(parquet-java) branch master updated: GH-3213: Add the configuration for ByteStreamSplit encoding (#3214)

[gangwu]

This is an automated email from the ASF dual-hosted git repository.

gangwu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/parquet-java.git


The following commit(s) were added to refs/heads/master by this push:
     new dfc025e17 GH-3213: Add the configuration for ByteStreamSplit encoding 
(#3214)
dfc025e17 is described below

commit dfc025e17e21a326addaf0e43c493e085cbac8f4
Author: Joey Tong <joeyut...@gmail.com>
AuthorDate: Sun Nov 9 21:22:31 2025 +0800

    GH-3213: Add the configuration for ByteStreamSplit encoding (#3214)
---
 .../org/apache/parquet/hadoop/ParquetWriter.java   |  5 +++
 .../apache/parquet/hadoop/TestParquetWriter.java   | 38 ++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git 
a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetWriter.java 
b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetWriter.java
index 05f0e2e3a..8eb5f7f17 100644
--- a/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetWriter.java
+++ b/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetWriter.java
@@ -700,6 +700,11 @@ public class ParquetWriter<T> implements Closeable {
       return self();
     }
 
+    public SELF withByteStreamSplitEncoding(String columnPath, boolean 
enableByteStreamSplit) {
+      encodingPropsBuilder.withByteStreamSplitEncoding(columnPath, 
enableByteStreamSplit);
+      return self();
+    }
+
     /**
      * Enable or disable dictionary encoding of the specified column for the 
constructed writer.
      *
diff --git 
a/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java 
b/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java
index 9a69ee478..03cd98ac6 100644
--- 
a/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java
+++ 
b/parquet-hadoop/src/test/java/org/apache/parquet/hadoop/TestParquetWriter.java
@@ -626,6 +626,44 @@ public class TestParquetWriter {
     }
   }
 
+  @Test
+  public void testByteStreamSplitEncodingControl() throws Exception {
+    MessageType schema = Types.buildMessage()
+        .required(FLOAT)
+        .named("float_field")
+        .required(INT32)
+        .named("int32_field")
+        .named("test_schema");
+
+    File file = temp.newFile();
+    temp.delete();
+
+    Path path = new Path(file.getAbsolutePath());
+    SimpleGroupFactory factory = new SimpleGroupFactory(schema);
+    try (ParquetWriter<Group> writer = ExampleParquetWriter.builder(path)
+        .withType(schema)
+        .withByteStreamSplitEncoding(true)
+        .withByteStreamSplitEncoding("int32_field", true)
+        .build()) {
+      writer.write(factory.newGroup().append("float_field", 
0.3f).append("int32_field", 42));
+    }
+
+    try (ParquetFileReader reader = 
ParquetFileReader.open(HadoopInputFile.fromPath(path, new Configuration()))) {
+      for (BlockMetaData block : reader.getFooter().getBlocks()) {
+        for (ColumnChunkMetaData column : block.getColumns()) {
+          
assertTrue(column.getEncodings().contains(Encoding.BYTE_STREAM_SPLIT));
+        }
+      }
+    }
+
+    try (ParquetReader<Group> reader =
+        ParquetReader.builder(new GroupReadSupport(), path).build()) {
+      Group group = reader.read();
+      assertEquals(0.3f, group.getFloat("float_field", 0), 0.0);
+      assertEquals(42, group.getInteger("int32_field", 0));
+    }
+  }
+
   @Test
   public void testV2WriteAllNullValues() throws Exception {
     testV2WriteAllNullValues(null, null);