大数据全系列 教程
1869个小节阅读:467.3k
408考研
JAVA全系列 教程
面向对象的程序设计语言
Python全系列 教程
Python3.x版本,未来主流的版本
人工智能 教程
顺势而为,AI创新未来
大厂算法 教程
算法,程序员自我提升必经之路
C++ 教程
一门通用计算机编程语言
微服务 教程
目前业界流行的框架组合
web前端全系列 教程
通向WEB技术世界的钥匙
大数据全系列 教程
站在云端操控万千数据
AIGC全能工具班
A A
White Night
xxxxxxxxxx
private <INKEY,INVALUE,OUTKEY,OUTVALUE>
void runNewMapper(final JobConf job,
final TaskSplitIndex splitIndex,
final TaskUmbilicalProtocol umbilical,
TaskReporter reporter
) throws IOException, ClassNotFoundException,
InterruptedException {
// make a task context so we can get the classes
org.apache.hadoop.mapreduce.TaskAttemptContext taskContext =
new org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl(job,
getTaskID(),
reporter);
// make a mapper 创建Mapper对象
org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE> mapper =
(org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE>)
ReflectionUtils.newInstance(taskContext.getMapperClass(), job);
// make the input format
org.apache.hadoop.mapreduce.InputFormat<INKEY,INVALUE> inputFormat =
(org.apache.hadoop.mapreduce.InputFormat<INKEY,INVALUE>)
ReflectionUtils.newInstance(taskContext.getInputFormatClass(), job);
// rebuild the input split
org.apache.hadoop.mapreduce.InputSplit split = null;
split = getSplitDetails(new Path(splitIndex.getSplitLocation()),
splitIndex.getStartOffset());
LOG.info("Processing split: " + split);
org.apache.hadoop.mapreduce.RecordReader<INKEY,INVALUE> input =
new NewTrackingRecordReader<INKEY,INVALUE>
(split, inputFormat, reporter, taskContext);
job.setBoolean(JobContext.SKIP_RECORDS, isSkipping());
org.apache.hadoop.mapreduce.RecordWriter output = null;
// get an output object
if (job.getNumReduceTasks() == 0) {
output =
new NewDirectOutputCollector(taskContext, job, umbilical, reporter);
} else {
output = new NewOutputCollector(taskContext, job, umbilical, reporter);
}
org.apache.hadoop.mapreduce.MapContext<INKEY, INVALUE, OUTKEY, OUTVALUE>
mapContext =
new MapContextImpl<INKEY, INVALUE, OUTKEY, OUTVALUE>(job, getTaskID(),
input, output,
committer,
reporter, split);
org.apache.hadoop.mapreduce.Mapper<INKEY,INVALUE,OUTKEY,OUTVALUE>.Context
mapperContext =
new WrappedMapper<INKEY, INVALUE, OUTKEY, OUTVALUE>().getMapContext(
mapContext);
try {
//初始化input对象
input.initialize(split, mapperContext);
//运行mapper任务,调用自定义的Mapper类覆写的map方法
mapper.run(mapperContext);
mapPhase.complete();
//设置任务的当前阶段:排序
setPhase(TaskStatus.Phase.SORT);
//更新任务的状态
statusUpdate(umbilical);
//input对象的关闭与置空
input.close();
input = null;
//output对象的关闭与置空
output.close(mapperContext);
output = null;
} finally {
closeQuietly(input);
closeQuietly(output, mapperContext);
}
}