[pre-commit.ci] pre-commit autoupdate (#3003)

<!--pre-commit.ci start-->
updates:
- [github.com/pre-commit/pre-commit-hooks: v4.4.0 →
v4.6.0](pre-commit/pre-commit-hooks@v4.4.0...v4.6.0)
- [github.com/astral-sh/ruff-pre-commit: v0.2.0 →
v0.4.9](astral-sh/ruff-pre-commit@v0.2.0...v0.4.9)
- [github.com/tox-dev/tox-ini-fmt: 0.5.2 →
1.3.1](tox-dev/tox-ini-fmt@0.5.2...1.3.1)
<!--pre-commit.ci end-->

---------

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

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.6.0
     hooks:
       - id: check-ast
       - id: check-builtin-literals
@@ -10,16 +10,16 @@ repos:
       - id: check-toml
       - id: debug-statements
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.2.0
+    rev: v0.4.9
     hooks:
       - id: ruff-format
       - id: ruff
         args: ["--fix", "--unsafe-fixes", "--exit-non-zero-on-fix"]
-  - repo: https://github.com/tox-dev/tox-ini-fmt
-    rev: "0.5.2"
-    hooks:
-      - id: tox-ini-fmt
-        args: ["-p", "fix_lint"]
+#  - repo: https://github.com/tox-dev/tox-ini-fmt
+#    rev: "1.3.1"
+#    hooks:
+#      - id: tox-ini-fmt
+#        args: ["-p", "fix_lint"]
   - repo: meta
     hooks:
       - id: check-hooks-apply

src/sourmash/__init__.py

@@ -15,6 +15,7 @@ class MinHash - hash sketch class
 The sourmash code is available at github.com/sourmash-bio/sourmash/ under the
 BSD 3-Clause license.
 """
+
 from deprecation import deprecated
 from importlib.metadata import version
 

src/sourmash/command_compute.py

@@ -1,6 +1,7 @@
 """
 Functions implementing the 'compute' command and related functions.
 """
+
 import os
 import os.path
 import sys

src/sourmash/command_sketch.py

@@ -1,6 +1,7 @@
 """
 Functions implementing the 'sketch' subcommands and related functions.
 """
+
 import sys
 import os
 from collections import defaultdict, Counter

src/sourmash/commands.py

@@ -1,6 +1,7 @@
 """
 Functions implementing the main command-line subcommands.
 """
+
 import csv
 import os
 import os.path

src/sourmash/distance_utils.py

@@ -3,6 +3,7 @@
 Equations from: https://github.com/KoslickiLab/mutation-rate-ci-calculator
 Reference: https://doi.org/10.1101/2022.01.11.475870
 """
+
 from dataclasses import dataclass, field
 from scipy.optimize import brentq
 from scipy.stats import norm as scipy_norm

src/sourmash/fig.py

@@ -2,6 +2,7 @@
 """
 Make plots using the distance matrix+labels output by `sourmash compare`.
 """
+
 from .logging import error, notify
 
 try:

src/sourmash/index/sqlite_index.py

@@ -73,6 +73,7 @@
   should work fine for many simultaneous queries; just don't write :).
 
 """
+
 import time
 import os
 import sqlite3

src/sourmash/lca/command_classify.py

@@ -2,6 +2,7 @@
 """
 Classify individual signature files down to deepest possible node.
 """
+
 import sys
 import csv
 

src/sourmash/lca/command_compare_csv.py

@@ -2,6 +2,7 @@
 """
 Compare two taxonomy spreadsheets.
 """
+
 import sys
 from collections import defaultdict
 

src/sourmash/lca/command_index.py

@@ -2,6 +2,7 @@
 """
 Build a lowest-common-ancestor database with given taxonomy and genome sigs.
 """
+
 import sys
 import csv
 import os

src/sourmash/lca/command_rankinfo.py

@@ -2,6 +2,7 @@
 """
 Summarize rank-specific information from LCAs in one or more databases.
 """
+
 import sys
 from collections import defaultdict
 

src/sourmash/lca/command_summarize.py

@@ -2,6 +2,7 @@
 """
 Summarize the taxonomic content of the given signatures, combined.
 """
+
 import sys
 import csv
 from collections import defaultdict

src/sourmash/lca/lca_db.py

@@ -1,4 +1,5 @@
 "LCA database class and utilities."
+
 import os
 import json
 import gzip
@@ -157,16 +158,12 @@ def insert(self, sig, ident=None, lineage=None):
 
         if minhash.ksize != self.ksize:
             raise ValueError(
-                "cannot insert signature with ksize {} into DB (ksize {})".format(
-                    minhash.ksize, self.ksize
-                )
+                f"cannot insert signature with ksize {minhash.ksize} into DB (ksize {self.ksize})"
             )
 
         if minhash.moltype != self.moltype:
             raise ValueError(
-                "cannot insert signature with moltype {} into DB (moltype {})".format(
-                    minhash.moltype, self.moltype
-                )
+                f"cannot insert signature with moltype {minhash.moltype} into DB (moltype {self.moltype})"
             )
 
