Merge pull request #19 from CountESS-Project/dev

version 1.3.0 updates

.github/workflows/python-package.yml

@@ -24,20 +24,19 @@ jobs:
       uses: actions/setup-python@v3
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Install package
       run: |
-        python -m pip install .
+        python -m pip install --upgrade pip
+        python -m pip install .[dev]
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names
         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        # exit-zero treats all errors as warnings
         flake8 . --count --exit-zero --statistics
     - name: Test with pytest
       run: |
-        pytest
+        python -m pytest
+    - name: Type check with mypy
+      run: |
+        python -m mypy src/

.pre-commit-config.yaml

@@ -8,3 +8,5 @@ repos:
     rev: 5.0.4
     hooks:
     -   id: flake8
+        additional_dependencies:
+          - Flake8-pyproject

pyproject.toml

@@ -34,8 +34,17 @@ dev = [
     "flake8",
     "pre-commit",
     "pytest",
+    "Flake8-pyproject",
+    "mypy",
 ]
 
+[tool.black]
+line-length = 120
+
+[tool.flake8]
+extend-ignore = ["E203", "E501"]
+max-complexity = 10
+
 [tool.hatch.version]
 path = "src/fqfa/__init__.py"
 

src/fqfa/__init__.py

@@ -9,7 +9,7 @@
 )
 from fqfa.util.translate import translate_dna, ncbi_genetic_code_to_dict
 
-__version__ = "1.2.3"
+__version__ = "1.3.0"
 
 __all__ = [
     "__version__",

src/fqfa/fastq/fastq.py

@@ -37,7 +37,8 @@ def parse_fastq_reads(handle: TextIO) -> Generator[FastqRead, None, None]:
             raise ValueError("incomplete FASTQ record")
         else:
             lines = [x.rstrip() for x in lines]  # remove trailing newlines
-            yield FastqRead(*lines)
+            # TODO: figure out why mypy doesn't like this
+            yield FastqRead(*lines)  # type: ignore[arg-type]
 
 
 def parse_fastq_pe_reads(
@@ -80,9 +81,9 @@ def parse_fastq_pe_reads(
     for fwd, rev in zip_longest(fwd_generator, rev_generator, fillvalue=None):
         if None in (fwd, rev):
             raise ValueError("mismatched FASTQ file lengths")
-        elif fwd.header.split()[0] != rev.header.split()[0]:
+        elif fwd.header.split()[0] != rev.header.split()[0]:  # type: ignore[union-attr]
             raise ValueError("forward and reverse read headers do not match")
         else:
             if revcomp:
-                rev.reverse_complement()
-            yield fwd, rev
+                rev.reverse_complement()  # type: ignore[union-attr]
+            yield fwd, rev  # type: ignore[misc]

src/fqfa/fastq/fastqread.py

@@ -4,7 +4,6 @@
 
 from dataclasses import dataclass, field, InitVar
 from typing import List, Optional, ClassVar, Callable, Match
-from statistics import mean
 from fqfa.util.nucleotide import reverse_complement
 from fqfa.validator.create import create_validator
 from fqfa.constants.iupac.dna import DNA_BASES
@@ -52,9 +51,7 @@ class FastqRead:
     quality: List[int] = field(init=False)
     quality_string: InitVar[str]
     quality_encoding_value: int = 33
-    _sequence_validator: ClassVar[
-        Callable[[str], Optional[Match[str]]]
-    ] = create_validator(DNA_BASES + ["N"])
+    _sequence_validator: ClassVar[Callable[[str], Optional[Match[str]]]] = create_validator(DNA_BASES + ["N"])
 
     def __post_init__(self, quality_string: str) -> None:
         """Perform some basic checks on the input and converts the quality string into a
@@ -99,7 +96,10 @@ def __post_init__(self, quality_string: str) -> None:
             # mypy false positive: https://github.com/python/mypy/issues/5485
             raise ValueError("unexpected characters in sequence")
 
-        self.quality = [ord(c) - self.quality_encoding_value for c in quality_string]
+        quality_string_bytes = quality_string.encode("ascii")
+        qev = self.quality_encoding_value
+        self.quality = [qsb - qev for qsb in quality_string_bytes]
+
         if min(self.quality) < 0:
             raise ValueError("sequence quality value below 0")
         if max(self.quality) > 93:
@@ -125,9 +125,7 @@ def __str__(self) -> str:
             Reconstruction of the original FASTQ record.
 
