{"id":50638,"date":"2023-10-24T02:11:17","date_gmt":"2022-11-23T09:56:16","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/"},"modified":"2024-05-04T05:42:45","modified_gmt":"2024-05-03T21:42:45","slug":"%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/","title":{"rendered":"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5"},"content":{"rendered":"<p>\u6211\u60f3\u548c\u5927\u5bb6\u5206\u4eab\u4e00\u4e0b\u6211\u5982\u4f55\u901a\u8fc7\u4e86Cloudera\u7684\u300cCCA Spark\u548cHadoop\u5f00\u53d1\u8005\u8003\u8bd5\uff08CCA175\uff09\u300d\u3002<\/p>\n<p>\u5728\u5b66\u4e60\u671f\u95f4\uff0c\u5305\u62ec\u5b66\u4e60hadoop\u548cspark\u76f8\u5173\u6280\u672f\uff0c\u5927\u7ea6\u9700\u89811.5\u4e2a\u6708\u7684\u65f6\u95f4\uff0c\u4f46\u5982\u679c\u4ec5\u4ec5\u662f\u4e3a\u4e86\u51c6\u5907\u8003\u8bd5\uff0c\u5927\u7ea6\u9700\u89812\u5468\u7684\u65f6\u95f4\u3002<\/p>\n<p>\u7531\u4e8e\u53ea\u662f\u82f1\u8bed\u8003\u8bd5\uff0c\u6240\u4ee5\u5728\u64b0\u5199\u672c\u6587\u65f6\uff0c\u6ca1\u6709\u627e\u5230\u4efb\u4f55\u4e0e\u73af\u5883\u8bbe\u7f6e\u3001\u5b66\u4e60\u65b9\u6cd5\u548c\u5b9e\u9645\u8003\u8bd5\u6240\u9700\u5185\u5bb9\u76f8\u5173\u7684\u65e5\u8bed\u53c2\u8003\u4fe1\u606f\u3002\u5e0c\u671b\u5bf9\u60f3\u5b66\u4e60hadoop\u76f8\u5173\u6280\u672f\u548cspark\u7684\u4eba\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<h2>\u76ee\u5f55<\/h2>\n<p>1. \u5173\u4e8eCCA175\u8003\u8bd5<br \/>\n2. \u6211\u7684\u8003\u8bd5\u524d\u4fe1\u606f\u548c\u8003\u8bd5\u52a8\u673a<br \/>\n3. \u662f\u5426\u9700\u8981\u79df\u7528\u529e\u516c\u5ba4\uff1f<br \/>\n4. \u8003\u524d\u548c\u8003\u8bd5\u671f\u95f4\u7684\u6ce8\u610f\u4e8b\u9879<br \/>\n5. \u9700\u8981\u4f1a\u8bf4\u82f1\u8bed\u5417\uff1f<br \/>\n6. \u53c2\u52a0Udemy\u8bfe\u7a0b\u548c\u6a21\u62df\u8003\u8bd5<br \/>\n7. \u5173\u4e8e\u5b66\u4e60\u65b9\u6cd5\u548c\u73af\u5883\u8bbe\u7f6e<br \/>\n8. \u5173\u4e8ehadoop\u751f\u6001\u7cfb\u7edf\u7684\u76f8\u5173\u5b66\u4e60<br \/>\n9. \u8003\u8bd5\u6280\u5de7\u548c\u4e34\u65f6\u51c6\u5907<br \/>\n10. \u4ee3\u7801\u793a\u4f8b\u4ecb\u7ecd<br \/>\n\u6700\u540e<\/p>\n<h2>\u8003\u8bd5\u76f8\u5173<\/h2>\n<p>CCA175\u662f\u7531Cloudera\u63d0\u4f9b\u7684hadoop\u00b7spark\u5f00\u53d1\u8005\u8d44\u683c\u8003\u8bd5\uff0cCloudera\u662fhadoop\u76f8\u5173\u7cfb\u7edf\u7684\u4e3b\u8981\u5206\u9500\u5546\u4e4b\u4e00\u3002\u5728hadoop\u76f8\u5173\u7684\u4e91\u670d\u52a1\u4e2d\uff0cAWS\u7684Amazon EMR\u548cGCP\u7684Dataproc\u4e5f\u662f\u4f17\u6240\u5468\u77e5\u7684\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/7-0.png\" alt=\"3_CLOUDERA_LOGO.png\" \/><\/div>\n<p>CCA175\u662f\u4e00\u4e2a\u4e3b\u8981\u8003\u5bdf\u4f7f\u7528Spark\u8fdb\u884cHDFS\u6570\u636e\u8bfb\u53d6\u3001\u6570\u636e\u8f6c\u6362\u3001\u6570\u636e\u52a0\u5de5\u548c\u6570\u636e\u5b58\u50a8\uff0c\u4ee5\u53ca\u4f7f\u7528Spark SQL\u548cHive\u8fdb\u884cSQL\u5206\u6790\u7684\u80fd\u529b\u7684\u8003\u8bd5\u3002\u8fd9\u4e2a\u8003\u8bd5\u4e0d\u6d89\u53caHadoop\u76f8\u5173\u6280\u672f\u7684\u77e5\u8bc6\u548c\u6570\u636e\u67b6\u6784\u7684\u54a8\u8be2\u80fd\u529b\uff0c\u56e0\u6b64\u5efa\u8bae\u5b66\u4e60\u76f8\u5173\u77e5\u8bc6\u6765\u8865\u5145\u8fd9\u65b9\u9762\u7684\u77e5\u8bc6\uff08\u7a0d\u540e\u4f1a\u4ecb\u7ecd\uff09\u3002CCA175\u7684\u57fa\u672c\u4fe1\u606f\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u8a00\u8a9e\uff1a\u82f1\u8a9e\u306e\u307f<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u8a66\u9a13\u6642\u9593\uff1a120\u5206<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u5408\u683c\u6c34\u6e96\uff1a70%\u4ee5\u4e0a\u3067\u5408\u683c<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u4fa1\u683c\uff1a295US\u30c9\u30eb\uff08\u65e5\u672c\u5186\u3067\u7d043\u4e07\u5186)<\/ul>\n<p>\u60a8\u53ef\u4ee5\u5728\u8fd9\u91cc\u8d2d\u4e70\u548c\u7533\u8bf7\u8003\u8bd5\u3002<br \/>\nhttps:\/\/www.cloudera.com\/about\/training\/certification\/cca-spark.html<br \/>\n\u8d2d\u4e70\u540e\uff0c\u6211\u4eec\u5c06\u901a\u8fc7\u90ae\u4ef6\u5411\u60a8\u53d1\u9001PSI\u5728\u7ebf\u6d4b\u8bd5\u7f51\u7ad9\u7684\u5b89\u6392\uff0c\u60a8\u53ef\u4ee5\u5728\u8be5\u7f51\u7ad9\u4e0a\u8bbe\u7f6e\u8003\u8bd5\u65f6\u95f4\u5e76\u53c2\u52a0\u8003\u8bd5\u3002<\/p>\n<p>\u5728\u65e5\u672c\u4f7f\u7528\u4fe1\u7528\u5361\u53ef\u4ee5\u987a\u5229\u7ed3\u7b97\uff08\u53ea\u80fd\u4f7f\u7528\u4fe1\u7528\u5361\u8fdb\u884c\u4ed8\u6b3e\uff09\u3002\u6211\u7684\u60c5\u51b5\u662f\u5728\u7535\u8111\u7248\u9047\u5230\u4e86\u73b0\u91d1\u95ee\u9898\uff0c\u6ca1\u6709\u6210\u529f\uff0c\u4f46\u5728\u624b\u673a\u4e0a\u5c1d\u8bd5\u540e\u6210\u529f\u8d2d\u4e70\u4e86\u3002<\/p>\n<h3>\u518d\u8003\u653f\u7b56\u3001\u5e38\u89c1\u95ee\u9898\u89e3\u7b54\u3001\u5f55\u53d6\u901a\u77e5<\/h3>\n<p>\u8bf7\u70b9\u51fb\u4ee5\u4e0b\u94fe\u63a5\u67e5\u770bFAQ:<br \/>\nhttps:\/\/www.cloudera.com\/about\/training\/certification\/faq.html<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u518d\u53d7\u9a13\u306f\u4f55\u5ea6\u3067\u3082\u53ef\u80fd\u3067\u3059\u304c\u300130\u65e5\u306e\u671f\u9593\u3092\u7a7a\u3051\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u5408\u683c\u901a\u77e5\u306fUS\u30d3\u30b8\u30cd\u30b9\u30c7\u30a4\u30673\u65e5\u307b\u3069\u306e\u3088\u3046\u3067\u3059\u3002\u79c1\u306e\u5834\u5408\u306f\u571f\u66dc\u5915\u65b9\u53d7\u9a13\u3001\u706b\u66dc\u65e9\u671d\u306b\u9023\u7d61\u304c\u6765\u307e\u3057\u305f\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">1\u9031\u9593\u307b\u3069\u3067\u30c7\u30b8\u30bf\u30eb\u8a3c\u660e\u66f8\u304c\u767a\u884c\u3055\u308c\u307e\u3059<\/ul>\n<p>\u203b \u5982\u679c\u60a8\u6709\u67d0\u79cd\u9644\u4ef6\uff0c\u5219\u6709\u53ef\u80fd\u4f1a\u88ab\u653e\u5165\u5783\u573e\u90ae\u4ef6\u6587\u4ef6\u5939\u3002\u5982\u679c\u957f\u65f6\u95f4\u672a\u6536\u5230\uff0c\u8bf7\u68c0\u67e5\u60a8\u7684\u5783\u573e\u90ae\u4ef6\u6587\u4ef6\u5939\u3002<\/p>\n<h4>\u586b\u88dc<\/h4>\n<p>\u8003\u8bd5\u4e2d\u5fc3\u4e0d\u63d0\u4f9b\u6d4b\u8bd5\u73af\u5883\uff0c\u8003\u751f\u9700\u8981\u901a\u8fc7PSI\u8fdc\u7a0b\u8bbf\u95eeCloudera\u7684\u73af\u5883\u6765\u8fdb\u884c\u8003\u8bd5\u3002\u8003\u9898\u5c06\u5728\u6d4f\u89c8\u5668\u4e0a\u663e\u793a\uff0c\u8003\u751f\u9700\u8981\u5728\u8fdc\u7a0b\u684c\u9762\u4e0a\u7684\u7ec8\u7aef\u4e2d\u542f\u52a8spark-shell\u5e76\u4f7f\u7528\u5b58\u50a8\u5728HDFS\u548chive metastore\u4e2d\u7684\u6570\u636e\u8fdb\u884c\u6570\u636e\u5904\u7406\uff0c\u4ee5\u6ee1\u8db3\u8003\u8bd5\u8981\u6c42\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u8a66\u9a13\u306f\u51689\u554f\u3067\u3001\u51e6\u7406\u3057\u305f\u30c7\u30fc\u30bf\u3092\u6307\u5b9a\u3057\u305f\u5f62\u5f0f\u3067HDFS\u3084hive