Serialized Form

Package com.datasalt.pangool

Class com.datasalt.pangool.PangoolRuntimeException extends RuntimeException implements Serializable

Package com.datasalt.pangool.io

Class com.datasalt.pangool.io.Schema extends Object implements Serializable

Serialized Fields

fields

List<E> fields

name

String name

indexByFieldName

Map<K,V> indexByFieldName

nullableFields

List<E> nullableFields

nullablePositionByIndex

int[] nullablePositionByIndex

Class com.datasalt.pangool.io.Schema.Field extends Object implements Serializable

Serialized Fields

name

String name

type

Schema.Field.Type type

nullable

boolean nullable

props

com.datasalt.pangool.io.Schema.Field.Props props

objectClass

Class<T> objectClass

serializationClass

Class<T> serializationClass

cachedDefaultValue

Object cachedDefaultValue

Class com.datasalt.pangool.io.Schema.SchemaParseException extends PangoolRuntimeException implements Serializable

Class com.datasalt.pangool.io.Tuple extends Object implements Serializable

Serialized Fields

array

Object[] array

schema

Schema schema

Class com.datasalt.pangool.io.Tuple.IDontKnowHowToCopyThisStuff extends RuntimeException implements Serializable

Class com.datasalt.pangool.io.Utf8 extends org.apache.hadoop.io.Text implements Serializable

Package com.datasalt.pangool.solr

Class com.datasalt.pangool.solr.DefaultTupleDocumentConverter extends Object implements Serializable

Class com.datasalt.pangool.solr.TupleSolrOutputFormat extends org.apache.hadoop.mapreduce.lib.output.FileOutputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

batchSize

int batchSize

Size of the batch size used for indexing

threadCount

int threadCount

The number of threads that will be used for indexing

queueSize

int queueSize

The SOLR writer queue size

outputZipFile

boolean outputZipFile

Whether the output should be a ZIP of the index or not

zipName

String zipName

The zip file name used for sending the SOLR configuration in the DistributedCache

localSolrHome

String localSolrHome

The local SOLR home to be used if this is run in Hadoop's local mode (no DC)

converter

TupleDocumentConverter converter

The document converter. By default, DefaultTupleDocumentConverter, but users may implement custom ones for boosting, etc.

Package com.datasalt.pangool.tuplemr

Class com.datasalt.pangool.tuplemr.IdentityTupleMapper extends TupleMapper<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Class com.datasalt.pangool.tuplemr.IdentityTupleReducer extends TupleReducer<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Class com.datasalt.pangool.tuplemr.TupleMapper extends org.apache.hadoop.mapreduce.Mapper<INPUT_KEY,INPUT_VALUE,DatumWrapper<ITuple>,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

collector

TupleMapper.Collector collector

context

TupleMapper.TupleMRContext context

Class com.datasalt.pangool.tuplemr.TupleMRException extends Exception implements Serializable

serialVersionUID: 1L

Class com.datasalt.pangool.tuplemr.TupleReducer extends Object implements Serializable

Class com.datasalt.pangool.tuplemr.TupleRollupReducer extends TupleReducer<OUTPUT_KEY,OUTPUT_VALUE> implements Serializable

Package com.datasalt.pangool.tuplemr.avro

Class com.datasalt.pangool.tuplemr.avro.AvroInputFormat extends org.apache.hadoop.mapreduce.lib.input.FileInputFormat<org.apache.avro.mapred.AvroWrapper<T>,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

schemaStr

String schemaStr

isReflect

boolean isReflect

Class com.datasalt.pangool.tuplemr.avro.AvroOutputFormat extends org.apache.hadoop.mapreduce.lib.output.FileOutputFormat<org.apache.avro.mapred.AvroWrapper<T>,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

schemaStr

String schemaStr

deflateLevel

int deflateLevel

codecName

String codecName

Package com.datasalt.pangool.tuplemr.mapred

Class com.datasalt.pangool.tuplemr.mapred.MapOnlyMapper extends org.apache.hadoop.mapreduce.Mapper<I1,I2,O1,O2> implements Serializable

Serialized Fields

collector

MultipleOutputsCollector collector

Class com.datasalt.pangool.tuplemr.mapred.SerializerComparator extends Object implements Serializable

Package com.datasalt.pangool.tuplemr.mapred.lib.input

Class com.datasalt.pangool.tuplemr.mapred.lib.input.CascadingTupleInputFormat extends org.apache.hadoop.mapreduce.lib.input.FileInputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

schemaName

String schemaName

fieldNames

String[] fieldNames

Class com.datasalt.pangool.tuplemr.mapred.lib.input.HadoopInputFormat extends org.apache.hadoop.mapreduce.InputFormat implements Serializable

Serialized Fields

clazz

Class<T> clazz

instance

org.apache.hadoop.mapreduce.InputFormat<K,V> instance

Class com.datasalt.pangool.tuplemr.mapred.lib.input.HCatTupleInputFormat extends org.apache.hadoop.mapreduce.InputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

schema

org.apache.hcatalog.data.schema.HCatSchema schema

pangoolSchema

Schema pangoolSchema

Class com.datasalt.pangool.tuplemr.mapred.lib.input.InvalidInputException extends IOException implements Serializable

serialVersionUID: -380668190578456802L

Serialized Fields

problems

List<E> problems

Class com.datasalt.pangool.tuplemr.mapred.lib.input.TupleInputFormat extends org.apache.hadoop.mapreduce.lib.input.FileInputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

targetSchema

Schema targetSchema

Class com.datasalt.pangool.tuplemr.mapred.lib.input.TupleTextInputFormat extends org.apache.hadoop.mapreduce.lib.input.FileInputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

type

com.datasalt.pangool.tuplemr.mapred.lib.input.TupleTextInputFormat.InputType type

schema

Schema schema

hasHeader

boolean hasHeader

strictQuotes

boolean strictQuotes

separatorCharacter

char separatorCharacter

quoteCharacter

char quoteCharacter

escapeCharacter

char escapeCharacter

fieldSelector

TupleTextInputFormat.FieldSelector fieldSelector

nullString

String nullString

fixedWidthFieldsPositions

int[] fixedWidthFieldsPositions

Class com.datasalt.pangool.tuplemr.mapred.lib.input.TupleTextInputFormat.FieldSelector extends Object implements Serializable

Serialized Fields

fieldIndexesToSelect

Integer[] fieldIndexesToSelect

Package com.datasalt.pangool.tuplemr.mapred.lib.output

Class com.datasalt.pangool.tuplemr.mapred.lib.output.HadoopOutputFormat extends org.apache.hadoop.mapreduce.OutputFormat implements Serializable

Serialized Fields

clazz

Class<T> clazz

instance

org.apache.hadoop.mapreduce.OutputFormat<K,V> instance

Class com.datasalt.pangool.tuplemr.mapred.lib.output.PangoolMultipleOutputs.InvalidNamedOutputException extends IOException implements Serializable

Class com.datasalt.pangool.tuplemr.mapred.lib.output.TupleOutputFormat extends org.apache.hadoop.mapreduce.lib.output.FileOutputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

outputSchema

Schema outputSchema

Class com.datasalt.pangool.tuplemr.mapred.lib.output.TupleTextOutputFormat extends org.apache.hadoop.mapreduce.lib.output.FileOutputFormat<ITuple,org.apache.hadoop.io.NullWritable> implements Serializable

Serialized Fields

schema

Schema schema

separatorCharacter

char separatorCharacter

quoteCharacter

char quoteCharacter

escapeCharacter

char escapeCharacter

addHeader

boolean addHeader

nullString

String nullString

Package com.datasalt.pangool.tuplemr.serialization

Class com.datasalt.pangool.tuplemr.serialization.SimpleTupleSerializer.CustomObjectSerializationException extends Exception implements Serializable

Package com.datasalt.pangool.utils

Class com.datasalt.pangool.utils.AvroBinaryComparator extends Object implements Serializable

Serialized Fields

schemaStr

String schemaStr