org.apache.spark.sql.catalyst.parser.CatalystSqlParser Scala Examples

The following examples show how to use org.apache.spark.sql.catalyst.parser.CatalystSqlParser. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: OrcFileOperator.scala    From drizzle-spark   with Apache License 2.0 6 votes vote down vote up 
package org.apache.spark.sql.hive.orc

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hive.ql.io.orc.{OrcFile, Reader}
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector

import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.types.StructType

private[orc] object OrcFileOperator extends Logging {
  
  def getFileReader(basePath: String, config: Option[Configuration] = None): Option[Reader] = {
    def isWithNonEmptySchema(path: Path, reader: Reader): Boolean = {
      reader.getObjectInspector match {
        case oi: StructObjectInspector if oi.getAllStructFieldRefs.size() == 0 =>
          logInfo(
            s"ORC file $path has empty schema, it probably contains no rows. " +
              "Trying to read another ORC file to figure out the schema.")
          false
        case _ => true
      }
    }

    val conf = config.getOrElse(new Configuration)
    val fs = {
      val hdfsPath = new Path(basePath)
      hdfsPath.getFileSystem(conf)
    }

    listOrcFiles(basePath, conf).iterator.map { path =>
      path -> OrcFile.createReader(fs, path)
    }.collectFirst {
      case (path, reader) if isWithNonEmptySchema(path, reader) => reader
    }
  }

  def readSchema(paths: Seq[String], conf: Option[Configuration]): Option[StructType] = {
    // Take the first file where we can open a valid reader if we can find one.  Otherwise just
    // return None to indicate we can't infer the schema.
    paths.flatMap(getFileReader(_, conf)).headOption.map { reader =>
      val readerInspector = reader.getObjectInspector.asInstanceOf[StructObjectInspector]
      val schema = readerInspector.getTypeName
      logDebug(s"Reading schema from file $paths, got Hive schema string: $schema")
      CatalystSqlParser.parseDataType(schema).asInstanceOf[StructType]
    }
  }

  def getObjectInspector(
      path: String, conf: Option[Configuration]): Option[StructObjectInspector] = {
    getFileReader(path, conf).map(_.getObjectInspector.asInstanceOf[StructObjectInspector])
  }

  def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = {
    // TODO: Check if the paths coming in are already qualified and simplify.
    val origPath = new Path(pathStr)
    val fs = origPath.getFileSystem(conf)
    val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath)
      .filterNot(_.isDirectory)
      .map(_.getPath)
      .filterNot(_.getName.startsWith("_"))
      .filterNot(_.getName.startsWith("."))
    paths
  }
}
Example 2
Source File: OrcFileOperator.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hive.orc

import java.io.IOException

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hive.ql.io.orc.{OrcFile, Reader}
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector

import org.apache.spark.SparkException
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.types.StructType

private[hive] object OrcFileOperator extends Logging {
  
  def getFileReader(basePath: String,
      config: Option[Configuration] = None,
      ignoreCorruptFiles: Boolean = false)
      : Option[Reader] = {
    def isWithNonEmptySchema(path: Path, reader: Reader): Boolean = {
      reader.getObjectInspector match {
        case oi: StructObjectInspector if oi.getAllStructFieldRefs.size() == 0 =>
          logInfo(
            s"ORC file $path has empty schema, it probably contains no rows. " +
              "Trying to read another ORC file to figure out the schema.")
          false
        case _ => true
      }
    }

    val conf = config.getOrElse(new Configuration)
    val fs = {
      val hdfsPath = new Path(basePath)
      hdfsPath.getFileSystem(conf)
    }

    listOrcFiles(basePath, conf).iterator.map { path =>
      val reader = try {
        Some(OrcFile.createReader(fs, path))
      } catch {
        case e: IOException =>
          if (ignoreCorruptFiles) {
            logWarning(s"Skipped the footer in the corrupted file: $path", e)
            None
          } else {
            throw new SparkException(s"Could not read footer for file: $path", e)
          }
      }
      path -> reader
    }.collectFirst {
      case (path, Some(reader)) if isWithNonEmptySchema(path, reader) => reader
    }
  }

  def readSchema(paths: Seq[String], conf: Option[Configuration], ignoreCorruptFiles: Boolean)
      : Option[StructType] = {
    // Take the first file where we can open a valid reader if we can find one.  Otherwise just
    // return None to indicate we can't infer the schema.
    paths.toIterator.map(getFileReader(_, conf, ignoreCorruptFiles)).collectFirst {
      case Some(reader) =>
        val readerInspector = reader.getObjectInspector.asInstanceOf[StructObjectInspector]
        val schema = readerInspector.getTypeName
        logDebug(s"Reading schema from file $paths, got Hive schema string: $schema")
        CatalystSqlParser.parseDataType(schema).asInstanceOf[StructType]
    }
  }

  def getObjectInspector(
      path: String, conf: Option[Configuration]): Option[StructObjectInspector] = {
    getFileReader(path, conf).map(_.getObjectInspector.asInstanceOf[StructObjectInspector])
  }

