GH-3464 Improve DeltaByteArrayWriter.writeBytes to avoid unnecessary allocation and scalar prefix comparison

parquet-column/src/main/java/org/apache/parquet/column/values/deltastrings/DeltaByteArrayWriter.java

@@ -18,6 +18,7 @@
  */
 package org.apache.parquet.column.values.deltastrings;
 
+import java.util.Arrays;
 import org.apache.parquet.bytes.ByteBufferAllocator;
 import org.apache.parquet.bytes.BytesInput;
 import org.apache.parquet.column.Encoding;
@@ -88,14 +89,19 @@ public String memUsageString(String prefix) {
 
   @Override
   public void writeBytes(Binary v) {
-    int i = 0;
-    byte[] vb = v.getBytes();
-    int length = previous.length < vb.length ? previous.length : vb.length;
-    // find the number of matching prefix bytes between this value and the previous one
-    for (i = 0; (i < length) && (previous[i] == vb[i]); i++)
-      ;
+    byte[] vb = v.getBytesUnsafe();
+    int length = Math.min(previous.length, vb.length);
+    // Find the number of matching prefix bytes between this value and the previous one.
+    // Arrays.mismatch is intrinsified by the JVM to use SIMD instructions.
+    int i = Arrays.mismatch(previous, 0, length, vb, 0, length);
+    if (i < 0) {
+      i = length; // all bytes in the common range matched
+    }
     prefixLengthWriter.writeInteger(i);
     suffixWriter.writeBytes(v.slice(i, vb.length - i));
-    previous = vb;
+    // Retain an owned copy for prefix comparison with the next value.
+    // getBytesUnsafe() may return the backing array directly, so we must copy
+    // if the Binary's backing bytes may be reused by the caller.
+    previous = v.isBackingBytesReused() ? v.getBytes() : vb;
   }
 }

parquet-column/src/test/java/org/apache/parquet/column/values/deltastrings/TestDeltaByteArray.java

@@ -19,6 +19,7 @@
 package org.apache.parquet.column.values.deltastrings;
 
 import java.io.IOException;
+import java.nio.charset.StandardCharsets;
 import org.apache.parquet.bytes.ByteBufferInputStream;
 import org.apache.parquet.bytes.DirectByteBufferAllocator;
 import org.apache.parquet.column.values.Utils;
@@ -128,4 +129,24 @@ public void testWriterReset() throws Exception {
 
     assertReadWrite(writer, new DeltaByteArrayReader(), values);
   }
+
+  @Test
+  public void testReusedBackingArrayRegression() throws Exception {
+    DeltaByteArrayWriter writer = new DeltaByteArrayWriter(64 * 1024, 64 * 1024, new DirectByteBufferAllocator());
+    DeltaByteArrayReader reader = new DeltaByteArrayReader();
+
+    byte[] buffer = "parquet-000".getBytes(StandardCharsets.UTF_8);
+    writer.writeBytes(Binary.fromReusedByteArray(buffer));
+
+    System.arraycopy("parquet-111".getBytes(StandardCharsets.UTF_8), 0, buffer, 0, buffer.length);
+    writer.writeBytes(Binary.fromReusedByteArray(buffer));
+
+    System.arraycopy("parquet-222".getBytes(StandardCharsets.UTF_8), 0, buffer, 0, buffer.length);
+    writer.writeBytes(Binary.fromReusedByteArray(buffer));
+
+    Binary[] decoded = Utils.readData(reader, writer.getBytes().toInputStream(), 3);
+    Assert.assertEquals(Binary.fromString("parquet-000"), decoded[0]);
+    Assert.assertEquals(Binary.fromString("parquet-111"), decoded[1]);
+    Assert.assertEquals(Binary.fromString("parquet-222"), decoded[2]);
+  }
 }