com.opencsv.CSVParser Java Examples

public static List<String[]> oneByOne(Reader reader) {
    List<String[]> list = new ArrayList<>();
    try {
        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

        CSVReader csvReader = new CSVReaderBuilder(reader)
                .withSkipLines(0)
                .withCSVParser(parser)
                .build();

        String[] line;
        while ((line = csvReader.readNext()) != null) {
            list.add(line);
        }
        reader.close();
        csvReader.close();
    } catch (Exception ex) {
        Helpers.err(ex);
    }
    return list;
}
 

protected static Set<TenantEntity> generateTenantEntities(final String groups, final UserGroupsEntity existingGroups)
    throws IOException, CommandException {
    final CSVParser csvParser = new CSVParser();
    final String[] groupArray = csvParser.parseLine(groups);
    final Set<TenantEntity> tenantEntities = new LinkedHashSet<>();

    for (String group : groupArray) {
        Optional<UserGroupEntity> existingGroup = existingGroups.getUserGroups().stream()
            .filter(entity -> group.equals(entity.getComponent().getIdentity())).findAny();

        if (!existingGroup.isPresent()) {
            throw new CommandException("User group with the identity '" + group + "' not found.");
        }

        tenantEntities.add(createTenantEntity(existingGroup.get().getId(), group));
    }

    return tenantEntities;
}
 

protected static Set<TenantEntity> generateTenantEntities(final String users, final UsersEntity existingUsers)
    throws IOException, CommandException {
    final CSVParser csvParser = new CSVParser();
    final String[] userArray = csvParser.parseLine(users);
    final Set<TenantEntity> tenantEntities = new LinkedHashSet<>();

    for (String user : userArray) {
        Optional<UserEntity> existingUser = existingUsers.getUsers().stream()
            .filter(entity -> user.equals(entity.getComponent().getIdentity())).findAny();

        if (!existingUser.isPresent()) {
            throw new CommandException("User with the identity '" + user + "' not found.");
        }

        tenantEntities.add(createTenantEntity(existingUser.get().getId(), user));
    }

    return tenantEntities;
}
 

public void convertOutputAddingNull() throws IOException, DataConversionException {
  JsonParser parser = new JsonParser();
  JsonElement jsonElement = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/schema_with_11_fields.json")));

  JsonArray outputSchema = jsonElement.getAsJsonArray();
  CSVParser csvParser = new CSVParser();
  String[] inputRecord = csvParser.parseLine(row11Cols);

  CsvToJsonConverterV2 converter = new CsvToJsonConverterV2();
  WorkUnitState wuState = new WorkUnitState();
  wuState.setProp(CsvToJsonConverterV2.CUSTOM_ORDERING, "0,1,-1,3,4,5,6,7,8,9,10");
  converter.init(wuState);

  JsonObject actual = converter.convertRecord(outputSchema, inputRecord, wuState).iterator().next();
  JsonObject expected = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/11_fields_with_null.json")))
                              .getAsJsonObject();
  Assert.assertEquals(expected, actual);
  converter.close();
}
 

public void convertOutputMismatchFields() throws IOException {
  JsonParser parser = new JsonParser();
  JsonElement jsonElement = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/schema_with_10_fields.json")));

  JsonArray outputSchema = jsonElement.getAsJsonArray();
  CSVParser csvParser = new CSVParser();
  String[] inputRecord = csvParser.parseLine(row11Cols);

  CsvToJsonConverterV2 converter = new CsvToJsonConverterV2();
  try {
    converter.createOutput(outputSchema, inputRecord);
    Assert.fail();
  } catch (Exception e) {

  }
  converter.close();
}
 

public void convertOutputSkippingField() throws IOException, DataConversionException {
  JsonParser parser = new JsonParser();
  JsonElement jsonElement = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/schema_with_10_fields.json")));

  JsonArray outputSchema = jsonElement.getAsJsonArray();
  CSVParser csvParser = new CSVParser();
  String[] inputRecord = csvParser.parseLine(row11Cols);

  CsvToJsonConverterV2 converter = new CsvToJsonConverterV2();
  WorkUnitState wuState = new WorkUnitState();
  wuState.setProp(CsvToJsonConverterV2.CUSTOM_ORDERING, "0,1,3,4,5,6,7,8,9,10");
  converter.init(wuState);

  JsonObject actual = converter.convertRecord(outputSchema, inputRecord, wuState).iterator().next();
  JsonObject expected = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/10_fields.json")))
                              .getAsJsonObject();

