Heritrix 3.1.0 源码解析（十一）

上文分析了Heritrix3.1.0系统是怎么添加CrawlURI curi对象的，那么在系统初始化的时候，是怎么载入CrawlURI curi种子的呢？

我们回顾前面的文章，在我们执行采集任务的launch指令的时候，实际会调用CrawlController对象的void requestCrawlStart()方法

/** 

     * Operator requested crawl begin

     */

    public void requestCrawlStart() {

        hasStarted = true; 

        sendCrawlStateChangeEvent(State.PREPARING, CrawlStatus.PREPARING);

        

        if(recoveryCheckpoint==null) {

            // only announce (trigger scheduling of) seeds

            // when doing a cold (non-recovery) start

            getSeeds().announceSeeds();

        }

        

        setupToePool();



        // A proper exit will change this value.

        this.sExit = CrawlStatus.FINISHED_ABNORMAL;

        

        if (getPauseAtStart()) {

            // frontier is already paused unless started, so just 

            // 'complete'/ack pause

            completePause();

        } else {

            getFrontier().run();

        }

    }

继续调用getSeeds().announceSeeds()方法，这里的getSeeds()真实对象是TextSeedModule（spring自动注入的），然后调用它的void announceSeeds()方法

/**

     * Announce all seeds from configured source to SeedListeners 

     * (including nonseed lines mixed in). 

     * @see org.archive.modules.seeds.SeedModule#announceSeeds()

     */

    public void announceSeeds() {

        if(getBlockAwaitingSeedLines()>-1) {

            final CountDownLatch latch = new CountDownLatch(getBlockAwaitingSeedLines());

            new Thread(){

                @Override

                public void run() {

                    announceSeeds(latch); 

                    while(latch.getCount()>0) {

                        latch.countDown();

                    }

                }

            }.start();

            try {

                latch.await();

            } catch (InterruptedException e) {

                // do nothing

            } 

        } else {

            announceSeeds(null); 

        }

    }

 上面方法中if后面的CountDownLatch latch是线程计数，else后面是null，继续调用void announceSeeds(CountDownLatch latchOrNull)方法 

protected void announceSeeds(CountDownLatch latchOrNull) {

        BufferedReader reader = new BufferedReader(textSource.obtainReader());       

        try {

            announceSeedsFromReader(reader,latchOrNull);    

        } finally {

            IOUtils.closeQuietly(reader);

        }

    }

 首先获取ReadSource textSource(org.archive.spring.ConfigString)的Reader(StringReader)，然后调用void announceSeedsFromReader(BufferedReader reader, CountDownLatch latchOrNull)方法 

/**

     * Announce all seeds (and nonseed possible-directive lines) from

     * the given Reader

     * @param reader source of seed/directive lines

     * @param latchOrNull if non-null, sent countDown after each line, allowing 

     * another thread to proceed after a configurable number of lines processed

     */

    protected void announceSeedsFromReader(BufferedReader reader, CountDownLatch latchOrNull) {

        String s;

        Iterator<String> iter = 

            new RegexLineIterator(

                    new LineReadingIterator(reader),

                    RegexLineIterator.COMMENT_LINE,

                    RegexLineIterator.NONWHITESPACE_ENTRY_TRAILING_COMMENT,

                    RegexLineIterator.ENTRY);



        int count = 0; 

        while (iter.hasNext()) {

            s = (String) iter.next();

            if(Character.isLetterOrDigit(s.charAt(0))) {

                // consider a likely URI

                seedLine(s);

                count++;

                if(count%20000==0) {

                    System.runFinalization();

                }

            } else {

                // report just in case it's a useful directive

                nonseedLine(s);

            }

            if(latchOrNull!=null) {

                latchOrNull.countDown(); 

            }

        }

        publishConcludedSeedBatch(); 

    }

 迭代url字符串并调用void seedLine(String uri)方法

/**

     * Handle a read line that is probably a seed.

     * 

     * @param uri String seed-containing line

     */

    protected void seedLine(String uri) {

        if (!uri.matches("[a-zA-Z][\\w+\\-]+:.*")) { // Rfc2396 s3.1 scheme,

                                                     // minus '.'

            // Does not begin with scheme, so try http://

            uri = "http://" + uri;

        }

        try {

            UURI uuri = UURIFactory.getInstance(uri);

            CrawlURI curi = new CrawlURI(uuri);

            curi.setSeed(true);

            curi.setSchedulingDirective(SchedulingConstants.MEDIUM);

            if (getSourceTagSeeds()) {

                curi.setSourceTag(curi.toString());

            }

            publishAddedSeed(curi);

        } catch (URIException e) {

            // try as nonseed line as fallback

            nonseedLine(uri);

        }

    }

最后调用父类SeedModule的void publishAddedSeed(CrawlURI curi)方法（observer模式）

protected void publishAddedSeed(CrawlURI curi) {

        for (SeedListener l: seedListeners) {

            l.addedSeed(curi);

        }

    }

BdbFrontier类间接实现了SeedListener接口（AbstractFrontier抽象类void addedSeed(CrawlURI puri)方法）

/**

     * When notified of a seed via the SeedListener interface, 

     * schedule it.

     * 

     * @see org.archive.modules.seeds.SeedListener#addedSeed(org.archive.modules.CrawlURI)

     */

    public void addedSeed(CrawlURI puri) {

        schedule(puri);

    }

---------------------------------------------------------------------------

本系列Heritrix 3.1.0 源码解析系本人原创

转载请注明出处 博客园 刺猬的温驯

本文链接 http://www.cnblogs.com/chenying99/archive/2013/04/20/3031924.html