try to bring in trackhubs

.gitattributes

@@ -0,0 +1,25 @@
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true
+
+# Binary files
+*.gz binary
+*.bam binary
+*.bai binary
+*.csi binary
+*.vcf.gz binary
+*.tbi binary
+*.dict binary
+tests/data/fixtures/** linguist-generated
+tests/data/fixtures/**/*.bam binary
+tests/data/fixtures/**/*.bam.bai binary
+tests/data/fixtures/**/*.bam.csi binary
+tests/data/fixtures/**/*.vcf.gz binary
+tests/data/fixtures/**/*.vcf.gz.tbi binary
+tests/data/fixtures/**/*.g.vcf.gz binary
+tests/data/fixtures/**/*.g.vcf.gz.tbi binary
+tests/data/fixtures/**/*.tar binary
+tests/data/fixtures/**/*.fa.gz binary
+tests/data/fixtures/**/*.d4 binary
+tests/data/fixtures/**/*.zarr/** binary
+tests/data/fixtures/**/*.tdb binary
+tests/data/fixtures/**/*.tdb.gz binary

.github/workflows/notify-docs.yml

@@ -0,0 +1,24 @@
+name: Notify docs site
+
+# When the docs sources under website/ change on main, tell the
+# snparcher/snparcher.github.io repo to rebuild and redeploy the site.
+on:
+  push:
+    branches: [main]
+    paths:
+      - "website/**"
+  workflow_dispatch:
+
+jobs:
+  notify:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger snparcher.github.io rebuild
+        env:
+          # Fine-grained PAT (or GitHub App token) with Contents: write
+          # on snparcher/snparcher.github.io. Store as a repo secret.
+          GH_TOKEN: ${{ secrets.DOCS_DEPLOY_TOKEN }}
+        run: |
+          gh api --method POST \
+            repos/snparcher/snparcher.github.io/dispatches \
+            -f event_type=docs-updated

.github/workflows/test.yaml

@@ -0,0 +1,161 @@
+name: Tests
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "**/Snakefile"
+      - "**/*.smk"
+      - "**/*.py"
+      - "workflow/**/*.yml"
+      - "workflow/**/*.yaml"
+      - "pyproject.toml"
+      - ".github/workflows/*"
+  pull_request:
+    paths:
+      - "**/Snakefile"
+      - "**/*.smk"
+      - "**/*.py"
+      - "workflow/**/*.yml"
+      - "workflow/**/*.yaml"
+      - "pyproject.toml"
+      - ".github/workflows/*"
+
+jobs:
+  dry-run-tests:
+    name: dry-run (${{ matrix.group }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - group: core
+            filter: "not metadata and not postprocess and not qc"
+          - group: metadata
+            filter: "metadata and not postprocess and not qc"
+          - group: postprocess
+            filter: "postprocess"
+          - group: qc
+            filter: "qc"
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: prefix-dev/setup-pixi@v0.9.3
+        with:
+          cache: true
+          environments: dev
+
+      - name: Run dry-run tests
+        run: pixi run -e dev pytest -v tests/tests.py --dry-run-only -k "${{ matrix.filter }}"
+
+  build-conda-envs:
+    name: build conda envs
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: prefix-dev/setup-pixi@v0.9.3
+        with:
+          cache: true
+          environments: dev
+
+      - name: Cache conda envs
+        id: conda-cache
+        uses: actions/cache@v4
+        with:
+          path: .snakemake/conda
+          key: conda-envs-${{ hashFiles('workflow/**/*.yml', 'workflow/**/*.yaml', 'pyproject.toml') }}
+
+      - name: Create conda envs
+        if: steps.conda-cache.outputs.cache-hit != 'true'
+        run: pixi run -e dev setup-test-envs
+
+  unit-tests:
+    name: unit (${{ matrix.group }})
+    needs: build-conda-envs
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        group: [1, 2, 3, 4]
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: prefix-dev/setup-pixi@v0.9.3
+        with:
+          cache: true
+          environments: dev
+
+      - name: Restore conda envs
+        uses: actions/cache/restore@v4
+        with:
+          path: .snakemake/conda
+          key: conda-envs-${{ hashFiles('workflow/**/*.yml', 'workflow/**/*.yaml', 'pyproject.toml') }}
+          fail-on-cache-miss: true
+
+      - name: Run unit tests
+        env:
+          TMPDIR: ${{ runner.temp }}
+        run: |
+          pixi run -e dev pytest -v tests/unit_tests.py \
+            --conda-prefix $(pwd)/.snakemake/conda \
+            --splits 4 --group ${{ matrix.group }}
+
+  full-run-tests:
+    name: full-run (${{ matrix.group }})
+    needs: build-conda-envs
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - group: core-1
+            filter: "not metadata and not postprocess and not qc"
+            split_group: 1
+          - group: core-2
+            filter: "not metadata and not postprocess and not qc"
+            split_group: 2
+          - group: core-3
+            filter: "not metadata and not postprocess and not qc"
+            split_group: 3
+          - group: qc
+            filter: "qc"
+            split_group: 0
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: prefix-dev/setup-pixi@v0.9.3
+        with:
+          cache: true
+          environments: dev
+
+      - name: Restore conda envs
+        uses: actions/cache/restore@v4
+        with:
+          path: .snakemake/conda
+          key: conda-envs-${{ hashFiles('workflow/**/*.yml', 'workflow/**/*.yaml', 'pyproject.toml') }}
+          fail-on-cache-miss: true
+
+      - name: Run full tests
+        env:
+          TMPDIR: ${{ runner.temp }}
+        run: |
+          SPLIT_ARGS=""
+          if [ "${{ matrix.split_group }}" != "0" ]; then
+            SPLIT_ARGS="--splits 3 --group ${{ matrix.split_group }}"
+          fi
+          pixi run -e dev pytest -v tests/tests.py \
+            --conda-prefix $(pwd)/.snakemake/conda \
+            -m full_run \
+            -k "${{ matrix.filter }}" \
+            $SPLIT_ARGS
+
+      - name: Upload QC dashboard
+        if: matrix.group == 'qc'
+        uses: actions/upload-artifact@v4
+        with:
+          name: qc-dashboard
+          path: test-artifacts/
+          retention-days: 5
+          if-no-files-found: ignore

.gitignore

@@ -1,44 +1,47 @@
+# OS files
 .DS_Store
-data_preparation/
+example/results
+example/logs
+example/.snakemake
+example/benchmarks
+# Editor settings
+.vscode/
+
+# Codex app
+.codex/
+.tmp/
+
+# Python cache/build artifacts
+__pycache__/
+*.egg-info/
+
+# Conda / Pixi environments
+.conda-envs/
+tests/.conda-envs/
+.pixi/
+!.pixi/config.toml
+
+# Snakemake + workflow outputs
 .snakemake*
-template_slurm.sh
-slurm_logs/*
-# indexing and creating a sequence dictionary gets done within pipeline
-data/zebraFinch/genome/*.sa
-data/zebraFinch/genome/*.pac
-data/zebraFinch/genome/*.bwt
-data/zebraFinch/genome/*.ann
-data/zebraFinch/genome/*.amb
-data/zebraFinch/genome/*.fai
-data/zebraFinch/genome/*.dict
-rules/.snakemake
-data/BHduck/genome/*.sa
-data/BHduck/genome/*.pac
-data/BHduck/genome/*.bwt
-data/BHduck/genome/*.ann
-data/BHduck/genome/*.amb
-data/BHduck/genome/*.fai
-data/BHduck/genome/*.dict
-/data/
-fastp.*
-intervalFiles/
-out
-err
-__pycache__
-log/
-fastq2bam/
-intervalFiles/
-freebayes/
-gatk/
-logs/
-*_dryrun.txt
 results/
+logs/
+benchmarks/
 tmp/
-.test/ecoli/benchmarks/
-.test/ecoli/logs/
-.test/ecoli/results/
-.test/ecoli/data/
+slurm_logs/
+*_dryrun.txt
+
+# Test outputs
+.test/*/benchmarks/
+.test/*/logs/
+.test/*/results/
+.test/*/.snakemake/
+.test/trackhub/*.sizes
+.test/trackhub/out.log
+
+# Licenses and secrets
 *.lic
-.test/ci/results
-.test/ci/benchmarks
-.test/ci/logs
+
+# MkDocs build output
+site/
+scratch
+*.bak