List of usage examples for org.apache.commons.csv CSVParser parse
public static CSVParser parse(final URL url, final Charset charset, final CSVFormat format) throws IOException
From source file:de.tudarmstadt.ukp.experiments.dip.wp1.documents.Step1PrepareContainers.java
public static void main(String[] args) throws IOException { // queries with narratives in CSV File queries = new File(args[0]); File relevantInformationExamplesFile = new File(args[1]); Map<Integer, Map<Integer, List<String>>> relevantInformationMap = parseRelevantInformationFile( relevantInformationExamplesFile); // output dir File outputDir = new File(args[2]); if (!outputDir.exists()) { outputDir.mkdirs();/*from www . jav a 2 s.c o m*/ } // iterate over queries CSVParser csvParser = CSVParser.parse(queries, Charset.forName("utf-8"), CSVFormat.DEFAULT); for (CSVRecord record : csvParser) { // create new container, fill, and store QueryResultContainer container = new QueryResultContainer(); container.qID = record.get(0); container.query = record.get(1); // Fill some dummy text first container.relevantInformationExamples.addAll(Collections.singletonList("ERROR. Information missing.")); container.irrelevantInformationExamples .addAll(Collections.singletonList("ERROR. Information missing.")); // and now fill it with existing information if available Integer queryID = Integer.valueOf(container.qID); if (relevantInformationMap.containsKey(queryID)) { if (relevantInformationMap.get(queryID).containsKey(0)) { container.irrelevantInformationExamples = new ArrayList<>( relevantInformationMap.get(queryID).get(0)); } if (relevantInformationMap.get(queryID).containsKey(1)) { container.relevantInformationExamples = new ArrayList<>( relevantInformationMap.get(queryID).get(1)); } } File outputFile = new File(outputDir, container.qID + ".xml"); FileUtils.writeStringToFile(outputFile, container.toXML()); System.out.println("Finished " + outputFile); } }
From source file:ch.bfh.unicert.certimport.Main.java
public static void main(String[] args) throws IOException, InvalidNameException { logger.info("File read"); File f = new File(csvPath); CSVParser parser = CSVParser.parse(f, Charset.forName("UTF-8"), CSVFormat.DEFAULT); for (CSVRecord record : parser) { createCertificate(record);//from w w w .j av a 2 s . c o m } }
From source file:io.mindmaps.migration.csv.Main.java
public static void main(String[] args) { String csvFileName = null;//w w w . jav a2 s . com String csvEntityType = null; String engineURL = null; String graphName = null; for (int i = 0; i < args.length; i++) { if ("-file".equals(args[i])) csvFileName = args[++i]; else if ("-graph".equals(args[i])) graphName = args[++i]; else if ("-engine".equals(args[i])) engineURL = args[++i]; else if ("-as".equals(args[i])) { csvEntityType = args[++i]; } else if ("csv".equals(args[0])) { continue; } else die("Unknown option " + args[i]); } if (csvFileName == null) { die("Please specify CSV file using the -csv option"); } File csvFile = new File(csvFileName); if (!csvFile.exists()) { die("Cannot find file: " + csvFileName); } if (graphName == null) { die("Please provide the name of the graph using -graph"); } if (csvEntityType == null) { csvEntityType = csvFile.getName().replaceAll("[^A-Za-z0-9]", "_"); } System.out.println("Migrating " + csvFileName + " using MM Engine " + (engineURL == null ? "local" : engineURL) + " into graph " + graphName); // perform migration CSVSchemaMigrator schemaMigrator = new CSVSchemaMigrator(); CSVDataMigrator dataMigrator = new CSVDataMigrator(); // try { MindmapsGraph graph = engineURL == null ? MindmapsClient.getGraph(graphName) : MindmapsClient.getGraph(graphName, engineURL); Loader loader = engineURL == null ? new BlockingLoader(graphName) : new DistributedLoader(graphName, Lists.newArrayList(engineURL)); CSVParser csvParser = CSVParser.parse(csvFile.toURI().toURL(), StandardCharsets.UTF_8, CSVFormat.DEFAULT.withHeader()); schemaMigrator.graph(graph).configure(csvEntityType, csvParser).migrate(loader); System.out.println("Schema migration successful"); dataMigrator.graph(graph).configure(csvEntityType, csvParser).migrate(loader); System.out.println("DataType migration successful"); } catch (Throwable throwable) { throwable.printStackTrace(System.err); } System.exit(0); }
From source file:edu.harvard.liblab.ecru.LoadCsvData.java
/** * @param args/* ww w .ja va2s. co m*/ */ public static void main(String[] args) { if (args.length > 7 | args.length == 0 || !args[0].equals("-f") || !args[2].equals("-u") || !args[4].equals("-i")) { System.err.println(USAGE); System.exit(1); } String filename = args[1].trim(); url = args[3].trim(); needsPrefix = !args[5].equals("unique"); isVerbose = (args.length == 7 && args[6].equals("-v")); System.out.println("Loading data from " + filename + " " + (needsPrefix ? "IDs will be prefixed " : " ")); long start = System.currentTimeMillis(); boolean isReading = false; CSVPrinter printer = null; CSVFormat format = CSVFormat.EXCEL.withHeader().withDelimiter(',').withAllowMissingColumnNames(true); CSVParser parser; try { if (isVerbose) { printer = new CSVPrinter(System.err, format.withDelimiter('|')); } parser = CSVParser.parse(new File(filename), Charset.forName("UTF-8"), format); solrSrvr = SingletonSolrServer.getSolrServer(url); for (CSVRecord record : parser) { numRecs++; HashMap<String, String> recMap = new HashMap<String, String>(); for (String field : FIELDS) { String value = null; try { value = record.get(field); } catch (IllegalArgumentException e) { if (e.getMessage().indexOf("expected one of") == -1) { e.printStackTrace(); System.exit(1); } } value = value == null ? "" : value.trim(); recMap.put(field, value); } String id = recMap.get("ID"); if (id.isEmpty()) { if (isVerbose) { System.err.println("Record missing ID: "); printer.printRecord(record); } } else { String type = recMap.get("Type"); SolrDocument sdoc = getDocFromSolr(recMap.get("ID")); try { if (type.toLowerCase().equals("course")) { processCourse(recMap, sdoc); isReading = false; } else { if (!isReading) { addUpdateCommit(); // just in case the preceeding course(s) are related } processReading(recMap, sdoc); isReading = true; } } catch (Exception e) { if (isVerbose) { System.err.println("Record # " + numRecs + " not used:\n\t" + e.getMessage()); } errRecs++; } } if (beans.size() > 20) { addUpdateCommit(); } } parser.close(); if (beans.size() > 0 || docUpdates.size() > 0) { addUpdateCommit(); } } catch (FileNotFoundException e) { System.err.println(filename + " not found"); System.exit(1); } catch (Exception e) { e.printStackTrace(); System.exit(1); } long end = System.currentTimeMillis(); long courseTime = (end - start) / (long) 1000; try { solrSrvr.optimize(); } catch (SolrServerException e) { e.printStackTrace(); System.exit(1); } catch (IOException e) { e.printStackTrace(); System.exit(1); } System.out.println(numRecs + " records found, of which " + errRecs + " had a problem; time: " + courseTime + " seconds " + ((courseTime > 60) ? ("(" + (courseTime / (long) 60) + " minutes)") : "")); System.exit(0); }
From source file:moacscoper.Parser.java
private List<CSVRecord> parse(String path) throws IOException { return CSVParser.parse(new File(path), StandardCharsets.UTF_8, CSVFormat.TDF).getRecords(); }
From source file:gradingfun.GradeParser.java
public GradeParser(File file) { try {// w w w.j av a 2 s. co m this.parser = CSVParser.parse(file, Charset.defaultCharset(), CSVFormat.RFC4180); } catch (IOException ex) { Logger.getLogger(GradeParser.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:com.univocity.articles.csvcomparison.parser.CommonsCsvParser.java
@Override public void processRows(File input) throws Exception { CSVFormat format = CSVFormat.RFC4180; CSVParser parser = CSVParser.parse(input, getEncoding(), format); for (CSVRecord record : parser) { process(record);/* ww w. j av a 2 s . c om*/ } }
From source file:functions.LoadCSVdata.java
public void LoadFeeDataToJTable(JTable t, String path) { try {//from w ww . j a v a 2 s . c o m file = new File(path); parser = CSVParser.parse(file, Charset.forName("UTF-8"), CSVFormat.DEFAULT); DefaultTableModel model = (DefaultTableModel) t.getModel(); model.setRowCount(0); for (CSVRecord c : parser) { if (c.getRecordNumber() == 1) continue; model.addRow( new Object[] { c.get(datatype.GlobalVariable.TYPE), c.get(datatype.GlobalVariable.AMOUNT), c.get(datatype.GlobalVariable.PAID_BY), c.get(datatype.GlobalVariable.PAYER) }); } } catch (Exception e) { System.out.println(e); } }
From source file:com.univocity.articles.csvcomparison.parser.CommonsCsvParser.java
@Override public List<String[]> parseRows(File input) throws Exception { CSVFormat format = CSVFormat.RFC4180; CSVParser parser = CSVParser.parse(input, getEncoding(), format); List<String[]> rows = new ArrayList<String[]>(); for (CSVRecord record : parser) { String[] row = new String[record.size()]; for (int i = 0; i < row.length; i++) { row[i] = record.get(i);//from w w w.j a v a2 s. co m } rows.add(row); } return rows; }
From source file:com.ibm.g11n.pipeline.example.CSVFilter.java
@Override public LanguageBundle parse(InputStream inStream, FilterOptions options) throws IOException, ResourceFilterException { LanguageBundleBuilder bundleBuilder = new LanguageBundleBuilder(true); CSVParser parser = CSVParser.parse(inStream, StandardCharsets.UTF_8, CSVFormat.RFC4180.withHeader("key", "value").withSkipHeaderRecord(true)); for (CSVRecord record : parser) { String key = record.get(0); String value = record.get(1); bundleBuilder.addResourceString(key, value); }// w w w .j a v a 2 s. c o m return bundleBuilder.build(); }