vdk-notebook: handle job with mixed .ipynb, .py, .sql files use-case (#…

…2279)

What:
Added string function to the stepBuilder, which is being called when a
new notebook step is added to the job.
This ensures that the steps are executed alphanumerically.

Why:
currently, when we execute "vdk run" firstly all the python and sql
files are executed and then the notebook files (which is not expected
since we expect vdk run to run files alphanumerically)

Signed-off-by: Duygu Hasan [hduygu@vmware.com](mailto:hduygu@vmware.com)

projects/vdk-plugins/vdk-notebook/src/vdk/plugin/notebook/notebook.py

@@ -82,7 +82,7 @@ def register_notebook_steps(file_path: Path, context: JobContext):
                         )
                         notebook_steps.append(step)
                         context.step_builder.add_step(step)
-
+            context.step_builder._StepBuilder__steps.sort(key=lambda step: step.name)
             log.debug(f"{len(notebook_steps)} " f"cells with vdk tag were detected!")
         except json.JSONDecodeError as e:
             errors.log_and_rethrow(

projects/vdk-plugins/vdk-notebook/tests/jobs/mixed-rest-api/10_delete_table.sql

@@ -0,0 +1 @@
+DROP TABLE IF EXISTS rest_target_table;

projects/vdk-plugins/vdk-notebook/tests/jobs/mixed-rest-api/20_create_table.ipynb

@@ -0,0 +1,42 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "826a105f-1874-4251-8abd-75fb898ba71c",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    },
+    "tags": [
+     "vdk"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "job_input.execute_query(\"CREATE TABLE rest_target_table (userId, id, title, completed);\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

projects/vdk-plugins/vdk-notebook/tests/jobs/mixed-rest-api/30_rest_ingest.py

@@ -0,0 +1,13 @@
+# Copyright 2021-2023 VMware, Inc.
+# SPDX-License-Identifier: Apache-2.0
+import requests
+
+
+def run(job_input):
+    response = requests.get("https://jsonplaceholder.typicode.com/todos/1")
+    response.raise_for_status()
+    payload = response.json()
+
+    job_input.send_object_for_ingestion(
+        payload=payload, destination_table="rest_target_table"
+    )

projects/vdk-plugins/vdk-notebook/tests/jobs/mixed-rest-api/config.ini

@@ -0,0 +1,16 @@
+; Supported format: https://docs.python.org/3/library/configparser.html#supported-ini-file-structure
+
+; This is the only file required to deploy a Data Job.
+; Read more to understand what each option means:
+
+; Information about the owner of the Data Job
+[owner]
+
+; Team is a way to group Data Jobs that belonged to the same team.
+team = jupyter-test-jobs
+
+[vdk]
+; Key value pairs of any configuration options that can be passed to vdk.
+; For possible options in your vdk installation execute command vdk config-help
+db_default_type=SQLITE
+ingest_method_default=SQLITE

projects/vdk-plugins/vdk-notebook/tests/jobs/mixed-rest-api/requirements.txt

@@ -0,0 +1,5 @@
+# Python jobs can specify extra library dependencies in requirements.txt file.
+# See https://pip.readthedocs.io/en/stable/user_guide/#requirements-files
+# The file is optional and can be deleted if no extra library dependencies are necessary.
+
+requests

projects/vdk-plugins/vdk-notebook/tests/test_plugin.py

@@ -54,3 +54,17 @@ def test_failing_job_with_sql_error(self) -> None:
             ["run", jobs_path_from_caller_directory("rest-api-job-sql-error")]
         )
         cli_assert_equal(1, result)
+
+    def test_mixed_job_with_py_and_sql(self) -> None:
+        result: Result = self.__runner.invoke(
+            ["run", jobs_path_from_caller_directory("mixed-rest-api")]
+        )
+        cli_assert_equal(0, result)
+        actual_rs: Result = self.__runner.invoke(
+            ["sqlite-query", "--query", "SELECT * FROM rest_target_table"]
+        )
+        assert actual_rs.stdout == (
+            "  userId    id  title                 completed\n"
+            "--------  ----  ------------------  -----------\n"
+            "       1     1  delectus aut autem            0\n"
+        )