/** * 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();}}

/*** 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(){@Overridepublic void run() {announceSeeds(latch); while(latch.getCount()>0) {latch.countDown();}}}.start();try {latch.await();} catch (InterruptedException e) {// do nothing
            } } else {announceSeeds(null); }}

protected void announceSeeds(CountDownLatch latchOrNull) {BufferedReader reader = new BufferedReader(textSource.obtainReader());       try {announceSeedsFromReader(reader,latchOrNull);    } finally {IOUtils.closeQuietly(reader);}}

/*** 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(); }

/*** 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);}}

protected void publishAddedSeed(CrawlURI curi) {for (SeedListener l: seedListeners) {l.addedSeed(curi);}}

/*** 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);}