diff --git a/hadoop-mapreduce-project/CHANGES.txt b/hadoop-mapreduce-project/CHANGES.txt index 5fd7d30cea2..5524b14d213 100644 --- a/hadoop-mapreduce-project/CHANGES.txt +++ b/hadoop-mapreduce-project/CHANGES.txt @@ -181,6 +181,9 @@ Trunk (Unreleased) MAPREDUCE-6234. TestHighRamJob fails due to the change in MAPREDUCE-5785. (Masatake Iwasaki via kasha) + MAPREDUCE-5657. Fix Javadoc errors caused by incorrect or illegal tags in doc + comments. (Akira AJISAKA via ozawa) + BREAKDOWN OF MAPREDUCE-2841 (NATIVE TASK) SUBTASKS MAPREDUCE-5985. native-task: Fix build on macosx. Contributed by diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapred/TaskAttemptListenerImpl.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapred/TaskAttemptListenerImpl.java index 5f39edd72e8..c8f2427fcd0 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapred/TaskAttemptListenerImpl.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapred/TaskAttemptListenerImpl.java @@ -174,7 +174,7 @@ public class TaskAttemptListenerImpl extends CompositeService /** * Child checking whether it can commit. * - *
+ *
* Commit is a two-phased protocol. First the attempt informs the * ApplicationMaster that it is * {@link #commitPending(TaskAttemptID, TaskStatus)}. Then it repeatedly polls @@ -208,7 +208,7 @@ public class TaskAttemptListenerImpl extends CompositeService * TaskAttempt is reporting that it is in commit_pending and it is waiting for * the commit Response * - *
+ *
* Commit it a two-phased protocol. First the attempt informs the * ApplicationMaster that it is * {@link #commitPending(TaskAttemptID, TaskStatus)}. Then it repeatedly polls diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/JobEndNotifier.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/JobEndNotifier.java index 981e6ffb4b4..05bb40bb9d9 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/JobEndNotifier.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/JobEndNotifier.java @@ -44,7 +44,6 @@ import org.mortbay.log.Log; * proxy if needed
  • * The URL may contain sentinels which will be replaced by jobId and jobStatus * (eg. SUCCEEDED/KILLED/FAILED)
    • - *

    */ public class JobEndNotifier implements Configurable { private static final String JOB_ID = "$jobId"; diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/main/java/org/apache/hadoop/mapreduce/v2/util/MRApps.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/main/java/org/apache/hadoop/mapreduce/v2/util/MRApps.java index 1520fc8139b..e4b43b5a703 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/main/java/org/apache/hadoop/mapreduce/v2/util/MRApps.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-common/src/main/java/org/apache/hadoop/mapreduce/v2/util/MRApps.java @@ -345,7 +345,7 @@ public class MRApps extends Apps { * {@link MRJobConfig#MAPREDUCE_JOB_CLASSLOADER} is set to true, and * the APP_CLASSPATH environment variable is set. * @param conf - * @returns the created job classloader, or null if the job classloader is not + * @return the created job classloader, or null if the job classloader is not * enabled or the APP_CLASSPATH environment variable is not set * @throws IOException */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/filecache/DistributedCache.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/filecache/DistributedCache.java index 370d67deb64..0783eb50f84 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/filecache/DistributedCache.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/filecache/DistributedCache.java @@ -113,7 +113,7 @@ import org.apache.hadoop.mapreduce.MRJobConfig; * } * } * - *

    + * * * It is also very common to use the DistributedCache by using * {@link org.apache.hadoop.util.GenericOptionsParser}. diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/ClusterStatus.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/ClusterStatus.java index 8b567872b1a..904897b1326 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/ClusterStatus.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/ClusterStatus.java @@ -48,7 +48,7 @@ import org.apache.hadoop.util.StringInterner; * Task capacity of the cluster. * *
  • - * The number of currently running map & reduce tasks. + * The number of currently running map and reduce tasks. *
    • *
  • * State of the JobTracker. @@ -56,7 +56,7 @@ import org.apache.hadoop.util.StringInterner; *
  • * Details regarding black listed trackers. *
    • - *

    + * * *

    Clients can query for the latest ClusterStatus, via * {@link JobClient#getClusterStatus()}.

    diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileOutputFormat.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileOutputFormat.java index 721c8a84637..821c1e8943f 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileOutputFormat.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileOutputFormat.java @@ -179,7 +179,7 @@ public abstract class FileOutputFormat implements OutputFormat { * Get the {@link Path} to the task's temporary output directory * for the map-reduce job * - *

    Tasks' Side-Effect Files

    + * Tasks' Side-Effect Files * *

    Note: The following is valid only if the {@link OutputCommitter} * is {@link FileOutputCommitter}. If OutputCommitter is not diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/IFile.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/IFile.java index 30ebd6b8ca3..32e07e7b9fb 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/IFile.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/IFile.java @@ -47,7 +47,7 @@ import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; /** - * IFile is the simple format + * IFile is the simple <key-len, value-len, key, value> format * for the intermediate map-outputs in Map-Reduce. * * There is a Writer to write out map-outputs in this format and diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobACLsManager.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobACLsManager.java index 37633ab504a..0dbbe5a86c3 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobACLsManager.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobACLsManager.java @@ -101,7 +101,6 @@ public class JobACLsManager { * @param jobOperation * @param jobOwner * @param jobACL - * @throws AccessControlException */ public boolean checkAccess(UserGroupInformation callerUGI, JobACL jobOperation, String jobOwner, AccessControlList jobACL) { diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobClient.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobClient.java index 89a966eb84c..e91fbfed37c 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobClient.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobClient.java @@ -79,7 +79,7 @@ import org.apache.hadoop.util.ToolRunner; * Submitting the job to the cluster and optionally monitoring * it's status. * - *

    + * * * Normally the user creates the application, describes various facets of the * job via {@link JobConf} and then uses the JobClient to submit @@ -101,9 +101,9 @@ import org.apache.hadoop.util.ToolRunner; * * // Submit the job, then poll for progress until the job is complete * JobClient.runJob(job); - *

    + * * - *

    Job Control

    + * Job Control * *

    At times clients would chain map-reduce jobs to accomplish complex tasks * which cannot be done via a single map-reduce job. This is fairly easy since @@ -127,7 +127,7 @@ import org.apache.hadoop.util.ToolRunner; * {@link JobConf#setJobEndNotificationURI(String)} : setup a notification * on job-completion, thus avoiding polling. * - *

    + * * * @see JobConf * @see ClusterStatus diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobConf.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobConf.java index 315c8299872..c388bda4953 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobConf.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/JobConf.java @@ -74,7 +74,7 @@ import org.apache.log4j.Level; * more complex for the user to control finely * (e.g. {@link #setNumMapTasks(int)}). * - *

    + * * *

    JobConf typically specifies the {@link Mapper}, combiner * (if any), {@link Partitioner}, {@link Reducer}, {@link InputFormat} and @@ -105,7 +105,7 @@ import org.apache.log4j.Level; * * job.setInputFormat(SequenceFileInputFormat.class); * job.setOutputFormat(SequenceFileOutputFormat.class); - *

    + * * * @see JobClient * @see ClusterStatus @@ -486,7 +486,7 @@ public class JobConf extends Configuration { /** A new map/reduce configuration where the behavior of reading from the * default resources can be turned off. - *

    + *

    * If the parameter {@code loadDefaults} is false, the new instance * will not load resources from the default files. * @@ -993,19 +993,19 @@ public class JobConf extends Configuration { /** * Set the user defined {@link RawComparator} comparator for * grouping keys in the input to the combiner. - *

    + * *

    This comparator should be provided if the equivalence rules for keys * for sorting the intermediates are different from those for grouping keys * before each call to * {@link Reducer#reduce(Object, java.util.Iterator, OutputCollector, Reporter)}.

    - *

    + * *

    For key-value pairs (K1,V1) and (K2,V2), the values (V1, V2) are passed * in a single call to the reduce function if K1 and K2 compare as equal.

    - *

    + * *

    Since {@link #setOutputKeyComparatorClass(Class)} can be used to control * how keys are sorted, this can be used in conjunction to simulate * secondary sort on values.

    - *

    + * *

    Note: This is not a guarantee of the combiner sort being * stable in any sense. (In any case, with the order of available * map-outputs to the combiner being non-deterministic, it wouldn't make @@ -1210,7 +1210,7 @@ public class JobConf extends Configuration { *

  • be side-effect free
    • *
  • have the same input and output key types and the same input and * output value types
    • - *

    + * * *

    Typically the combiner is same as the Reducer for the * job i.e. {@link #setReducerClass(Class)}.

    @@ -1309,7 +1309,7 @@ public class JobConf extends Configuration { * A custom {@link InputFormat} is typically used to accurately control * the number of map tasks for the job.

    * - *

    How many maps?

    + * How many maps? * *

    The number of maps is usually driven by the total size of the inputs * i.e. total number of blocks of the input files.

    @@ -1350,7 +1350,7 @@ public class JobConf extends Configuration { /** * Set the requisite number of reduce tasks for this job. * - *

    How many reduces?

    + * How many reduces? * *

    The right number of reduces seems to be 0.95 or * 1.75 multiplied by (<no. of nodes> * @@ -1370,7 +1370,7 @@ public class JobConf extends Configuration { * reserve a few reduce slots in the framework for speculative-tasks, failures * etc.

    * - *

    Reducer NONE

    + * Reducer NONE * *

    It is legal to set the number of reduce-tasks to zero.

    * @@ -1693,9 +1693,9 @@ public class JobConf extends Configuration { * given task's stdout, stderr, syslog, jobconf files as arguments.

