|
Oracle® In-Database Container for Hadoop Java API Reference Release 1.0.1 E54638-01 |
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.apache.hadoop.mapreduce.task.JobContextImpl
org.apache.hadoop.mapreduce.Job
oracle.sql.hadoop.Job
public class Job
The job submitter's view of the Job.
It allows the user to configure the job, and run it. The set methods only work until the job is submitted, afterwards they will throw an IllegalStateException.
Nested Class Summary | |
---|---|
static class |
Job.HiveTypes
|
protected static class |
Job.JobState
|
static class |
Job.Operation
Operations available in oc4hadoop |
Nested classes/interfaces inherited from class org.apache.hadoop.mapreduce.Job |
---|
org.apache.hadoop.mapreduce.Job.TaskStatusFilter |
Field Summary | |
---|---|
protected static java.lang.String |
CONF_KEY
|
protected static java.lang.String |
CREATE_DESERIALIZED_SPLITS_TABLE_ATTR
|
protected static java.lang.String |
CREATE_OUTPUT_TABLE_ATTR
|
protected static java.lang.String |
CREATE_SERIALIZED_SPLITS_TABLE_ATTR
|
protected static java.lang.String |
DATA_TYPE_CHECK_FLAG
|
protected static java.lang.String |
DEBUG_MODE_FLAG
|
protected static java.lang.String |
DESERIALIZED_SPLITS_TABLE_NAME_PROPERTY
|
protected static java.lang.String |
HINPUT_FUNCTION
|
protected static java.lang.String |
HINPUTANDMAP_FUNCTION
|
protected static java.lang.String |
ID_STRING_ATTR
|
protected static java.lang.String |
INPUT_CLASSES_ATTR
|
protected static java.lang.String |
INPUT_KEY_CLASS_ATTR
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_CLASSES_ATTR
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_DB_TYPES_PROPERTY
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_KEY_CLASS_ATTR
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_KEY_DB_TYPE_PROPERTY
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_OUTTYPE_PROPERTY
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_OUTTYPESET_PROPERTY
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_VALUE_CLASS_ATTR
|
protected static java.lang.String |
INPUT_SPLIT_RECORD_VALUE_DB_TYPE_PROPERTY
|
protected static java.lang.String |
INPUT_TABLE_NAME_PROPERTY
|
protected static java.lang.String |
INPUT_VALUE_CLASS_ATTR
|
protected static java.lang.String |
MAP_FUNCTION
|
protected static java.lang.String |
MAP_METHOD
|
protected static java.lang.String |
MAP_OUTPUT_KEY_CLASS_ATTR
|
protected static java.lang.String |
MAP_OUTPUT_KEY_DB_TYPE_PROPERTY
|
protected static java.lang.String |
MAP_OUTPUT_VALUE_CLASS_ATTR
|
protected static java.lang.String |
MAP_OUTPUT_VALUE_DB_TYPE_PROPERTY
|
protected static java.lang.String |
MAP_OUTTYPE_PROPERTY
|
protected static java.lang.String |
MAP_OUTTYPESET_PROPERTY
|
protected static java.lang.String |
MAP_SIGNATURE
|
protected static java.lang.String |
MAPPER_IMPL
|
protected static java.lang.String |
MULTI_VALUE
|
protected static java.lang.String |
NUM_HINPUT_TASKS_ATTR
|
protected static java.lang.String |
NUM_INSERT_TASKS_ATTR
|
protected static java.lang.String |
OPERATION_ATTR
|
protected static java.lang.String |
OUTPUT_KEY_CLASS_ATTR
|
protected static java.lang.String |
OUTPUT_KEY_DB_TYPE_PROPERTY
|
protected static java.lang.String |
OUTPUT_SCHEMA_NAME_ATTR
|
protected static java.lang.String |
OUTPUT_TABLE_NAME_PROPERTY
|
protected static java.lang.String |
OUTPUT_VALUE_CLASS_ATTR
|
protected static java.lang.String |
OUTPUT_VALUE_DB_TYPE_PROPERTY
|
protected static java.lang.String |
OUTTYPE_PROPERTY
|
protected static java.lang.String |
OUTTYPESET_PROPERTY
|
protected static java.lang.String |
REDUCE_FUNCTION
|
protected static java.lang.String |
REDUCER_IMPL
|
protected static java.lang.String |
SCHEMA_NAME_ATTR
|
protected static java.lang.String |
SERIALIZED_SPLITS_TABLE_NAME_PROPERTY
|
protected static java.lang.String |
SERIALIZED_SPLITS_TABLE_RAW_SIZE_ATTR
|
protected static java.lang.String |
SINGLE_COLUMN_ATTR
|
protected static java.lang.String |
SQLTYPES
|
Fields inherited from class org.apache.hadoop.mapreduce.Job |
---|
COMPLETION_POLL_INTERVAL_KEY, OUTPUT_FILTER, PROGRESS_MONITOR_POLL_INTERVAL_KEY, SUBMIT_REPLICATION, USED_GENERIC_PARSER |
Fields inherited from class org.apache.hadoop.mapreduce.task.JobContextImpl |
---|
conf, credentials |
Fields inherited from interface org.apache.hadoop.mapreduce.MRJobConfig |
---|
