Skip to content

Fix delete commit msg #67

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
CodingCat wants to merge 15 commits into
base: master
Choose a base branch
from
Open

Fix delete commit msg #67

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
6aa5948
fix delete version tag
CodingCat May 4, 2023
e0f366c
add all tests
CodingCat May 18, 2023
2e8f2ed
yo
CodingCat May 18, 2023
2c1b93f
add docs
CodingCat May 18, 2023
9773817
remove position
CodingCat May 18, 2023
8b39e57
3.3
CodingCat May 18, 2023
84d6c91
3.4
CodingCat May 18, 2023
a5d61b1
Update spark-configuration.md
CodingCat May 18, 2023
518a0ee
addr comments #1
CodingCat May 25, 2023
e86f181
addr comments #2
CodingCat May 25, 2023
8c7f206
rm doc updates
CodingCat May 25, 2023
24937af
stylistic fixes
CodingCat May 25, 2023
2fc5d9c
stylistic fixes
CodingCat May 25, 2023
5a33ad3
fix the tests
CodingCat May 25, 2023
6e32872
Update spark-configuration.md
CodingCat May 25, 2023
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
18 changes: 13 additions & 5 deletions spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.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.BaseMetadataTable;
import org.apache.iceberg.BaseTable;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.DeleteFiles;
import org.apache.iceberg.FileScanTask;
import org.apache.iceberg.MetadataColumns;
import org.apache.iceberg.PartitionSpec;
Expand All @@ -48,6 +49,7 @@
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet;
import org.apache.iceberg.relocated.com.google.common.collect.Iterables;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.Spark3Util;
import org.apache.iceberg.spark.SparkFilters;
import org.apache.iceberg.spark.SparkReadOptions;
Expand Down Expand Up @@ -326,11 +328,17 @@ public void deleteWhere(Filter[] filters) {
return;
}

icebergTable
.newDelete()
.set("spark.app.id", sparkSession().sparkContext().applicationId())
.deleteFromRowFilter(deleteExpr)
.commit();
DeleteFiles deleteFiles =
icebergTable
.newDelete()
.set("spark.app.id", sparkSession().sparkContext().applicationId())
.deleteFromRowFilter(deleteExpr);

if (!CommitMetadata.commitProperties().isEmpty()) {
CommitMetadata.commitProperties().forEach(deleteFiles::set);
}

deleteFiles.commit();
}

@Override
Expand Down
55 changes: 45 additions & 10 deletions spark/v3.2/spark/src/test/java/org/apache/iceberg/spark/source/TestDataSourceOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@
import java.math.RoundingMode;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.hadoop.conf.Configuration;
import org.apache.iceberg.AssertHelpers;
import org.apache.iceberg.DataFile;
Expand All @@ -40,26 +39,28 @@
import org.apache.iceberg.io.CloseableIterable;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.apache.iceberg.relocated.com.google.common.math.LongMath;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.SparkReadOptions;
import org.apache.iceberg.spark.SparkTestBaseWithCatalog;
import org.apache.iceberg.spark.SparkWriteOptions;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.SnapshotUtil;
import org.apache.spark.sql.Column;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException;
import org.junit.AfterClass;
import org.junit.Assert;
import org.junit.BeforeClass;
import org.junit.Rule;
import org.junit.Test;
import org.junit.rules.TemporaryFolder;

public class TestDataSourceOptions {
public class TestDataSourceOptions extends SparkTestBaseWithCatalog {

private static final Configuration CONF = new Configuration();
private static final Schema SCHEMA =
Expand Down Expand Up @@ -440,12 +441,46 @@ public void testExtraSnapshotMetadataWithSQL() throws InterruptedException, IOEx
writerThread.setName("test-extra-commit-message-writer-thread");
writerThread.start();
writerThread.join();
Set<String> threadNames = Sets.newHashSet();
for (Snapshot snapshot : table.snapshots()) {
threadNames.add(snapshot.summary().get("writer-thread"));
}
Assert.assertEquals(2, threadNames.size());
Assert.assertTrue(threadNames.contains(null));
Assert.assertTrue(threadNames.contains("test-extra-commit-message-writer-thread"));

List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-writer-thread", snapshots.get(1).summary().get("writer-thread"));
}

