{"id":61547,"date":"2024-10-13T11:54:13","date_gmt":"2024-10-13T03:54:13","guid":{"rendered":"https:\/\/server.hk\/cnblog\/61547\/"},"modified":"2024-10-13T11:54:13","modified_gmt":"2024-10-13T03:54:13","slug":"hdfs-api%e5%a6%82%e4%bd%95%e8%ae%80%e5%8f%96%e6%95%b8%e6%93%9a%e5%ba%ab%ef%bc%9f-hdfs-api-%e8%ae%80%e5%8f%96%e6%95%b8%e6%93%9a%e5%ba%ab","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/61547\/","title":{"rendered":"HDFS API\u5982\u4f55\u8b80\u53d6\u6578\u64da\u5eab\uff1f (hdfs api \u8b80\u53d6\u6578\u64da\u5eab)"},"content":{"rendered":"<h1 id=\"hdfs-api%e5%a6%82%e4%bd%95%e8%ae%80%e5%8f%96%e6%95%b8%e6%93%9a%e5%ba%ab%ef%bc%9f-kyCYiNdLzB\">HDFS API\u5982\u4f55\u8b80\u53d6\u6578\u64da\u5eab\uff1f<\/h1>\n<p>\u5728\u5927\u6578\u64da\u8655\u7406\u7684\u9818\u57df\u4e2d\uff0cHadoop\u5206\u4f48\u5f0f\u6587\u4ef6\u7cfb\u7d71\uff08HDFS\uff09\u662f\u4e00\u500b\u91cd\u8981\u7684\u7d44\u4ef6\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u500b\u53ef\u9760\u7684\u5b58\u5132\u89e3\u6c7a\u65b9\u6848\uff0c\u80fd\u5920\u8655\u7406\u5927\u91cf\u7684\u6578\u64da\u3002\u96a8\u8457\u6578\u64da\u91cf\u7684\u589e\u9577\uff0c\u8a31\u591a\u4f01\u696d\u958b\u59cb\u5c0b\u6c42\u5c07\u6578\u64da\u5eab\u4e2d\u7684\u6578\u64da\u8207HDFS\u9032\u884c\u6574\u5408\uff0c\u4ee5\u4fbf\u9032\u884c\u66f4\u9ad8\u6548\u7684\u6578\u64da\u5206\u6790\u548c\u8655\u7406\u3002\u672c\u6587\u5c07\u63a2\u8a0e\u5982\u4f55\u4f7f\u7528HDFS API\u4f86\u8b80\u53d6\u6578\u64da\u5eab\u4e2d\u7684\u6578\u64da\u3002<\/p>\n<h2 id=\"hdfs%e7%b0%a1%e4%bb%8b-kyCYiNdLzB\">HDFS\u7c21\u4ecb<\/h2>\n<p>HDFS\u662f\u4e00\u500b\u5206\u4f48\u5f0f\u6587\u4ef6\u7cfb\u7d71\uff0c\u5c08\u70ba\u5927\u6578\u64da\u61c9\u7528\u800c\u8a2d\u8a08\u3002\u5b83\u80fd\u5920\u5728\u591a\u53f0\u4f3a\u670d\u5668\u4e0a\u5b58\u5132\u6578\u64da\uff0c\u4e26\u63d0\u4f9b\u9ad8\u5bb9\u932f\u6027\u548c\u9ad8\u541e\u5410\u91cf\u3002HDFS\u7684\u67b6\u69cb\u7531\u5169\u500b\u4e3b\u8981\u7d44\u4ef6\u7d44\u6210\uff1aNameNode\u548cDataNode\u3002NameNode\u8ca0\u8cac\u7ba1\u7406\u6587\u4ef6\u7cfb\u7d71\u7684\u5143\u6578\u64da\uff0c\u800cDataNode\u5247\u8ca0\u8cac\u5be6\u969b\u7684\u6578\u64da\u5b58\u5132\u3002<\/p>\n<h2 id=\"%e6%95%b8%e6%93%9a%e5%ba%ab%e8%88%87hdfs%e7%9a%84%e6%95%b4%e5%90%88-kyCYiNdLzB\">\u6578\u64da\u5eab\u8207HDFS\u7684\u6574\u5408<\/h2>\n<p>\u5728\u8a31\u591a\u60c5\u6cc1\u4e0b\uff0c\u4f01\u696d\u9700\u8981\u5c07\u95dc\u4fc2\u578b\u6578\u64da\u5eab\uff08\u5982MySQL\u3001PostgreSQL\uff09\u4e2d\u7684\u6578\u64da\u5c0e\u5165HDFS\uff0c\u4ee5\u4fbf\u9032\u884c\u5927\u6578\u64da\u5206\u6790\u3002\u9019\u53ef\u4ee5\u901a\u904e\u591a\u7a2e\u65b9\u5f0f\u5be6\u73fe\uff0c\u5305\u62ec\u4f7f\u7528Apache Sqoop\u3001Apache Flume\u6216\u76f4\u63a5\u4f7f\u7528HDFS API\u3002<\/p>\n<h3 id=\"%e4%bd%bf%e7%94%a8apache-sqoop-kyCYiNdLzB\">\u4f7f\u7528Apache Sqoop<\/h3>\n<p>Apache Sqoop\u662f\u4e00\u500b\u5c08\u9580\u7528\u65bc\u5728Hadoop\u548c\u95dc\u4fc2\u578b\u6578\u64da\u5eab\u4e4b\u9593\u9032\u884c\u6578\u64da\u50b3\u8f38\u7684\u5de5\u5177\u3002\u5b83\u80fd\u5920\u8f15\u9b06\u5730\u5c07\u6578\u64da\u5f9e\u6578\u64da\u5eab\u5c0e\u5165HDFS\u3002\u4ee5\u4e0b\u662f\u4e00\u500b\u7c21\u55ae\u7684Sqoop\u547d\u4ee4\u793a\u4f8b\uff1a<\/p>\n<pre><code>sqoop import --connect jdbc:mysql:\/\/localhost:3306\/mydatabase \n--username myuser --password mypassword \n--table mytable --target-dir \/user\/hdfs\/mytable \n--incremental append --check-column id --last-value 1000<\/code><\/pre>\n<p>\u9019\u500b\u547d\u4ee4\u5c07\u5f9eMySQL\u6578\u64da\u5eab\u4e2d\u7684\u201cmytable\u201d\u8868\u5c0e\u5165\u6578\u64da\u5230HDFS\u7684\u6307\u5b9a\u76ee\u9304\u4e2d\u3002<\/p>\n<h3 id=\"%e4%bd%bf%e7%94%a8hdfs-api%e7%9b%b4%e6%8e%a5%e8%ae%80%e5%8f%96%e6%95%b8%e6%93%9a-kyCYiNdLzB\">\u4f7f\u7528HDFS API\u76f4\u63a5\u8b80\u53d6\u6578\u64da<\/h3>\n<p>\u5982\u679c\u9700\u8981\u66f4\u9748\u6d3b\u7684\u6578\u64da\u8b80\u53d6\u65b9\u5f0f\uff0c\u53ef\u4ee5\u8003\u616e\u4f7f\u7528HDFS API\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528Java\u8a9e\u8a00\u901a\u904eHDFS API\u8b80\u53d6\u6578\u64da\u7684\u57fa\u672c\u6b65\u9a5f\uff1a<\/p>\n<ol>\n<li>\u8a2d\u7f6eHadoop\u914d\u7f6e\u3002<\/li>\n<li>\u5275\u5efaHDFS\u6587\u4ef6\u7cfb\u7d71\u5c0d\u8c61\u3002<\/li>\n<li>\u8b80\u53d6\u6307\u5b9a\u8def\u5f91\u7684\u6587\u4ef6\u3002<\/li>\n<\/ol>\n<p>\u4ee5\u4e0b\u662f\u4e00\u6bb5\u793a\u4f8b\u4ee3\u78bc\uff1a<\/p>\n<pre><code>import org.apache.hadoop.conf.Configuration;\nimport org.apache.hadoop.fs.FileSystem;\nimport org.apache.hadoop.fs.Path;\nimport java.io.BufferedReader;\nimport java.io.InputStreamReader;\n\npublic class HDFSReadExample {\n    public static void main(String[] args) throws Exception {\n        Configuration conf = new Configuration();\n        FileSystem fs = FileSystem.get(conf);\n        Path path = new Path(\"\/user\/hdfs\/mytable\/data.txt\");\n        \n        BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(path)));\n        String line;\n        while ((line = br.readLine()) != null) {\n            System.out.println(line);\n        }\n        br.close();\n    }\n}<\/code><\/pre>\n<p>\u9019\u6bb5\u4ee3\u78bc\u5c55\u793a\u4e86\u5982\u4f55\u901a\u904eHDFS API\u8b80\u53d6\u5b58\u5132\u5728HDFS\u4e2d\u7684\u6587\u672c\u6587\u4ef6\u3002<\/p>\n<h2 id=\"%e7%b8%bd%e7%b5%90-kyCYiNdLzB\">\u7e3d\u7d50<\/h2>\n<p>HDFS API\u63d0\u4f9b\u4e86\u4e00\u7a2e\u9748\u6d3b\u7684\u65b9\u5f0f\u4f86\u8b80\u53d6\u6578\u64da\u5eab\u4e2d\u7684\u6578\u64da\uff0c\u7121\u8ad6\u662f\u901a\u904eApache Sqoop\u9032\u884c\u6279\u91cf\u5c0e\u5165\uff0c\u9084\u662f\u76f4\u63a5\u4f7f\u7528HDFS API\u9032\u884c\u6587\u4ef6\u8b80\u53d6\uff0c\u5747\u80fd\u6709\u6548\u5730\u652f\u6301\u5927\u6578\u64da\u5206\u6790\u9700\u6c42\u3002\u96a8\u8457\u6578\u64da\u91cf\u7684\u6301\u7e8c\u589e\u9577\uff0c\u638c\u63e1\u9019\u4e9b\u6280\u8853\u5c07\u5c0d\u4f01\u696d\u7684\u6578\u64da\u8655\u7406\u80fd\u529b\u7522\u751f\u6df1\u9060\u5f71\u97ff\u3002<\/p>\n<p>\u5982\u679c\u60a8\u5c0d\u65bc\u5982\u4f55\u5728\u9999\u6e2f\u4f7f\u7528 <a href=\"https:\/\/server.hk\">VPS<\/a> \u9032\u884c\u5927\u6578\u64da\u8655\u7406\u6709\u8208\u8da3\uff0c\u6216\u60f3\u4e86\u89e3\u66f4\u591a\u95dc\u65bc <a href=\"https:\/\/server.hk\">\u9999\u6e2f\u4f3a\u670d\u5668<\/a> \u7684\u8cc7\u8a0a\uff0c\u6b61\u8fce\u8a2a\u554f\u6211\u5011\u7684\u7db2\u7ad9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4e86\u89e3\u5982\u4f55\u4f7f\u7528HDFS API\u6709\u6548\u8b80\u53d6\u6578\u64da\u5eab\uff0c\u5be6\u73fe\u6578\u64da\u5b58\u53d6\u8207\u7ba1\u7406\u7684\u6700\u4f73\u5be6\u8e10\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-61547","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61547","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"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=61547"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61547\/revisions"}],"predecessor-version":[{"id":61548,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/61547\/revisions\/61548"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=61547"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=61547"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=61547"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}