Fix ruff FURB192 (#3785)

* tests/io/cp2k/test_sets.py rename TestSet->TestDftSet

* f-strings

* rename m->match and use walrus op

* tlist -> temperatures

* variable renames

* ruff check . --select FURB192 --preview --fix

* bump ruff, mypy, pyright pre-commit hooks

* collections.defaultdict -> defaultdict everywhere

.pre-commit-config.yaml

@@ -8,7 +8,7 @@ ci:
 
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.1
+    rev: v0.4.2
     hooks:
       - id: ruff
         args: [--fix, --unsafe-fixes]
@@ -22,7 +22,7 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.9.0
+    rev: v1.10.0
     hooks:
       - id: mypy
 
@@ -64,6 +64,6 @@ repos:
         args: [--drop-empty-cells, --keep-output]
 
   - repo: https://github.com/RobertCraigie/pyright-python
-    rev: v1.1.359
+    rev: v1.1.360
     hooks:
       - id: pyright

dev_scripts/update_pt_data.py

@@ -5,9 +5,9 @@
 
 from __future__ import annotations
 
-import collections
 import json
 import re
+from collections import defaultdict
 from itertools import product
 
 import requests
@@ -154,7 +154,7 @@ def parse_shannon_radii():
     sheet = wb["Sheet1"]
     i = 2
     el = charge = cn = None
-    radii = collections.defaultdict(dict)
+    radii = defaultdict(dict)
     while sheet[f"E{i}"].value:
         if sheet[f"A{i}"].value:
             el = sheet[f"A{i}"].value
@@ -277,7 +277,7 @@ def add_ionization_energies():
     for table in soup.find_all("table"):
         if "Hydrogen" in table.text:
             break
-    data = collections.defaultdict(list)
+    data = defaultdict(list)
     for row in table.find_all("tr"):
         row = [td.get_text().strip() for td in row.find_all("td")]
         if row:

pymatgen/analysis/bond_valence.py

@@ -2,10 +2,10 @@
 
 from __future__ import annotations
 
-import collections
 import functools
 import operator
 import os
+from collections import defaultdict
 from math import exp, sqrt
 from typing import TYPE_CHECKING
 
@@ -279,7 +279,7 @@ def get_valences(self, structure: Structure):
             self._best_vset = None
 
             def evaluate_assignment(v_set):
-                el_oxi = collections.defaultdict(list)
+                el_oxi = defaultdict(list)
                 for idx, sites in enumerate(equi_sites):
                     el_oxi[sites[0].specie.symbol].append(v_set[idx])
                 max_diff = max(max(v) - min(v) for v in el_oxi.values())
@@ -346,7 +346,7 @@ def _recurse(assigned=None):
             self._best_vset = None
 
             def evaluate_assignment(v_set):
-                el_oxi = collections.defaultdict(list)
+                el_oxi = defaultdict(list)
                 jj = 0
                 for sites in equi_sites:
                     for specie, _ in get_z_ordered_elmap(sites[0].species):
@@ -474,7 +474,7 @@ def add_oxidation_state_by_site_fraction(structure, oxidation_states):
     """
     try:
         for idx, site in enumerate(structure):
-            new_sp = collections.defaultdict(float)
+            new_sp = defaultdict(float)
             for j, (el, occu) in enumerate(get_z_ordered_elmap(site.species)):
                 specie = Species(el.symbol, oxidation_states[idx][j])
                 new_sp[specie] += occu

pymatgen/analysis/diffraction/core.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import abc
-import collections
+from collections import defaultdict
 from typing import TYPE_CHECKING
 
 import matplotlib.pyplot as plt
@@ -215,9 +215,9 @@ def get_unique_families(hkls):
     def is_perm(hkl1, hkl2) -> bool:
         h1 = np.abs(hkl1)
         h2 = np.abs(hkl2)
-        return all(i == j for i, j in zip(sorted(h1), sorted(h2)))
+        return np.all(np.sort(h1) == np.sort(h2))
 
-    unique = collections.defaultdict(list)
+    unique = defaultdict(list)
     for hkl1 in hkls:
         found = False
         for hkl2, v2 in unique.items():
@@ -229,7 +229,7 @@ def is_perm(hkl1, hkl2) -> bool:
             unique[hkl1].append(hkl1)
 
     pretty_unique = {}
-    for v in unique.values():
-        pretty_unique[sorted(v)[-1]] = len(v)
+    for val in unique.values():
+        pretty_unique[max(val)] = len(val)
 
     return pretty_unique

pymatgen/analysis/diffraction/neutron.py

@@ -98,8 +98,8 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
         )
 
         # Obtain crystallographic reciprocal lattice points within range
-        recip_latt = lattice.reciprocal_lattice_crystallographic
-        recip_pts = recip_latt.get_points_in_sphere([[0, 0, 0]], [0, 0, 0], max_r)
+        recip_lattice = lattice.reciprocal_lattice_crystallographic
+        recip_pts = recip_lattice.get_points_in_sphere([[0, 0, 0]], [0, 0, 0], max_r)
         if min_r:
             recip_pts = [pt for pt in recip_pts if pt[1] >= min_r]
 
@@ -129,7 +129,7 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
         coeffs = np.array(_coeffs)
         frac_coords = np.array(_frac_coords)
         occus = np.array(_occus)
-        dwfactors = np.array(_dwfactors)
+        dw_factors = np.array(_dwfactors)
         peaks: dict[float, list[float | list[tuple[int, ...]]]] = {}
         two_thetas: list[float] = []
 
@@ -147,7 +147,7 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
                 s = g_hkl / 2
 
                 # Calculate Debye-Waller factor
-                dw_correction = np.exp(-dwfactors * (s**2))
+                dw_correction = np.exp(-dw_factors * (s**2))
 
                 # Vectorized computation of g.r for all fractional coords and
                 # hkl.

pymatgen/analysis/diffraction/xrd.py

@@ -159,8 +159,8 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
         )
 
         # Obtain crystallographic reciprocal lattice points within range
-        recip_latt = lattice.reciprocal_lattice_crystallographic
-        recip_pts = recip_latt.get_points_in_sphere([[0, 0, 0]], [0, 0, 0], max_r)
+        recip_lattice = lattice.reciprocal_lattice_crystallographic
+        recip_pts = recip_lattice.get_points_in_sphere([[0, 0, 0]], [0, 0, 0], max_r)
         if min_r:
             recip_pts = [pt for pt in recip_pts if pt[1] >= min_r]
 
@@ -172,7 +172,7 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
         _coeffs = []
         _frac_coords = []
         _occus = []
-        _dwfactors = []
+        _dw_factors = []
 
         for site in structure:
             for sp, occu in site.species.items():
@@ -184,15 +184,15 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
                         f"Unable to calculate XRD pattern as there is no scattering coefficients for {sp.symbol}."
                     )
                 _coeffs.append(c)
-                _dwfactors.append(self.debye_waller_factors.get(sp.symbol, 0))
+                _dw_factors.append(self.debye_waller_factors.get(sp.symbol, 0))
                 _frac_coords.append(site.frac_coords)
                 _occus.append(occu)
 
         zs = np.array(_zs)
         coeffs = np.array(_coeffs)
         frac_coords = np.array(_frac_coords)
         occus = np.array(_occus)
-        dwfactors = np.array(_dwfactors)
+        dw_factors = np.array(_dw_factors)
         peaks: dict[float, list[float | list[tuple[int, ...]]]] = {}
         two_thetas: list[float] = []
 
@@ -227,7 +227,7 @@ def get_pattern(self, structure: Structure, scaled=True, two_theta_range=(0, 90)
                     axis=1,  # type: ignore
                 )
 
-                dw_correction = np.exp(-dwfactors * s2)
+                dw_correction = np.exp(-dw_factors * s2)
 
                 # Structure factor = sum of atomic scattering factors (with
                 # position factor exp(2j * pi * g.r and occupancies).

pymatgen/analysis/dimensionality.py

@@ -347,7 +347,7 @@ def get_dimensionality_cheon(
         else:
             dim = np.log2(float(max3) / max1) / np.log2(3)
             if dim == int(dim):
-                dim = str(int(dim)) + "D"
+                dim = f"{int(dim)}D"
             else:
                 return None
     else:
@@ -361,7 +361,7 @@ def get_dimensionality_cheon(
         else:
             dim = np.log2(float(max2) / max1)
             if dim == int(dim):
-                dim = str(int(dim)) + "D"
+                dim = f"{int(dim)}D"
             else:
                 structure = copy.copy(structure_save)
                 structure.make_supercell(np.eye(3) * 3)
@@ -372,7 +372,7 @@ def get_dimensionality_cheon(
                 else:
                     dim = np.log2(float(max3) / max1) / np.log2(3)
                     if dim == int(dim):
-                        dim = str(int(dim)) + "D"
+                        dim = f"{int(dim)}D"
                     else:
                         return None
     return dim

pymatgen/analysis/disorder.py

@@ -2,8 +2,8 @@
 
 from __future__ import annotations
 
-import collections
 import itertools
+from collections import defaultdict
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
@@ -24,8 +24,8 @@ def get_warren_cowley_parameters(structure: Structure, r: float, dr: float) -> d
     """
     comp = structure.composition
 
-    n_ij = collections.defaultdict(int)  # type: ignore
-    n_neighbors = collections.defaultdict(int)  # type: ignore
+    n_ij = defaultdict(int)  # type: ignore
+    n_neighbors = defaultdict(int)  # type: ignore
     for site in structure:
         for nn in structure.get_neighbors_in_shell(site.coords, r, dr):
             n_ij[(site.specie, nn.specie)] += 1

pymatgen/analysis/nmr.py

@@ -165,7 +165,7 @@ def principal_axis_system(self):
     def V_xx(self):
         """Returns: First diagonal element."""
         diags = np.diag(self.principal_axis_system)
-        return sorted(diags, key=np.abs)[0]
+        return min(diags, key=np.abs)
 
     @property
     def V_yy(self):

pymatgen/analysis/phase_diagram.py

@@ -2,14 +2,14 @@
 
 from __future__ import annotations
 
-import collections
 import itertools
 import json
 import logging
 import math
 import os
 import re
 import warnings
+from collections import defaultdict
 from functools import lru_cache
 from typing import TYPE_CHECKING, Any, Literal, no_type_check
 
@@ -1181,7 +1181,7 @@ def get_chempot_range_map(
         else:
             el_energies = dict.fromkeys(elements, 0)
 
-        chempot_ranges = collections.defaultdict(list)
+        chempot_ranges = defaultdict(list)
         vertices = [list(range(len(self.elements)))]
 
         if len(all_chempots) > len(self.elements):
@@ -2631,7 +2631,7 @@ def _create_plotly_figure_layout(self, label_stable=True):
                 if hasattr(el_ref, "original_entry"):  # for grand potential PDs, etc.
                     clean_formula = htmlify(el_ref.original_entry.reduced_formula)
 
-                layout["ternary"][axis + "axis"]["title"] = {
+                layout["ternary"][f"{axis}axis"]["title"] = {
                     "text": clean_formula,
                     "font": {"size": 24},
                 }

pymatgen/analysis/structure_analyzer.py

@@ -2,8 +2,8 @@
 
 from __future__ import annotations
 
-import collections
 import itertools
+from collections import defaultdict
 from math import acos, pi
 from typing import TYPE_CHECKING
 from warnings import warn
@@ -227,7 +227,7 @@ def get_percentage_bond_dist_changes(self, max_radius: float = 3.0) -> dict[int,
                 between site1 and site_n is the same as bonding between site_n and site1, there is no
                 reason to duplicate the information or computation.
         """
-        data: dict[int, dict[int, float]] = collections.defaultdict(dict)
+        data: dict[int, dict[int, float]] = defaultdict(dict)
         for indices in itertools.combinations(list(range(len(self.initial))), 2):
             ii, jj = sorted(indices)
             initial_dist = self.initial[ii].distance(self.initial[jj])
@@ -442,7 +442,7 @@ def parse_oxide(self) -> tuple[str, int]:
         if isinstance(structure.elements[0], Element):
             comp = structure.composition
         elif isinstance(structure.elements[0], Species):
-            elem_map: dict[Element, float] = collections.defaultdict(float)
+            elem_map: dict[Element, float] = defaultdict(float)
             for site in structure:
                 for species, occu in site.species.items():
                     elem_map[species.element] += occu

