【spark系列8】spark delta读数据实现分析

override def createRelation(
      sqlContext: SQLContext,
      parameters: Map[String, String]): BaseRelation = {
    val maybePath = parameters.getOrElse("path", {
      throw DeltaErrors.pathNotSpecifiedException
    })
    // Log any invalid options that are being passed in
    DeltaOptions.verifyOptions(CaseInsensitiveMap(parameters))
    val timeTravelByParams = DeltaDataSource.getTimeTravelVersion(parameters)
    DeltaTableV2(
      sqlContext.sparkSession,
      new Path(maybePath),
      timeTravelOpt = timeTravelByParams).toBaseRelation
  }

val validOptionKeys : Set[String] = Set(
    REPLACE_WHERE_OPTION,
    MERGE_SCHEMA_OPTION,
    EXCLUDE_REGEX_OPTION,
    OVERWRITE_SCHEMA_OPTION,
    USER_METADATA_OPTION,
    MAX_FILES_PER_TRIGGER_OPTION,
    IGNORE_FILE_DELETION_OPTION,
    IGNORE_CHANGES_OPTION,
    IGNORE_DELETES_OPTION,
    OPTIMIZE_WRITE_OPTION,
    DATA_CHANGE_OPTION,
    "queryName",
    "checkpointLocation",
    "path",
    "timestampAsOf",
    "versionAsOf"
  )

def toBaseRelation: BaseRelation = {
    if (deltaLog.snapshot.version == -1) {
      val id = catalogTable.map(ct => DeltaTableIdentifier(table = Some(ct.identifier)))
        .getOrElse(DeltaTableIdentifier(path = Some(path.toString)))
      throw DeltaErrors.notADeltaTableException(id)
    }
    val partitionPredicates = DeltaDataSource.verifyAndCreatePartitionFilters(
      path.toString, deltaLog.snapshot, partitionFilters)
    // TODO(burak): We should pass in the snapshot here
    deltaLog.createRelation(partitionPredicates, timeTravelSpec)
  }

def createRelation(
   partitionFilters: Seq[Expression] = Nil,
   timeTravel: Option[DeltaTimeTravelSpec] = None): BaseRelation = {
 val versionToUse = timeTravel.map { tt =>
   val (version, accessType) = DeltaTableUtils.resolveTimeTravelVersion(
     spark.sessionState.conf, this, tt)
   val source = tt.creationSource.getOrElse("unknown")
   recordDeltaEvent(this, s"delta.timeTravel.$source", data = Map(
     "tableVersion" -> snapshot.version,
     "queriedVersion" -> version,
     "accessType" -> accessType
   ))
   version
 }
 /** Used to link the files present in the table into the query planner. */
 val snapshotToUse = versionToUse.map(getSnapshotAt(_)).getOrElse(snapshot)
 val fileIndex = TahoeLogFileIndex(
   spark, this, dataPath, snapshotToUse.metadata.schema, partitionFilters, versionToUse)
 new HadoopFsRelation(
   fileIndex,
   partitionSchema = snapshotToUse.metadata.partitionSchema,
   dataSchema = snapshotToUse.metadata.schema,
   bucketSpec = None,
   snapshotToUse.fileFormat,
   snapshotToUse.metadata.format.options)(spark) with InsertableRelation {
   def insert(data: DataFrame, overwrite: Boolean): Unit = {
     val mode = if (overwrite) SaveMode.Overwrite else SaveMode.Append
     WriteIntoDelta(
       deltaLog = DeltaLog.this,
       mode = mode,
       new DeltaOptions(Map.empty[String, String], spark.sessionState.conf),
       partitionColumns = Seq.empty,
       configuration = Map.empty,
       data = data).run(spark)
   }
 }

override def inputFiles: Array[String] = {
getSnapshot(stalenessAcceptable = false).filesForScan(
  projection = Nil, partitionFilters).files.map(f => absolutePath(f.path).toString).toArray
}

def filesForScan(projection: Seq[Attribute], filters: Seq[Expression]): DeltaScan = {
implicit val enc = SingleAction.addFileEncoder
val partitionFilters = filters.flatMap { filter =>
  DeltaTableUtils.splitMetadataAndDataPredicates(filter, metadata.partitionColumns, spark)._1
}
val files = DeltaLog.filterFileList(
  metadata.partitionSchema,
  allFiles.toDF(),
  partitionFilters).as[AddFile].collect()
DeltaScan(version = version, files, null, null, null)(null, null, null, null)
}

def allFiles: Dataset[AddFile] = {
 val implicits = spark.implicits
 import implicits._
 state.where("add IS NOT NULL").select($"add".as[AddFile])
 }

private lazy val cachedState =
 cacheDS(stateReconstruction, s"Delta Table State #$version - $redactedPath")
 /** The current set of actions in this [[Snapshot]]. */
 def state: Dataset[SingleAction] = cachedState.getDS

private def stateReconstruction: Dataset[SingleAction] = {
 ...
 loadActions.mapPartitions { actions =>
     val hdpConf = hadoopConf.value.value
     actions.flatMap {
       _.unwrap match {
         case add: AddFile => Some(add.copy(path = canonicalizePath(add.path, hdpConf)).wrap)
         case rm: RemoveFile => Some(rm.copy(path = canonicalizePath(rm.path, hdpConf)).wrap)
         case other if other == null => None
         case other => Some(other.wrap)
       }
     }
    }
   ...
   .mapPartitions { iter =>
     val state = new InMemoryLogReplay(time)
     state.append(0, iter.map(_.unwrap))
     state.checkpoint.map(_.wrap)
   }
  }

  assert(currentVersion == -1 || version == currentVersion + 1,
   s"Attempted to replay version $version, but state is at $currentVersion")
 currentVersion = version
 actions.foreach {
   case a: SetTransaction =>
     transactions(a.appId) = a
   case a: Metadata =>
     currentMetaData = a
   case a: Protocol =>
     currentProtocolVersion = a
   case add: AddFile =>
     activeFiles(add.pathAsUri) = add.copy(dataChange = false)
     // Remove the tombstone to make sure we only output one `FileAction`.
     tombstones.remove(add.pathAsUri)
   case remove: RemoveFile =>
     activeFiles.remove(remove.pathAsUri)
     tombstones(remove.pathAsUri) = remove.copy(dataChange = false)
   case ci: CommitInfo => // do nothing
   case null => // Some crazy future feature. Ignore
  }
 }