-
Notifications
You must be signed in to change notification settings - Fork 27
Add feature to update table schemas for GCStoBQ load jobs #134
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
Merged
Merged
Changes from 6 commits
Commits
Show all changes
7 commits
Select commit
Hold shift + click to select a range
f2ee80f
Add feature to update table schemas for GCStoBQ load jobs
veliuenal 1f06f02
Revert the unnecessary change
veliuenal f6537f2
Add integration test
veliuenal adbf692
Revert unnecessary changes
veliuenal 99b2144
Update the test name
veliuenal e815fc0
Add a space before the parameter
veliuenal 954dceb
Add standard header to the integration test
veliuenal 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
242 changes: 242 additions & 0 deletions
242
...src/test/java/com/wepay/kafka/connect/bigquery/integration/GcsBatchSchemaEvolutionIT.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 +1,242 @@ | ||
| package com.wepay.kafka.connect.bigquery.integration; | ||
|
|
||
| import static io.confluent.kafka.serializers.AbstractKafkaSchemaSerDeConfig.SCHEMA_REGISTRY_URL_CONFIG; | ||
| import static org.apache.kafka.connect.runtime.ConnectorConfig.KEY_CONVERTER_CLASS_CONFIG; | ||
| import static org.apache.kafka.connect.runtime.ConnectorConfig.VALUE_CONVERTER_CLASS_CONFIG; | ||
| import static org.apache.kafka.connect.runtime.SinkConnectorConfig.TOPICS_CONFIG; | ||
| import static org.apache.kafka.test.TestUtils.waitForCondition; | ||
| import static org.junit.jupiter.api.Assertions.assertEquals; | ||
| import static org.junit.jupiter.api.Assertions.assertNotNull; | ||
|
|
||
| import com.google.cloud.bigquery.BigQuery; | ||
| import com.google.cloud.bigquery.Field; | ||
| import com.google.cloud.bigquery.LegacySQLTypeName; | ||
| import com.google.cloud.bigquery.StandardTableDefinition; | ||
| import com.google.cloud.bigquery.Table; | ||
| import com.google.cloud.bigquery.TableId; | ||
| import com.google.cloud.bigquery.TableInfo; | ||
| import com.wepay.kafka.connect.bigquery.config.BigQuerySinkConfig; | ||
| import com.wepay.kafka.connect.bigquery.integration.utils.BucketClearer; | ||
| import com.wepay.kafka.connect.bigquery.integration.utils.SchemaRegistryTestUtils; | ||
| import com.wepay.kafka.connect.bigquery.integration.utils.TableClearer; | ||
| import com.wepay.kafka.connect.bigquery.retrieve.IdentitySchemaRetriever; | ||
| import io.confluent.connect.avro.AvroConverter; | ||
| import java.time.Duration; | ||
| import java.util.ArrayList; | ||
| import java.util.Arrays; | ||
| import java.util.Collections; | ||
| import java.util.HashMap; | ||
| import java.util.List; | ||
| import java.util.Map; | ||
| import org.apache.kafka.connect.data.Schema; | ||
| import org.apache.kafka.connect.data.SchemaAndValue; | ||
| import org.apache.kafka.connect.data.SchemaBuilder; | ||
| import org.apache.kafka.connect.data.Struct; | ||
| import org.apache.kafka.connect.storage.Converter; | ||
| import org.junit.jupiter.api.AfterEach; | ||
| import org.junit.jupiter.api.BeforeEach; | ||
| import org.junit.jupiter.api.Tag; | ||
| import org.junit.jupiter.api.Test; | ||
|
|
||
| @Tag("integration") | ||
| public class GcsBatchSchemaEvolutionIT extends BaseConnectorIT { | ||
|
|
||
| private static final String CONNECTOR_NAME = "gcs-schema-evolution-connector"; | ||
| private static final int TASKS_MAX = 1; | ||
| private static final Duration LOAD_TIMEOUT = Duration.ofMinutes(2); | ||
|
|
||
| private BigQuery bigQuery; | ||
| private SchemaRegistryTestUtils schemaRegistry; | ||
| private String schemaRegistryUrl; | ||
| private Converter keyConverter; | ||
| private Converter valueConverter; | ||
| private Schema keySchema; | ||
| private Schema valueSchemaV1; | ||
| private Schema valueSchemaV2; | ||
