kafka-topics --bootstrap-server hadoop102:9092 --create --replication-factor 2 --partitions 10  --topic register_topic

kafka-topics --bootstrap-server hadoop102:9092 --create --replication-factor 2 --partitions 10  --topic qz_log

kafka-topics --bootstrap-server hadoop102:9092 --create --replication-factor 2 --partitions 10  --topic page_topic

kafka-topics --bootstrap-server hadoop102:9092 --create --replication-factor 2 --partitions 10  --topic course_learn

# 数据使用/t作为分隔符
7188    2    2019-07-16 16:01:55
7189    1    2019-07-16 16:01:55
7190    1    2019-07-16 16:01:55
7191    1    2019-07-16 16:01:55
7192    1    2019-07-16 16:01:55
7193    3    2019-07-16 16:01:55
7194    1    2019-07-16 16:01:55
7195    3    2019-07-16 16:01:55

# 数据使用/t作为分隔符
1006    504    8    7    0    2019-07-12 11:17:45
1007    505    16    9    1    2019-07-12 11:17:45
1002    505    29    3    0    2019-07-12 11:17:45
1006    504    10    5    0    2019-07-12 11:17:45
1001    502    28    8    0    2019-07-12 11:17:45
1006    505    27    0    1    2019-07-12 11:17:45
1004    503    25    3    0    2019-07-12 11:17:45
1007    504    12    1    0    2019-07-12 11:17:45
1006    501    7    6    0    2019-07-12 11:17:45

# 数据为json格式
{"app_id":"2","device_id":"100","distinct_id":"23a6d4a7-6903-46a4-bce2-a8317693da45","event_name":"-","ip":"123.235.113.225","last_event_name":"-","last_page_id":"0","next_event_name":"-","next_page_id":"2","page_id":"1","server_time":"-","uid":"0"}

# json格式化之后
{
  "app_id": "2",
  "device_id": "100",
  "distinct_id": "23a6d4a7-6903-46a4-bce2-a8317693da45",
  "event_name": "-",
  "ip": "123.235.113.225",
  "last_event_name": "-",
  "last_page_id": "0",
  "next_event_name": "-",
  "next_page_id": "2",
  "page_id": "1",
  "server_time": "-",
  "uid": "0"
}

# 数据为json格式
{"biz":"34e4b8fe-476c-4c7e-8e2c-274ec00bb5c9","chapterid":"2","cwareid":"2","edutypeid":"1","pe":"56","ps":"24","sourceType":"PC","speed":"2","subjectid":"1","te":"1563352144131","ts":"1563352128131","uid":"219","videoid":"6"}

# json格式化之后
{
  "biz": "34e4b8fe-476c-4c7e-8e2c-274ec00bb5c9",
  "chapterid": "2",
  "cwareid": "2",
  "edutypeid": "1",
  "pe": "56",
  "ps": "24",
  "sourceType": "PC",
  "speed": "2",
  "subjectid": "1",
  "te": "1563352144131",
  "ts": "1563352128131",
  "uid": "219",
  "videoid": "6"
}

import org.lionsoul.ip2region.{DbConfig, DbSearcher}

object IpTest {
  def main(args: Array[String]): Unit = {
    val ipSearch = new DbSearcher(new DbConfig(), this.getClass.getResource("/ip2region.db").getPath)
    val region = ipSearch.binarySearch("182.250.250.42").getRegion
    println(region)
    val city = region.split("\\|")(2)
    println(city)
  }
}

CREATE TABLE `offset_manager` (
  `groupid` varchar(50) DEFAULT NULL,
  `topic` varchar(50) DEFAULT NULL,
  `partition` int(11) DEFAULT NULL,
  `untiloffset` mediumtext,
  UNIQUE KEY `offset_unique` (`groupid`,`topic`,`partition`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

CREATE TABLE `qz_point_detail` (
  `userid` int(11) DEFAULT NULL,
  `courseid` int(11) DEFAULT NULL,
  `pointid` int(11) DEFAULT NULL,
  `qz_sum` int(11) DEFAULT NULL,
  `qz_count` int(11) DEFAULT NULL,
  `qz_istrue` int(11) DEFAULT NULL,
  `correct_rate` double(4,2) DEFAULT NULL,
  `mastery_rate` double(4,2) DEFAULT NULL,
  `createtime` datetime DEFAULT NULL,
  `updatetime` datetime DEFAULT NULL,
  UNIQUE KEY `qz_point_detail_unique` (`userid`,`courseid`,`pointid`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

CREATE TABLE `qz_point_history` (
  `userid` int(11) DEFAULT NULL,
  `courseid` int(11) DEFAULT NULL,
  `pointid` int(11) DEFAULT NULL,
  `questionids` text,
  `createtime` datetime DEFAULT NULL,
  `updatetime` datetime DEFAULT NULL,
  UNIQUE KEY `qz_point_set_unique` (`userid`,`courseid`,`pointid`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

CREATE TABLE `page_jump_rate` (
  `id` INT(11) NOT NULL AUTO_INCREMENT,
  `last_page_id` INT(11) DEFAULT NULL,
  `page_id` INT(11) DEFAULT NULL,
  `next_page_id` INT(11) DEFAULT NULL,
  `num` BIGINT(20) DEFAULT NULL,
  `jump_rate` VARCHAR(10) DEFAULT NULL,
  PRIMARY KEY (`id`),
  UNIQUE KEY `page_jum_rate_unique` (`page_id`)
) ENGINE=INNODB AUTO_INCREMENT=394 DEFAULT CHARSET=utf8;

CREATE TABLE `tmp_city_num_detail` (
  `id` INT(11) NOT NULL AUTO_INCREMENT,
  `province` VARCHAR(10) DEFAULT NULL,
  `num` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`id`),
  UNIQUE KEY `tmp_cityp_num_index_province` (`province`)
) ENGINE=INNODB AUTO_INCREMENT=4191 DEFAULT CHARSET=utf8;

CREATE TABLE `top_city_num` (
  `id` INT(11) NOT NULL AUTO_INCREMENT,
  `province` VARCHAR(10) DEFAULT NULL,
  `num` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=INNODB AUTO_INCREMENT=4 DEFAULT CHARSET=utf8;

CREATE TABLE `video_learn_detail` (
  `userid` INT(11) NOT NULL DEFAULT ‘0‘,
  `cwareid` INT(11) NOT NULL DEFAULT ‘0‘,
  `videoid` INT(11) NOT NULL DEFAULT ‘0‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  `effecttime` BIGINT(20) DEFAULT NULL,
  `completetime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`userid`,`cwareid`,`videoid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;

