Generalize entities

.github/dependabot.yaml

@@ -0,0 +1,18 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+- package-ecosystem: pip
+  directory: /
+  schedule:
+    interval: monthly
+  groups:
+    production-dependencies:
+      dependency-type: production
+    development-dependencies:
+      dependency-type: development
+- package-ecosystem: github-actions
+  directory: /
+  schedule:
+    interval: monthly

.github/workflows/ci.yaml

@@ -2,13 +2,12 @@ name: CI
 
 permissions:
   contents: read
-  pull-requests: write
 
 on:
   push:
-    branches: [ "main" ]
+    branches: ["main"]
   pull_request:
-    branches: [ "main" ]
+    branches: ["main"]
 
 env:
   UV_FROZEN: true
@@ -33,14 +32,15 @@ jobs:
     needs: format
     strategy:
       matrix:
-        python-version: [ "3.11", "3.12", "3.13", "3.14" ]
+        python-version: ["3.11", "3.12", "3.13", "3.14"]
     steps:
       - uses: actions/checkout@v6
         with:
           submodules: "true"
       - uses: astral-sh/setup-uv@v8.1.0
         with:
           python-version: ${{ matrix.python-version }}
+      - run: uv sync --all-extras
 
       - name: Run tests without cloudpathlib
         run: |
@@ -53,7 +53,7 @@ jobs:
 
       - name: Run tests with cloudpathlib
         run: |
-          uv run --extra cloud pytest \
+          uv run pytest \
             -m "cloud" \
             --junitxml=pytest-cloud.xml \
             --cov-report=xml:coverage.xml \
@@ -68,10 +68,16 @@ jobs:
             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
+      - name: Record PR number
+        if: github.event_name == 'pull_request' && matrix.python-version == env.COVERAGE_PYTHON
+        run: echo "${{ github.event.number }}" > pr-number.txt
+
+      - uses: actions/upload-artifact@v7
+        if: github.event_name == 'pull_request' && matrix.python-version == env.COVERAGE_PYTHON
         with:
-          pytest-xml-coverage-path: ./coverage.xml
-          junitxml-path: ./pytest.xml
+          name: coverage
+          retention-days: 1
+          path: |
+            coverage.xml
+            pytest.xml
+            pr-number.txt

.github/workflows/coverage.yaml

@@ -0,0 +1,33 @@
+name: Coverage report
+
+on:
+  workflow_run:
+    workflows: ["CI"]
+    types: [completed]
+
+permissions:
+  pull-requests: write
+  actions: read
+
+jobs:
+  coverage:
+    if: >-
+      github.event.workflow_run.event == 'pull_request' &&
+      github.event.workflow_run.conclusion == 'success'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/download-artifact@v8
+        with:
+          name: coverage
+          run-id: ${{ github.event.workflow_run.id }}
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+
+      - id: pr
+        run: echo "number=$(cat pr-number.txt)" >> "$GITHUB_OUTPUT"
+
+      - name: Pytest coverage comment
+        uses: MishaKav/pytest-coverage-comment@v1
+        with:
+          issue-number: ${{ steps.pr.outputs.number }}
+          pytest-xml-coverage-path: ./coverage.xml
+          junitxml-path: ./pytest.xml

.github/workflows/docs.yaml

@@ -1,12 +1,12 @@
-name: docs 
+name: docs
 
 on:
   workflow_run:
     workflows: [CI]
     types:
-    - completed
+      - completed
     branches:
-    - main
+      - main
 
 env:
   UV_FROZEN: true
@@ -17,16 +17,14 @@ jobs:
     if: ${{ github.event.workflow_run.conclusion == 'success' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          pyproject-file: pyproject.toml
+        uses: astral-sh/setup-uv@v8.1.0
       - name: Install the project
         run: uv sync --all-extras
       - name: Build docs
         run: uv run pdoc -o docs/ -d google bids2table
-      - uses: actions/upload-pages-artifact@v3
+      - uses: actions/upload-pages-artifact@v5
         with:
           path: docs/
 
@@ -43,4 +41,4 @@ jobs:
       url: ${{ steps.deployment.outputs.page_url }}
     steps:
       - id: deployment
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@v5

.github/workflows/release.yaml

@@ -18,11 +18,9 @@ jobs:
       # IMPORTANT: this permission is mandatory for Trusted Publishing
       id-token: write
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          pyproject-file: pyproject.toml
+        uses: astral-sh/setup-uv@v8.1.0
       - name: Build project
         run: |
           uv sync --no-dev --no-install-project

bids2table/__init__.py

@@ -9,13 +9,16 @@
     "parse_bids_entities",
     "validate_bids_entities",
     "set_bids_schema",
+    "clear_schema_caches",
     "get_bids_schema",
     "get_bids_entity_arrow_schema",
     "format_bids_path",
     "load_bids_metadata",
     "cloudpathlib_is_available",
+    "pybids",
 ]
 
+from . import pybids
 from ._entities import (
     format_bids_path,
     get_bids_entity_arrow_schema,
@@ -26,6 +29,7 @@
 )
 from ._indexing import (
     batch_index_dataset,
+    clear_schema_caches,
     find_bids_datasets,
     get_arrow_schema,
     get_column_names,

bids2table/__main__.py

@@ -31,7 +31,17 @@ def main():
         nargs="+",
         default=None,
         help="List of subject names or glob patterns to only include in the index.  "
-        "Only applies when indexing a single dataset.",
+        "Deprecated; use --filter instead.",
+    )
+    parser_index.add_argument(
+        "--filter",
+        "-f",
+        metavar="ENTITY=PATTERN",
+        type=str,
+        action="append",
+        default=None,
+        help="Filter indexed files by entity value (e.g. -f sub=sub-0* -f task=rest). "
+        "Can be specified multiple times.",
     )
     parser_index.add_argument(
         "--workers",
@@ -114,10 +124,29 @@ def _index_command(args: argparse.Namespace):
         else:
             root.append(path)
 
+    # Build filters dict from --filter args
+    filters: dict[str, str | list[str]] | None = None
+    if args.filter:
+        filters = {}
+        for item in args.filter:
+            parts = item.split("=", maxsplit=1)
+            if len(parts) == 2:
+                filters[parts[0]] = parts[1]
+            else:
+                _logger.warning(
+                    f"Ignoring malformed filter: '{item}' (expected ENTITY=PATTERN)"
+                )
+
+    # Merge deprecated --subjects into filters
+    if args.subjects:
+        if filters is None:
+            filters = {}
+        filters.setdefault("sub", args.subjects)
+
     if len(root) == 1:
         table = b2t2.index_dataset(
             root[0],
-            include_subjects=args.subjects,
+            filters=filters,
             show_progress=not args.no_progress,
         )
         pq.write_table(table, args.output)
@@ -135,6 +164,7 @@ def _index_command(args: argparse.Namespace):
                 max_workers=max_workers,
                 executor_cls=executor_cls,
                 show_progress=not args.no_progress,
+                filters=filters,
             ):
                 writer.write_table(table)