crawlorder.java

最强的爬虫工程

/*
 * CrawlOrder
 *
 * $Header: /cvsroot/archive-crawler/ArchiveOpenCrawler/src/java/org/archive/crawler/datamodel/CrawlOrder.java,v 1.57 2006/08/11 05:29:08 gojomo Exp $
 *
 * Created on May 15, 2003
 *
 * 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
 *
 */

package org.archive.crawler.datamodel;

import java.io.File;
import java.io.Serializable;
import java.util.logging.Logger;

import javax.management.AttributeNotFoundException;
import javax.management.MBeanException;
import javax.management.ReflectionException;

import org.archive.crawler.framework.CrawlController;
import org.archive.crawler.framework.CrawlScope;
import org.archive.crawler.framework.Frontier;
import org.archive.crawler.framework.Processor;
import org.archive.crawler.framework.exceptions.FatalConfigurationException;
import org.archive.crawler.settings.MapType;
import org.archive.crawler.settings.ModuleType;
import org.archive.crawler.settings.SimpleType;
import org.archive.crawler.settings.Type;
import org.archive.crawler.url.canonicalize.BaseRule;

/**
 * Represents the 'root' of the settings hierarchy. Contains those settings that
 * do not belong to any specific module, but rather relate to the crawl as a
 * whole (much of this is used by the CrawlController directly or indirectly).
 *
 * @see org.archive.crawler.settings.ModuleType
 */
public class CrawlOrder extends ModuleType implements Serializable {
    private static Logger logger =
        Logger.getLogger("org.archive.crawler.datamodel.CrawlOrder");

    public static final String ATTR_NAME = "crawl-order";
    public static final String ATTR_SETTINGS_DIRECTORY = "settings-directory";
    public static final String ATTR_DISK_PATH = "disk-path";
    public static final String ATTR_LOGS_PATH = "logs-path";
    public static final String ATTR_CHECKPOINTS_PATH = "checkpoints-path";
    public static final String ATTR_STATE_PATH = "state-path";
    public static final String ATTR_SCRATCH_PATH = "scratch-path";
    public static final String ATTR_RECOVER_PATH = "recover-path";
    public static final String ATTR_RECOVER_RETAIN_FAILURES =
        "recover-retain-failures";
    public static final String ATTR_MAX_BYTES_DOWNLOAD = "max-bytes-download";
    public static final String ATTR_MAX_DOCUMENT_DOWNLOAD =
        "max-document-download";
    public static final String ATTR_MAX_TIME_SEC = "max-time-sec";
    public static final String ATTR_MAX_TOE_THREADS = "max-toe-threads";
    public static final String ATTR_HTTP_HEADERS = "http-headers";
    public static final String ATTR_USER_AGENT = "user-agent";
    public static final String ATTR_FROM = "from";
    public static final String ATTR_PRE_FETCH_PROCESSORS =
        "pre-fetch-processors";
    public static final String ATTR_FETCH_PROCESSORS = "fetch-processors";
    public static final String ATTR_EXTRACT_PROCESSORS = "extract-processors";
    public static final String ATTR_WRITE_PROCESSORS = "write-processors";
    public static final String ATTR_POST_PROCESSORS = "post-processors";
    public static final String ATTR_LOGGERS = "loggers";
    public static final String ATTR_RULES = "uri-canonicalization-rules";
    public static final String ATTR_RECORDER_OUT_BUFFER =
        "recorder-out-buffer-bytes";
    public static final String ATTR_RECORDER_IN_BUFFER =
        "recorder-in-buffer-bytes";
    
    /** Percentage of heap to allocate to bdb cache */
    public static final String ATTR_BDB_CACHE_PERCENT =
        "bdb-cache-percent";
    
    /**
     * When checkpointing, copy the bdb logs.
     * Default is true.  If false, then we do not copy logs on checkpoint AND
     * we tell bdbje never to delete log files; instead it renames
     * files-to-delete with a '.del' extension.  Assumption is that when this
     * setting is false, an external process is managing the removing of
     * bdbje log files and that come time to recover from a checkpoint, the
     * files that comprise a checkpoint are manually assembled.
     */
    public static final String ATTR_CHECKPOINT_COPY_BDBJE_LOGS =
        "checkpoint-copy-bdbje-logs";
    public static final Boolean DEFAULT_CHECKPOINT_COPY_BDBJE_LOGS =
        Boolean.TRUE;
    
    /**
     * Default size of bdb cache.
     */
    private final static Integer DEFAULT_BDB_CACHE_PERCENT = new Integer(0);

    private transient String caseFlattenedUserAgent;

    private transient MapType httpHeaders;
    private transient MapType loggers;

    private transient CrawlController controller;

    /**
     * Regex for acceptable user-agent format.
     */
    private static String ACCEPTABLE_USER_AGENT =
        "\\S+.*\\(.*\\+http(s)?://\\S+\\.\\S+.*\\).*";

    /**
     * Regex for acceptable from address.
     */
    private static String ACCEPTABLE_FROM = "\\S+@\\S+\\.\\S+";
    

    /** Construct a CrawlOrder.
     */
    public CrawlOrder() {
        super(ATTR_NAME, "Heritrix crawl order. This forms the root of " +
                "the settings framework.");
        Type e;

        e = addElementToDefinition(new SimpleType(ATTR_SETTINGS_DIRECTORY,
                "Directory where override settings are kept. The settings " +
                "for many modules can be overridden based on the domain or " +
                "subdomain of the URI being processed. This setting specifies" +
                " a file level directory to store those settings. The path" +
                " is relative to 'disk-path' unless" +
                " an absolute path is provided.", "settings"));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_DISK_PATH,
                "Directory where logs, arcs and other run time files will " +
                "be kept. If this path is a relative path, it will be " +
                "relative to the crawl order.", ""));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_LOGS_PATH,
                "Directory where crawler log files will be kept. If this path " +
                "is a relative path, it will be relative to the 'disk-path'.",
                "logs"));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_CHECKPOINTS_PATH,
                "Directory where crawler checkpoint files will be kept. " +
                "If this path " +
                "is a relative path, it will be relative to the 'disk-path'.",
                "checkpoints"));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_STATE_PATH,
                "Directory where crawler-state files will be kept. If this path " +
                "is a relative path, it will be relative to the 'disk-path'.",
                "state"));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_SCRATCH_PATH,
                "Directory where discardable temporary files will be kept. " +
                "If this path " +
                "is a relative path, it will be relative to the 'disk-path'.",
                "scratch"));
        e.setOverrideable(false);
        e.setExpertSetting(true);

        e = addElementToDefinition(new SimpleType(ATTR_MAX_BYTES_DOWNLOAD,
                "Maximum number of bytes to download. Once this number is" +
                " exceeded the crawler will stop. " +
                "A value of zero means no upper limit.", new Long(0)));
        e.setOverrideable(false);

        e = addElementToDefinition(new SimpleType(ATTR_MAX_DOCUMENT_DOWNLOAD,
                "Maximum number of documents to download. Once this number" +
                " is exceeded the crawler will stop. " +
                "A value of zero means no upper limit.", new Long(0)));
        e.setOverrideable(false);

        e = addElementToDefinition(new SimpleType(ATTR_MAX_TIME_SEC,
                "Maximum amount of time to crawl (in seconds). Once this" +
                " much time has elapsed the crawler will stop. A value of" +
                " zero means no upper limit.",
                new Long(0)));
        e.setOverrideable(false);
        
        e = addElementToDefinition(new SimpleType(ATTR_MAX_TOE_THREADS,
                "Maximum number of threads processing URIs at the same time.",
                new Integer(100)));
        e.setOverrideable(false);

        e = addElementToDefinition(new SimpleType(ATTR_RECORDER_OUT_BUFFER,
                "Size in bytes of in-memory buffer to record outbound " +
                "traffic. One such buffer is reserved for every ToeThread.",
                new Integer(4096)));
        e.setOverrideable(false);
        e.setExpertSetting(true);
        
        e = addElementToDefinition(new SimpleType(ATTR_RECORDER_IN_BUFFER,
                "Size in bytes of in-memory buffer to record inbound " +
                "traffic. One such buffer is reserved for every ToeThread.",
                new Integer(65536)));
        e.setOverrideable(false);
        e.setExpertSetting(true);
        
        e = addElementToDefinition(new SimpleType(ATTR_BDB_CACHE_PERCENT,
                "Percentage of heap to allocate to BerkeleyDB JE cache. " +
                "Default of zero means no preference (accept BDB's default, " +
                "usually 60%, or the je.maxMemoryPercent property value).",
                DEFAULT_BDB_CACHE_PERCENT));
        e.setExpertSetting(true);
        e.setOverrideable(false);
        
        addElementToDefinition(new CrawlScope());

        httpHeaders = (MapType) addElementToDefinition(new MapType(
                ATTR_HTTP_HEADERS, "HTTP headers. Information that will " +
                        "be used when constructing the HTTP headers of " +
                        "the crawler's HTTP requests."));

        e = httpHeaders.addElementToDefinition(new SimpleType(ATTR_USER_AGENT,
                "User agent to act as. Field must contain valid URL " +
                "that links to website of person or organization " +
                "running the crawl. Replace 'PROJECT_URL_HERE' in " +
                "initial template. E.g. If organization " +
                "is Library of Congress, a valid user agent would be:" +
                "'Mozilla/5.0 (compatible; loc-crawler/0.11.0 " +
                "+http://loc.gov)'. " +