{"id":153299,"date":"2024-11-02T06:17:20","date_gmt":"2024-11-01T22:17:20","guid":{"rendered":"https:\/\/server.hk\/cnblog\/153299\/"},"modified":"2024-11-02T06:17:20","modified_gmt":"2024-11-01T22:17:20","slug":"%e5%be%9e%e9%9b%a2%e7%b7%9a%e5%88%b0%e5%af%a6%e6%99%82%e5%b0%8d%e5%ae%a2%ef%bc%8c%e6%b9%96%e5%80%89%e4%b8%80%e9%ab%94%e9%87%8b%e6%94%be%e5%85%a8%e9%87%8f%e6%95%b8%e6%93%9a%e5%83%b9%e5%80%bc","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/153299\/","title":{"rendered":"\u5f9e\u96e2\u7dda\u5230\u5be6\u6642\u5c0d\u5ba2\uff0c\u6e56\u5009\u4e00\u9ad4\u91cb\u653e\u5168\u91cf\u6578\u64da\u50f9\u503c"},"content":{"rendered":"<h1 id=\"%e5%be%9e%e9%9b%a2%e7%b7%9a%e5%88%b0%e5%af%a6%e6%99%82%e5%b0%8d%e5%ae%a2%ef%bc%8c%e6%b9%96%e5%80%89%e4%b8%80%e9%ab%94%e9%87%8b%e6%94%be%e5%85%a8%e9%87%8f%e6%95%b8%e6%93%9a%e5%83%b9%e5%80%bc-rBdUCkQSdL\">\u5f9e\u96e2\u7dda\u5230\u5be6\u6642\u5c0d\u5ba2\uff0c\u6e56\u5009\u4e00\u9ad4\u91cb\u653e\u5168\u91cf\u6578\u64da\u50f9\u503c<\/h1>\n<p>\u5728\u7576\u4eca\u6578\u5b57\u5316\u7684\u6642\u4ee3\uff0c\u4f01\u696d\u9762\u81e8\u8457\u524d\u6240\u672a\u6709\u7684\u6578\u64da\u6311\u6230\u8207\u6a5f\u9047\u3002\u96a8\u8457\u6280\u8853\u7684\u9032\u6b65\uff0c\u6578\u64da\u7684\u6536\u96c6\u3001\u5b58\u5132\u548c\u5206\u6790\u65b9\u5f0f\u4e5f\u5728\u4e0d\u65b7\u6f14\u8b8a\u3002\u6e56\u5009\u4e00\u9ad4\uff08Lakehouse\uff09\u4f5c\u70ba\u4e00\u7a2e\u65b0\u8208\u7684\u6578\u64da\u67b6\u69cb\uff0c\u6b63\u9010\u6f38\u6210\u70ba\u4f01\u696d\u91cb\u653e\u5168\u91cf\u6578\u64da\u50f9\u503c\u7684\u91cd\u8981\u5de5\u5177\u3002\u672c\u6587\u5c07\u63a2\u8a0e\u6e56\u5009\u4e00\u9ad4\u7684\u6982\u5ff5\u53ca\u5176\u5982\u4f55\u5e6b\u52a9\u4f01\u696d\u5f9e\u96e2\u7dda\u6578\u64da\u8f49\u5411\u5be6\u6642\u5c0d\u5ba2\u7684\u6578\u64da\u61c9\u7528\u3002<\/p>\n<h2 id=\"%e6%b9%96%e5%80%89%e4%b8%80%e9%ab%94%e7%9a%84%e6%a6%82%e5%bf%b5-rBdUCkQSdL\">\u6e56\u5009\u4e00\u9ad4\u7684\u6982\u5ff5<\/h2>\n<p>\u6e56\u5009\u4e00\u9ad4\u662f\u4e00\u7a2e\u7d50\u5408\u4e86\u6578\u64da\u6e56\uff08Data Lake\uff09\u548c\u6578\u64da\u5009\u5eab\uff08Data Warehouse\uff09\u7279\u6027\u7684\u67b6\u69cb\u3002\u6578\u64da\u6e56\u5141\u8a31\u4f01\u696d\u4ee5\u539f\u59cb\u683c\u5f0f\u5b58\u5132\u5927\u91cf\u7684\u7d50\u69cb\u5316\u548c\u975e\u7d50\u69cb\u5316\u6578\u64da\uff0c\u800c\u6578\u64da\u5009\u5eab\u5247\u63d0\u4f9b\u4e86\u9ad8\u6548\u7684\u67e5\u8a62\u548c\u5206\u6790\u80fd\u529b\u3002\u6e56\u5009\u4e00\u9ad4\u7684\u51fa\u73fe\uff0c\u65e8\u5728\u6d88\u9664\u9019\u5169\u8005\u4e4b\u9593\u7684\u754c\u9650\uff0c\u5be6\u73fe\u6578\u64da\u7684\u9748\u6d3b\u5b58\u53d6\u548c\u9ad8\u6548\u5206\u6790\u3002<\/p>\n<h3 id=\"%e6%b9%96%e5%80%89%e4%b8%80%e9%ab%94%e7%9a%84%e5%84%aa%e5%8b%a2-rBdUCkQSdL\">\u6e56\u5009\u4e00\u9ad4\u7684\u512a\u52e2<\/h3>\n<ul>\n<li><strong>\u5be6\u6642\u6578\u64da\u8655\u7406\uff1a<\/strong>\u6e56\u5009\u4e00\u9ad4\u67b6\u69cb\u652f\u6301\u5be6\u6642\u6578\u64da\u6d41\u7684\u8655\u7406\uff0c\u4f7f\u4f01\u696d\u80fd\u5920\u5373\u6642\u7372\u53d6\u548c\u5206\u6790\u6578\u64da\uff0c\u5f9e\u800c\u5feb\u901f\u505a\u51fa\u6c7a\u7b56\u3002<\/li>\n<li><strong>\u6578\u64da\u6574\u5408\uff1a<\/strong>\u901a\u904e\u5c07\u4e0d\u540c\u4f86\u6e90\u7684\u6578\u64da\u6574\u5408\u5230\u4e00\u500b\u5e73\u53f0\u4e0a\uff0c\u4f01\u696d\u53ef\u4ee5\u7372\u5f97\u66f4\u5168\u9762\u7684\u6578\u64da\u8996\u5716\uff0c\u63d0\u5347\u5206\u6790\u7684\u6e96\u78ba\u6027\u3002<\/li>\n<li><strong>\u6210\u672c\u6548\u76ca\uff1a<\/strong>\u6e56\u5009\u4e00\u9ad4\u67b6\u69cb\u901a\u5e38\u57fa\u65bc\u958b\u6e90\u6280\u8853\uff0c\u80fd\u5920\u964d\u4f4e\u6578\u64da\u5b58\u5132\u548c\u8655\u7406\u7684\u6210\u672c\u3002<\/li>\n<li><strong>\u9748\u6d3b\u6027\uff1a<\/strong>\u4f01\u696d\u53ef\u4ee5\u6839\u64da\u9700\u6c42\u96a8\u6642\u8abf\u6574\u6578\u64da\u67b6\u69cb\uff0c\u7121\u9700\u91cd\u65b0\u8a2d\u8a08\u6574\u500b\u7cfb\u7d71\u3002<\/li>\n<\/ul>\n<h2 id=\"%e5%be%9e%e9%9b%a2%e7%b7%9a%e5%88%b0%e5%af%a6%e6%99%82%e7%9a%84%e8%bd%89%e8%ae%8a-rBdUCkQSdL\">\u5f9e\u96e2\u7dda\u5230\u5be6\u6642\u7684\u8f49\u8b8a<\/h2>\n<p>\u50b3\u7d71\u7684\u6578\u64da\u8655\u7406\u65b9\u5f0f\u5f80\u5f80\u4f9d\u8cf4\u65bc\u6279\u91cf\u8655\u7406\uff0c\u9019\u610f\u5473\u8457\u6578\u64da\u5728\u6536\u96c6\u5f8c\u9700\u8981\u7d93\u904e\u4e00\u6bb5\u6642\u9593\u7684\u8655\u7406\u624d\u80fd\u88ab\u5206\u6790\u548c\u4f7f\u7528\u3002\u9019\u7a2e\u65b9\u5f0f\u5728\u5feb\u901f\u8b8a\u5316\u7684\u5546\u696d\u74b0\u5883\u4e2d\u986f\u5f97\u4e0d\u5920\u9748\u6d3b\u3002\u6e56\u5009\u4e00\u9ad4\u7684\u51fa\u73fe\uff0c\u8b93\u4f01\u696d\u80fd\u5920\u5be6\u73fe\u6578\u64da\u7684\u5be6\u6642\u8655\u7406\uff0c\u5f9e\u800c\u66f4\u5feb\u5730\u97ff\u61c9\u5e02\u5834\u9700\u6c42\u3002<\/p>\n<h3 id=\"%e5%af%a6%e6%99%82%e6%95%b8%e6%93%9a%e6%87%89%e7%94%a8%e7%9a%84%e6%a1%88%e4%be%8b-rBdUCkQSdL\">\u5be6\u6642\u6578\u64da\u61c9\u7528\u7684\u6848\u4f8b<\/h3>\n<p>\u4f8b\u5982\uff0c\u67d0\u5927\u578b\u96f6\u552e\u4f01\u696d\u5229\u7528\u6e56\u5009\u4e00\u9ad4\u67b6\u69cb\uff0c\u5be6\u6642\u5206\u6790\u9867\u5ba2\u7684\u8cfc\u7269\u884c\u70ba\u3002\u901a\u904e\u6574\u5408\u4f86\u81ea\u7dda\u4e0a\u548c\u7dda\u4e0b\u7684\u6578\u64da\uff0c\u4f01\u696d\u80fd\u5920\u5373\u6642\u8abf\u6574\u5eab\u5b58\u548c\u4fc3\u92b7\u7b56\u7565\uff0c\u5f9e\u800c\u63d0\u5347\u92b7\u552e\u984d\u548c\u9867\u5ba2\u6eff\u610f\u5ea6\u3002\u9019\u7a2e\u5be6\u6642\u7684\u6578\u64da\u61c9\u7528\u4e0d\u50c5\u63d0\u9ad8\u4e86\u904b\u71df\u6548\u7387\uff0c\u9084\u589e\u5f37\u4e86\u4f01\u696d\u7684\u5e02\u5834\u7af6\u722d\u529b\u3002<\/p>\n<h2 id=\"%e6%8a%80%e8%a1%93%e5%af%a6%e7%8f%be-rBdUCkQSdL\">\u6280\u8853\u5be6\u73fe<\/h2>\n<p>\u6e56\u5009\u4e00\u9ad4\u7684\u5be6\u73fe\u901a\u5e38\u4f9d\u8cf4\u65bc\u591a\u7a2e\u6280\u8853\u7684\u7d50\u5408\uff0c\u5305\u62ec\u5927\u6578\u64da\u8655\u7406\u6846\u67b6\uff08\u5982Apache Spark\uff09\u3001\u6578\u64da\u5eab\u6280\u8853\uff08\u5982Apache Hive\uff09\u4ee5\u53ca\u6d41\u8655\u7406\u6280\u8853\uff08\u5982Apache Kafka\uff09\u3002\u9019\u4e9b\u6280\u8853\u5171\u540c\u652f\u6301\u6578\u64da\u7684\u9ad8\u6548\u5b58\u5132\u3001\u8655\u7406\u548c\u5206\u6790\u3002<\/p>\n<pre><code>\n# \u4f7f\u7528Apache Spark\u9032\u884c\u5be6\u6642\u6578\u64da\u8655\u7406\u7684\u793a\u4f8b\nfrom pyspark.sql import SparkSession\n\nspark = SparkSession.builder \n    .appName(\"RealTimeDataProcessing\") \n    .getOrCreate()\n\n# \u8b80\u53d6\u5be6\u6642\u6578\u64da\u6d41\ndf = spark.readStream \n    .format(\"kafka\") \n    .option(\"kafka.bootstrap.servers\", \"localhost:9092\") \n    .option(\"subscribe\", \"topic_name\") \n    .load()\n\n# \u5be6\u6642\u6578\u64da\u8655\u7406\u908f\u8f2f\nprocessed_df = df.selectExpr(\"CAST(value AS STRING)\")\n\n# \u5beb\u5165\u6578\u64da\u6e56\nquery = processed_df.writeStream \n    .format(\"parquet\") \n    .option(\"path\", \"\/path\/to\/data_lake\") \n    .option(\"checkpointLocation\", \"\/path\/to\/checkpoint\") \n    .start()\n\nquery.awaitTermination()\n<\/code><\/pre>\n<h2 id=\"%e7%b5%90%e8%ab%96-rBdUCkQSdL\">\u7d50\u8ad6<\/h2>\n<p>\u6e56\u5009\u4e00\u9ad4\u67b6\u69cb\u7684\u51fa\u73fe\uff0c\u70ba\u4f01\u696d\u63d0\u4f9b\u4e86\u4e00\u7a2e\u5168\u65b0\u7684\u6578\u64da\u7ba1\u7406\u65b9\u5f0f\uff0c\u4f7f\u5176\u80fd\u5920\u5f9e\u96e2\u7dda\u6578\u64da\u8f49\u5411\u5be6\u6642\u5c0d\u5ba2\u7684\u6578\u64da\u61c9\u7528\u3002\u901a\u904e\u5be6\u6642\u6578\u64da\u8655\u7406\u548c\u9748\u6d3b\u7684\u6578\u64da\u6574\u5408\uff0c\u4f01\u696d\u80fd\u5920\u66f4\u597d\u5730\u61c9\u5c0d\u5e02\u5834\u8b8a\u5316\uff0c\u63d0\u5347\u7af6\u722d\u529b\u3002\u96a8\u8457\u6280\u8853\u7684\u9032\u4e00\u6b65\u767c\u5c55\uff0c\u6e56\u5009\u4e00\u9ad4\u5c07\u5728\u672a\u4f86\u7684\u6578\u64da\u7ba1\u7406\u4e2d\u626e\u6f14\u8d8a\u4f86\u8d8a\u91cd\u8981\u7684\u89d2\u8272\u3002<\/p>\n<p>\u5982\u9700\u4e86\u89e3\u66f4\u591a\u95dc\u65bc<em><a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a><\/em>\u548c<em><a href=\"https:\/\/server.hk\">\u4e91\u670d\u52a1\u5668<\/a><\/em>\u7684\u8cc7\u8a0a\uff0c\u8acb\u8a2a\u554f\u6211\u5011\u7684\u7db2\u7ad9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22\u6e56\u5009\u4e00\u9ad4\u5982\u4f55\u5be6\u73fe\u5f9e\u96e2\u7dda\u5230\u5be6\u6642\u5c0d\u5ba2\uff0c\u91cb\u653e\u5168\u91cf\u6578\u64da\u50f9\u503c\uff0c\u63d0\u5347\u696d\u52d9\u6c7a\u7b56\u6548\u7387\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-153299","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/153299","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=153299"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/153299\/revisions"}],"predecessor-version":[{"id":153300,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/153299\/revisions\/153300"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=153299"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=153299"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=153299"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}