Re: RTF - list-item-label encoding (was: RTF and table/column widths (moved from fop-users))

[Andreas L Delmelle <a_...@pandora.be>]

On Feb 28, 2006, at 23:17, Andreas L Delmelle wrote:

> <snip />
> Is it allowed to use unicode escapes in control words? If so, the  
> solution could be as simple as using RTFStringConverter to escape  
> any 'text' if necessary.
>
> In practice, my proposal would come down to

On that note, while browsing through the related sources, found some  
room for minor optimization in the RtfStringConverter itself. If this  
deals with many and/or large portions of text: see below.

If no one objects...

Cheers,

Andreas

Index: src/java/org/apache/fop/render/rtf/rtflib/rtfdoc/ 
RtfStringConverter.java
===================================================================
--- src/java/org/apache/fop/render/rtf/rtflib/rtfdoc/ 
RtfStringConverter.java    (revision 381394)
+++ src/java/org/apache/fop/render/rtf/rtflib/rtfdoc/ 
RtfStringConverter.java    (working copy)
@@ -1,5 +1,5 @@
/*
- * Copyright 1999-2004 The Apache Software Foundation.
+ * Copyright 1999-2006 The Apache Software Foundation.
   *
   * Licensed under the Apache License, Version 2.0 (the "License");
   * you may not use this file except in compliance with the License.
@@ -26,8 +26,6 @@
package org.apache.fop.render.rtf.rtflib.rtfdoc;
-import java.util.Map;
-import java.util.HashMap;
import java.io.IOException;
import java.io.Writer;
@@ -38,23 +36,6 @@
public class RtfStringConverter {
      private static final RtfStringConverter INSTANCE = new  
RtfStringConverter();
-    private static final Map SPECIAL_CHARS;
-    private static final Character DBLQUOTE = new Character('\"');
-    private static final Character QUOTE = new Character('\'');
-    private static final Character SPACE = new Character(' ');
-
-    /** List of characters to escape with corresponding replacement  
strings */
-    static {
-        SPECIAL_CHARS = new HashMap();
-        SPECIAL_CHARS.put(new Character('\t'), "tab");
-        SPECIAL_CHARS.put(new Character('\n'), "line");
-        SPECIAL_CHARS.put(new Character('\''), "rquote");
-        SPECIAL_CHARS.put(new Character('\"'), "rdblquote");
-        SPECIAL_CHARS.put(new Character('\\'), "\\");
-        SPECIAL_CHARS.put(new Character('{'), "{");
-        SPECIAL_CHARS.put(new Character('}'), "}");
-    }
-
      /** singleton pattern */
      private RtfStringConverter() {
      }
@@ -79,43 +60,50 @@
              return;
          }
+        StringBuffer sb = new StringBuffer();
+        String replacement;
+        char c, d;
          // TODO: could be made more efficient (binary lookup, etc.)
-        for (int i = 0; i < str.length(); i++) {
-            final Character c = new Character(str.charAt(i));
-            Character d;
-            String replacement;
-            if (i != 0) {
-                d = new Character(str.charAt(i - 1));
-            } else {
-                d = new Character(str.charAt(i));
+        for (int i = -1; ++i < str.length();) {
+            replacement = null;
+            c = str.charAt(i);
+            switch (c) {
+            case '\"':
+            case '\'':
+                d = str.charAt((i == 0) ? i : i - 1);
+                if (d == ' ') {
+                    replacement = (c == '\"') ? "ldblquote" : "lquote";
+                } else {
+                    replacement = (c == '\"') ? "rdblquote" : "rquote";
+                }
+                break;
+            case '\t':
+                replacement = "tab";
+                break;
+            case '\n':
+                replacement = "line";
+                break;
+            case '\\':
+            case '{':
+            case '}':
+                replacement = "" + c;
+                break;
+            default:
+                //nop
              }
-            //This section modified by Chris Scott
-            //add "smart" quote recognition
-            if (c.equals((Object)DBLQUOTE) && d.equals((Object) 
SPACE)) {
-                replacement = "ldblquote";
-            } else if (c.equals((Object)QUOTE) && d.equals((Object) 
SPACE)) {
-                replacement = "lquote";
-            } else {
-                replacement = (String)SPECIAL_CHARS.get(c);
-            }
-
              if (replacement != null) {
                  // RTF-escaped char
-                w.write('\\');
-                w.write(replacement);
-                w.write(' ');
-            } else if (c.charValue() > 127) {
+                sb.append('\\').append(replacement).append(' ');
+            } else if (c > 127) {
                  // write unicode representation - contributed by  
Michel Jacobson
                  // <ja...@idf.ext.jussieu.fr>
-                w.write("\\u");
-                w.write(Integer.toString((int)c.charValue()));
-                w.write("\\\'3f");
+                sb.append("\\u").append((int) c).append("\\\'3f");
              } else {
                  // plain char that is understood by RTF natively
-                w.write(c.charValue());
+                sb.append(c);
              }
          }
+        w.write(sb.toString());
      }
-
}