Setup integration test and workflow

.github/workflows/Tests.yml

@@ -86,15 +86,21 @@ jobs:
           cd zimui
           $(yarn bin)/cypress run
 
-  build-docker:
+  # this job replaces the standard "build_docker" job since it builds the docker image
+  run-integration-tests:
     runs-on: ubuntu-22.04
     steps:
       - uses: actions/checkout@v3
 
       - name: Ensure we can build the Docker image
         run: |
-          docker build -t testimage .
+          docker build -t youtube2zim .
 
-      - name: Ensure we can start the Docker image
-        run: |
-          docker run --rm testimage
+      - name: Run scraper
+        env:
+          YOUTUBE_API_KEY: ${{ secrets.YOUTUBE_API_KEY }}
+          OPTIMIZATION_CACHE_URL: ${{ secrets.OPTIMIZATION_CACHE_URL }}
+        run: docker run -v $PWD/output:/output youtube2zim youtube2zim --api-key "$YOUTUBE_API_KEY" --optimization-cache "$OPTIMIZATION_CACHE_URL" --type channel --id "UC8elThf5TGMpQfQc_VE917Q" --name "openZIM_testing" --zim-file "openZIM_testing.zim"
+
+      - name: Run integration test suite
+        run: docker run -v $PWD/scraper/tests-integration/integration.py:/src/scraper/tests-integration/integration.py -v $PWD/output:/output youtube2zim bash -c "pip install pytest; pytest -v /src/scraper/tests-integration/integration.py"

scraper/pyproject.toml

@@ -200,6 +200,7 @@ ban-relative-imports = "all"
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
+"tests-integration/**/*" = ["PLR2004", "S101", "TID252"]
 
 [tool.pytest.ini_options]
 minversion = "7.3"

scraper/tests-integration/integration.py

@@ -0,0 +1,29 @@
+import os
+
+from zimscraperlib.zim import Archive
+
+ZIM_FILE_PATH = "/output/openZIM_testing.zim"
+
+
+def test_is_file():
+    """Ensure ZIM file exists"""
+    assert os.path.isfile(ZIM_FILE_PATH)
+
+
+def test_zim_main_page():
+    """Ensure main page is a redirect to index.html"""
+
+    main_entry = Archive(ZIM_FILE_PATH).main_entry
+    assert main_entry.is_redirect
+    assert main_entry.get_redirect_entry().path == "index.html"
+
+
+def test_zim_scraper():
+    """Ensure scraper and zim title are present in metadata"""
+
+    zim_fh = Archive(ZIM_FILE_PATH)
+    scraper = zim_fh.get_text_metadata("scraper")
+    zim_title = zim_fh.get_text_metadata("Title")
+
+    assert "youtube2zim " in scraper
+    assert "openZIM_testing" in zim_title