pymdkit 1.2.6__tar.gz → 1.2.8__tar.gz

{pymdkit-1.2.6/src/pymdkit.egg-info → pymdkit-1.2.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pymdkit
-Version: 1.2.6
+Version: 1.2.8
 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

{pymdkit-1.2.6 → pymdkit-1.2.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pymdkit"
-version = "1.2.6"
+version = "1.2.8"
 description = "A unified command-line toolkit for atomistic / MD structure workflows."
 readme = "README.md"
 requires-python = ">=3.9"

{pymdkit-1.2.6 → pymdkit-1.2.8}/src/pymdkit/__init__.py

@@ -1,3 +1,3 @@
 """pymdkit -- a unified CLI for atomistic / MD structure workflows."""
 
-__version__ = "1.2.6"
+__version__ = "1.2.8"

pymdkit-1.2.8/src/pymdkit/commands/stable_entry.py

@@ -0,0 +1,239 @@
+"""Download stable Materials Project structures for a chemical system."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import re
+from pathlib import Path
+
+COMMAND = "stable-entry"
+HELP = "Download stable Materials Project structures for a chemical system."
+
+
+def safe_formula(formula):
+    return re.sub(r"[^A-Za-z0-9_.-]+", "", str(formula))
+
+
+def is_public_mpid(text):
+    return bool(re.fullmatch(r"mp-\d+", str(text or "")))
+
+
+def mpid_text(value):
+    if value is None:
+        return ""
+    if isinstance(value, dict):
+        for key in ("material_id", "task_id", "entry_id", "id", "identifier"):
+            if value.get(key):
+                return mpid_text(value[key])
+        return "-".join(f"{k}-{v}" for k, v in sorted(value.items()))
+    for attr in ("string", "identifier"):
+        text = getattr(value, attr, None)
+        if text:
+            return str(text)
+    text = str(value)
+    match = re.search(r"mp-\d+", text)
+    if match:
+        return match.group(0)
+    match = re.search(r"identifier=['\"]?(mp-[A-Za-z0-9]+)", text)
+    if match:
+        return match.group(1)
+    return text
+
+
+def entry_id_text(entry):
+    data = getattr(entry, "data", {}) or {}
+    for key in ("material_id", "task_id", "entry_id", "id"):
+        text = mpid_text(data.get(key))
+        if is_public_mpid(text):
+            return text
+    for key in ("material_id", "task_id", "entry_id", "id"):
+        text = mpid_text(data.get(key))
+        if text:
+            return text
+    entry_id = getattr(entry, "entry_id", None)
+    text = mpid_text(entry_id)
+    if text:
+        return text
+    return "unknown"
+
+
+def entry_sort_key(entry):
+    formula = str(entry.composition.reduced_formula)
+    return (len(entry.composition.elements), formula, entry_id_text(entry))
+
+
+def add_arguments(parser: argparse.ArgumentParser) -> None:
+    parser.add_argument("-s", nargs="+", required=True,
+                        help="Chemical system elements, e.g. -s Li La Ta Cl.")
+    parser.add_argument("-mp-api-key", default=None,
+                        help="Materials Project API key.")
+
+
+def doc_get(doc, name, default=None):
+    if isinstance(doc, dict):
+        return doc.get(name, default)
+    return getattr(doc, name, default)
+
+
+def resolve_public_material_ids(entries, api_key=None):
+    missing = [entry for entry in entries if not is_public_mpid(entry_id_text(entry))]
+    if not missing:
+        return
+    try:
+        from mp_api.client import MPRester as MPApiRester
+        from pymatgen.analysis.structure_matcher import StructureMatcher
+    except ModuleNotFoundError:
+        return
+
+    matcher = StructureMatcher()
+    cache = {}
+    with MPApiRester(api_key) as mpr:
+        for entry in missing:
+            formula = str(entry.composition.reduced_formula)
+            if formula not in cache:
+                cache[formula] = mpr.materials.summary.search(
+                    formula=formula,
+                    is_stable=True,
+                    fields=["material_id", "formula_pretty", "structure"],
+                )
+            for doc in cache[formula]:
+                structure = doc_get(doc, "structure")
+                material_id = mpid_text(doc_get(doc, "material_id"))
+                if not structure or not is_public_mpid(material_id):
+                    continue
+                if str(structure.composition.reduced_formula) != formula:
+                    continue
+                if matcher.fit(entry.structure, structure):
+                    data = getattr(entry, "data", None)
+                    if data is None:
+                        entry.data = {}
+                        data = entry.data
+                    data["material_id"] = material_id
+                    break
+
+
+def fetch_stable_entries(elements, api_key=None):
+    """Fetch entries and keep only entries stable on the full MP phase diagram."""
+    from pymatgen.analysis.phase_diagram import PhaseDiagram
+    from pymatgen.ext.matproj import MPRester
+
+    with MPRester(api_key) as mpr:
+        try:
+            entries = mpr.get_entries_in_chemsys(
+                elements,
+                inc_structure=True,
+                property_data=["material_id"],
+                additional_criteria={"thermo_types": ["GGA_GGA+U"]},
+            )
+        except (TypeError, KeyError):
+            entries = mpr.get_entries_in_chemsys(
+                elements,
+                inc_structure=True,
+                additional_criteria={"thermo_types": ["GGA_GGA+U"]},
+            )
+    phase_diagram = PhaseDiagram(entries)
+    stable_entries = list(phase_diagram.stable_entries)
+    resolve_public_material_ids(stable_entries, api_key)
+    print(f"Fetched {len(entries)} MP thermo entries; {len(stable_entries)} are stable on the full phase diagram.")
+    by_mpid = {}
+    for entry in stable_entries:
+        by_mpid[entry_id_text(entry)] = entry
+    return list(by_mpid.values())
+
+
+def api_key_value(api_key=None):
+    if api_key:
+        return api_key
+    try:
+        from pymatgen.ext.matproj import MPRester
+        return getattr(MPRester(), "api_key", None)
+    except Exception:
+        return None
+
+
+def extract_cif_text(text):
+    stripped = text.lstrip()
+    if not stripped.startswith(("{", "[")):
+        if "_symmetry_space_group_name_H-M" in text or stripped.startswith(("data_", "#")):
+            return text
+    try:
+        payload = json.loads(text)
+    except json.JSONDecodeError:
+        return None
+    candidates = []
+    if isinstance(payload, dict):
+        candidates.extend(payload.get("response", []) or [])
+        candidates.extend(payload.get("data", []) or [])
+        candidates.append(payload)
+    for item in candidates:
+        if isinstance(item, dict):
+            cif = item.get("cif") or item.get("cif_symmetrized") or item.get("symmetrized_cif")
+            if cif:
+                return cif
+    return None
+
+
+def download_mp_symmetrized_cif(material_id, path, api_key=None):
+    """Download the Materials Project CIF (Symmetrized) file for material_id."""
+    key = api_key_value(api_key)
+    headers = {"Accept": "text/plain", "User-Agent": "pymdkit"}
+    if key:
+        headers["X-API-KEY"] = key
+    quoted = quote(material_id, safe="")
+    urls = [
+        f"https://materialsproject.org/materials/{quoted}/cif?download=true&symmetrized=true",
+        f"https://materialsproject.org/materials/{quoted}/cif?symmetrized=true",
+        f"https://www.materialsproject.org/rest/v2/materials/{quoted}/cif",
+    ]
+    errors = []
+    for url in urls:
+        try:
+            req = Request(url, headers=headers)
+            with urlopen(req, timeout=60) as response:
+                text = response.read().decode("utf-8")
+            cif_text = extract_cif_text(text)
+            if cif_text:
+                Path(path).write_text(cif_text, encoding="utf-8")
+                return
+            errors.append(f"{url}: response did not contain CIF text")
+        except Exception as exc:  # noqa: BLE001 - try alternate MP endpoints
+            errors.append(f"{url}: {type(exc).__name__}: {exc}")
+    raise RuntimeError("Could not download MP CIF (Symmetrized): " + " | ".join(errors))
+
+
+def run(args) -> int:
+
+    elements = list(dict.fromkeys(args.s))
+    label = "-".join(elements)
+    out_dir = Path(f"{label}-stable-entries")
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    try:
+        entries = fetch_stable_entries(elements, args.mp_api_key)
+    except ModuleNotFoundError as exc:
+        if exc.name == "emmet":
+            raise SystemExit(
+                "Error: stable-entry requires emmet models from mp-api. "
+                "Reinstall pymdkit or run `pip install mp-api`."
+            ) from exc
+        raise
+
+    entries = sorted(entries, key=entry_sort_key)
+    written = 0
+    for entry in entries:
+        mpid = safe_formula(entry_id_text(entry).split(" ")[0])
+        formula = safe_formula(entry.composition.reduced_formula)
+        path = out_dir / f"{mpid}-{formula}.cif"
+        download_mp_symmetrized_cif(mpid, path, args.mp_api_key)
+        print(f"{mpid}\t{entry.composition.reduced_formula}\t-> {path}")
+        written += 1
+
+    print(f"Wrote {written} stable entr{'y' if written == 1 else 'ies'} to {out_dir}")
+    return 0 if written else 1
+
+
+if __name__ == "__main__":
+    _parser = argparse.ArgumentParser(description=__doc__)
+    add_arguments(_parser)
+    raise SystemExit(run(_parser.parse_args()))

{pymdkit-1.2.6 → pymdkit-1.2.8/src/pymdkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pymdkit
-Version: 1.2.6
+Version: 1.2.8
 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

pymdkit-1.2.6/src/pymdkit/commands/stable_entry.py

@@ -1,119 +0,0 @@
-"""Download stable Materials Project structures for a chemical system."""
-
-from __future__ import annotations
-
-import argparse
-import re
-from pathlib import Path
-
-COMMAND = "stable-entry"
-HELP = "Download stable Materials Project structures for a chemical system."
-
-
-def safe_formula(formula):
-    return re.sub(r"[^A-Za-z0-9_.-]+", "", str(formula))
-
-
-def mpid_text(value):
-    if value is None:
-        return ""
-    if isinstance(value, dict):
-        for key in ("material_id", "task_id", "entry_id", "id", "identifier"):
-            if value.get(key):
-                return mpid_text(value[key])
-        return "-".join(f"{k}-{v}" for k, v in sorted(value.items()))
-    for attr in ("string", "identifier"):
-        text = getattr(value, attr, None)
-        if text:
-            return str(text)
-    text = str(value)
-    match = re.search(r"mp-\d+", text)
-    if match:
-        return match.group(0)
-    match = re.search(r"identifier=['\"]?(mp-[A-Za-z0-9]+)", text)
-    if match:
-        return match.group(1)
-    return text
-
-
-def entry_id_text(entry):
-    data = getattr(entry, "data", {}) or {}
-    for key in ("material_id", "task_id", "entry_id", "id"):
-        text = mpid_text(data.get(key))
-        if text:
-            return text
-    entry_id = getattr(entry, "entry_id", None)
-    text = mpid_text(entry_id)
-    if text:
-        return text
-    return "unknown"
-
-
-def entry_sort_key(entry):
-    formula = str(entry.composition.reduced_formula)
-    return (len(entry.composition.elements), formula, entry_id_text(entry))
-
-
-def add_arguments(parser: argparse.ArgumentParser) -> None:
-    parser.add_argument("-s", nargs="+", required=True,
-                        help="Chemical system elements, e.g. -s Li La Ta Cl.")
-    parser.add_argument("-mp-api-key", default=None,
-                        help="Materials Project API key.")
-
-
-def fetch_stable_entries(elements, api_key=None):
-    """Fetch entries and keep only entries stable on the full MP phase diagram."""
-    from pymatgen.analysis.phase_diagram import PhaseDiagram
-    from pymatgen.ext.matproj import MPRester
-
-    with MPRester(api_key) as mpr:
-        entries = mpr.get_entries_in_chemsys(
-            elements,
-            inc_structure=True,
-            additional_criteria={"thermo_types": ["GGA_GGA+U"]},
-        )
-    phase_diagram = PhaseDiagram(entries)
-    stable_entries = list(phase_diagram.stable_entries)
-    print(f"Fetched {len(entries)} MP thermo entries; {len(stable_entries)} are stable on the full phase diagram.")
-    by_mpid = {}
-    for entry in stable_entries:
-        by_mpid[entry_id_text(entry)] = entry
-    return list(by_mpid.values())
-
-
-def run(args) -> int:
-    from pymatgen.io.cif import CifWriter
-
-    elements = list(dict.fromkeys(args.s))
-    label = "-".join(elements)
-    out_dir = Path(f"{label}-stable-entries")
-    out_dir.mkdir(parents=True, exist_ok=True)
-
-    try:
-        entries = fetch_stable_entries(elements, args.mp_api_key)
-    except ModuleNotFoundError as exc:
-        if exc.name == "emmet":
-            raise SystemExit(
-                "Error: stable-entry requires emmet models from mp-api. "
-                "Reinstall pymdkit or run `pip install mp-api`."
-            ) from exc
-        raise
-
-    entries = sorted(entries, key=entry_sort_key)
-    written = 0
-    for entry in entries:
-        mpid = safe_formula(entry_id_text(entry).split(" ")[0])
-        formula = safe_formula(entry.composition.reduced_formula)
-        path = out_dir / f"{mpid}-{formula}.cif"
-        CifWriter(entry.structure).write_file(str(path))
-        print(f"{mpid}\t{entry.composition.reduced_formula}\t-> {path}")
-        written += 1
-
-    print(f"Wrote {written} stable entr{'y' if written == 1 else 'ies'} to {out_dir}")
-    return 0 if written else 1
-
-
-if __name__ == "__main__":
-    _parser = argparse.ArgumentParser(description=__doc__)
-    add_arguments(_parser)
-    raise SystemExit(run(_parser.parse_args()))