Question

通过Spark读取文件时的默认输入文件分隔符是换行符（\ n）。可以使用＆＃34; textinputformat.record.delimiter＆＃34;定义自定义分隔符。属性。

但是，是否可以为同一个文件指定多个分隔符？

假设文件包含以下内容：

COMMENT,A,B,C
COMMENT,D,E,
F
LIKE,I,H,G
COMMENT,J,K,
L
COMMENT,M,N,O

我想用分隔符作为COMMENT和LIKE而不是换行符来读取此文件。

虽然如果火花中不允许多个分隔符，我想出了另一种选择。

val ss = SparkSession.builder().appName("SentimentAnalysis").master("local[*]").getOrCreate()
val sc = ss.sparkContext
sc.hadoopConfiguration.set("textinputformat.record.delimiter", "COMMENT")
val rdd = sc.textFile("<filepath>")
val finalRdd = rdd.flatmap(f=>f.split("LIKE"))

但是，我认为拥有多个自定义分隔符会更好。火花有可能吗？或者我必须使用上述替代方案吗？

Answer 1

通过创建一个自定义TextInputFormat类来解决上述问题，该类拆分两个类型的分隔符字符串。 @puhlen在评论中指出的帖子是一个很大的帮助。在下面找到我使用的代码段：

import numpy as np    
x = [1,2,3,4,5]
[(np.mean((x[i],x[i+1]))) for i in range(len(x)-1)]
# [1.5, 2.5, 3.5, 4.5]

在从文件系统读取文件时使用以下类，您的文件将根据需要使用两个分隔符进行读取。：）

class CustomInputFormat extends TextInputFormat {
  override def createRecordReader(inputSplit: InputSplit,  taskAttemptContext: TaskAttemptContext): RecordReader[LongWritable, Text] = {
    return new ParagraphRecordReader();
  }
}
class ParagraphRecordReader extends RecordReader[LongWritable, Text] {
  var end: Long = 0L;
  var stillInChunk = true;

  var key = new LongWritable();
  var value = new Text();

  var fsin: FSDataInputStream = null;
  val buffer = new DataOutputBuffer();
  val tempBuffer1 = MutableList[Int]();
  val tempBuffer2 = MutableList[Int]();

  val endTag1 = "COMMENT".getBytes();
  val endTag2 = "LIKE".getBytes();

  @throws(classOf[IOException])
  @throws(classOf[InterruptedException])
  override def initialize(inputSplit: org.apache.hadoop.mapreduce.InputSplit, taskAttemptContext: org.apache.hadoop.mapreduce.TaskAttemptContext) {
    val split = inputSplit.asInstanceOf[FileSplit];
    val conf = taskAttemptContext.getConfiguration();
    val path = split.getPath();
    val fs = path.getFileSystem(conf);

    fsin = fs.open(path);
    val start = split.getStart();
    end = split.getStart() + split.getLength();
    fsin.seek(start);

    if (start != 0) {
      readUntilMatch(endTag1, endTag2, false);
    }
  }

  @throws(classOf[IOException])
  override def nextKeyValue(): Boolean = {
    if (!stillInChunk) return false;

    val status = readUntilMatch(endTag1, endTag2, true);

    value = new Text();
    value.set(buffer.getData(), 0, buffer.getLength());
    key = new LongWritable(fsin.getPos());
    buffer.reset();

    if (!status) {
      stillInChunk = false;
    }

    return true;
  }

  @throws(classOf[IOException])
  @throws(classOf[InterruptedException])
  override def getCurrentKey(): LongWritable = {
    return key;

  }


  @throws(classOf[IOException])
  @throws(classOf[InterruptedException])
  override def getCurrentValue(): Text = {
    return value;
  }

  @throws(classOf[IOException])
  @throws(classOf[InterruptedException])
  override def getProgress(): Float = {
    return 0;
  }

  @throws(classOf[IOException])
  override def close() {
    fsin.close();
  }

  @throws(classOf[IOException])
  def readUntilMatch(match1: Array[Byte], match2: Array[Byte], withinBlock: Boolean): Boolean = {
    var i = 0;
    var j = 0;
    while (true) {
      val b = fsin.read();
      if (b == -1) return false;

      if (b == match1(i)) {
        tempBuffer1.+=(b)
        i = i + 1;
        if (i >= match1.length) {
          tempBuffer1.clear()
          return fsin.getPos() < end;
        }
      } else if (b == match2(j)) {
        tempBuffer2.+=(b)
        j = j + 1;
        if (j >= match2.length) {
          tempBuffer2.clear()
          return fsin.getPos() < end;
        }
      } else {
        if (tempBuffer1.size != 0)
          tempBuffer1.foreach { x => if (withinBlock) buffer.write(x) }
        else if (tempBuffer2.size != 0)
          tempBuffer2.foreach { x => if (withinBlock) buffer.write(x) }
        tempBuffer1.clear()
        tempBuffer2.clear()
        if (withinBlock) buffer.write(b);
        i = 0;
        j = 0;
      }
    }
    return false;
  }

如何在spark中为输入文件定义多个自定义分隔符？

1 个答案: