查询文件

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 {
    // 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 = "https://oss-cn-hangzhou.aliyuncs.com";
    // 填写Bucket名称，例如examplebucket。
    private static String bucketName = "examplebucket";

    public static void main(String[] args) throws Exception {
      
      	// 从环境变量中获取访问凭证。运行本代码示例之前，请确保已设置环境变量OSS_ACCESS_KEY_ID和OSS_ACCESS_KEY_SECRET。
        EnvironmentVariableCredentialsProvider credentialsProvider = CredentialsProviderFactory.newEnvironmentVariableCredentialsProvider();
        // 创建OSSClient实例。
      	OSS ossClient = new OSSClientBuilder().build(endpoint, credentialsProvider);
        // 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()));
        // 使用SELECT语句查询第4列，值大于40的所有记录。
        selectObjectRequest.setExpression("select * from ossobject where _4 > 40");
        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);
    }
}

import oss2
from oss2.credentials import EnvironmentVariableCredentialsProvider

def select_call_back(consumed_bytes, total_bytes =  None):
        print('Consumed Bytes:' + str(consumed_bytes) + '\n')

# 从环境变量中获取访问凭证。运行本代码示例之前，请确保已设置环境变量OSS_ACCESS_KEY_ID和OSS_ACCESS_KEY_SECRET。
auth = oss2.ProviderAuth(EnvironmentVariableCredentialsProvider())
# 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。
# 填写Bucket名称。
bucket = oss2.Bucket(auth, 'https://oss-cn-hangzhou.aliyuncs.com', 'examplebucket')
key =  'python_select.csv'
content =  'Tom Hanks,USA,45\r\n'*1024
filename =  'python_select.csv'

# 上传CSV文件。
bucket.put_object(key, content)
# Select API的参数。
csv_meta_params = {'RecordDelimiter': '\r\n'}
select_csv_params = {'CsvHeaderInfo': 'None',
                    'RecordDelimiter': '\r\n',
                    'LineRange': (500, 1000)}

csv_header = bucket.create_select_object_meta(key, csv_meta_params)
print(csv_header.rows)
print(csv_header.splits)
result = bucket.select_object(key, "select * from ossobject where _3 > 44", select_call_back, select_csv_params)
select_content = result.read()
print(select_content)

result = bucket.select_object_to_file(key, filename,
      "select * from ossobject where _3 > 44", select_call_back, select_csv_params)
bucket.delete_object(key)

###JSON DOCUMENT
key =  'python_select.json'
content =  "{\"contacts\":[{\"key1\":1,\"key2\":\"hello world1\"},{\"key1\":2,\"key2\":\"hello world2\"}]}"
filename =  'python_select.json'
# 上传JSON DOCUMENT。
bucket.put_object(key, content)
select_json_params = {'Json_Type': 'DOCUMENT'}
result = bucket.select_object(key, "select s.key2 from ossobject.contacts[*] s where s.key1 = 1", None, select_json_params)
select_content = result.read()
print(select_content)

result = bucket.select_object_to_file(key, filename,
      "select s.key2 from ossobject.contacts[*] s where s.key1 = 1", None, select_json_params)
bucket.delete_object(key)

###JSON LINES
key =  'python_select_lines.json'
content =  "{\"key1\":1,\"key2\":\"hello world1\"}\n{\"key1\":2,\"key2\":\"hello world2\"}"
filename =  'python_select.json'
# 上传JSON LINE。
bucket.put_object(key, content)
select_json_params = {'Json_Type': 'LINES'}
json_header = bucket.create_select_object_meta(key,select_json_params)
print(json_header.rows)
print(json_header.splits)

result = bucket.select_object(key, "select s.key2 from ossobject s where s.key1 = 1", None, select_json_params)
select_content =  result.read()
print(select_content)
result = bucket.select_object_to_file(key, filename,
           "select s.key2 from ossobject s where s.key1 = 1", None, select_json_params)
bucket.delete_object(key)

package main

import (
	"fmt"
	"github.com/aliyun/aliyun-oss-go-sdk/oss"
	"io/ioutil"
	"os"
)

func main() {
	// 从环境变量中获取访问凭证。运行本代码示例之前，请确保已设置环境变量OSS_ACCESS_KEY_ID和OSS_ACCESS_KEY_SECRET。
	provider, err := oss.NewEnvironmentVariableCredentialsProvider()
	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}
	// 创建OSSClient实例。
	// yourEndpoint填写Bucket对应的Endpoint，以华东1（杭州）为例，填写为https://oss-cn-hangzhou.aliyuncs.com。其它Region请按实际情况填写。
	client, err := oss.New("yourEndpoint", "", "", oss.SetCredentialsProvider(&provider))
	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}
	// 填写Bucket名称，例如examplebucket。
	bucket, err := client.Bucket("examplebucket")
	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}
	// 填写Object完整路径，完整路径中不能包含Bucket名称，例如exampledir/exampledata.csv。
	key := "exampledir/exampledata.csv"
	// 填写本地CSV文件的完整路径，例如D:\\localpath\\exampledata.csv。
	localCsvFile := "D:\\localpath\\exampledata.csv"
	err = bucket.PutObjectFromFile(key, localCsvFile)
	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}

	selReq := oss.SelectRequest{}
	// 使用SELECT语句查询文件中的数据。
	selReq.Expression = `select * from ossobject`
	body, err := bucket.SelectObject(key, selReq)

	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}
	// 读取内容。
	fc, err := ioutil.ReadAll(body)

	if err != nil {
		fmt.Println("Error:", err)
		os.Exit(-1)
	}
	defer body.Close()
	fmt.Println(string(fc))
}