public ArrayList<String> parseXML() throws Exception {
ArrayList<String> ret = new ArrayList<String>();
handshake();
URL url =
new URL(
"http://mangaonweb.com/page.do?cdn="
+ cdn
+ "&cpn=book.xml&crcod="
+ crcod
+ "&rid="
+ (int) (Math.random() * 10000));
String page = DownloaderUtils.getPage(url.toString(), "UTF-8", cookies);
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
InputSource is = new InputSource(new StringReader(page));
Document d = builder.parse(is);
Element doc = d.getDocumentElement();
NodeList pages = doc.getElementsByTagName("page");
total = pages.getLength();
for (int i = 0; i < pages.getLength(); i++) {
Element e = (Element) pages.item(i);
ret.add(e.getAttribute("path"));
}
return (ret);
}
private void guardaRes(String resu, CliGol cliGol)
throws ParserConfigurationException, SAXException, IOException {
String[] nodos = {"NoHit", "Hit", "Buro"};
DocumentBuilder db = DocumentBuilderFactory.newInstance().newDocumentBuilder();
InputSource is = new InputSource(new StringReader(resu));
Document xml = db.parse(is);
Element raiz = xml.getDocumentElement();
String nombre = obtenerNombre(raiz);
for (String s : nodos) {
Node nodo =
raiz.getElementsByTagName(s) == null ? null : raiz.getElementsByTagName(s).item(0);
if (nodo != null) {
String informacion = sustraerInformacionNodo(cliGol, nodo);
guardarEnListas(nodo.getNodeName(), nombre + "," + informacion);
}
}
}
/**
* Create from factory a DocumentBuilder and let it create a org.w3c.dom.Document. This method
* takes InputSource. After successful finish the document tree is returned.
*
* @param input a parser input (for URL users use: <code>new InputSource(url.toExternalForm())
* </code>
* @param validate if true validating parser is used
* @param namespaceAware if true DOM is created by namespace aware parser
* @param errorHandler a error handler to notify about exception or <code>null</code>
* @param entityResolver SAX entity resolver or <code>null</code>; see class Javadoc for hints
* @throws IOException if an I/O problem during parsing occurs
* @throws SAXException is thrown if a parser error occurs
* @throws FactoryConfigurationError Application developers should never need to directly catch
* errors of this type.
* @return document representing given input, or null if a parsing error occurs
*/
public static Document parse(
InputSource input,
boolean validate,
boolean namespaceAware,
ErrorHandler errorHandler,
EntityResolver entityResolver)
throws IOException, SAXException {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setValidating(validate);
factory.setNamespaceAware(namespaceAware);
DocumentBuilder builder = null;
try {
builder = factory.newDocumentBuilder();
} catch (ParserConfigurationException ex) {
throw new SAXException(
"Cannot create parser satisfying configuration parameters", ex); // NOI18N
}
if (errorHandler != null) {
builder.setErrorHandler(errorHandler);
}
if (entityResolver != null) {
builder.setEntityResolver(entityResolver);
}
return builder.parse(input);
}
/**
* Creates an AppConfig using class <code>pAppClass</code> to search for the config file resource.
* That class must have a resource file <code>AppConfig.xml</code>.
*/
private AppConfig(InputSource pInputSource) throws InvalidInputException, DataNotFoundException {
try {
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document document = builder.parse(pInputSource);
mConfigFileDocument = document;
} catch (Exception e) {
e.printStackTrace(System.err);
throw new InvalidInputException("unable to load XML configuration file", e);
}
}
/**
* Advanced users only; use loadXML() in PApplet.
*
* <p>Added extra code to handle \u2028 (Unicode NLF), which is sometimes inserted by web browsers
* (Safari?) and not distinguishable from a "real" LF (or CRLF) in some text editors (i.e.
* TextEdit on OS X). Only doing this for XML (and not all Reader objects) because LFs are
* essential. https://github.com/processing/processing/issues/2100
*
* @nowebref
*/
public XML(final Reader reader, String options)
throws IOException, ParserConfigurationException, SAXException {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
// Prevent 503 errors from www.w3.org
try {
factory.setAttribute("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
} catch (IllegalArgumentException e) {
// ignore this; Android doesn't like it
}
// without a validating DTD, this doesn't do anything since it doesn't know what is ignorable
// factory.setIgnoringElementContentWhitespace(true);
factory.setExpandEntityReferences(false);
// factory.setExpandEntityReferences(true);
// factory.setCoalescing(true);
// builderFactory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
DocumentBuilder builder = factory.newDocumentBuilder();
// builder.setEntityResolver()
// SAXParserFactory spf = SAXParserFactory.newInstance();
// spf.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true);
// SAXParser p = spf.newSAXParser();
// builder = DocumentBuilderFactory.newDocumentBuilder();
// builder = new SAXBuilder();
// builder.setValidation(validating);
Document document =
builder.parse(
new InputSource(
new Reader() {
@Override
public int read(char[] cbuf, int off, int len) throws IOException {
int count = reader.read(cbuf, off, len);
for (int i = 0; i < count; i++) {
if (cbuf[off + i] == '\u2028') {
cbuf[off + i] = '\n';
}
}
return count;
}
@Override
public void close() throws IOException {
reader.close();
}
}));
node = document.getDocumentElement();
}
public void load(InputStream is) throws IOException, ParserConfigurationException, SAXException {
doc = db.parse(is);
docElt = doc.getDocumentElement();
if (docElt.getTagName().equals(docElementName)) {
NodeList nl = docElt.getElementsByTagName(trackElementName);
for (int i = 0; i < nl.getLength(); i++) {
Element elt = (Element) nl.item(i);
Track track = new Track(elt);
tracks.add(track);
hash.put(track.getKey(), track);
}
}
}
public static void main(String args[]) {
try {
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setNamespaceAware(true);
factory.setValidating(true);
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(args[0]);
} catch (SAXException e) {
// e.printStackTrace();
System.out.println(e.getMessage());
} catch (Exception e) {
// e.printStackTrace();
}
}
static {
try {
URL url = SpellCheckActivator.bundleContext.getBundle().getResource(RESOURCE_LOC);
InputStream stream = url.openStream();
if (stream == null) throw new IOException();
// strict parsing options
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
factory.setValidating(false);
factory.setIgnoringComments(true);
factory.setIgnoringElementContentWhitespace(true);
// parses configuration xml
/*-
* Warning: Felix is unable to import the com.sun.rowset.internal
* package, meaning this can't use the XmlErrorHandler. This causes
* a warning and a default handler to be attached. Otherwise this
* should have: builder.setErrorHandler(new XmlErrorHandler());
*/
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(stream);
// iterates over nodes, parsing contents
Node root = doc.getChildNodes().item(1);
NodeList categories = root.getChildNodes();
for (int i = 0; i < categories.getLength(); ++i) {
Node node = categories.item(i);
if (node.getNodeName().equals(NODE_DEFAULTS)) {
parseDefaults(node.getChildNodes());
} else if (node.getNodeName().equals(NODE_LOCALES)) {
parseLocales(node.getChildNodes());
} else {
logger.warn("Unrecognized category: " + node.getNodeName());
}
}
} catch (IOException exc) {
logger.error("Unable to load spell checker parameters", exc);
} catch (SAXException exc) {
logger.error("Unable to parse spell checker parameters", exc);
} catch (ParserConfigurationException exc) {
logger.error("Unable to parse spell checker parameters", exc);
}
}
/**
* Unlike the loadXML() method in PApplet, this version works with files that are not in UTF-8
* format.
*
* @nowebref
*/
public XML(InputStream input, String options)
throws IOException, ParserConfigurationException, SAXException {
// this(PApplet.createReader(input), options); // won't handle non-UTF8
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
try {
// Prevent 503 errors from www.w3.org
factory.setAttribute("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
} catch (IllegalArgumentException e) {
// ignore this; Android doesn't like it
}
factory.setExpandEntityReferences(false);
DocumentBuilder builder = factory.newDocumentBuilder();
Document document = builder.parse(new InputSource(input));
node = document.getDocumentElement();
}
/**
* Method that reads a XML-file, and returns a Model that contains the information
*
* @param file
* @return
* @return
*/
public static Model readXML(String file) {
// initialize table to be filled with content of XML file
Model t = new Model();
try {
// Create file to be parsed by document parser
File xmlfile = new File(file);
// create parser
DocumentBuilder parser = DocumentBuilderFactory.newInstance().newDocumentBuilder();
// parse the file
Document parsedfile = parser.parse(xmlfile);
// normalize the parsed file (make it more user-friendly)
parsedfile.getDocumentElement().normalize();
NodeList cells = parsedfile.getElementsByTagName("CELL");
for (int i = 0; i < cells.getLength(); i++) {
// Get cell at list index i
Node currentcell = cells.item(i);
// read the elements "location" attributes row/column
if (Node.ELEMENT_NODE == currentcell.getNodeType()) {
Element cellinfo = (Element) currentcell;
// get the row number from node attribute
int row = Integer.parseInt(cellinfo.getAttribute("row")) - 1;
// get the column number from the node attribute
int col = Integer.parseInt(cellinfo.getAttribute("column")) - 1;
// get content from node
String content = cellinfo.getTextContent();
if (content != null) {
content = content.replace("\n", "");
}
// Make the content an Integer (if it is a number), easier
// for
// using it later on
// put content in table, with row/column inserted as x/y
t.setContent(row, col, (String) content);
}
}
} catch (ParserConfigurationException e) {
System.out.println("Fileparser could not be made");
} catch (IOException f) {
System.out.println("File could not be parsed, did you enter the correct file name?");
} catch (SAXException g) {
System.out.println("Something went wrong in parsing the file");
}
return t;
}
/**
* Reads an XML document from an input source and copies its values into the specified object
*
* @param ob The object to receive the values
* @param source The location of the XML document
* @throws IOException If there is an error reading the document
*/
public void readObject(Object ob, InputSource source) throws IOException {
try {
// Create a document builder to read the document
DocumentBuilder builder = factory.newDocumentBuilder();
// Read the document
Document doc = builder.parse(source);
// Get the root element
Element element = doc.getDocumentElement();
// Copy the root element into the bean
readObject(ob, element);
} catch (SAXException exc) {
throw new IOException("Error parsing XML document: " + exc.toString());
} catch (ParserConfigurationException exc) {
throw new IOException("Error parsing XML document: " + exc.toString());
}
}
private Document GetXMLDocument(String url) {
try {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
DocumentBuilder db = dbf.newDocumentBuilder();
InputStream input = HTMLTools.inputStream_GET(url, 5000);
InputStreamReader reader = new InputStreamReader(input, ENCODING_UTF8);
InputSource inSrc = new InputSource(reader);
inSrc.setEncoding(ENCODING_UTF8);
return db.parse(inSrc);
} catch (ParserConfigurationException pce) {
Print.logError("Parse error: " + pce);
return null;
} catch (SAXException se) {
Print.logError("Parse error: " + se);
return null;
} catch (IOException ioe) {
Print.logError("IO error: " + ioe);
return null;
}
}
public static MiningResult importFile(InputStream input) throws IOException {
try {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
Document doc;
// NodeList netNodes;
dbf.setValidating(false);
dbf.setIgnoringComments(true);
dbf.setIgnoringElementContentWhitespace(true);
// dbf.setExpandEntityReferences(false);
// dbf.setNamespaceAware(false);
DocumentBuilder db = dbf.newDocumentBuilder();
db.setEntityResolver(
new EntityResolver() {
public InputSource resolveEntity(String publicId, String systemId) {
if (systemId.indexOf("ARIS-Export") != -1) {
return new InputSource("file:" + About.EXTLIBLOCATION() + "ARIS-Export101.dtd");
} else {
return null;
}
}
});
InputSource inpStream = new InputSource(input);
inpStream.setSystemId("file:" + System.getProperty("user.dir", ""));
doc = db.parse(inpStream);
// check if root element is a aml tag
Message.add("parsing done" + doc, Message.DEBUG);
if (!(doc.getDocumentElement().getNodeName().equals("AML"))) {
Message.add("aml tag not found", Message.ERROR);
throw new Exception("aml tag not found");
} else {
Message.add("aml root element found");
}
EPCResult result = new EPCResult(null, (EPC) null);
HashMap ObjDef_LinkId = new HashMap();
HashMap modelid_net = new HashMap();
HashMap ObjDef_Name = new HashMap();
HashMap function_LinkId = new HashMap();
HashMap ModelId_ModelType = new HashMap();
traverseAMLforObjectNames(
ObjDef_Name, doc.getDocumentElement(), ObjDef_LinkId, ModelId_ModelType);
Iterator findLinkToEpc = ObjDef_LinkId.keySet().iterator();
while (findLinkToEpc.hasNext()) {
String currentObjDef = (String) findLinkToEpc.next();
String Links = (String) ObjDef_LinkId.get(currentObjDef);
StringTokenizer linkSet = new StringTokenizer(Links);
String realEpcLink = "";
while (linkSet.hasMoreTokens()) {
String currentLink = linkSet.nextToken();
if (ModelId_ModelType.get(currentLink).equals("MT_EEPC")) {
realEpcLink = currentLink;
break;
}
}
if (realEpcLink.equals(" ")) {
ObjDef_LinkId.remove(currentObjDef);
} else {
ObjDef_LinkId.put(currentObjDef, realEpcLink);
}
}
result =
traverseAML(
result,
doc.getDocumentElement(),
null,
ObjDef_Name,
ObjDef_LinkId,
modelid_net,
function_LinkId);
Iterator hierarchicalFunctions = function_LinkId.keySet().iterator();
while (hierarchicalFunctions.hasNext()) {
EPCSubstFunction f = (EPCSubstFunction) hierarchicalFunctions.next();
f.setSubstitutedEPC((EPC) modelid_net.get(function_LinkId.get(f)));
// Message.add(f.getSubstitutedEPC().getName());
}
return result;
} catch (Throwable x) {
Message.add(x.toString());
throw new IOException(x.getMessage());
}
}
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);
}
}