Skip to content

Z
ZHHT-IRN-BD-ANALYSIS
Commit 94d5691e by 吴延飞
Options

Merge remote-tracking branch 'origin/master'

parents 4c0870fe 47665cf9
Showing with 142 additions and 38 deletions
realtime/hologram-streaming/src/main/java/com/zhht/irn/entity/dto/Location.java
......@@ -2,6 +2,8 @@ package com.zhht.irn.entity.dto;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.Getter;
import lombok.NoArgsConstructor;
/**
* 位置信息
......@@ -11,6 +13,7 @@ import lombok.Data;
**/
@Data
@AllArgsConstructor
@NoArgsConstructor
public class Location implements Comparable<Location>{
private Double longitude ;//可选 经度
......
realtime/hologram-streaming/src/main/java/com/zhht/irn/entity/dto/TravelInfo.java
......@@ -11,7 +11,7 @@ import java.util.List;
* @create 2022-11-14 13:33{
**/
@Data
public class TravelInfo {
public class TravelInfo implements Comparable<TravelInfo> {
private Integer id ;//必填 ID
private String crossId ;//必填 路口ID
......@@ -45,4 +45,9 @@ public class TravelInfo {
private Double crossingTime ;//可选 旅行时长，单位 秒 (s)（驶离时刻-到达时刻）
private List<Location> locations ;//必填 数组，参考 位置信息字段
private String remark ;//可选 备注
@Override
public int compareTo(TravelInfo o) {
return (int)(inCrossTime-o.getInCrossTime());
}
}
realtime/hologram-streaming/src/main/java/com/zhht/irn/job/TravelSituationAnalysisJob.java
......@@ -2,21 +2,29 @@ package com.zhht.irn.job;
import com.zhht.irn.entity.dto.CycleSignalData;
import com.zhht.irn.entity.dto.TravelEvent;
import com.zhht.irn.entity.dto.TravelInfo;
import com.zhht.irn.entity.dto.TravelLineSinkInfo;
import com.zhht.irn.functions.TravelCarInfoCoProcessFunction;
import com.zhht.irn.functions.TravelEventAndCycleCoProcessFunction;
import com.zhht.irn.schema.CycleSignalKafkaSchema;
import com.zhht.irn.schema.TravelEventKafkaSchema;
import com.zhht.irn.schema.TravelInfoKafkaSchema;
import com.zhht.irn.sink.TravelLaneInfoSink;
import org.apache.flink.api.common.restartstrategy.RestartStrategies;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.common.time.Time;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.datastream.ConnectedStreams;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumerBase;
import org.apache.kafka.clients.consumer.ConsumerConfig;
import java.util.List;
import java.util.Properties;
/**
......@@ -26,7 +34,6 @@ import java.util.Properties;
* @create 2022-11-14 11:43
**/
public class TravelSituationAnalysisJob {
public static void main(String[] args) {
try {
......@@ -36,75 +43,68 @@ public class TravelSituationAnalysisJob {
// checkpoint配置
CheckpointConfig checkpointConfig = env.getCheckpointConfig();
// checkpoint时间间隔3分钟
checkpointConfig.setCheckpointInterval(1* 60 * 1000);
checkpointConfig.setCheckpointInterval(3 * 60 * 1000);
// 两次checkpoint中最短时间间隔1分钟
checkpointConfig.setMinPauseBetweenCheckpoints(60 * 1000);
checkpointConfig.setMinPauseBetweenCheckpoints(60 * 1000);
// 同时同时允许1个checkpoint进行
checkpointConfig.setMaxConcurrentCheckpoints(1);
env.getCheckpointConfig().setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
//设置重启策略
env.setRestartStrategy( RestartStrategies.fixedDelayRestart(5, Time.seconds(10)));
env.setRestartStrategy(RestartStrategies.fixedDelayRestart(10, Time.seconds(30)));
/*
关于flink checkpoint存储的设置统一在集群配置文件中设置
checkpointConfig.enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
env.setStateBackend(new RocksDBStateBackend("file:///opt/rocksDb/", true));*/
Properties kafkaProperties = new Properties();
kafkaProperties.setProperty("bootstrap.servers", "dn1.zhht:9092,dn2.zhht:9092,dn3.zhht:9092");
