第一篇：
安装hadoop 和 hive我就不多说了，网上太多文章 自己看去
首先，在机器上打开hiveservice
1. hive --service hiveserver -p 50000 &
打开50000端口，然后java就可以使用java连了，需要的jar包我发个图片
就这多jar包，必须的
不多说，直接上代码
1. package
2.
3. import
4. import
5. import
6. import
7.
8. /**
9. * User: liuxiaochen
10. * Date: 13-9-24
11. * Time: 下午5:47
12. * 修改描述
13. */
14. public class
15. private static final String URLHIVE = "jdbc:hive://ip:50000/default";
16. private static Connection connection = null;
17.
18. public static
19. if (null
20. synchronized (HiveService.class) {
21. if (null
22. try
23. "org.apache.hadoop.hive.jdbc.HiveDriver");
24. "", "");
25. catch
26. e.printStackTrace();
27. catch
28. e.printStackTrace();
29. }
30. }
31. }
32. }
33. return
34. }
35.
36. public static void createTable() throws
37. "DROP TABLE IF EXISTS hive_crm_tweet2222";
38. "CREATE EXTERNAL TABLE hive_crm_tweet2222(tweet_id string, cuser_id string, created_at bigint, year bigint, month bigint, day bigint, hour bigint, text string, comments_count bigint, reposts_count bigint, source string, retweeted_id string, post_type string, sentiment string, positive_tags_string string, predict_tags_string string, tags_string string) STORED BY 'org.apache.hadoop.hive.dynamodb.DynamoDBStorageHandler' TBLPROPERTIES (\"dynamodb.table.name\" = \"crm_tweet\",\"dynamodb.column.mapping\" = \"tweet_id:tweet_id,cuser_id:cuser_id,created_at:created_at,year:year,month:month,day:day,hour:hour,text:text,comments_count:comments_count,reposts_count:reposts_count,source:source,retweeted_id:retweeted_id,post_type:post_type,sentiment:sentiment,positive_tags_string:positive_tags_string,predict_tags_string:predict_tags_string,tags_string:tags_string\")";
39. "DROP TABLE IF EXISTS hive_tweet_comment2222";
40. "CREATE EXTERNAL TABLE hive_tweet_comment2222(tweet_id string,comment_id string, cuser_id string, user_id string, created_at bigint, year bigint, month bigint, day bigint, hour bigint, text string, comments_count bigint, reposts_count bigint, source string, topic_id string, post_type string, sentiment string) STORED BY 'org.apache.hadoop.hive.dynamodb.DynamoDBStorageHandler' TBLPROPERTIES (\"dynamodb.table.name\" = \"crm_tweet_comment\",\"dynamodb.column.mapping\" = \"tweet_id:tweet_id,comment_id:comment_id,cuser_id:cuser_id,user_id:user_id,created_at:created_at,year:year,month:month,day:day,hour:hour,text:text,comments_count:comments_count,reposts_count:reposts_count,source:source,topic_id:tweet_id,post_type:post_type,sentiment:sentiment\")";
41. "DROP TABLE IF EXISTS hive_tweet_retweet2222";
42. "CREATE EXTERNAL TABLE hive_tweet_retweet2222(tweet_id string, cuser_id string, user_id string, retweet_id string, created_at BIGINT, year BIGINT, month BIGINT, day BIGINT, hour BIGINT, text string, comments_count BIGINT, reposts_count BIGINT, source string, topic_id string, verified_type BIGINT, post_type string, sentiment string) STORED BY 'org.apache.hadoop.hive.dynamodb.DynamoDBStorageHandler' TBLPROPERTIES (\"dynamodb.table.name\" = \"crm_tweet_retweet\",\"dynamodb.column.mapping\" = \"tweet_id:tweet_id,cuser_id:cuser_id,user_id:user_id,retweet_id:retweet_id,created_at:created_at,year:year,month:month,day:day,hour:hour,text:text,comments_count:comments_count,reposts_count:reposts_count,source:source,topic_id:tweet_id,verified_type:verified_type,post_type:post_type,sentiment:sentiment\")";
43.
