Commit 2a6b474f by 吴延飞

车道任务和行车情况任务调整下flink-connector的写入写法,同时删除不必要的配置文件

parent 7d8d0355
......@@ -2,20 +2,15 @@ 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.*;
......@@ -37,8 +32,6 @@ 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)));
......@@ -92,7 +85,7 @@ public class LaneNormJob {
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());
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris-connector-lane-norm.properties",label);
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris.properties",args, "app_cross_dimension_norm");
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
......
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.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;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.runtime.state.filesystem.FsStateBackend;
......@@ -27,7 +20,6 @@ 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;
......@@ -45,12 +37,11 @@ public class TravelSituationAnalysisJob {
public static void main(String[] args) {
try {
InputStream inputStream = DorisUtils.class.getClassLoader().getResourceAsStream("kafka.properties");
ParameterTool tool = ParameterTool.fromPropertiesFile(inputStream);
//1、创建环境
//1、创建环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// checkpoint配置
CheckpointConfig checkpointConfig = env.getCheckpointConfig();
......@@ -63,7 +54,7 @@ public class TravelSituationAnalysisJob {
checkpointConfig.setMaxConcurrentCheckpoints(1);
//这如果不指定使用FsStateBackend 则默认使用flink集群中的配置,rocksDB
// env.setStateBackend(new FsStateBackend("file:///data/flink/state"));
// env.setStateBackend(new FsStateBackend("file:///data/flink/state"));
env.setStateBackend(new FsStateBackend(tool.getRequired("checkpoint.path")));
env.getCheckpointConfig().setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
env.getCheckpointConfig().setExternalizedCheckpointCleanup(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
......@@ -120,7 +111,7 @@ public class TravelSituationAnalysisJob {
// 获取builder
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris-connector-travel-situation.properties");
DorisSink.Builder<String> builder = DorisUtils.getBuilder("doris.properties", args, "app_cross_line_travel_car_info");
sinkDataStream.flatMap(new TravelLineSinkInfoFlatMapFunction()).sinkTo(builder.build());
......
package com.zhht.irn.sink;
import com.zhht.irn.entity.LaneNorm;
import com.zhht.irn.utils.*;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction;
import org.apache.flink.streaming.api.functions.sink.SinkFunction;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.util.List;
/**
* @Description:
* @Author :Marinh
* @Param:
* @retrun:
* @Creat :2022-10-31-14:11
**/
public class LaneNormSink extends RichSinkFunction<List<LaneNorm>> {
Connection connection;
PreparedStatement insertPstmt;
PreparedStatement updatePstmt;
@Override
public void open(Configuration parameters) throws Exception {
super.open(parameters);
// path暂定为固定值
connection = DorisUtils.getConnection();
insertPstmt = connection.prepareStatement("insert into " +
"app_cross_dimension_norm(cross_id,lane_id,direction,cycle_order,max_queue_length,effect_green_time,pass_capacity,traffic_capacity,saturation,residual_capacity," +
"spot_space_share,dimension_name,`order`,statistic_time,`type`,spot_space_length,cycle_start_time,cycle_end_time,record_date) values (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)");
}
@Override
public void close() throws Exception {
super.close();
if(insertPstmt != null) insertPstmt.close();
if(connection != null) connection.close();
}
/**
* 来一条数据就执行一次
*
* 1000w的数据 1000w次
*/
@Override
public void invoke(List<LaneNorm> laneNorms, SinkFunction.Context context) throws Exception {
if(laneNorms.size()==0){
return;
}
for (LaneNorm value: laneNorms){
insertPstmt.setString(1, value.getCorssId());
insertPstmt.setString(2, value.getLaneId());
insertPstmt.setString(3, value.getDirection());
insertPstmt.setLong(4, value.getCycleOrder());
insertPstmt.setDouble(5, value.getMaxQueueLength());
insertPstmt.setString(6,value.getEffectGreenTime());
insertPstmt.setDouble(7,value.getPassCapacity());
insertPstmt.setDouble(8,value.getTrafficCapacity());
insertPstmt.setDouble(9,value.getSaturation());
insertPstmt.setDouble(10,value.getResidualCapacity());
insertPstmt.setDouble(11,value.getSpotSpaceShare());
insertPstmt.setString(12,value.getLaneName());
insertPstmt.setInt(13,value.getOrder());
insertPstmt.setString(14, DateUtils.getTodayTime());
insertPstmt.setString(15,value.getType());
insertPstmt.setInt(16,value.getSpotSpaceLength());
insertPstmt.setString(17,value.getCycleStartTime());
insertPstmt.setString(18,value.getCycleEndTime());
insertPstmt.setString(19,DateUtils.getTodayTime());
insertPstmt.addBatch();
}
insertPstmt.executeBatch();
}
}
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.DorisUtils;
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 = DorisUtils.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);
//重新获取连接,避免超时的问题
connection = DorisUtils.getConnection();
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+"...");
preparedStatement.close();
connection.close();
}
}
host=10.243.0.22
port=8030
username=root
password=mima
database=qxlk
table=app_cross_dimension_norm
label=lanenorm-import
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