Skip to content

GH-3780: validate also writing and reading a file #2

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
jerolba wants to merge 4 commits into
base: pr3781-no-mapreduce-test
Choose a base branch
from
Open

GH-3780: validate also writing and reading a file #2

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
fd8d5a4
Add file read/write test
jerolba Sep 10, 2026
6f204b3
Add missing imports
jerolba Sep 11, 2026
1a1cbfe
Fix spotless issues
jerolba Sep 11, 2026
2ec9b9b
Add missing transitive dependencies
jerolba Sep 11, 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
12 changes: 12 additions & 0 deletions parquet-hadoop-no-mapreduce-test/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,18 @@
</properties>

<dependencies>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-common</artifactId>
<version>${project.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
<version>${project.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
Expand Down
58 changes: 58 additions & 0 deletions ...-test/src/test/java/org/apache/parquet/hadoop/ParquetReadOptionsWithoutMapReduceTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,10 +18,28 @@
*/
package org.apache.parquet.hadoop;

import static org.apache.parquet.schema.Types.primitive;
import static org.assertj.core.api.Assertions.assertThatCode;
import static org.assertj.core.api.Assertions.assertThatThrownBy;
import static org.junit.jupiter.api.Assertions.assertEquals;

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import org.apache.hadoop.conf.Configuration;
import org.apache.parquet.ParquetReadOptions;
import org.apache.parquet.example.data.Group;
import org.apache.parquet.example.data.simple.SimpleGroupFactory;
import org.apache.parquet.hadoop.api.ReadSupport;
import org.apache.parquet.hadoop.example.ExampleParquetWriter;
import org.apache.parquet.hadoop.example.GroupReadSupport;
import org.apache.parquet.hadoop.example.GroupWriteSupport;
import org.apache.parquet.io.LocalInputFile;
import org.apache.parquet.io.LocalOutputFile;
import org.apache.parquet.schema.MessageType;
import org.apache.parquet.schema.PrimitiveType;
import org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName;
import org.apache.parquet.schema.Type.Repetition;
import org.junit.jupiter.api.Test;

class ParquetReadOptionsWithoutMapReduceTest {
Expand All @@ -33,4 +51,44 @@ void buildsReadOptionsWithoutMapReduce() {

assertThatCode(() -> ParquetReadOptions.builder().build()).doesNotThrowAnyException();
}

@Test
void canWriteAndReadFiles() throws IOException {
Path path = Files.createTempDirectory("sample").resolve(java.util.UUID.randomUUID() + ".parquet");
Configuration conf = new Configuration();

PrimitiveType id =
primitive(PrimitiveTypeName.INT32, Repetition.OPTIONAL).named("id");
MessageType schema = new MessageType("schema", id);
GroupWriteSupport.setSchema(schema, conf);

SimpleGroupFactory f = new SimpleGroupFactory(schema);
LocalOutputFile localOutputFile = new LocalOutputFile(path);
try (ParquetWriter<Group> writer =
ExampleParquetWriter.builder(localOutputFile).withConf(conf).build()) {
writer.write(f.newGroup().append("id", 1));
writer.write(f.newGroup().append("id", 2));
}

LocalInputFile readFile = new LocalInputFile(path);
try (ParquetReader<Group> reader =
new GroupReaderBuilder().withFile(readFile).build()) {
Group group1 = reader.read();
assertEquals(1, group1.getInteger("id", 0));
Group group2 = reader.read();
assertEquals(2, group2.getInteger("id", 0));
}
}

public static class GroupReaderBuilder extends ParquetReader.Builder<Group> {

public GroupReaderBuilder() {
super();
}

@Override
public ReadSupport<Group> getReadSupport() {
return new GroupReadSupport();
}
}
}