@Test
public void testExtraSnapshotMetadataWithDelete()
throws InterruptedException, NoSuchTableException {
spark.sessionState().conf().setConfString("spark.sql.shuffle.partitions", "1");
sql("CREATE TABLE %s (id INT, data STRING) USING iceberg", tableName);
List<SimpleRecord> expectedRecords =
Lists.newArrayList(
new SimpleRecord(1, "a"), new SimpleRecord(2, "b"), new SimpleRecord(3, "c"));
Dataset<Row> originalDf = spark.createDataFrame(expectedRecords, SimpleRecord.class);
originalDf.repartition(5, new Column("data")).select("id", "data").writeTo(tableName).append();
Thread writerThread =
new Thread(
() -> {
Map<String, String> properties = Maps.newHashMap();
properties.put("writer-thread", String.valueOf(Thread.currentThread().getName()));
CommitMetadata.withCommitProperties(
properties,
() -> {
spark.sql("DELETE FROM " + tableName + " where id = 1");
return 0;
},
RuntimeException.class);
});
writerThread.setName("test-extra-commit-message-delete-thread");
writerThread.start();
writerThread.join();

Table table = validationCatalog.loadTable(tableIdent);
List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-delete-thread", snapshots.get(1).summary().get("writer-thread"));
}
}
5 changes: 4 additions & 1 deletion spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet;
import org.apache.iceberg.relocated.com.google.common.collect.Iterables;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.Spark3Util;
import org.apache.iceberg.spark.SparkFilters;
import org.apache.iceberg.spark.SparkReadOptions;
Expand Down Expand Up @@ -374,7 +375,9 @@ public void deleteWhere(Filter[] filters) {
if (branch != null) {
deleteFiles.toBranch(branch);
}

if (!CommitMetadata.commitProperties().isEmpty()) {
CommitMetadata.commitProperties().forEach(deleteFiles::set);
}
deleteFiles.commit();
}

Expand Down
55 changes: 45 additions & 10 deletions spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/source/TestDataSourceOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@
import java.math.RoundingMode;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.hadoop.conf.Configuration;
import org.apache.iceberg.AssertHelpers;
import org.apache.iceberg.DataFile;
Expand All @@ -40,26 +39,28 @@
import org.apache.iceberg.io.CloseableIterable;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.apache.iceberg.relocated.com.google.common.math.LongMath;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.SparkReadOptions;
import org.apache.iceberg.spark.SparkTestBaseWithCatalog;
import org.apache.iceberg.spark.SparkWriteOptions;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.SnapshotUtil;
import org.apache.spark.sql.Column;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException;
import org.junit.AfterClass;
import org.junit.Assert;
import org.junit.BeforeClass;
import org.junit.Rule;
import org.junit.Test;
import org.junit.rules.TemporaryFolder;

public class TestDataSourceOptions {
public class TestDataSourceOptions extends SparkTestBaseWithCatalog {

private static final Configuration CONF = new Configuration();
private static final Schema SCHEMA =
Expand Down Expand Up @@ -440,12 +441,46 @@ public void testExtraSnapshotMetadataWithSQL() throws InterruptedException, IOEx
writerThread.setName("test-extra-commit-message-writer-thread");
writerThread.start();
writerThread.join();
Set<String> threadNames = Sets.newHashSet();
for (Snapshot snapshot : table.snapshots()) {
threadNames.add(snapshot.summary().get("writer-thread"));
}
Assert.assertEquals(2, threadNames.size());
Assert.assertTrue(threadNames.contains(null));
Assert.assertTrue(threadNames.contains("test-extra-commit-message-writer-thread"));

List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-writer-thread", snapshots.get(1).summary().get("writer-thread"));
}

@Test
public void testExtraSnapshotMetadataWithDelete()
throws InterruptedException, NoSuchTableException {
spark.sessionState().conf().setConfString("spark.sql.shuffle.partitions", "1");
sql("CREATE TABLE %s (id INT, data STRING) USING iceberg", tableName);
List<SimpleRecord> expectedRecords =
Lists.newArrayList(
new SimpleRecord(1, "a"), new SimpleRecord(2, "b"), new SimpleRecord(3, "c"));
Dataset<Row> originalDf = spark.createDataFrame(expectedRecords, SimpleRecord.class);
originalDf.repartition(5, new Column("data")).select("id", "data").writeTo(tableName).append();
Thread writerThread =
new Thread(
() -> {
Map<String, String> properties = Maps.newHashMap();
properties.put("writer-thread", String.valueOf(Thread.currentThread().getName()));
CommitMetadata.withCommitProperties(
properties,
() -> {
spark.sql("DELETE FROM " + tableName + " where id = 1");
return 0;
},
RuntimeException.class);
});
writerThread.setName("test-extra-commit-message-delete-thread");
writerThread.start();
writerThread.join();

