Exciting things with XML

// uses the Scanner trick from http://weblogs.java.net/blog/pat/archive/2004/10/stupid_scanner.html
String rubbishHtml = new Scanner(new URL("http://www.microsoft.com").openStream(), 
  "UTF-8").useDelimiter("\\A").next();
String cleanXml = XmlUtil.getCleanXml(rubbishHtml, false);Document d = XmlUtil.toDocument(cleanXml);
Element titleEl = (Element) XPathAPI.selectSingleNode(d, "/html/head/title");

// uses the Scanner trick from http://weblogs.java.net/blog/pat/archive/2004/10/stupid_scanner.html
String rubbishHtml = new Scanner(new URL("http://www.microsoft.com").openStream(), 
  "UTF-8").useDelimiter("\\A").next();
String cleanXml = XmlUtil.getCleanXml(rubbishHtml, false);
Document d = XmlUtil.toDocument(cleanXml);
Element titleEl = (Element) XPathAPI.selectSingleNode(d, "/html/head/title");
String title = XmlUtil.getText(titleEl);System.out.println(title);

String input = "<p>Here is some formatted text <b>in bold</b>, <i>in italics</i>," +
  " <blink>blinking</blink>, and with an image at the end <img src=\"frog.png\"/></p>";
Document d = XmlUtil.toDocument(input);
Element paraEl = d.getDocumentElement();
System.out.println(XmlUtil.getText(paraEl));
System.out.println(XmlUtil.getTextPreserveElements(paraEl,   new String[] { "b", "i", "img" } ));

Here is some formatted text in bold, in italics, blinking, and with an image at the end 
Here is some formatted text <b>in bold</b>, <i>in italics</i>, blinking, and with an image at the end <img src="frog.png"></img>

String input = "<p>This is the bit we're interested in <span>but not this bit</span></p>";
Document d = XmlUtil.toDocument(input);
Element paraEl = d.getDocumentElement();
System.out.println(XmlUtil.getText(paraEl));
System.out.println(XmlUtil.getTextNonRecursive(paraEl));

This is the bit we're interested in but not this bit
This is the bit we're interested in

String rubbishHtml = new Scanner(new URL("http://www.google.com").openStream(), 
  "UTF-8").useDelimiter("\\A").next();
String cleanXml = XmlUtil.getCleanXml(rubbishHtml, false);
Document d = XmlUtil.toDocument(cleanXml);
NodeList nodes = XPathAPI.selectNodeList(d, "/html/head/meta");
for (int i=0; i<nodes.getLength(); i++) {
	System.out.println(i + ": " + XmlUtil.getXmlString(nodes.item(i),  true));
}

0: <meta content="/images/google_favicon_128.png" itemprop="image"/>

// from http://www.ibiblio.org/xml/examples/shakespeare/all_well.xml
String input = 
	"<PERSONAE>\n" +
	"    <TITLE>Dramatis Personae</TITLE>\n" +
	"    \n" +
	"    <PERSONA>KING OF FRANCE</PERSONA>\n" +
	"    <PERSONA>DUKE OF FLORENCE</PERSONA>\n" +
	"    <PERSONA>BERTRAM, Count of Rousillon.</PERSONA>\n" +
	"    <PERSONA>LAFEU, an old lord.</PERSONA>\n" +
	"    <PERSONA>PAROLLES, a follower of Bertram.</PERSONA>\n" +
	"    \n" +
	"    <PGROUP>\n" +
	"        <PERSONA>Steward</PERSONA>\n" +
	"        <PERSONA>Clown</PERSONA>\n" +
	"        <GRPDESCR>servants to the Countess of Rousillon.</GRPDESCR>\n" +
	"    </PGROUP>\n" +
	"    \n" +
	"    <PERSONA>A Page. </PERSONA>\n" +
	"    <PERSONA>COUNTESS OF ROUSILLON, mother to Bertram. </PERSONA>\n" +
	"    <PERSONA>HELENA, a gentlewoman protected by the Countess.</PERSONA>\n" +
	"    <PERSONA>An old Widow of Florence. </PERSONA>\n" +
	"    <PERSONA>DIANA, daughter to the Widow.</PERSONA>\n" +
	"    \n" +
	"    <PGROUP>\n" +
	"        <PERSONA>VIOLENTA</PERSONA>\n" +
	"        <PERSONA>MARIANA</PERSONA>\n" +
	"        <GRPDESCR>neighbours and friends to the Widow.</GRPDESCR>\n" +
	"    </PGROUP>\n" +
	"    \n" +
	"    <PERSONA>Lords, Officers, Soldiers, &amp;c., French and Florentine.</PERSONA>\n" +
	"</PERSONAE>\n";
 
Document d = XmlUtil.toDocument(input);
System.out.println("Before compact():");
System.out.println(XmlUtil.getXmlString(d, true));
 
XmlUtil.compact(d.getDocumentElement());System.out.println();
System.out.println("And after compact(), the much more readable:");
System.out.println(XmlUtil.getXmlString(d, true));

public static List<List<String>> getCurrencyRates(String date) throws MalformedURLException, IOException, SAXException, TransformerException {
	// this doesn't actually work due to http://www.xe.com/errors/noautoextract.htm
	// but I'm sure you enterprising types can get around that
	String url = "http://www.xe.com/currencytables/?from=AUD&date=" + date;
	String rubbishHtml = new Scanner(new URL(url).openStream(), 
	  "UTF-8").useDelimiter("\\A").next();
 
	// hint:
	// String rubbishHtml = Text.getFileContents(date.equals("2012-01-01") ? "c:\\rate1.txt" : "c:\\rate2.txt");
	String cleanXml = XmlUtil.getCleanXml(rubbishHtml, false);
 
	Document d = XmlUtil.toDocument(cleanXml);
	Element tableEl = (Element) XPathAPI.selectSingleNode(d, ".//table[@id=\"historicalRateTbl\"]");
 
	XmlUtil.SimpleTableContentHandler stch = new XmlUtil.SimpleTableContentHandler();	XmlUtil.processContentHandler(stch, XmlUtil.getXmlString(tableEl, false));
	List<List<String>> table = stch.getTable();
	return table;
}
 
// see what amount of abstract currency units you can get in exchange for
// the shiny Australian cylinder with a kangaroo on it.
List<List<String>> startTable = getCurrencyRates("2012-01-01");
List<List<String>> endTable = getCurrencyRates("2013-01-01");
 
// pick an investment strategy
int tradingOption = (int) (Math.random().nextGaussian() * startTable.size());
 
// sanity check that the row with the same index in each table contains the same currency
if (!startTable.get(tradingOption).get(0).equals(endTable.get(tradingOption).get(0))) {
	throw new RuntimeException("Rate tables don't line up");
}
 
System.out.println("You're investing in the " + startTable.get(tradingOption).get(1));
System.out.println("Of which you could pick up " + startTable.get(tradingOption).get(2) + " for a measly AUD$1 way back in 2012");
System.out.println("and then sell for AUD$" + endTable.get(tradingOption).get(3) + " each barely a year later");
 
// and then let's pretend that xe.com is accurate, and that rounding, 
// buy/sell prices and transaction costs don't exist
BigDecimal bd = new BigDecimal(startTable.get(tradingOption).get(2));
BigDecimal bd2 = new BigDecimal(endTable.get(tradingOption).get(3));
BigDecimal val = bd.multiply(bd2);
 
System.out.println("landing you AUD$" + val);
System.out.println(val.compareTo(new BigDecimal(1))>0 ? "Winner!" : "You lose!");

You're investing in the Belizean Dollar
Of which you could pick up 2.0266687920 for a measly AUD$1 way back in 2012
and then sell for AUD$0.4810598095 each barely a year later
landing you AUD$0.97494890299911512400
You lose!

public static class DeviceContentHandler 
  extends XmlUtil.AbstractStackContentHandler {	List<String> names = new ArrayList<String>();
 
	// process the start of an XML element
	public void element(String path) throws SAXException { }
 
	// process the text of an XML element 
	public void elementText(String path, String content) throws SAXException { 
		if (path.equals("devices/device/name")) {
			names.add(content);
		}
	}
 
	// return the names of all devices
	public List<String> getNames() { return names; }
}
 
DeviceContentHandler dch = new DeviceContentHandler();
XmlUtil.processContentHandler(dch, Text.getFileContents("c:\\device.xml"));
List<String> names = dch.getNames();
for (int i=0; i<names.size(); i++) {
	System.out.println(i + ": " + names.get(i));
}

0: DMXKing USB
1: Art-Net
2: WinAMP Controller
3: Ye olde dmxy plugigne

// get the Windows window tree in an XML object and attempt to find the Outlook windows in there
WindowTreeDom wtd = new WindowTreeDom();
Document windows = wtd.getDom();
NodeList outlookWindows = XPathAPI.selectNodeList(windows, 
  ".//window[@class='rctrl_renwnd32']/window[@class='AfxWndW']/window[@class='#32770']");   
 
for (Node n : new XmlUtil.NodeListIterator(outlookWindows)) {    Element e = (Element) n;
    logger.debug("Found possible window " + XmlUtil.getXmlString(n, true));
}