{"id":39016,"date":"2025-05-21T22:04:23","date_gmt":"2025-05-21T14:04:23","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/39016.html"},"modified":"2025-05-21T22:04:23","modified_gmt":"2025-05-21T14:04:23","slug":"%e5%bd%93-pyiceberg-%e5%92%8c-duckdb-%e9%81%87%e8%a7%81-aws-s3-tables%ef%bc%9a%e6%89%93%e9%80%a0-serverless-%e6%95%b0%e6%8d%ae%e6%b9%96%e5%bc%80%e6%ba%90%e6%a2%a6%e5%b9%bb%e7%bb%84%e5%90%88","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/39016.html","title":{"rendered":"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d"},"content":{"rendered":"

\u5f15\u8a00<\/h3>\n

\u5728\u4e00\u4e9b\u5927\u6570\u636e\u5206\u6790\u573a\u666f\u6bd4\u5982\u7535\u5546\u5927\u6570\u636e\u8425\u9500\u4e2d，\u6211\u4eec\u9700\u8981\u5feb\u901f\u5206\u6790\u5b58\u50a8\u6d77\u91cf\u7528\u6237\u884c\u4e3a\u6570\u636e（\u5982\u6d4f\u89c8\u3001\u52a0\u8d2d\u3001\u4e0b\u5355），\u4ee5\u8fdb\u884c\u7528\u6237\u884c\u4e3a\u5206\u6790，\u4f18\u5316\u8425\u9500\u7b56\u7565\u3002\u4f20\u7edf\u65b9\u6cd5\u4f9d\u8d56 Spark\/Presto \u96c6\u7fa4\u6216 Redshift \u67e5\u8be2 S3 \u4e0a\u7684 Parquet\/ORC \u6587\u4ef6，\u8fd9\u5bf9\u4e8e\u9700\u8981\u5feb\u901f\u8fed\u4ee3\u3001\u6309\u9700\u6267\u884c\u7684\u5206\u6790\u6765\u8bf4，\u6210\u672c\u9ad8\u3001\u8fd0\u7ef4\u590d\u6742\u4e14\u54cd\u5e94\u4e0d\u591f\u654f\u6377\u3002<\/p>\n

\u672c\u6587\u5c06\u4ecb\u7ecd\u4e00\u79cd\u73b0\u4ee3\u5316\u7684 Serverless \u89e3\u51b3\u65b9\u6848：\u5229\u7528 S3 Tables（\u5185\u7f6e\u4f18\u5316\u7684 Apache Iceberg \u652f\u6301）\u4f5c\u4e3a\u5b58\u50a8\u57fa\u7840，\u5e76\u7ed3\u5408 PyIceberg \u7684\u4fbf\u6377\u6027\u4e0e DuckDB \u7684\u9ad8\u6027\u80fd\u5d4c\u5165\u5f0f\u5206\u6790\u80fd\u529b，\u76f4\u63a5\u5728 AWS Lambda \u7b49\u73af\u5883\u4e2d\u5b9e\u73b0\u5bf9 S3 \u6570\u636e\u7684\u4f4e\u6210\u672c\u3001\u9ad8\u6548\u7387\u5373\u65f6\u67e5\u8be2，\u5f7b\u5e95\u6446\u8131\u96c6\u7fa4\u8fd0\u7ef4\u7684\u8d1f\u62c5，\u52a0\u901f\u60a8\u7684\u7528\u6237\u884c\u4e3a\u5206\u6790\u3002\u5173\u952e\u5de5\u5177\u53ca\u6280\u672f\u70b9：<\/p>\n

  • S3 Tables：\u5728 S3 \u4e0a\u4e3a\u8868\u683c\u6570\u636e（\u91c7\u7528\u5185\u5efa\u4f18\u5316\u7684 Apache Iceberg \u683c\u5f0f）\u8bbe\u8ba1\u7684\u3001\u5177\u5907\u81ea\u52a8\u6027\u80fd\u4f18\u5316\u7684\u667a\u80fd\u5bf9\u8c61\u5b58\u50a8\u3002<\/li>\n
  • Lambda：\u63d0\u4f9b\u6309\u9700\u8fd0\u884c\u4ee3\u7801\u7684\u65e0\u670d\u52a1\u5668\u8ba1\u7b97\u80fd\u529b<\/li>\n
  • PyIceberg：Iceberg \u5b98\u65b9\u5f00\u6e90\u9879\u76ee，\u63d0\u4f9b\u7b80\u6d01\u7684 Python API \u6765\u64cd\u4f5c Iceberg \u8868<\/li>\n
  • DuckDB：\u9ad8\u6027\u80fd\u5d4c\u5165\u5f0f\u5206\u6790\u5f15\u64ce，\u652f\u6301 Iceberg rest catalog \u63a5\u53e3<\/li>\n\n\n\n
    \n

    \"\"<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    \u6838\u5fc3\u5b9e\u8df5<\/h3>\n

    \u4f7f\u7528 PyIceberg \u521b\u5efa\u548c\u63d2\u5165 S3 Tables<\/h4>\n

    \u9996\u5148，\u5b89\u88c5 python \u4f9d\u8d56<\/p>\n

    pip install pyiceberg[s3fs, pyarrow] <\/p>\n

    \u521b\u5efa\u8868\u548c\u63d2\u5165\u8868\u7684\u6838\u5fc3\u4ee3\u7801\u5982\u4e0b，\u901a\u8fc7 pyiceberg \u5bf9\u63a5 S3 Tables \u7684 rest catalog api \u6765\u5b9e\u73b0 catalog \u7684\u83b7\u53d6，\u4ece\u800c\u5b9e\u73b0\u8868\u7684\u521b\u5efa\u3001\u5217\u51fa，\u4ee5\u53ca\u6570\u636e\u7684\u63d2\u5165\u7b49\u64cd\u4f5c\u3002<\/p>\n

    from pyiceberg.catalog import load_catalog
    \nimport pyarrow as pa
    \nrest_catalog = load_catalog(
    \n "catalog_name",
    \n **{
    \n "type": "rest",
    \n "warehouse": "arn:aws:s3tables:us-west-2:${awsAccountId}:bucket\/testtable",
    \n "uri": "https:\/\/s3tables.us-west-2.amazonaws.com\/iceberg",
    \n "rest.sigv4-enabled": "true",
    \n "rest.signing-name": "s3tables",
    \n "rest.signing-region": "us-west-2",
    \n "py-io-impl": "pyiceberg.io.fsspec.FsspecFileIO"
    \n }
    \n)
    \n# \u65b0\u5efanamespace
    \nrest_catalog.create_namespace("namespace_example")
    \n# \u65b0\u5efa\u8868
    \nrest_catalog.create_table(
    \n "namespace_example.test_table",
    \n schema=pa.schema(
    \n [
    \n ("id", pa.int32()),
    \n ("data", pa.string()),
    \n ]
    \n )
    \n)
    \n# \u6253\u5370\u8868\u5217\u8868
    \ntables_list = rest_catalog.list_tables("namespace_example")
    \nprint(tables_list)
    \n# \u83b7\u53d6\u8868\u5bf9\u8c61
    \ntable = rest_catalog.load_table("namespace_example.test_table")
    \ndf = pa.Table.from_pylist(
    \n [{"id": 303, "data": 'test insert icb'}], schema=table.schema().as_arrow()
    \n)
    \n#\u63d2\u5165\u8868
    \ntable.append(df)
    \n# \u8bfb\u53d6\u8868\u5e76\u6253\u5370
    \nfor row in table.scan().to_arrow().to_pylist():
    \nprint(row)<\/p>\n

    \u53ef\u4ee5\u5148\u901a\u8fc7\u672c\u5730\u914d\u7f6e AWS CLI \u6743\u9650\u7136\u540e\u8fd0\u884c\u4ee3\u7801\u8fdb\u884c\u6d4b\u8bd5，\u7136\u540e\u901a\u8fc7 docker \u7684\u65b9\u5f0f\u90e8\u7f72 Lambda\u3002<\/p>\n

    \u53c2\u8003 Dockerfile：<\/p>\n

    FROM public.ecr.aws\/lambda\/python:3.12
    \nCOPY requirements.txt ${LAMBDA_TASK_ROOT}
    \nRUN pip install -r requirements.txt
    \nCOPY lambda_function.py ${LAMBDA_TASK_ROOT}
    \nCMD [ "lambda_function.handler" ]<\/p>\n

