List of usage examples for java.lang IllegalArgumentException IllegalArgumentException
public IllegalArgumentException(Throwable cause)
From source file:GetDBInfo.java
public static void main(String[] args) { Connection c = null; // The JDBC connection to the database server try {//from w w w . j a v a2 s.com // Look for the properties file DB.props in the same directory as // this program. It will contain default values for the various // parameters needed to connect to a database Properties p = new Properties(); try { p.load(GetDBInfo.class.getResourceAsStream("DB.props")); } catch (Exception e) { } // Get default values from the properties file String driver = p.getProperty("driver"); // Driver class name String server = p.getProperty("server", ""); // JDBC URL for server String user = p.getProperty("user", ""); // db user name String password = p.getProperty("password", ""); // db password // These variables don't have defaults String database = null; // The db name (appended to server URL) String table = null; // The optional name of a table in the db // Parse the command-line args to override the default values above for (int i = 0; i < args.length; i++) { if (args[i].equals("-d")) driver = args[++i]; //-d <driver> else if (args[i].equals("-s")) server = args[++i];//-s <server> else if (args[i].equals("-u")) user = args[++i]; //-u <user> else if (args[i].equals("-p")) password = args[++i]; else if (database == null) database = args[i]; // <dbname> else if (table == null) table = args[i]; // <table> else throw new IllegalArgumentException("Unknown argument: " + args[i]); } // Make sure that at least a server or a database were specified. // If not, we have no idea what to connect to, and cannot continue. if ((server.length() == 0) && (database.length() == 0)) throw new IllegalArgumentException("No database specified."); // Load the db driver, if any was specified. if (driver != null) Class.forName(driver); // Now attempt to open a connection to the specified database on // the specified server, using the specified name and password c = DriverManager.getConnection(server + database, user, password); // Get the DatabaseMetaData object for the connection. This is the // object that will return us all the data we're interested in here DatabaseMetaData md = c.getMetaData(); // Display information about the server, the driver, etc. System.out.println("DBMS: " + md.getDatabaseProductName() + " " + md.getDatabaseProductVersion()); System.out.println("JDBC Driver: " + md.getDriverName() + " " + md.getDriverVersion()); System.out.println("Database: " + md.getURL()); System.out.println("User: " + md.getUserName()); // Now, if the user did not specify a table, then display a list of // all tables defined in the named database. Note that tables are // returned in a ResultSet, just like query results are. if (table == null) { System.out.println("Tables:"); ResultSet r = md.getTables("", "", "%", null); while (r.next()) System.out.println("\t" + r.getString(3)); } // Otherwise, list all columns of the specified table. // Again, information about the columns is returned in a ResultSet else { System.out.println("Columns of " + table + ": "); ResultSet r = md.getColumns("", "", table, "%"); while (r.next()) System.out.println("\t" + r.getString(4) + " : " + r.getString(6)); } } // Print an error message if anything goes wrong. catch (Exception e) { System.err.println(e); if (e instanceof SQLException) System.err.println(((SQLException) e).getSQLState()); System.err.println("Usage: java GetDBInfo [-d <driver] " + "[-s <dbserver>]\n" + "\t[-u <username>] [-p <password>] <dbname>"); } // Always remember to close the Connection object when we're done! finally { try { c.close(); } catch (Exception e) { } } }
From source file:com.tacitknowledge.util.migration.jdbc.DistributedMigrationInformation.java
