Merge branch 'main' into rf/schemaadapter

Author: effigies

.github/workflows/ci.yaml

@@ -1,27 +1,28 @@
 name: CI
 
+permissions:
+  contents: read
+  pull-requests: write
+
 on:
   push:
-    branches: ["main"]
+    branches: [ "main" ]
   pull_request:
-    branches: ["main"]
+    branches: [ "main" ]
 
 env:
   UV_FROZEN: true
+  COVERAGE_PYTHON: "3.12"
 
 jobs:
   format:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           submodules: "true"
-      - name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          pyproject-file: pyproject.toml
-      - name: Install the project
-        run: uv sync --all-extras
+      - uses: astral-sh/setup-uv@v8.1.0
+      - run: uv sync --all-extras
       - name: Check quality
         run: |
           uv run ruff check bids2table tests
@@ -32,26 +33,45 @@ jobs:
     needs: format
     strategy:
       matrix:
-        python-version: ["3.11", "3.12", "3.13"]
+        python-version: [ "3.11", "3.12", "3.13", "3.14" ]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           submodules: "true"
-      - name: Install uv with python version
-        uses: astral-sh/setup-uv@v6
+      - uses: astral-sh/setup-uv@v8.1.0
         with:
           python-version: ${{ matrix.python-version }}
 
       - name: Run tests without cloudpathlib
         run: |
-          uv run pytest tests
+          uv run pytest \
+            -m "not cloud" \
+            --junitxml=pytest-cloudless.xml \
+            --cov-report=xml:coverage.xml \
+            --cov bids2table \
+            tests
+
       - name: Run tests with cloudpathlib
         run: |
-          uv run --all-extras pytest \
-            --junitxml=pytest.xml \
+          uv run --extra cloud pytest \
+            -m "cloud" \
+            --junitxml=pytest-cloud.xml \
             --cov-report=xml:coverage.xml \
-            --cov=bids2table tests
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+            --cov=bids2table \
+            --cov-append \
+            tests
+
+      - name: Merge JUnit XML reports
+        run: |
+          uvx junitparser merge \
+            pytest-cloudless.xml \
+            pytest-cloud.xml \
+            pytest.xml
+
+      - name: Pytest coverage comment
+        if: github.event_name == 'pull_request' && matrix.python-version ==
+          env.COVERAGE_PYTHON
+        uses: MishaKav/pytest-coverage-comment@v1
         with:
-          token: ${{ secrets.CODECOV_TOKEN }}
+          pytest-xml-coverage-path: ./coverage.xml
+          junitxml-path: ./pytest.xml

pyproject.toml

@@ -68,3 +68,4 @@ lint.extend-select = ["I"]
 [tool.pytest.ini_options]
 log_cli = true
 log_cli_level = "INFO"
+markers = ["cloud: Tests requiring cloud group dependencies"]

tests/test_indexing.py

@@ -9,8 +9,6 @@
 from pytest import LogCaptureFixture
 
 import bids2table._indexing as indexing
-from bids2table._indexing import index_dataset
-from bids2table._pathlib import cloudpathlib_is_available
 
 BIDS_EXAMPLES = Path(__file__).parents[1] / "bids-examples"
 
@@ -55,9 +53,7 @@ def test_find_bids_datasets():
     assert datasets_no_derivatives == expected_datasets_no_derivatives
 
 
-@pytest.mark.skipif(
-    not cloudpathlib_is_available(), reason="cloudpathlib not installed"
-)
+@pytest.mark.cloud
 def test_find_bids_datasets_s3():
     root = "s3://openneuro.org"
     datasets = list(islice(indexing.find_bids_datasets(root, maxdepth=2), 10))
@@ -83,9 +79,7 @@ def test_index_dataset(root: str, expected_count: int):
     assert len(table) == expected_count
 
 
-@pytest.mark.skipif(
-    not cloudpathlib_is_available(), reason="cloudpathlib not installed"
-)
+@pytest.mark.cloud
 def test_index_dataset_s3():
     root = "s3://openneuro.org/ds000102"
     expected_count = 130
@@ -263,7 +257,7 @@ def test_index_dataset_accepts_schema_kwarg(tmp_path):
 
     ns = deepcopy(bidsschematools.schema.load_schema())
     ns.objects.entities.subject["description"] = "Modified once"
-    table = index_dataset(tmp_path / "ds", schema=ns, max_workers=0)
+    table = indexing.index_dataset(tmp_path / "ds", schema=ns, max_workers=0)
     assert table.num_rows == 1
     assert "sub" in table.column_names
     assert table.schema.field("sub").metadata[b"description"] == b"Modified once"
@@ -281,22 +275,20 @@ def test_index_dataset_propagates_schema_to_workers(tmp_path):
 
     ns = deepcopy(bidsschematools.schema.load_schema())
     ns.objects.entities.subject["description"] = "Modified again"
-    table = index_dataset(tmp_path / "ds", schema=ns, max_workers=2, chunksize=1)
+    table = indexing.index_dataset(tmp_path / "ds", schema=ns, max_workers=2, chunksize=1)
     assert table.num_rows == 1
     assert table.schema.field("sub").metadata[b"description"] == b"Modified again"
 
 
 def test_batch_index_dataset_accepts_schema_kwarg(tmp_path):
-    from bids2table._indexing import batch_index_dataset
-
     ds1 = tmp_path / "a"
     (ds1 / "sub-A01" / "anat").mkdir(parents=True)
     (ds1 / "dataset_description.json").write_text('{"Name": "a"}')
     (ds1 / "sub-A01" / "anat" / "sub-A01_T1w.nii.gz").touch()
 
     ns = deepcopy(bidsschematools.schema.load_schema())
     ns.objects.entities.subject["description"] = "And again"
-    tables = list(batch_index_dataset([ds1], schema=ns))
+    tables = list(indexing.batch_index_dataset([ds1], schema=ns))
     assert len(tables) == 1
     assert tables[0].num_rows == 1
     assert tables[0].schema.field("sub").metadata[b"description"] == b"And again"

tests/test_metadata.py

@@ -3,7 +3,6 @@
 import pytest
 
 from bids2table._metadata import load_bids_metadata
-from bids2table._pathlib import cloudpathlib_is_available
 
 BIDS_EXAMPLES = Path(__file__).parents[1] / "bids-examples"
 
@@ -24,9 +23,7 @@ def test_load_bids_metadata(inherit: bool):
     assert metadata == expected_metadata
 
 
-@pytest.mark.skipif(
-    not cloudpathlib_is_available(), reason="cloudpathlib not installed"
-)
+@pytest.mark.cloud
 def test_load_bids_metadata_s3():
     path = (
         "s3://openneuro.org/ds000102/sub-01/func/sub-01_task-flanker_run-1_bold.nii.gz"