From 339480f475d9869d0f196210a69a1721186344bb Mon Sep 17 00:00:00 2001 From: Jia Fan Date: Sat, 12 Apr 2025 17:50:59 +0800 Subject: [PATCH] [Improve][Doc] Unify the header format and fix some documents with abnormal formats --- docs/en/connector-v2/sink-common-options.md | 2 +- docs/en/connector-v2/sink/Cloudberry.md | 4 +-- docs/en/connector-v2/sink/Console.md | 4 +-- docs/en/connector-v2/sink/DB2.md | 4 +-- docs/en/connector-v2/sink/Doris.md | 4 +-- docs/en/connector-v2/sink/Feishu.md | 2 +- docs/en/connector-v2/sink/HdfsFile.md | 2 +- docs/en/connector-v2/sink/Iceberg.md | 6 ++-- docs/en/connector-v2/sink/Kafka.md | 2 +- docs/en/connector-v2/sink/Kingbase.md | 2 +- docs/en/connector-v2/sink/Kudu.md | 2 +- docs/en/connector-v2/sink/Mysql.md | 4 +-- docs/en/connector-v2/sink/Neo4j.md | 2 ++ docs/en/connector-v2/sink/OceanBase.md | 2 +- docs/en/connector-v2/sink/Oracle.md | 4 +-- docs/en/connector-v2/sink/PostgreSql.md | 4 +-- docs/en/connector-v2/sink/Pulsar.md | 2 +- docs/en/connector-v2/sink/Redshift.md | 2 +- docs/en/connector-v2/sink/S3File.md | 2 +- docs/en/connector-v2/sink/SelectDB-Cloud.md | 2 +- docs/en/connector-v2/sink/Slack.md | 2 +- docs/en/connector-v2/sink/Snowflake.md | 2 +- docs/en/connector-v2/sink/SqlServer.md | 2 +- docs/en/connector-v2/sink/StarRocks.md | 2 +- docs/en/connector-v2/sink/Vertica.md | 4 +-- docs/en/connector-v2/source-common-options.md | 2 +- docs/en/connector-v2/source/Cloudberry.md | 6 ++-- docs/en/connector-v2/source/DB2.md | 6 ++-- docs/en/connector-v2/source/FakeSource.md | 10 +++---- docs/en/connector-v2/source/HdfsFile.md | 2 +- docs/en/connector-v2/source/HiveJdbc.md | 6 ++-- docs/en/connector-v2/source/Iceberg.md | 10 +++---- docs/en/connector-v2/source/Jdbc.md | 4 +-- docs/en/connector-v2/source/Kingbase.md | 6 ++-- docs/en/connector-v2/source/Kudu.md | 2 +- docs/en/connector-v2/source/MongoDB-CDC.md | 2 +- docs/en/connector-v2/source/MySQL-CDC.md | 3 ++ docs/en/connector-v2/source/Mysql.md | 6 ++-- docs/en/connector-v2/source/OceanBase.md | 6 ++-- docs/en/connector-v2/source/Oracle-CDC.md | 2 +- docs/en/connector-v2/source/Oracle.md | 6 ++-- docs/en/connector-v2/source/PostgreSQL.md | 6 ++-- docs/en/connector-v2/source/Prometheus.md | 2 +- docs/en/connector-v2/source/Redshift.md | 4 +-- docs/en/connector-v2/source/RocketMQ.md | 8 ++--- docs/en/connector-v2/source/S3File.md | 14 --------- docs/en/connector-v2/source/Snowflake.md | 6 ++-- docs/en/connector-v2/source/SqlServer.md | 6 ++-- docs/en/connector-v2/source/Vertica.md | 6 ++-- docs/en/transform-v2/common-options.md | 2 +- docs/zh/connector-v2/sink/Console.md | 4 +-- docs/zh/connector-v2/sink/DB2.md | 4 +-- docs/zh/connector-v2/sink/Doris.md | 22 ++------------ docs/zh/connector-v2/sink/Feishu.md | 2 +- docs/zh/connector-v2/sink/HdfsFile.md | 2 +- docs/zh/connector-v2/sink/Iceberg.md | 6 ++-- docs/zh/connector-v2/sink/Kafka.md | 2 +- docs/zh/connector-v2/sink/Kudu.md | 2 +- docs/zh/connector-v2/sink/Mysql.md | 4 +-- docs/zh/connector-v2/sink/OceanBase.md | 2 +- docs/zh/connector-v2/sink/Oracle.md | 4 +-- docs/zh/connector-v2/sink/PostgreSql.md | 4 +-- docs/zh/connector-v2/sink/Pulsar.md | 2 +- docs/zh/connector-v2/sink/Redshift.md | 2 +- docs/zh/connector-v2/sink/S3File.md | 2 +- docs/zh/connector-v2/sink/SelectDB-Cloud.md | 2 +- docs/zh/connector-v2/sink/Slack.md | 2 +- docs/zh/connector-v2/sink/Snowflake.md | 2 +- docs/zh/connector-v2/sink/SqlServer.md | 2 +- docs/zh/connector-v2/sink/Vertica.md | 4 +-- docs/zh/connector-v2/source/DB2.md | 7 +++-- docs/zh/connector-v2/source/FakeSource.md | 10 +++---- docs/zh/connector-v2/source/HdfsFile.md | 2 +- docs/zh/connector-v2/source/Mysql.md | 6 ++-- docs/zh/connector-v2/source/PostgreSQL.md | 6 ++-- docs/zh/connector-v2/source/Prometheus.md | 2 +- .../seatunnel/api/file/MarkdownTest.java | 30 +++++++++++++++++++ 77 files changed, 173 insertions(+), 169 deletions(-) diff --git a/docs/en/connector-v2/sink-common-options.md b/docs/en/connector-v2/sink-common-options.md index d23d28c1c04..a0aeed7c6dd 100644 --- a/docs/en/connector-v2/sink-common-options.md +++ b/docs/en/connector-v2/sink-common-options.md @@ -22,7 +22,7 @@ When the job configuration `plugin_input` you must set the `plugin_output` param ## Task Example -### Simple: +### Simple > This is the process of passing a data source through two transforms and returning two different pipiles to different sinks diff --git a/docs/en/connector-v2/sink/Cloudberry.md b/docs/en/connector-v2/sink/Cloudberry.md index c7e5b6c99a9..47f08e08191 100644 --- a/docs/en/connector-v2/sink/Cloudberry.md +++ b/docs/en/connector-v2/sink/Cloudberry.md @@ -64,7 +64,7 @@ Key options include: ## Task Example -### Simple: +### Simple ```hocon env { @@ -114,7 +114,7 @@ sink { } ``` -### Exactly-once: +### Exactly-once ```hocon sink { diff --git a/docs/en/connector-v2/sink/Console.md b/docs/en/connector-v2/sink/Console.md index 74998884375..bd300869e5a 100644 --- a/docs/en/connector-v2/sink/Console.md +++ b/docs/en/connector-v2/sink/Console.md @@ -34,7 +34,7 @@ Used to send data to Console. Both support streaming and batch mode. ## Task Example -### Simple: +### Simple > This is a randomly generated data, written to the console, with a degree of parallelism of 1 @@ -63,7 +63,7 @@ sink { } ``` -### Multiple Sources Simple: +### Multiple Sources Simple > This is a multiple source and you can specify a data source to write to the specified end diff --git a/docs/en/connector-v2/sink/DB2.md b/docs/en/connector-v2/sink/DB2.md index d691325f481..72dfd08519d 100644 --- a/docs/en/connector-v2/sink/DB2.md +++ b/docs/en/connector-v2/sink/DB2.md @@ -88,7 +88,7 @@ semantics (using XA transaction guarantee). ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your DB2. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. @@ -153,7 +153,7 @@ sink { } ``` -### Exactly-once : +### Exactly-once > For accurate write scene we guarantee accurate once diff --git a/docs/en/connector-v2/sink/Doris.md b/docs/en/connector-v2/sink/Doris.md index 63d9d48ba5a..21bad549ce6 100644 --- a/docs/en/connector-v2/sink/Doris.md +++ b/docs/en/connector-v2/sink/Doris.md @@ -176,7 +176,7 @@ Otherwise, if you enable the 2pc by the property `sink.enable-2pc=true`.The `sin ## Task Example -### Simple: +### Simple > The following example describes writing multiple data types to Doris, and users need to create corresponding tables downstream @@ -234,7 +234,7 @@ sink { } ``` -### CDC(Change Data Capture) Event: +### CDC(Change Data Capture) Event > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to Doris Sink,FakeSource simulates CDC data with schema, score (int type),Doris needs to create a table sink named test.e2e_table_sink and a corresponding table for it. diff --git a/docs/en/connector-v2/sink/Feishu.md b/docs/en/connector-v2/sink/Feishu.md index 05a95adff61..ab4bef1476c 100644 --- a/docs/en/connector-v2/sink/Feishu.md +++ b/docs/en/connector-v2/sink/Feishu.md @@ -52,7 +52,7 @@ Used to launch Feishu web hooks using data. ## Task Example -### Simple: +### Simple ```hocon Feishu { diff --git a/docs/en/connector-v2/sink/HdfsFile.md b/docs/en/connector-v2/sink/HdfsFile.md index 62e4ebc0aac..33a7d637570 100644 --- a/docs/en/connector-v2/sink/HdfsFile.md +++ b/docs/en/connector-v2/sink/HdfsFile.md @@ -86,7 +86,7 @@ Output data to hdfs file ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to Hdfs. diff --git a/docs/en/connector-v2/sink/Iceberg.md b/docs/en/connector-v2/sink/Iceberg.md index dec2c03a244..990b4cc0731 100644 --- a/docs/en/connector-v2/sink/Iceberg.md +++ b/docs/en/connector-v2/sink/Iceberg.md @@ -83,7 +83,7 @@ libfb303-xxx.jar ## Task Example -### Simple: +### Simple ```hocon env { @@ -128,7 +128,7 @@ sink { } ``` -### Hive Catalog: +### Hive Catalog ```hocon sink { @@ -154,7 +154,7 @@ sink { } ``` -### Hadoop catalog: +### Hadoop catalog ```hocon sink { diff --git a/docs/en/connector-v2/sink/Kafka.md b/docs/en/connector-v2/sink/Kafka.md index 41ccb7a3312..8ab2b540631 100644 --- a/docs/en/connector-v2/sink/Kafka.md +++ b/docs/en/connector-v2/sink/Kafka.md @@ -99,7 +99,7 @@ This function by `MessageContentPartitioner` class implements `org.apache.kafka. ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to Kafka Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target topic is test_topic will also be 16 rows of data in the topic. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. diff --git a/docs/en/connector-v2/sink/Kingbase.md b/docs/en/connector-v2/sink/Kingbase.md index b5bc062df31..5f0f3bc5419 100644 --- a/docs/en/connector-v2/sink/Kingbase.md +++ b/docs/en/connector-v2/sink/Kingbase.md @@ -85,7 +85,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends > it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having 12 fields. The final target table is test_table will also be 16 rows of data in the table. diff --git a/docs/en/connector-v2/sink/Kudu.md b/docs/en/connector-v2/sink/Kudu.md index a461b4455d9..96ac22f7591 100644 --- a/docs/en/connector-v2/sink/Kudu.md +++ b/docs/en/connector-v2/sink/Kudu.md @@ -57,7 +57,7 @@ import ChangeLog from '../changelog/connector-kudu.md'; ## Task Example -### Simple: +### Simple > The following example refers to a FakeSource named "kudu" cdc write kudu table "kudu_sink_table" diff --git a/docs/en/connector-v2/sink/Mysql.md b/docs/en/connector-v2/sink/Mysql.md index 0f34b5dbe8f..af7e6b3e290 100644 --- a/docs/en/connector-v2/sink/Mysql.md +++ b/docs/en/connector-v2/sink/Mysql.md @@ -99,7 +99,7 @@ semantics (using XA transaction guarantee). ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your mysql. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. @@ -164,7 +164,7 @@ sink { } ``` -### Exactly-once : +### Exactly-once > For accurate write scene we guarantee accurate once diff --git a/docs/en/connector-v2/sink/Neo4j.md b/docs/en/connector-v2/sink/Neo4j.md index 7ec228f5994..b367a1dc6d8 100644 --- a/docs/en/connector-v2/sink/Neo4j.md +++ b/docs/en/connector-v2/sink/Neo4j.md @@ -118,6 +118,8 @@ sink { ## WriteBatchExample > The unwind keyword provided by cypher supports batch writing, and the default variable for a batch of data is batch. If you write a batch write statement, then you should declare cypher:unwind $batch as row to do someting + + ``` sink { Neo4j { diff --git a/docs/en/connector-v2/sink/OceanBase.md b/docs/en/connector-v2/sink/OceanBase.md index 81e2d7c739f..7313e290642 100644 --- a/docs/en/connector-v2/sink/OceanBase.md +++ b/docs/en/connector-v2/sink/OceanBase.md @@ -98,7 +98,7 @@ Write data through jdbc. Support Batch mode and Streaming mode, support concurre ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your mysql. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. diff --git a/docs/en/connector-v2/sink/Oracle.md b/docs/en/connector-v2/sink/Oracle.md index 3f305a77517..60dcda9a93f 100644 --- a/docs/en/connector-v2/sink/Oracle.md +++ b/docs/en/connector-v2/sink/Oracle.md @@ -98,7 +98,7 @@ semantics (using XA transaction guarantee). ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your Oracle. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. @@ -162,7 +162,7 @@ sink { } ``` -### Exactly-once : +### Exactly-once > For accurate write scene we guarantee accurate once diff --git a/docs/en/connector-v2/sink/PostgreSql.md b/docs/en/connector-v2/sink/PostgreSql.md index 1760eae203e..2bae4fc47e2 100644 --- a/docs/en/connector-v2/sink/PostgreSql.md +++ b/docs/en/connector-v2/sink/PostgreSql.md @@ -142,7 +142,7 @@ When data_save_mode selects CUSTOM_PROCESSING, you should fill in the CUSTOM_SQL ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your PostgreSQL. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. @@ -208,7 +208,7 @@ sink { } ``` -### Exactly-once : +### Exactly-once > For accurate write scene we guarantee accurate once diff --git a/docs/en/connector-v2/sink/Pulsar.md b/docs/en/connector-v2/sink/Pulsar.md index aef645c0b28..05f1bc2457b 100644 --- a/docs/en/connector-v2/sink/Pulsar.md +++ b/docs/en/connector-v2/sink/Pulsar.md @@ -132,7 +132,7 @@ Source plugin common parameters, please refer to [Source Common Options](../sink ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to Pulsar Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target topic is test_topic will also be 16 rows of data in the topic. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. diff --git a/docs/en/connector-v2/sink/Redshift.md b/docs/en/connector-v2/sink/Redshift.md index 88eee068f62..03e00888c00 100644 --- a/docs/en/connector-v2/sink/Redshift.md +++ b/docs/en/connector-v2/sink/Redshift.md @@ -60,7 +60,7 @@ semantics (using XA transaction guarantee). ## Task Example -### Simple: +### Simple ``` sink { diff --git a/docs/en/connector-v2/sink/S3File.md b/docs/en/connector-v2/sink/S3File.md index 0e817d1890d..d25a114c908 100644 --- a/docs/en/connector-v2/sink/S3File.md +++ b/docs/en/connector-v2/sink/S3File.md @@ -314,7 +314,7 @@ The encoding of the file to write. This param will be parsed by `Charset.forName ## Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to S3File Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target s3 dir will also create a file and all of the data in write in it. > Before run this job, you need create s3 path: /seatunnel/text. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. diff --git a/docs/en/connector-v2/sink/SelectDB-Cloud.md b/docs/en/connector-v2/sink/SelectDB-Cloud.md index a4fe9b8968c..6eedc97a2e5 100644 --- a/docs/en/connector-v2/sink/SelectDB-Cloud.md +++ b/docs/en/connector-v2/sink/SelectDB-Cloud.md @@ -79,7 +79,7 @@ The supported formats include CSV and JSON ## Task Example -### Simple: +### Simple > The following example describes writing multiple data types to SelectDBCloud, and users need to create corresponding tables downstream diff --git a/docs/en/connector-v2/sink/Slack.md b/docs/en/connector-v2/sink/Slack.md index d7db08d4c71..0a52c6e1f27 100644 --- a/docs/en/connector-v2/sink/Slack.md +++ b/docs/en/connector-v2/sink/Slack.md @@ -36,7 +36,7 @@ All data types are mapped to string. ## Task Example -### Simple: +### Simple ```hocon sink { diff --git a/docs/en/connector-v2/sink/Snowflake.md b/docs/en/connector-v2/sink/Snowflake.md index 87e58a12c26..5139d36cc36 100644 --- a/docs/en/connector-v2/sink/Snowflake.md +++ b/docs/en/connector-v2/sink/Snowflake.md @@ -77,7 +77,7 @@ Write data through jdbc. Support Batch mode and Streaming mode, support concurre > ## Task Example -### simple: +### simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your snowflake database. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. diff --git a/docs/en/connector-v2/sink/SqlServer.md b/docs/en/connector-v2/sink/SqlServer.md index 66652f79287..888c50dab78 100644 --- a/docs/en/connector-v2/sink/SqlServer.md +++ b/docs/en/connector-v2/sink/SqlServer.md @@ -96,7 +96,7 @@ semantics (using XA transaction guarantee). ## Task Example -### simple: +### simple > This is one that reads Sqlserver data and inserts it directly into another table diff --git a/docs/en/connector-v2/sink/StarRocks.md b/docs/en/connector-v2/sink/StarRocks.md index d78226fe4dc..4ce62704749 100644 --- a/docs/en/connector-v2/sink/StarRocks.md +++ b/docs/en/connector-v2/sink/StarRocks.md @@ -165,7 +165,7 @@ The supported formats include CSV and JSON ## Task Example -### Simple: +### Simple > The following example describes writing multiple data types to StarRocks, and users need to create corresponding tables downstream diff --git a/docs/en/connector-v2/sink/Vertica.md b/docs/en/connector-v2/sink/Vertica.md index 802a84f5ce0..a88b314cf73 100644 --- a/docs/en/connector-v2/sink/Vertica.md +++ b/docs/en/connector-v2/sink/Vertica.md @@ -96,7 +96,7 @@ semantics (using XA transaction guarantee). ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that automatically generates data through FakeSource and sends it to JDBC Sink. FakeSource generates a total of 16 rows of data (row.num=16), with each row having two fields, name (string type) and age (int type). The final target table is test_table will also be 16 rows of data in the table. Before run this job, you need create database test and table test_table in your vertical. And if you have not yet installed and deployed SeaTunnel, you need to follow the instructions in [Install SeaTunnel](../../start-v2/locally/deployment.md) to install and deploy SeaTunnel. And then follow the instructions in [Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) to run this job. @@ -161,7 +161,7 @@ sink { } ``` -### Exactly-once : +### Exactly-once > For accurate write scene we guarantee accurate once diff --git a/docs/en/connector-v2/source-common-options.md b/docs/en/connector-v2/source-common-options.md index f4902b6f613..9cc539da03d 100644 --- a/docs/en/connector-v2/source-common-options.md +++ b/docs/en/connector-v2/source-common-options.md @@ -23,7 +23,7 @@ When the job configuration `plugin_output` you must set the `plugin_input` param ## Task Example -### Simple: +### Simple > This registers a stream or batch data source and returns the table name `fake_table` at registration diff --git a/docs/en/connector-v2/source/Cloudberry.md b/docs/en/connector-v2/source/Cloudberry.md index 80880d6f984..7f8b95ad5d9 100644 --- a/docs/en/connector-v2/source/Cloudberry.md +++ b/docs/en/connector-v2/source/Cloudberry.md @@ -67,7 +67,7 @@ Cloudberry supports parallel reading following the same rules as PostgreSQL conn ## Task Example -### Simple: +### Simple ```hocon env { @@ -90,7 +90,7 @@ sink { } ``` -### Parallel reading with table_path: +### Parallel reading with table_path ```hocon env { @@ -114,7 +114,7 @@ sink { } ``` -### Multiple table read: +### Multiple table read ```hocon env { diff --git a/docs/en/connector-v2/source/DB2.md b/docs/en/connector-v2/source/DB2.md index 4f0d270cad7..9a551e4b470 100644 --- a/docs/en/connector-v2/source/DB2.md +++ b/docs/en/connector-v2/source/DB2.md @@ -88,7 +88,7 @@ Read external data source data through JDBC. ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -119,7 +119,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data You can do this if you want to read the whole table @@ -141,7 +141,7 @@ source { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured diff --git a/docs/en/connector-v2/source/FakeSource.md b/docs/en/connector-v2/source/FakeSource.md index 2ca6dd6ecde..016f9dd2bc9 100644 --- a/docs/en/connector-v2/source/FakeSource.md +++ b/docs/en/connector-v2/source/FakeSource.md @@ -72,7 +72,7 @@ just for some test cases such as type conversion or connector new feature testin ## Task Example -### Simple: +### Simple > This example Randomly generates data of a specified type. If you want to learn how to declare field types, click [here](../../concept/schema-feature.md#how-to-declare-type-supported). @@ -149,7 +149,7 @@ source { } ``` -### Customize the data content Simple: +### Customize the data content Simple > This is a self-defining data source information, defining whether each piece of data is an add or delete modification