All Downloads are FREE. Search and download functionalities are using the official Maven repository.

com.databricks.spark.csv.util.TextFile.scala Maven / Gradle / Ivy

The newest version!
/*
 * Copyright 2014 Databricks
 *
 * Licensed 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 com.databricks.spark.csv.util

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

private[csv] 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)
      )
    }
  }
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy