Skip to content

Core: Don't produce partition summaries on unpartitioned table #6411

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

Merged
rdblue merged 1 commit into from
Dec 19, 2022
Merged

Core: Don't produce partition summaries on unpartitioned table #6411

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
3 changes: 2 additions & 1 deletion core/src/main/java/org/apache/iceberg/SnapshotSummary.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import java.util.Set;
import org.apache.iceberg.relocated.com.google.common.base.Joiner;
import org.apache.iceberg.relocated.com.google.common.base.Joiner.MapJoiner;
import org.apache.iceberg.relocated.com.google.common.base.Strings;
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;

Expand Down Expand Up @@ -194,7 +195,7 @@ public Map<String, String> build() {
setIf(changedPartitions.size() > 0, builder, PARTITION_SUMMARY_PROP, "true");
for (String key : changedPartitions) {
setIf(
key != null,
!Strings.isNullOrEmpty(key),
builder,
CHANGED_PARTITION_PREFIX + key,
partitionSummary(partitionMetrics.get(key)));
Expand Down
31 changes: 31 additions & 0 deletions core/src/test/java/org/apache/iceberg/TestFastAppend.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import org.apache.iceberg.exceptions.CommitFailedException;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.assertj.core.api.Assertions;
import org.junit.Assert;
import org.junit.Test;
import org.junit.runner.RunWith;
Expand Down Expand Up @@ -405,6 +406,36 @@ public void testInvalidAppendManifest() throws IOException {
() -> table.newFastAppend().appendManifest(manifestWithDeletedFiles).commit());
}

@Test
public void testPartitionSummariesOnUnpartitionedTable() {
Table table =
TestTables.create(
tableDir,
"x",
SCHEMA,
PartitionSpec.unpartitioned(),
SortOrder.unsorted(),
formatVersion);

table.updateProperties().set(TableProperties.WRITE_PARTITION_SUMMARY_LIMIT, "1").commit();
table
.newFastAppend()
.appendFile(
DataFiles.builder(PartitionSpec.unpartitioned())
.withPath("/path/to/data-a.parquet")
.withFileSizeInBytes(10)
.withRecordCount(1)
.build())
.commit();

Assertions.assertThat(
table.currentSnapshot().summary().keySet().stream()
.filter(key -> key.startsWith(SnapshotSummary.CHANGED_PARTITION_PREFIX))
.collect(Collectors.toSet()))
.as("Should not include any partition summaries")
.isEmpty();
}

@Test
public void testDefaultPartitionSummaries() {
table.newFastAppend().appendFile(FILE_A).commit();
Expand Down
3 changes: 0 additions & 3 deletions core/src/test/java/org/apache/iceberg/TestRowDelta.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -904,9 +904,6 @@ public void testAddDeleteFilesMultipleSpecs() {
Assert.assertEquals("Should add 3 position deletes", "3", summary.get(ADDED_POS_DELETES_PROP));
Assert.assertEquals("Should have 3 position deletes", "3", summary.get(TOTAL_POS_DELETES_PROP));

Assert.assertTrue(
"Partition metrics must be correct",
summary.get(CHANGED_PARTITION_PREFIX).contains(ADDED_DELETE_FILES_PROP + "=1"));
Copy link
Contributor Author

@nastra nastra Dec 12, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this was in fact checking the entry, which we don't produce anymore:

 "partitions." -> "added-position-delete-files=1,added-delete-files=1,added-files-size=10,added-position-deletes=1"

The summaries map also had the following entries for the 3 partitions:

 "partitions.data_bucket=0" -> "added-position-delete-files=1,added-delete-files=1,added-files-size=10,added-position-deletes=1"
 "partitions.data=abc" -> "added-position-delete-files=1,added-delete-files=1,added-files-size=10,added-position-deletes=1"
 "partitions.data=xyz" -> "added-data-files=1,added-records=1,added-files-size=10"

Assert.assertTrue(
"Partition metrics must be correct",
summary
Expand Down