Example usage for java.text Normalizer normalize

List of usage examples for java.text Normalizer normalize

  1. HOME
  2. Java
  3. java
  4. java.text.*
  5. Normalizer
  6. 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:org.opensextant.util.TextUtils.java

/**
 * Normalize to "Normalization Form Canonical Decomposition" (NFD) REF:
 * http:/*  ww w .  j a  v a 2s.co m*/
 * //stackoverflow.com/questions/3610013/file-listfiles-mangles-unicode-
 * names-with-jdk-6-unicode-normalization-issues This supports proper file
 * name retrieval from file system, among other things. In many situations
 * we see unicode file names -- Java can list them, but in using the
 * Java-provided version of the filename the OS/FS may not be able to find
 * the file by the name given in a particular normalized form.
 *
 * @param str
 *            text
 * @return normalized string, encoded with NFD bytes
 */
public static String normalizeUnicode(String str) {
    Normalizer.Form form = Normalizer.Form.NFD;
    if (!Normalizer.isNormalized(str, form)) {
        return Normalizer.normalize(str, form);
    }
    return str;
}

From source file:bfile.util.StringUtils.java

/**
 * <p>Removes diacritics (~= accents) from a string. The case will not be altered.</p>
 * <p>For instance, '&agrave;' will be replaced by 'a'.</p>
 * <p>Note that ligatures will be left as is.</p>
 *
 * <pre>//from  ww w. ja  v a 2s  . c  o  m
 * StringUtils.stripAccents(null)                = null
 * StringUtils.stripAccents("")                  = ""
 * StringUtils.stripAccents("control")           = "control"
 * StringUtils.stripAccents("&eacute;clair")     = "eclair"
 * </pre>
 *
 * @param input String to be stripped
 * @return input text with diacritics removed
 *
 * @since 3.0
 */
// See also Lucene's ASCIIFoldingFilter (Lucene 2.9) that replaces accented characters by their unaccented equivalent (and uncommitted bug fix: https://issues.apache.org/jira/browse/LUCENE-1343?focusedCommentId=12858907&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#action_12858907).
public static String stripAccents(final String input) {
    if (input == null) {
        return null;
    }
    final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$
    final StringBuilder decomposed = new StringBuilder(Normalizer.normalize(input, Normalizer.Form.NFD));
    convertRemainingAccentCharacters(decomposed);
    // Note that this doesn't correctly remove ligatures...
    return pattern.matcher(decomposed).replaceAll(StringUtils.EMPTY);
}

From source file:com.rdm.common.util.StringUtils.java

/**
 * <p>Removes diacritics (~= accents) from a string. The case will not be altered.</p>
 * <p>For instance, '&agrave;' will be replaced by 'a'.</p>
 * <p>Note that ligatures will be left as is.</p>
 *
 * <pre>//ww w . j ava  2s  .  c o  m
 * StringUtils.stripAccents(null)                = null
 * StringUtils.stripAccents("")                  = ""
 * StringUtils.stripAccents("control")           = "control"
 * StringUtils.stripAccents("&eacute;clair")     = "eclair"
 * </pre>
 *
 * @param input String to be stripped
 * @return input text with diacritics removed
 *
 * @since 3.0
 */
// See also Lucene's ASCIIFoldingFilter (Lucene 2.9) that replaces accented characters by their unaccented equivalent (and uncommitted bug fix: https://issues.apache.org/jira/browse/LUCENE-1343?focusedCommentId=12858907&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#action_12858907).
public static String stripAccents(final String input) {
    if (input == null) {
        return null;
    }
    final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$
    final String decomposed = Normalizer.normalize(input, Normalizer.Form.NFD);
    // Note that this doesn't correctly remove ligatures...
    return pattern.matcher(decomposed).replaceAll("");//$NON-NLS-1$
}

From source file:example.rest.ApiREST.java

public static String stripAccents(String s) {
    s = Normalizer.normalize(s, Normalizer.Form.NFD);
    s = s.replaceAll("[\\p{InCombiningDiacriticalMarks}]", "");
    return s;//from ww w. ja v a  2s. c  o  m
}

From source file:org.exoplatform.utils.ExoDocumentUtils.java

/**
 * On Platform 4.1-M2, the upload service renames the uploaded file. Therefore
 * the link to this file in the activity becomes incorrect. To fix this, we
 * rename the file before upload so the same name is used in the activity.
 * //from  w  w w. j  a  v  a2  s.c o  m
 * @param originalName the name to clean
 * @return a String without forbidden characters
 */
public static String cleanupFilename(String originalName) {
    final String TILDE_HYPHENS_COLONS_SPACES = "[~_:\\s]";
    final String MULTIPLE_HYPHENS = "-{2,}";
    final String FORBIDDEN_CHARS = "[`!@#\\$%\\^&\\*\\|;\"'<>/\\\\\\[\\]\\{\\}\\(\\)\\?,=\\+\\.]+";
    String name = originalName;
    String ext = "";
    int lastDot = name.lastIndexOf('.');
    if (lastDot > 0 && lastDot < name.length()) {
        ext = name.substring(lastDot); // the ext with the dot
        name = name.substring(0, lastDot); // the name before the ext
    }
    // [~_:\s] Replaces ~ _ : and spaces by -
    name = Pattern.compile(TILDE_HYPHENS_COLONS_SPACES).matcher(name).replaceAll("-");
    // [`!@#\$%\^&\*\|;"'<>/\\\[\]\{\}\(\)\?,=\+\.]+ Deletes forbidden chars
    name = Pattern.compile(FORBIDDEN_CHARS).matcher(name).replaceAll("");
    // Converts accents to regular letters
    name = Normalizer.normalize(name, Normalizer.Form.NFD).replaceAll("[^\\p{ASCII}]", "");
    // Replaces upper case characters by lower case
    // Locale loc = new
    // Locale(SettingUtils.getPrefsLanguage(getApplicationContext()));
    name = name.toLowerCase(Locale.getDefault());
    // Remove consecutive -
    name = Pattern.compile(MULTIPLE_HYPHENS).matcher(name).replaceAll("-");
    // Save
    return (name + ext);
}

From source file:uk.sipperfly.ui.BackgroundWorker.java

/**
 * create bag-info.xml file at transfer destination
 *//*from   w w  w  .j  ava  2s  .  co m*/
public void createXML(String payload, String date, String size) {
    try {
        char[] charArray = { '<', '>', '&', '"', '\\', '!', '#', '$', '%', '\'', '(', ')', '*', '.', ':', '+',
                ',', '/', ';', '=', '?', '@', '[', ']', '^', '`', '{', '|', '}', '~' };
        //      List<char[]> asList = Arrays.asList(charArray);
        DocumentBuilderFactory docFactory = DocumentBuilderFactory.newInstance();
        DocumentBuilder docBuilder = docFactory.newDocumentBuilder();
        Document doc = docBuilder.newDocument();
        Element rootElement = doc.createElement("transfer_metadata");
        doc.appendChild(rootElement);

        Attr attr1 = doc.createAttribute("xmlns:xsi");
        attr1.setValue("http://www.w3.org/2001/XMLSchema-instance");
        rootElement.setAttributeNode(attr1);

        Element payLoad = doc.createElement("Payload-Oxum");
        payLoad.appendChild(doc.createTextNode(payload));
        rootElement.appendChild(payLoad);

        Element baggingDate = doc.createElement("Bagging-Date");
        baggingDate.appendChild(doc.createTextNode(date));
        rootElement.appendChild(baggingDate);

        Element bagsize = doc.createElement("Bag-Size");
        bagsize.appendChild(doc.createTextNode(size));
        rootElement.appendChild(bagsize);

        BagInfoRepo bagInfoRepo = new BagInfoRepo();
        List<BagInfo> bagInfo = bagInfoRepo.getOneOrCreateOne();

        for (BagInfo b : bagInfo) {
            StringBuilder stringBuilder = new StringBuilder();
            char[] txt = Normalizer.normalize(b.getLabel(), Normalizer.Form.NFD).toCharArray();
            for (int i = 0; i < b.getLabel().length(); i++) {
                int check = 0;
                for (int j = 0; j < charArray.length; j++) {
                    if (txt[i] == charArray[j]) {
                        check = 1;

                    }
                }
                if (check == 0) {
                    stringBuilder.append(txt[i]);
                }
            }
            Element firstname = doc.createElement(stringBuilder.toString().replace(" ", "-"));
            firstname.appendChild(doc.createTextNode(b.getValue().trim()));
            rootElement.appendChild(firstname);

        }
        // write the content into xml file
        TransformerFactory transformerFactory = TransformerFactory.newInstance();

        Transformer transformer = transformerFactory.newTransformer();
        transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        DOMSource source = new DOMSource(doc);
        StreamResult result = new StreamResult(
                new File(this.target.toString() + File.separator + "bag-info.xml"));
        transformer.transform(source, result);
    } catch (ParserConfigurationException ex) {
        Logger.getLogger(BackgroundWorker.class.getName()).log(Level.SEVERE, null, ex);
    } catch (TransformerConfigurationException ex) {
        Logger.getLogger(BackgroundWorker.class.getName()).log(Level.SEVERE, null, ex);
    } catch (TransformerException ex) {
        Logger.getLogger(BackgroundWorker.class.getName()).log(Level.SEVERE, null, ex);
    } catch (DOMException ex) {
        Logger.getLogger(BackgroundWorker.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:org.totschnig.myexpenses.util.Utils.java

/**
 * @param str/*from   w  w w . j ava 2  s.  com*/
 * @return a representation of str converted to lower case, Unicode
 *         normalization applied and markers removed this allows
 *         case-insentive comparison for non-ascii and non-latin strings works
 *         only above Gingerbread, on Froyo only lower case transformation is
 *         performed
 */
@SuppressLint({ "NewApi", "DefaultLocale" })
public static String normalize(String str) {
    str = str.toLowerCase();
    if (Build.VERSION.SDK_INT < Build.VERSION_CODES.GINGERBREAD) {
        return str;
    }
    // Credits: http://stackoverflow.com/a/3322174/1199911
    return Normalizer.normalize(str, Normalizer.Form.NFD).replaceAll("\\p{M}", "");
}

From source file:org.medici.bia.service.peoplebase.PeopleBaseServiceImpl.java

/**
 * {@inheritDoc}/* w w w .ja va  2 s . co m*/
 */
@Transactional(readOnly = false, propagation = Propagation.REQUIRED)
@Override
public People editDetailsPerson(People person) throws ApplicationThrowable {
    try {
        User user = getCurrentUser();

        People personToUpdate = getPeopleDAO().find(person.getPersonId());

        Set<AltName> altNames = personToUpdate.getAltName();
        AltName searchName = null;

        // fill fields to update person details section
        if (personToUpdate.getFirst() != null && !personToUpdate.getFirst().equals(person.getFirst())) {
            for (AltName current : altNames) {
                if (current.getAltName().equals(personToUpdate.getFirst())
                        && current.getNameType().equals(NameType.Given.toString())) {
                    current.setAltName(person.getFirst());
                    getAltNameDAO().merge(current);
                    break;
                }
            }
        }

        if (personToUpdate.getLast() != null && !personToUpdate.getLast().equals(person.getLast())) {
            for (AltName current : altNames) {
                if (current.getAltName().equals(personToUpdate.getLast())
                        && current.getNameType().equals(NameType.Family.toString())) {
                    current.setAltName(person.getLast());
                    getAltNameDAO().merge(current);
                    break;
                }
            }
        }

        if (!personToUpdate.getMapNameLf().equals(PersonUtils.generateMapNameLf(person))) {
            boolean found = false;
            String toCompare = personToUpdate.getMapNameLf();
            toCompare = Normalizer.normalize(toCompare, Normalizer.Form.NFD);
            toCompare = toCompare.replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
            toCompare = toCompare.replace(",", "");
            toCompare = toCompare.replace("(", "");
            toCompare = toCompare.replace(")", "");
            toCompare = toCompare.toUpperCase();
            for (AltName current : altNames) {
                if (current.getAltName().equals(toCompare)
                        && current.getNameType().equals(NameType.SearchName.toString())) {
                    current.setAltName(
                            Normalizer.normalize(PersonUtils.generateMapNameLf(person), Normalizer.Form.NFD));
                    current.setAltName(
                            current.getAltName().replaceAll("\\p{InCombiningDiacriticalMarks}+", ""));
                    current.setAltName(current.getAltName().replace(",", ""));
                    current.setAltName(current.getAltName().replace("(", ""));
                    current.setAltName(current.getAltName().replace(")", ""));
                    current.setAltName(current.getAltName().toUpperCase());
                    found = true;
                    getAltNameDAO().merge(current);
                    break;
                }

            }
            if (!found) {
                searchName = new AltName();
                searchName.setAltName(
                        Normalizer.normalize(PersonUtils.generateMapNameLf(person), Normalizer.Form.NFD));
                searchName.setAltName(
                        searchName.getAltName().replaceAll("\\p{InCombiningDiacriticalMarks}+", ""));
                searchName.setAltName(searchName.getAltName().replace(",", ""));
                searchName.setAltName(searchName.getAltName().toUpperCase());
                searchName.setNameType(NameType.SearchName.toString());
            }
        }

        personToUpdate.setFirst(person.getFirst());
        personToUpdate.setSucNum(person.getSucNum());
        personToUpdate.setMidPrefix(person.getMidPrefix());
        personToUpdate.setMiddle(person.getMiddle());
        personToUpdate.setLastPrefix(person.getLastPrefix());
        personToUpdate.setLast(person.getLast());
        personToUpdate.setPostLastPrefix(person.getPostLastPrefix());
        personToUpdate.setPostLast(person.getPostLast());
        personToUpdate.setGender((!person.getGender().equals(People.Gender.NULL)) ? person.getGender() : null);
        //Update setMapNameLf
        personToUpdate.setMapNameLf(PersonUtils.generateMapNameLf(personToUpdate));

        personToUpdate.setBornYear(person.getBornYear());
        if (person.getBornMonth() != null) {
            personToUpdate.setBornMonth(getMonthDAO().find(person.getBornMonth().getMonthNum()));
        } else {
            personToUpdate.setBornMonth(null);
        }

