Merge branch 'dev' into dev

.github/workflows/labeler/label-scope-conf.yml

@@ -257,11 +257,19 @@ activemq:
       - changed-files:
           - any-glob-to-any-file: seatunnel-connectors-v2/connector-activemq/**
           - all-globs-to-all-files: '!seatunnel-connectors-v2/connector-!(activemq)/**'
+
 qdrant:
   - all:
       - changed-files:
           - any-glob-to-any-file: seatunnel-connectors-v2/connector-qdrant/**
           - all-globs-to-all-files: '!seatunnel-connectors-v2/connector-!(qdrant)/**'
+
+typesense:
+  - all:
+      - changed-files:
+          - any-glob-to-any-file: seatunnel-connectors-v2/connector-typesense/**
+          - all-globs-to-all-files: '!seatunnel-connectors-v2/connector-!(typesense)/**'
+
 Zeta Rest API:
   - changed-files:
       - any-glob-to-any-file: seatunnel-engine/**/server/rest/**

config/plugin_config

@@ -89,5 +89,5 @@ connector-milvus
 connector-activemq
 connector-sls
 connector-qdrant
+connector-typesense
 connector-cdc-opengauss
---end--

docs/en/connector-v2/sink/Rabbitmq.md

@@ -57,6 +57,21 @@ convenience method for setting the fields in an AMQP URI: host, port, username,
 
 the queue to write the message to
 
+### durable [boolean]
+
+true: The queue will survive a server restart.
+false: The queue will be deleted on server restart.
+
+### exclusive [boolean]
+
+true: The queue is used only by the current connection and will be deleted when the connection closes.
+false: The queue can be used by multiple connections.
+
+### auto_delete [boolean]
+
+true: The queue will be deleted automatically when the last consumer unsubscribes.
+false: The queue will not be automatically deleted.
+
 ### schema [Config]
 