/** * Get the migration level information for the given system name * * @param arguments the command line arguments, if any (none are used) * @throws Exception if anything goes wrong *///www .j a va 2 s . c o m public static void main(String[] arguments) throws Exception { DistributedMigrationInformation info = new DistributedMigrationInformation(); String migrationName = System.getProperty("migration.systemname"); String migrationSettings = ConfigurationUtil.getOptionalParam("migration.settings", System.getProperties(), arguments, 1); if (migrationName == null) { if ((arguments != null) && (arguments.length > 0)) { migrationName = arguments[0].trim(); } else { throw new IllegalArgumentException("The migration.systemname " + "system property is required"); } } // info.getMigrationInformation(migrationName); info.getMigrationInformation(migrationName, migrationSettings); }
From source file:examples.mail.IMAPImportMbox.java
public static void main(String[] args) throws IOException { if (args.length < 2) { System.err.println(/*from w ww.ja v a2 s . com*/ "Usage: IMAPImportMbox imap[s]://user:password@host[:port]/folder/path <mboxfile> [selectors]"); System.err.println("\tWhere: a selector is a list of numbers/number ranges - 1,2,3-10" + " - or a list of strings to match in the initial From line"); System.exit(1); } final URI uri = URI.create(args[0]); final String file = args[1]; final File mbox = new File(file); if (!mbox.isFile() || !mbox.canRead()) { throw new IOException("Cannot read mailbox file: " + mbox); } String path = uri.getPath(); if (path == null || path.length() < 1) { throw new IllegalArgumentException("Invalid folderPath: '" + path + "'"); } String folder = path.substring(1); // skip the leading / List<String> contains = new ArrayList<String>(); // list of strings to find BitSet msgNums = new BitSet(); // list of message numbers for (int i = 2; i < args.length; i++) { String arg = args[i]; if (arg.matches("\\d+(-\\d+)?(,\\d+(-\\d+)?)*")) { // number,m-n for (String entry : arg.split(",")) { String[] parts = entry.split("-"); if (parts.length == 2) { // m-n int low = Integer.parseInt(parts[0]); int high = Integer.parseInt(parts[1]); for (int j = low; j <= high; j++) { msgNums.set(j); } } else { msgNums.set(Integer.parseInt(entry)); } } } else { contains.add(arg); // not a number/number range } } // System.out.println(msgNums.toString()); // System.out.println(java.util.Arrays.toString(contains.toArray())); // Connect and login final IMAPClient imap = IMAPUtils.imapLogin(uri, 10000, null); int total = 0; int loaded = 0; try { imap.setSoTimeout(6000); final BufferedReader br = new BufferedReader(new FileReader(file)); // TODO charset? String line; StringBuilder sb = new StringBuilder(); boolean wanted = false; // Skip any leading rubbish while ((line = br.readLine()) != null) { if (line.startsWith("From ")) { // start of message; i.e. end of previous (if any) if (process(sb, imap, folder, total)) { // process previous message (if any) loaded++; } sb.setLength(0); total++; wanted = wanted(total, line, msgNums, contains); } else if (startsWith(line, PATFROM)) { // Unescape ">+From " in body text line = line.substring(1); } // TODO process first Received: line to determine arrival date? if (wanted) { sb.append(line); sb.append(CRLF); } } br.close(); if (wanted && process(sb, imap, folder, total)) { // last message (if any) loaded++; } } catch (IOException e) { System.out.println(imap.getReplyString()); e.printStackTrace(); System.exit(10); return; } finally { imap.logout(); imap.disconnect(); } System.out.println("Processed " + total + " messages, loaded " + loaded); }
From source file:com.alibaba.simpleimage.ScaleSpeedTest.java
public static void main(String[] args) throws Exception { String method = "CSubSample"; String imgName = "large"; int times = 1000; float scale = 0.5f; String imgDir = "/src/test/resources/conf.test/simpleimage/scale"; File rootDir = null;//from www.ja va2s . com if (args.length > 0) { rootDir = new File(args[0].trim() + imgDir); } if (args.length > 1) { method = args[1]; } if (args.length > 2) { imgName = args[2]; } if (args.length > 3) { scale = Float.parseFloat(args[3]); } if (args.length > 4) { times = Integer.parseInt(args[4]); } ScaleSpeedTest instance = new ScaleSpeedTest(); if ("JSubSample".equalsIgnoreCase(method)) { instance.doScale(rootDir, imgName, instance.new