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);
}
private PageManifestDef loadRootPageDefinition(String manifestPathOrPath)
throws ParserConfigurationException, SAXException, XPathExpressionException, IOException {
PageManifestDef pmd = new PageManifestDef();
Document document = readPageDefinitionFile(manifestPathOrPath, pmd);
pmd.setSelectorStrategy(selectorExpr.evaluate(document));
return pmd;
}
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;
}
private SignatureData createSignatureDataFromXmlDigSig(String signature)
throws SignatureException {
// Start with setting some fields that are known directly
SignatureData signatureData = new SignatureData();
signatureData.setClientType(new ELegType("test", "test", PkiClient.NEXUS_PERSONAL_4X));
signatureData.setSignature(new String(Base64.encode(signature.getBytes())));
// For the rest we need to parse the XML
try {
Document document = createDocument(new ByteArrayInputStream(signature.getBytes()), false);
// nonce and tbs
XPath xpath = XPathFactory.newInstance().newXPath();
XPathExpression expression =
xpath.compile("/Signature/Object/bankIdSignedData/srvInfo/nonce/text()");
String encodedNonce = (String) expression.evaluate(document, XPathConstants.STRING);
String decodedNonce =
new String(Base64.decode(encodedNonce)); // will be re-encoded again before it is sent
signatureData.setNonce(decodedNonce);
expression = xpath.compile("/Signature/Object/bankIdSignedData/usrVisibleData/text()");
String encodedTbs = (String) expression.evaluate(document, XPathConstants.STRING);
String decodedTbs =
new String(Base64.decode(encodedTbs)); // this will be re-encoded again before it is sent
signatureData.setEncodedTbs(encodedTbs);
signatureData.setTbs(decodedTbs);
} catch (XPathExpressionException e) {
throw new SignatureException(e);
} catch (ParserConfigurationException e) {
throw new SignatureException(e);
} catch (SAXException e) {
throw new SignatureException(e);
} catch (IOException e) {
throw new SignatureException(e);
}
return signatureData;
}
/**
* extract the XPath from the content. the return value type is passed in input using one of the
* {@link XPathConstants}. See also {@link XPathExpression#evaluate(Object item, QName
* returnType)} ;
*
* @param ns
* @param xpathExpression
* @param content
* @param returnType
* @param charset
* @return the result
*/
public static Object extractXPath(
Map<String, String> ns,
String xpathExpression,
String content,
QName returnType,
String charset) {
if (null == ns) {
ns = new HashMap<String, String>();
}
String ch = charset;
if (ch == null) {
ch = Charset.defaultCharset().name();
}
Document doc = toDocument(content, charset);
XPathExpression expr = toExpression(ns, xpathExpression);
try {
Object o = expr.evaluate(doc, returnType);
return o;
} catch (XPathExpressionException e) {
throw new IllegalArgumentException("xPath expression cannot be executed: " + xpathExpression);
}
}
public Credentials authenticate() throws Exception {
HttpURLConnection urlConnection =
new ConnBuilder(authUrl)
.addHeader(HttpHeaders.CONTENT_TYPE_HEADER, "application/json")
.addHeader(HttpHeaders.ACCEPT_HEADER, "application/xml")
.getConnection();
StringBuilder jsonBuilder = new StringBuilder();
jsonBuilder
.append("{\"auth\": {\"tenantName\": \"")
.append(tenant)
.append("\", \"passwordCredentials\": {\"username\": \"")
.append(username)
.append("\", \"password\": \"")
.append(password)
.append("\"}}}");
HttpResponse response =
Utils.doOperation(urlConnection, jsonBuilder.toString().getBytes(), true);
if (response.isSuccessCode()) {
DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = documentBuilderFactory.newDocumentBuilder();
Document doc = builder.parse(new ByteArrayInputStream(response.payload));
String authToken = (String) tokenIdExpression.evaluate(doc, XPathConstants.STRING);
String storageUrl = (String) publicUrlExpression.evaluate(doc, XPathConstants.STRING);
log.trace("Authentication successful");
return new Credentials(authToken, storageUrl);
} else {
throw new IllegalStateException(
"Error authenticating to the service. Please check your credentials. Code = "
+ response.code);
}
}
/**
* Gets Xpath results
*
* @param contextNode
* @param xpathValue
* @return
* @throws XPathExpressionException
*/
private NodeList getXPathResults(Node contextNode, String xpathValue)
throws XPathExpressionException {
XPathFactory factory = XPathFactory.newInstance();
XPath xpath = factory.newXPath();
// see if the request root is in a namespace
String namespace = contextNode.getNamespaceURI();
// name spaces are used, so we need to lookup the correct
// prefix to use in the search string
NamedNodeMap namedNodeMap = contextNode.getAttributes();
Map<String, String> nsMap = new HashMap<String, String>();
for (int i = 0; i < namedNodeMap.getLength(); i++) {
Node n = namedNodeMap.item(i);
// we found the matching namespace, so get the prefix
// and then break out
String prefix = DOMHelper.getLocalName(n);
String nodeValue = n.getNodeValue();
nsMap.put(prefix, nodeValue);
}
// if there is not any namespace is defined for content element, default XACML request
// name space would be there.
if (XACMLConstants.REQUEST_CONTEXT_3_0_IDENTIFIER.equals(namespace)
|| XACMLConstants.REQUEST_CONTEXT_2_0_IDENTIFIER.equals(namespace)
|| XACMLConstants.REQUEST_CONTEXT_1_0_IDENTIFIER.equals(namespace)) {
nsMap.put("xacml", namespace);
}
NamespaceContext namespaceContext = new DefaultNamespaceContext(nsMap);
xpath.setNamespaceContext(namespaceContext);
XPathExpression expression = xpath.compile(xpathValue);
return (NodeList) expression.evaluate(contextNode, XPathConstants.NODESET);
}
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);
}
}
protected Document parse(InputStream inputStream) throws LibraryException {
Map<Integer, SongBean> songMap = new HashMap<Integer, SongBean>();
Map<Integer, AlbumBean> albumMap = new HashMap<Integer, AlbumBean>();
Map<Integer, AlbumBean> secondaryAlbumMap = new HashMap<Integer, AlbumBean>();
warningList.clear();
try {
// Create a builder factory
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setValidating(false);
factory.setNamespaceAware(true);
factory.setIgnoringElementContentWhitespace(true);
factory.setIgnoringComments(true);
// Create the builder and parse the file
DocumentBuilder builder = factory.newDocumentBuilder();
// Set an error listener and parse the document
builder.setErrorHandler(new iTradeTunesLibraryErrorHandler());
builder.setEntityResolver(new iTradeTunesLibraryResolver());
Document document = builder.parse(inputStream);
synchronized (libraryList) {
// Query the library document and build the library list
XPath xPath = XPathFactory.newInstance().newXPath();
XPathExpression xPathExpression = xPath.compile(XPATH_LIBRARY_LIST);
NodeList nodelist = (NodeList) xPathExpression.evaluate(document, XPathConstants.NODESET);
// Process the elements in the nodelist
SongBean song = null;
for (int i = 0; i < nodelist.getLength(); i++) {
boolean isTrackID = false;
// Get element and child nodes
Element elem = (Element) nodelist.item(i);
NodeList list = elem.getChildNodes();
// Get node value
Node childKey = list.item(0);
String key = childKey.getNodeValue();
// Check if we have to create a new bean
if (SongBean.NAME_TRACK_ID.equals(key)) {
isTrackID = true;
SongBean previousSong = song;
song = new SongBean();
if (previousSong != null
&& !("AAC audio file".equals(previousSong.getKind())
|| "MPEG audio file".equals(previousSong.getKind()))) {
songMap.remove(previousSong.getTrack_ID());
} else {
// Add an album bean
addOrUpdateAlbum(albumMap, previousSong, false);
}
}
// The first parameter is the key
String prop = childKey.getNodeValue().replace(' ', '_');
// The second parameter is the value
i++;
// Get element and child nodes
elem = (Element) nodelist.item(i);
// Check for boolean properties
Object value = null;
// Get node value
list = elem.getChildNodes();
childKey = list.item(0);
value = (childKey == null) ? elem.getNodeName() : childKey.getNodeValue();
if (isTrackID) {
isTrackID = false;
}
// Set the property of the song bean
Statement stmt = new Statement(song, "set" + prop, new Object[] {value});
try {
stmt.execute();
} catch (Exception e) {
// Ignore that field, we do not have it in our bean
}
// If the property is the track ID, add the song to the hash
// map
if (SongBean.NAME_TRACK_ID.equals(key)) {
int trackID = Integer.valueOf((String) value);
songMap.put(trackID, song);
}
}
// Update album for last song
addOrUpdateAlbum(albumMap, song, false);
// Check the album map for inconsistencies
Iterator<AlbumBean> albums = albumMap.values().iterator();
while (albums.hasNext()) {
AlbumBean album = albums.next();
if (album.checkConsistency()) {
libraryList.add(album);
album.setHashCode();
} else {
// Add an inconsistent album only using the album title
SongBean[] songs = album.getSongs();
for (int i = 0; i < songs.length; i++) {
addOrUpdateAlbum(secondaryAlbumMap, songs[i], true);
}
}
}
// Check secondary album map for consistency
albums = secondaryAlbumMap.values().iterator();
while (albums.hasNext()) {
AlbumBean album = albums.next();
if (album.checkConsistency()) {
libraryList.add(album);
album.setHashCode();
} else {
// This album cannot be matched
// TODO: Add to warning message
}
}
setChanged();
}
return document;
} catch (IOException ioe) {
// Log an expected connect exception
throw new LibraryException(ioe);
} catch (SAXException se) {
// Catch all other exceptions
throw new LibraryException(se);
} catch (ParserConfigurationException pce) {
// Catch all other exceptions
Utils.logSevere(pce);
throw new LibraryException(pce);
} catch (XPathExpressionException xpe) {
// Catch all other exceptions
Utils.logSevere(xpe);
throw new LibraryException(xpe);
} catch (NumberFormatException nfe) {
// Catch all other exceptions
throw new LibraryException(nfe);
}
}
@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;
}
