Let Ruff fix some typing issues

Author: marcelm

pyproject.toml

@@ -76,14 +76,12 @@ ignore = [
     "BLE001",  # Do not catch blind exception: `Exception`
     "C408",    # Unnecessary `dict()` call (rewrite as a literal)
     "S102",    # Use of `exec` detected
+    "SIM905",  # Consider using a list literal instead of `str.split`
 
     # Possibly disable the following ones:
     "I001",    # Import block is un-sorted or un-formatted
-    "UP035",   # Import from `collections.abc` instead: `Sequence`
+    "PLC0414", # Import alias does not rename original package
     "ISC004",  # Unparenthesized implicit string concatenation in collection
-    "SIM905",  # Consider using a list literal instead of `str.split`
-    "UP030",   # Use implicit references for positional format fields
-    "UP006",   # Use `list` instead of `List` for type annotation
     "RUF059",  # Unpacked variable `matches` is never used
     "SIM102",  # Use a single `if` statement instead of nested `if` statements
     "FA100",   # Add `from __future__ import annotations` to simplify `typing.Optional`
@@ -92,11 +90,9 @@ ignore = [
     "RUF012",  # Mutable default value for class attribute
     "FURB188", # Prefer `str.removesuffix()` over conditionally replacing with slice.
     "PYI029",  # Defining `__repr__` in a stub is almost always redundant
-    "PLC0414", # Import alias does not rename original package
     "PLR1704", # Redefining argument with the local name `s`
     "B020",    # Loop control variable `s` overrides iterable it iterates
     "RUF022",  # `__all__` is not sorted
     "B006",    # Do not use mutable data structures for argument defaults
     "RUF023",  # `SingleMatch.__slots__` is not sorted
-    "UP045",   # Use `X | None` for type annotations
 ]

src/cutadapt/_align.pyi

@@ -1,4 +1,4 @@
-from typing import Optional, Tuple, Iterable
+from collections.abc import Iterable
 
 class DPMatrix:
     m: int
@@ -24,7 +24,7 @@ class Aligner:
     def dpmatrix(self) -> DPMatrix: ...
     def scorematrix(self) -> DPMatrix: ...
     def enable_debug(self) -> None: ...
-    def locate(self, query: str) -> Optional[Tuple[int, int, int, int, int, int]]: ...
+    def locate(self, query: str) -> tuple[int, int, int, int, int, int] | None: ...
 
 class PrefixComparer:
     @property
@@ -38,9 +38,9 @@ class PrefixComparer:
         min_overlap: int = 1,
     ): ...
     def __repr__(self) -> str: ...
-    def locate(self, query: str) -> Optional[Tuple[int, int, int, int, int, int]]: ...
+    def locate(self, query: str) -> tuple[int, int, int, int, int, int] | None: ...
 
 class SuffixComparer(PrefixComparer): ...
 
 def hamming_sphere(s: str, k: int) -> Iterable[str]: ...
-def edit_environment(t: str, k: int) -> Iterable[Tuple[str, int, int]]: ...
+def edit_environment(t: str, k: int) -> Iterable[tuple[str, int, int]]: ...

src/cutadapt/_kmer_finder.pyi

@@ -1,11 +1,9 @@
-from typing import List, Optional, Tuple
-
 MAXIMUM_WORD_SIZE: int
 
 class KmerFinder:
     def __init__(
         self,
-        positions_and_kmers: List[Tuple[int, Optional[int], List[str]]],
+        positions_and_kmers: list[tuple[int, int | None, list[str]]],
         ref_wildcards: bool = False,
         query_wildcards: bool = False,
     ): ...

src/cutadapt/adapters.py

@@ -8,7 +8,8 @@
 import logging
 from enum import IntFlag
 from collections import defaultdict
-from typing import Optional, Tuple, Sequence, Dict, Any, List, Union
+from typing import Optional, Any, Union
+from collections.abc import Sequence
 from abc import ABC, abstractmethod
 import time
 
@@ -80,7 +81,7 @@ def __init__(self, adapter: "SingleAdapter"):
         self.adapter_type: str = adapter.descriptive_identifier()
         self.allows_partial_matches: bool = adapter.allows_partial_matches
         # self.errors[l][e] == n iff a sequence of length l matching at e errors was removed n times
-        self.errors: Dict[int, Dict[int, int]] = defaultdict(returns_defaultdict_int)
+        self.errors: dict[int, dict[int, int]] = defaultdict(returns_defaultdict_int)
         self.adjacent_bases = {"A": 0, "C": 0, "G": 0, "T": 0, "": 0}
         # TODO avoid hard-coding the list of classes
         self._remove_prefix = isinstance(adapter, FrontAdapter)
@@ -111,7 +112,7 @@ def lengths(self):
         d = {length: sum(errors.values()) for length, errors in self.errors.items()}
         return d
 
-    def random_match_probabilities(self, gc_content: float) -> List[float]:
+    def random_match_probabilities(self, gc_content: float) -> list[float]:
         """
         Estimate probabilities that this adapter end matches a
         random sequence. Indels are not taken into account.
@@ -147,7 +148,7 @@ def __iadd__(self, other):
         pass
 
     @abstractmethod
-    def end_statistics(self) -> Tuple[Optional[EndStatistics], Optional[EndStatistics]]:
+    def end_statistics(self) -> tuple[Optional[EndStatistics], Optional[EndStatistics]]:
         pass
 
     @abstractmethod
@@ -181,7 +182,7 @@ class FrontAdapterStatistics(SingleAdapterStatistics):
     def add_match(self, match: "RemoveBeforeMatch"):
         self.end.errors[match.removed_sequence_length()][match.errors] += 1
 
-    def end_statistics(self) -> Tuple[Optional[EndStatistics], Optional[EndStatistics]]:
+    def end_statistics(self) -> tuple[Optional[EndStatistics], Optional[EndStatistics]]:
         return self.end, None
 
 
@@ -194,7 +195,7 @@ def add_match(self, match: "RemoveAfterMatch"):
         except KeyError:
             self.end.adjacent_bases[""] += 1
 
-    def end_statistics(self) -> Tuple[Optional[EndStatistics], Optional[EndStatistics]]:
+    def end_statistics(self) -> tuple[Optional[EndStatistics], Optional[EndStatistics]]:
         return None, self.end
 
 
@@ -242,7 +243,7 @@ def add_match(self, match: "LinkedMatch"):
             except KeyError:
                 self.back.adjacent_bases[""] += 1
 
-    def end_statistics(self) -> Tuple[Optional[EndStatistics], Optional[EndStatistics]]:
+    def end_statistics(self) -> tuple[Optional[EndStatistics], Optional[EndStatistics]]:
         return self.front, self.back
 
 
@@ -281,23 +282,23 @@ def add_match(self, match: Union["RemoveBeforeMatch", "RemoveAfterMatch"]) -> No
             except KeyError:
                 self.back.adjacent_bases[""] += 1
 
-    def end_statistics(self) -> Tuple[Optional[EndStatistics], Optional[EndStatistics]]:
+    def end_statistics(self) -> tuple[Optional[EndStatistics], Optional[EndStatistics]]:
         return self.front, self.back
 
 
 class Match(ABC):
     adapter: "Adapter"
 
     @abstractmethod
-    def remainder_interval(self) -> Tuple[int, int]:
+    def remainder_interval(self) -> tuple[int, int]:
         pass
 
     @abstractmethod
-    def retained_adapter_interval(self) -> Tuple[int, int]:
+    def retained_adapter_interval(self) -> tuple[int, int]:
         pass
 
     @abstractmethod
-    def get_info_records(self, read) -> List[List]:
+    def get_info_records(self, read) -> list[list]:
         pass
 
     @abstractmethod
@@ -388,7 +389,7 @@ def wildcards(self, wildcard_char: str = "N") -> str:
         ]
         return "".join(wildcards)
 
-    def get_info_records(self, read) -> List[List]:
+    def get_info_records(self, read) -> list[list]:
         seq = read.sequence
         qualities = read.qualities
         info = [
@@ -432,14 +433,14 @@ def rest(self) -> str:
         """
         return self.sequence[: self.rstart]
 
-    def remainder_interval(self) -> Tuple[int, int]:
+    def remainder_interval(self) -> tuple[int, int]:
         """
         Return an interval (start, stop) that describes the part of the read that would
         remain after trimming
         """
         return self.rstop, len(self.sequence)
 
-    def retained_adapter_interval(self) -> Tuple[int, int]:
+    def retained_adapter_interval(self) -> tuple[int, int]:
         return self.rstart, len(self.sequence)
 
     def trim_slice(self):
@@ -465,14 +466,14 @@ def rest(self) -> str:
         """
         return self.sequence[self.rstop :]
 
-    def remainder_interval(self) -> Tuple[int, int]:
+    def remainder_interval(self) -> tuple[int, int]:
         """
         Return an interval (start, stop) that describes the part of the read that would
         remain after trimming
         """
         return 0, self.rstart
 
-    def retained_adapter_interval(self) -> Tuple[int, int]:
+    def retained_adapter_interval(self) -> tuple[int, int]:
         return 0, self.rstop
 
     def trim_slice(self):
@@ -710,7 +711,7 @@ def match_to(self, sequence: str):
         """
         if not self.kmer_finder.kmers_present(sequence):
             return None
-        alignment: Optional[Tuple[int, int, int, int, int, int]] = self.aligner.locate(
+        alignment: Optional[tuple[int, int, int, int, int, int]] = self.aligner.locate(
             sequence
         )
         if self._debug:
@@ -762,7 +763,7 @@ def match_to(self, sequence: str):
         reversed_sequence = sequence[::-1]
         if not self.kmer_finder.kmers_present(reversed_sequence):
             return None
-        alignment: Optional[Tuple[int, int, int, int, int, int]] = self.aligner.locate(
+        alignment: Optional[tuple[int, int, int, int, int, int]] = self.aligner.locate(
             reversed_sequence
         )
         if self._debug:
@@ -818,7 +819,7 @@ def match_to(self, sequence: str):
         """
         if not self.kmer_finder.kmers_present(sequence):
             return None
-        alignment: Optional[Tuple[int, int, int, int, int, int]] = self.aligner.locate(
+        alignment: Optional[tuple[int, int, int, int, int, int]] = self.aligner.locate(
             sequence
         )
         if self._debug:
@@ -866,7 +867,7 @@ def match_to(self, sequence: str):
         reversed_sequence = sequence[::-1]
         if not self.kmer_finder.kmers_present(reversed_sequence):
             return None
-        alignment: Optional[Tuple[int, int, int, int, int, int]] = self.aligner.locate(
+        alignment: Optional[tuple[int, int, int, int, int, int]] = self.aligner.locate(
             reversed_sequence
         )
         if self._debug:
@@ -1130,13 +1131,13 @@ def trimmed(self, read):
             read = self.back_match.trimmed(read)
         return read
 
-    def remainder_interval(self) -> Tuple[int, int]:
+    def remainder_interval(self) -> tuple[int, int]:
         matches = [
             match for match in [self.front_match, self.back_match] if match is not None
         ]
         return remainder(matches)
 
-    def retained_adapter_interval(self) -> Tuple[int, int]:
+    def retained_adapter_interval(self) -> tuple[int, int]:
         if self.front_match:
             start = self.front_match.rstart
             offset = self.front_match.rstop
@@ -1148,7 +1149,7 @@ def retained_adapter_interval(self) -> Tuple[int, int]:
             end = len(self.front_match.sequence)
         return start, end
 
-    def get_info_records(self, read) -> List[List]:
+    def get_info_records(self, read) -> list[list]:
         records = []
         for match, namesuffix in [
             (self.front_match, ";1"),
@@ -1295,7 +1296,7 @@ class AdapterIndex:
     Use the is_acceptable() method to check individual adapters.
     """
 
-    AdapterIndexDict = Dict[str, Tuple[SingleAdapter, int, int]]
+    AdapterIndexDict = dict[str, tuple[SingleAdapter, int, int]]
 
     def __init__(self, adapters, prefix: bool):
         """All given adapters must be of the same type"""
@@ -1387,7 +1388,7 @@ def is_acceptable(cls, adapter: SingleAdapter, prefix: bool):
             return False
         return True
 
-    def _make_index(self) -> Tuple[List[int], "AdapterIndexDict", int]:
+    def _make_index(self) -> tuple[list[int], "AdapterIndexDict", int]:
         start_time = time.time()
         max_k = max(
             (
@@ -1404,7 +1405,7 @@ def _make_index(self) -> Tuple[List[int], "AdapterIndexDict", int]:
                 "Indexing could take long and use a lot of memory. "
                 "If this becomes a problem, try --no-indels and/or --no-index."
             )
-        index: Dict[str, Tuple[SingleAdapter, int, int]] = dict()
+        index: dict[str, tuple[SingleAdapter, int, int]] = dict()
         lengths = set()
         ambiguous = {}
         for adapter in self._adapters:
@@ -1579,7 +1580,7 @@ def warn_duplicate_adapters(adapters):
         d[key] = adapter.name
 
 
-def remainder(matches: Sequence[Match]) -> Tuple[int, int]:
+def remainder(matches: Sequence[Match]) -> tuple[int, int]:
     """
     Determine which section of the read would not be trimmed. Return a tuple (start, stop)
     that gives the interval of the untrimmed part relative to the original read.

src/cutadapt/align.py

@@ -10,7 +10,7 @@
 ]
 
 from enum import IntFlag
-from typing import Iterator, Tuple
+from collections.abc import Iterator
 
 from cutadapt._align import (
     Aligner,
@@ -60,7 +60,7 @@ def edit_distance(s: str, t: str) -> int:
     return costs[-1]
 
 
-def hamming_environment(s: str, k: int) -> Iterator[Tuple[str, int, int]]:
+def hamming_environment(s: str, k: int) -> Iterator[tuple[str, int, int]]:
     """
     Find all strings t for which the hamming distance between s and t is at most k,
     assuming the alphabet is A, C, G, T.
@@ -96,7 +96,7 @@ def naive_edit_environment(s: str, k: int) -> Iterator[str]:
             yield s[:i] + s[i + 1 :]
 
 
-def py_edit_environment(s: str, k: int) -> Iterator[Tuple[str, int, int]]:
+def py_edit_environment(s: str, k: int) -> Iterator[tuple[str, int, int]]:
     """
     Find all strings t for which the edit distance between s and t is at most k,
     assuming the alphabet is A, C, G, T.
@@ -116,7 +116,7 @@ def py_edit_environment(s: str, k: int) -> Iterator[Tuple[str, int, int]]:
         yield t, errors, score
 
 
-def slow_edit_environment(s: str, k: int) -> Iterator[Tuple[str, int, int]]:
+def slow_edit_environment(s: str, k: int) -> Iterator[tuple[str, int, int]]:
     """
     Find all strings t for which the edit distance between s and t is at most k,
     assuming the alphabet is A, C, G, T.