🎉 New Destination: Typesense (#18349)

* Initial boilerplate

* 🎉 New Destination: Typesense

* remove .java-version

* fix doc

* add typesense to dest def

* add release stage

* add requirement to main

* auto-bump connector version

* add changelog

Co-authored-by: marcosmarxm <marcosmarxm@gmail.com>
Co-authored-by: Marcos Marx <marcosmarxm@users.noreply.github.com>
Co-authored-by: Octavia Squidington III <octavia-squidington-iii@users.noreply.github.com>

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

@@ -329,6 +329,12 @@
   documentationUrl: https://docs.airbyte.com/integrations/destinations/tidb
   icon: tidb.svg
   releaseStage: alpha
+- name: Typesense
+  destinationDefinitionId: 36be8dc6-9851-49af-b776-9d4c30e4ab6a
+  dockerRepository: airbyte/destination-typesense
+  dockerImageTag: 0.1.0
+  documentationUrl: https://docs.airbyte.com/integrations/destinations/typesense
+  releaseStage: alpha
 - name: YugabyteDB
   destinationDefinitionId: 2300fdcf-a532-419f-9f24-a014336e7966
   dockerRepository: airbyte/destination-yugabytedb

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

@@ -6145,6 +6145,51 @@
     supported_destination_sync_modes:
     - "overwrite"
     - "append"
+- dockerImage: "airbyte/destination-typesense:0.1.0"
+  spec:
+    documentationUrl: "https://docs.airbyte.com/integrations/destinations/typesense"
+    connectionSpecification:
+      $schema: "http://json-schema.org/draft-07/schema#"
+      title: "Destination Typesense"
+      type: "object"
+      required:
+      - "api_key"
+      - "host"
+      additionalProperties: false
+      properties:
+        api_key:
+          title: "API Key"
+          type: "string"
+          description: "Typesense API Key"
+          order: 0
+        host:
+          title: "Host"
+          type: "string"
+          description: "Hostname of the Typesense instance without protocol."
+          order: 1
+        port:
+          title: "Port"
+          type: "string"
+          description: "Port of the Typesense instance. Ex: 8108, 80, 443. Default\
+            \ is 443"
+          order: 2
+        protocol:
+          title: "Protocol"
+          type: "string"
+          description: "Protocol of the Typesense instance. Ex: http or https. Default\
+            \ is https"
+          order: 3
+        batch_size:
+          title: "Batch size"
+          type: "string"
+          description: "How many documents should be imported together. Default 1000"
+          order: 4
+    supportsIncremental: true
+    supportsNormalization: false
+    supportsDBT: false
+    supported_destination_sync_modes:
+    - "overwrite"
+    - "append"
 - dockerImage: "airbyte/destination-yugabytedb:0.1.0"
   spec:
     documentationUrl: "https://docs.airbyte.io/integrations/destinations/yugabytedb"

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

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

airbyte-integrations/connectors/destination-typesense/Dockerfile

@@ -0,0 +1,38 @@
+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
+
+
+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_typesense ./destination_typesense
+
+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-typesense

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

@@ -0,0 +1,123 @@
+# Typesense Destination
+
+This is the repository for the Typesense destination connector, written in Python.
+For information about how to use this connector within Airbyte, see [the documentation](https://docs.airbyte.io/integrations/destinations/typesense).
+
+## 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-typesense:build
+```
+
+#### Create credentials
+**If you are a community contributor**, follow the instructions in the [documentation](https://docs.airbyte.io/integrations/destinations/typesense)
+to generate the necessary credentials. Then create a file `secrets/config.json` conforming to the `destination_typesense/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 typesense 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-typesense:dev
+```
+
+You can also build the connector image via Gradle:
+```
+./gradlew :airbyte-integrations:connectors:destination-typesense: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-typesense:dev spec
+docker run --rm -v $(pwd)/secrets:/secrets airbyte/destination-typesense: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-typesense: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).
+#### 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-typesense:unitTest
+```
+To run acceptance and custom integration tests:
+```
+./gradlew :airbyte-integrations:connectors:destination-typesense: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-typesense/build.gradle

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

airbyte-integrations/connectors/destination-typesense/destination_typesense/__init__.py

@@ -0,0 +1,8 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+
+from .destination import DestinationTypesense
+
+__all__ = ["DestinationTypesense"]

airbyte-integrations/connectors/destination-typesense/destination_typesense/destination.py

@@ -0,0 +1,61 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+
+from logging import Logger
+from typing import Any, Iterable, Mapping
+
+from airbyte_cdk.destinations import Destination
+from airbyte_cdk.models import AirbyteConnectionStatus, AirbyteMessage, ConfiguredAirbyteCatalog, DestinationSyncMode, Status, Type
+from destination_typesense.writer import TypesenseWriter
+from typesense import Client
+
+
+def get_client(config: Mapping[str, Any]) -> Client:
+    api_key = config.get("api_key")
+    host = config.get("host")
+    port = config.get("port") or "8108"
+    protocol = config.get("protocol") or "https"
+
+    client = Client({"api_key": api_key, "nodes": [{"host": host, "port": port, "protocol": protocol}], "connection_timeout_seconds": 2})
+
+    return client
+
+
+class DestinationTypesense(Destination):
+    def write(
+        self, config: Mapping[str, Any], configured_catalog: ConfiguredAirbyteCatalog, input_messages: Iterable[AirbyteMessage]
+    ) -> Iterable[AirbyteMessage]:
+        client = get_client(config=config)
+
+        for configured_stream in configured_catalog.streams:
+            steam_name = configured_stream.stream.name
+            if configured_stream.destination_sync_mode == DestinationSyncMode.overwrite:
+                try:
+                    client.collections[steam_name].delete()
+                except Exception:
+                    pass
+                client.collections.create({"name": steam_name, "fields": [{"name": ".*", "type": "auto"}]})
+
+            writer = TypesenseWriter(client, steam_name, config.get("batch_size"))
+            for message in input_messages:
+                if message.type == Type.STATE:
+                    writer.flush()
+                    yield message
+                elif message.type == Type.RECORD:
+                    writer.queue_write_operation(message.record.data)
+                else:
+                    continue
+            writer.flush()
+
+    def check(self, logger: Logger, config: Mapping[str, Any]) -> AirbyteConnectionStatus:
+        try:
+            client = get_client(config=config)
+            client.collections.create({"name": "_airbyte", "fields": [{"name": "title", "type": "string"}]})
+            client.collections["_airbyte"].documents.create({"id": "1", "title": "The Hunger Games"})
+            client.collections["_airbyte"].documents["1"].retrieve()
+            client.collections["_airbyte"].delete()
+            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-typesense/destination_typesense/spec.json

@@ -0,0 +1,46 @@
+{
+  "documentationUrl": "https://docs.airbyte.com/integrations/destinations/typesense",
+  "supported_destination_sync_modes": ["overwrite", "append"],
+  "supportsIncremental": true,
+  "supportsDBT": false,
+  "supportsNormalization": false,
+  "connectionSpecification": {
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "title": "Destination Typesense",
+    "type": "object",
+    "required": ["api_key", "host"],
+    "additionalProperties": false,
+    "properties": {
+      "api_key": {
+        "title": "API Key",
+        "type": "string",
+        "description": "Typesense API Key",
+        "order": 0
+      },
+      "host": {
+        "title": "Host",
+        "type": "string",
+        "description": "Hostname of the Typesense instance without protocol.",
+        "order": 1
+      },
+      "port": {
+        "title": "Port",
+        "type": "string",
+        "description": "Port of the Typesense instance. Ex: 8108, 80, 443. Default is 443",
+        "order": 2
+      },
+      "protocol": {
+        "title": "Protocol",
+        "type": "string",
+        "description": "Protocol of the Typesense instance. Ex: http or https. Default is https",
+        "order": 3
+      },
+      "batch_size": {
+        "title": "Batch size",
+        "type": "string",
+        "description": "How many documents should be imported together. Default 1000",
+        "order": 4
+      }
+    }
+  }
+}

airbyte-integrations/connectors/destination-typesense/destination_typesense/writer.py

@@ -0,0 +1,35 @@
+#
+# Copyright (c) 2022 Airbyte, Inc., all rights reserved.
+#
+
+from collections.abc import Mapping
+from logging import getLogger
+from uuid import uuid4
+
+from typesense import Client
+
+logger = getLogger("airbyte")
+
+
+class TypesenseWriter:
+    write_buffer = []
+
+    def __init__(self, client: Client, steam_name: str, batch_size: int = 1000):
+        self.client = client
+        self.steam_name = steam_name
+        self.batch_size = batch_size
+
+    def queue_write_operation(self, data: Mapping):
+        random_key = str(uuid4())
+        data_with_id = data if "id" in data else {**data, "id": random_key}
+        self.write_buffer.append(data_with_id)
+        if len(self.write_buffer) == self.batch_size:
+            self.flush()
+
+    def flush(self):
+        buffer_size = len(self.write_buffer)
+        if buffer_size == 0:
+            return
+        logger.info(f"flushing {buffer_size} records")
+        self.client.collections[self.steam_name].documents.import_(self.write_buffer)
+        self.write_buffer.clear()