Spark SQL数据加载和保存实例讲解

import org.apache.spark.SparkConf;import org.apache.spark.api.java.JavaRDD;import org.apache.spark.api.java.JavaSparkContext;import org.apache.spark.api.java.function.Function;import org.apache.spark.sql.*;import org.apache.spark.sql.types.DataTypes;import org.apache.spark.sql.types.StructField;import org.apache.spark.sql.types.StructType;import java.util.ArrayList;import java.util.List;public class SparkSQLLoadSaveOps { public static void main(String[] args) {  SparkConf conf = new SparkConf().setMaster("local").setAppName("SparkSQLLoadSaveOps");  JavaSparkContext sc = new JavaSparkContext(conf);  SQLContext = new SQLContext(sc);  /**   * read()是DataFrameReader类型，load可以将数据读取出来   */  DataFrame peopleDF = sqlContext.read().format("json").load("E://Spark//Sparkinstanll_package//Big_Data_Software//spark-1.6.0-bin-hadoop2.6//examples//src//main//resources//people.json");  /**   * 直接对DataFrame进行操作   * Json: 是一种自解释的格式，读取Json的时候怎么判断其是什么格式？   * 通过扫描整个Json。扫描之后才会知道元数据   */  //通过mode来指定输出文件的是append。创建新文件来追加文件 peopleDF.select("name").write().mode(SaveMode.Append).save("E://personNames"); }}

/** * :: Experimental :: * Returns a [[DataFrameReader]] that can be used to read data in as a [[DataFrame]]. * {{{ *  sqlContext.read.parquet("/path/to/file.parquet") *  sqlContext.read.schema(schema).json("/path/to/file.json") * }}} * * @group genericdata * @since 1.4.0 */@Experimental//创建DataFrameReader实例，获得了DataFrameReader引用def read: DataFrameReader = new DataFrameReader(this)

/** * Specifies the input data source format. * * @since 1.4.0 */def format(source: String): DataFrameReader = { this.source = source this}

/** * Loads input in as a [[DataFrame]], for data sources that require a path (e.g. data backed by * a local or distributed file system). * * @since 1.4.0 */// TODO: Remove this one in Spark 2.0.def load(path: String): DataFrame = { option("path", path).load()}

/** * Selects a set of columns. This is a variant of `select` that can only select * existing columns using column names (i.e. cannot construct expressions). * * {{{ *  // The following two are equivalent: *  df.select("colA", "colB") *  df.select($"colA", $"colB") * }}} * @group dfops * @since 1.3.0 */@scala.annotation.varargsdef select(col: String, cols: String*): DataFrame = select((col +: cols).map(Column(_)) : _*)

/** * :: Experimental :: * Interface for saving the content of the [[DataFrame]] out into external storage. * * @group output * @since 1.4.0 */@Experimentaldef write: DataFrameWriter = new DataFrameWriter(this)

/** * Specifies the behavior when data or table already exists. Options include:// Overwrite是覆盖 *  - `SaveMode.Overwrite`: overwrite the existing data.//创建新的文件，然后追加 *  - `SaveMode.Append`: append the data. *  - `SaveMode.Ignore`: ignore the operation (i.e. no-op). *  - `SaveMode.ErrorIfExists`: default option, throw an exception at runtime. * * @since 1.4.0 */def mode(saveMode: SaveMode): DataFrameWriter = { this.mode = saveMode this}

/** * Saves the content of the [[DataFrame]] at the specified path. * * @since 1.4.0 */def save(path: String): Unit = { this.extraOptions += ("path" -> path) save()}

/** * Returns the dataset stored at path as a DataFrame, * using the default data source configured by spark.sql.sources.default. * * @group genericdata * @deprecated As of 1.4.0, replaced by `read().load(path)`. This will be removed in Spark 2.0. */@deprecated("Use read.load(path). This will be removed in Spark 2.0.", "1.4.0")def load(path: String): DataFrame = {//此时的read就是DataFrameReader read.load(path)}

/**  * Loads input in as a [[DataFrame]], for data sources that require a path (e.g. data backed by * a local or distributed file system). * * @since 1.4.0 */// TODO: Remove this one in Spark 2.0.def load(path: String): DataFrame = { option("path", path).load()}

/** * Loads input in as a [[DataFrame]], for data sources that don't require a path (e.g. external * key-value stores). * * @since 1.4.0 */def load(): DataFrame = {//对传入的Source进行解析 val resolved = ResolvedDataSource(  sqlContext,  userSpecifiedSchema = userSpecifiedSchema,  partitionColumns = Array.empty[String],  provider = source,  options = extraOptions.toMap) DataFrame(sqlContext, LogicalRelation(resolved.relation))}

/** * Specifies the input data source format.Built-in options include “parquet”,”json”,etc. * * @since 1.4.0 */def format(source: String): DataFrameReader = { this.source = source //FileType this}

/** * :: Experimental :: * Interface for saving the content of the [[DataFrame]] out into external storage. * * @group output * @since 1.4.0 */@Experimentaldef write: DataFrameWriter = new DataFrameWriter(this)1

/** * :: Experimental :: * Interface used to write a [[DataFrame]] to external storage systems (e.g. file systems, * key-value stores, etc). Use [[DataFrame.write]] to access this. * * @since 1.4.0 */@Experimentalfinal class DataFrameWriter private[sql](df: DataFrame) {

/** * Specifies the behavior when data or table already exists. Options include: *  - `SaveMode.Overwrite`: overwrite the existing data. *  - `SaveMode.Append`: append the data. *  - `SaveMode.Ignore`: ignore the operation (i.e. no-op).//默认操作 *  - `SaveMode.ErrorIfExists`: default option, throw an exception at runtime. * * @since 1.4.0 */def mode(saveMode: SaveMode): DataFrameWriter = { this.mode = saveMode this}

/** * Specifies the behavior when data or table already exists. Options include: *  - `overwrite`: overwrite the existing data. *  - `append`: append the data. *  - `ignore`: ignore the operation (i.e. no-op). *  - `error`: default option, throw an exception at runtime. * * @since 1.4.0 */def mode(saveMode: String): DataFrameWriter = { this.mode = saveMode.toLowerCase match {  case "overwrite" => SaveMode.Overwrite  case "append" => SaveMode.Append  case "ignore" => SaveMode.Ignore  case "error" | "default" => SaveMode.ErrorIfExists  case _ => throw new IllegalArgumentException(s"Unknown save mode: $saveMode. " +   "Accepted modes are 'overwrite', 'append', 'ignore', 'error'.") } this}

/** * Saves the content of the [[DataFrame]] at the specified path. * * @since 1.4.0 */def save(path: String): Unit = { this.extraOptions += ("path" -> path) save()}

/** * Saves the content of the [[DataFrame]] as the specified table. * * @since 1.4.0 */def save(): Unit = { ResolvedDataSource(  df.sqlContext,  source,  partitioningColumns.map(_.toArray).getOrElse(Array.empty[String]),  mode,  extraOptions.toMap,  df)}

// This is used to set the default data sourceval DEFAULT_DATA_SOURCE_NAME = stringConf("spark.sql.sources.default", defaultValue = Some("org.apache.spark.sql.parquet"), doc = "The default data source to use in input/output.")

/** * Returns the object itself. * @group basic * @since 1.3.0 */// This is declared with parentheses to prevent the Scala compiler from treating// `rdd.toDF("1")` as invoking this toDF and then apply on the returned DataFrame.def toDF(): DataFrame = this

/** * Displays the [[DataFrame]] in a tabular form. For example: * {{{ *  year month AVG('Adj Close) MAX('Adj Close) *  1980 12  0.503218    0.595103 *  1981 01  0.523289    0.570307 *  1982 02  0.436504    0.475256 *  1983 03  0.410516    0.442194 *  1984 04  0.450090    0.483521 * }}} * @param numRows Number of rows to show * @param truncate Whether truncate long strings. If true, strings more than 20 characters will *       be truncated and all cells will be aligned right * * @group action * @since 1.5.0 */// scalastyle:off printlndef show(numRows: Int, truncate: Boolean): Unit = println(showString(numRows, truncate))// scalastyle:on println

/** * Compose the string representing rows for output * @param _numRows Number of rows to show * @param truncate Whether truncate long strings and align cells right */private[sql] def showString(_numRows: Int, truncate: Boolean = true): String = { val numRows = _numRows.max(0) val sb = new StringBuilder val takeResult = take(numRows + 1) val hasMoreData = takeResult.length > numRows val data = takeResult.take(numRows) val numCols = schema.fieldNames.length