spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From HyukjinKwon <...@git.apache.org>
Subject [GitHub] spark pull request #16976: [SPARK-19610][SQL] Support parsing multiline CSV ...
Date Thu, 23 Feb 2017 08:50:40 GMT
Github user HyukjinKwon commented on a diff in the pull request:

    https://github.com/apache/spark/pull/16976#discussion_r102664118
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala
---
    @@ -0,0 +1,256 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *    http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.spark.sql.execution.datasources.csv
    +
    +import java.io.InputStream
    +import java.nio.charset.{Charset, StandardCharsets}
    +
    +import com.univocity.parsers.csv.{CsvParser, CsvParserSettings}
    +import org.apache.hadoop.conf.Configuration
    +import org.apache.hadoop.fs.{FileStatus, Path}
    +import org.apache.hadoop.io.{LongWritable, Text}
    +import org.apache.hadoop.mapred.TextInputFormat
    +import org.apache.hadoop.mapreduce.Job
    +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
    +
    +import org.apache.spark.TaskContext
    +import org.apache.spark.input.{PortableDataStream, StreamInputFormat}
    +import org.apache.spark.rdd.{BinaryFileRDD, RDD}
    +import org.apache.spark.sql.{Dataset, Encoders, SparkSession}
    +import org.apache.spark.sql.catalyst.InternalRow
    +import org.apache.spark.sql.execution.datasources._
    +import org.apache.spark.sql.execution.datasources.text.TextFileFormat
    +import org.apache.spark.sql.types.StructType
    +
    +/**
    + * Common functions for parsing CSV files
    + */
    +abstract class CSVDataSource extends Serializable {
    +  def isSplitable: Boolean
    +
    +  /**
    +   * Parse a [[PartitionedFile]] into [[InternalRow]] instances.
    +   */
    +  def readFile(
    +      conf: Configuration,
    +      file: PartitionedFile,
    +      parser: UnivocityParser,
    +      parsedOptions: CSVOptions): Iterator[InternalRow]
    +
    +  /**
    +   * Infers the schema from `inputPaths` files.
    +   */
    +  def infer(
    +      sparkSession: SparkSession,
    +      inputPaths: Seq[FileStatus],
    +      parsedOptions: CSVOptions): Option[StructType]
    +
    +  /**
    +   * Generates a header from the given row which is null-safe and duplicate-safe.
    +   */
    +  protected def makeSafeHeader(
    +      row: Array[String],
    +      caseSensitive: Boolean,
    +      options: CSVOptions): Array[String] = {
    +    if (options.headerFlag) {
    +      val duplicates = {
    +        val headerNames = row.filter(_ != null)
    +          .map(name => if (caseSensitive) name else name.toLowerCase)
    +        headerNames.diff(headerNames.distinct).distinct
    +      }
    +
    +      row.zipWithIndex.map { case (value, index) =>
    +        if (value == null || value.isEmpty || value == options.nullValue) {
    +          // When there are empty strings or the values set in `nullValue`, put the
    +          // index as the suffix.
    +          s"_c$index"
    +        } else if (!caseSensitive && duplicates.contains(value.toLowerCase))
{
    +          // When there are case-insensitive duplicates, put the index as the suffix.
    +          s"$value$index"
    +        } else if (duplicates.contains(value)) {
    +          // When there are duplicates, put the index as the suffix.
    +          s"$value$index"
    +        } else {
    +          value
    +        }
    +      }
    +    } else {
    +      row.zipWithIndex.map { case (_, index) =>
    +        // Uses default column names, "_c#" where # is its position of fields
    +        // when header option is disabled.
    +        s"_c$index"
    +      }
    +    }
    +  }
    +}
    +
    +object CSVDataSource {
    +  def apply(options: CSVOptions): CSVDataSource = {
    +    if (options.wholeFile) {
    +      WholeFileCSVDataSource
    +    } else {
    +      TextInputCSVDataSource
    +    }
    +  }
    +}
    +
    +object TextInputCSVDataSource extends CSVDataSource {
    +  override val isSplitable: Boolean = true
    +
    +  override def readFile(
    +      conf: Configuration,
    +      file: PartitionedFile,
    +      parser: UnivocityParser,
    +      parsedOptions: CSVOptions): Iterator[InternalRow] = {
    +    val lines = {
    +      val linesReader = new HadoopFileLinesReader(file, conf)
    +      Option(TaskContext.get()).foreach(_.addTaskCompletionListener(_ => linesReader.close()))
    +      linesReader.map { line =>
    +        new String(line.getBytes, 0, line.getLength, parsedOptions.charset)
    +      }
    +    }
    +
    +    val linesWithoutHeader = if (parsedOptions.headerFlag && file.start == 0)
{
    +      // Note that if there are only comments in the first block, the header would probably
    +      // be not dropped.
