org.apache.iceberg.spark.actions

Class RewriteManifestsSparkAction

java.lang.Object

org.apache.iceberg.spark.actions.RewriteManifestsSparkAction

All Implemented Interfaces:

org.apache.iceberg.actions.Action<org.apache.iceberg.actions.RewriteManifests,org.apache.iceberg.actions.RewriteManifests.Result>, org.apache.iceberg.actions.RewriteManifests, org.apache.iceberg.actions.SnapshotUpdate<org.apache.iceberg.actions.RewriteManifests,org.apache.iceberg.actions.RewriteManifests.Result>

public class RewriteManifestsSparkAction
extends java.lang.Object
implements org.apache.iceberg.actions.RewriteManifests

An action that rewrites manifests in a distributed manner and co-locates metadata for partitions.

By default, this action rewrites all manifests for the current partition spec and writes the result to the metadata folder. The behavior can be modified by passing a custom predicate to rewriteIf(Predicate) and a custom spec id to specId(int). In addition, there is a way to configure a custom location for new manifests via stagingLocation.

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.iceberg.actions.RewriteManifests

org.apache.iceberg.actions.RewriteManifests.Result

Field Summary

Fields

Modifier and Type	Field and Description
protected static org.apache.iceberg.relocated.com.google.common.base.Joiner	COMMA_JOINER
protected static org.apache.iceberg.relocated.com.google.common.base.Splitter	COMMA_SPLITTER
protected static java.lang.String	FILE_PATH
protected static java.lang.String	LAST_MODIFIED
protected static java.lang.String	MANIFEST
protected static java.lang.String	MANIFEST_LIST
protected static java.lang.String	OTHERS
protected static java.lang.String	STATISTICS_FILES
static java.lang.String	USE_CACHING
static boolean	USE_CACHING_DEFAULT

Method Summary

Modifier and Type	Method and Description
protected org.apache.spark.sql.Dataset<FileInfo>	allReachableOtherMetadataFileDS(org.apache.iceberg.Table table)
protected void	commit(org.apache.iceberg.SnapshotUpdate<?> update)
protected org.apache.spark.sql.Dataset<FileInfo>	contentFileDS(org.apache.iceberg.Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	contentFileDS(org.apache.iceberg.Table table, java.util.Set<java.lang.Long> snapshotIds)
protected org.apache.iceberg.spark.actions.BaseSparkAction.DeleteSummary	deleteFiles(java.util.concurrent.ExecutorService executorService, java.util.function.Consumer<java.lang.String> deleteFunc, java.util.Iterator<FileInfo> files) Deletes files and keeps track of how many files were removed for each file type.
protected org.apache.iceberg.spark.actions.BaseSparkAction.DeleteSummary	deleteFiles(org.apache.iceberg.io.SupportsBulkOperations io, java.util.Iterator<FileInfo> files)
org.apache.iceberg.actions.RewriteManifests.Result	execute()
protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	loadMetadataTable(org.apache.iceberg.Table table, org.apache.iceberg.MetadataTableType type)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestDS(org.apache.iceberg.Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestDS(org.apache.iceberg.Table table, java.util.Set<java.lang.Long> snapshotIds)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestListDS(org.apache.iceberg.Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestListDS(org.apache.iceberg.Table table, java.util.Set<java.lang.Long> snapshotIds)
protected JobGroupInfo	newJobGroupInfo(java.lang.String groupId, java.lang.String desc)
protected org.apache.iceberg.Table	newStaticTable(org.apache.iceberg.TableMetadata metadata, org.apache.iceberg.io.FileIO io)
ThisT	option(java.lang.String name, java.lang.String value)
protected java.util.Map<java.lang.String,java.lang.String>	options()
ThisT	options(java.util.Map<java.lang.String,java.lang.String> newOptions)
protected org.apache.spark.sql.Dataset<FileInfo>	otherMetadataFileDS(org.apache.iceberg.Table table)
RewriteManifestsSparkAction	rewriteIf(java.util.function.Predicate<org.apache.iceberg.ManifestFile> newPredicate)
protected RewriteManifestsSparkAction	self()
ThisT	snapshotProperty(java.lang.String property, java.lang.String value)
protected org.apache.spark.sql.SparkSession	spark()
protected org.apache.spark.api.java.JavaSparkContext	sparkContext()
RewriteManifestsSparkAction	specId(int specId)
RewriteManifestsSparkAction	stagingLocation(java.lang.String newStagingLocation)
protected org.apache.spark.sql.Dataset<FileInfo>	statisticsFileDS(org.apache.iceberg.Table table, java.util.Set<java.lang.Long> snapshotIds)
protected <T> T	withJobGroupInfo(JobGroupInfo info, java.util.function.Supplier<T> supplier)

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.iceberg.actions.SnapshotUpdate

snapshotProperty

Methods inherited from interface org.apache.iceberg.actions.Action

option, options

Field Detail

USE_CACHING

public static final java.lang.String USE_CACHING

See Also:

Constant Field Values

USE_CACHING_DEFAULT

public static final boolean USE_CACHING_DEFAULT

See Also:

Constant Field Values

MANIFEST

protected static final java.lang.String MANIFEST

See Also:

Constant Field Values

MANIFEST_LIST

protected static final java.lang.String MANIFEST_LIST

See Also:

Constant Field Values

STATISTICS_FILES

protected static final java.lang.String STATISTICS_FILES

See Also:

Constant Field Values

OTHERS

protected static final java.lang.String OTHERS

See Also:

Constant Field Values

FILE_PATH

protected static final java.lang.String FILE_PATH

See Also:

Constant Field Values

LAST_MODIFIED

protected static final java.lang.String LAST_MODIFIED

See Also:

Constant Field Values

COMMA_SPLITTER

protected static final org.apache.iceberg.relocated.com.google.common.base.Splitter COMMA_SPLITTER

COMMA_JOINER

protected static final org.apache.iceberg.relocated.com.google.common.base.Joiner COMMA_JOINER

Method Detail

self

protected RewriteManifestsSparkAction self()

specId

public RewriteManifestsSparkAction specId(int specId)

Specified by:

specId in interface org.apache.iceberg.actions.RewriteManifests

rewriteIf

public RewriteManifestsSparkAction rewriteIf(java.util.function.Predicate<org.apache.iceberg.ManifestFile> newPredicate)

Specified by:

rewriteIf in interface org.apache.iceberg.actions.RewriteManifests

stagingLocation

public RewriteManifestsSparkAction stagingLocation(java.lang.String newStagingLocation)

Specified by:

stagingLocation in interface org.apache.iceberg.actions.RewriteManifests

execute

public org.apache.iceberg.actions.RewriteManifests.Result execute()

Specified by:

execute in interface org.apache.iceberg.actions.Action<org.apache.iceberg.actions.RewriteManifests,org.apache.iceberg.actions.RewriteManifests.Result>

snapshotProperty

public ThisT snapshotProperty(java.lang.String property,
                              java.lang.String value)

commit

protected void commit(org.apache.iceberg.SnapshotUpdate<?> update)

spark

protected org.apache.spark.sql.SparkSession spark()

sparkContext

protected org.apache.spark.api.java.JavaSparkContext sparkContext()

option

public ThisT option(java.lang.String name,
                    java.lang.String value)

options

public ThisT options(java.util.Map<java.lang.String,java.lang.String> newOptions)

options

protected java.util.Map<java.lang.String,java.lang.String> options()

withJobGroupInfo

protected <T> T withJobGroupInfo(JobGroupInfo info,
                                 java.util.function.Supplier<T> supplier)

newJobGroupInfo

protected JobGroupInfo newJobGroupInfo(java.lang.String groupId,
                                       java.lang.String desc)

newStaticTable

protected org.apache.iceberg.Table newStaticTable(org.apache.iceberg.TableMetadata metadata,
                                                  org.apache.iceberg.io.FileIO io)

contentFileDS

protected org.apache.spark.sql.Dataset<FileInfo> contentFileDS(org.apache.iceberg.Table table)

contentFileDS

protected org.apache.spark.sql.Dataset<FileInfo> contentFileDS(org.apache.iceberg.Table table,
                                                               java.util.Set<java.lang.Long> snapshotIds)

manifestDS

protected org.apache.spark.sql.Dataset<FileInfo> manifestDS(org.apache.iceberg.Table table)

manifestDS

protected org.apache.spark.sql.Dataset<FileInfo> manifestDS(org.apache.iceberg.Table table,
                                                            java.util.Set<java.lang.Long> snapshotIds)

manifestListDS

protected org.apache.spark.sql.Dataset<FileInfo> manifestListDS(org.apache.iceberg.Table table)

manifestListDS

protected org.apache.spark.sql.Dataset<FileInfo> manifestListDS(org.apache.iceberg.Table table,
                                                                java.util.Set<java.lang.Long> snapshotIds)

statisticsFileDS

protected org.apache.spark.sql.Dataset<FileInfo> statisticsFileDS(org.apache.iceberg.Table table,
                                                                  java.util.Set<java.lang.Long> snapshotIds)

otherMetadataFileDS

protected org.apache.spark.sql.Dataset<FileInfo> otherMetadataFileDS(org.apache.iceberg.Table table)

allReachableOtherMetadataFileDS

protected org.apache.spark.sql.Dataset<FileInfo> allReachableOtherMetadataFileDS(org.apache.iceberg.Table table)

loadMetadataTable

protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> loadMetadataTable(org.apache.iceberg.Table table,
                                                                                   org.apache.iceberg.MetadataTableType type)

deleteFiles

protected org.apache.iceberg.spark.actions.BaseSparkAction.DeleteSummary deleteFiles(java.util.concurrent.ExecutorService executorService,
                                                                                     java.util.function.Consumer<java.lang.String> deleteFunc,
                                                                                     java.util.Iterator<FileInfo> files)

Deletes files and keeps track of how many files were removed for each file type.

Parameters:

executorService - an executor service to use for parallel deletes

deleteFunc - a delete func

files - an iterator of Spark rows of the structure (path: String, type: String)

Returns:

stats on which files were deleted

deleteFiles

protected org.apache.iceberg.spark.actions.BaseSparkAction.DeleteSummary deleteFiles(org.apache.iceberg.io.SupportsBulkOperations io,
                                                                                     java.util.Iterator<FileInfo> files)