Use pooch

.flake8

@@ -17,6 +17,7 @@ ignore =
 	D,
 	E,
 	F,
+	RST210,
 	W503
 per-file-ignores =
 rst-roles =

.github/workflows/main.yml

@@ -7,7 +7,7 @@ on:
   pull_request:
 
 env:
-  RAVEN_TESTING_DATA_BRANCH: master
+  RAVEN_TESTDATA_BRANCH: v2025.6.12
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -70,27 +70,12 @@ jobs:
       - name: Harden Runner
         uses: step-security/harden-runner@6c439dc8bdf85cadbbce9ed30d1c7b959517bc49 # v2.12.2
         with:
-          egress-policy: block
-          allowed-endpoints: >
-            api.github.com:443
-            azure.archive.ubuntu.com:80
-            coveralls.io:443
-            esm.ubuntu.com:443
-            files.pythonhosted.org:443
-            github.com:443
-            motd.ubuntu.com:443
-            objects.githubusercontent.com:443
-            packages.microsoft.com:443
-            pavics.ouranos.ca:443
-            pypi.org:443
-            raw.githubusercontent.com:443
-            test.opendap.org:80
-
+          disable-sudo: false
+          egress-policy: audit
       - name: Checkout Repository
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           persist-credentials: false
-
       - name: Set up Python${{ matrix.python-version }}
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
@@ -117,14 +102,32 @@ jobs:
       - name: Install CI libraries
         run: |
           python3 -m pip install --require-hashes -r CI/requirements_ci.txt
+
+      - name: Environment caching (macOS)
+        if: matrix.os == 'macos-latest'
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        with:
+          path: |
+            .tox
+            ~/Library/Caches/raven-testdata
+          key: ${{ hashFiles('src/ravenpy/testing/registry.txt') }}-${{ env.RAVEN_TESTDATA_BRANCH }}-${{ matrix.os }}
+      - name: Environment caching (Ubuntu)
+        if: matrix.os == 'ubuntu-latest'
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        with:
+          path: |
+            .tox
+            ~/.cache/raven-testdata
+          key: ${{ hashFiles('src/ravenpy/testing/registry.txt') }}-${{ env.RAVEN_TESTDATA_BRANCH }}-${{ matrix.os }}
+
       - name: Test with tox and report coverage
         run: |
           if [ "${{ matrix.tox-env }}" != "false" ]; then
-            python3 -m tox -e ${{ matrix.tox-env }}
+            python3 -m tox -e ${{ matrix.tox-env }}-prefetch
           elif [ "${{ matrix.python-version }}" != "3.13" ]; then
-            python3 -m tox -e py${{ matrix.python-version }}-coverage
+            python3 -m tox -e py${{ matrix.python-version }}-prefetch-coverage
           else
-            python3 -m tox -e py${{ matrix.python-version }}
+            python3 -m tox -e py${{ matrix.python-version }}-prefetch
           fi
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -151,18 +154,7 @@ jobs:
         uses: step-security/harden-runner@6c439dc8bdf85cadbbce9ed30d1c7b959517bc49 # v2.12.2
         with:
           disable-sudo: true
-          egress-policy: block
-          allowed-endpoints: >
-            api.github.com:443
-            conda.anaconda.org:443
-            coveralls.io:443
-            files.pythonhosted.org:443
-            github.com:443
-            objects.githubusercontent.com:443
-            pavics.ouranos.ca:443
-            pypi.org:443
-            raw.githubusercontent.com:443
-            test.opendap.org:80
+          egress-policy: audit
       - name: Checkout Repository
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
@@ -187,6 +179,25 @@ jobs:
         run: |
           micromamba list
           python -m pip check || true
+      - name: Cache test data (macOS)
+        if: matrix.os == 'macos-latest'
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        with:
+          path: |
+            ~/Library/Caches/raven-testdata
+          key: ${{ hashFiles('src/ravenpy/testing/registry.txt') }}-${{ env.RAVEN_TESTDATA_BRANCH }}-conda-${{ matrix.os }}
+      - name: Cache test data (Ubuntu)
+        if: matrix.os == 'ubuntu-latest'
+        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        with:
+          path: |
+            ~/.cache/raven-testdata
+          key: ${{ hashFiles('src/ravenpy/testing/registry.txt') }}-${{ env.RAVEN_TESTDATA_BRANCH }}-conda-${{ matrix.os }}
+
+      - name: Prefetch RavenPy test data
+        run: |
+          python -c "import ravenpy.testing.utils as rtu; rtu.populate_testing_data()"
+
       - name: Test RavenPy
         run: |
           python -m pytest --numprocesses=logical --cov=src/ravenpy --cov-report=lcov
@@ -207,11 +218,7 @@ jobs:
         uses: step-security/harden-runner@6c439dc8bdf85cadbbce9ed30d1c7b959517bc49 # v2.12.2
         with:
           disable-sudo: true
-          egress-policy: block
-          allowed-endpoints: >
-            coveralls.io:443
-            github.com:443
-            objects.githubusercontent.com:443
+          egress-policy: audit
       - name: Coveralls Finished
         uses: coverallsapp/github-action@648a8eb78e6d50909eff900e4ec85cab4524a45b # v2.3.6
         with:

.github/workflows/testdata-version.yml

@@ -0,0 +1,95 @@
+name: Verify Testing Data
+
+on:
+  pull_request:
+    types:
+      - opened
+      - reopened
+      - synchronize
+    paths:
+      - .github/workflows/main.yml
+
+permissions:
+  contents: read
+
+jobs:
+  use-latest-tag:
+    name: Check Latest raven-testdata Tag
+    runs-on: ubuntu-latest
+    if: |
+     (github.event.pull_request.head.repo.full_name == github.event.pull_request.base.repo.full_name)
+    permissions:
+      pull-requests: write
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
+        with:
+          disable-sudo: true
+          egress-policy: block
+          allowed-endpoints: >
+            api.github.com:443
+            github.com:443
+      - name: Checkout Repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          persist-credentials: false
+      - name: Find raven-testdata Tag and CI Testing Branch
+        run: |
+          RAVEN_TESTDATA_TAG="$( \
+          git -c 'versionsort.suffix=-' \
+          ls-remote --exit-code --refs --sort='version:refname' --tags https://github.com/Ouranosinc/raven-testdata '*.*.*' \
+          | tail --lines=1 \
+          | cut --delimiter='/' --fields=3)"
+          echo "RAVEN_TESTDATA_TAG=${RAVEN_TESTDATA_TAG}" >> $GITHUB_ENV
+          RAVEN_TESTDATA_BRANCH="$(grep -E "RAVEN_TESTDATA_BRANCH" .github/workflows/main.yml | cut -d ' ' -f4)"
+          echo "RAVEN_TESTDATA_BRANCH=${RAVEN_TESTDATA_BRANCH}" >> $GITHUB_ENV
+      - name: Report Versions Found
+        run: |
+          echo "Latest raven-testdata tag: ${RAVEN_TESTDATA_TAG}"
+          echo "Tag for raven-testdata in CI: ${RAVEN_TESTDATA_BRANCH}"
+        env:
+          RAVEN_TESTDATA_TAG: ${{ env.RAVEN_TESTDATA_TAG }}
+          RAVEN_TESTDATA_BRANCH: ${{ env.RAVEN_TESTDATA_BRANCH }}
+      - name: Find Comment
+        uses: peter-evans/find-comment@3eae4d37986fb5a8592848f6a574fdf654e61f9e # v3.1.0
+        id: fc
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          comment-author: 'github-actions[bot]'
+          body-includes: It appears that this Pull Request modifies the `main.yml` workflow.
+      - name: Compare Versions
+        if: ${{( env.RAVEN_TESTDATA_TAG != env.RAVEN_TESTDATA_BRANCH )}}
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            core.setFailed('Configured `raven-testdata` tag is not `latest`.')
+      - name: Update Failure Comment
+        if: ${{ failure() }}
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
+        with:
+          comment-id: ${{ steps.fc.outputs.comment-id }}
+          issue-number: ${{ github.event.pull_request.number }}
+          body: |
+            > [!WARNING]
+            > It appears that this Pull Request modifies the `main.yml` workflow.
+
+            On inspection, it seems that the `RAVEN_TESTDATA_BRANCH` environment variable is set to a tag that is not the latest in the `Ouranosinc/raven-testdata` repository.
+
+            This value must match the most recent tag (`${{ env.RAVEN_TESTDATA_TAG }}`) in order to merge this Pull Request.
+
+            If this PR depends on changes in a new testing dataset branch, be sure to tag a new version of `Ouranosinc/raven-testdata` once your changes have been merged to its `main` branch.
+          edit-mode: replace
+      - name: Update Success Comment
+        if: ${{ success() }}
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043 # v4.0.0
+        with:
+          comment-id: ${{ steps.fc.outputs.comment-id }}
+          issue-number: ${{ github.event.pull_request.number }}
+          body: |
+            > [!NOTE]
+            > It appears that this Pull Request modifies the `main.yml` workflow.
+
+            On inspection, the `RAVEN_TESTDATA_BRANCH` environment variable is set to the most recent tag (`${{ env.RAVEN_TESTDATA_TAG }}`).
+
+            No further action is required.
+          edit-mode: replace

