List of usage examples for java.util List clear
void clear();
From source file:it.units.malelab.ege.MappingPropertiesExperimenter.java
public static void main(String[] args) throws IOException, InterruptedException, ExecutionException { final int n = 10000; final int nDist = 10000; //prepare problems and methods List<String> problems = Lists.newArrayList("bool-parity5", "bool-mopm3", "sr-keijzer6", "sr-nguyen7", "sr-pagie1", "sr-vladislavleva4", "other-klandscapes3", "other-klandscapes7", "other-text"); List<String> mappers = new ArrayList<>(); for (int gs : new int[] { 64, 128, 256, 512, 1024 }) { mappers.add("ge-" + gs + "-2"); mappers.add("ge-" + gs + "-4"); mappers.add("ge-" + gs + "-8"); mappers.add("ge-" + gs + "-12"); mappers.add("pige-" + gs + "-4"); mappers.add("pige-" + gs + "-8"); mappers.add("pige-" + gs + "-16"); mappers.add("pige-" + gs + "-24"); mappers.add("hge-" + gs + "-0"); mappers.add("whge-" + gs + "-2"); mappers.add("whge-" + gs + "-3"); mappers.add("whge-" + gs + "-5"); }/*from w w w. j av a 2s . c o m*/ mappers.add("sge-0-5"); mappers.add("sge-0-6"); mappers.add("sge-0-7"); mappers.add("sge-0-8"); mappers.clear(); mappers.addAll(Lists.newArrayList("ge-1024-8", "pige-1024-16", "hge-1024-0", "whge-1024-3", "sge-0-6")); PrintStream filePrintStream = null; if (args.length > 0) { filePrintStream = new PrintStream(args[0]); } else { filePrintStream = System.out; } filePrintStream.printf("problem;mapper;genotypeSize;param;property;value%n"); //prepare distances Distance<Node<String>> phenotypeDistance = new CachedDistance<>(new LeavesEdit<String>()); Distance<Sequence> genotypeDistance = new CachedDistance<>(new Hamming()); //iterate for (String problemName : problems) { for (String mapperName : mappers) { System.out.printf("%20.20s, %20.20s", problemName, mapperName); //build problem Problem<String, NumericFitness> problem = null; if (problemName.equals("bool-parity5")) { problem = new Parity(5); } else if (problemName.equals("bool-mopm3")) { problem = new MultipleOutputParallelMultiplier(3); } else if (problemName.equals("sr-keijzer6")) { problem = new HarmonicCurve(); } else if (problemName.equals("sr-nguyen7")) { problem = new Nguyen7(1); } else if (problemName.equals("sr-pagie1")) { problem = new Pagie1(); } else if (problemName.equals("sr-vladislavleva4")) { problem = new Vladislavleva4(1); } else if (problemName.equals("other-klandscapes3")) { problem = new KLandscapes(3); } else if (problemName.equals("other-klandscapes7")) { problem = new KLandscapes(7); } else if (problemName.equals("other-text")) { problem = new Text(); } //build configuration and evolver Mapper mapper = null; int genotypeSize = Integer.parseInt(mapperName.split("-")[1]); int mapperMainParam = Integer.parseInt(mapperName.split("-")[2]); if (mapperName.split("-")[0].equals("ge")) { mapper = new StandardGEMapper<>(mapperMainParam, 1, problem.getGrammar()); } else if (mapperName.split("-")[0].equals("pige")) { mapper = new PiGEMapper<>(mapperMainParam, 1, problem.getGrammar()); } else if (mapperName.split("-")[0].equals("sge")) { mapper = new SGEMapper<>(mapperMainParam, problem.getGrammar()); } else if (mapperName.split("-")[0].equals("hge")) { mapper = new HierarchicalMapper<>(problem.getGrammar()); } else if (mapperName.split("-")[0].equals("whge")) { mapper = new WeightedHierarchicalMapper<>(mapperMainParam, false, true, problem.getGrammar()); } //prepare things Random random = new Random(1); Set<Sequence> genotypes = new LinkedHashSet<>(n); //build genotypes if (mapperName.split("-")[0].equals("sge")) { SGEGenotypeFactory<String> factory = new SGEGenotypeFactory<>((SGEMapper) mapper); while (genotypes.size() < n) { genotypes.add(factory.build(random)); } genotypeSize = factory.getBitSize(); } else { BitsGenotypeFactory factory = new BitsGenotypeFactory(genotypeSize); while (genotypes.size() < n) { genotypes.add(factory.build(random)); } } //build and fill map Multimap<Node<String>, Sequence> multimap = HashMultimap.create(); int progress = 0; for (Sequence genotype : genotypes) { Node<String> phenotype; try { if (mapperName.split("-")[0].equals("sge")) { phenotype = mapper.map((SGEGenotype<String>) genotype, new HashMap<>()); } else { phenotype = mapper.map((BitsGenotype) genotype, new HashMap<>()); } } catch (MappingException e) { phenotype = Node.EMPTY_TREE; } multimap.put(phenotype, genotype); progress = progress + 1; if (progress % Math.round(n / 10) == 0) { System.out.print("."); } } System.out.println(); //compute distances List<Pair<Double, Double>> allDistances = new ArrayList<>(); List<Pair<Double, Double>> allValidDistances = new ArrayList<>(); Multimap<Node<String>, Double> genotypeDistances = ArrayListMultimap.create(); for (Node<String> phenotype : multimap.keySet()) { for (Sequence genotype1 : multimap.get(phenotype)) { for (Sequence genotype2 : multimap.get(phenotype)) { double gDistance = genotypeDistance.d(genotype1, genotype2); genotypeDistances.put(phenotype, gDistance); if (genotypeDistances.get(phenotype).size() > nDist) { break; } } if (genotypeDistances.get(phenotype).size() > nDist) { break; } } } List<Map.Entry<Node<String>, Sequence>> entries = new ArrayList<>(multimap.entries()); Collections.shuffle(entries, random); for (Map.Entry<Node<String>, Sequence> entry1 : entries) { for (Map.Entry<Node<String>, Sequence> entry2 : entries) { double gDistance = genotypeDistance.d(entry1.getValue(), entry2.getValue()); double pDistance = phenotypeDistance.d(entry1.getKey(), entry2.getKey()); allDistances.add(new Pair<>(gDistance, pDistance)); if (!Node.EMPTY_TREE.equals(entry1.getKey()) && !Node.EMPTY_TREE.equals(entry2.getKey())) { allValidDistances.add(new Pair<>(gDistance, pDistance)); } if (allDistances.size() > nDist) { break; } } if (allDistances.size() > nDist) { break; } } //compute properties double invalidity = (double) multimap.get(Node.EMPTY_TREE).size() / (double) genotypes.size(); double redundancy = 1 - (double) multimap.keySet().size() / (double) genotypes.size(); double validRedundancy = redundancy; if (multimap.keySet().contains(Node.EMPTY_TREE)) { validRedundancy = 1 - ((double) multimap.keySet().size() - 1d) / (double) (genotypes.size() - multimap.get(Node.EMPTY_TREE).size()); } double locality = Utils.pearsonCorrelation(allDistances); double validLocality = Utils.pearsonCorrelation(allValidDistances); double[] sizes = new double[multimap.keySet().size()]; double[] meanGenotypeDistances = new double[multimap.keySet().size()]; int invalidIndex = -1; int c = 0; for (Node<String> phenotype : multimap.keySet()) { if (Node.EMPTY_TREE.equals(phenotype)) { invalidIndex = c; } sizes[c] = multimap.get(phenotype).size(); double[] distances = new double[genotypeDistances.get(phenotype).size()]; int k = 0; for (Double distance : genotypeDistances.get(phenotype)) { distances[k] = distance; k = k + 1; } meanGenotypeDistances[c] = StatUtils.mean(distances); c = c + 1; } double nonUniformity = Math.sqrt(StatUtils.variance(sizes)) / StatUtils.mean(sizes); double nonSynonymousity = StatUtils.mean(meanGenotypeDistances) / StatUtils.mean(firsts(allDistances)); double validNonUniformity = nonUniformity; double validNonSynonymousity = nonSynonymousity; if (invalidIndex != -1) { double[] validSizes = new double[multimap.keySet().size() - 1]; double[] validMeanGenotypeDistances = new double[multimap.keySet().size() - 1]; if (invalidIndex > 0) { System.arraycopy(sizes, 0, validSizes, 0, invalidIndex); System.arraycopy(meanGenotypeDistances, 0, validMeanGenotypeDistances, 0, invalidIndex); } System.arraycopy(sizes, invalidIndex + 1, validSizes, invalidIndex, sizes.length - invalidIndex - 1); System.arraycopy(meanGenotypeDistances, invalidIndex + 1, validMeanGenotypeDistances, invalidIndex, meanGenotypeDistances.length - invalidIndex - 1); validNonUniformity = Math.sqrt(StatUtils.variance(validSizes)) / StatUtils.mean(validSizes); validNonSynonymousity = StatUtils.mean(validMeanGenotypeDistances) / StatUtils.mean(firsts(allValidDistances)); } //compute locality filePrintStream.printf("%s;%s;%d;%d;invalidity;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, invalidity); filePrintStream.printf("%s;%s;%d;%d;redundancy;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, redundancy); filePrintStream.printf("%s;%s;%d;%d;validRedundancy;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, validRedundancy); filePrintStream.printf("%s;%s;%d;%d;locality;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, locality); filePrintStream.printf("%s;%s;%d;%d;validLLocality;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, validLocality); filePrintStream.printf("%s;%s;%d;%d;nonUniformity;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, nonUniformity); filePrintStream.printf("%s;%s;%d;%d;validNonUniformity;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, validNonUniformity); filePrintStream.printf("%s;%s;%d;%d;nonSynonymousity;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, nonSynonymousity); filePrintStream.printf("%s;%s;%d;%d;validNonSynonymousity;%f %n", problemName, mapperName.split("-")[0], genotypeSize, mapperMainParam, validNonSynonymousity); } } if (filePrintStream != null) { filePrintStream.close(); } }
From source file:com.hp.test.framework.Reporting.Utlis.java
public static void main(String ar[]) throws IOException { ArrayList<String> runs_list = new ArrayList<String>(); String basepath = replacelogs(); String path = basepath + "ATU Reports\\Results"; File directory = new File(path); File[] subdirs = directory.listFiles((FileFilter) DirectoryFileFilter.DIRECTORY); String htmlReport = basepath + "HTML_Design_Files\\CSS\\HtmlReport.html"; for (File dir : subdirs) { runs_list.add(dir.getName());//w w w . j ava 2 s. c o m } String Reports_path = basepath + "ATU Reports\\"; int LatestRun = Utlis.getLastRun(Reports_path); String Last_run_path = Reports_path + "Results\\Run_" + String.valueOf(LatestRun) + "\\"; HtmlParse.replaceMainTable(false, new File(Last_run_path + "/CurrentRun.html")); HtmlParse.replaceCountsinJSFile(new File("HTML_Design_Files/JS/3dChart.js"), Last_run_path); UpdateTestCaseDesciption.basepath = Last_run_path; UpdateTestCaseDesciption.getTestCaseHtmlPath(Last_run_path + "/CurrentRun.html"); UpdateTestCaseDesciption.replaceDetailsTable(Last_run_path + "/CurrentRun.html"); // GenerateFailReport.genarateFailureReport(new File(htmlReport), Reports_path + "Results\\Run_" + String.valueOf(LatestRun)); genarateFailureReport(new File(htmlReport), Reports_path + "Results\\"); Map<String, List<String>> runCounts = GetCountsrunsWise(runs_list, path); int success = replaceCounts(runCounts, path); if (success == 0) { File SourceFile = new File(path + "\\lineChart_temp.js"); File RenameFile = new File(path + "\\lineChart.js"); renameOriginalFile(SourceFile, RenameFile); File SourceFile1 = new File(path + "\\barChart_temp.js"); File RenameFile1 = new File(path + "\\barChart.js"); renameOriginalFile(SourceFile1, RenameFile1); Utlis.getpaths(Reports_path + "\\Results\\Run_" + String.valueOf(LatestRun)); try { Utlis.replaceMainTable(false, new File(Reports_path + "index.html")); Utlis.replaceMainTable(true, new File(Reports_path + "results\\" + "ConsolidatedPage.html")); Utlis.replaceMainTable(true, new File(Reports_path + "Results\\Run_" + String.valueOf(LatestRun) + "CurrentRun.html")); fileList.add( new File(Reports_path + "\\Results\\Run_" + String.valueOf(LatestRun) + "CurrentRun.html")); for (File f : fileList) { Utlis.replaceMainTable(true, f); } } catch (Exception ex) { log.info("Error in updating Report format" + ex.getMessage()); } Last_run_path = Reports_path + "Results\\Run_" + String.valueOf(LatestRun) + "\\"; // HtmlParse.replaceMainTable(false, new File(Last_run_path + "/CurrentRun.html")); // HtmlParse.replaceCountsinJSFile(new File("../HTML_Design_Files/JS/3dChart.js"), Last_run_path); ArrayList<String> to_list = new ArrayList<String>(); ReportingProperties reportingproperties = new ReportingProperties(); String temp_eml = reportingproperties.getProperty("TOLIST"); String JenkinsURL = reportingproperties.getProperty("JENKINSURL"); String ScreenShotsDir = reportingproperties.getProperty("ScreenShotsDirectory"); Boolean cleanScreenshotsDir = Boolean.valueOf(reportingproperties.getProperty("CleanPreScreenShots")); Boolean generatescreenshots = Boolean.valueOf(reportingproperties.getProperty("GenerateScreenShots")); String HtmlreportFilePrefix = reportingproperties.getProperty("HtmlreportFilePrefix"); if (cleanScreenshotsDir) { if (!CleanFilesinDir(ScreenShotsDir)) { log.error("Not able to Clean the Previous Run Details in the paht" + ScreenShotsDir); } else { log.info("Cleaning Previous Run Details in the paht" + ScreenShotsDir + "Sucess"); } } List<String> scr_fileList; List<String> html_fileList; if (generatescreenshots) { scr_fileList = GetFileListinDir(ScreenShotsDir, "png"); int len = scr_fileList.size(); len = len + 1; screenshot.generatescreenshot(Last_run_path + "CurrentRun.html", ScreenShotsDir + "screenshot_" + len + ".png"); File source = new File(Reports_path + "Results\\HtmlReport.html"); File dest = new File(ScreenShotsDir + HtmlreportFilePrefix + "_HtmlReport.html"); // Files.copy(f.toPath(), (new File((ScreenShotsDir+HtmlreportFilePrefix+"_HtmlReport.html").toPath(),StandardCopyOption.REPLACE_EXISTING); FileUtils.copyFile(source, dest); scr_fileList.clear(); } scr_fileList = GetFileListinDir(ScreenShotsDir, "png"); html_fileList = GetFileListinDir(ScreenShotsDir, "html"); if (temp_eml.length() > 1) { String[] to_list_temp = temp_eml.split(","); if (to_list_temp.length > 0) { for (String to_list_temp1 : to_list_temp) { to_list.add(to_list_temp1); } } if (to_list.size() > 0) { screenshot.generatescreenshot(Last_run_path + "CurrentRun.html", Last_run_path + "screenshot.png"); // cleanTempDir.cleanandCreate(Reports_path, LatestRun); // ZipUtils.ZipFolder(Reports_path + "temp", Reports_path + "ISTF_Reports.zip"); if (generatescreenshots) { SendingEmail.sendmail(to_list, JenkinsURL, scr_fileList, html_fileList); } else { SendingEmail.sendmail(to_list, JenkinsURL, Reports_path + "/Results/HtmlReport.html", Last_run_path + "screenshot.png"); } // FileUtils.deleteQuietly(new File(Reports_path + "ISTF_Reports.zip")); // FileUtils.deleteDirectory(new File(Reports_path + "temp")); } } } }
From source file:com.finderbots.miner2.pinterest.PinterestCrawlAndMinerTool.java
public static void main(String[] args) { Options options = new Options(); CmdLineParser parser = new CmdLineParser(options); try {//from www . ja va 2 s . c o m parser.parseArgument(args); } catch (CmdLineException e) { System.err.println(e.getMessage()); printUsageAndExit(parser); } // Before we get too far along, see if the domain looks valid. String domain = options.getDomain(); String urlsFile = options.getUrlsFile(); if (domain != null) { validateDomain(domain, parser); } else { if (urlsFile == null) { System.err.println( "Either a target domain should be specified or a file with a list of urls needs to be provided"); printUsageAndExit(parser); } } if (domain != null && urlsFile != null) { System.out.println("Warning: Both domain and urls file list provided - using domain"); } String outputDirName = options.getOutputDir(); if (options.isDebugLogging()) { System.setProperty("bixo.root.level", "DEBUG"); } else { System.setProperty("bixo.root.level", "INFO"); } if (options.getLoggingAppender() != null) { // Set console vs. DRFA vs. something else System.setProperty("bixo.appender", options.getLoggingAppender()); } String logsDir = options.getLogsDir(); if (!logsDir.endsWith("/")) { logsDir = logsDir + "/"; } try { JobConf conf = new JobConf(); Path outputPath = new Path(outputDirName); FileSystem fs = outputPath.getFileSystem(conf); // First check if the user wants to clean if (options.isCleanOutputDir()) { if (fs.exists(outputPath)) { fs.delete(outputPath, true); } } // See if the user isn't starting from scratch then set up the // output directory and create an initial urls subdir. if (!fs.exists(outputPath)) { fs.mkdirs(outputPath); // Create a "0-<timestamp>" sub-directory with just a /crawldb subdir // In the /crawldb dir the input file will have a single URL for the target domain. Path curLoopDir = CrawlDirUtils.makeLoopDir(fs, outputPath, 0); String curLoopDirName = curLoopDir.getName(); setLoopLoggerFile(logsDir + curLoopDirName, 0); Path crawlDbPath = new Path(curLoopDir, CrawlConfig.CRAWLDB_SUBDIR_NAME); if (domain != null) { importOneDomain(domain, crawlDbPath, conf); } else { importUrls(urlsFile, crawlDbPath); } } Path latestDirPath = CrawlDirUtils.findLatestLoopDir(fs, outputPath); if (latestDirPath == null) { System.err.println("No previous cycle output dirs exist in " + outputDirName); printUsageAndExit(parser); } Path crawlDbPath = new Path(latestDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); // Set up the start and end loop counts. int startLoop = CrawlDirUtils.extractLoopNumber(latestDirPath); int endLoop = startLoop + options.getNumLoops(); // Set up the UserAgent for the fetcher. UserAgent userAgent = new UserAgent(options.getAgentName(), CrawlConfig.EMAIL_ADDRESS, CrawlConfig.WEB_ADDRESS); // You also get to customize the FetcherPolicy FetcherPolicy defaultPolicy; if (options.getCrawlDuration() != 0) { defaultPolicy = new AdaptiveFetcherPolicy(options.getEndCrawlTime(), options.getCrawlDelay()); } else { defaultPolicy = new FetcherPolicy(); } defaultPolicy.setMaxContentSize(CrawlConfig.MAX_CONTENT_SIZE); defaultPolicy.setRequestTimeout(10L * 1000L);//10 seconds // COMPLETE for crawling a single site, EFFICIENT for many sites if (options.getCrawlPolicy().equals(Options.IMPOLITE_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.IMPOLITE); } else if (options.getCrawlPolicy().equals(Options.EFFICIENT_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.EFFICIENT); } else if (options.getCrawlPolicy().equals(Options.COMPLETE_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.COMPLETE); } // It is a good idea to set up a crawl duration when running long crawls as you may // end up in situations where the fetch slows down due to a 'long tail' and by // specifying a crawl duration you know exactly when the crawl will end. int crawlDurationInMinutes = options.getCrawlDuration(); boolean hasEndTime = crawlDurationInMinutes != Options.NO_CRAWL_DURATION; long targetEndTime = hasEndTime ? System.currentTimeMillis() + (crawlDurationInMinutes * CrawlConfig.MILLISECONDS_PER_MINUTE) : FetcherPolicy.NO_CRAWL_END_TIME; // By setting up a url filter we only deal with urls that we want to // instead of all the urls that we extract. BaseUrlFilter urlFilter = null; List<String> patterns = null; String regexUrlFiltersFile = options.getRegexUrlFiltersFile(); if (regexUrlFiltersFile != null) { patterns = RegexUrlDatumFilter.getUrlFilterPatterns(regexUrlFiltersFile); } else { patterns = RegexUrlDatumFilter.getDefaultUrlFilterPatterns(); if (domain != null) { String domainPatterStr = "+(?i)^(http|https)://([a-z0-9]*\\.)*" + domain; patterns.add(domainPatterStr); } else { String protocolPatterStr = "+(?i)^(http|https)://*"; patterns.add(protocolPatterStr); //Log.warn("Defaulting to basic url regex filtering (just suffix and protocol"); } } urlFilter = new RegexUrlDatumFilter(patterns.toArray(new String[patterns.size()])); // get a list of patterns which tell the miner which URLs to include or exclude. patterns.clear(); RegexUrlStringFilter urlsToMineFilter = null; String regexUrlsToMineFiltersFile = options.getRegexUrlToMineFile(); AnalyzeHtml analyzer = null; if (regexUrlsToMineFiltersFile != null) { patterns = RegexUrlDatumFilter.getUrlFilterPatterns(regexUrlsToMineFiltersFile); urlsToMineFilter = new RegexUrlStringFilter(patterns.toArray(new String[patterns.size()])); analyzer = new AnalyzeHtml(urlsToMineFilter); } // OK, now we're ready to start looping, since we've got our current // settings for (int curLoop = startLoop + 1; curLoop <= endLoop; curLoop++) { // Adjust target end time, if appropriate. if (hasEndTime) { int remainingLoops = (endLoop - curLoop) + 1; long now = System.currentTimeMillis(); long perLoopTime = (targetEndTime - now) / remainingLoops; defaultPolicy.setCrawlEndTime(now + perLoopTime); } Path curLoopDirPath = CrawlDirUtils.makeLoopDir(fs, outputPath, curLoop); String curLoopDirName = curLoopDirPath.getName(); setLoopLoggerFile(logsDir + curLoopDirName, curLoop); Flow flow = PinterestCrawlAndMinerWorkflow.createFlow(curLoopDirPath, crawlDbPath, defaultPolicy, userAgent, urlFilter, analyzer, options); flow.complete(); // Writing out .dot files is a good way to verify your flows. flow.writeDOT("valid-flow.dot"); // Update crawlDbPath to point to the latest crawl db crawlDbPath = new Path(curLoopDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); } } catch (PlannerException e) { e.writeDOT("failed-flow.dot"); System.err.println("PlannerException: " + e.getMessage()); e.printStackTrace(System.err); System.exit(-1); } catch (Throwable t) { System.err.println("Exception running tool: " + t.getMessage()); t.printStackTrace(System.err); System.exit(-1); } }
From source file:com.finderbots.miner2.tomatoes.RTCriticsCrawlAndMinerTool.java
