annotating-task-lineage

from airflow.sdk import Asset
 
# Using Airflow's native Asset type
orders_asset = Asset(uri="s3://my-bucket/data/orders")

from airflow.datasets import Dataset
 
# Using Airflow's Dataset type (Airflow 2.4-2.x)
orders_dataset = Dataset(uri="s3://my-bucket/data/orders")

from airflow import DAG
from airflow.operators.bash import BashOperator
from openlineage.client.event_v2 import Dataset
import pendulum
 
# Define your lineage datasets
source_table = Dataset(
    namespace="snowflake://account.snowflakecomputing.com",
    name="raw.orders",
)
target_table = Dataset(
    namespace="snowflake://account.snowflakecomputing.com",
    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],           # What this task reads
        outlets=[target_table],          # What this task writes
    )
 
    export = BashOperator(
        task_id="export_to_s3",
        bash_command="echo 'exporting...'",
        inlets=[target_table],           # Reads from previous output
        outlets=[output_file],           # Writes to S3
    )
 
    transform >> export

from openlineage.client.event_v2 import Dataset
 
# Multiple source tables
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")
 
# Multiple output tables
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],      # All inputs
    outlets=[daily_summary, customer_metrics], # All outputs
)

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):
        # ... perform the actual work ...
        self.log.info(f"Processing {self.source_table} -> {self.target_table}")
 
    def get_openlineage_facets_on_complete(self, task_instance):
        """Return lineage after successful execution."""
        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)],
        )

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):
        # Set lineage dynamically based on operator parameters
        self.inlets = [
            Dataset(namespace="warehouse://db", name=self.source_table)
        ]
        self.outlets = [
            Dataset(namespace="warehouse://db", name=self.target_table)
        ]
 
        # ... perform the actual work ...
        self.log.info(f"Processing {self.source_table} -> {self.target_table}")

from openlineage.client.event_v2 import Dataset
 
# Snowflake
from openlineage.client.naming.snowflake import SnowflakeDatasetNaming
 
naming = SnowflakeDatasetNaming(
    account_identifier="myorg-myaccount",
    database="mydb",
    schema="myschema",
    table="mytable",
)
dataset = Dataset(namespace=naming.get_namespace(), name=naming.get_name())
# -> namespace: "snowflake://myorg-myaccount", name: "mydb.myschema.mytable"
 
# BigQuery
from openlineage.client.naming.bigquery import BigQueryDatasetNaming
 
naming = BigQueryDatasetNaming(
    project="my-project",
    dataset="my_dataset",
    table="my_table",
)
dataset = Dataset(namespace=naming.get_namespace(), name=naming.get_name())
# -> namespace: "bigquery", name: "my-project.my_dataset.my_table"
 
# S3
from openlineage.client.naming.s3 import S3DatasetNaming
 
naming = S3DatasetNaming(bucket="my-bucket", key="path/to/file.parquet")
dataset = Dataset(namespace=naming.get_namespace(), name=naming.get_name())
# -> namespace: "s3://my-bucket", name: "path/to/file.parquet"
 
# PostgreSQL
from openlineage.client.naming.postgres import PostgresDatasetNaming
 
naming = PostgresDatasetNaming(
    host="localhost",
    port=5432,
    database="mydb",
    schema="public",
    table="users",
)
dataset = Dataset(namespace=naming.get_namespace(), name=naming.get_name())
# -> namespace: "postgres://localhost:5432", name: "mydb.public.users"

from openlineage.client.event_v2 import Dataset
from openlineage.client.naming.snowflake import SnowflakeDatasetNaming
 
 
def snowflake_dataset(schema: str, table: str) -> Dataset:
    """Create a Snowflake Dataset using the naming helper."""
    naming = SnowflakeDatasetNaming(
        account_identifier="mycompany",
        database="analytics",
        schema=schema,
        table=table,
    )
    return Dataset(namespace=naming.get_namespace(), name=naming.get_name())
 
 
# Usage
source = snowflake_dataset("raw", "orders")
target = snowflake_dataset("staging", "orders_clean")

transform = SqlOperator(
    task_id="transform_orders",
    sql="...",
    # Lineage: Reads raw orders, joins with customers, writes to staging
    inlets=[
        snowflake_dataset("raw", "orders"),
        snowflake_dataset("raw", "customers"),
    ],
    outlets=[
        snowflake_dataset("staging", "order_details"),
    ],
)