JSubSampleScaler(), times, scale); } else if ("CSubSample".equalsIgnoreCase(method)) { instance.doScale(rootDir, imgName, instance.new CSubSampleScaler(), times, scale); } else if ("Bicurbe".equalsIgnoreCase(method)) { instance.doScale(rootDir, imgName, instance.new BicurbeScaler(), times, scale); } else if ("Bicurbe2".equalsIgnoreCase(method)) { instance.doScale(rootDir, imgName, instance.new Bicube2Scaler(), times, scale); } else if ("lanczos".equalsIgnoreCase(method)) { instance.doScale(rootDir, imgName, instance.new LanczosScaler(), times, scale); } else { throw new IllegalArgumentException("Unknown alg"); } }
From source file:org.spring.springxdcloudInstaller.MainApp.java
public static void main(String[] args) throws TimeoutException { if (args.length < PARAMETERS) throw new IllegalArgumentException(INVALID_SYNTAX); // Args//from w ww . j a v a2 s.com String accesskeyid = args[0]; String secretkey = args[1]; String command = args[2]; String name = args[3]; String type = args[4]; DeployType deployType = getTypeByString(type); if (deployType == null) { throw new IllegalArgumentException(INVALID_TYPE); } // Init RestContext<EC2Client, EC2AsyncClient> context = ContextBuilder.newBuilder("aws-ec2") .credentials(accesskeyid, secretkey).build(); // Get a synchronous client EC2Client client = context.getApi(); CloudCommand cloudCommand = new CloudCommand(accesskeyid, secretkey); try { if (command.equals("create")) { // cloudCommand.runCommand("mkdir -p /home/ubuntu/org/spring/springxdcloudInstaller/util", "us-east-1/i-e16ae686"); // cloudCommand.sshCopy("/Users/renfrg/projects/xd-cloud-installer/target/classes/org/spring/springxdcloudInstaller/util/ConfigureSystem.class", // "ec2-50-16-90-175.compute-1.amazonaws.com","us-east-1/i-e16ae686"); // cloudCommand.runCommand("java -cp /home/ubuntu org.spring.springxdcloudInstaller.util.ConfigureSystem ", "us-east-1/i-e16ae686"); execute(client, name, getTypeByString(type), cloudCommand); System.out.println(getLatestBuild()); } else if (command.equals("destroy")) { destroySecurityGroupKeyPairAndInstance(client, name); } else { throw new IllegalArgumentException(INVALID_SYNTAX); } } catch (Exception ex) { ex.printStackTrace(); } finally { // Close connection context.close(); System.exit(0); } }
From source file:de.tudarmstadt.ukp.experiments.argumentation.convincingness.sampling.Step4MTurkOutputCollector.java
@SuppressWarnings("unchecked") public static void main(String[] args) throws Exception { String inputDirWithArgumentPairs = args[0]; File[] resultFiles;// w ww . ja v a 2 s. c o m if (args[1].contains("*")) { File path = new File(args[1]); File directory = path.getParentFile(); String regex = path.getName().replaceAll("\\*", ""); List<File> files = new ArrayList<>(FileUtils.listFiles(directory, new String[] { regex }, false)); resultFiles = new File[files.size()]; for (int i = 0; i < files.size(); i++) { resultFiles[i] = files.get(i); } } else { // result file is a comma-separated list of CSV files from MTurk String[] split = args[1].split(","); resultFiles = new File[split.length]; for (int i = 0; i < split.length; i++) { resultFiles[i] = new File(split[i]); } } File outputDir = new File(args[2]); if (!outputDir.exists()) { if (!outputDir.mkdirs()) { throw new IOException("Cannot create directory " + outputDir); } } // error if output folder not empty to prevent any confusion by mixing files if (!FileUtils.listFiles(outputDir, null, false).isEmpty()) { throw new IllegalArgumentException("Output dir " + outputDir + " is not empty"); } // collected assignments with empty reason for rejections Set<String> assignmentsWithEmptyReason = new HashSet<>(); // parse with first line as header MTurkOutputReader mTurkOutputReader = new MTurkOutputReader(resultFiles); Collection<File> files = FileUtils.listFiles(new File(inputDirWithArgumentPairs), new String[] { "xml" }, false); if (files.isEmpty()) { throw new IOException("No xml files found in " + inputDirWithArgumentPairs); } // statistics: how many hits with how many assignments ; hit ID / assignments