public class AvroParquetWriter<T extends org.apache.avro.generic.IndexedRecord> extends ParquetWriter<T>
DEFAULT_BLOCK_SIZE, DEFAULT_COMPRESSION_CODEC_NAME, DEFAULT_IS_DICTIONARY_ENABLED, DEFAULT_IS_VALIDATING_ENABLED, DEFAULT_PAGE_SIZE, DEFAULT_WRITER_VERSION
Constructor and Description |
---|
AvroParquetWriter(org.apache.hadoop.fs.Path file,
org.apache.avro.Schema avroSchema)
Create a new
AvroParquetWriter . |
AvroParquetWriter(org.apache.hadoop.fs.Path file,
org.apache.avro.Schema avroSchema,
CompressionCodecName compressionCodecName,
int blockSize,
int pageSize)
Create a new
AvroParquetWriter . |
AvroParquetWriter(org.apache.hadoop.fs.Path file,
org.apache.avro.Schema avroSchema,
CompressionCodecName compressionCodecName,
int blockSize,
int pageSize,
boolean enableDictionary)
Create a new
AvroParquetWriter . |
AvroParquetWriter(org.apache.hadoop.fs.Path file,
org.apache.avro.Schema avroSchema,
CompressionCodecName compressionCodecName,
int blockSize,
int pageSize,
boolean enableDictionary,
org.apache.hadoop.conf.Configuration conf)
Create a new
AvroParquetWriter . |
public AvroParquetWriter(org.apache.hadoop.fs.Path file, org.apache.avro.Schema avroSchema, CompressionCodecName compressionCodecName, int blockSize, int pageSize) throws IOException
AvroParquetWriter
.file
- avroSchema
- compressionCodecName
- blockSize
- pageSize
- IOException
public AvroParquetWriter(org.apache.hadoop.fs.Path file, org.apache.avro.Schema avroSchema, CompressionCodecName compressionCodecName, int blockSize, int pageSize, boolean enableDictionary) throws IOException
AvroParquetWriter
.file
- The file name to write to.avroSchema
- The schema to write with.compressionCodecName
- Compression code to use, or CompressionCodecName.UNCOMPRESSEDblockSize
- the block size threshold.pageSize
- See parquet write up. Blocks are subdivided into pages for alignment and other purposes.enableDictionary
- Whether to use a dictionary to compress columns.IOException
public AvroParquetWriter(org.apache.hadoop.fs.Path file, org.apache.avro.Schema avroSchema) throws IOException
AvroParquetWriter
. The default block size is 50 MB.The default
page size is 1 MB. Default compression is no compression. (Inherited from ParquetWriter
)file
- The file name to write to.avroSchema
- The schema to write with.IOException
public AvroParquetWriter(org.apache.hadoop.fs.Path file, org.apache.avro.Schema avroSchema, CompressionCodecName compressionCodecName, int blockSize, int pageSize, boolean enableDictionary, org.apache.hadoop.conf.Configuration conf) throws IOException
AvroParquetWriter
.file
- The file name to write to.avroSchema
- The schema to write with.compressionCodecName
- Compression code to use, or CompressionCodecName.UNCOMPRESSEDblockSize
- the block size threshold.pageSize
- See parquet write up. Blocks are subdivided into pages for alignment and other purposes.enableDictionary
- Whether to use a dictionary to compress columns.conf
- The Configuration to use.IOException
Copyright © 2015. All rights reserved.