mediaref 0.1.0__tar.gz

mediaref-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,32 @@
+name: "Publish"
+
+on:
+  push:
+    tags:
+      # Publish on any tag starting with a `v`, e.g., v0.1.0
+      - v*
+
+jobs:
+  run:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write
+      contents: read
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+      - name: Install Python 3.13
+        run: uv python install 3.13
+      - name: Build
+        run: uv build
+      # Check that basic features work and we didn't miss to include crucial files
+      # - name: Smoke test (wheel)
+      #   run: uv run --isolated --no-project --with dist/*.whl tests/smoke_test.py
+      # - name: Smoke test (source distribution)
+      #   run: uv run --isolated --no-project --with dist/*.tar.gz tests/smoke_test.py
+      - name: Publish
+        run: uv publish

mediaref-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,32 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main, develop ]
+  pull_request:
+    branches: [ main, develop ]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+    - uses: actions/checkout@v5
+    - name: Install uv
+      uses: astral-sh/setup-uv@v7
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Setup environments
+      run: |
+        uv venv
+        uv pip install -e ".[loader,dev]"
+    
+    - name: Run tests
+      run: |
+        uv run pytest --cov=mediaref --cov-report=xml --cov-report=term
+

mediaref-0.1.0/.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

mediaref-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,58 @@
+# Contributing to MediaRef
+
+Thank you for your interest in contributing to MediaRef!
+
+## Development Setup
+
+1. Clone the repository:
+```bash
+git clone https://github.com/open-world-agents/mediaref.git
+cd mediaref
+```
+
+2. Install in development mode with all dependencies:
+```bash
+pip install -e ".[loader,dev]"
+```
+
+## Running Tests
+
+```bash
+# Run all tests
+pytest
+
+# Run with coverage
+pytest --cov=mediaref --cov-report=html
+
+# Run specific test
+pytest tests/test_mediaref.py::TestMediaRefLoading::test_to_rgb_array
+```
+
+## Code Style
+
+- Follow PEP 8
+- Use type hints
+- Write docstrings for public APIs
+- Keep functions focused and small
+
+## Making Changes
+
+1. Create a new branch for your feature/fix
+2. Make your changes
+3. Add tests for new functionality
+4. Ensure all tests pass
+5. Update documentation if needed
+6. Submit a pull request
+
+## Reporting Issues
+
+Please include:
+- Python version
+- MediaRef version
+- Minimal reproducible example
+- Expected vs actual behavior
+
+## Questions?
+
+Open an issue or discussion on GitHub.
+

mediaref-0.1.0/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2025 Open World Agents Team
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