 #### fields [Config]
@@ -112,6 +127,30 @@ sink {
 }
 ```
 
+### Example 2
+
+queue with durable, exclusive, auto_delete:
+
+```hocon
+sink {
+      RabbitMQ {
+          host = "rabbitmq-e2e"
+          port = 5672
+          virtual_host = "/"
+          username = "guest"
+          password = "guest"
+          queue_name = "test1"
+          durable = "true"
+          exclusive = "false"
+          auto_delete = "false"
+          rabbitmq.config = {
+            requested-heartbeat = 10
+            connection-timeout = 10
+          }
+      }
+}
+```
+
 ## Changelog
 
 ### next version

docs/en/connector-v2/sink/Typesense.md

@@ -0,0 +1,93 @@
+# Typesense
+
+## Description
+
+Outputs data to `Typesense`.
+
+## Key Features
+
+- [ ] [Exactly Once](../../concept/connector-v2-features.md)
+- [x] [CDC](../../concept/connector-v2-features.md)
+
+## Options
+
+|       Name       |  Type  | Required |        Default Value         |
+|------------------|--------|----------|------------------------------|
+| hosts            | array  | Yes      | -                            |
+| collection       | string | Yes      | -                            |
+| schema_save_mode | string | Yes      | CREATE_SCHEMA_WHEN_NOT_EXIST |
+| data_save_mode   | string | Yes      | APPEND_DATA                  |
+| primary_keys     | array  | No       |                              |
+| key_delimiter    | string | No       | `_`                          |
+| api_key          | string | No       |                              |
+| max_retry_count  | int    | No       | 3                            |
+| max_batch_size   | int    | No       | 10                           |
+| common-options   |        | No       | -                            |
+
+### hosts [array]
+
+The access address for Typesense, formatted as `host:port`, e.g., `["typesense-01:8108"]`.
+
+### collection [string]
+
+The name of the collection to write to, e.g., "seatunnel".
+
+### primary_keys [array]
+
+Primary key fields used to generate the document `id`.
+
+### key_delimiter [string]
+
+Sets the delimiter for composite keys (default is `_`).
+
+### api_key [config]
+
+The `api_key` for secure access to Typesense.
+
+### max_retry_count [int]
+
+The maximum number of retry attempts for batch requests.
+
+### max_batch_size [int]
+
+The maximum size of document batches.
+
+### common options
+
+Common parameters for Sink plugins. Refer to [Common Sink Options](../source-common-options.md) for more details.
+
+### schema_save_mode
+
+Choose how to handle the target-side schema before starting the synchronization task:
+- `RECREATE_SCHEMA`: Creates the table if it doesn’t exist, and deletes and recreates it if it does.
+- `CREATE_SCHEMA_WHEN_NOT_EXIST`: Creates the table if it doesn’t exist, skips creation if it does.
+- `ERROR_WHEN_SCHEMA_NOT_EXIST`: Throws an error if the table doesn’t exist.
+
+### data_save_mode
+
+Choose how to handle existing data on the target side before starting the synchronization task:
+- `DROP_DATA`: Retains the database structure but deletes the data.
+- `APPEND_DATA`: Retains both the database structure and the data.
+- `ERROR_WHEN_DATA_EXISTS`: Throws an error if data exists.
+
+## Example
+
+Simple example:
+
+```bash
+sink {
+    Typesense {
+        source_table_name = "typesense_test_table"
+        hosts = ["localhost:8108"]
+        collection = "typesense_to_typesense_sink_with_query"
+        max_retry_count = 3
+        max_batch_size = 10
+        api_key = "xyz"
+        primary_keys = ["num_employees","id"]
+        key_delimiter = "="
+        schema_save_mode = "CREATE_SCHEMA_WHEN_NOT_EXIST"
+        data_save_mode = "APPEND_DATA"
+    }
+}
+```
+

docs/en/connector-v2/source/Typesense.md

@@ -0,0 +1,79 @@
+# Typesense
+
+> Typesense Source Connector
+
+## Description
+
+Reads data from Typesense.
+
+## Key Features
+
+- [x] [Batch Processing](../../concept/connector-v2-features.md)
+- [ ] [Stream Processing](../../concept/connector-v2-features.md)
+- [ ] [Exactly-Once](../../concept/connector-v2-features.md)
+- [x] [Schema](../../concept/connector-v2-features.md)
+- [x] [Parallelism](../../concept/connector-v2-features.md)
+- [ ] [User-Defined Splits Support](../../concept/connector-v2-features.md)
+
+## Options
+
+|    Name    |  Type  | Required | Default |
+|------------|--------|----------|---------|
+| hosts      | array  | yes      | -       |
+| collection | string | yes      | -       |
+| schema     | config | yes      | -       |
+| api_key    | string | no       | -       |
+| query      | string | no       | -       |
+| batch_size | int    | no       | 100     |
+
+### hosts [array]
+
+The access address of Typesense, for example: `["typesense-01:8108"]`.
+
+### collection [string]
+
+The name of the collection to write to, for example: `"seatunnel"`.
+
+### schema [config]
+
+The columns to be read from Typesense. For more information, please refer to the [guide](../../concept/schema-feature.md#how-to-declare-type-supported).
+
+### api_key [config]
+
+The `api_key` for Typesense security authentication.
+
+### batch_size
+
+The number of records to query per batch when reading data.
+
+### Common Options
+
+For common parameters of Source plugins, please refer to [Source Common Options](../source-common-options.md).
+
+## Example
+
+```bash
+source {
+   Typesense {
+      hosts = ["localhost:8108"]
+      collection = "companies"
+      api_key = "xyz"
+      query = "q=*&filter_by=num_employees:>9000"
+      schema = {
+            fields {
+              company_name_list = array<string>
+              company_name = string
+              num_employees = long
+              country = string
+              id = string
+              c_row = {
+                c_int = int
+                c_string = string
+                c_array_int = array<int>
+              }
+            }
+          }
+    }
+}
+```
+

docs/en/faq.md

@@ -203,23 +203,6 @@ spark {
 }
 ```
 
-## How do I specify a different JDK version for SeaTunnel on YARN?
-
-For example, if you want to set the JDK version to JDK8, there are two cases:
-
-- The YARN cluster has deployed JDK8, but the default JDK is not JDK8. Add two configurations to the SeaTunnel config file:
-
-  ```
-    env {
-   ...
-   spark.executorEnv.JAVA_HOME="/your/java_8_home/directory"
-   spark.yarn.appMasterEnv.JAVA_HOME="/your/java_8_home/directory"
-   ...
-  }
-  ```
-- YARN cluster does not deploy JDK8. At this time, start SeaTunnel attached with JDK8. For detailed operations, see:
-  https://www.cnblogs.com/jasondan/p/spark-specific-jdk-version.html
-
 ## What should I do if OOM always appears when running SeaTunnel in Spark local[*] mode?
 