Table table = validationCatalog.loadTable(tableIdent);
List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-delete-thread", snapshots.get(1).summary().get("writer-thread"));
}
}
5 changes: 5 additions & 0 deletions spark/v3.4/spark/src/main/java/org/apache/iceberg/spark/source/SparkTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet;
import org.apache.iceberg.relocated.com.google.common.collect.Iterables;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.Spark3Util;
import org.apache.iceberg.spark.SparkFilters;
import org.apache.iceberg.spark.SparkReadOptions;
Expand Down Expand Up @@ -375,6 +376,10 @@ public void deleteWhere(Filter[] filters) {
deleteFiles.toBranch(branch);
}

if (!CommitMetadata.commitProperties().isEmpty()) {
CommitMetadata.commitProperties().forEach(deleteFiles::set);
}

deleteFiles.commit();
}

Expand Down
55 changes: 45 additions & 10 deletions spark/v3.4/spark/src/test/java/org/apache/iceberg/spark/source/TestDataSourceOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@
import java.math.RoundingMode;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.hadoop.conf.Configuration;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.FileFormat;
Expand All @@ -39,18 +38,20 @@
import org.apache.iceberg.io.CloseableIterable;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.apache.iceberg.relocated.com.google.common.math.LongMath;
import org.apache.iceberg.spark.CommitMetadata;
import org.apache.iceberg.spark.SparkReadOptions;
import org.apache.iceberg.spark.SparkTestBaseWithCatalog;
import org.apache.iceberg.spark.SparkWriteOptions;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.SnapshotUtil;
import org.apache.spark.sql.Column;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.catalyst.analysis.NoSuchTableException;
import org.assertj.core.api.Assertions;
import org.junit.AfterClass;
import org.junit.Assert;
Expand All @@ -59,7 +60,7 @@
import org.junit.Test;
import org.junit.rules.TemporaryFolder;

public class TestDataSourceOptions {
public class TestDataSourceOptions extends SparkTestBaseWithCatalog {

private static final Configuration CONF = new Configuration();
private static final Schema SCHEMA =
Expand Down Expand Up @@ -437,12 +438,46 @@ public void testExtraSnapshotMetadataWithSQL() throws InterruptedException, IOEx
writerThread.setName("test-extra-commit-message-writer-thread");
writerThread.start();
writerThread.join();
Set<String> threadNames = Sets.newHashSet();
for (Snapshot snapshot : table.snapshots()) {
threadNames.add(snapshot.summary().get("writer-thread"));
}
Assert.assertEquals(2, threadNames.size());
Assert.assertTrue(threadNames.contains(null));
Assert.assertTrue(threadNames.contains("test-extra-commit-message-writer-thread"));

List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-writer-thread", snapshots.get(1).summary().get("writer-thread"));
}

@Test
public void testExtraSnapshotMetadataWithDelete()
throws InterruptedException, NoSuchTableException {
spark.sessionState().conf().setConfString("spark.sql.shuffle.partitions", "1");
sql("CREATE TABLE %s (id INT, data STRING) USING iceberg", tableName);
List<SimpleRecord> expectedRecords =
Lists.newArrayList(
new SimpleRecord(1, "a"), new SimpleRecord(2, "b"), new SimpleRecord(3, "c"));
Dataset<Row> originalDf = spark.createDataFrame(expectedRecords, SimpleRecord.class);
originalDf.repartition(5, new Column("data")).select("id", "data").writeTo(tableName).append();
Thread writerThread =
new Thread(
() -> {
Map<String, String> properties = Maps.newHashMap();
properties.put("writer-thread", String.valueOf(Thread.currentThread().getName()));
CommitMetadata.withCommitProperties(
properties,
() -> {
spark.sql("DELETE FROM " + tableName + " where id = 1");
return 0;
},
RuntimeException.class);
});
writerThread.setName("test-extra-commit-message-delete-thread");
writerThread.start();
writerThread.join();

Table table = validationCatalog.loadTable(tableIdent);
List<Snapshot> snapshots = Lists.newArrayList(table.snapshots());
Assert.assertEquals(2, snapshots.size());
Assert.assertNull(snapshots.get(0).summary().get("writer-thread"));
Assert.assertEquals(
"test-extra-commit-message-delete-thread", snapshots.get(1).summary().get("writer-thread"));
}
}