On 18/10/2009, bay...@apache.org <bay...@apache.org> wrote:
> Author: bayard
>  Date: Sun Oct 18 07:25:59 2009
>  New Revision: 826370
>
>  URL: http://svn.apache.org/viewvc?rev=826370&view=rev
>  Log:
>  Implementing an option to UnicodeUnescaper in which the syntax '\u+0047' is 
> supported. By default it remains unsupported to match Java's method of 
> parsing. Request in LANG-507
>
>  Modified:
>     
> commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnicodeUnescaper.java
>     
> commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnicodeUnescaperTest.java
>
>  Modified: 
> commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnicodeUnescaper.java
>  URL: 
> http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnicodeUnescaper.java?rev=826370&r1=826369&r2=826370&view=diff
>  
> ==============================================================================
>  --- 
> commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnicodeUnescaper.java
>  (original)
>  +++ 
> commons/proper/lang/trunk/src/java/org/apache/commons/lang/text/translate/UnicodeUnescaper.java
>  Sun Oct 18 07:25:59 2009
>  @@ -26,6 +26,15 @@
>   */
>   public class UnicodeUnescaper extends CharSequenceTranslator {
>
>  +    private boolean escapingPlus = false;
>  +
>  +    public void setEscapingPlus(boolean b) {
>  +        this.escapingPlus = b;
>  +    }
>  +    public boolean isEscapingPlus() {
>  +        return this.escapingPlus;
>  +    }
>  +

Would it not be better to make the class immutable (and thread-safe)
by providing the setting as a constructor parameter, rather than as
set/get methods?

>      /**
>       * {...@inheritdoc}
>       */
>  @@ -39,6 +48,13 @@
>                      i++;
>                  }
>
>  +                // consume + symbol in \\u+0045
>  +                if(isEscapingPlus()) {
>  +                    if( (index + i < input.length()) && (input.charAt(index 
> + i) == '+') ) {
>  +                        i++;
>  +                    }
>  +                }
>  +
>                  if( (index + i + 4 <= input.length()) ) {
>                      // Get 4 hex digits
>                      CharSequence unicode = input.subSequence(index + i, 
> index + i + 4);
>  @@ -47,7 +63,7 @@
>                          int value = Integer.parseInt(unicode.toString(), 16);
>                          out.write((char) value);
>                      } catch (NumberFormatException nfe) {
>  -                        throw new RuntimeException("Unable to parse unicode 
> value: " + unicode, nfe);
>  +                        throw new IllegalArgumentException("Unable to parse 
> unicode value: " + unicode, nfe);
>                      }
>                      return i + 4;
>                  } else {
>
>  Modified: 
> commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnicodeUnescaperTest.java
>  URL: 
> http://svn.apache.org/viewvc/commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnicodeUnescaperTest.java?rev=826370&r1=826369&r2=826370&view=diff
>  
> ==============================================================================
>  --- 
> commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnicodeUnescaperTest.java
>  (original)
>  +++ 
> commons/proper/lang/trunk/src/test/org/apache/commons/lang/text/translate/UnicodeUnescaperTest.java
>  Sun Oct 18 07:25:59 2009
>  @@ -27,6 +27,22 @@
>   */
>   public class UnicodeUnescaperTest extends TestCase {
>
>  +    // Requested in LANG-507
>  +    public void testUPlus() throws IOException {
>  +        UnicodeUnescaper uu = new UnicodeUnescaper();
>  +
>  +        String input = "\\u+0047";
>  +        try {
>  +            String result = uu.translate(input);
>  +            fail("Default behaviour should not parse u+");
>  +        } catch(IllegalArgumentException iae) {
>  +            // expected
>  +        }
>  +
>  +        uu.setEscapingPlus(true);
>  +        assertEquals("Failed to unescape unicode characters with 'u+' 
> notation", "G", uu.translate(input));
>  +    }
>  +
>      public void testUuuuu() throws IOException {
>          UnicodeUnescaper uu = new UnicodeUnescaper();
>
>
>
>

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@commons.apache.org
For additional commands, e-mail: dev-h...@commons.apache.org

Reply via email to