Using ruff for linting #04

pyproject.toml

@@ -73,32 +73,39 @@ isort.lines-after-imports = 2
 select = [
     "C",   # Complexity checks (e.g., McCabe complexity, comprehensions)
     # "ANN001", "ANN201", "ANN401", # flake8-annotations (required strict type annotations for public functions)
-    # "S",   # flake8-bandit (checks basic security issues in code)
+    "S",   # flake8-bandit (checks basic security issues in code)
     # "BLE", # flake8-blind-except (checks the except blocks that do not specify exception)
     # "FBT", # flake8-boolean-trap (ensure that boolean args can be used with kw only)
-    # "E",   # pycodestyle errors (PEP 8 style guide violations)
+    "E",   # pycodestyle errors (PEP 8 style guide violations)
     "W",   # pycodestyle warnings (e.g., extra spaces, indentation issues)
     # "DOC", # pydoclint issues (e.g., extra or missing return, yield, warnings)
-    # "A",   # flake8-buitins (check variable and function names to not shadow builtins)
-    # "N",   # Naming convention checks (e.g., PEP 8 variable and function names)
+    "A",   # flake8-buitins (check variable and function names to not shadow builtins)
+    "N",   # Naming convention checks (e.g., PEP 8 variable and function names)
     "F",   # Pyflakes errors (e.g., unused imports, undefined variables)
-    # "I",   # isort (Ensures imports are sorted properly)
-    # "B",   # flake8-bugbear (Detects likely bugs and bad practices)
+    "I",   # isort (Ensures imports are sorted properly)
+    "B",   # flake8-bugbear (Detects likely bugs and bad practices)
     "TID", # flake8-tidy-imports (Checks for banned or misplaced imports)
     "UP",  # pyupgrade (Automatically updates old Python syntax)
-    # "YTT", # flake8-2020 (Detects outdated Python 2/3 compatibility issues)
-    # "FLY", # flynt (Converts old-style string formatting to f-strings)
-    # "PIE", # flake8-pie
+    "YTT", # flake8-2020 (Detects outdated Python 2/3 compatibility issues)
+    "FLY", # flynt (Converts old-style string formatting to f-strings)
+    "PIE", # flake8-pie
     # "PL",  # pylint
     # "RUF", # Ruff-specific rules (Additional optimizations and best practices)
 ]
 
 ignore = [
-    "PLR2004",  # [magic-value-comparision](https://docs.astral.sh/ruff/rules/magic-value-comparison)
     "C90",      # [mccabe](https://docs.astral.sh/ruff/rules/#mccabe-c90)
+    "PLR2004",  # [magic-value-comparision](https://docs.astral.sh/ruff/rules/magic-value-comparison)
+    "S311",     # [suspicious-non-cryptographic-random-usage](https://docs.astral.sh/ruff/rules/suspicious-non-cryptographic-random-usage/)
+    "S404",     # [suspicious-subprocess-import](https://docs.astral.sh/ruff/rules/suspicious-subprocess-import/)
+    "S603",     # [subprocess-without-shell-equals-true](https://docs.astral.sh/ruff/rules/subprocess-without-shell-equals-true/)
 ]
 
 [tool.ruff.lint.per-file-ignores]
+# non-lowercase-variable-in-function (N806)
+"{femzip_api,femzip_mapper,d3plot,}.py" = ["N806"]
+# error-suffix-on-exception-name (N818)
+"{femzip_api}.py" = ["N818"]
 
 [tool.ruff.format]
 docstring-code-format = true

src/lasso/__init__.py

@@ -1,4 +1,5 @@
-from importlib.metadata import version, PackageNotFoundError
+from importlib.metadata import PackageNotFoundError, version
+
 
 try:
     __version__ = version("lasso-python")

src/lasso/diffcrash/__init__.py

@@ -1,3 +1,4 @@
 from .diffcrash_run import DiffcrashRun
 
+
 __all__ = ["DiffcrashRun"]

src/lasso/diffcrash/diffcrash_run.py

@@ -10,13 +10,14 @@
 import time
 import typing
 from concurrent import futures
-from typing import Union
 from pathlib import Path
+from typing import Union
+
 import psutil
 
-# from ..logging import str_error, str_info, str_running, str_success, str_warn
 from lasso.logging import str_error, str_info, str_running, str_success, str_warn
 
