*** src/demo/org/apache/lucene/demo/html/HTMLParser.jj	Sat Jan 26 10:01:31 2002
--- HTMLParser.jj	Sat Jun 29 18:01:13 2002
***************
*** 66,80 ****
  package org.apache.lucene.demo.html;
  
  import java.io.*;
  
  public class HTMLParser {
    public static int SUMMARY_LENGTH = 200;
!   
    StringBuffer title = new StringBuffer(SUMMARY_LENGTH);
    StringBuffer summary = new StringBuffer(SUMMARY_LENGTH * 2);
    int length = 0;
    boolean titleComplete = false;
    boolean inTitle = false;
    boolean inScript = false;
    boolean afterTag = false;
    boolean afterSpace = false;
--- 66,85 ----
  package org.apache.lucene.demo.html;
  
  import java.io.*;
+ import java.util.Properties;
  
  public class HTMLParser {
    public static int SUMMARY_LENGTH = 200;
! 
    StringBuffer title = new StringBuffer(SUMMARY_LENGTH);
    StringBuffer summary = new StringBuffer(SUMMARY_LENGTH * 2);
+   Properties metaTags=new Properties();
+   String currentMetaTag="";
    int length = 0;
    boolean titleComplete = false;
    boolean inTitle = false;
+   boolean inMetaTag = false;
+   boolean inStyle = false;
    boolean inScript = false;
    boolean afterTag = false;
    boolean afterSpace = false;
***************
*** 99,104 ****
--- 104,124 ----
      return title.toString().trim();
    }
  
+   public Properties getMetaTags() throws IOException,
+ InterruptedException {
+     if (pipeIn == null)
+       getReader();				  // spawn parsing thread
+     while (true) {
+       synchronized(this) {
+ 	if (titleComplete || (length > SUMMARY_LENGTH))
+ 	  break;
+ 	wait(10);
+       }
+     }
+     return metaTags;
+   }
+ 
+ 
    public String getSummary() throws IOException, InterruptedException {
      if (pipeIn == null)
        getReader();				  // spawn parsing thread
***************
*** 124,130 ****
      if (pipeIn == null) {
        pipeIn = new PipedReader();
        pipeOut = new PipedWriter(pipeIn);
!       
        Thread thread = new ParserThread(this);
        thread.start();				  // start parsing
      }
--- 144,150 ----
      if (pipeIn == null) {
        pipeIn = new PipedReader();
        pipeOut = new PipedWriter(pipeIn);
! 
        Thread thread = new ParserThread(this);
        thread.start();				  // start parsing
      }
***************
*** 146,151 ****
--- 166,178 ----
    void addText(String text) throws IOException {
      if (inScript)
        return;
+     if (inStyle)
+       return;
+     if (inMetaTag)
+     {
+ 	metaTags.setProperty(currentMetaTag, text);
+       	return;
+     }
      if (inTitle)
        title.append(text);
      else {
***************
*** 163,169 ****
  
      afterSpace = false;
    }
!   
    void addSpace() throws IOException {
      if (inScript)
        return;
--- 190,196 ----
  
      afterSpace = false;
    }
! 
    void addSpace() throws IOException {
      if (inScript)
        return;
***************
*** 172,178 ****
  	title.append(" ");
        else
  	addToSummary(" ");
!       
        String space = afterTag ? eol : " ";
        length += space.length();
        pipeOut.write(space);
--- 199,205 ----
  	title.append(" ");
        else
  	addToSummary(" ");
! 
        String space = afterTag ? eol : " ";
        length += space.length();
        pipeOut.write(space);
***************
*** 220,225 ****
--- 247,254 ----
  {
    t1=<TagName> {
      inTitle = t1.image.equalsIgnoreCase("<title"); // keep track if in <TITLE>
+     inMetaTag = t1.image.equalsIgnoreCase("<META"); // keep track if in <META>
+     inStyle = t1.image.equalsIgnoreCase("<STYLE"); // keep track if in <STYLE>
      inImg = t1.image.equalsIgnoreCase("<img");	  // keep track if in <IMG>
      if (inScript) {				  // keep track if in <SCRIPT>
        inScript = !t1.image.equalsIgnoreCase("</script");
***************
*** 233,238 ****
--- 262,281 ----
       {
         if (inImg && t1.image.equalsIgnoreCase("alt") && t2 != null)
           addText("[" + t2.image + "]");
+ 
+     	if(inMetaTag &&
+ 			(  t1.image.equalsIgnoreCase("name") ||
+ 			   t1.image.equalsIgnoreCase("HTTP-EQUIV")
+ 			)
+ 	   && t2 != null)
+ 	{
+ 		currentMetaTag=t2.image.toLowerCase();
+ 	}
+     	if(inMetaTag && t1.image.equalsIgnoreCase("content") && t2 !=
+ null)
+ 	{
+ 		addText(t2.image);
+ 	}
       }
      )?
     )?
***************
*** 272,278 ****
   |
    (<Comment2> ( <CommentText2> )* <CommentEnd2>)
  }
!   
  
  TOKEN :
  {
--- 315,321 ----
   |
    (<Comment2> ( <CommentText2> )* <CommentEnd2>)
  }
! 
  
  TOKEN :
  {