metastore\u306b\u683c\u7d0d\u3057\u305f\u7d50\u679c\u3067\u8a55\u4fa1\u3055\u308c\u307e\u3059\u3002\u90e8\u5206\u63a1\u70b9\u3082\u3042\u308b\u3068\u601d\u3044\u307e\u3059\u304c\u3001\u79c1\u306e\u5834\u5408\u306f7\u554f\u6b63\u89e3\u3067pass(\u5408\u683c)\u3067\u3057\u305f\u3002\u554f\u984c\u3054\u3068\u306b\u70b9\u6570\u304c\u9055\u3046\u53ef\u80fd\u6027\u3082\u3042\u308a\u306f\u3063\u304d\u308a\u3068\u306f\u3044\u3048\u307e\u305b\u3093\u304c6\u554f\u6b63\u89e3\u3060\u306866.7%\u306e\u305f\u3081\u4e0d\u5408\u683c\u3068\u306a\u308b\u3068\u601d\u308f\u308c\u3001\u4e0d\u6b63\u89e3\u306f2\u554f\u307e\u3067\u3068\u601d\u3063\u305f\u65b9\u304c\u3044\u3044\u3067\u3059\u3002<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">2\u6642\u9593\u7a0b\u5ea6\u3067\u3059\u304c\u30ea\u30e2\u30fc\u30c8\u74b0\u5883\u306e\u305f\u3081\u3084\u3084\u91cd\u305f\u304f\u3001\u307e\u305f\u30af\u30e9\u30b9\u30bf\u30fc\u51e6\u7406\u306e\u5f85\u3061\u6642\u9593\u306a\u3069\u3082\u3042\u308a1\u554f10\u5206\u7a0b\u5ea6\u306e\u6301\u3061\u6642\u9593\u306f\u76f8\u5f53\u77ed\u304f\u611f\u3058\u308b\u3068\u601d\u3044\u307e\u3059\u30021\uff5e2\u5206\u3067\u7d42\u308f\u308b\u3082\u306e\u3068\u6642\u9593\u306e\u304b\u304b\u308b\u3082\u306e\u3068\u3070\u3089\u3070\u3089\u3060\u3063\u305f\u308a\u3057\u307e\u3059\u3002<\/ul>\n<h3>\u5fc5\u9700\u54c1\uff0c\u51c6\u5907\u7269\u54c1<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u9854\u5199\u771f\u4ed8\u304d\u8eab\u5206\u8a3c\u660e\u66f81\u70b9(\u904b\u8ee2\u514d\u8a31\u8a3c\u3067OK)<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30de\u30a4\u30af\u30fb\u30ab\u30e1\u30e9\u4ed8\u304dPC<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u5468\u56f2\u306b\u4eba\u306e\u3044\u306a\u3044\u90e8\u5c4b\u30fb\u8a66\u9a13\u7528\u306e\u673a<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u554f\u984c\u6587\u3092\u7406\u89e3\u3059\u308b\u30ec\u30d9\u30eb\u306e\u82f1\u8a9e\u8aad\u89e3\u529b<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u8a66\u9a13\u76e3\u7763\u5b98\uff08\u30e2\u30cb\u30bf\u30fc\u30b9\u30bf\u30c3\u30d5\uff09\u3068\u306e\u30c1\u30e3\u30c3\u30c8\u304c\u3067\u304d\u308b\u7c21\u6613\u306a\u82f1\u8a9e\u529b<\/ul>\n<h3>\u5728\u4e2d\u6587\u4e2d\uff0c\u96e3\u6613\u5ea6\uff08\u6240\u611f\uff09\u7684\u542b\u7fa9\u53ef\u4ee5\u8868\u9054\u70ba\u8861\u91cf\u67d0\u4e8b\u7269\u7684\u96e3\u6613\u7a0b\u5ea6\u6240\u5e36\u4f86\u7684\u4e3b\u89c0\u611f\u53d7\u3002<\/h3>\n<p>\u8fd9\u6bb5\u5185\u5bb9\u672c\u8eab\u5f88\u7b80\u5355\uff0c\u8303\u56f4\u4e5f\u53ea\u6d89\u53ca\u5230Spark\u3001Hive\u548cSparkSQL\uff0c\u76f8\u5bf9\u8f83\u7a84\uff0c\u770b\u8d77\u6765\u5f88\u7b80\u5355\u3002\u4f46\u662f\uff0c\u5728\u4e00\u4e2a\u4e0d\u719f\u6089\u7684\u8fdc\u7a0b\u73af\u5883\u4e0b\uff0c\u9700\u8981\u5728\u77ed\u65f6\u95f4\u5185\u8fc5\u901f\u9002\u5e94\uff0c\u5e76\u4e14\u9700\u8981\u5b9e\u9645\u5904\u7406\u6570\u636e\u800c\u4e0d\u662f\u9009\u62e9\u9898\uff0c\u6240\u4ee5\u5fc5\u987b\u5b8c\u5168\u8bb0\u4f4f\u547d\u4ee4\u3002\u4ece\u5b9e\u9645\u64cd\u4f5c\u7684\u611f\u89c9\u6765\u770b\uff0c\u96be\u5ea6\u7565\u9ad8\u3002\u5982\u679c\u80fd\u591f\u51b7\u9759\u5e94\u5bf9\uff0c\u4e0d\u7b97\u96be\u7684\u4e00\u7c7b\u4efb\u52a1\u3002<\/p>\n<h2>\u8003\u8bd5\u524d\u7684\u60c5\u62a5\u548c\u53c2\u52a0\u8003\u8bd5\u7684\u52a8\u673a<\/h2>\n<p>\u4f5c\u4e3a\u5927\u6570\u636e\u5206\u6790\u6280\u80fd\u7684\u4e00\u90e8\u5206\uff0c\u6211\u5e0c\u671b\u638c\u63e1RDBMS\u3001DWH\u4ee5\u53caAWS\/GCP\u4e91\u76f8\u5173\u7684\u57fa\u672c\u77e5\u8bc6\uff0c\u5e76\u4e86\u89e3NoSQL\u4e2d\u7528\u4e8e\u5927\u89c4\u6a21\u5206\u5e03\u5f0f\u5904\u7406\u7684hadoop\u76f8\u5173\u6280\u672f\uff0c\u4ee5\u4fbf\u80fd\u591f\u83b7\u5f97\u5ba2\u89c2\u80fd\u529b\u7684\u8bc1\u660e\u3002\u56e0\u6b64\uff0c\u6211\u51b3\u5b9a\u8fdb\u884c\u76f8\u5e94\u7684\u8003\u8bd5\u3002<\/p>\n<p>\u6211\u4e4b\u524d\u6709\u7cfb\u7edf\u5f00\u53d1\u7684\u7ecf\u9a8c\uff0c\u4f46\u662f\u6ca1\u6709\u5b9e\u9645\u5de5\u4f5c\u7ecf\u9a8c\u6d89\u53caNoSQL\u3001Hadoop\u548cSpark\u76f8\u5173\u6280\u672f\u3002\u7531\u4e8e\u8003\u8bd5\u8d44\u683c\u6ca1\u6709\u5fc5\u8981\u7684\u8981\u6c42\uff0c\u6240\u4ee5\u6ca1\u6709\u5b9e\u9645\u5de5\u4f5c\u7ecf\u9a8c\u4e5f\u4e0d\u4f1a\u5bf9\u8003\u8bd5\u672c\u8eab\u6709\u7279\u522b\u7684\u95ee\u9898\u3002<\/p>\n<h2>\u662f\u5426\u9700\u8981\u79df\u7528\u529e\u516c\u5ba4\uff1f<\/h2>\n<p>\u6211\u662f\u5728\u5bb6\u53c2\u52a0\u7684\u8003\u8bd5\u3002\u8003\u573a\u76d1\u8003\u5b98\u901a\u8fc7\u804a\u5929\u544a\u8bc9\u6211\uff0c\u8981\u4e3e\u8d77\u5e26\u6444\u50cf\u5934\u7684\u7535\u8111\uff0c\u5168\u65b9\u4f4d\u5730\u62cd\u6444\u573a\u666f\u3002\u867d\u7136\u6211\u5468\u56f4\u6709\u4e66\u672c\u548c\u5176\u4ed6\u4e1c\u897f\uff0c\u4f46\u53ea\u8981\u5468\u56f4\u6ca1\u6709\u4eba\u7684\u8bdd\u5e94\u8be5\u6ca1\u6709\u95ee\u9898\u3002<br \/>\n\u5982\u679c\u62c5\u5fc3\u7684\u8bdd\uff0c\u6211\u8ba4\u4e3a\u53ef\u4ee5\u4f7f\u7528\u79df\u7528\u7684\u529e\u516c\u5ba4\uff0c\u4f46\u56e0\u4e3a\u8d39\u7528\u8f83\u9ad8\uff0c\u6211\u89c9\u5f97\u5728\u5bb6\u4e5f\u5b8c\u5168\u8db3\u591f\u3002<\/p>\n<p>\u8003\u8bd5\u65f6\uff0c\u8003\u8bd5\u684c\u5468\u56f4\u5fc5\u987b\u6ca1\u6709\u9664\u4e86\u7535\u8111\u9f20\u6807\u4ee5\u5916\u7684\u4efb\u4f55\u4e1c\u897f\uff08\u624b\u673a\uff0c\u5404\u79cd\u7535\u5b50\u8bbe\u5907\u7b49\uff09\u3002<\/p>\n<h2>\u8003\u8bd5\u524d\u548c\u8003\u8bd5\u671f\u95f4\u7684\u6ce8\u610f\u4e8b\u9879<\/h2>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u76f4\u524d\u306b\u6697\u8a18\u3057\u3088\u3046\u304b\u3068\u601d\u3044\u307e\u3057\u305f\u304c\u6e96\u5099\u306b\u624b\u9593\u53d6\u308a\u610f\u5916\u3068\u6642\u9593\u304b\u304b\u308a\u307e\u3057\u305f\u300215\u5206\u524d\u306b\u306f\u8a66\u9a13\u30b5\u30a4\u30c8\u306b\u9032\u3093\u3067\u3001\u8a66\u9a13\u958b\u59cb\u5b9a\u523b\u304b\u308915\u5206\u5f8c\u30b9\u30bf\u30fc\u30c8\u304c\u30ea\u30df\u30c3\u30c8\u306a\u306e\u3067\u305d\u3053\u307e\u3067\u306b\u306f\u7d42\u308f\u308b\u3088\u3046\u306b\u65e9\u3081\u306b\u6e96\u5099\u3059\u308b\u3053\u3068\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u96e2\u5e2d\u3082\u3067\u304d\u306a\u3044\u305f\u3081\u4e8b\u524d\u306b\u30c8\u30a4\u30ec\u30fb\u6c34\u5206\u88dc\u7d66\u306f\u5fc5\u9808\u3067\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u304a\u305d\u3089\u304f\u30a4\u30a2\u30d4\u30fc\u30b9\u3067\u4e0d\u6b63\u53d7\u9a13\u3059\u308b\u306e\u3092\u9632\u3050\u76ee\u7684\u3067\u3001\u554f\u984c\u6587\u3092\u8aad\u307f\u4e0a\u3052\u308b\u3053\u3068\u30fb\u53e3\u5143\u3092\u96a0\u3059\u3053\u3068\u304c\u7981\u6b62\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u8003\u3048\u3066\u308b\u3068\u304d\u306b\u624b\u3092\u53e3\u5143\u306b\u6301\u3063\u3066\u3044\u304f\u3068\u30c1\u30e3\u30c3\u30c8\u3067\u6ce8\u610f\u3055\u308c\u307e\u3059\uff08\u3059\u3050\u3084\u3081\u308c\u3070OK)<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u4e0d\u6b63\u3092\u7591\u308f\u308c\u308b\u306e\u3092\u9632\u3050\u305f\u3081\u3001\u76ee\u7dda\u3082\u753b\u9762\u304b\u3089\u5916\u3055\u306a\u3044\u65b9\u304c\u3044\u3044\u3067\u3059\u3002\u8003\u3048\u308b\u6642\u306b\u4e0a\u898b\u305f\u308a\u3059\u308b\u304f\u3089\u3044\u3067\u306f\u4f55\u3082\u8a00\u308f\u308c\u307e\u305b\u3093\u3067\u3057\u305f\u304c\u4e00\u5fdc<\/ul>\n<h2>\u5173\u4e8e\u82f1\u8bed\u80fd\u529b<\/h2>\n<p>\u9700\u8981\u80fd\u591f\u7406\u89e3\u95ee\u9898\u6587\u672c\u548c\u76d1\u8003\u5b98\u7684\u804a\u5929\u5185\u5bb9\uff0c\u4f46\u5e76\u4e0d\u9700\u8981\u4f1a\u8bdd\u80fd\u529b\u3002\u53ea\u9700\u8981\u8bfb\u61c2\u540e\uff0c\u5728\u804a\u5929\u4e2d\u56de\u590d&#8221;ok&#8221;\u6216&#8221;yes&#8221;\u5373\u53ef\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u3053\u3053\u306e\u30dc\u30bf\u30f3\u3092\u304a\u3057\u3066\u30ab\u30e1\u30e9\u30aa\u30f3\u306b\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u8eab\u5206\u8a3c\u660e\u66f8\u3092\u30ab\u30e1\u30e9\u306b\u6620\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u90e8\u5c4b\u3068\u30c7\u30b9\u30af\u5468\u308a\u3092\u6620\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u6e96\u5099\u304c\u3067\u304d\u305f\u3089\u8a66\u9a13\u958b\u59cb\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u8a00\u308f\u308c\u308b\u306e\u306f\u3053\u306e\u304f\u3089\u3044\u3067\u3059<\/ul>\n<h2>\u5728\u7ebf\u8bfe\u7a0b\u548c\u6a21\u62df\u8003\u8bd5<\/h2>\n<p>\u5982\u679c\u4f60\u80fd\u5920\u5728\u6c92\u6709\u770b\u4efb\u4f55\u6771\u897f\u7684\u60c5\u6cc1\u4e0b\uff0c\u6b63\u78ba\u5730\u5beb\u51fa\u9019\u5169\u500bUdemy\u8ab2\u7a0b\u7684\u6a21\u64ec\u8a66\u984c\u7684\u547d\u4ee4\uff0c\u6211\u76f8\u4fe1\u4f60\u53ef\u4ee5\u8f15\u9b06\u901a\u904e\u8003\u8a66\u3002\u5176\u4e2d\u4e00\u500b\u8ab2\u7a0b\u9644\u5e36\u6709\u89e3\u8aaa\u5f71\u7247\uff0c\u8acb\u52d9\u5fc5\u89c0\u770b\u3002<\/p>\n<p>\u4ef7\u683c\u5927\u7ea6\u4e3a5500\u65e5\u5143\u3002Udemy\u5b9a\u671f\u4e3e\u529e90%\u7684\u6298\u6263\u4fc3\u9500\u6d3b\u52a8\uff0c\u6240\u4ee5\u8bf7\u52a1\u5fc5\u4e0d\u8981\u5728\u9519\u8bef\u7684\u65f6\u5019\u4ee52-3\u4e07\u5143\u7684\u4ef7\u683c\u8d2d\u4e70\u3002<\/p>\n<p>\u2460\u300aCCA 