operation, and defining what each field stores @@ -199,7 +199,7 @@ source { > Due to the constraints of the [HOCON](https://github.com/lightbend/config/blob/main/HOCON.md) specification, users cannot directly create byte sequence objects. FakeSource uses strings to assign `bytes` type values. In the example above, the `bytes` type field is assigned `"bWlJWmo="`, which is encoded from "miIZj" with **base64**. Hence, when assigning values to `bytes` type fields, please use strings encoded with **base64**. -### Specified Data number Simple: +### Specified Data number Simple > This case specifies the number of data generated and the length of the generated value @@ -249,7 +249,7 @@ FakeSource { } ``` -### Template data Simple: +### Template data Simple > Randomly generated according to the specified template @@ -286,7 +286,7 @@ FakeSource { } ``` -### Range data Simple: +### Range data Simple > The specified data generation range is randomly generated diff --git a/docs/en/connector-v2/source/HdfsFile.md b/docs/en/connector-v2/source/HdfsFile.md index c7cd5b8073e..04a23c3d976 100644 --- a/docs/en/connector-v2/source/HdfsFile.md +++ b/docs/en/connector-v2/source/HdfsFile.md @@ -165,7 +165,7 @@ The encoding of the file to read. This param will be parsed by `Charset.forName( ## Task Example -### Simple: +### Simple > This example defines a SeaTunnel synchronization task that read data from Hdfs and sends it to Hdfs. diff --git a/docs/en/connector-v2/source/HiveJdbc.md b/docs/en/connector-v2/source/HiveJdbc.md index 72033cf8697..db87a8a7130 100644 --- a/docs/en/connector-v2/source/HiveJdbc.md +++ b/docs/en/connector-v2/source/HiveJdbc.md @@ -89,7 +89,7 @@ Read external data source data through JDBC. ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its > fields. You can also specify which fields to query for final output to the console. @@ -119,7 +119,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data You can do this if you want > to read the whole table @@ -140,7 +140,7 @@ source { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read > your data source according to the upper and lower boundaries you configured diff --git a/docs/en/connector-v2/source/Iceberg.md b/docs/en/connector-v2/source/Iceberg.md index 7b1ae2a3474..f19c6077db8 100644 --- a/docs/en/connector-v2/source/Iceberg.md +++ b/docs/en/connector-v2/source/Iceberg.md @@ -95,7 +95,7 @@ libfb303-xxx.jar ## Task Example -### Simple: +### Simple ```hocon env { @@ -126,7 +126,7 @@ sink { } ``` -### Multi-Table Read: +### Multi-Table Read ```hocon source { @@ -151,7 +151,7 @@ source { } ``` -### Hadoop S3 Catalog: +### Hadoop S3 Catalog ```hocon source { @@ -175,7 +175,7 @@ source { } ``` -### Hive Catalog: +### Hive Catalog ```hocon source { @@ -194,7 +194,7 @@ source { } ``` -### Column Projection: +### Column Projection ```hocon source { diff --git a/docs/en/connector-v2/source/Jdbc.md b/docs/en/connector-v2/source/Jdbc.md index ab79a5a45db..972294cb8a7 100644 --- a/docs/en/connector-v2/source/Jdbc.md +++ b/docs/en/connector-v2/source/Jdbc.md @@ -237,7 +237,7 @@ sink { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query. It is more efficient to read your data source according to the upper and lower boundaries you configured. @@ -291,7 +291,7 @@ sink { } ``` -### multiple table read: +### multiple table read ***Configuring `table_list` will turn on auto split, you can configure `split.*` to adjust the split strategy*** diff --git a/docs/en/connector-v2/source/Kingbase.md b/docs/en/connector-v2/source/Kingbase.md index d92d4d2a580..72b4474d3a4 100644 --- a/docs/en/connector-v2/source/Kingbase.md +++ b/docs/en/connector-v2/source/Kingbase.md @@ -78,7 +78,7 @@ Read external data source data through JDBC. ## Task Example -### Simple: +### Simple ``` env { @@ -106,7 +106,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data. You can do this if you want to read the whole table @@ -126,7 +126,7 @@ source { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to read your data source according to the upper and lower boundaries you configured diff --git a/docs/en/connector-v2/source/Kudu.md b/docs/en/connector-v2/source/Kudu.md index d7f898ee44e..7a57b8dba60 100644 --- a/docs/en/connector-v2/source/Kudu.md +++ b/docs/en/connector-v2/source/Kudu.md @@ -64,7 +64,7 @@ The tested kudu version is 1.11.1. ## Task Example -### Simple: +### Simple > The following example is for a Kudu table named "kudu_source_table", The goal is to print the data from this table on the console and write kudu table "kudu_sink_table" diff --git a/docs/en/connector-v2/source/MongoDB-CDC.md b/docs/en/connector-v2/source/MongoDB-CDC.md index 7addcbc4101..43f51d2eddd 100644 --- a/docs/en/connector-v2/source/MongoDB-CDC.md +++ b/docs/en/connector-v2/source/MongoDB-CDC.md @@ -124,7 +124,7 @@ For specific types in MongoDB, we use Extended JSON format to map them to Seatun | incremental.snapshot.chunk.size.mb | Long | No | 64 | The chunk size mb of incremental snapshot. | | common-options | | No | - | Source plugin common parameters, please refer to [Source Common Options](../source-common-options.md) for details. | -### Tips: +### Tips > 1.If the collection changes at a slow pace, it is strongly recommended to set an appropriate value greater than 0 for the heartbeat.interval.ms parameter. When we recover a Seatunnel job from a checkpoint or savepoint, the heartbeat events can push the resumeToken forward to avoid its expiration.
> 2.MongoDB has a limit of 16MB for a single document. Change documents include additional information, so even if the original document is not larger than 15MB, the change document may exceed the 16MB limit, resulting in the termination of the Change Stream operation.
