ruanwenjun commented on code in PR #5929:
URL: https://github.com/apache/seatunnel/pull/5929#discussion_r1411634652
##########
docs/en/connector-v2/sink/Hive.md:
##########
@@ -157,6 +157,56 @@ sink {
}
```
+### example 2
+
+We have multiple source table like this:
+
+```bash
+create table test_1(
+)
+PARTITIONED BY (xx);
+
+create table test_2(
+)
+PARTITIONED BY (xx);
+...
+```
+
+We need read data from these source tables and write to another tables:
+
+The job config file can like this:
+
+```
+env {
+ # You can set flink configuration here
+ parallelism = 3
+ job.name="test_hive_source_to_hive"
+}
+
+source {
+ Hive {
+ tables_configs = [
+ {
+ table_name = "test_hive.test_1"
+ metastore_uri = "thrift://ctyun7:9083"
Review Comment:
Yes, we can support different thrif server.
##########
seatunnel-connectors-v2/connector-hive/src/main/java/org/apache/seatunnel/connectors/seatunnel/hive/sink/HiveSink.java:
##########
@@ -20,110 +20,81 @@
import org.apache.seatunnel.shade.com.typesafe.config.Config;
import org.apache.seatunnel.shade.com.typesafe.config.ConfigValueFactory;
-import org.apache.seatunnel.api.common.PrepareFailException;
-import org.apache.seatunnel.api.common.SeaTunnelAPIErrorCode;
+import org.apache.seatunnel.api.common.JobContext;
+import org.apache.seatunnel.api.configuration.ReadonlyConfig;
+import org.apache.seatunnel.api.serialization.DefaultSerializer;
+import org.apache.seatunnel.api.serialization.Serializer;
import org.apache.seatunnel.api.sink.SeaTunnelSink;
import org.apache.seatunnel.api.sink.SinkAggregatedCommitter;
-import org.apache.seatunnel.common.config.CheckConfigUtil;
-import org.apache.seatunnel.common.config.CheckResult;
-import org.apache.seatunnel.common.constants.PluginType;
+import org.apache.seatunnel.api.sink.SinkWriter;
+import org.apache.seatunnel.api.table.catalog.CatalogTable;
+import org.apache.seatunnel.api.table.type.SeaTunnelRow;
import org.apache.seatunnel.common.exception.CommonErrorCodeDeprecated;
import org.apache.seatunnel.connectors.seatunnel.file.config.FileFormat;
-import org.apache.seatunnel.connectors.seatunnel.file.config.HadoopConf;
-import
org.apache.seatunnel.connectors.seatunnel.file.hdfs.sink.BaseHdfsFileSink;
+import org.apache.seatunnel.connectors.seatunnel.file.sink.BaseFileSinkWriter;
import
org.apache.seatunnel.connectors.seatunnel.file.sink.commit.FileAggregatedCommitInfo;
import
org.apache.seatunnel.connectors.seatunnel.file.sink.commit.FileCommitInfo;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.config.FileSinkConfig;
+import org.apache.seatunnel.connectors.seatunnel.file.sink.state.FileSinkState;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.util.FileSystemUtils;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.WriteStrategy;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.writer.WriteStrategyFactory;
import
org.apache.seatunnel.connectors.seatunnel.hive.commit.HiveSinkAggregatedCommitter;
-import org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig;
+import org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConstants;
+import org.apache.seatunnel.connectors.seatunnel.hive.config.HiveHadoopConfig;
import
org.apache.seatunnel.connectors.seatunnel.hive.exception.HiveConnectorErrorCode;
import
org.apache.seatunnel.connectors.seatunnel.hive.exception.HiveConnectorException;
+import
org.apache.seatunnel.connectors.seatunnel.hive.source.config.HiveSourceOptions;
+import org.apache.seatunnel.connectors.seatunnel.hive.utils.HiveTableUtils;
-import org.apache.commons.lang3.tuple.Pair;
import org.apache.hadoop.hive.metastore.api.FieldSchema;
import org.apache.hadoop.hive.metastore.api.Table;
-import com.google.auto.service.AutoService;
-
-import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.List;
import java.util.Map;
import java.util.Optional;
import java.util.stream.Collectors;
-import static
org.apache.hadoop.fs.CommonConfigurationKeysPublic.FS_DEFAULT_NAME_KEY;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.FIELD_DELIMITER;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.FILE_FORMAT_TYPE;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.FILE_NAME_EXPRESSION;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.FILE_PATH;
-import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.HAVE_PARTITION;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.IS_PARTITION_FIELD_WRITE_IN_FILE;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.PARTITION_BY;
-import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.PARTITION_DIR_EXPRESSION;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.ROW_DELIMITER;
import static
org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig.SINK_COLUMNS;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.METASTORE_URI;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.ORC_OUTPUT_FORMAT_CLASSNAME;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.PARQUET_OUTPUT_FORMAT_CLASSNAME;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.TABLE_NAME;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.TEXT_OUTPUT_FORMAT_CLASSNAME;
-
-@AutoService(SeaTunnelSink.class)
-public class HiveSink extends BaseHdfsFileSink {
- private String dbName;
- private String tableName;
- private Table tableInformation;
- @Override
- public String getPluginName() {
- return "Hive";
+public class HiveSink
Review Comment:
Thanks done.
##########
seatunnel-connectors-v2/connector-hive/src/main/java/org/apache/seatunnel/connectors/seatunnel/hive/sink/HiveSinkFactory.java:
##########
@@ -17,28 +17,100 @@
package org.apache.seatunnel.connectors.seatunnel.hive.sink;
+import org.apache.seatunnel.api.configuration.ReadonlyConfig;
import org.apache.seatunnel.api.configuration.util.OptionRule;
+import org.apache.seatunnel.api.sink.SinkReplaceNameConstant;
+import org.apache.seatunnel.api.sink.SupportMultiTableSink;
+import org.apache.seatunnel.api.table.catalog.CatalogTable;
+import org.apache.seatunnel.api.table.catalog.TableIdentifier;
+import org.apache.seatunnel.api.table.connector.TableSink;
import org.apache.seatunnel.api.table.factory.Factory;
import org.apache.seatunnel.api.table.factory.TableSinkFactory;
-import org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig;
+import org.apache.seatunnel.api.table.factory.TableSinkFactoryContext;
+import org.apache.seatunnel.api.table.type.SeaTunnelRow;
+import org.apache.seatunnel.connectors.seatunnel.file.config.BaseSinkConfig;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.commit.FileAggregatedCommitInfo;
+import
org.apache.seatunnel.connectors.seatunnel.file.sink.commit.FileCommitInfo;
+import org.apache.seatunnel.connectors.seatunnel.file.sink.state.FileSinkState;
+import org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConstants;
import com.google.auto.service.AutoService;
-import static
org.apache.seatunnel.connectors.seatunnel.hive.config.HiveConfig.ABORT_DROP_PARTITION_METADATA;
+import java.util.HashMap;
+import java.util.Map;
@AutoService(Factory.class)
-public class HiveSinkFactory implements TableSinkFactory {
- @Override
- public String factoryIdentifier() {
- return "Hive";
- }
+public class HiveSinkFactory
+ implements TableSinkFactory<
+ SeaTunnelRow, FileSinkState, FileCommitInfo,
FileAggregatedCommitInfo>,
+ SupportMultiTableSink {
Review Comment:
done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
