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. 利用工厂模式实现serviec层和dao层解耦

    利用工厂模式实现serveice和dao层的解耦,这样就可以不用在service层实例化dao层的对象,当dao层代码发生改变的时候(数据库实现发生改变)直接修改配置文件就不用改变service层的代 ...

  2. [转]Git 撤销操作

    二. Git撤消操作 12.1 修改最后一次提交 git commit --amend 1.新建一个文件 2.提交一个之前的更改 3.跟踪这个文件 4.跟前一次一起提交 提示你是否重新编辑提交说明,如 ...

  3. linux同步软件

    linux同步软件:scp,rsync,inotify,sersync 1.scp: scp就是secure copy,是用来进行远程文件拷贝的.数据传输使用 ssh,并且和ssh 使用相同的认证方式 ...

  4. ES6的新特性(7)——函数的扩展

    函数的扩展 函数参数的默认值 基本用法 ES6 之前,不能直接为函数的参数指定默认值,只能采用变通的方法. function log(x, y) { y = y || 'World'; console ...

  5. C++ STL 优先队列 priority_queue 详解(转)

    转自https://blog.csdn.net/c20182030/article/details/70757660,感谢大佬. 优先队列 引入 优先队列是一种特殊的队列,在学习堆排序的时候就有所了解 ...

  6. Is It A Tree?(并查集)

    Description A tree is a well-known data structure that is either empty (null, void, nothing) or is a ...

  7. LeetCode 454. 4Sum II (C++)

    题目: Given four lists A, B, C, D of integer values, compute how many tuples (i, j, k, l) there are su ...

  8. J2EE,J2SE,J2ME,JDK,SDK,JRE,JVM区别(转载)

    转载地址:http://blog.csdn.net/alspwx/article/details/20799017 一.J2EE.J2SE.J2ME区别 J2EE——全称Java 2 Enterpri ...

  9. Java中的网络编程-3

    用户数据协议(UDP)是网络信息传输的另外一种形式, 基于UDP的通信不同于基于TCP的通信, 基于UDP的信息传递更快, 但是不提供可靠的保证. 使用UDP传输数据时, 用户无法知道数据能否正确地到 ...

  10. Spark Shuffle之Hash Shuffle

    源文件放在github,如有谬误之处,欢迎指正.原文链接https://github.com/jacksu/utils4s/blob/master/spark-knowledge/md/hash-sh ...