Java: Support creating a scalar from utf8 string (#8294)

This is a small PR to support creating a scalar from an array of utf8 bytes. Since the PR #8257 added the support for ColumnVector creation, so I think we'd better add it for scalar creation to avoid conversions between utf8 strings and Java strings when used in Spark. Signed-off-by: Firestarman <[email protected]> Authors: - Liangcai Li (https://github.com/firestarman) Approvers: - Bobby Wang (https://github.com/wbo4958) URL: #8294
rapidsai · May 20, 2021 · 48647aa · 48647aa
1 parent 2da8473
commit 48647aa
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 1 deletion.
diff --git a/java/src/main/java/ai/rapids/cudf/Scalar.java b/java/src/main/java/ai/rapids/cudf/Scalar.java
@@ -329,10 +329,19 @@ public static Scalar timestampFromLong(DType type, Long value) {
   }
 
   public static Scalar fromString(String value) {
+    return fromUTF8String(value == null ? null : value.getBytes(StandardCharsets.UTF_8));
+  }
+
+  /**
+   * Creates a String scalar from an array of UTF8 bytes.
+   * @param value the array of UTF8 bytes
+   * @return a String scalar
+   */
+  public static Scalar fromUTF8String(byte[] value) {
     if (value == null) {
       return fromNull(DType.STRING);
     }
-    return new Scalar(DType.STRING, makeStringScalar(value.getBytes(StandardCharsets.UTF_8), true));
+    return new Scalar(DType.STRING, makeStringScalar(value, true));
   }
 
   /**

diff --git a/java/src/test/java/ai/rapids/cudf/ScalarTest.java b/java/src/test/java/ai/rapids/cudf/ScalarTest.java
@@ -27,6 +27,7 @@
 import org.junit.jupiter.api.Test;
 
 import java.math.BigDecimal;
+import java.nio.charset.StandardCharsets;
 import java.util.Arrays;
 
 import static ai.rapids.cudf.TableTest.assertColumnsAreEqual;
@@ -244,6 +245,22 @@ public void testString() {
     }
   }
 
+  @Test
+  public void testUTF8String() {
+    try (Scalar s = Scalar.fromUTF8String("TEST".getBytes(StandardCharsets.UTF_8))) {
+      assertEquals(DType.STRING, s.getType());
+      assertTrue(s.isValid());
+      assertEquals("TEST", s.getJavaString());
+      assertArrayEquals(new byte[]{'T', 'E', 'S', 'T'}, s.getUTF8());
+    }
+    try (Scalar s = Scalar.fromUTF8String("".getBytes(StandardCharsets.UTF_8))) {
+      assertEquals(DType.STRING, s.getType());
+      assertTrue(s.isValid());
+      assertEquals("", s.getJavaString());
+      assertArrayEquals(new byte[]{}, s.getUTF8());
+    }
+  }
+
   @Test
   public void testList() {
     // list of int