(iceberg) branch main updated: Data, Orc, Parquet: Throw exception when non-vectorized reader set recordsPerBatch (#15701)

[pvary]

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

pvary pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg.git


The following commit(s) were added to refs/heads/main by this push:
     new 406016bf2a Data, Orc, Parquet: Throw exception when non-vectorized 
reader set recordsPerBatch (#15701)
406016bf2a is described below

commit 406016bf2a60e25db121ee4895f1008037664dc7
Author: GuoYu <511955...@qq.com>
AuthorDate: Sat Mar 21 19:58:36 2026 +0800

    Data, Orc, Parquet: Throw exception when non-vectorized reader set 
recordsPerBatch (#15701)
    
    * Core: Throw exception when non-vectorized set recordsPerBatch
    
    * Remove useless assume
    
    * Remove FEATURE_RECORDS_PER_BATCH
---
 .../apache/iceberg/data/BaseFormatModelTests.java  | 29 +++++++++++++++++++---
 .../org/apache/iceberg/orc/ORCFormatModel.java     |  5 ++++
 .../apache/iceberg/parquet/ParquetFormatModel.java |  5 ++++
 3 files changed, 35 insertions(+), 4 deletions(-)

diff --git 
a/data/src/test/java/org/apache/iceberg/data/BaseFormatModelTests.java 
b/data/src/test/java/org/apache/iceberg/data/BaseFormatModelTests.java
index c9967ebcb1..e295b5fbc1 100644
--- a/data/src/test/java/org/apache/iceberg/data/BaseFormatModelTests.java
+++ b/data/src/test/java/org/apache/iceberg/data/BaseFormatModelTests.java
@@ -24,6 +24,7 @@ import static org.apache.iceberg.TestBase.SCHEMA;
 import static org.assertj.core.api.Assertions.assertThat;
 import static org.assertj.core.api.Assertions.assertThatThrownBy;
 import static org.assertj.core.api.Assumptions.assumeThat;
+import static org.junit.jupiter.api.Assumptions.assumeFalse;
 
 import java.io.IOException;
 import java.util.Arrays;
@@ -72,6 +73,10 @@ public abstract class BaseFormatModelTests<T> {
 
   protected abstract void assertEquals(Schema schema, List<T> expected, 
List<T> actual);
 
+  protected boolean supportsBatchReads() {
+    return false;
+  }
+
   private static final FileFormat[] FILE_FORMATS =
       new FileFormat[] {FileFormat.AVRO, FileFormat.PARQUET, FileFormat.ORC};
 
@@ -85,16 +90,13 @@ public abstract class BaseFormatModelTests<T> {
 
   static final String FEATURE_FILTER = "filter";
   static final String FEATURE_CASE_SENSITIVE = "caseSensitive";
-  static final String FEATURE_RECORDS_PER_BATCH = "recordsPerBatch";
   static final String FEATURE_SPLIT = "split";
   static final String FEATURE_REUSE_CONTAINERS = "reuseContainers";
 
   private static final Map<FileFormat, String[]> MISSING_FEATURES =
       Map.of(
           FileFormat.AVRO,
-          new String[] {
-            FEATURE_FILTER, FEATURE_CASE_SENSITIVE, FEATURE_RECORDS_PER_BATCH, 
FEATURE_SPLIT
-          },
+          new String[] {FEATURE_FILTER, FEATURE_CASE_SENSITIVE, FEATURE_SPLIT},
           FileFormat.ORC,
           new String[] {FEATURE_REUSE_CONTAINERS});
 
@@ -607,6 +609,25 @@ public abstract class BaseFormatModelTests<T> {
     reuseRecords.forEach(r -> assertThat(r).isSameAs(reuseRecords.get(0)));
   }
 
+  @ParameterizedTest
+  @FieldSource("FILE_FORMATS")
+  void testReaderBuilderRecordsPerBatchNotSupported(FileFormat fileFormat) 
throws IOException {
+    assumeFalse(supportsBatchReads(), engineType().getSimpleName() + " 
supports batch reads");
+
+    DataGenerator dataGenerator = new DataGenerators.DefaultSchema();
+    Schema schema = dataGenerator.schema();
+    List<Record> genericRecords = dataGenerator.generateRecords();
+    writeGenericRecords(fileFormat, schema, genericRecords);
+
+    InputFile inputFile = encryptedFile.encryptingOutputFile().toInputFile();
+    assertThatThrownBy(
+            () ->
+                FormatModelRegistry.readBuilder(fileFormat, engineType(), 
inputFile)
+                    .recordsPerBatch(100))
+        .hasMessageContaining("Batch reading is not supported")
+        .isInstanceOf(UnsupportedOperationException.class);
+  }
+
   private void readAndAssertGenericRecords(
       FileFormat fileFormat, Schema schema, List<Record> expected) throws 
IOException {
     InputFile inputFile = encryptedFile.encryptingOutputFile().toInputFile();
diff --git a/orc/src/main/java/org/apache/iceberg/orc/ORCFormatModel.java 
b/orc/src/main/java/org/apache/iceberg/orc/ORCFormatModel.java
index ed5d734ef9..e9d83cb27b 100644
--- a/orc/src/main/java/org/apache/iceberg/orc/ORCFormatModel.java
+++ b/orc/src/main/java/org/apache/iceberg/orc/ORCFormatModel.java
@@ -269,6 +269,11 @@ public class ORCFormatModel<D, S, R>
 
     @Override
     public ReadBuilder<D, S> recordsPerBatch(int numRowsPerBatch) {
+      if (!isBatchReader) {
+        throw new UnsupportedOperationException(
+            "Batch reading is not supported in non-vectorized reader");
+      }
+
       internal.recordsPerBatch(numRowsPerBatch);
       return this;
     }
diff --git 
a/parquet/src/main/java/org/apache/iceberg/parquet/ParquetFormatModel.java 
b/parquet/src/main/java/org/apache/iceberg/parquet/ParquetFormatModel.java
index 90d6e3ef41..fbd7a6e97f 100644
--- a/parquet/src/main/java/org/apache/iceberg/parquet/ParquetFormatModel.java
+++ b/parquet/src/main/java/org/apache/iceberg/parquet/ParquetFormatModel.java
@@ -279,6 +279,11 @@ public class ParquetFormatModel<D, S, R>
 
     @Override
     public ReadBuilder<D, S> recordsPerBatch(int numRowsPerBatch) {
+      if (!isBatchReader) {
+        throw new UnsupportedOperationException(
+            "Batch reading is not supported in non-vectorized reader");
+      }
+
       internal.recordsPerBatch(numRowsPerBatch);
       return this;
     }