pymdkit 1.6.1__tar.gz → 1.6.2__tar.gz

{pymdkit-1.6.1 → pymdkit-1.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pymdkit
-Version: 1.6.1
+Version: 1.6.2
 Summary: A unified command-line toolkit for atomistic / MD structure workflows.
 Author-email: Yueda Wang <ydwang0608@ustc.edu.cn>
 License-Expression: GPL-3.0-or-later
@@ -263,8 +263,9 @@ and `0.875`. Generated CIF occupancy fields use two decimal places.
 `-max-supercell AxBxC` searches bounded diagonal supercells, smallest volume
 first, until every multiplicity times occupancy times supercell determinant is
 an integer. Equal-volume choices favor the most isotropic resulting cell.
-All selections, site atom counts, oxidation states, charges, and failures are
-recorded in `OUTPUT/realloc-occ.txt`.
+All selections, site atom counts, oxidation states, charges, failures, the
+allowed occupancy grid, and the final summary are recorded in
+`OUTPUT/realloc-occ.txt` for both single-file and folder modes.
 
 `gather-fs` recursively scans all job folders below the current directory. For
 VASP it follows the global `vaspout.h5 > vasprun.xml > OUTCAR` priority and
@@ -330,6 +331,14 @@ International Tables setting from pymatgen/spglib and correspond to the
 [Bilbao Crystallographic Server WYCKPOS tables](https://cryst.ehu.es/cryst/get_wp.html);
 the provenance URL is also recorded inside each generated CIF.
 
+For structural conversion, supercell creation, and GPUMD grouping, PMK reads
+CIF input with pymatgen rather than ASE. ASE interprets
+`_space_group_crystal_system` as a setting hint only for rhombohedral groups
+and emits a potentially misleading warning for other crystal systems. Using
+pymatgen avoids that ambiguity while PMK continues to use ASE for non-CIF
+formats. A partially occupied CIF must first be ordered with `convert -d2o`
+before it can be represented as an explicit atom list.
+
 CIF `_atom_type_symbol` and `_atom_site_label` values use per-element
 inequivalent-site identifiers such as `Li1`, `Y1`, `Cl1`, and `Cl2`.
 The final atom-site loop starts with `_atom_site_label`, followed by

{pymdkit-1.6.1 → pymdkit-1.6.2}/README.md

@@ -236,9 +236,10 @@ and `0.875`. Generated CIF occupancy fields use two decimal places.
 `-max-supercell AxBxC` searches bounded diagonal supercells, smallest volume
 first, until every multiplicity times occupancy times supercell determinant is
 an integer. Equal-volume choices favor the most isotropic resulting cell.
-All selections, site atom counts, oxidation states, charges, and failures are
-recorded in `OUTPUT/realloc-occ.txt`.
-
+All selections, site atom counts, oxidation states, charges, failures, the
+allowed occupancy grid, and the final summary are recorded in
+`OUTPUT/realloc-occ.txt` for both single-file and folder modes.
+
 `gather-fs` recursively scans all job folders below the current directory. For
 VASP it follows the global `vaspout.h5 > vasprun.xml > OUTCAR` priority and
 requires full convergence before copying the selected `-fs-name` as `.vasp`. The gathered VASP file's first line is replaced with `energy=<final_energy> eV` for later screening.
@@ -301,7 +302,15 @@ atom-site loop. Multiplicity-letter
 assignments use the conventional
 International Tables setting from pymatgen/spglib and correspond to the
 [Bilbao Crystallographic Server WYCKPOS tables](https://cryst.ehu.es/cryst/get_wp.html);
-the provenance URL is also recorded inside each generated CIF.
+the provenance URL is also recorded inside each generated CIF.
+
+For structural conversion, supercell creation, and GPUMD grouping, PMK reads
+CIF input with pymatgen rather than ASE. ASE interprets
+`_space_group_crystal_system` as a setting hint only for rhombohedral groups
+and emits a potentially misleading warning for other crystal systems. Using
+pymatgen avoids that ambiguity while PMK continues to use ASE for non-CIF
+formats. A partially occupied CIF must first be ordered with `convert -d2o`
+before it can be represented as an explicit atom list.
 
 CIF `_atom_type_symbol` and `_atom_site_label` values use per-element
 inequivalent-site identifiers such as `Li1`, `Y1`, `Cl1`, and `Cl2`.

{pymdkit-1.6.1 → pymdkit-1.6.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pymdkit"
-version = "1.6.1"
+version = "1.6.2"
 description = "A unified command-line toolkit for atomistic / MD structure workflows."
 readme = "README.md"
 requires-python = ">=3.9"

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/__init__.py

@@ -1,3 +1,3 @@
 """pymdkit -- a unified CLI for atomistic / MD structure workflows."""
 
-__version__ = "1.6.1"
+__version__ = "1.6.2"

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/_symmetry.py

@@ -42,6 +42,10 @@ def load_structure(path):
     try:
         return Structure.from_file(str(path))
     except Exception as pymatgen_error:
+        if _cifio.is_cif(path):
+            raise ValueError(
+                f"pymatgen could not read CIF {path}: {pymatgen_error}"
+            ) from pymatgen_error
         try:
             from ase.io import read
             from pymatgen.io.ase import AseAtomsAdaptor

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/compute_rmsd.py

@@ -55,6 +55,9 @@ def load_structure(path):
     try:
         return Structure.from_file(str(path))
     except Exception as pymatgen_error:
+        if path.suffix.lower() == ".cif":
+            print(f"  [warn] pymatgen could not read CIF {path}: {pymatgen_error}")
+            return None
         try:
             from ase.io import read
             from pymatgen.io.ase import AseAtomsAdaptor

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/convert.py

@@ -21,7 +21,32 @@ COMMAND = "convert"
 HELP = "Convert structures, refine CIF symmetry, or order disorder."
 
 
+def _read_cif(path):
+    """Read CIF with pymatgen, avoiding ASE's setting-name ambiguity."""
+    from pymatgen.core import Structure
+    from pymatgen.io.ase import AseAtomsAdaptor
+
+    structure = Structure.from_file(str(path))
+    if not structure.is_ordered:
+        raise ValueError(
+            "partially occupied CIF cannot be converted to an explicit atom "
+            "format; use convert -d2o first"
+        )
+    return AseAtomsAdaptor.get_atoms(structure)
+
+
 def _read(path, all_frames=False):
+    path = Path(path)
+    if _cifio.is_cif(path):
+        if all_frames:
+            raise ValueError("CIF input is a structure, not a trajectory")
+        try:
+            return _read_cif(path)
+        except Exception as error:
+            raise ValueError(
+                f"pymatgen could not read CIF {path}: {error}"
+            ) from error
+
     from ase.io import read
 
     try:
@@ -234,6 +259,11 @@ def convert_one(
             angle_tolerance,
             add_oxidation,
         )
+    elif _cifio.is_cif(input_path) and _cifio.is_cif(output_path):
+        structure = _read_structure(input_path)
+        _write_structure(
+            output_path, structure, refine=False, symmetrize=False
+        )
     else:
         atoms = _read(input_path, all_frames=trajectory)
         _write(output_path, atoms, symmetrize=False)

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/gpumd_group.py

@@ -14,7 +14,7 @@ import argparse
 from pathlib import Path
 
 import numpy as np
-from ase.io import read, write
+from ase.io import write
 
 try:
     from . import _cifio, _fileio, convert
@@ -38,7 +38,7 @@ def add_arguments(parser):
 
 
 def _tag_one(in_path, out_path, elements):
-    atoms = read(str(in_path))
+    atoms = convert._read(in_path)
     groups = []
     for element in atoms.get_chemical_symbols():
         if element in elements:

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/realloc_occ.py

@@ -699,9 +699,15 @@ def run(args):
 
     output_root = Path(args.output_folder)
     output_root.mkdir(parents=True, exist_ok=True)
+    occupancy_text = (
+        "automatic"
+        if allowed_occupancies is None
+        else ", ".join(f"{value:.3f}" for value in allowed_occupancies)
+    )
     report = [
         "PMK realloc-occ summary",
         f"Target formula: {args.formula}",
+        f"Allowed occupancies: {occupancy_text}",
         f"Maximum supercell: {'x'.join(map(str, max_supercell))}",
         "",
     ]

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/substitute.py

@@ -212,7 +212,11 @@ def read_structure(path):
     path = Path(path)
     try:
         return Structure.from_file(str(path))
-    except Exception:
+    except Exception as pymatgen_error:
+        if _cifio.is_cif(path):
+            raise ValueError(
+                f"pymatgen could not read CIF {path}: {pymatgen_error}"
+            ) from pymatgen_error
         from ase.io import read as ase_read
         from pymatgen.io.ase import AseAtomsAdaptor
 

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit/commands/supercell.py

@@ -78,9 +78,7 @@ def make_supercell(
     max_abc=None,
     close_abc=None,
 ):
-    from ase.io import read
-
-    atoms = read(str(in_path))
+    atoms = convert._read(in_path)
     lengths, _, _ = _lattice.geometry_from_matrix(atoms.cell.array)
     supercell_matrix = _supercell.resolve_matrix(
         lengths,

{pymdkit-1.6.1 → pymdkit-1.6.2}/src/pymdkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pymdkit
-Version: 1.6.1
+Version: 1.6.2
 Summary: A unified command-line toolkit for atomistic / MD structure workflows.
 Author-email: Yueda Wang <ydwang0608@ustc.edu.cn>
 License-Expression: GPL-3.0-or-later
@@ -263,8 +263,9 @@ and `0.875`. Generated CIF occupancy fields use two decimal places.
 `-max-supercell AxBxC` searches bounded diagonal supercells, smallest volume
 first, until every multiplicity times occupancy times supercell determinant is
 an integer. Equal-volume choices favor the most isotropic resulting cell.
-All selections, site atom counts, oxidation states, charges, and failures are
-recorded in `OUTPUT/realloc-occ.txt`.
+All selections, site atom counts, oxidation states, charges, failures, the
+allowed occupancy grid, and the final summary are recorded in
+`OUTPUT/realloc-occ.txt` for both single-file and folder modes.
 
 `gather-fs` recursively scans all job folders below the current directory. For
 VASP it follows the global `vaspout.h5 > vasprun.xml > OUTCAR` priority and
@@ -330,6 +331,14 @@ International Tables setting from pymatgen/spglib and correspond to the
 [Bilbao Crystallographic Server WYCKPOS tables](https://cryst.ehu.es/cryst/get_wp.html);
 the provenance URL is also recorded inside each generated CIF.
 
+For structural conversion, supercell creation, and GPUMD grouping, PMK reads
+CIF input with pymatgen rather than ASE. ASE interprets
+`_space_group_crystal_system` as a setting hint only for rhombohedral groups
+and emits a potentially misleading warning for other crystal systems. Using
+pymatgen avoids that ambiguity while PMK continues to use ASE for non-CIF
+formats. A partially occupied CIF must first be ordered with `convert -d2o`
+before it can be represented as an explicit atom list.
+
 CIF `_atom_type_symbol` and `_atom_site_label` values use per-element
 inequivalent-site identifiers such as `Li1`, `Y1`, `Cl1`, and `Cl2`.
 The final atom-site loop starts with `_atom_site_label`, followed by

{pymdkit-1.6.1 → pymdkit-1.6.2}/tests/test_convert.py

@@ -9,10 +9,62 @@ from unittest.mock import patch
 sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
 
 from pymdkit import pymdkit_main
-from pymdkit.commands import _cifio, _supercell, _symmetry, convert
+from pymdkit.commands import (
+    _cifio,
+    _supercell,
+    _symmetry,
+    compute_rmsd,
+    convert,
+    substitute,
+)
 
 
 class ConvertTests(unittest.TestCase):
+    def test_cif_input_uses_pymatgen_reader(self):
+        atoms = object()
+        with patch.object(convert, "_read_cif", return_value=atoms) as reader:
+            self.assertIs(convert._read("input.cif"), atoms)
+        reader.assert_called_once_with(Path("input.cif"))
+        with self.assertRaisesRegex(ValueError, "not a trajectory"):
+            convert._read("input.cif", all_frames=True)
+
+    def test_failed_cif_parse_never_falls_back_to_ase(self):
+        class Structure:
+            @classmethod
+            def from_file(cls, path):
+                raise RuntimeError("invalid CIF")
+
+        pymatgen = types.ModuleType("pymatgen")
+        core = types.ModuleType("pymatgen.core")
+        core.Structure = Structure
+        pymatgen.core = core
+        modules = {"pymatgen": pymatgen, "pymatgen.core": core}
+        with patch.dict(sys.modules, modules):
+            with self.assertRaisesRegex(ValueError, "pymatgen could not read CIF"):
+                _symmetry.load_structure("broken.cif")
+            with self.assertRaisesRegex(ValueError, "pymatgen could not read CIF"):
+                substitute.read_structure("broken.cif")
+            self.assertIsNone(compute_rmsd.load_structure("broken.cif"))
+
+    def test_cif_to_cif_preserves_disorder_through_pymatgen(self):
+        structure = object()
+        with patch.object(
+            convert, "_read_structure", return_value=structure
+        ) as reader, patch.object(
+            convert, "_write_structure"
+        ) as writer, patch.object(
+            convert, "_read"
+        ) as ase_reader:
+            convert.convert_one("input.cif", "output.cif")
+        reader.assert_called_once_with(Path("input.cif"))
+        writer.assert_called_once_with(
+            Path("output.cif"),
+            structure,
+            refine=False,
+            symmetrize=False,
+        )
+        ase_reader.assert_not_called()
+
     def test_cli_defaults_to_p1_and_optional_supercell(self):
         parser = argparse.ArgumentParser()
         convert.add_arguments(parser)

{pymdkit-1.6.1 → pymdkit-1.6.2}/tests/test_realloc_occ.py

@@ -176,6 +176,10 @@ class ReallocOccTests(unittest.TestCase):
             ):
                 self.assertEqual(realloc_occ.run(args), 0)
             report = (output / "realloc-occ.txt").read_text(encoding="utf-8")
+            self.assertIn(
+                "Allowed occupancies: 0.250, 0.500, 0.750, 1.000",
+                report,
+            )
             self.assertIn("supercell=1x1x1", report)
             self.assertIn("Li1=6", report)
             self.assertIn("charge=0.00000000", report)