Map<String, Map<String, Integer>> assignmentsPerHits = new HashMap<>(); // collect accept/reject statistics for (Map<String, String> record : mTurkOutputReader) { boolean wasRejected = "Rejected".equals(record.get("assignmentstatus")); String hitID = record.get("hitid"); String hitTypeId = record.get("hittypeid"); if (!wasRejected) { // update statistics if (!assignmentsPerHits.containsKey(hitTypeId)) { assignmentsPerHits.put(hitTypeId, new HashMap<String, Integer>()); } if (!assignmentsPerHits.get(hitTypeId).containsKey(hitID)) { assignmentsPerHits.get(hitTypeId).put(hitID, 0); } assignmentsPerHits.get(hitTypeId).put(hitID, assignmentsPerHits.get(hitTypeId).get(hitID) + 1); } } // statistics: how many hits with how many assignments ; hit ID / assignments Map<String, Integer> approvedAssignmentsPerHit = new HashMap<>(); Map<String, Integer> rejectedAssignmentsPerHit = new HashMap<>(); // collect accept/reject statistics for (Map<String, String> record : mTurkOutputReader) { boolean approved = "Approved".equals(record.get("assignmentstatus")); boolean rejected = "Rejected".equals(record.get("assignmentstatus")); String hitID = record.get("hitid"); if (approved) { // update statistics if (!approvedAssignmentsPerHit.containsKey(hitID)) { approvedAssignmentsPerHit.put(hitID, 0); } approvedAssignmentsPerHit.put(hitID, approvedAssignmentsPerHit.get(hitID) + 1); } else if (rejected) { // update statistics if (!rejectedAssignmentsPerHit.containsKey(hitID)) { rejectedAssignmentsPerHit.put(hitID, 0); } rejectedAssignmentsPerHit.put(hitID, rejectedAssignmentsPerHit.get(hitID) + 1); } else { throw new IllegalStateException( "Unknown state: " + record.get("assignmentstatus") + " HITID: " + hitID); } } // System.out.println("Approved: " + approvedAssignmentsPerHit); // System.out.println("Rejected: " + rejectedAssignmentsPerHit); System.out.println("Approved (values): " + new HashSet<>(approvedAssignmentsPerHit.values())); System.out.println("Rejected (values): " + new HashSet<>(rejectedAssignmentsPerHit.values())); // rejection statistics int totalRejected = 0; for (Map.Entry<String, Integer> rejectionEntry : rejectedAssignmentsPerHit.entrySet()) { totalRejected += rejectionEntry.getValue(); } System.out.println("Total rejections: " + totalRejected); /* // generate .success files for adding more annotations for (File resultFile : resultFiles) { String hitTypeID = mTurkOutputReader.getHitTypeIdForFile().get(resultFile); // assignments for that hittypeid (= file) Map<String, Integer> assignments = assignmentsPerHits.get(hitTypeID); prepareUpdateHITsFiles(assignments, hitTypeID, resultFile); } */ int totalSavedPairs = 0; // load all previously prepared argument pairs for (File file : files) { List<ArgumentPair> argumentPairs = (List<ArgumentPair>) XStreamTools.getXStream().fromXML(file); List<AnnotatedArgumentPair> annotatedArgumentPairs = new ArrayList<>(); for (ArgumentPair argumentPair : argumentPairs) { AnnotatedArgumentPair annotatedArgumentPair = new AnnotatedArgumentPair(argumentPair); // is there such an answer? String key = "Answer." + argumentPair.getId(); // iterate only if there is such column to save time if (mTurkOutputReader.getColumnNames().contains(key)) { // now find the results for (Map<String, String> record : mTurkOutputReader) { if (record.containsKey(key)) { // extract the values AnnotatedArgumentPair.MTurkAssignment assignment = new AnnotatedArgumentPair.MTurkAssignment(); boolean wasRejected = "Rejected".equals(record.get("assignmentstatus")); // only non-rejected (if required) if (!wasRejected) { String hitID = record.get("hitid"); String workerID = record.get("workerid"); String assignmentId = record.get("assignmentid"); try { assignment.setAssignmentAcceptTime( DATE_FORMAT.parse(record.get("assignmentaccepttime"))); assignment.setAssignmentSubmitTime( DATE_FORMAT.parse(record.get("assignmentsubmittime"))); assignment.setHitComment(record.get("Answer.feedback")); assignment.setHitID(hitID); assignment.setTurkID(workerID); assignment.setAssignmentId(assignmentId); // and answer specific fields String valueRaw = record.get(key); // so