Fix fixable ruff rules (#4015)

* fix RUF017

* fix B018: useless expressions

* NEED confirm: fix TRY004 type error

* fix PGH003: bare # type: ignore

* fix FBT003 boolean-positional-value-in-call

* fix PYI024 collections-named-tuple

* relocate io.aims test file and rename test dir

* NEED CONFIRM: relocate io.aims test helper functions

* add __init__.py

* try to fix helper function path

* pre-commit auto-fixes

* clean up pyproject.toml

* relocate type check import

* use relative import, TODO how to use abs import in this case?

* fix NPY201

* turn of paradox box of S101

* Revert "turn of paradox box of S101"

This reverts commit 735cb62.

* tweak type and docstring

* fix PD011, got a lot false pos in cp2k keywords

* ignore PD011 as too many false pos astral-sh/ruff#6432

* one missing pd011

* fix usage of pytest raise message  PT011

* fix B009 get attribute

* fix B018, attr test

* use np array to avoid RUF005 error

* fix RUF005 with np array

* fix typo in hasattr use

* NEED CONFIRM: turn on SSL certificate check

* replace http with https, there're many other cases might need test and replace

* Revert "replace http with https, there're many other cases might need test and replace"

This reverts commit 8fdd1c5.

* Move to another PR, Revert "NEED CONFIRM: turn on SSL certificate check"

This reverts commit ae52433.

* rename _SpinMode to SpinModeTuple

* use list comprehension over function tool to flat list of lists

---------

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

dev_scripts/update_pt_data.py

@@ -217,7 +217,7 @@ def gen_iupac_ordering():
         ([17], range(6, 1, -1)),
     ]  # At -> F
 
-    order = sum((list(product(x, y)) for x, y in order), [])  # noqa: RUF017
+    order = [item for sublist in (list(product(x, y)) for x, y in order) for item in sublist]
     iupac_ordering_dict = dict(
         zip([Element.from_row_and_group(row, group) for group, row in order], range(len(order)), strict=True)
     )

pyproject.toml

@@ -206,18 +206,18 @@ ignore = [
     "D212",    # Multi-line docstring summary should start at the first line
     "FBT001",  # Boolean-typed positional argument in function definition
     "FBT002",  # Boolean default positional argument in function
-    "NPY201",  # TODO: enable after migration to NumPy 2.0
+    "PD011",   # (A lot of false positive on non-Pandas objects)
     "PERF203", # Use of try-except in for/while loop
     "PERF401", # Replace "for" loops with list comprehension
     "PLR0911", # Too many return statements
     "PLR0912", # Too many branches
     "PLR0913", # Too many arguments
     "PLR0915", # Too many statements
     "PLR1702", # Too many nested blocks
-    "PLR2004", # Magic-value-comparison TODO fix these
+    "PLR2004", # Magic-value-comparison TODO: fix these
     "PLW2901", # Outer for loop variable overwritten by inner assignment target
     "PT013",   # Incorrect import of pytest
-    "S101",    # Use of "assert"
+    "S101",    # Use of "assert"  TODO: fix these
     "S110",    # Log for try-except-pass
     "S112",    # Log for try-except-continue
     "S311",    # Use random module for cryptographic purposes
@@ -238,10 +238,14 @@ isort.known-first-party = ["pymatgen"]
 docstring-code-format = true
 
