_path.write_bytes(source.data)
+
+                    self._validate_args(resolved_output_file_type)
+                    output_path, args = self._get_conversion_args(tmp_path, tmpdir, resolved_output_file_type)
+
+                    subprocess.run(args, check=True)  # noqa: S603 - ruff doesn't know the arguments have been validated
+                    outputs.append(ByteStream(data=output_path.read_bytes()))
+                    continue
+
+                self._validate_args(resolved_output_file_type, str(source).split(".")[-1])
+                output_path, args = self._get_conversion_args(source, tmpdir, resolved_output_file_type)
+
+                subprocess.run(args, check=True)  # noqa: S603
+                outputs.append(ByteStream(data=output_path.read_bytes()))
+
+        return {"output": outputs}
+
+    @component.output_types(output=list[ByteStream])
+    async def run_async(
+        self,
+        sources: Iterable[str | Path | ByteStream],
+        output_file_type: OUTPUT_FILE_TYPE | None = None,
+    ) -> LibreOfficeFileConverterOutput:
+        """
+        Asynchronously convert office files to the specified output format using LibreOffice.
+
+        This is the asynchronous version of the `run` method with the same parameters and return values.
+
+        :param sources:
+            List of sources to convert. Each source can be a file path (`str` or
+            `Path`) or a `ByteStream`. For `ByteStream` sources, the input file
+            type cannot be inferred from the filename, so only `output_file_type` is
+            validated (not the source type).
+        :param output_file_type:
+            Target file format to convert to. Must be a valid conversion target for
+            each source's input type — see :attr:`SUPPORTED_TYPES` for the full mapping.
+            If set, it will override the `output_file_type` parameter provided during initialization.
+        :returns:
+            A dictionary with the following key:
+            - `output`: List of `ByteStream` objects containing the converted file
+              data, in the same order as `sources`.
+        :raises FileNotFoundError: If a source file path does not exist.
+        :raises OSError: If the internal temporary output directory is not writable.
+        :raises ValueError: If a source's file type is not in :attr:`SUPPORTED_TYPES`,
+            or if `output_file_type` is not a valid conversion target for it,
+            or if `output_file_type` has not been provided anywhere.
+        """
+        resolved_output_file_type = output_file_type or self.output_file_type
+        if resolved_output_file_type is None:
+            msg = "output_file_type must be provided either during initialization or for this method"
+            raise ValueError(msg)
+
+        outputs: list[ByteStream] = []
+        with TemporaryDirectory() as tmpdir:
+            for source in sources:
+                # Handle case where source is a `ByteStream`
+                if isinstance(source, ByteStream):
+                    tmp_path = Path(tmpdir) / "input"
+                    tmp_path.write_bytes(source.data)
+
+                    self._validate_args(resolved_output_file_type)
+                    output_path, args = self._get_conversion_args(tmp_path, tmpdir, resolved_output_file_type)
+
+                    process = await create_subprocess_exec(*args)
+                    # Wait for process to complete as only one instance of soffice can occur at once
+                    await process.wait()
+                    outputs.append(ByteStream(data=output_path.read_bytes()))
+                    continue
+
+                self._validate_args(resolved_output_file_type, str(source).split(".")[-1])
+                output_path, args = self._get_conversion_args(source, tmpdir, resolved_output_file_type)
+
+                process = await create_subprocess_exec(*args)
+                # Wait for process to complete as only one instance of soffice can occur at once
+                await process.wait()
+
+                outputs.append(ByteStream(data=output_path.read_bytes()))
+
+        return {"output": outputs}

libreoffice_haystack-1.0.0/tests/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0

libreoffice_haystack-1.0.0/tests/test_converter.py

@@ -0,0 +1,129 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from collections.abc import Generator
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+from haystack.dataclasses import ByteStream
+
+from haystack_integrations.components.converters.libreoffice import LibreOfficeFileConverter
+
+
+@pytest.fixture
+def converter() -> LibreOfficeFileConverter:
+    return LibreOfficeFileConverter()
+
+
+@pytest.fixture
+def mock_converter() -> Generator[LibreOfficeFileConverter, None]:
+    with patch("shutil.which", return_value="/usr/bin/soffice"):
+        yield LibreOfficeFileConverter()
+
+
+@pytest.fixture
+def test_files_path() -> Path:
+    return Path("tests") / "test_files"
+
+
+class TestLibreOfficeFileConverter:
+    def test_init(self, mock_converter: LibreOfficeFileConverter) -> None:
+        assert isinstance(mock_converter, LibreOfficeFileConverter)
+        assert isinstance(mock_converter.soffice_path, str)
+
+    def test_init_raises_when_soffice_not_found(self) -> None:
+        with patch("shutil.which", return_value=None):
+            with pytest.raises(FileNotFoundError, match="LibreOffice"):
+                LibreOfficeFileConverter()
+
+    def test_to_dict(self, mock_converter: LibreOfficeFileConverter) -> None:
+        data = mock_converter.to_dict()
+        assert data == {
+            "type": "haystack_integrations.components.converters.libreoffice.converter.LibreOfficeFileConverter",
+            "init_parameters": {},
+        }
+
+    def test_from_dict(self) -> None:
+        data = {
+            "type": "haystack_integrations.components.converters.libreoffice.converter.LibreOfficeFileConverter",
+            "init_parameters": {},
+        }
+        with patch("shutil.which", return_value="/usr/bin/soffice"):
+            converter = LibreOfficeFileConverter.from_dict(data)
+        assert isinstance(converter.soffice_path, str)
+
+    def test_run_unsupported_input_type(self, mock_converter: LibreOfficeFileConverter) -> None:
+        # .pdf is not a supported input type in SUPPORTED_TYPES
+        with pytest.raises(ValueError):
+            mock_converter.run(["test_file.pdf"], output_file_type="docx")
+
+    def test_run_unsupported_output_type(self, mock_converter: LibreOfficeFileConverter) -> None:
+        # .doc -> .png is not a valid conversion
+        with pytest.raises(ValueError):
+            mock_converter.run(["test_file.doc"], output_file_type="png")
+
+    def test_run_no_file(self, mock_converter: LibreOfficeFileConverter) -> None:
+        with pytest.raises(FileNotFoundError):
+            mock_converter.run(["nonexistent_file.doc"], output_file_type="docx")
+
+    @pytest.mark.integration
+    def test_run(self, converter: LibreOfficeFileConverter, test_files_path: Path) -> None:
+        paths = [
+            test_files_path / "doc" / "sample_doc.doc",
+            test_files_path / "ppt" / "sample_ppt.ppt",
+            test_files_path / "xls" / "basic_tables_two_sheets.xls",
+        ]
+
+        results = converter.run(paths, output_file_type="pdf")
+
+        output = results["output"]
+        assert len(output) == 3
+        for stream in output:
+            assert isinstance(stream, ByteStream)
+            assert len(stream.data) > 0
+
+    @pytest.mark.integration
+    def test_run_bytestream_source(self, converter: LibreOfficeFileConverter, test_files_path: Path) -> None:
+        source_path = test_files_path / "doc" / "sample_doc.doc"
+        bytestream = ByteStream(data=source_path.read_bytes())
+
+        results = converter.run([bytestream], output_file_type="pdf")
+
+        output = results["output"]
+        assert len(output) == 1
+        assert isinstance(output[0], ByteStream)
+        assert len(output[0].data) > 0
+
+    @pytest.mark.asyncio
+    @pytest.mark.integration
+    async def test_run_async(self, converter: LibreOfficeFileConverter, test_files_path: Path) -> None:
+        paths = [
+            test_files_path / "doc" / "sample_doc.doc",
+            test_files_path / "ppt" / "sample_ppt.ppt",
+            test_files_path / "xls" / "basic_tables_two_sheets.xls",
+        ]
+
+        results = await converter.run_async(paths, output_file_type="pdf")
+
+        output = results["output"]
+        assert len(output) == 3
+        for stream in output:
+            assert isinstance(stream, ByteStream)
+            assert len(stream.data) > 0
+
+    @pytest.mark.asyncio
+    @pytest.mark.integration
+    async def test_run_async_bytestream_source(
+        self, converter: LibreOfficeFileConverter, test_files_path: Path
+    ) -> None:
+        source_path = test_files_path / "doc" / "sample_doc.doc"
+        bytestream = ByteStream(data=source_path.read_bytes())
+
+        results = await converter.run_async([bytestream], output_file_type="pdf")
+
+        output = results["output"]
+        assert len(output) == 1
+        assert isinstance(output[0], ByteStream)
+        assert len(output[0].data) > 0