Skip to content

[core] Expire TIMESTAMP partitions with the values-time strategy #10851

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
cxzl25 wants to merge 1 commit into
base: master
Choose a base branch
from
+100 −7
Open

[core] Expire TIMESTAMP partitions with the values-time strategy #10851

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
6 changes: 3 additions & 3 deletions paimon-core/src/main/java/org/apache/paimon/operation/NormalPartitionExpire.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,6 @@
import javax.annotation.Nullable;

import java.time.Duration;
import java.time.LocalDate;
import java.time.LocalDateTime;
import java.util.ArrayList;
import java.util.Collection;
Expand Down Expand Up @@ -161,14 +160,15 @@ private List<Map<String, String>> doExpire(
List<List<String>> expiredPartValues = new ArrayList<>(partitionEntries.size());
for (PartitionEntry partition : partitionEntries) {
Object[] array = strategy.convertPartition(partition.partition());
// DATE values are normalized for time extraction; use the stored names for dropping.
// DATE and TIMESTAMP values are normalized for time extraction; use the stored
// names for dropping.
Map<String, String> partitionSpec =
commit.pathFactory()
.partitionComputer()
.generatePartValues(partition.partition());
int index = 0;
for (String value : partitionSpec.values()) {
if (array[index] instanceof LocalDate) {
if (array[index] != null && strategy.isNormalizedForTimeExtraction(index)) {
array[index] = value;
}
index++;
Expand Down
41 changes: 37 additions & 4 deletions paimon-core/src/main/java/org/apache/paimon/partition/PartitionExpireStrategy.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,13 @@
import org.apache.paimon.catalog.CatalogLoader;
import org.apache.paimon.catalog.Identifier;
import org.apache.paimon.data.BinaryRow;
import org.apache.paimon.data.Timestamp;
import org.apache.paimon.manifest.PartitionEntry;
import org.apache.paimon.operation.FileStoreScan;
import org.apache.paimon.types.DataTypeRoot;
import org.apache.paimon.types.DataType;
import org.apache.paimon.types.DataTypeChecks;
import org.apache.paimon.types.RowType;
import org.apache.paimon.utils.DateTimeUtils;
import org.apache.paimon.utils.RowDataToObjectArrayConverter;

import javax.annotation.Nullable;
Expand Down Expand Up @@ -74,13 +77,43 @@ public List<String> toPartitionValue(Object[] array) {
return list;
}

/**
* Whether {@link #convertPartition} renders the value at this index in a form meant for time
* extraction that can differ from the stored partition name.
*/
public boolean isNormalizedForTimeExtraction(int index) {
switch (toObjectArrayConverter.rowType().getTypeAt(index).getTypeRoot()) {
case DATE:
case TIMESTAMP_WITHOUT_TIME_ZONE:
case TIMESTAMP_WITH_LOCAL_TIME_ZONE:
return true;
default:
return false;
}
}

public Object[] convertPartition(BinaryRow partition) {
Object[] values = toObjectArrayConverter.convert(partition);
RowType partitionType = toObjectArrayConverter.rowType();
for (int index = 0; index < values.length; index++) {
if (values[index] != null
&& partitionType.getTypeAt(index).getTypeRoot() == DataTypeRoot.DATE) {
values[index] = LocalDate.ofEpochDay((Integer) values[index]);
if (values[index] == null) {
continue;
}
DataType type = partitionType.getTypeAt(index);
switch (type.getTypeRoot()) {
case DATE:
values[index] = LocalDate.ofEpochDay((Integer) values[index]);
break;
case TIMESTAMP_WITHOUT_TIME_ZONE:
case TIMESTAMP_WITH_LOCAL_TIME_ZONE:
// Timestamp#toString uses the ISO 'T' separator, which the default
// partition time formatter cannot parse. Render it as the SQL string.
values[index] =
DateTimeUtils.formatTimestamp(
(Timestamp) values[index], DataTypeChecks.getPrecision(type));
break;
default:
break;
}
}
return values;
Expand Down
60 changes: 60 additions & 0 deletions paimon-core/src/test/java/org/apache/paimon/operation/PartitionExpireTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.io.TempDir;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.CsvSource;
import org.junit.jupiter.params.provider.ValueSource;

import java.io.IOException;
Expand Down Expand Up @@ -313,6 +314,65 @@ public void testDateAndHourPartitionValues() {
assertThat(strategy.isExpired(partitionDate.atTime(13, 0), partition)).isTrue();
}

@ParameterizedTest
@CsvSource({
"values-time, false",
"values-time, true",
"update-time, false",
"update-time, true"
})
public void testExpireTimestampPartitionWithoutMetastore(
String expirationStrategy, boolean legacyPartitionName) throws Exception {
SchemaManager schemaManager = new FileSystemSchemaManager(LocalFileIO.create(), path);
Map<String, String> tableOptions = new HashMap<>();
tableOptions.put(METASTORE_PARTITIONED_TABLE.key(), "false");
tableOptions.put(
CoreOptions.PARTITION_GENERATE_LEGACY_NAME.key(),
String.valueOf(legacyPartitionName));
schemaManager.createTable(
new Schema(
RowType.of(DataTypes.TIMESTAMP(0), VarCharType.STRING_TYPE).getFields(),
singletonList("f0"),
emptyList(),
tableOptions,
""));
newTable();
org.apache.paimon.data.Timestamp expiredTs =
org.apache.paimon.data.Timestamp.fromLocalDateTime(date(1));
org.apache.paimon.data.Timestamp retainedTs =
org.apache.paimon.data.Timestamp.fromLocalDateTime(date(5));
write(GenericRow.of(expiredTs, BinaryString.fromString("expired")));
write(GenericRow.of(retainedTs, BinaryString.fromString("retained")));

Map<String, String> options = new HashMap<>();
options.put(PARTITION_EXPIRATION_TIME.key(), "2 d");
options.put(CoreOptions.PARTITION_EXPIRATION_STRATEGY.key(), expirationStrategy);
options.put(CoreOptions.PARTITION_TIMESTAMP_PATTERN.key(), "$f0");
table = table.copy(options);
NormalPartitionExpire expire =
(NormalPartitionExpire) table.store().newPartitionExpire("", table);
expire.setLastCheck(date(1));
// the legacy name is Timestamp#toString, the new name is the SQL timestamp string
String expiredName = legacyPartitionName ? "2023-01-01T00:00" : "2023-01-01 00:00:00";
String retainedName = legacyPartitionName ? "2023-01-05T00:00" : "2023-01-05 00:00:00";
List<Map<String, String>> expectedExpired = new ArrayList<>();
expectedExpired.add(Collections.singletonMap("f0", expiredName));
LocalDateTime checkTime = date(6);
List<org.apache.paimon.data.Timestamp> expectedRemaining = singletonList(retainedTs);
if ("update-time".equals(expirationStrategy)) {
checkTime = LocalDateTime.now().plusDays(3);
expectedExpired.add(Collections.singletonMap("f0", retainedName));
expectedRemaining = emptyList();
}
assertThat(expire.expire(checkTime, Long.MAX_VALUE))
.containsExactlyElementsOf(expectedExpired);
List<org.apache.paimon.data.Timestamp> remaining = new ArrayList<>();
table.newRead()
.createReader(table.newScan().plan().splits())
.forEachRemaining(row -> remaining.add(row.getTimestamp(0, 0)));
assertThat(remaining).containsExactlyElementsOf(expectedRemaining);
}

@ParameterizedTest
@ValueSource(strings = {"values-time", "update-time"})
public void testExpireDatePartitionWithoutMetastore(String expirationStrategy)
Expand Down
Loading