resolve mypy issues, update gitlab ci

Author: drickett

.github/workflows/python.yml

@@ -22,7 +22,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11.0-beta.5 - 3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
 
     steps:
       - uses: actions/checkout@v3
@@ -33,10 +33,10 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: Install Hatch
-        run: pip install --upgrade hatch
+        run: pip install uv
 
       - name: Run tests
-        run: hatch run ci-report
+        run: uv run pytest
 
       - name: Upload coverage data
         uses: actions/upload-artifact@v3

.gitlab-ci.yml

@@ -1,12 +1,13 @@
 ---
 variables:
+  JUNIT_TEST_REPORT: test_report_${CI_COMMIT_SHORT_SHA}.html
+  COVERAGE_TEST_REPORT: coverage_report_${CI_COMMIT_SHORT_SHA}
   PYTHON_VERSION:
-    value: "3.8"
+    value: "3.10"
     options:
-      - "3.8"
-      - "3.9"
       - "3.10"
       - "3.11"
+      - "3.12"
     description: Python version to use
 
 stages:
@@ -26,13 +27,21 @@ validate-yaml:
         - "*.yml"
         - "*.yaml"
 
-Check-For-Black:
+.python:
+  image:
+    name: python:${PYTHON_VERSION}-slim
+    pull_policy: if-not-present
+  before_script:
+    - pip install uv
+  allow_failure: false
+
+Code-Check:
+  extends: .python
   stage: validate
-  image: black
   script:
     - cd $CI_PROJECT_DIR
-    - black --check src/
-  allow_failure: false
+    - uv run mypy --check .
+    - uv run ruff check .
   rules:
     - if: $CI_JOB_MANUAL
     - if: $CI_PIPELINE_SOURCE == 'merge_request_event'
@@ -42,15 +51,14 @@ Check-For-Black:
 
 Check-HLA-Modified-Dates:
   stage: validate
-  image: python:${PYTHON_VERSION}-slim
-  before_script:
+  extends: .python
+  variables:
+    PYTHONPATH: "${CI_BUILDS_DIR}/src"
+  script:
     - apt update
     - apt install git-restore-mtime -y --no-install-recommends
-    - pip install typer
-  script:
     - cd $CI_PROJECT_DIR
-    - python tools/check_date_modified.py check-dates
-  allow_failure: false
+    - uv run tools/check_date_modified.py check-dates
   rules:
     - if: $CI_JOB_MANUAL
     - if: $CI_PIPELINE_SOURCE == 'merge_request_event'
@@ -59,23 +67,31 @@ Check-HLA-Modified-Dates:
         - src/**/*.mtime
 
 Unit-Tests:
-  image: python:${PYTHON_VERSION}-slim
-  before_script:
-    - pip install hatch
+  extends: .python
+  stage: test
   script:
-    - hatch env run --env test ci-report
+    - cd $CI_PROJECT_DIR
+    - uv run pytest
+      -vra
+      --html=${JUNIT_TEST_REPORT}
+      --self-contained-html
+      --cov-report=html:${COVERAGE_TEST_REPORT}
+      --cov-report=term
+      --junitxml=pytest.xml
   parallel:
     matrix:
       - PYTHON_VERSION:
-          - "3.8"
-          - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
   coverage: '/^TOTAL.+?(\d+\%)$/'
   interruptible: true
   artifacts:
     reports:
-      junit: unit_test.xml
+      junit: pytest.xml
       coverage_report:
         coverage_format: cobertura
         path: coverage.xml
+    paths:
+      - ${COVERAGE_TEST_REPORT}/*
+      - ${JUNIT_TEST_REPORT}

mypy.ini

@@ -37,6 +37,8 @@ dependencies = [
 dev = [
   "mypy>=1.15.0",
   "mypy-extensions>=1.0.0",
+  "pandas>=2.2.3",
+  "pandas-stubs>=2.2.3.241126",
   "pre-commit>=4.1.0",
   "pytest>=8.3.5",
   "pytest-cov>=6.0.0",
@@ -82,7 +84,7 @@ package = true
 [tool.pytest.ini_options]
 pythonpath = "src"
 minversion = "6.0"
-addopts = "-ra -n 4 --cov --cov-report xml --strict-markers -m 'not slow'"
+addopts = "-ra -n 4 --cov --cov-report term --cov-report xml --strict-markers -m 'not slow'"
 testpaths = ["tests"]
 markers = [
   "integration: Run integration tests",
@@ -123,3 +125,7 @@ ignore = ["E712"]
 
 [tool.pydocstyle]
 match = "src/**/*.py"
+
+[tool.mypy]
+plugins = ["numpy.typing.mypy_plugin"]
+ignore_missing_imports = true

pyproject.toml

@@ -552,7 +552,9 @@ def interpret(
             seq = np.concatenate((exon2_bin, exon3_bin))
         else:
             seq = self.pad_short(
-                self.nuc2bin(entry.seq), samp, hla_std=self.hla_stds[0]
+                self.nuc2bin(entry.seq),  # type: ignore
+                samp,
+                hla_std=self.hla_stds[0],
             )
             exon2 = self.bin2nuc(seq[: EasyHLA.EXON2_LENGTH])
             intron = self.bin2nuc(seq[EasyHLA.EXON2_LENGTH : -EasyHLA.EXON3_LENGTH])
@@ -617,7 +619,7 @@ def interpret(
             alleles_all_str=alleles_all_str,
             ambig=int(ambig),
             homozygous=int(homozygous),
-            mismatch_count=f"{mismatch_count}",
+            mismatch_count=mismatch_count,
             mismatches=f"{mismatches}",
             exon2=exon2.upper(),
             intron=intron.upper(),

