htmlparser.java

来自「java 写的一个新闻发布系统」· Java 代码 · 共 194 行

//
//                                   ____.
//                       __/\ ______|    |__/\.     _______
//            __   .____|    |       \   |    +----+       \
//    _______|  /--|    |    |    -   \  _    |    :    -   \_________
//   \\______: :---|    :    :           |    :    |         \________>
//           |__\---\_____________:______:    :____|____:_____\
//                                      /_____|
//
//                 . . . i n   j a h i a   w e   t r u s t . . .
//
//--------------------------
// HTMLParser
//--------------------------
// Jerome Bedat 14.12.2000
//--------------------------

package jahiatemplates.org.jahia.portlets_api;

import java.io.*;
import java.util.*;
import org.apache.regexp.*;             // Regular Expression
import org.jahia.utils.*;           // JahiaConsole


public class HTMLParser
{

    private static HTMLParser theObject = null;
    private String newHTML;
    private String newString;
    private String theScripts = "";
    private boolean matched;
    private String theResult;
    
	
    /**
     * HTMLParser
     *
     * @author Jerome Bedat
     *
     */
	private HTMLParser() 
	{
	    JahiaConsole.println( "HTML Parser", "Parsing..." );
	} // end Constructor


    /**
     * getInstance
     *
     * @author Jerome Bedat
     *
     */
	public static synchronized HTMLParser getInstance()
	{
	    if (theObject == null)
	    {
	        theObject = new HTMLParser();
	    }
	    return theObject;
	} // end getInstance


    /**
     * getDHTML  (replace ('")  with \' or \", delete new lines and set the content of script tags to a variable)
     *
     * @author Jerome Bedat
     *
     */   
    public String getDHTML(String oldHTML)
    {
        try 
        {
            newHTML = oldHTML;
            
            RE r = new RE("\\n");
            newHTML = r.subst(newHTML,"");
            
            r = new RE("\\r");
            newHTML = r.subst(newHTML,"");
 
            r = new RE("<script(.*?)</script>", RE.MATCH_CASEINDEPENDENT);
            matched = r.match(newHTML);      
            theResult = r.getParen(0);
            if (theResult != null) { setScripts(theResult); }
            newHTML = r.subst(newHTML,"");
            
            r = new RE("<style(.*?)</style>", RE.MATCH_CASEINDEPENDENT);
            matched = r.match(newHTML);                 
            theResult = r.getParen(0);
            if (theResult != null) { setScripts(theResult); }
            newHTML = r.subst(newHTML,"");

            r = new RE("<link(.*?)>", RE.MATCH_CASEINDEPENDENT);
            matched = r.match(newHTML);                 
            theResult = r.getParen(0);
            if (theResult != null) { setScripts(theResult); }
            newHTML = r.subst(newHTML,"");

            r = new RE("<!(.*?)>");
            newHTML = r.subst(newHTML,"");
            
            r = new RE("\'");
            newHTML = r.subst(newHTML,"\\'");
            
            // r = new RE("\"");
            // newHTML = r.subst(newHTML,"\\\"");
            
        }
        catch (RESyntaxException e)
        {
            JahiaConsole.println("HTML Parser",e.toString());
        }
        return newHTML;
    } // end getDHTML


    /**
     * getQuoteString  (replace ('")  with \' or \"
     *
     * @author Jerome Bedat
     *
     */   
    public String getQuoteString(String oldHTML) 
    {
        try 
        {
            newHTML = oldHTML;
            
            RE r = new RE("\'");
            newHTML = r.subst(newHTML,"\\'");
            
            // r = new RE("\"");
            // newHTML = r.subst(newHTML,"\\\"");
            
        }
        catch (RESyntaxException e)
        {
            JahiaConsole.println("HTML Parser",e.toString());
        }
        return newHTML;
    } // end getQuoteString

 
    /**
     * getHTMLString  (replace (" ")  with "%nbsp;")
     *
     * @author Jerome Bedat
     *
     */
    public String getHTMLString(String oldString) 
    {
        try 
        {
            newString = oldString;
            
            RE r = new RE(" ");
            newString = r.subst(newString,"&nbsp;");
        
        }
        catch (RESyntaxException e)
        {
            JahiaConsole.println("HTML Parser",e.toString());
        }
        return newString;
    } // end getHTMLString
    
    
    /**
     * setScripts  (Set content of script tags to a single variable)
     *
     * @author Jerome Bedat
     *
     */
    private void setScripts(String theScript) {
        theScripts += theScript;
    } // end setScripts


    /**
     * getScripts  (Get content of script tags)
     *
     * @author Jerome Bedat
     *
     */    
    public String getScripts() {
        theResult = theScripts;
        theScripts = ""; 
        return theResult;
    } // end getScripts


}