175-Spark\u5f00\u53d1\u8005\u8003\u8bd5\u51c6\u5907+\u5b9e\u8df5\u6d4b\u8bd5\u300b\u7531Navdeep Kaur<br \/>\nhttps:\/\/www.udemy.com\/course\/complete-cca-175-hadoop-spark-developer-with-practice-test\/<\/p>\n<p>\u2461 Navdeep Kaur \u7684 CCA 175 Spark \u5f00\u53d1\u8005\u5b9e\u8df5\u6d4b\u8bd5<br \/>\nhttps:\/\/www.udemy.com\/course\/cca175-hadoop-spark-developer-practice-test\/<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/39-0.png\" alt=\"4_UDEMY\u6a21\u64ec\u8a66\u9a13\u306e\u8b1b\u5ea7\u30a2\u30a4\u30b3\u30f3.png\" \/><\/div>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30cd\u30a4\u30c6\u30a3\u30d6\u3067\u306f\u306a\u3044\u305f\u3081\u8074\u304d\u53d6\u308a\u3065\u3089\u304f\u3001\u5b57\u5e55\u3082\u4e0d\u6b63\u78ba\u3067\u3059\u304c\u753b\u9762\u4e0a\u306e\u8cc7\u6599\u3092\u898b\u308c\u3070\u5185\u5bb9\u7406\u89e3\u3068\u30b3\u30de\u30f3\u30c9\u306e\u78ba\u8a8d\u3059\u308b\u4e0a\u3067\u306f\u554f\u984c\u306a\u304f\u5206\u304b\u308b\u3068\u601d\u3044\u307e\u3059\u30021.5\u500d\u901f\u304f\u3089\u3044\u306b\u3059\u308b\u306e\u3092\u304a\u3059\u3059\u3081\u3057\u307e\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">CCA175\u306f\u8a66\u9a13\u306e\u5f62\u614b\u304c\u5909\u308f\u3063\u3066\u304a\u308a\u3001\u4ee5\u524d\u306fflume\u7b49\u542b\u307e\u308c\u3066\u3044\u305f\u3068\u3053\u308d\u9664\u5916\u3055\u308c\u3001spark\u4e2d\u5fc3\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002\u4e0a\u8a18\u8b1b\u5ea7\u306f\u672c\u8a18\u4e8b\u57f7\u7b46\u6642\u70b9\u3067\u306f\u552f\u4e00\u304d\u3061\u3093\u3068\u6700\u65b0\u306e\u8a66\u9a13\u7bc4\u56f2\u306b\u66f4\u65b0\u3057\u3066\u3044\u308b\u8b1b\u5ea7\u306e\u3088\u3046\u3067\u3059\u3002<\/ul>\n<p>\u6211\u8ba4\u4e3a\uff0c\u5f53\u6709\u4e00\u4e9b\u76f8\u4f3c\u7684\u4e1c\u897f\u57fa\u4e8e\u65e7\u6709\u524d\u63d0\uff0c\u60f3\u8981\u8fdb\u884c\u8fdb\u4e00\u6b65\u5b66\u4e60\u6216\u8005\u5b66\u4e60\u8d85\u51fa\u8003\u8bd5\u8303\u56f4\u65f6\uff0c\u4f7f\u7528\u8fd9\u4e9b\u6750\u6599\u662f\u5f88\u597d\u7684\u3002<\/p>\n<h4>\u8b1b\u5ea7\u7684\u5185\u5bb9\u7b80\u4ecb<\/h4>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">GCP\u4e0a\u3067\u306e\u74b0\u5883\u8a2d\u5b9a<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">spark\u3068\u306f\u3001RDD\u3001DAG<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">fileter\u3084join\u306a\u3069\u57fa\u672c\u7684\u306a\u30c7\u30fc\u30bf\u52a0\u5de5\u65b9\u6cd5<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u3064\u3044\u3066\u3001json\u3084avro\u306a\u3069\u30c7\u30fc\u30bf\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u5909\u63db<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">sparkSQL(Windows\u95a2\u6570\u542b\u3080)<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u2460\u6a21\u64ec\u8a66\u9a132\u984c\uff0b\u2461\u6a21\u64ec\u8a66\u9a133\u984c<\/ul>\n<p>\u203b\u6a21\u62df\u8003\u8bd5\u6bcf\u7ec4\u67098\u4e2a\u95ee\u9898\uff0c\u800c\u5b9e\u9645\u8003\u8bd5\u5219\u75319\u4e2a\u95ee\u9898\u7ec4\u6210\u3002\u4ece\u96be\u5ea6\u4e0a\u770b\uff0c\u5b9e\u9645\u8003\u8bd5\u66f4\u7b80\u5355\u66f4\u5bb9\u6613\u4e00\u4e9b\u3002<\/p>\n<p>\u5982\u679c\u60a8\u60f3\u5168\u9762\u5b66\u4e60Scala\uff0c\u9700\u8981\u82b1\u8d39\u76f8\u5f53\u591a\u7684\u65f6\u95f4\u9605\u8bfb\u5176\u4ed6\u4e66\u7c4d\u7b49\u3002\u4f46\u662f\uff0c\u5982\u679c\u60a8\u53ea\u9700\u8981\u5728\u672c\u6b21\u8003\u8bd5\u4e2d\u638c\u63e1Spark Scala\u7684\u57fa\u672c\u7406\u89e3\u7a0b\u5ea6\uff0c\u672c\u8bfe\u7a0b\u6240\u4ecb\u7ecd\u7684\u5185\u5bb9\u5df2\u7ecf\u8db3\u591f\u4e86\u3002<\/p>\n<h2>\u5b66\u4e60\u65b9\u6cd5\u548c\u73af\u5883\u8bbe\u7f6e<\/h2>\n<p>\u5982\u679c\u4f60\u62e5\u6709\u9ad8\u89c4\u683c\u7684\u7535\u8111\uff0c\u6211\u8ba4\u4e3a\u6700\u597d\u4f7f\u7528\u4e0e\u672c\u6b21\u8003\u8bd5\u76f8\u540c\u7684clouderaVM\u5728\u672c\u5730\u7535\u8111\u4e0a\u5c1d\u8bd5\uff0c\u4f46\u8003\u8651\u5230\u5b66\u4e60\u5728\u4e91\u73af\u5883\u4e2d\u6784\u5efaspark\u5904\u7406\uff0c\u6211\u63a8\u8350\u4f7f\u7528GCP\u7684\u65b9\u6cd5\u3002<\/p>\n<p>\u8fd9\u79cd\u65b9\u6cd5\u5728\u4e0a\u8ff0\u7684Udemy\u8bfe\u7a0b\u91cc\u5df2\u7ecf\u8be6\u7ec6\u89e3\u91ca\u4e86\uff08\u8fd8\u9644\u5e26\u4e86\u547d\u4ee4\uff09\uff0c\u53ea\u8981\u6309\u7167\u90a3\u6837\u505a\u5c31\u53ef\u4ee5\u987a\u5229\u5b8c\u6210\u3002<\/p>\n<h3>\u5173\u4e8eGCP\uff08\u96c6\u7fa4\u73af\u5883\u8bbe\u7f6e\uff09\u3002<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30a2\u30ab\u30a6\u30f3\u30c8\u4f5c\u6210\u30fb\u30af\u30ec\u30b8\u30c3\u30c8\u30ab\u30fc\u30c9\u767b\u9332\u304c\u5fc5\u8981\u3067\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u8cbb\u7528\u306f\u3001\u79c1\u306e\u5834\u5408\u306f3,000\u5186\u5f31\u304b\u304b\u308a\u307e\u3057\u305f\u3002\u30af\u30e9\u30b9\u30bf\u3092\u7a3c\u50cd\u3055\u305b\u3066\u3044\u308b\u3068\u8cbb\u7528\u304c\u639b\u304b\u308b\u305f\u3081\u3001\u7d42\u308f\u3063\u305f\u3089\u30af\u30e9\u30b9\u30bf\u3092\u6bce\u56de\u5fd8\u308c\u305a\u306b\u524a\u9664\u3057\u3001\u7fcc\u65e5\u306b\u306f\u304a\u652f\u6255\u3044\uff08Billing)\u3067\u8acb\u6c42\u91d1\u984d\u3092\u78ba\u8a8d\u3057\u3066\u304a\u304d\u307e\u3057\u3087\u3046<\/ul>\n<p>\u30fb\u5c3d\u7ba1\u5728Udemy\u8bfe\u7a0b\u4e2d\u4ecb\u7ecd\u4e86\u4f7f\u7528sqoop\u6ce8\u518c\u6d4b\u8bd5\u6570\u636e\u7684\u65b9\u6cd5\uff0c\u4f46\u7531\u4e8e\u65e0\u6cd5\u6210\u529f\uff0c\u6211\u9009\u62e9\u624b\u52a8\u521b\u5efa\u4e86csv\u7b49\u6587\u4ef6\u3002\u53ea\u8981\u8bb0\u4f4favro\u3001json\u7b49\u683c\u5f0f\u7684\u5171\u540c\u64cd\u4f5c\u65b9\u6cd5\uff0c\u5982format\uff08\u201cavro\u201d\uff09\u3001format\uff08\u201cjson\u201d\uff09\uff0c\u5373\u4f7f\u65e0\u6cd5\u521b\u5efa\u6570\u636e\u4e5f\u4e0d\u4f1a\u6709\u95ee\u9898\u3002<\/p>\n<h4>\u5728\u4ee5\u4e0b\u60c5\u666f\u4e2d\u4f7f\u7528GCP\uff0c\u53ef\u4ee5\u63d0\u4f9b\u4e00\u4e2a\u826f\u597d\u7684\u5b66\u4e60\u73af\u5883\uff1a<\/h4>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/53-0.png\" alt=\"1_\u5b66\u7fd2\u74b0\u5883.png\" \/><\/div>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Cloud Dataproc\u3067\u30af\u30e9\u30b9\u30bf\u30fc\u3092\u4f5c\u6210\u3057\u3001Virtual Machine(VM\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9)\u306eSSH\u3067\u30bf\u30fc\u30df\u30ca\u30eb\u8d77\u52d5\u2192spark-shell\u30b3\u30de\u30f3\u30c9\u3067spark\u8d77\u52d5\u3001\u3068\u3044\u3046\u6d41\u308c\u3067\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u30af\u30e9\u30b9\u30bf\u30fc\u3092\u524a\u9664\u3059\u308b\u3068\u30c7\u30fc\u30bf\u3082\u6d88\u3048\u308b\u305f\u3081\u3001\u56f3\u306e\u901a\u308a\u30c7\u30fc\u30bf\u306f\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u306b\u4f5c\u6210\u3057\u3001Cloud Storage\u306b\u30d5\u30a1\u30a4\u30eb\u30a2\u30d7\u30ed\u30fc\u30c9\u3057\u3001Cloud Storage\u3068Cloud Dataproc\u306eVM(virtual machine)\u306e\u30ed\u30fc\u30ab\u30eb\u30d5\u30a9\u30eb\u30c0\u3092GCSFUSE\u3067\u30de\u30a6\u30f3\u30c8\u3057\u3001VM\u30ed\u30fc\u30ab\u30eb\u30d5\u30a9\u30eb\u30c0\u304b\u3089HDFS\u306e\u6307\u5b9a\u30d5\u30a9\u30eb\u30c0\u306bPUT(hdfs