.gitignore

@@ -5,3 +5,5 @@ benchmarks/longmemeval/*.json
 # Local model weights (MiniLM etc.) — large, not committed
 weights/
 .venv
+__pycache__/
+.pytest_cache/

CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ## Unreleased
 
+### Python bindings (2026-09-26)
+- **`pip install` / `maturin develop` now gives `import clawhdf5`.** The
+  distribution in `crates/clawhdf5-py/pyproject.toml` was still called
+  `rustyhdf5` while the extension module was `clawhdf5`, and the package's
+  tests imported `rustyhdf5`, so they failed at collection. Distribution,
+  module and tests now all say `clawhdf5`, and the module has
+  `__version__`.
+
 ### Plugin filters (2026-09-26)
 - **LZF, bitshuffle, bzip2 and Blosc read and write, in pure Rust.** Files
   written by h5py with `compression="lzf"`, or with hdf5plugin's

crates/clawhdf5-py/Cargo.toml

@@ -3,7 +3,7 @@ name = "clawhdf5-py"
 version = "2.7.0"
 edition = "2024"
 rust-version.workspace = true
-description = "Python bindings for rustyhdf5 — a pure-Rust HDF5 library"
+description = "Python bindings for clawhdf5 — a pure-Rust HDF5 library"
 license = "MIT"
 repository = "https://git.redclaw.dev/quantumclaw/clawhdf5"
 readme = "README.md"

crates/clawhdf5-py/pyproject.toml

@@ -3,12 +3,15 @@ requires = ["maturin>=1.0,<2.0"]
 build-backend = "maturin"
 
 [project]
-name = "rustyhdf5"
+name = "clawhdf5"
 version = "2.7.0"
-description = "Python bindings for rustyhdf5 — a pure-Rust HDF5 library"
+description = "Python bindings for clawhdf5 — a pure-Rust HDF5 library"
 requires-python = ">=3.8"
 license = { text = "MIT" }
 dependencies = ["numpy"]
 
 [tool.maturin]
 features = ["extension-module"]
+# The extension module is `clawhdf5` (the cdylib's [lib] name): the
+# distribution, the import name and the #[pymodule] all agree.
+module-name = "clawhdf5"

crates/clawhdf5-py/src/lib.rs

@@ -219,6 +219,7 @@ pub(crate) fn extract_numpy_data(
 /// The clawhdf5 Python module.
 #[pymodule]
 fn clawhdf5(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add("__version__", env!("CARGO_PKG_VERSION"))?;
     m.add_class::<PyFile>()?;
     m.add_class::<PyDataset>()?;
     m.add_class::<PyGroup>()?;

crates/clawhdf5-py/tests/test_write_read.py

@@ -1,4 +1,4 @@
-"""Tests for rustyhdf5 Python bindings."""
+"""Tests for clawhdf5 Python bindings."""
 
 import os
 import tempfile
@@ -6,7 +6,7 @@ import tempfile
 import numpy as np
 import pytest
 
-import rustyhdf5
+import clawhdf5
 
 
 @pytest.fixture
@@ -18,7 +18,7 @@ def tmp_h5(tmp_path):
 @pytest.fixture
 def sample_read_file(tmp_h5):
     """Create a sample HDF5 file for reading tests."""
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("temperatures", data=np.array([22.5, 23.1, 21.8]))
         f.create_dataset("counts", data=np.array([10, 20, 30], dtype=np.int32))
         f.attrs["version"] = 1
@@ -29,7 +29,7 @@ def sample_read_file(tmp_h5):
 @pytest.fixture
 def grouped_read_file(tmp_h5):
     """Create an HDF5 file with groups for reading tests."""
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("root_data", data=np.array([0.0, 1.0]))
         grp = f.create_group("sensors")
         grp.create_dataset("temperature", data=np.array([22.5, 23.1, 21.8]))
@@ -46,7 +46,7 @@ def grouped_read_file(tmp_h5):
 
 
 def test_open_and_read_f64(sample_read_file):
-    f = rustyhdf5.File(sample_read_file, "r")
+    f = clawhdf5.File(sample_read_file, "r")
     ds = f["temperatures"]
     data = ds[:]
     np.testing.assert_array_almost_equal(data, [22.5, 23.1, 21.8])
@@ -54,7 +54,7 @@ def test_open_and_read_f64(sample_read_file):
 
 
 def test_open_and_read_i32(sample_read_file):
-    f = rustyhdf5.File(sample_read_file, "r")
+    f = clawhdf5.File(sample_read_file, "r")
     ds = f["counts"]
     data = ds[:]
     np.testing.assert_array_equal(data, [10, 20, 30])
@@ -68,13 +68,13 @@ def test_open_and_read_i32(sample_read_file):
 
 
 def test_dataset_shape(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         ds = f["temperatures"]
         assert ds.shape == (3,)
 
 
 def test_dataset_dtype(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         assert f["temperatures"].dtype == "float64"
         assert f["counts"].dtype == "int32"
 
@@ -85,24 +85,24 @@ def test_dataset_dtype(sample_read_file):
 
 
 def test_read_root_attrs(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         assert f.attrs["version"] == 1
         assert f.attrs["description"] == "test file"
 
 
 def test_attrs_len(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         assert len(f.attrs) >= 2
 
 
 def test_attrs_contains(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         assert "version" in f.attrs
         assert "nonexistent" not in f.attrs
 
 
 def test_attrs_keys(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         keys = f.attrs.keys()
         assert "version" in keys
         assert "description" in keys
@@ -114,7 +114,7 @@ def test_attrs_keys(sample_read_file):
 
 
 def test_read_group_keys(grouped_read_file):
-    with rustyhdf5.File(grouped_read_file, "r") as f:
+    with clawhdf5.File(grouped_read_file, "r") as f:
         keys = f.keys()
         assert "sensors" in keys
         assert "metadata" in keys
@@ -122,7 +122,7 @@ def test_read_group_keys(grouped_read_file):
 
 
 def test_read_group_dataset(grouped_read_file):
-    with rustyhdf5.File(grouped_read_file, "r") as f:
+    with clawhdf5.File(grouped_read_file, "r") as f:
         grp = f["sensors"]
         ds = grp["temperature"]
         data = ds[:]
@@ -130,14 +130,14 @@ def test_read_group_dataset(grouped_read_file):
 
 
 def test_read_group_attrs(grouped_read_file):
-    with rustyhdf5.File(grouped_read_file, "r") as f:
+    with clawhdf5.File(grouped_read_file, "r") as f:
         grp = f["sensors"]
         assert grp.attrs["location"] == "lab"
 
 
 def test_nested_path_access(grouped_read_file):
     """Test f['group/dataset'] path navigation."""
-    with rustyhdf5.File(grouped_read_file, "r") as f:
+    with clawhdf5.File(grouped_read_file, "r") as f:
         ds = f["sensors/temperature"]
         data = ds[:]
         np.testing.assert_array_almost_equal(data, [22.5, 23.1, 21.8])
@@ -149,7 +149,7 @@ def test_nested_path_access(grouped_read_file):
 
 
 def test_context_manager(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         data = f["temperatures"][:]
         np.testing.assert_array_almost_equal(data, [22.5, 23.1, 21.8])
     # File should be closed after with block
@@ -162,30 +162,30 @@ def test_context_manager(sample_read_file):
 
 
 def test_write_simple(tmp_h5):
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=np.array([1.0, 2.0, 3.0]))
     # Verify by reading back
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         data = f["data"][:]
         np.testing.assert_array_almost_equal(data, [1.0, 2.0, 3.0])
 
 
 def test_write_with_attrs(tmp_h5):
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("values", data=np.array([10, 20], dtype=np.int32))
         f.attrs["author"] = "test"
         f.attrs["count"] = 42
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         assert f.attrs["author"] == "test"
         assert f.attrs["count"] == 42
 
 
 def test_write_with_group(tmp_h5):
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         grp = f.create_group("experiment")
         grp.create_dataset("results", data=np.array([3.14, 2.72]))
         grp.attrs["version"] = 1
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         ds = f["experiment/results"]
         np.testing.assert_array_almost_equal(ds[:], [3.14, 2.72])
         grp = f["experiment"]
@@ -199,9 +199,9 @@ def test_write_with_group(tmp_h5):
 
 def test_roundtrip_float64(tmp_h5):
     original = np.array([1.1, 2.2, 3.3], dtype=np.float64)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["data"][:]
         np.testing.assert_array_almost_equal(result, original)
         assert result.dtype == np.float64
@@ -209,9 +209,9 @@ def test_roundtrip_float64(tmp_h5):
 
 def test_roundtrip_float32(tmp_h5):
     original = np.array([1.5, 2.5, 3.5], dtype=np.float32)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["data"][:]
         np.testing.assert_array_almost_equal(result, original)
         assert result.dtype == np.float32
@@ -219,9 +219,9 @@ def test_roundtrip_float32(tmp_h5):
 
 def test_roundtrip_int32(tmp_h5):
     original = np.array([-10, 0, 10, 100], dtype=np.int32)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["data"][:]
         np.testing.assert_array_equal(result, original)
         assert result.dtype == np.int32
@@ -229,9 +229,9 @@ def test_roundtrip_int32(tmp_h5):
 
 def test_roundtrip_int64(tmp_h5):
     original = np.array([-1, 0, 1, 2**40], dtype=np.int64)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["data"][:]
         np.testing.assert_array_equal(result, original)
         assert result.dtype == np.int64
@@ -239,9 +239,9 @@ def test_roundtrip_int64(tmp_h5):
 
 def test_roundtrip_uint8(tmp_h5):
     original = np.array([0, 127, 255], dtype=np.uint8)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["data"][:]
         np.testing.assert_array_equal(result, original)
         assert result.dtype == np.uint8
@@ -254,7 +254,7 @@ def test_roundtrip_uint8(tmp_h5):
 
 def test_chunked_gzip(tmp_h5):
     original = np.arange(100, dtype=np.float64)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset(
             "compressed",
             data=original,
@@ -262,7 +262,7 @@ def test_chunked_gzip(tmp_h5):
             compression="gzip",
             compression_opts=6,
         )
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         result = f["compressed"][:]
         np.testing.assert_array_equal(result, original)
 
@@ -276,7 +276,7 @@ def test_h5py_can_read_our_file(tmp_h5):
     """Verify that h5py can read files we create."""
     import h5py
 
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("values", data=np.array([1.0, 2.0, 3.0]))
         f.attrs["meta"] = "hello"
     with h5py.File(tmp_h5, "r") as f:
@@ -292,7 +292,7 @@ def test_we_can_read_h5py_file(tmp_h5):
     with h5py.File(tmp_h5, "w") as f:
         f.create_dataset("data", data=np.array([10.0, 20.0, 30.0]))
         f.attrs["version"] = 2
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         data = f["data"][:]
         np.testing.assert_array_equal(data, [10.0, 20.0, 30.0])
         assert f.attrs["version"] == 2
@@ -305,9 +305,9 @@ def test_we_can_read_h5py_file(tmp_h5):
 
 def test_2d_array_roundtrip(tmp_h5):
     original = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype=np.float64)
-    with rustyhdf5.File(tmp_h5, "w") as f:
+    with clawhdf5.File(tmp_h5, "w") as f:
         f.create_dataset("matrix", data=original)
-    with rustyhdf5.File(tmp_h5, "r") as f:
+    with clawhdf5.File(tmp_h5, "r") as f:
         ds = f["matrix"]
         assert ds.shape == (2, 3)
         result = ds[:]
@@ -321,15 +321,15 @@ def test_2d_array_roundtrip(tmp_h5):
 
 def test_open_nonexistent_file():
     with pytest.raises(OSError):
-        rustyhdf5.File("/nonexistent/path.h5", "r")
+        clawhdf5.File("/nonexistent/path.h5", "r")
 
 
 def test_invalid_mode(tmp_h5):
     with pytest.raises(ValueError):
-        rustyhdf5.File(tmp_h5, "x")
+        clawhdf5.File(tmp_h5, "x")
 
 
 def test_key_error_on_missing_dataset(sample_read_file):
-    with rustyhdf5.File(sample_read_file, "r") as f:
+    with clawhdf5.File(sample_read_file, "r") as f:
         with pytest.raises(KeyError):
             f["nonexistent"]