public static void main(String[] args) { Options options = new Options(); CmdLineParser parser = new CmdLineParser(options); try {//from w w w. j av a 2 s . co m parser.parseArgument(args); } catch (CmdLineException e) { System.err.println(e.getMessage()); printUsageAndExit(parser); } // Before we get too far along, see if the domain looks valid. String domain = options.getDomain(); String urlsFile = options.getUrlsFile(); if (domain != null) { validateDomain(domain, parser); } else { if (urlsFile == null) { System.err.println( "Either a target domain should be specified or a file with a list of urls needs to be provided"); printUsageAndExit(parser); } } if (domain != null && urlsFile != null) { System.out.println("Warning: Both domain and urls file list provided - using domain"); } String outputDirName = options.getOutputDir(); if (options.isDebugLogging()) { System.setProperty("bixo.root.level", "DEBUG"); } else { System.setProperty("bixo.root.level", "INFO"); } if (options.getLoggingAppender() != null) { // Set console vs. DRFA vs. something else System.setProperty("bixo.appender", options.getLoggingAppender()); } String logsDir = options.getLogsDir(); if (!logsDir.endsWith("/")) { logsDir = logsDir + "/"; } try { JobConf conf = new JobConf(); Path outputPath = new Path(outputDirName); FileSystem fs = outputPath.getFileSystem(conf); // First check if the user wants to clean if (options.isCleanOutputDir()) { if (fs.exists(outputPath)) { fs.delete(outputPath, true); } } // See if the user isn't starting from scratch then set up the // output directory and create an initial urls subdir. if (!fs.exists(outputPath)) { fs.mkdirs(outputPath); // Create a "0-<timestamp>" sub-directory with just a /crawldb subdir // In the /crawldb dir the input file will have a single URL for the target domain. Path curLoopDir = CrawlDirUtils.makeLoopDir(fs, outputPath, 0); String curLoopDirName = curLoopDir.getName(); setLoopLoggerFile(logsDir + curLoopDirName, 0); Path crawlDbPath = new Path(curLoopDir, CrawlConfig.CRAWLDB_SUBDIR_NAME); if (domain != null) { importOneDomain(domain, crawlDbPath, conf); } else { importUrls(urlsFile, crawlDbPath); } } Path latestDirPath = CrawlDirUtils.findLatestLoopDir(fs, outputPath); if (latestDirPath == null) { System.err.println("No previous cycle output dirs exist in " + outputDirName); printUsageAndExit(parser); } Path crawlDbPath = new Path(latestDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); // Set up the start and end loop counts. int startLoop = CrawlDirUtils.extractLoopNumber(latestDirPath); int endLoop = startLoop + options.getNumLoops(); // Set up the UserAgent for the fetcher. UserAgent userAgent = new UserAgent(options.getAgentName(), CrawlConfig.EMAIL_ADDRESS, CrawlConfig.WEB_ADDRESS); // You also get to customize the FetcherPolicy FetcherPolicy defaultPolicy; if (options.getCrawlDuration() != 0) { defaultPolicy = new AdaptiveFetcherPolicy(options.getEndCrawlTime(), options.getCrawlDelay()); } else { defaultPolicy = new FetcherPolicy(); } defaultPolicy.setMaxContentSize(CrawlConfig.MAX_CONTENT_SIZE); defaultPolicy.setRequestTimeout(10L * 1000L);//10 seconds // COMPLETE for crawling a single site, EFFICIENT for many sites if (options.getCrawlPolicy().equals(Options.IMPOLITE_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.IMPOLITE); } else if (options.getCrawlPolicy().equals(Options.EFFICIENT_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.EFFICIENT); } else if (options.getCrawlPolicy().equals(Options.COMPLETE_CRAWL_POLICY)) { defaultPolicy.setFetcherMode(FetcherPolicy.FetcherMode.COMPLETE); } // It is a good idea to set up a crawl duration when running long crawls as you may // end up in situations where the fetch slows down due to a 'long tail' and by // specifying a crawl duration you know exactly when the crawl will end. int crawlDurationInMinutes = options.getCrawlDuration(); boolean hasEndTime = crawlDurationInMinutes != Options.NO_CRAWL_DURATION; long targetEndTime = hasEndTime ? System.currentTimeMillis() + (crawlDurationInMinutes * CrawlConfig.MILLISECONDS_PER_MINUTE) : FetcherPolicy.NO_CRAWL_END_TIME; // By setting up a url filter we only deal with urls that we want to // instead of all the urls that we extract. BaseUrlFilter urlFilter = null; List<String> patterns = null; String regexUrlFiltersFile = options.getRegexUrlFiltersFile(); if (regexUrlFiltersFile != null) { patterns = RegexUrlDatumFilter.getUrlFilterPatterns(regexUrlFiltersFile); } else { patterns = RegexUrlDatumFilter.getDefaultUrlFilterPatterns(); if (domain != null) { String domainPatterStr = "+(?i)^(http|https)://([a-z0-9]*\\.)*" + domain; patterns.add(domainPatterStr); } else { String protocolPatterStr = "+(?i)^(http|https)://*"; patterns.add(protocolPatterStr); //Log.warn("Defaulting to basic url regex filtering (just suffix and protocol"); } } urlFilter = new RegexUrlDatumFilter(patterns.toArray(new String[patterns.size()])); // get a list of patterns which tell the miner which URLs to include or exclude. patterns.clear(); RegexUrlStringFilter urlsToMineFilter = null; String regexUrlsToMineFiltersFile = options.getRegexUrlToMineFile(); MineRTCriticsPreferences prefsAnalyzer = null; if (regexUrlsToMineFiltersFile != null) { patterns = RegexUrlDatumFilter.getUrlFilterPatterns(regexUrlsToMineFiltersFile); urlsToMineFilter = new RegexUrlStringFilter(patterns.toArray(new String[patterns.size()])); prefsAnalyzer = new MineRTCriticsPreferences(urlsToMineFilter); } // OK, now we're ready to start looping, since we've got our current // settings for (int curLoop = startLoop + 1; curLoop <= endLoop; curLoop++) { // Adjust target end time, if appropriate. if (hasEndTime) { int remainingLoops = (endLoop - curLoop) + 1; long now = System.currentTimeMillis(); long perLoopTime = (targetEndTime - now) / remainingLoops; defaultPolicy.setCrawlEndTime(now + perLoopTime); } Path curLoopDirPath = CrawlDirUtils.makeLoopDir(fs, outputPath, curLoop); String curLoopDirName = curLoopDirPath.getName(); setLoopLoggerFile(logsDir + curLoopDirName, curLoop); Flow flow = RTCriticsCrawlAndMinerWorkflow.createFlow(curLoopDirPath, crawlDbPath, defaultPolicy, userAgent, urlFilter, prefsAnalyzer, options); flow.complete(); // Writing out .dot files is a good way to verify your flows. flow.writeDOT("valid-flow.dot"); // Update crawlDbPath to point to the latest crawl db crawlDbPath = new Path(curLoopDirPath, CrawlConfig.CRAWLDB_SUBDIR_NAME); } } catch (PlannerException e) { e.writeDOT("failed-flow.dot"); System.err.println("PlannerException: " + e.getMessage()); e.printStackTrace(System.err); System.exit(-1); } catch (Throwable t) { System.err.println("Exception running tool: " + t.getMessage()); t.printStackTrace(System.err); System.exit(-1); } }
From source file:com.github.ansell.shp.SHPDump.java
public static void main(String... args) throws Exception { final OptionParser parser = new OptionParser(); final OptionSpec<Void> help = parser.accepts("help").forHelp(); final OptionSpec<File> input = parser.accepts("input").withRequiredArg().ofType(File.class).required() .describedAs("The input SHP file"); final OptionSpec<File> output = parser.accepts("output").withRequiredArg().ofType(File.class).required() .describedAs("The output directory to use for debugging files"); final OptionSpec<String> outputPrefix = parser.accepts("prefix").withRequiredArg().ofType(String.class) .defaultsTo("shp-debug").describedAs("The output prefix to use for debugging files"); final OptionSpec<File> outputMappingTemplate = parser.accepts("output-mapping").withRequiredArg() .ofType(File.class).describedAs("The output mapping template file if it needs to be generated."); final OptionSpec<Integer> resolution = parser.accepts("resolution").withRequiredArg().ofType(Integer.class) .defaultsTo(2048).describedAs("The output image file resolution"); final OptionSpec<String> format = parser.accepts("format").withRequiredArg().ofType(String.class) .defaultsTo("png").describedAs("The output image format"); final OptionSpec<String> removeIfEmpty = parser.accepts("remove-if-empty").withRequiredArg() .ofType(String.class).describedAs( "The name of an attribute to remove if its value is empty before outputting the resulting shapefile. Use multiple times to specify multiple fields to check"); OptionSet options = null;// ww w . ja v a2 s.co m try { options = parser.parse(args); } catch (final OptionException e) { System.out.println(e.getMessage()); parser.printHelpOn(System.out); throw e; } if (options.has(help)) { parser.printHelpOn(System.out); return; } final Path inputPath = input.value(options).toPath(); if (!Files.exists(inputPath)) { throw new FileNotFoundException("Could not find input SHP file: " + inputPath.toString()); } final Path outputPath = output.value(options).toPath(); if (!Files.exists(outputPath)) { throw new FileNotFoundException("Output directory does not exist: " + outputPath.toString()); } final Path outputMappingPath = options.has(outputMappingTemplate) ? outputMappingTemplate.value(options).toPath() : null; if (options.has(outputMappingTemplate) && Files.exists(outputMappingPath)) { throw new FileNotFoundException( "Output mapping template file already exists: " + outputMappingPath.toString()); } final Set<String> filterFields = ConcurrentHashMap.newKeySet(); if (options.has(removeIfEmpty)) { for (String nextFilterField : removeIfEmpty.values(options)) { System.out.println("Will filter field if empty value found: " + nextFilterField); filterFields.add(nextFilterField); } } if (!filterFields.isEmpty()) { System.out.println("Full set of filter fields: " + filterFields); } final String prefix = outputPrefix.value(options); FileDataStore store = FileDataStoreFinder.getDataStore(inputPath.toFile()); if (store == null) { throw new RuntimeException("Could not read the given input as an ESRI Shapefile: " + inputPath.toAbsolutePath().toString()); } for (String typeName : new LinkedHashSet<>(Arrays.asList(store.getTypeNames()))) { System.out.println(""); System.out.println("Type: " + typeName); SimpleFeatureSource featureSource = store.getFeatureSource(typeName); SimpleFeatureType schema = featureSource.getSchema(); Name outputSchemaName = new NameImpl(schema.getName().getNamespaceURI(), schema.getName().getLocalPart().replace(" ", "").replace("%20", "")); System.out.println("Replacing name on schema: " + schema.getName() + " with " + outputSchemaName); SimpleFeatureType outputSchema = SHPUtils.changeSchemaName(schema, outputSchemaName); List<String> attributeList = new ArrayList<>(); for (AttributeDescriptor attribute : schema.getAttributeDescriptors()) { System.out.println("Attribute: " + attribute.getName().toString()); attributeList.add(attribute.getName().toString()); } CsvSchema csvSchema = CSVUtil.buildSchema(attributeList); SimpleFeatureCollection collection = featureSource.getFeatures(); int featureCount = 0; Path nextCSVFile = outputPath.resolve(prefix + ".csv"); Path nextSummaryCSVFile = outputPath .resolve(prefix + "-" + outputSchema.getTypeName() + "-Summary.csv"); List<SimpleFeature> outputFeatureList = new CopyOnWriteArrayList<>(); try (SimpleFeatureIterator iterator = collection.features(); Writer bufferedWriter = Files.newBufferedWriter(nextCSVFile, StandardCharsets.UTF_8, StandardOpenOption.CREATE_NEW); SequenceWriter csv = CSVUtil.newCSVWriter(bufferedWriter, csvSchema);) { List<String> nextLine = new ArrayList<>(); while (iterator.hasNext()) { SimpleFeature feature = iterator.next(); featureCount++; if (featureCount <= 2) { System.out.println(""); System.out.println(feature.getIdentifier()); } else if (featureCount % 100 == 0) { System.out.print("."); } boolean filterThisFeature = false; for (AttributeDescriptor attribute : schema.getAttributeDescriptors()) { String featureString = Optional.ofNullable(feature.getAttribute(attribute.getName())) .orElse("").toString(); nextLine.add(featureString); if (filterFields.contains(attribute.getName().toString()) && featureString.trim().isEmpty()) { filterThisFeature = true; } if (featureString.length() > 100) { featureString = featureString.substring(0, 100) + "..."; } if (featureCount <= 2) { System.out.print(attribute.getName() + "="); System.out.println(featureString); } } if (!filterThisFeature) { outputFeatureList.add(SHPUtils.changeSchemaName(feature, outputSchema)); csv.write(nextLine); } nextLine.clear(); } } try (Reader csvReader = Files.newBufferedReader(nextCSVFile, StandardCharsets.UTF_8); Writer summaryOutput = Files.newBufferedWriter(nextSummaryCSVFile, StandardCharsets.UTF_8, StandardOpenOption.CREATE_NEW); final Writer mappingWriter = options.has(outputMappingTemplate) ? Files.newBufferedWriter(outputMappingPath) : NullWriter.NULL_WRITER) { CSVSummariser.runSummarise(csvReader, summaryOutput, mappingWriter, CSVSummariser.DEFAULT_SAMPLE_COUNT, false); } if (featureCount > 100) { System.out.println(""); } System.out.println(""); System.out.println("Feature count: " + featureCount); SimpleFeatureCollection outputCollection = new ListFeatureCollection(outputSchema, outputFeatureList); Path outputShapefilePath = outputPath.resolve(prefix + "-" + outputSchema.getTypeName() + "-dump"); if (!Files.exists(outputShapefilePath)) { Files.createDirectory(outputShapefilePath); } SHPUtils.writeShapefile(outputCollection, outputShapefilePath); // Create ZIP file from the contents to keep the subfiles together Path outputShapefileZipPath = outputPath .resolve(prefix + "-" + outputSchema.getTypeName() + "-dump.zip"); try (final OutputStream out = Files.newOutputStream(outputShapefileZipPath, StandardOpenOption.CREATE_NEW); final ZipOutputStream zip = new ZipOutputStream(out, StandardCharsets.UTF_8);) { Files.list(outputShapefilePath).forEachOrdered(Unchecked.consumer(e -> { zip.putNextEntry(new ZipEntry(e.getFileName().toString())); Files.copy(e, zip); zip.closeEntry(); })); } try (final OutputStream outputStream = Files.newOutputStream( outputPath.resolve(prefix + "." + format.value(options)), StandardOpenOption.CREATE_NEW);) { MapContent map = new MapContent(); map.setTitle(prefix + "-" + outputSchema.getTypeName()); Style style = SLD.createSimpleStyle(featureSource.getSchema()); Layer layer = new FeatureLayer(new CollectionFeatureSource(outputCollection), style); map.addLayer(layer); SHPUtils.renderImage(map, outputStream, resolution.value(options), format.value(options)); } } }
From source file:cz.muni.fi.xklinec.zipstream.App.java
/** * Entry point. //from www . jav a2 s . com * * @param args * @throws FileNotFoundException * @throws IOException * @throws NoSuchFieldException * @throws ClassNotFoundException * @throws NoSuchMethodException */ public static void main(String[] args) throws FileNotFoundException, IOException, NoSuchFieldException, ClassNotFoundException, NoSuchMethodException, InterruptedException { OutputStream fos = null; InputStream fis = null; if ((args.length != 0 && args.length != 2)) { System.err.println(String.format("Usage: app.jar source.apk dest.apk")); return; } else if (args.length == 2) { System.err.println( String.format("Will use file [%s] as input file and [%s] as output file", args[0], args[1])); fis = new FileInputStream(args[0]); fos = new FileOutputStream(args[1]); } else if (args.length == 0) { System.err.println(String.format("Will use file [STDIN] as input file and [STDOUT] as output file")); fis = System.in; fos = System.out; } final Deflater def = new Deflater(9, true); ZipArchiveInputStream zip = new ZipArchiveInputStream(fis); // List of postponed entries for further "processing". List<PostponedEntry> peList = new ArrayList<PostponedEntry>(6); // Output stream ZipArchiveOutputStream zop = new ZipArchiveOutputStream(fos); zop.setLevel(9); // Read the archive ZipArchiveEntry ze = zip.getNextZipEntry(); while (ze != null) { ZipExtraField[] extra = ze.getExtraFields(true); byte[] lextra = ze.getLocalFileDataExtra(); UnparseableExtraFieldData uextra = ze.getUnparseableExtraFieldData(); byte[] uextrab = uextra != null ? uextra.getLocalFileDataData() : null; // ZipArchiveOutputStream.DEFLATED // // Data for entry byte[] byteData = Utils.readAll(zip); byte[] deflData = new byte[0]; int infl = byteData.length; int defl = 0; // If method is deflated, get the raw data (compress again). if (ze.getMethod() == ZipArchiveOutputStream.DEFLATED) { def.reset(); def.setInput(byteData); def.finish(); byte[] deflDataTmp = new byte[byteData.length * 2]; defl = def.deflate(deflDataTmp); deflData = new byte[defl]; System.arraycopy(deflDataTmp, 0, deflData, 0, defl); } System.err.println(String.format( "ZipEntry: meth=%d " + "size=%010d isDir=%5s " + "compressed=%07d extra=%d lextra=%d uextra=%d " + "comment=[%s] " + "dataDesc=%s " + "UTF8=%s " + "infl=%07d defl=%07d " + "name [%s]", ze.getMethod(), ze.getSize(), ze.isDirectory(), ze.getCompressedSize(), extra != null ? extra.length : -1, lextra != null ? lextra.length : -1, uextrab != null ? uextrab.length : -1, ze.getComment(), ze.getGeneralPurposeBit().usesDataDescriptor(), ze.getGeneralPurposeBit().usesUTF8ForNames(), infl, defl, ze.getName())); final String curName = ze.getName(); // META-INF files should be always on the end of the archive, // thus add postponed files right before them if (curName.startsWith("META-INF") && peList.size() > 0) { System.err.println( "Now is the time to put things back, but at first, I'll perform some \"facelifting\"..."); // Simulate som evil being done Thread.sleep(5000); System.err.println("OK its done, let's do this."); for (PostponedEntry pe : peList) { System.err.println( "Adding postponed entry at the end of the archive! deflSize=" + pe.deflData.length + "; inflSize=" + pe.byteData.length + "; meth: " + pe.ze.getMethod()); pe.dump(zop, false); } peList.clear(); } // Capturing interesting files for us and store for later. // If the file is not interesting, send directly to the stream. if ("classes.dex".equalsIgnoreCase(curName) || "AndroidManifest.xml".equalsIgnoreCase(curName)) { System.err.println("### Interesting file, postpone sending!!!"); PostponedEntry pe = new PostponedEntry(ze, byteData, deflData); peList.add(pe); } else { // Write ZIP entry to the archive zop.putArchiveEntry(ze); // Add file data to the stream zop.write(byteData, 0, infl); zop.closeArchiveEntry(); } ze = zip.getNextZipEntry(); } // Cleaning up stuff zip.close(); fis.close(); zop.finish(); zop.close(); fos.close(); System.err.println("THE END!"); }
From source file:edu.upenn.cis.FastAlign.java
/** * Prints alignments for options specified by command line arguments. * @param argv parameters to be used by FastAlign. *//* w w w.ja v a 2 s . c o m*/ public static void main(String[] argv) { FastAlign align = FastAlign.initCommandLine(argv); if (align == null) { System.err.println("Usage: java " + FastAlign.class.getCanonicalName() + " -i file.fr-en\n" + " Standard options ([USE] = strongly recommended):\n" + " -i: [REQ] Input parallel corpus\n" + " -v: [USE] Use Dirichlet prior on lexical translation distributions\n" + " -d: [USE] Favor alignment points close to the monotonic diagonoal\n" + " -o: [USE] Optimize how close to the diagonal alignment points should be\n" + " -r: Run alignment in reverse (condition on target and predict source)\n" + " -c: Output conditional probability table\n" + " -e: Start with existing conditional probability table\n" + " Advanced options:\n" + " -I: number of iterations in EM training (default = 5)\n" + " -p: p_null parameter (default = 0.08)\n" + " -N: No null word\n" + " -a: alpha parameter for optional Dirichlet prior (default = 0.01)\n" + " -T: starting lambda for diagonal distance parameter (default = 4)\n"); System.exit(1); } boolean use_null = !align.no_null_word; if (align.variational_bayes && align.alpha <= 0.0) { System.err.println("--alpha must be > 0\n"); System.exit(1); } double prob_align_not_null = 1.0 - align.prob_align_null; final int kNULL = align.d.Convert("<eps>"); TTable s2t = new TTable(); if (!align.existing_probability_filename.isEmpty()) { boolean success = s2t.ImportFromFile(align.existing_probability_filename, '\t', align.d); if (!success) { System.err.println("Can't read table " + align.existing_probability_filename); System.exit(1); } } Map<Pair, Integer> size_counts = new HashMap<Pair, Integer>(); double tot_len_ratio = 0; double mean_srclen_multiplier = 0; List<Double> probs = new ArrayList<Double>(); ; // E-M Iterations Loop TODO move this into a method? for (int iter = 0; iter < align.iterations || (iter == 0 && align.iterations == 0); ++iter) { final boolean final_iteration = (iter >= (align.iterations - 1)); System.err.println("ITERATION " + (iter + 1) + (final_iteration ? " (FINAL)" : "")); Scanner in = null; try { in = new Scanner(new File(align.input)); if (!in.hasNextLine()) { System.err.println("Can't read " + align.input); System.exit(1); } } catch (FileNotFoundException e) { e.printStackTrace(); System.err.println("Can't read " + align.input); System.exit(1); } double likelihood = 0; double denom = 0.0; int lc = 0; boolean flag = false; String line; // String ssrc, strg; ArrayList<Integer> src = new ArrayList<Integer>(); ArrayList<Integer> trg = new ArrayList<Integer>(); double c0 = 0; double emp_feat = 0; double toks = 0; // Iterate over each line of the input file while (in.hasNextLine()) { line = in.nextLine(); ++lc; if (lc % 1000 == 0) { System.err.print('.'); flag = true; } if (lc % 50000 == 0) { System.err.println(" [" + lc + "]\n"); System.err.flush(); flag = false; } src.clear(); trg.clear(); // TODO this is redundant; src and tgt cleared in ParseLine // Integerize and split source and target lines. align.ParseLine(line, src, trg); if (align.is_reverse) { ArrayList<Integer> tmp = src; src = trg; trg = tmp; } // TODO Empty lines break the parser. Should this be true? if (src.size() == 0 || trg.size() == 0) { System.err.println("Error in line " + lc + "\n" + line); System.exit(1); } if (iter == 0) { tot_len_ratio += ((double) trg.size()) / ((double) src.size()); } denom += trg.size(); probs.clear(); // Add to pair length counts only if first iteration. if (iter == 0) { Pair pair = new Pair(trg.size(), src.size()); Integer value = size_counts.get(pair); if (value == null) value = 0; size_counts.put(pair, value + 1); } boolean first_al = true; // used when printing alignments toks += trg.size(); // Iterate through the English tokens for (int j = 0; j < trg.size(); ++j) { final int f_j = trg.get(j); double sum = 0; double prob_a_i = 1.0 / (src.size() + (use_null ? 1 : 0)); // uniform (model 1) if (use_null) { if (align.favor_diagonal) { prob_a_i = align.prob_align_null; } probs.add(0, s2t.prob(kNULL, f_j) * prob_a_i); sum += probs.get(0); } double az = 0; if (align.favor_diagonal) az = DiagonalAlignment.computeZ(j + 1, trg.size(), src.size(), align.diagonal_tension) / prob_align_not_null; for (int i = 1; i <= src.size(); ++i) { if (align.favor_diagonal) prob_a_i = DiagonalAlignment.unnormalizedProb(j + 1, i, trg.size(), src.size(), align.diagonal_tension) / az; probs.add(i, s2t.prob(src.get(i - 1), f_j) * prob_a_i); sum += probs.get(i); } if (final_iteration) { double max_p = -1; int max_index = -1; if (use_null) { max_index = 0; max_p = probs.get(0); } for (int i = 1; i <= src.size(); ++i) { if (probs.get(i) > max_p) { max_index = i; max_p = probs.get(i); } } if (max_index > 0) { if (first_al) first_al = false; else System.out.print(' '); if (align.is_reverse) System.out.print("" + j + '-' + (max_index - 1)); else System.out.print("" + (max_index - 1) + '-' + j); } } else { if (use_null) { double count = probs.get(0) / sum; c0 += count; s2t.Increment(kNULL, f_j, count); } for (int i = 1; i <= src.size(); ++i) { final double p = probs.get(i) / sum; s2t.Increment(src.get(i - 1), f_j, p); emp_feat += DiagonalAlignment.feature(j, i, trg.size(), src.size()) * p; } } likelihood += Math.log(sum); } if (final_iteration) System.out.println(); } // log(e) = 1.0 double base2_likelihood = likelihood / Math.log(2); if (flag) { System.err.println(); } if (iter == 0) { mean_srclen_multiplier = tot_len_ratio / lc; System.err.println("expected target length = source length * " + mean_srclen_multiplier); } emp_feat /= toks; System.err.println(" log_e likelihood: " + likelihood); System.err.println(" log_2 likelihood: " + base2_likelihood); System.err.println(" cross entropy: " + (-base2_likelihood / denom)); System.err.println(" perplexity: " + Math.pow(2.0, -base2_likelihood / denom)); System.err.println(" posterior p0: " + c0 / toks); System.err.println(" posterior al-feat: " + emp_feat); //System.err.println(" model tension: " + mod_feat / toks ); System.err.println(" size counts: " + size_counts.size()); if (!final_iteration) { if (align.favor_diagonal && align.optimize_tension && iter > 0) { for (int ii = 0; ii < 8; ++ii) { double mod_feat = 0; Iterator<Map.Entry<Pair, Integer>> it = size_counts.entrySet().iterator(); for (; it.hasNext();) { Map.Entry<Pair, Integer> entry = it.next(); final Pair p = entry.getKey(); for (int j = 1; j <= p.first; ++j) mod_feat += entry.getValue() * DiagonalAlignment.computeDLogZ(j, p.first, p.second, align.diagonal_tension); } mod_feat /= toks; System.err.println(" " + ii + 1 + " model al-feat: " + mod_feat + " (tension=" + align.diagonal_tension + ")"); align.diagonal_tension += (emp_feat - mod_feat) * 20.0; if (align.diagonal_tension <= 0.1) align.diagonal_tension = 0.1; if (align.diagonal_tension > 14) align.diagonal_tension = 14; } System.err.println(" final tension: " + align.diagonal_tension); } if (align.variational_bayes) s2t.NormalizeVB(align.alpha); else s2t.Normalize(); //prob_align_null *= 0.8; // XXX //prob_align_null += (c0 / toks) * 0.2; prob_align_not_null = 1.0 - align.prob_align_null; } } if (!align.conditional_probability_filename.isEmpty()) { System.err.println("conditional probabilities: " + align.conditional_probability_filename); s2t.ExportToFile(align.conditional_probability_filename, align.d); } System.exit(0); }
From source file:diffhunter.DiffHunter.java
/** * @param args the command line arguments * @throws org.apache.commons.cli.ParseException * @throws java.io.IOException/*from w w w. j av a 2 s.c o m*/ */ public static void main(String[] args) throws ParseException, IOException { //String test_ = Paths.get("J:\\VishalData\\additional\\", "Sasan" + "_BDB").toAbsolutePath().toString(); // TODO code application logic here /*args = new String[] { "-i", "-b", "J:\\VishalData\\additional\\Ptbp2_E18_5_cortex_CLIP_mm9_plus_strand_sorted.bed", "-r", "J:\\VishalData\\additional\\mouse_mm9.txt", "-o", "J:\\VishalData" };*/ /*args = new String[] { "-c", "-r", "J:\\VishalData\\additional\\mouse_mm9.txt", "-1", "J:\\VishalData\\Ptbp2_Adult_testis_CLIP_mm9_plus_strand_sorted_BDB", "-2", "J:\\VishalData\\Ptbp2_E18_5_cortex_CLIP_mm9_plus_strand_sorted_BDB", "-w", "200", "-s", "50", "-o", "J:\\VishalData" };*/ Options options = new Options(); // add t option options.addOption("i", "index", false, "Indexing BED files."); options.addOption("b", "bed", true, "bed file to be indexed"); options.addOption("o", "output", true, "Folder that the index/comparison file will be created."); options.addOption("r", "reference", true, "Reference annotation file to be used for indexing"); options.addOption("c", "compare", false, "Finding differences between two conditions"); options.addOption("1", "first", true, "First sample index location"); options.addOption("2", "second", true, "Second sample index location"); options.addOption("w", "window", true, "Length of window for identifying differences"); options.addOption("s", "sliding", true, "Length of sliding"); CommandLineParser parser = new BasicParser(); CommandLine cmd = parser.parse(options, args); boolean indexing = false; boolean comparing = false; //Indexing! if (cmd.hasOption("i")) { //if(cmd.hasOption("1")) //System.err.println("sasan"); //System.out.println("sasa"); indexing = true; } else if (cmd.hasOption("c")) { //System.err.println(""); comparing = true; } else { //System.err.println("Option is not deteced."); HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("diffhunter", options); return; } //Indexing is selected // if (indexing == true) { //Since indexing is true. //User have to provide file for indexing. if (!(cmd.hasOption("o") || cmd.hasOption("r") || cmd.hasOption("b"))) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("diffhunter", options); return; } String bedfile_ = cmd.getOptionValue("b"); String reference_file = cmd.getOptionValue("r"); String folder_loc = cmd.getOptionValue("o"); String sample_name = FilenameUtils.getBaseName(bedfile_); try (Database B2 = BerkeleyDB_Box.Get_BerkeleyDB( Paths.get(folder_loc, sample_name + "_BDB").toAbsolutePath().toString(), true, sample_name)) { Indexer indexing_ = new Indexer(reference_file); indexing_.Make_Index(B2, bedfile_, Paths.get(folder_loc, sample_name + "_BDB").toAbsolutePath().toString()); B2.close(); } } else if (comparing == true) { if (!(cmd.hasOption("o") || cmd.hasOption("w") || cmd.hasOption("s") || cmd.hasOption("1") || cmd.hasOption("2"))) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("diffhunter", options); return; } String folder_loc = cmd.getOptionValue("o"); int window_ = Integer.parseInt(cmd.getOptionValue("w")); //int window_=600; int slide_ = Integer.parseInt(cmd.getOptionValue("s")); String first = cmd.getOptionValue("1").replace("_BDB", ""); String second = cmd.getOptionValue("2").replace("_BDB", ""); String reference_file = cmd.getOptionValue("r"); //String folder_loc=cmd.getOptionValue("o"); String sample_name_first = FilenameUtils.getBaseName(first); String sample_name_second = FilenameUtils.getBaseName(second); Database B1 = BerkeleyDB_Box.Get_BerkeleyDB(first + "_BDB", false, sample_name_first); Database B2 = BerkeleyDB_Box.Get_BerkeleyDB(second + "_BDB", false, sample_name_second); List<String> first_condition_genes = Files .lines(Paths.get(first + "_BDB", sample_name_first + ".txt").toAbsolutePath()) .collect(Collectors.toList()); List<String> second_condition_genes = Files .lines(Paths.get(second + "_BDB", sample_name_second + ".txt").toAbsolutePath()) .collect(Collectors.toList()); System.out.println("First and second condition are loaded!!! "); List<String> intersection_ = new ArrayList<>(first_condition_genes); intersection_.retainAll(second_condition_genes); BufferedWriter output = new BufferedWriter( new FileWriter(Paths.get(folder_loc, "differences_" + window_ + "_s" + slide_ + "_c" + ".txt") .toAbsolutePath().toString(), false)); List<Result_Window> final_results = Collections.synchronizedList(new ArrayList<>()); Worker_New worker_class = new Worker_New(); worker_class.Read_Reference(reference_file); while (!intersection_.isEmpty()) { List<String> selected_genes = new ArrayList<>(); //if (intersection_.size()<=10000){selected_genes.addAll(intersection_.subList(0, intersection_.size()));} //else selected_genes.addAll(intersection_.subList(0, 10000)); if (intersection_.size() <= intersection_.size()) { selected_genes.addAll(intersection_.subList(0, intersection_.size())); } else { selected_genes.addAll(intersection_.subList(0, intersection_.size())); } intersection_.removeAll(selected_genes); //System.out.println("Intersection count is:"+intersection_.size()); //final List<Result_Window> resultssss_=new ArrayList<>(); IntStream.range(0, selected_genes.size()).parallel().forEach(i -> { System.out.println(selected_genes.get(i) + "\tprocessing......"); String gene_of_interest = selected_genes.get(i);//"ENSG00000142657|PGD";//intersection_.get(6);////"ENSG00000163395|IGFN1";//"ENSG00000270066|SCARNA2"; int start = worker_class.dic_genes.get(gene_of_interest).start_loc; int end = worker_class.dic_genes.get(gene_of_interest).end_loc; Map<Integer, Integer> first_ = Collections.EMPTY_MAP; try { first_ = BerkeleyDB_Box.Get_Coord_Read(B1, gene_of_interest); } catch (IOException | ClassNotFoundException ex) { Logger.getLogger(DiffHunter.class.getName()).log(Level.SEVERE, null, ex); } Map<Integer, Integer> second_ = Collections.EMPTY_MAP; try { second_ = BerkeleyDB_Box.Get_Coord_Read(B2, gene_of_interest); } catch (IOException | ClassNotFoundException ex) { Logger.getLogger(DiffHunter.class.getName()).log(Level.SEVERE, null, ex); } List<Window> top_windows_first = worker_class.Get_Top_Windows(window_, first_, slide_); List<Window> top_windows_second = worker_class.Get_Top_Windows(window_, second_, slide_); //System.out.println("passed for window peak call for gene \t"+selected_genes.get(i)); // System.out.println("top_window_first_Count\t"+top_windows_first.size()); // System.out.println("top_window_second_Count\t"+top_windows_second.size()); if (top_windows_first.isEmpty() && top_windows_second.isEmpty()) { return; } List<Result_Window> res_temp = new Worker_New().Get_Significant_Windows(gene_of_interest, start, end, top_windows_first, top_windows_second, second_, first_, sample_name_first, sample_name_second, 0.01); if (!res_temp.isEmpty()) { final_results.addAll(res_temp);//final_results.addAll(worker_class.Get_Significant_Windows(gene_of_interest, start, end, top_windows_first, top_windows_second, second_, first_, first_condition, second_condition, 0.01)); } //System.out.println(selected_genes.get(i)+"\tprocessed."); }); /*selected_genes.parallelStream().forEach(i -> { });*/ List<Double> pvals = new ArrayList<>(); for (int i = 0; i < final_results.size(); i++) { pvals.add(final_results.get(i).p_value); } List<Double> qvals = MultipleTestCorrection.benjaminiHochberg(pvals); System.out.println("Writing to file..."); output.append("Gene_Symbol\tContributing_Sample\tStart\tEnd\tOddsRatio\tp_Value\tFDR"); output.newLine(); for (int i = 0; i < final_results.size(); i++) { Result_Window item = final_results.get(i); output.append(item.associated_gene_symbol + "\t" + item.contributing_windows + "\t" + item.start_loc + "\t" + item.end_loc + "\t" + item.oddsratio_ + "\t" + item.p_value + "\t" + qvals.get(i)); //+ "\t" + item.average_other_readcount_cotributing + "\t" + item.average_other_readcount_cotributing + "\t" + item.average_window_readcount_non + "\t" + item.average_other_readcount_non); output.newLine(); } /* for (Result_Window item : final_results) { output.append(item.associated_gene_symbol + "\t" + item.contributing_windows + "\t" + item.start_loc + "\t" + item.end_loc + "\t" + item.oddsratio_ + "\t" + item.p_value); //+ "\t" + item.average_other_readcount_cotributing + "\t" + item.average_other_readcount_cotributing + "\t" + item.average_window_readcount_non + "\t" + item.average_other_readcount_non); output.newLine(); } */ final_results.clear(); } output.close(); } System.out.println("Done."); }
From source file:edu.upenn.egricelab.AlignerBoost.FilterSAMAlignPE.java
public static void main(String[] args) { if (args.length == 0) { printUsage();/*w w w. ja v a2 s . c o m*/ return; } try { parseOptions(args); } catch (IllegalArgumentException e) { System.err.println("Error: " + e.getMessage()); printUsage(); return; } // Read in chrList, if specified if (chrFile != null) { chrFilter = new HashSet<String>(); try { BufferedReader chrFilterIn = new BufferedReader(new FileReader(chrFile)); String chr = null; while ((chr = chrFilterIn.readLine()) != null) chrFilter.add(chr); chrFilterIn.close(); if (verbose > 0) System.err.println( "Only looking at alignments on " + chrFilter.size() + " specified chromosomes"); } catch (IOException e) { System.err.println("Error: " + e.getMessage()); return; } } if (verbose > 0) { // Start the processMonitor processMonitor = new Timer(); // Start the ProcessStatusTask statusTask = new ProcessStatusTask(); // Schedule to show the status every 1 second processMonitor.scheduleAtFixedRate(statusTask, 0, statusFreq); } // Read in known SNP file, if specified if (knownSnpFile != null) { if (verbose > 0) System.err.println("Checking known SNPs from user specified VCF file"); knownVCF = new VCFFileReader(new File(knownSnpFile)); } SamReaderFactory readerFac = SamReaderFactory.makeDefault(); SAMFileWriterFactory writerFac = new SAMFileWriterFactory(); if (!isSilent) readerFac.validationStringency(ValidationStringency.LENIENT); // use LENIENT stringency else readerFac.validationStringency(ValidationStringency.SILENT); // use SILENT stringency SamReader in = readerFac.open(new File(inFile)); SAMFileHeader inHeader = in.getFileHeader(); if (inHeader.getGroupOrder() == GroupOrder.reference && inHeader.getSortOrder() == SortOrder.coordinate) System.err.println("Warning: Input file '" + inFile + "' might be sorted by coordinate and cannot be correctly processed!"); SAMFileHeader header = inHeader.clone(); // copy the inFile header as outFile header // Add new programHeader SAMProgramRecord progRec = new SAMProgramRecord(progName); progRec.setProgramName(progName); progRec.setProgramVersion(progVer); progRec.setCommandLine(StringUtils.join(" ", args)); header.addProgramRecord(progRec); //System.err.println(inFile + " groupOrder: " + in.getFileHeader().getGroupOrder() + " sortOrder: " + in.getFileHeader().getSortOrder()); // reset the orders header.setGroupOrder(groupOrder); header.setSortOrder(sortOrder); // write SAMHeader String prevID = null; SAMRecord prevRecord = null; List<SAMRecord> alnList = new ArrayList<SAMRecord>(); List<SAMRecordPair> alnPEList = null; // Estimate fragment length distribution by scan one-pass through the alignments SAMRecordIterator results = in.iterator(); if (!NO_ESTIMATE) { if (verbose > 0) { System.err.println("Estimating insert fragment size distribution ..."); statusTask.reset(); statusTask.setInfo("alignments scanned"); } long N = 0; double fragL_S = 0; // fragLen sum double fragL_SS = 0; // fragLen^2 sum while (results.hasNext()) { SAMRecord record = results.next(); if (verbose > 0) statusTask.updateStatus(); if (record.getFirstOfPairFlag() && !record.isSecondaryOrSupplementary()) { double fragLen = Math.abs(record.getInferredInsertSize()); if (fragLen != 0 && fragLen >= MIN_FRAG_LEN && fragLen <= MAX_FRAG_LEN) { // only consider certain alignments N++; fragL_S += fragLen; fragL_SS += fragLen * fragLen; } // stop estimate if already enough if (MAX_ESTIMATE_SCAN > 0 && N >= MAX_ESTIMATE_SCAN) break; } } if (verbose > 0) statusTask.finish(); // estimate fragment size if (N >= MIN_ESTIMATE_BASE) { // override command line values MEAN_FRAG_LEN = fragL_S / N; SD_FRAG_LEN = Math.sqrt((N * fragL_SS - fragL_S * fragL_S) / (N * (N - 1))); String estStr = String.format("Estimated fragment size distribution: N(%.1f, %.1f)", MEAN_FRAG_LEN, SD_FRAG_LEN); if (verbose > 0) System.err.println(estStr); // also add the estimation to comment header.addComment(estStr); } else { System.err.println( "Unable to estimate the fragment size distribution due to too few observed alignments"); System.err.println( "You have to specify the '--mean-frag-len' and '--sd-frag-len' on the command line and re-run this step"); statusTask.cancel(); processMonitor.cancel(); return; } // Initiate the normal model normModel = new NormalDistribution(MEAN_FRAG_LEN, SD_FRAG_LEN); // reset the iterator, if necessary if (in.type() == SamReader.Type.SAM_TYPE) { try { in.close(); } catch (IOException e) { System.err.println(e.getMessage()); } in = readerFac.open(new File(inFile)); } results.close(); results = in.iterator(); } // end of NO_ESTIMATE SAMFileWriter out = OUT_IS_SAM ? writerFac.makeSAMWriter(header, false, new File(outFile)) : writerFac.makeBAMWriter(header, false, new File(outFile)); // check each alignment again if (verbose > 0) { System.err.println("Filtering alignments ..."); statusTask.reset(); statusTask.setInfo("alignments processed"); } while (results.hasNext()) { SAMRecord record = results.next(); if (verbose > 0) statusTask.updateStatus(); String ID = record.getReadName(); // fix read and quality string for this read, if is a secondary hit from multiple hits, used for BWA alignment if (ID.equals(prevID) && record.getReadLength() == 0) SAMAlignFixer.fixSAMRecordRead(record, prevRecord); if (chrFilter != null && !chrFilter.contains(record.getReferenceName())) { prevID = ID; prevRecord = record; continue; } // fix MD:Z string for certain aligners with invalid format (i.e. seqAlto) if (fixMD) SAMAlignFixer.fixMisStr(record); // fix alignment, ignore if failed (unmapped or empty) if (!SAMAlignFixer.fixSAMRecord(record, knownVCF, DO_1DP)) { prevID = ID; prevRecord = record; continue; } if (!record.getReadPairedFlag()) { System.err.println("Error: alignment is not from a paired-end read at\n" + record.getSAMString()); out.close(); statusTask.cancel(); processMonitor.cancel(); return; } if (!ID.equals(prevID) && prevID != null || !results.hasNext()) { // a non-first new ID meet, or end of alignments // create alnPEList from filtered alnList alnPEList = createAlnPEListFromAlnList(alnList); //System.err.printf("%d alignments for %s transformed to %d alnPairs%n", alnList.size(), prevID, alnPEList.size()); int totalPair = alnPEList.size(); // filter highly unlikely PEhits filterPEHits(alnPEList, MIN_ALIGN_RATE, MIN_IDENTITY); // calculate posterior mapQ for each pair calcPEHitPostP(alnPEList, totalPair, MAX_HIT); // filter hits by mapQ if (MIN_MAPQ > 0) filterPEHits(alnPEList, MIN_MAPQ); // sort the list first with an anonymous class of comparator, with DESCREASING order Collections.sort(alnPEList, Collections.reverseOrder()); // control max-best if (MAX_BEST != 0 && alnPEList.size() > MAX_BEST) { // potential too much best hits int nBestStratum = 0; int bestMapQ = alnPEList.get(0).getPEMapQ(); // best mapQ from first PE for (SAMRecordPair pr : alnPEList) if (pr.getPEMapQ() == bestMapQ) nBestStratum++; else break; // stop searching for sorted list if (nBestStratum > MAX_BEST) alnPEList.clear(); } // filter alignments with auxiliary filters if (!MAX_SENSITIVITY) filterPEHits(alnPEList, MAX_SEED_MIS, MAX_SEED_INDEL, MAX_ALL_MIS, MAX_ALL_INDEL); // report remaining secondary alignments, up-to MAX_REPORT for (int i = 0; i < alnPEList.size() && (MAX_REPORT == 0 || i < MAX_REPORT); i++) { SAMRecordPair repPair = alnPEList.get(i); if (doUpdateBit) repPair.setNotPrimaryAlignmentFlags(i != 0); int nReport = MAX_REPORT == 0 ? Math.min(alnPEList.size(), MAX_REPORT) : alnPEList.size(); int nFiltered = alnPEList.size(); if (repPair.fwdRecord != null) { repPair.fwdRecord.setAttribute("NH", nReport); repPair.fwdRecord.setAttribute("XN", nFiltered); out.addAlignment(repPair.fwdRecord); } if (repPair.revRecord != null) { repPair.revRecord.setAttribute("NH", nReport); repPair.revRecord.setAttribute("XN", nFiltered); out.addAlignment(repPair.revRecord); } } // reset list alnList.clear(); alnPEList.clear(); } // update if (!ID.equals(prevID)) { prevID = ID; prevRecord = record; } alnList.add(record); } // end while try { in.close(); out.close(); } catch (IOException e) { System.err.println(e.getMessage()); } // Terminate the monitor task and monitor if (verbose > 0) { statusTask.cancel(); statusTask.finish(); processMonitor.cancel(); } }
