Example usage for java.text Normalizer normalize

Introduction

In this page you can find the example usage for java.text Normalizer normalize.

Prototype

public static String normalize(CharSequence src, Form form)

Source Link

Document

Normalize a sequence of char values.

Usage

From source file:com.albert.util.StringUtilCommon.java

/**
 * Convert string  to ascii .it returns ? for
 * non ascii characters//from  w  w  w  .  jav  a2 s  . c  o m
 * @param s
 * @return ascii format of s
 */
public static String toAscii(String s) {

    String s1 = Normalizer.normalize(s, Normalizer.Form.NFKD);
    String regex = "[\\p{InCombiningDiacriticalMarks}]+";
    String s2 = "";
    try {
        s2 = new String(s1.replaceAll(regex, "").getBytes("ascii"), "ascii");
    } catch (UnsupportedEncodingException e) {
        log.error("toAscii failed: " + s, e);
        return s1;
    }

    return s2;

}

From source file:org.betaconceptframework.astroboa.engine.jcr.util.CmsRepositoryEntityUtils.java

public String deAccent(String systemName) {

    String nfdNormalizedString = Normalizer.normalize(systemName, Normalizer.Form.NFD);

    return CmsConstants.DIACRITICAL_MARKS.matcher(nfdNormalizedString).replaceAll("");
}

From source file:org.esupportail.portlet.filemanager.services.ServersAccessService.java

private static String unAccent(String s) {
    String temp = Normalizer.normalize(s, Normalizer.Form.NFD);
    Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
    return pattern.matcher(temp).replaceAll("");
}

From source file:com.money.manager.ex.common.CategoryListFragment.java

public CategoryExpandableListAdapter getAdapter(Cursor data) {
    if (data == null)
        return null;

    mCategories.clear();/*from   ww w  .j av a2s. co m*/
    mSubCategories.clear();
    mPositionToExpand.clear();
    // create core and fixed string filter to highlight
    Core core = new Core(getActivity().getApplicationContext());
    String filter = mCurFilter != null ? mCurFilter.replace("%", "") : "";

    int key = -1;
    List<QueryCategorySubCategory> listSubCategories = null;

    // reset cursor if getting back on the fragment.
    if (data.getPosition() > 0) {
        data.moveToPosition(Constants.NOT_SET);
    }

    while (data.moveToNext()) {
        if (key != data.getInt(data.getColumnIndex(QueryCategorySubCategory.CATEGID))) {
            // check if listCategories > 0
            if (mCategories.size() > 0 && listSubCategories != null) {
                mSubCategories.put(mCategories.get(mCategories.size() - 1), listSubCategories);
            }
            // update key
            key = data.getInt(data.getColumnIndex(QueryCategorySubCategory.CATEGID));

            // create instance category
            Category category = new Category();
            category.setId(data.getInt(data.getColumnIndex(QueryCategorySubCategory.CATEGID)));
            category.setName(core
                    .highlight(filter, data.getString(data.getColumnIndex(QueryCategorySubCategory.CATEGNAME)))
                    .toString());

            // add list
            mCategories.add(category);
            listSubCategories = new ArrayList<>();
        }

        if (data.getInt(data.getColumnIndex(QueryCategorySubCategory.SUBCATEGID)) != Constants.NOT_SET) {
            QueryCategorySubCategory subCategory = new QueryCategorySubCategory(getActivity());
            // subcategory
            subCategory.setSubCategId(data.getInt(data.getColumnIndex(QueryCategorySubCategory.SUBCATEGID)));
            subCategory.setSubcategoryName(core.highlight(filter,
                    data.getString(data.getColumnIndex(QueryCategorySubCategory.SUBCATEGNAME))));
            subCategory.setCategId(data.getInt(data.getColumnIndex(QueryCategorySubCategory.CATEGID)));
            subCategory.setCategName(core.highlight(filter,
                    data.getString(data.getColumnIndex(QueryCategorySubCategory.CATEGNAME))));
            // add to hashmap
            listSubCategories.add(subCategory);
            // check if expand group
            if (!TextUtils.isEmpty(filter)) {
                String normalizedText = Normalizer
                        .normalize(subCategory.getSubcategoryName(), Normalizer.Form.NFD)
                        .replaceAll("\\p{InCombiningDiacriticalMarks}+", "").toLowerCase();
                if ((normalizedText.indexOf(filter) >= 0)
                        && (!mPositionToExpand.contains(mCategories.size() - 1))) {
                    mPositionToExpand.add(mCategories.size() - 1);
                }
            }
        }
    }
    if (mCategories.size() > 0 && listSubCategories != null) {
        mSubCategories.put(mCategories.get(mCategories.size() - 1), listSubCategories);
    }

