=====================================================================
Found a 56 line (309 tokens) duplication in the following files: 
Starting at line 771 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/SiteCapturer.java
Starting at line 142 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/WikiCapturer.java
        worker = new WikiCapturer ();
        if (0 >= args.length)
        {
            url = (String)JOptionPane.showInputDialog (
                null,
                "Enter the URL to capture:",
                "Web Site",
                JOptionPane.PLAIN_MESSAGE,
                null,
                null,
                "http://htmlparser.sourceforge.net/wiki");
            if (null != url)
                worker.setSource (url);
            else
                System.exit (1);
        }
        else
            worker.setSource (args[0]);
        if (1 >= args.length)
        {
            url = worker.getSource ();
            source = new URL (url);
            path = new File (new File ("." + File.separator), source.getHost () + File.separator).getCanonicalPath ();
            target = new File (path);
            chooser = new JFileChooser (target);
            chooser.setDialogType (JFileChooser.SAVE_DIALOG);
            chooser.setFileSelectionMode (JFileChooser.DIRECTORIES_ONLY);
            chooser.setSelectedFile (target); // this doesn't frickin' work
            chooser.setMultiSelectionEnabled (false);
            chooser.setDialogTitle ("Target Directory");
            ret = chooser.showSaveDialog (null);
            if (ret == JFileChooser.APPROVE_OPTION)
                worker.setTarget (chooser.getSelectedFile ().getAbsolutePath ());
            else
                System.exit (1);
        }
        else
            worker.setTarget (args[1]);
        if (2 >= args.length)
        {
            capture = (Boolean)JOptionPane.showInputDialog (
                null,
                "Should resources be captured:",
                "Capture Resources",
                JOptionPane.PLAIN_MESSAGE,
                null,
                new Object[] { Boolean.TRUE, Boolean.FALSE},
                Boolean.TRUE);
            if (null != capture)
                worker.setCaptureResources (capture.booleanValue ());
            else
                System.exit (1);
        }
        else
            worker.setCaptureResources ((Boolean.valueOf (args[2]).booleanValue ()));
        worker.setFilter (
=====================================================================
Found a 56 line (297 tokens) duplication in the following files: 
Starting at line 135 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
Starting at line 199 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
        theirs = sb.toString ();
        match = -1;
        for (int i = mIndex; i < Math.min (mIndex + 25, mNodes.size ()); i++)
        {
            node = (Node)mNodes.elementAt (i);
            ours = node.getText ();
            if (match (theirs, ours))
            {
                match = i;
                break;
            }
        }
        if (-1 == match)
        {
            node = (Node)mNodes.elementAt (mIndex);
            ours = node.getText ();
            System.out.println ("theirs: " + theirs);
            Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
            System.out.println ("ours " + cursor + ": " + ours);
        }
        else
        {
            boolean skipped = false;
            for (int i = mIndex; i < match; i++)
            {
                ours = ((Node)mNodes.elementAt (i)).toHtml ();
                if (0 != ours.trim ().length ())
                {
                    if (!skipped)
                        System.out.println ("skipping:");
                    System.out.println (ours);
                    skipped = true;
                }
            }
            if (skipped)
            {
                System.out.println ("to match:");
                node = (Node)mNodes.elementAt (match);
                Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
                System.out.println ("@" + cursor + ": " + node.toHtml ());
            }
//            System.out.println (" match: " + theirs);
            mIndex = match + 1;
        }
    }

    /**
     * Callback for a start tag lexeme.
     * @param t The tag extracted from the page.
     * @param a The attributes parsed out of the tag.
     * @param pos The position in the page.
     * <em>Note: This differs from the Lexer concept of position which is an
     * absolute location in the HTML input stream. This position is the character
     * position if the text from the page were displayed in a browser.</em>
     */
    public void handleStartTag (HTML.Tag t, MutableAttributeSet a, int pos)
=====================================================================
Found a 56 line (273 tokens) duplication in the following files: 
Starting at line 290 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/StreamTests.java
Starting at line 366 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/StreamTests.java
            (new Thread (stream)).start ();
            assertTrue ("mark not supported", stream.markSupported ());

            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }

            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + index, bytes1.get (index), bytes2.get (index));
                index++;
            }

            bytes1.clear ();
            bytes2.clear ();

            stream.mark (1000); // the 1000 is ignored
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }
            stream.close ();

            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + (index + 1000), bytes1.get (index), bytes2.get (index));
                index++;
            }
        }
        catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }

    /**
     * Test close.
     */
    public void testClose () throws IOException
=====================================================================
Found a 70 line (272 tokens) duplication in the following files: 
Starting at line 118 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/filterbuilder/wrappers/OrFilterWrapper.java
Starting at line 118 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/filterbuilder/wrappers/AndFilterWrapper.java
        mFilter = (AndFilter)filter;
    }

    /**
     * Get the underlying node filter's subordinate filters.
     * @return The node filter object's contained filters.
     */
    public NodeFilter[] getSubNodeFilters ()
    {
        return (mFilter.getPredicates ());
    }

    /**
     * Assign the underlying node filter's subordinate filters.
     * @param filters The filters to insert into the underlying node filter.
     */
    public void setSubNodeFilters (NodeFilter[] filters)
    {
        mFilter.setPredicates (filters);
    }

    /**
     * Convert this filter into Java code.
     * Output whatever text necessary and return the variable name.
     * @param out The output buffer.
     * @param context Three integers as follows:
     * <li>indent level - the number of spaces to insert at the beginning of each line</li>
     * <li>filter number - the next available filter number</li>
     * <li>filter array number - the next available array of filters number</li>
     * @return The variable name to use when referencing this filter (usually "filter" + context[1]++) 
     */
    public String toJavaCode (StringBuffer out, int[] context)
    {
        String array;
        NodeFilter[] predicates;
        String[] names;
        String ret;
        
        predicates = mFilter.getPredicates ();
        array = null; // stoopid Java compiler
        if (0 != predicates.length)
        {
            names = new String[predicates.length];
            for (int i = 0; i < predicates.length; i++)
            {
                names[i] = ((Filter)predicates[i]).toJavaCode (out, context);
            }
            array = "array" + context[2]++;
            spaces (out, context[0]);
            out.append ("NodeFilter[] ");
            out.append (array);
            out.append (" = new NodeFilter[");
            out.append (predicates.length);
            out.append ("];");
            newline (out);
            for (int i = 0; i < predicates.length; i++)
            {
                spaces (out, context[0]);
                out.append (array);
                out.append ("[");
                out.append (i);
                out.append ("] = ");
                out.append (names[i]);
                out.append (";");
                newline (out);
            }
        }
        ret = "filter" + context[1]++;
        spaces (out, context[0]);
        out.append ("AndFilter ");
=====================================================================
Found a 52 line (244 tokens) duplication in the following files: 
Starting at line 268 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
Starting at line 332 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
                ours = ((Attribute)(((Tag)node).getAttributesEx ().elementAt (0))).getName ().substring (1);
                if (match (theirs, ours))
                {
                    match = i;
                    break;
                }
            }
        }
        if (-1 == match)
        {
            node = (Node)mNodes.elementAt (mIndex);
            ours = node.getText ();
            System.out.println ("theirs: " + theirs);
            Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
            System.out.println ("ours " + cursor + ": " + ours);
        }
        else
        {
            boolean skipped = false;
            for (int i = mIndex; i < match; i++)
            {
                ours = ((Node)mNodes.elementAt (i)).toHtml ();
                if (0 != ours.trim ().length ())
                {
                    if (!skipped)
                        System.out.println ("skipping:");
                    System.out.println (ours);
                    skipped = true;
                }
            }
            if (skipped)
            {
                System.out.println ("to match:");
                node = (Node)mNodes.elementAt (match);
                Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
                System.out.println ("@" + cursor + ": " + node.toHtml ());
            }
//            System.out.println (" match: " + theirs);
            mIndex = match + 1;
        }
    }

    /**
     * Callback for a non-composite tag.
     * @param t The tag extracted from the page.
     * @param a The attributes parsed out of the tag.
     * @param pos The position in the page.
     * <em>Note: This differs from the Lexer concept of position which is an
     * absolute location in the HTML input stream. This position is the character
     * position if the text from the page were displayed in a browser.</em>
     */
    public void handleSimpleTag (HTML.Tag t, MutableAttributeSet a, int pos)
=====================================================================
Found a 51 line (243 tokens) duplication in the following files: 
Starting at line 269 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
Starting at line 403 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
                if (match (theirs, ours))
                {
                    match = i;
                    break;
                }
            }
        }
        if (-1 == match)
        {
            node = (Node)mNodes.elementAt (mIndex);
            ours = node.getText ();
            System.out.println ("theirs: " + theirs);
            Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
            System.out.println ("ours " + cursor + ": " + ours);
        }
        else
        {
            boolean skipped = false;
            for (int i = mIndex; i < match; i++)
            {
                ours = ((Node)mNodes.elementAt (i)).toHtml ();
                if (0 != ours.trim ().length ())
                {
                    if (!skipped)
                        System.out.println ("skipping:");
                    System.out.println (ours);
                    skipped = true;
                }
            }
            if (skipped)
            {
                System.out.println ("to match:");
                node = (Node)mNodes.elementAt (match);
                Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
                System.out.println ("@" + cursor + ": " + node.toHtml ());
            }
//            System.out.println (" match: " + theirs);
            mIndex = match + 1;
        }
    }


    /**
     * Callback for an error condition.
     * @param errorMsg The error condition as a text message.
     * @param pos The position in the page.
     * <em>Note: This differs from the Lexer concept of position which is an
     * absolute location in the HTML input stream. This position is the character
     * position if the text from the page were displayed in a browser.</em>
     */
    public void handleError (String errorMsg, int pos)
=====================================================================
Found a 46 line (234 tokens) duplication in the following files: 
Starting at line 292 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/HTMLParserUtilsTest.java
Starting at line 373 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/HTMLParserUtilsTest.java
            NodeFilter filter = new NodeClassFilter (Div.class);
            String[] tmpSplitTags = ParserUtils.splitTags("Begin <DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter);
            assertStringEquals(
                "modified text",
                "Begin * ALL OK",
                new String(tmpSplitTags[0] + '*' + tmpSplitTags[1])
            );
            tmpSplitTags = ParserUtils.splitTags("Begin <DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, false, false);
            assertStringEquals(
                "modified text",
                "Begin *<DIV>  +12.5 </DIV>* ALL OK",
                new String(tmpSplitTags[0] + '*' + tmpSplitTags[1] + '*' + tmpSplitTags[2])
            );
            tmpSplitTags = ParserUtils.splitTags("Begin <DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, true, false);
            assertStringEquals(
                "modified text",
                "Begin *  +12.5 * ALL OK",
                new String(tmpSplitTags[0] + '*' + tmpSplitTags[1] + '*' + tmpSplitTags[2])
            );
            tmpSplitTags = ParserUtils.splitTags("Begin <DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, false, true);
            assertStringEquals(
                "modified text",
                "Begin * ALL OK",
                new String(tmpSplitTags[0] + '*' + tmpSplitTags[1])
            );
            assertStringEquals(
                "modified text",
                " ALL OK",
                ParserUtils.trimTags("<DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter)
            );
            assertStringEquals(
                "modified text",
                "<DIV>  +12.5 </DIV> ALL OK",
                ParserUtils.trimTags("<DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, false, false)
            );
            assertStringEquals(
                "modified text",
                "  +12.5  ALL OK",
                ParserUtils.trimTags("<DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, true, false)
            );
            assertStringEquals(
                "modified text",
                " ALL OK",
                ParserUtils.trimTags("<DIV><DIV>  +12.5 </DIV></DIV> ALL OK", filter, false, true)
            );
            NodeFilter filterTableRow = new NodeClassFilter(TableRow.class);
=====================================================================
Found a 45 line (228 tokens) duplication in the following files: 
Starting at line 145 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
Starting at line 274 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
            }
        }
        if (-1 == match)
        {
            node = (Node)mNodes.elementAt (mIndex);
            ours = node.getText ();
            System.out.println ("theirs: " + theirs);
            Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
            System.out.println ("ours " + cursor + ": " + ours);
        }
        else
        {
            boolean skipped = false;
            for (int i = mIndex; i < match; i++)
            {
                ours = ((Node)mNodes.elementAt (i)).toHtml ();
                if (0 != ours.trim ().length ())
                {
                    if (!skipped)
                        System.out.println ("skipping:");
                    System.out.println (ours);
                    skipped = true;
                }
            }
            if (skipped)
            {
                System.out.println ("to match:");
                node = (Node)mNodes.elementAt (match);
                Cursor cursor = new Cursor (((AbstractNode)node).getPage (), node.getStartPosition ());
                System.out.println ("@" + cursor + ": " + node.toHtml ());
            }
//            System.out.println (" match: " + theirs);
            mIndex = match + 1;
        }
    }

