From 912e00e6e1665b0a9d2e7a9f8b1cee337b93f12d Mon Sep 17 00:00:00 2001
From: Ryan Blue <blue@apache.org>
Date: Wed, 31 Jul 2019 15:14:24 -0700
Subject: [PATCH] Use UnicodeUtil.truncateString for Truncate transform.

This truncates by unicode codepoint instead of Java chars.
---
 api/src/main/java/org/apache/iceberg/transforms/Truncate.java | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/api/src/main/java/org/apache/iceberg/transforms/Truncate.java b/api/src/main/java/org/apache/iceberg/transforms/Truncate.java
index d65d6462c918..2eacaa235e86 100644
--- a/api/src/main/java/org/apache/iceberg/transforms/Truncate.java
+++ b/api/src/main/java/org/apache/iceberg/transforms/Truncate.java
@@ -27,6 +27,7 @@
 import org.apache.iceberg.expressions.Expressions;
 import org.apache.iceberg.expressions.UnboundPredicate;
 import org.apache.iceberg.types.Type;
+import org.apache.iceberg.util.UnicodeUtil;
 
 import static org.apache.iceberg.expressions.Expression.Operation.IS_NULL;
 import static org.apache.iceberg.expressions.Expression.Operation.LT;
@@ -233,7 +234,7 @@ public Integer width() {
 
     @Override
     public CharSequence apply(CharSequence value) {
-      return value.subSequence(0, Math.min(value.length(), length));
+      return UnicodeUtil.truncateString(value, length);
     }
 
     @Override