 [tool.ruff.lint.per-file-ignores]
-"__init__.py" = ["F401"]
-# PLR2004: magic-value-comparison
-# PLR6301: no-self-use
-"tests/**" = ["ANN201", "D", "PLR0124", "PLR2004", "PLR6301"]
+"__init__.py" = ["F401"]  # unused-import
+"tests/**" = [
+    "ANN201",   # missing-return-type-undocumented-public-function
+    "D",        # pydocstyle
+    "PLR0124",  # comparison-with-itself
+    "PLR2004",  # magic-value-comparison
+    "PLR6301",  # no-self-use
+    ]
 "src/pymatgen/analysis/*" = ["D"]
 "src/pymatgen/io/*" = ["D"]
 "dev_scripts/*" = ["D"]
@@ -264,13 +268,11 @@ omit = [
 [tool.coverage.report]
 exclude_also = [
     "@deprecated",
-    "@np.deprecate",
     "def __repr__",
     "except ImportError:",
     "if TYPE_CHECKING:",
     "if self.debug:",
     "if settings.DEBUG",
-    "if typing.TYPE_CHECKING:",
     "pragma: no cover",
     "raise NotImplementedError",
     "show_plot",

src/pymatgen/analysis/adsorption.py

@@ -300,7 +300,7 @@ def find_adsorption_sites(
             sites = [site + distance * np.asarray(self.mvec) for site in sites]
 
             ads_sites[key] = sites
-        ads_sites["all"] = sum(ads_sites.values(), [])  # noqa: RUF017
+        ads_sites["all"] = [item for sublist in ads_sites.values() for item in sublist]
         return ads_sites
 
     def symm_reduce(self, coords_set, threshold=1e-6):

src/pymatgen/analysis/structure_prediction/volume_predictor.py

@@ -17,12 +17,7 @@
 
 
 def _is_ox(structure):
-    for elem in structure.composition:
-        try:
-            elem.oxi_state  # noqa: B018
-        except AttributeError:
-            return False
-    return True
+    return all(hasattr(elem, "oxi_state") for elem in structure.composition)
 
 
 class RLSVolumePredictor:

src/pymatgen/cli/pmg.py

@@ -441,10 +441,10 @@ def main():
     args = parser.parse_args()
 
     try:
-        args.func  # noqa: B018
-    except AttributeError:
+        _ = args.func
+    except AttributeError as exc:
         parser.print_help()
-        raise SystemExit("Please specify a command.")
+        raise SystemExit("Please specify a command.") from exc
     return args.func(args)
 
 

src/pymatgen/core/periodic_table.py

@@ -5,7 +5,6 @@
 import ast
 import functools
 import json
-import operator
 import re
 import warnings
 from collections import Counter
@@ -559,7 +558,7 @@ def ground_state_term_symbol(self) -> str:
                 "L": L_symbols.index(term[1]),
                 "J": float(term[2:]),
             }
-            for term in functools.reduce(operator.iadd, term_symbols, [])
+            for term in [item for sublist in term_symbols for item in sublist]
         }
 
         multi = [int(item["multiplicity"]) for _terms, item in term_symbol_flat.items()]

src/pymatgen/core/surface.py

@@ -554,7 +554,7 @@ def get_equi_index(site: PeriodicSite) -> int:
                             break
                     else:
                         # Move unselected atom to the opposite surface.
-                        frac_coords.append(struct_matcher.frac_coords + [0, 0, shift])  # noqa: RUF005
+                        frac_coords.append(struct_matcher.frac_coords + np.array([0, 0, shift]))
 
                 # sort by species to put all similar species together.
                 sp_fcoord = sorted(zip(species, frac_coords, strict=True), key=lambda x: x[0])

src/pymatgen/electronic_structure/boltztrap2.py

@@ -800,8 +800,8 @@ def compute_properties_doping(self, doping, temp_r=None) -> None:
                         self.nelect + dop_car,
                         temp,
                         self.dosweight,
-                        True,  # noqa: FBT003
-                        False,  # noqa: FBT003
+                        refine=True,
+                        try_center=False,
                     )
 
                 N, L0, L1, L2, Lm11 = BL.fermiintegrals(

src/pymatgen/electronic_structure/dos.py

@@ -8,6 +8,7 @@
 
 import numpy as np
 from monty.json import MSONable
+from packaging import version
 from scipy.constants import value as _constant
 from scipy.ndimage import gaussian_filter1d
 from scipy.signal import hilbert
@@ -18,6 +19,9 @@
 from pymatgen.electronic_structure.core import Orbital, OrbitalType, Spin
 from pymatgen.util.coord import get_linear_interpolated_value
 
+if version.parse(np.__version__) < version.parse("2.0.0"):
+    np.trapezoid = np.trapz  # noqa: NPY201
+
 if TYPE_CHECKING:
     from collections.abc import Sequence
     from typing import Any, Literal
@@ -916,7 +920,9 @@ def get_band_filling(
 
         # Only integrate up to Fermi level
         energies = dos.energies - dos.efermi
-        return np.trapz(dos_densities[energies < 0], x=energies[energies < 0]) / np.trapz(dos_densities, x=energies)
+        return np.trapezoid(dos_densities[energies < 0], x=energies[energies < 0]) / np.trapezoid(
+            dos_densities, x=energies
+        )
 
     def get_band_center(
         self,
@@ -1112,7 +1118,7 @@ def get_n_moment(
             p = energies
 
         # Take the nth moment
-        return np.trapz(p**n * dos_densities, x=energies) / np.trapz(dos_densities, x=energies)
+        return np.trapezoid(p**n * dos_densities, x=energies) / np.trapezoid(dos_densities, x=energies)
 
     def get_hilbert_transform(
         self,
@@ -1337,8 +1343,8 @@ def get_dos_fp_similarity(
             vec1 = np.array([pt[col] for pt in fp1_dict.values()]).flatten()
             vec2 = np.array([pt[col] for pt in fp2_dict.values()]).flatten()
         else:
-            vec1 = fp1_dict[fp1[2][pt]][col]  # type: ignore # noqa:PGH003
-            vec2 = fp2_dict[fp2[2][pt]][col]  # type: ignore # noqa:PGH003
+            vec1 = fp1_dict[fp1[2][pt]][col]
+            vec2 = fp2_dict[fp2[2][pt]][col]
 
         if not normalize and metric == "tanimoto":
             rescale = np.linalg.norm(vec1) ** 2 + np.linalg.norm(vec2) ** 2 - np.dot(vec1, vec2)

src/pymatgen/entries/mixing_scheme.py

@@ -292,8 +292,8 @@ def get_adjustments(self, entry, mixing_state_data: pd.DataFrame | None = None):
             )
 
         # Verify that the entry is included in the mixing state data
-        if (entry.entry_id not in mixing_state_data["entry_id_1"].values) and (  # noqa: PD011
-            entry.entry_id not in mixing_state_data["entry_id_2"].values  # noqa: PD011
+        if (entry.entry_id not in mixing_state_data["entry_id_1"].to_numpy()) and (
+            entry.entry_id not in mixing_state_data["entry_id_2"].to_numpy()
         ):
             raise CompatibilityError(
                 f"WARNING! Discarding {run_type} entry {entry.entry_id} for {entry.formula} "
@@ -303,8 +303,8 @@ def get_adjustments(self, entry, mixing_state_data: pd.DataFrame | None = None):
             )
 
         # Verify that the entry's energy has not been modified since mixing state data was generated
-        if (entry.energy_per_atom not in mixing_state_data["energy_1"].values) and (  # noqa: PD011
-            entry.energy_per_atom not in mixing_state_data["energy_2"].values  # noqa: PD011
+        if (entry.energy_per_atom not in mixing_state_data["energy_1"].to_numpy()) and (
+            entry.energy_per_atom not in mixing_state_data["energy_2"].to_numpy()
         ):
             raise CompatibilityError(
                 f"WARNING! Discarding {run_type} entry {entry.entry_id} for {entry.formula} "

src/pymatgen/io/abinit/abiobjects.py

@@ -3,11 +3,10 @@
 from __future__ import annotations
 
 import abc
-from collections import namedtuple
 from collections.abc import Iterable
 from enum import Enum, unique
 from pprint import pformat
-from typing import TYPE_CHECKING, cast
+from typing import TYPE_CHECKING, NamedTuple, cast
 
 import numpy as np
 from monty.collections import AttrDict
@@ -339,7 +338,14 @@ class DefaultVariable:
 DEFAULT = DefaultVariable()
 
 
-class SpinMode(namedtuple("SpinMode", "mode nsppol nspinor nspden"), AbivarAble, MSONable):  # noqa: PYI024
+class SpinModeTuple(NamedTuple):
+    mode: str
+    nsppol: int
+    nspinor: int
+    nspden: int
+
+
+class SpinMode(SpinModeTuple, AbivarAble, MSONable):
     """
     Different configurations of the electron density as implemented in abinit:
     One can use as_spinmode to construct the object via SpinMode.as_spinmode

src/pymatgen/io/abinit/pseudos.py

@@ -1401,7 +1401,7 @@ def plot_densities(self, ax: plt.Axes = None, **kwargs):
         for idx, density_name in enumerate(["ae_core_density", "pseudo_core_density"]):
             rden = getattr(self, density_name)
             label = "$n_c$" if idx == 1 else r"$\tilde{n}_c$"
-            ax.plot(rden.mesh, rden.mesh * rden.values, label=label, lw=2)  # noqa: PD011
+            ax.plot(rden.mesh, rden.mesh * rden.values, label=label, lw=2)
 
         ax.legend(loc="best")
 
@@ -1429,10 +1429,10 @@ def plot_waves(self, ax: plt.Axes = None, fontsize=12, **kwargs):
         # ax.annotate("$r_c$", xy=(self.paw_radius + 0.1, 0.1))
 
         for state, rfunc in self.pseudo_partial_waves.items():
-            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, lw=2, label=f"PS-WAVE: {state}")  # noqa: PD011
+            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, lw=2, label=f"PS-WAVE: {state}")
 
         for state, rfunc in self.ae_partial_waves.items():
-            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, lw=2, label=f"AE-WAVE: {state}")  # noqa: PD011
+            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, lw=2, label=f"AE-WAVE: {state}")
 
         ax.legend(loc="best", shadow=True, fontsize=fontsize)
 
@@ -1458,7 +1458,7 @@ def plot_projectors(self, ax: plt.Axes = None, fontsize=12, **kwargs):
         # ax.annotate("$r_c$", xy=(self.paw_radius + 0.1, 0.1))
 
         for state, rfunc in self.projector_functions.items():
-            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, label=f"TPROJ: {state}")  # noqa: PD011
+            ax.plot(rfunc.mesh, rfunc.mesh * rfunc.values, label=f"TPROJ: {state}")
 
         ax.legend(loc="best", shadow=True, fontsize=fontsize)
 

src/pymatgen/io/aims/sets/bs.py

@@ -83,7 +83,7 @@ def get_parameter_updates(
             dict: The updated for the parameters for the output section of FHI-aims
         """
         if isinstance(structure, Molecule):
-            raise ValueError("BandStructures can not be made for non-periodic systems")  # noqa: TRY004
+            raise TypeError("BandStructures can not be made for non-periodic systems")
 
         updated_outputs = prev_parameters.get("output", [])
         updated_outputs += prepare_band_input(structure, self.k_point_density)

src/pymatgen/io/ase.py

@@ -196,7 +196,7 @@ def get_atoms(structure: SiteCollection, msonable: bool = True, **kwargs) -> MSO
             atoms.set_array("oxi_states", np.array(oxi_states))
 
         # Atoms.info <---> Structure.properties
-        if properties := getattr(structure, "properties"):  # noqa: B009
+        if properties := structure.properties:
             atoms.info = properties
 
         # Regenerate Spacegroup object from `.todict()` representation

src/pymatgen/io/cp2k/inputs.py

@@ -111,7 +111,7 @@ def __eq__(self, other: object) -> bool:
             return NotImplemented
         if self.name.upper() == other.name.upper():
             v1 = [val.upper() if isinstance(val, str) else val for val in self.values]
-            v2 = [val.upper() if isinstance(val, str) else val for val in other.values]  # noqa: PD011
+            v2 = [val.upper() if isinstance(val, str) else val for val in other.values]
             if v1 == v2 and self.units == other.units:
                 return True
         return False

src/pymatgen/io/cp2k/outputs.py

@@ -177,12 +177,12 @@ def spin_polarized(self) -> bool:
     @property
     def charge(self) -> float:
         """Charge from the input file."""
-        return self.input["FORCE_EVAL"]["DFT"].get("CHARGE", Keyword("", 0)).values[0]  # noqa: PD011
+        return self.input["FORCE_EVAL"]["DFT"].get("CHARGE", Keyword("", 0)).values[0]
 
     @property
     def multiplicity(self) -> int:
         """The spin multiplicity from input file."""
-        return self.input["FORCE_EVAL"]["DFT"].get("Multiplicity", Keyword("")).values[0]  # noqa: PD011
+        return self.input["FORCE_EVAL"]["DFT"].get("Multiplicity", Keyword("")).values[0]
 
     @property
     def is_molecule(self) -> bool:
@@ -691,9 +691,9 @@ def parse_cell_params(self):
             cell = self.input["force_eval"]["subsys"]["cell"]
             if cell.get("abc"):
                 return [
-                    [cell["abc"].values[0], 0, 0],  # noqa: PD011
-                    [0, cell["abc"].values[1], 0],  # noqa: PD011
-                    [0, 0, cell["abc"].values[2]],  # noqa: PD011
+                    [cell["abc"].values[0], 0, 0],
+                    [0, cell["abc"].values[1], 0],
+                    [0, 0, cell["abc"].values[2]],
                 ]
             return [
                 list(cell.get("A").values),

src/pymatgen/io/cp2k/sets.py

@@ -988,7 +988,7 @@ def activate_motion(
         if not self.check("MOTION"):
             self.insert(Section("MOTION", subsections={}))
 
-        run_type = self["global"].get("run_type", Keyword("run_type", "energy")).values[0].upper()  # noqa: PD011
+        run_type = self["global"].get("run_type", Keyword("run_type", "energy")).values[0].upper()
         run_type = {"GEOMETRY_OPTIMIZATION": "GEO_OPT", "MOLECULAR_DYNAMICS": "MD"}.get(run_type, run_type)
 
         self["MOTION"].insert(Section("PRINT", subsections={}))
@@ -1296,7 +1296,7 @@ def modify_dft_print_iters(self, iters, add_last="no"):
                 no: do not explicitly include the last iteration
         """
         assert add_last.lower() in ["no", "numeric", "symbolic"]
-        run_type = self["global"].get("run_type", Keyword("run_type", "energy")).values[0].upper()  # noqa: PD011
+        run_type = self["global"].get("run_type", Keyword("run_type", "energy")).values[0].upper()
         if run_type not in ["ENERGY_FORCE", "ENERGY", "WAVEFUNCTION_OPTIMIZATION", "WFN_OPT"] and self.check(
             "FORCE_EVAL/DFT/PRINT"
         ):
@@ -1322,8 +1322,8 @@ def validate(self):
         for val in self["force_eval"]["subsys"].subsections.values():
             if (
                 val.name.upper() == "KIND"
-                and val["POTENTIAL"].values[0].upper() == "ALL"  # noqa: PD011
-                and self["force_eval"]["dft"]["qs"]["method"].values[0].upper() != "GAPW"  # noqa: PD011
+                and val["POTENTIAL"].values[0].upper() == "ALL"
+                and self["force_eval"]["dft"]["qs"]["method"].values[0].upper() != "GAPW"
             ):
                 raise Cp2kValidationError("All electron basis sets require GAPW method")