HIVE-26713: StringExpr ArrayIndexOutOfBoundsException with LIKE '%xxx%'

storage-api/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/StringExpr.java

@@ -342,7 +342,15 @@ public int find(byte[] input, int start, int len) {
           }
           s_tmp--;
         }
-        next += shift[input[next] & MAX_BYTE];
+
+        // if the character string contains control characters,
+        // overflow occurs.
+        int shiftIndex = input[next] & MAX_BYTE;
+        if (shiftIndex >= MAX_BYTE) {
+          next++;
+        } else {
+          next += shift[shiftIndex];
+        }
       }
       return -1;
     }

storage-api/src/test/org/apache/hadoop/hive/ql/exec/vector/expressions/TestStringExpr.java

@@ -20,6 +20,7 @@
 
 import org.junit.Test;
 
+import java.io.ByteArrayOutputStream;
 import java.nio.charset.StandardCharsets;
 
 import static org.junit.Assert.*;
@@ -49,6 +50,24 @@ public void test() throws Exception {
     assertEquals("Testing match at end of string", 24, find(pattern, input4));
   }
 
+  @Test
+  public void test2() throws Exception {
+    StringExpr.Finder pattern = compile("pattern");
+    assertNotNull(pattern);
+
+    byte b = -1;
+    byte[] controlBytes1 = "abcedf".getBytes(StandardCharsets.UTF_8);
+    byte[] controlBytes2 = "pattern".getBytes(StandardCharsets.UTF_8);
+    ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
+    outputStream.write(controlBytes1);
+    outputStream.write(b);
+    outputStream.write(controlBytes2);
+    byte[] controlChar = outputStream.toByteArray();
+    outputStream.close();
+
+    assertEquals("Testing valid match", 7, pattern.find(controlChar, 0, controlChar.length));
+  }
+
   private StringExpr.Finder compile(String pattern) {
     return StringExpr.compile(pattern.getBytes(StandardCharsets.UTF_8));
   }