far the label has had format aXXX_aYYY_a1, aXXX_aYYY_a2, or aXXX_aYYY_equal // strip now only true label String label = valueRaw.split("_")[2]; assignment.setValue(label); String reason = record.get(key + "_reason"); // missing reason if (reason == null) { assignmentsWithEmptyReason.add(assignmentId); } else { assignment.setReason(reason); // get worker's stance String stanceRaw = record.get(key + "_stance"); if (stanceRaw != null) { // parse stance String stance = stanceRaw.split("_stance_")[1]; assignment.setWorkerStance(stance); } // we take maximal 5 assignments Collections.sort(annotatedArgumentPair.mTurkAssignments, new Comparator<AnnotatedArgumentPair.MTurkAssignment>() { @Override public int compare(AnnotatedArgumentPair.MTurkAssignment o1, AnnotatedArgumentPair.MTurkAssignment o2) { return o1.getAssignmentAcceptTime() .compareTo(o2.getAssignmentAcceptTime()); } }); if (annotatedArgumentPair.mTurkAssignments .size() < MAXIMUM_ASSIGNMENTS_PER_HIT) { annotatedArgumentPair.mTurkAssignments.add(assignment); } } } catch (IllegalArgumentException | NullPointerException ex) { System.err.println("Malformed annotations for HIT " + hitID + ", worker " + workerID + ", assignment " + assignmentId + "; " + ex.getMessage() + ", full record: " + record); } } } } } // and if there are some annotations, add it to the result set if (!annotatedArgumentPair.mTurkAssignments.isEmpty()) { annotatedArgumentPairs.add(annotatedArgumentPair); } } if (!annotatedArgumentPairs.isEmpty()) { File outputFile = new File(outputDir, file.getName()); XStreamTools.toXML(annotatedArgumentPairs, outputFile); System.out.println("Saved " + annotatedArgumentPairs.size() + " annotated pairs to " + outputFile); totalSavedPairs += annotatedArgumentPairs.size(); } } System.out.println("Total saved " + totalSavedPairs + " pairs"); // print assignments with empty reasons if (!assignmentsWithEmptyReason.isEmpty()) { System.out.println( "== Assignments with empty reason:\nassignmentIdToReject\tassignmentIdToRejectComment"); for (String assignmentId : assignmentsWithEmptyReason) { System.out.println( assignmentId + "\t\"Dear worker, you did not fill the required field with a reason.\""); } } }
From source file:RemoveHTMLReader.java
/** The test program: read a text file, strip HTML, print to console */ public static void main(String[] args) { try {/* www . j a va 2s. c o m*/ if (args.length != 1) throw new IllegalArgumentException("Wrong number of args"); // Create a stream to read from the file and strip tags from it BufferedReader in = new BufferedReader(new RemoveHTMLReader(new FileReader(args[0]))); // Read line by line, printing lines to the console String line; while ((line = in.readLine()) != null) System.out.println(line); in.close(); // Close the stream. } catch (Exception e) { System.err.println(e); System.err.println("Usage: java RemoveHTMLReader$Test" + " <filename>"); } }
From source file:com.ciphertool.zodiacengine.CipherSolutionExecutor.java
/** * @param args//from w w w.j av a 2 s . c o m * @throws InterruptedException */ public static void main(String[] args) throws InterruptedException { // Spin up the Spring application context setUp(); CipherDto cipherDto = null; Cipher cipher = cipherDao.findByCipherName(cipherName); long start = System.currentTimeMillis(); ExecutorService executor = Executors.newFixedThreadPool(maxThreads); cipherDto = new CipherDto(String.valueOf(0), cipher); /* * We want to generate and validate a specific number of solutions, no * matter how long it takes. */ if (applicationDurationType == ApplicationDurationType.ITERATION) { if (numIterations <= 0) { throw new IllegalArgumentException( "ApplicationDurationType set to ITERATION, but numIterations was not set or was set incorrectly."); } log.info("Beginning solution generation. Generating " + numIterations + " solutions using " + maxThreads + " threads."); for (long i = 1; i <= numIterations; i++) { Runnable cipherTask = new CipherSolutionSynchronizedRunnable(solutionGenerator, solutionEvaluator, cipherDto); executor.execute(cipherTask); } // Make executor accept no new threads