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

import java.util

import com.trueaccord.scalapb.{GeneratedMessage, GeneratedMessageCompanion, Message}
import org.apache.hadoop.conf.Configuration
import org.apache.parquet.hadoop.api.{InitContext, ReadSupport}
import org.apache.parquet.hadoop.api.ReadSupport.ReadContext
import org.apache.parquet.io.api.{GroupConverter, RecordMaterializer}
import org.apache.parquet.schema.MessageType

class ScalaPBReadSupport[T <: GeneratedMessage with Message[T]] extends ReadSupport[T] {
  override def prepareForRead(
    configuration: Configuration,
    keyValueMetaData: util.Map[String, String],
    fileSchema: MessageType,
    readContext: ReadContext): RecordMaterializer[T] = {
    val protoClass = Option(keyValueMetaData.get(ScalaPBReadSupport.PB_CLASS)).getOrElse(throw new RuntimeException(s"Value for ${ScalaPBReadSupport.PB_CLASS} not found."))
    val cmp = {
      import scala.reflect.runtime.universe

      val runtimeMirror = universe.runtimeMirror(getClass.getClassLoader)

      val module = runtimeMirror.staticModule(protoClass)

      val obj = runtimeMirror.reflectModule(module)

      obj.instance.asInstanceOf[GeneratedMessageCompanion[T]]
    }

    new RecordMaterializer[T] {
      val root = new ProtoMessageConverter[T](cmp, fileSchema, onEnd = _ => ())

      override def getRootConverter: GroupConverter = root

      override def getCurrentRecord: T = root.getCurrentRecord
    }
  }

  override def init(context: InitContext): ReadContext = {
    new ReadContext(context.getFileSchema)
  }
}

object ScalaPBReadSupport {
  val PB_CLASS = "parquet.scalapb.class"
} 

//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.{Predicate, Row}
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.parquet.filter2.compat.FilterCompat
import org.apache.parquet.hadoop.api.ReadSupport
import org.apache.parquet.hadoop.{ParquetInputFormat, ParquetReader}
import org.apache.parquet.schema.Type


  def apply(path: Path,
            predicate: Option[Predicate],
            readSchema: Option[Type],
            dictionaryFiltering: Boolean)(implicit conf: Configuration): ParquetReader[Row] = {
    logger.debug(s"Opening parquet reader for $path")

    // The parquet reader can use a projection by setting a projected schema onto the supplied conf object
    def configuration(): Configuration = {
      val newconf = new Configuration(conf)
      readSchema.foreach { it =>
        newconf.set(ReadSupport.PARQUET_READ_SCHEMA, it.toString)
      }
      newconf.set(ParquetInputFormat.DICTIONARY_FILTERING_ENABLED, dictionaryFiltering.toString)
      newconf.set(org.apache.parquet.hadoop.ParquetFileReader.PARQUET_READ_PARALLELISM, config.parallelism.toString)
      newconf
    }

    // a filter is set when we have a predicate for the read
    def filter(): FilterCompat.Filter = predicate.map(ParquetPredicateBuilder.build)
      .map(FilterCompat.get)
      .getOrElse(FilterCompat.NOOP)

    ParquetReader.builder(new RowReadSupport, path)
      .withConf(configuration())
      .withFilter(filter())
      .build()
  }
}