compositetag.java

html 解析处理代码

// HTMLParser Library $Name: v1_6 $ - A java-based parser for HTML
// http://sourceforge.org/projects/htmlparser
// Copyright (C) 2004 Somik Raha
//
// Revision Control Information
//
// $Source: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tags/CompositeTag.java,v $
// $Author: derrickoswald $
// $Date: 2006/05/31 02:10:15 $
// $Revision: 1.82 $
//
// This library is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 2.1 of the License, or (at your option) any later version.
//
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
// Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License along with this library; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
//

package org.htmlparser.tags;

import java.util.Locale;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Text;
import org.htmlparser.Tag;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.nodes.AbstractNode;
import org.htmlparser.nodes.TagNode;
import org.htmlparser.scanners.CompositeTagScanner;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.SimpleNodeIterator;
import org.htmlparser.visitors.NodeVisitor;

/**
 * The base class for tags that have an end tag.
 * Provided extra accessors for the children above and beyond what the basic
 * {@link Tag} provides. Also handles the conversion of it's children for
 * the {@link #toHtml toHtml} method.
 */
public class CompositeTag extends TagNode
{
    /**
     * The tag that causes this tag to finish.
     * May be a virtual tag generated by the scanning logic.
     */
    protected Tag mEndTag;

    /**
     * The default scanner for non-composite tags.
     */
    protected final static CompositeTagScanner mDefaultCompositeScanner = new CompositeTagScanner ();

    /**
     * Create a composite tag.
     */
    public CompositeTag ()
    {
        setThisScanner (mDefaultCompositeScanner);
    }
    
    /**
     * Get an iterator over the children of this node.
     * @return Am iterator over the children of this node.
     */
    public SimpleNodeIterator children ()
    {
        SimpleNodeIterator ret;

        if (null != getChildren ())
            ret = getChildren ().elements ();
        else
            ret = (new NodeList ()).elements ();

        return (ret);
    }

    /**
     * Get the child of this node at the given position.
     * @param index The in the node list of the child.
     * @return The child at that index.
     */
    public Node getChild (int index)
    {
        return (
            (null == getChildren ()) ? null :
            getChildren ().elementAt (index));
    }

    /**
     * Get the children as an array of <code>Node</code> objects.
     * @return The children in an array.
     */
    public Node [] getChildrenAsNodeArray ()
    {
        return (
            (null == getChildren ()) ? new Node[0] :
            getChildren ().toNodeArray ());
    }

    /**
     * Remove the child at the position given.
     * @param i The index of the child to remove.
     */
    public void removeChild (int i)
    {
        if (null != getChildren ())
            getChildren ().remove (i);
    }

    /**
     * Return the child tags as an iterator.
     * Equivalent to calling getChildren ().elements ().
     * @return An iterator over the children.
     */
    public SimpleNodeIterator elements()
    {
        return (
            (null == getChildren ()) ? new NodeList ().elements () :
            getChildren ().elements ());
    }

    /**
     * Return the textual contents of this tag and it's children.
     * @return The 'browser' text contents of this tag.
     */
    public String toPlainTextString() {
        StringBuffer stringRepresentation = new StringBuffer();
        for (SimpleNodeIterator e=children();e.hasMoreNodes();) {
            stringRepresentation.append(e.nextNode().toPlainTextString());
        }
        return stringRepresentation.toString();
    }

    /**
     * Add the textual contents of the children of this node to the buffer.
     * @param verbatim If <code>true</code> return as close to the original
     * page text as possible.
     * @param sb The buffer to append to.
     */
    protected void putChildrenInto (StringBuffer sb, boolean verbatim)
    {
        Node node;
        for (SimpleNodeIterator e = children (); e.hasMoreNodes ();)
        {
            node = e.nextNode ();
            // eliminate virtual tags
            if (!verbatim || !(node.getStartPosition () == node.getEndPosition ()))
                sb.append (node.toHtml ());
        }
    }

    /**
     * Add the textual contents of the end tag of this node to the buffer.
     * @param verbatim If <code>true</code> return as close to the original
     * page text as possible.
     * @param sb The buffer to append to.
     */
    protected void putEndTagInto (StringBuffer sb, boolean verbatim)
    {
        // eliminate virtual tags
        if (!verbatim || !(mEndTag.getStartPosition () == mEndTag.getEndPosition ()))
            sb.append (getEndTag ().toHtml());
    }

