Examples with Node org.htmlparser.Node used on opensource projects

Example 1 with Node

use of org.htmlparser.Node in project jforum2 by rafaelsteil.

the class SafeHtml method makeSafe.

/**
 * Given an input, makes it safe for HTML displaying.
 * Removes any not allowed HTML tag or attribute, as well
 * unwanted Javascript statements inside the tags.
 * @param contents the input to analyze
 * @return the modified and safe string
 */
public String makeSafe(String contents) {
    if (contents == null || contents.length() == 0) {
        return contents;
    }
    StringBuffer sb = new StringBuffer(contents.length());
    try {
        Lexer lexer = new Lexer(contents);
        Node node;
        while ((node = lexer.nextNode()) != null) {
            boolean isTextNode = node instanceof TextNode;
            if (isTextNode) {
                // Text nodes are raw data, so we just
                // strip off all possible html content
                String text = node.toHtml();
                if (text.indexOf('>') > -1 || text.indexOf('<') > -1) {
                    StringBuffer tmp = new StringBuffer(text);
                    ViewCommon.replaceAll(tmp, "<", "&lt;");
                    ViewCommon.replaceAll(tmp, ">", "&gt;");
                    ViewCommon.replaceAll(tmp, "\"", "&quot;");
                    node.setText(tmp.toString());
                }
            }
            if (isTextNode || (node instanceof Tag && this.isTagWelcome(node))) {
                sb.append(node.toHtml());
            } else {
                StringBuffer tmp = new StringBuffer(node.toHtml());
                ViewCommon.replaceAll(tmp, "<", "&lt;");
                ViewCommon.replaceAll(tmp, ">", "&gt;");
                sb.append(tmp.toString());
            }
        }
    } catch (Exception e) {
        throw new ForumException("Error while parsing HTML: " + e, e);
    }
    return sb.toString();
}

Example 2 with Node

use of org.htmlparser.Node in project dhis2-core by dhis2.

the class GridUtils method getColumnCount.

/**
 * Returns the number of columns/cells in the given row, including cell
 * spacing.
 */
private static int getColumnCount(TableRow row) {
    Node[] cells = row.getChildren().extractAllNodesThatMatch(HTML_ROW_FILTER).toNodeArray();
    int cols = 0;
    for (Node cell : cells) {
        Integer colSpan = MathUtils.parseInt(((TagNode) cell).getAttribute("colspan"));
        cols += colSpan != null ? colSpan : 1;
    }
    return cols;
}

Example 3 with Node

use of org.htmlparser.Node in project jforum2 by rafaelsteil.

the class SafeHtml method ensureAllAttributesAreSafe.

/**
 * Given an input, analyze each HTML tag and remove unsecure attributes from them.
 * @param contents The content to verify
 * @return the content, secure.
 */
public String ensureAllAttributesAreSafe(String contents) {
    StringBuffer sb = new StringBuffer(contents.length());
    try {
        Lexer lexer = new Lexer(contents);
        Node node;
        while ((node = lexer.nextNode()) != null) {
            if (node instanceof Tag) {
                Tag tag = (Tag) node;
                this.checkAndValidateAttributes(tag, false);
                sb.append(tag.toHtml());
            } else {
                sb.append(node.toHtml());
            }
        }
    } catch (Exception e) {
        throw new ForumException("Problems while parsing HTML: " + e, e);
    }
    return sb.toString();
}

Example 4 with Node

use of org.htmlparser.Node in project omegat by omegat-org.

the class FilterVisitor method endup.

/**
 * Ends the segment collection and sends the translatable text out to OmegaT
 * core, and some extra tags to writer.
 */
protected void endup() {
    // detecting the first starting tag in 'befors'
    // that has its ending in the paragraph
    // all before this "first good" are simply written out
    List<Node> all = new ArrayList<Node>();
    all.addAll(befors);
    all.addAll(translatable);
    int firstgoodlimit = befors.size();
    int firstgood = 0;
    while (firstgood < firstgoodlimit) {
        Node goodNode = all.get(firstgood);
        if (!(goodNode instanceof Tag)) {
            firstgood++;
            continue;
        }
        Tag good = (Tag) goodNode;
        // trying to test
        int recursion = 1;
        boolean found = false;
        for (int i = firstgood + 1; i < all.size(); i++) {
            Node candNode = all.get(i);
            if (candNode instanceof Tag) {
                Tag cand = (Tag) candNode;
                if (cand.getTagName().equals(good.getTagName())) {
                    if (!cand.isEndTag()) {
                        recursion++;
                    } else {
                        recursion--;
                        if (recursion == 0) {
                            if (i >= firstgoodlimit) {
                                found = true;
                            }
                            // we've found an ending tag for this "good one"
                            break;
                        }
                    }
                }
            }
        }
        // this is a "good one"
        if (found) {
            break;
        }
        firstgood++;
    }
    // detecting the last ending tag in 'afters'
    // that has its starting in the paragraph
    // all after this "last good" is simply writen out
    int lastgoodlimit = all.size() - 1;
    all.addAll(afters);
    int lastgood = all.size() - 1;
    while (lastgood > lastgoodlimit) {
        Node goodNode = all.get(lastgood);
        if (!(goodNode instanceof Tag)) {
            lastgood--;
            continue;
        }
        Tag good = (Tag) goodNode;
        // trying to test
        int recursion = 1;
        boolean found = false;
        for (int i = lastgood - 1; i >= firstgoodlimit; i--) {
            Node candNode = all.get(i);
            if (candNode instanceof Tag) {
                Tag cand = (Tag) candNode;
                if (cand.getTagName().equals(good.getTagName())) {
                    if (cand.isEndTag()) {
                        recursion++;
                    } else {
                        recursion--;
                        if (recursion == 0) {
                            if (i <= lastgoodlimit) {
                                found = true;
                            }
                            // "good one"
                            break;
                        }
                    }
                }
            }
        }
        // this is a "good one"
        if (found) {
            break;
        }
        lastgood--;
    }
    boolean changed = true;
    while (changed) {
        changed = false;
        boolean removeTags = Core.getFilterMaster().getConfig().isRemoveTags();
        if (!removeTags) {
            for (int i = 0; i < firstgood; i++) {
                Node node = all.get(i);
                if (node instanceof Tag) {
                    firstgood = i;
                    changed = true;
                    break;
                }
            }
            for (int i = all.size() - 1; i > lastgood; i--) {
                Node node = all.get(i);
                if (node instanceof Tag) {
                    lastgood = i;
                    changed = true;
                    break;
                }
            }
        }
        boolean removeSpacesAround = Core.getFilterMaster().getConfig().isRemoveSpacesNonseg();
        if (!removeSpacesAround) {
            for (int i = 0; i < firstgood; i++) {
                Node node = all.get(i);
                if (node instanceof TextNode) {
                    firstgood = i;
                    changed = true;
                    break;
                }
            }
            for (int i = all.size() - 1; i > lastgood; i--) {
                Node node = all.get(i);
                if (node instanceof TextNode) {
                    lastgood = i;
                    changed = true;
                    break;
                }
            }
        }
    }
    // writing out all tags before the "first good" one
    for (int i = 0; i < firstgood; i++) {
        Node node = all.get(i);
        if (node instanceof Tag) {
            writeout("<" + node.getText() + ">");
        } else {
            writeout(compressWhitespace(node.getText()));
        }
    }
    // appending all tags until "last good" one to paragraph text
    StringBuilder paragraph = new StringBuilder();
    // appending all tags starting from "first good" one to paragraph text
    for (int i = firstgood; i <= lastgood; i++) {
        Node node = all.get(i);
        if (node instanceof Tag) {
            shortcut((Tag) node, paragraph);
        } else {
            // node instanceof Text
            paragraph.append(HTMLUtils.entitiesToChars(node.toHtml()));
        }
    }
    String uncompressed = paragraph.toString();
    String compressed = uncompressed;
    String spacePrefix = "";
    String spacePostfix = "";
    int size = uncompressed.length();
    // (This changes the layout, therefore it is an option)
    if (!preformatting) {
        for (int cp, i = 0; i < size; i += Character.charCount(cp)) {
            cp = uncompressed.codePointAt(i);
            if (!Character.isWhitespace(cp)) {
                spacePrefix = i == 0 ? "" : uncompressed.substring(0, options.getCompressWhitespace() ? Math.min(i, uncompressed.offsetByCodePoints(i, 1)) : i);
                break;
            }
        }
        for (int cp, i = size; i > 0; i -= Character.charCount(cp)) {
            cp = uncompressed.codePointBefore(i);
            if (!Character.isWhitespace(cp)) {
                spacePostfix = i == size ? "" : uncompressed.substring(i, options.getCompressWhitespace() ? Math.min(uncompressed.offsetByCodePoints(i, 1), size) : size);
                break;
            }
        }
        if (Core.getFilterMaster().getConfig().isRemoveSpacesNonseg()) {
            compressed = StringUtil.compressSpaces(uncompressed);
        } else {
            compressed = uncompressed;
        }
    }
    // getting the translation
    String translation = filter.privateProcessEntry(compressed, null);
    // writing out uncompressed
    if (compressed.equals(translation) && !options.getCompressWhitespace()) {
        translation = uncompressed;
    }
    // converting & < and > into &amp; &lt; and &gt; respectively
    // note that this doesn't change < and > of tag shortcuts
    translation = HTMLUtils.charsToEntities(translation, filter.getTargetEncoding(), sShortcuts);
    // expands tag shortcuts into full-blown tags
    translation = unshorcutize(translation);
    // writing out the paragraph into target file
    writeout(spacePrefix);
    writeout(translation);
    writeout(spacePostfix);
    // writing out all tags after the "last good" one
    for (int i = lastgood + 1; i < all.size(); i++) {
        Node node = all.get(i);
        if (node instanceof Tag) {
            writeout("<" + node.getText() + ">");
        } else {
            writeout(compressWhitespace(node.getText()));
        }
    }
    cleanup();
}

