Core: Check referencedDataFile existence for DV (#12088)

apache · Jan 28, 2025 · 491d906 · 491d906
1 parent e1d2401
commit 491d906
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 0 deletions.
diff --git a/core/src/main/java/org/apache/iceberg/FileMetadata.java b/core/src/main/java/org/apache/iceberg/FileMetadata.java
@@ -255,6 +255,8 @@ public DeleteFile build() {
       if (format == FileFormat.PUFFIN) {
         Preconditions.checkArgument(contentOffset != null, "Content offset is required for DV");
         Preconditions.checkArgument(contentSizeInBytes != null, "Content size is required for DV");
+        Preconditions.checkArgument(
+            referencedDataFile != null, "Referenced data file is required for DV");
       } else {
         Preconditions.checkArgument(contentOffset == null, "Content offset can only be set for DV");
         Preconditions.checkArgument(

diff --git a/core/src/test/java/org/apache/iceberg/TestDeleteFiles.java b/core/src/test/java/org/apache/iceberg/TestDeleteFiles.java
@@ -37,6 +37,7 @@
 import org.apache.iceberg.relocated.com.google.common.collect.Lists;
 import org.apache.iceberg.types.Types;
 import org.apache.iceberg.util.StructLikeWrapper;
+import org.junit.jupiter.api.Test;
 import org.junit.jupiter.api.TestTemplate;
 import org.junit.jupiter.api.extension.ExtendWith;
 
@@ -443,6 +444,31 @@ public void testDeleteFilesNoValidation() {
     assertThat(delete2.removedDataFiles(FILE_IO)).isEmpty();
   }
 
+  @Test
+  public void testRequiredFieldsForDV() {
+    FileMetadata.Builder builder =
+        FileMetadata.deleteFileBuilder(PartitionSpec.unpartitioned())
+            .ofPositionDeletes()
+            .withFormat(FileFormat.PUFFIN)
+            .withPath("/path/to/data-d-deletes.puffin")
+            .withFileSizeInBytes(4)
+            .withRecordCount(4);
+
+    assertThatThrownBy(builder::build)
+        .isInstanceOf(IllegalArgumentException.class)
+        .hasMessage("Content offset is required for DV");
+
+    builder.withContentOffset(1);
+    assertThatThrownBy(builder::build)
+        .isInstanceOf(IllegalArgumentException.class)
+        .hasMessage("Content size is required for DV");
+
+    builder.withContentSizeInBytes(10);
+    assertThatThrownBy(builder::build)
+        .isInstanceOf(IllegalArgumentException.class)
+        .hasMessage("Referenced data file is required for DV");
+  }
+
   private static ByteBuffer longToBuffer(long value) {
     return ByteBuffer.allocate(8).order(ByteOrder.LITTLE_ENDIAN).putLong(0, value);
   }