Examples with TextNode org.jsoup.nodes.TextNode used on opensource projects

Example 1 with TextNode

use of org.jsoup.nodes.TextNode in project sppanblog4springboot by whoismy8023.

the class HtmlFilter method truncateHTML.

/**
 * 使用Jsoup预览
 *
 * @param source 需要过滤的
 * @param dest   过滤后的对象
 * @param len    截取字符长度
 *               <p>
 *               Document dirtyDocument = Jsoup.parse(sb.toString());<br />
 *               Element source = dirtyDocument.body();<br />
 *               Document clean = Document.createShell(dirtyDocument.baseUri());<br />
 *               Element dest = clean.body();<br />
 *               int len = 6;<br />
 *               truncateHTML(source,dest,len);<br />
 *               System.out.println(dest.html());<br />
 */
private static void truncateHTML(Element source, Element dest, int len) {
    List<Node> sourceChildren = source.childNodes();
    for (Node sourceChild : sourceChildren) {
        if (sourceChild instanceof Element) {
            Element sourceEl = (Element) sourceChild;
            Element destChild = createSafeElement(sourceEl);
            int txt = dest.text().length();
            if (txt >= len) {
                break;
            } else {
                len = len - txt;
            }
            dest.appendChild(destChild);
            truncateHTML(sourceEl, destChild, len);
        } else if (sourceChild instanceof TextNode) {
            int destLeng = dest.text().length();
            if (destLeng >= len) {
                break;
            }
            TextNode sourceText = (TextNode) sourceChild;
            int txtLeng = sourceText.getWholeText().length();
            if ((destLeng + txtLeng) > len) {
                int tmp = len - destLeng;
                String txt = sourceText.getWholeText().substring(0, tmp);
                TextNode destText = new TextNode(txt, sourceChild.baseUri());
                dest.appendChild(destText);
                break;
            } else {
                TextNode destText = new TextNode(sourceText.getWholeText(), sourceChild.baseUri());
                dest.appendChild(destText);
            }
        }
    }
}

Example 2 with TextNode

use of org.jsoup.nodes.TextNode in project flow by vaadin.

the class TemplateParser method collectIncludeNodes.

private static List<TextNode> collectIncludeNodes(Element element) {
    List<TextNode> includeNodes = new ArrayList<>();
    new NodeTraversor(new NodeVisitor() {

        @Override
        public void head(Node node, int depth) {
        // nop
        }

        @Override
        public void tail(Node node, int depth) {
            if (node instanceof TextNode) {
                TextNode textNode = (TextNode) node;
                String text = textNode.getWholeText();
                if (text.contains(INCLUDE_PREFIX)) {
                    includeNodes.add(textNode);
                }
            }
        }
    }).traverse(element);
    return includeNodes;
}

Example 3 with TextNode

use of org.jsoup.nodes.TextNode in project ocreader by schaal.

the class ArticleWebView method prepareDocument.

private void prepareDocument(Document document) {
    // Some blog engines replace emojis with an image and place the emoji in the image tag.
    // Find images with the tag being a single character and check if they are emoji. Then
    // replace the img with the actual emoji in unicode.
    Elements imgs = document.select("img[alt~=^.$]");
    for (Element img : imgs) {
        final String possibleEmoji = img.attr("alt");
        if (EmojiManager.isEmoji(possibleEmoji))
            img.replaceWith(new TextNode(possibleEmoji));
    }
    Elements iframes = document.getElementsByTag("iframe");
    for (Element iframe : iframes) {
        if (iframe.hasAttr("src")) {
            String href = iframe.attr("src");
            String html = String.format(Locale.US, videoLink, href, href);
            // Check if url matches any known patterns
            for (IframePattern iframePattern : IframePattern.values()) {
                Matcher matcher = iframePattern.pattern.matcher(href);
                if (matcher.matches()) {
                    final String videoId = matcher.group(2);
                    String urlPrefix = matcher.group(1);
                    href = urlPrefix + iframePattern.baseUrl + videoId;
                    // use thumbnail if available
                    if (iframePattern.thumbUrl != null) {
                        String thumbUrl = String.format(iframePattern.thumbUrl, urlPrefix, videoId);
                        html = String.format(Locale.US, videoThumbLink, href, thumbUrl);
                    }
                    break;
                }
            }
            iframe.replaceWith(Jsoup.parse(html).body().child(0));
        } else {
            iframe.remove();
        }
    }
}

Example 4 with TextNode

use of org.jsoup.nodes.TextNode in project mylyn.docs by eclipse.

the class HtmlCleanerTest method testTrailingWhitespaceBodyNoBlock_WhitespaceOutsideBody2.

@Test
public void testTrailingWhitespaceBodyNoBlock_WhitespaceOutsideBody2() {
    // bug 406943
    Document document = Document.createShell("");
    document.body().appendChild(new TextNode("\n", ""));
    document.body().appendChild(new TextNode("text", ""));
    document.body().appendChild(new TextNode("\n", ""));
    document.body().appendChild(new TextNode("\n", ""));
    String result = cleanToBody(document);
    assertEquals("<body>text</body>", result);
}

Example 5 with TextNode

use of org.jsoup.nodes.TextNode in project mylyn.docs by eclipse.

the class DocumentProcessor method normalizeTextNodes.

/**
 * normalize text node children of the given parent element. Ensures that adjacent text nodes are combined into a
 * single text node, and whitespace is normalized.
 *
 * @param parentElement
 *            the parent element whose children should be normalized
 * @see StringUtil#normaliseWhitespace(String)
 */
protected static void normalizeTextNodes(Element parentElement) {
    List<Node> children = parentElement.childNodes();
    if (!children.isEmpty()) {
        children = new ArrayList<Node>(children);
        for (Node child : children) {
            if (child instanceof TextNode) {
                TextNode childTextNode = (TextNode) child;
                Node previousSibling = child.previousSibling();
                if (previousSibling instanceof TextNode) {
                    TextNode previousSiblingTextNode = (TextNode) previousSibling;
                    childTextNode.text(previousSiblingTextNode.text() + childTextNode.text());
                    previousSibling.remove();
                }
                String wholeText = childTextNode.getWholeText();
                if (!Html.isWhitespacePreserve(parentElement)) {
                    wholeText = StringUtil.normaliseWhitespace(wholeText);
                }
                childTextNode.text(wholeText);
            }
        }
    }
}