| private String topic; | ||
| private String table; | ||
| private String bucketName; | ||
|
|
||
| @BeforeEach | ||
| public void setup() throws Exception { | ||
| startConnect(); | ||
| bigQuery = newBigQuery(); | ||
|
|
||
| schemaRegistry = new SchemaRegistryTestUtils(connect.kafka().bootstrapServers()); | ||
| schemaRegistry.start(); | ||
| schemaRegistryUrl = schemaRegistry.schemaRegistryUrl(); | ||
|
|
||
| initialiseSchemas(); | ||
| initialiseConverters(); | ||
|
|
||
| topic = suffixedTableOrTopic("gcs_schema_evolution"); | ||
| table = suffixedAndSanitizedTable("gcs_schema_evolution"); | ||
| bucketName = gcsBucket() + "-" + System.nanoTime(); | ||
|
|
||
| connect.kafka().createTopic(topic); | ||
| TableClearer.clearTables(bigQuery, dataset(), table); | ||
| createInitialTable(); | ||
| } | ||
|
|
||
| @AfterEach | ||
| public void tearDown() throws Exception { | ||
| try { | ||
| if (connect != null) { | ||
| connect.deleteConnector(CONNECTOR_NAME); | ||
| } | ||
| } finally { | ||
| if (schemaRegistry != null) { | ||
| schemaRegistry.stop(); | ||
| } | ||
| if (bigQuery != null) { | ||
| TableClearer.clearTables(bigQuery, dataset(), table); | ||
| } | ||
| BucketClearer.clearBucket(keyFile(), project(), bucketName, gcsFolder(), keySource()); | ||
| stopConnect(); | ||
| } | ||
| } | ||
|
|
||
| @Test | ||
| public void testSchemaEvolutionAcrossBatchLoads() throws Exception { | ||
| connect.configureConnector(CONNECTOR_NAME, connectorProps()); | ||
| waitForConnectorToStart(CONNECTOR_NAME, TASKS_MAX); | ||
|
|
||
| schemaRegistry.produceRecordsWithKey( | ||
| keyConverter, | ||
| valueConverter, | ||
| Collections.singletonList(recordV1(1L, "snacks")), | ||
| topic | ||
| ); | ||
|
|
||
| waitForCommittedRecords(CONNECTOR_NAME, topic, 1, TASKS_MAX); | ||
| waitForRowCount(1L); | ||
|
|
||
| schemaRegistry.produceRecordsWithKey( | ||
| keyConverter, | ||
| valueConverter, | ||
| Collections.singletonList(recordV2(2L, null, "john")), | ||
| topic | ||
| ); | ||
|
|
||
| waitForCommittedRecords(CONNECTOR_NAME, topic, 2, TASKS_MAX); | ||
| waitForRowCount(2L); | ||
|
|
||
| Table destinationTable = bigQuery.getTable(dataset(), table); | ||
| com.google.cloud.bigquery.Schema destinationSchema = destinationTable.getDefinition().getSchema(); | ||
| Field categoryField = destinationSchema.getFields().get("category"); | ||
| assertNotNull(categoryField, "category field should exist after load"); | ||
| assertEquals(Field.Mode.NULLABLE, categoryField.getMode()); | ||
| Field usernameField = destinationSchema.getFields().get("username"); | ||
| assertNotNull(usernameField, "username field should be created"); | ||
| assertEquals(Field.Mode.NULLABLE, usernameField.getMode()); | ||
|
|
||
| List<List<Object>> rows = readAllRows(bigQuery, table, "id"); | ||
| assertEquals(Arrays.asList(1L, "snacks", null), rows.get(0)); | ||
| assertEquals(Arrays.asList(2L, null, "john"), rows.get(1)); | ||
| } | ||
|
|
||
| private Map<String, String> connectorProps() { | ||
| Map<String, String> props = baseConnectorProps(TASKS_MAX); | ||
| props.put(TOPICS_CONFIG, topic); | ||
| props.put( | ||
| KEY_CONVERTER_CLASS_CONFIG, | ||
| AvroConverter.class.getName() | ||
| ); | ||
| props.put( | ||
| KEY_CONVERTER_CLASS_CONFIG + "." + SCHEMA_REGISTRY_URL_CONFIG, | ||
| schemaRegistryUrl | ||
| ); | ||
| props.put( | ||
| VALUE_CONVERTER_CLASS_CONFIG, | ||
| AvroConverter.class.getName() | ||
| ); | ||
| props.put( | ||
| VALUE_CONVERTER_CLASS_CONFIG + "." + SCHEMA_REGISTRY_URL_CONFIG, | ||
| schemaRegistryUrl | ||
| ); | ||
| props.put(BigQuerySinkConfig.ALLOW_NEW_BIGQUERY_FIELDS_CONFIG, "true"); | ||
| props.put(BigQuerySinkConfig.ALLOW_BIGQUERY_REQUIRED_FIELD_RELAXATION_CONFIG, "true"); | ||
| props.put(BigQuerySinkConfig.ENABLE_BATCH_CONFIG, topic + "," + table); | ||