    +      CSVUtils.dropHeaderLine(lines, parsedOptions)
    +    } else {
    +      lines
    +    }
    +
    +    val filteredLines: Iterator[String] =
    +      CSVUtils.filterCommentAndEmpty(linesWithoutHeader, parsedOptions)
    +    filteredLines.flatMap(parser.parse(_: String))
    +  }
    +
    +  override def infer(
    +      sparkSession: SparkSession,
    +      inputPaths: Seq[FileStatus],
    +      parsedOptions: CSVOptions): Option[StructType] = {
    +    val csv: Dataset[String] = createBaseDataset(sparkSession, inputPaths, parsedOptions)
    +    val firstLine: String = CSVUtils.filterCommentAndEmpty(csv, parsedOptions).first()
    +    val firstRow = new CsvParser(parsedOptions.asParserSettings).parseLine(firstLine)
    +    val caseSensitive = sparkSession.sessionState.conf.caseSensitiveAnalysis
    +    val header = makeSafeHeader(firstRow, caseSensitive, parsedOptions)
    +    val tokenRDD = csv.rdd.mapPartitions { iter =>
    +      val filteredLines = CSVUtils.filterCommentAndEmpty(iter, parsedOptions)
    +      val linesWithoutHeader =
    +        CSVUtils.filterHeaderLine(filteredLines, firstLine, parsedOptions)
    +      val parser = new CsvParser(parsedOptions.asParserSettings)
    +      linesWithoutHeader.map(parser.parseLine)
    +    }
    +
    +    Some(CSVInferSchema.infer(tokenRDD, header, parsedOptions))
    +  }
    +
    +  private def createBaseDataset(
    +      sparkSession: SparkSession,
    +      inputPaths: Seq[FileStatus],
    +      options: CSVOptions): Dataset[String] = {
    +    val paths = inputPaths.map(_.getPath.toString)
    +    if (Charset.forName(options.charset) == StandardCharsets.UTF_8) {
    +      sparkSession.baseRelationToDataFrame(
    +        DataSource.apply(
    +          sparkSession,
    +          paths = paths,
    +          className = classOf[TextFileFormat].getName
    +        ).resolveRelation(checkFilesExist = false))
    +        .select("value").as[String](Encoders.STRING)
    +    } else {
    +      val charset = options.charset
    +      val rdd = sparkSession.sparkContext
    +        .hadoopFile[LongWritable, Text, TextInputFormat](paths.mkString(","))
    +        .mapPartitions(_.map(pair => new String(pair._2.getBytes, 0, pair._2.getLength,
charset)))
    +      sparkSession.createDataset(rdd)(Encoders.STRING)
    +    }
    +  }
    +}
    +
    +object WholeFileCSVDataSource extends CSVDataSource {
    +  override val isSplitable: Boolean = false
    +
    +  override def readFile(
    +      conf: Configuration,
    +      file: PartitionedFile,
    +      parser: UnivocityParser,
    +      parsedOptions: CSVOptions): Iterator[InternalRow] = {
    +    UnivocityParser.tokenizeStream(
    +      createInputStream(conf, file.filePath),
    +      parsedOptions.headerFlag,
    +      parsedOptions.asParserSettings).flatMap { tokens =>
    +        parser.convert(tokens)
    +      }
    +  }
    +
    +  override def infer(
    +      sparkSession: SparkSession,
    +      inputPaths: Seq[FileStatus],
    +      parsedOptions: CSVOptions): Option[StructType] = {
    +    val csv: RDD[PortableDataStream] = createBaseRdd(sparkSession, inputPaths, parsedOptions)
    +    val firstRow = csv.mapPartitions { iter =>
    +      // We need this header line always because even if `inferSchema` option is disabled,
    +      // it needs to know the number of columns that are string types without schema
inference.
    +      iter.flatMap { lines =>
    +        UnivocityParser.tokenizeStream(
    +          createInputStream(lines.getConfiguration, lines.getPath()),
    +          false,
    +          parsedOptions.asParserSettings)
    +      }
    +    }.first()
    --- End diff --
    
    Let me check and add a test.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message