Add BLE, C4, ISC, and PERF lints (#3579)

Author: flying-sheep

docs/extensions/git_ref.py

@@ -28,14 +28,14 @@ def get() -> str | None:
     try:
         git_ref = git("name-rev", "--name-only", "--no-undefined", "HEAD")
         git_ref = re.sub(r"^(remotes/[^/]+|tags)/", "", git_ref)
-    except Exception:
+    except Exception:  # noqa: BLE001
         pass
 
     # (if no name found or relative ref, use commit hash instead)
     if not git_ref or re.search(r"[\^~]", git_ref):
         try:
             git_ref = git("rev-parse", "HEAD")
-        except Exception:
+        except Exception:  # noqa: BLE001
             git_ref = "main"
     return git_ref
 

pyproject.toml

@@ -227,13 +227,17 @@ docstring-code-format = true
 [tool.ruff.lint]
 select = [
     "B",      # Likely bugs and design issues
+    "BLE",    # Blind exception raised
+    "C4",     # Comprehensions
     "D",      # Documentation style
     "E",      # Error detected by Pycodestyle
     "EM",     # Traceback-friendly error messages
     "F",      # Errors detected by Pyflakes
     "FBT",    # No positional boolean parameters
     "I",      # Import sorting
     "ICN",    # Follow import conventions
+    "ISC",    # Implicit string concatenation
+    "PERF",   # Performance
     "PIE",    # Syntax simplifications
     "PL",     # Pylint
     "PT",     # Pytest style
@@ -248,6 +252,8 @@ select = [
 ]
 external = [ "PLR0917" ] # preview lint that we use
 ignore = [
+    # dict() syntax is preferrable when creating dicts for kwargs
+    "C408",
     # E266 too many leading '#' for block comment -> Scanpy allows them for comments into sections
     "E262",
     # module level import not at top of file -> required to circumvent circular imports for Scanpys API

src/scanpy/_settings.py

@@ -26,16 +26,14 @@
 
 AnnDataFileFormat = Literal["h5ad", "zarr"]
 
-_VERBOSITY_TO_LOGLEVEL = {
+_VERBOSITY_TO_LOGLEVEL: dict[int | str, str] = {
     "error": "ERROR",
     "warning": "WARNING",
     "info": "INFO",
     "hint": "HINT",
     "debug": "DEBUG",
 }
-# Python 3.7+ ensures iteration order
-for v, level in enumerate(list(_VERBOSITY_TO_LOGLEVEL.values())):
-    _VERBOSITY_TO_LOGLEVEL[v] = level
+_VERBOSITY_TO_LOGLEVEL.update(dict(enumerate(list(_VERBOSITY_TO_LOGLEVEL.values()))))
 
 
 class Verbosity(IntEnum):

src/scanpy/plotting/_tools/paga.py

@@ -525,11 +525,11 @@ def is_flat(x):
         labels = [labels for _ in range(len(colors))]
 
     if title is None and len(colors) > 1:
-        title = [c for c in colors]
+        title = list(colors)
     elif isinstance(title, str):
-        title = [title for c in colors]
+        title = [title] * len(colors)
     elif title is None:
-        title = [None for c in colors]
+        title = [None] * len(colors)
 
     if colorbar is None:
         var_names = adata.var_names if adata.raw is None else adata.raw.var_names

src/scanpy/plotting/_tools/scatterplots.py

@@ -1387,6 +1387,4 @@ def _broadcast_args(*args):
     if not (set(lens) == {1, longest} or set(lens) == {longest}):
         msg = f"Could not broadcast together arguments with shapes: {lens}."
         raise ValueError(msg)
-    return list(
-        [[arg[0] for _ in range(longest)] if len(arg) == 1 else arg for arg in args]
-    )
+    return [[arg[0] for _ in range(longest)] if len(arg) == 1 else arg for arg in args]

src/scanpy/preprocessing/_combat.py

@@ -218,11 +218,8 @@ def combat(  # noqa: PLR0915
     gamma_hat = (
         la.inv(batch_design.T @ batch_design) @ batch_design.T @ s_data.T
     ).values
-    delta_hat = []
-
     # first estimate for the multiplicative batch effect
-    for batch_idxs in batch_info:
-        delta_hat.append(s_data.iloc[:, batch_idxs].var(axis=1))
+    delta_hat = [s_data.iloc[:, batch_idxs].var(axis=1) for batch_idxs in batch_info]
 
