本文介绍如何使用Java SDK的SelectObject查询CSV和JSON文件。

说明 关于SelectObject的更多信息,请参见开发指南中的 使用SelectObject查询文件和API参考中的 SelectObject

以下代码用于查询CSV和JSON文件。

import com.aliyun.oss.model.*;
import com.aliyun.oss.OSS;
import com.aliyun.oss.OSSClientBuilder;
import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.InputStreamReader;

/**
 * Examples of create select object metadata and select object.
 *
 */
public class SelectObjectSample {
    // yourEndpoint填写Bucket所在地域对应的Endpoint。以华东1(杭州)为例,Endpoint填写为https://oss-cn-hangzhou.aliyuncs.com。
    private static String endpoint = "yourEndpoint";
    // 阿里云账号AccessKey拥有所有API的访问权限,风险很高。强烈建议您创建并使用RAM用户进行API访问或日常运维,请登录RAM控制台创建RAM用户。
    private static String accessKeyId = "yourAccessKeyId";
    private static String accessKeySecret = "yourAccessKeySecret";
    // 填写Bucket名称,例如examplebucket。
    private static String bucketName = "examplebucket";

    public static void main(String[] args) throws Exception {
        OSS ossClient = new OSSClientBuilder().build(endpoint, accessKeyId, accessKeySecret);
        // 填写Object完整路径后,根据SELECT语句查询文件中的数据。Object完整路径中不能包含Bucket名称。
        // 填写CSV格式的Object完整路径。
        selectCsvSample("test.csv", ossClient);
        // 填写JSON格式的Object完整路径。
        selectJsonSample("test.json", ossClient);
        ossClient.shutdown();
    }

    private static void selectCsvSample(String key, OSS ossClient) throws Exception {
        // 填写上传的内容。
        String content = "name,school,company,age\r\n" +
                "Lora Francis,School A,Staples Inc,27\r\n" +
                "Eleanor Little,School B,\"Conectiv, Inc\",43\r\n" +
                "Rosie Hughes,School C,Western Gas Resources Inc,44\r\n" +
                "Lawrence Ross,School D,MetLife Inc.,24";

        ossClient.putObject(bucketName, key, new ByteArrayInputStream(content.getBytes()));

        SelectObjectMetadata selectObjectMetadata = ossClient.createSelectObjectMetadata(
                new CreateSelectObjectMetadataRequest(bucketName, key)
                        .withInputSerialization(
                                new InputSerialization().withCsvInputFormat(
                                        // 填写内容中不同记录之间的分隔符,例如\r\n。
                                        new CSVFormat().withHeaderInfo(CSVFormat.Header.Use).withRecordDelimiter("\r\n"))));
        System.out.println(selectObjectMetadata.getCsvObjectMetadata().getTotalLines());
        System.out.println(selectObjectMetadata.getCsvObjectMetadata().getSplits());

        SelectObjectRequest selectObjectRequest =
                new SelectObjectRequest(bucketName, key)
                        .withInputSerialization(
                                new InputSerialization().withCsvInputFormat(
                                        new CSVFormat().withHeaderInfo(CSVFormat.Header.Use).withRecordDelimiter("\r\n")))
                        .withOutputSerialization(new OutputSerialization().withCsvOutputFormat(new CSVFormat()));
       
        selectObjectRequest.setExpression("select * from ossobject where _4 > 40");// 使用SELECT语句查询文件中的数据。
        OSSObject ossObject = ossClient.selectObject(selectObjectRequest);

        // 读取内容。
        BufferedReader reader = new BufferedReader(new InputStreamReader(ossObject.getObjectContent()));
        while (true) {
            String line = reader.readLine();
            if (line == null) {
                break;
            }
            System.out.println(line);
        }
        reader.close();

        ossClient.deleteObject(bucketName, key);
    }

    private static void selectJsonSample(String key, OSS ossClient) throws Exception {
        // 填写上传的内容。
        final String content = "{\n" +
                "\t\"name\": \"Lora Francis\",\n" +
                "\t\"age\": 27,\n" +
                "\t\"company\": \"Staples Inc\"\n" +
                "}\n" +
                "{\n" +
                "\t\"name\": \"Eleanor Little\",\n" +
                "\t\"age\": 43,\n" +
                "\t\"company\": \"Conectiv, Inc\"\n" +
                "}\n" +
                "{\n" +
                "\t\"name\": \"Rosie Hughes\",\n" +
                "\t\"age\": 44,\n" +
                "\t\"company\": \"Western Gas Resources Inc\"\n" +
                "}\n" +
                "{\n" +
                "\t\"name\": \"Lawrence Ross\",\n" +
                "\t\"age\": 24,\n" +
                "\t\"company\": \"MetLife Inc.\"\n" +
                "}";

        ossClient.putObject(bucketName, key, new ByteArrayInputStream(content.getBytes()));

        SelectObjectRequest selectObjectRequest =
                new SelectObjectRequest(bucketName, key)
                        .withInputSerialization(new InputSerialization()
                                .withCompressionType(CompressionType.NONE)
                                .withJsonInputFormat(new JsonFormat().withJsonType(JsonType.LINES)))
                        .withOutputSerialization(new OutputSerialization()
                                .withCrcEnabled(true)
                                .withJsonOutputFormat(new JsonFormat()))
                        .withExpression("select * from ossobject as s where s.age > 40"); // 使用SELECT语句查询文件中的数据。

        OSSObject ossObject = ossClient.selectObject(selectObjectRequest);

        // 读取内容。
        BufferedReader reader = new BufferedReader(new InputStreamReader(ossObject.getObjectContent()));
        while (true) {
            String line = reader.readLine();
            if (line == null) {
                break;
            }
            System.out.println(line);
        }
        reader.close();

        ossClient.deleteObject(bucketName, key);
    }
}