    * *

    The debug command, run on the node where the map failed, is:

    - * 

     
+   * 
        * $script $stdout $stderr $syslog $jobconf.
-   *

    + * * *

    The script file is distributed through {@link DistributedCache} * APIs. The script needs to be symlinked.

    @@ -1705,7 +1705,7 @@ public class JobConf extends Configuration { * job.setMapDebugScript("./myscript"); * DistributedCache.createSymlink(job); * DistributedCache.addCacheFile("/debug/scripts/myscript#myscript"); - *

    + * * * @param mDbgScript the script name */ @@ -1730,9 +1730,9 @@ public class JobConf extends Configuration { * is given task's stdout, stderr, syslog, jobconf files as arguments.

    * *

    The debug command, run on the node where the map failed, is:

    - * 

     
+   * 
        * $script $stdout $stderr $syslog $jobconf.
-   *

    + * * *

    The script file is distributed through {@link DistributedCache} * APIs. The script file needs to be symlinked

    @@ -1742,7 +1742,7 @@ public class JobConf extends Configuration { * job.setReduceDebugScript("./myscript"); * DistributedCache.createSymlink(job); * DistributedCache.addCacheFile("/debug/scripts/myscript#myscript"); - *

    + * * * @param rDbgScript the script name */ @@ -1785,8 +1785,6 @@ public class JobConf extends Configuration { * * @param uri the job end notification uri * @see JobStatus - * @see Job Completion and Chaining */ public void setJobEndNotificationURI(String uri) { set(JobContext.MR_JOB_END_NOTIFICATION_URL, uri); @@ -1816,7 +1814,7 @@ public class JobConf extends Configuration { * * If a value is specified in the configuration, it is returned. * Else, it returns {@link JobContext#DEFAULT_MAP_MEMORY_MB}. - *

    + *

    * For backward compatibility, if the job configuration sets the * key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different * from {@link #DISABLED_MEMORY_LIMIT}, that value will be used @@ -1842,7 +1840,7 @@ public class JobConf extends Configuration { * * If a value is specified in the configuration, it is returned. * Else, it returns {@link JobContext#DEFAULT_REDUCE_MEMORY_MB}. - *

    + *

    * For backward compatibility, if the job configuration sets the * key {@link #MAPRED_TASK_MAXVMEM_PROPERTY} to a value different * from {@link #DISABLED_MEMORY_LIMIT}, that value will be used @@ -1915,7 +1913,6 @@ public class JobConf extends Configuration { * * @param my_class the class to find. * @return a jar file that contains the class, or null. - * @throws IOException */ public static String findContainingJar(Class my_class) { return ClassUtil.findContainingJar(my_class); @@ -1924,10 +1921,10 @@ public class JobConf extends Configuration { /** * Get the memory required to run a task of this job, in bytes. See * {@link #MAPRED_TASK_MAXVMEM_PROPERTY} - *

    + *

    * This method is deprecated. Now, different memory limits can be * set for map and reduce tasks of a job, in MB. - *

    + *

    * For backward compatibility, if the job configuration sets the * key {@link #MAPRED_TASK_MAXVMEM_PROPERTY}, that value is returned. * Otherwise, this method will return the larger of the values returned by @@ -1953,7 +1950,7 @@ public class JobConf extends Configuration { /** * Set the maximum amount of memory any task of this job can use. See * {@link #MAPRED_TASK_MAXVMEM_PROPERTY} - *

    + *

    * mapred.task.maxvmem is split into * mapreduce.map.memory.mb * and mapreduce.map.memory.mb,mapred @@ -2073,7 +2070,7 @@ public class JobConf extends Configuration { /** * Parse the Maximum heap size from the java opts as specified by the -Xmx option - * Format: -Xmx[g|G|m|M|k|K] + * Format: -Xmx<size>[g|G|m|M|k|K] * @param javaOpts String to parse to read maximum heap size * @return Maximum heap size in MB or -1 if not specified */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Mapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Mapper.java index eaa6c2b72c4..ac2c96df5f0 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Mapper.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Mapper.java @@ -117,7 +117,7 @@ import org.apache.hadoop.io.compress.CompressionCodec; * output.collect(key, val); * } * } - *

    + * * *

    Applications may write a custom {@link MapRunnable} to exert greater * control on map processing e.g. multi-threaded Mappers etc.

    diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/QueueManager.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/QueueManager.java index 39fae2a5312..794c55da1ea 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/QueueManager.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/QueueManager.java @@ -46,20 +46,20 @@ import java.net.URL; /** * Class that exposes information about queues maintained by the Hadoop * Map/Reduce framework. - *

    + *

    * The Map/Reduce framework can be configured with one or more queues, * depending on the scheduler it is configured with. While some * schedulers work only with one queue, some schedulers support multiple * queues. Some schedulers also support the notion of queues within * queues - a feature called hierarchical queues. - *

    + *

    * Queue names are unique, and used as a key to lookup queues. Hierarchical * queues are named by a 'fully qualified name' such as q1:q2:q3, where * q2 is a child queue of q1 and q3 is a child queue of q2. - *

    + *

    * Leaf level queues are queues that contain no queues within them. Jobs * can be submitted only to leaf level queues. - *

    + *

    * Queues can be configured with various properties. Some of these * properties are common to all schedulers, and those are handled by this * class. Schedulers might also associate several custom properties with @@ -69,11 +69,11 @@ import java.net.URL; * provided by the framework, but define their own mechanisms. In such cases, * it is likely that the name of the queue will be used to relate the * common properties of a queue with scheduler specific properties. - *

    + *

    * Information related to a queue, such as its name, properties, scheduling * information and children are exposed by this class via a serializable * class called {@link JobQueueInfo}. - *

    + *

    * Queues are configured in the configuration file mapred-queues.xml. * To support backwards compatibility, queues can also be configured * in mapred-site.xml. However, when configured in the latter, there is @@ -102,7 +102,7 @@ public class QueueManager { /** * Factory method to create an appropriate instance of a queue * configuration parser. - *

    + *

    * Returns a parser that can parse either the deprecated property * style queue configuration in mapred-site.xml, or one that can * parse hierarchical queues in mapred-queues.xml. First preference @@ -157,7 +157,7 @@ public class QueueManager { /** * Construct a new QueueManager using configuration specified in the passed * in {@link org.apache.hadoop.conf.Configuration} object. - *

    + *

    * This instance supports queue configuration specified in mapred-site.xml, * but without support for hierarchical queues. If no queue configuration * is found in mapred-site.xml, it will then look for site configuration @@ -173,7 +173,7 @@ public class QueueManager { /** * Create an instance that supports hierarchical queues, defined in * the passed in configuration file. - *

    + *

    * This is mainly used for testing purposes and should not called from * production code. * @@ -208,7 +208,7 @@ public class QueueManager { /** * Return the set of leaf level queues configured in the system to * which jobs are submitted. - *

    + *

    * The number of queues configured should be dependent on the Scheduler * configured. Note that some schedulers work with only one queue, whereas * others can support multiple queues. @@ -222,7 +222,7 @@ public class QueueManager { /** * Return true if the given user is part of the ACL for the given * {@link QueueACL} name for the given queue. - *

    + *

    * An operation is allowed if all users are provided access for this * operation, or if either the user or any of the groups specified is * provided access. @@ -283,7 +283,7 @@ public class QueueManager { /** * Set a generic Object that represents scheduling information relevant * to a queue. - *

    + *

    * A string representation of this Object will be used by the framework * to display in user facing applications like the JobTracker web UI and * the hadoop CLI. @@ -323,7 +323,7 @@ public class QueueManager { /** * Refresh acls, state and scheduler properties for the configured queues. - *

    + *

    * This method reloads configuration related to queues, but does not * support changes to the list of queues or hierarchy. The expected usage * is that an administrator can modify the queue configuration file and @@ -431,7 +431,7 @@ public class QueueManager { /** * JobQueueInfo for all the queues. - *

    + *

    * Contribs can use this data structure to either create a hierarchy or for * traversing. * They can also use this to refresh properties in case of refreshQueues @@ -450,7 +450,7 @@ public class QueueManager { /** * Generates the array of QueueAclsInfo object. - *

    + *

    * The array consists of only those queues for which user has acls. * * @return QueueAclsInfo[] diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/RecordReader.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/RecordReader.java index 0c95a147dc6..6e2c89fd8ca 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/RecordReader.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/RecordReader.java @@ -29,7 +29,7 @@ import org.apache.hadoop.classification.InterfaceStability; * *

    RecordReader, typically, converts the byte-oriented view of * the input, provided by the InputSplit, and presents a - * record-oriented view for the {@link Mapper} & {@link Reducer} tasks for + * record-oriented view for the {@link Mapper} and {@link Reducer} tasks for * processing. It thus assumes the responsibility of processing record * boundaries and presenting the tasks with keys and values.

    * diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Reducer.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Reducer.java index 3fefa4bed71..962e195b89b 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Reducer.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/Reducer.java @@ -42,7 +42,7 @@ import org.apache.hadoop.io.Closeable; *
      *
    1. * - *

      Shuffle

      + * Shuffle * *

      Reducer is input the grouped output of a {@link Mapper}. * In the phase the framework, for each Reducer, fetches the @@ -51,7 +51,7 @@ import org.apache.hadoop.io.Closeable; *

      2. * *
    2. - *

      Sort

      + * Sort * *

      The framework groups Reducer inputs by keys * (since different Mappers may have output the same key) in this @@ -60,7 +60,7 @@ import org.apache.hadoop.io.Closeable; *

      The shuffle and sort phases occur simultaneously i.e. while outputs are * being fetched they are merged.

      * - *
      SecondarySort
      + * SecondarySort * *

      If equivalence rules for keys while grouping the intermediates are * different from those for grouping keys before reduction, then one may @@ -86,11 +86,11 @@ import org.apache.hadoop.io.Closeable; *

      3. * *
    3. - *

      Reduce

      + * Reduce * *

      In this phase the * {@link #reduce(Object, Iterator, OutputCollector, Reporter)} - * method is called for each <key, (list of values)> pair in + * method is called for each <key, (list of values)> pair in * the grouped inputs.

      *

      The output of the reduce task is typically written to the * {@link FileSystem} via @@ -156,7 +156,7 @@ import org.apache.hadoop.io.Closeable; * } * } * } - *

      + * * * @see Mapper * @see Partitioner @@ -171,7 +171,7 @@ public interface Reducer extends JobConfigurable, Closeable { * Reduces values for a given key. * *

      The framework calls this method for each - * <key, (list of values)> pair in the grouped inputs. + * <key, (list of values)> pair in the grouped inputs. * Output values must be of the same type as input values. Input keys must * not be altered. The framework will reuse the key and value objects * that are passed into the reduce, therefore the application should clone diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/TaskUmbilicalProtocol.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/TaskUmbilicalProtocol.java index 5df02c7b5b1..c3678d67065 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/TaskUmbilicalProtocol.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/TaskUmbilicalProtocol.java @@ -178,7 +178,6 @@ public interface TaskUmbilicalProtocol extends VersionedProtocol { * * @param taskID task's id * @return the most recent checkpoint (if any) for this task - * @throws IOException */ TaskCheckpointID getCheckpointID(TaskID taskID); diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainMapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainMapper.java index 14f040af96a..723a234d301 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainMapper.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainMapper.java @@ -29,61 +29,61 @@ import java.io.IOException; /** * The ChainMapper class allows to use multiple Mapper classes within a single * Map task. - *

      + *

      * The Mapper classes are invoked in a chained (or piped) fashion, the output of * the first becomes the input of the second, and so on until the last Mapper, * the output of the last Mapper will be written to the task's output. - *

      + *

      * The key functionality of this feature is that the Mappers in the chain do not * need to be aware that they are executed in a chain. This enables having * reusable specialized Mappers that can be combined to perform composite * operations within a single task. - *

      + *

      * Special care has to be taken when creating chains that the key/values output * by a Mapper are valid for the following Mapper in the chain. It is assumed * all Mappers and the Reduce in the chain use maching output and input key and * value classes as no conversion is done by the chaining code. - *

      + *

      * Using the ChainMapper and the ChainReducer classes is possible to compose * Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And * immediate benefit of this pattern is a dramatic reduction in disk IO. - *

      + *

      * 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. - *

      + *

      * ChainMapper usage pattern: - *

      + *

      * 

        * ...
  * conf.setJobName("chain");
  * conf.setInputFormat(TextInputFormat.class);
  * conf.setOutputFormat(TextOutputFormat.class);
- * 
      
+ *
  * JobConf mapAConf = new JobConf(false);
  * ...
  * ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, mapAConf);
- * 
      
+ *
  * JobConf mapBConf = new JobConf(false);
  * ...
  * ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, mapBConf);
- * 
      
+ *
  * JobConf reduceConf = new JobConf(false);
  * ...
  * ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, reduceConf);
- * 
      
+ *
  * ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, null);
- * 
      
+ *
  * ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
  *   LongWritable.class, LongWritable.class, true, null);
- * 
      
+ *
  * FileInputFormat.setInputPaths(conf, inDir);
  * FileOutputFormat.setOutputPath(conf, outDir);
  * ...
- * 
      
+ *
  * JobClient jc = new JobClient(conf);
  * RunningJob job = jc.submitJob(conf);
  * ...
@@ -95,21 +95,21 @@ public class ChainMapper implements Mapper {
 
   /**
    * Adds a Mapper class to the chain job's JobConf.
-   * 
      
+   * 
      
    * 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.
-   * 
      
+   * 
      
    * For the added Mapper the configuration given for it,
    * mapperConf, have precedence over the job's JobConf. This
    * precedence is in effect when the task is running.
-   * 
      
+   * 
      
    * 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              job's JobConf to add the Mapper class.
    * @param klass            the Mapper class to add.
@@ -148,7 +148,7 @@ public class ChainMapper implements Mapper {
 
   /**
    * Configures the ChainMapper and all the Mappers in the chain.
-   * 
      
+   * 
      
    * If this method is overriden super.configure(...) should be
    * invoked at the beginning of the overwriter method.
    */
@@ -171,7 +171,7 @@ public class ChainMapper implements Mapper {
 
   /**
    * Closes  the ChainMapper and all the Mappers in the chain.
-   * 
      
+   * 
      
    * If this method is overriden super.close() should be
    * invoked at the end of the overwriter method.
    */
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainReducer.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainReducer.java
index 641d82c0839..6f5b7cde2e5 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainReducer.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/ChainReducer.java
@@ -27,63 +27,63 @@ import java.util.Iterator;
 /**
  * The ChainReducer class allows to chain multiple Mapper classes after a
  * Reducer within the Reducer task.
- * 
      
+ * 
      
  * For each record output by the Reducer, the Mapper classes are invoked in a
  * chained (or piped) fashion, the output of the first becomes the input of the
  * second, and so on until the last Mapper, the output of the last Mapper will
  * be written to the task's output.
- * 
      
+ * 
      
  * The key functionality of this feature is that the Mappers in the chain do not
  * need to be aware that they are executed after the Reducer or in a chain.
  * This enables having reusable specialized Mappers that can be combined to
  * perform composite operations within a single task.
- * 
      
+ * 
      
  * Special care has to be taken when creating chains that the key/values output
  * by a Mapper are valid for the following Mapper in the chain. It is assumed
  * all Mappers and the Reduce in the chain use maching output and input key and
  * value classes as no conversion is done by the chaining code.
- * 
      
+ * 
      
  * Using the ChainMapper and the ChainReducer classes is possible to compose
  * Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And
  * immediate benefit of this pattern is a dramatic reduction in disk IO.
- * 
      
+ * 
      
  * 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.
- * 
      
+ * 
      
  * ChainReducer usage pattern:
- * 
      
+ * 
      
  * 
        * ...
  * conf.setJobName("chain");
  * conf.setInputFormat(TextInputFormat.class);
  * conf.setOutputFormat(TextOutputFormat.class);
- * 
      
+ *
  * JobConf mapAConf = new JobConf(false);
  * ...
  * ChainMapper.addMapper(conf, AMap.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, mapAConf);
- * 
      
+ *
  * JobConf mapBConf = new JobConf(false);
  * ...
  * ChainMapper.addMapper(conf, BMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, mapBConf);
- * 
      
+ *
  * JobConf reduceConf = new JobConf(false);
  * ...
  * ChainReducer.setReducer(conf, XReduce.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, reduceConf);
- * 
      
+ *
  * ChainReducer.addMapper(conf, CMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, null);
- * 
      
+ *
  * ChainReducer.addMapper(conf, DMap.class, LongWritable.class, Text.class,
  *   LongWritable.class, LongWritable.class, true, null);
- * 
      
+ *
  * FileInputFormat.setInputPaths(conf, inDir);
  * FileOutputFormat.setOutputPath(conf, outDir);
  * ...
- * 
      
+ *
  * JobClient jc = new JobClient(conf);
  * RunningJob job = jc.submitJob(conf);
  * ...
@@ -95,18 +95,18 @@ public class ChainReducer implements Reducer {
 
   /**
    * Sets the Reducer class to the chain job's JobConf.
-   * 
      
+   * 
      
    * 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.
-   * 
      
+   * 
      
    * For the added Reducer the configuration given for it,
    * reducerConf, have precedence over the job's JobConf. This
    * precedence is in effect when the task is running.
-   * 
      
+   * 
      
    * 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.
@@ -139,18 +139,18 @@ public class ChainReducer implements Reducer {
 
   /**
    * Adds a Mapper class to the chain job's JobConf.
-   * 
      
+   * 
      
    * 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.
-   * 
      
+   * 
      
    * For the added Mapper the configuration given for it,
    * mapperConf, have precedence over the job's JobConf. This
    * precedence is in effect when the task is running.
-   * 
      
+   * 
      
    * 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
    * .
@@ -191,7 +191,7 @@ public class ChainReducer implements Reducer {
 
   /**
    * Configures the ChainReducer, the Reducer and all the Mappers in the chain.
-   * 
      
+   * 
      
    * If this method is overriden super.configure(...) should be
    * invoked at the beginning of the overwriter method.
    */
@@ -215,7 +215,7 @@ public class ChainReducer implements Reducer {
 
   /**
    * Closes  the ChainReducer, the Reducer and all the Mappers in the chain.
-   * 
      
+   * 
      
    * If this method is overriden super.close() should be
    * invoked at the end of the overwriter method.
    */
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/MultipleOutputs.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/MultipleOutputs.java
index 39e80f9a16b..f0f3652beb1 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/MultipleOutputs.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/MultipleOutputs.java
@@ -31,29 +31,29 @@ import java.util.*;
  * than the job default output via the OutputCollector passed to
  * the map() and reduce() methods of the
  * Mapper and Reducer implementations.
- * 
      
+ * 
      
  * Each additional output, or named output, may be configured with its own
  * OutputFormat, with its own key class and with its own value
  * class.
- * 
      
+ * 
      
  * A named output can be a single file or a multi file. The later is refered as
  * a multi named output.
- * 
      
+ * 
      
  * A multi named output is an unbound set of files all sharing the same
  * OutputFormat, key class and value class configuration.
- * 
      
+ * 
      
  * When named outputs are used within a Mapper implementation,
  * key/values written to a name output are not part of the reduce phase, only
  * key/values written to the job OutputCollector are part of the
  * reduce phase.
- * 
      
+ * 
      
  * MultipleOutputs supports counters, by default the are disabled. The counters
  * group is the {@link MultipleOutputs} class name.
  * 
      
  * The names of the counters are the same as the named outputs. For multi
  * named outputs the name of the counter is the concatenation of the named
  * output, and underscore '_' and the multiname.
- * 
      
+ * 
      
  * Job configuration usage pattern is:
  * 
        *
@@ -82,7 +82,7 @@ import java.util.*;
  *
  * ...
  * 
      
- * 
      
+ * 
      
  * Job configuration usage pattern is:
  * 
        *
@@ -271,7 +271,6 @@ public class MultipleOutputs {
 
   /**
    * Adds a named output for the job.
-   * 
      
    *
    * @param conf              job conf to add the named output
    * @param namedOutput       named output name, it has to be a word, letters
@@ -291,7 +290,6 @@ public class MultipleOutputs {
 
   /**
    * Adds a multi named output for the job.
-   * 
      
    *
    * @param conf              job conf to add the named output
    * @param namedOutput       named output name, it has to be a word, letters
@@ -311,7 +309,6 @@ public class MultipleOutputs {
 
   /**
    * Adds a named output for the job.
-   * 
      
    *
    * @param conf              job conf to add the named output
    * @param namedOutput       named output name, it has to be a word, letters
@@ -339,9 +336,9 @@ public class MultipleOutputs {
 
   /**
    * Enables or disables counters for the named outputs.
-   * 
      
+   * 
      
    * By default these counters are disabled.
-   * 
      
+   * 
      
    * MultipleOutputs supports counters, by default the are disabled.
    * The counters group is the {@link MultipleOutputs} class name.
    * 
      
@@ -358,9 +355,9 @@ public class MultipleOutputs {
 
   /**
    * Returns if the counters for the named outputs are enabled or not.
-   * 
      
+   * 
      
    * By default these counters are disabled.
-   * 
      
+   * 
      
    * MultipleOutputs supports counters, by default the are disabled.
    * The counters group is the {@link MultipleOutputs} class name.
    * 
      
@@ -465,7 +462,6 @@ public class MultipleOutputs {
 
   /**
    * Gets the output collector for a named output.
-   * 
      
    *
    * @param namedOutput the named output name
    * @param reporter    the reporter
@@ -480,7 +476,6 @@ public class MultipleOutputs {
 
   /**
    * Gets the output collector for a multi named output.
-   * 
      
    *
    * @param namedOutput the named output name
    * @param multiName   the multi name part
@@ -525,7 +520,7 @@ public class MultipleOutputs {
 
   /**
    * Closes all the opened named outputs.
-   * 
      
+   * 
      
    * If overriden subclasses must invoke super.close() at the
    * end of their close()
    *
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TokenCountMapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TokenCountMapper.java
index 8e884cee8bb..75179e110f9 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TokenCountMapper.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TokenCountMapper.java
@@ -32,7 +32,7 @@ import org.apache.hadoop.mapred.Reporter;
 
 
 /** 
- * A {@link Mapper} that maps text values into  pairs.  Uses
+ * A {@link Mapper} that maps text values into <token,freq> pairs.  Uses
  * {@link StringTokenizer} to break text into tokens. 
  */
 @InterfaceAudience.Public
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
index 8c20723b711..6251925ea2e 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
@@ -60,7 +60,7 @@ import org.apache.hadoop.util.GenericOptionsParser;
  * The developer using Aggregate will need only to provide a plugin class
  * conforming to the following interface:
  * 
- * public interface ValueAggregatorDescriptor { public ArrayList
+ * public interface ValueAggregatorDescriptor { public ArrayList<Entry>
  * generateKeyValPairs(Object key, Object value); public void
  * configure(JobConfjob); }
  * 
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorReducer.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorReducer.java
index a6b357324da..2738968d6b1 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorReducer.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorReducer.java
@@ -45,7 +45,8 @@ public class ValueAggregatorReducer values,
                      OutputCollector output, Reporter reporter) throws IOException {
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/db/DBInputFormat.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/db/DBInputFormat.java
index 2715705407e..159919f5a04 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/db/DBInputFormat.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/db/DBInputFormat.java
@@ -195,8 +195,8 @@ public class DBInputFormat
    * @param inputClass the class object implementing DBWritable, which is the 
    * Java object holding tuple fields.
    * @param tableName The table to read data from
-   * @param conditions The condition which to select data with, eg. '(updated >
-   * 20070101 AND length > 0)'
+   * @param conditions The condition which to select data with, eg. '(updated >
+   * 20070101 AND length > 0)'
    * @param orderBy the fieldNames in the orderBy clause.
    * @param fieldNames The field names in the table
    * @see #setInput(JobConf, Class, String, String)
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Cluster.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Cluster.java
index 60ff715cb83..34353acb878 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Cluster.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Cluster.java
@@ -134,6 +134,7 @@ public class Cluster {
   
   /**
    * Close the Cluster.
+   * @throws IOException
    */
   public synchronized void close() throws IOException {
     clientProtocolProvider.close(client);
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/ClusterMetrics.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/ClusterMetrics.java
index c4c2778dd0b..b5e54b5eaf2 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/ClusterMetrics.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/ClusterMetrics.java
@@ -40,15 +40,15 @@ import org.apache.hadoop.io.Writable;
  *   Slot capacity of the cluster. 
  *
      4. *
    4. - * The number of currently occupied/reserved map & reduce slots. + * The number of currently occupied/reserved map and reduce slots. *
      5. *
    5. - * The number of currently running map & reduce tasks. + * The number of currently running map and reduce tasks. *
      6. *
    6. * The number of job submissions. *
      7. - *

    + * * *

    Clients can query for the latest ClusterMetrics, via * {@link Cluster#getClusterStatus()}.

    diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/CryptoUtils.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/CryptoUtils.java index 184cdf0618f..ef061769093 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/CryptoUtils.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/CryptoUtils.java @@ -123,11 +123,11 @@ public class CryptoUtils { * "mapreduce.job.encrypted-intermediate-data.buffer.kb" Job configuration * variable. * - * If the value of 'length' is > -1, The InputStream is additionally wrapped - * in a LimitInputStream. CryptoStreams are late buffering in nature. This - * means they will always try to read ahead if they can. The LimitInputStream - * will ensure that the CryptoStream does not read past the provided length - * from the given Input Stream. + * If the value of 'length' is > -1, The InputStream is additionally + * wrapped in a LimitInputStream. CryptoStreams are late buffering in nature. + * This means they will always try to read ahead if they can. The + * LimitInputStream will ensure that the CryptoStream does not read past the + * provided length from the given Input Stream. * * @param conf * @param in diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Job.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Job.java index 470290c266b..f404175939e 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Job.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Job.java @@ -69,7 +69,7 @@ import org.apache.hadoop.yarn.api.records.ReservationId; * * // Submit the job, then poll for progress until the job is complete * job.waitForCompletion(true); - *

    + * * * */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobContext.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobContext.java index 836f1829079..6bd2d1f0d51 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobContext.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobContext.java @@ -289,7 +289,6 @@ public interface JobContext extends MRJobConfig { * Get the timestamps of the archives. Used by internal * DistributedCache and MapReduce code. * @return a string array of timestamps - * @throws IOException */ public String[] getArchiveTimestamps(); @@ -297,7 +296,6 @@ public interface JobContext extends MRJobConfig { * Get the timestamps of the files. Used by internal * DistributedCache and MapReduce code. * @return a string array of timestamps - * @throws IOException */ public String[] getFileTimestamps(); diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmissionFiles.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmissionFiles.java index 516e661133b..71250777473 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmissionFiles.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/JobSubmissionFiles.java @@ -100,7 +100,7 @@ public class JobSubmissionFiles { /** * Initializes the staging directory and returns the path. It also - * keeps track of all necessary ownership & permissions + * keeps track of all necessary ownership and permissions * @param cluster * @param conf */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Mapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Mapper.java index 3a6186b9b91..6b4147b900b 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Mapper.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Mapper.java @@ -42,9 +42,9 @@ import org.apache.hadoop.mapreduce.task.MapContextImpl; * *

    The framework first calls * {@link #setup(org.apache.hadoop.mapreduce.Mapper.Context)}, followed by - * {@link #map(Object, Object, Context)} + * {@link #map(Object, Object, org.apache.hadoop.mapreduce.Mapper.Context)} * for each key/value pair in the InputSplit. Finally - * {@link #cleanup(Context)} is called.

    + * {@link #cleanup(org.apache.hadoop.mapreduce.Mapper.Context)} is called.

    * *

    All intermediate values associated with a given output key are * subsequently grouped by the framework, and passed to a {@link Reducer} to @@ -84,9 +84,10 @@ import org.apache.hadoop.mapreduce.task.MapContextImpl; * } * } * } - *

    + * * - *

    Applications may override the {@link #run(Context)} method to exert + *

    Applications may override the + * {@link #run(org.apache.hadoop.mapreduce.Mapper.Context)} method to exert * greater control on map processing e.g. multi-threaded Mappers * etc.

    * diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Reducer.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Reducer.java index ddf67e18abb..ab67ab05734 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Reducer.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/Reducer.java @@ -39,14 +39,14 @@ import java.util.Iterator; *
      *
    1. * - *

      Shuffle

      + * Shuffle * *

      The Reducer copies the sorted output from each * {@link Mapper} using HTTP across the network.

