JxpSource getSource(File f) throws IOException {
if (DEBUG) System.err.println("getSource\n\t " + f);
File temp = _findFile(f);
if (DEBUG) System.err.println("\t " + temp);
if (!temp.exists()) return handleFileNotFound(f);
// if it's a directory (and we know we can't find the index file)
// TODO : at some point, do something where we return an index for the dir?
if (temp.isDirectory()) return null;
// if we are at init time, save it as an initializaiton file
loadedFile(temp);
// Ensure that this is w/in the right tree for the context
if (_localObject != null && _localObject.isIn(temp)) return _localObject.getSource(temp);
// if not, is it core?
if (_core.isIn(temp)) return _core.getSource(temp);
throw new RuntimeException("what? can't find:" + f);
}
/**
* Returns the index.jxp for the File argument if it's an existing directory, and the index.jxp
* file exists
*
* @param f directory to check
* @return new File for index.jxp in that directory, or same file object if not
*/
File tryIndex(File f) {
if (!(f.isDirectory() && f.exists())) return f;
for (int i = 0; i < JSFileLibrary._srcExtensions.length; i++) {
File temp = new File(f, "index" + JSFileLibrary._srcExtensions[i]);
if (temp.exists()) return temp;
}
return f;
}
/**
* Process an HTML get or post.
*
* @exception ServletException From inherited class.
* @exception IOException From inherited class.
*/
public void scanOutXML(PrintWriter out, String strDirectory) throws IOException {
File dir = new File(strDirectory);
if (!dir.isDirectory()) return;
File[] rgFiles = dir.listFiles(new Filter());
out.write("<directory>");
out.write(" <name>" + strDirectory + "</name>");
for (int x = 0; x < rgFiles.length; x++) {
for (int y = x + 1; y < rgFiles.length; y++) {
if (rgFiles[x].getName().compareTo(rgFiles[y].getName()) > 0) {
File file = rgFiles[x];
rgFiles[x] = rgFiles[y];
rgFiles[y] = file;
}
}
}
for (int i = 0; i < rgFiles.length; i++) {
File file = rgFiles[i];
out.write(" <file>");
out.write(" <name>" + file.getName() + "</name>");
out.write(" <size>" + file.length() + "</size>");
out.write(" </file>");
}
out.write("</directory>");
}
/**
* Constructs a new MultipartRequest to handle the specified request, saving any uploaded files to
* the given directory, and limiting the upload size to the specified length. If the content is
* too large, an IOException is thrown. This constructor actually parses the
* <tt>multipart/form-data</tt> and throws an IOException if there's any problem reading or
* parsing the request.
*
* <p>To avoid file collisions, this constructor takes an implementation of the FileRenamePolicy
* interface to allow a pluggable rename policy.
*
* @param request the servlet request.
* @param saveDirectory the directory in which to save any uploaded files.
* @param maxPostSize the maximum size of the POST content.
* @param encoding the encoding of the response, such as ISO-8859-1
* @param policy a pluggable file rename policy
* @exception IOException if the uploaded content is larger than <tt>maxPostSize</tt> or there's a
* problem reading or parsing the request.
*/
public MultipartRequest(
HttpServletRequest request,
String saveDirectory,
int maxPostSize,
String encoding,
FileRenamePolicy policy)
throws IOException {
// Sanity check values
if (request == null) throw new IllegalArgumentException("request cannot be null");
if (saveDirectory == null) throw new IllegalArgumentException("saveDirectory cannot be null");
if (maxPostSize <= 0) {
throw new IllegalArgumentException("maxPostSize must be positive");
}
// Save the dir
File dir = new File(saveDirectory);
// Check saveDirectory is truly a directory
if (!dir.isDirectory()) throw new IllegalArgumentException("Not a directory: " + saveDirectory);
// Check saveDirectory is writable
if (!dir.canWrite()) throw new IllegalArgumentException("Not writable: " + saveDirectory);
// Parse the incoming multipart, storing files in the dir provided,
// and populate the meta objects which describe what we found
MultipartParser parser = new MultipartParser(request, maxPostSize, true, true, encoding);
// Some people like to fetch query string parameters from
// MultipartRequest, so here we make that possible. Thanks to
// Ben Johnson, [email protected], for the idea.
if (request.getQueryString() != null) {
// Let HttpUtils create a name->String[] structure
Hashtable queryParameters = HttpUtils.parseQueryString(request.getQueryString());
// For our own use, name it a name->Vector structure
Enumeration queryParameterNames = queryParameters.keys();
while (queryParameterNames.hasMoreElements()) {
Object paramName = queryParameterNames.nextElement();
String[] values = (String[]) queryParameters.get(paramName);
Vector newValues = new Vector();
for (int i = 0; i < values.length; i++) {
newValues.add(values[i]);
}
parameters.put(paramName, newValues);
}
}
Part part;
while ((part = parser.readNextPart()) != null) {
String name = part.getName();
if (name == null) {
throw new IOException("Malformed input: parameter name missing (known Opera 7 bug)");
}
if (part.isParam()) {
// It's a parameter part, add it to the vector of values
ParamPart paramPart = (ParamPart) part;
String value = paramPart.getStringValue();
Vector existingValues = (Vector) parameters.get(name);
if (existingValues == null) {
existingValues = new Vector();
parameters.put(name, existingValues);
}
existingValues.addElement(value);
} else if (part.isFile()) {
// It's a file part
FilePart filePart = (FilePart) part;
String fileName = filePart.getFileName();
if (fileName != null) {
filePart.setRenamePolicy(policy); // null policy is OK
// The part actually contained a file
filePart.writeTo(dir);
files.put(
name,
new UploadedFile(
dir.toString(), filePart.getFileName(), fileName, filePart.getContentType()));
} else {
// The field did not contain a file
files.put(name, new UploadedFile(null, null, null, null));
}
}
}
}
public void init(ServletConfig config) throws ServletException {
super.init(config);
context = config.getServletContext();
TextProcessor tp = new CaseFolder();
try {
wikipedia =
new Wikipedia(
context.getInitParameter("mysql_server"),
context.getInitParameter("mysql_database"),
context.getInitParameter("mysql_user"),
context.getInitParameter("mysql_password"));
} catch (Exception e) {
throw new ServletException("Could not connect to wikipedia database.");
}
// Escaper escaper = new Escaper() ;
definer = new Definer(this);
comparer = new Comparer(this);
searcher = new Searcher(this);
try {
wikifier = new Wikifier(this, tp);
} catch (Exception e) {
System.err.println("Could not initialize wikifier");
}
try {
File dataDirectory = new File(context.getInitParameter("data_directory"));
if (!dataDirectory.exists() || !dataDirectory.isDirectory()) {
throw new Exception();
}
cachingThread = new CacherThread(dataDirectory, tp);
cachingThread.start();
} catch (Exception e) {
throw new ServletException("Could not locate wikipedia data directory.");
}
try {
TransformerFactory tf = TransformerFactory.newInstance();
transformersByName = new HashMap<String, Transformer>();
transformersByName.put(
"help", buildTransformer("help", new File("/research/wikipediaminer/web/xsl"), tf));
transformersByName.put(
"loading", buildTransformer("loading", new File("/research/wikipediaminer/web/xsl"), tf));
transformersByName.put(
"search", buildTransformer("search", new File("/research/wikipediaminer/web/xsl"), tf));
transformersByName.put(
"compare", buildTransformer("compare", new File("/research/wikipediaminer/web/xsl"), tf));
transformersByName.put(
"wikify", buildTransformer("wikify", new File("/research/wikipediaminer/web/xsl"), tf));
Transformer serializer = TransformerFactory.newInstance().newTransformer();
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "xml");
serializer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
transformersByName.put("serializer", serializer);
} catch (Exception e) {
throw new ServletException("Could not load xslt library.");
}
}
/**
* Convenience routine used by handleRequestForContentFile() and handleRequestForRootFile().
*
* @param pathPrefix
* @param path
* @param servlet
* @param req request
* @param res response
* @throws IOException on IO error
*/
private static void handleRequestForContentOrRootFile(
String pathPrefix,
String path,
HttpServlet servlet,
HttpServletRequest req,
HttpServletResponse res)
throws IOException {
if (!pathPrefix.equals("/content/") && !pathPrefix.equals("/root/")) {
log.error(
"handleRequestForContentFile(): The path prefix <"
+ pathPrefix
+ "> must be \"/content/\" or \"/root/\".");
throw new IllegalArgumentException("Path prefix must be \"/content/\" or \"/root/\".");
}
if (!path.startsWith(pathPrefix)) {
log.error(
"handleRequestForContentFile(): path <"
+ path
+ "> must start with \""
+ pathPrefix
+ "\".");
throw new IllegalArgumentException("Path must start with \"" + pathPrefix + "\".");
}
// Don't allow ".." directories in path.
if (path.indexOf("/../") != -1
|| path.equals("..")
|| path.startsWith("../")
|| path.endsWith("/..")) {
res.sendError(HttpServletResponse.SC_FORBIDDEN, "Path cannot contain \"..\" directory.");
log.info(UsageLog.closingMessageForRequestContext(HttpServletResponse.SC_FORBIDDEN, -1));
return;
}
// Find the requested file.
File file =
new File(
ServletUtil.formFilename(getContentPath(), path.substring(pathPrefix.length() - 1)));
if (file.exists()) {
// Do not allow request for a directory.
if (file.isDirectory()) {
if (!path.endsWith("/")) {
String redirectPath = req.getRequestURL().append("/").toString();
ServletUtil.sendPermanentRedirect(redirectPath, req, res);
return;
}
int i = HtmlWriter.getInstance().writeDirectory(res, file, path);
int status = i == 0 ? HttpServletResponse.SC_NOT_FOUND : HttpServletResponse.SC_OK;
log.info(UsageLog.closingMessageForRequestContext(status, i));
return;
}
// Return the requested file.
ServletUtil.returnFile(servlet, req, res, file, null);
} else {
// Requested file not found.
log.info(UsageLog.closingMessageForRequestContext(HttpServletResponse.SC_NOT_FOUND, -1));
res.sendError(HttpServletResponse.SC_NOT_FOUND); // 404
}
}
/**
* Handle a request for a raw/static file (i.e., not a catalog or dataset request).
*
* <p>Look in the content (user) directory then the root (distribution) directory for a file that
* matches the given path and, if found, return it as the content of the HttpServletResponse. If
* the file is forbidden (i.e., the path contains a "..", "WEB-INF", or "META-INF" directory),
* send a HttpServletResponse.SC_FORBIDDEN response. If no file matches the request (including an
* "index.html" file if the path ends in "/"), send an HttpServletResponse.SC_NOT_FOUND..
*
* <p>
*
* <ol>
* <li>Make sure the path does not contain ".." directories.
* <li>Make sure the path does not contain "WEB-INF" or "META-INF".
* <li>Check for requested file in the content directory (if the path is a directory, make sure
* the path ends with "/" and check for an "index.html" file).
* <li>Check for requested file in the root directory (if the path is a directory, make sure the
* path ends with "/" and check for an "index.html" file). </ol
*
* @param path the requested path
* @param servlet the servlet handling the request
* @param req the HttpServletRequest
* @param res the HttpServletResponse
* @throws IOException if can't complete request due to IO problems.
*/
public static void handleRequestForRawFile(
String path, HttpServlet servlet, HttpServletRequest req, HttpServletResponse res)
throws IOException {
// Don't allow ".." directories in path.
if (path.indexOf("/../") != -1
|| path.equals("..")
|| path.startsWith("../")
|| path.endsWith("/..")) {
res.sendError(HttpServletResponse.SC_FORBIDDEN, "Path cannot contain \"..\" directory.");
log.info(UsageLog.closingMessageForRequestContext(HttpServletResponse.SC_FORBIDDEN, -1));
return;
}
// Don't allow access to WEB-INF or META-INF directories.
String upper = path.toUpperCase();
if (upper.indexOf("WEB-INF") != -1 || upper.indexOf("META-INF") != -1) {
res.sendError(
HttpServletResponse.SC_FORBIDDEN, "Path cannot contain \"WEB-INF\" or \"META-INF\".");
log.info(UsageLog.closingMessageForRequestContext(HttpServletResponse.SC_FORBIDDEN, -1));
return;
}
// Find a regular file
File regFile = null;
// Look in content directory for regular file.
