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.sakaiproject.util.ParameterParser.java

/**
 * Get a FileItem parameter by name./*from   w w w  . j a  va2  s . com*/
 * 
 * @param name
 *        The parameter name.
 * @return The parameter FileItem value, or null if it's not defined.
 */
public FileItem getFileItem(String name) {
    // wrap the Apache FileItem in our own homegrown FileItem
    Object o = m_req.getAttribute(name);
    if (o != null && o instanceof org.apache.commons.fileupload.FileItem) {
        org.apache.commons.fileupload.FileItem item = (org.apache.commons.fileupload.FileItem) o;
        try {
            return new FileItem(Normalizer.normalize(item.getName(), Normalizer.Form.NFC),
                    item.getContentType(), item.getInputStream());
        } catch (IOException e) {
            return new FileItem(Normalizer.normalize(item.getName(), Normalizer.Form.NFC),
                    item.getContentType(), item.get());
        }
    }

    return null;
}

From source file:org.mycore.common.xml.MCRXMLFunctions.java

/**
 * returns the given String in unicode NFC normal form.
 *
 * @param arg0 String to be normalized// w  w  w  . ja v  a  2  s  . c  om
 * @see Normalizer#normalize(CharSequence, java.text.Normalizer.Form)
 */
public static String normalizeUnicode(String arg0) {
    return Normalizer.normalize(arg0, Normalizer.Form.NFC);
}

From source file:org.jajuk.services.lyrics.providers.LyricsManiaWebLyricsProvider.java

/**
 * Replace each accent in the string with the non accent character.
 * @param s the string to process// w  ww .  j a v a 2  s.c  o m
 * @return the string without accents
 */
public String removeAccent(String s) {
    String strTemp = Normalizer.normalize(s, Normalizer.Form.NFD);
    Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
    return pattern.matcher(strTemp).replaceAll("");
}

From source file:com.csc.fi.ioapi.utils.LDHelper.java

public static String removeAccents(String text) {
    return text == null ? null
            : Normalizer.normalize(text, Form.NFD).replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
}

From source file:com.aestheticsw.jobkeywords.service.termextractor.impl.fivefilters.FiveFiltersClient.java

private String removeHtmlTagsAndOtherBogusContent(String content, Locale locale) {

    content = content.toLowerCase(locale);
    // remote accented characters
    content = Normalizer.normalize(content, Normalizer.Form.NFD);

    for (Pattern key : regExMap.keySet()) {
        content = key.matcher(content).replaceAll(regExMap.get(key));
    }//  w w  w. jav  a  2s  .c om
    return content;
}

From source file:it.tidalwave.northernwind.core.impl.model.ResourcePropertiesDelegate.java

/*******************************************************************************************************************
 *
 * See http://stackoverflow.com/questions/1008802/converting-symbols-accent-letters-to-english-alphabet
 *
 ******************************************************************************************************************/
@Nonnull//  w  w w  .  ja  va2s  .  c  o m
public String deAccent(final @Nonnull String string) {
    final String nfdNormalizedString = Normalizer.normalize(string, Normalizer.Form.NFD);
    final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
    return pattern.matcher(nfdNormalizedString).replaceAll("");
}

From source file:org.tinymediamanager.scraper.thetvdb.TheTvDbMetadataProvider.java

public static String clearSearchString(String searchString) {

    // This will separate all of the accent marks from the characters
    String cleanedString = Normalizer.normalize(searchString, Normalizer.Form.NFD);
    // For unicode, \\P{M} matches the base glyph and \\p{M} (lowercase) matches each accent.
    cleanedString = cleanedString.replaceAll("\\p{M}", ""); // remove accents

    // cleanedString = cleanedString.replaceAll("\\p{Punct}", ""); // too much?
    // cleanedString = cleanedString.replaceAll("[^\\p{Alnum}\\s\\-]", ""); // damn - removes ALL cyrillic chars

    // next try: punctuation !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ plus , but not !-
    cleanedString = cleanedString.replaceAll("(?![\\-!])[\\p{Punct}]", "");

    return cleanedString;
}

From source file:com.moviejukebox.model.scriptablescraper.SectionContentSS.java

public String getVariable(final String name) {
    try {/*from   w w  w  .j a  va2  s.com*/
        String result = "";
        boolean safe = false;
        boolean htmldecode = false;
        boolean striptags = false;

        if (StringUtils.isNotBlank(name)) {
            preparedVariable variable = prepareVariable(name);
            if (isDebug()) {
                LOG.debug("getVariable: {} value: {} index0: {} index1: {}", name, variable.value,
                        variable.index0, variable.index1);
            }
            if (variable.value == null) {
                return "";
            }