From source file:com.netscape.cms.servlet.test.DRMTest.java
public static void main(String args[]) throws InvalidKeyException, NoSuchAlgorithmException, InvalidKeySpecException, SignatureException, IOException { String host = null;//ww w. ja v a2s . co m String port = null; String token_pwd = null; String db_dir = "./"; String protocol = "http"; String clientCertNickname = "KRA Administrator of Instance pki-kra's SjcRedhat Domain ID"; // parse command line arguments Options options = new Options(); options.addOption("h", true, "Hostname of the DRM"); options.addOption("p", true, "Port of the DRM"); options.addOption("w", true, "Token password"); options.addOption("d", true, "Directory for tokendb"); options.addOption("s", true, "Attempt Optional Secure SSL connection"); options.addOption("c", true, "Optional SSL Client cert Nickname"); try { CommandLineParser parser = new PosixParser(); CommandLine cmd = parser.parse(options, args); if (cmd.hasOption("h")) { host = cmd.getOptionValue("h"); } else { System.err.println("Error: no hostname provided."); usage(options); } if (cmd.hasOption("p")) { port = cmd.getOptionValue("p"); } else { System.err.println("Error: no port provided"); usage(options); } if (cmd.hasOption("w")) { token_pwd = cmd.getOptionValue("w"); } else { System.err.println("Error: no token password provided"); usage(options); } if (cmd.hasOption("d")) { db_dir = cmd.getOptionValue("d"); } if (cmd.hasOption("s")) { if (cmd.getOptionValue("s") != null && cmd.getOptionValue("s").equals("true")) { protocol = "https"; } } if (cmd.hasOption("c")) { String nick = cmd.getOptionValue("c"); if (nick != null && protocol.equals("https")) { clientCertNickname = nick; } } } catch (ParseException e) { System.err.println("Error in parsing command line options: " + e.getMessage()); usage(options); } // used for crypto operations byte iv[] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 }; try { iv = genIV(8); } catch (Exception e) { log("Can't generate initialization vector use default: " + e.toString()); } // used for wrapping to send data to DRM String transportCert = null; // Data to be archived SymmetricKey vek = null; String passphrase = null; // Session keys and passphrases for recovery SymmetricKey sessionKey = null; byte[] wrappedRecoveryKey = null; String recoveryPassphrase = null; byte[] wrappedRecoveryPassphrase = null; // retrieved data (should match archived data) byte[] encryptedData = null; String recoveredKey = null; // various ids used in recovery/archival operations KeyId keyId = null; String clientKeyId = null; RequestId recoveryRequestId = null; // Variables for data structures from calls KeyRequestResponse requestResponse = null; Key keyData = null; KeyInfo keyInfo = null; // Initialize token try { CryptoManager.initialize(db_dir); } catch (AlreadyInitializedException e) { // it is ok if it is already initialized } catch (Exception e) { log("INITIALIZATION ERROR: " + e.toString()); System.exit(1); } // Set base URI and get client KRAClient client; SystemCertClient systemCertClient; KeyClient keyClient; NSSCryptoProvider nssCrypto; try { ClientConfig config = new ClientConfig(); config.setServerURI(protocol + "://" + host + ":" + port + "/kra"); config.setCertNickname(clientCertNickname); config.setCertDatabase(db_dir); config.setCertPassword(token_pwd); nssCrypto = new NSSCryptoProvider(config); client = new KRAClient(new PKIClient(config, nssCrypto)); systemCertClient = (SystemCertClient) client.getClient("systemcert"); keyClient = (KeyClient) client.getClient("key"); } catch (Exception e) { e.printStackTrace(); return; } // Test 1: Get transport certificate from DRM transportCert = systemCertClient.getTransportCert().getEncoded(); transportCert = transportCert.substring(CertData.HEADER.length(), transportCert.indexOf(CertData.FOOTER)); keyClient.setTransportCert(transportCert); log("Transport Cert retrieved from DRM: " + transportCert); // Test 2: Get list of completed key archival requests log("\n\nList of completed archival requests"); KeyRequestInfoCollection list = keyClient.listRequests("complete", "securityDataEnrollment"); if (list.getTotal() == 0) { log("No requests found"); } else { Iterator<KeyRequestInfo> iter = list.getEntries().iterator(); while (iter.hasNext()) { KeyRequestInfo info = iter.next(); printRequestInfo(info); } } // Test 3: Get list of key recovery requests log("\n\nList of completed recovery requests"); KeyRequestInfoCollection list2 = keyClient.listRequests("complete", "securityDataRecovery"); if (list2.getTotal() == 0) { log("No requests found"); } else { Iterator<KeyRequestInfo> iter2 = list2.getEntries().iterator(); while (iter2.hasNext()) { KeyRequestInfo info = iter2.next(); printRequestInfo(info); } } // Test 4: Generate and archive a symmetric key log("Archiving symmetric key"); clientKeyId = "UUID: 123-45-6789 VEK " + Calendar.getInstance().getTime().toString(); try { vek = nssCrypto.generateSessionKey(); byte[] encoded = nssCrypto.createPKIArchiveOptions(transportCert, vek, null, KeyRequestResource.DES3_ALGORITHM, 0, iv); KeyRequestResponse info = keyClient.archivePKIOptions(clientKeyId, KeyRequestResource.SYMMETRIC_KEY_TYPE, KeyRequestResource.DES3_ALGORITHM, 0, encoded); log("Archival Results:"); printRequestInfo(info.getRequestInfo()); keyId = info.getKeyId(); } catch (Exception e) { log("Exception in archiving symmetric key:" + e.getMessage()); e.printStackTrace(); } //Test 5: Get keyId for active key with client ID log("Getting key ID for symmetric key"); keyInfo = keyClient.getActiveKeyInfo(clientKeyId); printKeyInfo(keyInfo); KeyId keyId2 = keyInfo.getKeyId(); if (keyId2 == null) { log("No archived key found"); } else { log("Archived Key found: " + keyId); } if (!keyId.equals(keyId2)) { log("Error: key ids from search and archival do not match"); } else { log("Success: keyids from search and archival match."); } // Test 6: Submit a recovery request for the symmetric key using a session key log("Submitting a recovery request for the symmetric key using session key"); try { sessionKey = nssCrypto.generateSessionKey(); wrappedRecoveryKey = CryptoUtil.wrapSymmetricKey(nssCrypto.getManager(), nssCrypto.getToken(), transportCert, sessionKey); keyData = keyClient.retrieveKey(keyId, wrappedRecoveryKey); } catch (Exception e) { log("Exception in recovering symmetric key using session key: " + e.getMessage()); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = Utils.base64encode(nssCrypto.unwrapWithSessionKey(encryptedData, sessionKey, KeyRequestResource.DES3_ALGORITHM, keyData.getNonceData())); } catch (Exception e) { log("Exception in unwrapping key: " + e.toString()); e.printStackTrace(); } if (!recoveredKey.equals(Utils.base64encode(vek.getEncoded()))) { log("Error: recovered and archived keys do not match!"); } else { log("Success: recoverd and archived keys match!"); } // Test 7: Submit a recovery request for the symmetric key using a passphrase log("Submitting a recovery request for the symmetric key using a passphrase"); recoveryPassphrase = "Gimme me keys please"; try { sessionKey = nssCrypto.generateSessionKey(); wrappedRecoveryPassphrase = nssCrypto.wrapWithSessionKey(recoveryPassphrase, iv, sessionKey, KeyRequestResource.DES3_ALGORITHM); wrappedRecoveryKey = nssCrypto.wrapSessionKeyWithTransportCert(sessionKey, transportCert); keyData = keyClient.retrieveKeyUsingWrappedPassphrase(keyId, wrappedRecoveryKey, wrappedRecoveryPassphrase, iv); } catch (Exception e) { log("Exception in recovering symmetric key using passphrase" + e.toString()); e.printStackTrace(); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = Utils.base64encode(nssCrypto.unwrapWithPassphrase(encryptedData, recoveryPassphrase)); } catch (Exception e) { log("Error: unable to unwrap key using passphrase"); e.printStackTrace(); } if (recoveredKey == null || !recoveredKey.equals(Utils.base64encode(vek.getEncoded()))) { log("Error: recovered and archived keys do not match!"); } else { log("Success: recovered and archived keys do match!"); } passphrase = "secret12345"; // Test 8: Generate and archive a passphrase clientKeyId = "UUID: 123-45-6789 RKEK " + Calendar.getInstance().getTime().toString(); try { requestResponse = keyClient.archivePassphrase(clientKeyId, passphrase); log("Archival Results:"); printRequestInfo(requestResponse.getRequestInfo()); keyId = requestResponse.getKeyId(); } catch (Exception e) { log("Exception in archiving symmetric key:" + e.toString()); e.printStackTrace(); } //Test 9: Get keyId for active passphrase with client ID log("Getting key ID for passphrase"); keyInfo = keyClient.getActiveKeyInfo(clientKeyId); printKeyInfo(keyInfo); keyId2 = keyInfo.getKeyId(); if (keyId2 == null) { log("No archived key found"); } else { log("Archived Key found: " + keyId); } if (!keyId.equals(keyId2)) { log("Error: key ids from search and archival do not match"); } else { log("Success: key ids from search and archival do match!"); } // Test 10: Submit a recovery request for the passphrase using a session key log("Submitting a recovery request for the passphrase using session key"); sessionKey = null; wrappedRecoveryKey = null; try { keyData = keyClient.retrieveKeyByPassphrase(keyId, recoveryPassphrase); } catch (Exception e) { log("Exception in recovering passphrase using session key: " + e.getMessage()); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = new String(nssCrypto.unwrapWithPassphrase(encryptedData, recoveryPassphrase), "UTF-8"); } catch (Exception e) { log("Exception in unwrapping key: " + e.toString()); e.printStackTrace(); } if (recoveredKey == null || !recoveredKey.equals(passphrase)) { log("Error: recovered and archived passphrases do not match!"); } else { log("Success: recovered and archived passphrases do match!"); } // Test 11: Submit a recovery request for the passphrase using a passphrase try { sessionKey = nssCrypto.generateSessionKey(); wrappedRecoveryKey = nssCrypto.wrapSessionKeyWithTransportCert(sessionKey, transportCert); wrappedRecoveryPassphrase = nssCrypto.wrapWithSessionKey(recoveryPassphrase, iv, sessionKey, KeyRequestResource.DES3_ALGORITHM); keyData = keyClient.retrieveKeyUsingWrappedPassphrase(keyId, wrappedRecoveryKey, wrappedRecoveryPassphrase, iv); } catch (Exception e1) { e1.printStackTrace(); System.out.println("Test 17: " + e1.getMessage()); System.exit(-1); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = new String(nssCrypto.unwrapWithPassphrase(encryptedData, recoveryPassphrase), "UTF-8"); } catch (Exception e) { log("Error: cannot unwrap key using passphrase"); e.printStackTrace(); } if (recoveredKey == null || !recoveredKey.equals(passphrase)) { log("Error: recovered and archived passphrases do not match!"); } else { log("Success: recovered and archived passphrases do match!"); } // Test 12: Get key log("Getting passphrase: " + keyId); try { keyData = keyClient.retrieveKeyByPassphrase(keyId, recoveryPassphrase); } catch (Exception e1) { e1.printStackTrace(); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = new String(nssCrypto.unwrapWithPassphrase(encryptedData, recoveryPassphrase), "UTF-8"); } catch (Exception e) { log("Error: Can't unwrap recovered key using passphrase"); e.printStackTrace(); } if (recoveredKey == null || !recoveredKey.equals(passphrase)) { log("Error: recovered and archived passphrases do not match!"); } else { log("Success: recovered and archived passphrases do match!"); } // Test 13: Get non-existent request RequestId requestId = new RequestId("0xabcdef"); log("Getting non-existent request: " + requestId.toHexString()); try { keyClient.getRequestInfo(requestId); log("Error: getting non-existent request does not throw an exception"); } catch (RequestNotFoundException e) { log("Success: getting non-existent request throws an exception: " + e.getMessage() + " (" + e.getRequestId().toHexString() + ")"); } // Test 14: Request x509 key recovery // This test requires to retrieve keyId and matching certificate // from installed instances of CA and DRM String keyID = "1"; String b64Certificate = "MIIC+TCCAeGgAwIBAgIBDDANBgkqhkiG9w0BAQsFADBOMSswKQYDVQQKDCJ1c2Vy" + "c3lzLnJlZGhhdC5jb20gU2VjdXJpdHkgRG9tYWluMR8wHQYDVQQDDBZDQSBTaWdu" + "aW5nIENlcnRpZmljYXRlMB4XDTEzMTAyNTE5MzQwM1oXDTE0MDQyMzE5MzQwM1ow" + "EzERMA8GCgmSJomT8ixkAQEMAXgwgZ8wDQYJKoZIhvcNAQEBBQADgY0AMIGJAoGB" + "ALhLfGmKvxFsKXPh49q1QsluXU3WlyS1XnpDLgOAhgTNgO4sG6CpPdv6hZYIvQBb" + "ZQ5bhuML+NXK+Q+EIiNk1cUTxgL3a30sPzy6QaFWxwM8i4uXm4nCBYv7T+n4V6/O" + "xHIM2Ch/dviAb3vz+M9trErv9t+d2H8jNXT3sHuDb/kvAgMBAAGjgaAwgZ0wHwYD" + "VR0jBBgwFoAUh1cxWFRY+nMsx4odQQI1GqyFxP8wSwYIKwYBBQUHAQEEPzA9MDsG" + "CCsGAQUFBzABhi9odHRwOi8vZG9ndGFnMjAudXNlcnN5cy5yZWRoYXQuY29tOjgw" + "ODAvY2Evb2NzcDAOBgNVHQ8BAf8EBAMCBSAwHQYDVR0lBBYwFAYIKwYBBQUHAwIG" + "CCsGAQUFBwMEMA0GCSqGSIb3DQEBCwUAA4IBAQCvmbUzQOouE2LgQQcKfmgwwJMJ" + "9tMrPwDUtyFdaIFoPL4uZaujSscaN4IWK2r5vIMJ65jwYCI7sI9En2ZfO28J9dQj" + "lpqu6TaJ+xtaMk7OvXpVB7lJk73HAttMGjETlkoq/6EjxcugmJsDqVD0b2tO7Vd0" + "hroBe2uPDHM2ASewZF415lUcRh0URtmxSazTInbyxpmy1wgSJQ0C6fMCeT+hUFlA" + "0P4k1TIprapGVq7FpKcqlhK2gTBfTSnoO7gmXG/9MxJiYpb/Aph8ptXq6quHz1Mj" + "greWr3xTsy6gF2yphUEkGHh4v22XvK+FLx9Jb6zloMWA2GG9gpUpvMnl1fH4"; log("Requesting X509 key recovery."); recoveryRequestId = keyClient.recoverKey(new KeyId(keyID), null, null, null, b64Certificate) .getRequestInfo().getRequestId(); log("Requesting X509 key recovery request: " + recoveryRequestId); // Test 55: Approve x509 key recovery log("Approving X509 key recovery request: " + recoveryRequestId); keyClient.approveRequest(recoveryRequestId); // Test 16: Recover x509 key log("Recovering X509 key based on request: " + recoveryRequestId); try { // KeyData recoveredX509Key = client.recoverKey(recoveryRequestId, "netscape"); // log("Success: X509Key recovered: "+ recoveredX509Key.getP12Data()); } catch (RequestNotFoundException e) { log("Error: recovering X509Key"); } // Test 1: Get transport certificate from DRM transportCert = systemCertClient.getTransportCert().getEncoded(); transportCert = transportCert.substring(CertData.HEADER.length(), transportCert.indexOf(CertData.FOOTER)); log("Transport Cert retrieved from DRM: " + transportCert); // Test 17: Get list of completed key archival requests log("\n\nList of completed archival requests"); list = keyClient.listRequests("complete", IRequest.SYMKEY_GENERATION_REQUEST); if (list.getTotal() == 0) { log("No requests found"); } else { Iterator<KeyRequestInfo> iter = list.getEntries().iterator(); while (iter.hasNext()) { KeyRequestInfo info = iter.next(); printRequestInfo(info); } } // test 18: Generate symmetric key clientKeyId = "Symmetric Key #1234f " + Calendar.getInstance().getTime().toString(); List<String> usages = new ArrayList<String>(); usages.add(SymKeyGenerationRequest.DECRYPT_USAGE); usages.add(SymKeyGenerationRequest.ENCRYPT_USAGE); KeyRequestResponse genKeyResponse = keyClient.generateSymmetricKey(clientKeyId, KeyRequestResource.AES_ALGORITHM, 128, usages, null); printRequestInfo(genKeyResponse.getRequestInfo()); keyId = genKeyResponse.getKeyId(); // test 19: Get keyId for active key with client ID log("Getting key ID for symmetric key"); keyInfo = keyClient.getActiveKeyInfo(clientKeyId); printKeyInfo(keyInfo); keyId2 = keyInfo.getKeyId(); if (keyId2 == null) { log("No archived key found"); } else { log("Archived Key found: " + keyId); } if (!keyId.equals(keyId2)) { log("Error: key ids from search and archival do not match"); } else { log("Success: keyids from search and archival match."); } // Test 20: Submit a recovery request for the symmetric key using a session key log("Submitting a recovery request for the symmetric key using session key"); try { sessionKey = nssCrypto.generateSessionKey(); wrappedRecoveryKey = nssCrypto.wrapSessionKeyWithTransportCert(sessionKey, transportCert); keyData = keyClient.retrieveKey(keyId, wrappedRecoveryKey); } catch (Exception e) { log("Exception in recovering symmetric key using session key: " + e.getMessage()); } encryptedData = keyData.getEncryptedData(); try { recoveredKey = new String(nssCrypto.unwrapWithSessionKey(encryptedData, sessionKey, KeyRequestResource.DES3_ALGORITHM, keyData.getNonceData())); } catch (Exception e) { log("Exception in unwrapping key: " + e.toString()); e.printStackTrace(); } // test 21: Generate symmetric key - invalid algorithm try { genKeyResponse = keyClient.generateSymmetricKey("Symmetric Key #1235", "AFS", 128, usages, null); } catch (Exception e) { log("Exception: " + e); } // test 22: Generate symmetric key - invalid key size try { genKeyResponse = keyClient.generateSymmetricKey("Symmetric Key #1236", "AES", 0, usages, null); } catch (Exception e) { log("Exception: " + e); } // test 23: Generate symmetric key - usages not defined try { genKeyResponse = keyClient.generateSymmetricKey("Symmetric Key #1236", "DES", 56, null, null); } catch (Exception e) { log("Exception: " + e); } // Test 24: Generate and archive a symmetric key of type AES log("Archiving symmetric key"); clientKeyId = "UUID: 123-45-6789 VEK " + Calendar.getInstance().getTime().toString(); try { vek = nssCrypto.generateSymmetricKey(KeyRequestResource.AES_ALGORITHM, 128); byte[] encoded = CryptoUtil.createPKIArchiveOptions(nssCrypto.getManager(), nssCrypto.getToken(), transportCert, vek, null, KeyGenAlgorithm.DES3, 0, new IVParameterSpec(iv)); KeyRequestResponse response = keyClient.archivePKIOptions(clientKeyId, KeyRequestResource.SYMMETRIC_KEY_TYPE, KeyRequestResource.AES_ALGORITHM, 128, encoded); log("Archival Results:"); printRequestInfo(response.getRequestInfo()); keyId = response.getKeyId(); } catch (Exception e) { log("Exception in archiving symmetric key:" + e.getMessage()); e.printStackTrace(); } //Test 25: Get keyId for active key with client ID log("Getting key ID for symmetric key"); keyInfo = keyClient.getActiveKeyInfo(clientKeyId); printKeyInfo(keyInfo); keyId2 = keyInfo.getKeyId(); if (keyId2 == null) { log("No archived key found"); } else { log("Archived Key found: " + keyId); } if (!keyId.equals(keyId2)) { log("Error: key ids from search and archival do not match"); } else { log("Success: keyids from search and archival match."); } // Test 26: Submit a recovery request for the symmetric key log("Submitting a recovery request for the symmetric key without using session key"); try { keyData = keyClient.retrieveKey(keyId); } catch (Exception e) { log("Exception in recovering symmetric key using session key: " + e.getMessage()); } // Since no session key is provided externally, the retrieveKey method // generates a session key, wraps it with transport cert and completes the request. // The encrypted data is then unwrapped using the temporary session key and set to // the attribute privateData. recoveredKey = Utils.base64encode(keyData.getData()); if (!recoveredKey.equals(Utils.base64encode(vek.getEncoded()))) { log("Error: recovered and archived keys do not match!"); } else { log("Success: recoverd and archived keys match!"); } // Test 27: Get key info log("getting key info for existing key"); printKeyInfo(keyClient.getKeyInfo(keyId)); //Test 28: Modify status log("modify the key status"); keyClient.modifyKeyStatus(keyId, KeyResource.KEY_STATUS_INACTIVE); keyInfo = keyClient.getKeyInfo(keyId); printKeyInfo(keyInfo); //Test 29: Confirm no more active keys with this ID log("look for active keys with this id"); clientKeyId = keyInfo.getClientKeyID(); try { keyInfo = keyClient.getActiveKeyInfo(clientKeyId); printKeyInfo(keyInfo); } catch (ResourceNotFoundException e) { log("Success: ResourceNotFound exception thrown: " + e); } // Test asymmetric key generation. String[] algs = { "RSA", "DSA" }; for (int i = 0; i < algs.length; i++) { // Test 30: Generate Asymmetric keys - RSA key System.out.println("\nTesting asymmetric key generation for algorithm " + algs[i]); clientKeyId = "AsymKey #" + Calendar.getInstance().getTimeInMillis(); usages.clear(); usages.add(AsymKeyGenerationRequest.SIGN); usages.add(AsymKeyGenerationRequest.VERIFY); KeyRequestResponse response = keyClient.generateAsymmetricKey(clientKeyId, algs[i], 1024, usages, null); printRequestInfo(response.getRequestInfo()); System.out.println(); // Test 31: Get information of the newly generated asymmetric keys System.out.println("Fetch information of the newly generated asymmetric keys."); System.out.println(); KeyInfo info = keyClient.getKeyInfo(response.getKeyId()); printKeyInfo(info); System.out.println(); // Test 32: Retrieve private key data System.out.println("Retrieving and verifying the generated private key."); try { keyData = keyClient.retrieveKey(response.getKeyId()); } catch (Exception e) { log("Exception retrieving the private key data."); e.printStackTrace(); } // Test 33: Verify the generated key pair. if (isKeyPairValid(algs[i], keyData.getData(), info.getPublicKey())) { log("The key pair generated using " + algs[i] + " algorithm is valid."); } else { log("The key pair generated using " + algs[i] + " algorithm is invalid."); } System.out.println(); } // Test 34: }