pymatgen/analysis/structure_matcher.py

@@ -979,7 +979,7 @@ def get_rms_anonymous(self, struct1, struct2):
 
         matches = self._anonymous_match(struct1, struct2, fu, s1_supercell, use_rms=True, break_on_match=False)
         if matches:
-            best = sorted(matches, key=lambda x: x[1][0])[0]
+            best = min(matches, key=lambda x: x[1][0])
             return best[1][0], best[0]
 
         return None, None

pymatgen/analysis/topological/spillage.py

@@ -203,9 +203,9 @@ def overlap_so_spinpol(self):
                                 "!!!!!!!!!!",
                             )
 
-        gmax = max(np.real(gamma_k))
-        nkmax = np.argmax(np.real(gamma_k))
-        kmax = kpoints[nkmax]
+        gamma_max = max(np.real(gamma_k))
+        n_kmax = np.argmax(np.real(gamma_k))
+        k_max = kpoints[n_kmax]
 
         print("------------------------------------")
         print("\n                   INDIRECT DIRECT      HOMO/LUMO (eV)")
@@ -223,5 +223,5 @@ def overlap_so_spinpol(self):
             "   ",
             [so_homo, so_lumo],
         )
-        print("gamma max", np.real(gmax), " at k =  ", kmax)
-        return gmax
+        print("gamma max", np.real(gamma_max), " at k =  ", k_max)
+        return gamma_max

pymatgen/analysis/xps.py

@@ -18,8 +18,8 @@
 
 from __future__ import annotations
 
-import collections
 import warnings
+from collections import defaultdict
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -49,7 +49,7 @@
 def _load_cross_sections(fname):
     data = pd.read_csv(fname)
 
-    dct = collections.defaultdict(dict)
+    dct = defaultdict(dict)
     for row in data.itertuples():
         sym = row.element
         el = Element(sym)

pymatgen/apps/borg/hive.py

@@ -124,8 +124,8 @@ def assimilate(self, path):
                 filepath = vasprun_files[0]
             elif len(vasprun_files) > 1:
                 # Since multiple files are ambiguous, we will always read
-                # the one that it the last one alphabetically.
-                filepath = sorted(vasprun_files)[-1]
+                # the last one alphabetically.
+                filepath = max(vasprun_files)
                 warnings.warn(f"{len(vasprun_files)} vasprun.xml.* found. {filepath} is being parsed.")
 
         try:
@@ -220,14 +220,14 @@ def assimilate(self, path):
             filenames = {"INCAR", "POTCAR", "CONTCAR", "OSZICAR", "POSCAR", "DYNMAT"}
             if "relax1" in files and "relax2" in files:
                 for filename in ("INCAR", "POTCAR", "POSCAR"):
-                    search_str = f"{path}/relax1", filename + "*"
+                    search_str = f"{path}/relax1", f"{filename}*"
                     files_to_parse[filename] = glob(search_str)[0]
                 for filename in ("CONTCAR", "OSZICAR"):
-                    search_str = f"{path}/relax2", filename + "*"
+                    search_str = f"{path}/relax2", f"{filename}*"
                     files_to_parse[filename] = glob(search_str)[-1]
             else:
                 for filename in filenames:
-                    files = sorted(glob(os.path.join(path, filename + "*")))
+                    files = sorted(glob(os.path.join(path, f"{filename}*")))
                     if len(files) == 1 or filename in ("INCAR", "POTCAR") or (len(files) == 1 and filename == "DYNMAT"):
                         files_to_parse[filename] = files[0]
                     elif len(files) > 1: