Skip to content

spark 4: add test to verify ignore partition fields that are dropped from the current-schema #13648

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
amogh-jahagirdar merged 2 commits into from
Jul 23, 2025
Merged

spark 4: add test to verify ignore partition fields that are dropped from the current-schema #13648

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4db679c
Ignore partition fields that are dropped from the current-schema
kevinjqliu Jul 23, 2025
f9683cb
spotless
kevinjqliu Jul 23, 2025
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
46 changes: 46 additions & 0 deletions ...ions/src/test/java/org/apache/iceberg/spark/extensions/TestAlterTablePartitionFields.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,13 +20,17 @@

import static org.assertj.core.api.Assertions.assertThat;

import java.time.LocalDateTime;
import java.time.ZoneOffset;
import java.util.List;
import org.apache.iceberg.Parameter;
import org.apache.iceberg.ParameterizedTestExtension;
import org.apache.iceberg.Parameters;
import org.apache.iceberg.PartitionSpec;
import org.apache.iceberg.Table;
import org.apache.iceberg.TableProperties;
import org.apache.iceberg.TestHelpers;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.spark.SparkCatalogConfig;
import org.apache.iceberg.spark.source.SparkTable;
import org.apache.spark.sql.connector.catalog.CatalogManager;
Expand Down Expand Up @@ -583,4 +587,46 @@ private void createTable(String schema, String spec) {
tableName, schema, spec, TableProperties.FORMAT_VERSION, formatVersion);
}
}

private void runCreateAndDropPartitionField(
String column, String partitionType, List<Object[]> expected, String predicate) {
sql("DROP TABLE IF EXISTS %s", tableName);
sql(
"CREATE TABLE %s (col_int INTEGER, col_ts TIMESTAMP_NTZ, col_long BIGINT) USING ICEBERG TBLPROPERTIES ('format-version' = %d)",
tableName, formatVersion);
sql("INSERT INTO %s VALUES (1000, CAST('2024-03-01 19:25:00' as TIMESTAMP), 2100)", tableName);
sql("ALTER TABLE %s ADD PARTITION FIELD %s AS col2_partition", tableName, partitionType);
sql("INSERT INTO %s VALUES (2000, CAST('2024-04-01 19:25:00' as TIMESTAMP), 2200)", tableName);
sql("ALTER TABLE %s DROP PARTITION FIELD col2_partition", tableName);
sql("INSERT INTO %s VALUES (3000, CAST('2024-05-01 19:25:00' as TIMESTAMP), 2300)", tableName);
sql("ALTER TABLE %s DROP COLUMN %s", tableName, column);

assertEquals(
"Should return correct data",
expected,
sql("SELECT * FROM %s WHERE %s ORDER BY col_int", tableName, predicate));
}

@TestTemplate
public void testDropPartitionAndSourceColumnLong() {
String predicateTs = "col_long >= 2200";
List<Object[]> expectedTs =
Lists.newArrayList(new Object[] {2000, 2200L}, new Object[] {3000, 2300L});
runCreateAndDropPartitionField("col_ts", "col_ts", expectedTs, predicateTs);
runCreateAndDropPartitionField("col_ts", "year(col_ts)", expectedTs, predicateTs);
runCreateAndDropPartitionField("col_ts", "month(col_ts)", expectedTs, predicateTs);
runCreateAndDropPartitionField("col_ts", "day(col_ts)", expectedTs, predicateTs);
}

@TestTemplate
public void testDropPartitionAndSourceColumnTimestamp() {
String predicate = "col_ts >= '2024-04-01 19:25:00'";
List<Object[]> expected =
Lists.newArrayList(
new Object[] {2000, LocalDateTime.ofEpochSecond(1711999500, 0, ZoneOffset.UTC)},
new Object[] {3000, LocalDateTime.ofEpochSecond(1714591500, 0, ZoneOffset.UTC)});
runCreateAndDropPartitionField("col_long", "col_long", expected, predicate);
runCreateAndDropPartitionField("col_long", "truncate(2, col_long)", expected, predicate);
runCreateAndDropPartitionField("col_long", "bucket(16, col_long)", expected, predicate);
}
}