xarray-dbd 0.2.0__tar.gz

xarray_dbd-0.2.0/.clang-tidy

@@ -0,0 +1,41 @@
+---
+# clang-tidy configuration for xarray-dbd C++ extension
+#
+# Focused checks for C++17 codebase with pybind11 bindings.
+# Run via: cmake -B build -DENABLE_CLANG_TIDY=ON && cmake --build build
+
+Checks: >
+  -*,
+  bugprone-*,
+  cppcoreguidelines-*,
+  modernize-*,
+  performance-*,
+  readability-braces-around-statements,
+  readability-container-size-empty,
+  readability-else-after-return,
+  readability-implicit-bool-conversion,
+  readability-redundant-smartptr-get,
+  readability-simplify-boolean-expr,
+  -bugprone-easily-swappable-parameters,
+  -cppcoreguidelines-avoid-magic-numbers,
+  -cppcoreguidelines-pro-type-reinterpret-cast,
+  -cppcoreguidelines-pro-type-union-access,
+  -cppcoreguidelines-pro-bounds-pointer-arithmetic,
+  -cppcoreguidelines-pro-bounds-array-to-pointer-decay,
+  -cppcoreguidelines-pro-bounds-constant-array-index,
+  -cppcoreguidelines-avoid-c-arrays,
+  -cppcoreguidelines-avoid-non-const-global-variables,
+  -cppcoreguidelines-owning-memory,
+  -cppcoreguidelines-special-member-functions,
+  -cppcoreguidelines-non-private-member-variables-in-classes,
+  -modernize-use-trailing-return-type,
+  -modernize-avoid-c-arrays,
+  -modernize-use-nodiscard,
+
+WarningsAsErrors: ''
+
+HeaderFilterRegex: 'csrc/.*\.H$'
+
+CheckOptions:
+  - key: readability-braces-around-statements.ShortStatementLines
+    value: '1'

xarray_dbd-0.2.0/.gitignore

@@ -0,0 +1,159 @@
+# 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
+*.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/
+
+# 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
+Pipfile.lock
+
+# PEP 582
+__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
+
+# ruff
+.ruff_cache/
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# macOS
+.DS_Store
+
+# CMake / scikit-build-core build artifacts
+_skbuild/
+CMakeCache.txt
+CMakeFiles/
+cmake_install.cmake
+
+# Project specific
+dbd2netcdf/
+cache/
+*.nc
+*.dbd
+*.dcd
+*.ebd
+*.ecd
+*.sbd
+*.scd
+*.tbd
+*.tcd
+*.mbd
+*.mcd
+*.nbd
+*.ncd

xarray_dbd-0.2.0/.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.10
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format

xarray_dbd-0.2.0/CHANGELOG.md

@@ -0,0 +1,25 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.0] - 2026-02-20
+
+### Added
+
+- C++ backend via pybind11 wrapping [dbd2netCDF](https://github.com/mousebrains/dbd2netcdf) parser
+- Native xarray engine integration (`xr.open_dataset(f, engine="dbd")`)
+- Multi-file reading with `open_multi_dbd_dataset()` using C++ SensorsMap two-pass approach
+- CLI tools: `dbd2nc` for single/multi-file conversion, `mkone` for batch directory processing
+- Native dtype support: int8, int16, float32, float64 columns (no double-conversion overhead)
+- LZ4 decompression for compressed `.?cd` files
+- Sensor filtering (`to_keep`), mission filtering (`skip_missions`/`keep_missions`)
+- Corrupted file recovery with `repair=True`
+- Python 3.10+ and free-threaded Python (PEP 703) support
+
+### Changed
+
+- Replaced pure-Python parser with C++ pybind11 extension for ~5x performance improvement
+- Fill values: NaN for float32/float64, 0 for int8/int16 (matching C++ double-NaN semantics)

