public class VectorizedParquetRecordReader extends ParquetRecordReaderBase implements org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
Modifier and Type | Field and Description |
---|---|
protected org.apache.parquet.schema.MessageType |
fileSchema |
static org.slf4j.Logger |
LOG |
protected org.apache.parquet.schema.MessageType |
requestedSchema |
protected long |
totalRowCount
The total number of rows this RecordReader will eventually read.
|
file, filtedBlocks, jobConf, projectionPusher, reader, schemaSize, serDeStats, skipTimestampConversion
Constructor and Description |
---|
VectorizedParquetRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit,
org.apache.hadoop.mapred.JobConf conf) |
VectorizedParquetRecordReader(org.apache.hadoop.mapred.InputSplit oldInputSplit,
org.apache.hadoop.mapred.JobConf conf) |
Modifier and Type | Method and Description |
---|---|
void |
close() |
org.apache.hadoop.io.NullWritable |
createKey() |
org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch |
createValue() |
long |
getPos() |
float |
getProgress() |
void |
initialize(org.apache.hadoop.mapreduce.InputSplit oldSplit,
org.apache.hadoop.mapred.JobConf configuration) |
boolean |
next(org.apache.hadoop.io.NullWritable nullWritable,
org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch vectorizedRowBatch) |
getFiltedBlocks, getSplit, getStats, setFilter
public static final org.slf4j.Logger LOG
protected org.apache.parquet.schema.MessageType fileSchema
protected org.apache.parquet.schema.MessageType requestedSchema
protected long totalRowCount
public VectorizedParquetRecordReader(org.apache.hadoop.mapreduce.InputSplit inputSplit, org.apache.hadoop.mapred.JobConf conf)
public VectorizedParquetRecordReader(org.apache.hadoop.mapred.InputSplit oldInputSplit, org.apache.hadoop.mapred.JobConf conf)
public void initialize(org.apache.hadoop.mapreduce.InputSplit oldSplit, org.apache.hadoop.mapred.JobConf configuration) throws IOException, InterruptedException
IOException
InterruptedException
public boolean next(org.apache.hadoop.io.NullWritable nullWritable, org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch vectorizedRowBatch) throws IOException
next
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
IOException
public org.apache.hadoop.io.NullWritable createKey()
createKey
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
public org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch createValue()
createValue
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
public long getPos() throws IOException
getPos
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
IOException
public void close() throws IOException
close
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
IOException
public float getProgress() throws IOException
getProgress
in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch>
IOException
Copyright © 2021 The Apache Software Foundation. All rights reserved.