public NodeList getAppletClassElements() {
try {
return (NodeList) appletClassXPression.evaluate(doc, XPathConstants.NODESET);
} catch (XPathExpressionException ex) {
return null;
}
}
/**
* Checks if there is a servlet element with specified Servlet name.
*
* @param servletName Servlet name to check.
* @return <code>true</code> if servle with specified name is present, <code>false</code>
* otherwise.
*/
public boolean isAppletDefined(String appletAID) {
try {
XPathExpression xPression =
xPath.compile("/applet-app/applet/applet-AID[text()='" + appletAID + "']"); // NOI18N
return (Boolean) xPression.evaluate(doc, XPathConstants.BOOLEAN);
} catch (XPathExpressionException ex) {
return false;
}
}
public Collection<String> getAllAppletAIDs() {
Set<String> names = new HashSet<String>();
try {
NodeList nodes = (NodeList) appletAIDXPression.evaluate(doc, XPathConstants.NODESET);
for (int i = 0; i < nodes.getLength(); i++) {
names.add(nodes.item(i).getNodeValue());
}
} catch (XPathExpressionException ex) {
Exceptions.printStackTrace(ex);
}
return names;
}
private String getConfigValue(String setting, String name, Document doc)
throws XPathExpressionException {
XPathFactory xPathfactory = XPathFactory.newInstance();
XPath xpath = xPathfactory.newXPath();
XPathExpression userExpr =
xpath.compile(
"wikipediaminer/setting[@name=\""
+ setting
+ "\"]/param[@name=\""
+ name
+ "\"]/@value");
return userExpr.evaluate(doc);
}
/**
* Removes empty #text nodes from a document. From James Murty on this StackOverflow post:
* http://stackoverflow.com/questions/978810/how-to-strip-whitespace-only-text-nodes-from-a-dom-before-serialization
*
* @param doc The document to remove empty text nodes from.
*/
private static void removeEmptyTextNodes(Document doc) {
try {
XPathFactory xpathFactory = XPathFactory.newInstance();
// XPath to find empty text nodes.
XPathExpression xpathExp =
xpathFactory.newXPath().compile("//text()[normalize-space(.) = '']");
NodeList emptyTextNodes = (NodeList) xpathExp.evaluate(doc, XPathConstants.NODESET);
// Remove each empty text node from document.
for (int i = 0; i < emptyTextNodes.getLength(); i++) {
Node emptyTextNode = emptyTextNodes.item(i);
emptyTextNode.getParentNode().removeChild(emptyTextNode);
}
} catch (Exception ex) {
ex.printStackTrace();
}
}
private NodeList findNodes(Document doc, Node operation) {
List<Node> xpaths = getChildNodes(operation, "xpath");
if (xpaths.isEmpty()) {
return null;
}
String xpathExpression = xpaths.get(0).getTextContent();
if (xpathExpression == null) {
return null;
}
XPathFactory xPathfactory = XPathFactory.newInstance();
XPath xpath = xPathfactory.newXPath();
NodeList nl = null;
try {
XPathExpression expr = xpath.compile(xpathExpression);
nl = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
} catch (XPathExpressionException ex) {
Utils.onError(new Error.WrongXpathExpression(xpathExpression));
}
return nl;
}
public void parseStartup(File file) {
Logger.getLogger(com.bombdiggity.amazon.ec2.install.Installer.class)
.info((new StringBuilder("InstallParser.parseStartup: ")).append(file).toString());
try {
Document doc = loadFile(file);
if (doc != null) {
XPathFactory factory = XMLUtils.newXPathFactory();
XPath xpath = factory.newXPath();
String rootXPath = "/Startup/Commands/*";
Element root = doc.getDocumentElement();
XPathExpression rootExp = xpath.compile(rootXPath);
NodeList streamList = (NodeList) rootExp.evaluate(root, XPathConstants.NODESET);
if (streamList != null) {
for (int i = 0; i < streamList.getLength(); i++) {
Node streamNode = streamList.item(i);
Element streamElem = (Element) streamNode;
if (streamElem.getNodeName().toLowerCase().equals("install")) {
String packageName = null;
String folderPath = null;
for (Node child = streamNode.getFirstChild();
child != null;
child = child.getNextSibling())
if (child.getNodeName().toLowerCase().equals("package"))
packageName = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("folder"))
folderPath = XMLUtils.getNodeValue(child).trim();
if (packageName != null) InstallCommands.installPackage(session, packageName);
else if (folderPath != null) InstallCommands.installFolder(session, folderPath);
else
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error("StartupParser.loadFile: <Install>: <Package> or <Folder> required");