  def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = {
    // TODO: Check if the paths coming in are already qualified and simplify.
    val origPath = new Path(pathStr)
    val fs = origPath.getFileSystem(conf)
    val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath)
      .filterNot(_.isDirectory)
      .map(_.getPath)
      .filterNot(_.getName.startsWith("_"))
      .filterNot(_.getName.startsWith("."))
    paths
  }
}
Example 3
Source File: PythonSQLUtils.scala    From XSQL   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.api.python

import java.io.InputStream
import java.nio.channels.Channels

import org.apache.spark.api.java.JavaRDD
import org.apache.spark.api.python.PythonRDDServer
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.sql.catalyst.analysis.FunctionRegistry
import org.apache.spark.sql.catalyst.expressions.ExpressionInfo
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.execution.arrow.ArrowConverters
import org.apache.spark.sql.types.DataType

private[sql] object PythonSQLUtils {
  def parseDataType(typeText: String): DataType = CatalystSqlParser.parseDataType(typeText)

  // This is needed when generating SQL documentation for built-in functions.
  def listBuiltinFunctionInfos(): Array[ExpressionInfo] = {
    FunctionRegistry.functionSet.flatMap(f => FunctionRegistry.builtin.lookupFunction(f)).toArray
  }

  
private[sql] class ArrowRDDServer(sqlContext: SQLContext) extends PythonRDDServer {

  override protected def streamToRDD(input: InputStream): RDD[Array[Byte]] = {
    // Create array to consume iterator so that we can safely close the inputStream
    val batches = ArrowConverters.getBatchesFromStream(Channels.newChannel(input)).toArray
    // Parallelize the record batches to create an RDD
    JavaRDD.fromRDD(sqlContext.sparkContext.parallelize(batches, batches.length))
  }

}
Example 4
Source File: OrcFileOperator.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hive.orc

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hive.ql.io.orc.{OrcFile, Reader}
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector

import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.types.StructType

private[orc] object OrcFileOperator extends Logging {
  
  def getFileReader(basePath: String, config: Option[Configuration] = None): Option[Reader] = {
    def isWithNonEmptySchema(path: Path, reader: Reader): Boolean = {
      reader.getObjectInspector match {
        case oi: StructObjectInspector if oi.getAllStructFieldRefs.size() == 0 =>
          logInfo(
            s"ORC file $path has empty schema, it probably contains no rows. " +
              "Trying to read another ORC file to figure out the schema.")
          false
        case _ => true
      }
    }

    val conf = config.getOrElse(new Configuration)
    val fs = {
      val hdfsPath = new Path(basePath)
      hdfsPath.getFileSystem(conf)
    }

    listOrcFiles(basePath, conf).iterator.map { path =>
      path -> OrcFile.createReader(fs, path)
    }.collectFirst {
      case (path, reader) if isWithNonEmptySchema(path, reader) => reader
    }
  }

  def readSchema(paths: Seq[String], conf: Option[Configuration]): Option[StructType] = {
    // Take the first file where we can open a valid reader if we can find one.  Otherwise just
    // return None to indicate we can't infer the schema.
    paths.flatMap(getFileReader(_, conf)).headOption.map { reader =>
      val readerInspector = reader.getObjectInspector.asInstanceOf[StructObjectInspector]
      val schema = readerInspector.getTypeName
      logDebug(s"Reading schema from file $paths, got Hive schema string: $schema")
      CatalystSqlParser.parseDataType(schema).asInstanceOf[StructType]
    }
  }

  def getObjectInspector(
      path: String, conf: Option[Configuration]): Option[StructObjectInspector] = {
    getFileReader(path, conf).map(_.getObjectInspector.asInstanceOf[StructObjectInspector])
  }

  def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = {
    // TODO: Check if the paths coming in are already qualified and simplify.
    val origPath = new Path(pathStr)
    val fs = origPath.getFileSystem(conf)
    val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath)
      .filterNot(_.isDirectory)
      .map(_.getPath)
      .filterNot(_.getName.startsWith("_"))
      .filterNot(_.getName.startsWith("."))
    paths
  }
}
Example 5
Source File: OrcFileOperator.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hive.orc

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hive.ql.io.orc.{OrcFile, Reader}
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector

import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.types.StructType

private[orc] object OrcFileOperator extends Logging {
  
  def getFileReader(basePath: String, config: Option[Configuration] = None): Option[Reader] = {
    def isWithNonEmptySchema(path: Path, reader: Reader): Boolean = {
      reader.getObjectInspector match {
        case oi: StructObjectInspector if oi.getAllStructFieldRefs.size() == 0 =>
          logInfo(
            s"ORC file $path has empty schema, it probably contains no rows. " +
              "Trying to read another ORC file to figure out the schema.")
          false
        case _ => true
      }
    }

    val conf = config.getOrElse(new Configuration)
    val fs = {
      val hdfsPath = new Path(basePath)
      hdfsPath.getFileSystem(conf)
    }

    listOrcFiles(basePath, conf).iterator.map { path =>
      path -> OrcFile.createReader(fs, path)
    }.collectFirst {
      case (path, reader) if isWithNonEmptySchema(path, reader) => reader
    }
  }

  def readSchema(paths: Seq[String], conf: Option[Configuration]): Option[StructType] = {
    // Take the first file where we can open a valid reader if we can find one.  Otherwise just
    // return None to indicate we can't infer the schema.
    paths.flatMap(getFileReader(_, conf)).headOption.map { reader =>
      val readerInspector = reader.getObjectInspector.asInstanceOf[StructObjectInspector]
      val schema = readerInspector.getTypeName
      logDebug(s"Reading schema from file $paths, got Hive schema string: $schema")
      CatalystSqlParser.parseDataType(schema).asInstanceOf[StructType]
    }
  }

  def getObjectInspector(
      path: String, conf: Option[Configuration]): Option[StructObjectInspector] = {
    getFileReader(path, conf).map(_.getObjectInspector.asInstanceOf[StructObjectInspector])
  }

  def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = {
    // TODO: Check if the paths coming in are already qualified and simplify.
    val origPath = new Path(pathStr)
    val fs = origPath.getFileSystem(conf)
    val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath)
      .filterNot(_.isDirectory)
      .map(_.getPath)
      .filterNot(_.getName.startsWith("_"))
      .filterNot(_.getName.startsWith("."))
    paths
  }
}
Example 6
Source File: ResolveHintsSuite.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.catalyst.analysis

import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.dsl.plans._
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.catalyst.plans.Inner
import org.apache.spark.sql.catalyst.plans.logical._

class ResolveHintsSuite extends AnalysisTest {
  import org.apache.spark.sql.catalyst.analysis.TestRelations._

  test("invalid hints should be ignored") {
    checkAnalysis(
      UnresolvedHint("some_random_hint_that_does_not_exist", Seq("TaBlE"), table("TaBlE")),
      testRelation,
      caseSensitive = false)
  }

  test("case-sensitive or insensitive parameters") {
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("TaBlE"), table("TaBlE")),
      ResolvedHint(testRelation, HintInfo(broadcast = true)),
      caseSensitive = false)

    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table"), table("TaBlE")),
      ResolvedHint(testRelation, HintInfo(broadcast = true)),
      caseSensitive = false)

    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("TaBlE"), table("TaBlE")),
      ResolvedHint(testRelation, HintInfo(broadcast = true)),
      caseSensitive = true)

    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table"), table("TaBlE")),
      testRelation,
      caseSensitive = true)
  }

  test("multiple broadcast hint aliases") {
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table", "table2"), table("table").join(table("table2"))),
      Join(ResolvedHint(testRelation, HintInfo(broadcast = true)),
        ResolvedHint(testRelation2, HintInfo(broadcast = true)), Inner, None),
      caseSensitive = false)
  }

  test("do not traverse past existing broadcast hints") {
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table"),
        ResolvedHint(table("table").where('a > 1), HintInfo(broadcast = true))),
      ResolvedHint(testRelation.where('a > 1), HintInfo(broadcast = true)).analyze,
      caseSensitive = false)
  }

  test("should work for subqueries") {
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("tableAlias"), table("table").as("tableAlias")),
      ResolvedHint(testRelation, HintInfo(broadcast = true)),
      caseSensitive = false)

    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("tableAlias"), table("table").subquery('tableAlias)),
      ResolvedHint(testRelation, HintInfo(broadcast = true)),
      caseSensitive = false)

    // Negative case: if the alias doesn't match, don't match the original table name.
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table"), table("table").as("tableAlias")),
      testRelation,
      caseSensitive = false)
  }

  test("do not traverse past subquery alias") {
    checkAnalysis(
      UnresolvedHint("MAPJOIN", Seq("table"), table("table").where('a > 1).subquery('tableAlias)),
      testRelation.where('a > 1).analyze,
      caseSensitive = false)
  }

  test("should work for CTE") {
    checkAnalysis(
      CatalystSqlParser.parsePlan(
        """
          |WITH ctetable AS (SELECT * FROM table WHERE a > 1)
          |SELECT  * FROM ctetable
        """.stripMargin
      ),
      testRelation.where('a > 1).select('a).select('a).analyze,
      caseSensitive = false)
  }
}
Example 7
Source File: PythonSQLUtils.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.api.python

import org.apache.spark.api.java.JavaRDD
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.sql.catalyst.analysis.FunctionRegistry
import org.apache.spark.sql.catalyst.expressions.ExpressionInfo
import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
import org.apache.spark.sql.execution.arrow.ArrowConverters
import org.apache.spark.sql.types.DataType

private[sql] object PythonSQLUtils {
  def parseDataType(typeText: String): DataType = CatalystSqlParser.parseDataType(typeText)

  // This is needed when generating SQL documentation for built-in functions.
  def listBuiltinFunctionInfos(): Array[ExpressionInfo] = {
    FunctionRegistry.functionSet.flatMap(f => FunctionRegistry.builtin.lookupFunction(f)).toArray
  }

  
  def arrowPayloadToDataFrame(
      payloadRDD: JavaRDD[Array[Byte]],
      schemaString: String,
      sqlContext: SQLContext): DataFrame = {
    ArrowConverters.toDataFrame(payloadRDD, schemaString, sqlContext)
  }
}