Spark: Support Parquet dictionary encoded UUIDs

While fixing some issues on the PyIceberg ends to fully support UUIDs:
apache/iceberg-python#2007

I noticed this issue, and was suprised since UUID used to work with
Spark, but it turns out that the dictionary encoded UUID was not
implemented yet.

For PyIceberg we only generate little data, so therefore this wasn't
caught previously.

Author: Fokko

arrow/src/main/java/org/apache/iceberg/arrow/vectorized/GenericArrowVectorAccessorFactory.java

@@ -156,7 +156,8 @@ public ArrowVectorAccessor<DecimalT, Utf8StringT, ArrayT, ChildVectorT> getVecto
       switch (primitive.getPrimitiveTypeName()) {
         case FIXED_LEN_BYTE_ARRAY:
         case BINARY:
-          return new DictionaryBinaryAccessor<>((IntVector) vector, dictionary);
+          return new DictionaryBinaryAccessor<>(
+              (IntVector) vector, dictionary, stringFactorySupplier.get());
         case FLOAT:
           return new DictionaryFloatAccessor<>((IntVector) vector, dictionary);
         case INT64:
@@ -452,17 +453,27 @@ private static class DictionaryBinaryAccessor<
       extends ArrowVectorAccessor<DecimalT, Utf8StringT, ArrayT, ChildVectorT> {
     private final IntVector offsetVector;
     private final Dictionary dictionary;
+    private final StringFactory<Utf8StringT> stringFactory;
 
-    DictionaryBinaryAccessor(IntVector vector, Dictionary dictionary) {
+    DictionaryBinaryAccessor(
+        IntVector vector, Dictionary dictionary, StringFactory<Utf8StringT> stringFactory) {
       super(vector);
       this.offsetVector = vector;
       this.dictionary = dictionary;
+      this.stringFactory = stringFactory;
     }
 
     @Override
     public final byte[] getBinary(int rowId) {
       return dictionary.decodeToBinary(offsetVector.get(rowId)).getBytes();
     }
+
+    @Override
+    public Utf8StringT getUTF8String(int rowId) {
+      return null == stringFactory
+          ? super.getUTF8String(rowId)
+          : stringFactory.ofRow(offsetVector, dictionary, rowId);
+    }
   }
 
   private static class DictionaryTimestampInt96Accessor<
@@ -815,6 +826,13 @@ default Utf8StringT ofRow(FixedSizeBinaryVector vector, int rowId) {
               getGenericClass().getSimpleName()));
     }
 
+    /** Create a UTF8 String from the row value in the Dictionary. */
+    default Utf8StringT ofRow(IntVector offsetVector, Dictionary dictionary, int rowId) {
+      throw new UnsupportedOperationException(
+          String.format(
+              "Creating %s from a Dictionary is not supported", getGenericClass().getSimpleName()));
+    }
+
     /** Create a UTF8 String from the byte array. */
     Utf8StringT ofBytes(byte[] bytes);
 

spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ArrowVectorAccessorFactory.java

@@ -22,11 +22,13 @@
 import java.nio.ByteBuffer;
 import org.apache.arrow.memory.ArrowBuf;
 import org.apache.arrow.vector.FixedSizeBinaryVector;
+import org.apache.arrow.vector.IntVector;
 import org.apache.arrow.vector.ValueVector;
 import org.apache.arrow.vector.VarCharVector;
 import org.apache.arrow.vector.complex.ListVector;
 import org.apache.iceberg.arrow.vectorized.GenericArrowVectorAccessorFactory;
 import org.apache.iceberg.util.UUIDUtil;
+import org.apache.parquet.column.Dictionary;
 import org.apache.spark.sql.types.Decimal;
 import org.apache.spark.sql.vectorized.ArrowColumnVector;
 import org.apache.spark.sql.vectorized.ColumnarArray;
@@ -81,6 +83,12 @@ public UTF8String ofRow(FixedSizeBinaryVector vector, int rowId) {
       return UTF8String.fromString(UUIDUtil.convert(vector.get(rowId)).toString());
     }
 
+    @Override
+    public UTF8String ofRow(IntVector offsetVector, Dictionary dictionary, int rowId) {
+      byte[] v = dictionary.decodeToBinary(offsetVector.get(rowId)).getBytes();
+      return UTF8String.fromString(UUIDUtil.convert(v).toString());
+    }
+
     @Override
     public UTF8String ofBytes(byte[] bytes) {
       return UTF8String.fromBytes(bytes);