[DOCS] Put Cloud snippets under test

.github/workflows/ci.yml

@@ -138,6 +138,10 @@ jobs:
           - docs-basic
           - docs-spark
     env:
+      # gx cloud
+      GX_CLOUD_BASE_URL: ${{vars.MERCURY_BASE_URL}}
+      GX_CLOUD_ORGANIZATION_ID: ${{secrets.MERCURY_ORGANIZATION_ID}}
+      GX_CLOUD_ACCESS_TOKEN: ${{secrets.MERCURY_ACCESS_TOKEN}}
       # google
       GE_TEST_GCP_CREDENTIALS: ${{secrets.GE_TEST_GCP_CREDENTIALS}}
       GE_TEST_GCP_PROJECT: ${{secrets.GE_TEST_GCP_PROJECT}}
@@ -168,6 +172,9 @@ jobs:
       SNOWFLAKE_SCHEMA: ${{secrets.SNOWFLAKE_SCHEMA}}
       SNOWFLAKE_WAREHOUSE: ${{secrets.SNOWFLAKE_WAREHOUSE}}
       SNOWFLAKE_ROLE: ${{secrets.SNOWFLAKE_ROLE}}
+    permissions:
+      id-token: write
+      contents: read
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -178,10 +185,9 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.9"
-      - name: Run docs_snippet_checker
-        run: |
-          yarn install
-          python ci/checks/validate_docs_snippets.py
+          cache: "pip"
+          cache-dependency-path: |
+            reqs/requirements-dev-test.txt
 
       - name: Authenticate with GCP
         uses: google-github-actions/auth@v2
@@ -209,24 +215,25 @@ jobs:
       - name: Install mssql odbc driver
         run: ./scripts/install_mssql_odbc_driver.sh
 
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.9"
-          cache: "pip"
-          cache-dependency-path: |
-            reqs/requirements-dev-test.txt
-
       - name: Install dependencies
         run: |
           pip install $(grep -E '^(invoke)' reqs/requirements-dev-contrib.txt)
           invoke deps --gx-install -m '${{ matrix.doc-step }}'
 
+      - name: Run docs_snippet_checker
+        run: |
+          yarn install
+          python ci/checks/validate_docs_snippets.py
+
+      - name: Configure ECR AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-region: us-east-1
+          role-to-assume: arn:aws:iam::258143015559:role/github-amazonec2containerregistryreadonly
+
       - name: Login to Amazon ECR
         id: login-ecr
         uses: aws-actions/amazon-ecr-login@v2
-        with:
-          registries: "258143015559"
 
       - name: Run the tests
         run: invoke docs-snippet-tests '${{ matrix.doc-step }}' --up-services --verbose  --reports

docs/docusaurus/docs/cloud/connect/connect_python.py

@@ -5,11 +5,6 @@
 # TODO: This needs to be put under test when the GX Cloud docs snippet testing environment has been created.
 """
 
-
-def set_up_context_for_example(context):
-    pass
-
-
 # EXAMPLE SCRIPT STARTS HERE:
 # <snippet name="docs/docusaurus/docs/cloud/connect/connect_python.py - full code example">
 # <snippet name="docs/docusaurus/docs/cloud/connect/connect_python.py - get cloud context">
@@ -24,7 +19,6 @@ def set_up_context_for_example(context):
 # Hide this
 assert type(context).__name__ == "CloudDataContext"
 # Hide this
-set_up_context_for_example(context)
 
 # <snippet name="docs/docusaurus/docs/cloud/connect/connect_python.py - list data sources">
 print(context.list_datasources())

docs/docusaurus/docs/components/examples_under_test.py

@@ -47,16 +47,20 @@
         # data_context_dir="",
         backend_dependencies=[],
     ),
-    # TODO: Re-enable this once a --docs-tests-cloud environment is available.
-    # IntegrationTestFixture(
-    #     # To test, run:
-    #     # pytest --docs-tests --cloud -k "create_a_cloud_data_context" tests/integration/test_script_runner.py
-    #     name="create_a_cloud_data_context",
-    #     user_flow_script="docs/docusaurus/docs/core/set_up_a_gx_environment/_create_a_data_context/cloud_data_context.py",
-    #     # data_dir="",
-    #     # data_context_dir="",
-    #     backend_dependencies=[],
-    # ),
+    IntegrationTestFixture(
+        # To test, run:
+        # pytest --docs-tests --cloud -k "connect_python" tests/integration/test_script_runner.py
+        name="connect_python",
+        user_flow_script="docs/docusaurus/docs/cloud/connect/connect_python.py",
+        backend_dependencies=[BackendDependencies.CLOUD],
+    ),
+    IntegrationTestFixture(
+        # To test, run:
+        # pytest --docs-tests --cloud -k "create_a_cloud_data_context" tests/integration/test_script_runner.py
+        name="create_a_cloud_data_context",
+        user_flow_script="docs/docusaurus/docs/core/set_up_a_gx_environment/_create_a_data_context/cloud_data_context.py",
+        backend_dependencies=[BackendDependencies.CLOUD],
+    ),
     IntegrationTestFixture(
         # To test, run:
         # pytest --docs-tests -k "create_a_file_data_context" tests/integration/test_script_runner.py
@@ -646,28 +650,17 @@
 
 # Extend the docs_tests list with the above sublists (only the docs_tests list is imported
 # into `test_script_runner.py` and actually used in CI checks).
-docs_tests.extend(install_gx)
-
-docs_tests.extend(try_gx)
-
+# docs_tests.extend(install_gx)
+# docs_tests.extend(try_gx)
 docs_tests.extend(create_a_data_context)
-
-docs_tests.extend(connect_to_filesystem_data_create_a_data_source)
-docs_tests.extend(connect_to_filesystem_data_create_a_data_asset)
-docs_tests.extend(connect_to_filesystem_data_create_a_batch_definition)
-
-docs_tests.extend(connect_to_dataframe_data)
-
-docs_tests.extend(docs_example_scripts_run_validations)
-
-docs_tests.extend(example_scripts_for_define_expectations)
-
-docs_tests.extend(docs_examples_customize_expectations)
-
-docs_tests.extend(docs_examples_trigger_actions_based_on_validation_results)
-
-docs_tests.extend(docs_example_configure_project_settings)
-
-docs_tests.extend(docs_examples_configure_data_docs)
-
-docs_tests.extend(learn_data_quality_use_cases)
+# docs_tests.extend(connect_to_filesystem_data_create_a_data_source)
+# docs_tests.extend(connect_to_filesystem_data_create_a_data_asset)
+# docs_tests.extend(connect_to_filesystem_data_create_a_batch_definition)
+# docs_tests.extend(connect_to_dataframe_data)
+# docs_tests.extend(docs_example_scripts_run_validations)
+# docs_tests.extend(example_scripts_for_define_expectations)
+# docs_tests.extend(docs_examples_customize_expectations)
+# docs_tests.extend(docs_examples_trigger_actions_based_on_validation_results)
+# docs_tests.extend(docs_example_configure_project_settings)
+# docs_tests.extend(docs_examples_configure_data_docs)
+# docs_tests.extend(learn_data_quality_use_cases)

pyproject.toml

@@ -658,27 +658,27 @@ markers = [
     "bigquery: mark test as bigquery-dependent.",
     "clickhouse: mark a test as Clickhouse-dependent.",
     "cloud: mark test as being relevant to Great Expectations Cloud.",
+    "databricks: mark test as requiring databricks.",
     "docs-basic: mark a test as a docs test, that does not require additional credentials.",
     "docs-creds-needed: mark a test as a docs test that needs additional cloud credentials (these will not run on public forks).",
-    "databricks: mark test as requiring databricks.",
-    "docs: mark a test as a docs test.",
     "docs-spark: temporarily mark a test as a docs test that depends on spark.",
-    "integration: mark test as an integration test.",
+    "docs: mark a test as a docs test.",
     "external_sqldialect: mark test as requiring install of an external sql dialect.",
     "filesystem: mark tests using the filesystem as the storage backend.",
+    "integration: mark test as an integration test.",
     "mssql: mark a test as mssql-dependent.",
     "mysql: mark a test as mysql-dependent.",
     "openpyxl: mark a test for openpyxl-dependent, which is for Excel files.",
     "performance: mark a test as a performance test for BigQuery. These aren't run in our PR or release pipeline",
     "postgresql: mark a test as postgresql-dependent.",
     "project: mark a test that verifies properties of the gx project",
     "pyarrow: mark a test as PyArrow-dependent.",
-    "snowflake: mark a test as snowflake-dependent.",
-    "sqlalchemy_version_compatibility: mark test as required for sqlalchemy version compatibility.",
-    "sqlite: mark test requiring sqlite",
     "slow: mark tests taking longer than 1 second.",
+    "snowflake: mark a test as snowflake-dependent.",
     "spark: mark a test as Spark-dependent.",
     "spark_connect: mark a test as Spark Connect-dependent.",
+    "sqlalchemy_version_compatibility: mark test as required for sqlalchemy version compatibility.",
+    "sqlite: mark test requiring sqlite",
     "trino: mark a test as trino-dependent.",
     "unit: mark a test as a unit test.",
     "v2_api: mark test as specific to the v2 api (e.g. pre Data Connectors).",

tasks.py

@@ -847,17 +847,20 @@ class TestDependencies(NamedTuple):
             "reqs/requirements-dev-test.txt",
             "reqs/requirements-dev-azure.txt",
             "reqs/requirements-dev-bigquery.txt",
+            "reqs/requirements-dev-cloud.txt",
             "reqs/requirements-dev-redshift.txt",
             "reqs/requirements-dev-snowflake.txt",
             # "Deprecated API features detected" warning/error for test_docs[split_data_on_whole_table_bigquery] when pandas>=2.0  # noqa: E501
             "reqs/requirements-dev-sqlalchemy1.txt",
         ),
+        services=("mercury",),
         extra_pytest_args=(
             "--aws",
             "--azure",
             "--bigquery",
             "--redshift",
             "--snowflake",
+            "--cloud",
             "--docs-tests",
         ),
     ),

tests/integration/backend_dependencies.py

@@ -17,3 +17,4 @@ class BackendDependencies(enum.Enum):
     SQLALCHEMY = "SQLALCHEMY"
     SNOWFLAKE = "SNOWFLAKE"
     TRINO = "TRINO"
+    CLOUD = "CLOUD"