      *
      2. * *
    2. - *

      Sort

      + * Sort * *

      The framework merge sorts Reducer inputs by * keys @@ -55,7 +55,7 @@ import java.util.Iterator; *

      The shuffle and sort phases occur simultaneously i.e. while outputs are * being fetched they are merged.

      * - *
      SecondarySort
      + * SecondarySort * *

      To achieve a secondary sort on the values returned by the value * iterator, the application should extend the key with the secondary @@ -83,10 +83,10 @@ import java.util.Iterator; *

      3. * *
    3. - *

      Reduce

      + * Reduce * *

      In this phase the - * {@link #reduce(Object, Iterable, Context)} + * {@link #reduce(Object, Iterable, org.apache.hadoop.mapreduce.Reducer.Context)} * method is called for each <key, (collection of values)> in * the sorted inputs.

      *

      The output of the reduce task is typically written to a @@ -113,7 +113,7 @@ import java.util.Iterator; * context.write(key, result); * } * } - *

      + * * * @see Mapper * @see Partitioner diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/filecache/DistributedCache.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/filecache/DistributedCache.java index 06737c99396..51fe69a7212 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/filecache/DistributedCache.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/filecache/DistributedCache.java @@ -115,7 +115,7 @@ import java.net.URI; * } * } * - *

      + * * * It is also very common to use the DistributedCache by using * {@link org.apache.hadoop.util.GenericOptionsParser}. @@ -235,7 +235,6 @@ public class DistributedCache { * DistributedCache and MapReduce code. * @param conf The configuration which stored the timestamps * @return a long array of timestamps - * @throws IOException * @deprecated Use {@link JobContext#getArchiveTimestamps()} instead */ @Deprecated @@ -250,7 +249,6 @@ public class DistributedCache { * DistributedCache and MapReduce code. * @param conf The configuration which stored the timestamps * @return a long array of timestamps - * @throws IOException * @deprecated Use {@link JobContext#getFileTimestamps()} instead */ @Deprecated @@ -434,7 +432,6 @@ public class DistributedCache { * internal DistributedCache and MapReduce code. * @param conf The configuration which stored the timestamps * @return a string array of booleans - * @throws IOException */ public static boolean[] getFileVisibilities(Configuration conf) { return parseBooleans(conf.getStrings(MRJobConfig.CACHE_FILE_VISIBILITIES)); diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/aggregate/ValueAggregatorJob.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/aggregate/ValueAggregatorJob.java index d8833da5255..de25f649062 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/aggregate/ValueAggregatorJob.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/aggregate/ValueAggregatorJob.java @@ -60,7 +60,7 @@ import org.apache.hadoop.util.GenericOptionsParser; * The developer using Aggregate will need only to provide a plugin class * conforming to the following interface: * - * public interface ValueAggregatorDescriptor { public ArrayList + * public interface ValueAggregatorDescriptor { public ArrayList<Entry> * generateKeyValPairs(Object key, Object value); public void * configure(Configuration conf); } * diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/Chain.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/Chain.java index 208616b66b5..1dad13e1536 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/Chain.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/Chain.java @@ -600,7 +600,7 @@ public class Chain { /** * Adds a Mapper class to the chain job. * - *

      + *

      * The configuration properties of the chain job have precedence over the * configuration properties of the Mapper. * @@ -738,7 +738,7 @@ public class Chain { /** * Sets the Reducer class to the chain job. * - *

      + *

      * The configuration properties of the chain job have precedence over the * configuration properties of the Reducer. * diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainMapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainMapper.java index c042ff0769c..c3bf0120153 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainMapper.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainMapper.java @@ -57,24 +57,24 @@ import org.apache.hadoop.mapreduce.lib.chain.Chain.ChainBlockingQueue; * ChainMapper, this is done by the addMapper for the last mapper in the chain. *

      * ChainMapper usage pattern: - *

      + *

      * * 

        * ...
  * Job = new Job(conf);
- * 
      
+ *
  * Configuration mapAConf = new Configuration(false);
  * ...
  * ChainMapper.addMapper(job, AMap.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, mapAConf);
- * 
      
+ *
  * Configuration mapBConf = new Configuration(false);
  * ...
  * ChainMapper.addMapper(job, BMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, mapBConf);
- * 
      
+ *
  * ...
- * 
      
+ *
  * job.waitForComplettion(true);
  * ...
  *
      diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainReducer.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainReducer.java index dc03d5d8cf6..1c375879052 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainReducer.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/chain/ChainReducer.java @@ -50,7 +50,7 @@ import java.io.IOException; * all Mappers and the Reduce in the chain use matching output and input key and * value classes as no conversion is done by the chaining code. *

      - *

      Using the ChainMapper and the ChainReducer classes is possible to + *

      Using the ChainMapper and the ChainReducer classes is possible to * compose Map/Reduce jobs that look like [MAP+ / REDUCE MAP*]. And * immediate benefit of this pattern is a dramatic reduction in disk IO.

      *

      @@ -59,26 +59,26 @@ import java.io.IOException; * element in the chain. *

      * ChainReducer usage pattern: - *

      + *

      * * 

        * ...
  * Job = new Job(conf);
  * ....
- * 
      
+ *
  * Configuration reduceConf = new Configuration(false);
  * ...
  * ChainReducer.setReducer(job, XReduce.class, LongWritable.class, Text.class,
  *   Text.class, Text.class, true, reduceConf);
- * 
      
+ *
  * ChainReducer.addMapper(job, CMap.class, Text.class, Text.class,
  *   LongWritable.class, Text.class, false, null);
- * 
      
+ *
  * ChainReducer.addMapper(job, DMap.class, LongWritable.class, Text.class,
  *   LongWritable.class, LongWritable.class, true, null);
- * 
      
+ *
  * ...
- * 
      
+ *
  * job.waitForCompletion(true);
  * ...
  *
      diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBInputFormat.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBInputFormat.java index a6953b7598a..78c3a0fd8e8 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBInputFormat.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBInputFormat.java @@ -319,7 +319,7 @@ public class DBInputFormat * Java object holding tuple fields. * @param tableName The table to read data from * @param conditions The condition which to select data with, - * eg. '(updated > 20070101 AND length > 0)' + * eg. '(updated > 20070101 AND length > 0)' * @param orderBy the fieldNames in the orderBy clause. * @param fieldNames The field names in the table * @see #setInput(Job, Class, String, String) diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBWritable.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBWritable.java index cc0d30a525b..5753a3b1cd3 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBWritable.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/db/DBWritable.java @@ -73,7 +73,7 @@ import org.apache.hadoop.io.Writable; * timestamp = resultSet.getLong(2); * } * } - *

      + * */ @InterfaceAudience.Public @InterfaceStability.Stable diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/join/TupleWritable.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/join/TupleWritable.java index af6b3f03588..2990ca99d36 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/join/TupleWritable.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/join/TupleWritable.java @@ -144,7 +144,7 @@ public class TupleWritable implements Writable, Iterable { /** * Convert Tuple to String as in the following. - * [,,...,] + * [<child1>,<child2>,...,<childn>] */ public String toString() { StringBuffer buf = new StringBuffer("["); diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/map/MultithreadedMapper.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/map/MultithreadedMapper.java index 814e4945123..733b18c9ec4 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/map/MultithreadedMapper.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/map/MultithreadedMapper.java @@ -44,15 +44,15 @@ import java.util.List; * Multithreaded implementation for @link org.apache.hadoop.mapreduce.Mapper. *

      * It can be used instead of the default implementation, - * @link org.apache.hadoop.mapred.MapRunner, when the Map operation is not CPU + * {@link org.apache.hadoop.mapred.MapRunner}, when the Map operation is not CPU * bound in order to improve throughput. *

      * Mapper implementations using this MapRunnable must be thread-safe. *

      * The Map-Reduce job has to be configured with the mapper to use via - * {@link #setMapperClass(Configuration, Class)} and + * {@link #setMapperClass(Job, Class)} and * the number of thread the thread-pool can use with the - * {@link #getNumberOfThreads(Configuration) method. The default + * {@link #getNumberOfThreads(JobContext)} method. The default * value is 10 threads. *

      */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/FileOutputFormat.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/FileOutputFormat.java index fa3708e7948..2c6954275f2 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/FileOutputFormat.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/FileOutputFormat.java @@ -181,7 +181,7 @@ public static final String OUTDIR = "mapreduce.output.fileoutputformat.outputdir * Get the {@link Path} to the task's temporary output directory * for the map-reduce job * - *

      Tasks' Side-Effect Files

      + * Tasks' Side-Effect Files * *

      Some applications need to create/write-to side-files, which differ from * the actual job-outputs. diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java index 24baa596b31..c31cab7ddd8 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/output/MultipleOutputs.java @@ -81,7 +81,7 @@ import java.util.*; *

      * Usage in Reducer: * 

      - *  String generateFileName(K k, V v) {
+ * <K, V> String generateFileName(K k, V v) {
  *   return k.toString() + "_" + v.toString();
  * }
  * 
@@ -124,16 +124,16 @@ import java.util.*;
  * 
      
  * 
  * 
      - * private MultipleOutputs out;
+ * private MultipleOutputs<Text, Text> out;
  * 
  * public void setup(Context context) {
- *   out = new MultipleOutputs(context);
+ *   out = new MultipleOutputs<Text, Text>(context);
  *   ...
  * }
  * 
- * public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
+ * public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
  * for (Text t : values) {
- *   out.write(key, t, generateFileName(<parameter list...>));
+ *   out.write(key, t, generateFileName(<parameter list...>));
  *   }
  * }
  * 
@@ -294,7 +294,6 @@ public class MultipleOutputs {
 
