add supported formats to README (#156)

* add supported formats to README

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update tests / supported table

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

.pre-commit-config.yaml

@@ -33,8 +33,8 @@ repos:
         args: [ --fix ]
       # Run the formatter.
       - id: ruff-format
-  - repo: https://github.com/executablebooks/mdformat
-    rev: 0.7.19
-    hooks:
-    - id: mdformat
-      args: ["--wrap=80"]
+  # - repo: https://github.com/executablebooks/mdformat
+  #   rev: 0.7.19
+  #   hooks:
+  #   - id: mdformat
+  #     args: ["--wrap=80"]

README.md

@@ -48,6 +48,50 @@ ZnH5MD circumvents two current limitations of the H5MD standard.
   first frame. Using this feature will not typically not break ompatibility with
   other H5MD tools but can lead to unexpected behaviour.
 
+## Supported
+
+### `atoms.info` entry
+
+`dict` and `list` entries assume python standard types if not otherwise specified.
+
+| Type                     | ZnH5MD |
+|--------------------------|--------|
+| `np.ndarray`             | ✅     |
+| `float`                  | ✅     |
+| `str`                    | ✅     |
+| `dict`                   | ✅     |
+| `list`                   | ✅     |
+| `list[np.ndarray]`       | ✅     |
+| `dict[str, np.ndarray]`  | ❌     |
+| `list[dict]`             | ❌     |
+
+### `atoms.arrays`
+
+| Type                     | ZnH5MD |
+|--------------------------|--------|
+| `np.ndarray`             | ✅     |
+| `float`                  | ✅     |
+| `str`                    | ✅     |
+| `dict`                   | ✅     |
+| `list`                   | ✅     |
+| `list[np.ndarray]`       | ✅     |
+| `dict[str, np.ndarray]`  | ❌     |
+| `list[dict]`             | ❌     |
+
+
+### `atoms.calc.results`
+
+| Type                     | ZnH5MD |
+|--------------------------|--------|
+| `np.ndarray`             | ✅     |
+| `float`                  | ✅     |
+| `str`                    | ✅     |
+| `dict`                   | ✅     |
+| `list`                   | ✅     |
+| `list[np.ndarray]`       | ✅     |
+| `dict[str, np.ndarray]`  | ❌     |
+| `list[dict]`             | ❌     |
+
 ## Current limitations
 
 This is a not necessarily complete list of Limitations that will be fixed

tests/conftest.py

@@ -86,10 +86,16 @@ def s22_info_arrays_calc() -> list[ase.Atoms]:
                 "mlip_stress": np.random.rand(6),
                 "collection": "s22",
                 "metadata": {"author": "Jane Doe", "date": "2021-09-01"},
+                "lst": [1, 2, 3],
+                # "lst_str": ["Jane Doe", "John Doe"],
+                # "lst_array": [np.random.rand(3), np.random.rand(3)],
             }
         )
         atoms.new_array("mlip_forces", np.random.rand(len(atoms), 3))
         atoms.new_array("mlip_forces_2", np.random.rand(len(atoms), 3))
+        # atoms.arrays["arr_lst_arr"] = [np.random.rand(3) for _ in range(len(atoms))]
+        # atoms.arrays["arr_lst"] = [[1, 2, 3] for _ in range(len(atoms))]
+        # atoms.new_array("arr_str", np.array(["abc" for _ in range(len(atoms))]))
         atoms.set_velocities(np.random.rand(len(atoms), 3))
         calc = SinglePointCalculator(
             atoms, energy=np.random.rand(), forces=np.random.rand(len(atoms), 3)
@@ -115,7 +121,17 @@ def s22_illegal_calc_results() -> list[ase.Atoms]:
     for atoms in ase.collections.s22:
         atoms.calc = SinglePointCalculator(atoms)
         atoms.calc.results["mlip_energy"] = np.random.rand()
-
+        atoms.calc.results["dict"] = {"author": "Jane Doe", "date": "2021-09-01"}
+        atoms.calc.results["float"] = 3.14
+        atoms.calc.results["int"] = 42
+        atoms.calc.results["list"] = [1, 2, 3]
+        atoms.calc.results["str"] = '{"author": "Jane Doe", "date": "2021-09-01"}'
+        atoms.calc.results["list_array"] = [np.random.rand(3), np.random.rand(3)]
+        atoms.calc.results["list_str"] = ["Jane Doe", "John Doe"]
+        # atoms.calc.results["list_dict"] = [
+        #     {"author": "Jane Doe", "date": "2021-09-01"},
+        #     {"author": "John Doe", "date": "2021-09-02"},
+        # ]
         images.append(atoms)
     return images
 

tests/format/test_info_array_calc.py

@@ -0,0 +1,143 @@
+import numpy as np
+import numpy.testing as npt
+import pytest
+from ase.build import molecule
+from ase.calculators.singlepoint import SinglePointCalculator
+
+import znh5md
+
+
+# Define assertion functions for different data types
+def assert_equal(actual, expected):
+    assert actual == expected
+
+
+def assert_allclose(actual, expected):
+    npt.assert_allclose(actual, expected)
+
+
+def assert_allclose_list(actual, expected):
+    for a, e in zip(actual, expected):
+        npt.assert_allclose(a, e)
+
+
+def assert_dict_allclose(actual, expected):
+    for key in expected:
+        npt.assert_allclose(actual[key], expected[key])
+
+
+# Pytest fixtures
+@pytest.fixture
+def io_fixture(tmp_path):
+    """Fixture to initialize the ZnH5MD IO object."""
+    return znh5md.IO(tmp_path / "test.h5")
+
+
+@pytest.fixture
+def water_molecule():
+    """Fixture to provide a simple water molecule."""
+    return molecule("H2O")
+
+
+@pytest.mark.parametrize(
+    "key,value,assert_fn",
+    [
+        ("str", "Hello World", assert_equal),
+        ("float", 3.14, assert_equal),
+        ("ndarray", np.random.rand(10), assert_allclose),
+        ("list_float", [1.0, 2.0, 3.0], assert_allclose),
+        ("list_str", ["Hello", "World"], assert_equal),
+        ("dict", {"a": 1, "b": 2}, assert_equal),
+        ("dict_str", {"a": "Hello", "b": "World"}, assert_equal),
+        ("list_array", [np.random.rand(10), np.random.rand(10)], assert_allclose_list),
+        ("dict_dict", {"a": {"x": 1, "y": 2}, "b": {"x": 3, "y": 4}}, assert_equal),
+        # (
+        #     "dict_array",
+        #     {"a": np.random.rand(10), "b": np.random.rand(10)},
+        #     assert_dict_allclose,
+        # ),
+        # ("list_dict", [{"a": 1, "b": 2}, {"c": 3, "d": 4}], assert_equal),
+    ],
+)
+def test_info(io_fixture, water_molecule, key, value, assert_fn):
+    """Generic test for different info types."""
+    # Assign the value to the molecule's info
+    water_molecule.info[key] = value
+
+    # Append to the ZnH5MD IO object
+    io_fixture.append(water_molecule)
+
+    # Retrieve and test
+    assert_fn(io_fixture[0].info[key], value)
+    assert key not in io_fixture[0].arrays
+    assert io_fixture[0].calc is None
+
+
+@pytest.mark.parametrize(
+    "key,value,assert_fn",
+    [
+        ("str", "Hello World", assert_equal),
+        ("float", 3.14, assert_equal),
+        ("ndarray", np.random.rand(10), assert_allclose),
+        ("list_float", [1.0, 2.0, 3.0], assert_allclose),
+        ("list_str", ["Hello", "World"], assert_equal),
+        ("dict", {"a": 1, "b": 2}, assert_equal),
+        ("dict_str", {"a": "Hello", "b": "World"}, assert_equal),
+        ("list_array", [np.random.rand(10), np.random.rand(10)], assert_allclose_list),
+        ("dict_dict", {"a": {"x": 1, "y": 2}, "b": {"x": 3, "y": 4}}, assert_equal),
+        # (
+        #     "dict_array",
+        #     {"a": np.random.rand(10), "b": np.random.rand(10)},
+        #     assert_dict_allclose,
+        # ),
+        # ("list_dict", [{"a": 1, "b": 2}, {"c": 3, "d": 4}], assert_equal),
+    ],
+)
+def test_calc(io_fixture, water_molecule, key, value, assert_fn):
+    """Generic test for different calc types."""
+    # Assign the value to the molecule's info
+    water_molecule.calc = SinglePointCalculator(water_molecule)
+    water_molecule.calc.results[key] = value
+
+    # Append to the ZnH5MD IO object
+    io_fixture.append(water_molecule)
+
+    # Retrieve and test
+    assert_fn(io_fixture[0].calc.results[key], value)
+    assert key not in io_fixture[0].arrays
+    assert io_fixture[0].info == {}
+
+
+@pytest.mark.parametrize(
+    "key,value,assert_fn",
+    [
+        ("str", "Hello World", assert_equal),
+        ("float", 3.14, assert_equal),
+        ("ndarray", np.random.rand(10), assert_allclose),
+        ("list_float", [1.0, 2.0, 3.0], assert_allclose),
+        ("list_str", ["Hello", "World"], assert_equal),
+        ("dict", {"a": 1, "b": 2}, assert_equal),
+        ("dict_str", {"a": "Hello", "b": "World"}, assert_equal),
+        ("list_array", [np.random.rand(10), np.random.rand(10)], assert_allclose_list),
+        ("dict_dict", {"a": {"x": 1, "y": 2}, "b": {"x": 3, "y": 4}}, assert_equal),
+        # (
+        #     "dict_array",
+        #     {"a": np.random.rand(10), "b": np.random.rand(10)},
+        #     assert_dict_allclose,
+        # ),
+        # ("list_dict", [{"a": 1, "b": 2}, {"c": 3, "d": 4}], assert_equal),
+    ],
+)
+def test_arrays(io_fixture, water_molecule, key, value, assert_fn):
+    """Generic test for different calc types."""
+    # Assign the value to the molecule's info
+    water_molecule.arrays[key] = value
+
+    # Append to the ZnH5MD IO object
+    io_fixture.append(water_molecule)
+
+    # Retrieve and test
+    assert_fn(io_fixture[0].arrays[key], value)
+    # assert key not in io_fixture[0].arrays
+    assert io_fixture[0].info == {}
+    assert io_fixture[0].calc is None