Skip to content

Z
ZHHT-IRN-BD-ANALYSIS
Commit 0f940087 by 吴延飞
Options

Merge remote-tracking branch 'origin/master'

# Conflicts: # realtime/hologram-streaming/src/main/java/com/zhht/irn/sink/GreenRadioSink.java # realtime/hologram-streaming/src/main/resources/doris-connector-travel-info.properties
parents 186cb966 7439d07b
Showing with 132 additions and 20 deletions
realtime/hologram-streaming/src/main/java/com/zhht/irn/functions/TravelLineSinkInfoFlatMapFunction.java 0 → 100644
package com.zhht.irn.functions;
import com.zhht.irn.entity.dto.TravelLineSinkInfo;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.util.Collector;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
/**
* TravelLineSinkInfoFlatMapFunction
*
* @author Rui meng
* @description 行车情况切分为字符串
* @date 2023/1/9 16:42
*/
public class TravelLineSinkInfoFlatMapFunction implements FlatMapFunction<List<TravelLineSinkInfo>, String> {
@Override
public void flatMap(List<TravelLineSinkInfo> travelLineSinkInfos, Collector<String> collector) throws Exception {
//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:travelLineSinkInfos) {
// 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());
// String record_date = "2023-01-09";
collector.collect(record_date+"\t"+t.getCross_id()+"\t"+statistic_time+"\t"+t.getCycle_begin_time()+"\t"+t.getCycle_end_time()
+"\t"+t.getLane_id()+"\t"+t.getCycle_id()+"\t"+t.getDirection()+"\t"+t.getFlow_direction()+"\t"+t.getPass_numbers()
+"\t"+t.getLast_car_inCross_time()+"\t"+t.getAverage_pass_time()+"\t"+t.getAverage_pass_speed()+"\t"+t.getAverage_control_delay()
+"\t"+t.getAverage_stop_delay()+"\t"+t.getAverage_stop_times()+"\t"+ t.getAverage_car_head_time_gap());
}
}
}
realtime/hologram-streaming/src/main/java/com/zhht/irn/job/LaneNormJob.java
......@@ -2,17 +2,22 @@ package com.zhht.irn.job;
import com.alibaba.fastjson.JSON;
import com.zhht.irn.entity.*;
import com.zhht.irn.entity.metric.DirectionEvalSecondMetric;
import com.zhht.irn.enums.EventType;
import com.zhht.irn.functions.LaneNormProcessFunction;
import com.zhht.irn.sink.LaneNormSink;
import com.zhht.irn.utils.DateUtils;
import com.zhht.irn.utils.DorisUtils;
import com.zhht.irn.utils.DruidConnectPoolUtils;
import com.zhht.irn.utils.FlinkUtils;
import org.apache.doris.flink.sink.DorisSink;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.functions.FilterFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.restartstrategy.RestartStrategies;
import org.apache.flink.api.common.time.Time;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.*;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
......@@ -20,6 +25,8 @@ import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import java.time.Duration;
import java.util.*;
import static com.zhht.irn.utils.DateUtils.longToStandardFormatString;
/**
* 两阶段提交参考文档：
* https://www.ververica.com/blog/end-to-end-exactly-once-processing-apache-flink-apache-kafka
......@@ -30,11 +37,16 @@ public class LaneNormJob {
public static void main(String[] args) throws Exception {
try {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
ParameterTool kafkaTool = ParameterTool.fromArgs(args);
String label = kafkaTool.get("label");
//env.setRestartStrategy(RestartStrategies.noRestart());
//设置重启策略
//env.setRestartStrategy( RestartStrategies.fixedDelayRestart(10, Time.seconds(10)));
DataStream<String> cycleStringStream = FlinkUtils.createKafkaStreamHuangzhun(args, env,"signal_cycle_data","laneNormJob1");
DataStream<String> carStringStream = FlinkUtils.createKafkaStreamHuangzhun(args, env,"trips_event_info","laneNormJob1");
//测试用topic
//DataStream<String> cycleStringStream = FlinkUtils.createKafkaStreamHuangzhun(args, env,"s_data2","laneNormJob1");
//DataStream<String> carStringStream = FlinkUtils.createKafkaStreamHuangzhun(args, env,"t_info2","laneNormJob1");
KeySelector<Cycle, String> cycleKeySelect = new KeySelector<Cycle, String>() {
@Override
public String getKey(Cycle cycle) throws Exception {
......@@ -79,12 +91,23 @@ public class LaneNormJob {