    \u4f7f\u7528 DuckDB \u5728 S3 Tables \u8fdb\u884c\u590d\u6742\u6570\u636e\u5206\u6790\u67e5\u8be2<\/h4>\n

    \u8fd9\u91cc\u4f7f\u7528 1.2.1 \u7248\u672c\u7684 DuckDB，\u901a\u8fc7 pip install duckdb==1.2.1 \u6765\u5b89\u88c5，DuckDB \u6700\u65b0\u7684\u591c\u95f4\u7248\u672c\u63d2\u4ef6\u652f\u6301\u4e86 Apache Iceberg REST \u76ee\u5f55，\u800c S3 Tables \u4e5f\u6709 REST \u76ee\u5f55\u63a5\u53e3\u3002\u53ef\u4ee5\u901a\u8fc7\u5728 Lambda \u4e0a\u90e8\u7f72 DuckDB \u6765\u8bfb\u53d6\u67e5\u8be2\u5206\u6790 S3 Tables \u91cc\u9762\u7684\u6570\u636e\u3002\u4e5f\u53ef\u4ee5\u628a DuckDB \u5d4c\u5165\u5230\u60a8\u7684\u5e94\u7528\u7a0b\u5e8f\u4e2d\u76f4\u63a5\u67e5\u8be2 S3 Tables\u3002<\/p>\n

    DuckDB \u7684 Lambda \u5b9e\u73b0\u4ee3\u7801\u5982\u4e0b，\u7ed3\u5408\u4e86 boto3 \u7684 S3 Tables \u5ba2\u6237\u7aef，\u901a\u8fc7 api \u628a S3 Tables \u91cc\u9762\u7684\u6876\u52a0\u8f7d\u5230 DuckDB \u7684 catalog \u4e2d，\u540e\u7eed\u5c31\u53ef\u4ee5\u76f4\u63a5\u901a\u8fc7 sql \u6765\u8fdb\u884c\u67e5\u8be2\u4e86\u3002Lambda \u7684\u5165\u53e3\u51fd\u6570\u63a5\u6536 sql，\u7136\u540e\u8fd4\u56de sql \u7684\u6267\u884c\u7ed3\u679c，\u793a\u4f8b sql: Select * from bucketname.namespace.tablename \u5c31\u53ef\u4ee5\u76f4\u63a5\u67e5\u8be2\u51fa\u5bf9\u5e94\u6876\u91cc\u9762\u7684\u8868\u7684\u6570\u636e\u4e86，\u9700\u8981\u6ce8\u610f\u7684\u662f\u5728 DuckDB \u91cc\u9762\u4e00\u822c\u901a\u8fc7 DETACH \u548c ATTACH \u6765\u83b7\u53d6\u6700\u65b0\u7684 catalog \u8868\u5143\u6570\u636e\u3002<\/p>\n

    import os
    \nimport duckdb
    \nimport boto3
    \nos.environ['HOME'] = '\/tmp'
    \ncon = duckdb.connect(database=':memory:', config={'memory_limit': '9GB','worker_threads': 5,'temp_directory':'\/tmp\/file\/overmem'})
    \n# \u9a8c\u8bc1\u8bbe\u7f6e
    \ncon.execute("""
    \nFORCE INSTALL aws FROM core_nightly;
    \nFORCE INSTALL httpfs FROM core_nightly;
    \nFORCE INSTALL iceberg FROM core_nightly;
    \nCREATE SECRET (
    \n TYPE s3,
    \n PROVIDER credential_chain
    \n);
    \n""")
    \ns3tables = boto3.client('s3tables')
    \ntable_buckets = s3tables.list_table_buckets(maxBuckets=1000)['tableBuckets']
    \ndef handler(event, context):
    \n for table_bucket in table_buckets:
    \n name = table_bucket['name']
    \n arn = table_bucket['arn']
    \n try:
    \n con.execute(f"DETACH {name};")
    \n except:
    \n pass
    \n con.execute(
    \n f"""
    \n ATTACH '{arn}' AS {name} (
    \n TYPE iceberg,
    \n ENDPOINT_TYPE s3_tables
    \n );
    \n """
    \n )
    \n sql = event.get("sql")
    \n try:
    \n result = con.execute(sql).fetchall()
    \n return {
    \n "statusCode": 200,
    \n "result": result
    \n }
    \n except Exception as e:
    \n return {
    \n "statusCode": 500,
    \n "error": str(e)
    \n }<\/p>\n

