Example usage for org.apache.commons.lang StringUtils splitPreserveAllTokens

Introduction

In this page you can find the example usage for org.apache.commons.lang StringUtils splitPreserveAllTokens.

Prototype

public static String[] splitPreserveAllTokens(String str, String separatorChars) 

Source Link

Document

Splits the provided text into an array, separators specified, preserving all tokens, including empty tokens created by adjacent separators.

Usage

From source file:corner.util.VectorUtils.java

/**
 * ??String/*from  w ww  .  j  ava  2 s  .  c  o m*/
 * split,',',split?String[][""],?List
 * 
 * @param str
 * @param regex
 * @return
 */
public static List<String> VectorSplit(String str, String regex) {
    if (str == null || str.trim().length() <= 0) {
        return null;
    } else {

        return Arrays.asList(StringUtils.splitPreserveAllTokens(str, ","));
    }
}

---

From source file:com.npower.dm.model.TestGenerateModelXMLByCSV.java

public void testStringUtils() throws Exception {
    {//  ww  w  .j  a  v a  2  s  .  c o  m
        String line1 = "0,1,2,3,4,5,6,7,8,9";
        String[] result = StringUtils.splitPreserveAllTokens(line1, ',');
        assertEquals(10, result.length);
    }
    {
        String line1 = ",1,,3,,5,,7,,9";
        String[] result = StringUtils.splitPreserveAllTokens(line1, ',');
        assertEquals(10, result.length);
        assertEquals("", result[0]);
        assertEquals("1", result[1]);
        assertEquals("", result[2]);
        assertEquals("3", result[3]);
        assertEquals("", result[4]);
        assertEquals("5", result[5]);
        assertEquals("", result[6]);
        assertEquals("7", result[7]);
        assertEquals("", result[8]);
        assertEquals("9", result[9]);
    }

    {
        String src = "break_list_of_links_with_br_element_recommended ";
        String result = WordUtils.capitalize(src, new char[] { '_', ' ' });
        assertEquals("Break_List_Of_Links_With_Br_Element_Recommended ", result);
    }
}

---

From source file:com.mapr.db.utils.ImportCSV.java

public void readAndImportCSV(String path, String delimiter) {

    String dataLine = "";
    String[] dataList;//from w  ww . j  av a  2 s . c  o m
    String data = "";

    ArrayList<Object> values = new ArrayList<>();
    int countColumnsInData = 0;

    try {
        Scanner scan = new Scanner(new FileReader(path));

        while (scan.hasNextLine()) {
            countColumnsInData = 0;
            dataLine = scan.nextLine().trim();
            //System.out.println(dataLine);
            if (dataLine.endsWith(delimiter)) {
                dataLine = dataLine.substring(0, dataLine.length() - 1);
            }
            dataList = StringUtils.splitPreserveAllTokens(dataLine, delimiter);

            for (int i = 0; i < dataList.length; i++) {

                data = dataList[i];
                if (data.isEmpty()) {
                    if (valueTypesInSchema.get(i) == "String") {
                        data = "null";
                    } else {
                        data = "0";
                    }
                }

                switch (valueTypesInSchema.get(i).toLowerCase()) {
                case "int":
                case "integer":
                case "bigint":
                case "long":
                    values.add(countColumnsInData, Long.valueOf(data));
                    break;
                case "float":
                case "double":
                    values.add(countColumnsInData, Double.valueOf(data));
                    break;
                case "date":
                    values.add(countColumnsInData, Date.valueOf(data));
                    break;
                default:
                    values.add(countColumnsInData, String.valueOf(data));
                    break;
                }

                //System.out.println("Inserting " + values.get(countColumnsInData)
                //        + " into column " + columnNamesInSchema.get(countColumnsInData));

                countColumnsInData++;
            }
            insertDocument(values, countColumnsInData, maprdbTable, maprdbTablePath);
        }
        scan.close();
    } catch (Exception e) {
        System.out.println("Error importing text:\n\t" + dataLine + "\ninto\n\t" + maprdbTablePath);
        e.printStackTrace();
        System.exit(-1);
    }
}

