List of usage examples for org.apache.commons.io FileUtils readLines
public static List readLines(File file) throws IOException
From source file:common.ReverseWordsCount.java
public static void main(String[] args) throws IOException { List<String> readLines = FileUtils.readLines(new File("G:\\\\LTNMT\\LTNMT\\sougou\\sougou2500.txt")); Map<String, Integer> words = new HashMap<>(); for (String line : readLines) { String[] split = line.split(" "); for (String wprd : split) { Integer get = words.get(wprd); if (get == null) { words.put(wprd, 1);/*from w w w . j a v a 2 s. co m*/ } else { words.put(wprd, get + 1); } } } Set<Map.Entry<String, Integer>> entrySet = words.entrySet(); List<Map.Entry<String, Integer>> reverseLists = new ArrayList<>(entrySet); Collections.sort(reverseLists, new Comparator<Map.Entry<String, Integer>>() { @Override public int compare(Map.Entry<String, Integer> o1, Map.Entry<String, Integer> o2) { return o2.getValue().compareTo(o1.getValue()); } }); PrintStream ps = new PrintStream("c:/reverseWords.txt"); for (Map.Entry<String, Integer> teEntry : reverseLists) { ps.println(teEntry.getKey() + " " + teEntry.getValue()); } ps.close(); }
From source file:eu.europeana.datamigration.ese2edm.LogCleaner.java
public static void main(String[] args) { try {//from w ww. ja v a2 s . co m List<String> lines = FileUtils.readLines(new File("/home/gmamakis/test.log")); List<String> newLines = new ArrayList<String>(); for (String line : lines) { if (!line.startsWith("Apr")) { newLines.add(line); } } FileUtils.writeLines(new File("/home/gmamakis/rdfslabel.log"), newLines); } catch (IOException ex) { Logger.getLogger(LogCleaner.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:de.tudarmstadt.ukp.dkpro.keyphrases.wikipediafilter.filter.util.FileFilter.java
public static void main(String[] args) throws IOException { Set<String> articles = new HashSet<String>(); articles.addAll(FileUtils.readLines(new File("target/wikipedia/articles.txt"))); BufferedWriter writer = new BufferedWriter(new FileWriter(new File("target/passwords.txt.filtered"))); for (String line : FileUtils.readLines(new File("target/passwords.txt"))) { if (articles.contains(line.split("\t")[0].toLowerCase())) { writer.write(line);// w w w.ja v a 2s. c o m writer.newLine(); } writer.close(); } }
From source file:edu.illinois.cs.cogcomp.wikifier.utils.freebase.cleanDL.java
public static void main(String[] args) throws IOException { List<String> lines = FileUtils.readLines(new File("/Users/Shyam/mention.eval.dl")); for (String line : lines) { String[] parts = line.split("\\s+"); System.out.println(parts[0] + parts[1] + parts[2]); StringBuilder sb = new StringBuilder(); for (int i = 3; i < parts.length; i++) sb.append(parts[i] + " "); if (mentionFilter(parts)) { System.out.println("removing " + Arrays.asList(parts)); continue; }/*from w w w . j a v a2s . c om*/ if (mentions.containsKey(parts[0])) { mentions.get(parts[0]).add(new DocMention(parts[0], sb.toString(), Integer.parseInt(parts[1]), Integer.parseInt(parts[2]))); } else { mentions.put(parts[0], new ArrayList<DocMention>()); mentions.get(parts[0]).add(new DocMention(parts[0], sb.toString(), Integer.parseInt(parts[1]), Integer.parseInt(parts[2]))); } } for (String doc : mentions.keySet()) { handleDoc(mentions.get(doc)); } outputMentions(); }
From source file:bixo.tools.RunUrlNormalizerTool.java
/** * @param args/*from www .j av a 2 s. co m*/ */ public static void main(String[] args) { String curUrl = null; try { List<String> lines = FileUtils.readLines(new File(args[0])); BaseUrlNormalizer urlNormalizer = new SimpleUrlNormalizer(); for (String url : lines) { curUrl = url; String normalized = urlNormalizer.normalize(curUrl); if (!normalized.equalsIgnoreCase(curUrl)) { System.out.println(curUrl + " ==> " + normalized); } } } catch (Throwable t) { System.err.println("Exception while processing URLs: " + t.getMessage()); System.err.println("Current url: " + curUrl); t.printStackTrace(System.err); System.exit(-1); } }
From source file:jsonparser.ToJSON.java
public static void main(String args[]) throws FileNotFoundException, IOException { String text_file = "C:/Users/Kevin/Documents/NetBeansProjects/JsonParser/src/jsonparser/sample.txt"; File file = new File(text_file); String s1, s2, s3;/*from w w w . j a v a 2s . c om*/ s1 = (String) FileUtils.readLines(file).get(0); String split1[] = s1.split("="); contact_id = split1[1]; s2 = (String) FileUtils.readLines(file).get(1); String split2[] = s2.split("="); confidence_level = Float.valueOf(split2[1]); s3 = (String) FileUtils.readLines(file).get(2); String split3[] = s3.split("="); if (split3[1].equals(" Found")) { is_matched = true; } else { is_matched = false; } System.out.println("Read from text file:"); System.out.println("contact_id =" + contact_id); System.out.println("confidence_level = " + confidence_level); System.out.println("is_matched = " + is_matched); FacialRecognition fr = new FacialRecognition(); fr.setContactID(contact_id); fr.setConfidenceLevel(confidence_level); fr.setIsMatched(is_matched); Gson gson = new GsonBuilder().setPrettyPrinting().create(); //convert java object to JSON format String json = gson.toJson(fr); //write JSON to a file try { //write converted json data to a file named "CountryGSON.json" FileWriter writer = new FileWriter( "C:/Users/Kevin/Documents/NetBeansProjects/JsonParser/src/jsonparser/test.json", true); writer.write("" + json + ",\n"); writer.close(); } catch (IOException e) { e.printStackTrace(); } //eventually need to change to send over back to client-side System.out.println(); System.out.println("Coverting strings into JSON..."); System.out.println(json); }
From source file:com.ifeng.sorter.NginxApp.java
public static void main(String[] args) { String input = "src/test/resources/data/nginx_report.txt"; PrintWriter pw = null;/*from www .ja v a2 s . co m*/ Map<String, List<LogBean>> resultMap = new HashMap<String, List<LogBean>>(); List<String> ips = new ArrayList<String>(); try { List<String> lines = FileUtils.readLines(new File(input)); List<LogBean> items = new ArrayList<LogBean>(); for (String line : lines) { String[] values = line.split("\t"); if (values != null && values.length == 3) {// ip total seria try { String ip = values[0].trim(); String total = values[1].trim(); String seria = values[2].trim(); LogBean bean = new LogBean(ip, Integer.parseInt(total), seria); items.add(bean); } catch (NumberFormatException e) { e.printStackTrace(); } } } Collections.sort(items); for (LogBean bean : items) { String key = bean.getIp(); if (resultMap.containsKey(key)) { resultMap.get(key).add(bean); } else { List<LogBean> keyList = new ArrayList<LogBean>(); keyList.add(bean); resultMap.put(key, keyList); ips.add(key); } } pw = new PrintWriter("src/test/resources/output/result.txt", "UTF-8"); for (String ip : ips) { List<LogBean> list = resultMap.get(ip); for (LogBean bean : list) { pw.append(bean.toString()); pw.println(); } } } catch (IOException e) { e.printStackTrace(); } finally { pw.flush(); pw.close(); } }
From source file:com.l2jfree.tools.ProjectSettingsSynchronizer.java
public static void main(String[] args) throws IOException { final File src = new File(".").getCanonicalFile(); System.out.println("Copying from: " + src); System.out.println();/* w w w . j av a2 s . c o m*/ final List<File> destinations = new ArrayList<File>(); for (File dest : src.getParentFile().listFiles()) { if (dest.isHidden() || !dest.isDirectory()) continue; destinations.add(dest); System.out.println("Copying to: " + dest); } System.out.println(); // .project System.out.println(".project"); System.out.println("================================================================================"); { final List<String> lines = FileUtils.readLines(new File(src, ".project")); for (File dest : destinations) { lines.set(2, lines.get(2).replaceAll(src.getName(), dest.getName())); writeLines(dest, ".project", lines); lines.set(2, lines.get(2).replaceAll(dest.getName(), src.getName())); } } System.out.println(); // .classpath System.out.println(".classpath"); System.out.println("================================================================================"); { final List<String> lines = FileUtils.readLines(new File(src, ".classpath")); for (File dest : destinations) { if (dest.getName().endsWith("-main") || dest.getName().endsWith("-datapack")) { final ArrayList<String> tmp = new ArrayList<String>(); for (String line : lines) if (!line.contains("classpathentry")) tmp.add(line); writeLines(dest, ".classpath", tmp); continue; } writeLines(dest, ".classpath", lines); } } System.out.println(); // .settings System.out.println(".settings"); System.out.println("================================================================================"); for (File settingsFile : new File(src, ".settings").listFiles()) { if (settingsFile.getName().endsWith(".prefs")) { System.out.println(".settings/" + settingsFile.getName()); System.out.println( "--------------------------------------------------------------------------------"); final List<String> lines = FileUtils.readLines(settingsFile); if (lines.get(0).startsWith("#")) lines.remove(0); for (File dest : destinations) { writeLines(new File(dest, ".settings"), settingsFile.getName(), lines); } System.out.println(); } } System.out.println(); }
From source file:edu.bigdata.training.fileformats.compress.SequenceFileWriter.java
public static void main(String[] args) throws IOException { String uri = "output"; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); Path path = new Path(uri); IntWritable key = new IntWritable(); Text value = new Text(); File infile = new File("src/main/resources/input.txt"); SequenceFile.Writer writer = null; try {//from w w w . j a v a 2 s . c o m writer = SequenceFile.createWriter(conf, Writer.file(path), Writer.keyClass(key.getClass()), Writer.valueClass(value.getClass()), Writer.bufferSize(fs.getConf().getInt("io.file.buffer.size", 4096)), Writer.replication(fs.getDefaultReplication()), Writer.blockSize(1073741824), Writer.compression(SequenceFile.CompressionType.BLOCK, new DefaultCodec()), Writer.progressable(null), Writer.metadata(new Metadata())); int ctr = 100; List<String> lines = FileUtils.readLines(infile); for (String line : lines) { key.set(ctr++); value.set(line); if (ctr < 150) { System.out.printf("[%s]\t%s\t%s\n", writer.getLength(), key, value); } writer.append(key, value); } } finally { IOUtils.closeStream(writer); } }
From source file:eu.annocultor.analyzers.SolrPropertyHitsAnalyzer.java
/** * @param args/*from ww w.j a va 2s . co m*/ */ public static void main(String[] args) throws Exception { String solrUrl = args[0]; SolrServer solr = new CommonsHttpSolrServer(solrUrl); String prefixOne = args[1]; String prefixTwo = args[2]; long prefixOneCount = 0; long prefixTwoCount = 0; long totalPassedCount = 0; for (File logLocation : FileUtils.listFiles(new File(args[3]), null, true)) { System.out.println("Parsing " + logLocation); for (String line : FileUtils.readLines(logLocation)) { if (StringUtils.contains(line, "FULL_RESULT_HMTL")) { line = StringUtils.substringAfter(line, "europeana_uri="); String solrDocumentId = StringUtils.substringBefore(line, ","); String query = extractQuery(line); if (StringUtils.startsWith(solrDocumentId, "http://") && isLongEnoughToCount(query)) { SolrQuery solrQuery = new SolrQuery("europeana_uri:\"" + solrDocumentId + "\""); QueryResponse response = solr.query(solrQuery); SolrDocumentList sourceDocs = response.getResults(); if (sourceDocs.isEmpty()) { System.out.println("Could not find object " + solrDocumentId); } else { SolrDocument document = sourceDocs.get(0); if (hasWord(document, prefixOne, query)) { prefixOneCount++; } else { if (hasWord(document, prefixTwo, query)) { prefixTwoCount++; } } } } totalPassedCount++; } } System.out.println(prefixOne + " : " + prefixOneCount + " " + prefixTwo + " : " + prefixTwoCount + " of total passed entries " + totalPassedCount); } }