Constructor and Description |
---|
FilteringParquetRowInputFormat() |
Modifier and Type | Method and Description |
---|---|
org.apache.hadoop.mapreduce.RecordReader<Void,org.apache.spark.sql.Row> |
createRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit,
org.apache.hadoop.mapreduce.TaskAttemptContext taskAttemptContext) |
java.util.List<parquet.hadoop.ParquetInputSplit> |
getClientSideSplits(org.apache.hadoop.conf.Configuration configuration,
java.util.List<parquet.hadoop.Footer> footers,
Long maxSplitSize,
Long minSplitSize,
parquet.hadoop.api.ReadSupport.ReadContext readContext) |
java.util.List<parquet.hadoop.ParquetInputSplit> |
getSplits(org.apache.hadoop.conf.Configuration configuration,
java.util.List<parquet.hadoop.Footer> footers) |
java.util.List<org.apache.hadoop.mapreduce.InputSplit> |
getSplits(org.apache.hadoop.mapreduce.JobContext jobContext) |
java.util.List<parquet.hadoop.ParquetInputSplit> |
getTaskSideSplits(org.apache.hadoop.conf.Configuration configuration,
java.util.List<parquet.hadoop.Footer> footers,
Long maxSplitSize,
Long minSplitSize,
parquet.hadoop.api.ReadSupport.ReadContext readContext) |
getFilter, getFooters, getFooters, getFooters, getGlobalMetaData, getReadSupport, getReadSupportClass, getUnboundRecordFilter, isTaskSideMetaData, setFilterPredicate, setReadSupportClass, setReadSupportClass, setTaskSideMetaData, setUnboundRecordFilter
addInputPath, addInputPaths, getInputPathFilter, getInputPaths, getMaxSplitSize, getMinSplitSize, setInputPathFilter, setInputPaths, setInputPaths, setMaxInputSplitSize, setMinInputSplitSize
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
initializeIfNecessary, initializeLogging, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning
public org.apache.hadoop.mapreduce.RecordReader<Void,org.apache.spark.sql.Row> createRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit, org.apache.hadoop.mapreduce.TaskAttemptContext taskAttemptContext)
createRecordReader
in class parquet.hadoop.ParquetInputFormat<org.apache.spark.sql.Row>
public java.util.List<org.apache.hadoop.mapreduce.InputSplit> getSplits(org.apache.hadoop.mapreduce.JobContext jobContext)
getSplits
in class parquet.hadoop.ParquetInputFormat<org.apache.spark.sql.Row>
public java.util.List<parquet.hadoop.ParquetInputSplit> getSplits(org.apache.hadoop.conf.Configuration configuration, java.util.List<parquet.hadoop.Footer> footers)
getSplits
in class parquet.hadoop.ParquetInputFormat<org.apache.spark.sql.Row>
public java.util.List<parquet.hadoop.ParquetInputSplit> getClientSideSplits(org.apache.hadoop.conf.Configuration configuration, java.util.List<parquet.hadoop.Footer> footers, Long maxSplitSize, Long minSplitSize, parquet.hadoop.api.ReadSupport.ReadContext readContext)
public java.util.List<parquet.hadoop.ParquetInputSplit> getTaskSideSplits(org.apache.hadoop.conf.Configuration configuration, java.util.List<parquet.hadoop.Footer> footers, Long maxSplitSize, Long minSplitSize, parquet.hadoop.api.ReadSupport.ReadContext readContext)