Commit emails of the iDok project

["AFS account Roman Geus" <geus AT savannah.psi.ch>]

Author: geus
Date: Fri Sep 26 11:49:38 2008
New Revision: 256

Log:
Deleted invalid XML characters from match environment, implemented workaround 
for bug in Restlet 1.1rc2 (incorrect handling of strings containing multibyte 
characters)

Modified:
   
trunk/java/ch/idok/service/server/search/rest/RestSearchServiceResource.java

Modified: 
trunk/java/ch/idok/service/server/search/rest/RestSearchServiceResource.java
==============================================================================
--- 
trunk/java/ch/idok/service/server/search/rest/RestSearchServiceResource.java  
      (original)
+++ 
trunk/java/ch/idok/service/server/search/rest/RestSearchServiceResource.java  
      Fri Sep 26 11:49:38 2008
@@ -78,6 +78,19 @@
     }
 
     /**
+     * Debugging code (will be removed) once the corresponding bug in 
Restlet is
+     * fixed
+     */
+    @GET
+    @Produces("text/plain")
+    public Response dsearch() {
+        String result = "Romän";
+        logger.finest("Length: " + result.length() + " "
+                + result.getBytes().length);
+        return Response.ok().entity(result).build();
+    }
+
+    /**
      * Resource method for all iDok search queries
      * 
      * @param path
@@ -228,7 +241,9 @@
 
                 if ((resultType & SearchService.MATCH_ENVIRONEMENT) != 0) {
                     Element envElement = doc.createElement("Environment");
-                    envElement.setTextContent(hit.getEnvironment());
+                    // Remove possible invalid XML characters in environment
+                    envElement.setTextContent(stripNonValidXMLCharacters(hit
+                            .getEnvironment()));
                     hitElement.appendChild(envElement);
                 }
 
@@ -311,19 +326,58 @@
                 serializer.setOutputProperty(OutputKeys.METHOD, "xml");
                 serializer.setOutputProperty(OutputKeys.ENCODING, 
"ISO-8859-1");
                 // Use of a non-existing DTD will cause JSNOP to fail in IE6
-//                serializer.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM,
-//                        "users.dtd");
+                // serializer.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM,
+                // "users.dtd");
                 serializer.setOutputProperty(OutputKeys.INDENT, "no");
                 serializer.transform(source, streamResult);
-                String json = new JSONObject().put("xml", 
out.toString()).toString();
+                String json = new JSONObject().put("xml", out.toString())
+                        .toString();
                 sb.append(json);
             } catch (Throwable e) {
                 logger.log(Level.FINER, "Could not render XML", e);
                 return RestExceptionResponse.generateXHTML(e);
             }
             sb.append(")");
-            return Response.ok().entity(sb).type("text/javascript").build();
+//            logger.finest(sb.toString());
+//            logger.finest("Length: " + sb.toString().length() + " "
+//                    + sb.toString().getBytes().length);
+            /*
+             * We directly return the byte array since Restlet 1.1rc2
+             * incorrectly deals with strings containing multibyte characters
+             */
+            return Response.ok().entity(sb.toString().getBytes()).type(
+                    "text/javascript").build();
         } else
             return response;
     }
+
+    /**
+     * This method ensures that the output String has only valid XML unicode
+     * characters as specified by the XML 1.0 standard. For reference, please
+     * see <a href="http://www.w3.org/TR/2000/REC-xml-20001006#NT-Char";>the
+     * standard</a>. This method will return an empty String if the input is
+     * null or empty.
+     * 
+     * @param in
+     *            The String whose non-valid characters we want to remove.
+     * @return The in String, stripped of non-valid characters.
+     */
+    public String stripNonValidXMLCharacters(String in) {
+        StringBuffer out = new StringBuffer(); // Used to hold the output.
+        char current; // Used to reference the current character.
+
+        if (in == null || ("".equals(in)))
+            return ""; // vacancy test.
+        for (int i = 0; i < in.length(); i++) {
+            current = in.charAt(i); // NOTE: No IndexOutOfBoundsException 
caught
+            // here; it should not happen.
+            if ((current == 0x9) || (current == 0xA) || (current == 0xD)
+                    || ((current >= 0x20) && (current <= 0xD7FF))
+                    || ((current >= 0xE000) && (current <= 0xFFFD))
+                    || ((current >= 0x10000) && (current <= 0x10FFFF)))
+                out.append(current);
+        }
+        return out.toString();
+    }
+
 }