🎉 New Destination: Google Firestore (#7231)

* destination-firestore: add connector

* destination-firestore: Add connector to indexes in docs

* destination-firestore: fix sync mode spec

* destination-firestore: fix typo after connector rename

* destination-firestore: fix required field in spec

* destination firestore: fix code formatting

* destionation-firestore: add python adnotation for writer

* destination firestore: add all used libraries into the setup file

* destionation-firestore: fix python formatting

airbyte-integrations/builds.md

@@ -111,6 +111,8 @@
 | Databricks | (Temporarily Not Available) |
 | Elasticsearch | (Temporarily Not Available) |
 | Google Cloud Storage (GCS) | [![destination-gcs](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fdestination-gcs%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/destination-gcs) |
+| Google Firestore | [![destination-firestore](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fdestination-firestore%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/destination-firestore) |
+
 | Google PubSub   | [![destination-pubsub](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fdestination-pubsub%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/destination-pubsub) |
 | Kafka   | [![destination-kafka](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fdestination-kafka%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/destination-kafka) |
 | Keen (Chargify)   | [![destination-keen](https://img.shields.io/endpoint?url=https%3A%2F%2Fdnsgjos7lj2fu.cloudfront.net%2Ftests%2Fsummary%2Fdestination-keen%2Fbadge.json)](https://dnsgjos7lj2fu.cloudfront.net/tests/summary/destination-keen) |

airbyte-integrations/connectors/destination-firestore/.dockerignore

@@ -0,0 +1,5 @@
+*
+!Dockerfile
+!main.py
+!destination_firestore
+!setup.py

airbyte-integrations/connectors/destination-firestore/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 destination_firestore ./destination_firestore
+
+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/destination-firestore

airbyte-integrations/connectors/destination-firestore/README.md

@@ -0,0 +1,127 @@
+# Google Firestore Destination
+
+This is the repository for the Google Firestore destination connector, written in Python.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/destinations/firestore).
+
+## 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:
+```
+./gradlew :airbyte-integrations:connectors:destination-firestore:build
+```
+
+#### Create credentials
+
+**If you are a community contributor**, follow the instructions in the [documentation](https://cloud.google.com/iam/docs/creating-managing-service-accounts)
+to generate the necessary credentials. You might need to create a [new Firestore database](https://firebase.google.com/docs/firestore/quickstart#create). Then create a file `secrets/config.json` conforming to the `destination_firestore/spec.json` file.
+Note that the `secrets` directory is gitignored by default, 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 `destination firestore 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/destination-firestore:dev
+```
+
+You can also build the connector image via Gradle:
+```
+./gradlew :airbyte-integrations:connectors:destination-firestore: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/destination-firestore:dev spec
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/destination-firestore:dev check --config /secrets/config.json
+# messages.jsonl is a file containing line-separated JSON representing AirbyteMessages
+cat messages.jsonl | docker run --rm -v $(pwd)/secrets:/secrets -v $(pwd)/integration_tests:/integration_tests airbyte/destination-firestore:dev write --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 destination connectors) and custom integration tests (which are specific to this connector).
+
+Integration tests will most likely delete all your data credentials has access to. Limit service account permissions in a separate project.
+
+#### Custom Integration tests
+Place custom tests inside `integration_tests/` folder, then, from the connector root, run
+```
+python -m pytest integration_tests
+```
+#### Acceptance Tests
+Coming soon: 
+
+### Using gradle to run tests
+All commands should be run from airbyte project root.
+To run unit tests:
+```
+./gradlew :airbyte-integrations:connectors:destination-firestore:unitTest
+```
+To run acceptance and custom integration tests:
+```
+./gradlew :airbyte-integrations:connectors:destination-firestore: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/destination-firestore/build.gradle

@@ -0,0 +1,8 @@
+plugins {
+    id 'airbyte-python'
+    id 'airbyte-docker'
+}
+
+airbytePython {
+    moduleDirectory 'destinationfirestore'
+}

airbyte-integrations/connectors/destination-firestore/destination_firestore/__init__.py

@@ -0,0 +1,8 @@
+#
+# Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+#
+
+
+from .destination import DestinationFirestore
+
+__all__ = ["DestinationFirestore"]

airbyte-integrations/connectors/destination-firestore/destination_firestore/destination.py

@@ -0,0 +1,67 @@
+#
+# Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+#
+
+
+from typing import Any, Iterable, Mapping
+
+from airbyte_cdk import AirbyteLogger
+from airbyte_cdk.destinations import Destination
+from airbyte_cdk.models import AirbyteConnectionStatus, AirbyteMessage, ConfiguredAirbyteCatalog, DestinationSyncMode, Status, Type
+
+from .writer import FirestoreWriter
+
+
+class DestinationFirestore(Destination):
+    def write(
+        self, config: Mapping[str, Any], configured_catalog: ConfiguredAirbyteCatalog, input_messages: Iterable[AirbyteMessage]
+    ) -> Iterable[AirbyteMessage]:
+        """
+        TODO
+        Reads the input stream of messages, config, and catalog to write data to the destination.
+
+        This method returns an iterable (typically a generator of AirbyteMessages via yield) containing state messages received
+        in the input message stream. Outputting a state message means that every AirbyteRecordMessage which came before it has been
+        successfully persisted to the destination. This is used to ensure fault tolerance in the case that a sync fails before fully completing,
+        then the source is given the last state message output from this method as the starting point of the next sync.
+
+        :param config: dict of JSON configuration matching the configuration declared in spec.json
+        :param configured_catalog: The Configured Catalog describing the schema of the data being received and how it should be persisted in the
+                                    destination
+        :param input_messages: The stream of input messages received from the source
+        :return: Iterable of AirbyteStateMessages wrapped in AirbyteMessage structs
+        """
+        writer = FirestoreWriter(**config)
+
+        for configured_stream in configured_catalog.streams:
+            if configured_stream.destination_sync_mode == DestinationSyncMode.overwrite:
+                writer.purge(configured_stream.stream.name)
+
+        for message in input_messages:
+            if message.type == Type.STATE:
+                yield message
+            elif message.type == Type.RECORD:
+                record = message.record
+                writer.write(record.stream, record.data)
+            else:
+                # ignore other message types for now
+                continue
+
+    def check(self, logger: AirbyteLogger, config: Mapping[str, Any]) -> AirbyteConnectionStatus:
+        """
+        Tests if the input configuration can be used to successfully connect to the destination with the needed permissions
+            e.g: if a provided API token or password can be used to connect and write to the destination.
+
+        :param logger: Logging object to display debug/info/error to the logs
+            (logs will not be accessible via airbyte UI if they are not passed to this logger)
+        :param config: Json object containing the configuration of this destination, content of this json is as specified in
+        the properties of the spec.json file
+
+        :return: AirbyteConnectionStatus indicating a Success or Failure
+        """
+        try:
+            writer = FirestoreWriter(**config)
+            writer.check()
+            return AirbyteConnectionStatus(status=Status.SUCCEEDED)
+        except Exception as e:
+            return AirbyteConnectionStatus(status=Status.FAILED, message=f"An exception occurred: {repr(e)}")

airbyte-integrations/connectors/destination-firestore/destination_firestore/spec.json

@@ -0,0 +1,27 @@
+{
+  "documentationUrl": "https://docs.airbyte.io/integrations/destinations/firestore",
+  "supported_destination_sync_modes": ["append", "overwrite"],
+  "supportsIncremental": true,
+  "supportsDBT": false,
+  "supportsNormalization": false,
+  "connectionSpecification": {
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "title": "Destination Google Firestore",
+    "type": "object",
+    "required": ["project_id"],
+    "additionalProperties": false,
+    "properties": {
+      "project_id": {
+        "type": "string",
+        "description": "The GCP project ID for the project containing the target BigQuery dataset.",
+        "title": "Project ID"
+      },
+      "credentials_json": {
+        "type": "string",
+        "description": "The contents of the JSON service account key. Check out the <a href=\"https://docs.airbyte.io/integrations/destinations/firestore\">docs</a> if you need help generating this key. Default credentials will be used if this field is left empty.",
+        "title": "Credentials JSON",
+        "airbyte_secret": true
+      }
+    }
+  }
+}

airbyte-integrations/connectors/destination-firestore/destination_firestore/writer.py

@@ -0,0 +1,36 @@
+#
+# Copyright (c) 2021 Airbyte, Inc., all rights reserved.
+#
+
+import json
+from typing import Any, Dict, Optional
+
+from google.cloud import firestore
+from google.oauth2 import service_account
+
+
+class FirestoreWriter:
+    def __init__(self, project_id: str, credentials_json: Optional[str] = None):
+        connection = {}
+
+        connection["project"] = project_id
+
+        if credentials_json:
+            try:
+                json_account_info = json.loads(credentials_json)
+            except ValueError:
+                raise ValueError("The 'credentials_json' field must contain a valid JSON document with service account access data.")
+            credentials = service_account.Credentials.from_service_account_info(json_account_info)
+            connection["credentials"] = credentials
+
+        self.client = firestore.Client(**connection)
+
+    def check(self) -> bool:
+        return bool(list(self.client.collections()))
+
+    def write(self, stream: str, data: Dict[str, Any]) -> None:
+        self.client.collection(stream).add(data)
+
+    def purge(self, stream: str) -> None:
+        for doc in self.client.collection(stream).stream():
+            doc.reference.delete()