diff --git a/docs/en/connector-v2/source/MySQL-CDC.md b/docs/en/connector-v2/source/MySQL-CDC.md index 694b24f81fd..0125d536b52 100644 --- a/docs/en/connector-v2/source/MySQL-CDC.md +++ b/docs/en/connector-v2/source/MySQL-CDC.md @@ -320,7 +320,10 @@ sink { ``` ### Support table-pattern for multi-table reading + > `table-pattern` and `table-names` are mutually exclusive + + ```hocon env { # You can set engine configuration here diff --git a/docs/en/connector-v2/source/Mysql.md b/docs/en/connector-v2/source/Mysql.md index 4a63da85786..063b709a973 100644 --- a/docs/en/connector-v2/source/Mysql.md +++ b/docs/en/connector-v2/source/Mysql.md @@ -159,7 +159,7 @@ How many splits do we need to split into, only support positive integer. default ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -246,7 +246,7 @@ sink { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured @@ -273,7 +273,7 @@ source { } ``` -### Multiple table read: +### Multiple table read ***Configuring `table_list` will turn on auto split, you can configure `split.*` to adjust the split strategy*** diff --git a/docs/en/connector-v2/source/OceanBase.md b/docs/en/connector-v2/source/OceanBase.md index 85628298d29..e4931d79dab 100644 --- a/docs/en/connector-v2/source/OceanBase.md +++ b/docs/en/connector-v2/source/OceanBase.md @@ -100,7 +100,7 @@ Read external data source data through JDBC. ## Task Example -### Simple: +### Simple ``` env { @@ -129,7 +129,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data. You can do this if you want to read the whole table @@ -157,7 +157,7 @@ sink { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to read your data source according to the upper and lower boundaries you configured diff --git a/docs/en/connector-v2/source/Oracle-CDC.md b/docs/en/connector-v2/source/Oracle-CDC.md index 4a9ce443844..fae6e857b20 100644 --- a/docs/en/connector-v2/source/Oracle-CDC.md +++ b/docs/en/connector-v2/source/Oracle-CDC.md @@ -110,7 +110,7 @@ GRANT SELECT ANY TABLE TO logminer_user; GRANT ANALYZE ANY TO logminer_user; ``` -#### To enable Logminer in Oracle with CDB (Container Database) + PDB (Pluggable Database) mode, follow the steps below: +#### To enable Logminer in Oracle with CDB (Container Database) + PDB (Pluggable Database) mode 1. The operating system creates an empty file directory to store Oracle archived logs and user tablespaces. diff --git a/docs/en/connector-v2/source/Oracle.md b/docs/en/connector-v2/source/Oracle.md index 65fa55ce5a0..ed7c3272cc8 100644 --- a/docs/en/connector-v2/source/Oracle.md +++ b/docs/en/connector-v2/source/Oracle.md @@ -175,7 +175,7 @@ How many splits do we need to split into, only support positive integer. default ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -264,7 +264,7 @@ sink { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured @@ -288,7 +288,7 @@ source { } ``` -### Multiple table read: +### Multiple table read ***Configuring `table_list` will turn on auto split, you can configure `split.*` to adjust the split strategy*** diff --git a/docs/en/connector-v2/source/PostgreSQL.md b/docs/en/connector-v2/source/PostgreSQL.md index 15d309d61aa..bff77f24e4c 100644 --- a/docs/en/connector-v2/source/PostgreSQL.md +++ b/docs/en/connector-v2/source/PostgreSQL.md @@ -166,7 +166,7 @@ How many splits do we need to split into, only support positive integer. default ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -248,7 +248,7 @@ sink { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured @@ -271,7 +271,7 @@ source{ } ``` -### Multiple table read: +### Multiple table read ***Configuring `table_list` will turn on auto split, you can configure `split.*` to adjust the split strategy*** diff --git a/docs/en/connector-v2/source/Prometheus.md b/docs/en/connector-v2/source/Prometheus.md index cb13c0366c4..0455afee189 100644 --- a/docs/en/connector-v2/source/Prometheus.md +++ b/docs/en/connector-v2/source/Prometheus.md @@ -98,7 +98,7 @@ Source plugin common parameters, please refer to [Source Common Options](../sour ## Example -### Instant: +### Instant ```hocon source { diff --git a/docs/en/connector-v2/source/Redshift.md b/docs/en/connector-v2/source/Redshift.md index 5b782ccfca2..079cd9dd484 100644 --- a/docs/en/connector-v2/source/Redshift.md +++ b/docs/en/connector-v2/source/Redshift.md @@ -61,7 +61,7 @@ Read external data source data through JDBC. ## Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -94,7 +94,7 @@ sink { } ``` -### Multiple table read: +### Multiple table read ***Configuring `table_list` will turn on auto split, you can configure `split.*` to adjust the split strategy*** diff --git a/docs/en/connector-v2/source/RocketMQ.md b/docs/en/connector-v2/source/RocketMQ.md index 5490ee38ec7..d2530bd1520 100644 --- a/docs/en/connector-v2/source/RocketMQ.md +++ b/docs/en/connector-v2/source/RocketMQ.md @@ -66,7 +66,7 @@ start.mode.offsets = { ## Task Example -### Simple: +### Simple > Consumer reads Rocketmq data and prints it to the console type @@ -114,7 +114,7 @@ sink { } ``` -### Specified format consumption Simple: +### Specified format consumption simple > When I consume the topic data in json format parsing and pulling the number of bars each time is 400, the consumption starts from the original location @@ -165,7 +165,7 @@ sink { } ``` -### Specified timestamp Simple: +### Specified timestamp simple > This is to specify a time to consume, and I dynamically sense the existence of a new partition every 1000 milliseconds to pull the consumption @@ -221,7 +221,7 @@ sink { } ``` -### Specified tag example: +### Specified tag example > Here you can specify a tag to consume data. If there are multiple tags, use `,` to separate them, for example: "tag1,tag2" diff --git a/docs/en/connector-v2/source/S3File.md b/docs/en/connector-v2/source/S3File.md index ae82ca1133e..2369096a546 100644 --- a/docs/en/connector-v2/source/S3File.md +++ b/docs/en/connector-v2/source/S3File.md @@ -427,18 +427,4 @@ sink { ## Changelog -### 2.3.0-beta 2022-10-20 - -- Add S3File Source Connector - -### Next version - -- [Feature] Support S3A protocol ([3632](https://github.com/apache/seatunnel/pull/3632)) - - Allow user to add additional hadoop-s3 parameters - - Allow the use of the s3a protocol - - Decouple hadoop-aws dependencies -- [Feature]Set S3 AK to optional ([3688](https://github.com/apache/seatunnel/pull/)) - -## Changelog - \ No newline at end of file diff --git a/docs/en/connector-v2/source/Snowflake.md b/docs/en/connector-v2/source/Snowflake.md index 4f447eccc51..fc2ac43011c 100644 --- a/docs/en/connector-v2/source/Snowflake.md +++ b/docs/en/connector-v2/source/Snowflake.md @@ -82,7 +82,7 @@ Read external data source data through JDBC. ## Task Example -### simple: +### simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. > @@ -111,7 +111,7 @@ Read external data source data through JDBC. > } > ``` -### parallel: +### parallel > Read your query table in parallel with the