org.apache.accumulo.core.client.mapreduce
Class AccumuloOutputFormat

java.lang.Object
  org.apache.hadoop.mapreduce.OutputFormat<org.apache.hadoop.io.Text,Mutation>
      org.apache.accumulo.core.client.mapreduce.AccumuloOutputFormat

public class AccumuloOutputFormat
extends org.apache.hadoop.mapreduce.OutputFormat<org.apache.hadoop.io.Text,Mutation>

This class allows MapReduce jobs to use Accumulo as the sink of data. This output format accepts keys and values of type Text (for a table name) and Mutation from the Map() and Reduce() functions. The user must specify the following via static methods:

• AccumuloOutputFormat.setOutputInfo(job, username, password, createTables, defaultTableName)
• AccumuloOutputFormat.setZooKeeperInstance(job, instanceName, hosts)

Other static methods are optional

Constructor Summary

AccumuloOutputFormat()

Method Summary

protected static boolean	canCreateTables(org.apache.hadoop.conf.Configuration conf)
protected static boolean	canCreateTables(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use canCreateTables(Configuration) instead
void	checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext job)
protected static String	getDefaultTableName(org.apache.hadoop.conf.Configuration conf)
protected static String	getDefaultTableName(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getDefaultTableName(Configuration) instead
protected static Instance	getInstance(org.apache.hadoop.conf.Configuration conf)
protected static Instance	getInstance(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getInstance(Configuration) instead
protected static org.apache.log4j.Level	getLogLevel(org.apache.hadoop.conf.Configuration conf)
protected static org.apache.log4j.Level	getLogLevel(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getLogLevel(Configuration) instead
protected static int	getMaxLatency(org.apache.hadoop.conf.Configuration conf)
protected static int	getMaxLatency(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getMaxLatency(Configuration) instead
protected static long	getMaxMutationBufferSize(org.apache.hadoop.conf.Configuration conf)
protected static long	getMaxMutationBufferSize(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getMaxMutationBufferSize(Configuration) instead
protected static int	getMaxWriteThreads(org.apache.hadoop.conf.Configuration conf)
protected static int	getMaxWriteThreads(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getMaxWriteThreads(Configuration) instead
org.apache.hadoop.mapreduce.OutputCommitter	getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context)
protected static byte[]	getPassword(org.apache.hadoop.conf.Configuration conf) WARNING: The password is stored in the Configuration and shared with all MapReduce tasks; It is BASE64 encoded to provide a charset safe conversion to a string, and is not intended to be secure.
protected static byte[]	getPassword(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getPassword(Configuration) instead
org.apache.hadoop.mapreduce.RecordWriter<org.apache.hadoop.io.Text,Mutation>	getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext attempt)
protected static boolean	getSimulationMode(org.apache.hadoop.conf.Configuration conf)
protected static boolean	getSimulationMode(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getSimulationMode(Configuration) instead
protected static String	getUsername(org.apache.hadoop.conf.Configuration conf)
protected static String	getUsername(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use getUsername(Configuration) instead
static void	setLogLevel(org.apache.hadoop.conf.Configuration conf, org.apache.log4j.Level level)
static void	setLogLevel(org.apache.hadoop.mapreduce.JobContext job, org.apache.log4j.Level level) Deprecated. Use setLogLevel(Configuration,Level) instead
static void	setMaxLatency(org.apache.hadoop.conf.Configuration conf, int numberOfMilliseconds)
static void	setMaxLatency(org.apache.hadoop.mapreduce.JobContext job, int numberOfMilliseconds) Deprecated. Use setMaxLatency(Configuration,int) instead
static void	setMaxMutationBufferSize(org.apache.hadoop.conf.Configuration conf, long numberOfBytes)
static void	setMaxMutationBufferSize(org.apache.hadoop.mapreduce.JobContext job, long numberOfBytes) Deprecated. Use setMaxMutationBufferSize(Configuration,long) instead
static void	setMaxWriteThreads(org.apache.hadoop.conf.Configuration conf, int numberOfThreads)
static void	setMaxWriteThreads(org.apache.hadoop.mapreduce.JobContext job, int numberOfThreads) Deprecated. Use setMaxWriteThreads(Configuration,int) instead
static void	setMockInstance(org.apache.hadoop.conf.Configuration conf, String instanceName)
static void	setMockInstance(org.apache.hadoop.mapreduce.JobContext job, String instanceName) Deprecated. Use setMockInstance(Configuration,String) instead
static void	setOutputInfo(org.apache.hadoop.conf.Configuration conf, String user, byte[] passwd, boolean createTables, String defaultTable) Configure the output format.
static void	setOutputInfo(org.apache.hadoop.mapreduce.JobContext job, String user, byte[] passwd, boolean createTables, String defaultTable) Deprecated. Use setOutputInfo(Configuration,String,byte[],boolean,String) instead
static void	setSimulationMode(org.apache.hadoop.conf.Configuration conf)
static void	setSimulationMode(org.apache.hadoop.mapreduce.JobContext job) Deprecated. Use setSimulationMode(Configuration) instead
static void	setZooKeeperInstance(org.apache.hadoop.conf.Configuration conf, String instanceName, String zooKeepers)
static void	setZooKeeperInstance(org.apache.hadoop.mapreduce.JobContext job, String instanceName, String zooKeepers) Deprecated. Use setZooKeeperInstance(Configuration,String,String) instead

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

AccumuloOutputFormat

public AccumuloOutputFormat()

Method Detail

setOutputInfo

@Deprecated
public static void setOutputInfo(org.apache.hadoop.mapreduce.JobContext job,
                                            String user,
                                            byte[] passwd,
                                            boolean createTables,
                                            String defaultTable)

Deprecated. Use setOutputInfo(Configuration,String,byte[],boolean,String) instead

Configure the output format.

Parameters:

job - the Map/Reduce job object

user - the username, which must have the Table.CREATE permission to create tables

passwd - the passwd for the username

createTables - the output format will create new tables as necessary. Table names can only be alpha-numeric and underscores.

defaultTable - the table to use when the tablename is null in the write call

setOutputInfo

public static void setOutputInfo(org.apache.hadoop.conf.Configuration conf,
                                 String user,
                                 byte[] passwd,
                                 boolean createTables,
                                 String defaultTable)

Configure the output format.

Parameters:

conf - the Map/Reduce job object

user - the username, which must have the Table.CREATE permission to create tables

passwd - the passwd for the username

createTables - the output format will create new tables as necessary. Table names can only be alpha-numeric and underscores.

defaultTable - the table to use when the tablename is null in the write call

setZooKeeperInstance

@Deprecated
public static void setZooKeeperInstance(org.apache.hadoop.mapreduce.JobContext job,
                                                   String instanceName,
                                                   String zooKeepers)

Deprecated. Use setZooKeeperInstance(Configuration,String,String) instead

setZooKeeperInstance

public static void setZooKeeperInstance(org.apache.hadoop.conf.Configuration conf,
                                        String instanceName,
                                        String zooKeepers)

setMockInstance

@Deprecated
public static void setMockInstance(org.apache.hadoop.mapreduce.JobContext job,
                                              String instanceName)

Deprecated. Use setMockInstance(Configuration,String) instead

setMockInstance

public static void setMockInstance(org.apache.hadoop.conf.Configuration conf,
                                   String instanceName)

setMaxMutationBufferSize

@Deprecated
public static void setMaxMutationBufferSize(org.apache.hadoop.mapreduce.JobContext job,
                                                       long numberOfBytes)

Deprecated. Use setMaxMutationBufferSize(Configuration,long) instead

setMaxMutationBufferSize

public static void setMaxMutationBufferSize(org.apache.hadoop.conf.Configuration conf,
                                            long numberOfBytes)

setMaxLatency

@Deprecated
public static void setMaxLatency(org.apache.hadoop.mapreduce.JobContext job,
                                            int numberOfMilliseconds)

Deprecated. Use setMaxLatency(Configuration,int) instead

setMaxLatency

public static void setMaxLatency(org.apache.hadoop.conf.Configuration conf,
                                 int numberOfMilliseconds)

setMaxWriteThreads

@Deprecated
public static void setMaxWriteThreads(org.apache.hadoop.mapreduce.JobContext job,
                                                 int numberOfThreads)

Deprecated. Use setMaxWriteThreads(Configuration,int) instead

setMaxWriteThreads

public static void setMaxWriteThreads(org.apache.hadoop.conf.Configuration conf,
                                      int numberOfThreads)

setLogLevel

@Deprecated
public static void setLogLevel(org.apache.hadoop.mapreduce.JobContext job,
                                          org.apache.log4j.Level level)

Deprecated. Use setLogLevel(Configuration,Level) instead

setLogLevel

public static void setLogLevel(org.apache.hadoop.conf.Configuration conf,
                               org.apache.log4j.Level level)

setSimulationMode

@Deprecated
public static void setSimulationMode(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use setSimulationMode(Configuration) instead

setSimulationMode

public static void setSimulationMode(org.apache.hadoop.conf.Configuration conf)

getUsername

@Deprecated
protected static String getUsername(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getUsername(Configuration) instead

getUsername

protected static String getUsername(org.apache.hadoop.conf.Configuration conf)

getPassword

@Deprecated
protected static byte[] getPassword(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getPassword(Configuration) instead

WARNING: The password is stored in the Configuration and shared with all MapReduce tasks; It is BASE64 encoded to provide a charset safe conversion to a string, and is not intended to be secure.

getPassword

protected static byte[] getPassword(org.apache.hadoop.conf.Configuration conf)

WARNING: The password is stored in the Configuration and shared with all MapReduce tasks; It is BASE64 encoded to provide a charset safe conversion to a string, and is not intended to be secure.

canCreateTables

@Deprecated
protected static boolean canCreateTables(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use canCreateTables(Configuration) instead

canCreateTables

protected static boolean canCreateTables(org.apache.hadoop.conf.Configuration conf)

getDefaultTableName

@Deprecated
protected static String getDefaultTableName(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getDefaultTableName(Configuration) instead

getDefaultTableName

protected static String getDefaultTableName(org.apache.hadoop.conf.Configuration conf)

getInstance

@Deprecated
protected static Instance getInstance(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getInstance(Configuration) instead

getInstance

protected static Instance getInstance(org.apache.hadoop.conf.Configuration conf)

getMaxMutationBufferSize

@Deprecated
protected static long getMaxMutationBufferSize(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getMaxMutationBufferSize(Configuration) instead

getMaxMutationBufferSize

protected static long getMaxMutationBufferSize(org.apache.hadoop.conf.Configuration conf)

getMaxLatency

@Deprecated
protected static int getMaxLatency(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getMaxLatency(Configuration) instead

getMaxLatency

protected static int getMaxLatency(org.apache.hadoop.conf.Configuration conf)

getMaxWriteThreads

@Deprecated
protected static int getMaxWriteThreads(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getMaxWriteThreads(Configuration) instead

getMaxWriteThreads

protected static int getMaxWriteThreads(org.apache.hadoop.conf.Configuration conf)

getLogLevel

@Deprecated
protected static org.apache.log4j.Level getLogLevel(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getLogLevel(Configuration) instead

getLogLevel

protected static org.apache.log4j.Level getLogLevel(org.apache.hadoop.conf.Configuration conf)

getSimulationMode

@Deprecated
protected static boolean getSimulationMode(org.apache.hadoop.mapreduce.JobContext job)

Deprecated. Use getSimulationMode(Configuration) instead

getSimulationMode

protected static boolean getSimulationMode(org.apache.hadoop.conf.Configuration conf)

checkOutputSpecs

public void checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext job)
                      throws IOException

Specified by:

checkOutputSpecs in class org.apache.hadoop.mapreduce.OutputFormat<org.apache.hadoop.io.Text,Mutation>

Throws:

IOException

getOutputCommitter

public org.apache.hadoop.mapreduce.OutputCommitter getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context)

Specified by:

getOutputCommitter in class org.apache.hadoop.mapreduce.OutputFormat<org.apache.hadoop.io.Text,Mutation>

getRecordWriter

public org.apache.hadoop.mapreduce.RecordWriter<org.apache.hadoop.io.Text,Mutation> getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext attempt)
                                                                                             throws IOException

Specified by:

getRecordWriter in class org.apache.hadoop.mapreduce.OutputFormat<org.apache.hadoop.io.Text,Mutation>

Throws:

IOException