APPLICATION_ATTEMPT_ID, APPLICATION_ATTEMPT_ID_ENV, APPLICATION_MASTER_CLASS, APPLICATION_TOKENS_FILE, CACHE_ARCHIVES, CACHE_ARCHIVES_SIZES, CACHE_ARCHIVES_TIMESTAMPS, CACHE_ARCHIVES_VISIBILITIES, CACHE_FILE_TIMESTAMPS, CACHE_FILE_VISIBILITIES, CACHE_FILES, CACHE_FILES_SIZES, CACHE_LOCALARCHIVES, CACHE_LOCALFILES, CACHE_SYMLINK, CLASSPATH_ARCHIVES, CLASSPATH_FILES, COMBINE_CLASS_ATTR, COMBINE_RECORDS_BEFORE_PROGRESS, COMBINER_GROUP_COMPARATOR_CLASS, COMPLETED_MAPS_FOR_REDUCE_SLOWSTART, COUNTER_GROUP_NAME_MAX_DEFAULT, COUNTER_GROUP_NAME_MAX_KEY, COUNTER_GROUPS_MAX_DEFAULT, COUNTER_GROUPS_MAX_KEY, COUNTER_NAME_MAX_DEFAULT, COUNTER_NAME_MAX_KEY, COUNTERS_MAX_DEFAULT, COUNTERS_MAX_KEY, DEFAULT_JOB_ACL_MODIFY_JOB, DEFAULT_JOB_ACL_VIEW_JOB, DEFAULT_JOB_AM_ACCESS_DISABLED, DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED, DEFAULT_LOG_LEVEL, DEFAULT_MAP_CPU_VCORES, DEFAULT_MAP_MEMORY_MB, DEFAULT_MAPRED_ADMIN_JAVA_OPTS, DEFAULT_MAPRED_ADMIN_USER_ENV, DEFAULT_MAPREDUCE_APPLICATION_CLASSPATH, DEFAULT_MAX_SHUFFLE_FETCH_RETRY_DELAY, DEFAULT_MR_AM_COMMAND_OPTS, DEFAULT_MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, DEFAULT_MR_AM_CONTAINERLAUNCHER_THREAD_COUNT_LIMIT, DEFAULT_MR_AM_CPU_VCORES, DEFAULT_MR_AM_HISTORY_COMPLETE_EVENT_FLUSH_TIMEOUT_MS, DEFAULT_MR_AM_HISTORY_JOB_COMPLETE_UNFLUSHED_MULTIPLIER, DEFAULT_MR_AM_HISTORY_MAX_UNFLUSHED_COMPLETE_EVENTS, DEFAULT_MR_AM_HISTORY_USE_BATCHED_FLUSH_QUEUE_SIZE_THRESHOLD, DEFAULT_MR_AM_IGNORE_BLACKLISTING_BLACKLISTED_NODE_PERCENT, DEFAULT_MR_AM_JOB_CLIENT_THREAD_COUNT, DEFAULT_MR_AM_JOB_REDUCE_PREEMPTION_LIMIT, DEFAULT_MR_AM_JOB_REDUCE_RAMP_UP_LIMIT, DEFAULT_MR_AM_LOG_LEVEL, DEFAULT_MR_AM_NUM_PROGRESS_SPLITS, DEFAULT_MR_AM_STAGING_DIR, DEFAULT_MR_AM_TASK_ESTIMATOR_SMOOTH_LAMBDA_MS, DEFAULT_MR_AM_TASK_LISTENER_THREAD_COUNT, DEFAULT_MR_AM_TO_RM_HEARTBEAT_INTERVAL_MS, DEFAULT_MR_AM_TO_RM_WAIT_INTERVAL_MS, DEFAULT_MR_AM_VMEM_MB, DEFAULT_MR_CLIENT_MAX_RETRIES, DEFAULT_MR_CLIENT_TO_AM_IPC_MAX_RETRIES, DEFAULT_REDUCE_CPU_VCORES, DEFAULT_REDUCE_MEMORY_MB, DEFAULT_SHELL, GROUP_COMPARATOR_CLASS, HADOOP_WORK_DIR, ID, INDEX_CACHE_MEMORY_LIMIT, INPUT_FORMAT_CLASS_ATTR, IO_SORT_FACTOR, IO_SORT_MB, JAR, JAR_UNPACK_PATTERN, JOB_ACL_MODIFY_JOB, JOB_ACL_VIEW_JOB, JOB_AM_ACCESS_DISABLED, JOB_CANCEL_DELEGATION_TOKEN, JOB_CONF_FILE, JOB_JAR, JOB_JOBTRACKER_ID, JOB_LOCAL_DIR, JOB_NAME, JOB_NAMENODES, JOB_SPLIT, JOB_SPLIT_METAINFO, JOB_SUBMIT_DIR, JOB_SUBMITHOST, JOB_SUBMITHOSTADDR, JOB_TOKEN_TRACKING_IDS, JOB_TOKEN_TRACKING_IDS_ENABLED, JOB_UBERTASK_ENABLE, JOB_UBERTASK_MAXBYTES, JOB_UBERTASK_MAXMAPS, JOB_UBERTASK_MAXREDUCES, JVM_NUMTASKS_TORUN, KEY_COMPARATOR, MAP_CLASS_ATTR, MAP_COMBINE_MIN_SPILLS, MAP_CPU_VCORES, MAP_DEBUG_SCRIPT, MAP_ENV, MAP_FAILURES_MAX_PERCENT, MAP_INPUT_FILE, MAP_INPUT_PATH, MAP_INPUT_START, MAP_JAVA_OPTS, MAP_LOG_LEVEL, MAP_MAX_ATTEMPTS, MAP_MEMORY_MB, MAP_OUTPUT_COLLECTOR_CLASS_ATTR, MAP_OUTPUT_COMPRESS, MAP_OUTPUT_COMPRESS_CODEC, MAP_OUTPUT_KEY_CLASS, MAP_OUTPUT_KEY_FIELD_SEPERATOR, MAP_OUTPUT_VALUE_CLASS, MAP_SKIP_INCR_PROC_COUNT, MAP_SKIP_MAX_RECORDS, MAP_SORT_SPILL_PERCENT, MAP_SPECULATIVE, MAPRED_ADMIN_USER_ENV, MAPRED_ADMIN_USER_SHELL, MAPRED_MAP_ADMIN_JAVA_OPTS, MAPRED_REDUCE_ADMIN_JAVA_OPTS, MAPREDUCE_APPLICATION_CLASSPATH, MAPREDUCE_JOB_CREDENTIALS_BINARY, MAPREDUCE_JOB_DIR, MAPREDUCE_JOB_USER_CLASSPATH_FIRST, MAPREDUCE_TASK_CLASSPATH_PRECEDENCE, MAPREDUCE_V2_CHILD_CLASS, MAX_SHUFFLE_FETCH_RETRY_DELAY, MAX_TASK_FAILURES_PER_TRACKER, MR_AM_COMMAND_OPTS, MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, MR_AM_CONTAINERLAUNCHER_THREAD_COUNT_LIMIT, MR_AM_CPU_VCORES, MR_AM_CREATE_JH_INTERMEDIATE_BASE_DIR, MR_AM_ENV, MR_AM_HISTORY_COMPLETE_EVENT_FLUSH_TIMEOUT_MS, MR_AM_HISTORY_JOB_COMPLETE_UNFLUSHED_MULTIPLIER, MR_AM_HISTORY_MAX_UNFLUSHED_COMPLETE_EVENTS, MR_AM_HISTORY_USE_BATCHED_FLUSH_QUEUE_SIZE_THRESHOLD, MR_AM_IGNORE_BLACKLISTING_BLACKLISTED_NODE_PERECENT, MR_AM_JOB_CLIENT_PORT_RANGE, MR_AM_JOB_CLIENT_THREAD_COUNT, MR_AM_JOB_NODE_BLACKLISTING_ENABLE, MR_AM_JOB_RECOVERY_ENABLE, MR_AM_JOB_REDUCE_PREEMPTION_LIMIT, MR_AM_JOB_REDUCE_RAMPUP_UP_LIMIT, MR_AM_JOB_SPECULATOR, MR_AM_LOG_LEVEL, MR_AM_NUM_PROGRESS_SPLITS, MR_AM_PREFIX, MR_AM_SECURITY_SERVICE_AUTHORIZATION_CLIENT, MR_AM_SECURITY_SERVICE_AUTHORIZATION_TASK_UMBILICAL, MR_AM_STAGING_DIR, MR_AM_TASK_ESTIMATOR, MR_AM_TASK_ESTIMATOR_EXPONENTIAL_RATE_ENABLE, MR_AM_TASK_ESTIMATOR_SMOOTH_LAMBDA_MS, MR_AM_TASK_LISTENER_THREAD_COUNT, MR_AM_TO_RM_HEARTBEAT_INTERVAL_MS, MR_AM_TO_RM_WAIT_INTERVAL_MS, MR_AM_VMEM_MB, MR_CLIENT_MAX_RETRIES, MR_CLIENT_TO_AM_IPC_MAX_RETRIES, MR_JOB_END_NOTIFICATION_MAX_ATTEMPTS, MR_JOB_END_NOTIFICATION_MAX_RETRY_INTERVAL, MR_JOB_END_NOTIFICATION_PROXY, MR_JOB_END_NOTIFICATION_URL, MR_JOB_END_RETRY_ATTEMPTS, MR_JOB_END_RETRY_INTERVAL, MR_PREFIX, NUM_MAP_PROFILES, NUM_MAPS, NUM_REDUCE_PROFILES, NUM_REDUCES, OUTPUT, OUTPUT_FORMAT_CLASS_ATTR, OUTPUT_KEY_CLASS, OUTPUT_VALUE_CLASS, PARTITIONER_CLASS_ATTR, PRESERVE_FAILED_TASK_FILES, PRESERVE_FILES_PATTERN, PRIORITY, QUEUE_NAME, RECORDS_BEFORE_PROGRESS, REDUCE_CLASS_ATTR, REDUCE_CPU_VCORES, REDUCE_DEBUG_SCRIPT, REDUCE_ENV, REDUCE_FAILURES_MAXPERCENT, REDUCE_INPUT_BUFFER_PERCENT, REDUCE_JAVA_OPTS, REDUCE_LOG_LEVEL, REDUCE_MARKRESET_BUFFER_PERCENT, REDUCE_MARKRESET_BUFFER_SIZE, REDUCE_MAX_ATTEMPTS, REDUCE_MEMORY_MB, REDUCE_MEMORY_TOTAL_BYTES, REDUCE_MEMTOMEM_ENABLED, REDUCE_MEMTOMEM_THRESHOLD, REDUCE_MERGE_INMEM_THRESHOLD, REDUCE_SKIP_INCR_PROC_COUNT, REDUCE_SKIP_MAXGROUPS, REDUCE_SPECULATIVE, SETUP_CLEANUP_NEEDED, SHUFFLE_CONNECT_TIMEOUT, SHUFFLE_FETCH_FAILURES, SHUFFLE_INPUT_BUFFER_PERCENT, SHUFFLE_MEMORY_LIMIT_PERCENT, SHUFFLE_MERGE_PERCENT, SHUFFLE_NOTIFY_READERROR, SHUFFLE_PARALLEL_COPIES, SHUFFLE_READ_TIMEOUT, SKIP_OUTDIR, SKIP_RECORDS, SKIP_START_ATTEMPTS, SPECULATIVE_SLOWNODE_THRESHOLD, SPECULATIVE_SLOWTASK_THRESHOLD, SPECULATIVECAP, SPLIT_FILE, STDERR_LOGFILE_ENV, STDOUT_LOGFILE_ENV, TASK_ATTEMPT_ID, TASK_CLEANUP_NEEDED, TASK_DEBUGOUT_LINES, TASK_ID, TASK_ISMAP, TASK_LOG_DIR, TASK_LOG_SIZE, TASK_MAP_PROFILE_PARAMS, TASK_OUTPUT_DIR, TASK_PARTITION, TASK_PROFILE, TASK_PROFILE_PARAMS, TASK_REDUCE_PROFILE_PARAMS, TASK_TEMP_DIR, TASK_TIMEOUT, TASK_TIMEOUT_CHECK_INTERVAL_MS, TASK_USERLOG_LIMIT, USER_LOG_RETAIN_HOURS, USER_NAME, WORKDIR, WORKING_DIR |
