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

List of usage examples for org.apache.commons.lang3 StringUtils stripAccents

Introduction

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

Prototype


public static String stripAccents(final String input) 

Source Link

Document

Removes diacritics (~= accents) from a string.

Usage

From source file:com.cz4031.SAXHandler.java

@Override
public void endElement(String uri, String localName, String qName) throws SAXException {

    String tempValue = stringBuilder.toString();
    String tempAccent = StringUtils.stripAccents(tempValue);
    String value = StringUtils.trimToEmpty(tempAccent);
    stringBuilder.setLength(0);// ww  w .  ja  v a  2  s . com

    if (publication != null) {

        if (qName.equalsIgnoreCase("author")) {

            String authorName = value.toLowerCase();
            AuthorList instance = AuthorList.getInstance();
            HashMap<Author, Set<Integer>> authorList = instance.getAuthorList();

            Author author = new Author();
            author.setName(authorName);

            if (authorList.containsKey(author)) {
                Set<Integer> publicationList = authorList.get(author);
                publicationList.add(publication.getPubId());
            } else {
                author.setId(++authorID);
                Set<Integer> publicationList = new HashSet<>();
                publicationList.add(publication.getPubId());
                authorList.put(author, publicationList);
            }
        } else if (qName.equalsIgnoreCase("article") || qName.equalsIgnoreCase("book")
                || qName.equalsIgnoreCase("incollection") || qName.equalsIgnoreCase("inproceedings")) {

            CSVWriter csvWriter = CSVWriter.getInstance();
            csvWriter.writeToPublication(publication);
            publication = null;
        } else if (qName.equalsIgnoreCase("title")) {
            publication.setTitle(value);
        } else if (qName.equalsIgnoreCase("year")) {
            int year = Integer.parseInt(value);
            publication.setYear(year);
        } else if (qName.equalsIgnoreCase("journal")) {
            publication.setJournal(value);
        } else if (qName.equalsIgnoreCase("volume")) {
            publication.setVolume(value);
        } else if (qName.equalsIgnoreCase("number")) {
            publication.setNumber(value);
        } else if (qName.equalsIgnoreCase("publisher")) {
            publication.setPublisher(value);
        } else if (qName.equalsIgnoreCase("isbn")) {
            publication.setIsbn(value);
        } else if (qName.equalsIgnoreCase("booktitle")) {
            publication.setBooktitle(value);
        } else if (qName.equalsIgnoreCase("editor")) {
            publication.setEditor(value);
        } else if (qName.equalsIgnoreCase("pages")) {
            String pageStr = value;
            parsePages(pageStr);
        }
    }
}

From source file:com.blackducksoftware.tools.idcopier.service.ProjectService.java

/**
 * Gets projects from internal map/*from   w  ww.j  a  v a 2 s  .  co  m*/
 *
 * @param server
 * @param proxy
 * @return
 * @throws Exception
 */
public List<ProjectInfo> getProjectsByServer(ProtexServerProxy proxy, IDCServer server) throws Exception {
    this.proxy = proxy;
    List<ProjectInfo> projects = projectMap.get(server.getServerName());
    if (projects == null) {
        projects = getProjectsByUser(proxy, server.getUserName());
        for (ProjectInfo pinfo : projects) {
            String projectName = pinfo.getName();
            String strippedName = StringUtils.stripAccents(projectName);
            pinfo.setName(strippedName);
        }
        projectMap.put(server.getServerName(), projects);
    } else {
        return projects;
    }
    Collections.sort(projects, new ProjectComparator());
    return projects;
}

From source file:investiagenofx2.view.InvestiaGenOFXController.java

private void getTransactionsFromWeb() {
    try {// w w w. j  av a 2  s .  c o m
        if (!htmlPage.getUrl().toString().contains("/TransactionReports/Select")) {
            if (InvestiaGenOFX.debug) {
                htmlPage = InvestiaGenOFX.getWebClient()
                        .getPage(InvestiaGenOFX.debugFullPath + "-Transactions.htm");
            } else {
                htmlPage = InvestiaGenOFX.getWebClient()
                        .getPage(txt_investiaURL.getText() + "/TransactionReports/Select" + "?wcag=true");
                waitForGeneratedTransactions();
            }
        }
        @SuppressWarnings(("unchecked"))
        List<HtmlHeading4> h4from = (List<HtmlHeading4>) htmlPage
                .getByXPath("//h4[contains(text(),'Priode: de ')]");
        String from = h4from.get(0).asText();
        int index = from.indexOf("Priode: de ");
        LocalDate selFromDate = LocalDate.parse(from.substring(index + 12, index + 12 + 10));

        if (dtp_lastDate.getValue().isBefore(selFromDate)) {
            @SuppressWarnings(("unchecked"))
            List<HtmlForm> forms = (List<HtmlForm>) htmlPage.getByXPath("//form");
            HtmlForm form = forms.get(1);
            HtmlTextInput selPerFrom = form.getInputByName("selPerFrom");
            selPerFrom.setValueAttribute(dtp_lastDate.getValue().toString());

            HtmlAnchor generate = (HtmlAnchor) form.getByXPath("//a[contains(@class, 'btn-investia-blue')]")
                    .get(0);
            if (InvestiaGenOFX.debug) {
                htmlPage = InvestiaGenOFX.getWebClient()
                        .getPage(InvestiaGenOFX.debugFullPath + "-Transactions.htm");
            } else {
                htmlPage = generate.click();
                waitForGeneratedTransactions();
            }
        }

        HtmlTable htmlTable = (HtmlTable) htmlPage.getElementById("tblTransactionReports");
        if (htmlTable == null) {
            return;
        }
        for (int i = 0; i < htmlTable.getRowCount(); i++) {
            LocalDate transacDate = LocalDate.parse(htmlTable.getCellAt(i, 0).getTextContent(),
                    DateTimeFormatter.ofPattern("dd MMM yyyy", Locale.CANADA_FRENCH));
            if (transacDate.isBefore(dtp_lastDate.getValue())) {
                break;
            }
            String transacType = htmlTable.getCellAt(i, 2).getTextContent();
            String[] token = transacType.split("[\\-/(]");
            switch (token[0].replace(" ", "")) {
            case "Dividendes":
                transacType = "Distribution";
                break;
            case "Achat":
            case "changeentrant":
            case "Prlvementautomatique":
            case "Transfertentrantdecourtier":
            case "Transfertexterneentrant":
            case "Transfertinterneentrant":
                transacType = "Purchase";
                break;
            case "changesortant":
            case "Rachat":
            case "Transfertexternesortant":
            case "Transf.int.sort.":
            case "Transf.Int.sortant":
            case "Transfertinternesortant":
                transacType = "Switch Out";
                break;
            case "Dpt":
                transacType = "Credit";
                break;
            case "Retrait":
            case "Retenue":
                transacType = "Debit";
                break;
            case "Crditenespces":
            case "Entred'espces":
            case "Fraisd'administration":
            case "Sortied'espces":
            case "Transfertd'espcesentrant":
            case "Transfertd'espcessortant":
                continue;
            default:
                try {
                    throw new MyOwnException("Type de transaction non prise en charge: " + transacType.trim());
                } catch (MyOwnException ex) {
                    Logger.getLogger(OFXUtilites.class.getName()).log(Level.SEVERE, null, ex);
                    continue;
                }
            }

            String transacAccount = accountOwnerName.split(" ")[0] + "\\"
                    + htmlTable.getCellAt(i, 1).getTextContent();
            String symbol = htmlTable.getCellAt(i, 3).getTextContent();
            String unit = htmlTable.getCellAt(i, 5).getTextContent().replaceAll("[^0-9,]", "").replace(",",
                    ".");
            String fitid = "";
            String price = "0.00";
            String amount;
            if ("Credit".equals(transacType) || "Debit".equals(transacType)) {
                amount = htmlTable.getCellAt(i, 9).getTextContent().replaceAll("[^0-9,]", "").replace(",", ".");
                fitid = StringUtils.stripAccents(htmlTable.getCellAt(i, 2).getTextContent());
            } else {
                amount = htmlTable.getCellAt(i, 10).getTextContent().replaceAll("[^0-9,]", "").replace(",",
                        ".");
                price = Float.toString(Float.parseFloat(amount) / Float.parseFloat(unit));
            }
            if (PropertiesInit.getLinkAccountsTransac().indexOf(transacAccount) < 0) {
                linkAccountTransac(transacAccount);
            }
            int idxAccount = linkAccountToLocalAccountIndex[PropertiesInit.getLinkAccountsTransac()
                    .indexOf(transacAccount)];
            accounts.get(idxAccount)
                    .add(new Transaction(transacDate, transacType, amount, fitid, symbol, unit, price, ""));
        }
    } catch (Exception ex) {
        Logger.getLogger(InvestiaGenOFXController.class.getName()).log(Level.SEVERE, null, ex);
    }
}

From source file:nl.inl.blacklab.filter.DesensitizeFilter.java

@Override
final public boolean incrementToken() throws IOException {
    if (input.incrementToken()) {
        String t = new String(termAtt.buffer(), 0, termAtt.length());
        if (removeAccents)
            t = StringUtils.stripAccents(t);
        if (lowerCase)
            t = t.toLowerCase();// w  ww.ja v  a 2s  .  c  o  m
        termAtt.copyBuffer(t.toCharArray(), 0, t.length());
        return true;
    }
    return false;
}

