序
  
  本文主要研究一下flink的CsvTableSource
  
  TableSource
  
  flink-table_2.11-1.7.1-sources.jar!/org/apache/flink/table/sources/TableSource.scala
  
  trait TableSource[T] {
  
  /** Returns the [[TypeInformation]] for the return type of the [[TableSource]].
  
  * The fields of the return type are mapped to the table schema based on their name.
  
  *
  
  * @return The type of the returned [[DataSet]] or [[DataStream]].
  
  */
  
  def getReturnType: TypeInformation[T]
  
  /**
  
  * Returns the schema of the produced table.
  
  *
  
  * @return The [[TableSchema]] of the produced table.
  
  */
  
  def getTableSchema: TableSchema
  
  /**
  
  * Describes the table source.
  
  *
  
  * @return A String explaining the [[TableSource]].
  
  */
  
  def explainSource(): String =
  
  TableConnectorUtil.generateRuntimeName(getClass, getTableSchema.getFieldNames)
  
  }
  
  TableSource定义了三个方法,分别是getReturnType、getTableSchema、explainSource
  
  BatchTableSource
  
  flink-table_2.11-1.7.1-sources.jar!/org/apache/flink/table/sources/BatchTableSource.scala
  
  trait BatchTableSource[T] extends TableSource[T] {
  
  /**
  
  * Returns the data of the table as a [[DataSet]].
  
  *
  
  * NOTE: This method is for internal use only for defining a [[TableSource]].
  
  * Do not use it in Table API programs.
  
  */
  
  def getDataSet(execEnv: ExecutionEnvironment): DataSet[T]
  
  }
  
  BatchTableSource继承了TableSource,它定义了getDataSet方法
  
  StreamTableSource
  
  flink-table_2.11-1.7.1-sources.jar!/org/apache/flink/table/sources/StreamTableSource.scala
  
  trait StreamTableSource[T] extends TableSource[T] {
  
  /**
  
  * Returns the data of the table as a [[DataStream]].
  
  *
  
  * NOTE: This method is for internal use only for defining a [[TableSource]].
  
  * Do not use it in Table API programs.
  
  */
  
  def getDataStream(execEnv: StreamExecutionEnvironment): DataStream[T]
  
  }
  
  StreamTableSource继承了TableSource,它定义了getDataStream方法
  
  CsvTableSource
  
  flink-table_2.11-1.7.1-sources.jar!/org/apache/flink/table/sources/CsvTableSource.scala
  
  class CsvTableSource private (
  
  private val path: String,
  
  private val fieldNames: Array[String],
  
  private val fieldTypes: Array[TypeInformation[_]],
  
  private val selectedFields: Array[Int],
  
  private val fieldDelim: String,
  
  private val rowDelim: String,
  
  private val quoteCharacter: Character,
  
  private val ignoreFirstLine: Boolean,
  
  private val ignoreComments: String,
  
  private val lenient: Boolean)
  
  extends BatchTableSource[Row]
  
  with StreamTableSource[Row]
  
  with ProjectableTableSource[Row] {
  
  def this(
  
  path: String,
  
  fieldNames: Array[String],
  
  fieldTypes: Array[TypeInformation[_]],
  
  fieldDelim: String = CsvInputFormat.DEFAULT_FIELD_DELIMITER,
  
  rowDelim: String = CsvInputFormat.DEFAULT_LINE_DELIMITER,
  
  quoteCharacter: Character = null,
  
  ignoreFirstLine: Boolean = false,
  
  ignoreComments: String = null,
  
  lenient: Boolean = false)www.michenggw.com = {
  
  this(
  
  path,
  
  fieldNames,
  
  fieldTypes,
  
  fieldTypes.indices.toArray, // initially, all fields are returned
  
  fieldDelim,
  
  rowDelim,
  
  quoteCharacter,
  
  ignoreFirstLine,
  
  ignoreComments,
  
  lenient)
  
  }
  
  def this(path: String, fieldNames: Array[String]www.fengshen157.com/, fieldTypes: Array[TypeInformation[_]]) = {
  
  this(path, fieldNames, fieldTypes, CsvInputFormat.DEFAULT_FIELD_DELIMITER,
  
  CsvInputFormat.DEFAULT_LINE_DELIMITER, null, false, null, false)
  
  }
  
  if (fieldNames.length != fieldTypes.length) {
  
  throw new TableException("Number of field names and field types must be equal.")
  
  }
  
  private val selectedFieldTypes = selectedFields.map(fieldTypes(_))
  
  private val selectedFieldNames = selectedFields.map(fieldNames(_))
  
  private val returnType: RowTypeInfo = new RowTypeInfo(selectedFieldTypes, selectedFieldNames)
  
  override def getDataSet(execEnv: ExecutionEnvironment): DataSet[Row] = {
  
  execEnv.createInput(createCsvInput(), returnType).name(explainSource())
  
  }
  
  /** Returns the [[RowTypeInfo]] for the return type of the [[CsvTableSource]]. */
  
  override def getReturnType: www.leyouzaixian2.com RowTypeInfo = returnType
  
  override def getDataStream(streamExecEnv: StreamExecutionEnvironment): DataStream[Row] = {
  
  streamExecEnv.createInput(createCsvInput(), returnType).name(explainSource())
  
  }
  
  /** Returns the schema of the produced table. */
  
  override def getTableSchema = new TableSchema(fieldNames, fieldTypes)
  
  /** Returns a copy of [[TableSource]] with ability to project fields */
  
  override def projectFields(fields: Array[Int]): CsvTableSource = {
  
  val selectedFields = if (fields.isEmpty) Array(0) else fields
  
  new CsvTableSource(
  
  path,
  
  fieldNames,
  
  fieldTypes,
  
  selectedFields,
  
  fieldDelim,
  
  rowDelim,
  
  quoteCharacter,
  
  ignoreFirstLine,
  
  ignoreComments,
  
  lenient)
  
  }
  
  private def createCsvInput(): RowCsvInputFormat = {
  
  val inputFormat = new RowCsvInputFormat(
  
  new Path(path),
  
  selectedFieldTypes,
  
  rowDelim,
  
  fieldDelim,
  
  selectedFields)
  
  inputFormat.setSkipFirstLineAsHeader(ignoreFirstLine)
  
  inputFormat.setLenient(www.dasheng178.com lenient)
  
  if (quoteCharacter != null) {
  
  inputFormat.enableQuotedStringParsing(quoteCharacter)
  
  }
  
  if (ignoreComments != null) {
  
  inputFormat.setCommentPrefix(ignoreComments)
  
  }
  
  inputFormat
  
  }
  
  override def equals(other: Any): Boolean = other match {
  
  case that: CsvTableSource => returnType == that.returnType &&
  
  path == that.path &&
  
  fieldDelim == that.fieldDelim &&
  
  rowDelim == that.rowDelim &&
  
  quoteCharacter == that.quoteCharacter &&
  
  ignoreFirstLine == that.ignoreFirstLine &&
  
  ignoreComments == that.ignoreComments &&
  
  lenient == that.lenient
  
  case _ => false
  
  }
  
  override def hashCode(www.hengda157.com): Int = {
  
  returnType.hashCode()
  
  }
  
  override def explainSource(): String = {
  
  s"CsvTableSource(" +
  
  s"read fields: ${getReturnType.getFieldNames.mkString(", ")})"
  
  }
  
  }
  
  CsvTableSource同时实现了BatchTableSource及StreamTableSource接口;getDataSet方法使用ExecutionEnvironment.createInput创建DataSet;getDataStream方法使用StreamExecutionEnvironment.createInput创建DataStream
  
  ExecutionEnvironment.createInput及StreamExecutionEnvironment.createInput接收的InputFormat为RowCsvInputFormat,通过createCsvInput创建而来
  
  getTableSchema方法返回的TableSchema通过fieldNames及fieldTypes创建;getReturnType方法返回的RowTypeInfo通过selectedFieldTypes及selectedFieldNames创建;explainSource方法这里返回的是CsvTableSource开头的字符串
  
  小结
  
  TableSource定义了三个方法,分别是getReturnType、getTableSchema、explainSource;BatchTableSource继承了TableSource,它定义了getDataSet方法;StreamTableSource继承了TableSource,它定义了getDataStream方法
  
  CsvTableSource同时实现了BatchTableSource及StreamTableSource接口;getDataSet方法使用ExecutionEnvironment.createInput创建DataSet;getDataStream方法使用StreamExecutionEnvironment.createInput创建DataStream
  
  ExecutionEnvironment.createInput及StreamExecutionEnvironment.createInput接收的InputFormat为RowCsvInputFormat,通过createCsvInput创建而来;getTableSchema方法返回的TableSchema通过fieldNames及fieldTypes创建;getReturnType方法返回的RowTypeInfo通过selectedFieldTypes及selectedFieldNames创建;explainSource方法这里返回的是CsvTableSource开头的字符串

聊聊flink的CsvTableSource的更多相关文章

  1. 聊聊flink的NetworkEnvironmentConfiguration

    本文主要研究一下flink的NetworkEnvironmentConfiguration NetworkEnvironmentConfiguration flink-1.7.2/flink-runt ...