Constructor Summary | |
---|---|
Job()
Constructor for the Job class |
|
Job(org.apache.hadoop.conf.Configuration conf)
Constructor for the Job class |
|
Job(org.apache.hadoop.conf.Configuration conf,
java.lang.String jobName)
Constructor for the Job class |
Method Summary | |
---|---|
java.lang.Boolean |
checkDataType()
Return the flag for data type check. |
static Job |
copy(long key)
Retrieve the configuration stored under key, if any. |
void |
drop()
If there is no stored version of the configuration signal an error, otherwise remove the stored configuration and the other database state created for the job by the init or run method. |
long |
getConfKey()
Get the retrieval key for the Hadoop job configuration. |
boolean |
getCreateDeserializedSplitsTable()
Return the boolean value indicating whether the output table will be created (or dropped and recreated) as part of executing the run method for ReadInputSplits operations. |
boolean |
getCreateOutputTable()
Return the boolean value indicating whether the output table will be created (or dropped and recreated) as part of executing the run method for MapReduce operations. |
boolean |
getCreateSerializedSplitsTable()
Return the boolean value indicating whether the output table will be created (or dropped and recreated) as part of executing the run method for GetInputSplits operations. |
java.lang.String |
getDeserializedSplitsTableName()
Get the name of the table to hold deserialized InputSplits. |
java.lang.String |
getIdString()
Get the job id string used for constructing schema object names |
java.lang.Class[] |
getInputClasses()
Returns an array of classes provided for identifying the argument types of map method. |
java.lang.Class<?> |
getInputKeyClass()
Get the input key class for the job. |
java.lang.Class[] |
getInputSplitRecordClasses()
For the ReadInputSplits operations, return an array of the java class types in the output record type. |
java.lang.String |
getInputSplitRecordDBType()
Get the database object type (row type of the table) for the input split record data. |
java.lang.String[] |
getInputSplitRecordDBTypes()
For the ReadInputSplits operations, return an array of the database column types in the output record type. |
java.lang.String |
getInputSplitRecordDBTypeSet()
Get the database table type for the input split record data. |
java.lang.Class<?> |
getInputSplitRecordKeyClass()
Get the InputSplit record key class for the job. |
java.lang.String |
getInputSplitRecordKeyDBType()
Get the input split record key database type. |
java.lang.Class<?> |
getInputSplitRecordValueClass()
Get the InputSplit record value class for the job. |
java.lang.String |
getInputSplitRecordValueDBType()
Get the input split record value database type. |
java.lang.String |
getInputTableName()
Get the input table name. |
java.lang.Class<?> |
getInputValueClass()
Get the input value class for the job. |
java.lang.String |
getMapMethodName()
Get the Map method name |
java.lang.Class[] |
getMapMethodSignature()
For the GetReadAndMapReduceInputSplits and ReadAndMapReduceInputSplits operations, this method provides for querying the actual arguments types of the map method that will be used. |
java.lang.String |
getMapOutputDBType()
Get the database object type (row type of the table) for the map output data. |
java.lang.String |
getMapOutputDBTypeSet()
Get the database table type for the map output data. |
java.lang.Class<?> |
getMapOutputKeyClass()
Get the key class for the map output data. |
java.lang.String |
getMapOutputKeyDBType()
Get the map output key database type. |
java.lang.Class<?> |
getMapOutputValueClass()
Get the value class for the map output data. |
java.lang.String |
getMapOutputValueDBType()
Get the map output value database type. |
java.lang.String |
getMapperImpl()
Get the database object type for the Mapper call specification. |
int |
getNumHInputTasks()
Get the number of hinput tasks for the job. |
int |
getNumMapTasks()
Get the number of map tasks for the job. |
Job.Operation |
getOperation()
Gets the operation value for Job |
java.lang.String |
getOutputDBType()
Get the database object type (row type of the table) for the (final) job output data. |
java.lang.String |
