Example usage for org.apache.commons.lang3 StringEscapeUtils unescapeHtml3

Introduction

In this page you can find the example usage for org.apache.commons.lang3 StringEscapeUtils unescapeHtml3.

Prototype

public static final String unescapeHtml3(final String input) 

Source Link

Document

Unescapes a string containing entity escapes to a string containing the actual Unicode characters corresponding to the escapes.

Usage

From source file:com.cotrino.knowledgemap.db.Question.java

public Question(Page page) {
    String realText = StringEscapeUtils.unescapeHtml3(page.getText());
    List<String> rawSentences = Question.tokenize(realText, "en", "US");
    if (rawSentences.size() >= QUESTION_SENTENCES) {
        //System.out.println("Asking about '" + title + "'");
        generateQuestion(page, rawSentences);
    }//w ww.  ja va  2 s.  c  om
}

---

From source file:com.hit.j2ee.sshTemplate.common.encrypt.EncodeUtils.java

/**
 * Html ?.
 */
public static String htmlUnescape(String htmlEscaped) {
    return StringEscapeUtils.unescapeHtml3(htmlEscaped);
}

---

From source file:es.ua.dlsi.patch.translation.LocalApertiumTranslator.java

public Map<String, Set<String>> getTranslation(final Set<String> inputset) {
    Map<String, Set<String>> dictionary = new HashMap<>();
    if (!inputset.isEmpty()) {
        try {//  www. j  ava 2s . com
            StringBuilder sb = new StringBuilder();
            List<String> input = new LinkedList<>(inputset);
            for (String s : input) {
                sb.append("<p>");
                sb.append(s);
                sb.append("</p>");
            }

            //String[] command = {"apertium", "-u", "-f html", langCmd};

            ProcessBuilder probuilder = new ProcessBuilder("apertium", "-u", "-fhtml", langCmd);

            Process process = probuilder.start();
            OutputStream stdin = process.getOutputStream();
            BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(stdin));
            writer.write(sb.toString());
            writer.flush();
            writer.close();

            InputStream is = process.getInputStream();
            InputStreamReader isr = new InputStreamReader(is);
            BufferedReader br = new BufferedReader(isr);
            String line;
            StringBuilder finalline = new StringBuilder();

            while ((line = br.readLine()) != null) {
                finalline.append(line);
            }
            br.close();
            String finaltranslation = StringEscapeUtils
                    .unescapeHtml3(finalline.toString().replaceAll("\\s<", "<").replaceAll(">\\s", ">")
                            .replaceAll("^<p>", "").replace("</p>", ""));
            List<String> translations = new LinkedList<>(Arrays.asList(finaltranslation.split("<p>")));
            for (int i = 0; i < translations.size(); i++) {
                if (dictionary.containsKey(input.get(i))) {
                    dictionary.get(input.get(i)).add(translations.get(i));
                } else {
                    Set<String> trans_set = new HashSet<>();
                    trans_set.add(translations.get(i));
                    dictionary.put(input.get(i), trans_set);
                }
            }

        } catch (Exception e) {
            e.printStackTrace(System.err);
            System.exit(-1);
        }
    }
    return dictionary;
}

---

From source file:com.kdmanalytics.toif.assimilator.XMLNode.java

/**
 * Parse the node information. Note that the "Attributes" here are XML Attributes, not KDM
 * attributes./*from   ww  w.  java 2 s  .c  o m*/
 * 
 * @param ns
 * @param sName
 * @param qName
 * @param attrs
 */
public XMLNode(String ns, String sName, String qName, Attributes attrs) {

    children = new ArrayList<XMLNode>();
    this.sName = sName;
    if ("".equals(sName))
        this.sName = qName; // Not namespace aware

    int size = attrs.getLength();
    for (int i = 0; i < size; i++) {
        String key = attrs.getLocalName(i); // Attr name
        if ("".equals(key))
            key = attrs.getQName(i);

