Example usage for org.apache.commons.csv CSVParser CSVParser

List of usage examples for org.apache.commons.csv CSVParser CSVParser

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

Introduction

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

Prototype

public CSVParser(final Reader reader, final CSVFormat format) throws IOException

Source Link

Document

Customized CSV parser using the given CSVFormat

If you do not read all records from the given reader , you should call #close() on the parser, unless you close the reader .

Usage

From source file:com.github.jferard.pgloaderutils.sniffer.csv.CSVOptionalHeaderSniffer.java

@Override
public void sniff(final InputStream inputStream, final int size) throws IOException {
    final Reader streamReader = new InputStreamReader(inputStream, this.charset);

    final CSVParser parser = new CSVParser(streamReader, this.csvFormat);
    try {//from  ww  w .ja  va 2 s .  co m
        final Iterator<CSVRecord> iterator = parser.iterator();

        if (iterator.hasNext()) {
            final CSVRecord firstRowRecord = iterator.next();
            final int firstRowSize = firstRowRecord.size();

            final char[] firstRowSignature = this.rowSignaturesAnalyzer.getSignature(firstRowRecord,
                    firstRowSize);

            if (this.containsAtLeastOneOnlyDigitsValue(firstRowSignature)) {
                this.header = null;
            } else {
                final char[] remainingRowsSignature = this.rowSignaturesAnalyzer
                        .getRemainingRowsSignature(iterator, firstRowSize);
                if (this.containsAtLeastOneColumnWithLetterHeaderAndDigitValues(firstRowSignature,
                        remainingRowsSignature, firstRowSize)) {
                    // copy firstRow in header
                    for (final String s : firstRowRecord)
                        this.header.add(s);
                }
            }
        } else
            this.header = null;
    } finally {
        parser.close();
    }
}

From source file:br.edimarmanica.trinity.intrasitemapping.manual.OffsetToRule.java

public void execute() {
    readMappings();/*from   w w w.  j a  v a  2  s .c o  m*/

    File dir = new File(Paths.PATH_TRINITY + site.getPath() + "/offset");

    for (File offset : dir.listFiles(new FilenameFilter() {
        @Override
        public boolean accept(File dir, String name) {
            return name.endsWith(".csv");
        }
    })) {

        try (Reader in = new FileReader(offset)) {
            try (CSVParser parser = new CSVParser(in, CSVFormat.EXCEL)) {
                for (CSVRecord record : parser) {
                    String page = record.get(0);
                    if (pages.contains(page)) {
                        continue;
                    } else {
                        pages.add(page);
                    }

                    List<String> dataRecord = new ArrayList<>();
                    for (Attribute attr : site.getDomain().getAttributes()) {
                        try {
                            int group = mappings.get(offset.getName()).get(attr.getAttributeID());

                            if (group != -1) {
                                dataRecord.add(record.get(group));
                            } else {
                                dataRecord.add("");
                            }
                        } catch (Exception ex) {
                            dataRecord.add("");
                        }
                    }
                    print(page, dataRecord);
                }
            }
        } catch (FileNotFoundException ex) {
            Logger.getLogger(Mapping.class.getName()).log(Level.SEVERE, null, ex);
        } catch (IOException ex) {
            Logger.getLogger(Mapping.class.getName()).log(Level.SEVERE, null, ex);
        }

    }

}

From source file:com.blackducksoftware.integration.hubdiff.HubDiffTest.java

@Test
public void csvTest() throws IOException, IllegalArgumentException, EncryptionException,
        HubIntegrationException, JSONException {
    HubDiff hubDiff = new HubDiff(doc1, doc2);

    hubDiff.writeDiffAsCSV(actualFile);//from   ww  w.j  a v  a  2s  .  c  om

    CSVParser expectedParser = new CSVParser(new FileReader(expectedFile), CSVFormat.EXCEL);
    CSVParser actualParser = new CSVParser(new FileReader(actualFile), CSVFormat.EXCEL);
    List<CSVRecord> expectedRecords = expectedParser.getRecords();
    List<CSVRecord> actualRecords = actualParser.getRecords();

    assertEquals(expectedRecords.size(), actualRecords.size());

    for (int i = 0; i < expectedRecords.size(); i++) {
        String expected = expectedRecords.get(i).toString();
        String actual = actualRecords.get(i).toString();
        assertEquals(expected, actual);
    }

