hive表增量抽取到oracle数据库的通用程序(二)-CSDN博客

前一篇介绍了java程序的如何编写、使用以及引用到的依赖包。这篇接着上一篇来介绍如何在oozie中使用该java程序。

在我的业务中，分为两段：

1. 查询hive表中的信息，通过oozie可以设置不同的变量作为增量查询的条件。

2. 将hive查询到的信息写入到oracle中。

对应oozie中的workflow文件如下：

<?xml version="1.0" encoding="UTF-8"?>
<!--
  Licensed to the Apache Software Foundation (ASF) under one
  or more contributor license agreements.  See the NOTICE file
  distributed with this work for additional information
  regarding copyright ownership.  The ASF licenses this file
  to you under the Apache License, Version 2.0 (the
  "License"); you may not use this file except in compliance
  with the License.  You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License.
-->
<workflow-app xmlns="uri:oozie:workflow:0.4" name="wf_${job_name}_day">
    <start to="hive-node"/>

    <!-- 统计day: dm_guba_loginlog -->
    <action name="hive-node" retry-max="10" retry-interval="3">
        <hive xmlns="uri:oozie:hive-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <job-xml>${hive_site_path}</job-xml>
            <configuration>
                <property>
                    <name>mapred.job.queue.name</name>
                    <value>${queueName}</value>
                </property>
            </configuration>
            <script>script.q</script>
            <param>tmp_table=tmp_dm_xxx_day</param>
            <param>params_dt=${params_dt}</param>
        </hive>
        <ok to="java-node"/>
        <error to="senderror"/>
    </action>

    <!-- 注意：hive_hql,rdms_presql语句结尾不能使用分号 -->
    <action name="java-node">
    <java>
        <job-tracker>${jobTracker}</job-tracker>
        <name-node>${nameNode}</name-node>
        <configuration>
        <property>
        <name>mapred.job.queue.name</name>
        <value>${queueName}</value>
        </property>
        </configuration>
        <main-class>com.exe.Hive2RMDS</main-class>
        <arg>--hive_url</arg>
        <arg>jdbc:hive2://xx.xx.xx.xx:10000/default</arg>
        <arg>--hive_hql</arg>
        <arg>select field1,field2,field3,dim,period,period_value from dw_dm.dm_xxx where period = 'day' and period_value = ${params_dt}</arg>
        <arg>--rdms_driver</arg>
        <arg>oracle.jdbc.driver.OracleDriver</arg>
        <arg>--rdms_url</arg>
        <arg>jdbc:oracle:thin:@xx.xx.xx.xx:1521:test001</arg>
        <arg>--rdms_username</arg>
        <arg>DW_test</arg>
        <arg>--rdms_password</arg>
        <arg>DW_test</arg>
        <arg>--rdms_tableName</arg>
        <arg>DW_DM.DM_xxx_TEST</arg>
        <arg>--rdms_columnNames</arg>
        <arg>field1,field2,field3,dim,period,period_value</arg>
        <arg>--rdms_presql</arg>
        <arg>delete from DW_DM.DM_xxx_TEST where period = 'day' and period_value = '${params_dt}'</arg>    
    
    </java>
    <ok to="end"/>
    <error to="senderror"/>
    </action>
    
    <!--出错发送邮件 -->
    <action name="senderror">
        <email xmlns="uri:oozie:email-action:0.1">
          <to>xxx@qq.com</to>
          <subject>${job_name} log error in ${params_dt}</subject>
          <body>Error: ${params_dt} ,error message[${wf:errorMessage(wf:lastErrorNode())}]</body>
        </email>
        <ok to="fail"/>
        <error to="fail"/>
    </action>

    <kill name="fail">
        <message>workflow: ${wf:id()}, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name="end"/>


</workflow-app>