         # downsample to specified scaled; this has the side effect of

src/sourmash/lca/lca_utils.py

@@ -1,6 +1,7 @@
 """
 Utility functions for lowest-common-ancestor analysis tools.
 """
+
 from os.path import exists
 from collections import namedtuple, defaultdict, Counter
 

src/sourmash/manifest.py

@@ -1,6 +1,7 @@
 """
 Manifests for collections of signatures.
 """
+
 import csv
 import ast
 import gzip

src/sourmash/minhash.py

@@ -4,6 +4,7 @@
 class MinHash - core MinHash class.
 class FrozenMinHash - read-only MinHash class.
 """
+
 from .distance_utils import (
     jaccard_to_distance,
     containment_to_distance,

src/sourmash/nodegraph.py

@@ -152,11 +152,11 @@ def calc_expected_collisions(graph, force=False, max_false_pos=0.2):
         print("** Do not use these results!!", file=sys.stderr)
         print("**", file=sys.stderr)
         print(
-            "** (estimated false positive rate of %.3f;" % fp_all,
+            f"** (estimated false positive rate of {fp_all:.3f};",
             file=sys.stderr,
             end=" ",
         )
-        print("max recommended %.3f)" % max_false_pos, file=sys.stderr)
+        print(f"max recommended {max_false_pos:.3f})", file=sys.stderr)
         print("**", file=sys.stderr)
 
         if not force:

src/sourmash/picklist.py

@@ -9,6 +9,7 @@
 and operate efficiently on manifests, so when used with e.g. zipfiles,
 only the selected sketches are loaded.
 """
+
 import csv
 import os
 from enum import Enum

src/sourmash/save_load.py

@@ -24,6 +24,7 @@
 CTB TODO:
 * consider replacing ValueError with IndexNotLoaded in the future.
 """
+
 import sys
 import os
 import gzip

src/sourmash/sbt.py

@@ -3,7 +3,6 @@
 An implementation of sequence bloom trees, Solomon & Kingsford, 2015.
 """
 
-
 from collections import namedtuple, Counter
 from collections.abc import Mapping
 
@@ -103,7 +102,7 @@ def popitem(self):
             # we just need to select the maximum key/node id
             (key, _) = max(c for c in common if c[1] == count)
         except IndexError:
-            msg = "%s is empty" % self.__class__.__name__
+            msg = f"{self.__class__.__name__} is empty"
             raise KeyError(msg) from None
         else:
             value = self.pop(key)
@@ -1404,11 +1403,7 @@ def __init__(self, factory, name=None, path=None, storage=None):
         self.metadata = {}
 
     def __str__(self):
-        return "*Node:{name} [occupied: {nb}, fpr: {fpr:.2}]".format(
-            name=self.name,
-            nb=self.data.n_occupied(),
-            fpr=calc_expected_collisions(self.data, True, 1.1),
-        )
+        return f"*Node:{self.name} [occupied: {self.data.n_occupied()}, fpr: {calc_expected_collisions(self.data, True, 1.1):.2}]"
 
     def save(self, path):
         buf = self.data.to_bytes(compression=1)
@@ -1468,12 +1463,7 @@ def __init__(self, metadata, data=None, name=None, storage=None, path=None):
         self._path = path
 
     def __str__(self):
-        return "**Leaf:{name} [occupied: {nb}, fpr: {fpr:.2}] -> {metadata}".format(
-            name=self.name,
-            metadata=self.metadata,
-            nb=self.data.n_occupied(),
-            fpr=calc_expected_collisions(self.data, True, 1.1),
-        )
+        return f"**Leaf:{self.name} [occupied: {self.data.n_occupied()}, fpr: {calc_expected_collisions(self.data, True, 1.1):.2}] -> {self.metadata}"
 
     def make_manifest_row(self, location):
         return None

src/sourmash/search.py

@@ -1,6 +1,7 @@
 """
 Code for searching collections of signatures.
 """
+
 import csv
 import numpy as np
 from enum import Enum

src/sourmash/sig/__main__.py

@@ -1,6 +1,7 @@
 """
 Command-line entry point for 'python -m sourmash.sig'
 """
+
 __all__ = [
     "cat",
     "split",
@@ -81,9 +82,7 @@
 def _check_abundance_compatibility(sig1, sig2):
     if sig1.minhash.track_abundance != sig2.minhash.track_abundance:
         raise ValueError(
-            "incompatible signatures: track_abundance is {} in first sig, {} in second".format(
-                sig1.minhash.track_abundance, sig2.minhash.track_abundance
-            )
+            f"incompatible signatures: track_abundance is {sig1.minhash.track_abundance} in first sig, {sig2.minhash.track_abundance} in second"
         )
 
