{"id":1335,"date":"2022-03-11T17:55:44","date_gmt":"2022-03-11T09:55:44","guid":{"rendered":"http:\/\/www.eait.co\/?p=1335"},"modified":"2022-03-11T17:57:39","modified_gmt":"2022-03-11T09:57:39","slug":"sqoop%e5%85%a5%e9%97%a8","status":"publish","type":"post","link":"https:\/\/notes.coremix.net\/?p=1335","title":{"rendered":"Sqoop\u5165\u95e8"},"content":{"rendered":"<h1>Sqoop\u539f\u7406<\/h1>\n<p>\u5c06\u5bfc\u5165\u6216\u5bfc\u51fa\u547d\u4ee4\u7ffb\u8bd1\u6210mapreduce\u7a0b\u5e8f\u6765\u5b9e\u73b0\u3002<\/p>\n<p>\u5728\u7ffb\u8bd1\u51fa\u7684mapreduce\u4e2d\u4e3b\u8981\u662f\u5bf9inputformat\u548coutputformat\u8fdb\u884c\u5b9a\u5236\u3002<\/p>\n<h1>Sqoop\u5b89\u88c5<\/h1>\n<p>\u5b89\u88c5Sqoop\u7684\u524d\u63d0\u662f\u5df2\u7ecf\u5177\u5907Java\u548cHadoop\u7684\u73af\u5883\u3002<\/p>\n<h2>3.1\u3001\u4e0b\u8f7d\u5e76\u89e3\u538b<\/h2>\n<p>1) \u6700\u65b0\u7248\u4e0b\u8f7d\u5730\u5740\uff1a<a href=\"http:\/\/mirrors.hust.edu.cn\/apache\/sqoop\/1.4.6\/\">http:\/\/mirrors.hust.edu.cn\/apache\/sqoop\/1.4.7\/<\/a><\/p>\n<p>2) \u4e0a\u4f20\u5b89\u88c5\u5305<\/p>\n<p>3) \u89e3\u538bsqoop\u5b89\u88c5\u5305\u5230\u6307\u5b9a\u76ee\u5f55\uff0c\u5982\uff1a<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"568\">$ tar -zxvf sqoop-1.4.6.bin__hadoop-2.0.4-alpha.tar.gz -C \/opt\/module\/<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>3.2\u3001\u4fee\u6539\u914d\u7f6e\u6587\u4ef6<\/h2>\n<p>Sqoop\u7684\u914d\u7f6e\u6587\u4ef6\u4e0e\u5927\u591a\u6570\u5927\u6570\u636e\u6846\u67b6\u7c7b\u4f3c\uff0c\u5728sqoop\u6839\u76ee\u5f55\u4e0b\u7684conf\u76ee\u5f55\u4e2d\u3002<\/p>\n<p><strong>1) <\/strong><strong>\u91cd\u547d\u540d\u914d\u7f6e\u6587\u4ef6<\/strong><\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"568\">$ mv sqoop-env-template.sh sqoop-env.sh<\/p>\n<p>$ mv sqoop-site-template.xml sqoop-site.xml \u6b64\u884c\u4e0d\u7528\u505a<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<p><strong>2) <\/strong><strong>\u4fee\u6539\u914d\u7f6e\u6587\u4ef6<\/strong><\/p>\n<p>sqoop-env.sh<\/p>\n<p><span style=\"color: #0000ff;\">\u4fee\u6539\u89c4\u5219\uff0c\u6b64\u5904\u6709\u7684\u4f46\u662fprofile\u4e2d\u6ca1\u6709\uff0c\u5219\u4e0d\u9700\u8981\u6539\uff0c\u5982\u679cprofile\u6709\u7684\u4f46\u662f\u6b64\u5904\u6ca1\u6709\u5c31\u9700\u8981\u6539\uff0c\u5e7a\u6635\u79f0ZOOKEEPER_HOME \u6539\u6210ZK_HOME<\/span><\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nexport HADOOP_COMMON_HOME=\/opt\/module\/hadoop-2.8.4\r\nexport HADOOP_MAPRED_HOME=\/opt\/module\/hadoop-2.8.4\r\nexport HIVE_HOME=\/opt\/module\/hive-1.2.1\r\nexport ZK_HOME=\/opt\/module\/zookeeper-3.4.10\r\nexport ZOOCFGDIR=\/opt\/module\/zookeeper-3.4.10\/conf\r\n<\/pre>\n<h2>3.3\u3001\u62f7\u8d1dJDBC\u9a71\u52a8<\/h2>\n<p>\u62f7\u8d1djdbc\u9a71\u52a8\u5230sqoop\u7684lib\u76ee\u5f55\u4e0b\uff0c\u5982\uff1a<\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"568\">$ cp -a mysql-connector-java-5.1.27-bin.jar \/opt\/module\/sqoop-1.4.6.bin__hadoop-2.0.4-alpha\/lib<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>3.4\u3001\u9a8c\u8bc1Sqoop<\/h2>\n<p>\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u67d0\u4e00\u4e2acommand (<span style=\"color: #0000ff;\">$ bin\/sqoop help<\/span>)\u6765\u9a8c\u8bc1sqoop\u914d\u7f6e\u662f\u5426\u6b63\u786e\uff1a<\/p>\n<p>\u5220\u9664\u8b66\u544a\u4fe1\u606f\u7684\u65b9\u6cd5\uff1a<\/p>\n<p>\u6ce8:\u6ce8\u91ca\u6389bin\/configure-sqoop 134\u884c\u5230143\u884c\u7684\u5185\u5bb9\uff0c\u5185\u5bb9\u5982\u4e0b<\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\n134 ## Moved to be a runtime check in sqoop.\r\n    135 #if &#x5B; ! -d &quot;${HCAT_HOME}&quot; ]; then\r\n    136 #  echo &quot;Warning: $HCAT_HOME does not exist! HCatalog jobs will fail.&quot;\r\n    137 #  echo 'Please set $HCAT_HOME to the root of your HCatalog installation.'\r\n    138 #fi\r\n    139 #\r\n    140 #if &#x5B; ! -d &quot;${ACCUMULO_HOME}&quot; ]; then\r\n    141 #  echo &quot;Warning: $ACCUMULO_HOME does not exist! Accumulo imports will fail.&quot;\r\n    142 #  echo 'Please set $ACCUMULO_HOME to the root of your Accumulo installation.'\r\n    143 #fi\r\n<\/pre>\n<p><strong>3.5<\/strong><strong>\u3001\u6d4b\u8bd5Sqoop\u662f\u5426\u80fd\u591f\u6210\u529f\u8fde\u63a5\u6570\u636e\u5e93<\/strong><\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nbin\/sqoop list-databases --connect jdbc:mysql:\/\/bigdata166:3306\/ --username root --password 000000\r\n<\/pre>\n<h2 style=\"line-height: 171%;\"><span lang=\"EN-US\" style=\"font-family: \u9ed1\u4f53;\">4.1<\/span><span style=\"font-family: \u9ed1\u4f53;\">\u3001\u5bfc\u5165\u6570\u636e<\/span><\/h2>\n<p>\u5728Sqoop\u4e2d\uff0c\u201c\u5bfc\u5165\u201d\u6982\u5ff5\u6307\uff1a\u4ece\u975e\u5927\u6570\u636e\u96c6\u7fa4\uff08RDBMS\uff09\u5411\u5927\u6570\u636e\u96c6\u7fa4\uff08HDFS\uff0cHIVE\uff0cHBASE\uff09\u4e2d\u4f20\u8f93\u6570\u636e\uff0c\u53eb\u505a\uff1a\u5bfc\u5165\uff0c\u5373\u4f7f\u7528import\u5173\u952e\u5b57\u3002<\/p>\n<h3>4.1.1\u3001RDBMS\u5230HDFS<\/h3>\n<p>1) \u786e\u5b9aMysql\u670d\u52a1\u5f00\u542f\u6b63\u5e38<\/p>\n<p>2) \u5728Mysql\u4e2d\u65b0\u5efa\u4e00\u5f20\u8868\u5e76\u63d2\u5165\u4e00\u4e9b\u6570\u636e<\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\n$ mysql -uroot -p000000\r\nmysql&gt; create database company;\r\nmysql&gt; create table company.staff(id int(4) primary key not null auto_increment, name varchar(255), sex varchar(255));\r\nmysql&gt; insert into company.staff(name, sex) values('Thomas', 'Male');\r\nmysql&gt; insert into company.staff(name, sex) values('Catalina', 'FeMale');\r\n\r\n<\/pre>\n<p><strong>\uff081\uff09\u5168\u90e8\u5bfc\u5165(mysql -&gt; HDFS)<\/strong><\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nbin\/sqoop import \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--table staff \\\r\n--target-dir \/user\/company \\\r\n--delete-target-dir \\\r\n--num-mappers 1 \\\r\n--fields-terminated-by &quot;\\t&quot;\r\n\r\n<\/pre>\n<p><strong>\u67e5\u8be2\u5bfc\u5165(mysql\u67e5\u8be2 -&gt; HDFS)<\/strong><\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1amust contain<span style=\"color: #ff0000;\"> &#8216;$CONDITIONS&#8217; in WHERE clause.<\/span>\u00a0\u00a0\u00a0\u00a0 \u6ce8\uff1aCONDITIONS \u7ffb\u8bd1\u2018\u6761\u4ef6\u2019<\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1a\u5982\u679cquery\u540e\u4f7f\u7528\u7684\u662f\u53cc\u5f15\u53f7\uff0c\u5219$CONDITIONS\u524d\u5fc5\u987b\u52a0\u8f6c\u79fb\u7b26\uff0c\u9632\u6b62shell\u8bc6\u522b\u4e3a\u81ea\u5df1\u7684\u53d8\u91cf\u3002<\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nbin\/sqoop import \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--target-dir \/user\/company \\\r\n--delete-target-dir \\\r\n--num-mappers 1 \\\r\n--fields-terminated-by &quot;\\t&quot; \\\r\n--query 'select name,sex from staff where id &amp;lt;=3 and $CONDITIONS;'\r\n\r\n<\/pre>\n<p><strong>\uff083\uff09\u5bfc\u5165\u6307\u5b9a\u5217<\/strong><\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1acolumns\u4e2d\u5982\u679c\u6d89\u53ca\u5230\u591a\u5217\uff0c<span style=\"color: #ff0000;\">\u7528\u9017\u53f7\u5206\u9694\uff0c\u5206\u9694\u65f6\u4e0d\u8981\u6dfb\u52a0\u7a7a\u683c<\/span><\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nbin\/sqoop import \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--target-dir \/user\/company \\\r\n--delete-target-dir \\\r\n--num-mappers 1 \\\r\n--fields-terminated-by &quot;\\t&quot; \\\r\n--columns id,sex \\\r\n--table staff\r\n<\/pre>\n<p><strong>\u4f7f\u7528sqoop\u5173\u952e\u5b57\u7b5b\u9009\u67e5\u8be2\u5bfc\u5165\u6570\u636e<\/strong><\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1a\u5728Sqoop\u4e2d\u53ef\u4ee5\u4f7f\u7528sqoop import -D property.name=property.value\u8fd9\u6837\u7684\u65b9\u5f0f\u52a0\u5165\u6267\u884c\u4efb\u52a1\u7684\u53c2\u6570\uff0c\u591a\u4e2a\u53c2\u6570\u7528\u7a7a\u683c\u9694\u5f00\u3002<\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\n bin\/sqoop import \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--target-dir \/user\/company \\\r\n--delete-target-dir \\\r\n--num-mappers 1 \\\r\n--fields-terminated-by &quot;\\t&quot; \\\r\n--table staff \\\r\n--where &quot;id=2&quot;\r\n<\/pre>\n<h3>RDBMS\u5230Hive<\/h3>\n<p>\u5c16\u53eb\u63d0\u793a\uff1a\u8be5\u8fc7\u7a0b\u5206\u4e3a\u4e24\u6b65\uff0c\u7b2c\u4e00\u6b65\u5c06\u6570\u636e\u5bfc\u5165\u5230HDFS\uff0c\u7b2c\u4e8c\u6b65\u5c06\u5bfc\u5165\u5230HDFS\u7684\u6570\u636e\u8fc1\u79fb\u5230Hive\u4ed3\u5e93<\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1a\u4eceMYSQL\u5230Hive\uff0c\u672c\u8d28\u65f6\u4eceMYSQL =&gt; HDFS =&gt; load To Hive<\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\nbin\/sqoop import \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--table staff \\\r\n--num-mappers 1 \\\r\n--hive-import \\\r\n--fields-terminated-by &quot;\\t&quot; \\\r\n--hive-overwrite \\\r\n--hive-table staff_hive\r\n<\/pre>\n<h2 style=\"line-height: 171%;\"><span lang=\"EN-US\" style=\"font-family: \u9ed1\u4f53;\">4.2<\/span><span style=\"font-family: \u9ed1\u4f53;\">\u3001\u5bfc\u51fa\u6570\u636e<\/span><\/h2>\n<p>\u5728Sqoop\u4e2d\uff0c\u201c\u5bfc\u51fa\u201d\u6982\u5ff5\u6307\uff1a<span style=\"color: #ff0000;\">\u4ece\u5927\u6570\u636e\u96c6\u7fa4\uff08HDFS\uff0cHIVE\uff0cHBASE\uff09\u5411\u975e\u5927\u6570\u636e\u96c6\u7fa4\uff08RDBMS\uff09\u4e2d\u4f20\u8f93\u6570\u636e\uff0c\u53eb\u505a\uff1a\u5bfc\u51fa<\/span>\uff0c\u5373\u4f7f\u7528export\u5173\u952e\u5b57\u3002<\/p>\n<p>\u5c16\u53eb\u63d0\u793a\uff1aMysql\u4e2d\u5982\u679c\u8868\u4e0d\u5b58\u5728\uff0c\u4e0d\u4f1a\u81ea\u52a8\u521b\u5efa,\u81ea\u884c\u6839\u636e\u8868\u7ed3\u6784\u521b\u5efa<\/p>\n<p>\u6ce8\u610f\uff1a\u6570\u636e\u53ef\u8ffd\u52a0\u5199\u5165<\/p>\n<h3>4.2.1\u3001HIVE\/HDFS\u5230RDBMS<\/h3>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\n\u521b\u5efaaca\u8868   \u6b64\u5904\u5e94\u6dfb\u52a0sex\u5217\r\ncreate table abc(id int,name VARCHAR(5));\r\n\r\nHive\/HDFS ----&gt; RDBMS  (\u7ecf\u5e38\u51fa\u73b0job\u5361\u6b7b\uff0c\u5f85\u4fee\u6b63)\r\nbin\/sqoop export \\\r\n--connect jdbc:mysql:\/\/bigdata166:3306\/company \\\r\n--username root \\\r\n--password 000000 \\\r\n--export-dir \/user\/hive\/warehouse\/staff_hive \\\r\n--table abc \\\r\n--num-mappers 1 \\\r\n--input-fields-terminated-by &quot;\\t&quot;\r\n<\/pre>\n<h2>4.3\u3001\u811a\u672c\u6253\u5305<\/h2>\n<p>\u4f7f\u7528opt\u683c\u5f0f\u7684\u6587\u4ef6\u6253\u5305sqoop\u547d\u4ee4\uff0c\u7136\u540e\u6267\u884c<\/p>\n<p><strong>1) <\/strong><strong>\u521b\u5efa\u4e00\u4e2a<\/strong><strong>.opt<\/strong><strong>\u6587\u4ef6<\/strong><\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"568\">$ touch job_HDFS2RDBMS.opt<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<p><strong>2) <\/strong><strong>\u7f16\u5199<\/strong><strong>sqoop<\/strong><strong>\u811a\u672c<\/strong><\/p>\n<pre class=\"brush: bash; title: ; notranslate\" title=\"\">\r\n\r\nexport\r\n--connect\r\njdbc:mysql:\/\/bigdata166:3306\/company\r\n--username\r\nroot\r\n--password\r\n000000\r\n--table\r\nabc\r\n--num-mappers\r\n1\r\n--export-dir\r\n\/user\/hive\/warehouse\/staff_hive\r\n--input-fields-terminated-by\r\n&quot;\\t&quot;\r\n<\/pre>\n<p><strong>3) <\/strong><strong>\u6267\u884c\u8be5\u811a\u672c<\/strong><\/p>\n<table>\n<tbody>\n<tr>\n<td width=\"568\">$ bin\/sqoop &#8211;options-file job_HDFS2RDBMS.opt<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"<p>Sqoop\u539f\u7406 \u5c06\u5bfc\u5165\u6216\u5bfc\u51fa\u547d\u4ee4\u7ffb\u8bd1\u6210mapreduce\u7a0b\u5e8f\u6765\u5b9e\u73b0\u3002 \u5728\u7ffb\u8bd1\u51fa\u7684mapreduce\u4e2d\u4e3b\u8981\u662f\u5bf9i [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-1335","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"blocksy_meta":[],"_links":{"self":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1335","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1335"}],"version-history":[{"count":4,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1335\/revisions"}],"predecessor-version":[{"id":1339,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=\/wp\/v2\/posts\/1335\/revisions\/1339"}],"wp:attachment":[{"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/notes.coremix.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}