File cFile = new File(ServletUtil.formFilename(getContentPath(), path));
if (cFile.exists()) {
if (cFile.isDirectory()) {
if (!path.endsWith("/")) {
String newPath = req.getRequestURL().append("/").toString();
ServletUtil.sendPermanentRedirect(newPath, req, res);
}
// If request path is a directory, check for index.html file.
cFile = new File(cFile, "index.html");
if (cFile.exists() && !cFile.isDirectory()) regFile = cFile;
}
// If not a directory, use this file.
else regFile = cFile;
}
if (regFile == null) {
// Look in root directory.
File rFile = new File(ServletUtil.formFilename(getRootPath(), path));
if (rFile.exists()) {
if (rFile.isDirectory()) {
if (!path.endsWith("/")) {
String newPath = req.getRequestURL().append("/").toString();
ServletUtil.sendPermanentRedirect(newPath, req, res);
}
rFile = new File(rFile, "index.html");
if (rFile.exists() && !rFile.isDirectory()) regFile = rFile;
} else regFile = rFile;
}
}
if (regFile == null) {
res.sendError(HttpServletResponse.SC_NOT_FOUND); // 404
log.info(UsageLog.closingMessageForRequestContext(HttpServletResponse.SC_NOT_FOUND, -1));
return;
}
ServletUtil.returnFile(servlet, req, res, regFile, null);
}
/**
* Process an HTML get or post.
*
* @exception ServletException From inherited class.
* @exception IOException From inherited class.
*/
public void scanOutXML(
PrintWriter out,
String strDirectory,
String strFilename,
String[] strPlus,
String[] strMinus,
boolean bExcludeParams,
boolean bAnalyzeParams)
throws IOException {
File dir = new File(strDirectory + '/' + strFilename);
if (dir.isDirectory()) return;
try {
FileReader is = new FileReader(strDirectory + '/' + strFilename);
BufferedReader r = new BufferedReader(is);
String string = null;
Hashtable ht = new Hashtable();
Set setstrExtensions = new HashSet();
int iCount = 0;
int iBytes = 0;
while ((string = r.readLine()) != null) {
StringTokenizer st = new StringTokenizer(string, " \"", false);
Data data = new Data();
int iTokenCount = 0;
while (st.hasMoreTokens()) {
iTokenCount++;
string = st.nextToken();
if (iTokenCount == IP) data.m_IP = string;
if (iTokenCount == URL) {
if (bExcludeParams)
if (string.indexOf('?') != -1) string = string.substring(0, string.indexOf('?'));
if (bAnalyzeParams)
if (string.indexOf('?') != -1) string = string.substring(string.indexOf('?') + 1);
data.m_URL = string;
}
if (iTokenCount == PROTOCOL)
if (!string.startsWith("HTTP")) {
data.m_URL += " " + string;
iTokenCount--;
}
if (iTokenCount == BYTES) data.m_iBytes = Integer.parseInt(string);
}
if (!this.filterURL(data.m_URL, strPlus, strMinus, setstrExtensions)) continue;
iCount++;
iBytes += data.m_iBytes;
if (ht.get(data.m_URL) == null) ht.put(data.m_URL, data);
else {
int iThisBytes = data.m_iBytes;
data = (Data) ht.get(data.m_URL);
data.m_iCount++;
data.m_iBytes += iThisBytes;
}
}
Comparator comparator = new Test();
TreeMap tm = new TreeMap(comparator);
Iterator iterator = ht.values().iterator();
while (iterator.hasNext()) {
Data data = (Data) iterator.next();
tm.put(new Integer(data.m_iCount), data);
}
out.println("<file>");
this.printXML(out, "directory", strDirectory);
this.printXML(out, "name", strFilename);
iterator = tm.values().iterator();
while (iterator.hasNext()) {
out.println("<data>");
Data data = (Data) iterator.next();
this.printXML(out, "url", data.m_URL);
this.printXML(out, "count", Integer.toString(data.m_iCount));
out.println("</data>");
}
this.printXML(out, "hits", Integer.toString(iCount));
this.printXML(out, "bytes", Integer.toString(iBytes));
this.printXML(out, "unique", Integer.toString(tm.size()));
iterator = setstrExtensions.iterator();
out.println("<extensions>");
while (iterator.hasNext()) {
this.printXML(out, "extension", (String) iterator.next());
}
out.println("</extensions>");
out.println("</file>");
} catch (FileNotFoundException ex) {
ex.printStackTrace();
} catch (IOException ex) {
ex.printStackTrace();
}
}