   /**
    * Adds a named output for the job.
-   * 
      
    *
    * @param job               job to add the named output
    * @param namedOutput       named output name, it has to be a word, letters
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/BinaryPartitioner.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/BinaryPartitioner.java
index 4a408409244..2a89908119f 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/BinaryPartitioner.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/partition/BinaryPartitioner.java
@@ -64,7 +64,7 @@ import org.apache.hadoop.mapreduce.Partitioner;
  *   
    4. {@link #setOffsets}
      5. 
  *   
    5. {@link #setLeftOffset}
      6. 
  *   
    6. {@link #setRightOffset}
      7. 
- * 
      
+ * 
  */
 @InterfaceAudience.Public
 @InterfaceStability.Evolving
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/JobContextImpl.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/JobContextImpl.java
index 247c2f2029b..b9014ef7861 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/JobContextImpl.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/task/JobContextImpl.java
@@ -374,7 +374,6 @@ public class JobContextImpl implements JobContext {
    * Get the timestamps of the archives.  Used by internal
    * DistributedCache and MapReduce code.
    * @return a string array of timestamps 
-   * @throws IOException
    */
   public String[] getArchiveTimestamps() {
     return toTimestampStrs(DistributedCache.getArchiveTimestamps(conf));
@@ -384,7 +383,6 @@ public class JobContextImpl implements JobContext {
    * Get the timestamps of the files.  Used by internal
    * DistributedCache and MapReduce code.
    * @return a string array of timestamps 
-   * @throws IOException
    */
   public String[] getFileTimestamps() {
     return toTimestampStrs(DistributedCache.getFileTimestamps(conf));
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomTextWriter.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomTextWriter.java
index 40e101ab8fd..6cb3211e1fa 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomTextWriter.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomTextWriter.java
@@ -42,7 +42,7 @@ import org.apache.hadoop.util.ToolRunner;
  * random sequence of words.
  * In order for this program to generate data for terasort with a 5-10 words
  * per key and 20-100 words per value, have the following config:
- * 
+ * <pre>{@code
  * <?xml version="1.0"?>
  * <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
  * <configuration>
@@ -66,7 +66,7 @@ import org.apache.hadoop.util.ToolRunner;
  *     <name>mapreduce.randomtextwriter.totalbytes</name>
  *     <value>1099511627776</value>
  *   </property>
- * </configuration>
+ * }
      
