Object Storage Service:Query objects

Usage notes

• In this topic, the public endpoint of the China (Hangzhou) region is used. If you want to access OSS from other Alibaba Cloud services in the same region as OSS, use an internal endpoint. For more information about OSS regions and endpoints, see Regions, endpoints and open ports.

• In this topic, access credentials are obtained from environment variables. For more information about how to configure access credentials, see Configure access credentials.

• In this topic, an OSSClient instance is created by using an OSS endpoint. If you want to create an OSSClient instance by using custom domain names or Security Token Service (STS), see Create an OSSClient instance.

• To query objects, you must have the oss:GetObject permission. For more information, see Attach a custom policy to a RAM user.

• Only objects in the CSV and JSON formats can be queried by using SelectObject.

Examples

The following sample code provides an example on how to query CSV and JSON objects:

import com.aliyun.oss.model.*;
import com.aliyun.oss.OSS;
import com.aliyun.oss.common.auth.*;
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 {
    // Specify the endpoint of the region in which the bucket is located. For example, if the bucket is located in the China (Hangzhou) region, set the endpoint to https://oss-cn-hangzhou.aliyuncs.com. 
    private static String endpoint = "https://oss-cn-hangzhou.aliyuncs.com";
    // Specify the name of the bucket. Example: examplebucket. 
    private static String bucketName = "examplebucket";

    public static void main(String[] args) throws Exception {
      
      	// Obtain access credentials from environment variables. Before you run the sample code, make sure that the OSS_ACCESS_KEY_ID and OSS_ACCESS_KEY_SECRET environment variables are configured. 
        EnvironmentVariableCredentialsProvider credentialsProvider = CredentialsProviderFactory.newEnvironmentVariableCredentialsProvider();
        // Specify the region in which the bucket is located. For example, if the bucket is located in the China (Hangzhou) region, set the region to cn-hangzhou.
        String region = "cn-hangzhou";

        // Create an OSSClient instance. 
        ClientBuilderConfiguration clientBuilderConfiguration = new ClientBuilderConfiguration();
        clientBuilderConfiguration.setSignatureVersion(SignVersion.V4);        
        OSS ossClient = OSSClientBuilder.create()
        .endpoint(endpoint)
        .credentialsProvider(credentialsProvider)
        .clientConfiguration(clientBuilderConfiguration)
        .region(region)               
        .build();
        // Specify the full path of the object that you want to query, and then query the data of the object by using SELECT statements. Do not include the bucket name in the full path. 
        // Specify the full path of the CSV object. 
        selectCsvSample("test.csv", ossClient);
        // Specify the full path of the JSON object. 
        selectJsonSample("test.json", ossClient);
        ossClient.shutdown();
    }

    private static void selectCsvSample(String key, OSS ossClient) throws Exception {
        // Specify the content of the object that you want to upload. 
        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(
                                        // Specify the delimiter that is used to separate different records in the content. Example: \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()));
        // Use a SELECT statement to query all records whose values are greater than 40 in the 4th column. 
        selectObjectRequest.setExpression("select * from ossobject where _4 > 40");
        OSSObject ossObject = ossClient.selectObject(selectObjectRequest);

        // Read the content of the object. 
        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 {
        // Specify the content of the object that you want to upload. 
        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"); // Use the SELECT statement to query data in the object. 

        OSSObject ossObject = ossClient.selectObject(selectObjectRequest);

        // Read the content of the object. 
        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);
    }
}

References

• For the complete sample code that is used to query objects, visit GitHub.

• For more information about the API operation that you can call to query objects, see SelectObject.