Java StringEscapeUtils.unescapeHtml4方法代码示例

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
/**
 * Gets a URL from a wiki page value.
 * @param htmlLink link as present on wiki page.
 * @return address the link points to (if it is an 'a'), the original link otherwise.
 */
public String getUrl(String htmlLink) {
    String result = htmlLink;
    if (htmlLink != null) {
        Matcher linkMatcher = LINKPATTERN.matcher(htmlLink);
        Matcher imgMatcher = IMAGEPATTERN.matcher(htmlLink);
        if (linkMatcher.matches()) {
            String href = linkMatcher.group(1);
            href = StringEscapeUtils.unescapeHtml4(href);
            result = href + linkMatcher.group(3);
        } else if (imgMatcher.matches()) {
            String src = imgMatcher.group(1);
            result = StringEscapeUtils.unescapeHtml4(src);
        }
    }
    return result;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
final public String getTitle() {
	if (titleCache != null)
		return titleCache;
	if (rootNode == null)
		return null;
	String[] p1 = { "html", "head", "title" };
	String title = rootNode.getFirstTextNode(p1);
	if (title == null) {
		String[] p2 = { "html", "title" };
		title = rootNode.getFirstTextNode(p2);
	}
	if (title == null)
		return null;
	titleCache = StringEscapeUtils.unescapeHtml4(title);
	return titleCache;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
/**
 * Removes HTML preformatting (if any).
 * @param value value (possibly pre-formatted)
 * @return value without HTML preformatting.
 */
public String cleanupPreFormatted(String value) {
    String result = value;
    if (value != null) {
        Matcher matcher = PRE_FORMATTED_PATTERN.matcher(value);
        if (matcher.matches()) {
            String escapedBody = matcher.group(1);
            result = StringEscapeUtils.unescapeHtml4(escapedBody);
        }
    }
    return result;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
/**
 * Write a {@link String} value into XML output.
 *
 * @param value
 * XML string
 *
 * @param minLength
 * minimal length
 *
 * @param maxLength
 * maximal length
 *
 * @return
 * XML string
 *
 * @throws IllegalArgumentException
 * if a validation error occured
 */
private static String printText( String value, Integer minLength, Integer maxLength )
{
  String val = StringUtils.trimToNull( value );
  if (val==null)
  {
    throw new IllegalArgumentException(
      "The provided text '" + value + "' is invalid!" );
  }
  if (minLength!=null && val.length()<minLength)
  {
    throw new IllegalArgumentException(
      "The provided text " + value + " is too short (minimum is " + minLength + ")!" );
  }
  val = StringEscapeUtils.unescapeHtml4( value );

  // replace <br> with line breaks
  Matcher m = BR_TAG_PATTERN.matcher( val );
  val = StringUtils.trimToEmpty( m.replaceAll( SystemUtils.LINE_SEPARATOR ) );

  // strip any other html code
  m = ANY_TAG_PATTERN.matcher( val );
  val = StringUtils.trimToEmpty( m.replaceAll( "" ) );
  val = StringUtils.replace( val, "<", "«" );
  val = StringUtils.replace( val, ">", "»" );

  return (maxLength!=null)?
    StringUtils.abbreviate( val, maxLength ): val;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
final public String mapFieldTarget(CommonFieldTarget dfTarget, String content) {
	if (StringUtils.isBlank(content))
		return null;
	if (dfTarget.isConvertHtmlEntities())
		content = StringEscapeUtils.unescapeHtml4(content);
	if (dfTarget.isRemoveTag())
		content = StringUtils.removeTag(content);
	if (dfTarget.hasRegexpPattern())
		content = dfTarget.applyRegexPattern(content);
	return content;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
@SneakyThrows
@Override
public List<Audio> getAudio(Long ownerId) {
    VkAudioDto audioDto;
    List<Audio> list = new ArrayList<>();
    int offset = 0;
    do {
        Connection.Response response = Jsoup.connect(PATH_BASE + "/al_audio.php")
                .userAgent(USER_AGENT).cookies(cookies).method(Connection.Method.POST)
                .data("access_hash", "")
                .data("act", "load_section")
                .data("al", "1")
                .data("claim", "0")
                .data("offset", String.valueOf(offset))
                .data("owner_id", ownerId.toString())
                .data("playlist_id", "-1")
                .data("type", "playlist")
                .execute();

        String body = response.body();
        String json = body.substring(body.indexOf(JSON_DELIMITER) + JSON_DELIMITER.length());
        json = json.substring(0, json.indexOf("<!>"));

        audioDto = JsonUtils.fromString(json, VkAudioDto.class);
        for (List values : audioDto.getList()) {
            Audio audio = new Audio(
                    ((Number) values.get(0)).longValue(),
                    ((Number) values.get(1)).longValue(),
                    StringEscapeUtils.unescapeHtml4((String) values.get(4)),
                    StringEscapeUtils.unescapeHtml4((String) values.get(3)),
                    (Integer) values.get(5)
            );

            list.add(audio);
        }
        offset = audioDto.getNextOffset();
    } while (audioDto.hasMore());

    log.debug("Total count: {}", audioDto.getTotalCount());
    log.debug("Fetched audio collection: {}", list.size());
    return list;
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
public void testHTMLDecode(String f) throws IOException {
    String out = StringEscapeUtils.unescapeHtml4(FileUtility.readFile(f));
    FileUtility.writeFile(out, f + ".out");
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
private void getBodyTextContent(ParserResultItem result, StringBuilder sb, HtmlNodeAbstract<Object> node,
		boolean bAddBlock, String[] directFields, int recursion, Set<Object> nodeExclusionsSet) {
	if (recursion == 0) {
		Logging.warn("Max recursion reached (getBodyTextContent)");
		return;
	}
	if (nodeExclusionsSet != null)
		if (nodeExclusionsSet.contains(node.node))
			return;

	recursion--;
	if (node.isComment())
		return;
	String nodeName = node.getNodeName();
	if ("script".equalsIgnoreCase(nodeName))
		return;
	if ("style".equalsIgnoreCase(nodeName))
		return;
	if ("object".equalsIgnoreCase(nodeName))
		return;
	if ("title".equalsIgnoreCase(nodeName))
		return;
	if ("oss".equalsIgnoreCase(nodeName)) {
		if ("yes".equalsIgnoreCase(node.getAttribute("ignore")))
			return;
	}

	boolean bEnterDirectField = false;
	String classNameAttribute = node.getAttribute("class");
	if (classNameAttribute != null) {
		String[] classNames = org.apache.commons.lang3.StringUtils.split(classNameAttribute);
		if (classNames != null) {
			for (String className : classNames) {
				if (OPENSEARCHSERVER_IGNORE.equalsIgnoreCase(className))
					return;
				if (className.startsWith(OPENSEARCHSERVER_FIELD)) {
					String directField = classNameAttribute.substring(OPENSEARCHSERVER_FIELD_LENGTH);
					if (directField.length() > 0) {
						directFields = directField.split("\\.");
						bEnterDirectField = directFields.length > 0;
					}
				}
			}
		}
	}

	if (node.isTextNode()) {
		String text = node.getText();
		text = text.replaceAll("\\r", " ");
		text = text.replaceAll("\\n", " ");
		text = StringUtils.replaceConsecutiveSpaces(text, " ");
		text = text.trim();
		if (text.length() > 0) {
			text = StringEscapeUtils.unescapeHtml4(text);
			if (sb.length() > 0)
				sb.append(' ');
			sb.append(text);
		}
	}
	final List<HtmlNodeAbstract<Object>> children = node.getChildNodes();
	if (children != null)
		for (HtmlNodeAbstract<Object> htmlNode : children)
			getBodyTextContent(result, sb, htmlNode, bAddBlock, directFields, recursion, nodeExclusionsSet);

	if (bAddBlock && nodeName != null && sb.length() > 0) {
		String currentTag = nodeName.toLowerCase();
		boolean bForSentence = sb.charAt(sb.length() - 1) != '.' && sentenceTagSet.contains(currentTag);
		if (bForSentence || bEnterDirectField) {
			if (directFields != null)
				result.addDirectFields(directFields, sb.toString());
			else
				addFieldBody(result, currentTag, sb.toString());
			sb.setLength(0);
		}
	}
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
final public static String getMetaContent(final HtmlNodeAbstract<?> node) {
	String content = node.getAttributeText("content");
	if (content == null)
		return null;
	return StringEscapeUtils.unescapeHtml4(content);
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
/**
 * Create a new instance of IndexDocument from an XML structure <br>
 * &lt;field name="FIELDNAME"&gt;<br>
 * &nbsp;&nbsp;&lt;value&gt;VALUE1&lt;/value&gt;<br>
 * &nbsp;&nbsp;&lt;value&gt;VALUE2&lt;/value&gt;<br>
 * &lt;/field&gt;
 *
 * @param client
 * @param parserSelector
 * @param documentNode
 * @param urlDefaultCredential
 * @param httpDownloader
 * @throws XPathExpressionException
 * @throws SearchLibException
 * @throws ClassNotFoundException
 * @throws IllegalAccessException
 * @throws InstantiationException
 * @throws DOMException
 * @throws IOException
 * @throws URISyntaxException
 */
public IndexDocument(Client client, ParserSelector parserSelector, Node documentNode,
		CredentialItem urlDefaultCredential, HttpDownloader httpDownloader)
		throws XPathExpressionException, SearchLibException, InstantiationException, IllegalAccessException,
		ClassNotFoundException, IOException, URISyntaxException {
	this(LanguageEnum.findByCode(XPathParser.getAttributeString(documentNode, "lang")));
	List<Node> fieldNodes = DomUtils.getNodes(documentNode, "field");
	for (Node fieldNode : fieldNodes) {
		List<String> copyFieldList = getCopyFieldList(fieldNode);
		String fieldName = XPathParser.getAttributeString(fieldNode, "name");
		List<Node> valueNodes = DomUtils.getNodes(fieldNode, "value");
		for (Node valueNode : valueNodes) {
			boolean removeTag = "yes".equalsIgnoreCase(XPathParser.getAttributeString(valueNode, "removeTag"));
			boolean convertHtmlEntities = "yes".equalsIgnoreCase(
					XPathParser.getAttributeString(valueNode, "convertHtmlEntities"));

			String textContent = valueNode.getTextContent();
			if (convertHtmlEntities)
				textContent = StringEscapeUtils.unescapeHtml4(textContent);
			if (removeTag)
				textContent = StringUtils.removeTag(textContent);
			Float boost = XPathParser.getAttributeFloat(valueNode, "boost");
			add(fieldName, textContent, boost);
			if (copyFieldList != null)
				for (String f : copyFieldList)
					add(f, textContent, boost);
		}
	}
	List<Node> binaryNodes = DomUtils.getNodes(documentNode, "binary");
	for (Node node : binaryNodes) {
		boolean bFaultTolerant = "yes".equalsIgnoreCase(XPathParser.getAttributeString(node, "faultTolerant"));
		String filename = XPathParser.getAttributeString(node, "fileName");
		if (filename == null || filename.length() == 0)
			filename = XPathParser.getAttributeString(node, "filename");
		String filePath = XPathParser.getAttributeString(node, "filePath");
		if (filePath == null || filePath.length() == 0)
			filePath = XPathParser.getAttributeString(node, "filepath");
		String contentType = XPathParser.getAttributeString(node, "contentType");
		if (contentType == null || contentType.length() == 0)
			contentType = XPathParser.getAttributeString(node, "contenttype");
		String content = node.getTextContent();
		String url = XPathParser.getAttributeString(node, "url");
		Parser parser = doBinary(url, content, filePath, filename, client, parserSelector, contentType,
				urlDefaultCredential, httpDownloader, bFaultTolerant);
		if (parser != null)
			parser.popupateResult(0, this);
	}
}
 

import org.apache.commons.text.StringEscapeUtils; //导入方法依赖的package包/类
/**
 * Unescapes supplied HTML content so it can be rendered inside a wiki page.
 * @param htmlSource HTML code to display (possibly surrounded by <pre></pre> tags).
 * @return unescaped content, enclosed in <div></div> so wiki will not escape it.
 */
public String html(String htmlSource) {
    String cleanSource = htmlCleaner.cleanupPreFormatted(htmlSource);
    return "<div>" + StringEscapeUtils.unescapeHtml4(cleanSource) + "</div>";
}