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.kuali.ole.docstore.model.bagit.BagExtractor.java

/**
 * @param bagFile//from   w  w  w. j  a v a  2  s . co m
 * @param outputDir
 * @throws IOException
 */
public static void extractBag(File bagFile, File outputDir) throws IOException {
    byte[] buffer = new byte[BUFFER_SIZE];
    ZipInputStream zis = new ZipInputStream(new BufferedInputStream(new FileInputStream(bagFile)));
    ZipEntry next;
    LOG.info("extractBag bagFile.getAbsolutePath " + bagFile.getAbsolutePath());
    LOG.info("extractBag outputDir.getAbsolutePath " + outputDir.getAbsolutePath());
    while ((next = zis.getNextEntry()) != null) {
        LOG.info("next.getName " + next.getName());
        System.out.println("next.getName " + next.getName());
        //String name = next.getName().replaceFirst("[^/]*/", "");
        String name = next.getName().replace('\\', '/').replaceFirst("[^/]*/", "");
        //System.out.println("replace nameunix "+nameunixreplace.replace('\\','/').replaceFirst("[^/]*/", ""));
        //   String name = next.getName();
        LOG.info("name " + name);
        LOG.info("normalize "
                + Normalizer.normalize(name.substring(DATA_DIR.length()), FILENAME_NORMALIZATION_FORM));
        LOG.info("substring " + name.substring(DATA_DIR.length()));
        LOG.info("DATA_DIR " + DATA_DIR);
        if (name.startsWith(DATA_DIR)) {
            LOG.info("in if name.startsWith(DATA_DIR)");
            File localFile = new File(outputDir,
                    Normalizer.normalize(name.substring(DATA_DIR.length()), FILENAME_NORMALIZATION_FORM));
            if (next.isDirectory()) {
                LOG.info("in if next.isDirectory");
                if (!localFile.exists() && !localFile.mkdir()) {
                    throw new IOException("error creating local directories in output directory");
                }
            } else {
                LOG.info("in else next.isDirectory");
                File parent = localFile.getParentFile();
                if (!parent.exists() && !parent.mkdirs()) {
                    throw new IOException("error creating local directories in output directory");
                }
                BufferedOutputStream bos = new BufferedOutputStream(new FileOutputStream(localFile));
                int bytesRead;
                while ((bytesRead = zis.read(buffer, 0, BUFFER_SIZE)) != -1) {
                    bos.write(buffer, 0, bytesRead);
                }
                bos.close();
            }
        }
    }
    zis.close();
}

From source file:org.sonar.fortify.crawler.Main.java

private static String slugifyForTags(String s) {
    return Normalizer.normalize(s, Normalizer.Form.NFD).replaceAll("[^\\p{ASCII}]", "")
            .replaceAll("[^\\w+]", "-").replaceAll("\\s+", "-").replaceAll("_", "-").replaceAll("[-]+", "-")
            .replaceAll("^-", "").replaceAll("-$", "").toLowerCase(Locale.ENGLISH);
}

From source file:de.thischwa.pmcms.tool.file.FileTool.java

/**
 * Replaces the german special chars and spaces in 'filename'.
 * //from   w  w w  . j a  v a2s. c o m
 * @param filename
 * @return normalized file name TODO Restrict special chars, replace unknown with something like that: -sp-
 */
public static String normalizeFileName(final String filename) {
    StringBuilder sb = new StringBuilder();
    String tmp = filename.toLowerCase();
    tmp = Normalizer.normalize(tmp, Normalizer.Form.NFC);
    for (char c : tmp.toCharArray()) {
        String replaceStr = specialCharReplacement.get(Integer.valueOf(c));
        if (replaceStr != null)
            sb.append(replaceStr);
        else if (Constants.ALLOWED_CHARS_FOR_FILES.contains(c + ""))
            sb.append(c);
    }
    return sb.toString();
}

From source file:org.exoplatform.wcm.webui.search.UISearchResult.java

public void processRender(WebuiRequestContext context) throws Exception {
    PortletRequestContext porletRequestContext = (PortletRequestContext) context;
    PortletPreferences portletPreferences = porletRequestContext.getRequest().getPreferences();
    if (resultType == null || resultType.trim().length() == 0) {
        resultType = "Document";
    }//from  w  w  w.j a  v  a 2  s . c o  m
    PortalRequestContext portalRequestContext = Util.getPortalRequestContext();
    String portal = portalRequestContext.getRequestParameter("portal");
    String keyword = portalRequestContext.getRequestParameter("keyword");
    if ((portal != null) && (keyword != null) && (keyword.length() > 0)) {
        UISearchPageLayout uiSearchPageContainer = getAncestorOfType(UISearchPageLayout.class);
        UISearchForm searchForm = uiSearchPageContainer.getChild(UISearchForm.class);
        // searchForm.getUIFormSelectBox(UISearchForm.PORTALS_SELECTOR).setSelectedValues(new
        // String[] {portal});
        searchForm.getUIStringInput(UISearchForm.KEYWORD_INPUT).setValue(keyword);
        if (searchForm.getUIFormSelectBox(UISearchForm.PORTALS_SELECTOR).getValue() != null) {
            portal = searchForm.getUIFormSelectBox(UISearchForm.PORTALS_SELECTOR).getValue();
        }
        if (searchForm.getUIStringInput(UISearchForm.KEYWORD_INPUT).getValue() != null) {
            keyword = searchForm.getUIStringInput(UISearchForm.KEYWORD_INPUT).getValue();
        }
        setKeyword(keyword);
        keyword = Normalizer.normalize(keyword, Normalizer.Form.NFD)
                .replaceAll("\\p{InCombiningDiacriticalMarks}+", "");

