Implement databricks connector as a copy destination #5748
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| package io.airbyte.integrations.destination.databricks; | ||
|
|
||
| import com.amazonaws.services.s3.AmazonS3; | ||
| import com.fasterxml.jackson.databind.ObjectMapper; | ||
| import io.airbyte.db.jdbc.JdbcDatabase; | ||
| import io.airbyte.integrations.destination.ExtendedNameTransformer; | ||
| import io.airbyte.integrations.destination.jdbc.SqlOperations; | ||
| import io.airbyte.integrations.destination.jdbc.copy.StreamCopier; | ||
| import io.airbyte.integrations.destination.jdbc.copy.s3.S3Config; | ||
| import io.airbyte.integrations.destination.s3.S3DestinationConfig; | ||
| import io.airbyte.integrations.destination.s3.parquet.S3ParquetFormatConfig; | ||
| import io.airbyte.integrations.destination.s3.parquet.S3ParquetWriter; | ||
| import io.airbyte.integrations.destination.s3.writer.S3WriterFactory; | ||
| import io.airbyte.protocol.models.AirbyteRecordMessage; | ||
| import io.airbyte.protocol.models.AirbyteStream; | ||
| import io.airbyte.protocol.models.ConfiguredAirbyteStream; | ||
| import java.sql.Timestamp; | ||
| import java.util.UUID; | ||
| import org.slf4j.Logger; | ||
| import org.slf4j.LoggerFactory; | ||
|
|
||
| /** | ||
| * This implementation is similar to {@link io.airbyte.integrations.destination.jdbc.copy.s3.S3StreamCopier}. | ||
| * The difference is that this implementation creates Parquet staging files, instead of CSV ones. | ||
| */ | ||
| public class DatabricksStreamCopier implements StreamCopier { | ||
|
There was a problem hiding this comment. We can focus on implementing the methods in this class to transfer the data from S3 to Databricks. |
||
|
|
||
| private static final Logger LOGGER = LoggerFactory.getLogger(DatabricksStreamCopier.class); | ||
| private static final ObjectMapper MAPPER = new ObjectMapper(); | ||
|
|
||
| private final AmazonS3 s3Client; | ||
| private final S3Config s3Config; | ||
| private final String tmpTableName; | ||
| private final AirbyteStream stream; | ||
| private final JdbcDatabase db; | ||
| private final ExtendedNameTransformer nameTransformer; | ||
| private final SqlOperations sqlOperations; | ||
| private final S3ParquetWriter parquetWriter; | ||
|
|
||
| public DatabricksStreamCopier(String stagingFolder, | ||
| String schema, | ||
| ConfiguredAirbyteStream configuredStream, | ||
| AmazonS3 s3Client, | ||
| JdbcDatabase db, | ||
| S3Config s3Config, | ||
| ExtendedNameTransformer nameTransformer, | ||
| SqlOperations sqlOperations, | ||
| S3WriterFactory writerFactory, | ||
| Timestamp uploadTime) throws Exception { | ||
| this.stream = configuredStream.getStream(); | ||
| this.db = db; | ||
| this.nameTransformer = nameTransformer; | ||
| this.sqlOperations = sqlOperations; | ||
| this.tmpTableName = nameTransformer.getTmpTableName(stream.getName()); | ||
| this.s3Client = s3Client; | ||
| this.s3Config = s3Config; | ||
| this.parquetWriter = (S3ParquetWriter) writerFactory | ||
| .create(getS3DestinationConfig(s3Config, stagingFolder), s3Client, configuredStream, uploadTime); | ||
| } | ||
|
|
||
| @Override | ||
| public void write(UUID id, AirbyteRecordMessage recordMessage) throws Exception { | ||
| parquetWriter.write(id, recordMessage); | ||
| } | ||
|
|
||
| @Override | ||
| public void closeStagingUploader(boolean hasFailed) throws Exception { | ||