  * 
  * Equivalently, {@link RandomTextWriter} also supports all the above options
  * and ones supported by {@link Tool} via the command-line.
diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomWriter.java b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomWriter.java
index a326c8ca2be..67c9ca8f0f3 100644
--- a/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomWriter.java
+++ b/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapreduce/RandomWriter.java
@@ -47,7 +47,7 @@ import org.apache.hadoop.util.ToolRunner;
  * random binary sequence file of BytesWritable.
  * In order for this program to generate data for terasort with 10-byte keys
  * and 90-byte values, have the following config:
- * 
+ * <pre>{@code
  * <?xml version="1.0"?>
  * <?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
  * <configuration>
@@ -71,8 +71,7 @@ import org.apache.hadoop.util.ToolRunner;
  *     <name>mapreduce.randomwriter.totalbytes</name>
  *     <value>1099511627776</value>
  *   </property>
- * </configuration>
- * 
+ * }
      * Equivalently, {@link RandomWriter} also supports all the above options * and ones supported by {@link GenericOptionsParser} via the command-line. */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/MultiFileWordCount.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/MultiFileWordCount.java index d3df4b303d0..b51946eb105 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/MultiFileWordCount.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/MultiFileWordCount.java @@ -199,7 +199,7 @@ public class MultiFileWordCount extends Configured implements Tool { } /** - * This Mapper is similar to the one in {@link WordCount.MapClass}. + * This Mapper is similar to the one in {@link WordCount.TokenizerMapper}. */ public static class MapClass extends Mapper { diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/QuasiMonteCarlo.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/QuasiMonteCarlo.java index d565098e0a1..25dee6bf5ff 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/QuasiMonteCarlo.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/QuasiMonteCarlo.java @@ -50,7 +50,7 @@ import org.apache.hadoop.util.ToolRunner; * where $S=[0,1)^2$ is a unit square, * $x=(x_1,x_2)$ is a 2-dimensional point, * and $f$ is a function describing the inscribed circle of the square $S$, - * $f(x)=1$ if $(2x_1-1)^2+(2x_2-1)^2 <= 1$ and $f(x)=0$, otherwise. + * $f(x)=1$ if $(2x_1-1)^2+(2x_2-1)^2 <= 1$ and $f(x)=0$, otherwise. * It is easy to see that Pi is equal to $4I$. * So an approximation of Pi is obtained once $I$ is evaluated numerically. * @@ -155,7 +155,7 @@ public class QuasiMonteCarlo extends Configured implements Tool { /** Map method. * @param offset samples starting from the (offset+1)th sample. * @param size the number of samples for this map - * @param context output {ture->numInside, false->numOutside} + * @param context output {ture->numInside, false->numOutside} */ public void map(LongWritable offset, LongWritable size, diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomTextWriter.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomTextWriter.java index 4d555c606d3..6309ee67e59 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomTextWriter.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomTextWriter.java @@ -42,7 +42,7 @@ import org.apache.hadoop.util.ToolRunner; * random sequence of words. * In order for this program to generate data for terasort with a 5-10 words * per key and 20-100 words per value, have the following config: - * + * <pre>{@code * <?xml version="1.0"?> * <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> * <configuration> @@ -66,7 +66,7 @@ import org.apache.hadoop.util.ToolRunner; * <name>mapreduce.randomtextwriter.totalbytes</name> * <value>1099511627776</value> * </property> - * </configuration> + * } * * Equivalently, {@link RandomTextWriter} also supports all the above options * and ones supported by {@link Tool} via the command-line. diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomWriter.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomWriter.java index e1c13ecfa27..8f322b154ee 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomWriter.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/RandomWriter.java @@ -47,7 +47,7 @@ import org.apache.hadoop.util.ToolRunner; * random binary sequence file of BytesWritable. * In order for this program to generate data for terasort with 10-byte keys * and 90-byte values, have the following config: - * + * <pre>{@code * <?xml version="1.0"?> * <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> * <configuration> @@ -71,8 +71,7 @@ import org.apache.hadoop.util.ToolRunner; * <name>mapreduce.randomwriter.totalbytes</name> * <value>1099511627776</value> * </property> - * </configuration> - * + * } * Equivalently, {@link RandomWriter} also supports all the above options * and ones supported by {@link GenericOptionsParser} via the command-line. */ diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/SecondarySort.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/SecondarySort.java index d536ec98c11..8841fdcfbb2 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/SecondarySort.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/SecondarySort.java @@ -74,7 +74,7 @@ public class SecondarySort { } /** * Read the two integers. - * Encoded as: MIN_VALUE -> 0, 0 -> -MIN_VALUE, MAX_VALUE-> -1 + * Encoded as: MIN_VALUE -> 0, 0 -> -MIN_VALUE, MAX_VALUE-> -1 */ @Override public void readFields(DataInput in) throws IOException { diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/DistBbp.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/DistBbp.java index 4484d20d2c9..268066cb848 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/DistBbp.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/DistBbp.java @@ -35,7 +35,7 @@ import org.apache.hadoop.util.ToolRunner; * A map/reduce program that uses a BBP-type method to compute exact * binary digits of Pi. * This program is designed for computing the n th bit of Pi, - * for large n, say n >= 10^8. + * for large n, say n >= 10^8. * For computing lower bits of Pi, consider using bbp. * * The actually computation is done by DistSum jobs. diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/math/Modular.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/math/Modular.java index 58f859d5352..1c039a2fea1 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/math/Modular.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/pi/math/Modular.java @@ -78,7 +78,7 @@ public class Modular { return x >= 1? x - 1: x < 0? x + 1: x; } - /** Given 0 < x < y, + /** Given 0 < x < y, * return x^(-1) mod y. */ public static long modInverse(final long x, final long y) { diff --git a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/terasort/GenSort.java b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/terasort/GenSort.java index 94f9baaf89b..beb07439fae 100644 --- a/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/terasort/GenSort.java +++ b/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples/terasort/GenSort.java @@ -28,7 +28,7 @@ import org.apache.hadoop.util.PureJavaCrc32; /** * A single process data generator for the terasort data. Based on gensort.c - * version 1.1 (3 Mar 2009) from Chris Nyberg . + * version 1.1 (3 Mar 2009) from Chris Nyberg <chris.nyberg@ordinal.com>. */ public class GenSort { diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/CopyListing.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/CopyListing.java index ab5b8024d72..a7b68a98a26 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/CopyListing.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/CopyListing.java @@ -38,10 +38,10 @@ import com.google.common.collect.Sets; /** * The CopyListing abstraction is responsible for how the list of * sources and targets is constructed, for DistCp's copy function. - * The copy-listing should be a SequenceFile, - * located at the path specified to buildListing(), - * each entry being a pair of (Source relative path, source file status), - * all the paths being fully qualified. + * The copy-listing should be a + * SequenceFile<Text, CopyListingFileStatus>, located at the path + * specified to buildListing(), each entry being a pair of (Source relative + * path, source file status), all the paths being fully qualified. */ public abstract class CopyListing extends Configured { @@ -95,8 +95,8 @@ public abstract class CopyListing extends Configured { * Validate input and output paths * * @param options - Input options - * @throws InvalidInputException: If inputs are invalid - * @throws IOException: any Exception with FS + * @throws InvalidInputException If inputs are invalid + * @throws IOException any Exception with FS */ protected abstract void validatePaths(DistCpOptions options) throws IOException, InvalidInputException; @@ -105,7 +105,7 @@ public abstract class CopyListing extends Configured { * The interface to be implemented by sub-classes, to create the source/target file listing. * @param pathToListFile Path on HDFS where the listing file is written. * @param options Input Options for DistCp (indicating source/target paths.) - * @throws IOException: Thrown on failure to create the listing file. + * @throws IOException Thrown on failure to create the listing file. */ protected abstract void doBuildListing(Path pathToListFile, DistCpOptions options) throws IOException; diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCp.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCp.java index d202f0a9bdf..28535a70016 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCp.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCp.java @@ -76,7 +76,7 @@ public class DistCp extends Configured implements Tool { * (E.g. source-paths, target-location, etc.) * @param inputOptions Options (indicating source-paths, target-location.) * @param configuration The Hadoop configuration against which the Copy-mapper must run. - * @throws Exception, on failure. + * @throws Exception */ public DistCp(Configuration configuration, DistCpOptions inputOptions) throws Exception { Configuration config = new Configuration(configuration); @@ -142,7 +142,7 @@ public class DistCp extends Configured implements Tool { * Implements the core-execution. Creates the file-list for copy, * and launches the Hadoop-job, to do the copy. * @return Job handle - * @throws Exception, on failure. + * @throws Exception */ public Job execute() throws Exception { assert inputOptions != null; diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCpOptionSwitch.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCpOptionSwitch.java index d263f8273dc..159d5ca16cc 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCpOptionSwitch.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/DistCpOptionSwitch.java @@ -105,7 +105,7 @@ public enum DistCpOptionSwitch { * Copy all the source files and commit them atomically to the target * This is typically useful in cases where there is a process * polling for availability of a file/dir. This option is incompatible - * with SYNC_FOLDERS & DELETE_MISSING + * with SYNC_FOLDERS and DELETE_MISSING */ ATOMIC_COMMIT(DistCpConstants.CONF_LABEL_ATOMIC_COPY, new Option("atomic", false, "Commit all changes or none")), diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/OptionsParser.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/OptionsParser.java index 4bbc30dea29..525136cbb27 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/OptionsParser.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/OptionsParser.java @@ -63,7 +63,7 @@ public class OptionsParser { * @param args Command-line arguments (excluding the options consumed * by the GenericOptionsParser). * @return The Options object, corresponding to the specified command-line. - * @throws IllegalArgumentException: Thrown if the parse fails. + * @throws IllegalArgumentException Thrown if the parse fails. */ public static DistCpOptions parse(String args[]) throws IllegalArgumentException { diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyCommitter.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyCommitter.java index 197edd91c32..d5fdd7fe80d 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyCommitter.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyCommitter.java @@ -70,7 +70,7 @@ public class CopyCommitter extends FileOutputCommitter { this.taskAttemptContext = context; } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public void commitJob(JobContext jobContext) throws IOException { Configuration conf = jobContext.getConfiguration(); @@ -102,7 +102,7 @@ public class CopyCommitter extends FileOutputCommitter { } } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public void abortJob(JobContext jobContext, JobStatus.State state) throws IOException { diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyMapper.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyMapper.java index ab57127ed78..cca36df67f5 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyMapper.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyMapper.java @@ -45,7 +45,7 @@ import org.apache.hadoop.util.StringUtils; /** * Mapper class that executes the DistCp copy operation. - * Implements the o.a.h.mapreduce.Mapper<> interface. + * Implements the o.a.h.mapreduce.Mapper interface. */ public class CopyMapper extends Mapper { @@ -182,10 +182,11 @@ public class CopyMapper extends Mapper } /** - * Implementation of the Mapper<>::map(). Does the copy. + * Implementation of the Mapper::map(). Does the copy. * @param relPath The target path. * @param sourceFileStatus The source path. * @throws IOException + * @throws InterruptedException */ @Override public void map(Text relPath, CopyListingFileStatus sourceFileStatus, diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyOutputFormat.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyOutputFormat.java index eb43aa3927b..a5bd605a8ef 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyOutputFormat.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/CopyOutputFormat.java @@ -97,13 +97,13 @@ public class CopyOutputFormat extends TextOutputFormat { } } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public OutputCommitter getOutputCommitter(TaskAttemptContext context) throws IOException { return new CopyCommitter(getOutputPath(context), context); } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public void checkOutputSpecs(JobContext context) throws IOException { Configuration conf = context.getConfiguration(); diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/RetriableFileCopyCommand.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/RetriableFileCopyCommand.java index 1d6115685e5..65d644bfefa 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/RetriableFileCopyCommand.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/RetriableFileCopyCommand.java @@ -84,8 +84,7 @@ public class RetriableFileCopyCommand extends RetriableCommand { * This is the actual copy-implementation. * @param arguments Argument-list to the command. * @return Number of bytes copied. - * @throws Exception: CopyReadException, if there are read-failures. All other - * failures are IOExceptions. + * @throws Exception */ @SuppressWarnings("unchecked") @Override diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/UniformSizeInputFormat.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/UniformSizeInputFormat.java index 4add0bb4690..8dc7a659856 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/UniformSizeInputFormat.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/UniformSizeInputFormat.java @@ -38,7 +38,7 @@ import java.util.List; import java.util.ArrayList; /** - * UniformSizeInputFormat extends the InputFormat<> class, to produce + * UniformSizeInputFormat extends the InputFormat class, to produce * input-splits for DistCp. * It looks at the copy-listing and groups the contents into input-splits such * that the total-number of bytes to be copied for each input split is @@ -55,7 +55,7 @@ public class UniformSizeInputFormat * approximately equal. * @param context JobContext for the job. * @return The list of uniformly-distributed input-splits. - * @throws IOException: On failure. + * @throws IOException * @throws InterruptedException */ @Override diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicInputFormat.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicInputFormat.java index f5303d54c5c..38269c755fe 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicInputFormat.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicInputFormat.java @@ -64,7 +64,7 @@ public class DynamicInputFormat extends InputFormat { * tasks. * @param jobContext JobContext for the map job. * @return The list of (empty) dynamic input-splits. - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -343,7 +343,7 @@ public class DynamicInputFormat extends InputFormat { * @param inputSplit The split for which the RecordReader is required. * @param taskAttemptContext TaskAttemptContext for the current attempt. * @return DynamicRecordReader instance. - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicRecordReader.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicRecordReader.java index 40d75f44713..00b3c69de3d 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicRecordReader.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/mapred/lib/DynamicRecordReader.java @@ -57,7 +57,7 @@ public class DynamicRecordReader extends RecordReader { * RecordReader to read from chunks. * @param inputSplit The InputSplit for the map. Ignored entirely. * @param taskAttemptContext The AttemptContext. - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -88,7 +88,7 @@ public class DynamicRecordReader extends RecordReader { * been completely exhausted, an new chunk is acquired and read, * transparently. * @return True, if the nextValue() could be traversed to. False, otherwise. - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -130,7 +130,7 @@ public class DynamicRecordReader extends RecordReader { /** * Implementation of RecordReader::getCurrentKey(). * @return The key of the current record. (i.e. the source-path.) - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -142,7 +142,7 @@ public class DynamicRecordReader extends RecordReader { /** * Implementation of RecordReader::getCurrentValue(). * @return The value of the current record. (i.e. the target-path.) - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -154,7 +154,7 @@ public class DynamicRecordReader extends RecordReader { /** * Implementation of RecordReader::getProgress(). * @return A fraction [0.0,1.0] indicating the progress of a DistCp mapper. - * @throws IOException, on failure. + * @throws IOException * @throws InterruptedException */ @Override @@ -192,7 +192,7 @@ public class DynamicRecordReader extends RecordReader { /** * Implementation of RecordReader::close(). * Closes the RecordReader. - * @throws IOException, on failure. + * @throws IOException */ @Override public void close() diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/DistCpUtils.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/DistCpUtils.java index ca7566b0f14..20fdf112e1c 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/DistCpUtils.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/DistCpUtils.java @@ -65,7 +65,7 @@ public class DistCpUtils { * @param path The path of the file whose size is sought. * @param configuration Configuration, to retrieve the appropriate FileSystem. * @return The file-size, in number of bytes. - * @throws IOException, on failure. + * @throws IOException */ public static long getFileSize(Path path, Configuration configuration) throws IOException { diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/RetriableCommand.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/RetriableCommand.java index 563372e0097..c27b2e1758e 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/RetriableCommand.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/RetriableCommand.java @@ -77,7 +77,7 @@ public abstract class RetriableCommand { * 2. the command may no longer be retried (e.g. runs out of retry-attempts). * @param arguments The list of arguments for the command. * @return Generic "Object" from doExecute(), on success. - * @throws IOException, IOException, on complete failure. + * @throws Exception */ public Object execute(Object... arguments) throws Exception { Exception latestException; diff --git a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/ThrottledInputStream.java b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/ThrottledInputStream.java index d08a3012e27..9e435d99afd 100644 --- a/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/ThrottledInputStream.java +++ b/hadoop-tools/hadoop-distcp/src/main/java/org/apache/hadoop/tools/util/ThrottledInputStream.java @@ -62,7 +62,7 @@ public class ThrottledInputStream extends InputStream { rawStream.close(); } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public int read() throws IOException { throttle(); @@ -73,7 +73,7 @@ public class ThrottledInputStream extends InputStream { return data; } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public int read(byte[] b) throws IOException { throttle(); @@ -84,7 +84,7 @@ public class ThrottledInputStream extends InputStream { return readLen; } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public int read(byte[] b, int off, int len) throws IOException { throttle(); @@ -155,7 +155,7 @@ public class ThrottledInputStream extends InputStream { return totalSleepTime; } - /** @inheritDoc */ + /** {@inheritDoc} */ @Override public String toString() { return "ThrottledInputStream{" + diff --git a/hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/Logalyzer.java b/hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/Logalyzer.java index 050bfbe2a20..449ecbf9129 100644 --- a/hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/Logalyzer.java +++ b/hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/Logalyzer.java @@ -60,7 +60,9 @@ import org.apache.hadoop.mapreduce.lib.map.RegexMapper; * b) Directory on dfs to archive the logs. * c) The sort/grep patterns for analyzing the files and separator for boundaries. * Usage: - * Logalyzer -archive -archiveDir -analysis -logs -grep -sort -separator + * Logalyzer -archive -archiveDir <directory to archive logs> -analysis + * <directory> -logs <log-list uri> -grep <pattern> -sort + * <col1, col2> -separator <separator> *

      */ diff --git a/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/emulators/resourceusage/ResourceUsageEmulatorPlugin.java b/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/emulators/resourceusage/ResourceUsageEmulatorPlugin.java index 593c1a462bf..7a80e8df6c8 100644 --- a/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/emulators/resourceusage/ResourceUsageEmulatorPlugin.java +++ b/hadoop-tools/hadoop-gridmix/src/main/java/org/apache/hadoop/mapred/gridmix/emulators/resourceusage/ResourceUsageEmulatorPlugin.java @@ -35,7 +35,7 @@ import org.apache.hadoop.conf.Configuration; * {@link ResourceUsageEmulatorPlugin} is also configured with a feedback module * i.e a {@link ResourceCalculatorPlugin}, to monitor the current resource * usage. {@link ResourceUsageMetrics} decides the final resource usage value to - * emulate. {@link Progressive} keeps track of the task's progress.

      + * emulate. {@link Progressive} keeps track of the task's progress. * *

      * diff --git a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/RestClientBindings.java b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/RestClientBindings.java index 25a7e9373d4..d11c369bb2c 100644 --- a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/RestClientBindings.java +++ b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/RestClientBindings.java @@ -31,10 +31,10 @@ import static org.apache.hadoop.fs.swift.http.SwiftProtocolConstants.*; /** * This class implements the binding logic between Hadoop configurations * and the swift rest client. - *

      + *

      * The swift rest client takes a Properties instance containing * the string values it uses to bind to a swift endpoint. - *

      + *

      * This class extracts the values for a specific filesystem endpoint * and then builds an appropriate Properties file. */ @@ -188,7 +188,7 @@ public final class RestClientBindings { /** * Copy a (trimmed) property from the configuration file to the properties file. - *

      + *

      * If marked as required and not found in the configuration, an * exception is raised. * If not required -and missing- then the property will not be set. diff --git a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/SwiftRestClient.java b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/SwiftRestClient.java index 28f8b47f4ac..55dad111242 100644 --- a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/SwiftRestClient.java +++ b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/http/SwiftRestClient.java @@ -1061,10 +1061,9 @@ public final class SwiftRestClient { * Authenticate to Openstack Keystone * As well as returning the access token, the member fields {@link #token}, * {@link #endpointURI} and {@link #objectLocationURI} are set up for re-use. - *

      + *

      * This method is re-entrant -if more than one thread attempts to authenticate * neither will block -but the field values with have those of the last caller. - *

      * * @return authenticated access token */ @@ -1575,6 +1574,7 @@ public final class SwiftRestClient { * @param path path to object * @param endpointURI damain url e.g. http://domain.com * @return valid URI for object + * @throws SwiftException */ public static URI pathToURI(SwiftObjectPath path, URI endpointURI) throws SwiftException { @@ -1820,7 +1820,7 @@ public final class SwiftRestClient { /** * Get the blocksize of this filesystem - * @return a blocksize >0 + * @return a blocksize > 0 */ public long getBlocksizeKB() { return blocksizeKB; diff --git a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystem.java b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystem.java index b70f7efef58..27a572fd842 100644 --- a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystem.java +++ b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystem.java @@ -225,10 +225,10 @@ public class SwiftNativeFileSystem extends FileSystem { * Return an array containing hostnames, offset and size of * portions of the given file. For a nonexistent * file or regions, null will be returned. - *

      + *

      * This call is most helpful with DFS, where it returns * hostnames of machines that contain the given file. - *

      + *

      * The FileSystem will simply return an elt containing 'localhost'. */ @Override @@ -645,7 +645,7 @@ public class SwiftNativeFileSystem extends FileSystem { /** * Low level method to do a deep listing of all entries, not stopping * at the next directory entry. This is to let tests be confident that - * recursive deletes &c really are working. + * recursive deletes really are working. * @param path path to recurse down * @param newest ask for the newest data, potentially slower than not. * @return a potentially empty array of file status diff --git a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystemStore.java b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystemStore.java index 0138eae412d..6d812a0e6ea 100644 --- a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystemStore.java +++ b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/snative/SwiftNativeFileSystemStore.java @@ -518,7 +518,7 @@ public class SwiftNativeFileSystemStore { * Rename through copy-and-delete. this is a consequence of the * Swift filesystem using the path as the hash * into the Distributed Hash Table, "the ring" of filenames. - *

      + *

      * Because of the nature of the operation, it is not atomic. * * @param src source file/dir @@ -847,7 +847,7 @@ public class SwiftNativeFileSystemStore { } /** - * Insert a throttled wait if the throttle delay >0 + * Insert a throttled wait if the throttle delay > 0 * @throws InterruptedIOException if interrupted during sleep */ public void throttle() throws InterruptedIOException { @@ -878,7 +878,7 @@ public class SwiftNativeFileSystemStore { * raised. This lets the caller distinguish a file not found with * other reasons for failure, so handles race conditions in recursive * directory deletes better. - *

      + *

      * The problem being addressed is: caller A requests a recursive directory * of directory /dir ; caller B requests a delete of a file /dir/file, * between caller A enumerating the files contents, and requesting a delete diff --git a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/util/SwiftTestUtils.java b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/util/SwiftTestUtils.java index c9e26acf3d4..01ec739eda8 100644 --- a/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/util/SwiftTestUtils.java +++ b/hadoop-tools/hadoop-openstack/src/main/java/org/apache/hadoop/fs/swift/util/SwiftTestUtils.java @@ -236,7 +236,7 @@ public class SwiftTestUtils extends org.junit.Assert { /** * Convert a byte to a character for printing. If the - * byte value is < 32 -and hence unprintable- the byte is + * byte value is < 32 -and hence unprintable- the byte is * returned as a two digit hex value * @param b byte * @return the printable character string diff --git a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/InputDemuxer.java b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/InputDemuxer.java index cd99e1ce989..0927a771d3b 100644 --- a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/InputDemuxer.java +++ b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/InputDemuxer.java @@ -45,12 +45,12 @@ public interface InputDemuxer extends Closeable { public void bindTo(Path path, Configuration conf) throws IOException; /** - * Get the next pair. The name should preserve the original job + * Get the next <name, input> pair. The name should preserve the original job * history file or job conf file name. The input object should be closed * before calling getNext() again. The old input object would be invalid after * calling getNext() again. * - * @return the next pair. + * @return the next <name, input> pair. */ public Pair getNext() throws IOException; } diff --git a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/datatypes/util/MapReduceJobPropertiesParser.java b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/datatypes/util/MapReduceJobPropertiesParser.java index c2537bec398..7547eca2319 100644 --- a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/datatypes/util/MapReduceJobPropertiesParser.java +++ b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/datatypes/util/MapReduceJobPropertiesParser.java @@ -67,8 +67,9 @@ import org.apache.log4j.Logger; * ignoring user-specific and hard-to-parse keys but also provides a consistent * view for all possible inputs. So if users invoke the * {@link #parseJobProperty(String, String)} API with either - * <"mapreduce.job.user.name", "bob"> or <"user.name", "bob">, then the result - * would be a {@link UserName} {@link DataType} wrapping the user-name "bob". + * <"mapreduce.job.user.name", "bob"> or <"user.name", "bob">, + * then the result would be a {@link UserName} {@link DataType} wrapping + * the user-name "bob". */ @SuppressWarnings("deprecation") public class MapReduceJobPropertiesParser implements JobPropertyParser { diff --git a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/package-info.java b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/package-info.java index b88b37e2c2e..22532252348 100644 --- a/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/package-info.java +++ b/hadoop-tools/hadoop-rumen/src/main/java/org/apache/hadoop/tools/rumen/package-info.java @@ -41,7 +41,7 @@ * String conf_filename = .. // assume the job configuration filename here * * // construct a list of interesting properties - * List interestedProperties = new ArrayList(); + * List<String> interestedProperties = new ArrayList<String>(); * interestedProperties.add("mapreduce.job.name"); * * JobConfigurationParser jcp = @@ -154,7 +154,7 @@ * TopologyBuilder tb = new TopologyBuilder(); * * // construct a list of interesting properties - * List interestingProperties = new ArrayList(); + * List<String> interestingProperties = new ArrayList%lt;String>(); * // add the interesting properties here * interestingProperties.add("mapreduce.job.name"); * @@ -207,7 +207,7 @@ * JobBuilder jb = new JobBuilder(jobID); * * // construct a list of interesting properties - * List interestingProperties = new ArrayList(); + * List<String> interestingProperties = new ArrayList%lt;String>(); * // add the interesting properties here * interestingProperties.add("mapreduce.job.name"); * @@ -269,7 +269,7 @@ * TopologyBuilder tb = new TopologyBuilder(); * * // construct a list of interesting properties - * List interestingProperties = new ArrayList(); + * List<String> interestingProperties = new ArrayList%lt;String>(); * // add the interesting properties here * interestingProperties.add("mapreduce.job.name"); *