【发布时间】:2018-09-12 21:16:39
【问题描述】:
我打算在 IntelliJ 中使用 Hadoop 的伪分布式模式。目前,我可以在笔记本电脑上成功运行 WordCount 示例代码。然后,我尝试编写另一个代码,其中包含 hbase 的使用。但是,我无法在我的代码中导入 import org.apache.hadoop.hbase.mapreduce.TableReducer;。我尝试添加不同的 Maven 依赖项,但它不起作用。
这里是hadoop代码:
package topten;
import java.io.*;
import java.util.Map;
import java.util.TreeMap;
import java.util.HashMap;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.filter.FirstKeyOnlyFilter;
public class TopTen {
public static class TopTenMapper extends Mapper<Object, Text, NullWritable, Text> {
// Stores a map of user reputation to the record
TreeMap<Integer, Text> repToRecordMap = new TreeMap<Integer, Text>();
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
//<FILL IN>
}
protected void cleanup(Context context) throws IOException, InterruptedException {
// Output our ten records to the reducers with a null key
//<FILL IN>
}
}
public static class TopTenReducer extends TableReducer<NullWritable, Text, NullWritable> {
// Stores a map of user reputation to the record
private TreeMap<Integer, Text> repToRecordMap = new TreeMap<Integer, Text>();
public void reduce(NullWritable key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
//<FILL IN>
}
}
public static void main(String[] args) throws Exception {
}
}
这是我的 Maven 配置文件:
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.dataintensivecomputing</groupId>
<artifactId>hadoop</artifactId>
<version>1.0-SNAPSHOT</version>
<repositories>
<repository>
<id>apache</id>
<url>http://maven.apache.org</url>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.2.1</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase</artifactId>
<version>2.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.2.4</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.4</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>1.2.4</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-mapreduce</artifactId>
<version>2.1.0</version>
</dependency>
</dependencies>
</project>
谁能告诉我应该将哪些 Maven 依赖项添加到 pom.xml 文件中?
【问题讨论】:
-
您确实需要为每个组 id 使用一致的版本号
-
但是该课程是为
hbase-mapreduce:2.1.0github.com/apache/hbase/blob/rel/2.1.0/hbase-mapreduce/src/main/…提供的