 If you run in local mode, you need to modify the `start-seatunnel.sh` startup script. After `spark-submit`, add a parameter `--driver-memory 4g` . Under normal circumstances, local mode is not used in the production environment. Therefore, this parameter generally does not need to be set during On YARN. See: [Application Properties](https://spark.apache.org/docs/latest/configuration.html#application-properties) for details.
@@ -334,10 +317,6 @@ spark-submit --verbose
     ...
 ```
 
-## How do I use SeaTunnel to synchronize data across HDFS clusters?
-
-Just configure hdfs-site.xml properly. Refer to: https://www.cnblogs.com/suanec/p/7828139.html.
-
 ## I want to learn the source code of SeaTunnel. Where should I start?
 
 SeaTunnel has a completely abstract and structured code implementation, and many people have chosen SeaTunnel As a way to learn Spark. You can learn the source code from the main program entry: SeaTunnel.java

docs/zh/connector-v2/sink/Typesense.md

@@ -0,0 +1,95 @@
+# Typesense
+
+## 描述
+
+输出数据到 `Typesense`
+
+## 主要特性
+
+- [ ] [精确一次](../../concept/connector-v2-features.md)
+- [x] [cdc](../../concept/connector-v2-features.md)
+
+## 选项
+
+|        名称        |   类型   | 是否必须 |             默认值              |
+|------------------|--------|------|------------------------------|
+| hosts            | array  | 是    | -                            |
+| collection       | string | 是    | -                            |
+| schema_save_mode | string | 是    | CREATE_SCHEMA_WHEN_NOT_EXIST |
+| data_save_mode   | string | 是    | APPEND_DATA                  |
+| primary_keys     | array  | 否    |                              |
+| key_delimiter    | string | 否    | `_`                          |
+| api_key          | string | 否    |                              |
+| max_retry_count  | int    | 否    | 3                            |
+| max_batch_size   | int    | 否    | 10                           |
+| common-options   |        | 否    | -                            |
+
+### hosts [array]
+
+Typesense的访问地址，格式为 `host:port`，例如：["typesense-01:8108"]
+
+### collection [string]
+
+要写入的集合名，例如：“seatunnel”
+
+### primary_keys [array]
+
+主键字段用于生成文档 `id`。
+
+### key_delimiter [string]
+
+设定复合键的分隔符（默认为 `_`）。
+
+### api_key [config]
+
+typesense 安全认证的 api_key。
+
+### max_retry_count [int]
+
+批次批量请求最大尝试大小
+
+### max_batch_size [int]
+
+批次批量文档最大大小
+
+### common options
+
+Sink插件常用参数，请参考 [Sink常用选项](../sink-common-options.md) 了解详情
+
+### schema_save_mode
+
+在启动同步任务之前，针对目标侧已有的表结构选择不同的处理方案<br/>
+选项介绍：<br/>
+`RECREATE_SCHEMA` ：当表不存在时会创建，当表已存在时会删除并重建<br/>
+`CREATE_SCHEMA_WHEN_NOT_EXIST` ：当表不存在时会创建，当表已存在时则跳过创建<br/>
+`ERROR_WHEN_SCHEMA_NOT_EXIST` ：当表不存在时将抛出错误<br/>
+
+### data_save_mode
+
+在启动同步任务之前，针对目标侧已存在的数据选择不同的处理方案<br/>
+选项介绍：<br/>
+`DROP_DATA`： 保留数据库结构，删除数据<br/>
+`APPEND_DATA`：保留数据库结构，保留数据<br/>
+`ERROR_WHEN_DATA_EXISTS`：当有数据时抛出错误<br/>
+
+## 示例
+
+简单示例
+
+```bash
+sink {
+    Typesense {
+        source_table_name = "typesense_test_table"
+        hosts = ["localhost:8108"]
+        collection = "typesense_to_typesense_sink_with_query"
+        max_retry_count = 3
+        max_batch_size = 10
+        api_key = "xyz"
+        primary_keys = ["num_employees","id"]
+        key_delimiter = "="
+        schema_save_mode = "CREATE_SCHEMA_WHEN_NOT_EXIST"
+        data_save_mode = "APPEND_DATA"
+      }
+}
+```
+