Only jsanitize before Store update and fix maggma 0.64.0 (#1835)

## Summary of Changes

Only call `jsanitize()` once: before `Store.update`. Closes #1992.

Requires:
- pymatgen > 2024.3.1

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com>

pyproject.toml

@@ -31,13 +31,13 @@ dependencies = [
     "cclib>=1.8", # for I/O parsing of molecular DFT codes
     "custodian>=2024.3.12", # for automated error corrections
     "emmet-core>=0.80.0", # for pre-made schemas
-    "maggma<=0.63.4", # for database handling
+    "maggma>=0.64.0", # for database handling
     "monty>=2024.2.26", # miscellaneous Python utilities
     "numpy>=1.25.0", # for array handling
     "psutil", # for getting compute architecture details
     "pydantic>=2.0.1", # for settings management
     "pydantic-settings>=2.2.0", # for settings management
-    "pymatgen>=2024.2.20", # for structure manipulation
+    "pymatgen>=2024.4.12", # for structure manipulation
     "typer>=0.12.1", # for the CLI
 ]
 

src/quacc/schemas/atoms.py

@@ -2,10 +2,10 @@
 
 from __future__ import annotations
 
+from copy import deepcopy
 from typing import TYPE_CHECKING
 
 from emmet.core.structure import MoleculeMetadata, StructureMetadata
-from monty.json import jsanitize
 from pymatgen.io.ase import AseAtomsAdaptor
 
 from quacc.atoms.core import (
@@ -83,9 +83,7 @@ def atoms_to_metadata(
         metadata = {}
 
     # Copy the info flags as a separate entry in the DB for easy querying
-    results["atoms_info"] = jsanitize(
-        atoms.info, enum_values=True, recursive_msonable=True
-    )
+    results["atoms_info"] = deepcopy(atoms.info)
 
     # Store Atoms object
     results["atoms"] = atoms

src/quacc/schemas/cclib.py

@@ -13,7 +13,6 @@
 import cclib
 from ase.atoms import Atoms
 from cclib.io import ccread
-from monty.json import jsanitize
 
 from quacc import SETTINGS
 from quacc.atoms.core import get_final_atoms_from_dynamics
@@ -328,7 +327,7 @@ def _make_cclib_schema(
         raise RuntimeError(msg)
 
     # Fetch all the attributes (i.e. all input/outputs from cclib)
-    attributes = jsanitize(cclib_obj.getattributes())
+    attributes = cclib_obj.getattributes()
 
     # monty datetime bug workaround:
     # github.com/materialsvirtuallab/monty/issues/275

src/quacc/wflow_tools/db.py

@@ -5,6 +5,8 @@
 import uuid
 from typing import TYPE_CHECKING
 
+from monty.json import jsanitize
+
 if TYPE_CHECKING:
     from typing import Any
 
@@ -31,8 +33,13 @@ def results_to_db(store: Store, results: dict[str, Any] | list[dict]) -> None:
     if not isinstance(results, list):
         results = [results]
 
-    for result in results:
+    sanitized_results = [
+        jsanitize(result, enum_values=True, recursive_msonable=True)
+        for result in results
+    ]
+
+    for result in sanitized_results:
         result["uuid"] = str(uuid.uuid4())
 
     with store:
-        store.update(results, key="uuid")
+        store.update(sanitized_results, key="uuid")

tests/core/schemas/test_ase.py

@@ -44,13 +44,11 @@ def test_summarize_run(tmpdir, monkeypatch):
 
     with gzip.open(Path(results["dir_name"], "quacc_results.pkl.gz"), "rb") as f:
         pickle_results = pickle.load(f)
-    output = results.copy()
-    output.pop("uuid")
-    assert pickle_results.keys() == output.keys()
+    assert pickle_results.keys() == results.keys()
 
-    assert pickle_results["nsites"] == output["nsites"]
-    assert pickle_results["results"]["energy"] == output["results"]["energy"]
-    assert pickle_results["atoms"].info == output["atoms"].info
+    assert pickle_results["nsites"] == results["nsites"]
+    assert pickle_results["results"]["energy"] == results["results"]["energy"]
+    assert pickle_results["atoms"].info == results["atoms"].info
 
 
 def test_summarize_run2(tmp_path, monkeypatch):
@@ -143,16 +141,13 @@ def test_summarize_opt_run(tmp_path, monkeypatch):
     with gzip.open(Path(results["dir_name"], "quacc_results.pkl.gz"), "rb") as f:
         pickle_results = pickle.load(f)
 
-    output = results.copy()
-    output.pop("uuid")
-
-    assert pickle_results.keys() == output.keys()
+    assert pickle_results.keys() == results.keys()
 
     # assert things on the trajectory are the same
-    assert pickle_results["trajectory"] == output["trajectory"]
+    assert pickle_results["trajectory"] == results["trajectory"]
     assert (
         pickle_results["trajectory_results"][-1]["energy"]
-        == output["trajectory_results"][-1]["energy"]
+        == results["trajectory_results"][-1]["energy"]
     )
 
     # Test DB

tests/core/wflow/test_db.py

@@ -12,3 +12,4 @@ def test_results_to_db():
     results_to_db(store, {"atoms": atoms})
     with store:
         assert store.count() == 1
+        assert store.query_one().get("uuid")

tests/requirements.txt

@@ -2,11 +2,11 @@ ase @ https://gitlab.com/ase/ase/-/archive/master/ase-master.zip
 cclib==1.8.1
 custodian==2024.3.12
 emmet-core==0.82.1
-maggma==0.63.4
+maggma==0.64.0
 monty==2024.3.31
 numpy==1.26.4
 psutil==5.9.8
 pydantic==2.6.4
 pydantic-settings==2.2.1
-pymatgen==2024.3.1
+pymatgen==2024.4.12
 typer==0.12.2