        SiteSearchService siteSearchService = getApplicationComponent(SiteSearchService.class);
        QueryCriteria queryCriteria = new QueryCriteria();

        UIFormRadioBoxInput searchOption = searchForm.getUIFormRadioBoxInput(UISearchForm.SEARCH_OPTION);
        boolean isSearchDocument = (searchOption.getValue().equals(UISearchForm.DOCUMENT_CHECKING));
        boolean isWebPage = (searchOption.getValue().equals(UISearchForm.PAGE_CHECKING));

        List<String> documentNodeTypes = new ArrayList<String>();
        if (isSearchDocument) {
            TemplateService templateService = WCMCoreUtils.getService(TemplateService.class);
            documentNodeTypes = templateService.getAllDocumentNodeTypes();
            portal = Util.getPortalRequestContext().getPortalOwner();
            resultType = "Document";
        } else {
            documentNodeTypes.add("gtn:language");
            documentNodeTypes.add("exo:pageMetadata");
            queryCriteria.setFulltextSearchProperty(
                    new String[] { "exo:metaKeywords", "exo:metaDescription", "gtn:name" });
            resultType = "Page";
        }

        String pageMode = portletPreferences.getValue(UIWCMSearchPortlet.PAGE_MODE,
                SiteSearchService.PAGE_MODE_NONE);

        queryCriteria.setContentTypes(documentNodeTypes.toArray(new String[documentNodeTypes.size()]));
        queryCriteria.setSiteName(portal);
        queryCriteria.setKeyword(
                org.exoplatform.services.cms.impl.Utils.escapeIllegalCharacterInQuery(keyword).toLowerCase());
        queryCriteria.setSearchWebpage(isWebPage);
        queryCriteria.setSearchDocument(isSearchDocument);
        queryCriteria.setSearchWebContent(isSearchDocument);
        queryCriteria.setPageMode(pageMode);

        queryCriteria.setLiveMode(WCMComposer.MODE_LIVE.equals(Utils.getCurrentMode()));
        queryCriteria.setSortBy(this.getSortField());
        queryCriteria.setOrderBy(this.getOrderType());
        int itemsPerPage = Integer
                .parseInt(portletPreferences.getValue(UIWCMSearchPortlet.ITEMS_PER_PAGE, null));
        try {
            AbstractPageList<ResultNode> pageList = null;
            if (isWebPage) {
                pageList = siteSearchService.searchPageContents(WCMCoreUtils.getSystemSessionProvider(),
                        queryCriteria, itemsPerPage, false);
            } else {
                pageList = siteSearchService.searchSiteContents(WCMCoreUtils.getUserSessionProvider(),
                        queryCriteria, itemsPerPage, false);
            }

            setSearchTime(pageList.getQueryTime() / 1000);
            setSuggestion(pageList.getSpellSuggestion());
            if (pageList.getAvailable() <= 0) {
                String suggestion = pageList.getSpellSuggestion();
                setSuggestionURL(suggestion);
                searchForm.setSubmitAction(suggestion);
            }
            setPageList(pageList);
        } catch (Exception e) {
            UIApplication uiApp = getAncestorOfType(UIApplication.class);
            uiApp.addMessage(new ApplicationMessage(UISearchForm.MESSAGE_NOT_SUPPORT_KEYWORD, null,
                    ApplicationMessage.WARNING));
        }
    }
    super.processRender(context);
}

From source file:com.cloudbees.hudson.plugins.folder.ChildNameGeneratorAltTest.java

public static String encode(String s) {
    // We force every name to NFD to ensure that the test works irrespective of what the filesystem does
    return Normalizer.normalize(s, Normalizer.Form.NFD);
}

From source file:com.cloudbees.hudson.plugins.folder.ChildNameGeneratorAltTest.java

public static String mangle(String s) {
    // We force every name to NFD to ensure that the test works irrespective of what the filesystem does
    s = Normalizer.normalize(s, Normalizer.Form.NFD);
    String hash = Util.getDigestOf(s);
    String base = Normalizer.normalize(s, Normalizer.Form.NFD).toLowerCase(Locale.ENGLISH);
    StringBuilder buf = new StringBuilder(32);
    for (char c : base.toCharArray()) {
        if (buf.length() >= 8)
            break;
        if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z') || ('0' <= c && c <= '9')) {
            buf.append(Character.toLowerCase(c));
        } else {//from  w  w w . j  ava 2 s. c om
            buf.append('_');
        }
    }
    buf.append('-');
    buf.append(hash.substring(0, 23));
    return buf.toString();
}

From source file:com.cloudbees.hudson.plugins.folder.ChildNameGeneratorRecTest.java

public static String mangle(String s) {
    String hash = Util.getDigestOf(s);
    String base = Normalizer.normalize(s, Normalizer.Form.NFD).toLowerCase(Locale.ENGLISH);
    StringBuilder buf = new StringBuilder(32);
    for (char c : base.toCharArray()) {
        if (buf.length() >= 8)
            break;
        if (('A' <= c && c <= 'Z') || ('a' <= c && c <= 'z') || ('0' <= c && c <= '9')) {
            buf.append(Character.toLowerCase(c));
        } else {/*from ww w  .  j a  v a  2  s  .co m*/
            buf.append('_');
        }
    }
    buf.append('-');
    buf.append(hash.substring(0, 23));
    return buf.toString();
}

From source file:org.redpill.alfresco.pdfapilot.worker.PdfaPilotWorker.java

private String getBasename(NodeRef node) {
    if (node == null || !_nodeService.exists(node)) {
        return "PPCTW_" + GUID.generate();
    }/*from   w  w w  .j a  va  2 s .co m*/

    try {
        String filename = (String) _nodeService.getProperty(node, ContentModel.PROP_NAME);

        String basename = FilenameUtils.getBaseName(filename);

        // TODO: Investigate if this is really needed
        // callas currently has a bug that makes it crash if the whole filepath is
        // longer than 260 characters
        basename = StringUtils.substring(basename, 0, 100);

        // 0x2013 is the long hyphen, not allowed here...
        char c = 0x2013;
        if (StringUtils.contains(basename, c)) {
            if (LOG.isTraceEnabled()) {
                LOG.trace("Long hyphen replaced with short one");
            }

            basename = StringUtils.replaceChars(basename, c, '-');
        }

        filename = basename;

        if (LOG.isTraceEnabled()) {
            LOG.trace("Filename before normalization");

            for (char character : filename.toCharArray()) {
                LOG.trace(character + " : " + (int) character);
            }
        }

        filename = Normalizer.normalize(filename, Form.NFKC);

        if (LOG.isTraceEnabled()) {
            LOG.trace("Filename after normalization");

            for (char character : filename.toCharArray()) {
                LOG.trace(character + " : " + (int) character);
            }
        }

        // pad the string with _ until it's at lest 3 characters long
        if (basename.length() < 3) {
            basename = StringUtils.rightPad(basename, 3, "_");
        }

        return basename;
    } catch (final Exception ex) {
        throw new RuntimeException(ex);
    }
}

From source file:be.wolkmaan.klimtoren.security.digest.StandardStringDigester.java

@Override
public String digest(final String message) {

    if (message == null) {
        return null;
    }//from   w  ww . ja va 2 s  . c  o m

    // Check initialization
    if (!isInitialized()) {
        initialize();
    }

    try {

        // Normalize Unicode message to NFC form
        String normalizedMessage;
        if (!this.unicodeNormalizationIgnored) {
            normalizedMessage = Normalizer.normalize(message, Normalizer.Form.NFC);
        } else {
            normalizedMessage = message;
        }

        // The input String is converted into bytes using MESSAGE_CHARSET
        // as a fixed charset to avoid problems with different platforms
        // having different default charsets (see MESSAGE_CHARSET doc).
        final byte[] messageBytes = normalizedMessage.getBytes(MESSAGE_CHARSET);

        // The StandardByteDigester does its job.
        byte[] digest = this.byteDigester.digest(messageBytes);

        // We build the result variable
        final StringBuffer result = new StringBuffer();

        if (this.prefix != null) {
            // Prefix is added
            result.append(this.prefix);
        }

        // We encode the result in BASE64 or HEXADECIMAL so that we obtain
        // the safest result String possible.
        if (this.stringOutputTypeBase64) {
            digest = this.base64.encode(digest);
            result.append(new String(digest, DIGEST_CHARSET));
        } else {
            result.append(CommonUtils.toHexadecimal(digest));
        }

        if (this.suffix != null) {
            // Suffix is added
            result.append(this.suffix);
        }

        return result.toString();

    } catch (EncryptionInitializationException | EncryptionOperationNotPossibleException e) {
        throw e;
    } catch (UnsupportedEncodingException e) {
        // If digest fails, it is more secure not to return any information
        // about the cause in nested exceptions. Simply fail.
        throw new EncryptionOperationNotPossibleException();
    }
}

From source file:fr.gouv.culture.thesaurus.util.TextUtils.java

/**
  * Supprime les accents//www.  ja  v  a  2  s  . c  o m
  * @param strIn
  * @return
  */
public final static String removeAccent(String strIn) {
    return Normalizer.normalize(strIn, Normalizer.Form.NFD).replaceAll("\\p{InCombiningDiacriticalMarks}+", "");
}