Skip to content

Add MOR snapshot reads, metadata index pruning, and table statistics to Hudi connector #28511

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
voonhous wants to merge 6 commits into
base: master
Choose a base branch
from
+11,451 −1,372
Open

Add MOR snapshot reads, metadata index pruning, and table statistics to Hudi connector #28511

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0602ec0
Add file abstraction types, core utilities, and inline I/O
voonhous Mar 3, 2026
b24a751
Add MOR (Merge-On-Read) read pipeline
voonhous Mar 3, 2026
d50cfc0
Add index support framework for partition and file pruning
voonhous Mar 3, 2026
5c3f7d7
Add table statistics infrastructure
voonhous Mar 3, 2026
79cafaa
Wire up split generation, indexes, statistics, and configuration
voonhous Mar 3, 2026
996fb72
Add comprehensive test data and smoke tests
voonhous Mar 3, 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
131 changes: 123 additions & 8 deletions plugin/trino-hudi/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,10 +16,18 @@

<properties>
<air.compiler.fail-warnings>true</air.compiler.fail-warnings>
<air.main.basedir>${project.parent.basedir}</air.main.basedir>
<dep.hudi.version>1.1.1</dep.hudi.version>
</properties>

<dependencies>
<dependency>
<!--Used to test execution in task executor after de-serializing-->
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo</artifactId>
<version>4.0.2</version>
</dependency>

<dependency>
<groupId>com.google.errorprone</groupId>
<artifactId>error_prone_annotations</artifactId>
Expand Down Expand Up @@ -67,6 +75,11 @@
<artifactId>units</artifactId>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-cache</artifactId>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-filesystem</artifactId>
Expand Down Expand Up @@ -123,16 +136,64 @@
<version>${dep.hudi.version}</version>
<exclusions>
<exclusion>
<groupId>*</groupId>
<groupId>io.dropwizard.metrics</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hbase</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.orc</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive-sync</artifactId>
<version>${dep.hudi.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-common</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-io</artifactId>
<version>${dep.hudi.version}</version>
<classifier>shaded</classifier>
<exclusions>
<exclusion>
<!-- Conflicts with org.lz4:lz4-java already on the classpath -->
<groupId>at.yawk.lz4</groupId>
<artifactId>lz4-java</artifactId>
</exclusion>
<exclusion>
<groupId>com.google.protobuf</groupId>
<artifactId>protobuf-java</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-sync-common</artifactId>
<version>${dep.hudi.version}</version>
<exclusions>
<exclusion>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-common</artifactId>
</exclusion>
</exclusions>
</dependency>

<dependency>
Expand Down Expand Up @@ -205,6 +266,12 @@
<scope>runtime</scope>
</dependency>

<dependency>
<groupId>io.opentelemetry</groupId>
<artifactId>opentelemetry-sdk-trace</artifactId>
<scope>runtime</scope>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-hive-formats</artifactId>
Expand All @@ -217,13 +284,6 @@
<scope>runtime</scope>
</dependency>

<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo-shaded</artifactId>
<version>4.0.3</version>
<scope>test</scope>
</dependency>

<dependency>
<groupId>io.airlift</groupId>
<artifactId>configuration-testing</artifactId>
Expand All @@ -242,6 +302,19 @@
<scope>test</scope>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-client</artifactId>
<scope>test</scope>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-filesystem</artifactId>
<type>test-jar</type>
<scope>test</scope>
</dependency>

<dependency>
<groupId>io.trino</groupId>
<artifactId>trino-hdfs</artifactId>
Expand Down Expand Up @@ -381,6 +454,13 @@
<scope>test</scope>
</dependency>

<dependency>
<groupId>org.json</groupId>
<artifactId>json</artifactId>
<version>20250107</version>
<scope>test</scope>
</dependency>

<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-api</artifactId>
Expand All @@ -392,6 +472,11 @@
<artifactId>junit-jupiter-engine</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-params</artifactId>
<scope>test</scope>
</dependency>
</dependencies>

<build>
Expand All @@ -418,11 +503,41 @@
<!-- org.apache.hudi:hudi-client-common and org.apache.hudi:hudi-java-client log4j.properties duplicates -->
<ignoredResourcePattern>log4j.properties</ignoredResourcePattern>
<ignoredResourcePattern>log4j-surefire.properties</ignoredResourcePattern>
<!-- about.html is an Eclipse license file bundled by both org.eclipse.jetty and org.glassfish.jersey artifacts -->
<ignoredResourcePattern>about.html</ignoredResourcePattern>
</ignoredResourcePatterns>

<ignoredClassPatterns>
<ignoredClassPattern>org.apache.parquet.conf.ParquetConfiguration</ignoredClassPattern>
</ignoredClassPatterns>

<ignoredDependencies>
<!-- hudi-io:shaded is an uber-jar that physically bundles protobuf .proto resources
inside the jar itself; these cannot be excluded as transitive dependencies -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-io</artifactId>
<classifier>shaded</classifier>
</dependency>
<!-- at.yawk.lz4:lz4-java (from trino-hive-formats) and org.lz4:lz4-java (from hudi-common)
are different group IDs providing the same net.jpountz.* package -->
<dependency>
<groupId>at.yawk.lz4</groupId>
<artifactId>lz4-java</artifactId>
</dependency>
</ignoredDependencies>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<configuration>
<ignoredUnusedDeclaredDependencies>
<!-- Kryo is not directly used but required for compilation:
HoodieRecord implements KryoSerializable, so the compiler
needs Kryo to verify the class hierarchy -->
<ignoredUnusedDeclaredDependency>com.esotericsoftware:kryo</ignoredUnusedDeclaredDependency>
</ignoredUnusedDeclaredDependencies>
</configuration>
</plugin>
</plugins>
Expand Down
Loading
Loading