You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-commits@hadoop.apache.org by sh...@apache.org on 2011/12/12 06:45:09 UTC
svn commit: r1213146 [2/3] -
/hadoop/common/trunk/hadoop-mapreduce-project/lib/jdiff/hadoop-mapred_0.22.0.xml
Added: hadoop/common/trunk/hadoop-mapreduce-project/lib/jdiff/hadoop-mapred_0.22.0.xml
URL: http://svn.apache.org/viewvc/hadoop/common/trunk/hadoop-mapreduce-project/lib/jdiff/hadoop-mapred_0.22.0.xml?rev=1213146&view=auto
==============================================================================
--- hadoop/common/trunk/hadoop-mapreduce-project/lib/jdiff/hadoop-mapred_0.22.0.xml (added)
+++ hadoop/common/trunk/hadoop-mapreduce-project/lib/jdiff/hadoop-mapred_0.22.0.xml Mon Dec 12 05:45:08 2011
@@ -0,0 +1,31740 @@
+<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
+<!-- Generated by the JDiff Javadoc doclet -->
+<!-- (http://www.jdiff.org) -->
+<!-- on Sun Dec 04 01:04:32 UTC 2011 -->
+
+<api
+ xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'
+ xsi:noNamespaceSchemaLocation='api.xsd'
+ name="hadoop-mapred 0.22.0"
+ jdversion="1.0.9">
+
+<!-- Command line arguments = -doclet org.apache.hadoop.classification.tools.ExcludePrivateAnnotationsJDiffDoclet -docletpath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/common/hadoop-common-0.22.0-SNAPSHOT.jar:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/jdiff/jdiff-1.0.9.jar:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/ivy/lib/Hadoop/jdiff/xerces-1.4.4.jar -classpath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/build/classes:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/conf:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-common/jars/hadoop-common-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/commons-cli/commons-cli/jars/commons-cli-1.2.jar:/home/jenkins/.ivy2/cache/xmlenc/xmlenc/jars/xmlenc-0.52.jar:/home/jenkins/.ivy2/cache/commons-codec/commons-codec/jars/commons-codec-1.4.jar:/home/jenkins/.ivy2/cac
he/commons-logging/commons-logging/jars/commons-logging-1.1.1.jar:/home/jenkins/.ivy2/cache/org.slf4j/slf4j-api/jars/slf4j-api-1.6.1.jar:/home/jenkins/.ivy2/cache/org.slf4j/slf4j-log4j12/jars/slf4j-log4j12-1.6.1.jar:/home/jenkins/.ivy2/cache/log4j/log4j/bundles/log4j-1.2.16.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jetty/jars/jetty-6.1.26.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jetty-util/jars/jetty-util-6.1.26.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/servlet-api/jars/servlet-api-2.5-20081211.jar:/home/jenkins/.ivy2/cache/tomcat/jasper-runtime/jars/jasper-runtime-5.5.12.jar:/home/jenkins/.ivy2/cache/tomcat/jasper-compiler/jars/jasper-compiler-5.5.12.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jsp-2.1-jetty/jars/jsp-2.1-jetty-6.1.26.jar:/home/jenkins/.ivy2/cache/org.eclipse.jdt/core/jars/core-3.1.1.jar:/home/jenkins/.ivy2/cache/org.mortbay.jetty/jsp-api-2.1-glassfish/jars/jsp-api-2.1-glassfish-2.1.v20091210.jar:/home/jenkins/.ivy2/cache/org.mortbay.je
tty/jsp-2.1-glassfish/jars/jsp-2.1-glassfish-2.1.v20091210.jar:/home/jenkins/.ivy2/cache/org.eclipse.jdt.core.compiler/ecj/jars/ecj-3.5.1.jar:/home/jenkins/.ivy2/cache/commons-el/commons-el/jars/commons-el-1.0.jar:/home/jenkins/.ivy2/cache/net.java.dev.jets3t/jets3t/jars/jets3t-0.7.1.jar:/home/jenkins/.ivy2/cache/commons-httpclient/commons-httpclient/jars/commons-httpclient-3.1.jar:/home/jenkins/.ivy2/cache/commons-net/commons-net/jars/commons-net-1.4.1.jar:/home/jenkins/.ivy2/cache/oro/oro/jars/oro-2.0.8.jar:/home/jenkins/.ivy2/cache/net.sf.kosmosfs/kfs/jars/kfs-0.3.jar:/home/jenkins/.ivy2/cache/junit/junit/jars/junit-4.8.1.jar:/home/jenkins/.ivy2/cache/hsqldb/hsqldb/jars/hsqldb-1.8.0.10.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro/jars/avro-1.5.3.jar:/home/jenkins/.ivy2/cache/org.codehaus.jackson/jackson-mapper-asl/jars/jackson-mapper-asl-1.7.3.jar:/home/jenkins/.ivy2/cache/org.codehaus.jackson/jackson-core-asl/jars/jackson-core-asl-1.7.3.jar:/home/jenkins/.ivy2/cach
e/com.thoughtworks.paranamer/paranamer/jars/paranamer-2.3.jar:/home/jenkins/.ivy2/cache/org.xerial.snappy/snappy-java/bundles/snappy-java-1.0.3.2.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro-ipc/jars/avro-ipc-1.5.3.jar:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-common-test/jars/hadoop-common-test-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/org.apache.hadoop/hadoop-hdfs/jars/hadoop-hdfs-0.22.0-SNAPSHOT.jar:/home/jenkins/.ivy2/cache/com.google.guava/guava/jars/guava-r09.jar:/home/jenkins/.ivy2/cache/org.apache.avro/avro-compiler/jars/avro-compiler-1.5.3.jar:/home/jenkins/.ivy2/cache/commons-lang/commons-lang/jars/commons-lang-2.5.jar:/home/jenkins/.ivy2/cache/org.apache.velocity/velocity/jars/velocity-1.6.4.jar:/home/jenkins/.ivy2/cache/commons-collections/commons-collections/jars/commons-collections-3.2.1.jar:/home/jenkins/.ivy2/cache/org.aspectj/aspectjrt/jars/aspectjrt-1.6.5.jar:/home/jenkins/.ivy2/cache/org.aspectj/aspectjtools/jars/aspectjtools-1.6.5.jar:/
home/jenkins/.ivy2/cache/jdiff/jdiff/jars/jdiff-1.0.9.jar:/home/jenkins/.ivy2/cache/xerces/xerces/jars/xerces-1.4.4.jar:/home/jenkins/tools/ant/latest/lib/ant-launcher.jar:/usr/share/java/xmlParserAPIs.jar:/usr/share/java/xercesImpl.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-resolver.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-bcel.jar:/home/jenkins/tools/ant/latest/lib/ant-jsch.jar:/home/jenkins/tools/ant/latest/lib/ant-jmf.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-oro.jar:/home/jenkins/tools/ant/latest/lib/ant-netrexx.jar:/home/jenkins/tools/ant/latest/lib/ant-testutil.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-xalan2.jar:/home/jenkins/tools/ant/latest/lib/ant-javamail.jar:/home/jenkins/tools/ant/latest/lib/ant.jar:/home/jenkins/tools/ant/latest/lib/ant-junit.jar:/home/jenkins/tools/ant/latest/lib/ant-swing.jar:/home/jenkins/tools/ant/latest/lib/ant-commons-net.jar:/home/jenkins/tools/ant/latest/lib/ant-jdepend.jar:/home/jenkins/tools/ant/latest
/lib/ant-junit4.jar:/home/jenkins/tools/ant/latest/lib/ant-commons-logging.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-bsf.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-log4j.jar:/home/jenkins/tools/ant/latest/lib/ant-jai.jar:/home/jenkins/tools/ant/latest/lib/ant-apache-regexp.jar:/home/jenkins/tools/ant/latest/lib/ant-antlr.jar:/tmp/jdk1.6.0_29/lib/tools.jar -sourcepath /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/src/java:/x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/src/tools -apidir /x1/jenkins/jenkins-slave/workspace/Hadoop-22-Build/common/mapreduce/lib/jdiff -apiname hadoop-mapred 0.22.0 -->
+<package name="org.apache.hadoop.filecache">
+ <!-- start class org.apache.hadoop.filecache.DistributedCache -->
+ <class name="DistributedCache" extends="org.apache.hadoop.mapreduce.filecache.DistributedCache"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use methods on {@link Job}.">
+ <constructor name="DistributedCache"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <doc>
+ <![CDATA[Distribute application-specific large, read-only files efficiently.
+
+ <p><code>DistributedCache</code> is a facility provided by the Map-Reduce
+ framework to cache files (text, archives, jars etc.) needed by applications.
+ </p>
+
+ <p>Applications specify the files, via urls (hdfs:// or http://) to be cached
+ via the {@link org.apache.hadoop.mapred.JobConf}. The
+ <code>DistributedCache</code> assumes that the files specified via urls are
+ already present on the {@link FileSystem} at the path specified by the url
+ and are accessible by every machine in the cluster.</p>
+
+ <p>The framework will copy the necessary files on to the slave node before
+ any tasks for the job are executed on that node. Its efficiency stems from
+ the fact that the files are only copied once per job and the ability to
+ cache archives which are un-archived on the slaves.</p>
+
+ <p><code>DistributedCache</code> can be used to distribute simple, read-only
+ data/text files and/or more complex types such as archives, jars etc.
+ Archives (zip, tar and tgz/tar.gz files) are un-archived at the slave nodes.
+ Jars may be optionally added to the classpath of the tasks, a rudimentary
+ software distribution mechanism. Files have execution permissions.
+ Optionally users can also direct it to symlink the distributed cache file(s)
+ into the working directory of the task.</p>
+
+ <p><code>DistributedCache</code> tracks modification timestamps of the cache
+ files. Clearly the cache files should not be modified by the application
+ or externally while the job is executing.</p>
+
+ <p>Here is an illustrative example on how to use the
+ <code>DistributedCache</code>:</p>
+ <p><blockquote><pre>
+ // Setting up the cache for the application
+
+ 1. Copy the requisite files to the <code>FileSystem</code>:
+
+ $ bin/hadoop fs -copyFromLocal lookup.dat /myapp/lookup.dat
+ $ bin/hadoop fs -copyFromLocal map.zip /myapp/map.zip
+ $ bin/hadoop fs -copyFromLocal mylib.jar /myapp/mylib.jar
+ $ bin/hadoop fs -copyFromLocal mytar.tar /myapp/mytar.tar
+ $ bin/hadoop fs -copyFromLocal mytgz.tgz /myapp/mytgz.tgz
+ $ bin/hadoop fs -copyFromLocal mytargz.tar.gz /myapp/mytargz.tar.gz
+
+ 2. Setup the application's <code>JobConf</code>:
+
+ JobConf job = new JobConf();
+ DistributedCache.addCacheFile(new URI("/myapp/lookup.dat#lookup.dat"),
+ job);
+ DistributedCache.addCacheArchive(new URI("/myapp/map.zip", job);
+ DistributedCache.addFileToClassPath(new Path("/myapp/mylib.jar"), job);
+ DistributedCache.addCacheArchive(new URI("/myapp/mytar.tar", job);
+ DistributedCache.addCacheArchive(new URI("/myapp/mytgz.tgz", job);
+ DistributedCache.addCacheArchive(new URI("/myapp/mytargz.tar.gz", job);
+
+ 3. Use the cached files in the {@link org.apache.hadoop.mapred.Mapper}
+ or {@link org.apache.hadoop.mapred.Reducer}:
+
+ public static class MapClass extends MapReduceBase
+ implements Mapper<K, V, K, V> {
+
+ private Path[] localArchives;
+ private Path[] localFiles;
+
+ public void configure(JobConf job) {
+ // Get the cached archives/files
+ localArchives = DistributedCache.getLocalCacheArchives(job);
+ localFiles = DistributedCache.getLocalCacheFiles(job);
+ }
+
+ public void map(K key, V value,
+ OutputCollector<K, V> output, Reporter reporter)
+ throws IOException {
+ // Use data from the cached archives/files here
+ // ...
+ // ...
+ output.collect(k, v);
+ }
+ }
+
+ </pre></blockquote></p>
+
+ It is also very common to use the DistributedCache by using
+ {@link org.apache.hadoop.util.GenericOptionsParser}.
+
+ This class includes methods that should be used by users
+ (specifically those mentioned in the example above, as well
+ as {@link DistributedCache#addArchiveToClassPath(Path, Configuration)}),
+ as well as methods intended for use by the MapReduce framework
+ (e.g., {@link org.apache.hadoop.mapred.JobClient}). For implementation
+ details, see {@link TrackerDistributedCacheManager} and
+ {@link TaskDistributedCacheManager}.
+
+ @see org.apache.hadoop.mapred.JobConf
+ @see org.apache.hadoop.mapred.JobClient
+ @see org.apache.hadoop.mapreduce.Job
+ @deprecated Use methods on {@link Job}.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.filecache.DistributedCache -->
+</package>
+<package name="org.apache.hadoop.mapred">
+ <!-- start class org.apache.hadoop.mapred.ClusterStatus -->
+ <class name="ClusterStatus" extends="java.lang.Object"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link ClusterMetrics} or {@link TaskTrackerInfo} instead">
+ <implements name="org.apache.hadoop.io.Writable"/>
+ <method name="getTaskTrackers" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the number of task trackers in the cluster.
+
+ @return the number of task trackers in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getActiveTrackerNames" return="java.util.Collection"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the names of task trackers in the cluster.
+
+ @return the active task trackers in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getBlacklistedTrackerNames" return="java.util.Collection"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the names of task trackers in the cluster.
+
+ @return the blacklisted task trackers in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getBlacklistedTrackers" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the number of blacklisted task trackers in the cluster.
+
+ @return the number of blacklisted task trackers in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getNumExcludedNodes" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the number of excluded hosts in the cluster.
+ @return the number of excluded hosts in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getTTExpiryInterval" return="long"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the tasktracker expiry interval for the cluster
+ @return the expiry interval in msec]]>
+ </doc>
+ </method>
+ <method name="getMapTasks" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the number of currently running map tasks in the cluster.
+
+ @return the number of currently running map tasks in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getReduceTasks" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the number of currently running reduce tasks in the cluster.
+
+ @return the number of currently running reduce tasks in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getMaxMapTasks" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the maximum capacity for running map tasks in the cluster.
+
+ @return the maximum capacity for running map tasks in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getMaxReduceTasks" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the maximum capacity for running reduce tasks in the cluster.
+
+ @return the maximum capacity for running reduce tasks in the cluster.]]>
+ </doc>
+ </method>
+ <method name="getJobTrackerState" return="org.apache.hadoop.mapred.JobTracker.State"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link #getJobTrackerStatus()} instead.">
+ <doc>
+ <![CDATA[Get the current state of the <code>JobTracker</code>,
+ as {@link JobTracker.State}
+
+ @return the current state of the <code>JobTracker</code>.
+ @deprecated Use {@link #getJobTrackerStatus()} instead.]]>
+ </doc>
+ </method>
+ <method name="getJobTrackerStatus" return="org.apache.hadoop.mapreduce.Cluster.JobTrackerStatus"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the JobTracker's status.
+
+ @return {@link JobTrackerStatus} of the JobTracker]]>
+ </doc>
+ </method>
+ <method name="getBlackListedTrackersInfo" return="java.util.Collection"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Gets the list of blacklisted trackers along with reasons for blacklisting.
+
+ @return the collection of {@link BlackListInfo} objects.]]>
+ </doc>
+ </method>
+ <method name="write"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="out" type="java.io.DataOutput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="readFields"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="in" type="java.io.DataInput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <doc>
+ <![CDATA[Status information on the current state of the Map-Reduce cluster.
+
+ <p><code>ClusterStatus</code> provides clients with information such as:
+ <ol>
+ <li>
+ Size of the cluster.
+ </li>
+ <li>
+ Name of the trackers.
+ </li>
+ <li>
+ Task capacity of the cluster.
+ </li>
+ <li>
+ The number of currently running map & reduce tasks.
+ </li>
+ <li>
+ State of the <code>JobTracker</code>.
+ </li>
+ <li>
+ Details regarding black listed trackers.
+ </li>
+ </ol></p>
+
+ <p>Clients can query for the latest <code>ClusterStatus</code>, via
+ {@link JobClient#getClusterStatus()}.</p>
+
+ @see JobClient
+ @deprecated Use {@link ClusterMetrics} or {@link TaskTrackerInfo} instead]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.ClusterStatus -->
+ <!-- start class org.apache.hadoop.mapred.ClusterStatus.BlackListInfo -->
+ <class name="ClusterStatus.BlackListInfo" extends="java.lang.Object"
+ abstract="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <implements name="org.apache.hadoop.io.Writable"/>
+ <method name="getTrackerName" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Gets the blacklisted tasktracker's name.
+
+ @return tracker's name.]]>
+ </doc>
+ </method>
+ <method name="getReasonForBlackListing" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Gets the reason for which the tasktracker was blacklisted.
+
+ @return reason which tracker was blacklisted]]>
+ </doc>
+ </method>
+ <method name="getBlackListReport" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Gets a descriptive report about why the tasktracker was blacklisted.
+
+ @return report describing why the tasktracker was blacklisted.]]>
+ </doc>
+ </method>
+ <method name="readFields"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="in" type="java.io.DataInput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="write"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="out" type="java.io.DataOutput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="toString" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <doc>
+ <![CDATA[Class which encapsulates information about a blacklisted tasktracker.
+
+ The information includes the tasktracker's name and reasons for
+ getting blacklisted. The toString method of the class will print
+ the information in a whitespace separated fashion to enable parsing.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.ClusterStatus.BlackListInfo -->
+ <!-- start class org.apache.hadoop.mapred.Counters -->
+ <class name="Counters" extends="java.lang.Object"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link org.apache.hadoop.mapreduce.Counters} instead.">
+ <implements name="org.apache.hadoop.io.Writable"/>
+ <implements name="java.lang.Iterable"/>
+ <constructor name="Counters"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="getGroupNames" return="java.util.Collection"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns the names of all counter classes.
+ @return Set of counter names.]]>
+ </doc>
+ </method>
+ <method name="iterator" return="java.util.Iterator"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <method name="getGroup" return="org.apache.hadoop.mapred.Counters.Group"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="groupName" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Returns the named counter group, or an empty group if there is none
+ with the specified name.]]>
+ </doc>
+ </method>
+ <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="key" type="java.lang.Enum"/>
+ <doc>
+ <![CDATA[Find the counter for the given enum. The same enum will always return the
+ same counter.
+ @param key the counter key
+ @return the matching counter object]]>
+ </doc>
+ </method>
+ <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="group" type="java.lang.String"/>
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Find a counter given the group and the name.
+ @param group the name of the group
+ @param name the internal name of the counter
+ @return the counter for that name]]>
+ </doc>
+ </method>
+ <method name="findCounter" return="org.apache.hadoop.mapred.Counters.Counter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="deprecated, no comment">
+ <param name="group" type="java.lang.String"/>
+ <param name="id" type="int"/>
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Find a counter by using strings
+ @param group the name of the group
+ @param id the id of the counter within the group (0 to N-1)
+ @param name the internal name of the counter
+ @return the counter for that name
+ @deprecated]]>
+ </doc>
+ </method>
+ <method name="incrCounter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="key" type="java.lang.Enum"/>
+ <param name="amount" type="long"/>
+ <doc>
+ <![CDATA[Increments the specified counter by the specified amount, creating it if
+ it didn't already exist.
+ @param key identifies a counter
+ @param amount amount by which counter is to be incremented]]>
+ </doc>
+ </method>
+ <method name="incrCounter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="group" type="java.lang.String"/>
+ <param name="counter" type="java.lang.String"/>
+ <param name="amount" type="long"/>
+ <doc>
+ <![CDATA[Increments the specified counter by the specified amount, creating it if
+ it didn't already exist.
+ @param group the name of the group
+ @param counter the internal name of the counter
+ @param amount amount by which counter is to be incremented]]>
+ </doc>
+ </method>
+ <method name="getCounter" return="long"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="key" type="java.lang.Enum"/>
+ <doc>
+ <![CDATA[Returns current value of the specified counter, or 0 if the counter
+ does not exist.]]>
+ </doc>
+ </method>
+ <method name="incrAllCounters"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="other" type="org.apache.hadoop.mapred.Counters"/>
+ <doc>
+ <![CDATA[Increments multiple counters by their amounts in another Counters
+ instance.
+ @param other the other Counters instance]]>
+ </doc>
+ </method>
+ <method name="sum" return="org.apache.hadoop.mapred.Counters"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="a" type="org.apache.hadoop.mapred.Counters"/>
+ <param name="b" type="org.apache.hadoop.mapred.Counters"/>
+ <doc>
+ <![CDATA[Convenience method for computing the sum of two sets of counters.]]>
+ </doc>
+ </method>
+ <method name="size" return="int"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns the total number of counters, by summing the number of counters
+ in each group.]]>
+ </doc>
+ </method>
+ <method name="write"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="out" type="java.io.DataOutput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Write the set of groups.
+ The external format is:
+ #groups (groupName group)*
+
+ i.e. the number of groups followed by 0 or more groups, where each
+ group is of the form:
+
+ groupDisplayName #counters (false | true counter)*
+
+ where each counter is of the form:
+
+ name (false | true displayName) value]]>
+ </doc>
+ </method>
+ <method name="readFields"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="in" type="java.io.DataInput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Read a set of groups.]]>
+ </doc>
+ </method>
+ <method name="log"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="log" type="org.apache.commons.logging.Log"/>
+ <doc>
+ <![CDATA[Logs the current counter values.
+ @param log The log to use.]]>
+ </doc>
+ </method>
+ <method name="toString" return="java.lang.String"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Return textual representation of the counter values.]]>
+ </doc>
+ </method>
+ <method name="makeCompactString" return="java.lang.String"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Convert a counters object into a single line that is easy to parse.
+ @return the string with "name=value" for each counter and separated by ","]]>
+ </doc>
+ </method>
+ <method name="makeEscapedCompactString" return="java.lang.String"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Represent the counter in a textual format that can be converted back to
+ its object form
+ @return the string in the following format
+ {(groupname)(group-displayname)[(countername)(displayname)(value)][][]}{}{}]]>
+ </doc>
+ </method>
+ <method name="fromEscapedCompactString" return="org.apache.hadoop.mapred.Counters"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="compactString" type="java.lang.String"/>
+ <exception name="ParseException" type="java.text.ParseException"/>
+ <doc>
+ <![CDATA[Convert a stringified counter representation into a counter object. Note
+ that the counter can be recovered if its stringified using
+ {@link #makeEscapedCompactString()}.
+ @return a Counter]]>
+ </doc>
+ </method>
+ <method name="hashCode" return="int"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <method name="equals" return="boolean"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="obj" type="java.lang.Object"/>
+ </method>
+ <doc>
+ <![CDATA[A set of named counters.
+
+ <p><code>Counters</code> represent global counters, defined either by the
+ Map-Reduce framework or applications. Each <code>Counter</code> can be of
+ any {@link Enum} type.</p>
+
+ <p><code>Counters</code> are bunched into {@link Group}s, each comprising of
+ counters from a particular <code>Enum</code> class.
+ @deprecated Use {@link org.apache.hadoop.mapreduce.Counters} instead.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.Counters -->
+ <!-- start class org.apache.hadoop.mapred.Counters.Counter -->
+ <class name="Counters.Counter" extends="org.apache.hadoop.mapreduce.Counter"
+ abstract="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <method name="setDisplayName"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="newName" type="java.lang.String"/>
+ </method>
+ <method name="makeEscapedCompactString" return="java.lang.String"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns the compact stringified version of the counter in the format
+ [(actual-name)(display-name)(value)]]]>
+ </doc>
+ </method>
+ <method name="getCounter" return="long"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[What is the current value of this counter?
+ @return the current value]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[A counter record, comprising its name and value.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.Counters.Counter -->
+ <!-- start class org.apache.hadoop.mapred.Counters.Group -->
+ <class name="Counters.Group" extends="java.lang.Object"
+ abstract="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <implements name="org.apache.hadoop.io.Writable"/>
+ <implements name="java.lang.Iterable"/>
+ <method name="getName" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns raw name of the group. This is the name of the enum class
+ for this group of counters.]]>
+ </doc>
+ </method>
+ <method name="getDisplayName" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns localized name of the group. This is the same as getName() by
+ default, but different if an appropriate ResourceBundle is found.]]>
+ </doc>
+ </method>
+ <method name="setDisplayName"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="displayName" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Set the display name]]>
+ </doc>
+ </method>
+ <method name="makeEscapedCompactString" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns the compact stringified version of the group in the format
+ {(actual-name)(display-name)(value)[][][]} where [] are compact strings for the
+ counters within.]]>
+ </doc>
+ </method>
+ <method name="hashCode" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <method name="equals" return="boolean"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="obj" type="java.lang.Object"/>
+ <doc>
+ <![CDATA[Checks for (content) equality of Groups]]>
+ </doc>
+ </method>
+ <method name="getCounter" return="long"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="counterName" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Returns the value of the specified counter, or 0 if the counter does
+ not exist.]]>
+ </doc>
+ </method>
+ <method name="getCounter" return="org.apache.hadoop.mapred.Counters.Counter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="use {@link #getCounter(String)} instead">
+ <param name="id" type="int"/>
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Get the counter for the given id and create it if it doesn't exist.
+ @param id the numeric id of the counter within the group
+ @param name the internal counter name
+ @return the counter
+ @deprecated use {@link #getCounter(String)} instead]]>
+ </doc>
+ </method>
+ <method name="getCounterForName" return="org.apache.hadoop.mapred.Counters.Counter"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Get the counter for the given name and create it if it doesn't exist.
+ @param name the internal counter name
+ @return the counter]]>
+ </doc>
+ </method>
+ <method name="size" return="int"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Returns the number of counters in this group.]]>
+ </doc>
+ </method>
+ <method name="write"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="out" type="java.io.DataOutput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="readFields"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="in" type="java.io.DataInput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="iterator" return="java.util.Iterator"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <doc>
+ <![CDATA[<code>Group</code> of counters, comprising of counters from a particular
+ counter {@link Enum} class.
+
+ <p><code>Group</code>handles localization of the class name and the
+ counter names.</p>]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.Counters.Group -->
+ <!-- start class org.apache.hadoop.mapred.FileAlreadyExistsException -->
+ <class name="FileAlreadyExistsException" extends="java.io.IOException"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="FileAlreadyExistsException"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <constructor name="FileAlreadyExistsException" type="java.lang.String"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <doc>
+ <![CDATA[Used when target file already exists for any operation and
+ is not configured to be overwritten.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.FileAlreadyExistsException -->
+ <!-- start class org.apache.hadoop.mapred.FileInputFormat -->
+ <class name="FileInputFormat" extends="java.lang.Object"
+ abstract="true"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
+ instead.">
+ <implements name="org.apache.hadoop.mapred.InputFormat"/>
+ <constructor name="FileInputFormat"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="setMinSplitSize"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="minSplitSize" type="long"/>
+ </method>
+ <method name="isSplitable" return="boolean"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
+ <param name="filename" type="org.apache.hadoop.fs.Path"/>
+ <doc>
+ <![CDATA[Is the given filename splitable? Usually, true, but if the file is
+ stream compressed, it will not be.
+
+ <code>FileInputFormat</code> implementations can override this and return
+ <code>false</code> to ensure that individual input files are never split-up
+ so that {@link Mapper}s process entire files.
+
+ @param fs the file system that the file is on
+ @param filename the file name to check
+ @return is this file splitable?]]>
+ </doc>
+ </method>
+ <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
+ abstract="true" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="setInputPathFilter"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="filter" type="java.lang.Class"/>
+ <doc>
+ <![CDATA[Set a PathFilter to be applied to the input paths for the map-reduce job.
+
+ @param filter the PathFilter class use for filtering the input paths.]]>
+ </doc>
+ </method>
+ <method name="getInputPathFilter" return="org.apache.hadoop.fs.PathFilter"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <doc>
+ <![CDATA[Get a PathFilter instance of the filter set for the input paths.
+
+ @return the PathFilter instance set for the job, NULL if none has been set.]]>
+ </doc>
+ </method>
+ <method name="addInputPathRecursively"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="result" type="java.util.List"/>
+ <param name="fs" type="org.apache.hadoop.fs.FileSystem"/>
+ <param name="path" type="org.apache.hadoop.fs.Path"/>
+ <param name="inputFilter" type="org.apache.hadoop.fs.PathFilter"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Add files in the input path recursively into the results.
+ @param result
+ The List to store all files.
+ @param fs
+ The FileSystem.
+ @param path
+ The input path.
+ @param inputFilter
+ The input filter that can be used to filter files/dirs.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="listStatus" return="org.apache.hadoop.fs.FileStatus[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[List input directories.
+ Subclasses may override to, e.g., select only files matching a regular
+ expression.
+
+ @param job the job to list input paths for
+ @return array of FileStatus objects
+ @throws IOException if zero items.]]>
+ </doc>
+ </method>
+ <method name="makeSplit" return="org.apache.hadoop.mapred.FileSplit"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="file" type="org.apache.hadoop.fs.Path"/>
+ <param name="start" type="long"/>
+ <param name="length" type="long"/>
+ <param name="hosts" type="java.lang.String[]"/>
+ <doc>
+ <![CDATA[A factory that makes the split for this class. It can be overridden
+ by sub-classes to make sub-types]]>
+ </doc>
+ </method>
+ <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="numSplits" type="int"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Splits files returned by {@link #listStatus(JobConf)} when
+ they're too big.]]>
+ </doc>
+ </method>
+ <method name="computeSplitSize" return="long"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="goalSize" type="long"/>
+ <param name="minSize" type="long"/>
+ <param name="blockSize" type="long"/>
+ </method>
+ <method name="getBlockIndex" return="int"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/>
+ <param name="offset" type="long"/>
+ </method>
+ <method name="setInputPaths"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="commaSeparatedPaths" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Sets the given comma separated paths as the list of inputs
+ for the map-reduce job.
+
+ @param conf Configuration of the job
+ @param commaSeparatedPaths Comma separated paths to be set as
+ the list of inputs for the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="addInputPaths"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="commaSeparatedPaths" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Add the given comma separated paths to the list of inputs for
+ the map-reduce job.
+
+ @param conf The configuration of the job
+ @param commaSeparatedPaths Comma separated paths to be added to
+ the list of inputs for the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="setInputPaths"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="inputPaths" type="org.apache.hadoop.fs.Path[]"/>
+ <doc>
+ <![CDATA[Set the array of {@link Path}s as the list of inputs
+ for the map-reduce job.
+
+ @param conf Configuration of the job.
+ @param inputPaths the {@link Path}s of the input directories/files
+ for the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="addInputPath"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="path" type="org.apache.hadoop.fs.Path"/>
+ <doc>
+ <![CDATA[Add a {@link Path} to the list of inputs for the map-reduce job.
+
+ @param conf The configuration of the job
+ @param path {@link Path} to be added to the list of inputs for
+ the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="getInputPaths" return="org.apache.hadoop.fs.Path[]"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <doc>
+ <![CDATA[Get the list of input {@link Path}s for the map-reduce job.
+
+ @param conf The configuration of the job
+ @return the list of input {@link Path}s for the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="getSplitHosts" return="java.lang.String[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ <param name="blkLocations" type="org.apache.hadoop.fs.BlockLocation[]"/>
+ <param name="offset" type="long"/>
+ <param name="splitSize" type="long"/>
+ <param name="clusterMap" type="org.apache.hadoop.net.NetworkTopology"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[This function identifies and returns the hosts that contribute
+ most for a given split. For calculating the contribution, rack
+ locality is treated on par with host locality, so hosts from racks
+ that contribute the most are preferred over hosts on racks that
+ contribute less
+ @param blkLocations The list of block locations
+ @param offset
+ @param splitSize
+ @return array of hosts that contribute most to this split
+ @throws IOException]]>
+ </doc>
+ </method>
+ <field name="LOG" type="org.apache.commons.logging.Log"
+ transient="false" volatile="false"
+ static="true" final="true" visibility="public"
+ deprecated="not deprecated">
+ </field>
+ <field name="NUM_INPUT_FILES" type="java.lang.String"
+ transient="false" volatile="false"
+ static="true" final="true" visibility="public"
+ deprecated="not deprecated">
+ </field>
+ <doc>
+ <![CDATA[A base class for file-based {@link InputFormat}.
+
+ <p><code>FileInputFormat</code> is the base class for all file-based
+ <code>InputFormat</code>s. This provides a generic implementation of
+ {@link #getSplits(JobConf, int)}.
+ Subclasses of <code>FileInputFormat</code> can also override the
+ {@link #isSplitable(FileSystem, Path)} method to ensure input-files are
+ not split-up and are processed as a whole by {@link Mapper}s.
+ @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileInputFormat}
+ instead.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.FileInputFormat -->
+ <!-- start class org.apache.hadoop.mapred.FileOutputCommitter -->
+ <class name="FileOutputCommitter" extends="org.apache.hadoop.mapred.OutputCommitter"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="FileOutputCommitter"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="setupJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="commitJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="cleanupJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="abortJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.JobContext"/>
+ <param name="runState" type="int"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="setupTask"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="commitTask"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="abortTask"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="needsTaskCommit" return="boolean"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="context" type="org.apache.hadoop.mapred.TaskAttemptContext"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <field name="LOG" type="org.apache.commons.logging.Log"
+ transient="false" volatile="false"
+ static="true" final="true" visibility="public"
+ deprecated="not deprecated">
+ </field>
+ <field name="TEMP_DIR_NAME" type="java.lang.String"
+ transient="false" volatile="false"
+ static="true" final="true" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Temporary directory name]]>
+ </doc>
+ </field>
+ <field name="SUCCEEDED_FILE_NAME" type="java.lang.String"
+ transient="false" volatile="false"
+ static="true" final="true" visibility="public"
+ deprecated="not deprecated">
+ </field>
+ <doc>
+ <![CDATA[An {@link OutputCommitter} that commits files specified
+ in job output directory i.e. ${mapreduce.output.fileoutputformat.outputdir}.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.FileOutputCommitter -->
+ <!-- start class org.apache.hadoop.mapred.FileOutputFormat -->
+ <class name="FileOutputFormat" extends="java.lang.Object"
+ abstract="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <implements name="org.apache.hadoop.mapred.OutputFormat"/>
+ <constructor name="FileOutputFormat"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="setCompressOutput"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="compress" type="boolean"/>
+ <doc>
+ <![CDATA[Set whether the output of the job is compressed.
+ @param conf the {@link JobConf} to modify
+ @param compress should the output of the job be compressed?]]>
+ </doc>
+ </method>
+ <method name="getCompressOutput" return="boolean"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <doc>
+ <![CDATA[Is the job output compressed?
+ @param conf the {@link JobConf} to look in
+ @return <code>true</code> if the job output should be compressed,
+ <code>false</code> otherwise]]>
+ </doc>
+ </method>
+ <method name="setOutputCompressorClass"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="codecClass" type="java.lang.Class"/>
+ <doc>
+ <![CDATA[Set the {@link CompressionCodec} to be used to compress job outputs.
+ @param conf the {@link JobConf} to modify
+ @param codecClass the {@link CompressionCodec} to be used to
+ compress the job outputs]]>
+ </doc>
+ </method>
+ <method name="getOutputCompressorClass" return="java.lang.Class"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="defaultValue" type="java.lang.Class"/>
+ <doc>
+ <![CDATA[Get the {@link CompressionCodec} for compressing the job outputs.
+ @param conf the {@link JobConf} to look in
+ @param defaultValue the {@link CompressionCodec} to return if not set
+ @return the {@link CompressionCodec} to be used to compress the
+ job outputs
+ @throws IllegalArgumentException if the class was specified, but not found]]>
+ </doc>
+ </method>
+ <method name="getRecordWriter" return="org.apache.hadoop.mapred.RecordWriter"
+ abstract="true" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="name" type="java.lang.String"/>
+ <param name="progress" type="org.apache.hadoop.util.Progressable"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="checkOutputSpecs"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="ignored" type="org.apache.hadoop.fs.FileSystem"/>
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <exception name="FileAlreadyExistsException" type="org.apache.hadoop.mapred.FileAlreadyExistsException"/>
+ <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="setOutputPath"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="outputDir" type="org.apache.hadoop.fs.Path"/>
+ <doc>
+ <![CDATA[Set the {@link Path} of the output directory for the map-reduce job.
+
+ @param conf The configuration of the job.
+ @param outputDir the {@link Path} of the output directory for
+ the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="getOutputPath" return="org.apache.hadoop.fs.Path"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <doc>
+ <![CDATA[Get the {@link Path} to the output directory for the map-reduce job.
+
+ @return the {@link Path} to the output directory for the map-reduce job.
+ @see FileOutputFormat#getWorkOutputPath(JobConf)]]>
+ </doc>
+ </method>
+ <method name="getWorkOutputPath" return="org.apache.hadoop.fs.Path"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <doc>
+ <![CDATA[Get the {@link Path} to the task's temporary output directory
+ for the map-reduce job
+
+ <h4 id="SideEffectFiles">Tasks' Side-Effect Files</h4>
+
+ <p><i>Note:</i> The following is valid only if the {@link OutputCommitter}
+ is {@link FileOutputCommitter}. If <code>OutputCommitter</code> is not
+ a <code>FileOutputCommitter</code>, the task's temporary output
+ directory is same as {@link #getOutputPath(JobConf)} i.e.
+ <tt>${mapreduce.output.fileoutputformat.outputdir}$</tt></p>
+
+ <p>Some applications need to create/write-to side-files, which differ from
+ the actual job-outputs.
+
+ <p>In such cases there could be issues with 2 instances of the same TIP
+ (running simultaneously e.g. speculative tasks) trying to open/write-to the
+ same file (path) on HDFS. Hence the application-writer will have to pick
+ unique names per task-attempt (e.g. using the attemptid, say
+ <tt>attempt_200709221812_0001_m_000000_0</tt>), not just per TIP.</p>
+
+ <p>To get around this the Map-Reduce framework helps the application-writer
+ out by maintaining a special
+ <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt>
+ sub-directory for each task-attempt on HDFS where the output of the
+ task-attempt goes. On successful completion of the task-attempt the files
+ in the <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_${taskid}</tt> (only)
+ are <i>promoted</i> to <tt>${mapreduce.output.fileoutputformat.outputdir}</tt>. Of course, the
+ framework discards the sub-directory of unsuccessful task-attempts. This
+ is completely transparent to the application.</p>
+
+ <p>The application-writer can take advantage of this by creating any
+ side-files required in <tt>${mapreduce.task.output.dir}</tt> during execution
+ of his reduce-task i.e. via {@link #getWorkOutputPath(JobConf)}, and the
+ framework will move them out similarly - thus she doesn't have to pick
+ unique paths per task-attempt.</p>
+
+ <p><i>Note</i>: the value of <tt>${mapreduce.task.output.dir}</tt> during
+ execution of a particular task-attempt is actually
+ <tt>${mapreduce.output.fileoutputformat.outputdir}/_temporary/_{$taskid}</tt>, and this value is
+ set by the map-reduce framework. So, just create any side-files in the
+ path returned by {@link #getWorkOutputPath(JobConf)} from map/reduce
+ task to take advantage of this feature.</p>
+
+ <p>The entire discussion holds true for maps of jobs with
+ reducer=NONE (i.e. 0 reduces) since output of the map, in that case,
+ goes directly to HDFS.</p>
+
+ @return the {@link Path} to the task's temporary output directory
+ for the map-reduce job.]]>
+ </doc>
+ </method>
+ <method name="getTaskOutputPath" return="org.apache.hadoop.fs.Path"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="name" type="java.lang.String"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Helper function to create the task's temporary output directory and
+ return the path to the task's output file.
+
+ @param conf job-configuration
+ @param name temporary task-output filename
+ @return path to the task's temporary output file
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="getUniqueName" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Helper function to generate a name that is unique for the task.
+
+ <p>The generated name can be used to create custom files from within the
+ different tasks for the job, the names for different tasks will not collide
+ with each other.</p>
+
+ <p>The given name is postfixed with the task type, 'm' for maps, 'r' for
+ reduces and the task partition number. For example, give a name 'test'
+ running on the first map o the job the generated name will be
+ 'test-m-00000'.</p>
+
+ @param conf the configuration for the job.
+ @param name the name to make unique.
+ @return a unique name accross all tasks of the job.]]>
+ </doc>
+ </method>
+ <method name="getPathForCustomFile" return="org.apache.hadoop.fs.Path"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="name" type="java.lang.String"/>
+ <doc>
+ <![CDATA[Helper function to generate a {@link Path} for a file that is unique for
+ the task within the job output directory.
+
+ <p>The path can be used to create custom files from within the map and
+ reduce tasks. The path name will be unique for each task. The path parent
+ will be the job output directory.</p>ls
+
+ <p>This method uses the {@link #getUniqueName} method to make the file name
+ unique for the task.</p>
+
+ @param conf the configuration for the job.
+ @param name the name for the file.
+ @return a unique path accross all tasks of the job.]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[A base class for {@link OutputFormat}.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.FileOutputFormat -->
+ <!-- start class org.apache.hadoop.mapred.FileSplit -->
+ <class name="FileSplit" extends="org.apache.hadoop.mapreduce.InputSplit"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
+ instead.">
+ <implements name="org.apache.hadoop.mapred.InputSplit"/>
+ <constructor name="FileSplit"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ </constructor>
+ <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, org.apache.hadoop.mapred.JobConf"
+ static="false" final="false" visibility="public"
+ deprecated="deprecated, no comment">
+ <doc>
+ <![CDATA[Constructs a split.
+ @deprecated
+ @param file the file name
+ @param start the position of the first byte in the file to process
+ @param length the number of bytes in the file to process]]>
+ </doc>
+ </constructor>
+ <constructor name="FileSplit" type="org.apache.hadoop.fs.Path, long, long, java.lang.String[]"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Constructs a split with host information
+
+ @param file the file name
+ @param start the position of the first byte in the file to process
+ @param length the number of bytes in the file to process
+ @param hosts the list of hosts containing the block, possibly null]]>
+ </doc>
+ </constructor>
+ <constructor name="FileSplit" type="org.apache.hadoop.mapreduce.lib.input.FileSplit"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="getPath" return="org.apache.hadoop.fs.Path"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[The file containing this split's data.]]>
+ </doc>
+ </method>
+ <method name="getStart" return="long"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[The position of the first byte in the file to process.]]>
+ </doc>
+ </method>
+ <method name="getLength" return="long"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[The number of bytes in the file to process.]]>
+ </doc>
+ </method>
+ <method name="toString" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </method>
+ <method name="write"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="out" type="java.io.DataOutput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="readFields"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="in" type="java.io.DataInput"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <method name="getLocations" return="java.lang.String[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ </method>
+ <doc>
+ <![CDATA[A section of an input file. Returned by {@link
+ InputFormat#getSplits(JobConf, int)} and passed to
+ {@link InputFormat#getRecordReader(InputSplit,JobConf,Reporter)}.
+ @deprecated Use {@link org.apache.hadoop.mapreduce.lib.input.FileSplit}
+ instead.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.FileSplit -->
+ <!-- start class org.apache.hadoop.mapred.ID -->
+ <class name="ID" extends="org.apache.hadoop.mapreduce.ID"
+ abstract="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="ID" type="int"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[constructs an ID object from the given int]]>
+ </doc>
+ </constructor>
+ <constructor name="ID"
+ static="false" final="false" visibility="protected"
+ deprecated="not deprecated">
+ </constructor>
+ <doc>
+ <![CDATA[A general identifier, which internally stores the id
+ as an integer. This is the super class of {@link JobID},
+ {@link TaskID} and {@link TaskAttemptID}.
+
+ @see JobID
+ @see TaskID
+ @see TaskAttemptID]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.ID -->
+ <!-- start interface org.apache.hadoop.mapred.InputFormat -->
+ <interface name="InputFormat" abstract="true"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.">
+ <method name="getSplits" return="org.apache.hadoop.mapred.InputSplit[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="numSplits" type="int"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Logically split the set of input files for the job.
+
+ <p>Each {@link InputSplit} is then assigned to an individual {@link Mapper}
+ for processing.</p>
+
+ <p><i>Note</i>: The split is a <i>logical</i> split of the inputs and the
+ input files are not physically split into chunks. For e.g. a split could
+ be <i><input-file-path, start, offset></i> tuple.
+
+ @param job job configuration.
+ @param numSplits the desired number of splits, a hint.
+ @return an array of {@link InputSplit}s for the job.]]>
+ </doc>
+ </method>
+ <method name="getRecordReader" return="org.apache.hadoop.mapred.RecordReader"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="split" type="org.apache.hadoop.mapred.InputSplit"/>
+ <param name="job" type="org.apache.hadoop.mapred.JobConf"/>
+ <param name="reporter" type="org.apache.hadoop.mapred.Reporter"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get the {@link RecordReader} for the given {@link InputSplit}.
+
+ <p>It is the responsibility of the <code>RecordReader</code> to respect
+ record boundaries while processing the logical split to present a
+ record-oriented view to the individual task.</p>
+
+ @param split the {@link InputSplit}
+ @param job the job that this split belongs to
+ @return a {@link RecordReader}]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[<code>InputFormat</code> describes the input-specification for a
+ Map-Reduce job.
+
+ <p>The Map-Reduce framework relies on the <code>InputFormat</code> of the
+ job to:<p>
+ <ol>
+ <li>
+ Validate the input-specification of the job.
+ <li>
+ Split-up the input file(s) into logical {@link InputSplit}s, each of
+ which is then assigned to an individual {@link Mapper}.
+ </li>
+ <li>
+ Provide the {@link RecordReader} implementation to be used to glean
+ input records from the logical <code>InputSplit</code> for processing by
+ the {@link Mapper}.
+ </li>
+ </ol>
+
+ <p>The default behavior of file-based {@link InputFormat}s, typically
+ sub-classes of {@link FileInputFormat}, is to split the
+ input into <i>logical</i> {@link InputSplit}s based on the total size, in
+ bytes, of the input files. However, the {@link FileSystem} blocksize of
+ the input files is treated as an upper bound for input splits. A lower bound
+ on the split size can be set via
+ <a href="{@docRoot}/../mapred-default.html#mapreduce.input.fileinputformat.split.minsize">
+ mapreduce.input.fileinputformat.split.minsize</a>.</p>
+
+ <p>Clearly, logical splits based on input-size is insufficient for many
+ applications since record boundaries are to respected. In such cases, the
+ application has to also implement a {@link RecordReader} on whom lies the
+ responsibilty to respect record-boundaries and present a record-oriented
+ view of the logical <code>InputSplit</code> to the individual task.
+
+ @see InputSplit
+ @see RecordReader
+ @see JobClient
+ @see FileInputFormat
+ @deprecated Use {@link org.apache.hadoop.mapreduce.InputFormat} instead.]]>
+ </doc>
+ </interface>
+ <!-- end interface org.apache.hadoop.mapred.InputFormat -->
+ <!-- start interface org.apache.hadoop.mapred.InputSplit -->
+ <interface name="InputSplit" abstract="true"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.">
+ <implements name="org.apache.hadoop.io.Writable"/>
+ <method name="getLength" return="long"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get the total number of bytes in the data of the <code>InputSplit</code>.
+
+ @return the number of bytes in the input split.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="getLocations" return="java.lang.String[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get the list of hostnames where the input split is located.
+
+ @return list of hostnames where data of the <code>InputSplit</code> is
+ located as an array of <code>String</code>s.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[<code>InputSplit</code> represents the data to be processed by an
+ individual {@link Mapper}.
+
+ <p>Typically, it presents a byte-oriented view on the input and is the
+ responsibility of {@link RecordReader} of the job to process this and present
+ a record-oriented view.
+
+ @see InputFormat
+ @see RecordReader
+ @deprecated Use {@link org.apache.hadoop.mapreduce.InputSplit} instead.]]>
+ </doc>
+ </interface>
+ <!-- end interface org.apache.hadoop.mapred.InputSplit -->
+ <!-- start class org.apache.hadoop.mapred.InvalidFileTypeException -->
+ <class name="InvalidFileTypeException" extends="java.io.IOException"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="InvalidFileTypeException"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <constructor name="InvalidFileTypeException" type="java.lang.String"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <doc>
+ <![CDATA[Used when file type differs from the desired file type. like
+ getting a file when a directory is expected. Or a wrong file type.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.InvalidFileTypeException -->
+ <!-- start class org.apache.hadoop.mapred.InvalidInputException -->
+ <class name="InvalidInputException" extends="java.io.IOException"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="InvalidInputException" type="java.util.List"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Create the exception with the given list.
+ @param probs the list of problems to report. this list is not copied.]]>
+ </doc>
+ </constructor>
+ <method name="getProblems" return="java.util.List"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get the complete list of the problems reported.
+ @return the list of problems, which must not be modified]]>
+ </doc>
+ </method>
+ <method name="getMessage" return="java.lang.String"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get a summary message of the problems found.
+ @return the concatenated messages from all of the problems.]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[This class wraps a list of problems with the input, so that the user
+ can get a list of problems together instead of finding and fixing them one
+ by one.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.InvalidInputException -->
+ <!-- start class org.apache.hadoop.mapred.InvalidJobConfException -->
+ <class name="InvalidJobConfException" extends="java.io.IOException"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="InvalidJobConfException"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <constructor name="InvalidJobConfException" type="java.lang.String"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <doc>
+ <![CDATA[This exception is thrown when jobconf misses some mendatory attributes
+ or value of some attributes is invalid.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.InvalidJobConfException -->
+ <!-- start class org.apache.hadoop.mapred.IsolationRunner -->
+ <class name="IsolationRunner" extends="java.lang.Object"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <constructor name="IsolationRunner"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ </constructor>
+ <method name="main"
+ abstract="false" native="false" synchronized="false"
+ static="true" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="args" type="java.lang.String[]"/>
+ <exception name="ClassNotFoundException" type="java.lang.ClassNotFoundException"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <exception name="InterruptedException" type="java.lang.InterruptedException"/>
+ <doc>
+ <![CDATA[Run a single task.
+
+ @param args the first argument is the task directory]]>
+ </doc>
+ </method>
+ <doc>
+ <![CDATA[IsolationRunner is intended to facilitate debugging by re-running a specific
+ task, given left-over task files for a (typically failed) past job.
+ Currently, it is limited to re-running map tasks.
+
+ Users may coerce MapReduce to keep task files around by setting
+ mapreduce.task.files.preserve.failedtasks. See mapred_tutorial.xml for more documentation.]]>
+ </doc>
+ </class>
+ <!-- end class org.apache.hadoop.mapred.IsolationRunner -->
+ <!-- start class org.apache.hadoop.mapred.JobClient -->
+ <class name="JobClient" extends="org.apache.hadoop.mapreduce.tools.CLI"
+ abstract="false"
+ static="false" final="false" visibility="public"
+ deprecated="Use {@link Job} and {@link Cluster} instead">
+ <constructor name="JobClient"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Create a job client.]]>
+ </doc>
+ </constructor>
+ <constructor name="JobClient" type="org.apache.hadoop.mapred.JobConf"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Build a job client with the given {@link JobConf}, and connect to the
+ default {@link JobTracker}.
+
+ @param conf the job configuration.
+ @throws IOException]]>
+ </doc>
+ </constructor>
+ <constructor name="JobClient" type="org.apache.hadoop.conf.Configuration"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Build a job client with the given {@link Configuration},
+ and connect to the default {@link JobTracker}.
+
+ @param conf the configuration.
+ @throws IOException]]>
+ </doc>
+ </constructor>
+ <constructor name="JobClient" type="java.net.InetSocketAddress, org.apache.hadoop.conf.Configuration"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Build a job client, connect to the indicated job tracker.
+
+ @param jobTrackAddr the job tracker to connect to.
+ @param conf configuration.]]>
+ </doc>
+ </constructor>
+ <method name="init"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Connect to the default {@link JobTracker}.
+ @param conf the job configuration.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="close"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Close the <code>JobClient</code>.]]>
+ </doc>
+ </method>
+ <method name="getFs" return="org.apache.hadoop.fs.FileSystem"
+ abstract="false" native="false" synchronized="true"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get a filesystem handle. We need this to prepare jobs
+ for submission to the MapReduce system.
+
+ @return the filesystem handle.]]>
+ </doc>
+ </method>
+ <method name="getClusterHandle" return="org.apache.hadoop.mapreduce.Cluster"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <doc>
+ <![CDATA[Get a handle to the Cluster]]>
+ </doc>
+ </method>
+ <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="jobFile" type="java.lang.String"/>
+ <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/>
+ <exception name="InvalidJobConfException" type="org.apache.hadoop.mapred.InvalidJobConfException"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Submit a job to the MR system.
+
+ This returns a handle to the {@link RunningJob} which can be used to track
+ the running-job.
+
+ @param jobFile the job configuration.
+ @return a handle to the {@link RunningJob} which can be used to track the
+ running-job.
+ @throws FileNotFoundException
+ @throws InvalidJobConfException
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="submitJob" return="org.apache.hadoop.mapred.RunningJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="conf" type="org.apache.hadoop.mapred.JobConf"/>
+ <exception name="FileNotFoundException" type="java.io.FileNotFoundException"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Submit a job to the MR system.
+ This returns a handle to the {@link RunningJob} which can be used to track
+ the running-job.
+
+ @param conf the job configuration.
+ @return a handle to the {@link RunningJob} which can be used to track the
+ running-job.
+ @throws FileNotFoundException
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="getJob" return="org.apache.hadoop.mapred.RunningJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="jobid" type="org.apache.hadoop.mapred.JobID"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get an {@link RunningJob} object to track an ongoing job. Returns
+ null if the id does not correspond to any known job.
+
+ @param jobid the jobid of the job.
+ @return the {@link RunningJob} handle to track the job, null if the
+ <code>jobid</code> doesn't correspond to any known job.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="getJob" return="org.apache.hadoop.mapred.RunningJob"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="Applications should rather use {@link #getJob(JobID)}.">
+ <param name="jobid" type="java.lang.String"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[@deprecated Applications should rather use {@link #getJob(JobID)}.]]>
+ </doc>
+ </method>
+ <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[Get the information of the current state of the map tasks of a job.
+
+ @param jobId the job to query.
+ @return the list of all of the map tips.
+ @throws IOException]]>
+ </doc>
+ </method>
+ <method name="getMapTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="Applications should rather use {@link #getMapTaskReports(JobID)}">
+ <param name="jobId" type="java.lang.String"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
+ <![CDATA[@deprecated Applications should rather use {@link #getMapTaskReports(JobID)}]]>
+ </doc>
+ </method>
+ <method name="getReduceTaskReports" return="org.apache.hadoop.mapred.TaskReport[]"
+ abstract="false" native="false" synchronized="false"
+ static="false" final="false" visibility="public"
+ deprecated="not deprecated">
+ <param name="jobId" type="org.apache.hadoop.mapred.JobID"/>
+ <exception name="IOException" type="java.io.IOException"/>
+ <doc>
[... 29802 lines stripped ...]