src/easyhla/easyhla.py

@@ -55,8 +55,8 @@ def main(
 
     easyhla.run(
         easyhla.letter,
-        sequence_file,
-        output_file,
+        sequence_file.as_posix(),
+        output_file.as_posix(),
         threshold=mismatch_threshold,
         to_stdout=print_to_stdout,
     )

src/easyhla/entrypoint.py

@@ -30,8 +30,8 @@ def make_comparison(easyhla: EasyHLA, ref_seq: str, test_seq: str) -> str:
             side_is_short = "test"
         elif len(ref) < len(test):
             side_is_short = "ref"
-        return easyhla.bin2nuc(masked_seq) + f" [{side_is_short} is short]"
-    return easyhla.bin2nuc(masked_seq)
+        return easyhla.bin2nuc(masked_seq) + f" [{side_is_short} is short]"  # type: ignore
+    return easyhla.bin2nuc(masked_seq)  # type: ignore
 
 
 def compare_ref_vs_test(
@@ -60,9 +60,9 @@ def compare_ref_vs_test(
 
     column_names = reference_file[0].strip().split(",")
 
-    assert len(reference_file) == len(
-        test_output_file
-    ), "Size of test output does not match reference file!"
+    assert len(reference_file) == len(test_output_file), (
+        "Size of test output does not match reference file!"
+    )
 
     for row_num, (ref, test) in enumerate(zip(reference_file, test_output_file)):
         try:
@@ -86,19 +86,19 @@ def compare_ref_vs_test(
 
                 _row_num = row_num + 1 + int(skip_preamble[1])
                 # Check that there is no strippable whitespace when there shouldn't be.
-                assert (
-                    _test == _test.strip()
-                ), f"Whitespace detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
-                assert (
-                    _ref == _ref.strip()
-                ), f"[REFERENCE FILE] Whitespace detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
-
-                assert len(_ref.strip()) == len(
-                    _test.strip()
-                ), f"Length mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
-                assert (
-                    _ref.strip() == _test.strip()
-                ), f"Content mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                assert _test == _test.strip(), (
+                    f"Whitespace detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                )
+                assert _ref == _ref.strip(), (
+                    f"[REFERENCE FILE] Whitespace detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                )
+
+                assert len(_ref.strip()) == len(_test.strip()), (
+                    f"Length mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                )
+                assert _ref.strip() == _test.strip(), (
+                    f"Content mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                )
 
                 if row_num > 0 and column_names[col_num] in [
                     "ALLELES_CLEAN",
@@ -107,7 +107,9 @@ def compare_ref_vs_test(
                     assert (
                         set(_ref.strip().split(";")) ^ set(_test.strip().split(";"))
                         == set()
-                    ), f"Order mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                    ), (
+                        f"Order mismatch detected at row {_row_num}, column {col_num} ('{column_names[col_num]}')"
+                    )
         except AssertionError as e:
             print("REF >>>", ref)
             print("OUT >>>", test)

tests/conftest.py

@@ -1,7 +1,7 @@
 import os
 from datetime import datetime
 from pathlib import Path
-from typing import List, Tuple
+from typing import Dict, List, Tuple
 
 import numpy as np
 import pytest
@@ -648,7 +648,7 @@ def test_get_matching_stds(
         hla_stds: List[HLAStandard],
         exp_result: List[HLAStandardMatch],
     ):
-        result = easyhla.get_matching_stds(seq=sequence, hla_stds=hla_stds)
+        result = easyhla.get_matching_stds(seq=sequence, hla_stds=hla_stds)  # type: ignore
         print(result)
         assert result == exp_result
 
@@ -1034,16 +1034,16 @@ def test_combine_stds(
         sequence: List[int],
         threshold: int,
         matching_standards: List[HLAStandardMatch],
-        exp_result: List[int],
+        exp_result: Dict[int, List[int]],
     ):
         result = easyhla.combine_stds(
             matching_stds=matching_standards,
             seq=sequence,
             max_mismatch_threshold=threshold,
         )
         print(sorted(result.items()))
-        print([(k, v) for k, v in exp_result.items()])
-        assert sorted(result.items()) == [(k, v) for k, v in exp_result.items()]
+        print((k, v) for k, v in exp_result.items())
+        assert sorted(result.items()) == list((k, v) for k, v in exp_result.items())  # noqa: C400
 
     @pytest.mark.parametrize(
         "best_matches, exp_homozygous, exp_alleles",

tests/easyhla_test.py

@@ -23,7 +23,7 @@
 
 import typer
 
-from src.easyhla.easyhla import DATE_FORMAT
+from easyhla.easyhla import DATE_FORMAT
 
 app = typer.Typer()
 

tools/check_date_modified.py

@@ -34,10 +34,9 @@
 
 # 0-1, percentage of input samples that should be suffixed '_exon#'
 # HLA Type A has to include the intron
+perc_pure_exon: float = 0.0
 if HLA_TYPE.upper() == "A":
-    perc_pure_exon: float = 0.0
-else:
-    perc_pure_exon: float = 0.0
+    perc_pure_exon = 0.0
 
 sample_input_df = df[[ENUM_IDENTIFIER[HLA_TYPE], "EXON2", "INTRON", "EXON3"]]
 sample_input_seqs: Dict[str, str] = {}