  2. 聊聊flink Table的groupBy操作

    本文主要研究一下flink Table的groupBy操作 Table.groupBy flink-table_2.11-1.7.0-sources.jar!/org/apache/flink/tab ...

  3. 聊聊flink的AsyncWaitOperator

    序本文主要研究一下flink的AsyncWaitOperator AsyncWaitOperatorflink-streaming-java_2.11-1.7.0-sources.jar!/org/a ...

  4. 聊聊flink的Async I/O

    // This example implements the asynchronous request and callback with Futures that have the // inter ...

  5. 聊聊flink的log.file配置

    本文主要研究一下flink的log.file配置 log4j.properties flink-release-1.6.2/flink-dist/src/main/flink-bin/conf/log ...

  6. [case49]聊聊flink的checkpoint配置

    序 本文主要研究下flink的checkpoint配置 实例 StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecut ...

  7. 聊聊flink的BlobStoreService

    序 本文主要研究一下flink的BlobStoreService BlobView flink-release-1.7.2/flink-runtime/src/main/java/org/apache ...

  8. [源码分析] 从源码入手看 Flink Watermark 之传播过程

    [源码分析] 从源码入手看 Flink Watermark 之传播过程 0x00 摘要 本文将通过源码分析,带领大家熟悉Flink Watermark 之传播过程,顺便也可以对Flink整体逻辑有一个 ...

  9. Flink与Spark Streaming在与kafka结合的区别!

    本文主要是想聊聊flink与kafka结合.当然,单纯的介绍flink与kafka的结合呢,比较单调,也没有可对比性,所以的准备顺便帮大家简单回顾一下Spark Streaming与kafka的结合. ...

随机推荐

  1. python基础——字符串

    Python的核心数据类型--字符串 常见字符串常量和表达式 操作 解释 s = '' 空字符串 s = "dodo's" 双引号和单引号 s = 'd\no\p\td\x00o' ...

  2. CentOS7安装及配置vsftpd (FTP服务器)

    CentOS7安装及配置vsftpd (FTP服务器) 1.安装vsftpd 1 yum -y install vsftpd 2.设置开机启动 1 systemctl enable vsftpd 3. ...

  3. socket编程为什么需要htonl(), ntohl(), ntohs(),htons() 函数-------转载

    在C/C++写网络程序的时候,往往会遇到字节的网络顺序和主机顺序的问题.这是就可能用到htons(), ntohl(), ntohs(),htons()这4个函数. 网络字节顺序与本地字节顺序之间的转 ...

  4. thinkphp5登录并保存session、根据不同用户权限跳转不同页面

    本文讲述如何在thinkphp5中完成登录并保存session.然后根据不同的用户权限跳转相应页面功能的实现.我也在学习thinkphp源码的路上,记录一下并与大家分享.完成该步骤主要有以下三个步骤完 ...

  5. vue关于img src动态赋值问题

    解决方法: 加个require()就可以了 <img :src="require('../assets/images/'+imgsrc+'.png')"/>

  6. 3星|麦肯锡合伙人《从1到N》:PPT讲稿,图表不错,讲解不够深入

    从1到N:企业数字化生存指南 两位作者是麦肯锡合伙人.全书插图比较多,图做的还比较有水平.但是相关文字不够深入,我读后的感觉是:图表不是两位执笔者做的,他们对细节不清楚,对图表涉及到的行业也缺乏深入的 ...

  7. Spring学习(3):Spring概述(转载)

    1. Spring是什么? Spring是一个开源的轻量级Java SE(Java 标准版本)/Java EE(Java 企业版本)开发应用框架,其目的是用于简化企业级应用程序开发. 在面向对象思想中 ...

  8. 二维DCT变换

    DCT(Discrete Consine Transform),又叫离散余弦变换,它的第二种类型,经常用于信号和图像数据的压缩.经过DCT变换后的数据能量非常集中,一般只有左上角的数值是非零的,也就是 ...

  9. 剑指offer-二维数组中的查找01

    题目描述 在一个二维数组中(每个一维数组的长度相同),每一行都按照从左到右递增的顺序排序,每一列都按照从上到下递增的顺序排序.请完成一个函数,输入这样的一个二维数组和一个整数,判断数组中是否含有该整数 ...

  10. 如何把node更新到最新的稳定版本

    先装n,再用n把node升级到最新稳定版 $ npm install -g n $ n stable