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

Introduction

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

Prototype

public Map<String, Integer> getHeaderMap() 

Source Link

Document

Returns a copy of the header map that iterates in column order.

Usage

From source file:umich.ms.batmass.filesupport.files.types.mzrt.model.MzrtFile.java

public void load() throws DataLoadingException {

    int[] counts = new int[3]; // [0] - \r\n, [1] - \n, [2] - \r
    final String[] separators = { "\r\n", "\n", "\r" };
    // detecting line separator
    try (InputStreamReader isr = new InputStreamReader(
            new BufferedInputStream(new FileInputStream(file.toFile())), Charsets.UTF_8)) {
        int c;//from w  w w.j  a v a  2s .  c om
        int encountered = 0;
        boolean isPrevR = false;
        int cutoff = 50;
        readLoop: while ((c = isr.read()) != -1) {
            char ch = (char) c;
            switch (ch) {
            case '\r':
                if (++counts[2] > cutoff) {
                    break readLoop;
                }
                isPrevR = true;
                break;
            case '\n':
                if (isPrevR) {
                    counts[2]--;
                    if (++counts[0] > cutoff) {
                        break readLoop;
                    }
                } else {
                    if (++counts[1] > cutoff) {
                        break readLoop;
                    }
                }
                isPrevR = false;
                break;
            default:
                isPrevR = false;
            }
        }
    } catch (IOException ex) {
        throw new DataLoadingException("Could not detect line separator", ex);
    }

    List<Integer> idxMax = new ArrayList<>();
    for (int i = 0; i < counts.length; i++) {
        if (idxMax.isEmpty()) {
            idxMax.add(i);
        } else if (counts[i] > counts[idxMax.get(0)]) {
            idxMax.clear();
            idxMax.add(i);
        } else if (counts[i] == counts[idxMax.get(0)]) {
            idxMax.add(i);
        }
    }

    String recordSeparator;
    if (idxMax.size() > 1) {
        if (idxMax.contains(0)) {
            recordSeparator = separators[0];
        } else if (idxMax.contains(1)) {
            recordSeparator = separators[1];
        } else {
            recordSeparator = separators[idxMax.get(0)];
        }
    } else {
        recordSeparator = separators[idxMax.get(0)];
    }

    // detecting delimiter
    char delimiter;
    try (BufferedReader br = new BufferedReader(new FileReader(file.toFile()))) {
        List<String> lines = new ArrayList<>();
        String line;
        int numTestLines = 10;
        while ((line = br.readLine()) != null) {
            if (!line.isEmpty()) {
                lines.add(line);
                if (lines.size() >= numTestLines)
                    break;
            }
        }

        delimiter = guessDelimiter(lines);
    } catch (IOException ex) {
        throw new DataLoadingException("Could not detect delimiter character", ex);
    }

    try (BufferedReader br = new BufferedReader(new FileReader(file.toFile()))) {
        CSVFormat fmt = CSVFormat.newFormat(delimiter);
        fmt = fmt.withHeader().withIgnoreEmptyLines(true).withTrim(true).withIgnoreHeaderCase(true)
                .withQuoteMode(QuoteMode.NON_NUMERIC).withRecordSeparator(recordSeparator).withQuote('"');

        CSVParser parser = fmt.parse(br);

        records = parser.getRecords();
        header = parser.getHeaderMap();

        String[] colNames = { HEAD_MZLO, HEAD_MZHI, HEAD_RTLO, HEAD_RTHI };
        for (int i = 0; i < colNames.length; i++) {
            Integer index = header.get(colNames[i]);
            if (index == null)
                throw new DataLoadingException(String.format("Missing header column [%s]", colNames[i]));
            indexesMzRtColorOpacity[i] = index;
        }
        Integer indexColor = header.get(HEAD_COLOR);
        if (indexColor != null && indexColor >= 0)
            indexesMzRtColorOpacity[4] = indexColor;
        Integer indexOpacity = header.get(HEAD_OPACITY);
        if (indexOpacity != null && indexOpacity >= 0)
            indexesMzRtColorOpacity[5] = indexOpacity;

    } catch (IOException ex) {
        throw new DataLoadingException(ex);
    }
}

---

From source file:us.parr.animl.data.DataTable.java

public static DataTable loadCSV(String fileName, String formatType, VariableType[] colTypesOverride,
        String[] colNamesOverride, boolean hasHeaderRow) {
    try {/* w  w w  . j ava  2 s .com*/
        // use apache commons io + csv to load but convert to list of String[]
        // byte-order markers are handled if present at start of file.
        FileInputStream fis = new FileInputStream(fileName);
        final Reader reader = new InputStreamReader(new BOMInputStream(fis), "UTF-8");
        CSVFormat format;
        if (formatType == null) {
            format = hasHeaderRow ? CSVFormat.RFC4180.withHeader() : CSVFormat.RFC4180;
        } else {
            switch (formatType.toLowerCase()) {
            case "tsv":
                format = hasHeaderRow ? CSVFormat.TDF.withHeader() : CSVFormat.TDF;
                break;
            case "mysql":
                format = hasHeaderRow ? CSVFormat.MYSQL.withHeader() : CSVFormat.MYSQL;
                break;
            case "excel":
                format = hasHeaderRow ? CSVFormat.EXCEL.withHeader() : CSVFormat.EXCEL;
                break;
            case "rfc4180":
            default:
                format = hasHeaderRow ? CSVFormat.RFC4180.withHeader() : CSVFormat.RFC4180;
                break;
            }
        }
        final CSVParser parser = new CSVParser(reader, format);
        List<String[]> rows = new ArrayList<>();
        int numHeaderNames = parser.getHeaderMap().size();
        try {
            for (final CSVRecord record : parser) {
                String[] row = new String[record.size()];
                for (int j = 0; j < record.size(); j++) {
                    row[j] = record.get(j);
                }
                rows.add(row);
            }
        } finally {
            parser.close();
            reader.close();
        }

        VariableType[] actualTypes = computeColTypes(rows, numHeaderNames);

        Set<String> colNameSet = parser.getHeaderMap().keySet();
        String[] colNames = colNameSet.toArray(new String[colNameSet.size()]);
        if (colNamesOverride != null) {
            colNames = colNamesOverride;
        }
        if (colTypesOverride != null) {
            actualTypes = colTypesOverride;
        }
        return fromStrings(rows, actualTypes, colNames, false);
    } catch (Exception e) {
        throw new IllegalArgumentException("Can't open and/or read " + fileName, e);
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• »