List of usage examples for org.apache.commons.io FileUtils readLines
public static List readLines(File file, String encoding) throws IOException
From source file:edu.ku.brc.specify.toycode.ResFileCompare.java
@SuppressWarnings("unchecked") public void fixPropertiesFiles(final String baseFileName, final String lang, final boolean doBranch) { System.out.println("-------------------- " + baseFileName + " --------------------"); File engFile;//www .java 2 s. co m File lngFile; String engName = String.format("src/%s_en.properties", baseFileName); String langName = String.format("src/%s_%s.properties", baseFileName, lang); if (doBranch) { engFile = new File( String.format("/home/rods/workspace/Specify_6202SF/src/%s_en.properties", baseFileName)); lngFile = new File( String.format("/home/rods/workspace/Specify_6202SF/src/%s_%s.properties", baseFileName, lang)); } else { engFile = new File(engName); lngFile = new File(langName); } try { List<String> engList = (List<String>) FileUtils.readLines(engFile, "UTF8"); List<String> lngListTmp = (List<String>) FileUtils.readLines(lngFile, "UTF8"); int lineCnt = -1; HashMap<String, String> transHash = new HashMap<String, String>(); for (String line : lngListTmp) { lineCnt++; if (line.startsWith("#") || StringUtils.deleteWhitespace(line).length() < 3 || line.indexOf('=') == -1) { continue; } String[] toks = StringUtils.split(line, '='); if (toks.length > 1) { if (toks.length == 2) { transHash.put(toks[0], toks[1]); } else { StringBuilder sb = new StringBuilder(); for (int i = 1; i < toks.length; i++) { sb.append(String.format("%s=", toks[i])); } sb.setLength(sb.length() - 1); // chomp extra '=' transHash.put(toks[0], sb.toString()); } } else { log.error("Skipping:[" + line + "] Line:" + lineCnt); } } log.info(String.format("Lines Eng: %d; Terms Hash size: %s: %d", engList.size(), lang, transHash.size())); File dir = new File("translations"); if (!dir.exists()) { if (!dir.mkdir()) { log.error("Unable to create directory[" + dir.getAbsolutePath() + "]"); return; } } File transFile = new File(dir.getPath() + File.separator + langName.substring(4)); PrintWriter transFileOutput = new PrintWriter(transFile, "UTF8"); for (String line : engList) { if (line.startsWith("#") || StringUtils.deleteWhitespace(line).length() < 3 || line.indexOf('=') == -1) { transFileOutput.println(line); continue; } boolean doMove = true; String[] toks = StringUtils.split(line, '='); if (toks.length > 1) { String key = null; String value = null; if (toks.length == 2) { key = toks[0]; value = toks[1]; } else { key = toks[0]; StringBuilder sb = new StringBuilder(); for (int i = 1; i < toks.length; i++) { sb.append(String.format("%s=", toks[i])); } sb.setLength(sb.length() - 1); // chomp extra '=' value = sb.toString(); } if (key != null) { String text = transHash.get(key); transFileOutput.println(String.format("%s=%s", key, text != null ? text : value)); if (text == null) { log.info("Adding new term: " + key); } doMove = false; } else { log.info("Adding new term: " + key); } } if (doMove) { transFileOutput.println(line); } } transFileOutput.flush(); transFileOutput.close(); log.info(String.format("Write file: %s", transFile.getPath())); } catch (IOException e) { e.printStackTrace(); } }
From source file:edu.cuhk.hccl.hadoop.YelpMapper.java
private void readItemSet(Path filePath, String category) { if (itemSet.isEmpty()) { try {//from w w w. j a va 2 s . com List<String> lines = FileUtils.readLines(new File(filePath.toString()), "UTF-8"); for (String line : lines) { Business business = gson.fromJson(line, Business.class); boolean isIn = false; for (String cate : business.categories) { if (category.equals(cate.toLowerCase())) { isIn = true; break; } } if (isIn) { if (!itemSet.contains(business.business_id)) { itemSet.add(business.business_id); } } } } catch (IOException e) { e.printStackTrace(); } } }
From source file:de.tudarmstadt.ukp.csniper.resbuild.stuff.BncLocalCorpusBuilder.java
private static List<String> read(String aFile, String aPatternPrefix) throws IOException { List<String> patterns = new ArrayList<String>(); for (String s : FileUtils.readLines(new File(aFile), "UTF-8")) { patterns.add(aPatternPrefix + s); }//from w w w . j a v a 2 s. c o m return patterns; }
From source file:com.bluexml.tools.miscellaneous.Translate.java
public static void writeBackValues(File values, File propertiesFile) throws IOException { List<String> readLines = FileUtils.readLines(values, "UTF-8"); Properties props = new Properties(); TreeMap<String, String> propsMap = loadProperties(propertiesFile); Set<String> keySet = propsMap.keySet(); int index = 0; for (String key : keySet) { String value = readLines.get(index); System.out.println("before trans :" + value); System.out.println("after trans :" + value); System.out.println();//from www . j a v a 2 s. c o m props.setProperty(key, value); index++; } FileOutputStream out = new FileOutputStream(propertiesFile); props.store(out, null); out.close(); }
From source file:core.test.server.mock.util.PersonNameUtil.java
/** * read last names from file and populate array * @throws IOException //from w w w .ja v a 2s .com */ private void initializeLastNames() throws IOException { URL url = getClass().getClassLoader().getResource("people-names/last-names.txt"); File file = new File(url.getFile()); lastNames = FileUtils.readLines(file, "UTF-8"); }
From source file:com.xiaomi.linden.server.TestLindenServer.java
public static void index() throws IOException { String dataFile = TestLindenServer.class.getClassLoader().getResource(INDEX_FILE).getFile(); List<String> lines = FileUtils.readLines(new File(dataFile), Charset.forName("UTF-8")); for (String line : lines) { JSONObject indexRequestJSON = new JSONObject(); indexRequestJSON.put("type", "index"); JSONObject json = JSONObject.parseObject(line); String sName = json.getString("sName"); // sNameStored has same value with sName, but different field type json.put("sNameStored", sName); indexRequestJSON.put("content", json); try {/*from w ww.j a v a 2s . co m*/ client1.index(indexRequestJSON.toJSONString()); } catch (Exception e) { e.printStackTrace(); } } JSONObject command = new JSONObject(); command.put("type", "MERGE_INDEX"); JSONObject options = new JSONObject(); options.put("count", 1); command.put("options", options); try { client1.executeCommand(command.toString()); } catch (Exception e) { e.printStackTrace(); } }
From source file:eu.annocultor.utils.HierarchyTracingFilter.java
public void doTracing(String fileWithTopConcepts, String fileWithSelection, String... fileWithRdf) throws Exception { Repository rdf = Helper.createLocalRepository(); File[] filesToLoad = new File[fileWithRdf.length]; for (int i = 0; i < fileWithRdf.length; i++) { filesToLoad[i] = new File(fileWithRdf[i]); }/*w w w . j a va 2s . com*/ Helper.importRDFXMLFile(rdf, Namespaces.ANNOCULTOR_CONVERTER.getUri(), filesToLoad); RepositoryConnection connection = rdf.getConnection(); ValueFactory factory = rdf.getValueFactory(); System.out.println("Loaded " + connection.size() + " statements"); List topConceptsStr = FileUtils.readLines(new File(fileWithTopConcepts), "UTF-8"); List<StringInStack> top = new ArrayList<StringInStack>(); for (Object object : topConceptsStr) { top.add(new StringInStack(object.toString(), 0)); } Set<String> passedUrls = traceBroaderDepthFirst(connection, factory, top); // save List<String> passedSorted = new LinkedList<String>(); passedSorted.addAll(passedUrls); Collections.sort(passedSorted); System.out.println("Saving " + passedSorted.size() + " terms"); saveListOfUrls(fileWithSelection, passedUrls, passedSorted); }
From source file:com.textocat.textokit.commons.cpe.XmiFileListReader.java
@Override protected Iterable<Resource> getResources(UimaContext ctx) throws IOException { String baseDirPath = this.baseDirPath; baseDirPath = FilenameUtils.normalize(baseDirPath); // ensure that baseDirPath ends with slash for proper relative path handling if (!baseDirPath.endsWith(File.separator)) { baseDirPath += File.separator; }// www . jav a 2s .c o m baseDir = new FileSystemResource(baseDirPath); if (!baseDir.exists()) { throw new IllegalStateException(String.format("Directory %s does not exist", baseDir)); } List<String> lines = FileUtils.readLines(listFile, "utf-8"); resources = Lists.transform(Lists.newArrayList(Iterables.filter(lines, notBlankString)), relativeFileResourceFunc); return resources; }
From source file:jp.igapyon.selecrawler.SeleCrawlerWebContentAnalyzer.java
public void process(final SeleCrawlerSettings settings) throws IOException { this.settings = settings; System.err.println("[jp.igapyon.selecrawler] Analyze web contents."); final List<File> files = new SimpleDirParser() { public boolean isProcessTarget(final File file) { if (file.isDirectory()) { return true; }// w w w .ja v a 2 s. c om if (file.getName().endsWith(SeleCrawlerConstants.EXT_SC_URL)) { return true; } return false; } }.listFiles(new File(settings.getPathTargetDir()), true); System.err.println("[selecrawler] create/update '*" + SeleCrawlerConstants.EXT_SC_HEAD + "' and '*" + SeleCrawlerConstants.EXT_SC_ANCHOR + "' files."); for (File fileMeta : files) { if (fileMeta.isDirectory()) { continue; } final List<String> metaUrlList = FileUtils.readLines(fileMeta, "UTF-8"); final File file = new File(fileMeta.getParentFile(), fileMeta.getName().substring(0, fileMeta.getName().length() - SeleCrawlerConstants.EXT_SC_URL.length())); processFile(file, metaUrlList.get(1)); } }
From source file:jp.igapyon.selecrawler.SeleCrawlerWebContentGetter.java
public void processDevice(final String deviceName) throws IOException { System.err.println("[selecrawler] Launch Chrome. UA:" + deviceName); final SimpleChromeWrapper chrome = new SimpleChromeWrapper(settings.getPathChromeDriver(), deviceName, settings.getPathUserDataDir()); chrome.open();/*from w w w . j a va2s . co m*/ int getcounter = 0; System.err.println( "[selecrawler] Load url list file: " + new File(settings.getPathUrllisttTxt()).getCanonicalPath()); System.err.println("[selecrawler] Target dir: " + new File(settings.getPathTargetDir()).getCanonicalPath()); final List<String> urls = FileUtils.readLines(new File(settings.getPathUrllisttTxt()), "UTF-8"); for (String urlLookup : urls) { if (getcounter >= 10) { // refresh chrome instance getcounter = 0; chrome.close(); chrome.open(); } final File outputFile = getFileHtml(deviceName, urlLookup); if (outputFile.getParentFile().exists() == false) { outputFile.getParentFile().mkdirs(); } final File outputMetaFile = new File(outputFile.getParentFile(), outputFile.getName() + SeleCrawlerConstants.EXT_SC_URL); final File outputLogFile = new File(outputFile.getParentFile(), outputFile.getName() + SeleCrawlerConstants.EXT_SC_LOG); if (outputMetaFile.exists()) { if (settings.isDebug()) { System.err.println("[selecrawler] skip(cache): " + urlLookup); } continue; } System.err.println("[selecrawler] fetch web: " + urlLookup); chrome.getDriver().get(urlLookup); { // check wait settings. final String urlActual = chrome.getDriver().getCurrentUrl(); for (String regex : settings.getUrllistWaitRegex()) { final Pattern pat = Pattern.compile(regex); final Matcher mat = pat.matcher(urlActual); if (mat.find()) { try { System.out.println("waiting browser operation"); Thread.sleep(10000); } catch (InterruptedException e) { e.printStackTrace(); } } } } final String contents = chrome.getDriver().getPageSource(); FileUtils.writeStringToFile(outputFile, contents, "UTF-8"); FileUtils.writeLines(outputLogFile, "UTF-8", chrome.getLogEntries()); // write meta finally. { final List<String> metaUrlList = new ArrayList<String>(); metaUrlList.add(urlLookup); metaUrlList.add(chrome.getDriver().getCurrentUrl()); FileUtils.writeLines(outputMetaFile, "UTF-8", metaUrlList); } getcounter++; try { Thread.sleep(1000); } catch (InterruptedException e) { e.printStackTrace(); } } chrome.close(); }