List of usage examples for java.io File exists
public boolean exists()
From source file:com.twentyn.patentSearch.DocumentIndexer.java
public static void main(String[] args) throws Exception { System.out.println("Starting up..."); System.out.flush();// w ww . j a v a 2 s.co m Options opts = new Options(); opts.addOption(Option.builder("i").longOpt("input").hasArg().required() .desc("Input file or directory to index").build()); opts.addOption(Option.builder("x").longOpt("index").hasArg().required() .desc("Path to index file to generate").build()); opts.addOption(Option.builder("h").longOpt("help").desc("Print this help message and exit").build()); opts.addOption(Option.builder("v").longOpt("verbose").desc("Print verbose log output").build()); HelpFormatter helpFormatter = new HelpFormatter(); CommandLineParser cmdLineParser = new DefaultParser(); CommandLine cmdLine = null; try { cmdLine = cmdLineParser.parse(opts, args); } catch (ParseException e) { System.out.println("Caught exception when parsing command line: " + e.getMessage()); helpFormatter.printHelp("DocumentIndexer", opts); System.exit(1); } if (cmdLine.hasOption("help")) { helpFormatter.printHelp("DocumentIndexer", opts); System.exit(0); } if (cmdLine.hasOption("verbose")) { // With help from http://stackoverflow.com/questions/23434252/programmatically-change-log-level-in-log4j2 LoggerContext ctx = (LoggerContext) LogManager.getContext(false); Configuration ctxConfig = ctx.getConfiguration(); LoggerConfig logConfig = ctxConfig.getLoggerConfig(LogManager.ROOT_LOGGER_NAME); logConfig.setLevel(Level.DEBUG); ctx.updateLoggers(); LOGGER.debug("Verbose logging enabled"); } LOGGER.info("Opening index at " + cmdLine.getOptionValue("index")); Directory indexDir = FSDirectory.open(new File(cmdLine.getOptionValue("index")).toPath()); /* The standard analyzer is too aggressive with chemical entities (it strips structural annotations, for one * thing), and the whitespace analyzer doesn't do any case normalization or stop word elimination. This custom * analyzer appears to treat chemical entities better than the standard analyzer without admitting too much * cruft to the index. */ Analyzer analyzer = CustomAnalyzer.builder().withTokenizer("whitespace").addTokenFilter("lowercase") .addTokenFilter("stop").build(); IndexWriterConfig writerConfig = new IndexWriterConfig(analyzer); writerConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); writerConfig.setRAMBufferSizeMB(1 << 10); IndexWriter indexWriter = new IndexWriter(indexDir, writerConfig); String inputFileOrDir = cmdLine.getOptionValue("input"); File splitFileOrDir = new File(inputFileOrDir); if (!(splitFileOrDir.exists())) { LOGGER.error("Unable to find directory at " + inputFileOrDir); System.exit(1); } DocumentIndexer indexer = new DocumentIndexer(indexWriter); PatentCorpusReader corpusReader = new PatentCorpusReader(indexer, splitFileOrDir); corpusReader.readPatentCorpus(); indexer.commitAndClose(); }
From source file:com.bcmcgroup.flare.client.PublisherOutbox11.java
public static void main(String[] args) { if (args.length != 1) { usage();//from w w w . j ava 2 s . co m } if (args[0].equals("-h") || args[0].equals("--help") || args[0].equals("?") || args[0].equals("help")) { usage(); } File file = new File(args[0]); if (file.isDirectory() && file.exists()) { new PublisherOutbox11(file); } }
From source file:com.bcmcgroup.flare.client.PublisherOutbox10.java
public static void main(String[] args) { if (args.length != 1) { usage();//from w ww .java2s . c o m } if (args[0].equals("-h") || args[0].equals("--help") || args[0].equals("?") || args[0].equals("help")) { usage(); } File file = new File(args[0]); if (file.isDirectory() && file.exists()) { new PublisherOutbox10(file); } }
From source file:Main.java
public static void main(String[] args) throws Exception { DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); dbf.setValidating(false);/*from w ww .j a v a2s. c o m*/ DocumentBuilder db = dbf.newDocumentBuilder(); Document doc = db.parse(new FileInputStream(new File("input.xml"))); File OutputDOM = new File("out.txt"); FileOutputStream fostream = new FileOutputStream(OutputDOM); OutputStreamWriter oswriter = new OutputStreamWriter(fostream); BufferedWriter bwriter = new BufferedWriter(oswriter); if (!OutputDOM.exists()) { OutputDOM.createNewFile(); } visitRecursively(doc, bwriter); bwriter.close(); oswriter.close(); fostream.close(); }
From source file:net.itransformers.idiscover.v2.core.Main.java
public static void main(String[] args) throws MalformedURLException { logger.debug("iDiscover v2. gearing up"); Map<String, String> params = CmdLineParser.parseCmdLine(args); // String connectionDetailsFileName = params.get("-f"); // if (connectionDetailsFileName == null) { // printUsage("fileName"); return; // }// w w w .j a va 2 s .com String depthCmdArg = params.get("-d"); // if (depthCmdArg == null) { // printUsage("depth"); return; // } String projectPath = params.get("-p"); if (projectPath == null) { File cwd = new File("."); System.out.println("Project path is not specified. Will use current dir: " + cwd.getAbsolutePath()); projectPath = cwd.getAbsolutePath(); } File workingDir = new File(projectPath); if (!workingDir.exists()) { System.out.println("Invalid project path!"); return; } System.out.println("Loading beans!!"); File conDetails = new File(projectPath, "iDiscover/conf/txt/connection-details.txt"); File generic = new File(projectPath, "iDiscover/conf/xml/generic.xml"); String genericContextPath = generic.toURI().toURL().toString(); File snmpDiscovery = new File(projectPath, "iDiscover/conf/xml/snmpNetworkDiscovery.xml"); String snmpDiscoveryContextPath = snmpDiscovery.toURI().toURL().toString(); File connectionsDetails = new File(projectPath, "iDiscover/conf/xml/connectionsDetails.xml"); String connectionsDetailsContextPath = connectionsDetails.toURI().toURL().toString(); DefaultListableBeanFactory beanFactory = new DefaultListableBeanFactory(); BeanDefinition beanDefinition = BeanDefinitionBuilder.rootBeanDefinition(String.class) .addConstructorArgValue(projectPath).getBeanDefinition(); String labelDirName = autolabel(projectPath); BeanDefinition beanDefinition2 = BeanDefinitionBuilder.rootBeanDefinition(String.class) .addConstructorArgValue(labelDirName).getBeanDefinition(); beanFactory.registerBeanDefinition("projectPath", beanDefinition); beanFactory.registerBeanDefinition("labelDirName", beanDefinition2); GenericApplicationContext cmdArgCxt = new GenericApplicationContext(beanFactory); // Must call refresh to initialize context cmdArgCxt.refresh(); String[] paths = new String[] { genericContextPath, snmpDiscoveryContextPath, connectionsDetailsContextPath }; // ,project.getAbsolutePath()+project.getAbsolutePath()+File.separator+"iDiscover/conf/xml/snmpNetworkDiscovery.xml", project.getAbsolutePath()+File.separator+"iDiscover/src/main/resources/connectionsDetails.xml" FileSystemXmlApplicationContext applicationContext = new FileSystemXmlApplicationContext(paths, cmdArgCxt); // ClassPathXmlApplicationContext applicationContext = new ClassPathXmlApplicationContext(workingDir+File.separator+"iDiscover/conf/xml/generic.xml",workingDir+File.separator+"/iDiscover/conf/xml/snmpNetworkDiscovery.xml","connectionsDetails.xml"); // NetworkDiscoverer discoverer = fileApplicationContext.getBean("bgpPeeringMapDiscovery", NetworkDiscoverer.class); //NetworkDiscoverer discoverer = fileApplicationContext.getBean("floodLightNodeDiscoverer", NetworkDiscoverer.class); NetworkDiscoverer discoverer = applicationContext.getBean("snmpDiscovery", NetworkDiscoverer.class); LinkedHashMap<String, ConnectionDetails> connectionList = (LinkedHashMap) applicationContext .getBean("connectionList", conDetails); int depth = (Integer) applicationContext.getBean("discoveryDepth", depthCmdArg == null ? "-1" : depthCmdArg); NetworkDiscoveryResult result = discoverer .discoverNetwork(new ArrayList<ConnectionDetails>(connectionList.values()), depth); if (result != null) { for (String s : result.getNodes().keySet()) { System.out.println("\nNode: " + s); } } // }
From source file:com.linkedin.pinot.core.segment.index.converter.SegmentV1V2ToV3FormatConverter.java
public static void main(String[] args) throws Exception { if (args.length < 1) { System.err.println("Usage: $0 <table directory with segments>"); System.exit(1);/*w w w. ja va 2s . c o m*/ } File tableDirectory = new File(args[0]); Preconditions.checkState(tableDirectory.exists(), "Directory: {} does not exist", tableDirectory); Preconditions.checkState(tableDirectory.isDirectory(), "Path: {} is not a directory", tableDirectory); File[] files = tableDirectory.listFiles(); SegmentFormatConverter converter = new SegmentV1V2ToV3FormatConverter(); for (File file : files) { if (!file.isDirectory()) { System.out.println("Path: " + file + " is not a directory. Skipping..."); continue; } long startTimeNano = System.nanoTime(); converter.convert(file); long endTimeNano = System.nanoTime(); long latency = (endTimeNano - startTimeNano) / (1000 * 1000); System.out.println("Converting segment: " + file + " took " + latency + " milliseconds"); } }
From source file:cc.twittertools.search.local.SearchStatuses.java
@SuppressWarnings("static-access") public static void main(String[] args) throws Exception { Options options = new Options(); options.addOption(/*w w w . j a v a 2s.co m*/ OptionBuilder.withArgName("path").hasArg().withDescription("index location").create(INDEX_OPTION)); options.addOption( OptionBuilder.withArgName("string").hasArg().withDescription("query id").create(QID_OPTION)); options.addOption( OptionBuilder.withArgName("string").hasArg().withDescription("query text").create(QUERY_OPTION)); options.addOption( OptionBuilder.withArgName("string").hasArg().withDescription("runtag").create(RUNTAG_OPTION)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("maxid").create(MAX_ID_OPTION)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of results to return") .create(NUM_RESULTS_OPTION)); options.addOption(OptionBuilder.withArgName("similarity").hasArg() .withDescription("similarity to use (BM25, LM)").create(SIMILARITY_OPTION)); options.addOption(new Option(VERBOSE_OPTION, "print out complete document")); CommandLine cmdline = null; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); System.exit(-1); } if (!cmdline.hasOption(QUERY_OPTION) || !cmdline.hasOption(INDEX_OPTION)) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(SearchStatuses.class.getName(), options); System.exit(-1); } File indexLocation = new File(cmdline.getOptionValue(INDEX_OPTION)); if (!indexLocation.exists()) { System.err.println("Error: " + indexLocation + " does not exist!"); System.exit(-1); } String qid = cmdline.hasOption(QID_OPTION) ? cmdline.getOptionValue(QID_OPTION) : DEFAULT_QID; String queryText = cmdline.hasOption(QUERY_OPTION) ? cmdline.getOptionValue(QUERY_OPTION) : DEFAULT_Q; String runtag = cmdline.hasOption(RUNTAG_OPTION) ? cmdline.getOptionValue(RUNTAG_OPTION) : DEFAULT_RUNTAG; long maxId = cmdline.hasOption(MAX_ID_OPTION) ? Long.parseLong(cmdline.getOptionValue(MAX_ID_OPTION)) : DEFAULT_MAX_ID; int numResults = cmdline.hasOption(NUM_RESULTS_OPTION) ? Integer.parseInt(cmdline.getOptionValue(NUM_RESULTS_OPTION)) : DEFAULT_NUM_RESULTS; boolean verbose = cmdline.hasOption(VERBOSE_OPTION); String similarity = "LM"; if (cmdline.hasOption(SIMILARITY_OPTION)) { similarity = cmdline.getOptionValue(SIMILARITY_OPTION); } PrintStream out = new PrintStream(System.out, true, "UTF-8"); IndexReader reader = DirectoryReader.open(FSDirectory.open(indexLocation)); IndexSearcher searcher = new IndexSearcher(reader); if (similarity.equalsIgnoreCase("BM25")) { searcher.setSimilarity(new BM25Similarity()); } else if (similarity.equalsIgnoreCase("LM")) { searcher.setSimilarity(new LMDirichletSimilarity(2500.0f)); } QueryParser p = new QueryParser(Version.LUCENE_43, IndexStatuses.StatusField.TEXT.name, IndexStatuses.ANALYZER); Query query = p.parse(queryText); Filter filter = NumericRangeFilter.newLongRange(StatusField.ID.name, 0L, maxId, true, true); TopDocs rs = searcher.search(query, filter, numResults); int i = 1; for (ScoreDoc scoreDoc : rs.scoreDocs) { Document hit = searcher.doc(scoreDoc.doc); out.println(String.format("%s Q0 %s %d %f %s", qid, hit.getField(StatusField.ID.name).numericValue(), i, scoreDoc.score, runtag)); if (verbose) { out.println("# " + hit.toString().replaceAll("[\\n\\r]+", " ")); } i++; } reader.close(); out.close(); }
From source file:com.athena.peacock.agent.Starter.java
/** * <pre>//from ww w. j a v a 2 s . c om * * </pre> * @param args */ @SuppressWarnings("resource") public static void main(String[] args) { int rand = (int) (Math.random() * 100) % 50; System.setProperty("random.seconds", Integer.toString(rand)); String configFile = null; try { configFile = PropertyUtil.getProperty(PeacockConstant.CONFIG_FILE_KEY); } catch (Exception e) { // nothing to do. } finally { if (StringUtils.isEmpty(configFile)) { configFile = "/peacock/agent/config/agent.conf"; } } /** * ${peacock.agent.config.file.name} ?? load ? ?? ? ? ? . */ String errorMsg = "\n\"" + configFile + "\" file does not exist or cannot read.\n" + "Please check \"" + configFile + "\" file exists and can read."; Assert.isTrue(AgentConfigUtil.exception == null, errorMsg); Assert.notNull(AgentConfigUtil.getConfig(PeacockConstant.SERVER_IP), "ServerIP cannot be empty."); Assert.notNull(AgentConfigUtil.getConfig(PeacockConstant.SERVER_PORT), "ServerPort cannot be empty."); /** * Agent ID ?? ${peacock.agent.agent.file.name} ? ?, * ?? ? Agent ID ? ?? . */ String agentFile = null; String agentId = null; try { agentFile = PropertyUtil.getProperty(PeacockConstant.AGENT_ID_FILE_KEY); } catch (Exception e) { // nothing to do. } finally { if (StringUtils.isEmpty(agentFile)) { agentFile = "/peacock/agent/.agent"; } } File file = new File(agentFile); boolean isNew = false; if (file.exists()) { try { agentId = IOUtils.toString(file.toURI()); // ? ? agent ID agent ID? ? 36? ? ?. if (StringUtils.isEmpty(agentId) || agentId.length() != 36) { throw new IOException(); } } catch (IOException e) { logger.error(agentFile + " file cannot read or saved invalid agent ID.", e); agentId = PeacockAgentIDGenerator.generateId(); isNew = true; } } else { agentId = PeacockAgentIDGenerator.generateId(); isNew = true; } if (isNew) { logger.info("New Agent-ID({}) be generated.", agentId); try { file.setWritable(true); OutputStreamWriter output = new OutputStreamWriter(new FileOutputStream(file)); output.write(agentId); file.setReadOnly(); IOUtils.closeQuietly(output); } catch (UnsupportedEncodingException e) { logger.error("UnsupportedEncodingException has occurred : ", e); } catch (FileNotFoundException e) { logger.error("FileNotFoundException has occurred : ", e); } catch (IOException e) { logger.error("IOException has occurred : ", e); } } // Spring Application Context Loading logger.debug("Starting application context..."); AbstractApplicationContext applicationContext = new ClassPathXmlApplicationContext( "classpath:spring/context-*.xml"); applicationContext.registerShutdownHook(); }
From source file:com.ctriposs.rest4j.tools.data.FilterSchemaGenerator.java
public static void main(String[] args) { final CommandLineParser parser = new GnuParser(); CommandLine cl = null;//from w w w. j ava 2 s . co m try { cl = parser.parse(_options, args); } catch (ParseException e) { _log.error("Invalid arguments: " + e.getMessage()); reportInvalidArguments(); } final String[] directoryArgs = cl.getArgs(); if (directoryArgs.length != 2) { reportInvalidArguments(); } final File sourceDirectory = new File(directoryArgs[0]); if (!sourceDirectory.exists()) { _log.error(sourceDirectory.getPath() + " does not exist"); System.exit(1); } if (!sourceDirectory.isDirectory()) { _log.error(sourceDirectory.getPath() + " is not a directory"); System.exit(1); } final URI sourceDirectoryURI = sourceDirectory.toURI(); final File outputDirectory = new File(directoryArgs[1]); if (outputDirectory.exists() && !sourceDirectory.isDirectory()) { _log.error(outputDirectory.getPath() + " is not a directory"); System.exit(1); } final boolean isAvroMode = cl.hasOption('a'); final String predicateExpression = cl.getOptionValue('e'); final Predicate predicate = PredicateExpressionParser.parse(predicateExpression); final Collection<File> sourceFiles = FileUtil.listFiles(sourceDirectory, null); int exitCode = 0; for (File sourceFile : sourceFiles) { try { final ValidationOptions val = new ValidationOptions(); val.setAvroUnionMode(isAvroMode); final SchemaParser schemaParser = new SchemaParser(); schemaParser.setValidationOptions(val); schemaParser.parse(new FileInputStream(sourceFile)); if (schemaParser.hasError()) { _log.error("Error parsing " + sourceFile.getPath() + ": " + schemaParser.errorMessageBuilder().toString()); exitCode = 1; continue; } final DataSchema originalSchema = schemaParser.topLevelDataSchemas().get(0); if (!(originalSchema instanceof NamedDataSchema)) { _log.error(sourceFile.getPath() + " does not contain valid NamedDataSchema"); exitCode = 1; continue; } final SchemaParser filterParser = new SchemaParser(); filterParser.setValidationOptions(val); final NamedDataSchema filteredSchema = Filters.removeByPredicate((NamedDataSchema) originalSchema, predicate, filterParser); if (filterParser.hasError()) { _log.error("Error applying predicate: " + filterParser.errorMessageBuilder().toString()); exitCode = 1; continue; } final String relativePath = sourceDirectoryURI.relativize(sourceFile.toURI()).getPath(); final String outputFilePath = outputDirectory.getPath() + File.separator + relativePath; final File outputFile = new File(outputFilePath); final File outputFileParent = outputFile.getParentFile(); outputFileParent.mkdirs(); if (!outputFileParent.exists()) { _log.error("Unable to write filtered schema to " + outputFileParent.getPath()); exitCode = 1; continue; } FileOutputStream fout = new FileOutputStream(outputFile); fout.write(filteredSchema.toString().getBytes(RestConstants.DEFAULT_CHARSET)); fout.close(); } catch (IOException e) { _log.error(e.getMessage()); exitCode = 1; } } System.exit(exitCode); }
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();//from w w w .j av a 2 s .com } // 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); } }