spark JsonUtils 源码

2022-10-20
浏览 (323)

spark JsonUtils 代码

文件路径：/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonUtils.scala

/*
 * 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.json

import org.apache.spark.SparkException
import org.apache.spark.input.PortableDataStream
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.Dataset
import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{DataTypeMismatch, TypeCheckSuccess}
import org.apache.spark.sql.catalyst.expressions.ExprUtils
import org.apache.spark.sql.catalyst.json.JSONOptions
import org.apache.spark.sql.errors.QueryCompilationErrors
import org.apache.spark.sql.types.DataType

object JsonUtils {
  /**
   * Sample JSON dataset as configured by `samplingRatio`.
   */
  def sample(json: Dataset[String], options: JSONOptions): Dataset[String] = {
    require(options.samplingRatio > 0,
      s"samplingRatio (${options.samplingRatio}) should be greater than 0")
    if (options.samplingRatio > 0.99) {
      json
    } else {
      json.sample(withReplacement = false, options.samplingRatio, 1)
    }
  }

  /**
   * Sample JSON RDD as configured by `samplingRatio`.
   */
  def sample(json: RDD[PortableDataStream], options: JSONOptions): RDD[PortableDataStream] = {
    require(options.samplingRatio > 0,
      s"samplingRatio (${options.samplingRatio}) should be greater than 0")
    if (options.samplingRatio > 0.99) {
      json
    } else {
      json.sample(withReplacement = false, options.samplingRatio, 1)
    }
  }

  def checkJsonSchema(schema: DataType): Unit = {
    ExprUtils.checkJsonSchema(schema) match {
      case DataTypeMismatch("INVALID_JSON_MAP_KEY_TYPE", _) =>
        throw QueryCompilationErrors.invalidJsonSchema(schema)
      case TypeCheckSuccess =>
      case result =>
        throw SparkException.internalError(s"Unknown type check result: $result.")
    }
  }
}

相关信息

spark 源码目录

相关文章

spark JsonDataSource 源码

spark JsonFileFormat 源码

spark JsonOutputWriter 源码

0 赞

所属分类： 前端技术
本文标签：
版权声明： 原创文章如转载，请注明本文链接: https://www.seaxiang.com/blog/84b2630a176b4f6f8dc6599443ac4726

热门推荐

1、直接访问google.com
2、 - 优质文章
3、 gate.io
4、 harmony 鸿蒙hdc使用指导
5、 harmony 鸿蒙ArkUI组件（ArkTS）开发常见问题
6、 harmony 鸿蒙初识ArkTS语言
7、 golang
8、 flink kafka connector scan.startup.mode 的几个选项
9、 openharmony
10、 Vue中input框自动聚焦

Loading...