Skip to content

Core: Fix rewrite_position_delete_files failure with array/map columns #15079

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
bk-mz wants to merge 4 commits into
base: main
Choose a base branch
from
+144 −1
Open

Core: Fix rewrite_position_delete_files failure with array/map columns #15079

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
20e6c8d
Add test reproducing rewrite_position_delete_files failure with array…
bk-mz Jan 19, 2026
aee5b6f
Fix rewrite_position_delete_files failure with array columns
bk-mz Jan 19, 2026
9c4e1c3
Add test for array columns to Spark 3.4, 4.0, and 4.1
bk-mz Jan 19, 2026
1b5cd6c
Remove comments from tests
bk-mz Jan 19, 2026
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
21 changes: 20 additions & 1 deletion api/src/main/java/org/apache/iceberg/expressions/ExpressionUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
import java.time.temporal.ChronoUnit;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.concurrent.TimeUnit;
import java.util.function.Function;
import java.util.regex.Pattern;
Expand All @@ -37,6 +38,7 @@
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.transforms.Transforms;
import org.apache.iceberg.types.Type;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.DateTimeUtil;
import org.apache.iceberg.variants.PhysicalType;
Expand Down Expand Up @@ -737,11 +739,28 @@ private static String sanitizeVariantValue(

private static PartitionSpec identitySpec(Schema schema, int... ids) {
PartitionSpec.Builder specBuilder = PartitionSpec.builderFor(schema);
Map<Integer, Integer> idToParent = TypeUtil.indexParents(schema.asStruct());

for (int id : ids) {
specBuilder.identity(schema.findColumnName(id));
String columnName = schema.findColumnName(id);
if (columnName != null && canBePartitionSource(id, schema, idToParent)) {
specBuilder.identity(columnName);
}
}

return specBuilder.build();
}

private static boolean canBePartitionSource(
int fieldId, Schema schema, Map<Integer, Integer> idToParent) {
Integer parentId = idToParent.get(fieldId);
while (parentId != null) {
Type parentType = schema.findType(parentId);
if (parentType == null || !parentType.isStructType()) {
return false;
}
parentId = idToParent.get(parentId);
}
return true;
}
}
31 changes: 31 additions & 0 deletions ...est/java/org/apache/iceberg/spark/extensions/TestRewritePositionDeleteFilesProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,6 +245,37 @@ public void testRewriteSummary() throws Exception {
EnvironmentContext.ENGINE_VERSION, v -> assertThat(v).startsWith("3.4"));
}

@TestTemplate
public void testRewritePositionDeletesWithArrayColumns() throws Exception {
sql(
"CREATE TABLE %s (id BIGINT, data STRING, items ARRAY<STRUCT<value:BIGINT, count:INT>>) "
+ "USING iceberg TBLPROPERTIES"
+ "('format-version'='2', 'write.delete.mode'='merge-on-read', 'write.update.mode'='merge-on-read')",
tableName);

sql(
"INSERT INTO %s VALUES "
+ "(1, 'a', array(named_struct('value', cast(10 as bigint), 'count', 1))), "
+ "(2, 'b', array(named_struct('value', cast(20 as bigint), 'count', 2))), "
+ "(3, 'c', array(named_struct('value', cast(30 as bigint), 'count', 3))), "
+ "(4, 'd', array(named_struct('value', cast(40 as bigint), 'count', 4))), "
+ "(5, 'e', array(named_struct('value', cast(50 as bigint), 'count', 5))), "
+ "(6, 'f', array(named_struct('value', cast(60 as bigint), 'count', 6)))",
tableName);

sql("DELETE FROM %s WHERE id = 1", tableName);
sql("DELETE FROM %s WHERE id = 2", tableName);

Table table = validationCatalog.loadTable(tableIdent);
assertThat(TestHelpers.deleteFiles(table)).hasSizeGreaterThanOrEqualTo(1);

sql(
"CALL %s.system.rewrite_position_delete_files("
+ "table => '%s',"
+ "options => map('rewrite-all','true'))",
catalogName, tableIdent);
}

private Map<String, String> snapshotSummary() {
return validationCatalog.loadTable(tableIdent).currentSnapshot().summary();
}
Expand Down
31 changes: 31 additions & 0 deletions ...est/java/org/apache/iceberg/spark/extensions/TestRewritePositionDeleteFilesProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,6 +245,37 @@ public void testRewriteSummary() throws Exception {
EnvironmentContext.ENGINE_VERSION, v -> assertThat(v).startsWith("3.5"));
}

@TestTemplate
public void testRewritePositionDeletesWithArrayColumns() throws Exception {
sql(
"CREATE TABLE %s (id BIGINT, data STRING, items ARRAY<STRUCT<value:BIGINT, count:INT>>) "
+ "USING iceberg TBLPROPERTIES"
+ "('format-version'='2', 'write.delete.mode'='merge-on-read', 'write.update.mode'='merge-on-read')",
tableName);

sql(
"INSERT INTO %s VALUES "
+ "(1, 'a', array(named_struct('value', cast(10 as bigint), 'count', 1))), "
+ "(2, 'b', array(named_struct('value', cast(20 as bigint), 'count', 2))), "
+ "(3, 'c', array(named_struct('value', cast(30 as bigint), 'count', 3))), "
+ "(4, 'd', array(named_struct('value', cast(40 as bigint), 'count', 4))), "
+ "(5, 'e', array(named_struct('value', cast(50 as bigint), 'count', 5))), "
+ "(6, 'f', array(named_struct('value', cast(60 as bigint), 'count', 6)))",
tableName);

sql("DELETE FROM %s WHERE id = 1", tableName);
sql("DELETE FROM %s WHERE id = 2", tableName);