mediaref-0.1.0/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.4
+Name: mediaref
+Version: 0.1.0
+Summary: Add your description here
+Author-email: Suhwan Choi <milkclouds00@gmail.com>
+License-File: LICENSE
+Requires-Python: >=3.9
+Requires-Dist: pydantic>=2.0
+Provides-Extra: dev
+Requires-Dist: ipython; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Provides-Extra: loader
+Requires-Dist: av>=15.0; extra == 'loader'
+Requires-Dist: loguru; extra == 'loader'
+Requires-Dist: numpy; extra == 'loader'
+Requires-Dist: opencv-python; extra == 'loader'
+Requires-Dist: pillow; extra == 'loader'
+Requires-Dist: requests; extra == 'loader'
+Description-Content-Type: text/markdown
+
+# MediaRef
+
+Pydantic-based media reference for images and video frames. Supports file paths, URLs, data URIs, and video timestamps. Designed for dataset metadata and lazy loading.
+
+## Installation
+
+```bash
+# Core package (MediaRef definition only)
+pip install -e .
+
+# With loader support (includes batch loading, video decoders)
+pip install -e ".[loader]"
+```
+
+## Usage
+
+```python
+from mediaref import MediaRef, load_batch
+
+# Reference creation - supports multiple URI schemes
+MediaRef(uri="image.png")                              # Local file
+MediaRef(uri="https://example.com/image.jpg")          # Remote URL
+MediaRef(uri="video.mp4", pts_ns=1_000_000_000)        # Video frame at 1.0s
+MediaRef(uri="data:image/png;base64,...")              # Embedded data URI
+
+# Loading
+ref.to_rgb_array()                                     # Returns (H, W, 3) numpy array
+ref.to_pil_image()                                     # Returns PIL.Image
+
+# Batch loading with automatic caching (default: PyAV decoder)
+refs = [MediaRef(uri="video.mp4", pts_ns=i*1e9) for i in range(10)]
+frames = load_batch(refs)                              # Reuses video container
+
+# Use TorchCodec decoder for GPU acceleration (requires torchcodec>=0.4.0)
+frames = load_batch(refs, decoder="torchcodec")
+
+# Embedding
+data_uri = ref.embed_as_data_uri(format="png")         # Encode to data URI
+MediaRef(uri=data_uri)                                 # Create from data URI
+
+# Path resolution for MCAP/rosbag datasets
+ref = MediaRef(uri="relative/video.mkv", pts_ns=123456)
+ref.resolve_relative_path("/data/recording.mcap")      # Returns absolute path
+
+# Serialization (Pydantic-based)
+ref.model_dump()                                       # {'uri': '...', 'pts_ns': ...}
+ref.model_dump_json()                                  # '{"uri":"...","pts_ns":...}'
+MediaRef.model_validate(data)                          # From dict
+MediaRef.model_validate_json(json_str)                 # From JSON string
+```
+
+## API Reference
+
+### MediaRef(uri: str, pts_ns: int | None = None)
+
+**Properties:** `is_embedded`, `is_video`, `is_remote`, `is_local`, `is_relative_path`
+
+**Methods:**
+- `to_rgb_array(**kwargs) -> np.ndarray` - Load as RGB array (H, W, 3)
+- `to_pil_image(**kwargs) -> PIL.Image` - Load as PIL Image
+- `embed_as_data_uri(format="png", quality=None) -> str` - Encode to data URI
+- `resolve_relative_path(base_path, allow_nonlocal=False) -> MediaRef` - Resolve relative paths
+- `validate_uri() -> bool` - Check if URI exists (local files only)
+- `model_dump() -> dict` - Serialize to dict
+- `model_dump_json() -> str` - Serialize to JSON
+- `model_validate(data) -> MediaRef` - Deserialize from dict
+- `model_validate_json(json_str) -> MediaRef` - Deserialize from JSON
+
+### Functions
+
+- `load_batch(refs: list[MediaRef], **kwargs) -> list[np.ndarray]` - Batch load with caching
+- `cleanup_cache()` - Clear video container cache
+
+### Video Decoders (requires `[loader]` extra)
+
+- `PyAVVideoDecoder(video_path)` - PyAV-based decoder with TorchCodec-compatible interface
+- `TorchCodecVideoDecoder(video_path)` - TorchCodec-based decoder (requires `torchcodec>=0.4.0`)
+
+## Design Notes
+
+- Video container caching uses reference counting with LRU eviction (default: 10 containers)
+- MCAP file path resolution: detects `.mcap` suffix and uses parent directory as base
+- Garbage collection triggered every 10 PyAV operations to handle reference cycles
+- Cache size configurable via `AV_CACHE_SIZE` environment variable
+
+## Acknowledgments
+
+The video decoder interface design references [TorchCodec](https://github.com/pytorch/torchcodec)'s API design.
+
+## Dependencies
+
+**Core:** `pydantic>=2.0` (requires Pydantic v2 API)
+
+**Loader (optional):** `numpy`, `opencv-python`, `pillow`, `av`, `requests`
+
+The loader dependencies use stable APIs with no version constraints. Install with `pip install mediaref[loader]` to enable batch loading and video decoding.
+

mediaref-0.1.0/README.md

@@ -0,0 +1,97 @@
+# MediaRef
+
+Pydantic-based media reference for images and video frames. Supports file paths, URLs, data URIs, and video timestamps. Designed for dataset metadata and lazy loading.
+
+## Installation
+
+```bash
+# Core package (MediaRef definition only)
+pip install -e .
+
+# With loader support (includes batch loading, video decoders)
+pip install -e ".[loader]"
+```
+
+## Usage
+
+```python
+from mediaref import MediaRef, load_batch
+
+# Reference creation - supports multiple URI schemes
+MediaRef(uri="image.png")                              # Local file
+MediaRef(uri="https://example.com/image.jpg")          # Remote URL
+MediaRef(uri="video.mp4", pts_ns=1_000_000_000)        # Video frame at 1.0s
+MediaRef(uri="data:image/png;base64,...")              # Embedded data URI
+
+# Loading
+ref.to_rgb_array()                                     # Returns (H, W, 3) numpy array
+ref.to_pil_image()                                     # Returns PIL.Image
+
+# Batch loading with automatic caching (default: PyAV decoder)
+refs = [MediaRef(uri="video.mp4", pts_ns=i*1e9) for i in range(10)]
+frames = load_batch(refs)                              # Reuses video container
+
+# Use TorchCodec decoder for GPU acceleration (requires torchcodec>=0.4.0)
+frames = load_batch(refs, decoder="torchcodec")
+
+# Embedding
+data_uri = ref.embed_as_data_uri(format="png")         # Encode to data URI
+MediaRef(uri=data_uri)                                 # Create from data URI
+
+# Path resolution for MCAP/rosbag datasets
+ref = MediaRef(uri="relative/video.mkv", pts_ns=123456)
+ref.resolve_relative_path("/data/recording.mcap")      # Returns absolute path
+
+# Serialization (Pydantic-based)
+ref.model_dump()                                       # {'uri': '...', 'pts_ns': ...}
+ref.model_dump_json()                                  # '{"uri":"...","pts_ns":...}'
+MediaRef.model_validate(data)                          # From dict
+MediaRef.model_validate_json(json_str)                 # From JSON string
+```
+
+## API Reference
+
+### MediaRef(uri: str, pts_ns: int | None = None)
+
+**Properties:** `is_embedded`, `is_video`, `is_remote`, `is_local`, `is_relative_path`
+
+**Methods:**
+- `to_rgb_array(**kwargs) -> np.ndarray` - Load as RGB array (H, W, 3)
+- `to_pil_image(**kwargs) -> PIL.Image` - Load as PIL Image
+- `embed_as_data_uri(format="png", quality=None) -> str` - Encode to data URI
+- `resolve_relative_path(base_path, allow_nonlocal=False) -> MediaRef` - Resolve relative paths
+- `validate_uri() -> bool` - Check if URI exists (local files only)
+- `model_dump() -> dict` - Serialize to dict
+- `model_dump_json() -> str` - Serialize to JSON
+- `model_validate(data) -> MediaRef` - Deserialize from dict
+- `model_validate_json(json_str) -> MediaRef` - Deserialize from JSON
+
+### Functions
+
+- `load_batch(refs: list[MediaRef], **kwargs) -> list[np.ndarray]` - Batch load with caching
+- `cleanup_cache()` - Clear video container cache
+
+### Video Decoders (requires `[loader]` extra)
+
+- `PyAVVideoDecoder(video_path)` - PyAV-based decoder with TorchCodec-compatible interface
+- `TorchCodecVideoDecoder(video_path)` - TorchCodec-based decoder (requires `torchcodec>=0.4.0`)
+
+## Design Notes
+
+- Video container caching uses reference counting with LRU eviction (default: 10 containers)
+- MCAP file path resolution: detects `.mcap` suffix and uses parent directory as base
+- Garbage collection triggered every 10 PyAV operations to handle reference cycles
+- Cache size configurable via `AV_CACHE_SIZE` environment variable
+
+## Acknowledgments
+
+The video decoder interface design references [TorchCodec](https://github.com/pytorch/torchcodec)'s API design.
+
+## Dependencies
+
+**Core:** `pydantic>=2.0` (requires Pydantic v2 API)
+
+**Loader (optional):** `numpy`, `opencv-python`, `pillow`, `av`, `requests`
+
+The loader dependencies use stable APIs with no version constraints. Install with `pip install mediaref[loader]` to enable batch loading and video decoding.
+