Java Parser类代码示例

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
public void download()
{
	UnicodeReader reader = new UnicodeReader(stream, "UTF-8"); //$NON-NLS-1$
	XMLReader r = new Parser();
	InputSource s = new InputSource();
	s.setCharacterStream(reader);
	try
	{
		r.setContentHandler(this);
		r.parse(s);
	}
	catch( Exception e )
	{
		throw new RuntimeException(e);
	}
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
@Override
public String modifyXml(Reader reader, HtmlContentHandler writer)
{
	InputSource s = new InputSource();
	s.setEncoding(Constants.UTF8);
	s.setCharacterStream(reader);
	try
	{
		XMLReader r = new Parser();
		r.setContentHandler(writer);
		r.parse(s);
		return writer.getOutput();
	}
	catch( Exception e )
	{
		throw new RuntimeException(e);
	}
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
private String changeHardcodedUrls(String html, final URL oldUrl, final URL newUrl)
{
	final XMLReader p = new Parser();
	final InputSource s = new InputSource();
	final StringWriter w = new StringWriter();
	final ItemConverterHrefCallback cb = new ItemConverterHrefCallback(oldUrl, newUrl);
	final FindHrefHandler x = new FindHrefHandler(w, cb, true, true);

	p.setContentHandler(x);
	s.setCharacterStream(new StringReader(html));
	try
	{
		p.parse(s);
		if( cb.wasChanged() )
		{
			return w.toString();
		}
		return null;
	}
	catch( Exception e )
	{
		throw new RuntimeException(e);
	}
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
/**
 * 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();
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
public String parse(String html) {
	Parser p = new Parser();
	p.setContentHandler(this);
	p.setErrorHandler(this);
	try {
		p.setFeature(Parser.defaultAttributesFeature, false); //or else some default attributes get added to <br>
		p.setFeature(Parser.ignorableWhitespaceFeature, false);

		p.setProperty(Parser.lexicalHandlerProperty, this);

		InputSource inputSource = new InputSource(new StringReader(html));
		p.parse(inputSource);

	} catch (Exception e) {
		// TODO Auto-generated catch block
	}

	return rebuiltHtml.toString();
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
/**
 * 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();
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
private void init(Result result, Reader in, ContentType type, HeaderSet headers, boolean html) throws HttpClientException {
  myContentType = type;
  myHeaders = headers;
  String sys_id = "TODO-find-a-useful-systemId";
  try {
    Source src;
    if (html) {
      Parser parser = new Parser();
      parser.setFeature(Parser.namespacesFeature, true);
      parser.setFeature(Parser.namespacePrefixesFeature, true);
      InputSource input = new InputSource(in);
      src = new SAXSource(parser, input);
      src.setSystemId(sys_id);
    } else {
      src = new StreamSource(in, sys_id);
    }
    result.add(src);
  } catch (SAXException ex) {
    throw new HttpClientException("error parsing result HTML", ex);
  }
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
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;
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
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);
 }
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
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();
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
@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);
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
/**
 * 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;
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
/**
 * 
 * @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;
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
/**
 * @see org.apache.sling.commons.html.HtmlParser#parse(java.lang.String, java.io.InputStream, java.lang.String)
 */
public Document parse(String systemId, InputStream stream, String encoding) throws IOException {
    final Parser parser = new Parser();
    final DOMBuilder builder = new DOMBuilder();
    final InputSource source = new InputSource(stream);
    source.setEncoding(encoding);
    source.setSystemId(systemId);
    try {
        parser.setProperty("http://xml.org/sax/properties/lexical-handler", builder);
        parser.setContentHandler(builder);
        parser.parse(source);
    } catch (SAXException se) {
        if ( se.getCause() instanceof IOException ) {
            throw (IOException) se.getCause();
        }
        throw (IOException) new IOException("Unable to parse xml.").initCause(se);
    }
    return builder.getDocument();
}
 

import org.ccil.cowan.tagsoup.Parser; //导入依赖的package包/类
@Override
public XmlScriptType getHtmlAsXml()
{
	try
	{
		XMLReader htmlParser = new Parser();
		htmlParser.setFeature(Parser.namespacesFeature, false);
		htmlParser.setFeature(Parser.namespacePrefixesFeature, false);

		Transformer transformer = TransformerFactory.newInstance().newTransformer();

		DOMResult result = new DOMResult();
		transformer.transform(new SAXSource(htmlParser, new InputSource(new StringReader(getAsText()))),
			result);

		Node node = result.getNode();
		if( node.getNodeType() == Node.DOCUMENT_NODE )
		{
			node = node.getFirstChild();
		}
		return new PropBagWrapper(new PropBagEx(node));
	}
	catch( Exception ex )
	{
		throw new RuntimeException("Response received from external URL could not be tidied into XML", ex);
	}
}