// Return IP addr used by LCAP. If specified by (misleadingly named) // localIPAddress prop, might not really be our address (if we are // behind NAT). String getLcapIPAddr() { String ip = CurrentConfig.getParam(PARAM_LOCAL_IP); if (ip == null || ip.length() <= 0) { return getLocalIPAddr(); } return ip; }
public void stopService() { // mainly important in testing to blank this lastPluginDir = INITIAL_PLUGIN_DIR; if (CurrentConfig.getBooleanParam(PARAM_CLEAR_DIR_MAP, DEFAULT_CLEAR_DIR_MAP)) { // This should be in RepositoryManager.stopService() localRepositories = new HashMap(); } super.stopService(); }
public CrawlRuleTester(int crawlDepth, long crawlDelay, String baseUrl, ArchivalUnit au) { super("crawlrule tester"); m_crawlDepth = crawlDepth; long minFetchDelay = CurrentConfig.getLongParam( BaseArchivalUnit.PARAM_MIN_FETCH_DELAY, BaseArchivalUnit.DEFAULT_MIN_FETCH_DELAY); m_crawlDelay = Math.max(crawlDelay, minFetchDelay); m_baseUrl = baseUrl; m_au = au; }
public static String getRepositorySpec(ArchivalUnit au) { Configuration auConfig = au.getConfiguration(); if (auConfig != null) { // can be null in unit tests String repoSpec = auConfig.get(PluginManager.AU_PARAM_REPOSITORY); if (repoSpec != null && repoSpec.startsWith("local:")) { return repoSpec; } } return "local:" + CurrentConfig.getParam(PARAM_CACHE_LOCATION); }
protected RateLimiter recomputeFetchRateLimiter(RateLimiter oldLimiter) { String rate = CurrentConfig.getParam(PARAM_REGISTRY_FETCH_RATE, DEFAULT_REGISTRY_FETCH_RATE); Object limiterKey = getFetchRateLimiterKey(); if (limiterKey == null) { return RateLimiter.getRateLimiter(oldLimiter, rate, DEFAULT_REGISTRY_FETCH_RATE); } else { RateLimiter.Pool pool = RateLimiter.getPool(); return pool.findNamedRateLimiter(limiterKey, rate, DEFAULT_REGISTRY_FETCH_RATE); } }
public V3Serializer(LockssDaemon daemon) throws PollSerializerException { this.daemon = daemon; Configuration config = CurrentConfig.getCurrentConfig(); File stateDir = PollUtil.ensurePollStateRoot(); if (!FileUtil.ensureDirExists(stateDir)) { throw new PollSerializerException("Could not create state directory " + stateDir); } try { this.pollDir = FileUtil.createTempDir("pollstate-", "", stateDir); } catch (IOException ex) { throw new PollSerializerException("Cannot create temp dir in state directory" + stateDir, ex); } }
private void handlePause(int entriesBetweenSleep) { if ((entriesBetweenSleep % sleepAfter) == 0) { long pauseTime = CurrentConfig.getTimeIntervalParam(PARAM_RETRY_PAUSE, DEFAULT_RETRY_PAUSE); Deadline pause = Deadline.in(pauseTime); logger.debug3("Sleeping for " + StringUtil.timeIntervalToString(pauseTime)); while (!pause.expired()) { try { pause.sleep(); } catch (InterruptedException ie) { // no action } } } }
public void testHandleEmptyFile() throws Exception { MockCachedUrlSetSpec mspec = new MockCachedUrlSetSpec("http://www.example.com", null); CachedUrlSet mcus = new MockCachedUrlSet(mau, mspec); NodeStateImpl nodeState = new NodeStateImpl(mcus, -1, null, null, repository); nodeState.setPollHistoryList(new ArrayList()); // storing empty vector repository.storePollHistories(nodeState); String filePath = LockssRepositoryImpl.mapAuToFileLocation(tempDirPath, mau); filePath = LockssRepositoryImpl.mapUrlToFileLocation( filePath, "http://www.example.com/" + HistoryRepositoryImpl.HISTORY_FILE_NAME); File xmlFile = new File(filePath); assertTrue(xmlFile.exists()); nodeState.setPollHistoryList(new ArrayList()); repository.loadPollHistories(nodeState); assertEquals(0, nodeState.pollHistories.size()); mspec = new MockCachedUrlSetSpec("http://www.example2.com", null); mcus = new MockCachedUrlSet(mau, mspec); nodeState = new NodeStateImpl(mcus, -1, null, null, repository); filePath = LockssRepositoryImpl.mapAuToFileLocation(tempDirPath, mau); filePath = LockssRepositoryImpl.mapUrlToFileLocation(filePath, "http://www.example2.com/"); xmlFile = new File(filePath); assertFalse(xmlFile.exists()); xmlFile.mkdirs(); filePath += HistoryRepositoryImpl.HISTORY_FILE_NAME; xmlFile = new File(filePath); OutputStream os = new BufferedOutputStream(new FileOutputStream(xmlFile)); os.write(new byte[0]); os.close(); assertTrue(xmlFile.exists()); nodeState.setPollHistoryList(new ArrayList()); repository.loadPollHistories(nodeState); assertEquals(0, nodeState.pollHistories.size()); assertFalse(xmlFile.exists()); xmlFile = new File( filePath + CurrentConfig.getParam( ObjectSerializer.PARAM_FAILED_DESERIALIZATION_EXTENSION, ObjectSerializer.DEFAULT_FAILED_DESERIALIZATION_EXTENSION)); assertTrue(xmlFile.exists()); }
public void loadAuConfigDescrs(Configuration config) throws ConfigurationException { super.loadAuConfigDescrs(config); this.m_registryUrl = config.get(ConfigParamDescr.BASE_URL.getKey()); // Now we can construct a valid CC permission checker. m_permissionCheckers = // ListUtil.list(new CreativeCommonsPermissionChecker(m_registryUrl)); ListUtil.list(new CreativeCommonsPermissionChecker()); paramMap.putLong( KEY_AU_NEW_CONTENT_CRAWL_INTERVAL, CurrentConfig.getTimeIntervalParam( PARAM_REGISTRY_CRAWL_INTERVAL, DEFAULT_REGISTRY_CRAWL_INTERVAL)); if (log.isDebug2()) { log.debug2( "Setting Registry AU recrawl interval to " + StringUtil.timeIntervalToString( paramMap.getLong(KEY_AU_NEW_CONTENT_CRAWL_INTERVAL))); } }
/** Common page setup. */ protected Page newPage() { // Compute heading String heading = getHeading(); if (heading == null) { heading = "Box Administration"; } // Create page and layout header Page page = ServletUtil.doNewPage(getPageTitle(), isFramed()); Iterator inNavIterator; if (myServletDescr().hasNoNavTable()) { inNavIterator = CollectionUtil.EMPTY_ITERATOR; } else { inNavIterator = new FilterIterator( new ObjectArrayIterator(getServletDescrs()), new Predicate() { public boolean evaluate(Object obj) { return isServletInNav((ServletDescr) obj); } }); } ServletUtil.layoutHeader( this, page, heading, isLargeLogo(), getMachineName(), getLockssApp().getStartDate(), inNavIterator); String warnMsg = CurrentConfig.getParam(PARAM_UI_WARNING); if (warnMsg != null) { Composite warning = new Composite(); warning.add("<center><font color=red size=+1>"); warning.add(warnMsg); warning.add("</font></center><br>"); page.add(warning); } return page; }
/** Set the session timeout to the configured value */ protected void setSessionTimeout(HttpSession session) { Configuration config = CurrentConfig.getCurrentConfig(); setSessionTimeout( session, config.getTimeInterval(PARAM_UI_SESSION_TIMEOUT, DEFAULT_UI_SESSION_TIMEOUT)); }
public MultiPartRequest getMultiPartRequest() throws FormDataTooLongException, IOException { int maxUpload = CurrentConfig.getIntParam(PARAM_MAX_UPLOAD_FILE_SIZE, DEFAULT_MAX_UPLOAD_FILE_SIZE); return getMultiPartRequest(maxUpload); }
/** Set the map from the parameter in CurrentConfig. */ private void setMap() { setMap(CurrentConfig.getList(PARAM_REPUTATION_TRANSFER_MAP)); }
private Element makeForm() { Composite comp = new Composite(); Form frm = new Form(srvURL(myServletDescr())); frm.method("POST"); frm.add("<br><center>"); Input reload = new Input(Input.Submit, KEY_ACTION, ACTION_RELOAD_CONFIG); setTabOrder(reload); frm.add(reload); frm.add(" "); Input backup = new Input(Input.Submit, KEY_ACTION, ACTION_MAIL_BACKUP); setTabOrder(backup); frm.add(backup); frm.add(" "); Input crawlplug = new Input(Input.Submit, KEY_ACTION, ACTION_CRAWL_PLUGINS); setTabOrder(crawlplug); frm.add(crawlplug); frm.add("</center>"); ServletDescr d1 = AdminServletManager.SERVLET_HASH_CUS; if (isServletRunnable(d1)) { frm.add("<br><center>" + srvLink(d1, d1.heading) + "</center>"); } Input findUrl = new Input(Input.Submit, KEY_ACTION, ACTION_FIND_URL); Input findUrlText = new Input(Input.Text, KEY_URL); findUrlText.setSize(50); setTabOrder(findUrl); setTabOrder(findUrlText); frm.add("<br><center>" + findUrl + " " + findUrlText + "</center>"); Input thrw = new Input(Input.Submit, KEY_ACTION, ACTION_THROW_IOEXCEPTION); Input thmsg = new Input(Input.Text, KEY_MSG); setTabOrder(thrw); setTabOrder(thmsg); frm.add("<br><center>" + thrw + " " + thmsg + "</center>"); frm.add("<br><center>AU Actions: select AU</center>"); Composite ausel = ServletUtil.layoutSelectAu(this, KEY_AUID, formAuid); frm.add("<br><center>" + ausel + "</center>"); setTabOrder(ausel); Input v3Poll = new Input( Input.Submit, KEY_ACTION, (showForcePoll ? ACTION_FORCE_START_V3_POLL : ACTION_START_V3_POLL)); Input crawl = new Input( Input.Submit, KEY_ACTION, (showForceCrawl ? ACTION_FORCE_START_CRAWL : ACTION_START_CRAWL)); frm.add("<br><center>"); frm.add(v3Poll); frm.add(" "); frm.add(crawl); if (CurrentConfig.getBooleanParam(PARAM_ENABLE_DEEP_CRAWL, DEFAULT_ENABLE_DEEP_CRAWL)) { Input deepCrawl = new Input( Input.Submit, KEY_ACTION, (showForceCrawl ? ACTION_FORCE_START_DEEP_CRAWL : ACTION_START_DEEP_CRAWL)); Input depthText = new Input(Input.Text, KEY_REFETCH_DEPTH, formDepth); depthText.setSize(4); setTabOrder(depthText); frm.add(" "); frm.add(deepCrawl); frm.add(depthText); } Input checkSubstance = new Input(Input.Submit, KEY_ACTION, ACTION_CHECK_SUBSTANCE); frm.add("<br>"); frm.add(checkSubstance); if (metadataMgr != null) { Input reindex = new Input( Input.Submit, KEY_ACTION, (showForceReindexMetadata ? ACTION_FORCE_REINDEX_METADATA : ACTION_REINDEX_METADATA)); frm.add(" "); frm.add(reindex); Input disableIndexing = new Input(Input.Submit, KEY_ACTION, ACTION_DISABLE_METADATA_INDEXING); frm.add(" "); frm.add(disableIndexing); } frm.add("</center>"); comp.add(frm); return comp; }
protected String getFetchRateLimiterSource() { return CurrentConfig.getParam( PARAM_REGISTRY_FETCH_RATE_LIMITER_SOURCE, DEFAULT_REGISTRY_FETCH_RATE_LIMITER_SOURCE); }
