Example usage for org.apache.commons.csv CSVRecord get

List of usage examples for org.apache.commons.csv CSVRecord get

  1. HOME
  2. Java
  3. org.apache.commons
  4. org.apache.commons.csv.*
  5. CSVRecord
  6. get

Introduction

In this page you can find the example usage for org.apache.commons.csv CSVRecord get.

Prototype

public String get(final String name)

Source Link

Document

Returns a value by name.

Usage

From source file:org.transitime.gtfs.readers.GtfsStopTimesReader.java

@Override
public GtfsStopTime handleRecord(CSVRecord record, boolean supplemental) throws ParseException {
    if (GtfsData.tripNotFiltered(record.get("trip_id")))
        return new GtfsStopTime(record, supplemental, getFileName());
    else// www . j  a v  a2 s.  c om
        return null;
}

From source file:org.transitime.gtfs.readers.GtfsTripsReader.java

@Override
public GtfsTrip handleRecord(CSVRecord record, boolean supplemental) throws ParseException {
    if (GtfsData.tripNotFiltered(record.get("trip_id")) && GtfsData.routeNotFiltered(record.get("route_id")))
        return new GtfsTrip(record, supplemental, getFileName());
    else//from   ww w  . j ava2s .co  m
        return null;
}

From source file:org.transitime.utils.csv.CsvBase.java

/**
 * For reading values from a CSVRecord. If the column was not defined then
 * CSVRecord.get() throws an exception. Therefore for optional CSV columns
 * better to use this function so don't get exception. This way can continue
 * processing and all errors for the data will be logged. Better than just
 * logging first error and then quitting.
 * <p>/*w  w w  . j  a v a2s  .  c  o m*/
 * Also, if the value is empty string then it is converted to null for
 * consistency. Also trims the resulting string since some agencies leave in
 * spaces.
 * 
 * @param record
 *            The data for the row in the CSV file
 * @param name
 *            The name of the column in the CSV file
 * @param required
 *            Whether this value is required. If required and the value is
 *            not set then an error is logged and null is returned.
 * @return The value, or null if it was not defined
 */
private String getValue(CSVRecord record, String name, boolean required) {
    // If the column is not defined in the file then return null.
    // After all, the item is optional so it is fine for it to
    // not be in the file.
    if (!record.isSet(name)) {
        if (required) {
            logger.error("Column {} not defined in file \"{}\" yet it is required", name, getFileName());
        }
        return null;
    }

    // Get the value. First trim whitespace so that
    // value will be consistent. Sometimes agencies will mistakenly have
    // some whitespace in the columns.
    String value = record.get(name).trim();

    // Return the value. But if the value is empty string
    // convert to null for consistency.
    if (value.isEmpty()) {
        if (required) {
            logger.error(
                    "For file \"{}\" line number {} for column {} value was not set " + "yet it is required",
                    getFileName(), lineNumber, name);
        }
        return null;
    } else {
        // Successfully got value so return intern() version of it. Using 
        // intern() because many strings are duplicates such as headsign
        // or shape info. By sharing the strings we can save a huge amount
        // of memory.
        return value.intern();
    }
}

From source file:org.wheatinitiative.vitro.webapp.ontology.update.OntologyChangeParser.java

/**
 * @param args//w  w w. ja va2 s  .  co  m
 * @throws IOException 
 */

@SuppressWarnings({ "unchecked", "null", "static-access" })
public ArrayList<AtomicOntologyChange> parseFile(String diffPath) throws IOException {
    AtomicOntologyChange changeObj;
    ArrayList<AtomicOntologyChange> changeObjects = new ArrayList<AtomicOntologyChange>();
    int countColumns = 0;
    String URI = null;
    String rename = null;
    String sourceURI = null;
    String destinationURI = null;
    StringTokenizer stArr = null;
    InputStreamReader in = new InputStreamReader(this.getClass().getResourceAsStream(diffPath));

    Iterable<CSVRecord> records = CSVFormat.TDF.parse(in);
    Iterator<CSVRecord> rows = records.iterator();
    //CSVReader readFile = new SimpleReader();
    //readFile.setSeperator('\t');

