Examples with Lexer org.htmlparser.lexer.Lexer used on opensource projects

Example 1 with Lexer

use of org.htmlparser.lexer.Lexer 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 Lexer

use of org.htmlparser.lexer.Lexer in project portfolio by buchen.

the class DestatisCPIFeed method getConsumerPriceIndices.

@Override
public List<ConsumerPriceIndex> getConsumerPriceIndices() throws IOException {
    try {
        disableCertificateValidation();
        URL url = new URL(// $NON-NLS-1$
        "https://www.destatis.de/DE/ZahlenFakten/GesamtwirtschaftUmwelt/Preise/Verbraucherpreisindizes/Tabellen_/VerbraucherpreiseKategorien.html");
        Lexer lexer = new Lexer(url.openConnection());
        List<ConsumerPriceIndex> prices = new Visitor().visit(lexer);
        if (prices.isEmpty())
            throw new IOException(Messages.MsgResponseContainsNoIndices);
        return prices;
    } catch (ParserException e) {
        throw new IOException(e);
    }
}

Example 3 with Lexer

use of org.htmlparser.lexer.Lexer in project portfolio by buchen.

the class DestatisCPIFeedTest method testParsingHtml.

@Test
public void testParsingHtml() throws IOException, ParserException {
    try (Scanner scanner = new Scanner(getClass().getResourceAsStream("response_destatis.txt"), "UTF-8")) {
        String html = scanner.useDelimiter("\\A").next();
        Lexer lexer = new Lexer(html);
        List<ConsumerPriceIndex> prices = new DestatisCPIFeed.Visitor().visit(lexer);
        assertThat(prices.size(), equalTo(19 * /* years in file */
        12 + 6));
        ConsumerPriceIndex p = prices.get(5);
        assertThat(p.getYear(), equalTo(2012));
        assertThat(p.getMonth(), equalTo(Month.JANUARY.getValue()));
        assertThat(p.getIndex(), equalTo(11150));
    }
}

Example 4 with Lexer

use of org.htmlparser.lexer.Lexer 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();
}