    expectedParser.close();
    actualParser.close();
}

From source file:mtsar.resources.TaskResource.java

@POST
@Consumes(MediaType.MULTIPART_FORM_DATA)
public Response postTasksCSV(@Context UriInfo uriInfo, @FormDataParam("file") InputStream stream)
        throws IOException {
    try (final Reader reader = new InputStreamReader(stream, StandardCharsets.UTF_8)) {
        try (final CSVParser csv = new CSVParser(reader, TaskCSV.FORMAT)) {
            taskDAO.insert(TaskCSV.parse(stage, csv));
        }//www.  j a  v a  2  s . c om
    }
    taskDAO.resetSequence();
    return Response.seeOther(getTasksURI(uriInfo)).build();
}

From source file:com.xoriant.akka.mongodb.bulkimport.actor.FileReaderActor.java

private void readAndInsertCSV(String filePath) {
    FileReader fileReader = null;

    CSVParser csvFileParser = null;//  ww w  . j a v a 2 s  . c  o m

    // Create the CSVFormat object with the header mapping
    CSVFormat csvFileFormat = CSVFormat.EXCEL.withHeader(FILE_HEADER_MAPPING);

    try {

        fileReader = new FileReader(filePath);

        csvFileParser = new CSVParser(fileReader, csvFileFormat);

        List<CSVRecord> csvRecords = csvFileParser.getRecords();
        CSVRecordBatchMsg csvRecordBatch = new CSVRecordBatchMsg();
        boolean batchSent = false;
        // Skip the header row and start reading CSV records
        for (int i = 1; i < csvRecords.size(); i++) {
            CSVRecord record = csvRecords.get(i);
            BasicDBObject person = new BasicDBObject();
            person.put(PERSON_GENDER, record.get(PERSON_GENDER));
            person.put(PERSON_TITLE, record.get(PERSON_TITLE));
            person.put(PERSON_NAMESET, record.get(PERSON_NAMESET));
            person.put(PERSON_SURNAME, record.get(PERSON_SURNAME));
            person.put(PERSON_CITY, record.get(PERSON_CITY));
            person.put(PERSON_STATE, record.get(PERSON_STATE));
            person.put(PERSON_ZIPCODE, record.get(PERSON_ZIPCODE));
            csvRecordBatch.add(person);
            batchSent = false;
            if (i % batchSize == 0) {
                batchSentCounter++;
                csvRecordBatch.setBatchNo(batchSentCounter);
                mongoInsertionActor.tell(csvRecordBatch, getSelf());
                csvRecordBatch = new CSVRecordBatchMsg();
                batchSent = true;
            }

        }

        // Last batch maybe pending if there are less than batch size left over records. Sending last batch of such records explicitly
        if (!batchSent) {
            batchSentCounter++;
            csvRecordBatch.setBatchNo(batchSentCounter);
            mongoInsertionActor.tell(csvRecordBatch, getSelf());
        }
        mongoInsertionActor.tell(new EndOfFileMsg(), getSelf());
        System.out.println("FileReaderActor: EOF sent");

    } catch (Exception e) {
        System.out.println("Error in CsvFileReader !!!" + e.getMessage());
    } finally {
        try {
            fileReader.close();
            csvFileParser.close();
        } catch (IOException e) {
            System.out.println("Error while closing fileReader/csvFileParser : " + e.getMessage());
        }
    }

}

From source file:fi.vm.kapa.identification.proxy.utils.SessionHandlingUtils.java

@PostConstruct
public void initSessionHandlingService() throws Exception {
    try {//from  w  w w .  j a  v a 2s.co  m
        CSVParser csvParser = new CSVParser(new FileReader(new File(attributeMapFile)),
                CSVFormat.DEFAULT.withDelimiter(';').withCommentMarker('#'));

        CSVParser csvLegacyParser = new CSVParser(new FileReader(new File(legacyAttributeMapFile)),
                CSVFormat.DEFAULT.withDelimiter(';').withCommentMarker('#'));

        /* The attribute mapper files have the following syntax:
         * [SP-attribute-key];[External-attribute-mapper-key]
         */
        csvParser.forEach(record -> attributeMap.put(record.get(0), record.get(1)));
        csvLegacyParser.forEach(record -> legacyAttributeMap.put(record.get(0), record.get(1)));
    } catch (Exception e) {
        logger.error("Error initializing CSV parser", e);
    }
}