Example 5 with Node

use of org.htmlparser.Node in project laogewen by wen4034.

the class HtmlParserTool method extracLinks.

public static Set<String> extracLinks(String url, LinkFilter filter, String... validate) {
    Set<String> links = Sets.newHashSet();
    try {
        URL realurl = new URL(url);
        URLConnection connection = realurl.openConnection();
        connection.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");
        connection.setReadTimeout(100000);
        connection.setConnectTimeout(100000);
        Parser parser = new Parser(connection);
        parser.setEncoding("UTF-8");
        // 过滤<frame>标签的filter,用来提取frame标签的src属性
        NodeFilter frameFilter = new NodeFilter() {

            @Override
            public boolean accept(Node node) {
                if (node.getText().startsWith("frame src=")) {
                    return true;
                } else {
                    return false;
                }
            }
        };
        OrFilter linkFilter = new OrFilter(new NodeClassFilter(LinkTag.class), frameFilter);
        NodeList list = parser.extractAllNodesThatMatch(linkFilter);
        for (int i = 0; i < list.size(); i++) {
            Node tag = list.elementAt(i);
            if (tag instanceof LinkTag) {
                LinkTag linkTag = (LinkTag) tag;
                String linkurl = linkTag.getLink();
                if (filter.accept(linkurl, validate)) {
                    links.add(linkurl);
                }
            } else {
                String fram = tag.getText();
                int start = fram.indexOf("src=");
                fram = fram.substring(start);
                int end = fram.indexOf(" ");
                if (end == -1) {
                    end = fram.indexOf(">");
                }
                String frameUrl = fram.substring(5, end - 1);
                if (filter.accept(frameUrl, validate)) {
                    links.add(frameUrl);
                }
            }
        }
    } catch (Exception e) {
        System.out.println(url + "链接失败");
        e.printStackTrace();
    }
    return links;
}