annotating-task-lineage

使用 Inlets 和 Outlets 标注任务血缘

本指南将带你通过 inlets 和 outlets，为 Airflow 任务添加手动血缘标注。

何时使用此方法

场景	使用 Inlets/Outlets？
操作符有 OpenLineage 方法	否，直接修改 OL 方法
操作符没有内置的 OpenLineage 提取器	是
简单的表级血缘已足够	是
无需自定义代码即可快速设置血缘	是
需要列级血缘	否，使用 OpenLineage 方法或自定义提取器
需要复杂的提取逻辑	否，使用 OpenLineage 方法或自定义提取器

Inlets/Outlets 支持的类型

OpenLineage 数据集（推荐）

from openlineage.client.event_v2 import Dataset

source_table = Dataset(
    namespace="postgres://mydb:5432",
    name="public.orders",
)

Airflow Assets（Airflow 3+）

from airflow.sdk import Asset

orders_asset = Asset(uri="s3://my-bucket/data/orders")

Airflow Datasets（Airflow 2.4+）

from airflow.datasets import Dataset

orders_dataset = Dataset(uri="s3://my-bucket/data/orders")

基本用法

在操作符上设置 Inlets 和 Outlets

from airflow import DAG
from airflow.operators.bash import BashOperator
from openlineage.client.event_v2 import Dataset
import pendulum

source_table = Dataset(namespace="snowflake://account", name="raw.orders")
target_table = Dataset(namespace="snowflake://account", name="staging.orders_clean")
output_file = Dataset(namespace="s3://my-bucket", name="exports/orders.parquet")

with DAG(
    dag_id="etl_with_lineage",
    start_date=pendulum.datetime(2024, 1, 1, tz="UTC"),
    schedule="@daily",
) as dag:

    transform = BashOperator(
        task_id="transform_orders",
        bash_command="echo 'transforming...'",
        inlets=[source_table],
        outlets=[target_table],
    )

    export = BashOperator(
        task_id="export_to_s3",
        bash_command="echo 'exporting...'",
        inlets=[target_table],
        outlets=[output_file],
    )

    transform >> export

多个输入和输出

from openlineage.client.event_v2 import Dataset

customers = Dataset(namespace="postgres://crm:5432", name="public.customers")
orders = Dataset(namespace="postgres://sales:5432", name="public.orders")
products = Dataset(namespace="postgres://inventory:5432", name="public.products")

daily_summary = Dataset(namespace="snowflake://account", name="analytics.daily_summary")
customer_metrics = Dataset(namespace="snowflake://account", name="analytics.customer_metrics")

aggregate_task = PythonOperator(
    task_id="build_daily_aggregates",
    python_callable=build_aggregates,
    inlets=[customers, orders, products],
    outlets=[daily_summary, customer_metrics],
)

自定义操作符

选项 1：实现 OpenLineage 方法（推荐）

from airflow.models import BaseOperator

class MyCustomOperator(BaseOperator):
    def __init__(self, source_table: str, target_table: str, **kwargs):
        super().__init__(**kwargs)
        self.source_table = source_table
        self.target_table = target_table

    def execute(self, context):
        self.log.info(f"Processing {self.source_table} -> {self.target_table}")

    def get_openlineage_facets_on_complete(self, task_instance):
        from openlineage.client.event_v2 import Dataset
        from airflow.providers.openlineage.extractors import OperatorLineage

        return OperatorLineage(
            inputs=[Dataset(namespace="warehouse://db", name=self.source_table)],
            outputs=[Dataset(namespace="warehouse://db", name=self.target_table)],
        )

选项 2：动态设置 Inlets/Outlets

from airflow.models import BaseOperator
from openlineage.client.event_v2 import Dataset

class MyCustomOperator(BaseOperator):
    def __init__(self, source_table: str, target_table: str, **kwargs):
        super().__init__(**kwargs)
        self.source_table = source_table
        self.target_table = target_table

    def execute(self, context):
        self.inlets = [Dataset(namespace="warehouse://db", name=self.source_table)]
        self.outlets = [Dataset(namespace="warehouse://db", name=self.target_table)]