[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserapplications SiteCapturer.java,1.7,1.8

[Derrick O. <der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv28518/htmlparser/src/org/htmlparser/parserapplications

Modified Files:
	SiteCapturer.java 
Log Message:
Update javadocs.
Enable SiteCapturer to handle resource names containing spaces.

Index: SiteCapturer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserapplications/SiteCapturer.java,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** SiteCapturer.java	14 Feb 2005 23:49:24 -0000	1.7
--- SiteCapturer.java	5 Apr 2005 00:48:12 -0000	1.8
***************
*** 345,348 ****
--- 345,395 ----
  
      /**
+      * Unescape a URL to form a file name.
+      * Very crude.
+      * @param raw The escaped URI.
+      * @return The native URI.
+      */
+     protected String decode (String raw)
+     {
+         int length;
+         int start;
+         int index;
+         int value;
+         StringBuffer ret;
+         
+         ret = new StringBuffer (raw.length ());
+ 
+         length = raw.length ();
+         start = 0;
+         while (-1 != (index = raw.indexOf ('%', start)))
+         {   // append the part up to the % sign
+             ret.append (raw.substring (start, index));
+             // there must be two hex digits after the percent sign
+             if (index + 2 < length)
+             {
+                 try
+                 {
+                     value = Integer.parseInt (raw.substring (index + 1, index + 3), 16);
+                     ret.append ((char)value);
+                     start = index + 3;
+                 }
+                 catch (NumberFormatException nfe)
+                 {
+                     ret.append ('%');
+                     start = index + 1;
+                 }
+             }
+             else
+             {   // this case is actually illegal in a URI, but...
+                 ret.append ('%');
+                 start = index + 1;
+             }
+         }
+         ret.append (raw.substring (start));
+         
+         return (ret.toString ());
+     }
+ 
+     /**
       * Copy a resource (image) locally.
       * Removes one element from the 'to be copied' list and saves the
***************
*** 352,355 ****
--- 399,404 ----
      {
          String link;
+         String raw;
+         String name;
          File file;
          File dir;
***************
*** 365,369 ****
          if (getCaptureResources ())
          {
!             file = new File (getTarget (), makeLocalLink (link, ""));
              System.out.println ("copying " + link + " to " + file.getAbsolutePath ());
              // ensure directory exists
--- 414,420 ----
          if (getCaptureResources ())
          {
!             raw = makeLocalLink (link, "");
!             name = decode (raw);
!             file = new File (getTarget (), name);
              System.out.println ("copying " + link + " to " + file.getAbsolutePath ());
              // ensure directory exists