当前位置: 首页>>代码示例>>Scala>>正文


Scala WriteSupport类代码示例

本文整理汇总了Scala中org.apache.parquet.hadoop.api.WriteSupport的典型用法代码示例。如果您正苦于以下问题:Scala WriteSupport类的具体用法?Scala WriteSupport怎么用?Scala WriteSupport使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。


在下文中一共展示了WriteSupport类的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Scala代码示例。

示例1: ScalaPBWriteSupport

//设置package包名称以及导入依赖的类
package com.trueaccord.scalapb.parquet

import java.util

import com.google.protobuf.Descriptors.Descriptor
import com.trueaccord.scalapb.{GeneratedMessage, Message}
import org.apache.hadoop.conf.Configuration
import org.apache.parquet.hadoop.BadConfigurationException
import org.apache.parquet.hadoop.api.WriteSupport
import org.apache.parquet.hadoop.api.WriteSupport.WriteContext
import org.apache.parquet.io.api.RecordConsumer
import org.apache.parquet.schema.MessageType

class ScalaPBWriteSupport[T <: GeneratedMessage with Message[T]] extends WriteSupport[T] {
  var pbClass: Class[T] = null
  var recordConsumer: RecordConsumer = null

  override def init(configuration: Configuration): WriteContext = {
    if (pbClass == null) {
      pbClass = configuration.getClass(ScalaPBWriteSupport.SCALAPB_CLASS_WRITE, null, classOf[GeneratedMessage]).asInstanceOf[Class[T]]
      if (pbClass == null) {
        throw new BadConfigurationException("ScalaPB class not specified. Please use ScalaPBOutputFormat.setMessageClass.")
      }
    }
    val descriptor: Descriptor = pbClass.getMethod("descriptor").invoke(null).asInstanceOf[Descriptor]
    val rootSchema: MessageType = SchemaConverter.convert(descriptor)
    val extraMetaDtata = new util.HashMap[String, String]
    extraMetaDtata.put(ScalaPBReadSupport.PB_CLASS, pbClass.getName)
    new WriteContext(rootSchema, extraMetaDtata)
  }

  override def write(record: T): Unit = {
    MessageWriter.writeTopLevelMessage(recordConsumer, record)
  }

  override def prepareForWrite(recordConsumer: RecordConsumer): Unit = {
    this.recordConsumer = recordConsumer
  }
}

object ScalaPBWriteSupport {
  val SCALAPB_CLASS_WRITE = "parquet.scalapb.writeClass"

  def setSchema[T <: GeneratedMessage](config: Configuration, protoClass: Class[T]) = {
    config.setClass(SCALAPB_CLASS_WRITE, protoClass, classOf[GeneratedMessage])
  }
} 
开发者ID:scalapb,项目名称:sparksql-scalapb,代码行数:48,代码来源:ScalaPBWriteSupport.scala

示例2: RowWriteSupport

//设置package包名称以及导入依赖的类
package io.eels.component.parquet

import com.sksamuel.exts.Logging
import io.eels.Row
import org.apache.hadoop.conf.Configuration
import org.apache.parquet.hadoop.api.WriteSupport
import org.apache.parquet.hadoop.api.WriteSupport.FinalizedWriteContext
import org.apache.parquet.io.api.RecordConsumer
import org.apache.parquet.schema.MessageType

import scala.collection.JavaConverters._
import scala.math.BigDecimal.RoundingMode.RoundingMode

// implementation of WriteSupport for Row's used by the native ParquetWriter
class RowWriteSupport(schema: MessageType,
                      roundingMode: RoundingMode,
                      metadata: Map[String, String]) extends WriteSupport[Row] with Logging {
  logger.trace(s"Created parquet row write support for schema message type $schema")

  private var writer: RowWriter = _

  override def finalizeWrite(): FinalizedWriteContext = new FinalizedWriteContext(metadata.asJava)

  def init(configuration: Configuration): WriteSupport.WriteContext = {
    new WriteSupport.WriteContext(schema, new java.util.HashMap())
  }

  def prepareForWrite(record: RecordConsumer) {
    writer = new RowWriter(record, roundingMode)
  }

  def write(row: Row) {
    writer.write(row)
  }
}

class RowWriter(record: RecordConsumer, roundingMode: RoundingMode) {

  def write(row: Row): Unit = {
    record.startMessage()
    val writer = new StructRecordWriter(row.schema, roundingMode, false)
    writer.write(record, row.values)
    record.endMessage()
  }
} 
开发者ID:51zero,项目名称:eel-sdk,代码行数:46,代码来源:RowWriteSupport.scala

示例3: RowParquetWriterFn

//设置package包名称以及导入依赖的类
package io.eels.component.parquet

import io.eels.Row
import io.eels.schema.StructType
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.parquet.column.ParquetProperties
import org.apache.parquet.hadoop.api.WriteSupport
import org.apache.parquet.hadoop.{ParquetFileWriter, ParquetWriter}
import org.apache.parquet.schema.MessageType

import scala.math.BigDecimal.RoundingMode.RoundingMode


object RowParquetWriterFn {

  class RowParquetWriterBuilder(path: Path,
                                schema: MessageType,
                                roundingMode: RoundingMode,
                                metadata: Map[String, String])
    extends ParquetWriter.Builder[Row, RowParquetWriterBuilder](path) {
    override def getWriteSupport(conf: Configuration): WriteSupport[Row] = new RowWriteSupport(schema, roundingMode, metadata)
    override def self(): RowParquetWriterBuilder = this
  }

  def apply(path: Path,
            schema: StructType,
            metadata: Map[String, String],
            dictionary: Boolean,
            roundingMode: RoundingMode): ParquetWriter[Row] = {
    val config = ParquetWriterConfig()
    val messageType = ParquetSchemaFns.toParquetMessageType(schema)
    new RowParquetWriterBuilder(path, messageType, roundingMode, metadata)
      .withCompressionCodec(config.compressionCodec)
      .withDictionaryEncoding(dictionary)
      .withDictionaryPageSize(ParquetProperties.DEFAULT_DICTIONARY_PAGE_SIZE)
      .withPageSize(config.pageSize)
      .withRowGroupSize(config.blockSize)
      .withValidation(config.validating)
      .withWriteMode(ParquetFileWriter.Mode.CREATE)
      .withWriterVersion(ParquetProperties.DEFAULT_WRITER_VERSION)
      .build()
  }
} 
开发者ID:51zero,项目名称:eel-sdk,代码行数:45,代码来源:RowParquetWriterFn.scala


注:本文中的org.apache.parquet.hadoop.api.WriteSupport类示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。