From source file:nl.inl.blacklab.filter.RemoveAllAccentsFilter.java

@Override
final public boolean incrementToken() throws IOException {
    if (input.incrementToken()) {
        String t = new String(termAtt.buffer(), 0, termAtt.length());
        t = StringUtils.stripAccents(t);
        termAtt.copyBuffer(t.toCharArray(), 0, t.length());
        return true;
    }//from  ww w .  j  av  a2 s .co  m
    return false;
}

From source file:nl.inl.blacklab.search.HitsImpl.java

/**
 * Count occurrences of context words around hit.
 *
 * @param propName the property to use for the collocations, or null if default
 * @param ctx query execution context, containing the sensitivity settings
 *
 * @return the frequency of each occurring token
 *///  ww  w  .  j av a 2 s.  c o  m
@Override
public synchronized TermFrequencyList getCollocations(String propName, QueryExecutionContext ctx) {
    if (propName == null)
        propName = searcher.getIndexStructure().getMainContentsField().getMainProperty().getName();
    if (ctx == null)
        ctx = searcher.getDefaultExecutionContext(settings().concordanceField());
    ctx = ctx.withProperty(propName);
    findContext(Arrays.asList(ctx.luceneField(false)));
    MutableIntIntMap coll = IntIntMaps.mutable.empty();
    for (int j = 0; j < hits.size(); j++) {
        int[] context = contexts[j];

        // Count words
        int contextHitStart = context[CONTEXTS_HIT_START_INDEX];
        int contextRightStart = context[CONTEXTS_RIGHT_START_INDEX];
        int contextLength = context[CONTEXTS_LENGTH_INDEX];
        int indexInContent = CONTEXTS_NUMBER_OF_BOOKKEEPING_INTS;
        for (int i = 0; i < contextLength; i++, indexInContent++) {
            if (i >= contextHitStart && i < contextRightStart)
                continue; // don't count words in hit itself, just around [option..?]
            int w = context[indexInContent];
            int n;
            if (!coll.contains(w))
                n = 1;
            else
                n = coll.get(w) + 1;
            coll.put(w, n);
        }
    }

    // Get the actual words from the sort positions
    boolean caseSensitive = searcher.isDefaultSearchCaseSensitive();
    boolean diacSensitive = searcher.isDefaultSearchDiacriticsSensitive();
    TermFrequencyList collocations = new TermFrequencyList(coll.size());
    Terms terms = searcher.getTerms(contextFieldsPropName.get(0));
    Map<String, Integer> wordFreq = new HashMap<>();
    for (IntIntPair e : coll.keyValuesView()) {
        int key = e.getOne();
        int value = e.getTwo();
        String word = terms.get(key);
        if (!diacSensitive) {
            word = StringUtils.stripAccents(word);
        }
        if (!caseSensitive) {
            word = word.toLowerCase();
        }
        // Note that multiple ids may map to the same word (because of sensitivity settings)
        // Here, those groups are merged.
        Integer n = wordFreq.get(word);
        if (n == null) {
            n = 0;
        }
        n += value;
        wordFreq.put(word, n);
    }

    // Transfer from map to list
    for (Map.Entry<String, Integer> e : wordFreq.entrySet()) {
        collocations.add(new TermFrequency(e.getKey(), e.getValue()));
    }
    return collocations;
}

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

@Test
public void testRemoveAccents() {
    Assert.assertEquals("He, jij!", StringUtils.stripAccents("H, jij!"));
}

From source file:nl.xs4all.home.freekdb.b52reader.general.Utilities.java

/**
 * Normalize a string by stripping all accents and converting it to lowercase.
 *
 * @param text the text to normalized.//from  w w w.j  av  a 2s .  c  om
 * @return the normalized version of text.
 */
public static String normalize(final String text) {
    return text != null ? StringUtils.stripAccents(text).toLowerCase() : null;
}

From source file:org.blocks4j.commons.environment.LocalHostname.java

private static String fallbackStrategy() {
    try {//ww w  . ja v  a 2 s . c om
        return StringUtils.stripAccents(InetAddress.getLocalHost().getHostName());
    } catch (Exception e) {
        return null;
    }
}

From source file:org.blocks4j.commons.environment.LocalHostname.java

private static String runtimeStrategy() {
    BufferedReader in = null;/*from  w w w.ja  v  a 2  s.com*/
    try {
        Process proc = Runtime.getRuntime().exec("hostname");
        proc.waitFor();
        in = new BufferedReader(new InputStreamReader(proc.getInputStream()));
        return StringUtils.stripAccents(in.readLine());
    } catch (Exception e) {
        return null;

    } finally {
        if (in != null) {
            try {
                in.close();
            } catch (Exception ignored) {
            }
        }
    }
}