        // Special cases
        // Stereotype/tag "type" is an attribute, not a reference
        if ("stereotype".equals(this.sName) && "type".equals(key))
            addAttribute(key, attrs.getValue(key));
        else if ("tag".equals(this.sName) && "type".equals(key))
            addAttribute(key, attrs.getValue(key));

        // Some attributes are really references
        else if (AttributeUtilities.isReference(key))
            addReference(key, attrs.getValue(key));

        // Unescape the fields which likely contain escaped HTML
        else if (stringFields.contains(key)) {
            String value = attrs.getValue(key);
            try {
                // value = StringEscapeUtils.unescapeHtml4(value);
                // value = StringEscapeUtils.unescapeXml(value);
                value = StringEscapeUtils.unescapeHtml3(value);
            } catch (StringIndexOutOfBoundsException e) {
                // String was most likely '&' which causes commons.lang3 to
                // throw... ignore it
                if (!value.contains("&")) {
                    throw e;
                }
            }
            addAttribute(key, value);
        }
        // Normal attribute
        else {
            addAttribute(key, attrs.getValue(key));
        }
    }

    // Use the xmiLid if it exists
    id = getAttribute("xmi:id");
    if (id == null)
        id = "" + UniqueID.get();
}

---

From source file:com.interopbridges.tools.windowsazure.JSONHelper.java

/**
 * This API will decode the given HTML encoded string.
 * //from ww  w. j  a va  2 s.  co  m
 * @param str
 * @return
 */
public static String decodeHTML(String str) {
    String decoded = StringEscapeUtils.unescapeHtml3(str);
    return decoded;
}

---

From source file:com.phone.cn.service.BaseService.java

/**
 *??//  www  . java2  s  .co  m
 * @param str
 * @return
 */
protected String doEditor(String str) {
    if (StringUtils.isNotEmpty(str)) {
        return StringEscapeUtils.unescapeHtml3(str).replace("\n", "").replace("\"", "\\\"").replace("\t", "")
                .replace("\r", "");
    }
    return str;
}

---

From source file:com.phone.cn.service.BaseService.java

/**
 *??/*from   w  ww  .  j a va 2 s .c o m*/
 * @param str
 * @return
 */
protected String doEditorForIndex(String str) {
    if (StringUtils.isNotEmpty(str)) {
        return StringEscapeUtils.unescapeHtml3(str).replace("\n", "")
                //               .replace("\"", "")
                .replace("\t", "").replace("\r", "");
    }
    return str;
}

---

From source file:com.rockagen.commons.util.CommUtil.java

/**
 * <p>/*www  . j ava  2 s .c o m*/
 * unescape HTML see StringEscapeUtils.unescapeHtml3(str)
 * </p>
 * <p>
 * Supports all known HTML 3.0 entities, including funky accents. Note that
 * the commonly used apostrophe escape character (&amp;apos;) is not a legal
 * entity and so is not supported).
 * </p>
 * <p>
 * For example:
 * </p>
 * <p>
 * <code>&amp;quot;bread&amp;quot; &amp;amp; &amp;quot;butter&amp;quot;</code>
 * </p>
 * becomes:
 * <p>
 * <code>"bread" &amp; "butter"</code>.
 * </p>
 *
 * @param str value
 * @return string
 */
public static String unescapeHtml3(String str) {
    if (isBlank(str)) {
        return str;
    }
    return StringEscapeUtils.unescapeHtml3(str);
}

---

From source file:com.trsst.Common.java

public static String unescapeHTML(String escapedHtml) {
    return StringEscapeUtils.unescapeHtml3(escapedHtml);
}

---

From source file:cn.sinobest.jzpt.framework.utils.string.StringUtils.java

/**
 * HTML
 *
 * @param s
 * @return
 */
public static String unescapeHtml(String s) {
    return StringEscapeUtils.unescapeHtml3(s);
}

---

• «
• 1
• 2
• »