catalogue SeaweedFS

{
  "identities": [
    {
      "name": "analyst",
      "credentials": [
        {
          "accessKey": "tutorialkey",
          "secretKey": "tutorialsecret"
        }
      ],
      "actions": ["Admin", "Read", "Write", "List", "Tagging"]
    }
  ]
}

services:
  seaweedfs:
    image: chrislusf/seaweedfs:latest
    command: mini -dir=/data -s3.config=/etc/seaweedfs/s3config.json -tableBucket=analytics
    ports:
      - "8333:8333"   # S3 endpoint
      - "8181:8181"   # Iceberg REST catalog
    volumes:
      - ./s3config.json:/etc/seaweedfs/s3config.json
      - seaweedfs_data:/data
    networks:
      - iceberg_net

  clickhouse:
    image: clickhouse/clickhouse-server:latest
    container_name: seaweedfs-clickhouse
    ports:
      - "8123:8123"
      - "9000:9000"
    depends_on:
      - seaweedfs
    networks:
      - iceberg_net

volumes:
  seaweedfs_data:

networks:
  iceberg_net:
    driver: bridge

docker compose up -d

import pyarrow as pa
from pyiceberg.catalog.rest import RestCatalog

catalog = RestCatalog(
    "seaweedfs",
    uri="http://localhost:8181",
    warehouse="s3://analytics",
    credential="tutorialkey:tutorialsecret",
    **{
        "s3.endpoint": "http://localhost:8333",
        "s3.access-key-id": "tutorialkey",
        "s3.secret-access-key": "tutorialsecret",
        "s3.region": "us-east-1",
        "s3.path-style-access": "true",
    },
)

rows = pa.table({
    "id": pa.array([1, 2, 3, 4, 5, 6], pa.int64()),
    "region": ["NA", "EU", "EU", "APAC", "NA", "EU"],
    "amount": pa.array([12.5, 40.0, 7.25, 99.9, 3.5, 61.0], pa.float64()),
})

catalog.create_namespace("sales")
table = catalog.create_table("sales.orders", schema=rows.schema)
table.append(rows)

docker exec -it seaweedfs-clickhouse clickhouse-client

SET allow_experimental_database_iceberg = 1;

CREATE DATABASE lake
ENGINE = DataLakeCatalog('http://seaweedfs:8181/v1', 'tutorialkey', 'tutorialsecret')
SETTINGS catalog_type = 'rest',
    warehouse = 's3://analytics',
    storage_endpoint = 'http://seaweedfs:8333/analytics',
    catalog_credential = 'tutorialkey:tutorialsecret',
    oauth_server_uri = 'http://seaweedfs:8181/v1/oauth/tokens'

USE lake;

SHOW TABLES;

┌─name─────────┐
│ sales.orders │
└──────────────┘

SELECT region, sum(amount) AS total
FROM `sales.orders`
GROUP BY region
ORDER BY total DESC;

┌─region─┬──total─┐
│ EU     │ 108.25 │
│ APAC   │   99.9 │
│ NA     │     16 │
└────────┴────────┘

SET allow_experimental_database_iceberg = 1;
SET allow_experimental_insert_into_iceberg = 1;
SET write_full_path_in_iceberg_metadata = 1;

CREATE TABLE lake.`sales.returns` (id Int64, reason String)
ENGINE = IcebergS3('http://seaweedfs:8333/analytics/sales/returns/', 'tutorialkey', 'tutorialsecret');

INSERT INTO lake.`sales.returns` VALUES (1, 'damaged'), (2, 'wrong size');

SELECT * FROM lake.`sales.returns` ORDER BY id;

┌─id─┬─reason─────┐
│  1 │ damaged    │
│  2 │ wrong size │
└────┴────────────┘

CREATE TABLE default.orders
(
    `id` Int64,
    `region` String,
    `amount` Float64
)
ENGINE = MergeTree()
ORDER BY (region, id);

INSERT INTO default.orders
SELECT * FROM lake.`sales.orders`;