Merge pull request #1603 from hf200012/doriswriter-doc-fix

doris writer write error
This commit is contained in:
Trafalgar 2022-11-15 18:03:30 +08:00 committed by GitHub
commit 3e13d6a788
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 29 additions and 26 deletions

View File

@ -72,9 +72,9 @@ DorisWriter 通过Doris原生支持Stream load方式导入数据 DorisWriter
* **jdbcUrl**
- 描述Doris 的 JDBC 连接串,用户执行 preSql 或 postSQL。
- 必选:是
- 默认值:无
- 描述Doris 的 JDBC 连接串,用户执行 preSql 或 postSQL。
- 必选:是
- 默认值:无
* **loadUrl**
@ -84,31 +84,31 @@ DorisWriter 通过Doris原生支持Stream load方式导入数据 DorisWriter
* **username**
- 描述访问Doris数据库的用户名
- 必选:是
- 默认值:无
- 描述访问Doris数据库的用户名
- 必选:是
- 默认值:无
* **password**
- 描述访问Doris数据库的密码
- 必选:否
- 默认值:空
- 描述访问Doris数据库的密码
- 必选:否
- 默认值:空
* **connection.selectedDatabase**
- 描述需要写入的Doris数据库名称。
- 必选:是
- 默认值:无
- 描述需要写入的Doris数据库名称。
- 必选:是
- 默认值:无
* **connection.table**
- 描述需要写入的Doris表名称。
- 必选:是
- 默认值:无
* **column**
- 描述:目的表**需要写入数据**的字段,这些字段将作为生成的 Json 数据的字段名。字段之间用英文逗号分隔。例如: "column": ["id","name","age"]。
- 必选:是
- 默认值:否
- 描述:目的表**需要写入数据**的字段,这些字段将作为生成的 Json 数据的字段名。字段之间用英文逗号分隔。例如: "column": ["id","name","age"]。
- 必选:是
- 默认值:否
* **preSql**
@ -165,16 +165,16 @@ DorisWriter 通过Doris原生支持Stream load方式导入数据 DorisWriter
```json
"loadProps": {
"column_separator": "\\x01",
"row_delimiter": "\\x02"
"column_separator": "\\x01",
"line_delimiter": "\\x02"
}
```
如需更改导入格式为`json` 则正确配置 `loadProps` 即可:
```json
"loadProps": {
"format": "json",
"strip_outer_array": true
"format": "json",
"strip_outer_array": true
}
```

View File

@ -3,6 +3,7 @@ package com.alibaba.datax.plugin.writer.doriswriter;
import com.alibaba.fastjson.JSON;
import org.apache.commons.codec.binary.Base64;
import org.apache.http.HttpEntity;
import org.apache.http.HttpHeaders;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
@ -124,7 +125,7 @@ public class DorisStreamLoadObserver {
private byte[] addRows(List<byte[]> rows, int totalBytes) {
if (Keys.StreamLoadFormat.CSV.equals(options.getStreamLoadFormat())) {
Map<String, Object> props = (options.getLoadProps() == null ? new HashMap<> () : options.getLoadProps());
byte[] lineDelimiter = DelimiterParser.parse((String)props.get("row_delimiter"), "\n").getBytes(StandardCharsets.UTF_8);
byte[] lineDelimiter = DelimiterParser.parse((String)props.get("line_delimiter"), "\n").getBytes(StandardCharsets.UTF_8);
ByteBuffer bos = ByteBuffer.allocate(totalBytes + rows.size() * lineDelimiter.length);
for (byte[] row : rows) {
bos.put(row);
@ -161,6 +162,8 @@ public class DorisStreamLoadObserver {
});
try ( CloseableHttpClient httpclient = httpClientBuilder.build()) {
HttpPut httpPut = new HttpPut(loadUrl);
httpPut.removeHeaders(HttpHeaders.CONTENT_LENGTH);
httpPut.removeHeaders(HttpHeaders.TRANSFER_ENCODING);
List<String> cols = options.getColumns();
if (null != cols && !cols.isEmpty() && Keys.StreamLoadFormat.CSV.equals(options.getStreamLoadFormat())) {
httpPut.setHeader("columns", String.join(",", cols.stream().map(f -> String.format("`%s`", f)).collect(Collectors.toList())));
@ -172,9 +175,9 @@ public class DorisStreamLoadObserver {
}
httpPut.setHeader("Expect", "100-continue");
httpPut.setHeader("label", label);
httpPut.setHeader("Content-Type", "application/x-www-form-urlencoded");
httpPut.setHeader("two_phase_commit", "false");
httpPut.setHeader("Authorization", getBasicAuthHeader(options.getUsername(), options.getPassword()));
httpPut.setEntity(new ByteArrayEntity (data));
httpPut.setEntity(new ByteArrayEntity(data));
httpPut.setConfig(RequestConfig.custom().setRedirectsEnabled(true).build());
try ( CloseableHttpResponse resp = httpclient.execute(httpPut)) {
HttpEntity respEntity = getHttpEntity(resp);