flink多表join的例子-成都快上网建站

flink多表join的例子

今天写了一个稍微复杂的例子, 实现了类似MySQL group_concat 功能,记录一下
MapToString 参考bug 那篇博客

成都创新互联公司是一家专注于网站设计、成都网站制作与策划设计,偃师网站建设哪家好?成都创新互联公司做网站,专注于网站建设十多年,网设计领域的专业建站公司;建站业务涵盖:偃师等地区。偃师做网站价格咨询:13518219792

public static void main(String[] arg) throws Exception {

        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        BatchTableEnvironment tableEnv = new BatchTableEnvironment(env, TableConfig.DEFAULT());
        tableEnv.registerFunction("mapToString", new MapToString());

        getProjectInfo(env,tableEnv);
        getProject(env,tableEnv);
        joinTableProjectWithInfo(tableEnv);

        Table query = tableEnv.sqlQuery("select id, name, type from result_agg");
        DataSet ds=  tableEnv.toDataSet(query, Row.class);
        ds.print();
        ds.writeAsText("/home/test", WriteMode.OVERWRITE);
        env.execute("multiple-table");          
    }

    public static void getProjectInfo(ExecutionEnvironment env,BatchTableEnvironment tableEnv) {

        TypeInformation[] fieldTypes = new TypeInformation[] { BasicTypeInfo.STRING_TYPE_INFO, BasicTypeInfo.STRING_TYPE_INFO };
        String[] fieldNames = new String[] { "id",  "type" };
        RowTypeInfo rowTypeInfo = new RowTypeInfo(fieldTypes, fieldNames);
        JDBCInputFormat jdbcInputFormat = JDBCInputFormat.buildJDBCInputFormat().setDrivername("com.mysql.jdbc.Driver")
                .setDBUrl("jdbc:mysql://ip:3306/space?characterEncoding=utf8")
                .setUsername("user").setPassword("pwd")
                .setQuery("select project_fid, cast(project_info_type as CHAR) as type from project").setRowTypeInfo(rowTypeInfo).finish();
        DataSource s = env.createInput(jdbcInputFormat);   
        tableEnv.registerDataSet("project_info", s);
        aggProjectInfo(tableEnv,"project_info");
    }

    public static void aggProjectInfo(BatchTableEnvironment tableEnv, String tableName) {   
        Table tapiResult = tableEnv.scan(tableName);
        tapiResult.printSchema();               
        Table query = tableEnv.sqlQuery("select id, mapToString(collect(type)) as type from project_info group by id");
        tableEnv.registerTable(tableName+"_agg", query);        
        tapiResult = tableEnv.scan(tableName+"_agg");
        tapiResult.printSchema();   
    }

    public static void getProject(ExecutionEnvironment env,BatchTableEnvironment tableEnv) {

        TypeInformation[] fieldTypes = new TypeInformation[] { BasicTypeInfo.STRING_TYPE_INFO, BasicTypeInfo.STRING_TYPE_INFO };
        String[] fieldNames = new String[] { "pid",  "name" };
        RowTypeInfo rowTypeInfo = new RowTypeInfo(fieldTypes, fieldNames);
        JDBCInputFormat jdbcInputFormat = JDBCInputFormat.buildJDBCInputFormat().setDrivername("com.mysql.jdbc.Driver")
                .setDBUrl("jdbc:mysql://ip:3306/space?characterEncoding=utf8")
                .setUsername("user").setPassword("pwd")
                .setQuery("select fid, project_name  from t_project").setRowTypeInfo(rowTypeInfo).finish();
        DataSource s = env.createInput(jdbcInputFormat);
        tableEnv.registerDataSet("project", s);

    }

    public static void joinTableProjectWithInfo(BatchTableEnvironment tableEnv) {
        Table result =tableEnv.sqlQuery("select a.pid as id , a.name , b.type  from project a inner join  project_info_agg  b on a.pid=b.id");
        tableEnv.registerTable("result_agg", result);
        result.printSchema();
    }

当前名称:flink多表join的例子
文章地址:http://kswjz.com/article/isjhjs.html
扫二维码与项目经理沟通

我们在微信上24小时期待你的声音

解答本文疑问/技术咨询/运营咨询/技术建议/互联网交流