            safe = name.contains(":safe");
            htmldecode = name.contains(":htmldecode");
            striptags = -1 <= name.indexOf(":striptags");

            if (variable.index0 > -1) {
                if (variable.value.contains(ARRAY_GROUP_DIVIDER)) {
                    List<String> values = Arrays.asList(variable.value.split(ARRAY_GROUP_DIVIDER));
                    if (values.size() > variable.index0) {
                        variable.value = values.get(variable.index0);
                        if (variable.index1 > -1) {
                            values = Arrays.asList(variable.value.split(ARRAY_ITEM_DIVIDER));
                            if (values.size() > variable.index1) {
                                result = values.get(variable.index1);
                            }
                        } else {
                            result = variable.value;
                        }
                    }
                } else if (variable.index1 == -1) {
                    List<String> values = Arrays.asList(variable.value.split(ARRAY_ITEM_DIVIDER));
                    if (values.size() > variable.index0) {
                        result = values.get(variable.index0);
                    }
                }
            } else {
                result = variable.value;
            }
        }

        if (safe) {
            result = Normalizer.normalize(result, Normalizer.Form.NFD)
                    .replaceAll("\\p{InCombiningDiacriticalMarks}+", "").replace(" ", "+");
            if (name.contains(":safe(")) {
                String encodeName = name.substring(name.indexOf(":safe(") + 6);
                encodeName = name.substring(0, name.indexOf(")"));
                if (isDebug()) {
                    LOG.debug("encode result to ''{}'", encodeName);
                }
                result = URLEncoder.encode(result, encodeName);
            }
        }
        if (striptags) {
            result = HTMLTools.removeHtmlTags(result);
        }
        if (htmldecode) {
            result = HTMLTools.decodeHtml(result);
        }

        if (isDebug()) {
            LOG.debug("getVariable: result: '{}'", result);
        }
        return result;
    } catch (IOException error) {
        LOG.error("Failed get variable : {}", name);
        LOG.error("Error : {}", error.getMessage());
        return "";
    }
}

From source file:com.evolveum.midpoint.model.common.expression.functions.BasicExpressionFunctions.java

public String toAscii(Object input) {
    if (input == null) {
        return null;
    }/*from   w  ww.j a va 2 s  . co m*/
    String inputString = stringify(input);
    String decomposed = Normalizer.normalize(inputString, Normalizer.Form.NFKD);
    return decomposed.replaceAll("\\p{M}", "");
}

From source file:module.entities.NameFinder.RegexNameFinder.java

public static String getSignatureFromParagraphs(Elements paragraphs) {
    String signature = "";
    String signName = "", roleName = "";
    int signIdx = 0, roleIdx = 0;
    int row = 0;/*from ww  w.  jav a2s. c  o  m*/
    TreeMap<Integer, String> roles = new TreeMap<Integer, String>();
    for (Element n : paragraphs) {
        row++;
        String formatedText = Normalizer.normalize(n.text().toUpperCase(locale), Normalizer.Form.NFD)
                .replaceAll("\\p{M}", "");
        if (formatedText.contains(" ") && !formatedText.matches(".*[0-9].*")) {
            //                  if (formatedText.contains("<br>")) {
            //                      formatedText = formatedText.replaceAll("<br\\s*/>", " ");
            //                   }
            String[] splitedText = formatedText.split(" ");
            //                    System.out.println(splitedText.length);
            if (splitedText.length < 7) {
                boolean isSign = false;
                String text = "";
                for (int z = 0; z < splitedText.length; z++) {
                    String splText = splitedText[z].replaceAll("[\\s.]", "").replaceAll("\u00a0", "")
                            .replaceAll("", "").replaceAll(",", "");
                    if (names.contains(splText) || surnames.contains(splText)) {
                        signName += splText + " ";
                        signIdx = row;
                        isSign = true;
                    }
                    text += splText + " ";
                    //                            if (z == splitedText.length-1){
                    //                                System.out.println(signName.trim());
                    //                            }
                }
                if (!isSign) {
                    roleIdx = row;
                    if (!text.contains(" ") && !text.contains("")) {
                        roles.put(roleIdx, text.trim());
                    }
                }
            }
        }
    }
    for (Integer roleRow : roles.keySet()) {
        //                    if (signName.length() == 0) {
        if (Math.abs(signIdx - roleRow) < 4) {
            roleName += roles.get(roleRow) + " ";
        }

    }

    if (signName.length() > 0) {
        signature = signName + "#" + roleName;
    }
    return signature;
}