        // Born Information
        personToUpdate.setBornDay(person.getBornDay());
        personToUpdate.setBornDate(DateUtils.getLuceneDate(personToUpdate.getBornYear(),
                personToUpdate.getBornMonth(), personToUpdate.getBornDay()));
        personToUpdate.setBornApprox(person.getBornApprox());
        personToUpdate.setBornDateBc(person.getBornDateBc());
        if (!ObjectUtils.toString(person.getBornPlace()).equals("")) {
            personToUpdate.setBornPlace(getPlaceDAO().find(person.getBornPlace().getPlaceAllId()));
            if (personToUpdate.getBornPlace().getPrefFlag().equals("V")) {
                personToUpdate.setBornPlace(
                        getPlaceDAO().findPrinicipalPlace(personToUpdate.getBornPlace().getGeogKey()));
            }
        } else {
            personToUpdate.setBornPlace(null);
        }
        personToUpdate.setBornPlaceUnsure(person.getBornPlaceUnsure());

        if (ObjectUtils.toString(person.getActiveStart()).equals("")) {
            personToUpdate.setActiveStart(null);
        } else {
            personToUpdate.setActiveStart(person.getActiveStart());
        }

        // Death Information
        personToUpdate.setDeathYear(person.getDeathYear());
        if (person.getDeathMonth() != null) {
            personToUpdate.setDeathMonth(getMonthDAO().find(person.getDeathMonth().getMonthNum()));
        } else {
            personToUpdate.setDeathMonth(null);
        }
        personToUpdate.setDeathDay(person.getDeathDay());
        personToUpdate.setDeathDate(DateUtils.getLuceneDate(personToUpdate.getDeathYear(),
                personToUpdate.getDeathMonth(), personToUpdate.getDeathDay()));

        personToUpdate.setDeathApprox(person.getDeathApprox());
        personToUpdate.setDeathDateBc(person.getDeathDateBc());
        if (!ObjectUtils.toString(person.getDeathPlace()).equals("")) {
            personToUpdate.setDeathPlace(getPlaceDAO().find(person.getDeathPlace().getPlaceAllId()));
            if (personToUpdate.getDeathPlace().getPrefFlag().equals("V")) {
                personToUpdate.setDeathPlace(
                        getPlaceDAO().findPrinicipalPlace(personToUpdate.getDeathPlace().getGeogKey()));
            }
        } else {
            personToUpdate.setDeathPlace(null);
        }
        personToUpdate.setDeathPlaceUnsure(person.getDeathPlaceUnsure());

        if (ObjectUtils.toString(person.getActiveEnd()).equals("")) {
            personToUpdate.setActiveEnd(null);
        } else {
            personToUpdate.setActiveEnd(person.getActiveEnd());
        }

        personToUpdate.setLastUpdate(new Date());
        personToUpdate.setLastUpdateBy(user);

        getPeopleDAO().merge(personToUpdate);

        if (searchName != null) {
            searchName.setPerson(personToUpdate);
            getAltNameDAO().persist(searchName);
        }

        getUserHistoryDAO()
                .persist(new UserHistory(user, "Edit details", Action.MODIFY, Category.PEOPLE, personToUpdate));
        getVettingHistoryDAO().persist(
                new VettingHistory(user, "Edit details", org.medici.bia.domain.VettingHistory.Action.MODIFY,
                        org.medici.bia.domain.VettingHistory.Category.PEOPLE, personToUpdate));

        return personToUpdate;
    } catch (Throwable th) {
        throw new ApplicationThrowable(th);
    }
}

From source file:info.ajaxplorer.synchro.SyncJob.java

protected String normalizeUnicode(String str) {
    Normalizer.Form form = Normalizer.Form.NFD;
    if (!Normalizer.isNormalized(str, form)) {
        return Normalizer.normalize(str, form);
    }//ww  w .j  ava 2 s  . com
    return str;
}

From source file:edu.ucsd.library.xdre.imports.RDFDAMS4ImportTsHandler.java

private String encodeLiteralValue(Node node) {
    String value = null;//from  www.j ava  2 s.c  o m
    if (node != null) {
        value = "\"" + StringEscapeUtils.escapeJava(Normalizer.normalize(node.getText(), Normalizer.Form.NFC))
                .replace("'", "\\'").replace("\"", "\\\"") + "\"";
        Node langAttr = node.selectSingleNode("@xml:lang");
        if (langAttr != null)
            value += "@" + langAttr.getStringValue();
    }
    return value;
}