  Assert.assertEquals(expected, actual);
  converter.close();
}
 

public void convertOutput() throws IOException {
  JsonParser parser = new JsonParser();
  JsonElement jsonElement = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/schema_with_10_fields.json")));

  JsonArray outputSchema = jsonElement.getAsJsonArray();
  CSVParser csvParser = new CSVParser();
  String[] inputRecord = csvParser.parseLine(row10Cols);

  CsvToJsonConverterV2 converter = new CsvToJsonConverterV2();
  converter.init(new WorkUnitState());
  JsonObject actual = converter.createOutput(outputSchema, inputRecord);
  JsonObject expected = parser.parse(new InputStreamReader(getClass().getResourceAsStream("/converter/csv/10_fields.json")))
                              .getAsJsonObject();

  Assert.assertEquals(expected, actual);
  converter.close();
}
 

public static List<String[]> readAll(Reader reader) {

        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

        CSVReader csvReader = new CSVReaderBuilder(reader)
                .withSkipLines(0)
                .withCSVParser(parser)
                .build();

        List<String[]> list = new ArrayList<>();
        try {
            list = csvReader.readAll();
            reader.close();
            csvReader.close();
        } catch (Exception ex) {
            Helpers.err(ex);
        }
        return list;
    }
 

@Override
public void doProcessStream(InputStream stream, String source, JCas jCas) throws IOException {
  super.doProcessStream(stream, source, jCas);
  CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).build();
  try (CSVReader reader =
      new CSVReaderBuilder(new InputStreamReader(stream, StandardCharsets.UTF_8))
          .withCSVParser(parser)
          .build()) {
    String[] cols = reader.readNext();
    if (cols == null || cols.length < contentColumn) {
      throw new IOException("Not enough columns");
    }

    for (int i = 0; i < cols.length; i++) {
      if (i == (contentColumn - 1)) {
        jCas.setDocumentText(cols[i]);
      } else {
        addMetadata(jCas, i, cols[i]);
      }
    }
  }
}
 

/**
 * Reads a csv file with structure of yahoo api: No info line with name and timeFormatId, just header line and
 * {@link TimeFormatType timeFormat YAHOO}
 * @param name the name of this symbol
 * @param file the csv file with financial data in yahoo format
 * @return the corresponding TimeSeries object
 * @throws IOException IOException
 */
public TaBarSeries getSeriesFromYahooFile(String name, File file) throws IOException{
    CSVReader reader = new CSVReaderBuilder(new FileReader(file)).withCSVParser(new CSVParser()).build();
    String line[];
    line = reader.readNext();
    Map<Parameter.Columns, Integer> headers = FormatUtils.getHeaderMap(Arrays.asList(line));
    List<Bar> Bars = new ArrayList<>();
    while((line = reader.readNext()) != null) {
        Bars.add(FormatUtils.extractOHLCData(
                headers, DateTimeFormatter.ofPattern(TimeFormatType.YAHOO.pattern),line,false));
    }
    reader.close();
    if(Bars.get(Bars.size()-1).getEndTime().isBefore(Bars.get(0).getEndTime())){
        Collections.reverse(Bars);
    }
    String yahooIntervall = YahooSettingsManager.getProperties().getProperty(Parameter.PROPERTY_YAHOO_INTERVAL);
    GeneralTimePeriod timePeriod = YahooTimePeriod.of(yahooIntervall).generalTimePeriod;
    return new TaBarSeries(name==null?"unnamed":name.toUpperCase(),Bars,Currency.getInstance("USD"),timePeriod);
}
 

/**
 * Connects to the airports list and build a map of {@link Airport} with the name as key.
 *
 * @throws CsvValidationException when the parsing of the file fails
 * @throws IOException            when network error
 * @throws URISyntaxException     when the URI is invalid
 */
public void buildAirport() throws URISyntaxException, IOException, CsvValidationException {
    URI airportsURI = new URI(AIRPORT_URI);
    airports = new HashMap<>();
    try (InputStream airportStream = airportsURI.toURL().openStream();
            CSVReader reader = new CSVReaderBuilder(new InputStreamReader(airportStream, StandardCharsets.UTF_8)).withCSVParser(new CSVParser()).withSkipLines(1).build()) {
        String[] line;

        while ((line = reader.readNext()) != null) {
            Airport airport = new Airport();
            airport.setIcao(line[1]);
            airport.setName(line[3]);
            airport.setLatitude(NumberUtils.toDouble(line[4], 0));
            airport.setLongitude(NumberUtils.toDouble(line[5], 0));
            airport.setAltitude(NumberUtils.toInt(line[6], 0));
            airport.setCountry(countries.get(line[8]));
            airport.setCity(line[10]);
            airport.setIata(line[13]);
            airports.put(airport.getIcao(), airport);
        }
    }
}
 

