List of usage examples for org.apache.commons.csv CSVParser CSVParser
public CSVParser(final Reader reader, final CSVFormat format) throws IOException
If you do not read all records from the given reader , you should call #close() on the parser, unless you close the reader .
From source file:de.upb.wdqa.wdvd.labels.CorpusLabelReader.java
/** * Initializes the label reader./*from ww w.j av a2 s . com*/ */ public void startReading() { try { BufferedReader csvReader = new BufferedReader(new InputStreamReader(labelsStream, "UTF-8"), BUFFER_SIZE); csvParser = new CSVParser(csvReader, CSVFormat.RFC4180.withHeader(FILE_HEADER)); iterator = csvParser.iterator(); CSVRecord headerRecord = iterator.next(); for (int i = 0; i < FILE_HEADER.length; i++) { if (!FILE_HEADER[i].equals(headerRecord.get(i))) { throw new IOException("The header of the CSV file is wrong."); } } } catch (IOException e) { logger.error("", e); finishReading(); } }
From source file:com.datascience.hadoop.CsvRecordReader.java
public CsvRecordReader(Reader reader, CSVFormat format, long length, boolean strict) throws IOException { this.length = length; this.strict = strict; parser = new CSVParser(reader, format); iterator = parser.iterator();/*from w w w.j a v a 2 s .c o m*/ if (parser.getHeaderMap() == null) { colLength = null; } else { colLength = parser.getHeaderMap().size(); } }
From source file:edu.emory.mathcs.nlp.zzz.CSVRadiology.java
public void tokenize(String inputFile, int outputStart) throws Exception { CSVParser parser = new CSVParser(IOUtils.createBufferedReader(inputFile), CSVFormat.DEFAULT); String inputPath = FileUtils.getPath(inputFile) + "/"; List<CSVRecord> records = parser.getRecords(); Tokenizer tokenizer = new EnglishTokenizer(); P_BEFORE = new ArrayList<>(); P_AFTER = new ArrayList<>(); for (String s : BEFORE) P_BEFORE.add(new Pair<>(Pattern.compile(s), "\n" + s)); for (String s : AFTER) P_AFTER.add(new Pair<>(Pattern.compile(s), s + "\n")); for (int i = 0; i < records.size(); i++) { PrintStream fout = IOUtils.createBufferedPrintStream(getOuputFilename(inputPath, i + outputStart)); for (List<Token> tokens : tokenizer.segmentize(records.get(i).get(0))) print(fout, tokens);//from ww w .ja v a 2s .co m fout.close(); } parser.close(); }
From source file:com.twentyn.TargetMolecule.java
public static List<TargetMolecule> loadTargets(File inputFile) throws IOException { List<TargetMolecule> results = new ArrayList<>(); try (CSVParser parser = new CSVParser(new FileReader(inputFile), TSV_FORMAT)) { for (CSVRecord record : parser) { results.add(TargetMolecule.fromCSVRecord(record)); }//from ww w . j a v a 2 s . co m } return results; }
From source file:com.act.utils.TSVParser.java
public void parse(InputStream inStream) throws IOException { List<Map<String, String>> results = new ArrayList<>(); try (CSVParser parser = new CSVParser(new InputStreamReader(inStream), TSV_FORMAT)) { headerMap = parser.getHeaderMap(); Iterator<CSVRecord> iter = parser.iterator(); while (iter.hasNext()) { CSVRecord r = iter.next();/*from w w w . j av a 2s.c o m*/ results.add(r.toMap()); } } this.results = results; }
From source file:com.itemanalysis.jmetrik.data.Scorer.java