    Dockerfile \u53ef\u4ee5\u53c2\u8003\u63d2\u5165\u90e8\u5206\u7684 Dockerfile，\u901a\u8fc7\u955c\u50cf\u90e8\u7f72\u5230 Lambda，\u5e76\u8bbe\u7f6e\u597d\u5bf9\u5e94\u7684 IAM \u89d2\u8272\u6743\u9650\u4ee5\u53ca Lambda \u7684\u8d85\u65f6\u4ee5\u53ca\u5185\u5b58\u8bbe\u7f6e\u3002\u8fd9\u91cc\u4ee3\u7801\u901a\u8fc7 duckdb.connect(database=\u2019:memory:\u2019, config={\u2018memory_limit\u2019: \u20189GB\u2019,\u2019worker_threads\u2019: 5,\u2019temp_directory\u2019:\u2019\/tmp\/file\/overmem\u2019})\u6765\u8bbe\u7f6e\u6700\u5927\u5185\u5b58\u7684\u4f7f\u7528\u548c\u5de5\u4f5c\u7684\u7ebf\u7a0b\u6570，\u8fd9\u4e2a\u53ef\u4ee5\u6839\u636e\u5b9e\u9645\u7684\u9700\u8981\u6765\u8c03\u6574<\/p>\n

    \u6570\u636e\u5206\u6790\u5b9e\u8df5<\/h3>\n

    \u6d4b\u8bd5\u6570\u636e\u96c6：\u7535\u5546\u7528\u6237\u884c\u4e3a\u6570\u636e，\u603b\u91cf 13 \u4ebf\u6570\u636e，\u5b57\u6bb5\u5982\u4e0b：<\/p>\n

    user_id\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0STRING\u00a0\u00a0 \u00a0 \u00a0\u00a0\u2018\u7528\u6237ID（\u975e\u771f\u5b9eID），\u7ecf\u62bd\u6837&\u5b57\u6bb5\u8131\u654f\u5904\u7406\u540e\u5f97\u5230\u2019<\/p>\n

    item_id\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0STRING\u00a0 \u00a0\u00a0 \u00a0\u00a0\u2018\u5546\u54c1ID（\u975e\u771f\u5b9eID），\u7ecf\u62bd\u6837&\u5b57\u6bb5\u8131\u654f\u5904\u7406\u540e\u5f97\u5230\u2019<\/p>\n

    item_category\u00a0\u00a0\u00a0 STRING\u00a0\u00a0 \u00a0 \u00a0\u00a0\u2018\u5546\u54c1\u7c7b\u522bID（\u975e\u771f\u5b9eID），\u7ecf\u62bd\u6837&\u5b57\u6bb5\u8131\u654f\u5904\u7406\u540e\u5f97\u5230\u2019<\/p>\n

    behavior_type\u00a0\u00a0\u00a0 STRING\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u2018\u7528\u6237\u5bf9\u5546\u54c1\u7684\u884c\u4e3a\u7c7b\u578b,\u5305\u62ec\u6d4f\u89c8\u3001\u6536\u85cf\u3001\u52a0\u8d2d\u7269\u8f66\u3001\u8d2d\u4e70，pv,fav,cart,buy)\u2019<\/p>\n

    behavior_time\u00a0\u00a0\u00a0 STRING\u00a0\u00a0 \u00a0 \u00a0\u00a0\u2018\u884c\u4e3a\u65f6\u95f4,\u7cbe\u786e\u5230\u5c0f\u65f6\u7ea7\u522b\u2019<\/p>\n

    \u6d4b\u8bd5 sql：\u7528\u6237\u884c\u4e3a\u6570\u636e\u6f0f\u6597\u5206\u6790<\/p>\n