---

From source file:corner.util.VectorUtilsTest.java

public void testVectorSplit() {
    List<String> strList = VectorUtils.VectorSplit(COMMAEND_ARR[0], ",");
    assertEquals(4, strList.size());//w ww  .ja  v  a 2 s  .c om
    assertEquals(strList.get(0).toString(), "");
    assertEquals(strList.get(1).toString(), "a");
    assertEquals(strList.get(2).toString(), "b");
    assertEquals(strList.get(3).toString(), "");

    List<String> strList1 = VectorUtils.VectorSplit(COMMAEND_ARR[1], ",");
    assertEquals(2, strList1.size());
    assertEquals(strList1.get(0).toString(), "");
    assertEquals(strList1.get(1).toString(), "");

    List<String> strList2 = VectorUtils.VectorSplit(COMMAEND_ARR[2], ",");
    assertEquals(4, strList2.size());
    assertEquals(strList2.get(0).toString(), "");
    assertEquals(strList2.get(1).toString(), "");

    List<String> strList3 = VectorUtils.VectorSplit(COMMAEND_ARR[3], ",");
    assertEquals(3, strList3.size());
    assertEquals(strList3.get(0).toString(), "a");
    assertEquals(strList3.get(1).toString(), "b");
    assertEquals(strList3.get(2).toString(), "");

    List<String> strList4 = VectorUtils.VectorSplit("1,2,,,,", ",");
    assertEquals(6, strList4.size());

    String[] list5 = StringUtils.splitPreserveAllTokens("1,2,,,,", ",");

    assertEquals(6, list5.length);
}

---

From source file:edu.cornell.med.icb.io.TsvToFromMap.java

/**
 * Given a line of text, convert it to a Map[columnName, value] of data.
 * @param line the line of data to convert to the the Map
 * @return the Map of data//from   www.  j ava  2  s .  c om
 * @throws IOException error converting the data, the number of columns found
 * in the data is incorrect given the number of columns expected in the TSV file
 */
public LinkedHashToMultiTypeMap<String> readDataToMap(final String line) throws IOException {
    if (line.startsWith("#")) {
        return null;
    }
    final String[] parts = StringUtils.splitPreserveAllTokens(line, '\t');
    if ((!lenientColumnCount) && (parts.length != numColumnHeaders)) {
        throw new IOException(
                String.format("Line should have %d columns but has %d", numColumnHeaders, parts.length));
    }
    final LinkedHashToMultiTypeMap<String> result = new LinkedHashToMultiTypeMap<String>();
    int i = 0;
    final int numActualParts = parts.length;
    for (final String columnHeader : columnHeaders) {
        if (lenientColumnCount && (i >= numActualParts)) {
            result.put(columnHeader, "");
        } else {
            result.put(columnHeader, parts[i]);
        }
        i++;
    }
    return result;
}

---

From source file:edu.ku.brc.specify.toycode.BugParse.java

/**
 * @param lines/* w  w  w.ja v a 2  s .c  o  m*/
 */
protected void createChart(final List<String> lines, final String engineer) {

    int[] mins = new int[lines.size() - 1];
    for (int index = 1; index < lines.size(); index++) {
        String line = lines.get(index);
        String[] values = StringUtils.splitPreserveAllTokens(line, ",");
        int inx = 0;
        while (inx < values.length && values[inx].equals("0")) {
            inx++;
        }
        mins[index - 1] = inx < values.length ? inx : Integer.MAX_VALUE;
        System.err.println(mins[index - 1]);
    }

    int startInx = Integer.MAX_VALUE;
    for (int min : mins) {
        startInx = Math.min(startInx, min);
        System.out.println(min + "  " + startInx);
    }

    DefaultCategoryDataset dataset = new DefaultCategoryDataset();

    String[] headers = StringUtils.split(lines.get(0), ",");
    int len = headers.length - startInx;
    System.out.println(headers.length + "  " + len);
    List<double[]> valArray = new Vector<double[]>();

    for (int i = 1; i < lines.size(); i++) {
        String[] values = StringUtils.splitPreserveAllTokens(lines.get(i), ",");
        double[] vals = new double[len];
        int inx = 0;
        double prev = -1;
        for (int j = startInx; j < headers.length; j++) {
            if (StringUtils.isNotEmpty(values[j])) {
                prev = Double.parseDouble(values[j]);
                vals[inx++] = prev;
            } else {
                vals[inx++] = 0.0;
            }
        }
        valArray.add(vals);
    }

    double[] vals = valArray.get(0);
    for (int i = 0; i < vals.length; i++) {
        dataset.addValue(vals[i], "Bugs", headers[i + startInx]);
    }
    vals = valArray.get(1);
    for (int i = 0; i < vals.length; i++) {
        dataset.addValue(vals[i], "Resolved", headers[i + startInx]);
    }

    vals = valArray.get(2);
    for (int i = 0; i < vals.length; i++) {
        dataset.addValue(vals[i], "Open", headers[i + startInx]);
    }

    JFreeChart chart = ChartFactory.createLineChart("Bugs - " + engineer, "Time", "Bugs", dataset,
            PlotOrientation.VERTICAL, true, true, false);
    final CategoryPlot plot = (CategoryPlot) chart.getPlot();
    //plot.setBackgroundPaint(Color.lightGray);
    //plot.setRangeGridlinePaint(Color.white);

    // customise the range axis...
    final NumberAxis rangeAxis = (NumberAxis) plot.getRangeAxis();
    rangeAxis.setStandardTickUnits(NumberAxis.createIntegerTickUnits());
    rangeAxis.setAutoRangeIncludesZero(false);
    rangeAxis.setAxisLineVisible(true);

    CategoryAxis catAxis = plot.getDomainAxis();
    catAxis.setAxisLineVisible(true);
    catAxis.setTickMarksVisible(true);

    ChartFrame frame = new ChartFrame("", chart, false);
    frame.setBackground(Color.WHITE);
    frame.setSize(500, 500);
    frame.setVisible(true);
}

---

From source file:com.seer.datacruncher.utils.generic.CommonUtils.java

/**
 * Splits <tt>str</tt> around matches of the delimiter character.
 *
 * @param   str//www .j  a va 2  s.  co m
 *          the string to split
 *
 * @param   delimiter
 *          the delimiting field string
 *
 * @param   chrDelim
 *          the delimiting character
 *
 * @return  the array of strings computed by splitting string
 *          around matches of the delimiter character.
 *
 **/
public static String[] fieldSplit(String str, String delimiter, char chrDelim) {
    if ((str.indexOf(chrDelim, 0)) < 0) {
        return StringUtils.splitPreserveAllTokens(str, delimiter);
    } else {
        ArrayList<String> list = new ArrayList<String>();
        String record;
        List<String> streamsList = Arrays.asList(StringUtils.splitPreserveAllTokens(str, delimiter));
        int fEnd;
        for (int i = 0; i < streamsList.size(); i++) {
            record = streamsList.get(i);
            if ((record.indexOf(chrDelim, 0)) < 0) {
                list.add(record);
            } else {
                if (record.startsWith(chrDelim + "")) { // check in start field
                    fEnd = record.indexOf(chrDelim, 1); // find end
                    if (fEnd < 0) { //not found
                        if ((i + 1) < streamsList.size()) {
                            streamsList.set(i + 1, record + delimiter + streamsList.get(i + 1));
                        } else {
                            list.add(record);
                        }
                    } else {
                        list.add(record);
                    }
                }
            }
        }
        int resultSize = list.size();
        String[] result = new String[resultSize];
        return list.subList(0, resultSize).toArray(result);
    }
}

