Skip to content

[fix](load) Preserve routine load CSV header formats #67513

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
0AyanamiRei wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[fix](load) Preserve routine load CSV header formats #67513

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
4 changes: 3 additions & 1 deletion fe/fe-core/src/main/java/org/apache/doris/load/routineload/RoutineLoadJob.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,7 +408,9 @@ protected void setOptional(CreateRoutineLoadInfo info) throws UserException {
FileFormatProperties fileFormatProperties = info.getFileFormatProperties();
if (fileFormatProperties instanceof CsvFileFormatProperties) {
CsvFileFormatProperties csvFileFormatProperties = (CsvFileFormatProperties) fileFormatProperties;
jobProperties.put(FileFormatProperties.PROP_FORMAT, "csv");
String headerType = csvFileFormatProperties.getHeaderType();
jobProperties.put(FileFormatProperties.PROP_FORMAT, headerType.isEmpty()
? FileFormatProperties.FORMAT_CSV : headerType);
jobProperties.put(CsvFileFormatProperties.PROP_ENCLOSE,
new String(new byte[]{csvFileFormatProperties.getEnclose()}));
jobProperties.put(CsvFileFormatProperties.PROP_ESCAPE,
Expand Down
6 changes: 6 additions & 0 deletions fe/fe-core/src/main/java/org/apache/doris/nereids/load/NereidsRoutineLoadTaskInfo.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.doris.common.Config;
import org.apache.doris.common.util.TimeUtils;
import org.apache.doris.datasource.property.fileformat.CsvFileFormatProperties;
import org.apache.doris.datasource.property.fileformat.FileFormatProperties;
import org.apache.doris.load.loadv2.LoadTask;
import org.apache.doris.nereids.trees.expressions.Expression;
import org.apache.doris.nereids.trees.plans.commands.LoadCommand;
Expand Down Expand Up @@ -305,6 +306,11 @@ public boolean isLoadToSingleTablet() {

@Override
public String getHeaderType() {
String format = getFormat();
if (format.equals(FileFormatProperties.FORMAT_CSV_WITH_NAMES)
|| format.equals(FileFormatProperties.FORMAT_CSV_WITH_NAMES_AND_TYPES)) {
return format;
}
return "";
}

Expand Down
71 changes: 45 additions & 26 deletions fe/fe-core/src/test/java/org/apache/doris/load/routineload/KafkaRoutineLoadJobTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
import org.apache.doris.common.jmockit.Deencapsulation;
import org.apache.doris.datasource.InternalCatalog;
import org.apache.doris.datasource.kafka.KafkaUtil;
import org.apache.doris.datasource.property.fileformat.FileFormatProperties;
import org.apache.doris.load.RoutineLoadDesc;
import org.apache.doris.load.loadv2.LoadTask;
import org.apache.doris.load.routineload.kafka.KafkaConfiguration;
Expand All @@ -40,11 +41,14 @@
import org.apache.doris.load.routineload.kafka.KafkaRoutineLoadJob;
import org.apache.doris.load.routineload.kafka.KafkaTaskInfo;
import org.apache.doris.mysql.privilege.MockedAuth;
import org.apache.doris.nereids.load.NereidsDataDescription;
import org.apache.doris.nereids.load.NereidsRoutineLoadTaskInfo;
import org.apache.doris.nereids.trees.plans.commands.info.CreateRoutineLoadInfo;
import org.apache.doris.nereids.trees.plans.commands.info.LabelNameInfo;
import org.apache.doris.nereids.trees.plans.commands.load.LoadProperty;
import org.apache.doris.nereids.trees.plans.commands.load.LoadSeparator;
import org.apache.doris.qe.ConnectContext;
import org.apache.doris.thrift.TFileFormatType;
import org.apache.doris.thrift.TResourceInfo;
import org.apache.doris.thrift.TRoutineLoadTask;

Expand Down Expand Up @@ -637,33 +641,48 @@ public void testFromCreateStmt() throws UserException {
return pairList;
});

CreateRoutineLoadInfo createRoutineLoadInfo = initCreateRoutineLoadInfo();
createRoutineLoadInfo.validate(connectContext);
RoutineLoadDesc routineLoadDesc = new RoutineLoadDesc(columnSeparator, null, null, null, null, partitionNames, null,
LoadTask.MergeType.APPEND, sequenceColumnName);
Deencapsulation.setField(createRoutineLoadInfo, "routineLoadDesc", routineLoadDesc);
List<Pair<Integer, Long>> partitionIdToOffset = Lists.newArrayList();
List<PartitionInfo> kafkaPartitionInfoList = Lists.newArrayList();
for (String s : kafkaPartitionString.split(",")) {
partitionIdToOffset.add(Pair.of(Integer.valueOf(s), 0L));
PartitionInfo partitionInfo = new PartitionInfo(topicName, Integer.valueOf(s), null, null, null);
kafkaPartitionInfoList.add(partitionInfo);
for (String csvFormat : Arrays.asList(FileFormatProperties.FORMAT_CSV,
FileFormatProperties.FORMAT_CSV_WITH_NAMES,
FileFormatProperties.FORMAT_CSV_WITH_NAMES_AND_TYPES)) {
CreateRoutineLoadInfo createRoutineLoadInfo = initCreateRoutineLoadInfo();
createRoutineLoadInfo.getJobProperties().put(FileFormatProperties.PROP_FORMAT, csvFormat);
createRoutineLoadInfo.validate(connectContext);
RoutineLoadDesc routineLoadDesc = new RoutineLoadDesc(columnSeparator, null, null, null, null,
partitionNames, null, LoadTask.MergeType.APPEND, sequenceColumnName);
Deencapsulation.setField(createRoutineLoadInfo, "routineLoadDesc", routineLoadDesc);
List<Pair<Integer, Long>> partitionIdToOffset = Lists.newArrayList();
List<PartitionInfo> kafkaPartitionInfoList = Lists.newArrayList();
for (String s : kafkaPartitionString.split(",")) {
partitionIdToOffset.add(Pair.of(Integer.valueOf(s), 0L));
PartitionInfo partitionInfo = new PartitionInfo(topicName, Integer.valueOf(s), null, null, null);
kafkaPartitionInfoList.add(partitionInfo);
}
KafkaDataSourceProperties dsProperties = new KafkaDataSourceProperties(null);
dsProperties.setKafkaPartitionOffsets(partitionIdToOffset);
Deencapsulation.setField(dsProperties, "brokerList", serverAddress);
Deencapsulation.setField(dsProperties, "topic", topicName);
Deencapsulation.setField(createRoutineLoadInfo, "dataSourceProperties", dsProperties);

KafkaRoutineLoadJob kafkaRoutineLoadJob =
KafkaRoutineLoadJob.fromCreateInfo(createRoutineLoadInfo, connectContext);
Assert.assertEquals(jobName, kafkaRoutineLoadJob.getName());
Assert.assertEquals(dbId, kafkaRoutineLoadJob.getDbId());
Assert.assertEquals(tableId, kafkaRoutineLoadJob.getTableId());
Assert.assertEquals(serverAddress, Deencapsulation.getField(kafkaRoutineLoadJob, "brokerList"));
Assert.assertEquals(topicName, Deencapsulation.getField(kafkaRoutineLoadJob, "topic"));
List<Integer> kafkaPartitionResult =
Deencapsulation.getField(kafkaRoutineLoadJob, "customKafkaPartitions");
Assert.assertEquals(kafkaPartitionString, Joiner.on(",").join(kafkaPartitionResult));
Assert.assertEquals(sequenceColumnName, kafkaRoutineLoadJob.getSequenceCol());
Assert.assertEquals(csvFormat, kafkaRoutineLoadJob.getFormat());

NereidsRoutineLoadTaskInfo taskInfo = kafkaRoutineLoadJob.toNereidsRoutineLoadTaskInfo();
String expectedHeaderType = csvFormat.equals(FileFormatProperties.FORMAT_CSV) ? "" : csvFormat;
Assert.assertEquals(TFileFormatType.FORMAT_CSV_PLAIN, taskInfo.getFormatType());
Assert.assertEquals(expectedHeaderType, taskInfo.getHeaderType());
Assert.assertTrue(new NereidsDataDescription(tableNameString, taskInfo).toSql()
.contains("FORMAT AS '" + csvFormat + "'"));
}
KafkaDataSourceProperties dsProperties = new KafkaDataSourceProperties(null);
dsProperties.setKafkaPartitionOffsets(partitionIdToOffset);
Deencapsulation.setField(dsProperties, "brokerList", serverAddress);
Deencapsulation.setField(dsProperties, "topic", topicName);
Deencapsulation.setField(createRoutineLoadInfo, "dataSourceProperties", dsProperties);

KafkaRoutineLoadJob kafkaRoutineLoadJob = KafkaRoutineLoadJob.fromCreateInfo(createRoutineLoadInfo, connectContext);
Assert.assertEquals(jobName, kafkaRoutineLoadJob.getName());
Assert.assertEquals(dbId, kafkaRoutineLoadJob.getDbId());
Assert.assertEquals(tableId, kafkaRoutineLoadJob.getTableId());
Assert.assertEquals(serverAddress, Deencapsulation.getField(kafkaRoutineLoadJob, "brokerList"));
Assert.assertEquals(topicName, Deencapsulation.getField(kafkaRoutineLoadJob, "topic"));
List<Integer> kafkaPartitionResult = Deencapsulation.getField(kafkaRoutineLoadJob, "customKafkaPartitions");
Assert.assertEquals(kafkaPartitionString, Joiner.on(",").join(kafkaPartitionResult));
Assert.assertEquals(sequenceColumnName, kafkaRoutineLoadJob.getSequenceCol());
}
}

Expand Down