+
 # pylint: disable = too-many-lines
 
 DC_STAGE_SETUP = "SETUP"
@@ -337,9 +338,7 @@ def _parse_crash_code(self, crash_code) -> str:
         self.logger.info(self._msg_option.format("crash-code", crash_code))
 
         if not crash_code_ok:
-            err_msg = (
-                f"Invalid crash code '{crash_code}'. Please use one of: {str(valid_crash_codes)}"
-            )
+            err_msg = f"Invalid crash code '{crash_code}'. Please use one of: {valid_crash_codes!s}"
             self.logger.error(err_msg)
             raise RuntimeError(str_error(err_msg))
 
@@ -647,22 +646,21 @@ def run_import(self, pool: futures.ThreadPoolExecutor):
                         str(i_filepath + counter_offset),
                     ]
             # indeed there is a parameter file
+            elif self.use_id_mapping:
+                args = [
+                    self.diffcrash_home / f"DFC_Import_{self.crash_code}",
+                    "-ID",
+                    self.simulation_runs[i_filepath],
+                    self.project_dir,
+                    str(i_filepath + counter_offset),
+                ]
             else:
-                if self.use_id_mapping:
-                    args = [
-                        self.diffcrash_home / f"DFC_Import_{self.crash_code}",
-                        "-ID",
-                        self.simulation_runs[i_filepath],
-                        self.project_dir,
-                        str(i_filepath + counter_offset),
-                    ]
-                else:
-                    args = [
-                        self.diffcrash_home / f"DFC_Import_{self.crash_code}",
-                        self.simulation_runs[i_filepath],
-                        self.project_dir,
-                        str(i_filepath + counter_offset),
-                    ]
+                args = [
+                    self.diffcrash_home / f"DFC_Import_{self.crash_code}",
+                    self.simulation_runs[i_filepath],
+                    self.project_dir,
+                    str(i_filepath + counter_offset),
+                ]
 
             # append args to list
             import_arguments.append(args)
@@ -689,7 +687,11 @@ def run_import(self, pool: futures.ThreadPoolExecutor):
 
             if n_imports_finished != n_new_imports_finished:
                 # pylint: disable = consider-using-f-string
-                msg = f"Running Imports ... [{n_new_imports_finished}/{len(return_code_futures)}] - {percentage:3.2f}%\r"
+                msg = (
+                    f"Running Imports ... [{n_new_imports_finished}/{len(return_code_futures)}] - "
+                    f"{percentage:3.2f}%\r"
+                )
+
                 print(str_running(msg), end="", flush=True)
                 self.logger.info(msg)
 
@@ -1206,7 +1208,7 @@ def read_config_file(self, config_file: str) -> list[str]:
             conf_lines = conf.readlines()
         line = 0
 
-        for i in range(0, len(conf_lines)):
+        for i in range(len(conf_lines)):
             if conf_lines[i].find("FUNCTION") >= 0:
                 line = i + 1
                 break
@@ -1216,7 +1218,7 @@ def read_config_file(self, config_file: str) -> list[str]:
         if line != 0:
             while 1:
                 while 1:
-                    for i in range(0, len(conf_lines[line])):
+                    for i in range(len(conf_lines[line])):
                         if conf_lines[line][i] == "<":
                             element_start = i + 1
                         if conf_lines[line][i] == ">":
@@ -1231,7 +1233,7 @@ def read_config_file(self, config_file: str) -> list[str]:
                     j += 1
                     items = check.split(" ")
                     pos = -1
-                    for n in range(0, len(items)):
+                    for n in range(len(items)):
                         if items[n].startswith("!"):
                             msg = f"FOUND at {n}"
                             print(msg)
@@ -1240,7 +1242,7 @@ def read_config_file(self, config_file: str) -> list[str]:
                             break
                         pos = len(items)
 
-                    for n in range(0, pos):
+                    for n in range(pos):
                         if items[n] == "PDMX" or items[n] == "pdmx":
                             break
                         if items[n] == "PDXMX" or items[n] == "pdxmx":
@@ -1262,7 +1264,7 @@ def read_config_file(self, config_file: str) -> list[str]:
 
                     for k in range(n, pos):
                         postval = None
-                        for m in range(0, n):
+                        for m in range(n):
                             if items[m] == "coordinates":
                                 items[m] = "geometry"
                             if postval is None:

src/lasso/diffcrash/run.py

@@ -12,7 +12,6 @@
     DiffcrashRun,
     parse_diffcrash_args,
 )
-
 from lasso.logging import str_error
 
