HIVE学习总结
Hive只需要装载一台机器上，可以通过webui，console，thrift接口访问（jdbc，odbc），仅适合离线数据分析，降低数据分析成本（不用编写mapreduce）。
Hive优势
1. 简单易上手，类sql的hql、
2. 有大数据集的计算和扩展能力，mr作为计算引擎，hdfs作为存储系统
3. 统一的元数据管理（可与pig。presto）等共享
Hive缺点
1. Hive表达能力有限。迭代和复杂运算不易表达
2. Hive效率较低，mr作业不够智能，hql调优困难，可控性差
Hive访问
1. 提供jdbc、odbc访问方式。
2. 采用开源软件thrift实现C/S模型，支持任何语言。
3. WebUI的方式
4. 控制台方式
Hive WEBUI使用
在HIVE_HOME/conf目录hive-site.xml文件中添加如下文件
修改配置文件：hive-site.xml增加如下三个参数项：
<property>
<name>hive.hwi.listen.host</name>
<value>0.0.0.0</value>
</property>
<property>
<name>hive.hwi.listen.port</name>
<value>9999</value>
</property>
<property>
<name>hive.hwi.war.file</name>
<value>lib/hive-hwi-0.13.1.war</value>
</property>
其中lib/hive-hwi-0.13.1.war为hive页面对应的war包，0.13.1版本没有对应的war包需要自己打包，步骤如下：
wgethttp://apache.fayea.com/apache-mirror/hive/hive-0.13.1/apache-hive-0.13.1-src.tar.gz
tar-zxvf apache-hive-0.13.1-src.tar.gz
cdapache-hive-0.13.1-src
cdhwi/web
ziphive-hwi-0.13.1.zip ./* //打包成.zip文件。
scphive-hwi-0.13.1.war db96:/usr/local/hive/lib/ //放到hive的安装目录的lib目录下。
启动hwi:
hive --service hwi
如有下报错：
Problem accessing /hwi/. Reason:
Unable to find a javac compiler;
com.sun.tools.javac.Main is not on theclasspath.
Perhaps JAVA_HOME does not point to the JDK.
Itis currently set to "/usr/java/jdk1.7.0_55/jre"
解决办法：
cp/usr/java/jdk1.7.0_55/lib/tools.jar /usr/local/hive/lib/
hive --service hwi
重启即可。
典型部署：采用主备结构mysql存储元数据信息。
Java通过jdbc调用hive
使用jdbc连接hive必须启动hiveserver，默认端口为10000,也可以指定。
bin/hive --service hiveserver -p 10002
显示Starting Hive Thrift Server说明启动成功。
创建eclipse创建java工程，导入hive/lib下的所有jar,及hadoop的一下三个jar
hadoop-2.5.0/share/hadoop/common/hadoop-common-2.5.0.jar
hadoop-2.5.0/share/hadoop/common/lib/slf4j-api-1.7.5.jar
hadoop-2.5.0/share/hadoop/common/lib/slf4j-log4j12-1.7.5.jar
理论上只用导入hive下面的jar，
$HIVE_HOME/lib/hive-exec-0.13.1.jar
$HIVE_HOME/lib/hive-jdbc-0.13.1.jar
$HIVE_HOME/lib/hive-metastore-0.13.1.jar
$HIVE_HOME/lib/hive-service-0.13.1.jar
$HIVE_HOME/lib/libfb303-0.9.0.jar
$HIVE_HOME/lib/commons-logging-1.1.3.jar
测试数据/home/hadoop01/data
内容如下（中间用tab键隔开）：
1 abd
2 2sdf
3 Fdd
Java代码如下：
package org.apache.hadoop.hive;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import org.apache.log4j.Logger;
public class HiveJdbcCli {
private static String driverName ="org.apache.hadoop.hive.jdbc.HiveDriver";
private static String url ="jdbc:hive://hadoop3:10000/default";
private static String user ="";
private static String password ="";
private static String sql = "";
private static ResultSet res;
private static final Logger log =Logger.getLogger(HiveJdbcCli.class);
public static void main(String[] args){
Connection conn = null;
Statement stmt = null;
try {
conn = getConn();
stmt =conn.createStatement();
//
第一步:存在就先删除
String tableName =dropTable(stmt);
//
第二步:不存在就创建
createTable(stmt, tableName);
//
第三步:查看创建的表
showTables(stmt, tableName);
//
执行describe table操作
describeTables(stmt,tableName);
//
执行load data intotable操作
loadData(stmt, tableName);
//
执行 select * query 操作
selectData(stmt, tableName);
//
执行 regular hive query统计操作
countData(stmt, tableName);
} catch (ClassNotFoundException e){
e.printStackTrace();
log.error(driverName + " notfound!", e);
System.exit(1);
} catch (SQLException e) {
e.printStackTrace();
log.error("Connectionerror!", e);
System.exit(1);
} finally {
try {
if (conn != null) {
conn.close();
conn = null;
}
if (stmt != null) {
stmt.close();
stmt = null;
}
} catch (SQLException e) {
e.printStackTrace();
}
}
}
private static void countData(Statementstmt, String tableName)
throws SQLException {
sql = "select count(1) from" + tableName;
System.out.println("Running:" + sql);
res = stmt.executeQuery(sql);
System.out.println("执行“regularhive query”运行结果:");
while (res.next()) {
System.out.println("count------>" + res.getString(1));
}
}
private static void selectData(Statementstmt, String tableName)
throws SQLException {
sql = "select * from " +tableName;
System.out.println("Running:" + sql);
res = stmt.executeQuery(sql);
System.out.println("执行 select *query运行结果:");
while (res.next()) {
System.out.println(res.getInt(1) +"\t" + res.getString(2));
}
}
private static void loadData(Statementstmt, String tableName)
throws SQLException {
String filepath ="/home/hadoop01/data";
sql = "load data local inpath‘" + filepath + "‘ into table "
+ tableName;
System.out.println("Running:" + sql);
res = stmt.executeQuery(sql);
}
private static voiddescribeTables(Statement stmt, String tableName)
throws SQLException {
sql = "describe " +tableName;
System.out.println("Running:"+ sql);
res = stmt.executeQuery(sql);
System.out.println("执行 describetable运行结果:");
while (res.next()) {
System.out.println(res.getString(1) + "\t" +res.getString(2));
}
}
private static void showTables(Statementstmt, String tableName)
throws SQLException {
sql = "show tables ‘" +tableName + "‘";
System.out.println("Running:" + sql);
res = stmt.executeQuery(sql);
System.out.println("执行 showtables运行结果:");
if (res.next()) {
System.out.println(res.getString(1));
}
}
private static void createTable(Statementstmt, String tableName)
throws SQLException {
sql = "create table "
+ tableName
+ " (key int, valuestring) row format delimited fieldsterminated by ‘\t‘";
stmt.executeQuery(sql);
}
private static String dropTable(Statementstmt) throws SQLException {
//
创建的表名
String tableName ="testHive";
sql = "drop table " +tableName;
stmt.executeQuery(sql);
return tableName;
}
private static Connection getConn() throwsClassNotFoundException,
SQLException {
Class.forName(driverName);
Connection conn =DriverManager.getConnection(url, user, password);
return conn;
}
}