//根据corssid 分组 保证同一路口的数据进行一个进程
DataStream<Cycle> cycleDataStreamSource = cycleStringStream.map(getCycleFunction).assignTimestampsAndWatermarks(cycleWatermarkStrategy).keyBy(cycleKeySelect);
DataStream<TravelEvent> carStream = carStringStream.map(getTravelEventFunction).assignTimestampsAndWatermarks(travelEventWatermarkStrategy).keyBy(carKeySelector).filter(filterFunction);
ConnectedStreams<Cycle, TravelEvent> cycleTravelEventConnectedStreams = cycleDataStreamSource.connect(carStream).keyBy(cycle -> cycle.getCrossCode(), travelEvent -> travelEvent.getCrossId());
SingleOutputStreamOperator<List<LaneNorm>> process = cycleTravelEventConnectedStreams.process(new LaneNormProcessFunction()).setParallelism(4);
process.addSink(new LaneNormSink()).name(" ");
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris-connector-lane-norm.properties",label);
cycleTravelEventConnectedStreams.process(new LaneNormProcessFunction()).setParallelism(4)
.map((MapFunction<LaneNorm, String>) desm -> {
// 将结果实体类，拼接成制表符分割的字符串，进行sink，要保持字段顺序跟表的字段顺序相一致
return desm.getCorssId() + "\t" + desm.getLaneId() + "\t" + desm.getDirection() + "\t" + desm.getCycleOrder() + "\t"
+ desm.getLaneName() + "\t" + desm.getOrder() + "\t" + desm.getCycleStartTime() + "\t"
+ desm.getCycleEndTime()+ "\t" + desm.getMaxQueueLength() + "\t" + desm.getEffectGreenTime() + "\t"
+ desm.getPassCapacity()+ "\t" + desm.getTrafficCapacity() + "\t" + desm.getSaturation() + "\t"
+ desm.getResidualCapacity()+ "\t" + desm.getSpotSpaceShare() + "\t"
+ DateUtils.getTodayTime() + "\t" + longToStandardFormatString(System.currentTimeMillis())+ "\t"
+ desm.getType()+ "\t" + desm.getSpotSpaceLength();
}).sinkTo(builder.build());
//process.addSink(new LaneNormSink()).name(" ");
env.execute("laneNormJob");
}catch (Exception e){
e.printStackTrace();
System.out.println("程序异常关闭->"+e);
}
......
realtime/hologram-streaming/src/main/java/com/zhht/irn/job/TravelSituationAnalysisJob.java
......@@ -6,11 +6,14 @@ 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.functions.TravelLineSinkInfoFlatMapFunction;
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 com.zhht.irn.utils.DorisUtils;
import org.apache.doris.flink.sink.DorisSink;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.restartstrategy.RestartStrategies;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.common.time.Time;
......@@ -24,6 +27,7 @@ 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.util.Collector;
import org.apache.kafka.clients.consumer.ConsumerConfig;
......@@ -65,7 +69,7 @@ public class TravelSituationAnalysisJob {
env.getCheckpointConfig().setExternalizedCheckpointCleanup(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
//设置重启策略 这里不设置重启策略，由平台统一拉起任务
// env.setRestartStrategy(RestartStrategies.fixedDelayRestart(10, Time.seconds(30)));
//env.setRestartStrategy(RestartStrategies.fixedDelayRestart(10, Time.seconds(30)));
env.setRestartStrategy(RestartStrategies.noRestart());
......@@ -90,16 +94,16 @@ public class TravelSituationAnalysisJob {
//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);
// 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<>("s_data2", new CycleSignalKafkaSchema(), kafkaProperties2);
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);
//2、使用connect，把2个流联合处理
ConnectedStreams<TravelInfo, CycleSignalData> connect = travelInfoStream
.connect(cycleSignalDataStream);
......@@ -112,7 +116,13 @@ public class TravelSituationAnalysisJob {
SingleOutputStreamOperator<List<TravelLineSinkInfo>> sinkDataStream = travelInfoCycleSignalDataConnectedStreams
.process(new TravelCarInfoCoProcessFunction()).setParallelism(3);
sinkDataStream.addSink(new TravelLaneInfoSink()).setParallelism(3);
// sinkDataStream.addSink(new TravelLaneInfoSink()).setParallelism(3);
// 获取builder
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris-connector-travel-situation.properties");
sinkDataStream.flatMap(new TravelLineSinkInfoFlatMapFunction()).sinkTo(builder.build());
env.execute("TravelSituationAnalysisJob");
......
