/* Copyright (C) 2003 Internet Archive.
 *
 * This file is part of the Heritrix web crawler (crawler.archive.org).
 *
 * Heritrix is free software; you can redistribute it and/or modify
 * it under the terms of the GNU Lesser Public License as published by
 * the Free Software Foundation; either version 2.1 of the License, or
 * any later version.
 *
 * Heritrix 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 Public License for more details.
 *
 * You should have received a copy of the GNU Lesser Public License
 * along with Heritrix; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * Created on Nov 17, 2003
 *
 * To change the template for this generated file go to
 * Window>Preferences>Java>Code Generation>Code and Comments
 */
package org.archive.crawler.extractor;

import java.io.IOException;
import java.util.logging.Logger;
import java.util.regex.Matcher;

import org.apache.commons.httpclient.URIException;
import org.archive.crawler.datamodel.CoreAttributeConstants;
import org.archive.crawler.datamodel.CrawlURI;
import org.archive.crawler.framework.CrawlController;
import org.archive.io.ReplayCharSequence;
import org.archive.net.UURI;
import org.archive.util.DevUtils;
import org.archive.util.TextUtils;
import org.archive.util.UriUtils;

/**
 * Processes Javascript files for strings that are likely to be
 * crawlable URIs.
 *
 * @contributor gojomo
 * @contributor szznax
 *
 */
public class ExtractorJS extends Extractor implements CoreAttributeConstants {

    private static final long serialVersionUID = -2231962381454717720L;

    private static Logger LOGGER =
        Logger.getLogger("org.archive.crawler.extractor.ExtractorJS");

    // finds whitespace-free strings in Javascript
    // (areas between paired ' or " characters, possibly backslash-quoted
    // on the ends, but not in the middle)
    static final String JAVASCRIPT_STRING_EXTRACTOR =
        "(\\\\{0,8}+(?:\"|\'))(\\S{0,"+UURI.MAX_URL_LENGTH+"}?)(?:\\1)";
    // GROUPS:
    // (G1) ' or " with optional leading backslashes
    // (G2) whitespace-free string delimited on boths ends by G1


    protected long numberOfCURIsHandled = 0;
    protected static long numberOfLinksExtracted = 0;

    
    // URIs known to produce false-positives with the current JS extractor.
    // e.g. currently (2.0.3) the JS extractor produces 13 false-positive 
    // URIs from http://www.google-analytics.com/urchin.js and only 2 
    // good URIs, which are merely one pixel images.
    // TODO: remove this blacklist when JS extractor is improved 
    protected final static String[] EXTRACTOR_URI_EXCEPTIONS = {
        "http://www.google-analytics.com/urchin.js"
        };
    
    /**
     * @param name
     */
    public ExtractorJS(String name) {
        super(name, "JavaScript extractor. Link extraction on JavaScript" +
                " files (.js).");
    }

    /* (non-Javadoc)
     * @see org.archive.crawler.framework.Processor#process(org.archive.crawler.datamodel.CrawlURI)
     */
    public void extract(CrawlURI curi) {
        // special-cases, for when we know our current JS extractor does poorly.
        // TODO: remove this test when JS extractor is improved 
        for (String s: EXTRACTOR_URI_EXCEPTIONS) {
            if (curi.toString().equals(s))
                return;
        }
            
        if (!isHttpTransactionContentToProcess(curi)) {
            return;
        }
        String contentType = curi.getContentType();
        if ((contentType == null)) {
            return;
        }
        // If content type is not js and if the viaContext
        // does not begin with 'script',