这很简单。

这是源代码，

import java.nio.charset.Charset

import org.apache.hadoop.io.{Text, LongWritable}
import org.apache.hadoop.mapred.TextInputFormat
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD

object TextFile {
  val DEFAULT_CHARSET = Charset.forName("UTF-8")

  def withCharset(context: SparkContext, location: String, charset: String): RDD[String] = {
    if (Charset.forName(charset) == DEFAULT_CHARSET) {
      context.textFile(location)
    } else {
      // can't pass a Charset object here cause its not serializable
      // TODO: maybe use mapPartitions instead?
      context.hadoopFile[LongWritable, Text, TextInputFormat](location).map(
        pair => new String(pair._2.getBytes, 0, pair._2.getLength, charset)
      )
    }
  }
}

从这里复制。

https://github.com/databricks/spark-csv/blob/master/src/main/scala/com/databricks/spark/csv/util/TextFile.scala

使用它。

https://github.com/databricks/spark-csv/blob/master/src/test/scala/com/databricks/spark/csv/util/TextFileSuite.scala

编辑：

如果您需要全文文件，

这是实现的实际来源。

def wholeTextFiles(
      path: String,
      minPartitions: Int = defaultMinPartitions): RDD[(String, String)] = withScope {
    assertNotStopped()
    val job = NewHadoopJob.getInstance(hadoopConfiguration)
    // Use setInputPaths so that wholeTextFiles aligns with hadoopFile/textFile in taking
    // comma separated files as input. (see SPARK-7155)
    NewFileInputFormat.setInputPaths(job, path)
    val updateConf = job.getConfiguration
    new WholeTextFileRDD(
      this,
      classOf[WholeTextFileInputFormat],
      classOf[Text],
      classOf[Text],
      updateConf,
      minPartitions).map(record => (record._1.toString, record._2.toString)).setName(path)
  }

尝试改变：

.map(record => (record._1.toString, record._2.toString))

到（可能）：

.map(record => (record._1.toString, new String(record._2.getBytes, 0, record._2.getLength, "myCustomCharset")))