Skip to content

ignore-duplicate-key-error #152

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.

Sign up for GitHub

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
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

ignore-duplicate-key-error #152

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
82 changes: 82 additions & 0 deletions src/integrationTest/java/com/mongodb/kafka/connect/MongoSinkConnectorIntegrationTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,10 +49,13 @@
import org.junit.jupiter.api.Test;
import org.opentest4j.AssertionFailedError;

import com.mongodb.client.model.IndexOptions;
import com.mongodb.client.model.Indexes;
import com.mongodb.client.model.Sorts;

import com.mongodb.kafka.connect.avro.TweetMsg;
import com.mongodb.kafka.connect.mongodb.MongoKafkaTestCase;
import com.mongodb.kafka.connect.sink.MongoSinkTopicConfig;
import com.mongodb.kafka.connect.util.jmx.SinkTaskStatistics;

class MongoSinkConnectorIntegrationTest extends MongoKafkaTestCase {
Expand Down Expand Up @@ -226,6 +229,85 @@ private void assertProducesMessages(
assertProducesMessages(topicName, collectionName, false, partitionCount);
}

@Test
@DisplayName("Ignore MongoDB duplicate key error")
void testSinkSavesIgnoringMongoDBDuplicateKeyError() {
String topicName = getTopicName();
KAFKA.createTopic(topicName);

Properties sinkProperties = createSinkProperties();
sinkProperties.put("topics", topicName);
sinkProperties.put(MongoSinkTopicConfig.BULK_WRITE_ORDERED_CONFIG, String.valueOf(false));
KAFKA.addSinkConnector(sinkProperties);

int partitionCount = 1;
String collectionName = getCollectionName();

Properties producerProps = new Properties();
producerProps.put(ProducerConfig.TRANSACTIONAL_ID_CONFIG, topicName);
producerProps.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, KAFKA.bootstrapServers());
producerProps.put(
ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG,
"io.confluent.kafka.serializers.KafkaAvroSerializer");
producerProps.put(
ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG,
"io.confluent.kafka.serializers.KafkaAvroSerializer");
producerProps.put(
KafkaAvroSerializerConfig.SCHEMA_REGISTRY_URL_CONFIG, KAFKA.schemaRegistryUrl());

MONGODB.getDatabase().createCollection(collectionName);
MONGODB
.getDatabase()
.getCollection(collectionName)
.createIndex(Indexes.ascending("text"), new IndexOptions().unique(true));

List<TweetMsg> tweets =
IntStream.range(0, 3)
.mapToObj(
i ->
TweetMsg.newBuilder()
.setId$1(i)
.setText(
format(
"test tweet %s end2end testing apache kafka <-> mongodb sink connector is fun!",
i))
.setHashtags(asList(format("t%s", i), "kafka", "mongodb", "testing"))
.build())
.collect(Collectors.toList());

try (KafkaProducer<Long, TweetMsg> producer = new KafkaProducer<>(producerProps)) {
producer.initTransactions();
producer.beginTransaction();
producer.send(
new ProducerRecord<>(
topicName, RANDOM.nextInt(partitionCount), tweets.get(0).getId$1(), tweets.get(0)));
producer.send(
new ProducerRecord<>(
topicName, RANDOM.nextInt(partitionCount), tweets.get(0).getId$1(), tweets.get(0)));
producer.send(
new ProducerRecord<>(
topicName, RANDOM.nextInt(partitionCount), tweets.get(1).getId$1(), tweets.get(1)));
producer.commitTransaction();
producer.flush();
}

assertEventuallyEquals(
2L, () -> getCollection(collectionName).countDocuments(), collectionName);

try (KafkaProducer<Long, TweetMsg> producer = new KafkaProducer<>(producerProps)) {
producer.initTransactions();
producer.beginTransaction();
producer.send(
new ProducerRecord<>(
topicName, RANDOM.nextInt(partitionCount), tweets.get(2).getId$1(), tweets.get(2)));
producer.commitTransaction();
producer.flush();
}

assertEventuallyEquals(
3L, () -> getCollection(collectionName).countDocuments(), collectionName);
}

private void assertProducesMessages(
final String topicName,
final String collectionName,
Expand Down
9 changes: 9 additions & 0 deletions src/main/java/com/mongodb/kafka/connect/sink/StartedMongoSinkTask.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@

import com.mongodb.MongoBulkWriteException;
import com.mongodb.MongoNamespace;
import com.mongodb.bulk.BulkWriteError;
import com.mongodb.bulk.BulkWriteResult;
import com.mongodb.client.MongoClient;
import com.mongodb.client.model.BulkWriteOptions;
Expand All @@ -58,6 +59,9 @@ final class StartedMongoSinkTask implements AutoCloseable {

private final SinkTaskStatistics statistics;
private final InnerOuterTimer inTaskPutInConnectFrameworkTimer;
private static final int DUPLICATE_KYE_ERROR_CODE = 11000;
// TODO move this flag to settings
private final boolean ignoreDuplicateKeyError = true;

StartedMongoSinkTask(
final MongoSinkConfig sinkConfig,
Expand Down Expand Up @@ -218,13 +222,18 @@ private void handleTolerableWriteException(
(MongoBulkWriteException) e,
errorReporter,
StartedMongoSinkTask::log);
List<BulkWriteError> errors = ((MongoBulkWriteException) e).getWriteErrors();
if (logErrors) {
LOGGER.error(
"Failed to put into the sink some records, see log entries below for the details", e);
analyzedBatch.log();
}
if (tolerateErrors) {
analyzedBatch.report();
} else if (errors.size() == 1
&& errors.get(0).getCode() == DUPLICATE_KYE_ERROR_CODE
&& ignoreDuplicateKeyError) {
LOGGER.error("Failed to put into the sink some records: Duplicate Key Error");
} else {
throw new DataException(e);
}
Expand Down