CREATE TABLE `chapter_learn_detail` (
  `chapterid` INT(11) NOT NULL DEFAULT ‘0‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`chapterid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;

CREATE TABLE `cwareid_learn_detail` (
  `cwareid` INT(11) NOT NULL DEFAULT ‘0‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`cwareid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;


CREATE TABLE `edutype_learn_detail` (
  `edutypeid` INT(11) NOT NULL DEFAULT ‘0‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`edutypeid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;


CREATE TABLE `sourcetype_learn_detail` (
  `sourcetype` VARCHAR(10) NOT NULL DEFAULT ‘‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`sourcetype_learn`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;

CREATE TABLE `subject_learn_detail` (
  `subjectid` INT(11) NOT NULL DEFAULT ‘0‘,
  `totaltime` BIGINT(20) DEFAULT NULL,
  PRIMARY KEY (`subjectid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;

CREATE TABLE `video_interval` (
  `userid` INT(11) NOT NULL DEFAULT ‘0‘,
  `cwareid` INT(11) NOT NULL DEFAULT ‘0‘,
  `videoid` INT(11) NOT NULL DEFAULT ‘0‘,
  `play_interval` TEXT,
  PRIMARY KEY (`userid`,`cwareid`,`videoid`)
) ENGINE=INNODB DEFAULT CHARSET=utf8;

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <parent>
        <artifactId>education-online</artifactId>
        <groupId>com.atguigu</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

    <artifactId>com_atguigu_sparkstreaming</artifactId>
    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
                        <scope>provided</scope>
            <version>${spark.version}</version>
            <!-- provider如果存在，那么运行时该Jar包不存在，也不会打包到最终的发布版本中，只是编译器有效 -->
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>2.4.0</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
                        <scope>provided</scope>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
                        <scope>provided</scope>
            <version>${spark.version}</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/bk/ring-gzip -->

        <!--MySql连接池-->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>druid</artifactId>
            <version>1.1.16</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.29</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.47</version>
        </dependency>

        <dependency>
            <groupId>org.lionsoul</groupId>
            <artifactId>ip2region</artifactId>
            <version>1.4</version>
        </dependency>

        <dependency>
            <groupId>org.xerial.snappy</groupId>
            <scope>provided</scope>
            <artifactId>snappy-java</artifactId>
            <version>1.1.2.6</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.1</version>
                <executions>
                    <execution>
                        <id>compile-scala</id>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>test-compile-scala</id>
                        <goals>
                            <goal>add-source</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <archive>
                        <manifest>
                        </manifest>
                    </archive>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

jdbc.url=jdbc:mysql://hadoop102:3306/course_learn?useUnicode=true&characterEncoding=utf8&serverTimezone=Asia/Shanghai&useSSL=false
jdbc.user=root
jdbc.password=123456

package com.atguigu.qzpoint.util;

import java.io.InputStream;
import java.util.Properties;

/**
 *
 * 读取配置文件工具类
 */
public class ConfigurationManager {

  private static Properties prop = new Properties();

  static {
    try {
      InputStream inputStream = ConfigurationManager.class.getClassLoader()
          .getResourceAsStream("comerce.properties");
      prop.load(inputStream);
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

  //获取配置项
  public static String getProperty(String key) {
    return prop.getProperty(key);
  }

  //获取布尔类型的配置项
  public static boolean getBoolean(String key) {
    String value = prop.getProperty(key);
    try {
      return Boolean.valueOf(value);
    } catch (Exception e) {
      e.printStackTrace();
    }
    return false;
  }

}

在com.atguigu.qz.point.util创建ParseJsonData类

package com.atguigu.qzpoint.util;

import com.alibaba.fastjson.JSONObject;


public class ParseJsonData {

    public static JSONObject getJsonData(String data) {
        try {
            return JSONObject.parseObject(data);
        } catch (Exception e) {
            return null;
        }
    }
}

package com.atguigu.qzpoint.util;

import com.alibaba.druid.pool.DruidDataSourceFactory;

import javax.sql.DataSource;
import java.io.Serializable;
import java.sql.*;
import java.util.Properties;

/**
 * 德鲁伊连接池
 */
public class DataSourceUtil implements Serializable {
    public static DataSource dataSource = null;

    static {
        try {
            Properties props = new Properties();
            props.setProperty("url", ConfigurationManager.getProperty("jdbc.url"));
            props.setProperty("username", ConfigurationManager.getProperty("jdbc.user"));
            props.setProperty("password", ConfigurationManager.getProperty("jdbc.password"));
            props.setProperty("initialSize", "5"); //初始化大小
            props.setProperty("maxActive", "10"); //最大连接
            props.setProperty("minIdle", "5");  //最小连接
            props.setProperty("maxWait", "60000"); //等待时长
            props.setProperty("timeBetweenEvictionRunsMillis", "2000");//配置多久进行一次检测,检测需要关闭的连接 单位毫秒
            props.setProperty("minEvictableIdleTimeMillis", "600000");//配置连接在连接池中最小生存时间 单位毫秒
            props.setProperty("maxEvictableIdleTimeMillis", "900000"); //配置连接在连接池中最大生存时间 单位毫秒
            props.setProperty("validationQuery", "select 1");
            props.setProperty("testWhileIdle", "true");
            props.setProperty("testOnBorrow", "false");
            props.setProperty("testOnReturn", "false");
            props.setProperty("keepAlive", "true");
            props.setProperty("phyMaxUseCount", "100000");
//            props.setProperty("driverClassName", "com.mysql.jdbc.Driver");
            dataSource = DruidDataSourceFactory.createDataSource(props);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    //提供获取连接的方法
    public static Connection getConnection() throws SQLException {
        return dataSource.getConnection();
    }

    // 提供关闭资源的方法【connection是归还到连接池】
    // 提供关闭资源的方法 【方法重载】3 dql
    public static void closeResource(ResultSet resultSet, PreparedStatement preparedStatement,
                                     Connection connection) {
        // 关闭结果集
        // ctrl+alt+m 将java语句抽取成方法
        closeResultSet(resultSet);
        // 关闭语句执行者
        closePrepareStatement(preparedStatement);
        // 关闭连接
        closeConnection(connection);
    }

    private static void closeConnection(Connection connection) {
        if (connection != null) {
            try {
                connection.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
    }

    private static void closePrepareStatement(PreparedStatement preparedStatement) {
        if (preparedStatement != null) {
            try {
                preparedStatement.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
    }


    private static void closeResultSet(ResultSet resultSet) {
        if (resultSet != null) {
            try {
                resultSet.close();
            } catch (SQLException e) {
                e.printStackTrace();
            }
        }
    }
}

package com.atguigu.qzpoint.util

import java.sql.{Connection, PreparedStatement, ResultSet}

trait QueryCallback {
  def process(rs: ResultSet)
}

class SqlProxy {
  private var rs: ResultSet = _
  private var psmt: PreparedStatement = _

  /**
    * 执行修改语句
    *
    * @param conn
    * @param sql
    * @param params
    * @return
    */
  def executeUpdate(conn: Connection, sql: String, params: Array[Any]): Int = {
    var rtn = 0
    try {
      psmt = conn.prepareStatement(sql)
      if (params != null && params.length > 0) {
        for (i <- 0 until params.length) {
          psmt.setObject(i + 1, params(i))
        }
      }
      rtn = psmt.executeUpdate()
    } catch {
      case e: Exception => e.printStackTrace()
    }
    rtn
  }

  /**
    * 执行查询语句
    * 执行查询语句
    *
    * @param conn
    * @param sql
    * @param params
    * @return
    */
  def executeQuery(conn: Connection, sql: String, params: Array[Any], queryCallback: QueryCallback) = {
    rs = null
    try {
      psmt = conn.prepareStatement(sql)
      if (params != null && params.length > 0) {
        for (i <- 0 until params.length) {
          psmt.setObject(i + 1, params(i))
        }
      }
      rs = psmt.executeQuery()
      queryCallback.process(rs)
    } catch {
      case e: Exception => e.printStackTrace()
    }
  }

  def shutdown(conn: Connection): Unit = DataSourceUtil.closeResource(rs, psmt, conn)
}

package com.atguigu.qzpoint.streaming

import java.lang
import java.sql.ResultSet
import java.util.Random

import com.atguigu.qzpoint.util.{DataSourceUtil, QueryCallback, SqlProxy}
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}

import scala.collection.mutable

object RegisterStreaming {
  private val groupid = "register_group_test"

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local[2]")
      .set("spark.streaming.kafka.maxRatePerPartition", "50")
      .set("spark.streaming.stopGracefullyOnShutdown", "true")
    val ssc = new StreamingContext(conf, Seconds(3))
    val topics = Array("register_topic")
    val kafkaMap: Map[String, Object] = Map[String, Object](
      "bootstrap.servers" -> "hadoop102:9092,hadoop103:9092,hadoop104:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> groupid,
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: lang.Boolean)
    )
    ssc.checkpoint("hdfs://hadoop102:9000/user/atguigu/sparkstreaming/checkpoint")
    //查询mysql中是否有偏移量
    val sqlProxy = new SqlProxy()
    val offsetMap = new mutable.HashMap[TopicPartition, Long]()
    val client = DataSourceUtil.getConnection
    try {
      sqlProxy.executeQuery(client, "select * from `offset_manager` where groupid=?", Array(groupid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            val model = new TopicPartition(rs.getString(2), rs.getInt(3))
            val offset = rs.getLong(4)
            offsetMap.put(model, offset)
          }
          rs.close() //关闭游标
        }
      })
    } catch {
      case e: Exception => e.printStackTrace()
    } finally {
      sqlProxy.shutdown(client)
    }
    //设置kafka消费数据的参数  判断本地是否有偏移量  有则根据偏移量继续消费 无则重新消费
    val stream: InputDStream[ConsumerRecord[String, String]] = if (offsetMap.isEmpty) {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap))
    } else {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap, offsetMap))
    }
    val resultDStream = stream.filter(item => item.value().split("\t").length == 3).
      mapPartitions(partitions => {
        partitions.map(item => {
          val line = item.value()
          val arr = line.split("\t")
          val app_name = arr(1) match {
            case "1" => "PC"
            case "2" => "APP"
            case _ => "Other"
          }
          (app_name, 1)
        })
      })
    resultDStream.cache()
    //    resultDStream.reduceByKeyAndWindow((x: Int, y: Int) => x + y, Seconds(60), Seconds(6)).print()
    val updateFunc = (values: Seq[Int], state: Option[Int]) => {
      val currentCount = values.sum //本批次求和
      val previousCount = state.getOrElse(0) //历史数据
      Some(currentCount + previousCount)
    }
    resultDStream.updateStateByKey(updateFunc).print()


//        val dsStream = stream.filter(item => item.value().split("\t").length == 3)
//          .mapPartitions(partitions =>
//            partitions.map(item => {
//              val rand = new Random()
//              val line = item.value()
//              val arr = line.split("\t")
//              val app_id = arr(1)
//              (rand.nextInt(3) + "_" + app_id, 1)
//            }))
//        dsStream.print()
//        val a = dsStream.reduceByKey(_ + _)
//        a.print()
//        a.map(item => {
//          val appid = item._1.split("_")(1)
//          (appid, item._2)
//        }).reduceByKey(_ + _).print()

    //处理完 业务逻辑后 手动提交offset维护到本地 mysql中
    stream.foreachRDD(rdd => {
      val sqlProxy = new SqlProxy()
      val client = DataSourceUtil.getConnection
      try {
        val offsetRanges: Array[OffsetRange] = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
        for (or <- offsetRanges) {
          sqlProxy.executeUpdate(client, "replace into `offset_manager` (groupid,topic,`partition`,untilOffset) values(?,?,?,?)",
            Array(groupid, or.topic, or.partition.toString, or.untilOffset))
        }
      } catch {
        case e: Exception => e.printStackTrace()
      } finally {
        sqlProxy.shutdown(client)
      }
    })
    ssc.start()
    ssc.awaitTermination()
  }
}

package com.atguigu.qzpoint.streaming

import java.lang
import java.sql.{Connection, ResultSet}
import java.time.LocalDateTime
import java.time.format.DateTimeFormatter

import com.atguigu.qzpoint.util.{DataSourceUtil, QueryCallback, SqlProxy}
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}

import scala.collection.mutable

/**
  * 知识点掌握度实时统计
  */
object QzPointStreaming {

  private val groupid = "qz_point_group"

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local[*]")
      .set("spark.streaming.kafka.maxRatePerPartition", "50")
      .set("spark.streaming.stopGracefullyOnShutdown", "true")
    val ssc = new StreamingContext(conf, Seconds(3))
    val topics = Array("qz_log")
    val kafkaMap: Map[String, Object] = Map[String, Object](
      "bootstrap.servers" -> "hadoop102:9092,hadoop103:9092,hadoop104:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> groupid,
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: lang.Boolean)
    )
    //查询mysql中是否存在偏移量
    val sqlProxy = new SqlProxy()
    val offsetMap = new mutable.HashMap[TopicPartition, Long]()
    val client = DataSourceUtil.getConnection
    try {
      sqlProxy.executeQuery(client, "select * from `offset_manager` where groupid=?", Array(groupid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            val model = new TopicPartition(rs.getString(2), rs.getInt(3))
            val offset = rs.getLong(4)
            offsetMap.put(model, offset)
          }
          rs.close() //关闭游标
        }
      })
    } catch {
      case e: Exception => e.printStackTrace()
    } finally {
      sqlProxy.shutdown(client)
    }
    //设置kafka消费数据的参数  判断本地是否有偏移量  有则根据偏移量继续消费 无则重新消费
    val stream: InputDStream[ConsumerRecord[String, String]] = if (offsetMap.isEmpty) {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap))
    } else {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap, offsetMap))
    }
    //过滤不正常数据 获取数据
    val dsStream = stream.filter(item => item.value().split("\t").length == 6).
      mapPartitions(partition => partition.map(item => {
        val line = item.value()
        val arr = line.split("\t")
        val uid = arr(0) //用户id
        val courseid = arr(1) //课程id
        val pointid = arr(2) //知识点id
        val questionid = arr(3) //题目id
        val istrue = arr(4) //是否正确
        val createtime = arr(5) //创建时间
        (uid, courseid, pointid, questionid, istrue, createtime)
      }))
    dsStream.foreachRDD(rdd => {
      //获取相同用户 同一课程 同一知识点的数据
      val groupRdd = rdd.groupBy(item => item._1 + "-" + item._2 + "-" + item._3)
      groupRdd.foreachPartition(partition => {
        //在分区下获取jdbc连接
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partition.foreach { case (key, iters) =>
            qzQuestionUpdate(key, iters, sqlProxy, client) //对题库进行更新操作
          }
        } catch {
          case e: Exception => e.printStackTrace()
        }
        finally {
          sqlProxy.shutdown(client)
        }
      }
      )
    })
    //处理完 业务逻辑后 手动提交offset维护到本地 mysql中
    stream.foreachRDD(rdd => {
      val sqlProxy = new SqlProxy()
      val client = DataSourceUtil.getConnection
      try {
        val offsetRanges: Array[OffsetRange] = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
        for (or <- offsetRanges) {
          sqlProxy.executeUpdate(client, "replace into `offset_manager` (groupid,topic,`partition`,untilOffset) values(?,?,?,?)",
            Array(groupid, or.topic, or.partition.toString, or.untilOffset))
        }
      } catch {
        case e: Exception => e.printStackTrace()
      } finally {
        sqlProxy.shutdown(client)
      }
    })
    ssc.start()
    ssc.awaitTermination()
  }

  /**
    * 对题目表进行更新操作
    *
    * @param key
    * @param iters
    * @param sqlProxy
    * @param client
    * @return
    */
  def qzQuestionUpdate(key: String, iters: Iterable[(String, String, String, String, String, String)], sqlProxy: SqlProxy, client: Connection) = {
    val keys = key.split("-")
    val userid = keys(0).toInt
    val courseid = keys(1).toInt
    val pointid = keys(2).toInt
    val array = iters.toArray
    val questionids = array.map(_._4).distinct //对当前批次的数据下questionid 去重
    //查询历史数据下的 questionid
    var questionids_history: Array[String] = Array()
    sqlProxy.executeQuery(client, "select questionids from qz_point_history where userid=? and courseid=? and pointid=?",
      Array(userid, courseid, pointid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            questionids_history = rs.getString(1).split(",")
          }
          rs.close() //关闭游标
        }
      })
    //获取到历史数据后再与当前数据进行拼接 去重
    val resultQuestionid = questionids.union(questionids_history).distinct
    val countSize = resultQuestionid.length
    val resultQuestionid_str = resultQuestionid.mkString(",")
    val qz_count = questionids.length //去重后的题个数
    var qz_sum = array.length //获取当前批次题总数
    var qz_istrue = array.filter(_._5.equals("1")).size //获取当前批次做正确的题个数
    val createtime = array.map(_._6).min //获取最早的创建时间 作为表中创建时间
    //更新qz_point_set 记录表 此表用于存当前用户做过的questionid表
    val updatetime = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss").format(LocalDateTime.now())
    sqlProxy.executeUpdate(client, "insert into qz_point_history(userid,courseid,pointid,questionids,createtime,updatetime) values(?,?,?,?,?,?) " +
      " on duplicate key update questionids=?,updatetime=?", Array(userid, courseid, pointid, resultQuestionid_str, createtime, createtime, resultQuestionid_str, updatetime))

    var qzSum_history = 0
    var istrue_history = 0
    sqlProxy.executeQuery(client, "select qz_sum,qz_istrue from qz_point_detail where userid=? and courseid=? and pointid=?",
      Array(userid, courseid, pointid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            qzSum_history += rs.getInt(1)
            istrue_history += rs.getInt(2)
          }
          rs.close()
        }
      })
    qz_sum += qzSum_history
    qz_istrue += istrue_history
    val correct_rate = qz_istrue.toDouble / qz_sum.toDouble //计算正确率
    //计算完成率
    //假设每个知识点下一共有30道题  先计算题的做题情况 再计知识点掌握度
    val qz_detail_rate = countSize.toDouble / 30 //算出做题情况乘以 正确率 得出完成率 假如30道题都做了那么正确率等于 知识点掌握度
    val mastery_rate = qz_detail_rate * correct_rate
    sqlProxy.executeUpdate(client, "insert into qz_point_detail(userid,courseid,pointid,qz_sum,qz_count,qz_istrue,correct_rate,mastery_rate,createtime,updatetime)" +
      " values(?,?,?,?,?,?,?,?,?,?) on duplicate key update qz_sum=?,qz_count=?,qz_istrue=?,correct_rate=?,mastery_rate=?,updatetime=?",
      Array(userid, courseid, pointid, qz_sum, countSize, qz_istrue, correct_rate, mastery_rate, createtime, updatetime, qz_sum, countSize, qz_istrue, correct_rate, mastery_rate, updatetime))

  }
}

package com.atguigu.qzpoint.streaming

import java.lang
import java.sql.{Connection, ResultSet}
import java.text.NumberFormat

import com.atguigu.qzpoint.util.{DataSourceUtil, ParseJsonData, QueryCallback, SqlProxy}
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkFiles}
import org.lionsoul.ip2region.{DbConfig, DbSearcher}

import scala.collection.mutable
import scala.collection.mutable.ArrayBuffer

/**
  * 页面转换率实时统计
  */
object PageStreaming {
  private val groupid = "vip_count_groupid"

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local[*]")
      .set("spark.streaming.kafka.maxRatePerPartition", "30")
      .set("spark.streaming.stopGracefullyOnShutdown", "true")
  
    val ssc = new StreamingContext(conf, Seconds(3))
    val topics = Array("page_topic")
    val kafkaMap: Map[String, Object] = Map[String, Object](
      "bootstrap.servers" -> "hadoop102:9092,hadoop103:9092,hadoop104:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> groupid,
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: lang.Boolean)
    )
    //查询mysql中是否存在偏移量
    val sqlProxy = new SqlProxy()
    val offsetMap = new mutable.HashMap[TopicPartition, Long]()
    val client = DataSourceUtil.getConnection
    try {
      sqlProxy.executeQuery(client, "select *from `offset_manager` where groupid=?", Array(groupid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            val model = new TopicPartition(rs.getString(2), rs.getInt(3))
            val offset = rs.getLong(4)
            offsetMap.put(model, offset)
          }
          rs.close()
        }
      })
    } catch {
      case e: Exception => e.printStackTrace()
    } finally {
      sqlProxy.shutdown(client)
    }

    //设置kafka消费数据的参数 判断本地是否有偏移量  有则根据偏移量继续消费 无则重新消费
    val stream: InputDStream[ConsumerRecord[String, String]] = if (offsetMap.isEmpty) {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap))
    } else {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap, offsetMap))
    }
    //解析json数据
    val dsStream = stream.map(item => item.value()).mapPartitions(partition => {
      partition.map(item => {
        val jsonObject = ParseJsonData.getJsonData(item)
        val uid = if (jsonObject.containsKey("uid")) jsonObject.getString("uid") else ""
        val app_id = if (jsonObject.containsKey("app_id")) jsonObject.getString("app_id") else ""
        val device_id = if (jsonObject.containsKey("device_id")) jsonObject.getString("device_id") else ""
        val ip = if (jsonObject.containsKey("ip")) jsonObject.getString("ip") else ""
        val last_page_id = if (jsonObject.containsKey("last_page_id")) jsonObject.getString("last_page_id") else ""
        val pageid = if (jsonObject.containsKey("page_id")) jsonObject.getString("page_id") else ""
        val next_page_id = if (jsonObject.containsKey("next_page_id")) jsonObject.getString("next_page_id") else ""
        (uid, app_id, device_id, ip, last_page_id, pageid, next_page_id)
      })
    }).filter(item => {
      !item._5.equals("") && !item._6.equals("") && !item._7.equals("")
    })
    dsStream.cache()
    val pageValueDStream = dsStream.map(item => (item._5 + "_" + item._6 + "_" + item._7, 1))
    val resultDStream = pageValueDStream.reduceByKey(_ + _)
    resultDStream.foreachRDD(rdd => {
      rdd.foreachPartition(partition => {
        //在分区下获取jdbc连接
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partition.foreach(item => {
            calcPageJumpCount(sqlProxy, item, client) //计算页面跳转个数
          })
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(client)
        }
      })
    })

    ssc.sparkContext.addFile(this.getClass.getResource("/ip2region.db").getPath) //广播文件
    val ipDStream = dsStream.mapPartitions(patitions => {
      val dbFile = SparkFiles.get("ip2region.db")
      val ipsearch = new DbSearcher(new DbConfig(), dbFile)
      patitions.map { item =>
        val ip = item._4
        val province = ipsearch.memorySearch(ip).getRegion().split("\\|")(2) //获取ip详情   中国|0|上海|上海市|有线通
        (province, 1l) //根据省份 统计点击个数
      }
    }).reduceByKey(_ + _)


    ipDStream.foreachRDD(rdd => {
      //查询mysql历史数据 转成rdd
      val ipSqlProxy = new SqlProxy()
      val ipClient = DataSourceUtil.getConnection
      try {
        val history_data = new ArrayBuffer[(String, Long)]()
        ipSqlProxy.executeQuery(ipClient, "select province,num from tmp_city_num_detail", null, new QueryCallback {
          override def process(rs: ResultSet): Unit = {
            while (rs.next()) {
              val tuple = (rs.getString(1), rs.getLong(2))
              history_data += tuple
            }
          }
        })
        val history_rdd = ssc.sparkContext.makeRDD(history_data)
        val resultRdd = history_rdd.fullOuterJoin(rdd).map(item => {
          val province = item._1
          val nums = item._2._1.getOrElse(0l) + item._2._2.getOrElse(0l)
          (province, nums)
        })
        resultRdd.foreachPartition(partitions => {
          val sqlProxy = new SqlProxy()
          val client = DataSourceUtil.getConnection
          try {
            partitions.foreach(item => {
              val province = item._1
              val num = item._2
              //修改mysql数据 并重组返回最新结果数据
              sqlProxy.executeUpdate(client, "insert into tmp_city_num_detail(province,num)values(?,?) on duplicate key update num=?",
                Array(province, num, num))
            })
          } catch {
            case e: Exception => e.printStackTrace()
          } finally {
            sqlProxy.shutdown(client)
          }
        })
        val top3Rdd = resultRdd.sortBy[Long](_._2, false).take(3)
        sqlProxy.executeUpdate(ipClient, "truncate table top_city_num", null)
        top3Rdd.foreach(item => {
          sqlProxy.executeUpdate(ipClient, "insert into top_city_num (province,num) values(?,?)", Array(item._1, item._2))
        })
      } catch {
        case e: Exception => e.printStackTrace()
      } finally {
        sqlProxy.shutdown(ipClient)
      }
    })

    //计算转换率
    //处理完 业务逻辑后 手动提交offset维护到本地 mysql中
    stream.foreachRDD(rdd => {
      val sqlProxy = new SqlProxy()
      val client = DataSourceUtil.getConnection
      try {
        calcJumRate(sqlProxy, client) //计算转换率
        val offsetRanges: Array[OffsetRange] = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
        for (or <- offsetRanges) {
          sqlProxy.executeUpdate(client, "replace into `offset_manager` (groupid,topic,`partition`,untilOffset) values(?,?,?,?)",
            Array(groupid, or.topic, or.partition.toString, or.untilOffset))
        }
      } catch {
        case e: Exception => e.printStackTrace()
      } finally {
        sqlProxy.shutdown(client)
      }
    })
    ssc.start()
    ssc.awaitTermination()
  }

  /**
    * 计算页面跳转个数
    *
    * @param sqlProxy
    * @param item
    * @param client
    */
  def calcPageJumpCount(sqlProxy: SqlProxy, item: (String, Int), client: Connection): Unit = {
    val keys = item._1.split("_")
    var num: Long = item._2
    val page_id = keys(1).toInt //获取当前page_id
    val last_page_id = keys(0).toInt //获取上一page_id
    val next_page_id = keys(2).toInt //获取下页面page_id
    //查询当前page_id的历史num个数
    sqlProxy.executeQuery(client, "select num from page_jump_rate where page_id=?", Array(page_id), new QueryCallback {
      override def process(rs: ResultSet): Unit = {
        while (rs.next()) {
          num += rs.getLong(1)
        }
        rs.close()
      }

      //对num 进行修改 并且判断当前page_id是否为首页
      if (page_id == 1) {
        sqlProxy.executeUpdate(client, "insert into page_jump_rate(last_page_id,page_id,next_page_id,num,jump_rate)" +
          "values(?,?,?,?,?) on duplicate key update num=num+?", Array(last_page_id, page_id, next_page_id, num, "100%", num))
      } else {
        sqlProxy.executeUpdate(client, "insert into page_jump_rate(last_page_id,page_id,next_page_id,num)" +
          "values(?,?,?,?) on duplicate key update num=num+?", Array(last_page_id, page_id, next_page_id, num, num))
      }
    })
  }

  /**
    * 计算转换率
    */
  def calcJumRate(sqlProxy: SqlProxy, client: Connection): Unit = {
    var page1_num = 0l
    var page2_num = 0l
    var page3_num = 0l
    sqlProxy.executeQuery(client, "select num from page_jump_rate where page_id=?", Array(1), new QueryCallback {
      override def process(rs: ResultSet): Unit = {
        while (rs.next()) {
          page1_num = rs.getLong(1)
        }
      }
    })
    sqlProxy.executeQuery(client, "select num from page_jump_rate where page_id=?", Array(2), new QueryCallback {
      override def process(rs: ResultSet): Unit = {
        while (rs.next()) {
          page2_num = rs.getLong(1)
        }
      }
    })
    sqlProxy.executeQuery(client, "select num from page_jump_rate where page_id=?", Array(3), new QueryCallback {
      override def process(rs: ResultSet): Unit = {
        while (rs.next()) {
          page3_num = rs.getLong(1)
        }
      }
    })
    val nf = NumberFormat.getPercentInstance
    val page1ToPage2Rate = if (page1_num == 0) "0%" else nf.format(page2_num.toDouble / page1_num.toDouble)
    val page2ToPage3Rate = if (page2_num == 0) "0%" else nf.format(page3_num.toDouble / page2_num.toDouble)
    sqlProxy.executeUpdate(client, "update page_jump_rate set jump_rate=? where page_id=?", Array(page1ToPage2Rate, 2))
    sqlProxy.executeUpdate(client, "update page_jump_rate set jump_rate=? where page_id=?", Array(page2ToPage3Rate, 3))
  }

}

package com.atguigu.qzpoint.streaming

import java.lang
import java.sql.{Connection, ResultSet}

import com.atguigu.qzpoint.bean.LearnModel
import com.atguigu.qzpoint.util.{DataSourceUtil, ParseJsonData, QueryCallback, SqlProxy}
import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.TopicPartition
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010._
import org.apache.spark.streaming.{Seconds, StreamingContext}

import scala.collection.mutable
import scala.collection.mutable.ArrayBuffer

object CourseLearnStreaming {
  private val groupid = "course_learn_test1"

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName)
      .set("spark.streaming.kafka.maxRatePerPartition", "30")
      .set("spark.streaming.stopGracefullyOnShutdown", "true")

    val ssc = new StreamingContext(conf, Seconds(3))
    val topics = Array("course_learn")
    val kafkaMap: Map[String, Object] = Map[String, Object](
      "bootstrap.servers" -> "hadoop102:9092,hadoop103:9092,hadoop104:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> groupid,
      "auto.offset.reset" -> "earliest",
      "enable.auto.commit" -> (false: lang.Boolean)
    )
    //查询mysql是否存在偏移量
    val sqlProxy = new SqlProxy()
    val offsetMap = new mutable.HashMap[TopicPartition, Long]()
    val client = DataSourceUtil.getConnection
    try {
      sqlProxy.executeQuery(client, "select *from `offset_manager` where groupid=?", Array(groupid), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            val model = new TopicPartition(rs.getString(2), rs.getInt(3))
            val offset = rs.getLong(4)
            offsetMap.put(model, offset)
          }
          rs.close()
        }
      })
    } catch {
      case e: Exception => e.printStackTrace()
    } finally {
      sqlProxy.shutdown(client)
    }
    //设置kafka消费数据的参数 判断本地是否有偏移量  有则根据偏移量继续消费 无则重新消费
    val stream: InputDStream[ConsumerRecord[String, String]] = if (offsetMap.isEmpty) {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap))
    } else {
      KafkaUtils.createDirectStream(
        ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String, String](topics, kafkaMap, offsetMap))
    }

    //解析json数据
    val dsStream = stream.mapPartitions(partitions => {
      partitions.map(item => {
        val json = item.value()
        val jsonObject = ParseJsonData.getJsonData(json)
        val userId = jsonObject.getIntValue("uid")
        val cwareid = jsonObject.getIntValue("cwareid")
        val videoId = jsonObject.getIntValue("videoid")
        val chapterId = jsonObject.getIntValue("chapterid")
        val edutypeId = jsonObject.getIntValue("edutypeid")
        val subjectId = jsonObject.getIntValue("subjectid")
        val sourceType = jsonObject.getString("sourceType")
        val speed = jsonObject.getIntValue("speed")
        val ts = jsonObject.getLong("ts")
        val te = jsonObject.getLong("te")
        val ps = jsonObject.getIntValue("ps")
        val pe = jsonObject.getIntValue("pe")
        LearnModel(userId, cwareid, videoId, chapterId, edutypeId, subjectId, sourceType, speed, ts, te, ps, pe)
      })
    })

    dsStream.foreachRDD(rdd => {
      rdd.cache()
      //统计播放视频 有效时长 完成时长 总时长
      rdd.groupBy(item => item.userId + "_" + item.cwareId + "_" + item.videoId).foreachPartition(partitoins => {
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partitoins.foreach { case (key, iters) =>
            calcVideoTime(key, iters, sqlProxy, client) //计算视频时长
          }
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(client)
        }
      })
      //统计章节下视频播放总时长
      rdd.mapPartitions(partitions => {
        partitions.map(item => {
          val totaltime = Math.ceil((item.te - item.ts) / 1000).toLong
          val key = item.chapterId
          (key, totaltime)
        })
      }).reduceByKey(_ + _)
        .foreachPartition(partitoins => {
          val sqlProxy = new SqlProxy()
          val client = DataSourceUtil.getConnection
          try {
            partitoins.foreach(item => {
              sqlProxy.executeUpdate(client, "insert into chapter_learn_detail(chapterid,totaltime) values(?,?) on duplicate key" +
                " update totaltime=totaltime+?", Array(item._1, item._2, item._2))
            })
          } catch {
            case e: Exception => e.printStackTrace()
          } finally {
            sqlProxy.shutdown(client)
          }
        })

      //统计课件下的总播放时长
      rdd.mapPartitions(partitions => {
        partitions.map(item => {
          val totaltime = Math.ceil((item.te - item.ts) / 1000).toLong
          val key = item.cwareId
          (key, totaltime)
        })
      }).reduceByKey(_ + _).foreachPartition(partitions => {
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partitions.foreach(item => {
            sqlProxy.executeUpdate(client, "insert into cwareid_learn_detail(cwareid,totaltime) values(?,?) on duplicate key " +
              "update totaltime=totaltime+?", Array(item._1, item._2, item._2))
          })
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(client)
        }
      })

      //统计辅导下的总播放时长
      rdd.mapPartitions(partitions => {
        partitions.map(item => {
          val totaltime = Math.ceil((item.te - item.ts) / 1000).toLong
          val key = item.edutypeId
          (key, totaltime)
        })
      }).reduceByKey(_ + _).foreachPartition(partitions => {
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partitions.foreach(item => {
            sqlProxy.executeUpdate(client, "insert into edutype_learn_detail(edutypeid,totaltime) values(?,?) on duplicate key " +
              "update totaltime=totaltime+?", Array(item._1, item._2, item._2))
          })
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(client)
        }
      })

      //统计同一资源平台下的总播放时长
      rdd.mapPartitions(partitions => {
        partitions.map(item => {
          val totaltime = Math.ceil((item.te - item.ts) / 1000).toLong
          val key = item.sourceType
          (key, totaltime)
        })
      }).reduceByKey(_ + _).foreachPartition(partitions => {
        val sqlProxy = new SqlProxy()
        val client = DataSourceUtil.getConnection
        try {
          partitions.foreach(item => {
            sqlProxy.executeUpdate(client, "insert into sourcetype_learn_detail (sourcetype_learn,totaltime) values(?,?) on duplicate key " +
              "update totaltime=totaltime+?", Array(item._1, item._2, item._2))
          })
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(client)
        }
      })
      // 统计同一科目下的播放总时长
      rdd.mapPartitions(partitions => {
        partitions.map(item => {
          val totaltime = Math.ceil((item.te - item.ts) / 1000).toLong
          val key = item.subjectId
          (key, totaltime)
        })
      }).reduceByKey(_ + _).foreachPartition(partitons => {
        val sqlProxy = new SqlProxy()
        val clinet = DataSourceUtil.getConnection
        try {
          partitons.foreach(item => {
            sqlProxy.executeUpdate(clinet, "insert into subject_learn_detail(subjectid,totaltime) values(?,?) on duplicate key " +
              "update totaltime=totaltime+?", Array(item._1, item._2, item._2))
          })
        } catch {
          case e: Exception => e.printStackTrace()
        } finally {
          sqlProxy.shutdown(clinet)
        }
      })

    })
    //计算转换率
    //处理完 业务逻辑后 手动提交offset维护到本地 mysql中
    stream.foreachRDD(rdd => {
      val sqlProxy = new SqlProxy()
      val client = DataSourceUtil.getConnection
      try {
        val offsetRanges: Array[OffsetRange] = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
        for (or <- offsetRanges) {
          sqlProxy.executeUpdate(client, "replace into `offset_manager` (groupid,topic,`partition`,untilOffset) values(?,?,?,?)",
            Array(groupid, or.topic, or.partition.toString, or.untilOffset))
        }
      } catch {
        case e: Exception => e.printStackTrace()
      } finally {
        sqlProxy.shutdown(client)
      }
    })
    ssc.start()
    ssc.awaitTermination()
  }

  /**
    * 计算视频 有效时长  完成时长 总时长
    *
    * @param key
    * @param iters
    * @param sqlProxy
    * @param client
    */
  def calcVideoTime(key: String, iters: Iterable[LearnModel], sqlProxy: SqlProxy, client: Connection) = {
    val keys = key.split("_")
    val userId = keys(0).toInt
    val cwareId = keys(1).toInt
    val videoId = keys(2).toInt
    //查询历史数据
    var interval_history = ""
    sqlProxy.executeQuery(client, "select play_interval from video_interval where userid=? and cwareid=? and videoid=?",
      Array(userId, cwareId, videoId), new QueryCallback {
        override def process(rs: ResultSet): Unit = {
          while (rs.next()) {
            interval_history = rs.getString(1)
          }
          rs.close()
        }
      })
    var effective_duration_sum = 0l //有效总时长
    var complete_duration_sum = 0l //完成总时长
    var cumulative_duration_sum = 0l //播放总时长
    val learnList = iters.toList.sortBy(item => item.ps) //转成list 并根据开始区间升序排序
    learnList.foreach(item => {
      if ("".equals(interval_history)) {
        //没有历史区间
        val play_interval = item.ps + "-" + item.pe //有效区间
        val effective_duration = Math.ceil((item.te - item.ts) / 1000) //有效时长
        val complete_duration = item.pe - item.ps //完成时长
        effective_duration_sum += effective_duration.toLong
        cumulative_duration_sum += effective_duration.toLong
        complete_duration_sum += complete_duration
        interval_history = play_interval
      } else {
        //有历史区间进行对比
        val interval_arry = interval_history.split(",").sortBy(a => (a.split("-")(0).toInt, a.split("-")(1).toInt))
        val tuple = getEffectiveInterval(interval_arry, item.ps, item.pe)
        val complete_duration = tuple._1 //获取实际有效完成时长
        val effective_duration = Math.ceil((item.te - item.ts) / 1000) / (item.pe - item.ps) * complete_duration //计算有效时长
        val cumulative_duration = Math.ceil((item.te - item.ts) / 1000) //累计时长
        interval_history = tuple._2
        effective_duration_sum += effective_duration.toLong
        complete_duration_sum += complete_duration
        cumulative_duration_sum += cumulative_duration.toLong
      }
      sqlProxy.executeUpdate(client, "insert into video_interval(userid,cwareid,videoid,play_interval) values(?,?,?,?) " +
        "on duplicate key update play_interval=?", Array(userId, cwareId, videoId, interval_history, interval_history))
      sqlProxy.executeUpdate(client, "insert into video_learn_detail(userid,cwareid,videoid,totaltime,effecttime,completetime) " +
        "values(?,?,?,?,?,?) on duplicate key update totaltime=totaltime+?,effecttime=effecttime+?,completetime=completetime+?",
        Array(userId, cwareId, videoId, cumulative_duration_sum, effective_duration_sum, complete_duration_sum, cumulative_duration_sum,
          effective_duration_sum, complete_duration_sum))
    })
  }