dfs -put\u30b3\u30de\u30f3\u30c9)\u3059\u308b\u3053\u3068\u3067\u30c7\u30fc\u30bf\u6e96\u5099\u304c\u3067\u304d\u307e\u3059\u3002\u3053\u306e\u8fba\u306e\u624b\u9806\u3082\u8b1b\u5ea7\u306e\u8aac\u660e\u901a\u308a\u3084\u308c\u3070\u554f\u984c\u306a\u304f\u3067\u304d\u307e\u3059\u3002<\/ul>\n<p>\u4e0b\u9762\u662f\u4e00\u90e8\u4ecb\u7ecd\u7684\u5185\u5bb9<\/p>\n<pre class=\"post-pre\"><code>\/\/ GCSFUSE\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb<span class=\"o\">(<\/span>\u30b3\u30de\u30f3\u30c9\u306f\u4e00\u90e8\u306e\u307f\u629c\u7c8b\uff09\r\n<span class=\"nb\">export <\/span><span class=\"nv\">GCSFUSE_REPO<\/span><span class=\"o\">=<\/span>gcsfuse-lsb_release <span class=\"nt\">-c<\/span> <span class=\"nt\">-s<\/span>\r\n\r\n\r\n\/\/ VM\u30ed\u30fc\u30ab\u30eb\u306bGoogle Storage\u30de\u30a6\u30f3\u30c8\u30dd\u30a4\u30f3\u30c8\u7528\u30d5\u30a9\u30eb\u30c0\u4f5c\u6210\r\n<span class=\"nb\">mkdir<\/span> ~\/spark-dataset\r\n\r\n\/\/ GCP\u753b\u9762\u4e0a\u3067\u3001Cloud Storage\u306b\u30c7\u30fc\u30bf\u30a2\u30c3\u30d7\u30ed\u30fc\u30c9\u7528\u30d5\u30a9\u30eb\u30c0\u4f5c\u6210\u3000spark-dataframe\r\n\r\n\/\/ Cloud Storage\u3068VM\u30ed\u30fc\u30ab\u30eb\u30d5\u30a9\u30eb\u30c0\u3092\u30de\u30a6\u30f3\u30c8\r\ngcsfuse spark-dataframe ~\/spark-dataset\r\n\r\n\/\/ VM\u30ed\u30fc\u30ab\u30eb\u306e\u30d5\u30a9\u30eb\u30c0\u306bCloud Storage\u306e\u30d5\u30a9\u30eb\u30c0\u5185\u5bb9\u304c\u8868\u793a\u3055\u308c\u308b\u3053\u3068\u3092\u78ba\u8a8d\r\n<span class=\"nb\">cd<\/span> .\/spark-dataset\r\n<span class=\"nb\">ls<\/span>\r\n\r\n\/\/ hdfs\u306b\u4f5c\u696d\u7528\u30d5\u30a9\u30eb\u30c0\u4f5c\u6210\r\nhdfs dfs <span class=\"nt\">-mkdir<\/span> \/user\/testdata\r\n\r\n\/\/ VM\u30ed\u30fc\u30ab\u30eb\u30d5\u30a9\u30eb\u30c0<span class=\"o\">(<\/span>Cloud Storage\u3068\u30de\u30a6\u30f3\u30c8\u6e08\u307f<span class=\"o\">)<\/span>\u306e\u914d\u4e0b\u30c7\u30fc\u30bf\u5168\u90e8\u3092hdfs\u4f5c\u696d\u30d5\u30a9\u30eb\u30c0\u306b\u30b3\u30d4\u30fc<span class=\"o\">(<\/span>put<span class=\"o\">)<\/span>\r\nhdfs dfs <span class=\"nt\">-put<\/span> ~\/spark-dataset\/<span class=\"k\">*<\/span> \/user\/testdata\r\n\r\n\/\/ hdfs\u306e\u30d5\u30a1\u30a4\u30eb\u78ba\u8a8d<span class=\"o\">(<\/span>\u6b63\u3057\u304f\u30c7\u30fc\u30bf\u304c\u6e96\u5099\u3055\u308c\u3066\u3044\u308b\u3053\u3068<span class=\"o\">)<\/span>\r\nhdfs dfs <span class=\"nt\">-ls<\/span> \/user\/testdata\r\n<\/code><\/pre>\n<h4>\u5173\u4e8eavro<\/h4>\n<p>\u6211\u9700\u8981\u5728avro\u73af\u5883\u4e2d\u5bfc\u5165\u5916\u90e8\u5305\uff0c\u4f46\u662f\u5728\u6211\u7684\u60c5\u51b5\u4e0b\u6ca1\u6709\u6210\u529f\u3002\u5728\u8fd9\u4e2a\u6d4b\u8bd5\u73af\u5883\u4e2d\u5df2\u7ecf\u8bbe\u7f6e\u597d\u4e86\uff0c\u6240\u4ee5\u4e0d\u9700\u8981\u62c5\u5fc3\uff0c\u4f46\u662f\u5982\u679c\u6709\u4eba\u77e5\u9053\u65b9\u6cd5\uff0c\u8bf7\u544a\u8bc9\u6211\u3002<\/p>\n<p>\u5728\u5b66\u4e60\u4e2d\uff0cjson\u683c\u5f0f\u548cavro\u683c\u5f0f\u4e4b\u95f4\u7684\u5dee\u5f02\u5f88\u5c0f\uff0c\u6240\u4ee5\u6ca1\u6709\u7279\u522b\u7684\u95ee\u9898\uff08\u4e3a\u4ec0\u4e48\u8981\u8f6c\u6362\u4e3aavro\u3001\u662f\u5426\u66f4\u9ad8\u6548\u7b49\u65b9\u9762\u8fd8\u662f\u81ea\u5df1\u8c03\u67e5\u5e76\u7406\u89e3\u4e3a\u597d\uff09\u3002<\/p>\n<h3>\u63a8\u8350\u7684\u5b66\u4e60\u65b9\u6cd5<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u6700\u521d\u306f\u6a21\u64ec\u8a66\u9a13\u306e\u56de\u7b54\u3082\u306f\u3058\u3081\u304b\u3089\u5168\u90e8\u898b\u3066\u3001\u5168\u554f\u3067\u306a\u304f\u3066\u3082\u3044\u3044\u306e\u3067\u4e00\u90e8\u306f\u81ea\u5206\u3067\u30b3\u30de\u30f3\u30c9\u3092\u6253\u3061\u8fbc\u3093\u3067\u30c7\u30fc\u30bf\u64cd\u4f5c\u3067\u304d\u308b\u611f\u899a\u3092\u63b4\u3080<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u56de\u7b54\u306e\u30b3\u30de\u30f3\u30c9\u306f\u3059\u3079\u30661\u5ea6\u306f\u6253\u3061\u8fbc\u3093\u3067\u624b\u3067\u899a\u3048\u308b\uff08\u30c7\u30fc\u30bf\u306f\u7121\u3057\u3067\u3082\u3044\u3044\u306e\u3067\u30ad\u30fc\u30dc\u30fc\u30c9\u53e9\u3044\u3066\u899a\u3048\u308b\uff09<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u65b0\u3057\u3044\u60c5\u5831\u304c\u3067\u3066\u304f\u308b\u305f\u3073\u306b\u30dd\u30a4\u30f3\u30c8\u3092\u53d6\u308a\u51fa\u3057\u3066\u5206\u985e\u3057\u3001github\u306b.md\u30d5\u30a1\u30a4\u30eb\u3067\u81ea\u5206\u306a\u308a\u306e\u8f9e\u66f8\u3092\u4f5c\u308b<\/ul>\n<p>\u4f8b\uff09<br \/>\n\u6848\u4f8b\u7c7b<br \/>\n\u8fde\u63a5<br \/>\n\u7b5b\u9009<br \/>\n\u8702\u5de2\uff08Hive\uff09<br \/>\n\u5199\u5165\u683c\u5f0f<br \/>\n\u7b49\u7b49<\/p>\n<p>\u2192 \u8fd9\u4e9b\u5c06\u6709\u52a9\u4e8e\u77e5\u8bc6\u7684\u5de9\u56fa\uff0c\u800c\u4e14\u4ee5\u540e\u5728\u5b9e\u9645\u5de5\u4f5c\u4e2d\u4e5f\u4f1a\u6709\u7528\uff0c\u6bd4\u5982\u60f3\u8981\u52a0\u8f7d\u5e26\u6709\u6807\u9898\u7684CSV\u6587\u4ef6\u65f6\uff0c\u53ea\u9700\u53c2\u8003\u8fd9\u4e2a\u9875\u9762\u5373\u53ef\u3002<\/p>\n<h2>\u5b66\u4e60\u76f8\u5173\u77e5\u8bc6<\/h2>\n<p>\u9451\u65bcCCA175\u4e3b\u8981\u6d89\u53caSpark\u548cSparkSQL\u7684\u6578\u64da\u5de5\u7a0b\u6280\u80fd\uff0c\u70ba\u4e86\u7372\u5f97\u6709\u95dcHadoop\u76f8\u95dc\u6280\u8853\u7684\u77e5\u8b58\uff0c\u5efa\u8b70\u60a8\u984d\u5916\u5b78\u7fd2\u4ee5\u4e0b\u9805\u76ee\u3002<\/p>\n<p>\u7ec8\u6781\u5b9e\u8df5Hadoop &#8211; \u9a7e\u9a6d\u4f60\u7684\u5927\u6570\u636e\uff01<br \/>\nhttps:\/\/www.udemy.com\/course\/the-ultimate-hands-on-hadoop-tame-your-big-data\/<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/66-0.png\" alt=\"5_AMAZON\u51fa\u8eab.png\" \/><\/div>\n<p>\u6211\u662f\u4e9a\u9a6c\u900a\u7684\u9ad8\u7ea7\u5de5\u7a0b\u5e08\uff0c\u4e13\u6ce8\u4e8e\u5927\u6570\u636e\u5904\u7406\u548c\u673a\u5668\u5b66\u4e60\u65b9\u9762\uff0c\u5e76\u63d0\u4f9b\u591a\u4e2a\u8bfe\u7a0b\u3002\u8fd9\u4e9b\u8bfe\u7a0b\u5185\u5bb9\u53ef\u9760\u53ef\u4fe1\u3002<\/p>\n<p>\u5bf9\u4e8eHadoop\u751f\u6001\u7cfb\u7edf\u7684\u6982\u8ff0\uff0c\u7279\u522b\u662f\u7b2c7\u90e8\u5206\uff0c\u6700\u597d\u4fdd\u6301\u4e00\u5b9a\u7684\u5173\u6ce8\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/69-0.png\" alt=\"6.hadoopecosystem.png\" \/><\/div>\n<p>\u5bf9\u4e8e\u8fd9\u4e9b\u5173\u4e8e\u5927\u6570\u636e\u7684\u6d41\u884c\u8bcd\u6c47\uff0c\u6211\u8ba4\u4e3a\u6211\u4eec\u53ef\u4ee5\u7406\u89e3\u5b83\u4eec\u4e4b\u95f4\u7684\u533a\u522b\u4ee5\u53ca\u672f\u8bed\u7684\u542b\u4e49\u3002\u50cfApache Ambari\u3001YARN\u3001MESOS\u3001HBASE\u3001MapReduce\u3001TEZ\u3001Spark\u3001Pigs\u3001Hive\u3001HBASE\u3001Apache Storm\u3001Oozie\u3001Zookeeper\u3001sqoop\u3001flume\u3001kafka\u3001mongoDB\u3001cassandra\u3001MySQL\u3001Apache Drill\u3001HIVE\u3001Apache Phoenix\u3001Presto\u548cApache