// kafkaProperties.setProperty("bootstrap.servers", "172.25.1.251:9092,172.25.1.122:9092,172.25.1.67:9092");
kafkaProperties.setProperty("group.id", "travel_event");
kafkaProperties.setProperty("bootstrap.servers", "dn3.zhht:9092");
// kafkaProperties.setProperty("bootstrap.servers", "139.9.157.176:9092");
// kafkaProperties.setProperty("group.id", "travel_event");
kafkaProperties.setProperty("group.id", "trips_info2");
kafkaProperties.setProperty(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true");
kafkaProperties.setProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "latest");
Properties kafkaProperties2 = new Properties();
kafkaProperties2.setProperty("bootstrap.servers", "dn1.zhht:9092,dn2.zhht:9092,dn3.zhht:9092");
// kafkaProperties2.setProperty("bootstrap.servers", "172.25.1.251:9092,172.25.1.122:9092,172.25.1.67:9092");
kafkaProperties2.setProperty("group.id", "cycle_signal");
kafkaProperties2.setProperty("bootstrap.servers", "dn3.zhht:9092");
// kafkaProperties2.setProperty("bootstrap.servers", "139.9.157.176:9092");
kafkaProperties2.setProperty("group.id", "cycle_signal2");
kafkaProperties2.setProperty(ConsumerConfig.ENABLE_AUTO_COMMIT_CONFIG, "true");
kafkaProperties2.setProperty(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "latest");
//旅行事件
FlinkKafkaConsumerBase<TravelEvent> travelEvent =
new FlinkKafkaConsumer<TravelEvent>("trips_event_info",
new TravelEventKafkaSchema(),
kafkaProperties) {
};
DataStreamSource<TravelEvent> travelEventStream = env.addSource(travelEvent);
travelEventStream.print();
//旅行信息数据
// FlinkKafkaConsumer<TravelInfo> travelInfo = new FlinkKafkaConsumer<>("t_info2", new TravelInfoKafkaSchema(), kafkaProperties);
FlinkKafkaConsumer<TravelInfo> travelInfo = new FlinkKafkaConsumer<>("trips_info", new TravelInfoKafkaSchema(), kafkaProperties);
DataStreamSource<TravelInfo> travelInfoStream = env.addSource(travelInfo).setParallelism(3);
//周期信号
FlinkKafkaConsumer<CycleSignalData> cycleSignalData =
new FlinkKafkaConsumer<>("signal_cycle_data",
new CycleSignalKafkaSchema(),
kafkaProperties2);
// FlinkKafkaConsumer<CycleSignalData> cycleSignalData = new FlinkKafkaConsumer<>("s_data2", new CycleSignalKafkaSchema(), kafkaProperties2);
FlinkKafkaConsumer<CycleSignalData> cycleSignalData = new FlinkKafkaConsumer<>("signal_cycle_data", new CycleSignalKafkaSchema(), kafkaProperties2);
DataStreamSource<CycleSignalData> cycleSignalDataStream = env.addSource(cycleSignalData);
cycleSignalDataStream.print();
//2、使用connect，把2个流联合处理
ConnectedStreams<TravelEvent, CycleSignalData> connect = travelEventStream
.connect(cycleSignalDataStream);
ConnectedStreams<TravelInfo, CycleSignalData> connect = travelInfoStream
.connect(cycleSignalDataStream);
ConnectedStreams<TravelEvent, CycleSignalData> travelInfoCycleSignalDataConnectedStreams = connect.keyBy(
(KeySelector<TravelEvent, String>) travelInfo1 -> travelInfo1.getCrossId(),
(KeySelector<CycleSignalData, String>) cycleSignalData1 -> cycleSignalData1.getCrossCode()
);
ConnectedStreams<TravelInfo, CycleSignalData> travelInfoCycleSignalDataConnectedStreams = connect.keyBy(
(KeySelector<TravelInfo, String>) travelInfo1 -> travelInfo1.getCrossId(),
(KeySelector<CycleSignalData, String>) cycleSignalData1 -> cycleSignalData1.getCrossCode()
);
travelInfoCycleSignalDataConnectedStreams.process(new TravelEventAndCycleCoProcessFunction());
SingleOutputStreamOperator<List<TravelLineSinkInfo>> sinkDataStream = travelInfoCycleSignalDataConnectedStreams