  /**
    * 计算有效区间
    *
    * @param array
    * @param start
    * @param end
    * @return
    */
  def getEffectiveInterval(array: Array[String], start: Int, end: Int) = {
    var effective_duration = end - start
    var bl = false //是否对有效时间进行修改
    import scala.util.control.Breaks._
    breakable {
      for (i <- 0 until array.length) {
        //循环各区间段
        var historyStart = 0 //获取其中一段的开始播放区间
        var historyEnd = 0 //获取其中一段结束播放区间
        val item = array(i)
        try {
          historyStart = item.split("-")(0).toInt
          historyEnd = item.split("-")(1).toInt
        } catch {
          case e: Exception => throw new Exception("error array:" + array.mkString(","))
        }
        if (start >= historyStart && historyEnd >= end) {
          //已有数据占用全部播放时长 此次播放无效
          effective_duration = 0
          bl = true
          break()
        } else if (start <= historyStart && end > historyStart && end < historyEnd) {
          //和已有数据左侧存在交集 扣除部分有效时间（以老数据为主进行对照）
          effective_duration -= end - historyStart
          array(i) = start + "-" + historyEnd
          bl = true
        } else if (start > historyStart && start < historyEnd && end >= historyEnd) {
          //和已有数据右侧存在交集 扣除部分有效时间
          effective_duration -= historyEnd - start
          array(i) = historyStart + "-" + end
          bl = true
        } else if (start < historyStart && end > historyEnd) {
          //现数据 大于旧数据 扣除旧数据所有有效时间
          effective_duration -= historyEnd - historyStart
          array(i) = start + "-" + end
          bl = true
        }
      }
    }
    val result = bl match {
      case false => {
        //没有修改原array 没有交集 进行新增
        val distinctArray2 = ArrayBuffer[String]()
        distinctArray2.appendAll(array)
        distinctArray2.append(start + "-" + end)
        val distinctArray = distinctArray2.distinct.sortBy(a => (a.split("-")(0).toInt, a.split("-")(1).toInt))
        val tmpArray = ArrayBuffer[String]()
        tmpArray.append(distinctArray(0))
        for (i <- 1 until distinctArray.length) {
          val item = distinctArray(i).split("-")
          val tmpItem = tmpArray(tmpArray.length - 1).split("-")
          val itemStart = item(0)
          val itemEnd = item(1)
          val tmpItemStart = tmpItem(0)
          val tmpItemEnd = tmpItem(1)
          if (tmpItemStart.toInt < itemStart.toInt && tmpItemEnd.toInt < itemStart.toInt) {
            //没有交集
            tmpArray.append(itemStart + "-" + itemEnd)
          } else {
            //有交集
            val resultStart = tmpItemStart
            val resultEnd = if (tmpItemEnd.toInt > itemEnd.toInt) tmpItemEnd else itemEnd
            tmpArray(tmpArray.length - 1) = resultStart + "-" + resultEnd
          }
        }
        val play_interval = tmpArray.sortBy(a => (a.split("-")(0).toInt, a.split("-")(1).toInt)).mkString(",")
        play_interval
      }
      case true => {
        //修改了原array 进行区间重组
        val distinctArray = array.distinct.sortBy(a => (a.split("-")(0).toInt, a.split("-")(1).toInt))
        val tmpArray = ArrayBuffer[String]()
        tmpArray.append(distinctArray(0))
        for (i <- 1 until distinctArray.length) {
          val item = distinctArray(i).split("-")
          val tmpItem = tmpArray(tmpArray.length - 1).split("-")
          val itemStart = item(0)
          val itemEnd = item(1)
          val tmpItemStart = tmpItem(0)
          val tmpItemEnd = tmpItem(1)
          if (tmpItemStart.toInt < itemStart.toInt && tmpItemEnd.toInt < itemStart.toInt) {
            //没有交集
            tmpArray.append(itemStart + "-" + itemEnd)
          } else {
            //有交集
            val resultStart = tmpItemStart
            val resultEnd = if (tmpItemEnd.toInt > itemEnd.toInt) tmpItemEnd else itemEnd
            tmpArray(tmpArray.length - 1) = resultStart + "-" + resultEnd
          }
        }
        val play_interval = tmpArray.sortBy(a => (a.split("-")(0).toInt, a.split("-")(1).toInt)).mkString(",")
        play_interval
      }
    }
    (effective_duration, result)
  }
}

spark-submit --master yarn --deploy-mode client --driver-memory 1g --num-executors 2 --executor-cores 2 --executor-memory 2g  --class com.atguigu.qzpoint.streaming.CourseLearnStreaming com_atguigu_sparkstreaming-1.0-SNAPSHOT-jar-with-dependencies.jar

spark-submit --master yarn --deploy-mode client --driver-memory 1g --num-executors 2 --executor-cores 2 --executor-memory 2g  --class com.atguigu.qzpoint.streaming.PageStreaming com_atguigu_sparkstreaming-1.0-SNAPSHOT-jar-with-dependencies.jar

spark-submit --master yarn --deploy-mode client --driver-memory 1g --num-executors 2 --executor-cores 2 --executor-memory 2g  --class com.atguigu.qzpoint.streaming.QzPointStreaming com_atguigu_sparkstreaming-1.0-SNAPSHOT-jar-with-dependencies.jar

spark-submit --master yarn --deploy-mode client --driver-memory 1g --num-executors 2 --executor-cores 2 --executor-memory 2g  --class com.atguigu.qzpoint.streaming.RegisterStreaming com_atguigu_sparkstreaming-1.0-SNAPSHOT-jar-with-dependencies.jar

dstream.foreachRdd{rdd=>{
     rdd.foreachPartition{partitions=>{
        //循环分区
//创建connection  
        partitions.foreach(record=>{
          //业务处理  使用当前connection
            }
}  
        //归还连接
}
}

title ibm-heap-analyzer

path=%PATH%;%C:\JAVA\jdk1.8.0_51\bin

E:

cd E:\IBM heapAnalyzer\IBM_DUMP_wjfx

java.exe -Xms1048M -Xmx4096M -jar ha456.jar

ps -ef |grep com.atguigu.qzpoint.streaming.QzPointStreaming

jmap -heap 6860

jmap -histo 6860 > a.log

jmap -dump:live,format=b,file=dump.log 6860