标签：tar new while imp extend pen nal att click
写在前面：
需要保证hadoop版本 各个jar版本一致，否则可能出现各种哦莫名奇妙的错误！
maven 依赖：
<?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> <packaging>jar</packaging> <groupId>BaseTecLearn</groupId> <artifactId>BaseTecLearn</artifactId> <version>1.0-SNAPSHOT</version> <dependencies> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-core_2.11</artifactId> <version>2.2.0</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql_2.11</artifactId> <version>2.2.0</version> </dependency> <dependency> <groupId>org.apache.thrift</groupId> <artifactId>libthrift</artifactId> <version>0.6.1</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-common</artifactId> <version>2.7.1</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-mapreduce-client-core</artifactId> <version>2.7.4</version> </dependency> </dependencies> </project>
resource目录下配置日志（很重要，可以查看警告啥的）
log4j.rootLogger=WARN,stdout,logfile
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
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=hadoop.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%ns
package top.letsgogo; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; 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.output.FileOutputFormat; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path("/home/panteng/IdeaProjects/pushscore-sdk/baseTecLearn/target/classes/regular.txt")); FileOutputFormat.setOutputPath(job, new Path("/home/panteng/IdeaProjects/pushscore-sdk/baseTecLearn/target/classes/regular")); System.out.println(job.waitForCompletion(true)); //System.exit(job.waitForCompletion(true) ? 0 : 1); } }
标签：tar new while imp extend pen nal att click
原文地址：http://www.cnblogs.com/tengpan-cn/p/7553495.html
