org.apache.paimon.operation

Class AbstractFileStoreScan

java.lang.Object

org.apache.paimon.operation.AbstractFileStoreScan

All Implemented Interfaces:

FileStoreScan

Direct Known Subclasses:

AppendOnlyFileStoreScan, KeyValueFileStoreScan

public abstract class AbstractFileStoreScan
extends Object
implements FileStoreScan

Default implementation of FileStoreScan.

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.paimon.operation.FileStoreScan

FileStoreScan.Plan

Field Summary

Fields

Modifier and Type	Field and Description
protected ScanMode	scanMode

Constructor Summary

Constructors

Constructor and Description
AbstractFileStoreScan(ManifestsReader manifestsReader, SnapshotManager snapshotManager, SchemaManager schemaManager, TableSchema schema, ManifestFile.Factory manifestFileFactory, Integer parallelism)

Method Summary

Modifier and Type	Method and Description
protected abstract boolean	filterByStats(ManifestEntry entry) Note: Keep this thread-safe.
protected abstract List<ManifestEntry>	filterWholeBucketByStats(List<ManifestEntry> entries) Note: Keep this thread-safe.
ManifestsReader	manifestsReader()
Integer	parallelism()
FileStoreScan.Plan	plan() Produce a FileStoreScan.Plan.
<T extends FileEntry> Collection<T>	readAndMergeFileEntries(List<ManifestFileMeta> manifests, java.util.function.Function<ManifestFileMeta,List<T>> manifestReader)
List<BucketEntry>	readBucketEntries()
Iterator<ManifestEntry>	readFileIterator()
List<ManifestEntry>	readManifest(ManifestFileMeta manifest) Note: Keep this thread-safe.
List<PartitionEntry>	readPartitionEntries()
List<SimpleFileEntry>	readSimpleEntries() Read SimpleFileEntrys, SimpleFileEntry only retains some critical information, so it cannot perform filtering based on statistical information.
protected TableSchema	scanTableSchema(long id) Note: Keep this thread-safe.
FileStoreScan	withBucket(int bucket)
FileStoreScan	withBucketFilter(Filter<Integer> bucketFilter)
FileStoreScan	withDataFileNameFilter(Filter<String> fileNameFilter)
FileStoreScan	withKind(ScanMode scanMode)
FileStoreScan	withLevelFilter(Filter<Integer> levelFilter)
FileStoreScan	withManifestCacheFilter(ManifestCacheFilter manifestFilter)
FileStoreScan	withManifestEntryFilter(Filter<ManifestEntry> filter)
FileStoreScan	withManifestList(List<ManifestFileMeta> manifests)
FileStoreScan	withMetrics(ScanMetrics metrics)
FileStoreScan	withPartitionBucket(BinaryRow partition, int bucket)
FileStoreScan	withPartitionFilter(List<BinaryRow> partitions)
FileStoreScan	withPartitionFilter(PartitionPredicate predicate)
FileStoreScan	withPartitionFilter(Predicate predicate)
FileStoreScan	withSnapshot(long snapshotId)
FileStoreScan	withSnapshot(Snapshot snapshot)
FileStoreScan	withTotalAwareBucketFilter(BiFilter<Integer,Integer> totalAwareBucketFilter)

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.paimon.operation.FileStoreScan

listPartitions, totalRecordCount

Field Detail

scanMode

protected ScanMode scanMode

Constructor Detail

AbstractFileStoreScan

public AbstractFileStoreScan(ManifestsReader manifestsReader,
                             SnapshotManager snapshotManager,
                             SchemaManager schemaManager,
                             TableSchema schema,
                             ManifestFile.Factory manifestFileFactory,
                             @Nullable
                             Integer parallelism)

Method Detail

withPartitionFilter

public FileStoreScan withPartitionFilter(Predicate predicate)

Specified by:

withPartitionFilter in interface FileStoreScan

withPartitionFilter

public FileStoreScan withPartitionFilter(List<BinaryRow> partitions)

Specified by:

withPartitionFilter in interface FileStoreScan

withPartitionFilter

public FileStoreScan withPartitionFilter(PartitionPredicate predicate)