realtime/hologram-streaming/src/main/java/com/zhht/irn/sink/LaneNormSink.java
......@@ -52,12 +52,6 @@ public class LaneNormSink extends RichSinkFunction<List<LaneNorm>> {
if(laneNorms.size()==0){
return;
}
/**
* 添加连接判断 防止jdbc 失效
*/
if(!DataSourceUtils.isDbConnected(connection)){
connection=DorisUtils.getConnection();
}
for (LaneNorm value: laneNorms){
insertPstmt.setString(1, value.getCorssId());
insertPstmt.setString(2, value.getLaneId());
......
realtime/hologram-streaming/src/main/java/com/zhht/irn/utils/DataSourceUtils.java
......@@ -12,10 +12,10 @@ import java.sql.SQLException;
**/
public class DataSourceUtils {
public static boolean isDbConnected(Connection con) {
public static boolean isDbConnected(Connection con) {
//final String CHECK_SQL_QUERY = "SELECT 1";
try {
if(con != null && !con.isValid(1000)){
if(con != null && con.isValid(1000)){
return true;
}
} catch (SQLException e) {
......
realtime/hologram-streaming/src/main/java/com/zhht/irn/utils/DorisUtils.java
......@@ -83,4 +83,33 @@ public class DorisUtils {
.setDorisOptions(dorisBuilder.build());
return builder;
}
public static DorisSink.Builder<String> getBuilder(String filePath,String label1) throws IOException {
DorisSink.Builder<String> builder = DorisSink.builder();
DorisOptions.Builder dorisBuilder = DorisOptions.builder();
InputStream inputStream = DorisUtils.class.getClassLoader().getResourceAsStream(filePath);
ParameterTool tool = ParameterTool.fromPropertiesFile(inputStream);
// 根据路径的配置文件获取MySQL链接参数
String username = tool.getRequired("username");
String password = tool.getRequired("password");
String host = tool.getRequired("host");
String port = tool.getRequired("port");
String database = tool.get("database", "default");
String table = tool.getRequired("table");
String label = tool.getRequired("label");
dorisBuilder.setFenodes(host + ":" + port)
.setTableIdentifier(database + "." + table)
.setUsername(username)
.setPassword(password);
DorisExecutionOptions.Builder executionBuilder = DorisExecutionOptions.builder();
executionBuilder.setLabelPrefix(StringUtils.isNotEmpty(label1)?label1:label); // streamload label prefix
builder.setDorisReadOptions(DorisReadOptions.builder().build())
.setDorisExecutionOptions(executionBuilder.build())
.setSerializer(new SimpleStringSerializer()) //serialize according to string
.setDorisOptions(dorisBuilder.build());
return builder;
}
}
realtime/hologram-streaming/src/main/java/com/zhht/irn/utils/FlinkUtils.java
......@@ -156,7 +156,7 @@ public class FlinkUtils {
* 暂时不需要失败自动重试
*/
//env.setRestartStrategy(RestartStrategies.fixedDelayRestart(2, Time.of(5, TimeUnit.SECONDS)));
env.setRestartStrategy(RestartStrategies.noRestart());
// 基于Kafka 原始JSON格式的字符串，获取消息流
FlinkKafkaConsumer<String> kafkaConsumer = new FlinkKafkaConsumer<>(topicList, new SimpleStringSchema(), properties);
DataStream<String> rawStringStream = env.addSource(kafkaConsumer);
......@@ -187,7 +187,7 @@ public class FlinkUtils {
env.enableCheckpointing(checkpointInterval);
env.setStateBackend(new FsStateBackend(checkpointPath));
env.getCheckpointConfig().enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
//env.setRestartStrategy(RestartStrategies.fixedDelayRestart(2, Time.of(5, TimeUnit.SECONDS)));
env.setRestartStrategy(RestartStrategies.noRestart());
// 基于Kafka 原始JSON格式的字符串，获取消息流
FlinkKafkaConsumer<String> kafkaConsumer = new FlinkKafkaConsumer<>(topicList, new SimpleStringSchema(), properties);
kafkaConsumer.setStartFromLatest();
......
realtime/hologram-streaming/src/main/resources/doris-connector-lane-norm.properties 0 → 100644
host=10.243.0.22
port=8030
username=root
password=mima
database=qxlk
table=app_cross_dimension_norm
label=lanenorm-import
realtime/hologram-streaming/src/main/resources/doris-connector-travel-situation.properties 0 → 100644
host=10.243.0.22
port=8030
username=root
password=mima
database=qxlk
table=app_cross_line_travel_car_info
label=app_cross_line_travel_car_info-import
\ No newline at end of file
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