Java Code Examples for org.apache.hadoop.mapred.SkipBadRecords#setAutoIncrMapperProcCount()

The following examples show how to use org.apache.hadoop.mapred.SkipBadRecords#setAutoIncrMapperProcCount() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: PipeMapper.java    From hadoop with Apache License 2.0 6 votes vote down vote up 
public void configure(JobConf job) {
  super.configure(job);
  //disable the auto increment of the counter. For streaming, no of 
  //processed records could be different(equal or less) than the no of 
  //records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
  skipping = job.getBoolean(MRJobConfig.SKIP_RECORDS, false);
  if (mapInputWriterClass_.getCanonicalName().equals(TextInputWriter.class.getCanonicalName())) {
    String inputFormatClassName = job.getClass("mapred.input.format.class", TextInputFormat.class).getCanonicalName();
    ignoreKey = job.getBoolean("stream.map.input.ignoreKey", 
      inputFormatClassName.equals(TextInputFormat.class.getCanonicalName()));
  }
  
  try {
    mapOutputFieldSeparator = job.get("stream.map.output.field.separator", "\t").getBytes("UTF-8");
    mapInputFieldSeparator = job.get("stream.map.input.field.separator", "\t").getBytes("UTF-8");
    numOfMapOutputKeyFields = job.getInt("stream.num.map.output.key.fields", 1);
  } catch (UnsupportedEncodingException e) {
    throw new RuntimeException("The current system does not support UTF-8 encoding!", e);
  }
}
Example 2
Source File: PipeMapper.java    From big-c with Apache License 2.0 6 votes vote down vote up 
public void configure(JobConf job) {
  super.configure(job);
  //disable the auto increment of the counter. For streaming, no of 
  //processed records could be different(equal or less) than the no of 
  //records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
  skipping = job.getBoolean(MRJobConfig.SKIP_RECORDS, false);
  if (mapInputWriterClass_.getCanonicalName().equals(TextInputWriter.class.getCanonicalName())) {
    String inputFormatClassName = job.getClass("mapred.input.format.class", TextInputFormat.class).getCanonicalName();
    ignoreKey = job.getBoolean("stream.map.input.ignoreKey", 
      inputFormatClassName.equals(TextInputFormat.class.getCanonicalName()));
  }
  
  try {
    mapOutputFieldSeparator = job.get("stream.map.output.field.separator", "\t").getBytes("UTF-8");
    mapInputFieldSeparator = job.get("stream.map.input.field.separator", "\t").getBytes("UTF-8");
    numOfMapOutputKeyFields = job.getInt("stream.num.map.output.key.fields", 1);
  } catch (UnsupportedEncodingException e) {
    throw new RuntimeException("The current system does not support UTF-8 encoding!", e);
  }
}
Example 3
Source File: PipeMapper.java    From RDFS with Apache License 2.0 6 votes vote down vote up 
public void configure(JobConf job) {
  super.configure(job);
  //disable the auto increment of the counter. For streaming, no of 
  //processed records could be different(equal or less) than the no of 
  //records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
  skipping = job.getBoolean("mapred.skip.on", false);
  String inputFormatClassName = job.getClass("mapred.input.format.class", TextInputFormat.class).getCanonicalName();
  ignoreKey = inputFormatClassName.equals(TextInputFormat.class.getCanonicalName());

  try {
    mapOutputFieldSeparator = job.get("stream.map.output.field.separator", "\t").getBytes("UTF-8");
    mapInputFieldSeparator = job.get("stream.map.input.field.separator", "\t").getBytes("UTF-8");
    numOfMapOutputKeyFields = job.getInt("stream.num.map.output.key.fields", 1);
  } catch (UnsupportedEncodingException e) {
    throw new RuntimeException("The current system does not support UTF-8 encoding!", e);
  }
}
Example 4
Source File: PipeMapper.java    From hadoop-gpu with Apache License 2.0 6 votes vote down vote up 
public void configure(JobConf job) {
  super.configure(job);
  //disable the auto increment of the counter. For streaming, no of 
  //processed records could be different(equal or less) than the no of 
  //records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
  skipping = job.getBoolean("mapred.skip.on", false);
  String inputFormatClassName = job.getClass("mapred.input.format.class", TextInputFormat.class).getCanonicalName();
  ignoreKey = inputFormatClassName.equals(TextInputFormat.class.getCanonicalName());

  try {
    mapOutputFieldSeparator = job.get("stream.map.output.field.separator", "\t").getBytes("UTF-8");
    mapInputFieldSeparator = job.get("stream.map.input.field.separator", "\t").getBytes("UTF-8");
    numOfMapOutputKeyFields = job.getInt("stream.num.map.output.key.fields", 1);
  } catch (UnsupportedEncodingException e) {
    throw new RuntimeException("The current system does not support UTF-8 encoding!", e);
  }
}
Example 5
Source File: PipesMapRunner.java    From hadoop with Apache License 2.0 5 votes vote down vote up 
/**
 * Get the new configuration.
 * @param job the job's configuration
 */
public void configure(JobConf job) {
  this.job = job;
  //disable the auto increment of the counter. For pipes, no of processed 
  //records could be different(equal or less) than the no of records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
}
Example 6
Source File: PipesMapRunner.java    From big-c with Apache License 2.0 5 votes vote down vote up 
/**
 * Get the new configuration.
 * @param job the job's configuration
 */
public void configure(JobConf job) {
  this.job = job;
  //disable the auto increment of the counter. For pipes, no of processed 
  //records could be different(equal or less) than the no of records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
}
Example 7
Source File: PipesMapRunner.java    From RDFS with Apache License 2.0 5 votes vote down vote up 
/**
 * Get the new configuration.
 * @param job the job's configuration
 */
public void configure(JobConf job) {
  this.job = job;
  //disable the auto increment of the counter. For pipes, no of processed 
  //records could be different(equal or less) than the no of records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
}
Example 8
Source File: PipesGPUMapRunner.java    From hadoop-gpu with Apache License 2.0 5 votes vote down vote up 
/**
 * Get the new configuration.
 * @param job the job's configuration
 */
public void configure(JobConf job) {
  this.job = job;
  //disable the auto increment of the counter. For pipes, no of processed 
  //records could be different(equal or less) than the no of records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
}
Example 9
Source File: PipesMapRunner.java    From hadoop-gpu with Apache License 2.0 5 votes vote down vote up 
/**
 * Get the new configuration.
 * @param job the job's configuration
 */
public void configure(JobConf job) {
  this.job = job;
  //disable the auto increment of the counter. For pipes, no of processed 
  //records could be different(equal or less) than the no of records input.
  SkipBadRecords.setAutoIncrMapperProcCount(job, false);
}