Table table = validationCatalog.loadTable(tableIdent);
assertThat(TestHelpers.deleteFiles(table)).hasSizeGreaterThanOrEqualTo(1);

sql(
"CALL %s.system.rewrite_position_delete_files("
+ "table => '%s',"
+ "options => map('rewrite-all','true'))",
catalogName, tableIdent);
}

private Map<String, String> snapshotSummary() {
return validationCatalog.loadTable(tableIdent).currentSnapshot().summary();
}
Expand Down
31 changes: 31 additions & 0 deletions ...est/java/org/apache/iceberg/spark/extensions/TestRewritePositionDeleteFilesProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,6 +245,37 @@ public void testRewriteSummary() throws Exception {
EnvironmentContext.ENGINE_VERSION, v -> assertThat(v).startsWith("4.0"));
}

@TestTemplate
public void testRewritePositionDeletesWithArrayColumns() throws Exception {
sql(
"CREATE TABLE %s (id BIGINT, data STRING, items ARRAY<STRUCT<value:BIGINT, count:INT>>) "
+ "USING iceberg TBLPROPERTIES"
+ "('format-version'='2', 'write.delete.mode'='merge-on-read', 'write.update.mode'='merge-on-read')",
tableName);

sql(
"INSERT INTO %s VALUES "
+ "(1, 'a', array(named_struct('value', cast(10 as bigint), 'count', 1))), "
+ "(2, 'b', array(named_struct('value', cast(20 as bigint), 'count', 2))), "
+ "(3, 'c', array(named_struct('value', cast(30 as bigint), 'count', 3))), "
+ "(4, 'd', array(named_struct('value', cast(40 as bigint), 'count', 4))), "
+ "(5, 'e', array(named_struct('value', cast(50 as bigint), 'count', 5))), "
+ "(6, 'f', array(named_struct('value', cast(60 as bigint), 'count', 6)))",
tableName);

sql("DELETE FROM %s WHERE id = 1", tableName);
sql("DELETE FROM %s WHERE id = 2", tableName);

Table table = validationCatalog.loadTable(tableIdent);
assertThat(TestHelpers.deleteFiles(table)).hasSizeGreaterThanOrEqualTo(1);

sql(
"CALL %s.system.rewrite_position_delete_files("
+ "table => '%s',"
+ "options => map('rewrite-all','true'))",
catalogName, tableIdent);
}

private Map<String, String> snapshotSummary() {
return validationCatalog.loadTable(tableIdent).currentSnapshot().summary();
}
Expand Down
31 changes: 31 additions & 0 deletions ...est/java/org/apache/iceberg/spark/extensions/TestRewritePositionDeleteFilesProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,6 +245,37 @@ public void testRewriteSummary() throws Exception {
EnvironmentContext.ENGINE_VERSION, v -> assertThat(v).startsWith("4.1"));
}

@TestTemplate
public void testRewritePositionDeletesWithArrayColumns() throws Exception {
sql(
"CREATE TABLE %s (id BIGINT, data STRING, items ARRAY<STRUCT<value:BIGINT, count:INT>>) "
+ "USING iceberg TBLPROPERTIES"
+ "('format-version'='2', 'write.delete.mode'='merge-on-read', 'write.update.mode'='merge-on-read')",
tableName);

sql(
"INSERT INTO %s VALUES "
+ "(1, 'a', array(named_struct('value', cast(10 as bigint), 'count', 1))), "
+ "(2, 'b', array(named_struct('value', cast(20 as bigint), 'count', 2))), "
+ "(3, 'c', array(named_struct('value', cast(30 as bigint), 'count', 3))), "
+ "(4, 'd', array(named_struct('value', cast(40 as bigint), 'count', 4))), "
+ "(5, 'e', array(named_struct('value', cast(50 as bigint), 'count', 5))), "
+ "(6, 'f', array(named_struct('value', cast(60 as bigint), 'count', 6)))",
tableName);

sql("DELETE FROM %s WHERE id = 1", tableName);
sql("DELETE FROM %s WHERE id = 2", tableName);

Table table = validationCatalog.loadTable(tableIdent);
assertThat(TestHelpers.deleteFiles(table)).hasSizeGreaterThanOrEqualTo(1);

sql(
"CALL %s.system.rewrite_position_delete_files("
+ "table => '%s',"
+ "options => map('rewrite-all','true'))",
catalogName, tableIdent);
}

private Map<String, String> snapshotSummary() {
return validationCatalog.loadTable(tableIdent).currentSnapshot().summary();
}
Expand Down