provenance default for schema

devtools/conda-envs/minimal.yaml

@@ -8,7 +8,7 @@ dependencies:
   - nomkl
   - python
   - pint=0.10.0  # technically, qcel has no lower bound for pint version for py36,37 but needs 0.10 for 38
-  - pydantic=1.2.0  # technically, qcel works with 1.0.0 but c-f doesn't have py38 builds for it
+  - pydantic=1.5.0
 
     # Testing
   - pytest=4.6.4  # technically, qcel works with 4.0.0 but c-f doesn't have py38 builds for it

qcelemental/models/__init__.py

@@ -14,3 +14,13 @@
 from .molecule import Molecule
 from .procedures import Optimization, OptimizationInput, OptimizationResult
 from .results import AtomicInput, AtomicResult, AtomicResultProperties, Result, ResultInput, ResultProperties
+
+
+def qcschema_models():
+    return [
+        AtomicInput,
+        AtomicResult,
+        BasisSet,
+        Molecule,
+        Provenance,
+    ]

qcelemental/models/basis.py

@@ -130,7 +130,7 @@ class BasisSet(ProtoModel):
     A quantum chemistry basis description.
     """
 
-    schema_name: constr(strip_whitespace=True, regex="qcschema_basis") = "qcschema_basis"
+    schema_name: constr(strip_whitespace=True, regex="qcschema_basis") = "qcschema_basis"  # type: ignore
     schema_version: int = 1
 
     name: str = Field(..., description="A standard basis name if available (e.g., 'cc-pVDZ').")

qcelemental/models/molecule.py

@@ -5,13 +5,19 @@
 import hashlib
 import json
 import warnings
+from functools import partial
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Tuple, Union, cast
 
 import numpy as np
 from pydantic import Field, constr, validator
 
-from ..molparse import from_arrays, from_schema, from_string, to_schema, to_string
+# molparse imports separated b/c https://github.com/python/mypy/issues/7203
+from ..molparse.from_arrays import from_arrays
+from ..molparse.from_schema import from_schema
+from ..molparse.from_string import from_string
+from ..molparse.to_schema import to_schema
+from ..molparse.to_string import to_string
 from ..periodic_table import periodictable
 from ..physical_constants import constants
 from ..testing import compare, compare_values
@@ -23,7 +29,6 @@
 if TYPE_CHECKING:
     from pydantic.typing import ReprArgs
 
-
 # Rounding quantities for hashing
 GEOMETRY_NOISE = 8
 MASS_NOISE = 6
@@ -225,8 +230,8 @@ class Molecule(ProtoModel):
         None, description="Maximal point group symmetry which ``geometry`` should be treated. Lowercase."
     )
     # Extra
-    provenance: Provenance = Field(  # type: ignore
-        provenance_stamp(__name__),
+    provenance: Provenance = Field(
+        default_factory=partial(provenance_stamp, __name__),
         description="The provenance information about how this Molecule (and its attributes) were generated, "
         "provided, and manipulated.",
     )
@@ -1042,7 +1047,7 @@ def nuclear_repulsion_energy(self, ifr: int = None) -> float:
         Nuclear repulsion energy in entire molecule or in fragment.
 
         """
-        Zeff = [z * int(real) for z, real in zip(self.atomic_numbers, self.real)]
+        Zeff = [z * int(real) for z, real in zip(cast(Iterable[int], self.atomic_numbers), self.real)]
         atoms = list(range(self.geometry.shape[0]))
 
         if ifr is not None:
@@ -1068,7 +1073,7 @@ def nelectrons(self, ifr: int = None) -> int:
         Number of electrons in entire molecule or in fragment.
 
         """
-        Zeff = [z * int(real) for z, real in zip(self.atomic_numbers, self.real)]
+        Zeff = [z * int(real) for z, real in zip(cast(Iterable[int], self.atomic_numbers), self.real)]
 
         if ifr is None:
             nel = sum(Zeff) - self.molecular_charge
@@ -1146,7 +1151,7 @@ def align(
         runiq = np.asarray(
             [
                 hashlib.sha1((sym + str(mas)).encode("utf-8")).hexdigest()
-                for sym, mas in zip(ref_mol.symbols, ref_mol.masses)
+                for sym, mas in zip(cast(Iterable[str], ref_mol.symbols), ref_mol.masses)
             ]
         )
         concern_mol = self
@@ -1157,7 +1162,7 @@ def align(
         cuniq = np.asarray(
             [
                 hashlib.sha1((sym + str(mas)).encode("utf-8")).hexdigest()
-                for sym, mas in zip(concern_mol.symbols, concern_mol.masses)
+                for sym, mas in zip(cast(Iterable[str], concern_mol.symbols), concern_mol.masses)
             ]
         )
 
@@ -1293,7 +1298,7 @@ def scramble(
         runiq = np.asarray(
             [
                 hashlib.sha1((sym + str(mas)).encode("utf-8")).hexdigest()
-                for sym, mas in zip(ref_mol.symbols, ref_mol.masses)
+                for sym, mas in zip(cast(Iterable[str], ref_mol.symbols), ref_mol.masses)
             ]
         )
         nat = rgeom.shape[0]

qcelemental/models/results.py

@@ -1,4 +1,5 @@
 from enum import Enum
+from functools import partial
 from typing import TYPE_CHECKING, Any, Dict, Optional, Set, Union
 
 import numpy as np
@@ -347,7 +348,9 @@ class AtomicInput(ProtoModel):
 
     extras: Dict[str, Any] = Field({}, description="Extra fields that are not part of the schema.")
 
-    provenance: Provenance = Field(Provenance(**provenance_stamp(__name__)), description=str(Provenance.__base_doc__))
+    provenance: Provenance = Field(
+        default_factory=partial(provenance_stamp, __name__), description=str(Provenance.__base_doc__)
+    )
 
     def __repr_args__(self) -> "ReprArgs":
         return [

qcelemental/molparse/chgmult.py

@@ -360,8 +360,8 @@ def validate_and_fill_chgmult(
     cgmp_rules.append("4")
     for ifr in range(nfr):
         cgmp_range.append(
-            lambda c, fc, m, fm, ifr=ifr: _sufficient_electrons_for_mult(fzel[ifr], fc[ifr], fm[ifr])
-        )  # type: ignore
+            lambda c, fc, m, fm, ifr=ifr: _sufficient_electrons_for_mult(fzel[ifr], fc[ifr], fm[ifr])  # type: ignore
+        )
         cgmp_rules.append("4-" + str(ifr))
 
     #   * (R5) require total parity consistent among neutral_electrons, chg, and mult

qcelemental/molparse/to_string.py

@@ -384,7 +384,7 @@ def to_dict(self) -> Dict:
 
         atom_format = "{elem}"
         ghost_format = "@{elem}"
-        umap = {"bohr": True, "angstrom": False}
+        umap = {"bohr": "True", "angstrom": "False"}
 
         atoms = _atoms_formatter(molrec, geom, atom_format, ghost_format, width, prec, 2)
 

qcelemental/molutil/molecular_formula.py

@@ -1,6 +1,6 @@
 import collections
 import re
-from typing import List
+from typing import Dict, List
 
 
 def order_molecular_formula(formula: str, order: str = "alphabetical") -> str:
@@ -23,7 +23,7 @@ def order_molecular_formula(formula: str, order: str = "alphabetical") -> str:
     matches = re.findall(r"[A-Z][^A-Z]*", formula)
     if not "".join(matches) == formula:
         raise ValueError(f"{formula} is not a valid molecular formula.")
-    count = collections.defaultdict(int)
+    count: Dict[str, int] = collections.defaultdict(int)
     for match in matches:
         match_n = re.match(r"(\D+)(\d*)", match)
         assert match_n

qcelemental/tests/test_molecule.py

@@ -651,14 +651,14 @@ def test_show():
 
 def test_molecule_connectivity():
     data = {"geometry": np.random.rand(5, 3), "symbols": ["he"] * 5, "validate": False}
-    mol = Molecule(**data, connectivity=None)
+    Molecule(**data, connectivity=None)
 
     connectivity = [[n, n + 1, 1] for n in range(4)]
-    mol = Molecule(**data, connectivity=connectivity)
+    Molecule(**data, connectivity=connectivity)
 
     connectivity[0][0] = -1
     with pytest.raises(ValueError):
-        mol = Molecule(**data, connectivity=connectivity)
+        Molecule(**data, connectivity=connectivity)
 
 
 def test_orient_nomasses():
@@ -719,7 +719,7 @@ def test_sparse_molecule_connectivity():
 
 
 def test_bad_isotope_spec():
-    with pytest.raises(NotAnElementError) as e:
+    with pytest.raises(NotAnElementError):
         qcel.models.Molecule(symbols=["He3"], geometry=[0, 0, 0])
 
 

qcelemental/util/importing.py

@@ -1,7 +1,7 @@
 import os
 import shutil
 import sys
-from typing import Union
+from typing import List, Union
 
 
 def which_import(
@@ -12,7 +12,7 @@ def which_import(
     raise_msg: str = None,
     package: str = None,
     namespace_ok: bool = False,
-) -> Union[bool, None, str]:
+) -> Union[bool, None, str, List[str]]:
     """Tests to see if a Python module is available.
 
     Returns

setup.py

@@ -31,7 +31,7 @@
         package_data={'': [os.path.join('qcelemental', 'data', '*.json')]},
         setup_requires=[] + pytest_runner,
         python_requires='>=3.6',
-        install_requires=['numpy >= 1.12.0', 'pint >= 0.10.0', 'pydantic >= 1.0.0'],
+        install_requires=["numpy >= 1.12.0", "pint >= 0.10.0", "pydantic >= 1.5.0"],
         extras_require={
             'docs': [
                 'numpydoc',