Zeppelin\u7b49\u3002<\/p>\n<h2>\u8003\u8bd5\u6280\u5de7\u548c\u4e34\u65f6\u5907\u8003\u7684\u76f8\u5173\u65b9\u9762<\/h2>\n<p>\u901a\u8fc7PSI\u5728\u7ebf\u6d4b\u8bd5\u7f51\u7ad9\uff0c\u4f7f\u7528\u6d4f\u89c8\u5668\u8fdb\u884c\u5c4f\u5e55\u5171\u4eab\uff0c\u5728\u8fdc\u7a0b\u73af\u5883\u4e0b\u8bbf\u95eeCloudera\u7684\u865a\u62df\u684c\u9762\u6765\u53c2\u52a0\u672c\u6b21\u8003\u8bd5\u3002<\/p>\n<p>\u4ee5\u4e0b\u662f\u7c7b\u4f3c\u4e0b\u56fe\u7684\u5f62\u8c61\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/74-0.png\" alt=\"2_\u8a66\u9a13\u74b0\u5883.png\" \/><\/div>\n<h3>\u4e3a\u4e86\u8ba9\u81ea\u5df1\u51b7\u9759\u4e0b\u6765\uff0c\u9996\u5148\u8981\u505a\u7684\u662f\u3010\u4e8b\u524d\u51c6\u5907\u3011\u90e8\u5206\u3002<\/h3>\n<p>\u4e3a\u4e86\u76d1\u63a7\u4e0d\u6b63\u9632\u6b62\uff0c\u6211\u4eec\u5c06\u76d1\u89c6\u60a8\u7684\u89c6\u7ebf\u548c\u9f20\u6807\u70b9\u51fb\u3002\u867d\u7136\u8fd9\u53ef\u80fd\u4f1a\u4ea7\u751f\u4e00\u4e9b\u526f\u4f5c\u7528\uff0c\u4f46\u662f\u7535\u6ce2\u58f0\u4f1a\u6301\u7eed\u4e0d\u65ad\u5730\u53d1\u51fa\u55e1\u55e1\u58f0\uff0c\u58f0\u97f3\u4f1a\u968f\u7740\u60a8\u7684\u64cd\u4f5c\u800c\u54cd\u8d77\u3002<\/p>\n<p>\u5982\u679c\u4f60\u72ec\u81ea\u5728\u623f\u95f4\u91cc\u53c2\u52a0\u8003\u8bd5\uff0c\u8fd9\u4f1a\u5bf9\u4f60\u7684\u7cbe\u795e\u9020\u6210\u76f8\u5f53\u5927\u7684\u7535\u6ce2\u653b\u51fb\uff0c\u6240\u4ee5\u53ea\u9700\u8981\u4e8b\u5148\u77e5\u9053\u8fd9\u4e00\u70b9\u5c31\u53ef\u4ee5\u4f7f\u81ea\u5df1\u51b7\u9759\u4e0b\u6765\uff08\u53ef\u4ee5\u8c03\u4f4e\u97f3\u91cf\u6216\u91c7\u53d6\u63aa\u65bd\uff09\u3002<\/p>\n<p>\u4e3a\u4e86\u5c06\u6d4f\u89c8\u5668\u754c\u9762\u9650\u5236\u5728\u8bd5\u9a8c\u9875\u9762\u4e0a\uff0c\u4e8b\u5148\u5173\u95ed\u6d4f\u89c8\u5668\u7684\u5176\u4ed6\u6807\u7b7e\u9875\uff0c\u5e76\u786e\u4fdd\u4e66\u7b7e\u680f\u7edd\u4e0d\u5448\u73b0\u5168\u5c4f\u663e\u793a\u3002\u540c\u65f6\u8fd8\u5e94\u8c03\u6574\u8bbe\u7f6e\u4ee5\u9690\u85cf\u4efb\u52a1\u680f\u3002<\/p>\n<h3>\u9996\u5148\uff0c\u4e3a\u4e86\u5e73\u9759\u4e0b\u6765\uff0c\u5148\u5c1d\u8bd5\u3010\u8003\u8bd5\u5f00\u59cb\u540e\u7bc7\u3011\u3002<\/h3>\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\u7531\u4e8e\u8fdc\u7a0b\u73af\u5883\u538b\u529b\u8f83\u5927\uff0c\u662f\u4e00\u4e2a\u7e41\u91cd\u7684\u6c34\u4e0b\u73af\u5883\uff0c\u4f46\u662f\u53ef\u4ee5\u5c06\u95ee\u9898\u6587\u7684\u6d4f\u89c8\u5668\u5411\u53f3\u79fb\u52a8\u3002<\/ol>\n<\/li>\n<\/ol>\n<p>\u542f\u52a8\u7ec8\u7aef\uff0c\u8c03\u6574\u7a97\u53e3\u5927\u5c0f\u5e76\u5c06\u5176\u9760\u5de6\u4fa7\u3002(\u4e3a\u4e86\u53ef\u4ee5\u5c06\u95ee\u9898\u6587\u548c\u7ec8\u7aef\u5e76\u6392\u67e5\u770b)<br \/>\n\u5148\u505a\u4e00\u9053\u9898\uff0c\u5c31\u53ef\u4ee5\u5b89\u5fc3\u4e86\uff0c\u6240\u4ee5\u9996\u5148\u8f93\u5165\u4ee5\u4e0b\u5185\u5bb9\u4ee5\u83b7\u5f97\u64cd\u4f5c\u7684\u81ea\u4fe1\u662f\u5f88\u91cd\u8981\u7684\u3002\u4e00\u65e6\u638c\u63e1\u4e86\u611f\u89c9\uff0c\u7531\u4e8e\u4efb\u52a1\u672c\u8eab\u5f88\u7b80\u5355\uff0c\u6211\u8ba4\u4e3a\u5de5\u4f5c\u4f1a\u8d8a\u6765\u8d8a\u987a\u5229\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\">\/\/ \u8d77\u52d5<\/span>\r\n<span class=\"n\">spark<\/span><span class=\"o\">-<\/span><span class=\"n\">shell<\/span>\r\n\r\n<span class=\"c1\">\/\/ \u4ee5\u4e0b\u3001scala\u30d7\u30ed\u30f3\u30d7\u30c8(\u30d1\u30b9\u306f\u554f\u984c\u6587\u8a18\u8f09\u306e\u5165\u529b\u30c7\u30fc\u30bf\u7528\u30d1\u30b9)<\/span>\r\n<span class=\"c1\">\/\/ \u3068\u308a\u3042\u3048\u305a\u3056\u3063\u304f\u308a\u30ed\u30fc\u30c9<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">datadf<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/aaaaa\/bbbb\/xxxfile\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"c1\">\/\/ \u4e2d\u8eab\u3092\u898b\u308b\uff08\u30bf\u30d6\u533a\u5207\u308a\u306a\u30891\u5217\u306b\u51fa\u3066\u304f\u308b)<\/span>\r\n<span class=\"nv\">datadf<\/span><span class=\"o\">.<\/span><span class=\"py\">show<\/span><span class=\"o\">(<\/span><span class=\"mi\">5<\/span><span class=\"o\">)<\/span>\r\n<span class=\"nv\">datadf<\/span><span class=\"o\">.<\/span><span class=\"py\">printSchema<\/span><span class=\"o\">()<\/span>\r\n<\/code><\/pre>\n<p>\u6ce8\u610f\uff1a\u5982\u679c\u6709\u6ce8\u660e\u5b83\u662f\u5927\u89c4\u6a21\u6570\u636e\u7684\u63d0\u793a\uff0c\u4f8b\u59823000\u4e07\u4e2a\u6570\u636e\uff0c\u8bf7\u907f\u514d\u64cd\u4f5c\uff0c\u56e0\u4e3a\u4f1a\u82b1\u8d39\u5f88\u957f\u65f6\u95f4\u3002\u7b2c\u4e00\u4e2a\u95ee\u9898\u57fa\u672c\u4e0a\u6ca1\u6709\u8fd9\u79cd\u53ef\u80fd\u6027\u3002<\/p>\n<h4>\u65e0\u6cd5\u4f7f\u7528hadoop fs\uff08hdfs dfs\uff09\u547d\u4ee4\u5417\uff1f<\/h4>\n<p>\u5728\u6211\u7684\u60c5\u51b5\u4e0b\uff0c\u4e0d\u77e5\u4e3a\u4f55\u5728\u6b63\u5f0f\u8003\u8bd5\u73af\u5883\u4e2d\u65e0\u6cd5\u4f7f\u7528hadoop fs\u3001hdfs dfs\u547d\u4ee4\uff0c\u6211\u672c\u6765\u60f3\u7528cat\u547d\u4ee4\u6765\u786e\u8ba4\u6570\u636e\u60c5\u51b5\uff0c\u4f46\u5374\u65e0\u6cd5\u5b9e\u73b0\uff0c\u6211\u611f\u5230\u5f88\u7126\u8651\u3002\u867d\u7136\u6700\u540e\u8fd8\u662f\u89e3\u51b3\u4e86\uff0c\u4f46\u5982\u679c\u6709\u4eba\u77e5\u9053\u89e3\u51b3\u65b9\u6cd5\uff0c\u8bf7\u544a\u8bc9\u6211\u3002\u8fd9\u53ef\u80fd\u53ea\u662f\u8003\u8bd5\u7279\u6b8a\u7684\u60c5\u51b5\u3002<\/p>\n<h3>\u8003\u8bd5\u7ecf\u5386\u611f\u53d7\uff08\u4e0e\u6a21\u62df\u8003\u8bd5\u7684\u4e0d\u540c\u4e4b\u5904\uff09<\/h3>\n<p>\u7531\u4e8e\u5728\u6a21\u62df\u8003\u8bd5\u7684\u7ec3\u4e60\u7248\u672c\u4e2d\uff0c\u6211\u610f\u8bc6\u5230\u4e86\u4e00\u4e9b\u4e4b\u524d\u6ca1\u6709\u6ce8\u610f\u5230\u7684\u95ee\u9898\uff0c\u4ee5\u4e0b\u662f\u6211\u8bb0\u5f55\u4e0b\u6765\u7684\u3002<\/p>\n<ol>\u5728\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\uff08\u7ea63000\u4e07\u6761\uff09\u65f6\uff0c\u5982\u679c\u80fd\u591f\u4e00\u6c14\u5475\u6210\u5730\u4ece\u52a0\u8f7d\u5230\u5199\u5165\uff0c\u800c\u4e0d\u9700\u8981\u5b58\u50a8\u5728\u53d8\u91cf\u4e2d\uff0c\u5904\u7406\u65f6\u95f4\u4e5f\u4f1a\u66f4\u5feb\u3002\u5c3d\u7ba1\u5c06\u6570\u636e\u5b58\u50a8\u5728\u53d8\u91cf\u4e2d\u66f4\u4e3a\u53ef\u9760\uff0c\u4f46\u5bf9\u4e8e\u8f83\u5927\u7684\u6570\u636e\u6765\u8bf4\uff0c\u8fd9\u4f1a\u589e\u52a0\u5904\u7406\u65f6\u95f4\u3002<\/ol>\n<pre class=\"post-pre\"><code><span class=\"c1\">\/\/ \u5909\u6570\u306b\u5165\u308c\u308b\u30d1\u30bf\u30fc\u30f3(dataDF\u7d4c\u7531)<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">dataDF<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"sep\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"\\t\"<\/span><span class=\"o\">).<\/span><span class=\"py\">csv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/xxx\/inputfile\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">select<\/span><span class=\"o\">(<\/span><span class=\"n\">$<\/span><span class=\"s\">\"_c0\"<\/span><span class=\"o\">,<\/span><span class=\"n\">$<\/span><span class=\"s\">\"_c1\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"nv\">dataDF<\/span><span class=\"o\">.<\/span><span class=\"py\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nv\">x<\/span><span class=\"o\">.<\/span><span class=\"py\">mkString<\/span><span class=\"o\">(<\/span><span class=\"s\">\"|\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nv\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"text\"<\/span><span class=\"o\">).<\/span><span class=\"py\">save<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n\r\n\r\n<span class=\"c1\">\/\/ \u5909\u6570\u306b\u5165\u308c\u305a\u306b\u51e6\u7406\u3059\u308b\u30d1\u30bf\u30fc\u30f3(load\u3057\u3066\u305d\u306e\u307e\u307ewrite)<\/span>\r\n<span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"sep\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"\\t\"<\/span><span class=\"o\">).<\/span><span class=\"py\">csv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/xxx\/inputfile\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">select<\/span><span class=\"o\">(<\/span><span class=\"n\">$<\/span><span class=\"s\">\"_c0\"<\/span><span class=\"o\">,<\/span><span class=\"n\">$<\/span><span class=\"s\">\"_c1\"<\/span><span class=\"o\">).<\/span><span class=\"py\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nv\">x<\/span><span class=\"o\">.<\/span><span class=\"py\">mkString<\/span><span class=\"o\">(<\/span><span class=\"s\">\"|\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nv\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"text\"<\/span><span class=\"o\">).