 

src/lasso/dimred/__init__.py

@@ -1,3 +1,4 @@
 from .dimred_run import DimredRun, DimredStage
 
+
 __all__ = ["DimredRun", "DimredStage"]

src/lasso/dimred/dimred_run.py

@@ -6,9 +6,9 @@
 import shutil
 import sys
 import time
+from collections.abc import Sequence
 from concurrent.futures.process import ProcessPoolExecutor
 from typing import Union
-from collections.abc import Sequence
 
 import h5py
 import numpy as np
@@ -18,7 +18,6 @@
 from rich.table import Table
 from rich.text import Text
 
-from lasso.utils.rich_progress_bars import PlaceHolderBar, WorkingDots
 from lasso.dimred.svd.clustering_betas import (
     create_cluster_arg_dict,
     create_detector_arg_dict,
@@ -27,6 +26,8 @@
 from lasso.dimred.svd.plot_beta_clusters import plot_clusters_js
 from lasso.dimred.svd.pod_functions import calculate_v_and_betas
 from lasso.dimred.svd.subsampling_methods import create_reference_subsample, remap_random_subsample
+from lasso.utils.rich_progress_bars import PlaceHolderBar, WorkingDots
+
 
 # pylint: disable = too-many-lines
 
@@ -505,7 +506,8 @@ def _parse_part_ids(self, part_ids: Union[Sequence[int], None]) -> Sequence[int]
         if not part_ids:
             return ()
 
-        assert all(isinstance(pid, int) for pid in part_ids), "All part ids must be of type 'int'"
+        if not all(isinstance(pid, int) for pid in part_ids):
+            raise TypeError("All part ids must be of type 'int'")
 
         return part_ids
 
@@ -583,14 +585,13 @@ def _parse_simulation_and_reference_runs(
                 self.raise_error(err_msg)
 
             reference_run = os.path.normpath(reference_run_pattern)
+        # use first simulation run if no reference run was provided
+        # check if enough simulation runs remain
+        elif len(simulation_runs) > 1:
+            reference_run = simulation_runs[0]
         else:
-            # use first simulation run if no reference run was provided
-            # check if enough simulation runs remain
-            if len(simulation_runs) > 1:
-                reference_run = simulation_runs[0]
-            else:
-                err_msg = "Number of Simulation runs after using first as reference run is zero."
-                self.raise_error(err_msg)
+            err_msg = "Number of Simulation runs after using first as reference run is zero."
+            self.raise_error(err_msg)
 
         # add to table
         table.add_row("reference-run", reference_run)
@@ -804,7 +805,10 @@ def subsample_to_reference_run(self):
                             h5_sample.attrs[HDF5FileNames.SUBSAMPLE_PROCESS_TIME.value] = sub[
                                 1
                             ].result()[1]
-                            submitted_samples.pop(i)
+                            # FIXME: loop-iterator-mutation (B909)
+                            # Mutation to loop iterable `submitted_samples` during iteration
+                            # See: https://docs.astral.sh/ruff/rules/loop-iterator-mutation/
+                            submitted_samples.pop(i)  # noqa B909
                             prog.advance(task1)  # type: ignore
                             t_cum_io += sub[1].result()[2]
                             t_cum += sub[1].result()[1]

src/lasso/dimred/graph_laplacian.py

@@ -76,7 +76,8 @@ def _laplacian_gauss_idw(
     L: array-like, shape (n_points, n_points)
       The laplacian matrix for manifold given by its sampling `points`.
     """
-    assert 2 == points.ndim
+    if points.ndim != 2:
+        raise TypeError("Only 2D arrays are supported.")
 
     if min_neighbors is None:
         min_neighbors = points.shape[1]
@@ -110,7 +111,8 @@ def _laplacian_gauss_idw(
         graph[i, j] = d = np.exp(d)
         graph[j, i] = d[:, np.newaxis]
 
-    assert 0 == (graph != graph.T).sum()
+    if not np.array_equal(graph, graph.T):
+        raise RuntimeError("graph matrix is not symetric.")
 
