ParquetExtractor implements BatchableExtractor, Extractor, FileExtractor, MetadataColumnsExtractor, SplittableExtractor
FinalYes
Interfaces
- BatchableExtractor
- Extractor
- FileExtractor
- MetadataColumnsExtractor
- SplittableExtractor
Methods
- __construct() : mixed
- __destruct() : mixed
- batchSize() : int<1, max>
- extract() : Generator<Signal|null, void>
- isRepeatable() : bool
- partitionSchema() : Schema
- partitionTypes() : static
- prunes() : bool
- reader() : FileSplitReader
- refresh() : void
- schema() : Schema
- source() : Path
- splits() : array<int, FileSplit>
- Byte windows over every admitted file; a row group belongs to the window holding its midpoint.
- statistics() : Statistics
- unionByName() : self
- Reconcile every listed file's schema instead of trusting the first one.
- withBatchSize() : static
- withByteOrder() : self
- withColumns() : self
- withEngine() : self
- withMetadataColumns() : static
- withOptions() : self
- withSchema() : static
Methods
__construct()
public
__construct(Path $path[, Filesystem $filesystem = new NativeLocalFilesystem() ]) : mixed
Parameters
- $path : Path
- $filesystem : Filesystem = new NativeLocalFilesystem()
__destruct()
public
__destruct() : mixed
batchSize()
public
batchSize() : int<1, max>
Return values
int<1, max>extract()
public
extract(Backend $backend, Criteria $criteria) : Generator<Signal|null, void>
Parameters
- $backend : Backend
- $criteria : Criteria
Return values
Generator<Signal|null, void>isRepeatable()
public
isRepeatable() : bool
Return values
boolpartitionSchema()
public
partitionSchema() : Schema
Return values
SchemapartitionTypes()
public
partitionTypes(PartitionTypes $types) : static
Parameters
- $types : PartitionTypes
Return values
staticprunes()
public
prunes(ScalarFunction $conjunct) : bool
Parameters
- $conjunct : ScalarFunction
Return values
boolreader()
public
reader() : FileSplitReader
Return values
FileSplitReaderrefresh()
public
refresh() : void
schema()
public
schema() : Schema
Return values
Schemasource()
public
source() : Path
Return values
Pathsplits()
Byte windows over every admitted file; a row group belongs to the window holding its midpoint.
public
splits(Criteria $criteria, int $targetSplitBytes) : array<int, FileSplit>
Parameters
- $criteria : Criteria
- $targetSplitBytes : int
Return values
array<int, FileSplit>statistics()
public
statistics() : Statistics
Return values
StatisticsunionByName()
Reconcile every listed file's schema instead of trusting the first one.
public
unionByName([bool $union = true ]) : self
Parameters
- $union : bool = true
Return values
selfwithBatchSize()
public
withBatchSize(int $batchSize) : static
Parameters
- $batchSize : int
Return values
staticwithByteOrder()
public
withByteOrder(ByteOrder $byteOrder) : self
Parameters
- $byteOrder : ByteOrder
Return values
selfwithColumns()
public
withColumns(array<string|int, string> $columns) : self
Parameters
- $columns : array<string|int, string>
Return values
selfwithEngine()
public
withEngine(ParquetEngine|null $engine) : self
Parameters
- $engine : ParquetEngine|null
Return values
selfwithMetadataColumns()
public
withMetadataColumns(bool $addMetadataColumns) : static
Parameters
- $addMetadataColumns : bool
Return values
staticwithOptions()
public
withOptions(Options $options) : self
Parameters
- $options : Options
Return values
selfwithSchema()
public
withSchema(Schema $schema) : static
Parameters
- $schema : Schema