---

From source file:com.mapr.db.utils.ImportCSV_MR.java

public DBDocument readAndImportCSV(String dataLine) {

    ArrayList<Object> values = new ArrayList<>();
    int countColumnsInData = 0;

    if (dataLine.endsWith(conf.get("delimiter"))) {
        dataLine = dataLine.substring(0, dataLine.length() - 1);
    }/*from   w  w  w  .j av  a  2  s  .  c om*/

    String[] dataList = StringUtils.splitPreserveAllTokens(dataLine, conf.get("delimiter"));

    for (int i = 0; i < dataList.length; i++) {

        logger.info("Processing column " + i + " off " + dataList.length);
        System.out.println("Processing column " + i + " off " + dataList.length);

        String data = dataList[i];

        logger.info("Processing data " + data);
        System.out.println("Processing data " + data);

        if (data.isEmpty()) {
            if (conf.getStrings("valueTypesInSchema")[i] == "String") {
                data = "null";
            } else {
                data = "0";
            }
        }

        printSchema();

        switch (conf.getStrings("valueTypesInSchema")[i].toLowerCase()) {
        case "int":
        case "integer":
        case "bigint":
        case "long":
            values.add(countColumnsInData, Long.valueOf(data));
            break;
        case "float":
        case "double":
            values.add(countColumnsInData, Double.valueOf(data));
            break;
        case "date":
            values.add(countColumnsInData, Date.valueOf(data));
            break;
        default:
            values.add(countColumnsInData, String.valueOf(data));
            break;
        }

        countColumnsInData++;
    }
    return insertDocument(values, countColumnsInData, conf.get("tablePath"));
}

---

From source file:de.awtools.grooocle.inout.InOutUtils.java

/**
 * Splits a text String into pieces. Example:
 * //from  ww w .j  a v a 2s .  c om
 * <pre>
 * Groovy:
 * def expected = [&quot;&quot;, &quot;a&quot;, &quot;b&quot;, &quot;c&quot;, &quot;&quot;]
 * assert expected == InOutUtils.split(&quot;|a|b|c|&quot;, &quot;|&quot;)
 * </pre>
 * 
 * @param _text
 *            The text for splitting.
 * 
 * @param _seperator
 *            The seperator.
 * 
 * @return The splitted string.
 */
public static String[] split(final String _text, final String _seperator) {
    return StringUtils.splitPreserveAllTokens(_text, _seperator);
}

---

From source file:edu.mayo.informatics.lexgrid.convert.directConversions.NCIThesaurusHistoryFileToSQL.java

private void loadSystemReleaseFile(URI filePath, boolean failOnAllErrors) throws Exception {
    BufferedReader reader = getReader(filePath);

    int lineNumber = 0;
    String line = reader.readLine();
    while (line != null) {
        // format of line is
        // releaseDate|releaseAgency|releaseURN|releaseId|basedOnRelease|entityDescription
        if (line.startsWith("#") || line.length() == 0) {
            line = reader.readLine();/*from  w w  w .j a  va  2 s  .  c  om*/
            continue;
        }

        String[] tokens = StringUtils.splitPreserveAllTokens(line, token_);

        SystemRelease systemRelease = new SystemRelease();
        try {
            systemRelease.setReleaseDate(new Timestamp(dateFormat_.parse(tokens[0]).getTime()));
        } catch (ParseException e) {
            md_.fatalAndThrowException("Invalid date on line " + lineNumber, e);
        }
        systemRelease.setReleaseAgency(tokens[1]);
        systemRelease.setReleaseURI(tokens[2]);
        systemRelease.setReleaseId(tokens[3]);
        systemRelease.setBasedOnRelease(tokens[4]);

        EntityDescription ed = new EntityDescription();

        ed.setContent(tokens[5]);
        systemRelease.setEntityDescription(ed);

        LexEvsServiceLocator.getInstance().getDatabaseServiceManager().getNciHistoryService()
                .insertSystemRelease(this.codingSchemeUri, systemRelease);

        lineNumber++;
        line = reader.readLine();
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• »