List of usage examples for java.io BufferedWriter BufferedWriter
public BufferedWriter(Writer out)
From source file:com.kappaware.logtrawler.Main.java
@SuppressWarnings("static-access") static public void main(String[] argv) throws Throwable { Config config;/* w ww.j a v a 2 s . c o m*/ Options options = new Options(); options.addOption(OptionBuilder.hasArg().withArgName("configFile").withLongOpt("config-file") .withDescription("JSON configuration file").create("c")); options.addOption(OptionBuilder.hasArg().withArgName("folder").withLongOpt("folder") .withDescription("Folder to monitor").create("f")); options.addOption(OptionBuilder.hasArg().withArgName("exclusion").withLongOpt("exclusion") .withDescription("Exclusion regex").create("x")); options.addOption(OptionBuilder.hasArg().withArgName("adminEndpoint").withLongOpt("admin-endpoint") .withDescription("Endpoint for admin REST").create("e")); options.addOption(OptionBuilder.hasArg().withArgName("outputFlow").withLongOpt("output-flow") .withDescription("Target to post result on").create("o")); options.addOption(OptionBuilder.hasArg().withArgName("hostname").withLongOpt("hostname") .withDescription("This hostname").create("h")); options.addOption(OptionBuilder.withLongOpt("displayDot").withDescription("Display Dot").create("d")); options.addOption(OptionBuilder.hasArg().withArgName("mimeType").withLongOpt("mime-type") .withDescription("Valid MIME type").create("m")); options.addOption(OptionBuilder.hasArg().withArgName("allowedAdmin").withLongOpt("allowedAdmin") .withDescription("Allowed admin network").create("a")); options.addOption(OptionBuilder.hasArg().withArgName("configFile").withLongOpt("gen-config-file") .withDescription("Generate JSON configuration file").create("g")); options.addOption(OptionBuilder.hasArg().withArgName("maxBatchSize").withLongOpt("max-batch-size") .withDescription("Max JSON batch (array) size").create("b")); CommandLineParser clParser = new BasicParser(); CommandLine line; String configFile = null; try { // parse the command line argument line = clParser.parse(options, argv); if (line.hasOption("c")) { configFile = line.getOptionValue("c"); config = Json.fromJson(Config.class, new BufferedReader(new InputStreamReader(new FileInputStream(configFile)))); } else { config = new Config(); } if (line.hasOption("f")) { String[] fs = line.getOptionValues("f"); // Get the first agent (Create it if needed) if (config.getAgents() == null || config.getAgents().size() == 0) { Config.Agent agent = new Config.Agent("default"); config.addAgent(agent); } Config.Agent agent = config.getAgents().iterator().next(); for (String f : fs) { agent.addFolder(new Config.Agent.Folder(f, false)); } } if (line.hasOption("e")) { String e = line.getOptionValue("e"); config.setAdminEndpoint(e); } if (line.hasOption("o")) { String[] es = line.getOptionValues("o"); if (config.getAgents() != null) { for (Agent agent : config.getAgents()) { for (String s : es) { agent.addOuputFlow(s); } } } } if (line.hasOption("h")) { String e = line.getOptionValue("h"); config.setHostname(e); } if (line.hasOption("x")) { if (config.getAgents() != null) { for (Agent agent : config.getAgents()) { if (agent.getFolders() != null) { for (Folder folder : agent.getFolders()) { String[] exs = line.getOptionValues("x"); for (String ex : exs) { folder.addExcludedPath(ex); } } } } } } if (line.hasOption("m")) { if (config.getAgents() != null) { for (Agent agent : config.getAgents()) { String[] exs = line.getOptionValues("m"); for (String ex : exs) { agent.addLogMimeType(ex); } } } } if (line.hasOption("a")) { String[] exs = line.getOptionValues("a"); for (String ex : exs) { config.addAdminAllowedNetwork(ex); } } if (line.hasOption("d")) { config.setDisplayDot(true); } if (line.hasOption("b")) { Integer i = getIntegerParameter(line, "b"); if (config.getAgents() != null) { for (Agent agent : config.getAgents()) { agent.setOutputMaxBatchSize(i); } } } config.setDefault(); if (line.hasOption("g")) { String fileName = line.getOptionValue("g"); PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(fileName, false))); out.println(Json.toJson(config, true)); out.flush(); out.close(); System.exit(0); } } catch (ParseException exp) { // oops, something went wrong usage(options, exp.getMessage()); return; } try { // Check config if (config.getAgents() == null || config.getAgents().size() < 1) { throw new ConfigurationException("At least one folder to monitor must be provided!"); } Map<String, AgentHandler> agentHandlerByName = new HashMap<String, AgentHandler>(); for (Config.Agent agent : config.getAgents()) { agentHandlerByName.put(agent.getName(), new AgentHandler(agent)); } if (!Utils.isNullOrEmpty(config.getAdminEndpoint())) { new AdminServer(config, agentHandlerByName); } } catch (ConfigurationException e) { log.error(e.toString()); System.exit(1); } catch (Throwable t) { log.error("Error in main", t); System.exit(2); } }
From source file:com.joliciel.frenchTreebank.FrenchTreebank.java
/** * @param args//from w w w .j av a 2 s . com */ public static void main(String[] args) throws Exception { String command = args[0]; String outFilePath = ""; String outDirPath = ""; String treebankPath = ""; String ftbFileName = ""; String rawTextDir = ""; String queryPath = ""; String sentenceNumber = null; boolean firstArg = true; for (String arg : args) { if (firstArg) { firstArg = false; continue; } int equalsPos = arg.indexOf('='); String argName = arg.substring(0, equalsPos); String argValue = arg.substring(equalsPos + 1); if (argName.equals("outfile")) outFilePath = argValue; else if (argName.equals("outdir")) outDirPath = argValue; else if (argName.equals("ftbFileName")) ftbFileName = argValue; else if (argName.equals("treebank")) treebankPath = argValue; else if (argName.equals("sentence")) sentenceNumber = argValue; else if (argName.equals("query")) queryPath = argValue; else if (argName.equals("rawTextDir")) rawTextDir = argValue; else throw new RuntimeException("Unknown argument: " + argName); } TalismaneServiceLocator talismaneServiceLocator = TalismaneServiceLocator.getInstance(); TreebankServiceLocator locator = TreebankServiceLocator.getInstance(talismaneServiceLocator); if (treebankPath.length() == 0) locator.setDataSourcePropertiesFile("jdbc-live.properties"); if (command.equals("search")) { final SearchService searchService = locator.getSearchService(); final XmlPatternSearch search = searchService.newXmlPatternSearch(); search.setXmlPatternFile(queryPath); List<SearchResult> searchResults = search.perform(); FileWriter fileWriter = new FileWriter(outFilePath); for (SearchResult searchResult : searchResults) { String lineToWrite = ""; Sentence sentence = searchResult.getSentence(); Phrase phrase = searchResult.getPhrase(); lineToWrite += sentence.getFile().getFileName() + "|"; lineToWrite += sentence.getSentenceNumber() + "|"; List<PhraseUnit> phraseUnits = searchResult.getPhraseUnits(); LOG.debug("Phrase: " + phrase.getId()); for (PhraseUnit phraseUnit : phraseUnits) lineToWrite += phraseUnit.getLemma().getText() + "|"; lineToWrite += phrase.getText(); fileWriter.write(lineToWrite + "\n"); } fileWriter.flush(); fileWriter.close(); } else if (command.equals("load")) { final TreebankService treebankService = locator.getTreebankService(); final TreebankSAXParser parser = new TreebankSAXParser(); parser.setTreebankService(treebankService); parser.parseDocument(treebankPath); } else if (command.equals("loadAll")) { final TreebankService treebankService = locator.getTreebankService(); File dir = new File(treebankPath); String firstFile = null; if (args.length > 2) firstFile = args[2]; String[] files = dir.list(); if (files == null) { throw new RuntimeException("Not a directory or no children: " + treebankPath); } else { boolean startProcessing = true; if (firstFile != null) startProcessing = false; for (int i = 0; i < files.length; i++) { if (!startProcessing && files[i].equals(firstFile)) startProcessing = true; if (startProcessing) { String filePath = args[1] + "/" + files[i]; LOG.debug(filePath); final TreebankSAXParser parser = new TreebankSAXParser(); parser.setTreebankService(treebankService); parser.parseDocument(filePath); } } } } else if (command.equals("loadRawText")) { final TreebankService treebankService = locator.getTreebankService(); final TreebankRawTextAssigner assigner = new TreebankRawTextAssigner(); assigner.setTreebankService(treebankService); assigner.setRawTextDirectory(rawTextDir); assigner.loadRawText(); } else if (command.equals("tokenize")) { Writer csvFileWriter = null; if (outFilePath != null && outFilePath.length() > 0) { if (outFilePath.lastIndexOf("/") > 0) { String outputDirPath = outFilePath.substring(0, outFilePath.lastIndexOf("/")); File outputDir = new File(outputDirPath); outputDir.mkdirs(); } File csvFile = new File(outFilePath); csvFile.delete(); csvFile.createNewFile(); csvFileWriter = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(csvFile, false), "UTF8")); } try { final TreebankService treebankService = locator.getTreebankService(); TreebankExportService treebankExportService = locator.getTreebankExportServiceLocator() .getTreebankExportService(); TreebankUploadService treebankUploadService = locator.getTreebankUploadServiceLocator() .getTreebankUploadService(); TreebankReader treebankReader = null; if (treebankPath.length() > 0) { File treebankFile = new File(treebankPath); if (sentenceNumber != null) treebankReader = treebankUploadService.getXmlReader(treebankFile, sentenceNumber); else treebankReader = treebankUploadService.getXmlReader(treebankFile); } else { treebankReader = treebankService.getDatabaseReader(TreebankSubSet.ALL, 0); } TokeniserAnnotatedCorpusReader reader = treebankExportService .getTokeniserAnnotatedCorpusReader(treebankReader, csvFileWriter); while (reader.hasNextTokenSequence()) { TokenSequence tokenSequence = reader.nextTokenSequence(); List<Integer> tokenSplits = tokenSequence.getTokenSplits(); String sentence = tokenSequence.getText(); LOG.debug(sentence); int currentPos = 0; StringBuilder sb = new StringBuilder(); for (int split : tokenSplits) { if (split == 0) continue; String token = sentence.substring(currentPos, split); sb.append('|'); sb.append(token); currentPos = split; } LOG.debug(sb.toString()); } } finally { csvFileWriter.flush(); csvFileWriter.close(); } } else if (command.equals("export")) { if (outDirPath.length() == 0) throw new RuntimeException("Parameter required: outdir"); File outDir = new File(outDirPath); outDir.mkdirs(); final TreebankService treebankService = locator.getTreebankService(); FrenchTreebankXmlWriter xmlWriter = new FrenchTreebankXmlWriter(); xmlWriter.setTreebankService(treebankService); if (ftbFileName.length() == 0) { xmlWriter.write(outDir); } else { TreebankFile ftbFile = treebankService.loadTreebankFile(ftbFileName); String fileName = ftbFileName.substring(ftbFileName.lastIndexOf('/') + 1); File xmlFile = new File(outDir, fileName); xmlFile.delete(); xmlFile.createNewFile(); Writer xmlFileWriter = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(xmlFile, false), "UTF8")); xmlWriter.write(xmlFileWriter, ftbFile); xmlFileWriter.flush(); xmlFileWriter.close(); } } else { throw new RuntimeException("Unknown command: " + command); } LOG.debug("========== END ============"); }
From source file:eu.fbk.utils.lsa.util.Anvur.java
public static void main(String[] args) throws Exception { String logConfig = System.getProperty("log-config"); if (logConfig == null) { logConfig = "log-config.txt"; }/*ww w . j ava2 s . c o m*/ PropertyConfigurator.configure(logConfig); /* if (args.length != 2) { log.println("Usage: java -mx512M eu.fbk.utils.lsa.util.Anvur in-file out-dir"); System.exit(1); } File l = new File(args[1]); if (!l.exists()) { l.mkdir(); } List<String[]> list = readText(new File(args[0])); String oldCategory = ""; for (int i=0;i<list.size();i++) { String[] s = list.get(i); if (!oldCategory.equals(s[0])) { File f = new File(args[1] + File.separator + s[0]); boolean b = f.mkdir(); logger.debug(f + " created " + b); } File g = new File(args[1] + File.separator + s[0] + File.separator + s[1] + ".txt"); logger.debug("writing " + g + "..."); PrintWriter pw = new PrintWriter(new FileWriter(g)); //pw.println(tokenize(s[1].substring(0, s[1].indexOf(".")).replace('_', ' ') + " " + s[2])); if (s.length == 5) { pw.println(tokenize(s[1].substring(0, s[1].indexOf(".")).replace('_', ' ') + " " + s[2] + " " + s[4].replace('_', ' '))); } else { pw.println(tokenize(s[1].substring(0, s[1].indexOf(".")).replace('_', ' ') + " " + s[2])); } pw.flush(); pw.close(); } // end for i */ if (args.length != 7) { System.out.println(args.length); System.out.println( "Usage: java -mx2G eu.fbk.utils.lsa.util.Anvur input threshold size dim idf in-file-csv fields\n\n"); System.exit(1); } // DecimalFormat dec = new DecimalFormat("#.00"); File Ut = new File(args[0] + "-Ut"); File Sk = new File(args[0] + "-S"); File r = new File(args[0] + "-row"); File c = new File(args[0] + "-col"); File df = new File(args[0] + "-df"); double threshold = Double.parseDouble(args[1]); int size = Integer.parseInt(args[2]); int dim = Integer.parseInt(args[3]); boolean rescaleIdf = Boolean.parseBoolean(args[4]); //"author_check"0, "authors"1, "title"2, "year"3, "pubtype"4, "publisher"5, "journal"6, "volume"7, "number"8, "pages"9, "abstract"10, "nauthors", "citedby" String[] labels = { "author_check", "authors", "title", "year", "pubtype", "publisher", "journal", "volume", "number", "pages", "abstract", "nauthors", "citedby" //author_id authors title year pubtype publisher journal volume number pages abstract nauthors citedby }; String name = buildName(labels, args[6]); File bwf = new File(args[5] + name + "-bow.txt"); PrintWriter bw = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(bwf), "UTF-8"))); File bdf = new File(args[5] + name + "-bow.csv"); PrintWriter bd = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(bdf), "UTF-8"))); File lwf = new File(args[5] + name + "-ls.txt"); PrintWriter lw = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(lwf), "UTF-8"))); File ldf = new File(args[5] + name + "-ls.csv"); PrintWriter ld = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(ldf), "UTF-8"))); File blwf = new File(args[5] + name + "-bow+ls.txt"); PrintWriter blw = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(blwf), "UTF-8"))); File bldf = new File(args[5] + name + "-bow+ls.csv"); PrintWriter bld = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(bldf), "UTF-8"))); File logf = new File(args[5] + name + ".log"); PrintWriter log = new PrintWriter( new BufferedWriter(new OutputStreamWriter(new FileOutputStream(logf), "UTF-8"))); //System.exit(0); LSM lsm = new LSM(Ut, Sk, r, c, df, dim, rescaleIdf); LSSimilarity lss = new LSSimilarity(lsm, size); List<String[]> list = readText(new File(args[5])); // author_check authors title year pubtype publisher journal volume number pages abstract nauthors citedby //header for (int i = 0; i < list.size(); i++) { String[] s1 = list.get(i); String t1 = s1[0].toLowerCase(); bw.print("\t"); lw.print("\t"); blw.print("\t"); bw.print(i + "(" + s1[0] + ")"); lw.print(i + "(" + s1[0] + ")"); blw.print(i + "(" + s1[0] + ")"); } // end for i bw.print("\n"); lw.print("\n"); blw.print("\n"); for (int i = 0; i < list.size(); i++) { logger.info(i + "\t"); String[] s1 = list.get(i); String t1 = buildText(s1, args[6]); BOW bow1 = new BOW(t1); logger.info(bow1); Vector d1 = lsm.mapDocument(bow1); d1.normalize(); log.println("d1:" + d1); Vector pd1 = lsm.mapPseudoDocument(d1); pd1.normalize(); log.println("pd1:" + pd1); Vector m1 = merge(pd1, d1); log.println("m1:" + m1); // write the orginal line for (int j = 0; j < s1.length; j++) { bd.print(s1[j]); bd.print("\t"); ld.print(s1[j]); ld.print("\t"); bld.print(s1[j]); bld.print("\t"); } // write the bow, ls, and bow+ls vectors bd.println(d1); ld.println(pd1); bld.println(m1); bw.print(i + "(" + s1[0] + ")"); lw.print(i + "(" + s1[0] + ")"); blw.print(i + "(" + s1[0] + ")"); for (int j = 0; j < i + 1; j++) { bw.print("\t"); lw.print("\t"); blw.print("\t"); } // end for j for (int j = i + 1; j < list.size(); j++) { logger.info(i + "\t" + j); String[] s2 = list.get(j); String t2 = buildText(s2, args[6]); BOW bow2 = new BOW(t2); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") t1:" + t1); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") t2:" + t2); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") bow1:" + bow1); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") bow2:" + bow2); Vector d2 = lsm.mapDocument(bow2); d2.normalize(); log.println("d2:" + d2); Vector pd2 = lsm.mapPseudoDocument(d2); pd2.normalize(); log.println("pd2:" + pd2); Vector m2 = merge(pd2, d2); log.println("m2:" + m2); float cosVSM = d1.dotProduct(d2) / (float) Math.sqrt(d1.dotProduct(d1) * d2.dotProduct(d2)); float cosLSM = pd1.dotProduct(pd2) / (float) Math.sqrt(pd1.dotProduct(pd1) * pd2.dotProduct(pd2)); float cosBOWLSM = m1.dotProduct(m2) / (float) Math.sqrt(m1.dotProduct(m1) * m2.dotProduct(m2)); bw.print("\t"); bw.print(dec.format(cosVSM)); lw.print("\t"); lw.print(dec.format(cosLSM)); blw.print("\t"); blw.print(dec.format(cosBOWLSM)); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") bow\t" + cosVSM); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") ls:\t" + cosLSM); log.println(i + ":" + j + "(" + s1[0] + ":" + s2[0] + ") bow+ls:\t" + cosBOWLSM); } bw.print("\n"); lw.print("\n"); blw.print("\n"); } // end for i logger.info("wrote " + bwf); logger.info("wrote " + bwf); logger.info("wrote " + bdf); logger.info("wrote " + lwf); logger.info("wrote " + ldf); logger.info("wrote " + blwf); logger.info("wrote " + bldf); logger.info("wrote " + logf); ld.close(); bd.close(); bld.close(); bw.close(); lw.close(); blw.close(); log.close(); }
From source file:microbiosima.Microbiosima.java
/** * @param args//from www . jav a2 s . co m * the command line arguments * @throws java.io.FileNotFoundException * @throws java.io.UnsupportedEncodingException */ public static void main(String[] args) throws FileNotFoundException, UnsupportedEncodingException { //Init with default values int populationSize = 500; int microSize = 1000; int numberOfSpecies = 150; int numberOfGeneration = 10000; int numberOfObservation = 100; int numberOfReplication = 1; double pctEnv = 0; double pctPool = 0; Options options = new Options(); Option help = new Option("h", "help", false, "print this message"); Option version = new Option("v", "version", false, "print the version information and exit"); options.addOption(help); options.addOption(version); options.addOption(Option.builder("o").longOpt("obs").hasArg().argName("OBS") .desc("Number generation for observation [default: 100]").build()); options.addOption(Option.builder("r").longOpt("rep").hasArg().argName("REP") .desc("Number of replication [default: 1]").build()); Builder C = Option.builder("c").longOpt("config").numberOfArgs(4).argName("Pop Micro Spec Gen") .desc("Four Parameters in the following orders: " + "(1) population size, (2) microbe size, (3) number of species, (4) number of generation" + " [default: 500 1000 150 10000]"); options.addOption(C.build()); HelpFormatter formatter = new HelpFormatter(); String syntax = "microbiosima pctEnv pctPool"; String header = "\nSimulates the evolutionary and ecological dynamics of microbiomes within a population of hosts.\n\n" + "required arguments:\n" + " pctEnv Percentage of environmental acquisition\n" + " pctPool Percentage of pooled environmental component\n" + "\noptional arguments:\n"; String footer = "\n"; formatter.setWidth(80); CommandLineParser parser = new DefaultParser(); CommandLine cmd = null; try { cmd = parser.parse(options, args); String[] pct_config = cmd.getArgs(); if (cmd.hasOption("h") || args.length == 0) { formatter.printHelp(syntax, header, options, footer, true); System.exit(0); } if (cmd.hasOption("v")) { System.out.println("Microbiosima " + VERSION); System.exit(0); } if (pct_config.length != 2) { System.out.println("ERROR! Required exactly two argumennts for pct_env and pct_pool. It got " + pct_config.length + ": " + Arrays.toString(pct_config)); formatter.printHelp(syntax, header, options, footer, true); System.exit(3); } else { pctEnv = Double.parseDouble(pct_config[0]); pctPool = Double.parseDouble(pct_config[1]); if (pctEnv < 0 || pctEnv > 1) { System.out.println( "ERROR: pctEnv (Percentage of environmental acquisition) must be between 0 and 1 (pctEnv=" + pctEnv + ")! EXIT"); System.exit(3); } if (pctPool < 0 || pctPool > 1) { System.out.println( "ERROR: pctPool (Percentage of pooled environmental component must) must be between 0 and 1 (pctPool=" + pctPool + ")! EXIT"); System.exit(3); } } if (cmd.hasOption("config")) { String[] configs = cmd.getOptionValues("config"); populationSize = Integer.parseInt(configs[0]); microSize = Integer.parseInt(configs[1]); numberOfSpecies = Integer.parseInt(configs[2]); numberOfGeneration = Integer.parseInt(configs[3]); } if (cmd.hasOption("obs")) { numberOfObservation = Integer.parseInt(cmd.getOptionValue("obs")); } if (cmd.hasOption("rep")) { numberOfReplication = Integer.parseInt(cmd.getOptionValue("rep")); } } catch (ParseException e) { e.printStackTrace(); System.exit(3); } StringBuilder sb = new StringBuilder(); sb.append("Configuration Summary:").append("\n\tPopulation size: ").append(populationSize) .append("\n\tMicrobe size: ").append(microSize).append("\n\tNumber of species: ") .append(numberOfSpecies).append("\n\tNumber of generation: ").append(numberOfGeneration) .append("\n\tNumber generation for observation: ").append(numberOfObservation) .append("\n\tNumber of replication: ").append(numberOfReplication).append("\n"); System.out.println(sb.toString()); // System.exit(3); // LogNormalDistribution lgd=new LogNormalDistribution(0,1); // environment=lgd.sample(150); // double environment_sum=0; // for (int i=0;i<No;i++){ // environment_sum+=environment[i]; // } // for (int i=0;i<No;i++){ // environment[i]/=environment_sum; // } double[] environment = new double[numberOfSpecies]; for (int i = 0; i < numberOfSpecies; i++) { environment[i] = 1 / (double) numberOfSpecies; } for (int rep = 0; rep < numberOfReplication; rep++) { String prefix = "" + (rep + 1) + "_"; String sufix = "_E" + pctEnv + "_P" + pctPool + ".txt"; System.out.println("Output 5 result files in the format of: " + prefix + "[****]" + sufix); try { PrintWriter file1 = new PrintWriter( new BufferedWriter(new FileWriter(prefix + "gamma_diversity" + sufix))); PrintWriter file2 = new PrintWriter( new BufferedWriter(new FileWriter(prefix + "alpha_diversity" + sufix))); PrintWriter file3 = new PrintWriter( new BufferedWriter(new FileWriter(prefix + "beta_diversity" + sufix))); PrintWriter file4 = new PrintWriter(new BufferedWriter(new FileWriter(prefix + "sum" + sufix))); PrintWriter file5 = new PrintWriter( new BufferedWriter(new FileWriter(prefix + "inter_generation_distance" + sufix))); PrintWriter file6 = new PrintWriter( new BufferedWriter(new FileWriter(prefix + "environment_population_distance" + sufix))); Population population = new Population(microSize, environment, populationSize, pctEnv, pctPool, 0, 0); while (population.getNumberOfGeneration() < numberOfGeneration) { population.sumSpecies(); if (population.getNumberOfGeneration() % numberOfObservation == 0) { file1.println(population.gammaDiversity(true)); file2.println(population.alphaDiversity(true)); file3.print(population.betaDiversity(true)); file3.print("\t"); file3.println(population.BrayCurtis(true)); file4.println(population.printOut()); file5.println(population.interGenerationDistance()); file6.println(population.environmentPopulationDistance()); } population.getNextGen(); } file1.close(); file2.close(); file3.close(); file4.close(); file5.close(); file6.close(); } catch (IOException e) { e.printStackTrace(); } } }
From source file:edu.usc.qufd.Main.java
/** * The main method.//from w ww . j a va2 s . com * * @param args the arguments * @throws IOException Signals that an I/O exception has occurred. */ public static void main(String[] args) throws IOException { if (parseInputs(args) == false) { System.exit(-1); //The input files do not exist } /* * Parsing inputs: fabric & qasm file */ PrintWriter outputFile; RandomAccessFile raf = null; String latencyPlaceHolder; if (RuntimeConfig.OUTPUT_TO_FILE) { latencyPlaceHolder = "Total Latency: " + Long.MAX_VALUE + " us" + System.lineSeparator(); raf = new RandomAccessFile(outputFileAddr, "rws"); //removing the old values in the file raf.setLength(0); //writing a place holder for the total latency raf.writeBytes(latencyPlaceHolder); raf.close(); outputFile = new PrintWriter(new BufferedWriter(new FileWriter(outputFileAddr, true)), true); } else { //writing to stdout outputFile = new PrintWriter(new BufferedWriter(new OutputStreamWriter(System.out)), true); } /* parsing the input*/ layout = LayoutParser.parse(pmdFileAddr); qasm = QASMParser.QASMParser(qasmFileAddr, layout); long totalLatency = qufd(outputFile); if (RuntimeConfig.OUTPUT_TO_FILE) { outputFile.close(); //Over writing the place holder with the actual latency String latencyActual = "Total Latency: " + totalLatency + " " + layout.getTimeUnit(); latencyActual = StringUtils.rightPad(latencyActual, latencyPlaceHolder.length() - System.lineSeparator().length()); raf = new RandomAccessFile(outputFileAddr, "rws"); //Writing to the top of a file raf.seek(0); //writing the actual total latency in the at the top of the output file raf.writeBytes(latencyActual + System.lineSeparator()); raf.close(); } else { outputFile.flush(); System.out.println("Total Latency: " + totalLatency + " " + layout.getTimeUnit()); } if (RuntimeConfig.VERBOSE) { System.out.println("Done."); } outputFile.close(); }
From source file:net.java.sen.tools.MkSenDic.java
/** * Build sen dictionary.//ww w . j a va2 s . com * * @param args * custom dictionary files. see dic/build.xml. */ public static void main(String args[]) { ResourceBundle rb = ResourceBundle.getBundle("dictionary"); DictionaryMaker dm1 = new DictionaryMaker(); DictionaryMaker dm2 = new DictionaryMaker(); DictionaryMaker dm3 = new DictionaryMaker(); // 1st field information of connect file. Vector rule1 = new Vector(); // 2nd field information of connect file. Vector rule2 = new Vector(); // 3rd field information of connect file. Vector rule3 = new Vector(); // 4th field information of connect file. // this field shows cost of morpheme connection // [size3*(x3*size2+x2)+x1] // [size3*(Attr1*size2+Attr2)+Attl] short score[] = new short[20131]; long start = System.currentTimeMillis(); // ///////////////////////////////////////// // // Step1. Loading connetion file. // log.info("(1/7): reading connection matrix ... "); try { log.info("connection file = " + rb.getString("text_connection_file")); log.info("charset = " + rb.getString("dic.charset")); CSVParser csvparser = new CSVParser(new FileInputStream(rb.getString("text_connection_file")), rb.getString("dic.charset")); String t[]; int line = 0; while ((t = csvparser.nextTokens()) != null) { if (t.length < 4) { log.warn("invalid line in " + rb.getString("text_connection_file") + ":" + line); log.warn(rb.getString("text_connection_file") + "may be broken."); break; } dm1.add(t[0]); rule1.add(t[0]); dm2.add(t[1]); rule2.add(t[1]); dm3.add(t[2]); rule3.add(t[2]); if (line == score.length) { score = resize(score); } score[line++] = (short) Integer.parseInt(t[3]); } // ///////////////////////////////////////// // // Step2. Building internal dictionary // log.info("(2/7): building type dictionary ... "); dm1.build(); dm2.build(); dm3.build(); // if you want check specified morpheme, you uncomment and modify // following line: /* * System.out.print("22="); dm3.getById(22); * System.out.print("368="); dm3.getById(368); * * System.out.println(dm3.getDicId("?????*,*,*,*,?")); * DictionaryMaker.debug = true; * System.out.println(dm3.getDicId("?????*,*,*,*,?")); * System.out.println(dm3.getDicIdNoCache("?????*,*,*,*,?")); */ } catch (IOException e) { e.printStackTrace(); System.exit(0); } // ------------------------------------------------- int size1 = dm1.size(); int size2 = dm2.size(); int size3 = dm3.size(); int ruleSize = rule1.size(); short matrix[] = new short[size1 * size2 * size3]; short default_cost = (short) Integer.parseInt(rb.getString("default_connection_cost")); // ///////////////////////////////////////// // // Step3. Writing Connection Matrix // log.info("(3/7): writing conection matrix (" + size1 + " x " + size2 + " x " + size3 + " = " + size1 * size2 * size3 + ") ..."); for (int i = 0; i < (int) (size1 * size2 * size3); i++) matrix[i] = default_cost; for (int i = 0; i < ruleSize; i++) { Vector r1 = dm1.getRuleIdList((String) rule1.get(i)); Vector r2 = dm2.getRuleIdList((String) rule2.get(i)); Vector r3 = dm3.getRuleIdList((String) rule3.get(i)); for (Iterator i1 = r1.iterator(); i1.hasNext();) { int ii1 = ((Integer) i1.next()).intValue(); for (Iterator i2 = r2.iterator(); i2.hasNext();) { int ii2 = ((Integer) i2.next()).intValue(); for (Iterator i3 = r3.iterator(); i3.hasNext();) { int ii3 = ((Integer) i3.next()).intValue(); int pos = size3 * (size2 * ii1 + ii2) + ii3; matrix[pos] = score[i]; } } } } try { DataOutputStream out = new DataOutputStream( new BufferedOutputStream(new FileOutputStream(rb.getString("matrix_file")))); out.writeShort(size1); out.writeShort(size2); out.writeShort(size3); for (int i1 = 0; i1 < size1; i1++) for (int i2 = 0; i2 < size2; i2++) for (int i3 = 0; i3 < size3; i3++) { out.writeShort(matrix[size3 * (size2 * i1 + i2) + i3]); // if (matrix[size3 * (size2 * i1 + i2) + i3] != // default_cost) { // } } out.close(); } catch (IOException e) { e.printStackTrace(); System.exit(0); } matrix = null; score = null; // ------------------------------------------------- int pos_start = Integer.parseInt(rb.getString("pos_start")); int pos_size = Integer.parseInt(rb.getString("pos_size")); int di = 0; int offset = 0; ArrayList dicList = new ArrayList(); // ///////////////////////////////////////// // // Step4. Reading Morpheme Information // log.info("(4/7): reading morpheme information ... "); String t = null; String[] csv = null; try { // writer for feature file. BufferedWriter bw = new BufferedWriter(new OutputStreamWriter( new FileOutputStream(rb.getString("pos_file")), rb.getString("sen.charset"))); log.info("load dic: " + rb.getString("text_dic_file")); BufferedReader dicStream = null; int custom_dic = -1; if (args.length == 0) { dicStream = new BufferedReader(new InputStreamReader( new FileInputStream(rb.getString("text_dic_file")), rb.getString("dic.charset"))); } else { custom_dic = 0; dicStream = new BufferedReader( new InputStreamReader(new FileInputStream(args[custom_dic]), rb.getString("dic.charset"))); } int line = 0; CSVData key_b = new CSVData(); CSVData pos_b = new CSVData(); while (true) { t = dicStream.readLine(); if (t == null) { dicStream.close(); custom_dic++; if (args.length == custom_dic) { break; } else { // read custum dictionary log.info("load dic: " + "args[custum_dic]"); dicStream = new BufferedReader(new InputStreamReader(new FileInputStream(args[custom_dic]), rb.getString("dic.charset"))); } continue; } CSVParser parser = new CSVParser(t); csv = parser.nextTokens(); if (csv.length < (pos_size + pos_start)) { throw new RuntimeException("format error:" + t); } key_b.clear(); pos_b.clear(); for (int i = pos_start; i < (pos_start + pos_size - 1); i++) { key_b.append(csv[i]); pos_b.append(csv[i]); } key_b.append(csv[pos_start + pos_size - 1]); pos_b.append(csv[pos_start + pos_size - 1]); for (int i = pos_start + pos_size; i < (csv.length - 1); i++) { pos_b.append(csv[i]); } pos_b.append(csv[csv.length - 1]); CToken token = new CToken(); token.rcAttr2 = (short) dm1.getDicId(key_b.toString()); token.rcAttr1 = (short) dm2.getDicId(key_b.toString()); token.lcAttr = (short) dm3.getDicId(key_b.toString()); token.posid = 0; token.posID = offset; token.length = (short) csv[0].length(); token.cost = (short) Integer.parseInt(csv[1]); dicList.add(new PairObject(csv[0], token)); byte b[] = pos_b.toString().getBytes(rb.getString("sen.charset")); offset += (b.length + 1); String pos_b_str = pos_b.toString(); bw.write(pos_b_str, 0, pos_b_str.length()); // bw.write(b, 0, b.length); bw.write(0); if (++di % 50000 == 0) log.info("" + di + "... "); } bw.close(); // ----end of writing feature.cha ---- } catch (Exception e) { log.error("Error: " + t); e.printStackTrace(); System.exit(1); } rule1 = null; rule2 = null; rule3 = null; // ///////////////////////////////////////// // // Step5. Sort lexs and write to file // log.info("(5/7): sorting lex... "); int value[] = new int[dicList.size()]; char key[][] = new char[dicList.size()][]; int spos = 0; int dsize = 0; int bsize = 0; String prev = ""; Collections.sort(dicList); // ///////////////////////////////////////// // // Step6. Writing Token Information // log.info("(6/7): writing token... "); try { // writer for token file. DataOutputStream out = new DataOutputStream( new BufferedOutputStream(new FileOutputStream(rb.getString("token_file")))); // writing 'bos' and 'eos' and 'unknown' token. CToken token = new CToken(); token.rcAttr2 = (short) dm1.getDicId(rb.getString("bos_pos")); token.rcAttr1 = (short) dm2.getDicId(rb.getString("bos_pos")); token.lcAttr = (short) dm3.getDicId(rb.getString("bos_pos")); token.write(out); token.rcAttr2 = (short) dm1.getDicId(rb.getString("eos_pos")); token.rcAttr1 = (short) dm2.getDicId(rb.getString("eos_pos")); token.lcAttr = (short) dm3.getDicId(rb.getString("eos_pos")); token.write(out); token.rcAttr2 = (short) dm1.getDicId(rb.getString("unknown_pos")); token.rcAttr1 = (short) dm2.getDicId(rb.getString("unknown_pos")); token.lcAttr = (short) dm3.getDicId(rb.getString("unknown_pos")); token.posID = -1; token.write(out); log.info("key size = " + key.length); for (int i = 0; i < key.length; i++) { String k = (String) ((PairObject) dicList.get(i)).key; if (!prev.equals(k) && i != 0) { key[dsize] = ((String) ((PairObject) dicList.get(spos)).key).toCharArray(); value[dsize] = bsize + (spos << 8); dsize++; bsize = 1; spos = i; } else { bsize++; } prev = (String) ((PairObject) dicList.get(i)).key; ((CToken) (((PairObject) dicList.get(i)).value)).write(out); } out.flush(); out.close(); } catch (Exception e) { e.printStackTrace(); System.exit(1); } key[dsize] = ((String) ((PairObject) dicList.get(spos)).key).toCharArray(); value[dsize] = bsize + (spos << 8); dsize++; dm1 = null; dm2 = null; dm3 = null; dicList = null; // ///////////////////////////////////////// // // Step7. Build Double Array // log.info("(7/7): building Double-Array (size = " + dsize + ") ..."); DoubleArrayTrie da = new DoubleArrayTrie(); da.build(key, null, value, dsize); try { da.save(rb.getString("double_array_file")); } catch (Exception e) { e.printStackTrace(); } log.info("total time = " + (System.currentTimeMillis() - start) / 1000 + "[ms]"); }
From source file:at.riemers.velocity2js.velocity.Velocity2Js.java
/** * @param args the command line arguments *//*from w w w. j av a2 s . c om*/ public static void main(String[] args) { try { if (args.length == 0) { printUsage(); return; } if (args[0].equals("-d") && args.length >= 3) { String resource = null; if (args.length >= 4) { resource = args[3]; } List<I18NBundle> bundles = getBundles(resource); Velocity2Js.generateDir(args[1], args[2], bundles); return; } if (args[0].equals("-f") && args.length >= 4) { Properties p = new Properties(); p.setProperty("resource.loader", "file"); p.setProperty("file.resource.loader.description", "Velocity File Resource Loader"); p.setProperty("file.resource.loader.class", "org.apache.velocity.runtime.resource.loader.FileResourceLoader"); p.setProperty("file.resource.loader.path", args[1]); Velocity2Js.init(p); String function = createFunctionName(args[2]); String resource = null; if (args.length >= 5) { resource = args[4]; } List<I18NBundle> bundles = getBundles(resource); for (I18NBundle bundle : bundles) { String fname = args[3]; int e = args[3].lastIndexOf('.'); if (e <= 0 || e > args[3].length()) e = args[3].length(); fname = args[3].substring(0, e) + bundle.getLocale() + args[3].substring(e); BufferedWriter writer = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(fname), "UTF8")); Velocity2Js.generate(args[2], function, writer, bundle.getBundle()); writer.flush(); writer.close(); } return; } printUsage(); return; } catch (ResourceNotFoundException rnfe) { log.error("[velocity2js] : cannot find template : " + rnfe.getMessage()); } catch (ParseErrorException pee) { log.error("[velocity2js] : Syntax error in template :" + pee); } catch (Exception ex) { System.out.flush(); log.error("[velocity2js] : unknown error " + ex.getMessage()); ex.printStackTrace(System.out); System.out.println(ex.getLocalizedMessage()); System.exit(1); } }
From source file:examples.mail.IMAPExportMbox.java
public static void main(String[] args) throws IOException { int connect_timeout = CONNECT_TIMEOUT; int read_timeout = READ_TIMEOUT; int argIdx = 0; String eol = EOL_DEFAULT;/* ww w . j ava 2 s . c om*/ boolean printHash = false; boolean printMarker = false; int retryWaitSecs = 0; for (argIdx = 0; argIdx < args.length; argIdx++) { if (args[argIdx].equals("-c")) { connect_timeout = Integer.parseInt(args[++argIdx]); } else if (args[argIdx].equals("-r")) { read_timeout = Integer.parseInt(args[++argIdx]); } else if (args[argIdx].equals("-R")) { retryWaitSecs = Integer.parseInt(args[++argIdx]); } else if (args[argIdx].equals("-LF")) { eol = LF; } else if (args[argIdx].equals("-CRLF")) { eol = CRLF; } else if (args[argIdx].equals("-.")) { printHash = true; } else if (args[argIdx].equals("-X")) { printMarker = true; } else { break; } } final int argCount = args.length - argIdx; if (argCount < 2) { System.err.println("Usage: IMAPExportMbox [-LF|-CRLF] [-c n] [-r n] [-R n] [-.] [-X]" + " imap[s]://user:password@host[:port]/folder/path [+|-]<mboxfile> [sequence-set] [itemnames]"); System.err.println( "\t-LF | -CRLF set end-of-line to LF or CRLF (default is the line.separator system property)"); System.err.println("\t-c connect timeout in seconds (default 10)"); System.err.println("\t-r read timeout in seconds (default 10)"); System.err.println("\t-R temporary failure retry wait in seconds (default 0; i.e. disabled)"); System.err.println("\t-. print a . for each complete message received"); System.err.println("\t-X print the X-IMAP line for each complete message received"); System.err.println( "\tthe mboxfile is where the messages are stored; use '-' to write to standard output."); System.err.println( "\tPrefix filename with '+' to append to the file. Prefix with '-' to allow overwrite."); System.err.println( "\ta sequence-set is a list of numbers/number ranges e.g. 1,2,3-10,20:* - default 1:*"); System.err .println("\titemnames are the message data item name(s) e.g. BODY.PEEK[HEADER.FIELDS (SUBJECT)]" + " or a macro e.g. ALL - default (INTERNALDATE BODY.PEEK[])"); System.exit(1); } final URI uri = URI.create(args[argIdx++]); final String file = args[argIdx++]; String sequenceSet = argCount > 2 ? args[argIdx++] : "1:*"; final String itemNames; // Handle 0, 1 or multiple item names if (argCount > 3) { if (argCount > 4) { StringBuilder sb = new StringBuilder(); sb.append("("); for (int i = 4; i <= argCount; i++) { if (i > 4) { sb.append(" "); } sb.append(args[argIdx++]); } sb.append(")"); itemNames = sb.toString(); } else { itemNames = args[argIdx++]; } } else { itemNames = "(INTERNALDATE BODY.PEEK[])"; } final boolean checkSequence = sequenceSet.matches("\\d+:(\\d+|\\*)"); // are we expecting a sequence? final MboxListener chunkListener; if (file.equals("-")) { chunkListener = null; } else if (file.startsWith("+")) { final File mbox = new File(file.substring(1)); System.out.println("Appending to file " + mbox); chunkListener = new MboxListener(new BufferedWriter(new FileWriter(mbox, true)), eol, printHash, printMarker, checkSequence); } else if (file.startsWith("-")) { final File mbox = new File(file.substring(1)); System.out.println("Writing to file " + mbox); chunkListener = new MboxListener(new BufferedWriter(new FileWriter(mbox, false)), eol, printHash, printMarker, checkSequence); } else { final File mbox = new File(file); if (mbox.exists()) { throw new IOException("mailbox file: " + mbox + " already exists!"); } System.out.println("Creating file " + mbox); chunkListener = new MboxListener(new BufferedWriter(new FileWriter(mbox)), eol, printHash, printMarker, checkSequence); } String path = uri.getPath(); if (path == null || path.length() < 1) { throw new IllegalArgumentException("Invalid folderPath: '" + path + "'"); } String folder = path.substring(1); // skip the leading / // suppress login details final PrintCommandListener listener = new PrintCommandListener(System.out, true) { @Override public void protocolReplyReceived(ProtocolCommandEvent event) { if (event.getReplyCode() != IMAPReply.PARTIAL) { // This is dealt with by the chunk listener super.protocolReplyReceived(event); } } }; // Connect and login final IMAPClient imap = IMAPUtils.imapLogin(uri, connect_timeout * 1000, listener); String maxIndexInFolder = null; try { imap.setSoTimeout(read_timeout * 1000); if (!imap.select(folder)) { throw new IOException("Could not select folder: " + folder); } for (String line : imap.getReplyStrings()) { maxIndexInFolder = matches(line, PATEXISTS, 1); if (maxIndexInFolder != null) { break; } } if (chunkListener != null) { imap.setChunkListener(chunkListener); } // else the command listener displays the full output without processing while (true) { boolean ok = imap.fetch(sequenceSet, itemNames); // If the fetch failed, can we retry? if (!ok && retryWaitSecs > 0 && chunkListener != null && checkSequence) { final String replyString = imap.getReplyString(); //includes EOL if (startsWith(replyString, PATTEMPFAIL)) { System.err.println("Temporary error detected, will retry in " + retryWaitSecs + "seconds"); sequenceSet = (chunkListener.lastSeq + 1) + ":*"; try { Thread.sleep(retryWaitSecs * 1000); } catch (InterruptedException e) { // ignored } } else { throw new IOException( "FETCH " + sequenceSet + " " + itemNames + " failed with " + replyString); } } else { break; } } } catch (IOException ioe) { String count = chunkListener == null ? "?" : Integer.toString(chunkListener.total); System.err.println("FETCH " + sequenceSet + " " + itemNames + " failed after processing " + count + " complete messages "); if (chunkListener != null) { System.err.println("Last complete response seen: " + chunkListener.lastFetched); } throw ioe; } finally { if (printHash) { System.err.println(); } if (chunkListener != null) { chunkListener.close(); final Iterator<String> missingIds = chunkListener.missingIds.iterator(); if (missingIds.hasNext()) { StringBuilder sb = new StringBuilder(); for (;;) { sb.append(missingIds.next()); if (!missingIds.hasNext()) { break; } sb.append(","); } System.err.println("*** Missing ids: " + sb.toString()); } } imap.logout(); imap.disconnect(); } if (chunkListener != null) { System.out.println("Processed " + chunkListener.total + " messages."); } if (maxIndexInFolder != null) { System.out.println("Folder contained " + maxIndexInFolder + " messages."); } }
From source file:com.joliciel.talismane.terminology.TalismaneTermExtractorMain.java
public static void main(String[] args) throws Exception { String termFilePath = null;/*from w w w. j a v a 2 s .co m*/ String outFilePath = null; Command command = Command.extract; int depth = -1; String databasePropertiesPath = null; String projectCode = null; String terminologyPropertiesPath = null; Map<String, String> argMap = StringUtils.convertArgs(args); String logConfigPath = argMap.get("logConfigFile"); if (logConfigPath != null) { argMap.remove("logConfigFile"); Properties props = new Properties(); props.load(new FileInputStream(logConfigPath)); PropertyConfigurator.configure(props); } Map<String, String> innerArgs = new HashMap<String, String>(); for (Entry<String, String> argEntry : argMap.entrySet()) { String argName = argEntry.getKey(); String argValue = argEntry.getValue(); if (argName.equals("command")) command = Command.valueOf(argValue); else if (argName.equals("termFile")) termFilePath = argValue; else if (argName.equals("outFile")) outFilePath = argValue; else if (argName.equals("depth")) depth = Integer.parseInt(argValue); else if (argName.equals("databaseProperties")) databasePropertiesPath = argValue; else if (argName.equals("terminologyProperties")) terminologyPropertiesPath = argValue; else if (argName.equals("projectCode")) projectCode = argValue; else innerArgs.put(argName, argValue); } if (termFilePath == null && databasePropertiesPath == null) throw new TalismaneException("Required argument: termFile or databasePropertiesPath"); if (termFilePath != null) { String currentDirPath = System.getProperty("user.dir"); File termFileDir = new File(currentDirPath); if (termFilePath.lastIndexOf("/") >= 0) { String termFileDirPath = termFilePath.substring(0, termFilePath.lastIndexOf("/")); termFileDir = new File(termFileDirPath); termFileDir.mkdirs(); } } long startTime = new Date().getTime(); try { if (command.equals(Command.analyse)) { innerArgs.put("command", "analyse"); } else { innerArgs.put("command", "process"); } String sessionId = ""; TalismaneServiceLocator locator = TalismaneServiceLocator.getInstance(sessionId); TalismaneService talismaneService = locator.getTalismaneService(); TalismaneConfig config = talismaneService.getTalismaneConfig(innerArgs, sessionId); TerminologyServiceLocator terminologyServiceLocator = TerminologyServiceLocator.getInstance(locator); TerminologyService terminologyService = terminologyServiceLocator.getTerminologyService(); TerminologyBase terminologyBase = null; if (projectCode == null) throw new TalismaneException("Required argument: projectCode"); File file = new File(databasePropertiesPath); FileInputStream fis = new FileInputStream(file); Properties dataSourceProperties = new Properties(); dataSourceProperties.load(fis); terminologyBase = terminologyService.getPostGresTerminologyBase(projectCode, dataSourceProperties); TalismaneSession talismaneSession = talismaneService.getTalismaneSession(); if (command.equals(Command.analyse) || command.equals(Command.extract)) { Locale locale = talismaneSession.getLocale(); Map<TerminologyProperty, String> terminologyProperties = new HashMap<TerminologyProperty, String>(); if (terminologyPropertiesPath != null) { Map<String, String> terminologyPropertiesStr = StringUtils.getArgMap(terminologyPropertiesPath); for (String key : terminologyPropertiesStr.keySet()) { try { TerminologyProperty property = TerminologyProperty.valueOf(key); terminologyProperties.put(property, terminologyPropertiesStr.get(key)); } catch (IllegalArgumentException e) { throw new TalismaneException("Unknown terminology property: " + key); } } } else { terminologyProperties = getDefaultTerminologyProperties(locale); } if (depth <= 0 && !terminologyProperties.containsKey(TerminologyProperty.maxDepth)) throw new TalismaneException("Required argument: depth"); InputStream regexInputStream = getInputStreamFromResource( "parser_conll_with_location_input_regex.txt"); Scanner regexScanner = new Scanner(regexInputStream, "UTF-8"); String inputRegex = regexScanner.nextLine(); regexScanner.close(); config.setInputRegex(inputRegex); Charset outputCharset = config.getOutputCharset(); TermExtractor termExtractor = terminologyService.getTermExtractor(terminologyBase, terminologyProperties); if (depth > 0) termExtractor.setMaxDepth(depth); termExtractor.setOutFilePath(termFilePath); if (outFilePath != null) { if (outFilePath.lastIndexOf("/") >= 0) { String outFileDirPath = outFilePath.substring(0, outFilePath.lastIndexOf("/")); File outFileDir = new File(outFileDirPath); outFileDir.mkdirs(); } File outFile = new File(outFilePath); outFile.delete(); outFile.createNewFile(); Writer writer = new BufferedWriter( new OutputStreamWriter(new FileOutputStream(outFilePath), outputCharset)); TermAnalysisWriter termAnalysisWriter = new TermAnalysisWriter(writer); termExtractor.addTermObserver(termAnalysisWriter); } Talismane talismane = config.getTalismane(); talismane.setParseConfigurationProcessor(termExtractor); talismane.process(); } else if (command.equals(Command.list)) { List<Term> terms = terminologyBase.findTerms(2, null, 0, null, null); for (Term term : terms) { LOG.debug("Term: " + term.getText()); LOG.debug("Frequency: " + term.getFrequency()); LOG.debug("Heads: " + term.getHeads()); LOG.debug("Expansions: " + term.getExpansions()); LOG.debug("Contexts: " + term.getContexts()); } } } finally { long endTime = new Date().getTime(); long totalTime = endTime - startTime; LOG.info("Total time: " + totalTime); } }
From source file:com.github.s4ke.moar.cli.Main.java
public static void main(String[] args) throws ParseException, IOException { // create Options object Options options = new Options(); options.addOption("rf", true, "file containing the regexes to test against (multiple regexes are separated by one empty line)"); options.addOption("r", true, "regex to test against"); options.addOption("mf", true, "file/folder to read the MOA from"); options.addOption("mo", true, "folder to export the MOAs to (overwrites if existent)"); options.addOption("sf", true, "file to read the input string(s) from"); options.addOption("s", true, "string to test the MOA/Regex against"); options.addOption("m", false, "multiline matching mode (search in string for regex)"); options.addOption("ls", false, "treat every line of the input string file as one string"); options.addOption("t", false, "trim lines if -ls is set"); options.addOption("d", false, "only do determinism check"); options.addOption("help", false, "prints this dialog"); CommandLineParser parser = new DefaultParser(); CommandLine cmd = parser.parse(options, args); if (args.length == 0 || cmd.hasOption("help")) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("moar-cli", options); return;//from w w w. j av a2 s. c o m } List<String> patternNames = new ArrayList<>(); List<MoaPattern> patterns = new ArrayList<>(); List<String> stringsToCheck = new ArrayList<>(); if (cmd.hasOption("r")) { String regexStr = cmd.getOptionValue("r"); try { patterns.add(MoaPattern.compile(regexStr)); patternNames.add(regexStr); } catch (Exception e) { System.out.println(e.getMessage()); } } if (cmd.hasOption("rf")) { String fileName = cmd.getOptionValue("rf"); List<String> regexFileContents = readFileContents(new File(fileName)); int emptyLineCountAfterRegex = 0; StringBuilder regexStr = new StringBuilder(); for (String line : regexFileContents) { if (emptyLineCountAfterRegex >= 1) { if (regexStr.length() > 0) { patterns.add(MoaPattern.compile(regexStr.toString())); patternNames.add(regexStr.toString()); } regexStr.setLength(0); emptyLineCountAfterRegex = 0; } if (line.trim().equals("")) { if (regexStr.length() > 0) { ++emptyLineCountAfterRegex; } } else { regexStr.append(line); } } if (regexStr.length() > 0) { try { patterns.add(MoaPattern.compile(regexStr.toString())); patternNames.add(regexStr.toString()); } catch (Exception e) { System.out.println(e.getMessage()); return; } regexStr.setLength(0); } } if (cmd.hasOption("mf")) { String fileName = cmd.getOptionValue("mf"); File file = new File(fileName); if (file.isDirectory()) { System.out.println(fileName + " is a directory, using all *.moar files as patterns"); File[] moarFiles = file.listFiles(pathname -> pathname.getName().endsWith(".moar")); for (File moar : moarFiles) { String jsonString = readWholeFile(moar); patterns.add(MoarJSONSerializer.fromJSON(jsonString)); patternNames.add(moar.getAbsolutePath()); } } else { System.out.println(fileName + " is a single file. using it directly (no check for *.moar suffix)"); String jsonString = readWholeFile(file); patterns.add(MoarJSONSerializer.fromJSON(jsonString)); patternNames.add(fileName); } } if (cmd.hasOption("s")) { String str = cmd.getOptionValue("s"); stringsToCheck.add(str); } if (cmd.hasOption("sf")) { boolean treatLineAsString = cmd.hasOption("ls"); boolean trim = cmd.hasOption("t"); String fileName = cmd.getOptionValue("sf"); StringBuilder stringBuilder = new StringBuilder(); boolean firstLine = true; for (String str : readFileContents(new File(fileName))) { if (treatLineAsString) { if (trim) { str = str.trim(); if (str.length() == 0) { continue; } } stringsToCheck.add(str); } else { if (!firstLine) { stringBuilder.append("\n"); } if (firstLine) { firstLine = false; } stringBuilder.append(str); } } if (!treatLineAsString) { stringsToCheck.add(stringBuilder.toString()); } } if (cmd.hasOption("d")) { //at this point we have already built the Patterns //so just give the user a short note. System.out.println("All Regexes seem to be deterministic."); return; } if (patterns.size() == 0) { System.out.println("no patterns to check"); return; } if (cmd.hasOption("mo")) { String folder = cmd.getOptionValue("mo"); File folderFile = new File(folder); if (!folderFile.exists()) { System.out.println(folder + " does not exist. creating..."); if (!folderFile.mkdirs()) { System.out.println("folder " + folder + " could not be created"); } } int cnt = 0; for (MoaPattern pattern : patterns) { String patternAsJSON = MoarJSONSerializer.toJSON(pattern); try (BufferedWriter writer = new BufferedWriter( new FileWriter(new File(folderFile, "pattern" + ++cnt + ".moar")))) { writer.write(patternAsJSON); } } System.out.println("stored " + cnt + " patterns in " + folder); } if (stringsToCheck.size() == 0) { System.out.println("no strings to check"); return; } boolean multiline = cmd.hasOption("m"); for (String string : stringsToCheck) { int curPattern = 0; for (MoaPattern pattern : patterns) { MoaMatcher matcher = pattern.matcher(string); if (!multiline) { if (matcher.matches()) { System.out.println("\"" + patternNames.get(curPattern) + "\" matches \"" + string + "\""); } else { System.out.println( "\"" + patternNames.get(curPattern) + "\" does not match \"" + string + "\""); } } else { StringBuilder buffer = new StringBuilder(string); int additionalCharsPerMatch = ("<match>" + "</match>").length(); int matchCount = 0; while (matcher.nextMatch()) { buffer.replace(matcher.getStart() + matchCount * additionalCharsPerMatch, matcher.getEnd() + matchCount * additionalCharsPerMatch, "<match>" + string.substring(matcher.getStart(), matcher.getEnd()) + "</match>"); ++matchCount; } System.out.println(buffer.toString()); } } ++curPattern; } }