} else if (streamElem.getNodeName().toLowerCase().equals("download")) {
String url = null;
String method = "get";
String data = null;
String destination = "/opt";
String action = null;
List headers = new ArrayList();
for (Node child = streamNode.getFirstChild();
child != null;
child = child.getNextSibling())
if (child.getNodeName().toLowerCase().equals("url"))
url = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("method"))
method = XMLUtils.getNodeValue(child).toLowerCase().trim();
else if (child.getNodeName().toLowerCase().equals("data"))
data = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("destination"))
destination = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("action"))
action = XMLUtils.getNodeValue(child).toLowerCase().trim();
else if (child.getNodeName().toLowerCase().equals("header")) {
Node nameNode = XMLUtils.getNodeByTagName((Element) child, "Name");
Node valueNode = XMLUtils.getNodeByTagName((Element) child, "Value");
if (nameNode != null && valueNode != null) {
Map namePair = new HashMap();
namePair.put(
XMLUtils.getNodeValue(nameNode).trim(),
XMLUtils.getNodeValue(valueNode).trim());
headers.add(namePair);
} else {
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error(
"StartupParser.loadFile: <Download/Header>: <Name> and <Value> required");
}
}
if (url != null && destination != null)
InstallCommands.downloadFile(
session, url, method, data, headers, destination, action);
else
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error("StartupParser.loadFile: <Download>: <URL> and <Destination> required");
} else if (streamElem.getNodeName().toLowerCase().equals("s3fetch")) {
String awsAccessKeyId = null;
String awsSecretAccessKey = null;
String bucket = null;
String key = null;
String destination = null;
String action = null;
for (Node child = streamNode.getFirstChild();
child != null;
child = child.getNextSibling())
if (child.getNodeName().toLowerCase().equals("awsaccesskeyid"))
awsAccessKeyId = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("awssecretaccesskey"))
awsSecretAccessKey = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("bucket"))
bucket = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("key"))
key = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("destination"))
destination = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("action"))
action = XMLUtils.getNodeValue(child).toLowerCase().trim();
if (awsAccessKeyId != null
&& awsSecretAccessKey != null
&& bucket != null
&& key != null
&& destination != null)
InstallCommands.fetchFile(
session, awsAccessKeyId, awsSecretAccessKey, bucket, key, destination, action);
else
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error(
"StartupParser.loadFile: <Fetch>: <AWSAccessKeyId>, <AWSSecretAccessKey>, <Bucket>, <Key> and <Destination> required");
} else if (streamElem.getNodeName().toLowerCase().equals("runscript")) {
String script = null;
List params = new ArrayList();
for (Node child = streamNode.getFirstChild();
child != null;
child = child.getNextSibling())
if (child.getNodeName().toLowerCase().equals("script"))
script = XMLUtils.getNodeValue(child).trim();
else if (child.getNodeName().toLowerCase().equals("param")) {
String param = XMLUtils.getNodeValue(child).trim();
params.add(param);
}
if (script != null) InstallCommands.runScript(session, script, params);
else
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error("StartupParser.loadFile: <RunScript>: <Script> required");
}
}
}
}
} catch (Exception e) {
Logger.getLogger(com.bombdiggity.amazon.ec2.install.InstallParser.class)
.error(
(new StringBuilder("InstallParser.parseStartup: ")).append(e.toString()).toString());
e.printStackTrace();
}
}
public static void main(String[] args) {
try {
DocumentBuilderFactory db = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = db.newDocumentBuilder();
Document dom = builder.parse("data/geographic-area-data.html");
XPathFactory xpath = XPathFactory.newInstance();
XPath path = xpath.newXPath();
XPathExpression table =
path.compile("//div[@id='mw-content-text']/table[contains(@class,'wikitable')]/tr");
NodeList wikiData = (NodeList) table.evaluate(dom, XPathConstants.NODESET);
NodeList children;
String currentData, cleanData;
/* Open output stream */
FileWriter fstream = new FileWriter("data/parsed.yaml");
BufferedWriter out = new BufferedWriter(fstream);
for (int i = 0; i < wikiData.getLength(); i++) {
if (i == 0) {
continue;
}
out.write(new Integer(i).toString() + ":\n");
children = wikiData.item(i).getChildNodes();
for (int j = 0; j < children.getLength(); j++) {
currentData = (String) children.item(j).getTextContent();
switch (j) {
case 0:
/* Current Data is empty */
break;
case 1:
cleanData = decompose(currentData).trim().replaceAll("[^a-zA-Z\\s]+", "");
out.write("\t\"Geographic entity\": \"" + cleanData + "\"\n");
break;
case 2:
/* Current Data is empty */
break;
case 3:
cleanData = decompose(currentData).trim().replaceAll(",", "");
out.write("\t\"Area\": \"" + cleanData + "\"\n");
break;
case 4:
/* Current Data is empty */
break;
case 5:
cleanData = decompose(currentData).trim();
out.write("\t\"Notes\": \"" + cleanData + "\"\n");
break;
case 6:
/* Current Data is empty */
break;
default:
/* System.out.println("[" + j + "] Hit default case statement. Current Data is: " + currentData); */
break;
}
}
}
/* Close output stream */
out.close();
} catch (Exception e) {
System.out.println(e);
}
}
@Override
public HashSet<ScoredAnnotation> solveSa2W(String text) throws AnnotationException {
HashSet<ScoredAnnotation> res;
try {
res = new HashSet<ScoredAnnotation>();
lastTime = Calendar.getInstance().getTimeInMillis();
URL wikiApi = new URL(url);
String parameters =
"references=true&repeatMode=all&minProbability=0.0&source="
+ URLEncoder.encode(text, "UTF-8");
HttpURLConnection slConnection = (HttpURLConnection) wikiApi.openConnection();
slConnection.setRequestProperty("accept", "text/xml");
slConnection.setDoOutput(true);
slConnection.setDoInput(true);
slConnection.setRequestMethod("POST");
slConnection.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
slConnection.setRequestProperty("charset", "utf-8");
slConnection.setRequestProperty(
"Content-Length", "" + Integer.toString(parameters.getBytes().length));
slConnection.setUseCaches(false);
DataOutputStream wr = new DataOutputStream(slConnection.getOutputStream());
wr.writeBytes(parameters);
wr.flush();
wr.close();
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(slConnection.getInputStream());
/* URL wikiApi = new URL(url+"?references=true&repeatMode=all&minProbability=0.0&source="+URLEncoder.encode(text, "UTF-8"));
URLConnection wikiConnection = wikiApi.openConnection();
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(wikiConnection.getInputStream());
*/
lastTime = Calendar.getInstance().getTimeInMillis() - lastTime;
XPathFactory xPathfactory = XPathFactory.newInstance();
XPath xpath = xPathfactory.newXPath();
XPathExpression idExpr = xpath.compile("//detectedTopic/@id");
XPathExpression weightExpr = xpath.compile("//detectedTopic/@weight");
XPathExpression referenceExpr = xpath.compile("//detectedTopic/references");
NodeList ids = (NodeList) idExpr.evaluate(doc, XPathConstants.NODESET);
NodeList weights = (NodeList) weightExpr.evaluate(doc, XPathConstants.NODESET);
NodeList references = (NodeList) referenceExpr.evaluate(doc, XPathConstants.NODESET);
for (int i = 0; i < weights.getLength(); i++) {
if (weights.item(i).getNodeType() != Node.TEXT_NODE) {
int id = Integer.parseInt(ids.item(i).getNodeValue());
float weight = Float.parseFloat(weights.item(i).getNodeValue());
// System.out.println("ID="+ids.item(i).getNodeValue()+" weight="+weight);
XPathExpression startExpr =
xpath.compile("//detectedTopic[@id=" + id + "]/references/reference/@start");
XPathExpression endExpr =
xpath.compile("//detectedTopic[@id=" + id + "]/references/reference/@end");
NodeList starts =
(NodeList) startExpr.evaluate(references.item(i), XPathConstants.NODESET);
NodeList ends = (NodeList) endExpr.evaluate(references.item(i), XPathConstants.NODESET);
for (int j = 0; j < starts.getLength(); j++) {
int start = Integer.parseInt(starts.item(j).getNodeValue());
int end = Integer.parseInt(ends.item(j).getNodeValue());
int len = end - start;
res.add(new ScoredAnnotation(start, len, id, weight));
}
}
}
} catch (Exception e) {
e.printStackTrace();
throw new AnnotationException(
"An error occurred while querying Wikipedia Miner API. Message: " + e.getMessage());
}
return res;
}