(arrow-java) branch main updated: GH-704: Fix initialization of offset buffer when exporting VarChar vectors through C Data Interface (#705)

[lidavidm]

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

lidavidm pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-java.git


The following commit(s) were added to refs/heads/main by this push:
     new f92585c2 GH-704: Fix initialization of offset buffer when exporting 
VarChar vectors through C Data Interface (#705)
f92585c2 is described below

commit f92585c272ea4b2db5b1717f6642f3edc8f99903
Author: Kristin Cowalcijk <b...@wherobots.com>
AuthorDate: Tue Apr 8 14:11:32 2025 +0800

    GH-704: Fix initialization of offset buffer when exporting VarChar vectors 
through C Data Interface (#705)
    
    ## What's Changed
    
    This patch fixes the initialization of offset buffers when exporting
    variable width arrays through Arrow C Data Interface. The original code
    incorrectly mess up with the member `this.offsetBuffer` while we should
    actually initialize the newly allocated offsetBuffer. I think the diff
    itself will be quite self-explanatory.
    
    Closes #704 and probably #88 .
---
 .../java/org/apache/arrow/c/RoundtripTest.java     | 23 ++++++++++++++++++++++
 .../arrow/vector/BaseLargeVariableWidthVector.java |  2 +-
 .../arrow/vector/BaseVariableWidthVector.java      |  2 +-
 3 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/c/src/test/java/org/apache/arrow/c/RoundtripTest.java 
b/c/src/test/java/org/apache/arrow/c/RoundtripTest.java
index 67ab282d..6d68449c 100644
--- a/c/src/test/java/org/apache/arrow/c/RoundtripTest.java
+++ b/c/src/test/java/org/apache/arrow/c/RoundtripTest.java
@@ -38,6 +38,8 @@ import org.apache.arrow.memory.ArrowBuf;
 import org.apache.arrow.memory.BufferAllocator;
 import org.apache.arrow.memory.RootAllocator;
 import org.apache.arrow.memory.util.hash.ArrowBufHasher;
+import org.apache.arrow.vector.BaseLargeVariableWidthVector;
+import org.apache.arrow.vector.BaseVariableWidthVector;
 import org.apache.arrow.vector.BigIntVector;
 import org.apache.arrow.vector.BitVector;
 import org.apache.arrow.vector.DateDayVector;
@@ -181,6 +183,13 @@ public class RoundtripTest {
           clazz.isInstance(imported),
           String.format("expected %s but was %s", clazz, imported.getClass()));
       result = VectorEqualsVisitor.vectorEquals(vector, imported);
+
+      if (imported instanceof BaseVariableWidthVector
+          || imported instanceof BaseLargeVariableWidthVector) {
+        ArrowBuf offsetBuffer = imported.getOffsetBuffer();
+        assertTrue(offsetBuffer.capacity() > 0);
+        assertEquals(0, offsetBuffer.getInt(0));
+      }
     }
 
     // Check that the ref counts of the buffers are the same after the 
roundtrip
@@ -602,6 +611,13 @@ public class RoundtripTest {
     }
   }
 
+  @Test
+  public void testEmptyVarCharVector() {
+    try (final VarCharVector vector = new VarCharVector("v", allocator)) {
+      assertTrue(roundtrip(vector, VarCharVector.class));
+    }
+  }
+
   @Test
   public void testLargeVarBinaryVector() {
     try (final LargeVarBinaryVector vector = new LargeVarBinaryVector("", 
allocator)) {
@@ -635,6 +651,13 @@ public class RoundtripTest {
     }
   }
 
+  @Test
+  public void testEmptyLargeVarCharVector() {
+    try (final LargeVarCharVector vector = new LargeVarCharVector("v", 
allocator)) {
+      assertTrue(roundtrip(vector, LargeVarCharVector.class));
+    }
+  }
+
   @Test
   public void testListVector() {
     try (final ListVector vector = ListVector.empty("v", allocator)) {
diff --git 
a/vector/src/main/java/org/apache/arrow/vector/BaseLargeVariableWidthVector.java
 
b/vector/src/main/java/org/apache/arrow/vector/BaseLargeVariableWidthVector.java
index 552a896e..7e0d0aff 100644
--- 
a/vector/src/main/java/org/apache/arrow/vector/BaseLargeVariableWidthVector.java
+++ 
b/vector/src/main/java/org/apache/arrow/vector/BaseLargeVariableWidthVector.java
@@ -496,7 +496,7 @@ public abstract class BaseLargeVariableWidthVector extends 
BaseValueVector
   private ArrowBuf allocateOffsetBuffer(final long size) {
     ArrowBuf offsetBuffer = allocator.buffer(size);
     offsetBuffer.readerIndex(0);
-    initOffsetBuffer();
+    offsetBuffer.setZero(0, offsetBuffer.capacity());
     return offsetBuffer;
   }
 
diff --git 
a/vector/src/main/java/org/apache/arrow/vector/BaseVariableWidthVector.java 
b/vector/src/main/java/org/apache/arrow/vector/BaseVariableWidthVector.java
index aaccec60..7b8d2cdf 100644
--- a/vector/src/main/java/org/apache/arrow/vector/BaseVariableWidthVector.java
+++ b/vector/src/main/java/org/apache/arrow/vector/BaseVariableWidthVector.java
@@ -514,7 +514,7 @@ public abstract class BaseVariableWidthVector extends 
BaseValueVector
     final int curSize = (int) size;
     ArrowBuf offsetBuffer = allocator.buffer(curSize);
     offsetBuffer.readerIndex(0);
-    initOffsetBuffer();
+    offsetBuffer.setZero(0, offsetBuffer.capacity());
     return offsetBuffer;
   }