    /**
     * Callback for an end tag lexeme.
     * @param t The tag extracted from the page.
     * @param pos The position in the page.
     * <em>Note: This differs from the Lexer concept of position which is an
     * absolute location in the HTML input stream. This position is the character
     * position if the text from the page were displayed in a browser.</em>
     */
    public void handleEndTag (HTML.Tag t, int pos)
=====================================================================
Found a 33 line (197 tokens) duplication in the following files: 
Starting at line 835 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 1083 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
        StringBuffer output = new StringBuffer();
        
        String dummyString = createDummyString (' ', input.length());

        // loop inside the tags of the same type
        NodeList links = getLinks (input, filter, recursive);
        for (int j=0; j<links.size(); j++)
        {
            CompositeTag beginTag = (CompositeTag)links.elementAt(j);
            Tag endTag = beginTag.getEndTag();

            // positions of begin and end tags
            int beginTagBegin = beginTag.getStartPosition ();
            int endTagBegin = beginTag.getEndPosition ();
            int beginTagEnd = endTag.getStartPosition ();
            int endTagEnd = endTag.getEndPosition ();

            if (insideTag)
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagEnd);
            }
            else
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagBegin);
                dummyString = modifyDummyString (new String(dummyString), beginTagEnd, endTagEnd);
            }
        }
        for (int k=dummyString.indexOf(' '); (k<dummyString.length()) && (k!=-1);)
        {
            int kNew = dummyString.indexOf('*',k);
            if (kNew!=-1)
            {
                output = output.append(input.substring(k,kNew));
=====================================================================
Found a 33 line (191 tokens) duplication in the following files: 
Starting at line 294 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tags/AppletTag.java
Starting at line 396 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tags/ObjectTag.java
        parameters = getObjectParams ();
        params = parameters.keys ();
        if (null == params)
            ret.append ("No Params found.\n");
        else
            for (int cnt = 0; params.hasMoreElements (); cnt++)
            {
                paramName = (String)params.nextElement ();
                paramValue = (String)parameters.get (paramName);
                ret.append (cnt);
                ret.append (": Parameter name = ");
                ret.append (paramName);
                ret.append (", Parameter value = ");
                ret.append (paramValue);
                ret.append ("\n");
            }
        found = false;
        for (SimpleNodeIterator e = children (); e.hasMoreNodes ();)
        {
            node = e.nextNode ();
            if (node instanceof Tag)
                if (((Tag)node).getTagName ().equals ("PARAM"))
                    continue;
            if (!found)
                ret.append ("Miscellaneous items :\n");
            else
                ret.append (" ");
            found = true;
            ret.append (node.toString ());
        }
        if (found)
            ret.append ("\n");
        ret.append ("End of Object Tag\n");
=====================================================================
Found a 29 line (185 tokens) duplication in the following files: 
Starting at line 715 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 984 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
            NodeList links = getLinks (inputModified, tags[i], recursive);
            for (int j=0; j<links.size(); j++)
            {
                CompositeTag beginTag = (CompositeTag)links.elementAt(j);
                Tag endTag = beginTag.getEndTag();

                // positions of begin and end tags
                int beginTagBegin = beginTag.getStartPosition ();
                int endTagBegin = beginTag.getEndPosition ();
                int beginTagEnd = endTag.getStartPosition ();
                int endTagEnd = endTag.getEndPosition ();


                if (insideTag)
                {
                    dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagEnd);
                }
                else
                {
                    dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagBegin);
                    dummyString = modifyDummyString (new String(dummyString), beginTagEnd, endTagEnd);
                }
            }
            for (int k=dummyString.indexOf(' '); (k<dummyString.length()) && (k!=-1);)
            {
                int kNew = dummyString.indexOf('*',k);
                if (kNew!=-1)
                {
                    output = output.append(inputModified.substring(k,kNew));
=====================================================================
Found a 48 line (185 tokens) duplication in the following files: 
Starting at line 118 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 552 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
            if (!(charFound))
            {
                str.append(input.charAt(index));
                toBeAdd=false;
            }
            else
                if (!toBeAdd)
                    toBeAdd=true;
            // finished to parse one string
            if (toBeAdd && (str.length()!=0)) {
                minCapacity++;
                output.ensureCapacity(minCapacity);
                if (output.add(str.toString()))
                    str = new StringBuffer();
                else
                    minCapacity--;
            }
        }
        // add the last string
        if (str.length()!=0) {
            minCapacity++;
            output.ensureCapacity(minCapacity);
            if (output.add(str.toString()))
                str = new StringBuffer();
            else
                minCapacity--;
        }

        output.trimToSize();
        Object[] outputObj = output.toArray();
        String[] outputStr = new String[output.size()];
        for (int i=0; i<output.size(); i++)
            outputStr[i] = new String((String) outputObj[i]);
        return outputStr;
        
    }

    /**
     * Remove from the input string all the chars specified in the input variable charsToBeRemoved.
     * <BR>For example if you call trimChars(&quot;&lt;DIV&gt;  +12.5 &lt;/DIV&gt;&quot;, &quot;<>DIV/ &quot;),
     * <BR>you obtain a string &quot;+12.5&quot; as output (&lt;,&gt;,D,I,V,/ and space char are chars that must be removed).
     * <BR>For example if you call trimChars(&quot;&lt;DIV&gt;  Trim All Chars Also The Ones Inside The String &lt;/DIV&gt;&quot;, &quot;<>DIV/ &quot;),
     * <BR>you obtain a string &quot;TrimAllCharsAlsoTheOnesInsideTheString&quot; as output (all the spaces inside the string are removed).
     * @param input The string in input.
     * @param charsToBeRemoved The chars to be removed.
     * @return The string as output.
    */
    public static String trimChars (String input, String charsToBeRemoved)
=====================================================================
Found a 38 line (184 tokens) duplication in the following files: 
Starting at line 826 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/lexer/Page.java
Starting at line 103 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/LinkProcessor.java
        return (string);
    }

    /**
     * @deprecated Use Page.constructUrl() instead.
     */
    public URL constructUrl(String link, String base)
        throws MalformedURLException {
        String path;
        boolean modified;
        boolean absolute;
        int index;
        URL url; // constructed URL combining relative link and base
        url = new URL (new URL (base), link);
        path = url.getFile ();
        modified = false;
        absolute = link.startsWith ("/");
        if (!absolute) {   // we prefer to fix incorrect relative links
            // this doesn't fix them all, just the ones at the start
            while (path.startsWith ("/.")) {
                if (path.startsWith ("/../")) {
                    path = path.substring (3);
                    modified = true;
                }
                else if (path.startsWith ("/./") || path.startsWith("/.")) {
                    path = path.substring (2);
                    modified = true;
                } else break;
            }
        }
        // fix backslashes
        while (-1 != (index = path.indexOf ("/\\"))) {
            path = path.substring (0, index + 1) + path.substring (index + 2);
            modified = true;
        }
        if (modified)
            url = new URL (url, path);
        return url;
=====================================================================
Found a 49 line (183 tokens) duplication in the following files: 
Starting at line 118 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 263 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
            if (!((Character.isWhitespace(input.charAt(index))) || (Character.isSpaceChar(input.charAt(index))) || (charFound)))
            {
                str.append(input.charAt(index));
                toBeAdd=false;
            }
            else
                if (!toBeAdd)
                    toBeAdd=true;
            // finished to parse one string
            if (toBeAdd && (str.length()!=0)) {
                minCapacity++;
                output.ensureCapacity(minCapacity);
                if (output.add(str.toString()))
                    str = new StringBuffer();
                else
                    minCapacity--;
            }
        }
        // add the last string
        if (str.length()!=0) {
            minCapacity++;
            output.ensureCapacity(minCapacity);
            if (output.add(str.toString()))
                str = new StringBuffer();
            else
                minCapacity--;
        }

        output.trimToSize();
        Object[] outputObj = output.toArray();
        String[] outputStr = new String[output.size()];
        for (int i=0; i<output.size(); i++)
            outputStr[i] = new String((String) outputObj[i]);
        return outputStr;
        
    }

    /**
     * Remove from the input string all the spaces and tabs like chars.
     * Remove also the chars specified in the input variable charsToBeRemoved.
     * <BR>For example if you call trimSpaces(&quot;&lt;DIV&gt;  +12.5 &lt;/DIV&gt;&quot;, &quot;&lt;>DIV/&quot;),
     * <BR>you obtain a string &quot;+12.5&quot; as output (space chars and &lt;,&gt;,D,I,V,/ are chars that must be removed).
     * <BR>For example if you call trimSpaces(&quot;&lt;DIV&gt;  Trim All Spaces Also The Ones Inside The String &lt;/DIV&gt;&quot;, &quot;&lt;>DIV/&quot;),
     * <BR>you obtain a string &quot;TrimAllSpacesAlsoTheOnesInsideTheString&quot; as output (all the spaces inside the string are removed).
     * @param input The string in input.
     * @param charsToBeRemoved The chars to be removed.
     * @return The string as output.
    */
    public static String trimSpaces (String input, String charsToBeRemoved)
=====================================================================
Found a 43 line (182 tokens) duplication in the following files: 
Starting at line 1209 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
Starting at line 1314 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
        String string;

        random = new Random ();
        list = getReferences ();
        stimulus = new StringBuffer ();
        response = new StringBuffer ();
        for (int i = 0; i < 1000; i++)
        {
            for (int j = 0; j < 10; j++)
            {
                // some random characters
                for (int k = 0; k < 10; k++)
                {
                    character = (char)random.nextInt (127);
                    if (character >= ' ')
                    {
                        if ('&' == character)
                        {
                            stimulus.append (character);
                            response.append ("&amp;");
                        }
                        else if ('"' == character)
                        {
                            stimulus.append (character);
                            response.append ("&quot;");
                        }
                        else if ('<' == character)
                        {
                            stimulus.append (character);
                            response.append ("&lt;");
                        }
                        else if ('>' == character)
                        {
                            stimulus.append (character);
                            response.append ("&gt;");
                        }
                        else
                        {
                            stimulus.append (character);
                            response.append (character);
                        }
                    }
                }
=====================================================================
Found a 49 line (182 tokens) duplication in the following files: 
Starting at line 118 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 408 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
            if (charFound)
            {
                str.append(input.charAt(index));
                toBeAdd=false;
            }
            else
                if (!toBeAdd)
                    toBeAdd=true;
            // finished to parse one string
            if (toBeAdd && (str.length()!=0)) {
                minCapacity++;
                output.ensureCapacity(minCapacity);
                if (output.add(str.toString()))
                    str = new StringBuffer();
                else
                    minCapacity--;
            }
        }
        // add the last string
        if (str.length()!=0) {
            minCapacity++;
            output.ensureCapacity(minCapacity);
            if (output.add(str.toString()))
                str = new StringBuffer();
            else
                minCapacity--;
        }

        output.trimToSize();
        Object[] outputObj = output.toArray();
        String[] outputStr = new String[output.size()];
        for (int i=0; i<output.size(); i++)
            outputStr[i] = new String((String) outputObj[i]);
        return outputStr;
        
    }
    
    /**
     * Remove from the input string all the characters
     * with the only exception of the characters specified in charsDoNotBeRemoved param.
     * <BR>For example if you call trimButChars(&quot;&lt;DIV&gt;  +12.5 &lt;/DIV&gt;&quot;, &quot;+.1234567890&quot;),
     * <BR>you obtain a string &quot;+12.5&quot; as output (+,.,1,2,3,4,5,6,7,8,9,0 are chars that do not be removed).
     * <BR>For example if you call trimButChars(&quot;&lt;DIV&gt;  +1 2 . 5 &lt;/DIV&gt;&quot;, &quot;+.1234567890&quot;),
     * <BR>you obtain a string &quot;+12.5&quot; as output (the spaces between 1 and 2, 2 and ., . and 5 are removed).
     * @param input The string in input.
     * @param charsDoNotBeRemoved The chars that do not be removed.
     * @return The string as output.
    */
    public static String trimButChars (String input, String charsDoNotBeRemoved)
=====================================================================
Found a 28 line (178 tokens) duplication in the following files: 
Starting at line 984 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 1088 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
        NodeList links = getLinks (input, filter, recursive);
        for (int j=0; j<links.size(); j++)
        {
            CompositeTag beginTag = (CompositeTag)links.elementAt(j);
            Tag endTag = beginTag.getEndTag();

            // positions of begin and end tags
            int beginTagBegin = beginTag.getStartPosition ();
            int endTagBegin = beginTag.getEndPosition ();
            int beginTagEnd = endTag.getStartPosition ();
            int endTagEnd = endTag.getEndPosition ();

            if (insideTag)
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagEnd);
            }
            else
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagBegin);
                dummyString = modifyDummyString (new String(dummyString), beginTagEnd, endTagEnd);
            }
        }
        for (int k=dummyString.indexOf(' '); (k<dummyString.length()) && (k!=-1);)
        {
            int kNew = dummyString.indexOf('*',k);
            if (kNew!=-1)
            {
                output = output.append(input.substring(k,kNew));
=====================================================================
Found a 28 line (174 tokens) duplication in the following files: 
Starting at line 715 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 840 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
        NodeList links = getLinks (input, filter, recursive);
        for (int j=0; j<links.size(); j++)
        {
            CompositeTag beginTag = (CompositeTag)links.elementAt(j);
            Tag endTag = beginTag.getEndTag();

            // positions of begin and end tags
            int beginTagBegin = beginTag.getStartPosition ();
            int endTagBegin = beginTag.getEndPosition ();
            int beginTagEnd = endTag.getStartPosition ();
            int endTagEnd = endTag.getEndPosition ();

            if (insideTag)
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagEnd);
            }
            else
            {
                dummyString = modifyDummyString (new String(dummyString), beginTagBegin, endTagBegin);
                dummyString = modifyDummyString (new String(dummyString), beginTagEnd, endTagEnd);
            }
        }
        for (int k=dummyString.indexOf(' '); (k<dummyString.length()) && (k!=-1);)
        {
            int kNew = dummyString.indexOf('*',k);
            if (kNew!=-1)
            {
                output = input.substring(k,kNew);
=====================================================================
Found a 22 line (157 tokens) duplication in the following files: 
Starting at line 54 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/PerformanceTest.java
Starting at line 80 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/PerformanceTest.java
        System.out.println("*    Test With Scanners Registered    *");
        System.out.println("***************************************");
        for (int i=0;i<=numTimes;i++) {
            // Create the parser object
            parser = new Parser(file,new DefaultParserFeedback());
            long start=System.currentTimeMillis();
            for (NodeIterator e = parser.elements();e.hasMoreNodes();)
                e.nextNode();
            long elapsedTime=System.currentTimeMillis()-start;
            if (i!=0)
            sumTimes += elapsedTime;
            System.out.print("Iteration "+i);
            if (i==0) System.out.print(" (not counted)");
            System.out.println(" : time taken = "+elapsedTime+" ms");
        }
        avg = sumTimes/(float)numTimes;
        System.out.println("***************************************");
        System.out.println("Average Time : "+avg+" ms");
        System.out.println("***************************************");
    }

    public static void main(String[] args) {
=====================================================================
Found a 34 line (153 tokens) duplication in the following files: 
Starting at line 1158 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 1198 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
        links = parser.extractAllNodesThatMatch(filter);

        // loop to remove tags added recursively
        // so if you have selected 'not recursive option'
        // you have only the tag container and not the contained tags.
        if (!recursive)
        {
            for (int j=0; j<links.size(); j++)
            {
                CompositeTag jStartTag = (CompositeTag)links.elementAt(j);
                Tag jEndTag = jStartTag.getEndTag();
                int jStartTagBegin = jStartTag.getStartPosition ();
                int jEndTagEnd = jEndTag.getEndPosition ();
                for (int k=0; k<links.size(); k++)
                {
                    CompositeTag kStartTag = (CompositeTag)links.elementAt(k);
                    Tag kEndTag = kStartTag.getEndTag();
                    int kStartTagBegin = kStartTag.getStartPosition ();
                    int kEndTagEnd = kEndTag.getEndPosition ();
                    if ((k!=j) && (kStartTagBegin>jStartTagBegin) && (kEndTagEnd<jEndTagEnd))
                    {
                        links.remove(k);
                        k--;
                        j--;
                    }
                }
            }
        }
        
        return links;
        
    }
    
    private static String createDummyString (char fillingChar, int length)
=====================================================================
Found a 18 line (147 tokens) duplication in the following files: 
Starting at line 258 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
Starting at line 524 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
        source = new StringSource (reference);
        buffer = new char[reference.length ()];
        for (int i = 0; i < part1.length (); i++)
            buffer[i] = (char)source.read ();
        length = source.read (buffer, part1.length (), part2.length ());
        assertTrue ("incorrect length", part2.length () == length);
        length += part1.length ();
        for (int i = 0; i < part3.length (); i++)
            buffer[i + length] = (char)source.read ();
        assertTrue ("string incorrect", reference.equals (new String (buffer)));
        assertTrue ("extra character", -1 == source.read ());
        source.close ();
    }

    /**
     * Test ready of a StringSource.
     */
    public void testStringSourceReady () throws IOException
=====================================================================
Found a 16 line (139 tokens) duplication in the following files: 
Starting at line 47 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
Starting at line 105 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
Starting at line 178 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
    public void testChangeAppletParams() throws ParserException {
        String [][]paramsData = {{"Param1","Value1"},{"Name","Somik"},{"Age","23"}};
        Hashtable paramsMap = new Hashtable();
        String testHTML = new String("<APPLET CODE=Myclass.class ARCHIVE=test.jar CODEBASE=www.kizna.com>\n");
        for (int i = 0;i<paramsData.length;i++)
        {
            testHTML+="<PARAM NAME=\""+paramsData[i][0]+"\" VALUE=\""+paramsData[i][1]+"\">\n";
            paramsMap.put(paramsData[i][0],paramsData[i][1]);
        }
        testHTML+=
            "</APPLET>\n"+
            "</HTML>";
        createParser(testHTML);
        parseAndAssertNodeCount(3);
        assertTrue("Node should be an applet tag",node[0] instanceof AppletTag);
        AppletTag appletTag = (AppletTag)node[0];
=====================================================================
Found a 36 line (137 tokens) duplication in the following files: 
Starting at line 1256 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
Starting at line 1395 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
                while (0 != character);
                // some more random characters
                for (int k = 0; k < 10; k++)
                {
                    character = (char)random.nextInt (127);
                    if (character >= ' ')
                    {
                        if ('&' == character)
                        {
                            stimulus.append (character);
                            response.append ("&amp;");
                        }
                        else if ('"' == character)
                        {
                            stimulus.append (character);
                            response.append ("&quot;");
                        }
                        else if ('<' == character)
                        {
                            stimulus.append (character);
                            response.append ("&lt;");
                        }
                        else if ('>' == character)
                        {
                            stimulus.append (character);
                            response.append ("&gt;");
                        }
                        else
                        {
                            stimulus.append (character);
                            response.append (character);
                        }
                    }
                }
            }
            string = Translate.decode (response.toString ());
=====================================================================
Found a 32 line (131 tokens) duplication in the following files: 
Starting at line 1220 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
Starting at line 1258 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java
                for (int k = 0; k < 10; k++)
                {
                    character = (char)random.nextInt (127);
                    if (character >= ' ')
                    {
                        if ('&' == character)
                        {
                            stimulus.append (character);
                            response.append ("&amp;");
                        }
                        else if ('"' == character)
                        {
                            stimulus.append (character);
                            response.append ("&quot;");
                        }
                        else if ('<' == character)
                        {
                            stimulus.append (character);
                            response.append ("&lt;");
                        }
                        else if ('>' == character)
                        {
                            stimulus.append (character);
                            response.append ("&gt;");
                        }
                        else
                        {
                            stimulus.append (character);
                            response.append (character);
                        }
                    }
                }
=====================================================================
Found a 39 line (128 tokens) duplication in the following files: 
Starting at line 572 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/beans/StringBean.java
Starting at line 293 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/beans/FilterBean.java
        }
    }

    /**
     * Get the current connection.
     * @return The connection that the parser has or <code>null</code> if it
     * hasn't been set or the parser hasn't been constructed yet.
     */
    public URLConnection getConnection ()
    {
        return ((null != mParser) ? mParser.getConnection () : null);
    }

    /**
     * Set the parser's connection.
     * The text from the URL will be fetched, which may be expensive, so this
     * property should be set last.
     * @param connection New value of property Connection.
     */
    public void setConnection (URLConnection connection)
    {
        String url;
        URLConnection conn;

        url = getURL ();
        conn = getConnection ();
        if (((null == conn) && (null != connection)) || ((null != conn)
            && !conn.equals (connection)))
        {
            try
            {
                if (null == mParser)
                    mParser = new Parser (connection);
                else
                    mParser.setConnection (connection);
                mPropertySupport.firePropertyChange (
                    PROP_URL_PROPERTY, url, getURL ());
                mPropertySupport.firePropertyChange (
                    PROP_CONNECTION_PROPERTY, conn, mParser.getConnection ());
=====================================================================
Found a 38 line (127 tokens) duplication in the following files: 
Starting at line 458 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/beans/StringBean.java
Starting at line 249 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/beans/FilterBean.java
    }

    /**
     * Get the current URL.
     * @return The URL from which text has been extracted, or <code>null</code>
     * if this property has not been set yet.
     */
    public String getURL ()
    {
         return ((null != mParser) ? mParser.getURL () : null);
    }

    /**
     * Set the URL to extract strings from.
     * The text from the URL will be fetched, which may be expensive, so this
     * property should be set last.
     * @param url The URL that text should be fetched from.
     */
    public void setURL (String url)
    {
        String old;
        URLConnection conn;

        old = getURL ();
        conn = getConnection ();
        if (((null == old) && (null != url)) || ((null != old)
            && !old.equals (url)))
        {
            try
            {
                if (null == mParser)
                    mParser = new Parser (url);
                else
                    mParser.setURL (url);
                mPropertySupport.firePropertyChange (
                    PROP_URL_PROPERTY, old, getURL ());
                mPropertySupport.firePropertyChange (
                    PROP_CONNECTION_PROPERTY, conn, mParser.getConnection ());
=====================================================================
Found a 39 line (125 tokens) duplication in the following files: 
Starting at line 179 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/nodes/TextNode.java
Starting at line 206 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/nodes/RemarkNode.java
            ret.append ("Rem (");
            ret.append (startpos);
            ret.append (",");
            ret.append (endpos);
            ret.append ("): ");
            for (int i = 0; i < mText.length (); i++)
            {
                c = mText.charAt (i);
                switch (c)
                {
                    case '\t':
                        ret.append ("\\t");
                        break;
                    case '\n':
                        ret.append ("\\n");
                        break;
                    case '\r':
                        ret.append ("\\r");
                        break;
                    default:
                        ret.append (c);
                }
                if (77 <= ret.length ())
                {
                    ret.append ("...");
                    break;
                }
            }
        }

        return (ret.toString ());
    }

    /**
     * Remark visiting code.
     * @param visitor The <code>NodeVisitor</code> object to invoke 
     * <code>visitRemarkNode()</code> on.
     */
    public void accept (NodeVisitor visitor)
=====================================================================
Found a 33 line (123 tokens) duplication in the following files: 
Starting at line 338 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/HTMLParserUtilsTest.java
Starting at line 419 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/HTMLParserUtilsTest.java
            NodeFilter filterTableColumn = new NodeClassFilter(TableColumn.class);
            OrFilter filterOr = new OrFilter(filterTableRow, filterTableColumn);
            assertStringEquals(
                "modified text",
                " ALL OK",
                ParserUtils.trimTags("<TR><TD>  +12.5 </TD></TR> ALL OK", filterOr)
            );
            assertStringEquals(
                "modified text",
                "<TD>  +12.5 </TD> ALL OK",
                ParserUtils.trimTags("<TR><TD>  +12.5 </TD></TR> ALL OK", filterOr, false, false)
            );
            assertStringEquals(
                "modified text",
                "  +12.5  ALL OK",
                ParserUtils.trimTags("<TR><TD>  +12.5 </TD></TR> ALL OK", filterOr, true, false)
            );
            assertStringEquals(
                "modified text",
                " ALL OK",
                ParserUtils.trimTags("<TR><TD>  +12.5 </TD></TR> ALL OK", filterOr, false, true)
            );
        }
        catch (Exception e)
        {
            String msg = e.getMessage ();
            if (null == msg)
                msg = e.getClass ().getName ();
            fail (msg);
        }
    }
    
    public void testTagsComplexMethods() {
=====================================================================
Found a 19 line (122 tokens) duplication in the following files: 
Starting at line 180 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
Starting at line 446 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
        source = new StringSource (reference);
        assertTrue ("not markable", source.markSupported ());
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < 25; i++)
            buffer.append ((char)source.read ());
        source.mark (88);
        for (int i = 0; i < 25; i++)
            source.read ();
        source.reset ();
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test skipping a StringSource.
     */
    public void testStringSourceSkip () throws IOException
=====================================================================
Found a 29 line (121 tokens) duplication in the following files: 
Starting at line 174 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java
Starting at line 202 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java
    public void testSerializableScanners ()
        throws
            IOException,
            ClassNotFoundException,
            ParserException
    {
        Parser parser;
        Vector vector;
        NodeIterator enumeration;
        byte[] data;

        parser = new Parser ("http://htmlparser.sourceforge.net/test/example.html");
        enumeration = parser.elements ();
        vector = new Vector (50);
        while (enumeration.hasMoreNodes ())
            vector.addElement (enumeration.nextNode ());

        data = pickle (parser);
        parser = (Parser)unpickle (data);

        enumeration = parser.elements ();
        while (enumeration.hasMoreNodes ())
            assertEquals (
                "Nodes before and after serialization differ",
                ((Node)vector.remove (0)).toHtml (),
                enumeration.nextNode ().toHtml ());
    }

    public void testSerializableStringBean ()
=====================================================================
Found a 25 line (120 tokens) duplication in the following files: 
Starting at line 89 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tags/AppletTag.java
Starting at line 87 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tags/ObjectTag.java
    public Hashtable createObjectParamsTable ()
    {
        NodeList kids;
        Node node;
        Tag tag;
        String paramName;
        String paramValue;
        Hashtable ret;

        ret = new Hashtable ();
        kids = getChildren ();
        if (null != kids)
            for (int i = 0; i < kids.size (); i++)
            {
                node = children.elementAt(i);
                if (node instanceof Tag)
                {
                    tag = (Tag)node;
                    if (tag.getTagName().equals ("PARAM"))
                    {
                        paramName = tag.getAttribute ("NAME");
                        if (null != paramName && 0 != paramName.length ())
                        {
                            paramValue = tag.getAttribute ("VALUE");
                            ret.put (paramName.toUpperCase(),paramValue);
=====================================================================
Found a 24 line (120 tokens) duplication in the following files: 
Starting at line 597 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/SiteCapturer.java
Starting at line 640 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/SiteCapturer.java
            link = getFrameLocation ();
            // check if it needs to be captured
            if (isToBeCaptured (link))
            {
                // add the link to a list to be processed
                if (mFinished.contains (link))
                    html = true;
                else if (mPages.contains (link))
                    html = true;
                else if (mCopied.contains (link))
                    html = false;
                else if (mImages.contains (link))
                    html = false;
                else
                {   // this test is expensive, do it reluctantly
                    html = isHtml (link);
                    if (html)
                        mPages.add (link);
                    else
                        mImages.add (link);
                }
                // alter the link
                if (html || (!html && getCaptureResources ()))
                    link = makeLocalLink (link, mParser.getLexer ().getPage ().getUrl ());
=====================================================================
Found a 20 line (119 tokens) duplication in the following files: 
Starting at line 254 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
Starting at line 383 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java
    public void handleSimpleTag (HTML.Tag t, MutableAttributeSet a, int pos)
    {
        String theirs;
        Node node;
        int match;
        String ours;

        theirs = t.toString ();
        match = -1;
        for (int i = mIndex; i < Math.min (mIndex + 25, mNodes.size ()); i++)
        {
            node = (Node)mNodes.elementAt (i);
            if (node instanceof Tag)
            {
                ours = ((Attribute)(((Tag)node).getAttributesEx ().elementAt (0))).getName ();
                if (match (theirs, ours))
                {
                    match = i;
                    break;
                }
=====================================================================
Found a 12 line (115 tokens) duplication in the following files: 
Starting at line 546 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java
Starting at line 565 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java
Starting at line 584 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java
        createParser(testHTML);
        parseAndAssertNodeCount(1);
        assertTrue("Only node should be an HTML node",node[0] instanceof Html);
        Html html = (Html)node[0];
        assertTrue("HTML node should have one child",1 == html.getChildCount ());
        assertTrue("Only node should be an BODY node",html.getChild(0) instanceof BodyTag);
        BodyTag body = (BodyTag)html.getChild(0);
        assertTrue("BODY node should have one child",1 == body.getChildCount ());
        assertTrue("Only node should be a string node",body.getChild(0) instanceof Text);
        Text stringNode = (Text)body.getChild(0);
        String actual = stringNode.getText();
        assertEquals("Third node has incorrect text","text<>\ntext",actual);
=====================================================================
Found a 53 line (111 tokens) duplication in the following files: 
Starting at line 319 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/filterbuilder/wrappers/StringFilterWrapper.java
Starting at line 301 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/parserapplications/filterbuilder/wrappers/RegexFilterWrapper.java
    }

    //
    // DocumentListener interface
    //

    /**
     * Handle an insert update event.
     * @param e Details about the insert event.
     */
    public void insertUpdate (DocumentEvent e)
    {
        Document doc;
        
        doc = e.getDocument ();
        try
        {
            mFilter.setPattern (doc.getText (0, doc.getLength ()));
        }
        catch (BadLocationException ble)
        {
            ble.printStackTrace ();
        }
    }

    /**
     * Handle a remove update event.
     * @param e Details about the remove event.
     */
    public void removeUpdate (DocumentEvent e)
    {
        Document doc;
        
        doc = e.getDocument ();
        try
        {
            mFilter.setPattern (doc.getText (0, doc.getLength ()));
        }
        catch (BadLocationException ble)
        {
            ble.printStackTrace ();
        }
    }

    /**
     * Handle a change update event.
     * @param e Details about the change event.
     */
    public void changedUpdate (DocumentEvent e)
    {
        // plain text components don't fire these events
    }
}
=====================================================================
Found a 19 line (109 tokens) duplication in the following files: 
Starting at line 333 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/ParserTest.java
Starting at line 384 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/ParserTest.java
        NodeIterator enumeration;

        path = System.getProperty ("user.dir");
        if (!path.endsWith (File.separator))
            path += File.separator;
        file = new File (path + "delete_me.html");
        try
        {
            out = new PrintWriter (new FileWriter (file));
            out.println ("<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\">");
            out.println ("<html>");
            out.println ("<head>");
            out.println ("<title>test</title>");
            out.println ("<meta http-equiv=\"Content-Type\" content=\"text/html; charset=iso-8859-1\">");
            out.println ("</head>");
            out.println ("<body>");
            out.println ("This is a test page ");
            out.println ("</body>");
            out.println ("</html>");
=====================================================================
Found a 17 line (109 tokens) duplication in the following files: 
Starting at line 132 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
Starting at line 398 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
        source = new StringSource (reference);
        buffer = new StringBuffer (reference.length ());
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.reset ();
        buffer.setLength (0);
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test resetting a StringSource in the middle of reading.
     */
    public void testStringSourceMidReset () throws IOException
=====================================================================
Found a 10 line (107 tokens) duplication in the following files: 
Starting at line 47 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
Starting at line 73 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
Starting at line 155 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java
    public void testChangeAppletClass() throws ParserException {
        String [][]paramsData = {{"Param1","Value1"},{"Name","Somik"},{"Age","23"}};
        Hashtable paramsMap = new Hashtable();
        String testHTML = new String("<APPLET CODE=Myclass.class ARCHIVE=test.jar CODEBASE=www.kizna.com>\n");
        for (int i = 0;i<paramsData.length;i++)
        {
            testHTML+="<PARAM NAME=\""+paramsData[i][0]+"\" VALUE=\""+paramsData[i][1]+"\">\n";
            paramsMap.put(paramsData[i][0],paramsData[i][1]);
        }
        testHTML+=
=====================================================================
Found a 17 line (106 tokens) duplication in the following files: 
Starting at line 156 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
Starting at line 422 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
        source = new StringSource (reference);
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < 25; i++)
            buffer.append ((char)source.read ());
        source.reset ();
        for (int i = 0; i < 25; i++)
            source.read ();
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test mark/reset of a StringSource in the middle of reading.
     */
    public void testStringSourceMarkReset () throws IOException
=====================================================================
Found a 19 line (106 tokens) duplication in the following files: 
Starting at line 180 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/AttributeTests.java
Starting at line 268 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/AttributeTests.java
        attribute = new PageAttribute ();
        attribute.setName ("name");
        attribute.setAssignment ("=");
        attribute.setValue ("topFrame");
        attribute.setQuote ('"');
        assertTrue ("should not be standalone", !attribute.isStandAlone ());
        assertTrue ("should not be whitespace", !attribute.isWhitespace ());
        assertTrue ("should be valued", attribute.isValued ());
        assertTrue ("should not be empty", !attribute.isEmpty ());
         attributes.add (attribute);
        tag = new TagNode (null, 0, 0, attributes);
        html = "<wombat label=\"The civil war.\" frameborder= no name=\"topFrame\">";
        assertStringEquals ("tag contents", html, tag.toHtml ());
    }

    /**
     * Test simple value.
     */
    public void testParseParameters() {
=====================================================================
Found a 10 line (103 tokens) duplication in the following files: 
Starting at line 528 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java
Starting at line 546 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java
        createParser(testHTML);
        parseAndAssertNodeCount(1);
        assertTrue("Only node should be an HTML node",node[0] instanceof Html);
        Html html = (Html)node[0];
        assertTrue("HTML node should have one child",1 == html.getChildCount ());
        assertTrue("Only node should be an BODY node",html.getChild(0) instanceof BodyTag);
        BodyTag body = (BodyTag)html.getChild(0);
        assertTrue("BODY node should have one child",1 == body.getChildCount ());
        assertTrue("Only node should be a string node",body.getChild(0) instanceof Text);
        Text stringNode = (Text)body.getChild(0);
=====================================================================
Found a 15 line (102 tokens) duplication in the following files: 
Starting at line 212 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
Starting at line 478 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java
        source = new StringSource (reference);
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < part1.length (); i++)
            buffer.append ((char)source.read ());
        source.skip (part2.length ());
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", (part1 + part3).equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test multi-byte read with a StringSource.
     */
    public void testStringSourceMultByte () throws IOException
=====================================================================
Found a 34 line (100 tokens) duplication in the following files: 
Starting at line 146 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/nodes/TextNode.java
Starting at line 173 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/nodes/RemarkNode.java
            while (start.getPosition () < endpos)
            {
                try
                {
                    c = mPage.getCharacter (start);
                    switch (c)
                    {
                        case '\t':
                            ret.append ("\\t");
                            break;
                        case '\n':
                            ret.append ("\\n");
                            break;
                        case '\r':
                            ret.append ("\\r");
                            break;
                        default:
                            ret.append (c);
                    }
                }
                catch (ParserException pe)
                {
                    // not really expected, but we're only doing toString, so ignore
                }
                if (77 <= ret.length ())
                {
                    ret.append ("...");
                    break;
                }
            }
        }
        else
        {
            ret.append ("Rem (");
=====================================================================
Found a 15 line (100 tokens) duplication in the following files: 
Starting at line 132 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/scannersTests/CompositeTagScannerTest.java
Starting at line 422 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/tests/scannersTests/CompositeTagScannerTest.java
        );
        parser.setNodeFactory (
            new PrototypicalNodeFactory (
                new Tag[]
                {
                    new CustomTag (),
                    new AnotherTag (true),
                }));
        parseAndAssertNodeCount(1);
        assertType("node",CustomTag.class,node[0]);
        CustomTag customTag = (CustomTag)node[0];
        assertEquals("child count",1,customTag.getChildCount());
        assertFalse("custom tag should not be xml end tag",customTag.isEmptyXmlTag());
        assertEquals("starting loc",0,customTag.getStartPosition ());
        assertEquals("ending loc",8,customTag.getEndPosition ());
=====================================================================
Found a 16 line (100 tokens) duplication in the following files: 
Starting at line 343 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
Starting at line 630 of /home/tom/pmd/pmd-web/src/htmlparser/src/org/htmlparser/util/ParserUtils.java
    public static String trimCharsBeginEnd (String input, String charsToBeRemoved)
    {
 	
        String output = new String();

        int begin=0;
        int end=input.length()-1;
        boolean charFound=false;
        boolean ok=true;
        for (int index=begin; (index<input.length()) && ok; index++)
        {                
            charFound=false;
            for (int charsCount=0; charsCount<charsToBeRemoved.length(); charsCount++)
                if (charsToBeRemoved.charAt(charsCount)==input.charAt(index))
                    charFound=true;
            if (!(charFound))