xarray_dbd-0.2.0/CMakeLists.txt

@@ -0,0 +1,75 @@
+cmake_minimum_required(VERSION 3.17)
+project(xarray_dbd_cpp LANGUAGES C CXX)
+
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+
+# Compiler warning flags
+if(MSVC)
+    add_compile_options(/W4)
+else()
+    add_compile_options(-Wall -Wextra -Wpedantic
+                        -Wshadow -Wconversion -Wsign-conversion -Wnon-virtual-dtor)
+endif()
+
+# Optional clang-tidy integration
+option(ENABLE_CLANG_TIDY "Enable clang-tidy static analysis" OFF)
+if(ENABLE_CLANG_TIDY)
+    find_program(CLANG_TIDY_EXE NAMES clang-tidy)
+    if(CLANG_TIDY_EXE)
+        set(CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_EXE}")
+    else()
+        message(WARNING "clang-tidy requested but not found")
+    endif()
+endif()
+
+find_package(pybind11 2.11...4 CONFIG REQUIRED)
+
+pybind11_add_module(_dbd_cpp
+    csrc/dbd_python.cpp
+    csrc/ColumnData.C
+    csrc/Header.C
+    csrc/Sensor.C
+    csrc/Sensors.C
+    csrc/SensorsMap.C
+    csrc/KnownBytes.C
+    csrc/Decompress.C
+    csrc/Data.C
+    csrc/lz4.c
+)
+
+target_include_directories(_dbd_cpp PRIVATE csrc)
+
+# Suppress warnings for vendored lz4.c
+if(MSVC)
+    set_source_files_properties(csrc/lz4.c PROPERTIES COMPILE_FLAGS /w)
+else()
+    set_source_files_properties(csrc/lz4.c PROPERTIES COMPILE_FLAGS -w)
+endif()
+
+# std::filesystem needs explicit linking on GCC < 9
+include(CheckCXXSourceCompiles)
+set(CMAKE_REQUIRED_FLAGS "-std=c++17")
+check_cxx_source_compiles("
+    #include <filesystem>
+    int main() { std::filesystem::path p(\"/tmp\"); return p.empty(); }
+" STDFS_NO_LIB)
+if(NOT STDFS_NO_LIB)
+    set(CMAKE_REQUIRED_LIBRARIES stdc++fs)
+    check_cxx_source_compiles("
+        #include <filesystem>
+        int main() { std::filesystem::path p(\"/tmp\"); return p.empty(); }
+    " STDFS_NEEDS_STDC_FS)
+    unset(CMAKE_REQUIRED_LIBRARIES)
+    if(STDFS_NEEDS_STDC_FS)
+        target_link_libraries(_dbd_cpp PRIVATE stdc++fs)
+    endif()
+endif()
+
+# Platform-specific: Windows needs winsock2 for ntohs/ntohl
+if(WIN32)
+    target_link_libraries(_dbd_cpp PRIVATE ws2_32)
+endif()
+
+install(TARGETS _dbd_cpp LIBRARY DESTINATION xarray_dbd)

xarray_dbd-0.2.0/CONTRIBUTING.md

@@ -0,0 +1,82 @@
+# Contributing to xarray-dbd
+
+Thank you for your interest in contributing! This guide covers the development
+workflow for xarray-dbd.
+
+## Development Setup
+
+**Prerequisites:** Python 3.13+, a C++17 compiler, and CMake ≥ 3.15.
+
+```bash
+git clone https://github.com/mousebrains/dbd2netcdf-python
+cd dbd2netcdf-python
+pip install -e ".[dev]"
+```
+
+The editable install compiles the C++ extension (`_dbd_cpp`) in-place.
+Re-run `pip install -e .` after changing any C++ source in `csrc/`.
+
+## Running Tests
+
+```bash
+pytest                       # all tests
+pytest tests/test_backend.py # backend integration tests only
+pytest -v --tb=short         # verbose with short tracebacks
+```
+
+Some tests require sample `.dbd`/`.dcd` files in `dbd_files/`. Tests that need
+data are skipped automatically when the directory is absent.
+
+## Linting and Formatting
+
+```bash
+ruff check xarray_dbd/ tests/ *.py   # lint
+ruff format xarray_dbd/ tests/ *.py  # auto-format
+mypy xarray_dbd/                     # type checking
+```
+
+Configuration for all tools lives in `pyproject.toml`. The project uses a
+100-character line length.
+
+## Syncing C++ Changes from Upstream
+
+The C++ parser in `csrc/` is a copy of
+[dbd2netCDF](https://github.com/mousebrains/dbd2netcdf) (`src/` directory).
+To incorporate upstream changes:
+
+1. Copy updated `.C` / `.H` files from `dbd2netcdf/src/` into `csrc/`.
+2. Keep `csrc/Logger.H` (our no-op stub replacing spdlog) and
+   `csrc/dbd_python.cpp` (pybind11 bindings) — these are local files.
+3. Rebuild: `pip install -e .`
+4. Run the full test suite and compare output against the C++ reference.
+
+See `docs/SYNC.md` for the detailed file mapping.
+
+## Project Layout
+
+```
+csrc/           C++ source (pybind11 extension)
+xarray_dbd/    Python package (backend, CLI, public API)
+tests/         pytest test suite
+scripts/       Utility and debug scripts
+docs/          Project documentation
+conda/         Conda build recipe
+```
+
+## Pull Request Guidelines
+
+- Keep changes focused — one logical change per PR.
+- Add or update tests for any behavioral changes.
+- Run `ruff check`, `ruff format`, and `mypy` before submitting.
+- Include a clear description of *what* and *why* in the PR body.
+
+## Commit Messages
+
+Use conventional-style messages:
+
+```
+Fix sensor cache lookup for compressed .ccc files
+
+The cache reader was only checking .cac files. Now tries .ccc
+(LZ4-compressed) as a fallback, matching dbd2netCDF behavior.
+```