SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("jsonfile");
SparkContext sc = new SparkContext(conf);
        
//创建sqlContext
SQLContext sqlContext = new SQLContext(sc);//SprakSQL中是SQLContext对象
        
/**
 * DataFrame的底层是一个一个的RDD  RDD的泛型是Row类型。
 * 以下两种方式都可以读取json格式的文件
 */
 DataFrame df = sqlContext.read().format("json").load("sparksql/json");
// DataFrame df2 = sqlContext.read().json("sparksql/json.txt");
// df2.show();
 /**
  * DataFrame转换成RDD
  */
 RDD<Row> rdd = df.rdd();
/**
 * 显示 DataFrame中的内容，默认显示前20行。如果现实多行要指定多少行show(行数)
 * 注意：当有多个列时，显示的列先后顺序是按列的ascii码先后显示。
 */
// df.show();
/**
 * 树形的形式显示schema信息
 */
 df.printSchema();
        
 /**
  * dataFram自带的API 操作DataFrame（很麻烦）
  */
  //select name from table
 // df.select("name").show();
 //select name age+10 as addage from table
     df.select(df.col("name"),df.col("age").plus(10).alias("addage")).show();
 //select name ,age from table where age>19
     df.select(df.col("name"),df.col("age")).where(df.col("age").gt(19)).show();
 //select count(*) from table group by age
 df.groupBy(df.col("age")).count().show();
        
 /**
   * 将DataFrame注册成临时的一张表，这张表临时注册到内存中，是逻辑上的表，不会雾化到磁盘
  */
 df.registerTempTable("jtable");
        
 DataFrame sql = sqlContext.sql("select age,count(1) from jtable group by age");
 DataFrame sql2 = sqlContext.sql("select * from jtable");
        
 sc.stop();

SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("jsonRDD");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
JavaRDD<String> nameRDD = sc.parallelize(Arrays.asList(
    "{\"name\":\"zhangsan\",\"age\":\"18\"}",
    "{\"name\":\"lisi\",\"age\":\"19\"}",
    "{\"name\":\"wangwu\",\"age\":\"20\"}"
));
JavaRDD<String> scoreRDD = sc.parallelize(Arrays.asList(
"{\"name\":\"zhangsan\",\"score\":\"100\"}",
"{\"name\":\"lisi\",\"score\":\"200\"}",
"{\"name\":\"wangwu\",\"score\":\"300\"}"
));

DataFrame namedf = sqlContext.read().json(nameRDD);
DataFrame scoredf = sqlContext.read().json(scoreRDD);
namedf.registerTempTable("name");
scoredf.registerTempTable("score");

DataFrame result = sqlContext.sql("select name.name,name.age,score.score from name,score where name.name = score.name");
result.show();

sc.stop();

/**
* 注意：
* 1.自定义类必须是可序列化的
* 2.自定义类访问级别必须是Public
* 3.RDD转成DataFrame会把自定义类中字段的名称按assci码排序
*/
SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("RDD");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
JavaRDD<String> lineRDD = sc.textFile("sparksql/person.txt");
JavaRDD<Person> personRDD = lineRDD.map(new Function<String, Person>() {

    /**
    * 
    */
    private static final long serialVersionUID = 1L;

    @Override
    public Person call(String s) throws Exception {
          Person p = new Person();
          p.setId(s.split(",")[0]);
          p.setName(s.split(",")[1]);
          p.setAge(Integer.valueOf(s.split(",")[2]));
          return p;
    }
});
/**
* 传入进去Person.class的时候，sqlContext是通过反射的方式创建DataFrame
* 在底层通过反射的方式获得Person的所有field，结合RDD本身，就生成了DataFrame
*/
DataFrame df = sqlContext.createDataFrame(personRDD, Person.class);
df.show();
df.registerTempTable("person");
sqlContext.sql("select  name from person where id = 2").show();

/**
* 将DataFrame转成JavaRDD
* 注意：
* 1.可以使用row.getInt(0),row.getString(1)...通过下标获取返回Row类型的数据，但是要注意列顺序问题---不常用
* 2.可以使用row.getAs("列名")来获取对应的列值。
* 
*/
JavaRDD<Row> javaRDD = df.javaRDD();
JavaRDD<Person> map = javaRDD.map(new Function<Row, Person>() {

    /**
    * 
    */
    private static final long serialVersionUID = 1L;

    @Override
    public Person call(Row row) throws Exception {
            Person p = new Person();
            //p.setId(row.getString(1));
            //p.setName(row.getString(2));
            //p.setAge(row.getInt(0));

            p.setId((String)row.getAs("id"));
            p.setName((String)row.getAs("name"));
            p.setAge((Integer)row.getAs("age"));
            return p;
    }
});
map.foreach(new VoidFunction<Person>() {
    
    /**
    * 
    */
    private static final long serialVersionUID = 1L;

    @Override
    public void call(Person t) throws Exception {
          System.out.println(t);
    }
});

sc.stop();

SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("rddStruct");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
JavaRDD<String> lineRDD = sc.textFile("./sparksql/person.txt");
/**
 * 转换成Row类型的RDD
 */
JavaRDD<Row> rowRDD = lineRDD.map(new Function<String, Row>() {

    /**
     * 
     */
    private static final long serialVersionUID = 1L;

    @Override
    public Row call(String s) throws Exception {
          return RowFactory.create(//这里字段顺序一定要和下边 StructField对应起来
                String.valueOf(s.split(",")[0]),
                String.valueOf(s.split(",")[1]),
                Integer.valueOf(s.split(",")[2])
    );
    }
});
/**
 * 动态构建DataFrame中的元数据，一般来说这里的字段可以来源自字符串，也可以来源于外部数据库
 */
List<StructField> asList =Arrays.asList(//这里字段顺序一定要和上边对应起来
    DataTypes.createStructField("id", DataTypes.StringType, true),
    DataTypes.createStructField("name", DataTypes.StringType, true),
    DataTypes.createStructField("age", DataTypes.IntegerType, true)
);

StructType schema = DataTypes.createStructType(asList);
DataFrame df = sqlContext.createDataFrame(rowRDD, schema);

df.show();

    JavaRDD<Row> javaRDD = df.javaRDD();
        javaRDD.foreach(new VoidFunction<Row>() {

            /**
             *
             */
            private static final long serialVersionUID = 1L;

            @Override
            public void call(Row row) throws Exception {//Row类型的RDD
                System.out.println(row.getString(0));
            }
        })

sc.stop();

SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("parquet");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
JavaRDD<String> jsonRDD = sc.textFile("sparksql/json");
DataFrame df = sqlContext.read().json(jsonRDD);
/**
 * 将DataFrame保存成parquet文件，SaveMode指定存储文件时的保存模式
 * 保存成parquet文件有以下两种方式：
 */
df.write().mode(SaveMode.Overwrite).format("parquet").save("./sparksql/parquet");
df.write().mode(SaveMode.Overwrite).parquet("./sparksql/parquet");
df.show();
/**
 * 加载parquet文件成DataFrame    
 * 加载parquet文件有以下两种方式：    
 */

DataFrame load = sqlContext.read().format("parquet").load("./sparksql/parquet");
load = sqlContext.read().parquet("./sparksql/parquet");
load.show();

sc.stop()

SparkConf conf = new SparkConf();
conf.setMaster("local").setAppName("mysql");
JavaSparkContext sc = new JavaSparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
/**
 * 第一种方式读取MySql数据库表，加载为DataFrame
 */
Map<String, String> options = new HashMap<String,String>();
options.put("url", "jdbc:mysql://192.168.179.4:3306/spark");
options.put("driver", "com.mysql.jdbc.Driver");
options.put("user", "root");
options.put("password", "123456");
options.put("dbtable", "person");
DataFrame person = sqlContext.read().format("jdbc").options(options).load();
person.show();
person.registerTempTable("person");
/**
 * 第二种方式读取MySql数据表加载为DataFrame
 */
DataFrameReader reader = sqlContext.read().format("jdbc");
reader.option("url", "jdbc:mysql://192.168.179.4:3306/spark");
reader.option("driver", "com.mysql.jdbc.Driver");
reader.option("user", "root");
reader.option("password", "123456");
reader.option("dbtable", "score");
DataFrame score = reader.load();
score.show();
score.registerTempTable("score");

DataFrame result = 
sqlContext.sql("select person.id,person.name,score.score from person,score where person.name = score.name");
result.show();
/**
 * 将DataFrame结果保存到Mysql中
 */
Properties properties = new Properties();
properties.setProperty("user", "root");
properties.setProperty("password", "123456");
result.write().mode(SaveMode.Overwrite).jdbc("jdbc:mysql://192.168.179.4:3306/spark", "result", properties);

sc.stop();