| parquetWriter.close(hasFailed); | ||
| } | ||
|
|
||
| @Override | ||
| public void createTemporaryTable() throws Exception { | ||
|
|
||
| } | ||
|
|
||
| @Override | ||
| public void copyStagingFileToTemporaryTable() throws Exception { | ||
|
|
||
| } | ||
|
|
||
| @Override | ||
| public void createDestinationSchema() throws Exception { | ||
|
|
||
| } | ||
|
|
||
| @Override | ||
| public String createDestinationTable() throws Exception { | ||
| return null; | ||
| } | ||
|
|
||
| @Override | ||
| public String generateMergeStatement(String destTableName) throws Exception { | ||
| return null; | ||
| } | ||
|
|
||
| @Override | ||
| public void removeFileAndDropTmpTable() throws Exception { | ||
|
|
||
| } | ||
|
|
||
| private S3DestinationConfig getS3DestinationConfig(S3Config s3Config, String stagingFolder) { | ||
| return new S3DestinationConfig( | ||
| s3Config.getEndpoint(), | ||
| s3Config.getBucketName(), | ||
| stagingFolder, | ||
| s3Config.getRegion(), | ||
| s3Config.getAccessKeyId(), | ||
| s3Config.getSecretAccessKey(), | ||
| // use default parquet format config | ||
| new S3ParquetFormatConfig(MAPPER.createObjectNode()) | ||
| ); | ||
| } | ||
|
|
||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| package io.airbyte.integrations.destination.databricks; | ||
|
|
||
| import com.amazonaws.services.s3.AmazonS3; | ||
| import io.airbyte.db.jdbc.JdbcDatabase; | ||
| import io.airbyte.integrations.destination.ExtendedNameTransformer; | ||
| import io.airbyte.integrations.destination.jdbc.SqlOperations; | ||
| import io.airbyte.integrations.destination.jdbc.copy.StreamCopier; | ||
| import io.airbyte.integrations.destination.jdbc.copy.StreamCopierFactory; | ||
| import io.airbyte.integrations.destination.jdbc.copy.s3.S3Config; | ||
| import io.airbyte.integrations.destination.jdbc.copy.s3.S3StreamCopier; | ||
| import io.airbyte.integrations.destination.s3.parquet.S3ParquetWriter; | ||
| import io.airbyte.integrations.destination.s3.writer.ProductionWriterFactory; | ||
| import io.airbyte.integrations.destination.s3.writer.S3WriterFactory; | ||
| import io.airbyte.protocol.models.AirbyteStream; | ||
| import io.airbyte.protocol.models.ConfiguredAirbyteStream; | ||
| import java.sql.Timestamp; | ||
|
|
||
| public class DatabricksStreamCopierFactory implements StreamCopierFactory<S3Config> { | ||
|
|
||
| @Override | ||
| public StreamCopier create(String configuredSchema, | ||
| S3Config s3Config, | ||
| String stagingFolder, | ||
| ConfiguredAirbyteStream configuredStream, | ||
| ExtendedNameTransformer nameTransformer, | ||
| JdbcDatabase db, | ||
| SqlOperations sqlOperations) { | ||
| try { | ||
| AirbyteStream stream = configuredStream.getStream(); | ||
| String schema = StreamCopierFactory.getSchema(stream, configuredSchema, nameTransformer); | ||
| AmazonS3 s3Client = S3StreamCopier.getAmazonS3(s3Config); | ||
| S3WriterFactory writerFactory = new ProductionWriterFactory(); | ||
| Timestamp uploadTimestamp = new Timestamp(System.currentTimeMillis()); | ||
|
|
||
| return new DatabricksStreamCopier( | ||
| stagingFolder, schema, configuredStream, s3Client, db, s3Config, nameTransformer, sqlOperations, writerFactory, uploadTimestamp); | ||
| } catch (Exception e) { | ||
| throw new RuntimeException(e); | ||
| } | ||
|
|
||
| } | ||
|
|
||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's depend on the s3 destination for now and DRY it later.