| props.put(BigQuerySinkConfig.BATCH_LOAD_INTERVAL_SEC_CONFIG, "5"); | ||
| props.put(BigQuerySinkConfig.GCS_BUCKET_NAME_CONFIG, bucketName); | ||
| props.put(BigQuerySinkConfig.GCS_FOLDER_NAME_CONFIG, gcsFolder()); | ||
| props.put(BigQuerySinkConfig.SCHEMA_RETRIEVER_CONFIG, IdentitySchemaRetriever.class.getName()); | ||
| props.put(BigQuerySinkConfig.TABLE_CREATE_CONFIG, "false"); | ||
| return props; | ||
| } | ||
|
|
||
| private void initialiseSchemas() { | ||
| keySchema = SchemaBuilder.struct() | ||
| .name("com.wepay.kafka.connect.bigquery.integration.Key") | ||
| .field("id", Schema.INT64_SCHEMA) | ||
| .build(); | ||
|
|
||
| valueSchemaV1 = SchemaBuilder.struct() | ||
| .name("com.wepay.kafka.connect.bigquery.integration.ValueV1") | ||
| .field("id", Schema.INT64_SCHEMA) | ||
| .field("category", Schema.STRING_SCHEMA) | ||
| .build(); | ||
|
|
||
| valueSchemaV2 = SchemaBuilder.struct() | ||
| .name("com.wepay.kafka.connect.bigquery.integration.ValueV2") | ||
| .field("id", Schema.INT64_SCHEMA) | ||
| .field("category", SchemaBuilder.string().optional().build()) | ||
| .field("username", SchemaBuilder.string().optional().build()) | ||
| .build(); | ||
| } | ||
|
|
||
| private void initialiseConverters() { | ||
| keyConverter = new AvroConverter(); | ||
| valueConverter = new AvroConverter(); | ||
| Map<String, Object> keyConfig = new HashMap<>(); | ||
| keyConfig.put(SCHEMA_REGISTRY_URL_CONFIG, schemaRegistryUrl); | ||
| keyConverter.configure(keyConfig, true); | ||
| Map<String, Object> valueConfig = new HashMap<>(); | ||
| valueConfig.put(SCHEMA_REGISTRY_URL_CONFIG, schemaRegistryUrl); | ||
| valueConverter.configure(valueConfig, false); | ||
| } | ||
|
|
||
| private List<SchemaAndValue> recordV1(long id, String category) { | ||
| Struct key = new Struct(keySchema) | ||
| .put("id", id); | ||
| Struct value = new Struct(valueSchemaV1) | ||
| .put("id", id) | ||
| .put("category", category); | ||
| List<SchemaAndValue> record = new ArrayList<>(2); | ||
| record.add(new SchemaAndValue(keySchema, key)); | ||
| record.add(new SchemaAndValue(valueSchemaV1, value)); | ||
| return record; | ||
| } | ||
|
|
||
| private List<SchemaAndValue> recordV2(long id, String category, String username) { | ||
| Struct key = new Struct(keySchema) | ||
| .put("id", id); | ||
| Struct value = new Struct(valueSchemaV2) | ||
| .put("id", id) | ||
| .put("category", category) | ||
| .put("username", username); | ||
| List<SchemaAndValue> record = new ArrayList<>(2); | ||
| record.add(new SchemaAndValue(keySchema, key)); | ||
| record.add(new SchemaAndValue(valueSchemaV2, value)); | ||
| return record; | ||
| } | ||
|
|
||
| private void createInitialTable() { | ||
| TableId tableId = TableId.of(dataset(), table); | ||
| com.google.cloud.bigquery.Schema schema = com.google.cloud.bigquery.Schema.of( | ||
| Field.newBuilder("id", LegacySQLTypeName.INTEGER).setMode(Field.Mode.REQUIRED).build(), | ||
| Field.newBuilder("category", LegacySQLTypeName.STRING).setMode(Field.Mode.REQUIRED).build() | ||
| ); | ||
| bigQuery.create(TableInfo.newBuilder(tableId, StandardTableDefinition.of(schema)).build()); | ||
| } | ||
|
|
||
| private void waitForRowCount(long expected) throws InterruptedException { | ||
| waitForCondition(() -> { | ||
| try { | ||
| return countRows(bigQuery, table) >= expected; | ||
| } catch (Exception e) { | ||
| return false; | ||
| } | ||
| }, LOAD_TIMEOUT.toMillis(), "Timed out waiting for " + expected + " rows"); | ||
| } | ||
| } | ||
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.
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.
This file needs the standard header for the build to complete.
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.
Added it 👍