getOutputDBTypeSet()
Get the database table type for the (final) job output data. |
java.lang.Class<?> |
getOutputKeyClass()
Get the key class for the (final) job output data. |
java.lang.String |
getOutputKeyDBType()
Get the output key database type. |
java.lang.String |
getOutputSchemaName()
Get the schema name for output tables. |
java.lang.String |
getOutputTableName()
Get the output table name. |
java.lang.Class<?> |
getOutputValueClass()
Get the output value class. |
java.lang.String |
getOutputValueDBType()
Get the output value database type. |
java.lang.Class<? extends org.apache.hadoop.mapreduce.Partitioner<?,?>> |
getPartitionerClass()
Get the Partitioner class for the job. |
java.lang.String |
getReducerImpl()
Get the database object type for the Reducer call specification. |
java.lang.String |
getSchemaName()
Get the schema name for input tables. |
java.lang.String |
getSerializedSplitsTableName()
Get the name of the table to hold serialized InputSplits. |
int |
getSerializedSplitsTableRawSize()
For the GetInputSplits operation, returns the size of the RAW column used in output table |
boolean |
getUsingHive()
Wrapper over getHiveMetaStoreData that forces reconnection and retrieval of metadata if properties required for connection are present, and returns whether hive is in use (ie whether those properties are set). |
long |
init()
Initialize a job by creating the database state required for executing the job. |
long |
init(Job.Operation operation)
Initialize a job by creating the database state required for executing the job. |
static void |
initializeLogging()
Initializes log4j from the oc4hadoop_log4j.properties file loaded as a JAVA Resource |
static Job |
lookup(long key)
Retrieve the configuration stored under key, if any. |
void |
reopen(boolean dropGeneratedObjects)
Change state back to DEFINE so that fields can be modified. |
void |
resetConfigDBStore()
Reset the sequence and table for storing Hadoop job configurations. |
void |
run()
Run the job with the table names as set in the configuration. |
void |
run(java.lang.String table)
Runs the job for GetInputSplits operation |
void |
run(java.lang.String inTable,
java.lang.String outTable)
Run the job with the given tables. |
void |
setCreateDeserializedSplitsTable(boolean value)
Set the boolean value determining whether the output table will be created (or dropped and recreated) as part of executing the run method for ReadInputSplits operations. |
void |
setCreateOutputTable(boolean value)
Set the boolean value determining whether the output table will be created (or dropped and recreated) as part of executing the run method for MapReduce operations. |
void |
setCreateSerializedSplitsTable(boolean value)
Set the boolean value determining whether the output table will be created (or dropped and recreated) as part of executing the run method for GetInputSplits operations. |
void |
setDataTypeCheck(java.lang.Boolean flag)
Set if data type checks between SQL and Hadoop writable types for map/reduce input data are performed at the beginning of each stage. |
void |
setDeserializedSplitsTableName(java.lang.String theTable)
Set the name of the table to hold deserialized InputSplits. |
void |
setIdString(java.lang.String theId)
Set the job id string used for constructing schema object names |
void |
setInputClasses(java.lang.String value)
Sets the class names for identifying the argument types of map method. |
void |
setInputFormatClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.InputFormat> cls)
Set the InputFormat for the job. |
void |
setInputKeyClass(java.lang.Class<?> theClass)
Set the input key class for the job. |
void |
setInputSplitRecordClasses(java.lang.String value)
For the ReadInputSplits operations, set the values in the array returned by getInputSplitRecordClasses. |
void |
setInputSplitRecordDBTypes(java.lang.String value)
For the ReadInputSplits operations, set the values in the array returned by getInputSplitRecordDBTypes. |
void |
setInputSplitRecordKeyClass(java.lang.Class<?> theClass)
Set the InputSplit record key class for the job. |
void |
setInputSplitRecordKeyDBType(java.lang.String theType)
Set the key database type for the input split record data. |
void |
setInputSplitRecordValueClass(java.lang.Class<?> theClass)
Set the InputSplit record value class for the job. |
void |
setInputSplitRecordValueDBType(java.lang.String theType)
Set the value database type for the input split record data. |
void |
setInputTableName(java.lang.String theTable)
Set the input table name. |
void |
setInputValueClass(java.lang.Class<?> theClass)
Set the input value class for the job. |
void |
setJobName(java.lang.String name)
Set the user-specified job name. |
void |
setMapMethodName(java.lang.String methodName)
Set the Map method name |
void |
setMapOutputKeyClass(java.lang.Class<?> theClass)
Set the key class for the map output data. |
void |
setMapOutputKeyDBType(java.lang.String theType)