and finish all existing // threads in the queue executor.shutdown(); } /* * We want to generate and validate solutions for a set amount of time, * no matter how many we can generate in that time period. */ else if (applicationDurationType == ApplicationDurationType.TEMPORAL) { if (applicationRunMillis <= 0) { throw new IllegalArgumentException( "ApplicationDurationType set to TEMPORAL, but applicationRunMillis was not set or was set incorrectly."); } log.info("Beginning solution generation. Generating solutions for " + applicationRunMillis + "ms using " + maxThreads + " threads."); long count = 0; while (true) { Runnable cipherTask = new CipherSolutionSynchronizedRunnable(solutionGenerator, solutionEvaluator, cipherDto); executor.execute(cipherTask); /* * This is a fairly rudimentary way of managing the number of * tasks sent to the executor. * * If we don't manage it somehow, the app will get bogged down * by the continuous while loop and performance will degrade * significantly. */ if (++count >= queueTaskLimit) { count = 0; executor.shutdown(); /* * We are mainly concerned about blocking until all tasks * are finished, so the timeout is not a big concern. */ executor.awaitTermination(1, TimeUnit.MINUTES); executor = Executors.newFixedThreadPool(maxThreads); if ((System.currentTimeMillis() - start) > applicationRunMillis) { break; } } } // Make executor stop immediately executor.shutdownNow(); } // Wait until all threads are finished while (!executor.isTerminated()) { } SolutionChromosome solutionMostMatches = cipherDto.getSolutionMostMatches(); SolutionChromosome solutionMostUnique = cipherDto.getSolutionMostUnique(); SolutionChromosome solutionMostAdjacent = cipherDto.getSolutionMostAdjacent(); /* * Print out summary information */ log.info("Took " + (System.currentTimeMillis() - start) + "ms to generate and validate " + cipherDto.getNumSolutions() + " solutions."); log.info("Highest total matches achieved: " + solutionMostMatches.getTotalMatches()); log.info("Average total matches: " + (cipherDto.getTotalMatchSum() / cipherDto.getNumSolutions())); log.info("Best solution found: " + solutionMostMatches); log.info("Most unique matches achieved: " + solutionMostUnique.getUniqueMatches()); log.info("Average unique matches: " + (cipherDto.getUniqueMatchSum() / cipherDto.getNumSolutions())); log.info("Solution with most unique matches found: " + solutionMostUnique); log.info("Most adjacent matches achieved: " + solutionMostAdjacent.getAdjacentMatchCount()); log.info("Average adjacent matches: " + (cipherDto.getAdjacentMatchSum() / cipherDto.getNumSolutions())); log.info("Solution with most adjacent matches found: " + solutionMostAdjacent); }
From source file:com.datatorrent.stram.StreamingAppMaster.java
/** * @param args// www. j a v a2s. co m * Command line args * @throws Throwable */ public static void main(final String[] args) throws Throwable { StdOutErrLog.tieSystemOutAndErrToLog(); LOG.info("Master starting with classpath: {}", System.getProperty("java.class.path")); LOG.info("version: {}", VersionInfo.APEX_VERSION.getBuildVersion()); StringWriter sw = new StringWriter(); for (Map.Entry<String, String> e : System.getenv().entrySet()) { sw.append("\n").append(e.getKey()).append("=").append(e.getValue()); } LOG.info("appmaster env:" + sw.toString()); Options opts = new Options(); opts.addOption("app_attempt_id", true, "App Attempt ID. Not to be used unless for testing purposes"); opts.addOption("help", false, "Print usage"); CommandLine cliParser = new GnuParser().parse(opts, args); // option "help" overrides and cancels any run if (cliParser.hasOption("help")) { new HelpFormatter().printHelp("ApplicationMaster", opts); return; } Map<String, String> envs = System.getenv(); ApplicationAttemptId appAttemptID = Records.newRecord(ApplicationAttemptId.class); if (!envs.containsKey(Environment.CONTAINER_ID.name())) { if (cliParser.hasOption("app_attempt_id")) { String appIdStr = cliParser.getOptionValue("app_attempt_id", ""); appAttemptID = ConverterUtils.toApplicationAttemptId(appIdStr); } else { throw new IllegalArgumentException("Application Attempt Id not set in the environment"); } } else { ContainerId containerId = ConverterUtils.toContainerId(envs.get(Environment.CONTAINER_ID.name())); appAttemptID = containerId.getApplicationAttemptId(); } boolean result = false; StreamingAppMasterService appMaster = null; try { appMaster = new StreamingAppMasterService(appAttemptID); LOG.info("Initializing Application Master."); Configuration conf = new YarnConfiguration(); appMaster.init(conf); appMaster.start(); result = appMaster.run(); } catch (Throwable t) { LOG.error("Exiting Application Master", t); System.exit(1); } finally { if (appMaster != null) { appMaster.stop(); } } if (result) { LOG.info("Application Master completed."); System.exit(0); } else { LOG.info("Application Master failed."); System.exit(2); } }
From source file:de.tudarmstadt.ukp.experiments.dip.wp1.documents.Step5LinguisticPreprocessing.java
public static void main(String[] args) throws Exception { // input dir - list of xml query containers // step4-boiler-plate/ File inputDir = new File(args[0]); // output dir File outputDir = new File(args[1]); if (!outputDir.exists()) { outputDir.mkdirs();// w w w . j ava 2 s .c o m } // iterate over query containers for (File f : FileUtils.listFiles(inputDir, new String[] { "xml" }, false)) { QueryResultContainer queryResultContainer = QueryResultContainer .fromXML(FileUtils.readFileToString(f, "utf-8")); for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) { // System.out.println(rankedResults.plainText); if (rankedResults.plainText != null) { String[] lines = StringUtils.split(rankedResults.plainText, "\n"); // collecting all cleaned lines List<String> cleanLines = new ArrayList<>(lines.length); // collecting line tags List<String> lineTags = new ArrayList<>(lines.length); for (String line : lines) { // get the tag String tag = null; Matcher m = OPENING_TAG_PATTERN.matcher(line); if (m.find()) { tag = m.group(1); } if (tag == null) { throw new IllegalArgumentException("No html tag found for line:\n" + line); } // replace the tag at the beginning and the end String noTagText = line.replaceAll("^<\\S+>", "").replaceAll("</\\S+>$", ""); // do some html cleaning noTagText = noTagText.replaceAll(" ", " "); noTagText = noTagText.trim(); // add to the output if (!noTagText.isEmpty()) { cleanLines.add(noTagText); lineTags.add(tag); } } if (cleanLines.isEmpty()) { // the document is empty System.err.println("Document " + rankedResults.clueWebID + " in query " + queryResultContainer.qID + " is empty"); } else { // now join them back to paragraphs String text = StringUtils.join(cleanLines, "\n"); // create JCas JCas jCas = JCasFactory.createJCas(); jCas.setDocumentText(text); jCas.setDocumentLanguage("en"); // annotate WebParagraph SimplePipeline.runPipeline(jCas, AnalysisEngineFactory.createEngineDescription(WebParagraphAnnotator.class)); // fill the original tag information List<WebParagraph> webParagraphs = new ArrayList<>( JCasUtil.select(jCas, WebParagraph.class)); // they must be the same size as original ones if (webParagraphs.size() != lineTags.size()) { throw new IllegalStateException( "Different size of annotated paragraphs and original lines"); } for (int i = 0; i < webParagraphs.size(); i++) { WebParagraph p = webParagraphs.get(i); // get tag String tag = lineTags.get(i); p.setOriginalHtmlTag(tag); } SimplePipeline.runPipeline(jCas, AnalysisEngineFactory.createEngineDescription(StanfordSegmenter.class, // only on existing WebParagraph annotations StanfordSegmenter.PARAM_ZONE_TYPES, WebParagraph.class.getCanonicalName())); // now convert to XMI ByteArrayOutputStream byteOutputStream = new ByteArrayOutputStream(); XmiCasSerializer.serialize(jCas.getCas(), byteOutputStream); // encode to base64 String encoded = new BASE64Encoder().encode(byteOutputStream.toByteArray()); rankedResults.originalXmi = encoded; } } } // and save the query to output dir File outputFile = new File(outputDir, queryResultContainer.qID + ".xml"); FileUtils.writeStringToFile(outputFile, queryResultContainer.toXML(), "utf-8"); System.out.println("Finished " + outputFile); } }