44. Statement stmt = getHiveConnection().createStatement();
45. stmt.executeQuery(tweetTableSql);
46. stmt.executeQuery(createTable1);
47. stmt.executeQuery(commentTableSql);
48. stmt.executeQuery(createTable2);
49. stmt.executeQuery(retweetTableSql);
50. stmt.executeQuery(createTable3);
51. }
52.
53. public static void selectTweet() throws
54. long
55. long start = DateUtils.getNDaysAgo(DateUtils.getMidNight(), 15).getTime().getTime();
56. long end = DateUtils.getNDaysAgo(DateUtils.getMidNight(), 13).getTime().getTime();
57. "select cuser_id, count(*) as tw_hour, year, month, day from hive_crm_tweet2222 where created_at > ? and created_at < ? and cuser_id = ? group by cuser_id, year, month, day, hour";
58. PreparedStatement pstm = getHiveConnection().prepareStatement(sql);
59. 1, start);
60. 2, end);
61. 3, "2176270443");
62. ResultSet rss = pstm.executeQuery();
63. while
64. "1: " + rss.getString("cuser_id") + " 2: " + rss.getInt("tw_hour") + " 3: " + rss.getInt("year") + " 4: " + rss.getInt("month") + " 5: " + rss.getInt("day"));
65. }
66.
67. System.out.println(System.currentTimeMillis() - aaa);
68.
69. }
70.
71. public static void selectTweet22() throws
72. long
73. long start = DateUtils.getNDaysAgo(DateUtils.getMidNight(), 15).getTime().getTime();
74. long end = DateUtils.getNDaysAgo(DateUtils.getMidNight(), 13).getTime().getTime();
75. "select cuser_id, created_at, tweet_id from hive_crm_tweet2222 where created_at > ? and created_at < ? and cuser_id = ?";
76. PreparedStatement pstm = getHiveConnection().prepareStatement(sql);
77. 1, start);
78. 2, end);
79. 3, "2176270443");
80. ResultSet rss = pstm.executeQuery();
81. new SimpleDateFormat("yyyy-MM-dd HH");
82. while
83. long cc = Long.valueOf(String.valueOf(rss.getInt("created_at")) + "000");
84. new
85. System.out.println(dateFormat.format(date));
86. "cuser_id") + " " + rss.getString("tweet_id"));
87. }
88.
89. System.out.println(System.currentTimeMillis() - aaa);
90.
91. }
92.
93. public static void main(String[] args) throws
94. // Class.forName("org.apache.hadoop.hive.jdbc.HiveDriver");
95. // String querySQL = "SELECT a.* FROM test_time a";
96. //
97. // Connection con = DriverManager.getConnection(URLHIVE, "", "");
98. // Statement stmt = con.createStatement();
99. // ResultSet res = stmt.executeQuery(querySQL); // 执行查询语句
100. //
101. // while (res.next()) {
102. // System.out.println("Result: key:" + res.getString(1) + " –> value:" + res.getString(2));
103. // }
104. selectTweet22();
105.
106. // SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd HH");
107. // System.out.println(dateFormat.format(new java.util.Date()));
108. }
109. }第二篇：
我们可以通过CLI、Client、Web UI等Hive提供的用户接口来和Hive通信，但这三种方式最常用的是CLI；Client 是Hive的客户端，用户连接至 Hive Server。在启动 Client 模式的时候，需要指出Hive Server所在节点，并且在该节点启动 Hive Server。 WUI 是通过浏览器访问 Hive。今天我们来谈谈怎么通过HiveServer来操作Hive。
Java代码来连接Hive并进行一些类关系型数据库的sql语句查询等操作。同关系型数据库一样，我们也需要将Hive的服务打开；在Hive 0.11.0版本之前，只有HiveServer服务可用，你得在程序操作Hive之前，必须在Hive安装的服务器上打开HiveServer服务，如下：
[wyp @localhost /home/q/hive- 0.11 . 0 ]$ bin/hive --service hiveserver -p 10002
Starting Hive Thrift Server
Java代码来连接hiveserver，代码如下：
package com.wyp;
/**
* User: 过往记忆
* Date: 13-11-27
* Time: 下午5:52
*/
import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;
public class HiveJdbcTest {
private static String driverName =
"org.apache.hadoop.hive.jdbc.HiveDriver" ;
public static void main(String[] args)
throws SQLException {
try {
Class.forName(driverName);
} catch (ClassNotFoundException e) {
e.printStackTrace();
System.exit( 1 );
}
Connection con = DriverManager.getConnection(
"jdbc:hive://localhost:10002/default" , "wyp" , "" );
Statement stmt = con.createStatement();
String tableName = "wyphao" ;
stmt.execute( "drop table if exists " + tableName);
stmt.execute( "create table " + tableName +
" (key int, value string)" );
System.out.println( "Create table success!" );
// show tables
String sql = "show tables '" + tableName + "'" ;
System.out.println( "Running: " + sql);
ResultSet res = stmt.executeQuery(sql);
if (res.next()) {
System.out.println(res.getString( 1 ));
}
// describe table
sql = "describe " + tableName;
System.out.println( "Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString( 1 ) + "\t" + res.getString( 2 ));
}
sql = "select * from " + tableName;
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(String.valueOf(res.getInt( 1 )) + "\t"
+ res.getString( 2 ));
}
sql = "select count(1) from " + tableName;
System.out.println( "Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString( 1 ));
}
}
}
编译上面的代码，之后就可以运行(我是在集成开发环境下面运行这个程序的)，结果如下：
Create table success!
Running: show tables 'wyphao'
wyphao
Running: describe wyphao
key int
value string
Running: select count( 1 ) from wyphao
0
Process finished with exit code 0
#!/bin/bash
HADOOP_HOME=/home/q/hadoop- 2.2 . 0
HIVE_HOME=/home/q/hive- 0.11 . 0 -bin
CLASSPATH=$CLASSPATH:
for i in /home/wyp/lib/*.jar ; do
CLASSPATH=$CLASSPATH:$i
done
echo $CLASSPATH
/home/q/java/jdk1. 6 .0_20/bin/java -cp \
$CLASSPATH:/export1/tmp/yangping.wu/OutputText.jar com.wyp.HiveJdbcTest
上面是用Java连接HiveServer，而HiveServer本身存在很多问题（比如：安全性、并发性等）；针对这些问题，Hive0.11.0版本提供了一个全新的服务：HiveServer2，这个很好的解决HiveServer存在的安全性、并发性等问题。这个服务启动程序在${HIVE_HOME}/bin/hiveserver2里面，你可以通过下面的方式来启动HiveServer2服务：
$HIVE_HOME/bin/hiveserver2
也可以通过下面的方式启动HiveServer2
$HIVE_HOME/bin/hive --service hiveserver2
两种方式效果都一样的。但是以前的程序需要修改两个地方，如下所示：
private static String driverName = "org.apache.hadoop.hive.jdbc.HiveDriver" ;
改为
private static String driverName = "org.apache.hive.jdbc.HiveDriver" ;
Connection con = DriverManager.getConnection(
"jdbc:hive://localhost:10002/default" , "wyp" , "" );
改为
Connection con = DriverManager.getConnection(
"jdbc:hive2://localhost:10002/default" , "wyp" , "" );
其他的不变就可以了。
这里顺便说说本程序所依赖的jar包，一共有以下几个：
hadoop- 2.2 . 0 /share/hadoop/common/hadoop-common- 2.2 . 0 .jar
$HIVE_HOME/lib/hive-exec- 0.11 . 0 .jar
$HIVE_HOME/lib/hive-jdbc- 0.11 . 0 .jar
$HIVE_HOME/lib/hive-metastore- 0.11 . 0 .jar
$HIVE_HOME/lib/hive-service- 0.11 . 0 .jar
$HIVE_HOME/lib/libfb303- 0.9 . 0 .jar
$HIVE_HOME/lib/commons-logging- 1.0 . 4 .jar
$HIVE_HOME/lib/slf4j-api- 1.6 . 1 .jar
如果你是用Maven，加入以下依赖
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-jdbc</artifactId>
<version> 0.11 . 0 </version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version> 2.2 . 0 </version>
</dependency>本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