.process(new TravelCarInfoCoProcessFunction()).setParallelism(3);
env.execute();
sinkDataStream.addSink(new TravelLaneInfoSink()).setParallelism(3);
env.execute("TravelSituationAnalysisJob");
} catch (Exception e){
e.printStackTrace();
}
}
}
realtime/hologram-streaming/src/main/java/com/zhht/irn/sink/TravelLaneInfoSink.java 0 → 100644
package com.zhht.irn.sink;
import com.alibaba.druid.pool.DruidPooledConnection;
import com.zhht.irn.entity.dto.TravelLineSinkInfo;
import com.zhht.irn.functions.TravelCarInfoCoProcessFunction;
import com.zhht.irn.utils.DruidConnectPoolUtils;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction;
import org.apache.log4j.Logger;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
/**
* TravelLaneInfoSink
*
* @author Rui meng
* @description 行车情况信息sink
* @date 2022/12/15 9:39
*/
public class TravelLaneInfoSink extends RichSinkFunction<List<TravelLineSinkInfo>> {
private static Logger logger = Logger.getLogger(TravelLaneInfoSink.class);
Connection connection;
@Override
public void open(Configuration parameters) throws Exception {
super.open(parameters);
connection = DruidConnectPoolUtils.getConnection();
logger.info("建立数据库连接成功。。。。。。。");
}
@Override
public void close() throws Exception {
super.close();
if(connection!=null){
connection.close();
}
}
@Override
public void invoke(List<TravelLineSinkInfo> value, Context context) throws Exception {
super.invoke(value, context);
String sql = "INSERT INTO app_cross_line_travel_car_info" +
"(record_date,cross_id,statistic_time,cycle_begin_time,cycle_end_time, lane_id, cycle_order, direction," +
" flow_direction, pass_numbers," +
" last_car_inCross_time, average_pass_time, average_pass_speed, average_control_delay, " +
"average_stop_delay, average_stop_times, average_car_head_time_gap" +
")" +
"VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?,?,?,?,?) ";
PreparedStatement preparedStatement = connection.prepareStatement(sql);
//TODO 这里的时间使用数据携带的时间，使用最后进入路口车辆的时间，这样在补数据时，可以补充到对应的分区下
Date date = new Date();
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
SimpleDateFormat sdf2 = new SimpleDateFormat("yyyy-MM-dd");
String statistic_time = sdf.format(date);
for (TravelLineSinkInfo t :value) {
// 使用事件数据的时间划分数据分区，这样可以进行补数操作
String record_date = sdf2.format(t.getLast_car_inCross_time());
preparedStatement.setString(1, record_date);
preparedStatement.setString(2, t.getCross_id());
preparedStatement.setString(3, statistic_time);
preparedStatement.setString(4, sdf.format(t.getCycle_begin_time()));
preparedStatement.setString(5, sdf.format(t.getCycle_end_time()));
preparedStatement.setString(6, t.getLane_id());
preparedStatement.setString(7, t.getCycle_id().toString());
preparedStatement.setString(8, t.getDirection());
preparedStatement.setString(9, t.getFlow_direction());
preparedStatement.setInt(10, t.getPass_numbers());
preparedStatement.setLong(11, t.getLast_car_inCross_time());
preparedStatement.setDouble(12, t.getAverage_pass_time());
preparedStatement.setDouble(13, t.getAverage_pass_speed());
preparedStatement.setDouble(14, t.getAverage_control_delay());
preparedStatement.setDouble(15, t.getAverage_stop_delay());
preparedStatement.setDouble(16, t.getAverage_stop_times());
preparedStatement.setDouble(17, t.getAverage_car_head_time_gap());
preparedStatement.addBatch();
}
int[] ints = preparedStatement.executeBatch();
logger.info("写入数据成功。。。。。"+ints.length+"...");
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment