FlinkSQL使用自定义UDTF函数行转列-IK分词器

三、代码过程
由于Flink一般在流式环境使用，故这里数据源使用Kafka，并建立动态表的形式实现，以更好的贴近实际的业务环境。

工具类：
package com.test.UDTF;
import org.apache.flink.table.annotation.DataTypeHint;
import org.apache.flink.table.annotation.FunctionHint;
import org.apache.flink.table.functions.TableFunction;
import org.apache.flink.types.Row;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
import java.io.IOException;
import java.io.StringReader;
import java.util.ArrayList;
import java.util.List;
/**

• @author: Rango

• @create: 2021-05-04 16:50

• @description: 建立函数，继承TableFunction并建立eval方法
  /
  @FunctionHint(output = @DataTypeHint(“ROW”))
  public class KeywordUDTF extends TableFunction {
  //按官方文档说明，须按eval命名
  public void eval(String value){
  List stringList = analyze(value);
  for (String s : stringList) {
  Row row = new Row(1);
  row.setField(0,s);
  collect(row);
  }
  }
  //自定义分词方式
  public List analyze(String text){
  //字符串转文件流
  StringReader sr = new StringReader(text);
  //建立分词器对象
  IKSegmenter ik = new IKSegmenter(sr,true);
  //ik分词后对象为Lexeme
  Lexeme lex = null;
  //分词后转入列表
  List keywordList = new ArrayList<>();
  while(true){
  try {
  if ((lex = ik.next())!=null){
  keywordList.add(lex.getLexemeText());
  }else{
  break;
  }
  } catch(IOException e) {
  e.printStackTrace();
  }
  }return keywordList;
  }
  }
  实现类
  package com.test.UDTF;
  import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
  import org.apache.flink.table.api.EnvironmentSettings;
  import org.apache.flink.table.api.Table;
  import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
  import org.apache.flink.types.Row;
  /

• @author: Rango

• @create: 2021-05-04 17:11

• @description:
  **/
  public class KeywordStatsApp {
  public static void main(String[] args) throws Exception {
  //建立环境
  StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
  env.setParallelism(1);

   EnvironmentSettings settings = EnvironmentSettings.newInstance().inStreamingMode().build();
   StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env, settings);
  
   //注册函数
   tableEnv.createTemporaryFunction("ik_analyze", KeywordUDTF.class);
  
   //建立动态表
   tableEnv.executeSql("CREATE TABLE wordtable (" +
           "word STRING" +
           ") WITH ('connector' = 'kafka'," +
           "'topic' = 'keywordtest'," +
           "'properties.bootstrap.servers' = 'hadoop102:9092'," +
           "'properties.group.id' = 'keyword_stats_app'," +
           "'format' = 'json')");
   //未切分效果
   Table wordTable = tableEnv.sqlQuery("select word from wordtable");
   //利用自定义函数对文本进行分切，切分后计为1，方便后续统计使用
   Table wordTable1 = tableEnv.sqlQuery("select splitword,1 ct from wordtable," +
           "LATERAL TABLE(ik_analyze(word)) as T(splitword)");
  
   tableEnv.toAppendStream(wordTable, Row.class).print("原格式>>>");
   tableEnv.toAppendStream(wordTable1, Row.class).print("使用UDTF函数效果>>>");
  
   env.execute();
  

  }
  }
  补充下依赖
  
  <java.version>1.8</java.version>
  <flink.version>1.12.0</flink.version>
  <scala.version>2.12</scala.version>
  
  
  
  org.apache.flink
  flink-java
  KaTeX parse error: Expected group after '_' at position 157: …api-java-bridge_̲{scala.version}
  KaTeX parse error: Expected group after '_' at position 155: …e-planner-blink_̲{scala.version}
  KaTeX parse error: Expected group after '_' at position 309: …connector-kafka_̲{scala.version}
  $flink.version</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-json</artifactId><version>${flink.version}
  
  
  org.apache.flink
  flink-clients_$scala.version</artifactId><version>${flink.version}
  
  USB Microphone https://www.soft-voice.com/
  Wooden Speakers https://www.zeshuiplatform.com/
  亚马逊测评 www.yisuping.cn
  深圳网站建设www.sz886.com