cmshtmlimportconverter.java

cms是开源的框架

/*
 * File   :
 * Date   : 
 * Version: 
 *
 * This library is part of OpenCms -
 * the Open Source Content Mananagement System
 *
 * Copyright (c) 2005 Alkacon Software GmbH (http://www.alkacon.com)
 *
 * 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.
 *
 * For further information about Alkacon Software GmbH, please see the
 * company website: http://www.alkacon.com
 *
 * For further information about OpenCms, please see the
 * project website: http://www.opencms.org
 * 
 * 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.opencms.workplace.tools.database;

import org.opencms.file.CmsPropertyDefinition;
import org.opencms.i18n.CmsEncoder;
import org.opencms.main.CmsLog;
import org.opencms.util.CmsStringUtil;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintWriter;
import java.io.Reader;
import java.io.StringReader;
import java.io.StringWriter;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
import java.util.HashSet;
import java.util.Hashtable;
import java.util.StringTokenizer;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.tidy.Tidy;

/**
 * This class implements Html-converting routines based on tidy to modify the
 * Html code of the imported Html pages.<p>
 * 
 * @author Michael Emmerich 
 * 
 * @version $Revision: 1.9 $ 
 * 
 * @since 6.0.0 
 */
public class CmsHtmlImportConverter {

    /** defintition of the alt attribute. */
    private static final String ATTRIB_ALT = "alt";

    /** defintition of the content attribute. */
    private static final String ATTRIB_CONTENT = "content";

    /** defintition of the href attribute.  */
    private static final String ATTRIB_HREF = "href";

    /** defintition of the name attribute. */
    private static final String ATTRIB_NAME = "name";

    /** defintition of the src attribute. */
    private static final String ATTRIB_SRC = "src";

    /** defintition of the &lt;BODY&gt;&lt;/BODY&gt; node. */
    private static final String NODE_BODY = "body";

    /** defintition of the &lt;HEAD&gt;&lt;/HEAD&gt; node. */
    private static final String NODE_HEAD = "head";

    /** defintition of the &lt;A&gt;&lt;/A&gt; node. */
    private static final String NODE_HREF = "a";

    /** defintition of the &lt;HTML&gt;&lt;/HTML&gt; node. */
    private static final String NODE_HTML = "html";

    /** defintition of the &lt;IMG&gt;&lt;/IMG&gt; node. */
    private static final String NODE_IMG = "img";

    /** defintition of the &lt;META&gt;&lt;/META&gt; node. */
    private static final String NODE_META = "meta";

    /** defintition of the &lt;TITLE&gt;&lt;/TITLE&gt;  node. */
    private static final String NODE_TITLE = "title";

    /**
     * HashMap stores tag names, after the end-tag, a "\n" is added to the output.<p>
     */
    private HashSet m_enterTags = new HashSet();

    /** 
     * the absolute path in the real filesystem of the file to convert. 
     */
    private String m_filename;

    /**
     * reference to the HtmlImport object, required to access the link translation.
     */
    private CmsHtmlImport m_htmlImport;

    /** 
     * temporary buffer used in transformation method. 
     */
    private StringBuffer m_tempString;

    /** instance of JTidy. */
    private Tidy m_tidy = new Tidy();

    /** flag to write the output. */
    private boolean m_write;

    /**
     * Default constructor, creates a new HtmlConverter.<p>
     * 
     * @param htmlImport reference to the htmlimport
     * @param xmlMode switch for setting the import to HTML or XML mode
     */
    public CmsHtmlImportConverter(CmsHtmlImport htmlImport, boolean xmlMode) {

        m_tidy.setTidyMark(false);
        m_tidy.setShowWarnings(false);
        m_tidy.setQuiet(true);
        m_tidy.setForceOutput(true);

        if (xmlMode) {
            m_tidy.setXmlTags(xmlMode);
            m_tidy.setXmlSpace(true);
        }

        initialiseTags();
        m_htmlImport = htmlImport;
    }

    /**
     * Extracts the content of a HTML page.<p>
     * 
     * This method should be pretty robust and work even if the input HTML does not contains
     * the specified matchers.<p> 
     * 
     * @param content the content to extract the body from
     * @param startpoint the point where matching starts
     * @param endpoint the point where matching ends
     * @return the extracted body tag content
     */
    public static String extractHtml(String content, String startpoint, String endpoint) {

        /** Regex that matches a start body tag. */
        Pattern startPattern = Pattern.compile(startpoint, Pattern.CASE_INSENSITIVE);

        /** Regex that matches an end body tag. */
        Pattern endPattern = Pattern.compile(endpoint, Pattern.CASE_INSENSITIVE);