    WITH user_behavior_counts AS (
    \n SELECT
    \n user_id,
    \n SUM(CASE WHEN behavior_type = 'pv' THEN 1 ELSE 0 END) AS view_count,
    \n SUM(CASE WHEN behavior_type = 'fav' THEN 1 ELSE 0 END) AS favorite_count,
    \n SUM(CASE WHEN behavior_type = 'cart' THEN 1 ELSE 0 END) AS cart_count,
    \n SUM(CASE WHEN behavior_type = 'buy' THEN 1 ELSE 0 END) AS purchase_count
    \n FROM testtable.testdb.commerce_shopping
    \n GROUP BY user_id
    \n),
    \nfunnel_stages AS (
    \n SELECT
    \n COUNT(DISTINCT user_id) AS total_users,
    \n COUNT(DISTINCT CASE WHEN view_count > 0 THEN user_id END) AS users_with_views,
    \n COUNT(DISTINCT CASE WHEN favorite_count > 0 THEN user_id END) AS users_with_favorites,
    \n COUNT(DISTINCT CASE WHEN cart_count > 0 THEN user_id END) AS users_with_cart_adds,
    \n COUNT(DISTINCT CASE WHEN purchase_count > 0 THEN user_id END) AS users_with_purchases
    \n FROM user_behavior_counts
    \n)
    \nSELECT
    \n total_users,
    \n users_with_views,
    \n users_with_favorites,
    \n users_with_cart_adds,
    \n users_with_purchases,
    \n ROUND(100.0 * users_with_views \/ total_users, 2) AS view_rate,
    \n ROUND(100.0 * users_with_favorites \/ users_with_views, 2) AS view_to_favorite_rate,
    \n ROUND(100.0 * users_with_cart_adds \/ users_with_favorites, 2) AS favorite_to_cart_rate,
    \n ROUND(100.0 * users_with_purchases \/ users_with_cart_adds, 2) AS cart_to_purchase_rate,
    \n ROUND(100.0 * users_with_purchases \/ total_users, 2) AS overall_conversion_rate
    \nFROM funnel_stages;<\/p>\n

    Lambda \u6d4b\u8bd5\u7ed3\u679c：\u6d88\u8017\u5185\u5b58 1934M<\/p>\n

    \u7528\u65f6：37s<\/p>\n

    \u5173\u952e\u4f18\u52bf<\/h3>\n

    \u5c06 PyIceberg \u548c DuckDB \u8fd0\u884c\u5728 AWS Lambda \u4e0a\u6765\u8bbf\u95ee S3 \u4e0a\u7684 Iceberg \u8868，\u8fd9\u79cd Serverless \u6570\u636e\u6e56\u6a21\u5f0f\u4e3b\u8981\u7684\u4f18\u52bf\u5982\u4e0b：<\/p>\n

      \n
    • \u4f4e\u95e8\u69db：\u4e3b\u8981\u4f9d\u8d56 python \u548c sql，\u8fd9\u4e24\u79cd\u662f\u6570\u636e\u5f00\u53d1\u9886\u57df\u6700\u5e38\u89c1\u7684\u6280\u80fd，\u5927\u5927\u964d\u4f4e\u4e86\u5b66\u4e60\u548c\u4f7f\u7528\u7684\u95e8\u69db，\u540c\u65f6\u57fa\u7840\u8bbe\u65bd 0 \u4f9d\u8d56\u4e14\u6613\u4e8e\u90e8\u7f72，\u4e0d\u9700\u8981\u6295\u5165\u57fa\u7840\u8bbe\u65bd\u8fd0\u7ef4\u3002<\/li>\n
    • \u9ad8\u6027\u4ef7\u6bd4：Lambda \u6309\u5b9e\u9645\u8ba1\u7b97\u65f6\u95f4\u4ed8\u8d39\u4e14\u81ea\u52a8\u4f38\u7f29，\u800c S3 \u7684\u5b58\u50a8\u6210\u672c\u4e5f\u8f83\u4e3a\u4f4e\u5ec9\u3002\u52a0\u4e0a DuckDB \u9ad8\u6027\u80fd\u7684\u7279\u6027，\u8fd9\u610f\u5473\u7740\u66f4\u77ed\u7684 Lambda \u6267\u884c\u65f6\u95f4，\u8fdb\u4e00\u6b65\u964d\u4f4e\u6210\u672c\u3002<\/li>\n
    • \u5f00\u6e90\u4e0e\u7075\u6d3b\u6027：\u6838\u5fc3\u7ec4\u4ef6 Apache Iceberg\u3001DuckDB \u548c PyIceberg \u5747\u4e3a\u5e7f\u6cdb\u5e94\u7528\u7684\u5f00\u6e90\u9879\u76ee\u3002\u53d7\u76ca\u4e8e\u6d3b\u8dc3\u7684\u5f00\u6e90\u793e\u533a\u652f\u6301，\u53ef\u4ee5\u83b7\u5f97\u6301\u7eed\u7684\u529f\u80fd\u66f4\u65b0\u3001\u95ee\u9898\u4fee\u590d\u548c\u4e30\u5bcc\u7684\u5b66\u4e60\u8d44\u6e90\u3002<\/li>\n<\/ul>\n

