public class ParquetUtil
extends java.lang.Object
Modifier and Type | Method and Description |
---|---|
static long |
extractTimestampInt96(java.nio.ByteBuffer buffer)
Method to read timestamp (parquet Int96) from bytebuffer.
|
static Metrics |
fileMetrics(InputFile file,
MetricsConfig metricsConfig) |
static Metrics |
fileMetrics(InputFile file,
MetricsConfig metricsConfig,
NameMapping nameMapping) |
static Metrics |
footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata,
java.util.stream.Stream<FieldMetrics<?>> fieldMetrics,
MetricsConfig metricsConfig) |
static Metrics |
footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata,
java.util.stream.Stream<FieldMetrics<?>> fieldMetrics,
MetricsConfig metricsConfig,
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) |
public static Metrics fileMetrics(InputFile file, MetricsConfig metricsConfig)
public static Metrics fileMetrics(InputFile file, MetricsConfig metricsConfig, NameMapping nameMapping)
public static Metrics footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata, java.util.stream.Stream<FieldMetrics<?>> fieldMetrics, MetricsConfig metricsConfig)
public static Metrics footerMetrics(org.apache.parquet.hadoop.metadata.ParquetMetadata metadata, java.util.stream.Stream<FieldMetrics<?>> fieldMetrics, MetricsConfig metricsConfig, NameMapping nameMapping)
public static java.util.List<java.lang.Long> getSplitOffsets(org.apache.parquet.hadoop.metadata.ParquetMetadata md)
public static boolean hasNonDictionaryPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)
public static boolean hasNoBloomFilterPages(org.apache.parquet.hadoop.metadata.ColumnChunkMetaData meta)
public static org.apache.parquet.column.Dictionary readDictionary(org.apache.parquet.column.ColumnDescriptor desc, org.apache.parquet.column.page.PageReader pageSource)
public static boolean isIntType(org.apache.parquet.schema.PrimitiveType primitiveType)
public static long extractTimestampInt96(java.nio.ByteBuffer buffer)