    /**
     * Return this tag as HTML code.
     * @param verbatim If <code>true</code> return as close to the original
     * page text as possible.
     * @return This tag and it's contents (children) and the end tag
     * as HTML code.
     */
    public String toHtml (boolean verbatim)
    {
        StringBuffer ret;
        
        ret = new StringBuffer ();
        ret.append (super.toHtml (verbatim));
        if (!isEmptyXmlTag ())
        {
            putChildrenInto (ret, verbatim);
            if (null != getEndTag ())
                putEndTagInto (ret, verbatim);
        }
        return (ret.toString ());
    }

    /**
     * Searches all children who for a name attribute. Returns first match.
     * @param name Attribute to match in tag
     * @return Tag Tag matching the name attribute
     */
    public Tag searchByName(String name) {
        Node node;
        Tag tag = null;
        boolean found = false;
        for (SimpleNodeIterator e = children();e.hasMoreNodes() && !found;) {
            node = e.nextNode();
            if (node instanceof Tag)
            {
                tag = (Tag)node;
                String nameAttribute = tag.getAttribute("NAME");
                if (nameAttribute!=null && nameAttribute.equals(name))
                    found=true;
            }
        }
        if (found)
            return tag;
        else
            return null;
    }

    /**
     * Searches for all nodes whose text representation contains the search string.
     * Collects all nodes containing the search string into a NodeList.
     * This search is <b>case-insensitive</b> and the search string and the
     * node text are converted to uppercase using an English locale.
     * For example, if you wish to find any textareas in a form tag containing
     * "hello world", the code would be:
     * <code>
     * NodeList nodeList = formTag.searchFor("Hello World");
     * </code>
     * @param searchString Search criterion.
     * @return A collection of nodes whose string contents or
     * representation have the <code>searchString</code> in them.
     */
    public NodeList searchFor (String searchString)
    {
        return (searchFor (searchString, false));
    }

    /**
     * Searches for all nodes whose text representation contains the search string.
     * Collects all nodes containing the search string into a NodeList.
     * For example, if you wish to find any textareas in a form tag containing
     * "hello world", the code would be:
     * <code>
     * NodeList nodeList = formTag.searchFor("Hello World");
     * </code>
     * @param searchString Search criterion.
     * @param caseSensitive If <code>true</code> this search should be case
     * sensitive. Otherwise, the search string and the node text are converted
     * to uppercase using an English locale.
     * @return A collection of nodes whose string contents or
     * representation have the <code>searchString</code> in them.
     */
    public NodeList searchFor (String searchString, boolean caseSensitive)
    {
        return (searchFor (searchString, caseSensitive, Locale.ENGLISH));
    }

    /**
     * Searches for all nodes whose text representation contains the search string.
     * Collects all nodes containing the search string into a NodeList.
     * For example, if you wish to find any textareas in a form tag containing
     * "hello world", the code would be:
     * <code>
     * NodeList nodeList = formTag.searchFor("Hello World");
     * </code>
     * @param searchString Search criterion.
     * @param caseSensitive If <code>true</code> this search should be case
     * sensitive. Otherwise, the search string and the node text are converted
     * to uppercase using the locale provided.
     * @param locale The locale for uppercase conversion.
     * @return A collection of nodes whose string contents or
     * representation have the <code>searchString</code> in them.
     */
    public NodeList searchFor (String searchString, boolean caseSensitive, Locale locale)
    {
        Node node;
        String text;
        NodeList ret;
        
        ret = new NodeList ();

        if (!caseSensitive)
            searchString = searchString.toUpperCase (locale);
        for (SimpleNodeIterator e = children (); e.hasMoreNodes (); )
        {
            node = e.nextNode ();
            text = node.toPlainTextString ();
            if (!caseSensitive)
                text = text.toUpperCase (locale);
            if (-1 != text.indexOf (searchString))
                ret.add (node);
        }

        return (ret);
    }

    /**
     * Collect all objects that are of a certain type
     * Note that this will not check for parent types, and will not
     * recurse through child tags
     * @param classType The class to search for.
     * @param recursive If true, recursively search through the children.
     * @return A list of children found.
     */
    public NodeList searchFor (Class classType, boolean recursive)
    {
        NodeList children;
        NodeList ret;

        children = getChildren ();
        if (null == children)
            ret = new NodeList ();
        else
            ret = children.extractAllNodesThatMatch (
                new NodeClassFilter (classType), recursive);