     return csgraph.laplacian(graph, normed=True)
 

src/lasso/dimred/hashing.py

@@ -1,8 +1,8 @@
 import multiprocessing
 import os
 import time
-from typing import Union
 from collections.abc import Sequence
+from typing import Union
 
 import h5py
 import numpy as np
@@ -83,7 +83,10 @@ def is_orientation_flip_required(eigenvectors1: np.ndarray, eigenvectors2: np.nd
         The eigenmodes require switching if the dot product of the knn-eigenfields yield
         a negative result.
     """
-    assert eigenvectors1.shape == eigenvectors2.shape
+    if eigenvectors1.shape != eigenvectors2.shape:
+        raise AssertionError(
+            f"shape mismatch detected. {eigenvectors1.shape} not equal to {eigenvectors2.shape}"
+        )
 
     # one eigenmode only
     if eigenvectors1.ndim == 1:
@@ -133,7 +136,10 @@ def _compute_mode_similarities(
 
     mode_similarities = []
     for i_hash, j_hash in matches:
-        assert hashes1.shape[2] == hashes2.shape[2]
+        if hashes1.shape[2] != hashes2.shape[2]:
+            raise AssertionError(
+                f"Unequal number of columns. {hashes1.shape[2]} is not equal to {hashes2.shape[2]}"
+            )
 
         field1 = eigenvectors_sub1[:, i_hash]
         field2 = eigenvectors_sub2[:, j_hash]
@@ -238,7 +244,8 @@ def run_hash_comparison(
 
     # pylint: disable = too-many-locals, too-many-statements
 
-    assert n_threads > 0
+    if n_threads <= 0:
+        raise ValueError("Number of threads cannot be negative or zero.")
 
     # fixed settings
     hdf5_dataset_compression = "gzip"
@@ -621,7 +628,11 @@ def compute_hashes(
         For comparison, only y is usually used.
     """
 
-    assert eig_vecs.shape[0] == len(result_field), f"{eig_vecs.shape[0]} != {len(result_field)}"
+    if eig_vecs.shape[0] != len(result_field):
+        raise AssertionError(
+            f"Unequal number of rows detected. {eig_vecs.shape[0]} "
+            f"is not equal to {len(result_field)}"
+        )
 
     # Note: needs to be vectorized to speed it up
 

src/lasso/dimred/hashing_sphere.py

@@ -11,6 +11,7 @@
 from scipy.stats import binned_statistic_2d
 from sklearn.preprocessing import normalize
 
+
 warnings.simplefilter(action="ignore", category=FutureWarning)
 
 
@@ -31,7 +32,8 @@ def _create_sphere_mesh(diameter: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
         beta bin boundaries
     """
 
-    assert diameter.dtype == np.float32
+    if diameter.dtype != np.float32:
+        raise TypeError("diameter array must be of type `np.float32`.")
 
     # partition latitude
     n_alpha = 145
@@ -59,8 +61,7 @@ def _create_sphere_mesh(diameter: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
     bin_beta = 1 - tmp
 
     # In case of trailing floats (-1.00000004 for example)
-    if bin_beta[-1] < -1:
-        bin_beta[-1] = -1
+    bin_beta[-1] = max(bin_beta[-1], -1)
 
     bin_beta = np.arccos(bin_beta)
 
@@ -139,10 +140,16 @@ def sphere_hashing(
     """
     # bin_numbers holds the bin_number for its respective index and must have
     # same length as the number of points
-    assert len(bin_numbers[0] == len(field))
+    if not len(bin_numbers[0] == len(field)):
+        raise AssertionError(
+            "bin_numbers holds the bin_number for its respective index and"
+            "must have same length as the number of points."
+        )
     # check data types
-    assert bin_numbers.dtype == np.int
-    assert bin_counts.dtype == np.float32
+    if not np.issubdtype(bin_numbers.dtype, np.integer):
+        raise TypeError(f"Expected int dtype got {bin_numbers.dtype}")
+    if not np.issubdtype(bin_counts.dtype, np.floating):
+        raise TypeError(f"Expected float dtype got {bin_counts.dtype}.")
 
     n_rows = bin_counts.shape[0]
     n_cols = bin_counts.shape[1]