[Htmlparser-cvs] htmlparser/src/org/htmlparser Parser.java,1.84,1.85

[<der...@pr...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv19868

Modified Files:
	Parser.java 
Log Message:
Fix RFE #817723 enhancement: add user-agent
Add get/setDefaultRequestProperties() which is used when creating a new connection
to condition the connection prior to connecting.
Currently, the only request property is  "User-Agent", which is set to "HTMLParser/1.4".
Sophisticated users may set other properties to tailor the parser behaviour.



Index: Parser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/Parser.java,v
retrieving revision 1.84
retrieving revision 1.85
diff -C2 -d -r1.84 -r1.85
*** Parser.java	19 Jan 2004 23:14:18 -0000	1.84
--- Parser.java	26 Jan 2004 00:27:34 -0000	1.85
***************
*** 33,36 ****
--- 33,39 ----
  import java.net.URL;
  import java.net.URLConnection;
+ import java.util.HashMap;
+ import java.util.Iterator;
+ import java.util.Map;
  
  import org.htmlparser.filters.TagNameFilter;
***************
*** 98,101 ****
--- 101,114 ----
  
      /**
+      * Default Request header fields.
+      * So far this is just "User-Agent".
+      */
+     protected static Map mDefaultRequestProperties = new HashMap ();
+     static
+     {
+         mDefaultRequestProperties.put ("User-Agent", "HTMLParser/" + VERSION_NUMBER);
+     }
+    
+     /**
       * Feedback object.
       */
***************
*** 161,164 ****
--- 174,241 ----
      }
  
+     /**
+      * Get the current default request header properties.
+      * A String-to-String map of header keys and values.
+      * These fields are set by the parser when creating a connection.
+      */
+     public static Map getDefaultRequestProperties ()
+     {
+         return (mDefaultRequestProperties);
+     }
+ 
+     /**
+      * Set the default request header properties.
+      * A String-to-String map of header keys and values.
+      * These fields are set by the parser when creating a connection.
+      * Some of these can be set directly on a <code>URLConnection</code>,
+      * i.e. If-Modified-Since is set with setIfModifiedSince(long),
+      * but since the parser transparently opens the connection on behalf
+      * of the developer, these properties are not available before the
+      * connection is fetched. Setting these request header fields affects all
+      * subsequent connections opened by the parser. For more direct control
+      * create a <code>URLConnection</code> and set it on the parser.<p>
+      * From <a href="http://www.ietf.org/rfc/rfc2616.txt">RFC 2616 Hypertext Transfer Protocol -- HTTP/1.1</a>: 
+      * <pre>
+      * 5.3 Request Header Fields
+      * 
+      *    The request-header fields allow the client to pass additional
+      *    information about the request, and about the client itself, to the
+      *    server. These fields act as request modifiers, with semantics
+      *    equivalent to the parameters on a programming language method
+      *    invocation.
+      * 
+      *        request-header = Accept                   ; Section 14.1
+      *                       | Accept-Charset           ; Section 14.2
+      *                       | Accept-Encoding          ; Section 14.3
+      *                       | Accept-Language          ; Section 14.4
+      *                       | Authorization            ; Section 14.8
+      *                       | Expect                   ; Section 14.20
+      *                       | From                     ; Section 14.22
+      *                       | Host                     ; Section 14.23
+      *                       | If-Match                 ; Section 14.24
+      *                       | If-Modified-Since        ; Section 14.25
+      *                       | If-None-Match            ; Section 14.26
+      *                       | If-Range                 ; Section 14.27
+      *                       | If-Unmodified-Since      ; Section 14.28
+      *                       | Max-Forwards             ; Section 14.31
+      *                       | Proxy-Authorization      ; Section 14.34
+      *                       | Range                    ; Section 14.35
+      *                       | Referer                  ; Section 14.36
+      *                       | TE                       ; Section 14.39
+      *                       | User-Agent               ; Section 14.43
+      * 
+      *    Request-header field names can be extended reliably only in
+      *    combination with a change in the protocol version. However, new or
+      *    experimental header fields MAY be given the semantics of request-
+      *    header fields if all parties in the communication recognize them to
+      *    be request-header fields. Unrecognized header fields are treated as
+      *    entity-header fields.
+      * </pre>
+      */
+     public static void setDefaultRequestProperties (Map properties)
+     {
+         mDefaultRequestProperties = properties;
+     }
+ 
      //
      // Constructors
***************
*** 500,503 ****
--- 577,583 ----
              ParserException
      {
+         Map properties;
+         String key;
+         String value;
          URLConnection ret;
  
***************
*** 505,508 ****
--- 585,596 ----
          {
              ret = url.openConnection ();
+             properties = getDefaultRequestProperties ();
+             if (null != properties)
+                 for (Iterator iterator = properties.keySet ().iterator (); iterator.hasNext (); )
+                 {
+                     key = (String)iterator.next ();
+                     value = (String)properties.get (key);
+                     ret.setRequestProperty (key, value);
+                 }
          }
          catch (IOException ioe)