Java Utililty Methods HTML Unescape

List of utility methods to do HTML Unescape

  1. HOME
  2. Java
  3. H
  4. HTML Unescape

Description

The list of methods to do HTML Unescape are organized into topic(s).

Method

StringhtmlUnescape(String s)
Turn HTML character references into their plain text UNICODE equivalent. 
if (s == null) {
    return null;
StringBuffer unescaped = new StringBuffer(s.length());
for (int i = 0; i < s.length(); i++) {
    char c = s.charAt(i);
    if (c == '&') {
        int start = Math.min(i + 1, s.length() - 1);
...
StringhtmlUnescape(String source)
Reverses htmlEscape. 
StringBuffer buf = new StringBuffer();
if (source != null) {
    for (int i = 0; i < source.length(); ++i) {
        char ch = source.charAt(i);
        if (ch == '&') {
            int semi = source.indexOf(';', i + 1);
            if (semi == -1) {
                buf.append(ch);
...
StringunEscapeHTML(final String escapedHTML)
Replace HTML escape sequences with the correct characters 
String retVal = escapedHTML;
retVal = retVal.replaceAll("&gt;", ">");
retVal = retVal.replaceAll("&lt;", "<");
retVal = retVal.replaceAll("&amp;", "&");
retVal = retVal.replaceAll("&nbsp;", " ");
return retVal;
StringunescapeHtml(final String input)
Unescapes HTML characters from the input. 
String unescapeHexHtmlOutput = unescapeHtmlByNumber(input);
return unescapeHtmlByName(unescapeHexHtmlOutput);
StringunescapeHTML(String comment)
unescape HTML 
int length = comment.length();
StringBuffer buffer = new StringBuffer();
for (int i = 0; i < length; ++i) {
    String comp = comment.substring(i, i + 1);
    if (" ".compareTo(comp) == 0) {
        comp = comment.substring(++i, i + 1);
        buffer.append("&nbsp");
    } else if ("\r".compareTo(comp) == 0) {
...
StringunescapeHTML(String html)
Given escaped html characters, unescapes them. 
return html.replace("&apos;", "'").replace("&quot;", "\"").replace("&gt;", ">").replace("&lt;", "<")
        .replace("&amp;", "&");
StringunescapeHtml(String s)
unescape Html 
if (s == null || s.indexOf('&') == -1)
    return s;
s = s.replace("&lt;", "<");
s = s.replace("&gt;", ">");
s = s.replace("&quot;", "\"");
s = s.replace("&#39;", "'");
s = s.replace("&amp;", "&");
return s;
...
StringunescapeHTML(String s)
Turn any HTML escape entities in the string into characters and return the resulting string. 
StringBuffer result = new StringBuffer(s.length());
int ampInd = s.indexOf("&");
int lastEnd = 0;
while (ampInd >= 0) {
    int nextAmp = s.indexOf("&", ampInd + 1);
    int nextSemi = s.indexOf(";", ampInd + 1);
    if (nextSemi != -1 && (nextAmp == -1 || nextSemi < nextAmp)) {
        int value = -1;
...
StringunescapeHtml(String s)
Reverses the escaping done by escapeForHtml. 
final int sLength = s.length();
final StringBuilder result = new StringBuilder(sLength);
for (int i = 0; i < sLength; ++i) {
    final char ch = s.charAt(i);
    if (ch == '&') {
        if (s.startsWith("&amp;", i)) {
            result.append('&');
            i += 4;
...
StringunescapeHTML(String s)
unescape HTML 
String[][] escape = { { "&lt;", "<" }, { "&gt;", ">" }, { "&amp;", "&" }, { "&quot;", "\"" },
        { "&agrave;", "\u00e0" }, { "&Agrave;", "\u00c0" }, { "&acirc;", "\u00e2" }, { "&auml;", "\u00e4" },
        { "&Auml;", "\u00c4" }, { "&Acirc;", "\u00c2" }, { "&aring;", "\u00e5" }, { "&Aring;", "\u00c5" },
        { "&aelig;", "\u00e6" }, { "&AElig;", "\u00c6" }, { "&ccedil;", "\u00e7" },
        { "&Ccedil;", "\u00c7" }, { "&eacute;", "\u00e9" }, { "&Eacute;", "\u00c9" },
        { "&egrave;", "\u00e8" }, { "&Egrave;", "\u00c8" }, { "&ecirc;", "\u00ea" },
        { "&Ecirc;", "\u00ca" }, { "&euml;", "\u00eb" }, { "&Euml;", "\u00cb" }, { "&iuml;", "\u00ef" },
        { "&Iuml;", "\u00cf" }, { "&ocirc;", "\u00f4" }, { "&Ocirc;", "\u00d4" }, { "&ouml;", "\u00f6" },
...