.pre-commit-config.yaml

@@ -7,6 +7,7 @@ repos:
     hooks:
       - id: pyupgrade
         args: [ '--py39-plus' ]
+        exclude: ^tests/conftest\.py$
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0
     hooks:
@@ -52,7 +53,7 @@ repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.12.2
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: [ '--fix' ]
       # - id: ruff-format
   - repo: https://github.com/pycqa/flake8
@@ -74,11 +75,11 @@ repos:
     hooks:
       - id: nbqa-pyupgrade
         args: [ '--py39-plus' ]
-        additional_dependencies: [ 'pyupgrade==3.19.1' ]
+        additional_dependencies: [ 'pyupgrade==3.20.0' ]
       - id: nbqa-black
         additional_dependencies: [ 'black==25.1.0' ]
       - id: nbqa-isort
-        additional_dependencies: [ 'isort==6.0.0' ]
+        additional_dependencies: [ 'isort==6.0.1' ]
   - repo: https://github.com/kynan/nbstripout
     rev: 0.8.1
     hooks:

CHANGELOG.rst

@@ -7,7 +7,15 @@ v0.18.3 (unreleased)
 
 New features
 ^^^^^^^^^^^^
-* Added `parsers.parse_rv` to extract a Command value from an RV file.
+* Added `parsers.parse_rv` to extract a Command value from an RV file. (PR #503)
+* New module `ravenpy.testing` has been added to provide utility functions and support for testing and testing data management. (PR #513)
+
+Breaking changes
+^^^^^^^^^^^^^^^^
+* `ravenpy` now requires `pooch>=1.8.0` for downloading and caching remote testing data. (PR #513)
+* `ravenpy.utilities.testdata` has been refactored to new module `ravenpy.testing`. The `publish_release_notes` function is now located in `ravenpy.utilities.publishing`. (PR #513)
+* The `ravenpy.testing.utils` module now provides a `yangtze()` class for fetching and caching the `raven-testdata` testing data. A convenience function (`get_file`) replaces the previous `get_local_testdata`. (PR #513)
+* The `ravenpy.testing.utils.open_dataset` function no longer supports OPeNDAP URLs or local file paths. Instead, it uses the `yangtze()` class to fetch datasets from the testing data repository or the local cache. Users should now use `xarray.open_dataset()` directly for OPeNDAP URLs or local files. (PR #513)
 
 Bug fixes
 ^^^^^^^^^
@@ -18,6 +26,7 @@ Bug fixes
 Internal changes
 ^^^^^^^^^^^^^^^^
 * `ravenpy` now requires `xclim>=0.57.0` and `xsdba` (v0.4.0+). (PR #511)
+* The `tests` folder no longer contains an `__init__.py` file and is no longer treated as a package. `pytest` fixtures from `emulators.py` are now directly imported into `conftest.py` for use in tests, and existing `pytest` fixtures have been modified to use the new `yangtze()` class for fetching testing data. (PR #513)
 
 v0.18.2 (2025-05-05)
 --------------------

docs/notebooks/02_Extract_geographical_watershed_properties.ipynb

@@ -37,10 +37,10 @@
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "import rasterio\n",
-    "import rioxarray as rio\n",
     "from birdy import WPSClient\n",
     "\n",
-    "from ravenpy.utilities.testdata import get_file\n",
+    "# Utility that simplifies working with test data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file\n",
     "\n",
     "# This is the URL of the Geoserver that will perform the computations for us.\n",
     "url = os.environ.get(\n",
@@ -74,8 +74,7 @@
     "\"\"\"\n",
     "feature_url = \"input.geojson\"\n",
     "\"\"\"\n",
-    "# However, to keep things tidy, we have also prepared a version that can be accessed easily for\n",
-    "# demonstration purposes:\n",
+    "# However, to keep things tidy, we have also prepared a version that can be accessed easily for demonstration purposes:\n",
     "feature_url = get_file(\"notebook_inputs/input.geojson\")\n",
     "df = gpd.read_file(feature_url)\n",
     "display(df)\n",

docs/notebooks/03_Extracting_forcing_data.ipynb

@@ -31,7 +31,8 @@
     "import xarray as xr\n",
     "from clisops.core import subset\n",
     "\n",
-    "from ravenpy.utilities.testdata import get_file"
+    "# Utility that simplifies working with test data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file"
    ]
   },
   {

docs/notebooks/04_Emulating_hydrological_models.ipynb

@@ -43,7 +43,9 @@
     "from pathlib import Path\n",
     "\n",
     "from ravenpy.config import commands as rc\n",
-    "from ravenpy.utilities.testdata import get_file"
+    "\n",
+    "# Utility that simplifies fetching and caching test data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file"
    ]
   },
   {

docs/notebooks/05_Advanced_RavenPy_configuration.ipynb

@@ -26,8 +26,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Utility that simplifies getting data hosted on the remote PAVICS-Hydro data server.\n",
-    "from ravenpy.utilities.testdata import get_file"
+    "# Utility that simplifies fetching and caching data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file"
    ]
   },
   {
@@ -216,7 +216,7 @@
     "\n",
     "# Observed weather data for the Salmon river. We extracted this using Tutorial Notebook 03 and the\n",
     "# salmon_river.geojson file as the contour.\n",
-    "ts = get_file(\"notebook_inputs/ERA5_weather_data_Salmon.nc\")\n",
+    "ts = yangtze.fetch(\"notebook_inputs/ERA5_weather_data_Salmon.nc\")\n",
     "\n",
     "# Set alternate variable names in the timeseries data file\n",
     "alt_names = {\n",

docs/notebooks/06_Raven_calibration.ipynb

@@ -33,6 +33,9 @@
     "\n",
     "from ravenpy.config import commands as rc\n",
     "from ravenpy.config import emulators\n",
+    "\n",
+    "# Utility that simplifies working with test data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file\n",
     "from ravenpy.utilities.calibration import SpotSetup"
    ]
   },
@@ -52,9 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from ravenpy.utilities.testdata import get_file\n",
-    "\n",
-    "# We get the netCDF for testing on a server. You can replace the getfile method by a string containing the path to your own netCDF\n",
+    "# We get the netCDF for testing on a server. You can replace the yangtze method with a string containing the absolute or relative path to your own netCDF\n",
     "nc_file = get_file(\n",
     "    \"raven-gr4j-cemaneige/Salmon-River-Near-Prince-George_meteo_daily.nc\"\n",
     ")\n",

docs/notebooks/07_Making_and_using_hotstart_files.ipynb

@@ -41,7 +41,9 @@
     "# Import the GR4JCN model\n",
     "from ravenpy.config import commands as rc\n",
     "from ravenpy.config import emulators\n",
-    "from ravenpy.utilities.testdata import get_file"
+    "\n",
+    "# Utility that simplifies working with test data hosted on GitHub\n",
+    "from ravenpy.testing.utils import get_file"
    ]
   },
   {