     # empirically fix the prior hyperparameters
     gamma_bar = gamma_hat.mean(axis=1)

src/scanpy/preprocessing/_scrublet/core.py

@@ -436,7 +436,7 @@ def call_doublets(
                     logg.info(
                         f"Automatically set threshold at doublet score = {threshold:.2f}"
                     )
-            except Exception:
+            except Exception:  # noqa: BLE001
                 self.predicted_doublets_ = None
                 if verbose:
                     logg.warning(

src/scanpy/readwrite.py

@@ -1039,8 +1039,7 @@ def get_used_files():
     for proc in loop_over_scanpy_processes:
         try:
             flist = proc.open_files()
-            for nt in flist:
-                filenames.append(nt.path)
+            filenames.extend(nt.path for nt in flist)
         # This catches a race condition where a process ends
         # before we can examine its files
         except psutil.NoSuchProcess:

src/scanpy/tools/_dpt.py

@@ -903,19 +903,17 @@ def _detect_branching(  # noqa: PLR0915
 
     def _detect_branching_single_haghverdi16(self, Dseg, tips):
         """Detect branching on given segment."""
-        # compute branchings using different starting points the first index of
-        # tips is the starting point for the other two, the order does not
-        # matter
-        ssegs = []
         # permutations of tip cells
         ps = [
             [0, 1, 2],  # start by computing distances from the first tip
             [1, 2, 0],  #             -"-                       second tip
             [2, 0, 1],  #             -"-                       third tip
         ]
-        for p in ps:
-            ssegs.append(self.__detect_branching_haghverdi16(Dseg, tips[p]))
-        return ssegs
+
+        # compute branchings using different starting points the first index of
+        # tips is the starting point for the other two, the order does not
+        # matter
+        return [self.__detect_branching_haghverdi16(Dseg, tips[p]) for p in ps]
 
     def _detect_branching_single_wolf17_tri(self, Dseg, tips):
         # all pairwise distances

src/scanpy/tools/_sim.py

@@ -595,21 +595,22 @@ def read_model(self):
         # version of the discrete model)
         self.build_boolCoeff()
 
-    def set_coupl(self, Coupl=None) -> None:  # noqa: PLR0912
+    def set_coupl(self, Coupl=None) -> None:
         """Construct the coupling matrix (and adjacancy matrix) from predefined models or via sampling."""
         self.varNames = {str(i): i for i in range(self.dim)}
         if self.model not in self.availModels and Coupl is None:
             self.read_model()
         elif "var" in self.model.name:
             # vector auto regressive process
             self.Coupl = Coupl
-            self.boolRules = {s: "" for s in self.varNames}
+            self.boolRules = dict.fromkeys(self.varNames, "")
             names = list(self.varNames.keys())
             for gp in range(self.dim):
-                pas = []
-                for g in range(self.dim):
-                    if np.abs(self.Coupl[gp, g] > 1e-10):
-                        pas.append(names[g])
+                pas = [
+                    names[g]
+                    for g in range(self.dim)
+                    if np.abs(self.Coupl[gp, g] > 1e-10)
+                ]
                 self.boolRules[names[gp]] = "".join(
                     pas[:1] + [" or " + pa for pa in pas[1:]]
                 )
@@ -761,7 +762,7 @@ def branch_init_model1(self, tmax=100):
             settings.m(
                 0,
                 "... either no fixed point in [0,1]^2! \n"
-                + "    or fixed point is too close to bounds",
+                "    or fixed point is too close to bounds",
             )
             return None
         XbackUp = self.sim_model_backwards(
@@ -1246,7 +1247,7 @@ def sample_static_data(model, dir, verbosity=0):
         default="",
         help=(
             "specify directory to store data, "
-            + ' must start with "sim/MODEL_...", see possible values for MODEL below '
+            ' must start with "sim/MODEL_...", see possible values for MODEL below '
         ),
     )
     aa("--show", action="store_true", help="show plots")