    boolean showSelector = mAction.equals(Intent.ACTION_PICK);
    CategoryExpandableListAdapter adapter = new CategoryExpandableListAdapter(getActivity(), mLayout,
            mCategories, mSubCategories, showSelector);
    adapter.setIdChildChecked(mIdGroupChecked, mIdChildChecked);
    return adapter;
}

From source file:org.apache.pdfbox.text.TextPosition.java

/**
 * Combine the diacritic, for example, convert non-combining diacritic characters to their
 * combining counterparts./*from ww  w .jav  a 2s . c o m*/
 *
 * @param str String to normalize
 * @return Normalized string
 */
private String combineDiacritic(String str) {
    // Unicode contains special combining forms of the diacritic characters which we want to use
    int codePoint = str.codePointAt(0);

    // convert the characters not defined in the Unicode spec
    if (DIACRITICS.containsKey(codePoint)) {
        return DIACRITICS.get(codePoint);
    } else {
        return Normalizer.normalize(str, Normalizer.Form.NFKC).trim();
    }
}

From source file:org.sejda.sambox.text.TextPosition.java

/**
 * Combine the diacritic, for example, convert non-combining diacritic characters to their combining counterparts.
 *
 * @param str String to normalize/*  w w  w. j av a2  s. c o  m*/
 * @return Normalized string
 */
private String combineDiacritic(String str) {
    // Unicode contains special combining forms of the diacritic characters which we want to use
    int codePoint = str.codePointAt(0);

    // convert the characters not defined in the Unicode spec
    if (DIACRITICS.containsKey(codePoint)) {
        return DIACRITICS.get(codePoint);
    }
    return Normalizer.normalize(str, Normalizer.Form.NFKC).trim();
}

From source file:org.nuxeo.ecm.platform.semanticentities.service.LocalEntityServiceImpl.java

public String normalizeName(String name) {
    // remove punctuation and normalize whitespaces
    name = name.replaceAll(SEPARATOR_CHARS_TO_IGNORE, " ").trim();

    // strip accents and diacritics
    name = Normalizer.normalize(name, Normalizer.Form.NFD).replaceAll(CHARS_TO_IGNORE, "");

    // make name lookups case insensitive by normalizing case
    return name.toLowerCase();
}

From source file:nl.inl.util.StringUtil.java

/**
 * Convert accented letters to their unaccented counterparts.
 *
 * @param input/*from   w w  w  .  ja  v  a  2  s.c o m*/
 *            the string possibly containing accented letters.
 * @return the unaccented version
 */
public static String removeAccents(String input) {
    // Separate characters into base character and diacritics characters
    String normalized = Normalizer.normalize(input, Normalizer.Form.NFD);

    // Remove diacritics
    return PATT_DIACRITICS.matcher(normalized).replaceAll("");
}

From source file:br.com.blackhubos.eventozero.util.Framework.java

/**
 * Remove acentos e afins./*w w  w.j av a  2  s.c  o m*/
 *
 * @param arg A string a ser convertida
 * @return A string processada
 */
public static String normalize(String arg) {
    arg = Normalizer.normalize(arg, Normalizer.Form.NFD);
    arg = arg.replaceAll("[^\\p{ASCII}]", "");
    return arg;
}

From source file:org.mycore.common.MCRUtils.java

private static String getHash(int iterations, byte[] salt, String text, String algorithm)
        throws NoSuchAlgorithmException {
    MessageDigest digest;//from   www. j  a v  a 2  s .co  m
    if (--iterations < 0) {
        iterations = 0;
    }
    byte[] data;
    try {
        digest = MessageDigest.getInstance(algorithm);
        text = Normalizer.normalize(text, Form.NFC);
        if (salt != null) {
            digest.update(salt);
        }
        data = digest.digest(text.getBytes("UTF-8"));
        for (int i = 0; i < iterations; i++) {
            data = digest.digest(data);
        }
    } catch (UnsupportedEncodingException e) {
        throw new MCRException("Could not get " + algorithm + " checksum", e);
    }
    return toHexString(data);
}