Specified by:

withPartitionFilter in interface FileStoreScan

withBucket

public FileStoreScan withBucket(int bucket)

Specified by:

withBucket in interface FileStoreScan

withBucketFilter

public FileStoreScan withBucketFilter(Filter<Integer> bucketFilter)

Specified by:

withBucketFilter in interface FileStoreScan

withTotalAwareBucketFilter

public FileStoreScan withTotalAwareBucketFilter(BiFilter<Integer,Integer> totalAwareBucketFilter)

Specified by:

withTotalAwareBucketFilter in interface FileStoreScan

withPartitionBucket

public FileStoreScan withPartitionBucket(BinaryRow partition,
                                         int bucket)

Specified by:

withPartitionBucket in interface FileStoreScan

withSnapshot

public FileStoreScan withSnapshot(long snapshotId)

Specified by:

withSnapshot in interface FileStoreScan

withSnapshot

public FileStoreScan withSnapshot(Snapshot snapshot)

Specified by:

withSnapshot in interface FileStoreScan

withManifestList

public FileStoreScan withManifestList(List<ManifestFileMeta> manifests)

Specified by:

withManifestList in interface FileStoreScan

withKind

public FileStoreScan withKind(ScanMode scanMode)

Specified by:

withKind in interface FileStoreScan

withLevelFilter

public FileStoreScan withLevelFilter(Filter<Integer> levelFilter)

Specified by:

withLevelFilter in interface FileStoreScan

withManifestEntryFilter

public FileStoreScan withManifestEntryFilter(Filter<ManifestEntry> filter)

Specified by:

withManifestEntryFilter in interface FileStoreScan

withManifestCacheFilter

public FileStoreScan withManifestCacheFilter(ManifestCacheFilter manifestFilter)

Specified by:

withManifestCacheFilter in interface FileStoreScan

withDataFileNameFilter

public FileStoreScan withDataFileNameFilter(Filter<String> fileNameFilter)

Specified by:

withDataFileNameFilter in interface FileStoreScan

withMetrics

public FileStoreScan withMetrics(ScanMetrics metrics)

Specified by:

withMetrics in interface FileStoreScan

parallelism

@Nullable
public Integer parallelism()

Specified by:

parallelism in interface FileStoreScan

manifestsReader

public ManifestsReader manifestsReader()

Specified by:

manifestsReader in interface FileStoreScan

plan

public FileStoreScan.Plan plan()

Description copied from interface: FileStoreScan

Produce a FileStoreScan.Plan.

Specified by:

plan in interface FileStoreScan

readSimpleEntries

public List<SimpleFileEntry> readSimpleEntries()

Description copied from interface: FileStoreScan

Read SimpleFileEntrys, SimpleFileEntry only retains some critical information, so it cannot perform filtering based on statistical information.

Specified by:

readSimpleEntries in interface FileStoreScan

readPartitionEntries

public List<PartitionEntry> readPartitionEntries()

Specified by:

readPartitionEntries in interface FileStoreScan

readBucketEntries

public List<BucketEntry> readBucketEntries()

Specified by:

readBucketEntries in interface FileStoreScan

readFileIterator

public Iterator<ManifestEntry> readFileIterator()

Specified by:

readFileIterator in interface FileStoreScan

readAndMergeFileEntries

public <T extends FileEntry> Collection<T> readAndMergeFileEntries(List<ManifestFileMeta> manifests,
                                                                   java.util.function.Function<ManifestFileMeta,List<T>> manifestReader)

scanTableSchema

protected TableSchema scanTableSchema(long id)

Note: Keep this thread-safe.

filterByStats

protected abstract boolean filterByStats(ManifestEntry entry)

Note: Keep this thread-safe.

filterWholeBucketByStats

protected abstract List<ManifestEntry> filterWholeBucketByStats(List<ManifestEntry> entries)

Note: Keep this thread-safe.

readManifest

public List<ManifestEntry> readManifest(ManifestFileMeta manifest)

Note: Keep this thread-safe.

Specified by:

readManifest in interface FileStoreScan