/**
 * Initiate airports map.
 */
private void initAirports() {
    Objects.requireNonNull(airportsFile);
    airports = new HashMap<>();
    String[] line;
    try (CSVReader reader = new CSVReaderBuilder(new InputStreamReader(airportsFile, StandardCharsets.UTF_8)).withCSVParser(new CSVParser()).withSkipLines(0).build()) {
        while ((line = reader.readNext()) != null) {
            Airport airport = new Airport();
            airport.setName(line[1]);
            airport.setCity(line[2]);
            airport.setCountry(countries.get(line[3]));
            airport.setIata(line[4]);
            airport.setIcao(line[5]);
            airport.setLatitude(Double.parseDouble(line[6]));
            airport.setLongitude(Double.parseDouble(line[7]));
            airport.setAltitude(Integer.parseInt(line[8]));
            airport.setTimezone(line[9]);
            airport.setDst(line[10]);
            airports.put(airport.getIcao(), airport);
        }
    } catch (IOException | CsvValidationException exception) {
        throw new IllegalStateException(exception.getMessage());
    }
}
 

public static void main(String[] args) throws FileNotFoundException, IOException {
    // TODO code application logic here 
    File phase3File = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\phase3_corrected.psam");
    File traitFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\TraitFile.txt");
    File probeAnnotationFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\ProbeAnnotationFile.txt");
    File couplingFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\CouplingFile.txt");
    //FileReader(String phase3_corrected)
    final CSVParser gmtParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
    final CSVReader gmtReader = new CSVReaderBuilder(new BufferedReader(new FileReader(phase3File))).withSkipLines(1).withCSVParser(gmtParser).build();


    List<String> iids = new ArrayList<>();

    String[] inputLine;
    while ((inputLine = gmtReader.readNext()) != null) {

        String iid = inputLine[0];

        iids.add(iid);
    }

    trait(iids, traitFile);
    probeAnnotation(probeAnnotationFile);
    coupling(iids, couplingFile);
}
 

public CSVReader createCSVReader() throws IOException {
	Path path = Paths.get(this.datasetPath + this.datasetName + this.datasetEnding);
	
	CSVParser parser = new CSVParserBuilder()
			.withSeparator(this.valueSeparator)
			.withQuoteChar(this.valueQuote)
			.withEscapeChar(this.valueEscape)
			.withStrictQuotes(this.valueStrictQuotes)
			.withIgnoreLeadingWhiteSpace(this.valueIgnoreLeadingWhitespace)
			.withFieldAsNull(CSVReaderNullFieldIndicator.EMPTY_SEPARATORS)
			.build();
	
	BufferedReader buffer = Files.newBufferedReader(path, this.charset);
	CSVReader reader = new CSVReaderBuilder(buffer).withCSVParser(parser).build();
	
	if (this.fileHasHeader)
		reader.readNext();
	
	return reader;
}
 

@Override
  public boolean connect(File resource){
      String separator = properties.getProperty(Parameter.PROPERTY_CSV_SEPARATOR, ",");
      String quote = properties.getProperty(Parameter.PROPERTY_CSV_QUOTE, "\\\\");
      CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).withQuoteChar(quote.charAt(0)).build();
      try(CSVReader reader = new CSVReaderBuilder(new FileReader(resource)).withCSVParser(parser).build();)
      {
      	lines = reader.readAll();
      	String[] infoLine = lines.get(0);
	name = infoLine[0];
       id = FormatUtils.extractInteger(infoLine[1]);
       isDateTwoColumn = id == TimeFormatType.yyyy_MM_ddHmsz.id;
       dateTimeFormatter = FormatUtils.getDateTimeFormatter(id);
       String currencyString = null;
       if(infoLine.length>2) {
           currencyString = infoLine[2].replaceAll("\\s", "");
       }
       if(currencyString == null || currencyString.length() != 3)
           currencyString = Parameter.DEFAULT_CURRENCY;
       currency = Currency.getInstance(currencyString);
       lines.remove(0); // remove InfoLine
} catch (FileNotFoundException e) {
	log.error(e.getMessage());
	e.printStackTrace();
	return false;
} catch (IOException ioe) {
	log.error(ioe.getMessage());
	ioe.printStackTrace();
	return false;
}
      return true;
  }
 

@ProcessElement
public void processElement(ProcessContext c) throws IOException {
  String csvLine = c.element();
  CSVParser parser = new CSVParserBuilder().withQuoteChar(CSV_QUOTE_CHAR.charAt(0)).build();
  String[] parts = parser.parseLine(csvLine);
  c.output(parts);
}
 

/**
 * Connects to the countries list and build a map of {@link Country} with the name as key.
 *
 * @throws CsvValidationException when the parsing of the file fails
 * @throws IOException            when network error
 * @throws URISyntaxException     when the URI is invalid
 */
public void buildCountries() throws URISyntaxException, IOException, CsvValidationException {
    countries = new HashMap<>();
    URI countriesUri = new URI(COUNTRIES_URI);
    try (InputStream countriesStream = countriesUri.toURL().openStream();
            CSVReader reader = new CSVReaderBuilder(new InputStreamReader(countriesStream, StandardCharsets.UTF_8)).withCSVParser(new CSVParser()).withSkipLines(1).build()) {
        String[] line;
        while ((line = reader.readNext()) != null) {
            Country c = new Country();
            c.setName(line[2]);
            countries.put(line[1], c);
        }
    }
}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

private static HashMap<String, HashSet<String>> readClusterFile(File hpoFile) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(0).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		HashSet<String> allMyoclonusGenes = new HashSet<>();
		hpoToGenes.put("AllMyoclonus", allMyoclonusGenes);

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String gene = nextLine[0];
			String cluster = nextLine[1];

			HashSet<String> hpoGenes = hpoToGenes.get(cluster);
			if (hpoGenes == null) {
				hpoGenes = new HashSet<>();
				hpoToGenes.put(cluster, hpoGenes);
			}

			allMyoclonusGenes.add(gene);
			hpoGenes.add(gene);

		}

		return hpoToGenes;

	}
 

public static final List<String> readMatrixAnnotations(File file) throws IOException {

        final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
        final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(file))).withCSVParser(parser).build();

        ArrayList<String> identifiers = new ArrayList<>();

        String[] nextLine;
        while ((nextLine = reader.readNext()) != null) {
            identifiers.add(nextLine[0]);
        }

        return identifiers;
    }
 

@Override
public Map<String, SameState> parse(InputStream is) {
	LOGGER.debug("Parsing NWS SAME Code State Name Mapping input data file");

	Map<String, SameState> sameStates = new HashMap<String,SameState>();

	try (CSVReader reader = new CSVReader(new InputStreamReader(is), 0, new CSVParser())) {
		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {
			if (nextLine.length < 2) { // error in input file, skip the record and continue
				continue;
			}

           /*
            * The NWS SAME code data file can contain whitespace around state
            * codes on load, strip this out
            */
			String stateCode = nextLine[0].trim(); 
			String state = nextLine[1];

			if (StringUtils.isEmpty(stateCode) || StringUtils.isEmpty(state)) {
				LOGGER.warn(
						"Invalid NWS SAME Code State Name mapping file record, null value(s) found while parsing input data file with values: State Code:{} and State Name:{}",
						stateCode, state);
				continue;
			}

			sameStates.put(stateCode, new SameState(stateCode, state));
		}
	} catch (Exception e) {
		LOGGER.warn("Error parsing NWS SAME Code State Name Mapping input data file", e);
		throw new IllegalStateException(e);
	}
	
	if (sameStates.isEmpty()) {
		return null;
	}
	
	return sameStates;
}
 

private static HashMap<String, HashMap<String, HashSet<String>>> loadTfData(File tfFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(tfFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, HashMap<String, HashSet<String>>> tfdatabasesPathwayToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if (nextLine[0].charAt(0) == '!') {
				continue;
			}

			String database = nextLine[0];
			String pathway = nextLine[1];
			String ensgId = nextLine[3];

			HashMap<String, HashSet<String>> pathwayToGenes = tfdatabasesPathwayToGenes.get(database);
			if (pathwayToGenes == null) {
				pathwayToGenes = new HashMap<>();
				tfdatabasesPathwayToGenes.put(database, pathwayToGenes);
			}

			HashSet<String> pathwayGenes = pathwayToGenes.get(pathway);
			if (pathwayGenes == null) {
				pathwayGenes = new HashSet<>();
				pathwayToGenes.put(pathway, pathwayGenes);
			}

			pathwayGenes.add(ensgId);

		}

		return tfdatabasesPathwayToGenes;

	}
 

protected static Set<TenantEntity> generateTenantEntities(final String ids)
    throws IOException {
    final CSVParser csvParser = new CSVParser();
    return Arrays.stream(csvParser.parseLine(ids))
        .map(AbstractNiFiCommand::createTenantEntity)
        .collect(Collectors.toCollection(LinkedHashSet::new));
}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

private static HashSet<String> getMutatedGenes(File genoFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(genoFile))).withSkipLines(1).withCSVParser(parser).build();

		HashSet<String> genes = new HashSet<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			genes.add(nextLine[8]);

		}

		reader.close();

		return genes;

	}
 

private static ArrayList<String> readGenes(File geneOrderFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(geneOrderFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		ArrayList<String> geneOrder = new ArrayList<>();

		while ((nextLine = reader.readNext()) != null) {

			geneOrder.add(nextLine[0]);

		}

		return geneOrder;

	}
 

public static TObjectDoubleMap<String> readSignificantPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		TObjectDoubleMap<String> hpos = new TObjectDoubleHashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if(Double.parseDouble(nextLine[4]) <= 0.05){
				hpos.put(nextLine[0], Double.parseDouble(nextLine[3]));
			}
			

		}

		reader.close();

		return hpos;

	}
 

public static LinkedHashSet<String> readPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		LinkedHashSet<String> hpos = new LinkedHashSet<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			hpos.add(nextLine[0]);

		}

		reader.close();

		return hpos;

	}
 

private static HashMap<String, LinkedHashSet<String>> loadCaseHpo(File caseHpoFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(caseHpoFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, LinkedHashSet<String>> caseHpo = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if (nextLine[5].isEmpty()) {

				LinkedHashSet<String> hpo = caseHpo.get(nextLine[0]);
				if (hpo == null) {
					hpo = new LinkedHashSet<>();
					caseHpo.put(nextLine[0], hpo);
				}
				hpo.add(nextLine[1]);

			}

		}

		return caseHpo;

	}
 

/**
	 * @param args the command line arguments
	 */
	public static void main(String[] args) throws FileNotFoundException, IOException {
//
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\rankingCandidateGenes");

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\rankingCandidateGenes");
		
		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\samplesWithGeno.txt");
		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\gavinRes\\");
		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\Prioritisations");
		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\extraUnsolved\\rankingCandidateGenes");

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsDcm\\rankingCandidateGenes");
//
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations3\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsSpiked");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsSpiked\\rankingCandidateGenes");
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\Gavin\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioMieke\\");
//		
//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\Prioritisations\\samples.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\CandidateGenes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\PrioritisationsCardioEdgar\\");
//
//		
		resultFolder.mkdirs();

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader sampleFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(sampleFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		while ((nextLine = sampleFileReader.readNext()) != null) {

			String sample = nextLine[0];

			String genoSampleName = new File(nextLine[1]).getName();
			if (!genoSampleName.endsWith(".txt")) {
				genoSampleName += ".txt";
			}

			File genoFile = new File(genoFolder, genoSampleName);
			File prioFile = new File(prioFolder, sample + ".txt");
			File rankingFile = new File(resultFolder, sample + ".txt");

			System.out.println("------------------------------------------------------------------");
			System.out.println("Sample: " + sample);
			System.out.println("Geno: " + genoFile.getAbsolutePath());
			System.out.println("Prio: " + prioFile.getAbsolutePath());
			System.out.println("Ranking: " + rankingFile.getAbsolutePath());

			HashSet<String> genesWithMutation = getMutatedGenes(genoFile);

			final CSVReader prioFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(prioFile))).withSkipLines(0).withCSVParser(parser).build();

			CSVWriter writer = new CSVWriter(new FileWriter(rankingFile), '\t', '\0', '\0', "\n");

			String[] outputLine = prioFileReader.readNext();
			writer.writeNext(outputLine);

			while ((outputLine = prioFileReader.readNext()) != null) {

				if (genesWithMutation.contains(outputLine[1])) {
					writer.writeNext(outputLine);
				}

			}

			writer.close();
			prioFileReader.close();

		}

	}