 

src/sourmash/sig/grep.py

@@ -1,6 +1,7 @@
 """
 Command-line entry point for 'python -m sourmash.sig grep'
 """
+
 import sys
 import re
 

src/sourmash/signature.py

@@ -2,6 +2,7 @@
 """
 Save and load MinHash sketches in a JSON format, along with some metadata.
 """
+
 import sys
 import os
 import weakref
@@ -367,7 +368,7 @@ def _detect_input_type(data):
         except TypeError:
             if data.find(b"sourmash_signature") > 0:
                 return SigInput.BUFFER
-            elif data.startswith(b"\x1F\x8B"):  # gzip compressed
+            elif data.startswith(b"\x1f\x8b"):  # gzip compressed
                 return SigInput.BUFFER
 
     try:

src/sourmash/sketchcomparison.py

@@ -1,6 +1,7 @@
 """
 Sketch Comparison Classes
 """
+
 import numpy as np
 from dataclasses import dataclass
 

src/sourmash/sourmash_args.py

@@ -36,6 +36,7 @@
 misc support:
 * FileInputCSV - context manager for reading CSVs
 """
+
 import sys
 import os
 import csv

src/sourmash/sqlite_utils.py

@@ -1,6 +1,7 @@
 """
 Common utility functions for handling sqlite3 databases.
 """
+
 import os
 import sqlite3
 from .logging import debug_literal

src/sourmash/tax/__main__.py

@@ -1,6 +1,7 @@
 """
 Command-line entry point for 'python -m sourmash.tax'
 """
+
 import sys
 import csv
 import os

src/sourmash/tax/tax_utils.py

@@ -1,6 +1,7 @@
 """
 Utility functions for taxonomy analysis tools.
 """
+
 import os
 import csv
 from collections import abc, defaultdict
@@ -1001,9 +1002,9 @@ def aggregate_by_lineage_at_rank(query_gather_results, rank, *, by_query=False):
         for res in queryResult.summarized_lineage_results[rank]:
             lineage = res.lineage.display_lineage(null_as_unclassified=True)
             if by_query:
-                lineage_summary[lineage][
-                    query_name
-                ] = res.fraction  # v5?: res.f_weighted_at_rank
+                lineage_summary[lineage][query_name] = (
+                    res.fraction
+                )  # v5?: res.f_weighted_at_rank
             else:
                 lineage_summary[lineage] += res.fraction
 
@@ -2346,15 +2347,15 @@ def summarize_up_ranks(self, single_rank=None, force_resummarize=False):
                         rank in lininfo.filled_ranks
                     ):  # only store if this rank is filled.
                         lin_at_rank = lininfo.pop_to_rank(rank)
-                        self.sum_uniq_weighted[rank][
-                            lin_at_rank
-                        ] += taxres.f_unique_weighted
-                        self.sum_uniq_to_query[rank][
-                            lin_at_rank
-                        ] += taxres.f_unique_to_query
-                        self.sum_uniq_bp[rank][
-                            lin_at_rank
-                        ] += taxres.unique_intersect_bp
+                        self.sum_uniq_weighted[rank][lin_at_rank] += (
+                            taxres.f_unique_weighted
+                        )
+                        self.sum_uniq_to_query[rank][lin_at_rank] += (
+                            taxres.f_unique_to_query
+                        )
+                        self.sum_uniq_bp[rank][lin_at_rank] += (
+                            taxres.unique_intersect_bp
+                        )
         # reset ranks levels to the ones that were actually summarized + that we can access for summarized result
         self.summarized_ranks = [
             x for x in self.summarized_ranks if x in self.sum_uniq_bp.keys()

src/sourmash/utils.py

@@ -12,7 +12,7 @@ class RustObject:
     _shared = False
 
     def __init__(self):
-        raise TypeError("Cannot instanciate %r objects" % self.__class__.__name__)
+        raise TypeError(f"Cannot instanciate {self.__class__.__name__!r} objects")
 
     @classmethod
     def _from_objptr(cls, ptr, shared=False):

tests/sourmash_tst_utils.py

@@ -1,4 +1,5 @@
 "Various utilities used by sourmash tests."
+
 import sys
 import os
 import tempfile