云数据库 SelectDB 版：Stream Load

脚本示例

1. 创建待导入的SelectDB数据表，示例如下。

   CREATE TABLE test_table
   (
       id int,
       name varchar(50),
       age int,
       address varchar(50),
       url varchar(500)
   )
   UNIQUE KEY(`id`, `name`)
   DISTRIBUTED BY HASH(id) BUCKETS 16
   PROPERTIES("replication_num" = "1");

2. 创建待导入文件test.data，示例如下。

   1,yang,32,shanghai,http://example.com
   2,wang,22,beijing,http://example.com
   3,xiao,23,shenzhen,http://example.com
   4,jess,45,hangzhou,http://example.com
   5,jack,14,shanghai,http://example.com
   6,tomy,25,hangzhou,http://example.com
   7,lucy,45,shanghai,http://example.com
   8,tengyin,26,shanghai,http://example.com
   9,wangli,27,shenzhen,http://example.com
   10,xiaohua,37,shanghai,http://example.com

3. 使用不同参数配置导入数据，示例如下。

   • 将本地文件test.data中的数据导入到数据库test_db中的test_table表，使用Label用于去重，指定超时时间为100秒。

      curl --location-trusted -u root -H "label:123" -H "timeout:100" -H "expect:100-continue" -H "column_separator:," -T test.data http://host:port/api/test_db/test_table/_stream_load

   • 将本地文件test.data中的数据导入到数据库test_db中的test_table表，使用Label用于去重，指定文件的列名，并且只导入address等于hangzhou的数据。

     curl --location-trusted -u root -H "label:123" -H "columns: id,name,age,address,url" -H "where: address='hangzhou'" -H "expect:100-continue" -H "column_separator:," -T test.data http://host:port/api/test_db/test_table/_stream_load

   • 将本地文件test.data中的数据导入到数据库test_db中的test_table表，允许20%的错误率。

     curl --location-trusted -u root -H "label:123" -H "max_filter_ratio:0.2" -H "expect:100-continue" -T test.data http://host:port/api/test_db/test_table/_stream_load

   • 导入数据进行严格模式过滤，并设置时区为Africa/Abidjan。

     curl --location-trusted -u root -H "strict_mode: true" -H "timezone: Africa/Abidjan" -H "expect:100-continue" -T test.data http://host:port/api/test_db/test_table/_stream_load

   • 删除与这批导入Key相同的数据。

     curl --location-trusted -u root -H "merge_type: DELETE" -H "expect:100-continue" -T test.data http://host:port/api/test_db/test_table/_stream_load

   • 将这批数据中address列为hangzhou的数据的行删除，其他行正常追加。

     curl --location-trusted -u root: -H "expect:100-continue" -H "columns: id,name,age,address,url" -H "merge_type: MERGE" -H "delete: address='hangzhou'" -H "column_separator:," -T test.data http://host:port/api/testDb/testTbl/_stream_load

Java代码示例

package com.selectdb.x2doris.connector.doris.writer;

import com.alibaba.fastjson2.JSON;
import org.apache.http.HttpHeaders;
import org.apache.http.HttpResponse;
import org.apache.http.HttpStatus;
import org.apache.http.client.HttpClient;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.HttpPut;
import org.apache.http.entity.BufferedHttpEntity;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.DefaultRedirectStrategy;
import org.apache.http.impl.client.HttpClientBuilder;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.protocol.RequestContent;
import org.apache.http.util.EntityUtils;

import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.util.Arrays;
import java.util.Base64;
import java.util.List;
import java.util.Map;

public class DorisLoadCase {
    public static void main(String[] args) throws Exception {

        // 1. 参数配置
        String loadUrl = "http://<Host:Port>/api/<DB>/<TABLE>/_stream_load?";
        String userName = "admin";
        String password = "****";

        // 2. 构建httpclient，特别注意需要开启重定向（isRedirectable）
        HttpClientBuilder httpClientBuilder = HttpClients.custom().setRedirectStrategy(new DefaultRedirectStrategy() {
            // 开启重定向
            @Override
            protected boolean isRedirectable(String method) {
                return true;
            }
        });
        httpClientBuilder.addInterceptorLast(new RequestContent(true));
        HttpClient httpClient = httpClientBuilder.build();

        // 3. 构建httpPut请求对象
        HttpPut httpPut = new HttpPut(loadUrl);

        // 设置httpHeader...
        String basicAuth = Base64.getEncoder().encodeToString(String.format("%s:%s", userName, password).getBytes(StandardCharsets.UTF_8));
        httpPut.addHeader(HttpHeaders.AUTHORIZATION, "Basic " + basicAuth);
        httpPut.addHeader(HttpHeaders.EXPECT, "100-continue");
        httpPut.addHeader(HttpHeaders.CONTENT_TYPE, "text/plain; charset=UTF-8");

        RequestConfig reqConfig = RequestConfig.custom().setConnectTimeout(30000).build();
        httpPut.setConfig(reqConfig);

        // 4. 设置要发送的数据，这里写入csv
        // 假设有一张表，字段如下：
        // field1,field2,field3,field4
        // 这里模拟了三条csv记录，doris 中csv的行分隔符默认是\n，列分隔符默认是\t
        String data =
                "1\t2\t3\t4\n" +
                "11\t22\t33\t44\n" +
                "111\t222\t333\t444";

        httpPut.setEntity(new StringEntity(data));

        // 5. 发送请求，处理结果
        HttpResponse httpResponse = httpClient.execute(httpPut);
        int httpStatus = httpResponse.getStatusLine().getStatusCode();
        String respContent = EntityUtils.toString(new BufferedHttpEntity(httpResponse.getEntity()), StandardCharsets.UTF_8);
        String respMsg = httpResponse.getStatusLine().getReasonPhrase();

        if (httpStatus == HttpStatus.SC_OK) {
            // 选择适合的JSON序列化组件，对返回结果进行序列化
            Map<String, String> respAsMap = JSON.parseObject(respContent, Map.class);
            // 获取SelectDB返回的状态码...
            String dorisStatus = respAsMap.get("Status");
            // SelectDB返回以下状态，都表示数据写入成功
            List<String> DORIS_SUCCESS_STATUS = Arrays.asList("Success", "Publish Timeout", "200");
            if (!DORIS_SUCCESS_STATUS.contains(dorisStatus) || !respMsg.equals("OK")) {
                throw new RuntimeException("StreamLoad failed, status: " + dorisStatus + ", Response: " + respMsg);
            } else {
                System.out.println("successful....");
            }
        } else {
            throw new IOException("StreamLoad Response HTTP Status Error, httpStatus: "+ httpStatus +",  url: " + loadUrl + ", error: " + respMsg);
        }
    }
}