Skip to content

[HUDI-4527] fix MOR read after compaction by flink #6282

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

Closed
wuwenchi wants to merge 2 commits into from
Closed

[HUDI-4527] fix MOR read after compaction by flink #6282

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0182ff
fix MOR after compaction
Aug 3, 2022
1805ca0
Merge branch 'master' into fix_merge_on_read_after_compaction
wuwenchi Aug 3, 2022
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
7 changes: 6 additions & 1 deletion ...rce/hudi-flink/src/main/java/org/apache/hudi/table/format/mor/MergeOnReadInputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
import org.apache.hudi.util.DataTypeUtils;
import org.apache.hudi.util.RowDataProjection;
import org.apache.hudi.util.RowDataToAvroConverters;
import org.apache.hudi.util.StreamerUtil;
import org.apache.hudi.util.StringToRowDataConverter;

import org.apache.avro.Schema;
Expand All @@ -63,6 +64,7 @@
import java.util.Iterator;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Properties;
import java.util.Set;
import java.util.stream.IntStream;

Expand Down Expand Up @@ -634,6 +636,8 @@ static class MergeIterator implements RecordIterator {

private final Set<String> keyToSkip = new HashSet<>();

private Properties payloadProps;

private RowData currentRecord;

MergeIterator(
Expand All @@ -651,6 +655,7 @@ static class MergeIterator implements RecordIterator {
this.tableSchema = tableSchema;
this.reader = reader;
this.scanner = FormatUtils.logScanner(split, tableSchema, finkConf, hadoopConf);
this.payloadProps = StreamerUtil.getHoodieClientConfig(finkConf).getPayloadConfig().getProps();
this.logKeysIterator = scanner.getRecords().keySet().iterator();
this.requiredSchema = requiredSchema;
this.requiredPos = requiredPos;
Expand Down Expand Up @@ -751,7 +756,7 @@ private Option<IndexedRecord> mergeRowWithLog(
String curKey) throws IOException {
final HoodieAvroRecord<?> record = (HoodieAvroRecord) scanner.getRecords().get(curKey);
GenericRecord historyAvroRecord = (GenericRecord) rowDataToAvroConverter.convert(tableSchema, curRow);
return record.getData().combineAndGetUpdateValue(historyAvroRecord, tableSchema);
return record.getData().combineAndGetUpdateValue(historyAvroRecord, tableSchema, payloadProps);
}
}

Expand Down
51 changes: 51 additions & 0 deletions ...ink-datasource/hudi-flink/src/test/java/org/apache/hudi/table/ITTestHoodieDataSource.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1327,6 +1327,56 @@ void testWriteAndReadWithDataSkipping() {
+ "+I[id7, Bob, 44, 1970-01-01T00:00:07, par4], "
+ "+I[id8, Han, 56, 1970-01-01T00:00:08, par4]]");
}

@ParameterizedTest
@EnumSource(value = HoodieTableType.class)
void testWriteAndCompactAndRead(HoodieTableType tableType) {
TableEnvironment tableEnv = streamTableEnv;
String hoodieTableDDL = sql("t1")
.field("uuid int")
.field("ts int")
.noPartition()
.option(FlinkOptions.PATH, tempFile.getAbsolutePath())
.option(FlinkOptions.READ_DATA_SKIPPING_ENABLED, true)
.option(FlinkOptions.COMPACTION_DELTA_COMMITS, 3)
.option("hoodie.compact.inline", true)
.option(FlinkOptions.PRE_COMBINE, true)
.option(FlinkOptions.RECORD_KEY_FIELD, "uuid")
.option(FlinkOptions.TABLE_TYPE, tableType.name())
.end();
tableEnv.executeSql(hoodieTableDDL);

System.out.println(hoodieTableDDL);

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 1)");
List<Row> result1 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result1, "[+I[1, 1]]");

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 100)");
List<Row> result2 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result2, "[+I[1, 100]]");

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 50)");
List<Row> result3 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result3, "[+I[1, 100]]");

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 2)");
List<Row> result4 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result4, "[+I[1, 100]]");

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 80)");
List<Row> result5 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result5, "[+I[1, 100]]");

execInsertSql(tableEnv, "INSERT INTO t1 values (1, 180)");
List<Row> result6 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select * from t1").execute().collect());
assertRowsEquals(result6, "[+I[1, 180]]");

@Test
void testBuiltinFunctionWithHMSCatalog() {
Expand Down Expand Up @@ -1393,6 +1443,7 @@ void testWriteReadWithComputedColumns() {
List<Row> result2 = CollectionUtil.iterableToList(
() -> tableEnv.sqlQuery("select f3 from t1").execute().collect());
assertRowsEquals(result2, "[+I[3]]");

}

// -------------------------------------------------------------------------
Expand Down