/**
* Chains the <code>reduce(...)</code> method of the Reducer with the <code>map(...) </code>
* methods of the Mappers in the chain.
*/
@SuppressWarnings({"unchecked"})
public void reduce(Object key, Iterator values, OutputCollector output, Reporter reporter)
throws IOException {
Reducer reducer = chain.getReducer();
if (reducer != null) {
reducer.reduce(key, values, chain.getReducerCollector(output, reporter), reporter);
}
}
/**
* Adds a Mapper class to the chain job's JobConf.
*
* <p>It has to be specified how key and values are passed from one element of the chain to the
* next, by value or by reference. If a Mapper leverages the assumed semantics that the key and
* values are not modified by the collector 'by value' must be used. If the Mapper does not expect
* this semantics, as an optimization to avoid serialization and deserialization 'by reference'
* can be used.
*
* <p>For the added Mapper the configuration given for it, <code>mapperConf</code>, have
* precedence over the job's JobConf. This precedence is in effect when the task is running.
*
* <p>IMPORTANT: There is no need to specify the output key/value classes for the ChainMapper,
* this is done by the addMapper for the last mapper in the chain .
*
* @param job chain job's JobConf to add the Mapper class.
* @param klass the Mapper class to add.
* @param inputKeyClass mapper input key class.
* @param inputValueClass mapper input value class.
* @param outputKeyClass mapper output key class.
* @param outputValueClass mapper output value class.
* @param byValue indicates if key/values should be passed by value to the next Mapper in the
* chain, if any.
* @param mapperConf a JobConf with the configuration for the Mapper class. It is recommended to
* use a JobConf without default values using the <code>JobConf(boolean loadDefaults)</code>
* constructor with FALSE.
*/
public static <K1, V1, K2, V2> void addMapper(
JobConf job,
Class<? extends Mapper<K1, V1, K2, V2>> klass,
Class<? extends K1> inputKeyClass,
Class<? extends V1> inputValueClass,
Class<? extends K2> outputKeyClass,
Class<? extends V2> outputValueClass,
boolean byValue,
JobConf mapperConf) {
job.setOutputKeyClass(outputKeyClass);
job.setOutputValueClass(outputValueClass);
Chain.addMapper(
false,
job,
klass,
inputKeyClass,
inputValueClass,
outputKeyClass,
outputValueClass,
byValue,
mapperConf);
}
/**
* Sets the Reducer class to the chain job's JobConf.
*
* <p>It has to be specified how key and values are passed from one element of the chain to the
* next, by value or by reference. If a Reducer leverages the assumed semantics that the key and
* values are not modified by the collector 'by value' must be used. If the Reducer does not
* expect this semantics, as an optimization to avoid serialization and deserialization 'by
* reference' can be used.
*
* <p>For the added Reducer the configuration given for it, <code>reducerConf</code>, have
* precedence over the job's JobConf. This precedence is in effect when the task is running.
*
* <p>IMPORTANT: There is no need to specify the output key/value classes for the ChainReducer,
* this is done by the setReducer or the addMapper for the last element in the chain.
*
* @param job job's JobConf to add the Reducer class.
* @param klass the Reducer class to add.
* @param inputKeyClass reducer input key class.
* @param inputValueClass reducer input value class.
* @param outputKeyClass reducer output key class.
* @param outputValueClass reducer output value class.
* @param byValue indicates if key/values should be passed by value to the next Mapper in the
* chain, if any.
* @param reducerConf a JobConf with the configuration for the Reducer class. It is recommended to
* use a JobConf without default values using the <code>JobConf(boolean loadDefaults)</code>
* constructor with FALSE.
*/
public static <K1, V1, K2, V2> void setReducer(
JobConf job,
Class<? extends Reducer<K1, V1, K2, V2>> klass,
Class<? extends K1> inputKeyClass,
Class<? extends V1> inputValueClass,
Class<? extends K2> outputKeyClass,
Class<? extends V2> outputValueClass,
boolean byValue,
JobConf reducerConf) {
job.setReducerClass(ChainReducer.class);
job.setOutputKeyClass(outputKeyClass);
job.setOutputValueClass(outputValueClass);
Chain.setReducer(
job,
klass,
inputKeyClass,
inputValueClass,
outputKeyClass,
outputValueClass,
byValue,
reducerConf);
}
/**
* Closes the ChainReducer, the Reducer and all the Mappers in the chain.
*
* <p>If this method is overriden <code>super.close()</code> should be invoked at the end of the
* overwriter method.
*/
public void close() throws IOException {
chain.close();
}
/**
* Configures the ChainReducer, the Reducer and all the Mappers in the chain.
*
* <p>If this method is overriden <code>super.configure(...)</code> should be invoked at the
* beginning of the overwriter method.
*/
public void configure(JobConf job) {
chain.configure(job);
}