src/java.base/share/classes/java/util/zip/ZipCoder.java

*** 1,7 ****
  /*
!  * Copyright (c) 2009, 2011, Oracle and/or its affiliates. All rights reserved.
   * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   *
   * This code is free software; you can redistribute it and/or modify it
   * under the terms of the GNU General Public License version 2 only, as
   * published by the Free Software Foundation.  Oracle designates this
--- 1,7 ----
  /*
!  * Copyright (c) 2009, 2017, Oracle and/or its affiliates. All rights reserved.
   * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
   *
   * This code is free software; you can redistribute it and/or modify it
   * under the terms of the GNU General Public License version 2 only, as
   * published by the Free Software Foundation.  Oracle designates this
*** 41,51 ****
--- 41,78 ----
   * Utility class for zipfile name and comment decoding and encoding
   */
  
  final class ZipCoder {
  
+     private static boolean isASCII(byte[] ba, int off, int len) {
+         for (int i = off; i < off + len; i++) {
+             if (ba[i] < 0)
+                 return false;
+         }
+         return true;
+     }
+ 
+     private static boolean hasReplaceChar(byte[] ba) {
+         for (int i = 0; i < ba.length; i++) {
+             if (ba[i] == (byte)'?')
+                 return true;
+         }
+         return false;
+     }
+ 
      String toString(byte[] ba, int off, int length) {
+ 
+         // fastpath for UTF-8 cs and ascii only name, leverage the
+         // compact string impl to avoid the unnecessary char[] copy/
+         // paste. A temporary workaround before we have better approach,
+         // such as a String constructor that throws exception for
+         // malformed and/or unmappable characters, instead of silently
+         // replacing with repl char
+         if (isUTF8 && isASCII(ba, off, length)) {
+             return new String(ba, off, length, cs);
+         }
+ 
          CharsetDecoder cd = decoder().reset();
          int len = (int)(length * cd.maxCharsPerByte());
          char[] ca = new char[len];
          if (len == 0)
              return new String(ca);
*** 76,85 ****
--- 103,121 ----
      String toString(byte[] ba) {
          return toString(ba, 0, ba.length);
      }
  
      byte[] getBytes(String s) {
+         if (isUTF8) {
+             // fastpath for UTF8. should only occur when the string
+             // has malformed surrogates. A postscan should still be
+             // faster and use less memory.
+             byte[] ba = s.getBytes(cs);
+             if (!hasReplaceChar(ba)) {
+                 return ba;
+             }
+         }
          CharsetEncoder ce = encoder().reset();
          char[] ca = s.toCharArray();
          int len = (int)(ca.length * ce.maxBytesPerChar());
          byte[] ba = new byte[len];
          if (len == 0)