private void readScoringFile(String fileName) throws IOException { File f = new File(fileName); CSVParser parser = null;// ww w. jav a 2 s .c o m Reader reader = null; GenericItemScoring itemScoring = null; SpecialDataCodes specialCodes = null; String name = ""; String option = ""; int score = 0; try { reader = new InputStreamReader(new BOMInputStream(new FileInputStream(f)), "UTF-8"); parser = new CSVParser(reader, CSVFormat.EXCEL.withHeader()); for (CSVRecord csvRecord : parser) { name = csvRecord.get("name"); option = csvRecord.get("option"); score = Integer.parseInt(csvRecord.get("score")); itemScoring = new GenericItemScoring(name); itemScoring.addCategory(option, score); specialCodes = new SpecialDataCodes(); if (csvRecord.isMapped("missing")) specialCodes.setMissingDataCode(csvRecord.get("missing")); if (csvRecord.isMapped("missing score")) specialCodes.setMissingDataScore(Integer.parseInt(csvRecord.get("missing score"))); if (csvRecord.isMapped("notreached")) specialCodes.setMissingDataCode(csvRecord.get("notreached")); if (csvRecord.isMapped("notreached score")) specialCodes.setMissingDataScore(Integer.parseInt(csvRecord.get("notreached score"))); if (csvRecord.isMapped("omitted")) specialCodes.setMissingDataCode(csvRecord.get("omitted")); if (csvRecord.isMapped("omitted score")) specialCodes.setMissingDataScore(Integer.parseInt(csvRecord.get("omitted score"))); scoring.put(name, itemScoring); } } catch (IOException ex) { throw (ex); } finally { parser.close(); reader.close(); } }
From source file:com.leadscope.commanda.sources.CSVSource.java
@Override public Stream<CSVRecord> stream(InputStream inputStream) { try {/* w w w . j ava 2 s . c om*/ CSVParser parser = new CSVParser(new InputStreamReader(inputStream, charset), format); return StreamSupport.stream(parser.spliterator(), false); } catch (RuntimeException re) { throw re; } catch (Exception e) { throw new RuntimeException(e); } }
From source file:edu.clemson.lph.civet.addons.VspsCviFile.java
private void saveme(Window parent, File fIn) { try {//from w ww . jav a 2s. c o m File fOut = fixCSV(fIn); CSVParser parserIn = new CSVParser(new FileReader(fOut), CSVFormat.EXCEL); parser = new LabeledCSVParser(parserIn); aCols = parser.getNext(); } catch (FileNotFoundException e) { logger.error(e.getMessage() + "\nCould not read file: " + fIn.getName()); } catch (IOException e) { logger.error(e.getMessage() + "\nCould not read file: " + fIn.getName()); } InsertVspsCviThread thread = new InsertVspsCviThread(parent, this); thread.start(); }
From source file:edu.emory.mathcs.nlp.zzz.CSVSentiment.java
public void toTSV(String inputFile) throws Exception { CSVParser parser = new CSVParser(IOUtils.createBufferedReader(inputFile), CSVFormat.DEFAULT); PrintStream fout = IOUtils.createBufferedPrintStream(inputFile + ".tsv"); List<CSVRecord> records = parser.getRecords(); List<Token> tokens;/*ww w . jav a 2 s.co m*/ CSVRecord record; int label; System.out.println(inputFile); for (int i = 0; i < records.size(); i++) { if (i == 0) continue; record = records.get(i); label = toIntLabel(record.get(0)); tokens = tokenizer.tokenize(record.get(6)); fout.println(label + "\t" + Joiner.join(tokens, " ", Token::getWordForm)); } fout.close(); parser.close(); }
From source file:br.edimarmanica.weir2.check.CheckDistanceExpectedMapping.java
private String getMasterRule(Site site, Attribute attribute) { try (Reader in = new FileReader(Paths.PATH_INTRASITE + "/" + site.getPath() + "/result.csv")) { try (CSVParser parser = new CSVParser(in, CSVFormat.EXCEL.withHeader())) { for (CSVRecord record : parser) { if (record.get("ATTRIBUTE").equals(attribute.getAttributeID())) { if (record.get("RULE").equals("Attribute not found")) { return null; }/*from ww w.jav a 2s.co m*/ return record.get("RULE"); } } } } catch (FileNotFoundException ex) { Logger.getLogger(CheckDistanceExpectedMapping.class.getName()).log(Level.SEVERE, null, ex); } catch (IOException ex) { Logger.getLogger(CheckDistanceExpectedMapping.class.getName()).log(Level.SEVERE, null, ex); } return null; }