pyadata-cli 0.5.0__tar.gz

pyadata_cli-0.5.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Cellular Genomics Informatics
+
+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.

pyadata_cli-0.5.0/PKG-INFO

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: pyadata-cli
+Version: 0.5.0
+Summary: Streaming CLI for exploring and editing large AnnData .h5ad and .zarr stores
+Keywords: anndata,h5ad,zarr,bioinformatics,single-cell,cli
+Author: Aljes Binkevich
+Author-email: Aljes Binkevich <ab76@sanger.ac.uk>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Typing :: Typed
+Requires-Dist: h5py>=3.15.1
+Requires-Dist: numpy>=2.3.5
+Requires-Dist: pillow>=12.1.0
+Requires-Dist: rich>=14.2.0
+Requires-Dist: typer>=0.20.0
+Requires-Dist: zarr>=3.1.5
+Requires-Dist: pytest>=8.3.4 ; extra == 'dev'
+Requires-Dist: pytest-cov>=6.0.0 ; extra == 'dev'
+Requires-Dist: pytest-timeout>=2.3.0 ; extra == 'dev'
+Requires-Dist: anndata>=0.13 ; extra == 'dev'
+Maintainer: Aljes Binkevich
+Maintainer-email: Aljes Binkevich <ab76@sanger.ac.uk>
+Requires-Python: >=3.12
+Project-URL: Changelog, https://github.com/cellgeni/adata-cli/blob/main/CHANGELOG.md
+Project-URL: Documentation, https://cellgeni.github.io/adata-cli/
+Project-URL: Homepage, https://github.com/cellgeni/adata-cli
+Project-URL: Issues, https://github.com/cellgeni/adata-cli/issues
+Project-URL: Repository, https://github.com/cellgeni/adata-cli
+Provides-Extra: dev
+Description-Content-Type: text/markdown
+
+# adata CLI
+
+A command-line tool for exploring huge AnnData stores (`.h5ad` and `.zarr`) without loading them fully into memory. Streams data directly from disk for efficient inspection of structure, metadata, and matrices.
+
+## Features
+
+- Streaming access to very large `.h5ad` and `.zarr` stores
+- Auto-detects `.h5ad` files vs `.zarr` directories
+- Chunked processing for dense and sparse matrices (CSR/CSC)
+- Reads every AnnData on-disk layout, from 0.7.x through the current spec, and always writes the current one
+- Converts between HDF5 and Zarr (v2 and v3) in either direction
+- Rich terminal output with progress indicators, kept on stderr so results pipe cleanly
+
+**Documentation: [cellgeni.github.io/adata-cli](https://cellgeni.github.io/adata-cli/)**
+
+## Installation
+
+```bash
+pip install pyadata-cli
+```
+
+The command is `adata`. The distribution is named `pyadata-cli` because
+`adata-cli` was already taken on PyPI by an unrelated project.
+
+From source with [uv](https://docs.astral.sh/uv/):
+```bash
+git clone https://github.com/cellgeni/adata-cli.git
+cd adata-cli
+uv sync
+```
+
+For development and testing:
+```bash
+uv sync --extra dev
+```
+
+Alternative with pip:
+```bash
+git clone https://github.com/cellgeni/adata-cli.git
+cd adata-cli
+pip install .
+```
+
+For development and testing with pip:
+```bash
+pip install -e ".[dev]"
+```
+
+## Commands (Overview)
+
+Run help at any level (e.g. `adata --help`, `adata export --help`).
+
+- `view` – AnnData-aware inspection: store layout, shapes, and encodings; supports drilling into paths like `obsm/X_pca` or `uns`.
+- `ls` – list the contents of any HDF5 or Zarr store as a tree, with no AnnData assumptions (works on `.loom` and plain `.h5`); `-1` emits bare paths for piping.
+- `create` – write a new, empty AnnData store for `import` to fill in.
+- `subset` – stream and write a filtered copy, selected by obs/var name lists (`--obs`/`--var`) or by expression (`--obs-query`/`--var-query`).
+- `split` – write one store per distinct value of an annotation column, with a CSV manifest.
+- `concat` – concatenate stores along the obs axis, with `--join inner|outer` and merge strategies for var and uns.
+- `export` – extract data from a store; subcommands: `dataframe` (any dataframe group to CSV), `array` (dense to `.npy`), `sparse` (CSR/CSC to `.mtx`), `dict` (JSON), `image` (PNG). Results go to stdout when no `--output` is given.
+- `import` – write new data into a store at any path; subcommands: `dataframe` (CSV), `array` (`.npy`), `sparse` (`.mtx`), `dict` (JSON), `image` (PNG/JPEG/TIFF).
+
+### Building a store from scratch
+
+```bash
+adata create out.h5ad --obs-names cells.txt --var-names genes.txt
+adata import sparse    out.h5ad X            counts.mtx --inplace
+adata import dataframe out.h5ad obs          cells.csv  --inplace -i cell_id
+adata import array     out.h5ad obsm/X_umap  umap.npy   --inplace
+adata import dict      out.h5ad uns/params   params.json --inplace
+```
+
+### Filtering without a name list
+
+```bash
+adata subset data.h5ad -o cortex.h5ad --obs-query "cluster == Cortex_2"
+adata subset data.h5ad -o big.h5ad    -q "n_counts > 1000 and cluster in A,B"
+adata split  data.h5ad --by sample -o per_sample/
+adata concat per_sample/*.h5ad -o merged.h5ad --join outer --label sample
+```
+
+## Documentation
+
+- [Get started](docs/GET_STARTED.md) — a short tutorial
+- [Command reference](docs/COMMANDS.md) — every command and flag
+- [Element spec: HDF5](docs/ELEMENTS_h5ad.md) / [Zarr](docs/ELEMENTS_zarr.md) — the on-disk format, and what this tool does with it
+- [Testing](docs/TESTING.md) — how the suite is organised, and how compatibility is verified against six anndata releases
+- [Changelog](CHANGELOG.md)
+
+## Docker
+
+A docker image is available on QUAY: `quay.io/cellgeni/adata-cli:latest`. Pull and run with:
+
+```bash
+docker run --rm -it -v /path/to/data:/data quay.io/cellgeni/adata-cli:latest view /data/your_file.h5ad
+```

