Improved unit test coverage.

markhamstra · Jun 11, 2015 · 4eff7bd · 4eff7bd
1 parent 8e89a3c
commit 4eff7bd
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 2 deletions.
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/types/UTF8StringSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/types/UTF8StringSuite.scala
@@ -44,25 +44,32 @@ class UTF8StringSuite extends SparkFunSuite {
   test("contains") {
     assert(UTF8String.fromString("hello").contains(UTF8String.fromString("ello")))
     assert(!UTF8String.fromString("hello").contains(UTF8String.fromString("vello")))
+    assert(!UTF8String.fromString("hello").contains(UTF8String.fromString("hellooo")))
     assert(UTF8String.fromString("大千世界").contains(UTF8String.fromString("千世")))
     assert(!UTF8String.fromString("大千世界").contains(UTF8String.fromString("世千")))
+    assert(!UTF8String.fromString("大千世界").contains(UTF8String.fromString("大千世界好")))
   }
 
   test("prefix") {
     assert(UTF8String.fromString("hello").startsWith(UTF8String.fromString("hell")))
     assert(!UTF8String.fromString("hello").startsWith(UTF8String.fromString("ell")))
+    assert(!UTF8String.fromString("hello").startsWith(UTF8String.fromString("hellooo")))
     assert(UTF8String.fromString("大千世界").startsWith(UTF8String.fromString("大千")))
     assert(!UTF8String.fromString("大千世界").startsWith(UTF8String.fromString("千")))
+    assert(!UTF8String.fromString("大千世界").startsWith(UTF8String.fromString("大千世界好")))
   }
 
   test("suffix") {
     assert(UTF8String.fromString("hello").endsWith(UTF8String.fromString("ello")))
     assert(!UTF8String.fromString("hello").endsWith(UTF8String.fromString("ellov")))
+    assert(!UTF8String.fromString("hello").endsWith(UTF8String.fromString("hhhello")))
     assert(UTF8String.fromString("大千世界").endsWith(UTF8String.fromString("世界")))
     assert(!UTF8String.fromString("大千世界").endsWith(UTF8String.fromString("世")))
+    assert(!UTF8String.fromString("大千世界").endsWith(UTF8String.fromString("我的大千世界")))
   }
 
   test("slice") {
+    assert(UTF8String.fromString("hello").slice(0, 0) == UTF8String.fromString(""))
     assert(UTF8String.fromString("hello").slice(1, 3) == UTF8String.fromString("el"))
     assert(UTF8String.fromString("大千世界").slice(0, 1) == UTF8String.fromString("大"))
     assert(UTF8String.fromString("大千世界").slice(1, 3) == UTF8String.fromString("千世"))

diff --git a/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java b/unsafe/src/main/java/org/apache/spark/unsafe/types/UTF8String.java
@@ -97,11 +97,11 @@ public byte[] getBytes() {
   /**
    * Returns a substring of this.
    * @param start the position of first code point
-   * @param until the position after last code point
+   * @param until the position after last code point, exclusive.
    */
   public UTF8String slice(final int start, final int until) {
     if (until <= start || start >= bytes.length) {
-      return new UTF8String();
+      return UTF8String.fromBytes(new byte[0]);
     }
 
     int i = 0;