         """
-        quality_string = "".join(
-            [chr(q + self.quality_encoding_value) for q in self.quality]
-        )
+        quality_string = "".join([chr(q + self.quality_encoding_value) for q in self.quality])
         return "\n".join((self.header, self.sequence, self.header2, quality_string))
 
     def average_quality(self) -> float:
@@ -139,7 +137,7 @@ def average_quality(self) -> float:
             Mean quality value.
 
         """
-        return mean(self.quality)
+        return sum(self.quality) / len(self.quality)
 
     def min_quality(self) -> int:
         """Calculates and returns the read's minimum quality value.

src/fqfa/util/infer.py

@@ -59,9 +59,7 @@ def infer_sequence_type(seq: str, report_iupac: bool = True) -> Optional[str]:
         return None
 
 
-def infer_all_sequence_types(  # noqa: max-complexity: 11
-    seq: str, report_iupac: bool = True
-) -> Optional[List[str]]:
+def infer_all_sequence_types(seq: str, report_iupac: bool = True) -> Optional[List[str]]:  # noqa: max-complexity: 11
     """Return all inferred types for the given sequence.
 
     Sequence types include:

src/fqfa/util/translate.py

@@ -9,9 +9,7 @@
 __all__ = ["translate_dna", "ncbi_genetic_code_to_dict"]
 
 
-def translate_dna(
-    seq: str, table: Optional[Dict[str, str]] = None, frame: int = 0
-) -> Tuple[str, Optional[str]]:
+def translate_dna(seq: str, table: Optional[Dict[str, str]] = None, frame: int = 0) -> Tuple[str, Optional[str]]:
     """
     Translate a DNA sequence into the corresponding amino acid sequence.
 
@@ -116,11 +114,7 @@ def ncbi_genetic_code_to_dict(  # noqa: max-complexity: 11
         If the AAs row contains a character other than an amino acid.
 
     """
-    lines = [
-        s.strip()
-        for s in ncbi_string.split("\n")
-        if len(s) > 0 and not s.startswith("#") and not s.isspace()
-    ]
+    lines = [s.strip() for s in ncbi_string.split("\n") if len(s) > 0 and not s.startswith("#") and not s.isspace()]
     if len(lines) != 5:
         raise ValueError("transl_table string must have 5 lines")
 
@@ -152,12 +146,7 @@ def ncbi_genetic_code_to_dict(  # noqa: max-complexity: 11
     codon_dict: Dict[str, str] = dict()
     for aa, codon in zip(
         transl_table["AAs"],
-        (
-            "".join(nts)
-            for nts in zip(
-                transl_table["Base1"], transl_table["Base2"], transl_table["Base3"]
-            )
-        ),
+        ("".join(nts) for nts in zip(transl_table["Base1"], transl_table["Base2"], transl_table["Base3"])),
     ):
         if codon not in codon_dict:
             codon_dict[codon] = aa

tests/test_fastqread.py

@@ -22,9 +22,7 @@ def test_creation_no_errors(self) -> None:
         self.assertEqual(test_read.sequence, self.test_kwargs["sequence"])
         self.assertEqual(test_read.header2, self.test_kwargs["header2"])
         self.assertListEqual(test_read.quality, self.test_quality)
-        self.assertEqual(
-            test_read.quality_encoding_value, self.test_kwargs["quality_encoding_value"]
-        )
+        self.assertEqual(test_read.quality_encoding_value, self.test_kwargs["quality_encoding_value"])
 
     def test_creation_bad_header(self) -> None:
         test_kwargs = self.test_kwargs.copy()
@@ -55,9 +53,7 @@ def test_creation_bad_bases(self) -> None:
 
         # bad internal base/ambiguity character
         test_kwargs = self.test_kwargs.copy()
-        test_kwargs["sequence"] = (
-            self.test_kwargs["sequence"][:1] + "W" + self.test_kwargs["sequence"][2:]
-        )
+        test_kwargs["sequence"] = self.test_kwargs["sequence"][:1] + "W" + self.test_kwargs["sequence"][2:]
         self.assertRaises(ValueError, FastqRead, **test_kwargs)
 
         # bad last base/number
@@ -74,9 +70,7 @@ def test_creation_bad_quality(self) -> None:
         # bad internal value/unicode character
         test_kwargs = self.test_kwargs.copy()
         test_kwargs["quality_string"] = (
-            self.test_kwargs["quality_string"][:1]
-            + "µ"
-            + self.test_kwargs["quality_string"][2:]
+            self.test_kwargs["quality_string"][:1] + "µ" + self.test_kwargs["quality_string"][2:]
         )
         self.assertRaises(ValueError, FastqRead, **test_kwargs)
 
@@ -117,9 +111,7 @@ def test_trim_start(self) -> None:
         test_read.trim(start=len(test_read))
         self.assertEqual(len(test_read), 1)
         self.assertEqual(len(test_read.sequence), len(test_read.quality))
-        self.assertEqual(
-            test_read.sequence, FastqRead(**self.test_kwargs).sequence[-1:]
-        )
+        self.assertEqual(test_read.sequence, FastqRead(**self.test_kwargs).sequence[-1:])
 
     def test_trim_end(self) -> None:
         test_read = FastqRead(**self.test_kwargs)
@@ -130,9 +122,7 @@ def test_trim_end(self) -> None:
         test_read.trim(end=len(test_read) - 1)
         self.assertEqual(len(test_read), len(FastqRead(**self.test_kwargs)) - 1)
         self.assertEqual(len(test_read.sequence), len(test_read.quality))
-        self.assertEqual(
-            test_read.sequence, FastqRead(**self.test_kwargs).sequence[:-1]
-        )
+        self.assertEqual(test_read.sequence, FastqRead(**self.test_kwargs).sequence[:-1])
 
         test_read = FastqRead(**self.test_kwargs)
         test_read.trim(end=1)
@@ -145,17 +135,13 @@ def test_trim_both_ends(self) -> None:
         test_read.trim(start=2, end=2)
         self.assertEqual(len(test_read), 1)
         self.assertEqual(len(test_read.sequence), len(test_read.quality))
-        self.assertEqual(
-            test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:2]
-        )
+        self.assertEqual(test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:2])
 
         test_read = FastqRead(**self.test_kwargs)
         test_read.trim(start=2, end=4)
         self.assertEqual(len(test_read), 3)
         self.assertEqual(len(test_read.sequence), len(test_read.quality))
-        self.assertEqual(
-            test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:4]
-        )
+        self.assertEqual(test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:4])
 
     def test_trim_bad_parameters(self) -> None:
         test_read = FastqRead(**self.test_kwargs)
@@ -201,21 +187,15 @@ def test_trim_length(self) -> None:
         test_read.trim_length(start=2, length=4)
         self.assertEqual(len(test_read), 4)
         self.assertEqual(len(test_read.sequence), len(test_read.quality))
-        self.assertEqual(
-            test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:5]
-        )
+        self.assertEqual(test_read.sequence, FastqRead(**self.test_kwargs).sequence[1:5])
 
     def test_trim_length_bad_parameters(self) -> None:
         test_read = FastqRead(**self.test_kwargs)
 
         # bad start parameters
-        self.assertRaises(
-            ValueError, test_read.trim_length, start=-1, length=len(test_read)
-        )
+        self.assertRaises(ValueError, test_read.trim_length, start=-1, length=len(test_read))
         self.assertEqual(test_read, FastqRead(**self.test_kwargs))
-        self.assertRaises(
-            ValueError, test_read.trim_length, start=0, length=len(test_read)
-        )
+        self.assertRaises(ValueError, test_read.trim_length, start=0, length=len(test_read))
         self.assertEqual(test_read, FastqRead(**self.test_kwargs))
         self.assertRaises(
             ValueError,
@@ -236,24 +216,18 @@ def test_trim_length_bad_parameters(self) -> None:
         # bad parameter combinations
         self.assertRaises(ValueError, test_read.trim_length, start=-1, length=0)
         self.assertEqual(test_read, FastqRead(**self.test_kwargs))
-        self.assertRaises(
-            ValueError, test_read.trim_length, start=2, length=len(test_read)
-        )
+        self.assertRaises(ValueError, test_read.trim_length, start=2, length=len(test_read))
         self.assertEqual(test_read, FastqRead(**self.test_kwargs))
 
     def test_reverse_complement(self) -> None:
         test_read = FastqRead(**self.test_kwargs)
         test_read.reverse_complement()
 
         self.assertEqual(test_read.header, self.test_kwargs["header"])
-        self.assertEqual(
-            test_read.sequence, reverse_complement(self.test_kwargs["sequence"])
-        )
+        self.assertEqual(test_read.sequence, reverse_complement(self.test_kwargs["sequence"]))
         self.assertEqual(test_read.header2, self.test_kwargs["header2"])
         self.assertListEqual(test_read.quality, self.test_quality[::-1])
-        self.assertEqual(
-            test_read.quality_encoding_value, self.test_kwargs["quality_encoding_value"]
-        )
+        self.assertEqual(test_read.quality_encoding_value, self.test_kwargs["quality_encoding_value"])
 
 
 if __name__ == "__main__":

tests/test_util_infer.py

@@ -21,9 +21,7 @@ def test_protein(self):
         self.assertEqual(infer_sequence_type("MDLSALRVEE"), "protein")
 
     def test_protein_iupac(self):
-        self.assertEqual(
-            infer_sequence_type("LIVWZ", report_iupac=True), "protein-iupac"
-        )
+        self.assertEqual(infer_sequence_type("LIVWZ", report_iupac=True), "protein-iupac")
         self.assertEqual(infer_sequence_type("LIVWZ", report_iupac=False), "protein")
 
     def test_lowercase(self):
@@ -50,25 +48,19 @@ def test_dna(self):
             infer_all_sequence_types("ACGT", report_iupac=True),
             ["dna", "dna-iupac", "protein", "protein-iupac"],
         )
-        self.assertListEqual(
-            infer_all_sequence_types("ACGT", report_iupac=False), ["dna", "protein"]
-        )
+        self.assertListEqual(infer_all_sequence_types("ACGT", report_iupac=False), ["dna", "protein"])
         self.assertListEqual(
             infer_all_sequence_types("TTTTT", report_iupac=True),
             ["dna", "dna-iupac", "protein", "protein-iupac"],
         )
-        self.assertListEqual(
-            infer_all_sequence_types("TTTTT", report_iupac=False), ["dna", "protein"]
-        )
+        self.assertListEqual(infer_all_sequence_types("TTTTT", report_iupac=False), ["dna", "protein"])
 
     def test_dna_iupac(self):
         self.assertListEqual(
             infer_all_sequence_types("AWGT", report_iupac=True),
             ["dna-iupac", "protein", "protein-iupac"],
         )
-        self.assertListEqual(
-            infer_all_sequence_types("AWGT", report_iupac=False), ["dna", "protein"]
-        )
+        self.assertListEqual(infer_all_sequence_types("AWGT", report_iupac=False), ["dna", "protein"])
 
     def test_rna(self):
         self.assertListEqual(infer_all_sequence_types("ACGU"), ["rna"])
@@ -79,17 +71,11 @@ def test_protein(self):
             infer_all_sequence_types("LIVW", report_iupac=True),
             ["protein", "protein-iupac"],
         )
-        self.assertListEqual(
-            infer_all_sequence_types("MDLSALRVEE", report_iupac=False), ["protein"]
-        )
+        self.assertListEqual(infer_all_sequence_types("MDLSALRVEE", report_iupac=False), ["protein"])
 
     def test_protein_iupac(self):
-        self.assertListEqual(
-            infer_all_sequence_types("LIVWZ", report_iupac=True), ["protein-iupac"]
-        )
-        self.assertListEqual(
-            infer_all_sequence_types("LIVWZ", report_iupac=False), ["protein"]
-        )
+        self.assertListEqual(infer_all_sequence_types("LIVWZ", report_iupac=True), ["protein-iupac"])
+        self.assertListEqual(infer_all_sequence_types("LIVWZ", report_iupac=False), ["protein"])
 
     def test_lowercase(self):
         self.assertIsNone(infer_all_sequence_types("acgt"))

tests/test_validator_create.py

@@ -64,13 +64,9 @@ def test_create_from_list(self) -> None:
 
         # invalid list arguments
         self.assertRaises(ValueError, create_validator, ["A", "C", "GT"])
-        self.assertRaises(
-            ValueError, create_validator, ["A", "C", "GT"], case_sensitive=False
-        )
+        self.assertRaises(ValueError, create_validator, ["A", "C", "GT"], case_sensitive=False)
         self.assertRaises(ValueError, create_validator, ["A", "C", ""])
-        self.assertRaises(
-            ValueError, create_validator, ["A", "C", ""], case_sensitive=False
-        )
+        self.assertRaises(ValueError, create_validator, ["A", "C", ""], case_sensitive=False)
 
 
 if __name__ == "__main__":