Calcite使用SQL实现查询csv/json文件内容

<!-- calcite文件系统支持 -->
<dependency>
    <groupId>org.apache.calcite</groupId>
    <artifactId>calcite-file</artifactId>
    <version>1.37.0</version>
</dependency>
<dependency>
    <groupId>org.apache.calcite</groupId>
    <artifactId>calcite-core</artifactId>
    <version>1.37.0</version>
</dependency>

ID:long,姓名:string,GENDER:string,BIRTHDAY:date
100,"张三",,"2001-01-01"
110,"李四","M","2001-01-01"
120,"王五","M","2002-05-03"
130,"赵六","F","2005-09-07"
140,"张铁牛","M","2007-01-01"

[
  {
    "id": 123,
    "name": "管理员",
    "key": "manager"
  },
  {
    "id": 234,
    "name": "老师",
    "key": "teacher"
  },
  {
    "id": 345,
    "name": "学生",
    "key": "student"
  }
]

package com.ldx.calcite;

import com.google.common.collect.ImmutableMap;
import lombok.SneakyThrows;
import lombok.extern.slf4j.Slf4j;
import org.apache.calcite.adapter.file.FileSchemaFactory;
import org.apache.calcite.jdbc.CalciteConnection;
import org.apache.calcite.schema.Schema;
import org.apache.calcite.schema.SchemaPlus;
import org.apache.calcite.util.Sources;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.testng.collections.Maps;

import java.net.URL;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.ResultSetMetaData;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.Map;
import java.util.Properties;

@Slf4j
public class CalciteFileTest {
    private static Connection connection;

    private static SchemaPlus rootSchema;

    private static Statement statement;

    @BeforeAll
    @SneakyThrows
    public static void beforeAll() {
        Properties info = new Properties();
        // 不区分sql大小写
        info.setProperty("caseSensitive", "false");
        // 创建Calcite连接
        connection = DriverManager.getConnection("jdbc:calcite:", info);
        CalciteConnection calciteConnection = connection.unwrap(CalciteConnection.class);
        // 构建RootSchema，在Calcite中，RootSchema是所有数据源schema的parent，多个不同数据源schema可以挂在同一个RootSchema下
        rootSchema = calciteConnection.getRootSchema();
        final Schema schema = FileSchemaFactory.INSTANCE.create(rootSchema, "x",
                ImmutableMap.of("directory", resourcePath("file"), "flavor", "scannable"));
        rootSchema.add("test", schema);
        // 创建SQL语句执行查询
        statement = calciteConnection.createStatement();
    }

    @Test
    @SneakyThrows
    public void execute_simple_query() {
        ResultSet resultSet = statement.executeQuery("SELECT * FROM test.user_info");
        printResultSet(resultSet);
    }
  
    @Test
    @SneakyThrows
    public void test_execute_join_query() {
        ResultSet resultSet = statement.executeQuery("SELECT * FROM test.user_info ui inner join test.role_info ri on ui.role_id = ri.id");
        printResultSet(resultSet);
    }

    @AfterAll
    @SneakyThrows
    public static void closeResource() {
        statement.close();
        connection.close();
    }

    private static String resourcePath(String path) {
        final URL url = CalciteFileTest.class.getResource("/" + path);
        return Sources.of(url).file().getAbsolutePath();
    }

    public static void printResultSet(ResultSet resultSet) throws SQLException {
        // 获取 ResultSet 元数据
        ResultSetMetaData metaData = resultSet.getMetaData();

        // 获取列数
        int columnCount = metaData.getColumnCount();
        log.info("Number of columns: {}",columnCount);

        // 遍历 ResultSet 并打印结果
        while (resultSet.next()) {
            final Map<String, String> item = Maps.newHashMap();
            // 遍历每一列并打印
            for (int i = 1; i <= columnCount; i++) {
                String columnName = metaData.getColumnName(i);
                String columnValue = resultSet.getString(i);
                item.put(columnName, columnValue);
            }

            log.info(item.toString());
        }
    }
}

// 这里的第二个参数“x”没什么意义, 源码中没用到, 可以随便填
final Schema schema = FileSchemaFactory.INSTANCE.create(rootSchema, "x",
               ImmutableMap.of("directory", resourcePath("file"), "flavor", "scannable"));
// 使用目录名称为schema名称, 这里的test就是schema名称
rootSchema.add("test", schema);