Set the key database type for the map output data. |
void |
setMapOutputValueClass(java.lang.Class<?> theClass)
Set the value class for the map output data. |
void |
setMapOutputValueDBType(java.lang.String theType)
Set the value database type for the map output data. |
void |
setMapperClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Mapper> cls)
Set the Mapper for the job. |
void |
setMultiValue(boolean value)
|
void |
setNumHInputTasks(int tasks)
Set the number of hinput tasks for the job. |
void |
setNumMapTasks(int tasks)
Set the number of map tasks for the job. |
void |
setNumReduceTasks(int tasks)
Set the number of reduce tasks for the job. |
void |
setOperation(Job.Operation operation)
Sets the operation property of Job. |
void |
setOutputKeyClass(java.lang.Class<?> theClass)
Set the key class for the (final) job output data. |
void |
setOutputKeyDBType(java.lang.String theType)
Set the key database type for the (final) job output data. |
void |
setOutputSchemaName(java.lang.String theSchema)
Set the optional schema name for output tables. |
void |
setOutputTableName(java.lang.String theTable)
Set the output table name. |
void |
setOutputValueClass(java.lang.Class<?> theClass)
Set the value class for the (final) job output data. |
void |
setOutputValueDBType(java.lang.String theType)
Set the value database type for the (final) job output data. |
void |
setPartitionerClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Partitioner> cls)
Set the Partitioner for the job. |
void |
setReducerClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Reducer> cls)
Set the Reducer for the job. |
void |
setSchemaName(java.lang.String theSchema)
Set the schema name for input tables. |
void |
setSerializedSplitsTableName(java.lang.String theTable)
Set the name of the table to hold serialized InputSplits. |
void |
setSerializedSplitsTableRawSize(int value)
For GetInputSplits operation, sets the size of RAW column used in output table. |
void |
setTypeMap(java.util.Map<java.lang.String,java.lang.Class<?>> map)
Map a User Defined Type defined in SQL to the Java Class to be used as Hadoop Key and Value. |
boolean |
singleColumn()
|
long |
store()
Create or update the stored version of the configuration. |
long |
update()
Update the stored version of the configuration created by a previous call to the init, run or store methods, so that the stored version matches the current settings in the job. |
boolean |
waitForCompletion(boolean verbose)
Submit the job and wait for it to finish. |
Methods inherited from class org.apache.hadoop.mapreduce.Job |
---|
addArchiveToClassPath, addCacheArchive, addCacheFile, addFileToClassPath, cleanupProgress, createSymlink, failTask, getCluster, getCompletionPollInterval, getCounters, getFinishTime, getHistoryUrl, getInstance, getInstance, getInstance, getInstance, getInstance, getInstance, getInstance, getJobFile, getJobName, getJobState, getJobSubmitter, getPriority, getProgressPollInterval, getSchedulingInfo, getStartTime, getStatus, getTaskCompletionEvents, getTaskCompletionEvents, getTaskDiagnostics, getTaskOutputFilter, getTaskReports, getTrackingURL, isComplete, isRetired, isSuccessful, isUber, killJob, killTask, mapProgress, monitorAndPrintJob, reduceProgress, setCacheArchives, setCacheFiles, setCancelDelegationTokenUponJobCompletion, setCombinerClass, setCombinerKeyGroupingComparatorClass, setGroupingComparatorClass, setJar, setJarByClass, setJobSetupCleanupNeeded, setMapSpeculativeExecution, setMaxMapAttempts, setMaxReduceAttempts, setOutputFormatClass, setPriority, setProfileEnabled, setProfileParams, setProfileTaskRange, setReduceSpeculativeExecution, setSortComparatorClass, setSpeculativeExecution, setTaskOutputFilter, setupProgress, setUser, setUserClassesTakesPrecedence, setWorkingDirectory, submit, toString |
Methods inherited from class org.apache.hadoop.mapreduce.task.JobContextImpl |
---|
getArchiveClassPaths, getArchiveTimestamps, getCacheArchives, getCacheFiles, getCombinerClass, getCombinerKeyGroupingComparator, getConfiguration, getCredentials, getFileClassPaths, getFileTimestamps, getGroupingComparator, getInputFormatClass, getJar, getJobID, getJobSetupCleanupNeeded, getLocalCacheArchives, getLocalCacheFiles, getMapperClass, getMaxMapAttempts, getMaxReduceAttempts, getNumReduceTasks, getOutputFormatClass, getProfileEnabled, getProfileParams, getProfileTaskRange, getReducerClass, getSortComparator, getSymlink, getTaskCleanupNeeded, getUser, getWorkingDirectory, setJobID, userClassesTakesPrecedence |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait |
Methods inherited from interface org.apache.hadoop.mapreduce.JobContext |
---|
getArchiveClassPaths, getArchiveTimestamps, getCacheArchives, getCacheFiles, getCombinerClass, getCombinerKeyGroupingComparator, getConfiguration, getCredentials, getFileClassPaths, getFileTimestamps, getGroupingComparator, getInputFormatClass, getJar, getJobID, getJobSetupCleanupNeeded, getLocalCacheArchives, getLocalCacheFiles, getMapperClass, getMaxMapAttempts, getMaxReduceAttempts, getNumReduceTasks, getOutputFormatClass, getProfileEnabled, getProfileParams, getProfileTaskRange, getReducerClass, getSortComparator, getSymlink, getTaskCleanupNeeded, getUser, getWorkingDirectory, userClassesTakesPrecedence |
Field Detail |
---|
protected static final java.lang.String OPERATION_ATTR
protected static final java.lang.String SCHEMA_NAME_ATTR
protected static final java.lang.String OUTPUT_SCHEMA_NAME_ATTR
protected static final java.lang.String INPUT_TABLE_NAME_PROPERTY
protected static final java.lang.String OUTPUT_TABLE_NAME_PROPERTY
protected static final java.lang.String SERIALIZED_SPLITS_TABLE_NAME_PROPERTY
protected static final java.lang.String DESERIALIZED_SPLITS_TABLE_NAME_PROPERTY
protected static final java.lang.String INPUT_KEY_CLASS_ATTR
protected static final java.lang.String INPUT_VALUE_CLASS_ATTR
protected static final java.lang.String INPUT_CLASSES_ATTR
protected static final java.lang.String MAP_OUTPUT_KEY_CLASS_ATTR
protected static final java.lang.String MAP_OUTPUT_VALUE_CLASS_ATTR
protected static final java.lang.String OUTPUT_KEY_CLASS_ATTR
protected static final java.lang.String OUTPUT_VALUE_CLASS_ATTR
protected static final java.lang.String INPUT_SPLIT_RECORD_KEY_CLASS_ATTR
protected static final java.lang.String INPUT_SPLIT_RECORD_VALUE_CLASS_ATTR
protected static final java.lang.String INPUT_SPLIT_RECORD_CLASSES_ATTR
protected static final java.lang.String SINGLE_COLUMN_ATTR
protected static final java.lang.String NUM_HINPUT_TASKS_ATTR
protected static final java.lang.String NUM_INSERT_TASKS_ATTR
protected static final java.lang.String MAP_OUTPUT_KEY_DB_TYPE_PROPERTY
protected static final java.lang.String MAP_OUTPUT_VALUE_DB_TYPE_PROPERTY
protected static final java.lang.String OUTPUT_KEY_DB_TYPE_PROPERTY
protected static final java.lang.String OUTPUT_VALUE_DB_TYPE_PROPERTY
protected static final java.lang.String INPUT_SPLIT_RECORD_KEY_DB_TYPE_PROPERTY
protected static final java.lang.String INPUT_SPLIT_RECORD_VALUE_DB_TYPE_PROPERTY
protected static final java.lang.String INPUT_SPLIT_RECORD_DB_TYPES_PROPERTY
protected static final java.lang.String MAP_OUTTYPE_PROPERTY
protected static final java.lang.String MAP_OUTTYPESET_PROPERTY
protected static final java.lang.String OUTTYPE_PROPERTY
protected static final java.lang.String OUTTYPESET_PROPERTY
protected static final java.lang.String INPUT_SPLIT_RECORD_OUTTYPE_PROPERTY
protected static final java.lang.String INPUT_SPLIT_RECORD_OUTTYPESET_PROPERTY
protected static final java.lang.String MAPPER_IMPL
protected static final java.lang.String REDUCER_IMPL
protected static final java.lang.String MAP_FUNCTION
protected static final java.lang.String REDUCE_FUNCTION
protected static final java.lang.String HINPUT_FUNCTION
protected static final java.lang.String HINPUTANDMAP_FUNCTION
protected static final java.lang.String MAP_METHOD
protected static final java.lang.String MAP_SIGNATURE
protected static final java.lang.String CONF_KEY
protected static final java.lang.String DEBUG_MODE_FLAG
protected static final java.lang.String DATA_TYPE_CHECK_FLAG
protected static final java.lang.String ID_STRING_ATTR
protected static final java.lang.String CREATE_OUTPUT_TABLE_ATTR
protected static final java.lang.String CREATE_SERIALIZED_SPLITS_TABLE_ATTR
protected static final java.lang.String CREATE_DESERIALIZED_SPLITS_TABLE_ATTR
protected static final java.lang.String SERIALIZED_SPLITS_TABLE_RAW_SIZE_ATTR
protected static final java.lang.String SQLTYPES
protected static final java.lang.String MULTI_VALUE
Constructor Detail |
---|
public Job() throws java.io.IOException
java.io.IOException
public Job(org.apache.hadoop.conf.Configuration conf) throws java.io.IOException
conf
- the Hadoop configuration
java.io.IOException
public Job(org.apache.hadoop.conf.Configuration conf, java.lang.String jobName) throws java.io.IOException
conf
- the Hadoop configurationjobName
- the job name
java.io.IOException
Method Detail |
---|
public boolean singleColumn()
public long update() throws java.lang.Exception
java.lang.Exception
public long store() throws java.lang.Exception
java.lang.Exception
public void drop() throws java.lang.Exception
java.lang.Exception
public void reopen(boolean dropGeneratedObjects) throws java.lang.Exception
dropGeneratedObjects
is true, remove any database objects
created when Job.init was called (if it had in fact been called
in the past, as is indicated by state having a value other than DEFINE)
dropGeneratedObjects
- remove any database objects created when
Job.init was called
java.lang.Exception
public static Job lookup(long key)
key
- job key
public static Job copy(long key)
key
- configuration key
public Job.Operation getOperation()
public void setOperation(Job.Operation operation)
operation
property of Job.
operation
- operation of jobpublic boolean getCreateOutputTable()
public void setCreateOutputTable(boolean value)
value
- boolean value determining whether the output table will be
created (or dropped and recreated)public boolean getCreateSerializedSplitsTable()
public void setCreateSerializedSplitsTable(boolean value)
value
- boolean value determining whether the output table will be
created (or dropped and recreated)public int getSerializedSplitsTableRawSize()
public void setSerializedSplitsTableRawSize(int value)
value
outside the range [1, 32767] is treated as
32767
value
- size of RAW column used in output table,public boolean getCreateDeserializedSplitsTable()
public void setCreateDeserializedSplitsTable(boolean value)
value
- boolean value determining whether the output table will be
created (or dropped and recreated)public void setNumMapTasks(int tasks) throws java.lang.IllegalStateException
tasks
- the number of map tasks
java.lang.IllegalStateException
public int getNumMapTasks()
public void setNumReduceTasks(int tasks) throws java.lang.IllegalStateException
setNumReduceTasks
in class org.apache.hadoop.mapreduce.Job
tasks
- number of reduce tasks
java.lang.IllegalStateException
public void setNumHInputTasks(int tasks) throws java.lang.IllegalStateException
tasks
- the number of hinput tasks
java.lang.IllegalStateException
public int getNumHInputTasks()
public final void setJobName(java.lang.String name) throws java.lang.IllegalStateException
setJobName
in class org.apache.hadoop.mapreduce.Job
name
- the job's new name
java.lang.IllegalStateException
public void setIdString(java.lang.String theId) throws java.lang.IllegalStateException
theId
- the id string
java.lang.IllegalStateException
public java.lang.String getIdString()
public void setSchemaName(java.lang.String theSchema) throws java.lang.IllegalStateException
theSchema
- the schema name
java.lang.IllegalStateException
public java.lang.String getSchemaName()
public void setOutputSchemaName(java.lang.String theSchema) throws java.lang.IllegalStateException
theSchema
- the schema name
java.lang.IllegalStateException
public java.lang.String getOutputSchemaName()
public void setInputTableName(java.lang.String theTable) throws java.lang.IllegalStateException
theTable
- the input table name
java.lang.IllegalStateException
public java.lang.String getInputTableName()
public void setOutputTableName(java.lang.String theTable) throws java.lang.IllegalStateException
theTable
- the output table name
java.lang.IllegalStateException
public java.lang.String getOutputTableName()
public void setSerializedSplitsTableName(java.lang.String theTable) throws java.lang.IllegalStateException
theTable
- the name of the table to hold serialized InputSplits
java.lang.IllegalStateException
public java.lang.String getSerializedSplitsTableName()
public void setDeserializedSplitsTableName(java.lang.String theTable) throws java.lang.IllegalStateException
theTable
- the name of the table to hold deserialized InputSplits
java.lang.IllegalStateException
public java.lang.String getDeserializedSplitsTableName()
public void setInputFormatClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.InputFormat> cls) throws java.lang.IllegalStateException
InputFormat
for the job.
setInputFormatClass
in class org.apache.hadoop.mapreduce.Job
cls
- the InputFormat
to use
java.lang.IllegalStateException
- if the job is submittedpublic void setMapperClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Mapper> cls) throws java.lang.IllegalStateException
Mapper
for the job.
setMapperClass
in class org.apache.hadoop.mapreduce.Job
cls
- the Mapper to use
java.lang.IllegalStateException
public void setReducerClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Reducer> cls) throws java.lang.IllegalStateException
Reducer
for the job.
setReducerClass
in class org.apache.hadoop.mapreduce.Job
cls
- the Reducer to use
java.lang.IllegalStateException
public void setPartitionerClass(java.lang.Class<? extends org.apache.hadoop.mapreduce.Partitioner> cls) throws java.lang.IllegalStateException
Partitioner
for the job.
setPartitionerClass
in class org.apache.hadoop.mapreduce.Job
cls
- the Partitioner
to use
java.lang.IllegalStateException
- if the job is submittedpublic java.lang.Class<? extends org.apache.hadoop.mapreduce.Partitioner<?,?>> getPartitionerClass() throws java.lang.ClassNotFoundException
Partitioner
class for the job. Overrides the
JobContext version to change the default from
HashPartitioner.class to null.
getPartitionerClass
in interface org.apache.hadoop.mapreduce.JobContext
getPartitionerClass
in class org.apache.hadoop.mapreduce.task.JobContextImpl
Partitioner
class for the job.
