Check if downloading sample data is stable

.github/actions/regenerate/action.yml

@@ -9,6 +9,7 @@ runs:
         python-version: 3.12
 
     - name: Verify registry
+      shell: bash
       run: |
         git config --global user.name "$GITHUB_ACTOR"
         git config --global user.email "$CI_COMMIT_EMAIL"

.github/workflows/ci.yaml

@@ -37,8 +37,13 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
+      - name: List nc dependencies
+        run: |
+          uv run python -c 'import netCDF4;print(f"netcdf: {netCDF4.__version__}");print(f"hdf5: {netCDF4.__hdf5libversion__}");print(f"libnetcdf: {netCDF4.__netcdf4libversion__}")'
+
       - name: Verify registry
         run: |
+          make fetch-test-data
           make registry.txt
           git diff --exit-code
 

.github/workflows/pr-comment.yaml

@@ -41,9 +41,11 @@ jobs:
           PR_NUMBER: ${{ github.event.issue.number }}
           NODE_ID: ${{ github.event.comment.node_id }}
 
-      - name: Get PR HEAD Ref
-        id: getRef
-        run: echo "pr_ref=$(gh pr view $PR_NUMBER --repo ${{ github.repository }} --json headRefOid | jq -r '.headRefOid')" >> $GITHUB_OUTPUT
+      - name: Get PR HEAD branch
+        id: getBranch
+        # This gets the PR's head ref name (aka branch)
+        # We can't use the SHA or the default because of how this workflow is triggered
+        run: echo "pr_branch=$(gh pr view $PR_NUMBER --repo ${{ github.repository }} --json headRefName | jq -r '.headRefName')" >> $GITHUB_OUTPUT
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           PR_NUMBER: ${{ github.event.issue.number }}
@@ -52,7 +54,7 @@ jobs:
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
-          ref: ${{ steps.getRef.outputs.pr_ref }}
+          ref: ${{ steps.getBranch.outputs.pr_branch }}
           token: ${{ secrets.PAT }}
 
       - name: Run the regeneration
@@ -78,6 +80,9 @@ jobs:
   notify-job:
     needs: [regenerate]
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
     if: ${{ always() && contains(needs.*.result, 'failure') }}
     steps:
       - name: Notify on Failure

changelog/7.feature.md

@@ -1,3 +1,3 @@
 Added an action to regenerate the sample data in Pull Requests.
 
-A comment containing `\regenerate` will trigger the action.
+A comment containing `/regenerate` will trigger the action.

registry.txt

@@ -1,13 +1,13 @@
-CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rlut/gn/v20191115/rlut_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 95341df80de95ddb0b45da11aed67db771414fff94508687fb30fce63b82c104
-CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rsdt/gn/v20191115/rsdt_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 25e9e817a05ffab4a2b073078f6be0e52096fa9da8eb55f009d079842c708614
-CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rsut/gn/v20191115/rsut_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 139c4c59d98c737ce2d7ca777e52e35e38d49fcb8b08dd98175ed0f1354f8e75
-CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/tas/gn/v20191115/tas_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc be4a191c75b3643aad34238970c0587128a3852694f2c61425b4bbda42e5ff08
-CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/fx/areacella/gn/v20191115/areacella_fx_ACCESS-ESM1-5_historical_r1i1p1f1_gn.nc d9d07cacc65c196b9ec47d60cabcf86fd397b1e22063a32c3798a98ee3dfb16e
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rlut/gn/v20210318/rlut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 1083d92079e9c40d3797ecc4235df1c86c99af7ca3b9458b21f1d34054351041
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsdt/gn/v20210318/rsdt_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc 9f9ae50efc55f4e18dc174d7c3af10f4e67a391c84d81cdb6ba574fa8b61b276
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsdt/gn/v20210318/rsdt_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 2299e10eb6ccf190fe07f7b60aa40b8700f7f964ca68c989f3572abe39eb22c7
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsut/gn/v20210318/rsut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc 5141bb64d6f457550d8bf429a4233af1bd706ed8b2131fc2ef329bcb6db7a236
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsut/gn/v20210318/rsut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 49fbd6c0d7b8c0d10a270e8d88191764c02ba651f80b464605dfa5b0221d622b
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/tas/gn/v20210318/tas_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc bff52adef26d48d4b747368816aff3712c606cafa92f6b78f4974f23efcba510
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/tas/gn/v20210318/tas_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc b61faa48540472be5b208a4ecf40873860c1d4cfb7f50a4dff4ac17ee2ba4f73
-CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/fx/areacella/gn/v20210318/areacella_fx_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn.nc e8e3b873d9ba115974329c0f7785c9e30dcca66007fa973c22cd734efc46dcfd
+CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rlut/gn/v20191115/rlut_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 3d5e70004253f4973cb07265373bfb63f4c7fba25e2a048b300a5eba1b6dad56
+CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rsdt/gn/v20191115/rsdt_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 8c80ab4f64ad31caf0d7743984d0f6f1a23c961beeb23e41e96e457422643e7a
+CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/rsut/gn/v20191115/rsut_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc 13c2c3e0f42cbad60e4096d3dc8ac96e867880d4f10742ec635f9648fe16e298
+CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/Amon/tas/gn/v20191115/tas_Amon_ACCESS-ESM1-5_historical_r1i1p1f1_gn_185001-201412.nc f07bc7bc43712a160626b18f660a244be21cfd8fe3b4488def9b4d002007212e
+CMIP6/CMIP/CSIRO/ACCESS-ESM1-5/historical/r1i1p1f1/fx/areacella/gn/v20191115/areacella_fx_ACCESS-ESM1-5_historical_r1i1p1f1_gn.nc 85a64eacd4c38f25ede96ce644f654e98596ff5aed0c521681b27fef0bc7a6b3
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rlut/gn/v20210318/rlut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 3770c7856ebbd1c4888d3267d176e37ed6659883ab04fe319bcf090b9a2112e5
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsdt/gn/v20210318/rsdt_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc 5e322846c0308d793169044a4bdc05c1686ce7ba335b453194c353a142b4d94f
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsdt/gn/v20210318/rsdt_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 5076b51d075029a038ca3af981d9cede902eec9bf667767a232b87fba1cb1e8c
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsut/gn/v20210318/rsut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc 10a9431638626c0358be581c6fcc96bd4a0f2051ab9ae92be3e43811f149ee63
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/rsut/gn/v20210318/rsut_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc 43d68491eada7b2cf1adf11170346584af1662c0472eafe8180ab6965752bcd8
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/tas/gn/v20210318/tas_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_201501-210012.nc 4bdd770ccf0c305284f4b7df30da11be9b463a734498da627ab99d10067cd9a7
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/Amon/tas/gn/v20210318/tas_Amon_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn_210101-230012.nc a33f0c940a8ef87bba0ccceb43f174df31e9635d5806f2b3aea07468f17592ec
+CMIP6/ScenarioMIP/CSIRO/ACCESS-ESM1-5/ssp126/r1i1p1f1/fx/areacella/gn/v20210318/areacella_fx_ACCESS-ESM1-5_ssp126_r1i1p1f1_gn.nc b1bee7c317e19f68d5bdbb60b3485badb99cc32bc3859f970d01dc28a57a14da

scripts/fetch_test_data.py

@@ -144,12 +144,14 @@ def create_out_filename(metadata: pd.Series, ds: xr.Dataset) -> pathlib.Path:
     for _, dataset in datasets.iterrows():
         print(dataset.key)
         for ds_filename in dataset["files"]:
+            print(f"Raw Hash: {pooch.file_hash(ds_filename)}")
             ds_orig = xr.open_dataset(ds_filename)
 
             ds_downscaled = decimate_dataset(ds_orig)
 
             output_filename = OUTPUT_PATH / create_out_filename(dataset, ds_orig)
             output_filename.parent.mkdir(parents=True, exist_ok=True)
             ds_downscaled.to_netcdf(output_filename)
+            print(f"Finished Hash: {pooch.file_hash(str(output_filename))}")
 
     pooch.make_registry(OUTPUT_PATH, "registry.txt")