org.ccil.cowan.tagsoup.Parser Java Examples

public static Document loadDom(String url) {
 Parser parser = new Parser();

 try {
   parser.setFeature(Parser.namespacesFeature, false);
   parser.setFeature(Parser.namespacePrefixesFeature, false);
   Reader reader = openReader(url);
   DOMResult result = new DOMResult();
   Transformer transformer = TransformerFactory.newInstance().newTransformer();
   transformer.transform(new SAXSource(parser, new InputSource(reader)), result);
   reader.close();
   return (Document) result.getNode();
 } catch (Exception e) {
   throw new RuntimeException(e);
 }
}
 

public ConvertHTML(CommandBuilder builder, Config config, Command parent, Command child, MorphlineContext context) throws SAXNotRecognizedException, SAXNotSupportedException {
  super(builder, config, parent, child, context);
  this.charset = getConfigs().getCharset(config, "charset", null);
  this.omitXMLDeclaration = getConfigs().getBoolean(config, "omitXMLDeclaration", false);      
  this.xmlReader = new Parser(); // no reuse?
  xmlReader.setProperty(Parser.schemaProperty, htmlSchema);
  xmlReader.setFeature(Parser.CDATAElementsFeature, getConfigs().getBoolean(config, "noCDATA", false));
  xmlReader.setFeature(Parser.namespacesFeature, !getConfigs().getBoolean(config, "noNamespaces", true));
  xmlReader.setFeature(Parser.ignoreBogonsFeature, getConfigs().getBoolean(config, "noBogons", false)); // also see TIKA-599
  xmlReader.setFeature(Parser.bogonsEmptyFeature, getConfigs().getBoolean(config, "emptyBogons", false));
  xmlReader.setFeature(Parser.rootBogonsFeature, getConfigs().getBoolean(config, "noRootBogons", false));
  xmlReader.setFeature(Parser.defaultAttributesFeature, getConfigs().getBoolean(config, "noDefaultAttributes", false));
  xmlReader.setFeature(Parser.translateColonsFeature, getConfigs().getBoolean(config, "noColons", false));
  xmlReader.setFeature(Parser.restartElementsFeature, getConfigs().getBoolean(config, "noRestart", false));
  xmlReader.setFeature(Parser.ignorableWhitespaceFeature, !getConfigs().getBoolean(config, "suppressIgnorableWhitespace", true));
  validateArguments();
}
 

/**
 * 
 * @param xpath
 *            of the NodeList
 * @return a list of nodes found at the xpath
 * @throws Exception
 */
private NodeList getNodeListUsingJavaXPath(String xpath) throws Exception {
    XPathFactory xpathFac = XPathFactory.newInstance();
    XPath theXpath = xpathFac.newXPath();

    String html = getGUIDriver().getHtmlSource();
    html = html.replaceAll(">\\s+<", "><");
    InputStream input = new ByteArrayInputStream(html.getBytes(Charset.forName("UTF-8")));

    XMLReader reader = new Parser();
    reader.setFeature(Parser.namespacesFeature, false);
    Transformer transformer = TransformerFactory.newInstance().newTransformer();

    DOMResult result = new DOMResult();
    transformer.transform(new SAXSource(reader, new InputSource(input)), result);

    // This code gets a Node from the result.
    Node htmlNode = result.getNode();
    NodeList nodes = (NodeList) theXpath.evaluate(xpath, htmlNode, XPathConstants.NODESET);

    return nodes;
}
 

/**
 * Returns displayable styled text from the provided HTML string. Any <img> tags in the
 * HTML will use the specified ImageGetter to request a representation of the image (use null
 * if you don't want this) and the specified TagHandler to handle unknown tags (specify null if
 * you don't want this).
 * <p>
 * <p>This uses TagSoup to handle real HTML, including all of the brokenness found in the wild.
 */
public static Spanned fromHtml(@NonNull Context context, @NonNull String source, int flags,
                               @Nullable ImageGetter imageGetter, @Nullable TagHandler tagHandler,
                               @Nullable SpanCallback spanCallback) {
    if (source == null) {
        return null;
    }
    Parser parser = new Parser();
    try {
        parser.setProperty(Parser.schemaProperty, HtmlParser.schema);
    } catch (org.xml.sax.SAXNotRecognizedException | org.xml.sax.SAXNotSupportedException e) {
        // Should not happen.
        throw new RuntimeException(e);
    }
    HtmlToSpannedConverter converter =
            new HtmlToSpannedConverter(context, source, imageGetter, tagHandler, spanCallback, parser, flags);
    return converter.convert();
}
 

/**
 * Get the list of nodes which satisfy the xpath expression passed in
 * 
 * @param xpath
 *            the input xpath expression
 * @return the nodeset of matching elements
 * @throws Exception
 */
private NodeList getNodeListUsingJavaXPath(String xpath) throws Exception {
	XPathFactory xpathFac = XPathFactory.newInstance();
	XPath theXpath = xpathFac.newXPath();

	String html = getGUIDriver().getHtmlSource();
	html = html.replaceAll(">\\s+<", "><");
	InputStream input = new ByteArrayInputStream(html.getBytes(Charset.forName("UTF-8")));

	XMLReader reader = new Parser();
	reader.setFeature(Parser.namespacesFeature, false);
	Transformer transformer = TransformerFactory.newInstance().newTransformer();

	DOMResult result = new DOMResult();
	transformer.transform(new SAXSource(reader, new InputSource(input)), result);

	Node htmlNode = result.getNode(); // This code gets a Node from the
										// result.
	NodeList nodes = (NodeList) theXpath.evaluate(xpath, htmlNode, XPathConstants.NODESET);

	return nodes;
}
 

@Override
public String evaluateXpath(String xpath) throws Exception {
	XPathFactory xpathFac = XPathFactory.newInstance();
	XPath theXpath = xpathFac.newXPath();

	String html = getHtmlSource();
	html = html.replaceAll(">\\s+<", "><");
	InputStream input = new ByteArrayInputStream(html.getBytes(Charset.forName("UTF-8")));

	XMLReader reader = new Parser();
	reader.setFeature(Parser.namespacesFeature, false);
	Transformer transformer = TransformerFactory.newInstance()
			.newTransformer();

	DOMResult result = new DOMResult();
	transformer.transform(new SAXSource(reader, new InputSource(input)),
			result);

	Node htmlNode = result.getNode(); // This code gets a Node from the
										// result.
	return (String) theXpath.evaluate(xpath, htmlNode,
			XPathConstants.STRING);
}
 

/**
 * Returns displayable styled text from the provided HTML string.
 * Any <img> tags in the HTML will use the specified ImageGetter
 * to request a representation of the image (use null if you don't
 * want this) and the specified TagHandler to handle unknown tags
 * (specify null if you don't want this).
 *
 * <p>This uses TagSoup to handle real HTML, including all of the brokenness found in the wild.
 */
public static SpannableStringBuilder fromHtml(String source, ImageGetter imageGetter,
        TagHandler tagHandler) {
    Parser parser = new Parser();
    try {
        parser.setProperty(Parser.schemaProperty, HtmlParser.schema);
    } catch (org.xml.sax.SAXNotRecognizedException | org.xml.sax.SAXNotSupportedException e) {
        // Should not happen.
        throw new RuntimeException(e);
    }

    HtmlToSpannedConverter converter =
            new HtmlToSpannedConverter(source, imageGetter, tagHandler,
                    parser);
    return converter.convert();
}
 

public HtmlToSpannedConverter(String subject, String source, ThemeColors colors, HtmlParser.ImageGetter imageGetter, boolean openSpoilers,
        Parser parser) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    if (!TextUtils.isEmpty(subject)) {
        mSpannableStringBuilder.append(subject);
        int len = mSpannableStringBuilder.length();
        mSpannableStringBuilder.setSpan(new RelativeSizeSpan(1.25f), 0, len, Spannable.SPAN_EXCLUSIVE_EXCLUSIVE);
        mSpannableStringBuilder.setSpan(new StyleSpan(Typeface.BOLD), 0, len, Spannable.SPAN_EXCLUSIVE_EXCLUSIVE);
        if (colors != null) {
            mSpannableStringBuilder.setSpan(new ForegroundColorSpan(colors.subjectForeground), 0, len, Spannable.SPAN_EXCLUSIVE_EXCLUSIVE);
        }
        mSpannableStringBuilder.append('\n');
        mStartLength = mSpannableStringBuilder.length();
    }
    mColors = colors;
    mOpenSpoilers = openSpoilers;
    mImageGetter = imageGetter;
    mReader = parser;
}
 

public CustomHtmlToSpannedConverter(String source,
                                    Html.ImageGetter imageGetter, Html.TagHandler tagHandler,
                                    Parser parser, Html.ImageGetter emojiGetter, String baseUri, Context context) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
    mEmojiGetter = emojiGetter;
    mBaseUri = baseUri;
    userMentionColor = ContextCompat.getColor(context, R.color.dark_red);
    userMentionSelfColor = ContextCompat.getColor(context, R.color.self_mention_color);
}
 

public HtmlToSpannedConverter(String source, Html.ImageGetter imageGetter,
                              Html.TagHandler tagHandler, Parser parser, int flags) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
    mFlags = flags;
}
 

public HtmlToSpannedConverter(
        String source, Html.ImageGetter imageGetter, Html.TagHandler tagHandler,
        Parser parser) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
}
 

public HtmlToSpannedConverter( String source, Html.ImageGetter imageGetter,
        Html.TagHandler tagHandler, Parser parser, int flags) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
    mFlags = flags;
}
 

public HtmlToSpannedConverter(
        String source, Html.ImageGetter imageGetter, Html.TagHandler tagHandler,
        Parser parser) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
}
 

private BaseFinancialInstitutionData loadInstitutionData(String href) throws IOException, SAXException {
  if (LOG.isInfoEnabled()) {
    LOG.info("Loading institution data from: " + href);
  }
  
  URL url = new URL(href);
  XMLReader xmlReader = new Parser();
  xmlReader.setFeature("http://xml.org/sax/features/namespaces", false);
  xmlReader.setFeature("http://xml.org/sax/features/validation", false);
  InstitutionContentHandler institutionHandler = new InstitutionContentHandler();
  xmlReader.setContentHandler(institutionHandler);
  xmlReader.parse(new InputSource(url.openStream()));
  return institutionHandler.data;
}
 

private void initializeFIData() throws IOException, SAXException {
  URL url = new URL(getUrl());
  XMLReader xmlReader = new Parser();
  xmlReader.setFeature("http://xml.org/sax/features/namespaces", false);
  xmlReader.setFeature("http://xml.org/sax/features/validation", false);
  xmlReader.setContentHandler(new DirectoryContentHandler());
  xmlReader.parse(new InputSource(url.openStream()));
}
 

public HtmlToSpannedConverter(String source, Html.ImageGetter imageGetter,
                              Html.TagHandler tagHandler, Parser parser, int flags) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
    mFlags = flags;
}
 

HtmlToSpannedConverter(Context context, String source, HtmlCompat.ImageGetter imageGetter,
                       HtmlCompat.TagHandler tagHandler, HtmlCompat.SpanCallback spanCallback,
                       Parser parser, int flags) {
    mContext = context;
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mSpanCallback = spanCallback;
    mReader = parser;
    mFlags = flags;
}
 

public HtmlToSpannedConverter(String source, Html.ImageGetter imageGetter,
                              Html.TagHandler tagHandler, Parser parser, int flags) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
    mFlags = flags;
}
 

public HtmlToSpannedConverter(
        String source, Html.ImageGetter imageGetter, Html.TagHandler tagHandler,
        Parser parser) {
    mSource = source;
    mSpannableStringBuilder = new SpannableStringBuilder();
    mImageGetter = imageGetter;
    mTagHandler = tagHandler;
    mReader = parser;
}
 

private TagSoupDocumentParser() throws SAXNotRecognizedException, SAXNotSupportedException {
  parser = new Parser();
  // We do xpath evaluations which are not namespace aware. So make the parser
  // not use any namespaces.
  parser.setFeature(Parser.namespacesFeature, false);
}