org.apache.iceberg.parquet

Class ParquetUtil

java.lang.Object

org.apache.iceberg.parquet.ParquetUtil

public class ParquetUtil
extends java.lang.Object

Method Summary

Modifier and Type	Method and Description
static org.apache.iceberg.Metrics	fileMetrics(org.apache.iceberg.io.InputFile file, org.apache.iceberg.MetricsConfig metricsConfig)
static org.apache.iceberg.Metrics	fileMetrics(org.apache.iceberg.io.InputFile file, org.apache.iceberg.MetricsConfig metricsConfig, org.apache.iceberg.mapping.NameMapping nameMapping)
static org.apache.iceberg.Metrics	footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata, java.util.stream.Stream<org.apache.iceberg.FieldMetrics<?>> fieldMetrics, org.apache.iceberg.MetricsConfig metricsConfig)
static org.apache.iceberg.Metrics	footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata, java.util.stream.Stream<org.apache.iceberg.FieldMetrics<?>> fieldMetrics, org.apache.iceberg.MetricsConfig metricsConfig, org.apache.iceberg.mapping.NameMapping nameMapping)
static java.util.List<java.lang.Long>	getSplitOffsets(org.apache.parquet.hadoop.metadata.ParquetMetadata md) Returns a list of offsets in ascending order determined by the starting position of the row groups.
static boolean	hasNoBloomFilterPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)
static boolean	hasNonDictionaryPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)
static boolean	isIntType(org.apache.parquet.schema.PrimitiveType primitiveType)
static org.apache.parquet.column.Dictionary	readDictionary(org.apache.parquet.column.ColumnDescriptor desc, org.apache.parquet.column.page.PageReader pageSource)

Methods inherited from class java.lang.Object

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

Method Detail

fileMetrics

public static org.apache.iceberg.Metrics fileMetrics(org.apache.iceberg.io.InputFile file,
                                                     org.apache.iceberg.MetricsConfig metricsConfig)

fileMetrics

public static org.apache.iceberg.Metrics fileMetrics(org.apache.iceberg.io.InputFile file,
                                                     org.apache.iceberg.MetricsConfig metricsConfig,
                                                     org.apache.iceberg.mapping.NameMapping nameMapping)

footerMetrics

public static org.apache.iceberg.Metrics footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata,
                                                       java.util.stream.Stream<org.apache.iceberg.FieldMetrics<?>> fieldMetrics,
                                                       org.apache.iceberg.MetricsConfig metricsConfig)

footerMetrics

public static org.apache.iceberg.Metrics footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata,
                                                       java.util.stream.Stream<org.apache.iceberg.FieldMetrics<?>> fieldMetrics,
                                                       org.apache.iceberg.MetricsConfig metricsConfig,
                                                       org.apache.iceberg.mapping.NameMapping nameMapping)

getSplitOffsets

public static java.util.List<java.lang.Long> getSplitOffsets(org.apache.parquet.hadoop.metadata.ParquetMetadata md)

Returns a list of offsets in ascending order determined by the starting position of the row groups.

hasNonDictionaryPages

public static boolean hasNonDictionaryPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)

hasNoBloomFilterPages

public static boolean hasNoBloomFilterPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)

readDictionary

public static org.apache.parquet.column.Dictionary readDictionary(org.apache.parquet.column.ColumnDescriptor desc,
                                                                  org.apache.parquet.column.page.PageReader pageSource)

isIntType

public static boolean isIntType(org.apache.parquet.schema.PrimitiveType primitiveType)