    //List<String[]> rows = readFile.parse(in);

    int rowNum = 0;
    while (rows.hasNext()) {
        rowNum++;
        CSVRecord row = rows.next();
        if (row.size() != 5) {
            log.error("Invalid PromptDiff data at row " + (rowNum + 1) + ". Expected 5 columns; found "
                    + row.size());
        } else {
            changeObj = new AtomicOntologyChange();
            if (row.get(0) != null && row.get(0).length() > 0) {
                changeObj.setSourceURI(row.get(0));
            }
            if (row.get(1) != null && row.get(1).length() > 0) {
                changeObj.setDestinationURI(row.get(1));
            }
            if (row.get(4) != null && row.get(4).length() > 0) {
                changeObj.setNotes(row.get(4));
            }
            if ("Yes".equals(row.get(2))) {
                changeObj.setAtomicChangeType(AtomicChangeType.RENAME);
            } else if ("Delete".equals(row.get(3))) {
                changeObj.setAtomicChangeType(AtomicChangeType.DELETE);
            } else if ("Add".equals(row.get(3))) {
                changeObj.setAtomicChangeType(AtomicChangeType.ADD);
            } else {
                log.error("Invalid rename or change type data: '" + row.get(2) + " " + row.get(3) + "'");
            }
            log.debug(changeObj);
            changeObjects.add(changeObj);
        }

    }
    if (changeObjects.size() == 0) {
        log.debug("No ABox updates are required.");
    }
    return changeObjects;
}

From source file:org.wildfly.swarm.proc.FailFastComparator.java

@Override
public void compare(List<CSVRecord> previous, List<CSVRecord> current) throws ThresholdExceeded {
    List<ComparisonResult> comparisonResults = new ArrayList<>();
    int maxChars = 0;
    for (CSVRecord prevRecord : previous) {
        String fileName = prevRecord.get(CSVCollector.SHORT_FILE_NAME_COLUMN);
        if (fileName.length() > maxChars)
            maxChars = fileName.length();
        CSVRecord matching = findMatching(fileName, current);
        if (matching != null) {

            for (Measure measure : criteria) {
                double prevVal = Double.valueOf(prevRecord.get(measure.column75Percentile()));
                double currVal = Double.valueOf(matching.get(measure.column75Percentile()));

                if (currVal > prevVal) {

                    double increasePercentage = currVal * 100 / prevVal;
                    boolean failed = increasePercentage - threshold > 100;
                    String message = StringUtils.rightPad(measure.getShortName(), 10) + " +"
                            + Math.floor(increasePercentage - 100) + "% (" + prevVal + " -> " + currVal + ")";
                    comparisonResults.add(new ComparisonResult(measure, fileName, failed, message));
                } else {
                    double decreasePercentage = prevVal * 100 / currVal;
                    String message = StringUtils.rightPad(measure.getShortName(), 10) + " -"
                            + Math.floor(decreasePercentage - 100) + "% (" + prevVal + " -> " + currVal + ")";

                    comparisonResults.add(new ComparisonResult(measure, fileName, message));
                }// ww  w. ja  v a  2 s  .  c  o m
            }

        } else {
            System.err.println("No matching record for test " + fileName + ". Skipping ...");
        }
    }

    // dump results
    final int pad = maxChars + 2;
    Collections.sort(comparisonResults, Comparator.comparing(ComparisonResult::getMeasure));

    comparisonResults
            .forEach(r -> System.out.println(StringUtils.rightPad(r.getFile(), pad) + ": " + r.getMessage()));

    // decide if ThresholdExceeded
    List<ComparisonResult> failedTests = comparisonResults.stream().filter(r -> !r.isFailure())
            .collect(Collectors.toList());
    if (failedTests.size() > 0) {
        System.err.println("There have been test errors. See previous logs for details ...");
        throw new ThresholdExceeded(
                failedTests.size() + " test(s) did exceed the " + this.threshold + "% tolerance.");
    }

}

From source file:org.wso2.carbon.event.simulator.csvFeedSimulation.core.CSVFeedEventSimulator.java

/**
 * This method must be called within a synchronized block to avoid multiple file simulators from running simultaneously.
 * Read the values from uploaded CSV file and convert those values into event and send those events to
 * input handler/*from w w w  . j  ava  2  s  . c  o m*/
 * <p>
 * <p>
 * To read the CSV file It uses CSV parser Library.
 * {@link <a href="https://commons.apache.org/proper/commons-csv/apidocs/org/apache/commons/csv/CSVParser.html">CSVParser</a>}
 * </p>
 * <p>
 * <p>
 * CSV file can be separated by one of these fallowing character , , ; , \t by default
 * It has capability to have user defined delimiter
 * Any field may be quoted (with double quotes)
 * Fields with embedded commas or delimiter characters must be double quoted.
 * </p>
 * <p>
 * Initialize CSVParser
 *
 * @param executionPlanDto ExecutionPlanDto
 * @param csvFileConfig    CSVFileSimulationDto
 */
private void sendEvent(ExecutionPlanDto executionPlanDto, CSVFileSimulationDto csvFileConfig) {

    /*
      return no of events read from CSV file during ever iteration
     */
    long noOfEvents = 0;
    int delay = csvFileConfig.getDelay();
    /*
    Reader for reading character streams from file
     */
    Reader in = null;
    /*
    CSVParser to read CSV Values
     */
    CSVParser csvParser = null;
    if (delay <= 0) {
        log.warn("Events will be sent continuously since the delay between events are set to " + delay
                + "milliseconds");
        delay = 0;
    }

    try {
        /*
        Initialize Reader
         */
        in = new FileReader(String.valueOf(Paths.get(System.getProperty("java.io.tmpdir"),
                csvFileConfig.getFileDto().getFileInfo().getFileName())));

        /*
        Initialize CSVParser with appropriate CSVFormat according to delimiter
         */

        switch (csvFileConfig.getDelimiter()) {
        case ",":
            csvParser = CSVParser.parse(in, CSVFormat.DEFAULT);
            break;
        case ";":
            csvParser = CSVParser.parse(in, CSVFormat.EXCEL);
            break;
        case "\\t":
            csvParser = CSVParser.parse(in, CSVFormat.TDF);
            break;
        default:
            csvParser = CSVParser.parse(in, CSVFormat.newFormat(csvFileConfig.getDelimiter().charAt(0)));
        }

        int attributeSize = executionPlanDto.getInputStreamDtoMap().get(csvFileConfig.getStreamName())
                .getStreamAttributeDtos().size();

        /*
        Iterate through the CSV file line by line
         */

        for (CSVRecord record : csvParser) {
            try {
                synchronized (this) {
                    if (isStopped) {
                        isStopped = false;
                        break;
                    }
                    if (isPaused) {
                        this.wait();
                    }
                }

                if (record.size() != attributeSize) {
                    log.warn("No of attribute is not equal to attribute size: " + attributeSize + " is needed"
                            + "in Row no:" + noOfEvents + 1);
                }
                String[] attributes = new String[attributeSize];
                noOfEvents = csvParser.getCurrentLineNumber();

                for (int i = 0; i < record.size(); i++) {
                    attributes[i] = record.get(i);
                }

                //convert Attribute values into event
                Event event = EventConverter.eventConverter(csvFileConfig.getStreamName(), attributes,
                        executionPlanDto);
                // TODO: 13/12/16 delete sout
                System.out.println("Input Event " + Arrays.deepToString(event.getEventData()));
                //

                //send the event to input handler
                send(csvFileConfig.getStreamName(), event);

                //delay between two events
                if (delay > 0) {
                    Thread.sleep(delay);
                }
            } catch (EventSimulationException e) {
                log.error("Event dropped due to Error occurred during generating an event" + e.getMessage());
            } catch (InterruptedException e) {
                log.error("Error occurred during send event" + e.getMessage());
            }
        }

    } catch (IllegalArgumentException e) {
        // TODO: 02/12/16 proper error message
        throw new EventSimulationException("File Parameters are null" + e.getMessage());
    } catch (FileNotFoundException e) {
        throw new EventSimulationException(
                "File not found :" + csvFileConfig.getFileDto().getFileInfo().getFileName());
    } catch (IOException e) {
        throw new EventSimulationException("Error occurred while reading the file");
    } finally {
        try {
            if (in != null && csvParser != null)
                in.close();
            csvParser.close();
        } catch (IOException e) {
            throw new EventSimulationException("Error occurred during closing the file");
        }
    }
}

From source file:org.wso2.carbon.event.simulator.randomdatafeedsimulation.bean.CustomBasedAttribute.java

/**
 * Method to split the data list into seperated values and assign it to customDataList
 *
 * @param customData String that has data list values
 *                   Initial string format is ""CEP,Siddhi",ESB,DAS"
 *//*from   w  ww.j a  v  a2s . c  o m*/
public void setCustomData(String customData) {
    CSVParser csvParser = null;
    List<String> dataList = null;
    try {
        csvParser = CSVParser.parse(customData, CSVFormat.newFormat(',').withQuote('/'));
        dataList = new ArrayList<>();
        for (CSVRecord record : csvParser) {
            for (int i = 0; i < record.size(); i++) {
                dataList.add(record.get(i));
            }
        }
    } catch (IOException e) {
        throw new EventSimulationException("I/O error occurs :" + e.getMessage());
    } catch (IllegalArgumentException e) {
        throw new EventSimulationException("Data set is null :" + e.getMessage());
    }
    customDataList = dataList.toArray(new String[dataList.size()]);
}

From source file:org.wso2.carbon.ml.dataset.internal.DatasetSummary.java

/**
 * Finds the columns with Categorical data and Numerical data. Stores the raw-data in a list.
 *
 * @param datasetIterator   Iterator for the CSV parser.
 * @param sampleSize        Size of the sample.
 * @throws                  DatasetSummaryException
 *//* ww w.  ja v a 2 s .  c o  m*/
private void identifyColumnDataType(Iterator<CSVRecord> datasetIterator, int sampleSize) {
    int recordsCount = 0;
    CSVRecord row;
    int[] stringCellCount = new int[this.headerMap.size()];

    // Count the number of cells contain strings in each column.
    while (datasetIterator.hasNext() && recordsCount != sampleSize) {
        row = datasetIterator.next();
        for (int currentCol = 0; currentCol < this.headerMap.size(); currentCol++) {
            if (!row.get(currentCol).isEmpty()) {
                if (!NumberUtils.isNumber(row.get(currentCol))) {
                    stringCellCount[currentCol]++;
                }
            } else {
                // If the cell is empty, increase the missing value count.
                this.missing[currentCol]++;
            }
            // Append the cell to the respective column.
            this.columnData.get(currentCol).add(row.get(currentCol));
        }
        recordsCount++;
    }

    // If atleast one cell contains strings, then the column is considered to has string data.
    for (int col = 0; col < headerMap.size(); col++) {
        if (stringCellCount[col] > 0) {
            this.stringDataColumnPositions.add(col);
            this.type[col] = FeatureType.CATEGORICAL;
        } else {
            this.numericDataColumnPositions.add(col);
            this.type[col] = FeatureType.NUMERICAL;
        }
    }
}

From source file:org.zanata.adapter.glossary.GlossaryCSVReader.java

public Map<LocaleId, List<GlossaryEntry>> extractGlossary(Reader reader, String qualifiedName)
        throws IOException {
    try {//from   w  ww  . jav a2 s .  co m
        Iterable<CSVRecord> rawRecords = CSVFormat.RFC4180.parse(reader);
        List<CSVRecord> records = Lists.newArrayList(rawRecords);

        validateCSVEntries(records);
        Map<String, Integer> descriptionMap = setupDescMap(records);
        Map<Integer, LocaleId> localeColMap = setupLocalesMap(records, descriptionMap);

        LocaleId srcLocale = localeColMap.get(0);

        if (!srcLang.equals(srcLocale)) {
            throw new RuntimeException("input source language '" + srcLang
                    + "' does not match source language in file '" + srcLocale + "'");
        }
        Map<LocaleId, List<GlossaryEntry>> results = Maps.newHashMap();

        for (int i = 1; i < records.size(); i++) {
            CSVRecord row = records.get(i);
            for (int x = 1; x < row.size() && localeColMap.containsKey(x); x++) {

                GlossaryEntry entry = new GlossaryEntry();
                entry.setSrcLang(srcLocale);
                entry.setPos(row.get(descriptionMap.get(POS)));
                entry.setDescription(row.get(descriptionMap.get(DESC)));
                entry.setQualifiedName(new QualifiedName(qualifiedName));

                GlossaryTerm srcTerm = new GlossaryTerm();
                srcTerm.setLocale(srcLocale);
                srcTerm.setContent(row.get(0));

                entry.getGlossaryTerms().add(srcTerm);

                LocaleId transLocaleId = localeColMap.get(x);
                String transContent = row.get(x);

                GlossaryTerm transTerm = new GlossaryTerm();
                transTerm.setLocale(transLocaleId);
                transTerm.setContent(transContent);

                entry.getGlossaryTerms().add(transTerm);
                List<GlossaryEntry> list = results.get(transLocaleId);
                if (list == null) {
                    list = Lists.newArrayList();
                }
                list.add(entry);
                results.put(transLocaleId, list);
            }
        }
        return results;
    } finally {
        reader.close();
    }
}

From source file:org.zanata.adapter.glossary.GlossaryCSVReader.java

/**
 * Parser reads from all from first row and exclude column from description
 * map. Format of CVS: {source locale},{locale},{locale}...,pos,description
 *//*www.j a v  a 2  s .  c  o m*/
private Map<Integer, LocaleId> setupLocalesMap(List<CSVRecord> records, Map<String, Integer> descriptionMap) {
    Map<Integer, LocaleId> localeColMap = new HashMap<Integer, LocaleId>();
    CSVRecord headerRow = records.get(0);
    for (int row = 0; row <= headerRow.size() && !descriptionMap.containsValue(row); row++) {
        LocaleId locale = new LocaleId(StringUtils.trim(headerRow.get(row)));
        localeColMap.put(row, locale);
    }
    return localeColMap;
}