创建maven工程
略
pom.xml
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>3.0.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>3.0.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>3.0.3</version>
</dependency>
</dependencies>
在 pom.xml 点击右键 -> 【maven】 -> 【reimport】 导入依赖
log4j.properties
打印 hadoop debug 信息
在 resources 文件夹下创建 log4j.properties 文件,内容如下:
log4j.rootLogger=DEBUG, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
java
package top.malaoshi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.util.ReflectionUtils;
public class Read {
public static void main(String[] args) throws Exception {
//设置客户端运行身份 以root去操作访问HDFS
System.setProperty("HADOOP_USER_NAME","root");
//Configuration 用于指定相关参数属性
Configuration conf = new Configuration();
//指定要读取的文件
Path path=new Path("hdfs://hadoop1:8020/4.txt.gz");
SequenceFile.Reader.Option option1 = SequenceFile.Reader.file(path);
SequenceFile.Reader reader = null;
try {
reader = new SequenceFile.Reader(conf,option1);
//通过反射创建key
Writable key = (Writable) ReflectionUtils.newInstance(
reader.getKeyClass(), conf);
//通过反射创建value
Writable value = (Writable) ReflectionUtils.newInstance(
reader.getValueClass(), conf);
while (reader.next(key, value)) {
System.out.println(key+"===="+value);
}
} finally {
IOUtils.closeStream(reader);
}
}
}