pyadata_cli-0.5.0/README.md

@@ -0,0 +1,95 @@
+# adata CLI
+
+A command-line tool for exploring huge AnnData stores (`.h5ad` and `.zarr`) without loading them fully into memory. Streams data directly from disk for efficient inspection of structure, metadata, and matrices.
+
+## Features
+
+- Streaming access to very large `.h5ad` and `.zarr` stores
+- Auto-detects `.h5ad` files vs `.zarr` directories
+- Chunked processing for dense and sparse matrices (CSR/CSC)
+- Reads every AnnData on-disk layout, from 0.7.x through the current spec, and always writes the current one
+- Converts between HDF5 and Zarr (v2 and v3) in either direction
+- Rich terminal output with progress indicators, kept on stderr so results pipe cleanly
+
+**Documentation: [cellgeni.github.io/adata-cli](https://cellgeni.github.io/adata-cli/)**
+
+## Installation
+
+```bash
+pip install pyadata-cli
+```
+
+The command is `adata`. The distribution is named `pyadata-cli` because
+`adata-cli` was already taken on PyPI by an unrelated project.
+
+From source with [uv](https://docs.astral.sh/uv/):
+```bash
+git clone https://github.com/cellgeni/adata-cli.git
+cd adata-cli
+uv sync
+```
+
+For development and testing:
+```bash
+uv sync --extra dev
+```
+
+Alternative with pip:
+```bash
+git clone https://github.com/cellgeni/adata-cli.git
+cd adata-cli
+pip install .
+```
+
+For development and testing with pip:
+```bash
+pip install -e ".[dev]"
+```
+
+## Commands (Overview)
+
+Run help at any level (e.g. `adata --help`, `adata export --help`).
+
+- `view` – AnnData-aware inspection: store layout, shapes, and encodings; supports drilling into paths like `obsm/X_pca` or `uns`.
+- `ls` – list the contents of any HDF5 or Zarr store as a tree, with no AnnData assumptions (works on `.loom` and plain `.h5`); `-1` emits bare paths for piping.
+- `create` – write a new, empty AnnData store for `import` to fill in.
+- `subset` – stream and write a filtered copy, selected by obs/var name lists (`--obs`/`--var`) or by expression (`--obs-query`/`--var-query`).
+- `split` – write one store per distinct value of an annotation column, with a CSV manifest.
+- `concat` – concatenate stores along the obs axis, with `--join inner|outer` and merge strategies for var and uns.
+- `export` – extract data from a store; subcommands: `dataframe` (any dataframe group to CSV), `array` (dense to `.npy`), `sparse` (CSR/CSC to `.mtx`), `dict` (JSON), `image` (PNG). Results go to stdout when no `--output` is given.
+- `import` – write new data into a store at any path; subcommands: `dataframe` (CSV), `array` (`.npy`), `sparse` (`.mtx`), `dict` (JSON), `image` (PNG/JPEG/TIFF).
+
+### Building a store from scratch
+
+```bash
+adata create out.h5ad --obs-names cells.txt --var-names genes.txt
+adata import sparse    out.h5ad X            counts.mtx --inplace
+adata import dataframe out.h5ad obs          cells.csv  --inplace -i cell_id
+adata import array     out.h5ad obsm/X_umap  umap.npy   --inplace
+adata import dict      out.h5ad uns/params   params.json --inplace
+```
+
+### Filtering without a name list
+
+```bash
+adata subset data.h5ad -o cortex.h5ad --obs-query "cluster == Cortex_2"
+adata subset data.h5ad -o big.h5ad    -q "n_counts > 1000 and cluster in A,B"
+adata split  data.h5ad --by sample -o per_sample/
+adata concat per_sample/*.h5ad -o merged.h5ad --join outer --label sample
+```
+
+## Documentation
+
+- [Get started](docs/GET_STARTED.md) — a short tutorial
+- [Command reference](docs/COMMANDS.md) — every command and flag
+- [Element spec: HDF5](docs/ELEMENTS_h5ad.md) / [Zarr](docs/ELEMENTS_zarr.md) — the on-disk format, and what this tool does with it
+- [Testing](docs/TESTING.md) — how the suite is organised, and how compatibility is verified against six anndata releases
+- [Changelog](CHANGELOG.md)
+
+## Docker
+
+A docker image is available on QUAY: `quay.io/cellgeni/adata-cli:latest`. Pull and run with:
+
+```bash
+docker run --rm -it -v /path/to/data:/data quay.io/cellgeni/adata-cli:latest view /data/your_file.h5ad
+```

