Skip to content

[DNR]refactor: Update Parquet dependencies #27040

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

Draft
Joe-Abraham wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

[DNR]refactor: Update Parquet dependencies #27040

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
115 changes: 115 additions & 0 deletions presto-parquet/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,124 @@
<artifactId>presto-memory-context</artifactId>
</dependency>

<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
<version>${dep.parquet.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.yetus</groupId>
<artifactId>audience-annotations</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
<version>${dep.parquet.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.yetus</groupId>
<artifactId>audience-annotations</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-common</artifactId>
<version>${dep.parquet.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-format</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.yetus</groupId>
<artifactId>audience-annotations</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-encoding</artifactId>
<version>${dep.parquet.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.yetus</groupId>
<artifactId>audience-annotations</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-format-structures</artifactId>
<version>${dep.parquet.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.yetus</groupId>
<artifactId>audience-annotations</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>com.facebook.presto.hive</groupId>
<artifactId>hive-apache</artifactId>
<scope>test</scope>
<exclusions>
<exclusion>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.avro</groupId>
<artifactId>avro-mapred</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-format-structures</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-common</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>jcl-over-slf4j</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-nop</artifactId>
</exclusion>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
Expand Down
8 changes: 3 additions & 5 deletions presto-parquet/src/main/java/org/apache/parquet/io/ColumnIOConverter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,12 +34,10 @@
import static com.facebook.presto.parquet.ParquetTypeUtils.getArrayElementColumn;
import static com.facebook.presto.parquet.ParquetTypeUtils.getMapKeyValueColumn;
import static com.facebook.presto.parquet.ParquetTypeUtils.lookupColumnByName;
import static org.apache.parquet.io.ColumnIOUtil.columnDefinitionLevel;
import static org.apache.parquet.io.ColumnIOUtil.columnRepetitionLevel;
import static org.apache.parquet.schema.Type.Repetition.OPTIONAL;

/**
* Placed in org.apache.parquet.io package to have access to ColumnIO getRepetitionLevel() and getDefinitionLevel() methods.
* Utility class for converting ColumnIO to Field representations.
*/
public class ColumnIOConverter
{
Expand All @@ -53,8 +51,8 @@ public static Optional<Field> constructField(Type type, ColumnIO columnIO)
return Optional.empty();
}
boolean required = columnIO.getType().getRepetition() != OPTIONAL;
int repetitionLevel = columnRepetitionLevel(columnIO);
int definitionLevel = columnDefinitionLevel(columnIO);
int repetitionLevel = columnIO.getRepetitionLevel();
int definitionLevel = columnIO.getDefinitionLevel();
if (ROW.equals(type.getTypeSignature().getBase())) {
GroupColumnIO groupColumnIO = (GroupColumnIO) columnIO;
List<Type> parameters = type.getTypeParameters();
Expand Down
6 changes: 2 additions & 4 deletions presto-parquet/src/test/java/com/facebook/presto/parquet/reader/TestEncryption.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,6 @@
import static com.facebook.presto.parquet.ParquetTypeUtils.getColumnIO;
import static com.facebook.presto.parquet.ParquetTypeUtils.getMapKeyValueColumn;
import static com.facebook.presto.parquet.ParquetTypeUtils.lookupColumnByName;
import static org.apache.parquet.io.ColumnIOUtil.columnDefinitionLevel;
import static org.apache.parquet.io.ColumnIOUtil.columnRepetitionLevel;
import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.BINARY;
import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.INT32;
import static org.apache.parquet.schema.PrimitiveType.PrimitiveTypeName.INT64;
Expand Down Expand Up @@ -456,8 +454,8 @@ static Optional<Field> constructField(Type type, ColumnIO columnIO)
return Optional.empty();
}
boolean required = columnIO.getType().getRepetition() != OPTIONAL;
int repetitionLevel = columnRepetitionLevel(columnIO);
int definitionLevel = columnDefinitionLevel(columnIO);
int repetitionLevel = columnIO.getRepetitionLevel();
int definitionLevel = columnIO.getDefinitionLevel();
if (type instanceof RowType) {
RowType rowType = (RowType) type;
GroupColumnIO groupColumnIO = (GroupColumnIO) columnIO;
Expand Down
Loading