-
Notifications
You must be signed in to change notification settings - Fork 3k
Implement Iceberg Kafka Connect with Delta Writer Support in DV Mode for in-batch deduplication #14797
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
t3hw
wants to merge
10
commits into
apache:main
Choose a base branch
from
nanit:cdc-support-with-DV
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Implement Iceberg Kafka Connect with Delta Writer Support in DV Mode for in-batch deduplication #14797
Changes from all commits
Commits
Show all changes
10 commits
Select commit
Hold shift + click to select a range
0553f6a
Iceberg Kafka Connect, DV Mode - with and without Upsert
t3hw d27bd2e
set useDV->true by default.
t3hw f2b9219
update readme
t3hw fc28332
Merge branch 'apache:main' into cdc-support-with-DV
t3hw 3d4c3eb
Change the fromString translation method to align it more closely to …
t3hw 835529b
Merge remote-tracking branch 'origin/main' into cdc-support-with-DV
t3hw a440ece
Add support for nested cdc fields
t3hw 79a1cd8
spotless apply
t3hw 6e5d469
Remove the useDv parameter in favor of automatic detection of table f…
t3hw 6a47746
Merge remote-tracking branch 'origin/main' into cdc-support-with-DV
t3hw File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
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
145 changes: 145 additions & 0 deletions
145
...-connect/kafka-connect/src/main/java/org/apache/iceberg/connect/data/BaseDeltaWriter.java
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 +1,145 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one | ||
| * or more contributor license agreements. See the NOTICE file | ||
| * distributed with this work for additional information | ||
| * regarding copyright ownership. The ASF licenses this file | ||
| * to you under the Apache License, Version 2.0 (the | ||
| * "License"); you may not use this file except in compliance | ||
| * with the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, | ||
| * software distributed under the License is distributed on an | ||
| * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY | ||
| * KIND, either express or implied. See the License for the | ||
| * specific language governing permissions and limitations | ||
| * under the License. | ||
| */ | ||
| package org.apache.iceberg.connect.data; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.Set; | ||
| import org.apache.iceberg.FileFormat; | ||
| import org.apache.iceberg.PartitionKey; | ||
| import org.apache.iceberg.PartitionSpec; | ||
| import org.apache.iceberg.Schema; | ||
| import org.apache.iceberg.StructLike; | ||
| import org.apache.iceberg.data.InternalRecordWrapper; | ||
| import org.apache.iceberg.data.Record; | ||
| import org.apache.iceberg.deletes.DeleteGranularity; | ||
| import org.apache.iceberg.io.BaseTaskWriter; | ||
| import org.apache.iceberg.io.FileIO; | ||
| import org.apache.iceberg.io.FileWriterFactory; | ||
| import org.apache.iceberg.io.OutputFileFactory; | ||
| import org.apache.iceberg.relocated.com.google.common.collect.Sets; | ||
| import org.apache.iceberg.types.TypeUtil; | ||
|
|
||
| abstract class BaseDeltaWriter extends BaseTaskWriter<Record> { | ||
|
|
||
| private final Schema schema; | ||
| private final Schema deleteSchema; | ||
| private final InternalRecordWrapper wrapper; | ||
| private final InternalRecordWrapper keyWrapper; | ||
| private final RecordProjection keyProjection; | ||
| private final boolean upsert; | ||
| private final String[] cdcField; | ||
|
|
||
| BaseDeltaWriter( | ||
| PartitionSpec spec, | ||
| FileFormat format, | ||
| FileWriterFactory<Record> writerFactory, | ||
| OutputFileFactory fileFactory, | ||
| FileIO io, | ||
| long targetFileSize, | ||
| Schema schema, | ||
| Set<Integer> identifierFieldIds, | ||
| boolean upsert, | ||
| boolean useDv, | ||
| String cdcField) { | ||
| super(spec, format, writerFactory, fileFactory, io, targetFileSize, useDv); | ||
|
|
||
| this.schema = schema; | ||
| this.deleteSchema = TypeUtil.select(schema, Sets.newHashSet(identifierFieldIds)); | ||
| this.wrapper = new InternalRecordWrapper(schema.asStruct()); | ||
| this.keyWrapper = new InternalRecordWrapper(deleteSchema.asStruct()); | ||
| this.keyProjection = RecordProjection.create(schema, deleteSchema); | ||
| this.upsert = upsert; | ||
|
|
||
| if (cdcField == null || cdcField.isEmpty()) { | ||
| throw new IllegalArgumentException("CDC field must be provided for delta writer"); | ||
| } | ||
| this.cdcField = cdcField.split("\\."); | ||
| } | ||
|
|
||
| abstract RowDataDeltaWriter route(Record row); | ||
|
|
||
| @Override | ||
| public void write(Record row) throws IOException { | ||
|
|
||
| Operation op = Operation.fromString(getCdcOpFromRow(row)); | ||
| RowDataDeltaWriter writer = route(row); | ||
|
|
||
| switch (op) { | ||
| case INSERT: | ||
| writer.write(row); | ||
| break; | ||
| case UPDATE: | ||
| if (upsert) { | ||
| writer.deleteKey(keyProjection.wrap(row)); | ||
| } else { | ||
| writer.delete(row); | ||
| } | ||
| writer.write(row); | ||
| break; | ||
| case DELETE: | ||
| if (upsert) { | ||
| writer.deleteKey(keyProjection.wrap(row)); | ||
| } else { | ||
| writer.delete(row); | ||
| } | ||
| break; | ||
|
|
||
| default: | ||
| throw new UnsupportedOperationException("Unknown row kind: " + op); | ||
| } | ||
| } | ||
|
|
||
| private String getCdcOpFromRow(Record row) { | ||
| Record currentFieldLookup = row; | ||
| for (String field : cdcField) { | ||
| Object value = currentFieldLookup.getField(field); | ||
| if (value == null) { | ||
| throw new IllegalArgumentException("CDC field " + String.join(".", cdcField) + " is null"); | ||
| } | ||
| if (value instanceof String) { | ||
| return (String) value; | ||
| } else { | ||
| currentFieldLookup = (Record) value; | ||
| } | ||
| } | ||
| throw new IllegalArgumentException( | ||
| "CDC field " + String.join(".", cdcField) + " is not a string"); | ||
| } | ||
|
|
||
| public InternalRecordWrapper getWrapper() { | ||
| return wrapper; | ||
| } | ||
|
|
||
| protected class RowDataDeltaWriter extends BaseEqualityDeltaWriter { | ||
|
|
||
| RowDataDeltaWriter(PartitionKey partition) { | ||
| super(partition, schema, deleteSchema, DeleteGranularity.FILE, dvFileWriter()); | ||
| } | ||
|
|
||
| @Override | ||
| protected StructLike asStructLike(Record data) { | ||
| return wrapper.wrap(data); | ||
| } | ||
|
|
||
| @Override | ||
| protected StructLike asStructLikeKey(Record data) { | ||
| return keyWrapper.wrap(data); | ||
| } | ||
| } | ||
| } | ||
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.