java.lang.ClassNotFoundException
public void setInputKeyClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
theClass
- the input key class
java.lang.IllegalStateException
public java.lang.Class<?> getInputKeyClass()
public void setInputValueClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
theClass
- the input value class
java.lang.IllegalStateException
public java.lang.Class<?> getInputValueClass()
public void setInputSplitRecordKeyClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
theClass
- the InputSplit record key class
java.lang.IllegalStateException
public java.lang.Class<?> getInputSplitRecordKeyClass()
public void setInputSplitRecordValueClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
theClass
- the InputSplit record value class
java.lang.IllegalStateException
public java.lang.Class<?> getInputSplitRecordValueClass()
public void setMapOutputKeyClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
setMapOutputKeyClass
in class org.apache.hadoop.mapreduce.Job
theClass
- the map output key class
java.lang.IllegalStateException
public java.lang.Class<?> getMapOutputKeyClass()
getMapOutputKeyClass
in interface org.apache.hadoop.mapreduce.JobContext
getMapOutputKeyClass
in class org.apache.hadoop.mapreduce.task.JobContextImpl
public void setMapOutputValueClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
setMapOutputValueClass
in class org.apache.hadoop.mapreduce.Job
theClass
- the map output value class
java.lang.IllegalStateException
public java.lang.Class<?> getMapOutputValueClass()
getMapOutputValueClass
in interface org.apache.hadoop.mapreduce.JobContext
getMapOutputValueClass
in class org.apache.hadoop.mapreduce.task.JobContextImpl
public void setOutputKeyClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
setOutputKeyClass
in class org.apache.hadoop.mapreduce.Job
theClass
- the output key class
java.lang.IllegalStateException
public java.lang.Class<?> getOutputKeyClass()
getOutputKeyClass
in interface org.apache.hadoop.mapreduce.JobContext
getOutputKeyClass
in class org.apache.hadoop.mapreduce.task.JobContextImpl
public void setOutputValueClass(java.lang.Class<?> theClass) throws java.lang.IllegalStateException
setOutputValueClass
in class org.apache.hadoop.mapreduce.Job
theClass
- the output value class
java.lang.IllegalStateException
public java.lang.Class<?> getOutputValueClass()
getOutputValueClass
in interface org.apache.hadoop.mapreduce.JobContext
getOutputValueClass
in class org.apache.hadoop.mapreduce.task.JobContextImpl
public void setMapOutputKeyDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the map key database type
java.lang.IllegalStateException
public java.lang.String getMapOutputKeyDBType()
public void setMapOutputValueDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the map value database type
java.lang.IllegalStateException
public java.lang.String getMapOutputValueDBType()
public void setOutputKeyDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the output key database type
java.lang.IllegalStateException
public java.lang.String getOutputKeyDBType()
public void setOutputValueDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the output value database type
java.lang.IllegalStateException
public java.lang.String getOutputValueDBType()
public void setInputSplitRecordKeyDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the input split record key database type
java.lang.IllegalStateException
public java.lang.String getInputSplitRecordKeyDBType()
public void setInputSplitRecordValueDBType(java.lang.String theType) throws java.lang.IllegalStateException
theType
- the input split record value database type
java.lang.IllegalStateException
public java.lang.String getInputSplitRecordValueDBType()
public java.lang.String getMapOutputDBType()
public java.lang.String getMapOutputDBTypeSet()
public java.lang.String getOutputDBType()
public java.lang.String getOutputDBTypeSet()
public java.lang.String getInputSplitRecordDBType()
public java.lang.String getInputSplitRecordDBTypeSet()
public java.lang.String[] getInputSplitRecordDBTypes()
public void setInputSplitRecordDBTypes(java.lang.String value)
value
- comma separated list of the values that are used to set the
values in the array returned by getInputSplitRecordDBTypespublic java.lang.Class[] getInputSplitRecordClasses()
public void setInputSplitRecordClasses(java.lang.String value)
value
- comma separated list of the values that are to be used to set
the values in the array returned by getInputSplitRecordClassespublic java.lang.Class[] getInputClasses()
public void setInputClasses(java.lang.String value) throws java.lang.IllegalStateException, java.lang.ClassNotFoundException
value
- a single string comprised of comma separated class names
java.lang.IllegalStateException
java.lang.ClassNotFoundException
public void setMultiValue(boolean value)
public java.lang.String getMapperImpl()
public java.lang.String getReducerImpl()
public void setMapMethodName(java.lang.String methodName) throws java.lang.IllegalStateException
methodName
- the name of the Map method
java.lang.IllegalStateException
public java.lang.String getMapMethodName()
public java.lang.Class[] getMapMethodSignature()
public long getConfKey()
public void setDataTypeCheck(java.lang.Boolean flag) throws java.lang.IllegalStateException
flag
- the flag for data type check
java.lang.IllegalStateException
public java.lang.Boolean checkDataType()
public void resetConfigDBStore() throws java.sql.SQLException
java.sql.SQLException
public boolean getUsingHive() throws java.lang.Exception
java.lang.Exception
public static void initializeLogging()
public long init() throws java.lang.Exception
java.lang.Exception
public long init(Job.Operation operation) throws java.lang.Exception
operation
- operation of job
java.lang.Exception
public void run() throws java.lang.Exception
java.lang.Exception
public void run(java.lang.String inTable, java.lang.String outTable) throws java.lang.Exception
inTable
- the input table nameoutTable
- the output table name
java.lang.Exception
public void run(java.lang.String table) throws java.lang.Exception
table
- output table
java.lang.Exception
public boolean waitForCompletion(boolean verbose) throws java.io.IOException
waitForCompletion
in class org.apache.hadoop.mapreduce.Job
verbose
- print the progress to the user
java.io.IOException
- thrown if the Job execution failspublic void setTypeMap(java.util.Map<java.lang.String,java.lang.Class<?>> map)
map
- the java.util.Map
|
Oracle® In-Database Container for Hadoop Java API Reference Release 1.0.1 E54638-01 |
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |