Run dataset tests on Woodpecker with full data access

.github/workflows/eval.yml

@@ -50,15 +50,7 @@ jobs:
 
       - name: Download datasets
         run: |
-          lenskit data fetch -D data --movielens ml-100k ml-1m ml-10m
-          lenskit data fetch -D data/az23 --amazon --core Video_Games
-          lenskit data fetch -D data/az18 --amazon --edition 2018 Video_Games
-          lenskit data fetch -D data/az14 --amazon --edition 2014 Video_Games
-          lenskit data fetch --ms-web
-          if [[ ! -f data/australian_users_items.json.gz ]]; then
-            curl -fsL -o data/australian_users_items.json.gz.tmp https://mcauleylab.ucsd.edu/public_datasets/data/steam/australian_users_items.json.gz
-            mv data/australian_users_items.json.gz.tmp data/australian_users_items.json.gz
-          fi
+          lenskit data fetch -D data --movielens ml-100k
 
       - name: Run Eval Tests
         run: |
@@ -103,15 +95,7 @@ jobs:
 
       - name: Download datasets
         run: |
-          coverage run -a --source=src/lenskit -m lenskit data fetch -D data --movielens ml-100k ml-20m ml-1m ml-10m
-          coverage run -a --source=src/lenskit -m lenskit data fetch -D data/az23 --amazon --core Video_Games
-          coverage run -a --source=src/lenskit -m lenskit data fetch -D data/az18 --amazon --edition 2018 Video_Games
-          coverage run -a --source=src/lenskit -m lenskit data fetch -D data/az14 --amazon --edition 2014 Video_Games
-          coverage run -a --source=src/lenskit -m lenskit data fetch --ms-web
-          if [[ ! -f data/australian_users_items.json.gz ]]; then
-            curl -fsL -o data/australian_users_items.json.gz.tmp https://mcauleylab.ucsd.edu/public_datasets/data/steam/australian_users_items.json.gz
-            mv data/australian_users_items.json.gz.tmp data/australian_users_items.json.gz
-          fi
+          coverage run -a --source=src/lenskit -m lenskit data fetch -D data --movielens ml-100k
 
       - name: 🕺🏻 Test LensKit CLI
         run: |

.woodpecker/dataset-tests.yml

@@ -0,0 +1,23 @@
+when:
+  - event: push
+    branch: main
+  - event: pull_request
+
+labels:
+  backend: docker
+
+steps:
+  - name: build and run data tests
+    image: codeberg.org/mdekstrand/woodpecker-mise:v1-f44-dev
+    pull: true
+    settings:
+      task: "ci:prepare ::: test -v --coverage -m realdata ::: test-cli tests/cli/test-data-convert.sh"
+      mise-env: ci
+
+  - name: upload code coverage
+    image: woodpeckerci/plugin-codecov
+    settings:
+      files:
+        - coverage.xml
+      token:
+        from_secret: codecov-token

LICENSE.md

@@ -1,3 +1,8 @@
+> [!NOTE]
+> The following license applies to the LensKit source code. The data sets
+> under `data/` have their own terms, described in their respective README
+> files.
+
 Copyright (c) 2018–2023 Boise State University
 Copyright (c) 2023-2026 Drexel University and contributors
 

codecov.yml

@@ -2,6 +2,7 @@ codecov:
   notify:
     after_n_builds: 10
     wait_for_ci: true
+  token: ab58c9cf-25b8-4283-a485-0b6382dc9a61
 ignore:
   - build*.py
   - build-tools/*

mise/config.ci.toml

@@ -0,0 +1,5 @@
+[settings]
+disable_tools = ["pkl", "perl"]
+
+[settings.python]
+uv_venv_auto = "source"

mise/config.toml

@@ -2,6 +2,7 @@
 rust = "stable"
 usage = "latest"
 uv = "latest"
+jq = "latest"
 shfmt = "latest"
 tombi = "latest"
 perl = { version = "latest", os = ["linux", "macos"] }
@@ -12,15 +13,22 @@ yamlfmt = "latest"
 ruff = "latest"
 
 [settings]
+experimental = true
 idiomatic_version_file_enable_tools = ["rust"]
 github.github_attestations = false
 aqua.github_attestations = false
 
 [settings.python]
 # uv_venv_auto = "source"
 
+[deps.uv]
+
 [env]
 HK_MISE = 1
 
 [hooks]
-postinstall = "hk install"
+postinstall = '''
+if [ -z "$CI" ]; then
+  hk install
+fi
+'''

mise/tasks/ci/prepare.sh

@@ -0,0 +1,23 @@
+#!/bin/zsh
+#MISE description="Prepare CI environment"
+#USAGE flag "-v --verbose" help="Enable verbose logging."
+
+. "$MISE_PROJECT_ROOT/mise/task-functions.sh"
+. "${UV_PROJECT_ENVIRONMENT:-$MISE_PROJECT_ROOT/.venv}/bin/activate"
+
+if [[ -z $CI ]]; then
+    msg "not in CI, skipping environment setup"
+fi
+
+if [[ $CI_SYSTEM_NAME = woodpecker ]]; then
+    if [[ -d /datasets ]]; then
+        msg "linking data from /datasets"
+        for f in /datasets/*; do
+            ln -s $f data/${f#/datasets/}
+        done
+    else
+        msg -warn "running on Woodpecker but /datasets does not exist"
+    fi
+else
+    msg "nothing to do for CI $CI_SYSTEM_NAME"
+fi

mise/tasks/test-cli.sh

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
 #MISE description="Run CLI tests"
+#MISE wait_for=["test"]
 
 exec ./tests/cli/run.sh "$@"

mise/tasks/test.sh

@@ -1,5 +1,6 @@
 #!/usr/bin/env bash
 #MISE description="Run tests"
+#MISE wait_for=["ci:prepare"]
 #USAGE flag "--coverage" help="Run tests with coverage."
 #USAGE flag "--accel-coverage" help="Run tests with Rust accelerator coverage."
 #USAGE flag "--slow" help="Include slow tests."