        Matcher startMatcher = startPattern.matcher(content);
        Matcher endMatcher = endPattern.matcher(content);

        int start = 0;
        int end = content.length();

        if (startMatcher.find()) {
            start = startMatcher.end();
        }

        if (endMatcher.find(start)) {
            end = endMatcher.start();
        }

        return content.substring(start, end);
    }

    /**
     * Transforms HTML code into user defined output.<p>
     * 
     * @param input Reader with HTML code
     * @param output Writer with transformed code
     * @param startPattern the start pattern definition for content extracting
     * @param endPattern the end pattern definition for content extracting 
     * @param properties the file properties
     */
    public void convertHTML(Reader input, Writer output, String startPattern, String endPattern, Hashtable properties) {

        /* local variables */
        StringBuffer htmlString = new StringBuffer();
        Node node;
        String outString = "";

        try {
            /* write InputStream input in StringBuffer htmlString */
            int c;
            while ((c = input.read()) != -1) {
                htmlString.append((char)c);
            }
        } catch (IOException e) {
            if (CmsLog.INIT.isWarnEnabled()) {
                CmsLog.INIT.warn(Messages.get().getBundle().key(Messages.LOG_HTMLIMPORT_CONVERSION_ERROR_0, e.getLocalizedMessage()));
            }
            return;
        }
        outString = htmlString.toString();
        // extract from html if even both patterns are defined
        if (CmsStringUtil.isNotEmpty(startPattern) && CmsStringUtil.isNotEmpty(endPattern)) {
            String extractMain = extractHtml(outString, startPattern, endPattern);
            if (extractMain.length() != outString.length()) {
                String extractHead = extractHtml(outString, "<html>", CmsStringUtil.BODY_START_REGEX);
                //String extractHead = extractHtml(extractMain, "<html>", CmsStringUtil.C_BODY_START_REGEX);     
                StringBuffer buffer = new StringBuffer(extractHead.length() + extractMain.length() + 255);
                buffer.append("<html>");
                buffer.append(extractHead);
                buffer.append("<body>");
                buffer.append(extractMain);
                buffer.append("</body></html>");
                outString = buffer.toString();
            }
        }

        /* convert htmlString in InputStream for parseDOM */
        InputStream in;
        try {
            in = new ByteArrayInputStream(outString.getBytes(CmsEncoder.ENCODING_UTF_8));
        } catch (UnsupportedEncodingException e) {
            // this should never happen since UTF-8 is always supported
            in = new ByteArrayInputStream(outString.getBytes());
        }
        m_tidy.setInputEncoding(CmsEncoder.ENCODING_UTF_8);
        m_tidy.setOutputEncoding(CmsEncoder.ENCODING_UTF_8);

        // hold tidy error information into a new PrintWriter Object
        PrintWriter errorLog = new PrintWriter(new ByteArrayOutputStream(), true);
        m_tidy.setErrout(errorLog);

        node = m_tidy.parseDOM(in, null);
        /* check if html code has errors */
        if (m_tidy.getParseErrors() != 0) {
            if (CmsLog.INIT.isWarnEnabled()) {
                CmsLog.INIT.warn(Messages.get().getBundle().key(Messages.LOG_HTMLIMPORT_CONVERSION_ERROR_0));
            }
        }
        /* second step: create transformed output with printDocument from DOM */
        this.printDocument(node, properties);

        try {
            String content = m_tempString.toString();
            content = CmsStringUtil.substitute(content, "<br></br>", "<br>");
            content = CmsStringUtil.substitutePerl(content, "</a>(\\w+)", "</a> $1", "g");
            output.write(content);
            output.close();

        } catch (IOException e) {
            if (CmsLog.INIT.isWarnEnabled()) {
                CmsLog.INIT.warn(Messages.get().getBundle().key(Messages.LOG_HTMLIMPORT_CONVERSION_ERROR_1, e.getLocalizedMessage()));
            }
            return;
        }
    }

    /**
     * Transforms HTML code into user defined output.<p>
     * 
     * @param filename the absolute path in the real filesystem of the file to convert
     * @param inString String with HTML code
     * @param startPattern the start pattern definition for content extracting
     * @param endPattern the end pattern definition for content extracting 
     * @param properties the file properties
     * @return String with transformed code
     */
    public String convertHTML(
        String filename,
        String inString,
        String startPattern,
        String endPattern,
        Hashtable properties) {

        m_tempString = new StringBuffer();
        m_write = true;
        m_filename = filename.replace('\\', '/');
        Reader in = new StringReader(inString);
        Writer out = new StringWriter();
        convertHTML(in, out, startPattern, endPattern, properties);
        return out.toString();
    }

    /**
     * Initialises Vector m_enterTags with tag names.<p>
     */
    private void initialiseTags() {