<\/span><span class=\"py\">save<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<ol>\u4ece\u672a\u89c1\u8fc7\u7684\u538b\u7f29\u683c\u5f0f\u548c\u6587\u4ef6\u683c\u5f0f<\/ol>\n<p>\u5728\u6a21\u62df\u8003\u8bd5\u4e2d\uff0c\u5f88\u5c11\u51fa\u73b0\u7684orc\u6587\u4ef6\u683c\u5f0f\u548csnappy\u538b\u7f29\u683c\u5f0f\u88ab\u9891\u7e41\u95ee\u5230\u3002\u7136\u800c\uff0c\u53ea\u9700\u5c06option(&#8220;compression&#8221;,&#8221;gzip&#8221;)\u4e2d\u7684\u201cgzip\u201d\u6539\u4e3a\u201csnappy\u201d\uff0c\u6240\u4ee5\u6ca1\u6709\u7279\u522b\u7d27\u8feb\u7684\u9700\u8981\u3002<\/p>\n<h3>\u6700\u597d\u4e8b\u5148\u590d\u4e60\u8bb0\u5fc6\u7684\u4e1c\u897f<\/h3>\n<p>\u5373\u4f7f\u7406\u89e3\u4e86\u57fa\u672c\u64cd\u4f5c\uff0c\u4f46\u6709\u4e9b\u7ec6\u8282\u5982\u679c\u4e0d\u9884\u5148\u8bb0\u4f4f\u7684\u8bdd\u53ef\u80fd\u4f1a\u51fa\u9519\uff0c\u6240\u4ee5\u6211\u91c7\u53d6\u4e86\u4ee5\u4e0b\u63aa\u65bd\u3002\u5b9e\u9645\u4e0a\uff0c\u8fd9\u4e9b\u63aa\u65bd\u5728\u8003\u8bd5\u4e2d\u6839\u672c\u6ca1\u6709\u6d89\u53ca\uff0c\u4f46\u6211\u8fd8\u662f\u7528\u62ec\u53f7\u8fdb\u884c\u4e86\u8865\u5145\u8bf4\u660e\u3002<\/p>\n<p>sequence (\u672a\u51fa\u73b0)<br \/>\nxml (\u672a\u51fa\u73b0)<br \/>\nhive\uff0cpartition (\u672a\u51fa\u73b0)<br \/>\ndense_rank (\u672a\u51fa\u73b0)<br \/>\narg sum (\u672a\u51fa\u73b0)<br \/>\nunixtime\u8f6c\u6362 (\u672a\u51fa\u73b0)<br \/>\nchmod (\u672a\u51fa\u73b0)<\/p>\n<p>\u5b8c\u5168\u4e0d\u719f\u6089\u3002\u66f4\u597d\u7684\u662f\u8981\u5145\u5206\u7df4\u7fd2Hive\u548cMeta Store\u8868\u7684\u8b80\u5beb\u3002<br \/>\n\u7136\u800c\uff0c\u5728\u5be6\u969b\u8003\u8a66\u4e2d\uff0c\u6211\u5b8c\u5168\u7121\u6cd5\u6210\u529f\u5275\u5efaHive\u8868\uff08\u4e0d\u662f\u9810\u8a2d\u7684\uff0c\u800c\u662f\u5728\u500b\u5225\u7684\u6578\u64da\u5eab\u4e0b\uff09\u3002\u5176\u4e2d\u4e00\u500b\u932f\u8aa4\u554f\u984c\u662f\u9019\u500b\uff0c\u53e6\u4e00\u500b\u662fjoin\u3002<\/p>\n<p>\u5982\u679c\u53c2\u8003\u6700\u65b0\u7248\u672c\u7684Udemy\u8bfe\u7a0b\uff0c\u4e5f\u8bb8\u80fd\u591f\u5f88\u597d\u5730\u4f53\u73b0\u51fa\u6765\u3002<\/p>\n<h3>spark-shell\u547d\u4ee4\u7684\u91cd\u70b9<\/h3>\n<p>\u5728\u6570\u636e\u64cd\u4f5c\u65b9\u9762\u6709\u591a\u79cd\u65b9\u6cd5\uff0c\u867d\u7136\u80fd\u591f\u540c\u65f6\u638c\u63e1\u5168\u90e8\u65b9\u6cd5\u662f\u6700\u597d\u7684\uff0c\u4f46\u53ea\u8981\u6709\u4e00\u79cd\u65b9\u6cd5\u786e\u5b9e\u638c\u63e1\u4e86\uff0c\u4e5f\u80fd\u591f\u5e94\u5bf9\uff0c\u6240\u4ee5\u6700\u597d\u662f\u9996\u5148\u786e\u4fdd\u80fd\u591f\u7a33\u5b9a\u5730\u638c\u63e1\u90a3\u4e00\u79cd\u65b9\u6cd5\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">case class\u3067schema\u5b9a\u7fa9\u3057\u3066\u304a\u304f\u2192\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3084sparkSQL\u64cd\u4f5c\u304c\u3067\u304d\u308b\u306e\u3067<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u203binferSchema\u306e\u65b9\u6cd5\u3082\u304a\u3055\u3048\u3066\u304a\u3044\u305f\u65b9\u304c\u3044\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u6a21\u64ec\u8a66\u9a13\u306e\u56de\u7b54\u3068\u306f\u9055\u3044\u3001\u4e00\u3064\u30c7\u30fc\u30bf\u52a0\u5de5\u3059\u308b\u3054\u3068\u306b val datadfxx = xxxx\u3068\u5909\u6570\u306b\u683c\u7d0d\u3057\u3066 datadfxx.show(5)\u306a\u3069\u3067\u78ba\u8a8d\u3057\u3064\u3064\u78ba\u5b9f\u306b\u9032\u3081\u308b\u65b9\u304c\u3044\u3044\u3067\u3059\u3002\u30df\u30b9\u3082\u6e1b\u3089\u305b\u308b\u306e\u3067\u3002\u305f\u3060\u3057\u3001\u6570\u5343\u4e07\u4ef6\u306e\u30c7\u30fc\u30bf\u3001\u3068\u6ce8\u610f\u304c\u5165\u3063\u3066\u3044\u308b\u3068\u304d\u306f\u907f\u3051\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u8a66\u9a13\u6642\u9593\u304c\u7121\u304f\u306a\u308b\u306e\u3067<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u554f\u984c\u300cjson\u30d5\u30a1\u30a4\u30eb\u3067\u683c\u7d0d\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u30d5\u30a1\u30a4\u30eb\u306f\u5727\u7e2e\u3057\u3066\u304a\u3044\u3066\u304f\u3060\u3055\u3044\u300d\u306f\u3001\u5727\u7e2e\u3057\u3066\u304b\u3089json\u3067\u4fdd\u5b58\u3059\u308b\u3068\u3044\u3046\u9806\u756a\u3067\u52a0\u5de5\u3059\u308b\u3053\u3068\u306b\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<pre class=\"post-pre\"><code><span class=\"c1\">\/\/ \u65b9\u6cd5\u2460<\/span>\r\n<span class=\"nv\">dataFile<\/span><span class=\"o\">.<\/span><span class=\"py\">select<\/span><span class=\"o\">(<\/span><span class=\"s\">\"aaa\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"aaaa\"<\/span><span class=\"o\">).<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"compression\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"gzip\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">json<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"c1\">\/\/ \u65b9\u6cd5\u2461<\/span>\r\n<span class=\"nv\">dataFile<\/span><span class=\"o\">.<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">mode<\/span><span class=\"o\">(<\/span><span class=\"s\">\"overwrite\"<\/span><span class=\"o\">).<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"compression\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"gzip\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"json\"<\/span><span class=\"o\">).<\/span><span class=\"py\">save<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">join\u306e\u30c7\u30d5\u30a9\u30eb\u30c8\u304cInner Join\u3067\u3042\u308b\u3053\u3068\u3092\u7406\u89e3\u3002join\u306f\u307b\u307c\u78ba\u5b9f\u306b\u554f\u308f\u308c\u307e\u3059<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u203bjoin left-anti\u3082\u4f7f\u3048\u308b\u65b9\u304c\u3044\u3044\u3067\u3059<\/ul>\n<pre class=\"post-pre\"><code>\u4f8b\r\n\u25c6\u2460user_id\r\nA\r\nB\r\nC\r\n\r\n\u25c6\u2461order_id,user_id\r\n1,A\r\n2,A\r\n3,A\r\n4,C\r\n\r\n\/\/ \u2460\uff0b\u2461join\u7d50\u679c\r\n\u2460.join(\u2461,\"user_id\") \r\n\u7d50\u679c\uff1a\r\n1\r\n3\r\n<\/code><\/pre>\n<p>\u203b\u7531\u4e8e\u5185\u8fde\u63a5\u662f\u9ed8\u8ba4\u9009\u9879\uff0c\u53ea\u6709\u5b58\u5728\u4e8e\u9009\u98792\u4e2d\u7684A\u548cB\u624d\u4f1a\u4fdd\u7559\u4e0b\u6765\u3002<br \/>\n\u203b\u6ce8\u610f\u8f93\u51fa\u5355\u4f4d\uff0c\u8981\u4fdd\u7559\u5de6\u8868\u7684\u9009\u98791\u4e2d\u7684user_id\uff0c\u786e\u4fdd\u6570\u636e\u80fd\u591f\u88ab\u8fde\u63a5\u5728\u4e00\u8d77\u3002\u5bf9\u4e8e\u8fde\u63a5\u952e\u76f8\u540c\u4f46\u540d\u79f0\u4e0d\u540c\u7684\u6a21\u5f0f\uff0c\u9700\u8981\u4e86\u89e3\u6bcf\u79cd\u5199\u6cd5\uff0c\u5e76\u5efa\u8bae\u5145\u5206\u7406\u89e3\u5982\u4f55\u9010\u6e10\u589e\u52a0\u5217\u7684\u65b9\u6cd5\u3002<\/p>\n<h2>\u4ecb\u7ecd\u793a\u4f8b\u4ee3\u7801<\/h2>\n<p>\u6700\u540e\uff0c\u6211\u5e0c\u671b\u4ecb\u7ecd\u4e00\u4e9b\u5728CCA175\u4e2d\u5904\u7406\u7684\u6311\u6218\uff0c\u4f5c\u4e3a\u7ed3\u675f\u3002<\/p>\n<h3>\u25bc\u7b2c\u4e00\u8981\u7d20<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">avro\u30d5\u30a1\u30a4\u30eb\u3092gzip\u5727\u7e2e\u3057\u3066parquet\u5f62\u5f0f\u3067\u683c\u7d0d\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u51fa\u529b\u30d5\u30a1\u30a4\u30eb\u306ffname,state\u5217\u3060\u3051\u306b\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<pre class=\"post-pre\"><code><span class=\"k\">val<\/span> <span class=\"nv\">datadf<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"avro\"<\/span><span class=\"o\">).<\/span><span class=\"py\">load<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/avrofile\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"nv\">datadf<\/span><span class=\"o\">.<\/span><span class=\"py\">select<\/span><span class=\"o\">(<\/span><span class=\"s\">\"fname\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"state\"<\/span><span class=\"o\">).<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"compression\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"gzip\"<\/span><span class=\"o\">).<\/span><span class=\"py\">parquet<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u25bc\u7b2c\u4e8c\u8981\u70b9<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30d1\u30a4\u30d7\u533a\u5207\u308a\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092gzip\u5727\u7e2e\u3055\u308c\u305fparquet\u5f62\u5f0f\u3067\u300ccustomer_m\u300d\u3068\u3044\u3046\u540d\u524d\u3067meta store\u306b\u66f8\u304d\u8fbc\u307f\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">fname(\u540d\u524d\uff09\u306bM\u3092\u542b\u3080\u884c\u3060\u3051\u306b\u3057\u3066\u3001state\u3054\u3068\u306e\u30e6\u30fc\u30b6\u30fc\u4ef6\u6570\u3092\u30ab\u30a6\u30f3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<pre class=\"post-pre\"><code><span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"sep\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"|\"<\/span><span class=\"o\">).<\/span><span class=\"py\">csv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/tab\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">select<\/span><span class=\"o\">(<\/span><span class=\"nf\">col<\/span><span class=\"o\">(<\/span><span class=\"s\">\"_c1\"<\/span><span class=\"o\">).<\/span><span class=\"py\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"fname\"<\/span><span class=\"o\">),<\/span><span class=\"nf\">col<\/span><span class=\"o\">(<\/span><span class=\"s\">\"_c2\"<\/span><span class=\"o\">).<\/span><span class=\"py\">as<\/span><span class=\"o\">(<\/span><span class=\"s\">\"state\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">where<\/span><span class=\"o\">(<\/span><span class=\"s\">\"fname like '%M%'\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">groupBy<\/span><span class=\"o\">(<\/span><span class=\"s\">\"state\"<\/span><span class=\"o\">).<\/span><span class=\"py\">count<\/span><span class=\"o\">.<\/span>\r\n<span class=\"nv\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">mode<\/span><span class=\"o\">(<\/span><span class=\"s\">\"overwrite\"<\/span><span class=\"o\">).<\/span><span class=\"py\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"compression\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"gzip\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">option<\/span><span class=\"o\">(<\/span><span class=\"s\">\"fileFormat\"<\/span><span class=\"o\">,<\/span><span class=\"s\">\"parquet\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"hive\"<\/span><span class=\"o\">).<\/span><span class=\"py\">saveAsTable<\/span><span class=\"o\">(<\/span><span class=\"s\">\"customer_m\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u25bc\u7b2c\u4e09\u8981\u4ef6<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">HDFS(\/user\/infile)\u306b\u3042\u308bparquet\u5f62\u5f0f\u306e\u30d5\u30a1\u30a4\u30eb\u304b\u3089\u30012020\u5e743\u6708\u306epending\u4e2d\u306e\u6ce8\u6587\u6570\u3092\u65e5\u5225\u306b\u30ab\u30a6\u30f3\u30c8\u3057\u3066json\u5f62\u5f0f\u3067HDFS(\/user\/output)\u306b\u683c\u7d0d\u3057\u3066\u304f\u3060\u3055\u3044<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u6ce8\u6587\u65e5\u306funix\u30bf\u30a4\u30e0\u5f62\u5f0f\u3067\u3059<\/ul>\n<pre class=\"post-pre\"><code><span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"parquet\"<\/span><span class=\"o\">).<\/span><span class=\"py\">load<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/infile\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">withColumn<\/span><span class=\"o\">(<\/span><span class=\"s\">\"order_date\"<\/span><span class=\"o\">,<\/span><span class=\"nf\">to_date<\/span><span class=\"o\">(<\/span><span class=\"nf\">from_unixtime<\/span><span class=\"o\">(<\/span><span class=\"n\">$<\/span><span class=\"s\">\"order_date\"<\/span><span class=\"o\">\/<\/span><span class=\"mi\">1000<\/span><span class=\"o\">))).<\/span>\r\n<span class=\"nf\">filter<\/span><span class=\"o\">(<\/span><span class=\"s\">\"order_date LIKE '2020-03%' and order_status='PENDING'\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">groupBy<\/span><span class=\"o\">(<\/span><span class=\"n\">$<\/span><span class=\"s\">\"order_date\"<\/span><span class=\"o\">).<\/span><span class=\"py\">count<\/span><span class=\"o\">.<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">mode<\/span><span class=\"o\">(<\/span><span class=\"s\">\"overwrite\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"json\"<\/span><span class=\"o\">).<\/span><span class=\"py\">save<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u7532\u65b9\u9700\u8981\u63d0\u4f9b\u4ee5\u4e0b\u8981\u4ef6\u3002<\/h3>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">case class\u3092\u4f7f\u7528\u3057\u3066spark.sql\u3067\u30c7\u30fc\u30bf\u51e6\u7406\u3059\u308b\u4f8b<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u30d7\u30ed\u30c0\u30af\u30c8id\u5225\u306e\u6ce8\u6587\u6570\u30c8\u30c3\u30d710\u3092\u96c6\u8a08<\/ul>\n<pre class=\"post-pre\"><code><span class=\"c1\">\/\/ 1.case class\u3067\u30b9\u30ad\u30fc\u30de\u5b9a\u7fa9<\/span>\r\n<span class=\"k\">case<\/span> <span class=\"k\">class<\/span> <span class=\"nc\">Products<\/span><span class=\"o\">(<\/span><span class=\"n\">pId<\/span><span class=\"k\">:<\/span><span class=\"kt\">Integer<\/span><span class=\"o\">,<\/span><span class=\"n\">name<\/span><span class=\"k\">:<\/span><span class=\"kt\">String<\/span><span class=\"o\">)<\/span>\r\n<span class=\"k\">case<\/span> <span class=\"k\">class<\/span> <span class=\"nc\">Orders<\/span><span class=\"o\">(<\/span><span class=\"n\">prodId<\/span><span class=\"k\">:<\/span><span class=\"kt\">Integer<\/span><span class=\"o\">,<\/span><span class=\"n\">order_total<\/span><span class=\"k\">:<\/span><span class=\"kt\">Float<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"c1\">\/\/ 2.\u30ab\u30f3\u30de\u533a\u5207\u308acsv\u30d5\u30a1\u30a4\u30eb\u3092\u5b9a\u7fa9\u3057\u305f\u30b9\u30ad\u30fc\u30de\u3067\u683c\u7d0d\u3002<\/span>\r\n<span class=\"c1\">\/\/   float\u306a\u3069\u30c7\u30fc\u30bf\u5f62\u5f0f\u3082\u3053\u3053\u3067\u5909\u63db<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">prodDF<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/testdata\/xxxx\/\"<\/span><span class=\"o\">).<\/span>\r\n<span class=\"nf\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nv\">x<\/span><span class=\"o\">.<\/span><span class=\"py\">split<\/span><span class=\"o\">(<\/span><span class=\"s\">\",\"<\/span><span class=\"o\">)).<\/span><span class=\"py\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">c<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nc\">Products<\/span><span class=\"o\">(<\/span><span class=\"nf\">c<\/span><span class=\"o\">(<\/span><span class=\"mi\">0<\/span><span class=\"o\">).<\/span><span class=\"py\">toInt<\/span><span class=\"o\">,<\/span><span class=\"nf\">c<\/span><span class=\"o\">(<\/span><span class=\"mi\">2<\/span><span class=\"o\">)))<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">ordDF<\/span>  <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/testdata\/xxxx\/\"<\/span><span class=\"o\">).<\/span>\r\n\r\n<span class=\"nf\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nv\">x<\/span><span class=\"o\">.<\/span><span class=\"py\">split<\/span><span class=\"o\">(<\/span><span class=\"s\">\",\"<\/span><span class=\"o\">)).<\/span><span class=\"py\">map<\/span><span class=\"o\">(<\/span><span class=\"n\">c<\/span> <span class=\"k\">=&gt;<\/span> <span class=\"nc\">Orders<\/span><span class=\"o\">(<\/span><span class=\"nf\">o<\/span><span class=\"o\">(<\/span><span class=\"mi\">0<\/span><span class=\"o\">).<\/span><span class=\"py\">toInt<\/span><span class=\"o\">,<\/span><span class=\"nf\">o<\/span><span class=\"o\">(<\/span><span class=\"mi\">4<\/span><span class=\"o\">).<\/span><span class=\"py\">toFloat<\/span><span class=\"o\">))<\/span>\r\n\r\n<span class=\"c1\">\/\/ 3.\u30c6\u30fc\u30d6\u30eb\u3092join\u3057\u3001meta store\u306b\u4e00\u6642\u30c6\u30fc\u30d6\u30eb\u3092\u4f5c\u6210\u3057\u3001spark.sql\u3067\u30d1\u30a4\u30d7\u533a\u5207\u308a\u30c7\u30fc\u30bf\u3092\u4f5c\u6210<\/span>\r\n<span class=\"nv\">ordDF<\/span><span class=\"o\">.<\/span><span class=\"py\">join<\/span><span class=\"o\">(<\/span><span class=\"n\">prodDF<\/span><span class=\"o\">,<\/span><span class=\"nf\">ordDF<\/span><span class=\"o\">(<\/span><span class=\"s\">\"prodId\"<\/span><span class=\"o\">)===<\/span><span class=\"nf\">prodDF<\/span><span class=\"o\">(<\/span><span class=\"s\">\"pId\"<\/span><span class=\"o\">)).<\/span>\r\n<span class=\"nf\">createOrReplaceTempView<\/span><span class=\"o\">(<\/span><span class=\"s\">\"joined\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">filtDF<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">sql<\/span><span class=\"o\">(<\/span><span class=\"s\">\"select concat(prodId,'|',sum(order_total)) \r\n             from joined group by prodId order by sum(order_total) desc limit 10\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"c1\">\/\/ 4.text\u30d5\u30a1\u30a4\u30eb\u5f62\u5f0f\u3067HDFS\u306b\u66f8\u304d\u8fbc\u307f<\/span>\r\n\r\n<span class=\"nv\">filtDF<\/span><span class=\"o\">.<\/span><span class=\"py\">write<\/span><span class=\"o\">.<\/span><span class=\"py\">mode<\/span><span class=\"o\">(<\/span><span class=\"s\">\"overwrite\"<\/span><span class=\"o\">).<\/span><span class=\"py\">format<\/span><span class=\"o\">(<\/span><span class=\"s\">\"text\"<\/span><span class=\"o\">).<\/span><span class=\"py\">save<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\/user\/output\"<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h2>\u6700\u7ec8<\/h2>\n<p>\u60f3\u77e5\u9053\u6709\u591a\u5c11\u65e5\u672c\u5de5\u7a0b\u5e08\u60f3\u8981\u53c2\u52a0CCA175\u8003\u8bd5\uff1f<br \/>\n\u6211\u89c9\u5f97\u5373\u4f7f\u6ca1\u6709\u65e5\u8bed\u4fe1\u606f\uff0c\u7531\u4e8e\u5b58\u5728\u5404\u79cd\u969c\u788d\uff0c\u6311\u6218\u8003\u8bd5\u7684\u4eba\u53ef\u80fd\u5f88\u5c11\u3002\u4f46\u5982\u679c\u60a8\u6709\u5174\u8da3\u4eca\u540e\u53c2\u52a0CCA175\u8003\u8bd5\u5e76\u5b66\u4e60Spark\u548cHadoop\uff0c\u6216\u8005\u60f3\u8981\u8bc1\u660e\u60a8\u7684\u5f00\u53d1\u80fd\u529b\uff0c\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6211\u60f3\u548c\u5927\u5bb6\u5206\u4eab\u4e00\u4e0b\u6211\u5982\u4f55\u901a\u8fc7\u4e86Cloudera\u7684\u300cCCA Spark\u548cHadoop\u5f00\u53d1\u8005\u8003\u8bd5\uff08CCA175\uff09\u300d [&hellip;]<\/p>\n","protected":false},"author":8,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-50638","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5 - Blog - Silicon Cloud<\/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.silicloud.com\/zh\/blog\/\u6211\u6210\u529f\u901a\u8fc7\u4e86spark\u548chadoop\u5f00\u53d1\u8005\u8ba4\u8bc1cca175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5\" \/>\n<meta property=\"og:description\" content=\"\u6211\u60f3\u548c\u5927\u5bb6\u5206\u4eab\u4e00\u4e0b\u6211\u5982\u4f55\u901a\u8fc7\u4e86Cloudera\u7684\u300cCCA Spark\u548cHadoop\u5f00\u53d1\u8005\u8003\u8bd5\uff08CCA175\uff09\u300d [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u6211\u6210\u529f\u901a\u8fc7\u4e86spark\u548chadoop\u5f00\u53d1\u8005\u8ba4\u8bc1cca175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2022-11-23T09:56:16+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-03T21:42:45+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/7-0.png\" \/>\n<meta name=\"author\" content=\"\u96c5, \u609f\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u96c5, \u609f\" \/>\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.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/\",\"name\":\"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2022-11-23T09:56:16+00:00\",\"dateModified\":\"2024-05-03T21:42:45+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6\",\"name\":\"\u96c5, \u609f\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g\",\"caption\":\"\u96c5, \u609f\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yawu\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5 - Blog - Silicon Cloud","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.silicloud.com\/zh\/blog\/\u6211\u6210\u529f\u901a\u8fc7\u4e86spark\u548chadoop\u5f00\u53d1\u8005\u8ba4\u8bc1cca175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\/","og_locale":"zh_CN","og_type":"article","og_title":"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5","og_description":"\u6211\u60f3\u548c\u5927\u5bb6\u5206\u4eab\u4e00\u4e0b\u6211\u5982\u4f55\u901a\u8fc7\u4e86Cloudera\u7684\u300cCCA Spark\u548cHadoop\u5f00\u53d1\u8005\u8003\u8bd5\uff08CCA175\uff09\u300d [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u6211\u6210\u529f\u901a\u8fc7\u4e86spark\u548chadoop\u5f00\u53d1\u8005\u8ba4\u8bc1cca175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2022-11-23T09:56:16+00:00","article_modified_time":"2024-05-03T21:42:45+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d92cb913a08637a6e424c\/7-0.png"}],"author":"\u96c5, \u609f","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u96c5, \u609f","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/","name":"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2022-11-23T09:56:16+00:00","dateModified":"2024-05-03T21:42:45+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u6211\u6210\u529f\u901a\u8fc7\u4e86Spark\u548cHadoop\u5f00\u53d1\u8005\u8ba4\u8bc1CCA175\uff0c\u73b0\u5728\u6211\u8981\u5206\u4eab\u5b66\u4e60\u7684\u65b9\u6cd5"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/f044a4b7fa4ee2701702942002419ca6","name":"\u96c5, \u609f","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/e71a913e914f1aad1efc391f92084294bac54bc782acd289638580134cf667a6?s=96&d=mm&r=g","caption":"\u96c5, \u609f"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yawu\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e6%88%91%e6%88%90%e5%8a%9f%e9%80%9a%e8%bf%87%e4%ba%86spark%e5%92%8chadoop%e5%bc%80%e5%8f%91%e8%80%85%e8%ae%a4%e8%af%81cca175%ef%bc%8c%e7%8e%b0%e5%9c%a8%e6%88%91%e8%a6%81%e5%88%86%e4%ba%ab%e5%ad%a6\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50638","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=50638"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50638\/revisions"}],"predecessor-version":[{"id":96460,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/50638\/revisions\/96460"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=50638"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=50638"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=50638"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}