Skip to content

GH-3043: Ignore V1 level encodings for omitted streams #3867

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
skyon0522-ai wants to merge 1 commit into
base: master
Choose a base branch
from
Open

GH-3043: Ignore V1 level encodings for omitted streams #3867

Show file tree
Hide file tree
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
9 changes: 7 additions & 2 deletions parquet-column/src/main/java/org/apache/parquet/column/impl/ColumnReaderBase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@
import org.apache.parquet.column.values.RequiresPreviousReader;
import org.apache.parquet.column.values.ValuesReader;
import org.apache.parquet.column.values.rle.RunLengthBitPackingHybridDecoder;
import org.apache.parquet.column.values.rle.ZeroIntegerValuesReader;
import org.apache.parquet.io.ParquetDecodingException;
import org.apache.parquet.io.api.Binary;
import org.apache.parquet.io.api.PrimitiveConverter;
Expand Down Expand Up @@ -727,8 +728,12 @@ private void initDataReader(Encoding dataEncoding, ByteBufferInputStream in, int
}

private void readPageV1(DataPageV1 page) {
ValuesReader rlReader = page.getRlEncoding().getValuesReader(path, REPETITION_LEVEL);
ValuesReader dlReader = page.getDlEncoding().getValuesReader(path, DEFINITION_LEVEL);
ValuesReader rlReader = path.getMaxRepetitionLevel() == 0
? new ZeroIntegerValuesReader()
: page.getRlEncoding().getValuesReader(path, REPETITION_LEVEL);
ValuesReader dlReader = path.getMaxDefinitionLevel() == 0
? new ZeroIntegerValuesReader()
: page.getDlEncoding().getValuesReader(path, DEFINITION_LEVEL);
this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader);
this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader);
int valueCount = page.getValueCount();
Expand Down
62 changes: 62 additions & 0 deletions parquet-column/src/test/java/org/apache/parquet/column/impl/TestColumnReaderImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
import org.apache.parquet.column.ColumnDescriptor;
import org.apache.parquet.column.ColumnReader;
import org.apache.parquet.column.Dictionary;
import org.apache.parquet.column.Encoding;
import org.apache.parquet.column.ParquetProperties;
import org.apache.parquet.column.ParquetProperties.WriterVersion;
import org.apache.parquet.column.page.DataPage;
Expand All @@ -44,6 +45,8 @@
import org.apache.parquet.schema.MessageType;
import org.apache.parquet.schema.MessageTypeParser;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.CsvSource;

public class TestColumnReaderImpl {

Expand Down Expand Up @@ -188,6 +191,65 @@ public Dictionary decode(ColumnDescriptor path) {
validateExpectedValuesAndCount(col, pageReader);
}

@ParameterizedTest
@CsvSource({
"required, PLAIN, RLE",
"required, RLE, PLAIN",
"required, PLAIN, PLAIN",
"required, RLE, RLE",
"optional, PLAIN, RLE",
"repeated, RLE, RLE"
})
public void testV1AbsentLevelEncodings(String repetition, Encoding rlEncoding, Encoding dlEncoding)
throws Exception {
MessageType schema = MessageTypeParser.parseMessageType("message test { " + repetition + " double foo; }");
ColumnDescriptor col = schema.getColumns().get(0);
MemPageWriter pageWriter = new MemPageWriter();
ColumnWriterV1 writer = new ColumnWriterV1(
col,
pageWriter,
ParquetProperties.builder()
.withWriterVersion(PARQUET_1_0)
.withDictionaryEncoding(false)
.build());
for (int i = 0; i < 4; i++) {
writer.write(12.5 + i, (i % 2) * col.getMaxRepetitionLevel(), col.getMaxDefinitionLevel());
if (i % 2 == 1) {
writer.writePage();
}
}
writer.finalizeColumnChunk();
writer.close();
assertThat(pageWriter.getPages()).hasSize(2);
List<DataPage> pages = new ArrayList<>();
for (DataPage page : pageWriter.getPages()) {
DataPageV1 v1 = (DataPageV1) page;
assertThat(v1.getValueEncoding()).isEqualTo(Encoding.PLAIN);
if (col.getMaxDefinitionLevel() == 0) {
assertThat(v1.getBytes().size()).isEqualTo(2 * Double.BYTES);
}
pages.add(new DataPageV1(
v1.getBytes(),
v1.getValueCount(),
v1.getUncompressedSize(),
v1.getStatistics(),
rlEncoding,
dlEncoding,
v1.getValueEncoding()));
}
ColumnReader reader = new ColumnReaderImpl(
col,
new MemPageReader(4, pages.iterator(), null),
new PrimitiveConverter() {},
VersionParser.parse(Version.FULL_VERSION));
for (int i = 0; i < 4; i++) {
assertThat(reader.getCurrentRepetitionLevel()).isEqualTo((i % 2) * col.getMaxRepetitionLevel());
assertThat(reader.getCurrentDefinitionLevel()).isEqualTo(col.getMaxDefinitionLevel());
assertThat(reader.getDouble()).isEqualTo(12.5 + i);
reader.consume();
}
}

@Test
public void testSynchronizingLastRowV1() throws Exception {
testSynchronizingReader(PARQUET_1_0, false);
Expand Down