      \u5178\u578b\u5e94\u7528\u573a\u666f<\/h3>\n
        \n
      • \u4f4e\u6210\u672c\u6d77\u91cf\u5206\u6790\u8d1f\u8f7d：\u5bf9\u4e8e\u9700\u8981\u63a7\u5236\u6210\u672c，\u4f46\u4ecd\u9700\u8fdb\u884c\u6709\u6548\u6570\u636e\u5206\u6790\u7684\u573a\u666f，\u5982\u4e2d\u5c0f\u578b\u4f01\u4e1a\u6216\u7279\u5b9a\u9879\u76ee\u9884\u7b97\u6709\u9650\u7684\u60c5\u51b5\u3002<\/li>\n
      • \u975e\u9891\u7e41\u6216\u7a81\u53d1\u6027\u67e5\u8be2：\u5982\u5b9a\u671f\u7684\u62a5\u8868\u751f\u6210\u3001\u4e34\u65f6\u7684\u4e1a\u52a1\u6570\u636e\u6d1e\u5bdf\u3001\u5076\u5c14\u8fdb\u884c\u7684\u6570\u636e\u63a2\u7d22\u7b49，\u8fd9\u4e9b\u573a\u666f\u4e0b\u6309\u9700\u4ed8\u8d39\u7684 Lambda + DuckDB \u6781\u5177\u4f18\u52bf\u3002<\/li>\n
      • \u4e8b\u4ef6\u9a71\u52a8\u7684\u6570\u636e\u5904\u7406：\u7531 S3 \u4e8b\u4ef6\u89e6\u53d1 Lambda (PyIceberg) \u8fdb\u884c\u6570\u636e\u9a8c\u8bc1\u3001\u8f6c\u6362\u548c\u52a0\u8f7d\u5230 Iceberg \u8868，\u540e\u7eed\u53ef\u7531\u53e6\u4e00\u4e2a Lambda (DuckDB) \u8fdb\u884c\u5373\u65f6\u67e5\u8be2\u6216\u805a\u5408\u3002<\/li>\n
      • \u4ea4\u4e92\u5f0f\u67e5\u8be2\u63a5\u53e3\u540e\u7aef：\u901a\u8fc7 API Gateway \u66b4\u9732\u4e00\u4e2a Lambda (DuckDB) \u7aef\u70b9，\u4e3a\u5185\u90e8\u7528\u6237\u6216\u5e94\u7528\u63d0\u4f9b\u4e00\u4e2a\u4f4e\u6210\u672c\u7684 SQL \u67e5\u8be2\u63a5\u53e3，\u7528\u4e8e\u67e5\u8be2\u7279\u5b9a\u8303\u56f4\u7684\u6570\u636e\u3002<\/li>\n
      • \u5feb\u901f\u539f\u578b\u9a8c\u8bc1：\u5728\u5f00\u53d1\u6216\u7814\u7a76\u9636\u6bb5，\u5feb\u901f\u642d\u5efa\u4e00\u4e2a\u529f\u80fd\u5b8c\u5907\u7684\u6570\u636e\u6e56\u67e5\u8be2\u73af\u5883，\u7528\u4e8e\u9a8c\u8bc1\u60f3\u6cd5\u6216\u8fdb\u884c\u5c0f\u89c4\u6a21\u5b9e\u9a8c\u3002<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"

        \u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb763\u6b21\uff0c\u70b9\u8d5e27\u6b21\uff0c\u6536\u85cf18\u6b21\u3002\u5728\u5927\u6570\u636e\u5206\u6790\u9886\u57df\uff0c\u5982\u7535\u5546\u7528\u6237\u884c\u4e3a\u5206\u6790\uff0c\u4f20\u7edf\u65b9\u6cd5\u4f9d\u8d56\u590d\u6742\u7684\u96c6\u7fa4\u548c\u5b58\u50a8\u89e3\u51b3\u65b9\u6848\uff0c\u6210\u672c\u9ad8\u4e14\u54cd\u5e94\u6162\u3002\u672c\u6587\u63d0\u51fa\u4e86\u4e00\u79cd\u73b0\u4ee3\u5316\u7684Serverless\u89e3\u51b3\u65b9\u6848\uff0c\u5229\u7528S3Tables\uff08\u652f\u6301Apache Iceberg\uff09\u4f5c\u4e3a\u5b58\u50a8\u57fa\u7840\uff0c\u7ed3\u5408PyIceberg\u548cDuckDB\uff0c\u5728AWSLambda\u7b49\u73af\u5883\u4e2d\u5b9e\u73b0\u4f4e\u6210\u672c\u3001\u9ad8\u6548\u7387\u7684\u5373\u65f6\u67e5\u8be2\u3002\u8fd9\u79cd\u65b9\u6cd5\u65e0\u9700\u96c6\u7fa4\u8fd0\u7ef4\uff0c\u901a\u8fc7Python\u548cSQL\u5373\u53ef\u64cd\u4f5c\uff0c\u964d\u4f4e\u4e86\u6280\u672f\u95e8\u69db\u548c\u6210\u672c\u3002DuckDB\u7684\u9ad8\u6027\u80fd\u5d4c\u5165\u5f0f\u5206\u6790\u80fd\u529b\u4f7f\u5f97\u5728Lambda\u4e0a\u6267\u884c\u590d\u6742\u67e5\u8be2\u6210\u4e3a\u53ef\u80fd\uff0c\u9002\u7528\u4e8e\u4f4e\u6210\u672c\u6d77\u91cf\u5206\u6790\u3001\u975e\u9891\u7e41\u67e5\u8be2\u3001\u4e8b\u4ef6\u9a71\u52a8\u6570\u636e\u5904_\u91c7\u7528aws s3\u4f5c\u4e3a\u6570\u636e\u6e56\u5b58\u50a8<\/p>\n","protected":false},"author":2,"featured_media":39015,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[593,828,227],"topic":[],"class_list":["post-39016","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-aws","tag-serverless","tag-227"],"yoast_head":"\n\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/39016.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb763\u6b21\uff0c\u70b9\u8d5e27\u6b21\uff0c\u6536\u85cf18\u6b21\u3002\u5728\u5927\u6570\u636e\u5206\u6790\u9886\u57df\uff0c\u5982\u7535\u5546\u7528\u6237\u884c\u4e3a\u5206\u6790\uff0c\u4f20\u7edf\u65b9\u6cd5\u4f9d\u8d56\u590d\u6742\u7684\u96c6\u7fa4\u548c\u5b58\u50a8\u89e3\u51b3\u65b9\u6848\uff0c\u6210\u672c\u9ad8\u4e14\u54cd\u5e94\u6162\u3002\u672c\u6587\u63d0\u51fa\u4e86\u4e00\u79cd\u73b0\u4ee3\u5316\u7684Serverless\u89e3\u51b3\u65b9\u6848\uff0c\u5229\u7528S3Tables\uff08\u652f\u6301Apache Iceberg\uff09\u4f5c\u4e3a\u5b58\u50a8\u57fa\u7840\uff0c\u7ed3\u5408PyIceberg\u548cDuckDB\uff0c\u5728AWSLambda\u7b49\u73af\u5883\u4e2d\u5b9e\u73b0\u4f4e\u6210\u672c\u3001\u9ad8\u6548\u7387\u7684\u5373\u65f6\u67e5\u8be2\u3002\u8fd9\u79cd\u65b9\u6cd5\u65e0\u9700\u96c6\u7fa4\u8fd0\u7ef4\uff0c\u901a\u8fc7Python\u548cSQL\u5373\u53ef\u64cd\u4f5c\uff0c\u964d\u4f4e\u4e86\u6280\u672f\u95e8\u69db\u548c\u6210\u672c\u3002DuckDB\u7684\u9ad8\u6027\u80fd\u5d4c\u5165\u5f0f\u5206\u6790\u80fd\u529b\u4f7f\u5f97\u5728Lambda\u4e0a\u6267\u884c\u590d\u6742\u67e5\u8be2\u6210\u4e3a\u53ef\u80fd\uff0c\u9002\u7528\u4e8e\u4f4e\u6210\u672c\u6d77\u91cf\u5206\u6790\u3001\u975e\u9891\u7e41\u67e5\u8be2\u3001\u4e8b\u4ef6\u9a71\u52a8\u6570\u636e\u5904_\u91c7\u7528aws s3\u4f5c\u4e3a\u6570\u636e\u6e56\u5b58\u50a8\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/39016.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-21T14:04:23+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/05\/20250521140422-682ddd6612da8.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/39016.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/39016.html\",\"name\":\"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2025-05-21T14:04:23+00:00\",\"dateModified\":\"2025-05-21T14:04:23+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/39016.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/39016.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/39016.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/39016.html","og_locale":"zh_CN","og_type":"article","og_title":"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u6d4f\u89c8\u9605\u8bfb763\u6b21\uff0c\u70b9\u8d5e27\u6b21\uff0c\u6536\u85cf18\u6b21\u3002\u5728\u5927\u6570\u636e\u5206\u6790\u9886\u57df\uff0c\u5982\u7535\u5546\u7528\u6237\u884c\u4e3a\u5206\u6790\uff0c\u4f20\u7edf\u65b9\u6cd5\u4f9d\u8d56\u590d\u6742\u7684\u96c6\u7fa4\u548c\u5b58\u50a8\u89e3\u51b3\u65b9\u6848\uff0c\u6210\u672c\u9ad8\u4e14\u54cd\u5e94\u6162\u3002\u672c\u6587\u63d0\u51fa\u4e86\u4e00\u79cd\u73b0\u4ee3\u5316\u7684Serverless\u89e3\u51b3\u65b9\u6848\uff0c\u5229\u7528S3Tables\uff08\u652f\u6301Apache Iceberg\uff09\u4f5c\u4e3a\u5b58\u50a8\u57fa\u7840\uff0c\u7ed3\u5408PyIceberg\u548cDuckDB\uff0c\u5728AWSLambda\u7b49\u73af\u5883\u4e2d\u5b9e\u73b0\u4f4e\u6210\u672c\u3001\u9ad8\u6548\u7387\u7684\u5373\u65f6\u67e5\u8be2\u3002\u8fd9\u79cd\u65b9\u6cd5\u65e0\u9700\u96c6\u7fa4\u8fd0\u7ef4\uff0c\u901a\u8fc7Python\u548cSQL\u5373\u53ef\u64cd\u4f5c\uff0c\u964d\u4f4e\u4e86\u6280\u672f\u95e8\u69db\u548c\u6210\u672c\u3002DuckDB\u7684\u9ad8\u6027\u80fd\u5d4c\u5165\u5f0f\u5206\u6790\u80fd\u529b\u4f7f\u5f97\u5728Lambda\u4e0a\u6267\u884c\u590d\u6742\u67e5\u8be2\u6210\u4e3a\u53ef\u80fd\uff0c\u9002\u7528\u4e8e\u4f4e\u6210\u672c\u6d77\u91cf\u5206\u6790\u3001\u975e\u9891\u7e41\u67e5\u8be2\u3001\u4e8b\u4ef6\u9a71\u52a8\u6570\u636e\u5904_\u91c7\u7528aws s3\u4f5c\u4e3a\u6570\u636e\u6e56\u5b58\u50a8","og_url":"https:\/\/www.wsisp.com\/helps\/39016.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2025-05-21T14:04:23+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2025\/05\/20250521140422-682ddd6612da8.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/39016.html","url":"https:\/\/www.wsisp.com\/helps\/39016.html","name":"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2025-05-21T14:04:23+00:00","dateModified":"2025-05-21T14:04:23+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/39016.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/39016.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/39016.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u5f53 PyIceberg \u548c DuckDB \u9047\u89c1 AWS S3 Tables\uff1a\u6253\u9020 Serverless \u6570\u636e\u6e56\u201c\u5f00\u6e90\u68a6\u5e7b\u7ec4\u5408\u201d"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/39016","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=39016"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/39016\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/39015"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=39016"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=39016"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=39016"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=39016"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}