pyadata_cli-0.5.0/pyproject.toml

@@ -0,0 +1,90 @@
+[project]
+# The short name `adata-cli` was taken on PyPI by an unrelated project,
+# so the distribution is published as `pyadata-cli`. The import package
+# and the command are both still `adata`.
+name = "pyadata-cli"
+version = "0.5.0"
+description = "Streaming CLI for exploring and editing large AnnData .h5ad and .zarr stores"
+readme = "README.md"
+requires-python = ">=3.12"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Aljes Binkevich", email = "ab76@sanger.ac.uk" },
+]
+maintainers = [
+    { name = "Aljes Binkevich", email = "ab76@sanger.ac.uk" },
+]
+keywords = [
+    "anndata",
+    "h5ad",
+    "zarr",
+    "bioinformatics",
+    "single-cell",
+    "cli",
+]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Console",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Typing :: Typed",
+]
+
+dependencies = [
+    "h5py>=3.15.1",
+    "numpy>=2.3.5",
+    "pillow>=12.1.0",
+    "rich>=14.2.0",
+    "typer>=0.20.0",
+    "zarr>=3.1.5",
+]
+
+[project.urls]
+Homepage = "https://github.com/cellgeni/adata-cli"
+Repository = "https://github.com/cellgeni/adata-cli"
+Documentation = "https://cellgeni.github.io/adata-cli/"
+Issues = "https://github.com/cellgeni/adata-cli/issues"
+Changelog = "https://github.com/cellgeni/adata-cli/blob/main/CHANGELOG.md"
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.3.4",
+    "pytest-cov>=6.0.0",
+    # Turns a hang into a failure with a traceback. Without it a stuck test
+    # burns the CI job's whole timeout and reports nothing useful.
+    "pytest-timeout>=2.3.0",
+    # Used only by tests/test_anndata_roundtrip.py, to check that what this
+    # tool reads and writes matches what anndata itself produces.
+    "anndata>=0.13",
+]
+
+[build-system]
+requires = ["uv_build>=0.8.0,<0.9.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-name = "adata"
+
+
+[project.scripts]
+adata = "adata.cli:main"
+# Deprecated alias, removed in 1.0.0
+h5ad = "adata.cli:main_deprecated"
+
+[tool.coverage.run]
+source = ["src/adata"]
+omit = [
+    "*/tests/*",
+    "*/__pycache__/*",
+]
+
+[tool.coverage.report]
+precision = 2
+show_missing = true
+skip_covered = false

pyadata_cli-0.5.0/src/adata/__init__.py

@@ -0,0 +1,10 @@
+"""adata-cli: streaming CLI for large AnnData .h5ad and .zarr stores."""
+
+from importlib.metadata import PackageNotFoundError, version as _version
+
+try:
+    __version__ = _version("pyadata-cli")
+except PackageNotFoundError:  # pragma: no cover - running from a source tree
+    __version__ = "0.0.0+unknown"
+
+__all__ = ["__version__"]