From source file:com.appspot.relaxe.tools.CSVInsertTask.java

public void run(Connection connection, Reader input, Table table) throws IOException, SQLException {

    if (connection == null) {
        throw new NullPointerException("'connection' must not be null");
    }/*from w w w . ja v  a 2s.  com*/

    if (input == null) {
        throw new NullPointerException("'input' must not be null");
    }

    if (table == null) {
        throw new NullPointerException("'table' must not be null");
    }

    boolean committed = false;

    try {
        connection.setAutoCommit(false);
        CSVStrategy cs = new CSVStrategy('\t', '"', CSVStrategy.COMMENTS_DISABLED, false, false, false);
        CSVParser p = new CSVParser(input, cs);

        // get header line
        String[] line = p.getLine();

        // configure by using the column headers:        
        ColumnMap cm = table.getColumnMap();
        List<Identifier> names = new ArrayList<Identifier>();
        List<Column> columnList = new ArrayList<Column>();

        for (String n : line) {
            Column column = cm.get(n);

            if (column == null) {
                throw new IllegalArgumentException("column not found " + n);
            }

            columnList.add(column);
            names.add(column.getColumnName());
        }

        if (names.isEmpty()) {
            throw new IllegalStateException("no column names available");
        }

        ElementList<Identifier> nel = ElementList.newElementList(names);

        final int expectedColumnCount = line.length;
        //            int recno = 0;        

        PreparedStatement ps = null;
        InsertStatement ins = null;

        VarcharParameter[] params = new VarcharParameter[expectedColumnCount];
        ValueAssignerFactory vaf = getImplementation().getValueAssignerFactory();

        AssignmentVisitor pa = null;

        while ((line = p.getLine()) != null) {
            //                recno++;
            final int cols = line.length;
            int lineno = p.getLineNumber();

            if (cols != expectedColumnCount) {
                throw new IllegalStateException("unexpected column count: " + cols + " at line " + lineno);
            }

            if (ps == null) {

                List<RowValueConstructorElement> vl = new ArrayList<RowValueConstructorElement>(params.length);

                for (int i = 0; i < params.length; i++) {
                    Column column = columnList.get(i);
                    VarcharHolder h = parse(column, line[i]);

                    VarcharParameter param = new VarcharParameter(column, h);
                    params[i] = param;
                    vl.add(param);
                }

                RowValueConstructor rvc = AbstractRowValueConstructor.of(vl);
                ins = new InsertStatement(table, nel, rvc);

                String q = ins.generate();
                ps = connection.prepareStatement(q);
                pa = new AssignmentVisitor(vaf, ps);

                //                System.err.println("lineno: " + lineno);
                //                System.err.println("record: " + recno);
                //                System.err.println("query: " + q);
            } else {
                pa.reset();

                for (int i = 0; i < line.length; i++) {
                    Column column = columnList.get(i);
                    VarcharHolder h = parse(column, line[i]);
                    VarcharParameter param = params[i];
                    param.setValue(h);
                }
            }

            ins.traverse(null, pa);
            ps.addBatch();
        }

        int[] updateCounts = ps.executeBatch();
        updated(updateCounts);
        connection.commit();
        committed = true;
    } finally {
        if (!(committed)) {
            QueryHelper.doRollback(connection);
        }
    }
}

From source file:com.itemanalysis.jmetrik.data.JmetrikFileImporterTest.java

@Test
public void readJmetrikFileTest() {
    System.out.println("JmetrikFileImporterTest: Reading *.jmetrik file");
    CSVParser parser = null;/*from  ww w.jav a 2 s  . com*/
    Reader reader = null;

    try {
        File dataFile = FileUtils.toFile(this.getClass().getResource("/data/example-import-file.jmetrik"));
        reader = new InputStreamReader(new BOMInputStream(new FileInputStream(dataFile)), "UTF-8");

        parser = new CSVParser(reader, CSVFormat.DEFAULT.withCommentMarker('#'));
        Iterator<CSVRecord> iter = parser.iterator();
        CSVRecord temp = null;

        boolean readAttributes = false;
        boolean readData = false;
        int attCount = 0;

        while (iter.hasNext()) {
            temp = iter.next();

            if ("VERSION".equals(temp.getComment())) {
                System.out.println("VERSION: " + temp.get(0));

            } else if ("METADATA".equals(temp.getComment())) {
                System.out.println("CASES: " + temp.get(0));
            } else if ("ATTRIBUTES".equals(temp.getComment())) {
                readAttributes = true;
            } else if ("DATA".equals(temp.getComment())) {
                readAttributes = false;
                readData = true;
            }

            if (readAttributes) {
                System.out.print("ATTRIBUTE-" + attCount + ": ");
                Iterator<String> innerIter = temp.iterator();
                while (innerIter.hasNext()) {
                    System.out.print(innerIter.next());
                    if (innerIter.hasNext()) {
                        System.out.print(",");
                    }
                }
                System.out.println();
                attCount++;
            }

            if (readData) {
                Iterator<String> innerIter = temp.iterator();
                while (innerIter.hasNext()) {
                    System.out.print(innerIter.next());
                    if (innerIter.hasNext()) {
                        System.out.print(",");
                    }
                }
                System.out.println();
            }

        }

    } catch (IOException ex) {
        ex.printStackTrace();
    } finally {
        try {
            parser.close();
            reader.close();
        } catch (IOException ex) {
            ex.printStackTrace();
        }
    }

}

From source file:com.publictransitanalytics.scoregenerator.datalayer.directories.GTFSReadingServiceTypeCalendar.java

private void parseCalendarFile(final Reader calendarReader, final Multimap<LocalDate, String> serviceTypesMap)
        throws IOException {

    final CSVParser calendarParser = new CSVParser(calendarReader, CSVFormat.DEFAULT.withHeader());
    final List<CSVRecord> calendarRecords = calendarParser.getRecords();

    LocalDate earliestDate = null;
    LocalDate latestDate = null;/*from www .j av  a2  s. co m*/
    for (final CSVRecord record : calendarRecords) {
        final String serviceType = record.get("service_id");

        final LocalDate start = LocalDate.parse(record.get("start_date"), DateTimeFormatter.BASIC_ISO_DATE);
        if (earliestDate == null || start.isBefore(earliestDate)) {
            earliestDate = start;
        }

        final LocalDate end = LocalDate.parse(record.get("end_date"), DateTimeFormatter.BASIC_ISO_DATE);
        if (latestDate == null || end.isAfter(latestDate)) {
            latestDate = end;
        }

        final EnumSet<DayOfWeek> daysOfWeek = EnumSet.noneOf(DayOfWeek.class);
        if (record.get("monday").equals("1")) {
            daysOfWeek.add(DayOfWeek.MONDAY);
        }
        if (record.get("tuesday").equals("1")) {
            daysOfWeek.add(DayOfWeek.TUESDAY);
        }
        if (record.get("wednesday").equals("1")) {
            daysOfWeek.add(DayOfWeek.WEDNESDAY);
        }
        if (record.get("thursday").equals("1")) {
            daysOfWeek.add(DayOfWeek.THURSDAY);
        }
        if (record.get("friday").equals("1")) {
            daysOfWeek.add(DayOfWeek.FRIDAY);
        }
        if (record.get("saturday").equals("1")) {
            daysOfWeek.add(DayOfWeek.SATURDAY);
        }
        if (record.get("sunday").equals("1")) {
            daysOfWeek.add(DayOfWeek.SUNDAY);
        }

        LocalDate targetDate = start;
        while (!targetDate.isAfter(end)) {
            if (daysOfWeek.contains(targetDate.getDayOfWeek())) {
                serviceTypesMap.put(targetDate, serviceType);
            }
            targetDate = targetDate.plusDays(1);
        }
    }
}

From source file:br.edimarmanica.weir2.rule.filter.RulesFilter.java

public static List<String> loadFilteredRules(Site site) {
    List<String> remainingRules = new ArrayList<>();

    try (Reader in = new FileReader(new File(Paths.PATH_WEIR_V2 + "/" + site.getPath() + "/filter.csv"))) {
        try (CSVParser parser = new CSVParser(in, CSVFormat.EXCEL.withHeader())) {
            for (CSVRecord record : parser) { //para cada value
                remainingRules.add(record.get("RULE"));
            }/*from ww w  .j  a v  a2  s  .c om*/
        }
    } catch (FileNotFoundException ex) {
        Logger.getLogger(RulesDataTypeController.class.getName()).log(Level.SEVERE, null, ex);
    } catch (IOException ex) {
        Logger.getLogger(RulesDataTypeController.class.getName()).log(Level.SEVERE, null, ex);
    }
    return remainingRules;
}