shard field you configured and the shard data You can do this if you want to read the whole table > @@ -131,7 +131,7 @@ Read external data source data through JDBC. > } > ``` -### parallel boundary: +### parallel boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured > diff --git a/docs/en/connector-v2/source/SqlServer.md b/docs/en/connector-v2/source/SqlServer.md index c99060a4410..ffe68e807a2 100644 --- a/docs/en/connector-v2/source/SqlServer.md +++ b/docs/en/connector-v2/source/SqlServer.md @@ -159,7 +159,7 @@ How many splits do we need to split into, only support positive integer. default ## Task Example -### Simple: +### Simple > Simple single task to read the data table @@ -189,7 +189,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data You can do this if you want to read the whole table @@ -225,7 +225,7 @@ sink { ``` -### Fragmented Parallel Read Simple: +### Fragmented Parallel Read Simple > It is a shard that reads data in parallel fast diff --git a/docs/en/connector-v2/source/Vertica.md b/docs/en/connector-v2/source/Vertica.md index f634e07fbc0..4226bc0400d 100644 --- a/docs/en/connector-v2/source/Vertica.md +++ b/docs/en/connector-v2/source/Vertica.md @@ -85,7 +85,7 @@ Read external data source data through JDBC. ## Task Example -### Simple: +### Simple > This example queries type_bin 'table' 16 data in your test "database" in single parallel and queries all of its fields. You can also specify which fields to query for final output to the console. @@ -116,7 +116,7 @@ sink { } ``` -### Parallel: +### Parallel > Read your query table in parallel with the shard field you configured and the shard data You can do this if you want to read the whole table @@ -138,7 +138,7 @@ source { } ``` -### Parallel Boundary: +### Parallel Boundary > It is more efficient to specify the data within the upper and lower bounds of the query It is more efficient to read your data source according to the upper and lower boundaries you configured diff --git a/docs/en/transform-v2/common-options.md b/docs/en/transform-v2/common-options.md index 495da85a19d..b7d197edf11 100644 --- a/docs/en/transform-v2/common-options.md +++ b/docs/en/transform-v2/common-options.md @@ -19,7 +19,7 @@ The old configuration name `source_table_name`/`result_table_name` is deprecated ## Task Example -### Simple: +### Simple > This is the process of converting the data source to fake and write it to two different sinks, Detailed reference `transform` diff --git a/docs/zh/connector-v2/sink/Console.md b/docs/zh/connector-v2/sink/Console.md index f8373ce6573..0d97ec7f647 100644 --- a/docs/zh/connector-v2/sink/Console.md +++ b/docs/zh/connector-v2/sink/Console.md @@ -34,7 +34,7 @@ import ChangeLog from '../changelog/connector-console.md'; ## 任务示例 -### 简单示例: +### 简单示例 > 随机生成的数据,包含两个字段，即 `name`（字符串类型）和 `age`（整型），写入控制台，并行度为 `1` @@ -63,7 +63,7 @@ sink { } ``` -### 多数据源示例： +### 多数据源示例 > 多数据源示例，通过配置可以指定数据源写入指定接收器 diff --git a/docs/zh/connector-v2/sink/DB2.md b/docs/zh/connector-v2/sink/DB2.md index 42d772fc66a..4e77a986be8 100644 --- a/docs/zh/connector-v2/sink/DB2.md +++ b/docs/zh/connector-v2/sink/DB2.md @@ -88,7 +88,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单: +### 简单 > 此示例定义了一个SeaTunnel同步任务，该任务通过FakeSource自动生成数据并将其发送到JDBC Sink。FakeSource总共生成16行数据（row.num=16），每行有两个字段，name（字符串类型）和age（int类型）。最终的目标表是test_table，表中也将有16行数据。在运行此作业之前，您需要在DB2中创建数据库测试和表test_table。如果您尚未安装和部署SeaTunnel，则需要按照[Install SeaTunnel](../../start-v2/locally/deployment.md)中的说明安装和部署SeaTunnel。然后按照[Quick Start With SeaTunnel Engine](../../start-v2/locally/quick-start-seatunnel-engine.md) 中的说明运行此作业. @@ -153,7 +153,7 @@ sink { } ``` -### 精确一次 : +### 精确一次 > 为了准确的书写场景，我们保证一次准确 diff --git a/docs/zh/connector-v2/sink/Doris.md b/docs/zh/connector-v2/sink/Doris.md index bdc8152c392..d95d321a052 100644 --- a/docs/zh/connector-v2/sink/Doris.md +++ b/docs/zh/connector-v2/sink/Doris.md @@ -173,7 +173,7 @@ CREATE TABLE IF NOT EXISTS `${database}`.`${table_name}` ## 任务示例 -### 简单示例: +### 简单示例 > 下面的例子描述了向Doris写入多种数据类型，用户需要在下游创建对应的表。 @@ -231,7 +231,7 @@ sink { } ``` -### CDC（监听数据变更捕获）事件： +### CDC（监听数据变更捕获）事件 > 本示例定义了一个SeaTunnel同步任务，通过FakeSource自动生成数据并发送给Doris Sink，FakeSource使用schema、score（int类型）模拟CDC数据，Doris需要创建一个名为test.e2e_table_sink的sink任务及其对应的表 。 @@ -348,22 +348,4 @@ sink { ## 变更日志 -### 2.3.0-beta 2022-10-20 - -- 添加 Doris sink连接器 - -### Next version - -- [Improve] Change Doris Config Prefix [3856](https://github.com/apache/seatunnel/pull/3856) - -- [Improve] Refactor some Doris Sink code as well as support 2pc and cdc [4235](https://github.com/apache/seatunnel/pull/4235) - -:::tip - -PR 4235 is an incompatible modification to PR 3856. Please refer to PR 4235 to use the new Doris connector - -::: - -## 变更日志 - \ No newline at end of file diff --git a/docs/zh/connector-v2/sink/Feishu.md b/docs/zh/connector-v2/sink/Feishu.md index 6456bf1eb5f..cedf166d40f 100644 --- a/docs/zh/connector-v2/sink/Feishu.md +++ b/docs/zh/connector-v2/sink/Feishu.md @@ -52,7 +52,7 @@ import ChangeLog from '../changelog/connector-http-feishu.md'; ## 任务示例 -### 简单示例: +### 简单示例 ```hocon Feishu { diff --git a/docs/zh/connector-v2/sink/HdfsFile.md b/docs/zh/connector-v2/sink/HdfsFile.md index d0e4b2f520d..5e3becf4620 100644 --- a/docs/zh/connector-v2/sink/HdfsFile.md +++ b/docs/zh/connector-v2/sink/HdfsFile.md @@ -80,7 +80,7 @@ import ChangeLog from '../changelog/connector-file-hadoop.md'; ## 任务示例 -### 简单示例: +### 简单示例 > 此示例定义了一个 SeaTunnel 同步任务，通过 FakeSource 自动生成数据并将其发送到 Hdfs。 diff --git a/docs/zh/connector-v2/sink/Iceberg.md b/docs/zh/connector-v2/sink/Iceberg.md index f130e998326..9bcf8aea238 100644 --- a/docs/zh/connector-v2/sink/Iceberg.md +++ b/docs/zh/connector-v2/sink/Iceberg.md @@ -83,7 +83,7 @@ libfb303-xxx.jar ## 任务示例 -### 简单示例: +### 简单示例 ```hocon env { @@ -128,7 +128,7 @@ sink { } ``` -### Hive Catalog: +### Hive Catalog ```hocon sink { @@ -154,7 +154,7 @@ sink { } ``` -### Hadoop catalog: +### Hadoop catalog ```hocon sink { diff --git a/docs/zh/connector-v2/sink/Kafka.md b/docs/zh/connector-v2/sink/Kafka.md index c584e3f929f..eca17e7390c 100644 --- a/docs/zh/connector-v2/sink/Kafka.md +++ b/docs/zh/connector-v2/sink/Kafka.md @@ -99,7 +99,7 @@ assign_partitions = ["shoe", "clothing"] ## 任务示例 -### 简单: +### 简单 > 此示例展示了如何定义一个 SeaTunnel 同步任务，该任务能够通过 FakeSource 自动产生数据并将其发送到 Kafka Sink。在这个例子中，FakeSource 会生成总共 16 行数据（`row.num=16`），每一行都包含两个字段，即 `name`（字符串类型）和 `age`（整型）。最终，这些数据将被发送到名为 test_topic 的 topic 中，因此该 topic 也将包含 16 行数据。 > 如果你还未安装和部署 SeaTunnel，你需要参照 [安装SeaTunnel](../../start-v2/locally/deployment.md) 的指南来进行安装和部署。完成安装和部署后，你可以按照 [快速开始使用 SeaTunnel 引擎](../../start-v2/locally/quick-start-seatunnel-engine.md) 的指南来运行任务。 diff --git a/docs/zh/connector-v2/sink/Kudu.md b/docs/zh/connector-v2/sink/Kudu.md index b28225bab47..a812b5037ec 100644 --- a/docs/zh/connector-v2/sink/Kudu.md +++ b/docs/zh/connector-v2/sink/Kudu.md @@ -57,7 +57,7 @@ import ChangeLog from '../changelog/connector-kudu.md'; ## 任务示例 -### 简单示例: +### 简单示例 > 以下示例引用了FakeSource kudu写入表kudu_sink_table diff --git a/docs/zh/connector-v2/sink/Mysql.md b/docs/zh/connector-v2/sink/Mysql.md index ed69109485e..d8e8e1c0122 100644 --- a/docs/zh/connector-v2/sink/Mysql.md +++ b/docs/zh/connector-v2/sink/Mysql.md @@ -100,7 +100,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单的例子: +### 简单的例子 >此示例定义了一个SeaTunnel同步任务，该任务通过FakeSource自动生成数据并将其发送到JDBC Sink。FakeSource总共生成16行数据（row.num=16），每行有两个字段，name（字符串类型）和age（int类型）。最终的目标表是test_table，表中也将有16行数据。在运行此作业之前，您需要在mysql中创建数据库测试表test_table。如果您尚未安装和部署SeaTunnel，则需要按照[安装SeaTunnel]（../../start-v2/local/deployment.md）中的说明安装和部署SeaTunnel。然后按照[快速启动SeaTunnel引擎]（../../Start-v2/locale/Quick-Start SeaTunnel Engine.md）中的说明运行此作业。 @@ -165,7 +165,7 @@ sink { } ``` -### 精确一次： +### 精确一次 为了准确的书写场景，我们保证精确一次 diff --git a/docs/zh/connector-v2/sink/OceanBase.md b/docs/zh/connector-v2/sink/OceanBase.md index 94288aafc51..172a9a978c9 100644 --- a/docs/zh/connector-v2/sink/OceanBase.md +++ b/docs/zh/connector-v2/sink/OceanBase.md @@ -98,7 +98,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例: +### 简单示例 > 此示例定义了一个SeaTunnel同步任务，该任务通过FakeSource自动生成数据并将其发送到JDBC Sink。FakeSource总共生成16行数据（row.num=16），每行有两个字段，name（字符串类型）和age（int类型）。最终的目标表是test_table，表中也将有16行数据。在运行此作业之前，您需要在mysql中创建数据库测试和表test_table。如果您尚未安装和部署SeaTunnel，则需要按照[安装SeaTunnel]（../../start-v2/local/deployment.md）中的说明安装和部署SeaTunnel。然后按照[快速启动SeaTunnel引擎]（../../Start-v2/locale/Quick-Start-SeaTunnel-Engine.md）中的说明运行此作业。 diff --git a/docs/zh/connector-v2/sink/Oracle.md b/docs/zh/connector-v2/sink/Oracle.md index 4a3dab419d5..ba5027d1a51 100644 --- a/docs/zh/connector-v2/sink/Oracle.md +++ b/docs/zh/connector-v2/sink/Oracle.md @@ -98,7 +98,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单的例子: +### 简单的例子 >此示例定义了一个SeaTunnel同步任务，该任务通过FakeSource自动生成数据并将其发送到JDBC Sink。FakeSource总共生成16行数据（row.num=16），每行有两个字段，name（字符串类型）和age（int类型）。最终的目标表是test_table，表中也将有16行数据。在运行此作业之前，您需要在Oracle中创建测试数据库和表test_table。如果您尚未安装和部署SeaTunnel，则需要按照[安装SeaTunnel]（../../start-v2/local/deployment.md）中的说明安装和部署SeaTunnel。然后按照[快速启动SeaTunnel引擎]（../../Start-v2/locale/Quick-Start-SeaTunnel-Engine.md）中的说明运行此作业。 @@ -162,7 +162,7 @@ sink { } ``` -### 精确一次： +### 精确一次 为了准确的写入场景，我们保证一次准确 diff --git a/docs/zh/connector-v2/sink/PostgreSql.md b/docs/zh/connector-v2/sink/PostgreSql.md index 9ca73ce2f55..a08cbae51dc 100644 --- a/docs/zh/connector-v2/sink/PostgreSql.md +++ b/docs/zh/connector-v2/sink/PostgreSql.md @@ -137,7 +137,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例： +### 简单示例 > 此示例定义了一个 SeaTunnel 同步任务，通过 FakeSource 自动生成数据并将其发送到 JDBC Sink。FakeSource 生成总共 16 行数据（`row.num=16`），每行有两个字段，`name`（字符串类型）和 `age`（整数类型）。最终目标表 `test_table` 也将包含 16 行数据。在运行此作业之前，您需要在 PostgreSQL 中创建数据库 `test` 和表 `test_table`。如果您还未安装和部署 SeaTunnel，请按照 [安装 SeaTunnel](../../start-v2/locally/deployment.md) 中的说明进行安装和部署。然后按照 [快速开始 SeaTunnel 引擎](../../start-v2/locally/quick-start-seatunnel-engine.md) 中的说明运行此作业。 @@ -204,7 +204,7 @@ sink { } ``` -### 精确一次： +### 精确一次 > 对于精确写入场景，我们保证精确一次。 diff --git a/docs/zh/connector-v2/sink/Pulsar.md b/docs/zh/connector-v2/sink/Pulsar.md index 3fba01c5501..74c6734a969 100644 --- a/docs/zh/connector-v2/sink/Pulsar.md +++ b/docs/zh/connector-v2/sink/Pulsar.md @@ -123,7 +123,7 @@ Pulsar 服务的 Service URL 提供程序。要使用客户端库连接到 Pulsa ## 任务示例 -### 简单: +### 简单 > 该示例定义了一个 SeaTunnel 同步任务，该任务通过 FakeSource 自动生成数据并将其发送到 Pulsar Sink。FakeSource 总共生成 16 行数据 （row.num=16），每行有两个字段，name（字符串类型）和 age（int 类型）。最终目标主题是test_topic主题中还将有 16 行数据。 如果您尚未安装和部署 SeaTunnel，则需要按照[安装Seatunnel](../../start-v2/locally/deployment.md) SeaTunnel 中的说明安装和部署 SeaTunnel。然后按照 [SeaTunnel 引擎快速入门](../../start-v2/locally/quick-start-seatunnel-engine.md)中的说明运行此作业。 diff --git a/docs/zh/connector-v2/sink/Redshift.md b/docs/zh/connector-v2/sink/Redshift.md index f5eaceea154..12710198a93 100644 --- a/docs/zh/connector-v2/sink/Redshift.md +++ b/docs/zh/connector-v2/sink/Redshift.md @@ -59,7 +59,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例: +### 简单示例 ``` sink { diff --git a/docs/zh/connector-v2/sink/S3File.md b/docs/zh/connector-v2/sink/S3File.md index 2636475fb62..7b7afd5d657 100644 --- a/docs/zh/connector-v2/sink/S3File.md +++ b/docs/zh/connector-v2/sink/S3File.md @@ -313,7 +313,7 @@ Sink 插件通用参数，请参考 [Sink 通用选项](../sink-common-options.m ## 示例 -### 简单示例： +### 简单示例 > 此示例定义了一个 SeaTunnel 同步任务，通过 FakeSource 自动生成数据并将其发送到 S3File Sink。FakeSource 总共生成 16 行数据 (row.num=16)，每行有两个字段，name (字符串类型) 和 age (int 类型)。最终的目标 s3 目录将创建一个文件，并将所有数据写入其中。 > 在运行此作业之前，您需要创建 s3 路径：/seatunnel/text。如果您尚未安装和部署 SeaTunnel，您需要按照 [安装 SeaTunnel](../../start-v2/locally/deployment.md) 中的说明安装和部署 SeaTunnel。然后按照 [使用 SeaTunnel Engine 快速入门](../../start-v2/locally/quick-start-seatunnel-engine.md) 中的说明运行此作业。 diff --git a/docs/zh/connector-v2/sink/SelectDB-Cloud.md b/docs/zh/connector-v2/sink/SelectDB-Cloud.md index 306631bb0b9..3e536c44531 100644 --- a/docs/zh/connector-v2/sink/SelectDB-Cloud.md +++ b/docs/zh/connector-v2/sink/SelectDB-Cloud.md @@ -80,7 +80,7 @@ SelectDB Cloud 接收器连接器的内部实现是在批量缓存后上传数 ## 任务示例 -### 简单示例： +### 简单示例 > 以下示例描述了将多种数据类型写入 SelectDBCloud，用户需要在下游创建相应的表 diff --git a/docs/zh/connector-v2/sink/Slack.md b/docs/zh/connector-v2/sink/Slack.md index 3f8b9d1226f..f5501bd6d4e 100644 --- a/docs/zh/connector-v2/sink/Slack.md +++ b/docs/zh/connector-v2/sink/Slack.md @@ -36,7 +36,7 @@ import ChangeLog from '../changelog/connector-slack.md'; ## 任务示例 -### 简单示例: +### 简单示例 ```hocon sink { diff --git a/docs/zh/connector-v2/sink/Snowflake.md b/docs/zh/connector-v2/sink/Snowflake.md index a42de17d2b9..21437c9e02d 100644 --- a/docs/zh/connector-v2/sink/Snowflake.md +++ b/docs/zh/connector-v2/sink/Snowflake.md @@ -77,7 +77,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例： +### 简单示例 > 此示例定义了一个SeaTunnel同步任务，通过FakeSource自动生成数据并发送到JDBC Sink。FakeSource总共生成16行数据（row.num=16），每行有两个字段，name（字符串类型）和age（int类型）。最终目标表`test_table`中也将有16行数据。在运行此作业之前，您需要在Snowflake数据库中创建数据库`test`和表`test_table`。如果您尚未安装和部署SeaTunnel，请按照[安装SeaTunnel](../../start-v2/locally/deployment.md)中的说明进行安装和部署。然后按照[使用SeaTunnel Engine快速入门](../../start-v2/locally/quick-start-seatunnel-engine.md)中的说明运行此作业。 diff --git a/docs/zh/connector-v2/sink/SqlServer.md b/docs/zh/connector-v2/sink/SqlServer.md index 4a9fe1ebb8f..dd80c11d62c 100644 --- a/docs/zh/connector-v2/sink/SqlServer.md +++ b/docs/zh/connector-v2/sink/SqlServer.md @@ -94,7 +94,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例： +### 简单示例 > 这是一个读取 SQL Server 数据并直接插入到另一个表的示例 diff --git a/docs/zh/connector-v2/sink/Vertica.md b/docs/zh/connector-v2/sink/Vertica.md index e8800722b1c..e52d466d2a6 100644 --- a/docs/zh/connector-v2/sink/Vertica.md +++ b/docs/zh/connector-v2/sink/Vertica.md @@ -94,7 +94,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单示例： +### 简单示例 > 此示例定义了一个 SeaTunnel 同步任务，通过 FakeSource 自动生成数据并发送到 JDBC Sink。FakeSource 总共生成 16 行数据（row.num=16），每行有两个字段，name（字符串类型）和 age（int 类型）。最终目标表 test_table 中也将有 16 行数据。在运行此任务之前，您需要在 Vertica 中创建数据库 test 和表 test_table。如果您尚未安装和部署 SeaTunnel，请按照 [安装 SeaTunnel](../../start-v2/locally/deployment.md) 中的说明进行安装和部署。然后按照 [使用 SeaTunnel Engine 快速开始](../../start-v2/locally/quick-start-seatunnel-engine.md) 中的说明运行此任务。 @@ -159,7 +159,7 @@ sink { } ``` -### 精确一次： +### 精确一次 > 对于精确写入场景，我们保证精确一次语义。 diff --git a/docs/zh/connector-v2/source/DB2.md b/docs/zh/connector-v2/source/DB2.md index 7b7e161f80c..7a40e39c1ed 100644 --- a/docs/zh/connector-v2/source/DB2.md +++ b/docs/zh/connector-v2/source/DB2.md @@ -88,7 +88,7 @@ import ChangeLog from '../changelog/connector-jdbc.md'; ## 任务示例 -### 简单: +### 简单 > 此示例以单并行方式在您的测试“database”中查询类型容器（type_bin）'table'的16条数据。并查询其所有字段。您还可以指定要查询哪些字段以将最终输出到控制台。 @@ -119,9 +119,10 @@ sink { } ``` -### 并行度： +### 并行 > 并行读取您的查询表，利用您配置的分片字段以及分片数据。若您希望读取整个表，您可以采取此操作。 + ``` source { Jdbc { @@ -140,7 +141,7 @@ source { } ``` -### 并行边界: +### 并行的同时指定边界 > 在查询的上下界范围内指定数据更为高效。根据您配置的上下边界读取数据源，效率更佳。 diff --git a/docs/zh/connector-v2/source/FakeSource.md b/docs/zh/connector-v2/source/FakeSource.md index 358b57ea7fa..41509358aba 100644 --- a/docs/zh/connector-v2/source/FakeSource.md +++ b/docs/zh/connector-v2/source/FakeSource.md @@ -71,7 +71,7 @@ FakeSource 是一个虚拟数据源，它根据用户定义的 schema 数据结 ## 任务示例 -### 简单示例： +### 简单示例 > 此示例随机生成指定类型的数据。如果您想了解如何声明字段类型，请点击 [这里](../../concept/schema-feature.md#how-to-declare-type-supported)。 @@ -148,7 +148,7 @@ source { } ``` -### 自定义数据内容简单示例： +### 自定义数据内容简单示例 > 这是一个自定义数据源信息的示例，定义每条数据是添加还是删除修改操作，并定义每个字段存储的内容 @@ -198,7 +198,7 @@ source { > 由于 [HOCON](https://github.com/lightbend/config/blob/main/HOCON.md) 规范的限制，用户无法直接创建字节序列对象。FakeSource 使用字符串来分配 `bytes` 类型的值。在上面的示例中，`bytes` 类型字段被分配了 `"bWlJWmo="`，这是通过 **base64** 编码的 "miIZj"。因此，在为 `bytes` 类型字段赋值时，请使用 **base64** 编码的字符串。 -### 指定数据数量简单示例： +### 指定数据数量简单示例 > 此案例指定生成数据的数量以及生成值的长度 @@ -248,7 +248,7 @@ FakeSource { } ``` -### 模板数据简单示例： +### 模板数据简单示例 > 根据指定模板随机生成 @@ -285,7 +285,7 @@ FakeSource { } ``` -### 范围数据简单示例： +### 范围数据简单示例 > 在指定的数据生成范围内随机生成 diff --git a/docs/zh/connector-v2/source/HdfsFile.md b/docs/zh/connector-v2/source/HdfsFile.md index 4fa69937482..cd06a3dbd9a 100644 --- a/docs/zh/connector-v2/source/HdfsFile.md +++ b/docs/zh/connector-v2/source/HdfsFile.md @@ -143,7 +143,7 @@ import ChangeLog from '../changelog/connector-file-hadoop.md'; ## 任务示例 -### 简单示例: +### 简单示例 > 此示例定义了一个 SeaTunnel 同步任务，从 Hdfs 中读取数据并将其发送到 Hdfs。 diff --git a/docs/zh/connector-v2/source/Mysql.md b/docs/zh/connector-v2/source/Mysql.md index 90156b954f6..fab85f17b92 100644 --- a/docs/zh/connector-v2/source/Mysql.md +++ b/docs/zh/connector-v2/source/Mysql.md @@ -159,7 +159,7 @@ JDBC 源连接器支持从表中并行读取数据。SeaTunnel 将使用特定 ## 任务示例 -### 简单的例子: +### 简单的例子 > 这个示例以单线程并行的方式查询测试数据库中 `type_bin` 为 'table' 的16条数据，并查询所有字段。你也可以指定查询哪些字段，并将最终结果输出到控制台。 @@ -246,7 +246,7 @@ sink { } ``` -### 并行边界： +### 并行的同时指定边界 > 指定数据的上下边界查询会更加高效。根据您配置的上下边界读取数据源会更高效。 @@ -273,7 +273,7 @@ source { } ``` -### 多表读取： +### 多表读取 ***配置 `table_list` 将启用自动拆分，您可以配置 `split.*` 来调整拆分策略*** diff --git a/docs/zh/connector-v2/source/PostgreSQL.md b/docs/zh/connector-v2/source/PostgreSQL.md index 5c71459fa39..591166706b4 100644 --- a/docs/zh/connector-v2/source/PostgreSQL.md +++ b/docs/zh/connector-v2/source/PostgreSQL.md @@ -165,7 +165,7 @@ JDBC 源连接器支持从表中并行读取数据。SeaTunnel 将使用某些 ## 任务示例 -### 简单示例： +### 简单示例 > 此示例查询您测试 "database" 中 type_bin 为 'table' 的 16 条数据，并以单并行方式查询其所有字段。您还可以指定要查询的字段，以便最终输出到控制台。 @@ -247,7 +247,7 @@ sink { } ``` -### 并行边界： +### 并行的同时指定边界 > 在查询中指定上下边界内的数据更为高效。根据您配置的上下边界读取数据源将更为高效。 @@ -270,7 +270,7 @@ source{ } ``` -### 多表读取： +### 多表读取 ***配置 `table_list` 将启用自动拆分，您可以配置 `split.*` 来调整拆分策略*** diff --git a/docs/zh/connector-v2/source/Prometheus.md b/docs/zh/connector-v2/source/Prometheus.md index 42c5dbafcb2..108f95bc25e 100644 --- a/docs/zh/connector-v2/source/Prometheus.md +++ b/docs/zh/connector-v2/source/Prometheus.md @@ -98,7 +98,7 @@ http请求失败，最大重试回退时间(毫秒) ## 示例 -### Instant: +### Instant ```hocon source { diff --git a/seatunnel-ci-tools/src/test/java/org/apache/seatunnel/api/file/MarkdownTest.java b/seatunnel-ci-tools/src/test/java/org/apache/seatunnel/api/file/MarkdownTest.java index d2bdd11e8c2..19be677b0cc 100644 --- a/seatunnel-ci-tools/src/test/java/org/apache/seatunnel/api/file/MarkdownTest.java +++ b/seatunnel-ci-tools/src/test/java/org/apache/seatunnel/api/file/MarkdownTest.java @@ -163,6 +163,36 @@ public void testPrimaryHeadersHaveNoTextAbove() { }); } + @Test + public void testAllHeaderNotEndWithSymbol() { + connectorsDirectories.forEach( + docsDirectory -> { + try (Stream paths = Files.walk(docsDirectory)) { + List mdFiles = + paths.filter(Files::isRegularFile) + .filter(path -> path.toString().endsWith(".md")) + .collect(Collectors.toList()); + + for (Path mdPath : mdFiles) { + List lines = Files.readAllLines(mdPath, StandardCharsets.UTF_8); + for (String line : lines) { + String trimmedLine = line.trim(); + if (trimmedLine.startsWith("#")) { + if (trimmedLine.endsWith(":") || trimmedLine.endsWith("：")) { + Assertions.fail( + String.format( + "The header in the file %s ends with a symbol. Header content: “%s”", + mdPath, trimmedLine)); + } + } + } + } + } catch (IOException e) { + throw new RuntimeException(e); + } + }); + } + @Test public void testConnectorDocWithChangeLogFlagAndFile() { Pattern importPattern =