✨Source Apify Dataset: Migrate Python CDK to Low-code CDK (#29859)

Co-authored-by: Marcos Marx <marcosmarxm@users.noreply.github.com>
Co-authored-by: marcosmarxm <marcosmarxm@gmail.com>

airbyte-integrations/connectors/source-apify-dataset/.dockerignore

@@ -1,6 +1,5 @@
 *
 !Dockerfile
-!Dockerfile.test
 !main.py
 !source_apify_dataset
 !setup.py

airbyte-integrations/connectors/source-apify-dataset/Dockerfile

@@ -1,16 +1,38 @@
-FROM python:3.9-slim
+FROM python:3.9.11-alpine3.15 as base
+
+# build and load all requirements
+FROM base as builder
+WORKDIR /airbyte/integration_code
+
+# upgrade pip to the latest version
+RUN apk --no-cache upgrade \
+    && pip install --upgrade pip \
+    && apk --no-cache add tzdata build-base
 
-# Bash is installed for more convenient debugging.
-RUN apt-get update && apt-get install -y bash && rm -rf /var/lib/apt/lists/*
 
+COPY setup.py ./
+# install necessary packages to a temporary folder
+RUN pip install --prefix=/install .
+
+# build a clean environment
+FROM base
 WORKDIR /airbyte/integration_code
-COPY source_apify_dataset ./source_apify_dataset
+
+# copy all loaded and built libraries to a pure basic image
+COPY --from=builder /install /usr/local
+# add default timezone settings
+COPY --from=builder /usr/share/zoneinfo/Etc/UTC /etc/localtime
+RUN echo "Etc/UTC" > /etc/timezone
+
+# bash is installed for more convenient debugging.
+RUN apk --no-cache add bash
+
+# copy payload code only
 COPY main.py ./
-COPY setup.py ./
-RUN pip install .
+COPY source_apify_dataset ./source_apify_dataset
 
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.2.0
+LABEL io.airbyte.version=1.0.0
 LABEL io.airbyte.name=airbyte/source-apify-dataset

airbyte-integrations/connectors/source-apify-dataset/README.md

@@ -1,63 +1,27 @@
 # Apify Dataset Source
 
-This is the repository for the Apify Dataset source connector, written in Python.
-For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/sources/apify-dataset).
-
-# About connector
-This connector allows you to download data from Apify [dataset](https://docs.apify.com/storage/dataset) to Airbyte. All you need
-is Apify dataset ID.
+This is the repository for the Apify Dataset configuration based source connector.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.com/integrations/sources/apify-dataset).
 
 ## Local development
 
-### Prerequisites
-**To iterate on this connector, make sure to complete this prerequisites section.**
-
-#### Minimum Python version required `= 3.7.0`
-
-#### Build & Activate Virtual Environment and install dependencies
-From this connector directory, create a virtual environment:
-```
-python -m venv .venv
-```
-
-This will generate a virtualenv for this module in `.venv/`. Make sure this venv is active in your
-development environment of choice. To activate it from the terminal, run:
-```
-source .venv/bin/activate
-pip install -r requirements.txt
-```
-If you are in an IDE, follow your IDE's instructions to activate the virtualenv.
-
-Note that while we are installing dependencies from `requirements.txt`, you should only edit `setup.py` for your dependencies. `requirements.txt` is
-used for editable installs (`pip install -e`) to pull in Python dependencies from the monorepo and will call `setup.py`.
-If this is mumbo jumbo to you, don't worry about it, just put your deps in `setup.py` but install using `pip install -r requirements.txt` and everything
-should work as you expect.
-
 #### Building via Gradle
-From the Airbyte repository root, run:
+You can also build the connector in Gradle. This is typically used in CI and not needed for your development workflow.
+
+To build using Gradle, from the Airbyte repository root, run:
 ```
 ./gradlew :airbyte-integrations:connectors:source-apify-dataset:build
 ```
 
 #### Create credentials
-**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.io/integrations/sources/apify-dataset)
-to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `source_apify_dataset/spec.json` file.
-Note that the `secrets` directory is gitignored by default, so there is no danger of accidentally checking in sensitive information.
+**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.com/integrations/sources/apify-dataset)
+to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `source_apify_dataset/spec.yaml` file.
+Note that any directory named `secrets` is gitignored across the entire Airbyte repo, so there is no danger of accidentally checking in sensitive information.
 See `integration_tests/sample_config.json` for a sample config file.
 
-You can get your Apify credentials from Settings > Integration [section](https://my.apify.com/account#/integrations) of the Apify app 
-
 **If you are an Airbyte core member**, copy the credentials in Lastpass under the secret name `source apify-dataset test creds`
 and place them into `secrets/config.json`.
 
-### Locally running the connector
-```
-python main.py spec
-python main.py check --config secrets/config.json
-python main.py discover --config secrets/config.json
-python main.py read --config secrets/config.json --catalog integration_tests/configured_catalog.json
-```
-
 ### Locally running the connector docker image
 
 #### Build
@@ -82,32 +46,15 @@ docker run --rm -v $(pwd)/secrets:/secrets airbyte/source-apify-dataset:dev disc
 docker run --rm -v $(pwd)/secrets:/secrets -v $(pwd)/integration_tests:/integration_tests airbyte/source-apify-dataset:dev read --config /secrets/config.json --catalog /integration_tests/configured_catalog.json
 ```
 ## Testing
-   Make sure to familiarize yourself with [pytest test discovery](https://docs.pytest.org/en/latest/goodpractices.html#test-discovery) to know how your test files and methods should be named.
-First install test dependencies into your virtual environment:
-```
-pip install .[tests]
-```
-### Unit Tests
-To run unit tests locally, from the connector directory run:
-```
-python -m pytest unit_tests
-```
 
-### Integration Tests
-There are two types of integration tests: Acceptance Tests (Airbyte's test suite for all source connectors) and custom integration tests (which are specific to this connector).
-#### Custom Integration tests
-Place custom tests inside `integration_tests/` folder, then, from the connector root, run
-```
-python -m pytest integration_tests
-```
 #### Acceptance Tests
-Customize `acceptance-test-config.yml` file to configure tests. See [Connector Acceptance Tests](https://docs.airbyte.io/connector-development/testing-connectors/connector-acceptance-tests-reference) for more information.
+Customize `acceptance-test-config.yml` file to configure tests. See [Connector Acceptance Tests](https://docs.airbyte.com/connector-development/testing-connectors/connector-acceptance-tests-reference) for more information.
 If your connector requires to create or destroy resources for use during acceptance tests create fixtures for it and place them inside integration_tests/acceptance.py.
-To run your integration tests with acceptance tests, from the connector root, run
+
+To run your integration tests with Docker, run:
 ```
-python -m pytest integration_tests -p integration_tests.acceptance
+./acceptance-test-docker.sh
 ```
-To run your integration tests with docker
 
 ### Using gradle to run tests
 All commands should be run from airbyte project root.

airbyte-integrations/connectors/source-apify-dataset/unit_tests/unit_test.py → airbyte-integrations/connectors/source-apify-dataset/__init__.py

@@ -1,7 +1,3 @@
 #
 # Copyright (c) 2023 Airbyte, Inc., all rights reserved.
 #
-
-
-def test_example_method():
-    assert True

airbyte-integrations/connectors/source-apify-dataset/acceptance-test-config.yml

@@ -1,19 +1,44 @@
-# See [Connector Acceptance Tests](https://docs.airbyte.com/connector-development/testing-connectors/connector-acceptance-tests-reference)
-# for more information about how to configure these tests
 connector_image: airbyte/source-apify-dataset:dev
-tests:
+acceptance_tests:
   spec:
-    - spec_path: "source_apify_dataset/spec.json"
+    tests:
+      - spec_path: "source_apify_dataset/spec.yaml"
+        backward_compatibility_tests_config:
+          disable_for_version: 0.2.0
   connection:
-    - config_path: "secrets/config.json"
-      status: "succeed"
-    - config_path: "integration_tests/invalid_config.json"
-      status: "failed"
+    tests:
+      - config_path: "secrets/config.json"
+        status: "succeed"
+      - config_path: "integration_tests/invalid_config.json"
+        status: "failed"
   discovery:
-    - config_path: "secrets/config.json"
+    tests:
+      - config_path: "secrets/config.json"
+        backward_compatibility_tests_config:
+          disable_for_version: 0.2.0
   basic_read:
-    - config_path: "secrets/config.json"
-      configured_catalog_path: "integration_tests/configured_catalog.json"
+    tests:
+      - config_path: "secrets/config.json"
+        configured_catalog_path: "integration_tests/configured_catalog.json"
+  incremental:
+    bypass_reason: Connector doesn't use incremental sync
+    # tests:
+    #   - config_path: "secrets/config.json"
+    #     configured_catalog_path: "integration_tests/configured_catalog.json"
+    #     future_state:
+    #       future_state_path: "integration_tests/abnormal_state.json"
   full_refresh:
-    - config_path: "secrets/config.json"
-      configured_catalog_path: "integration_tests/configured_catalog.json"
+    tests:
+      - config_path: "secrets/config.json"
+        configured_catalog_path: "integration_tests/configured_catalog.json"
+        ignored_fields:
+          datasets:
+            - name: "accessedAt"
+              bypass_reason: "Change everytime"
+            - name: "stats/readCount"
+              bypass_reason: "Change everytime"
+          dataset:
+            - name: "accessedAt"
+              bypass_reason: "Change everytime"
+            - name: "stats/readCount"
+              bypass_reason: "Change everytime"

airbyte-integrations/connectors/source-apify-dataset/acceptance-test-docker.sh

@@ -1,2 +1,3 @@
 #!/usr/bin/env sh
+
 source "$(git rev-parse --show-toplevel)/airbyte-integrations/bases/connector-acceptance-test/acceptance-test-docker.sh"

airbyte-integrations/connectors/source-apify-dataset/integration_tests/__init__.py

@@ -0,0 +1,3 @@
+#
+# Copyright (c) 2023 Airbyte, Inc., all rights reserved.
+#

airbyte-integrations/connectors/source-apify-dataset/integration_tests/abnormal_state.json

@@ -0,0 +1,16 @@
+[
+  {
+    "type": "STREAM",
+    "stream": {
+      "stream_state": { "modifiedAt": "3021-09-08T07:04:28.000Z" },
+      "stream_descriptor": { "name": "dataset" }
+    }
+  },
+  {
+    "type": "STREAM",
+    "stream": {
+      "stream_state": { "modifiedAt": "3021-09-08T07:04:28.000Z" },
+      "stream_descriptor": { "name": "datasets" }
+    }
+  }
+]

airbyte-integrations/connectors/source-apify-dataset/integration_tests/acceptance.py

@@ -11,4 +11,6 @@
 @pytest.fixture(scope="session", autouse=True)
 def connector_setup():
     """This fixture is a placeholder for external resources that acceptance test might require."""
+    # TODO: setup test dependencies if needed. otherwise remove the TODO comments
     yield
+    # TODO: clean up test dependencies

airbyte-integrations/connectors/source-apify-dataset/integration_tests/configured_catalog.json

@@ -1,24 +1,31 @@
 {
   "streams": [
     {
+      "stream": {
+        "name": "datasets",
+        "json_schema": {},
+        "supported_sync_modes": ["full_refresh"]
+      },
+      "sync_mode": "full_refresh",
+      "destination_sync_mode": "overwrite"
+    },
+    {
+      "stream": {
+        "name": "dataset",
+        "json_schema": {},
+        "supported_sync_modes": ["full_refresh"]
+      },
       "sync_mode": "full_refresh",
-      "destination_sync_mode": "overwrite",
+      "destination_sync_mode": "overwrite"
+    },
+    {
       "stream": {
-        "name": "DatasetItems",
-        "supported_sync_modes": ["full_refresh"],
-        "destination_sync_mode": "overwrite",
-        "json_schema": {
-          "$schema": "http://json-schema.org/draft-07/schema#",
-          "type": "object",
-          "properties": {
-            "data": {
-              "type": "object",
-              "additionalProperties": true
-            }
-          },
-          "additionalProperties": true
-        }
-      }
+        "name": "item_collection",
+        "json_schema": {},
+        "supported_sync_modes": ["full_refresh"]
+      },
+      "sync_mode": "full_refresh",
+      "destination_sync_mode": "overwrite"
     }
   ]
 }

airbyte-integrations/connectors/source-apify-dataset/integration_tests/expected_records.jsonl

@@ -0,0 +1,2 @@
+{"stream": "datasets", "data": {"id":"Mxnvcv4Rspg9P9aP0","name":"my-dataset-name","userId":"YnGtyk7naKpwpousW","username":"encouraging_cliff","createdAt":"2023-08-25T19:19:33.588Z","modifiedAt":"2023-08-25T19:19:33.588Z","accessedAt":"2023-08-25T19:19:43.646Z","itemCount":0,"cleanItemCount":0,"actId":null,"actRunId":null,"schema":null,"stats":{"inflatedBytes":0,"readCount":0,"writeCount":0}}, "emitted_at": 1692990238010}
+{"stream": "dataset", "data": {"id":"Mxnvcv4Rspg9P9aP0","name":"my-dataset-name","userId":"YnGtyk7naKpwpousW","createdAt":"2023-08-25T19:19:33.588Z","modifiedAt":"2023-08-25T19:19:33.588Z","accessedAt":"2023-08-25T19:19:43.646Z","itemCount":0,"cleanItemCount":0,"actId":null,"actRunId":null,"schema":null,"stats":{"readCount":0,"writeCount":0,"storageBytes":0},"fields":[]}, "emitted_at": 1692990238010}

airbyte-integrations/connectors/source-apify-dataset/integration_tests/invalid_config.json

@@ -1,4 +1,4 @@
 {
-  "datasetId": "non_existent_dataset_id",
-  "clean": false
+  "token": "abc",
+  "start_date": "2099-08-25T00:00:59.244Z"
 }

airbyte-integrations/connectors/source-apify-dataset/integration_tests/sample_config.json

@@ -0,0 +1,4 @@
+{
+  "token": "apify_api_XXXXXXXXXXXXXXXXXXXX",
+  "start_date": "2023-08-25T00:00:59.244Z"
+}

airbyte-integrations/connectors/source-apify-dataset/integration_tests/sample_state.json

@@ -0,0 +1,9 @@
+[
+  {
+    "type": "STREAM",
+    "stream": {
+      "stream_state": { "modifiedAt": "3021-09-08T07:04:28.000Z" },
+      "stream_descriptor": { "name": "example" }
+    }
+  }
+]

airbyte-integrations/connectors/source-apify-dataset/metadata.yaml

@@ -1,24 +1,30 @@
 data:
+  allowedHosts:
+    hosts:
+      - api.apify.com
+  registries:
+    oss:
+      enabled: true
+    cloud:
+      enabled: true
   connectorSubtype: api
   connectorType: source
   definitionId: 47f17145-fe20-4ef5-a548-e29b048adf84
-  dockerImageTag: 0.2.0
+  dockerImageTag: 1.0.0
   dockerRepository: airbyte/source-apify-dataset
   githubIssueLabel: source-apify-dataset
-  icon: apify.svg
+  icon: apify-dataset.svg
   license: MIT
   name: Apify Dataset
-  registries:
-    cloud:
-      enabled: true
-    oss:
-      enabled: true
+  releaseDate: 2023-08-25
   releaseStage: alpha
+  releases:
+    breakingChanges:
+      1.0.0:
+        upgradeDeadline: 2023-08-30
+        message: "Update spec to use token and ingest all 3 streams correctly"
+  supportLevel: community
   documentationUrl: https://docs.airbyte.com/integrations/sources/apify-dataset
   tags:
-    - language:python
-  ab_internal:
-    sl: 100
-    ql: 100
-  supportLevel: community
+    - language:lowcode
 metadataSpecVersion: "1.0"