Add Java-side charset validation before JNI call

thirtiseven · claude · thirtiseven · commit 405c0c7eb313 · 2026-04-03T14:13:05.000+08:00
Co-Authored-By: Claude Opus 4.6 (1M context) &lt;noreply@anthropic.com&gt;
diff --git a/src/main/java/com/nvidia/spark/rapids/jni/CharsetDecode.java b/src/main/java/com/nvidia/spark/rapids/jni/CharsetDecode.java
@@ -34,6 +34,9 @@ public class CharsetDecode {
    * @return UTF-8 string column
    */
   public static ColumnVector decode(ColumnView cv, int charset) {
+    if (charset != GBK) {
+      throw new IllegalArgumentException("Unsupported charset: " + charset);
+    }
     return new ColumnVector(decodeNative(cv.getNativeView(), charset));
   }
 

Original file line number	Diff line number	Diff line change
`@@ -34,6 +34,9 @@ public class CharsetDecode {`
`34`	`34`	`* @return UTF-8 string column`
`35`	`35`	`*/`
`36`	`36`	`public static ColumnVector decode(ColumnView cv, int charset) {`
	`37`	`+ if (charset != GBK) {`
	`38`	`+ throw new IllegalArgumentException("Unsupported charset: " + charset);`
	`39`	`+ }`
`37`	`40`	`return new ColumnVector(decodeNative(cv.getNativeView(), charset));`
`38`	`41`	`}`
`39`	`42`