Package org.apache.iceberg.spark.actions

Class RewriteDataFilesSparkAction

java.lang.Object

org.apache.iceberg.spark.actions.RewriteDataFilesSparkAction

All Implemented Interfaces:

Action<RewriteDataFiles,RewriteDataFiles.Result>, RewriteDataFiles, SnapshotUpdate<RewriteDataFiles,RewriteDataFiles.Result>

public class RewriteDataFilesSparkAction
extends java.lang.Object
implements RewriteDataFiles

Nested Class Summary

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

RewriteDataFiles.FileGroupInfo, RewriteDataFiles.FileGroupRewriteResult, RewriteDataFiles.Result

Field Summary

Fields

Modifier and Type	Field	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

Fields inherited from interface org.apache.iceberg.actions.RewriteDataFiles

MAX_CONCURRENT_FILE_GROUP_REWRITES, MAX_CONCURRENT_FILE_GROUP_REWRITES_DEFAULT, MAX_FILE_GROUP_SIZE_BYTES, MAX_FILE_GROUP_SIZE_BYTES_DEFAULT, PARTIAL_PROGRESS_ENABLED, PARTIAL_PROGRESS_ENABLED_DEFAULT, PARTIAL_PROGRESS_MAX_COMMITS, PARTIAL_PROGRESS_MAX_COMMITS_DEFAULT, REWRITE_JOB_ORDER, REWRITE_JOB_ORDER_DEFAULT, TARGET_FILE_SIZE_BYTES, USE_STARTING_SEQUENCE_NUMBER, USE_STARTING_SEQUENCE_NUMBER_DEFAULT

Method Summary

Modifier and Type	Method	Description
protected org.apache.spark.sql.Dataset<FileInfo>	allReachableOtherMetadataFileDS(Table table)
RewriteDataFilesSparkAction	binPack()	Choose BINPACK as a strategy for this rewrite operation
protected void	commit(SnapshotUpdate<?> update)
protected org.apache.spark.sql.Dataset<FileInfo>	contentFileDS(Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	contentFileDS(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(SupportsBulkOperations io, java.util.Iterator<FileInfo> files)
RewriteDataFiles.Result	execute()	Executes this action.
RewriteDataFilesSparkAction	filter(Expression expression)	A user provided filter for determining which files will be considered by the rewrite strategy.
protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	loadMetadataTable(Table table, MetadataTableType type)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestDS(Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestDS(Table table, java.util.Set<java.lang.Long> snapshotIds)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestListDS(Table table)
protected org.apache.spark.sql.Dataset<FileInfo>	manifestListDS(Table table, java.util.Set<java.lang.Long> snapshotIds)
protected JobGroupInfo	newJobGroupInfo(java.lang.String groupId, java.lang.String desc)
protected Table	newStaticTable(TableMetadata metadata, 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(Table table)
protected RewriteDataFilesSparkAction	self()
ThisT	snapshotProperty(java.lang.String property, java.lang.String value)
RewriteDataFilesSparkAction	sort()	Choose SORT as a strategy for this rewrite operation using the table's sortOrder
RewriteDataFilesSparkAction	sort(SortOrder sortOrder)	Choose SORT as a strategy for this rewrite operation and manually specify the sortOrder to use
protected org.apache.spark.sql.SparkSession	spark()
protected org.apache.spark.api.java.JavaSparkContext	sparkContext()
protected org.apache.spark.sql.Dataset<FileInfo>	statisticsFileDS(Table table, java.util.Set<java.lang.Long> snapshotIds)
protected <T> T	withJobGroupInfo(JobGroupInfo info, java.util.function.Supplier<T> supplier)
RewriteDataFilesSparkAction	zOrder(java.lang.String... columnNames)	Choose Z-ORDER as a strategy for this rewrite operation with a specified list of columns to use

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.Action

option, options

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

snapshotProperty

Field Detail

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 RewriteDataFilesSparkAction self()

binPack

public RewriteDataFilesSparkAction binPack()

Description copied from interface: RewriteDataFiles

Choose BINPACK as a strategy for this rewrite operation

Specified by:

binPack in interface RewriteDataFiles

Returns:

this for method chaining

sort

public RewriteDataFilesSparkAction sort(SortOrder sortOrder)

Description copied from interface: RewriteDataFiles

Choose SORT as a strategy for this rewrite operation and manually specify the sortOrder to use

Specified by:

sort in interface RewriteDataFiles

Parameters:

sortOrder - user defined sortOrder

Returns:

this for method chaining

sort

public RewriteDataFilesSparkAction sort()

Description copied from interface: RewriteDataFiles

Choose SORT as a strategy for this rewrite operation using the table's sortOrder

Specified by:

sort in interface RewriteDataFiles

Returns:

this for method chaining

zOrder

public RewriteDataFilesSparkAction zOrder(java.lang.String... columnNames)

Description copied from interface: RewriteDataFiles

Choose Z-ORDER as a strategy for this rewrite operation with a specified list of columns to use

Specified by:

zOrder in interface RewriteDataFiles

Parameters:

columnNames - Columns to be used to generate Z-Values

Returns:

this for method chaining

filter

public RewriteDataFilesSparkAction filter(Expression expression)

Description copied from interface: RewriteDataFiles

A user provided filter for determining which files will be considered by the rewrite strategy. This will be used in addition to whatever rules the rewrite strategy generates. For example this would be used for providing a restriction to only run rewrite on a specific partition.

Specified by:

filter in interface RewriteDataFiles

Parameters:

expression - An iceberg expression used to determine which files will be considered for rewriting

Returns:

this for chaining

execute

public RewriteDataFiles.Result execute()

Description copied from interface: Action

Executes this action.

Specified by:

execute in interface Action<RewriteDataFiles,RewriteDataFiles.Result>

Returns:

the result of this action

snapshotProperty

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

commit

protected void commit(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 Table newStaticTable(TableMetadata metadata,
                               FileIO io)

contentFileDS

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

contentFileDS

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

manifestDS

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

manifestDS

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

manifestListDS

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

manifestListDS

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

statisticsFileDS

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

otherMetadataFileDS

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

allReachableOtherMetadataFileDS

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

loadMetadataTable

protected org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> loadMetadataTable(Table table,
                                                                                   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(SupportsBulkOperations io,
                                                                                     java.util.Iterator<FileInfo> files)