🎉 New Source: Notion (airbytehq#7092)

* add source notion

* update PR number in change log

* bug fix and code improvement as code review suggestions

* code improvement as review advices

* new connector notion

* format

* correct creds file

* run seed

* bump connector version

* format

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

airbyte-config/init/src/main/resources/config/STANDARD_SOURCE_DEFINITION/6e00b415-b02e-4160-bf02-58176a0ae687.json

@@ -0,0 +1,7 @@
+{
+  "sourceDefinitionId": "6e00b415-b02e-4160-bf02-58176a0ae687",
+  "name": "Notion",
+  "dockerRepository": "airbyte/source-notion",
+  "dockerImageTag": "0.1.0",
+  "documentationUrl": "https://hub.docker.com/r/airbyte/source-notion"
+}

airbyte-config/init/src/main/resources/seed/source_definitions.yaml

@@ -370,6 +370,12 @@
   documentationUrl: https://docs.airbyte.io/integrations/sources/mysql
   icon: mysql.svg
   sourceType: database
+- name: Notion
+  sourceDefinitionId: 6e00b415-b02e-4160-bf02-58176a0ae687
+  dockerRepository: airbyte/source-notion
+  dockerImageTag: 0.1.0
+  documentationUrl: https://docs.airbyte.io/integrations/sources/notion
+  sourceType: api
 - name: Okta
   sourceDefinitionId: 1d4fdb25-64fc-4569-92da-fcdca79a8372
   dockerRepository: airbyte/source-okta

airbyte-config/init/src/main/resources/seed/source_specs.yaml

@@ -3841,6 +3841,34 @@
     supportsNormalization: false
     supportsDBT: false
     supported_destination_sync_modes: []
+- dockerImage: "airbyte/source-notion:0.1.0"
+  spec:
+    documentationUrl: "https://docsurl.com"
+    connectionSpecification:
+      $schema: "http://json-schema.org/draft-07/schema#"
+      title: "Notion Source Spec"
+      type: "object"
+      required:
+      - "access_token"
+      - "start_date"
+      additionalProperties: false
+      properties:
+        access_token:
+          type: "string"
+          description: "Notion API access token, see the <a href=\"https://developers.notion.com/docs/authorization\"\
+            >docs</a> for more information on how to obtain this token."
+          airbyte_secret: true
+        start_date:
+          type: "string"
+          description: "The date from which you'd like to replicate data for Notion\
+            \ API, in the format YYYY-MM-DDT00:00:00.000Z. All data generated after\
+            \ this date will be replicated."
+          examples:
+          - "2020-11-16T00:00:00.000Z"
+          pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}.[0-9]{3}Z$"
+    supportsNormalization: false
+    supportsDBT: false
+    supported_destination_sync_modes: []
 - dockerImage: "airbyte/source-okta:0.1.4"
   spec:
     documentationUrl: "https://docs.airbyte.io/integrations/sources/okta"

airbyte-integrations/builds.md

@@ -59,6 +59,7 @@
 | Mongo DB  | [![source-mongodb-v2](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-mongodb-v2%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-mongodb-v2) |
 | Monday  | [![source-monday](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-monday%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-monday) |
 | MySQL   | [![source-mysql](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-mysql%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-mysql) |
+| Notion   | [![source-notion](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-notion%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-notion) |
 | OneSignal   | [![source-onesignal](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-onesignal%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-onesignal) |
 | Oracle DB   | [![source-oracle](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-oracle%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-oracle) |
 | Paypal Transaction   | [![paypal-transaction](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fsource-paypal-transaction%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/source-paypal-transaction) |

airbyte-integrations/connectors/destination-e2e-test/src/main/java/io/airbyte/integrations/destination/e2e_test/FailAfterNDestination.java

@@ -1,6 +1,8 @@
-package io.airbyte.integrations.destination.e2e_test;
+/*
+ * Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+ */
 
-import static java.lang.Thread.sleep;
+package io.airbyte.integrations.destination.e2e_test;
 
 import com.fasterxml.jackson.databind.JsonNode;
 import io.airbyte.integrations.BaseConnector;
@@ -26,8 +28,8 @@ public AirbyteConnectionStatus check(final JsonNode config) {
 
   @Override
   public AirbyteMessageConsumer getConsumer(final JsonNode config,
-      final ConfiguredAirbyteCatalog catalog,
-      final Consumer<AirbyteMessage> outputRecordCollector) {
+                                            final ConfiguredAirbyteCatalog catalog,
+                                            final Consumer<AirbyteMessage> outputRecordCollector) {
     return new FailAfterNConsumer(config.get("num_messages").asLong(), outputRecordCollector);
   }
 
@@ -66,4 +68,5 @@ public void accept(final AirbyteMessage message) throws Exception {
     public void close() {}
 
   }
+
 }

airbyte-integrations/connectors/source-notion/.dockerignore

@@ -0,0 +1,7 @@
+*
+!Dockerfile
+!Dockerfile.test
+!main.py
+!source_notion
+!setup.py
+!secrets

airbyte-integrations/connectors/source-notion/Dockerfile

@@ -0,0 +1,38 @@
+FROM python:3.7.11-alpine3.14 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
+
+
+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 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 source_notion ./source_notion
+
+ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
+ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
+
+LABEL io.airbyte.version=0.1.0
+LABEL io.airbyte.name=airbyte/source-notion

airbyte-integrations/connectors/source-notion/README.md

@@ -0,0 +1,132 @@
+# Notion Source
+
+This is the repository for the Notion source connector, written in Python.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/sources/notion).
+
+## 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
+pip install '.[tests]'
+```
+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
+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-notion:build
+```
+
+#### Create credentials
+**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.io/integrations/sources/notion)
+to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `source_notion/spec.json` 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.
+
+**If you are an Airbyte core member**, copy the credentials in Lastpass under the secret name `source notion 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
+First, make sure you build the latest Docker image:
+```
+docker build . -t airbyte/source-notion:dev
+```
+
+You can also build the connector image via Gradle:
+```
+./gradlew :airbyte-integrations:connectors:source-notion:airbyteDocker
+```
+When building via Gradle, the docker image name and tag, respectively, are the values of the `io.airbyte.name` and `io.airbyte.version` `LABEL`s in
+the Dockerfile.
+
+#### Run
+Then run any of the connector commands as follows:
+```
+docker run --rm airbyte/source-notion:dev spec
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/source-notion:dev check --config /secrets/config.json
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/source-notion:dev discover --config /secrets/config.json
+docker run --rm -v $(pwd)/secrets:/secrets -v $(pwd)/integration_tests:/integration_tests airbyte/source-notion: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 [Source Acceptance Tests](https://docs.airbyte.io/connector-development/testing-connectors/source-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
+```
+python -m pytest integration_tests -p integration_tests.acceptance
+```
+To run your integration tests with docker
+
+### Using gradle to run tests
+All commands should be run from airbyte project root.
+To run unit tests:
+```
+./gradlew :airbyte-integrations:connectors:source-notion:unitTest
+```
+To run acceptance and custom integration tests:
+```
+./gradlew :airbyte-integrations:connectors:source-notion:integrationTest
+```
+
+## Dependency Management
+All of your dependencies should go in `setup.py`, NOT `requirements.txt`. The requirements file is only used to connect internal Airbyte dependencies in the monorepo for local development.
+We split dependencies between two groups, dependencies that are:
+* required for your connector to work need to go to `MAIN_REQUIREMENTS` list.
+* required for the testing need to go to `TEST_REQUIREMENTS` list
+
+### Publishing a new version of the connector
+You've checked out the repo, implemented a million dollar feature, and you're ready to share your changes with the world. Now what?
+1. Make sure your changes are passing unit and integration tests.
+1. Bump the connector version in `Dockerfile` -- just increment the value of the `LABEL io.airbyte.version` appropriately (we use [SemVer](https://semver.org/)).
+1. Create a Pull Request.
+1. Pat yourself on the back for being an awesome contributor.
+1. Someone from Airbyte will take a look at your PR and iterate with you to merge it into master.

airbyte-integrations/connectors/source-notion/acceptance-test-config.yml

@@ -0,0 +1,26 @@
+# See [Source Acceptance Tests](https://docs.airbyte.io/connector-development/testing-connectors/source-acceptance-tests-reference)
+# for more information about how to configure these tests
+connector_image: airbyte/source-notion:dev
+tests:
+  spec:
+    - spec_path: "source_notion/spec.json"
+  connection:
+    - config_path: "secrets/config.json"
+      status: "succeed"
+    - config_path: "integration_tests/invalid_config.json"
+      status: "failed"
+  discovery:
+    - config_path: "secrets/config.json"
+  basic_read:
+    - config_path: "secrets/config.json"
+      configured_catalog_path: "integration_tests/configured_catalog.json"
+      empty_streams: []
+  incremental:
+    - config_path: "secrets/config.json"
+      configured_catalog_path: "integration_tests/configured_catalog.json"
+      future_state_path: "integration_tests/abnormal_state.json"
+  full_refresh:
+    - config_path: "secrets/config.json"
+      configured_catalog_path: "integration_tests/configured_catalog.json"
+      ignored_fields:
+        "pages": ["icon"]

airbyte-integrations/connectors/source-notion/acceptance-test-docker.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env sh
+
+# Build latest connector image
+docker build . -t $(cat acceptance-test-config.yml | grep "connector_image" | head -n 1 | cut -d: -f2)
+
+# Pull latest acctest image
+docker pull airbyte/source-acceptance-test:latest
+
+# Run
+docker run --rm -it \
+    -v /var/run/docker.sock:/var/run/docker.sock \
+    -v /tmp:/tmp \
+    -v $(pwd):/test_input \
+    airbyte/source-acceptance-test \
+    --acceptance-test-config /test_input
+

airbyte-integrations/connectors/source-notion/bootstrap.md

@@ -0,0 +1,32 @@
+# Notion
+
+## Overview
+
+Notion is an application that provides components such as notes, databases, kanban boards, wikis, calendars and reminders. Notion REST API allows a developer to retrieve pages, databases, blocks, and users on the Notion platform.
+
+## Endpoints
+
+Notion API consists of three endpoints which can be extracted data from:
+
+1. **User**: The User object represents a user in a Notion workspace. Users include guests, full workspace members, and bots.
+2. **Block**: A block object represents content within Notion. Blocks can be text, lists, media, and more. Page and database is also a type of block.
+3. **Search**: This endpoint is used to get list of pages and databases.
+
+## Quick Notes
+
+- Notion stores content in hierarchy, each node is called a 'block'. Block is a generic term which can be text, lists, media, even page and database are also block.
+
+- Due to this hierarchical structure, we use recursive request to get the full list of blocks.
+
+- Pages and databases can be extracted from the `Search` endpoint separately, so they are excluded from the block list request.
+
+- Airbyte CDK doesn't support recursive schema, so some elements of the block schema which can be recursive are replaced with empty objects.
+
+- Page and database must grant permission to the internal integration, otherwise API cannot extract data from them. See [https://developers.notion.com/docs/authorization#authorizing-internal-integrations](https://developers.notion.com/docs/authorization#authorizing-internal-integrations)
+
+- Rate limiting is a standard exponential backoff when a 429 HTTP status code returned. The rate limit for incoming requests is an average of 3 requests per second. Some bursts beyond the average rate are allowed. Notion API also has size limit, see [https://developers.notion.com/reference/errors#request-limits](https://developers.notion.com/reference/errors#request-limits)
+
+## API Reference
+
+The API reference documents: [https://developers.notion.com/reference/intro](https://developers.notion.com/reference)
+

airbyte-integrations/connectors/source-notion/build.gradle

@@ -0,0 +1,14 @@
+plugins {
+    id 'airbyte-python'
+    id 'airbyte-docker'
+    id 'airbyte-source-acceptance-test'
+}
+
+airbytePython {
+    moduleDirectory 'source_notion'
+}
+
+dependencies {
+    implementation files(project(':airbyte-integrations:bases:source-acceptance-test').airbyteDocker.outputs)
+    implementation files(project(':airbyte-integrations:bases:base-python').airbyteDocker.outputs)
+}

airbyte-integrations/connectors/source-notion/integration_tests/__init__.py

@@ -0,0 +1,3 @@
+#
+# Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+#

airbyte-integrations/connectors/source-notion/integration_tests/abnormal_state.json

@@ -0,0 +1,11 @@
+{
+  "databases": {
+    "last_edited_time": "2099-10-10T04:40:00.000Z"
+  },
+  "pages": {
+    "last_edited_time": "2099-10-10T04:40:00.000Z"
+  },
+  "blocks": {
+    "last_edited_time": "2099-10-10T04:00:00.000Z"
+  }
+}

airbyte-integrations/connectors/source-notion/integration_tests/acceptance.py

@@ -0,0 +1,14 @@
+#
+# Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+#
+
+
+import pytest
+
+pytest_plugins = ("source_acceptance_test.plugin",)
+
+
+@pytest.fixture(scope="session", autouse=True)
+def connector_setup():
+    """This fixture is a placeholder for external resources that acceptance test might require."""
+    yield