Skip to content

[test] Add test case for format read nested type with purning #4210

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
JingsongLi merged 1 commit into from
Sep 19, 2024
Merged

[test] Add test case for format read nested type with purning #4210

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
46 changes: 42 additions & 4 deletions paimon-common/src/test/java/org/apache/paimon/format/FormatReadWriteTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,10 +106,6 @@ public void testSimpleTypes() throws IOException {
GenericRow.of(1, 1L), GenericRow.of(2, 2L), GenericRow.of(3, null));
}

/**
* Currently, Parquet format doesn't support nested row in array, so this test handles Parquet
* specially.
*/
@Test
public void testFullTypes() throws IOException {
RowType rowType = rowTypeForFullTypesTest();
Expand All @@ -133,6 +129,48 @@ public void testFullTypes() throws IOException {
validateFullTypesResult(result.get(0), expected);
}

@Test
public void testNestedReadPruning() throws Exception {
FileFormat format = fileFormat();

RowType writeType =
DataTypes.ROW(
DataTypes.FIELD(0, "f0", DataTypes.INT()),
DataTypes.FIELD(
1,
"f1",
DataTypes.ROW(
DataTypes.FIELD(2, "f0", DataTypes.INT()),
DataTypes.FIELD(3, "f1", DataTypes.INT()),
DataTypes.FIELD(4, "f2", DataTypes.INT()))));

try (PositionOutputStream out = fileIO.newOutputStream(file, false);
FormatWriter writer = format.createWriterFactory(writeType).create(out, "zstd")) {
writer.addElement(GenericRow.of(0, GenericRow.of(10, 11, 12)));
}

// skip read f0, f1.f1
RowType readType =
DataTypes.ROW(
DataTypes.FIELD(
1,
"f1",
DataTypes.ROW(
DataTypes.FIELD(2, "f0", DataTypes.INT()),
DataTypes.FIELD(4, "f2", DataTypes.INT()))));

List<InternalRow> result = new ArrayList<>();
try (RecordReader<InternalRow> reader =
format.createReaderFactory(readType)
.createReader(
new FormatReaderContext(fileIO, file, fileIO.getFileSize(file)))) {
InternalRowSerializer serializer = new InternalRowSerializer(readType);
reader.forEachRemaining(row -> result.add(serializer.copy(row)));
}

assertThat(result).containsExactly(GenericRow.of(GenericRow.of(10, 12)));
}

private RowType rowTypeForFullTypesTest() {
RowType.Builder builder =
RowType.builder()
Expand Down