Example usage for org.apache.commons.lang3 StringUtils splitPreserveAllTokens

Introduction

In this page you can find the example usage for org.apache.commons.lang3 StringUtils splitPreserveAllTokens.

Prototype

public static String[] splitPreserveAllTokens(final String str, final String separatorChars, final int max) 

Source Link

Document

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

The separator is not included in the returned String array.

Usage

From source file:org.apache.carbondata.processing.loading.DataLoadProcessBuilder.java

/**
 * set sort column info in configuration
 * @param carbonTable carbon table//  w ww  .j a v  a 2 s  . c  o  m
 * @param loadModel load model
 * @param configuration configuration
 */
private static void setSortColumnInfo(CarbonTable carbonTable, CarbonLoadModel loadModel,
        CarbonDataLoadConfiguration configuration) {
    List<String> sortCols = carbonTable.getSortColumns(carbonTable.getTableName());
    SortScopeOptions.SortScope sortScope = SortScopeOptions.getSortScope(loadModel.getSortScope());
    if (!SortScopeOptions.SortScope.LOCAL_SORT.equals(sortScope) || sortCols.size() == 0
            || StringUtils.isBlank(loadModel.getSortColumnsBoundsStr())) {
        if (!StringUtils.isBlank(loadModel.getSortColumnsBoundsStr())) {
            LOGGER.warn("sort column bounds will be ignored");
        }

        configuration.setSortColumnRangeInfo(null);
        return;
    }
    // column index for sort columns
    int[] sortColIndex = new int[sortCols.size()];
    boolean[] isSortColNoDict = new boolean[sortCols.size()];

    DataField[] outFields = configuration.getDataFields();
    int j = 0;
    boolean columnExist;
    for (String sortCol : sortCols) {
        columnExist = false;

        for (int i = 0; !columnExist && i < outFields.length; i++) {
            if (outFields[i].getColumn().getColName().equalsIgnoreCase(sortCol)) {
                columnExist = true;

                sortColIndex[j] = i;
                isSortColNoDict[j] = !outFields[i].hasDictionaryEncoding();
                j++;
            }
        }

        if (!columnExist) {
            throw new CarbonDataLoadingException("Field " + sortCol + " does not exist.");
        }
    }

    String[] sortColumnBounds = StringUtils.splitPreserveAllTokens(loadModel.getSortColumnsBoundsStr(),
            CarbonLoadOptionConstants.SORT_COLUMN_BOUNDS_ROW_DELIMITER, -1);
    for (String bound : sortColumnBounds) {
        String[] fieldInBounds = StringUtils.splitPreserveAllTokens(bound,
                CarbonLoadOptionConstants.SORT_COLUMN_BOUNDS_FIELD_DELIMITER, -1);
        if (fieldInBounds.length != sortCols.size()) {
            String msg = new StringBuilder(
                    "The number of field in bounds should be equal to that in sort columns.")
                            .append(" Expected ").append(sortCols.size()).append(", actual ")
                            .append(String.valueOf(fieldInBounds.length)).append(".")
                            .append(" The illegal bound is '").append(bound).append("'.").toString();
            throw new CarbonDataLoadingException(msg);
        }
    }

    SortColumnRangeInfo sortColumnRangeInfo = new SortColumnRangeInfo(sortColIndex, isSortColNoDict,
            sortColumnBounds, CarbonLoadOptionConstants.SORT_COLUMN_BOUNDS_FIELD_DELIMITER);
    configuration.setSortColumnRangeInfo(sortColumnRangeInfo);
}

---

From source file:org.apache.carbondata.processing.loading.steps.DataConverterProcessorStepImpl.java

/**
 * initialize partitioner for sort column ranges
 *//*from  w  ww.  java  2s.  co m*/
private void initializeSortColumnRangesPartitioner() {
    // convert user specified sort-column ranges
    SortColumnRangeInfo sortColumnRangeInfo = configuration.getSortColumnRangeInfo();
    int rangeValueCnt = sortColumnRangeInfo.getUserSpecifiedRanges().length;
    CarbonRow[] convertedSortColumnRanges = new CarbonRow[rangeValueCnt];
    for (int i = 0; i < rangeValueCnt; i++) {
        Object[] fakeOriginRow = new Object[configuration.getDataFields().length];
        String[] oneBound = StringUtils.splitPreserveAllTokens(sortColumnRangeInfo.getUserSpecifiedRanges()[i],
                sortColumnRangeInfo.getSeparator(), -1);
        // set the corresponding sort column
        int j = 0;
        for (int colIdx : sortColumnRangeInfo.getSortColumnIndex()) {
            fakeOriginRow[colIdx] = oneBound[j++];
        }
        CarbonRow fakeCarbonRow = new CarbonRow(fakeOriginRow);
        convertFakeRow(fakeCarbonRow, sortColumnRangeInfo);
        convertedSortColumnRanges[i] = fakeCarbonRow;
    }
    // sort the range bounds (sort in carbon is a little different from what we think)
    Arrays.sort(convertedSortColumnRanges,
            new RawRowComparator(sortColumnRangeInfo.getSortColumnIndex(),
                    sortColumnRangeInfo.getIsSortColumnNoDict(),
                    CarbonDataProcessorUtil.getNoDictDataTypes(configuration.getTableSpec().getCarbonTable())));

    // range partitioner to dispatch rows by sort columns
    this.partitioner = new RangePartitionerImpl(convertedSortColumnRanges,
            new RawRowComparator(sortColumnRangeInfo.getSortColumnIndex(),
                    sortColumnRangeInfo.getIsSortColumnNoDict(),
                    CarbonDataProcessorUtil.getNoDictDataTypes(configuration.getTableSpec().getCarbonTable())));
}

---

From source file:org.flowr.utils.NamingStrategy.java

private static String camelCase(String name, String separatorChars, String space) {
    String[] tokens = StringUtils.splitPreserveAllTokens(name, separatorChars, 0);
    StringBuilder b = new StringBuilder();
    for (String word : tokens) {
        if (space != null && b.length() > 0) {
            b.append(space);//from  w w w  .  j a  v a  2s .  c  o  m
        }
        b.append(StringUtils.capitalize(word));
    }
    return b.toString();
}

---

From source file:org.spicyurl.UrlParser.java

private void parseQueryFregmant(String queryFragment) {
    if (StringUtils.isEmpty(queryFragment)) {
        url.setQuery(queryFragment);//from w  w w. j  a  v a  2  s. co m
        return;
    }

    String[] parts = StringUtils.splitPreserveAllTokens(queryFragment, FRAGMENT_SEP, 2);
    url.setQuery(parts[0]);
    if (parts.length == 2) {
        url.setFragment(parts[1]);
    }
}

---

From source file:org.wikipedia.nirvana.nirvanabot.templates.TemplateFindItem.java

public static TemplateFindItem parseTemplateFindData(String templateFindData) throws BadFormatException {
    int slashes = StringTools.howMany(templateFindData, '/');
    if (slashes == 2) {
        String parts[] = StringUtils.splitPreserveAllTokens(templateFindData, "/", 3);
        parts = StringUtils.stripAll(parts);
        if (parts[0].isEmpty()) {
            throw new BadFormatException();
        }/*ww  w .  ja v a  2 s. c  om*/
        return new TemplateFindItem(parts[0], parts[1], parts[2]);
    } else if (slashes == 1) {
        String parts[] = StringUtils.splitPreserveAllTokens(templateFindData, "/", 3);
        parts = StringUtils.stripAll(parts);
        if (parts[0].isEmpty()) {
            throw new BadFormatException();
        }
        return new TemplateFindItem(parts[0], parts[1], "");
    } else if (slashes == 0) {
        if (templateFindData.trim().isEmpty()) {
            throw new BadFormatException();
        }
        return new TemplateFindItem(templateFindData.trim(), "", "");
    } else {
        throw new BadFormatException();
    }
}

---