/** Explode the archive into its constituent elements */ public void explode() throws CacheException { CachedUrl cachedUrl = null; int goodEntries = 0; int badEntries = 0; int ignoredEntries = 0; int entriesBetweenSleep = 0; ArchiveReader arcReader = null; logger.info( (storeArchive ? "Storing" : "Fetching") + " WARC file: " + origUrl + " will explode"); try { if (storeArchive) { UrlCacher uc = au.makeUrlCacher(new UrlData(arcStream, arcProps, fetchUrl)); BitSet bs = new BitSet(); bs.set(UrlCacher.DONT_CLOSE_INPUT_STREAM_FLAG); uc.setFetchFlags(bs); uc.storeContent(); archiveData.resetInputStream(); arcStream = archiveData.input; } // Wrap it in an ArchiveReader logger.debug3("About to wrap stream"); arcReader = wrapStream(fetchUrl, arcStream); logger.debug3("wrapStream() returns " + (arcReader == null ? "null" : "non-null")); // Explode it if (arcReader == null) { throw new CacheException.ExploderException("no WarcReader for " + origUrl); } ArchivalUnit au = crawlFacade.getAu(); Set stemSet = new HashSet(); logger.debug("Exploding " + fetchUrl); // Iterate through the elements in the WARC file, except the first Iterator i = arcReader.iterator(); // Skip first record for (i.next(); i.hasNext(); ) { // XXX probably not necessary helper.pokeWDog(); if ((++entriesBetweenSleep % sleepAfter) == 0) { long pauseTime = CurrentConfig.getTimeIntervalParam(PARAM_RETRY_PAUSE, DEFAULT_RETRY_PAUSE); Deadline pause = Deadline.in(pauseTime); logger.debug3("Sleeping for " + StringUtil.timeIntervalToString(pauseTime)); while (!pause.expired()) { try { pause.sleep(); } catch (InterruptedException ie) { // no action } } } ArchiveRecord element = (ArchiveRecord) i.next(); // Each element is a URL to be cached in a suitable AU ArchiveRecordHeader elementHeader = element.getHeader(); String elementUrl = elementHeader.getUrl(); String elementMimeType = elementHeader.getMimetype(); long elementLength = elementHeader.getLength(); logger.debug2("WARC url " + elementUrl + " mime " + elementMimeType); if (elementUrl.startsWith("http:")) { ArchiveEntry ae = new ArchiveEntry( elementUrl, elementLength, 0, // XXX need to convert getDate string to long element, // ArchiveRecord extends InputStream this, fetchUrl); ae.setHeaderFields(makeCIProperties(elementHeader)); long bytesStored = elementLength; logger.debug3("ArchiveEntry: " + ae.getName() + " bytes " + bytesStored); try { helper.process(ae); } catch (PluginException ex) { throw new CacheException.ExploderException("helper.process() threw", ex); } if (ae.getBaseUrl() != null) { if (ae.getRestOfUrl() != null && ae.getHeaderFields() != null) { storeEntry(ae); handleAddText(ae); goodEntries++; crawlFacade.getCrawlerStatus().addContentBytesFetched(bytesStored); } else { ignoredEntries++; } } else { badEntries++; logger.debug2("Can't map " + elementUrl + " from " + archiveUrl); } } } } catch (IOException ex) { throw new CacheException.ExploderException(ex); } finally { if (arcReader != null) try { arcReader.close(); arcReader = null; } catch (IOException ex) { throw new CacheException.ExploderException(ex); } if (cachedUrl != null) { cachedUrl.release(); } IOUtil.safeClose(arcStream); } if (badEntries == 0 && goodEntries > 0) { // Make it look like a new crawl finished on each AU to which // URLs were added. for (Iterator it = touchedAus.iterator(); it.hasNext(); ) { ArchivalUnit au = (ArchivalUnit) it.next(); logger.debug3(archiveUrl + " touching " + au.toString()); AuUtil.getDaemon(au).getNodeManager(au).newContentCrawlFinished(); } } else { ArchivalUnit au = crawlFacade.getAu(); String msg = archiveUrl + ": " + badEntries + "/" + goodEntries + " bad entries"; throw new CacheException.UnretryableException(msg); } }