/** Generate the concordance for the given file. */
private void execute() {
TET tet = null;
int pageno = 0;
try {
tet = new TET();
tet.set_option(GLOBAL_OPTLIST);
final int doc = tet.open_document(filename, DOC_OPTLIST);
if (doc == -1) {
System.err.println(
"Error " + tet.get_errnum() + " in " + tet.get_apiname() + "(): " + tet.get_errmsg());
} else {
/*
* Loop over pages in the document
*/
final int n_pages = (int) tet.pcos_get_number(doc, "length:pages");
for (pageno = 1; pageno <= n_pages; ++pageno) {
process_page(tet, doc, pageno);
}
print_concordance(tet, doc);
tet.close_document(doc);
}
} catch (TETException e) {
if (pageno == 0) {
System.err.println(
"Error " + e.get_errnum() + " in " + e.get_apiname() + "(): " + e.get_errmsg() + "\n");
} else {
System.err.println(
"Error "
+ e.get_errnum()
+ " in "
+ e.get_apiname()
+ "() on page "
+ pageno
+ ": "
+ e.get_errmsg()
+ "\n");
}
System.exit(1);
} finally {
tet.delete();
}
}
/** @see HttpServlet#doGet(HttpServletRequest request, HttpServletResponse response) */
protected void doGet(HttpServletRequest request, HttpServletResponse response)
throws ServletException, IOException {
response.setContentType("text/html; charset=UTF-8");
PrintWriter writer = response.getWriter();
writer.println("<html>");
writer.println("<head>");
writer.println("<title>TET J2EE TETML Servlet Example<title>");
writer.println("</head>");
writer.println("<body>");
writer.println("<pre>");
/*
* For JRE 1.4 the property must be set what XML parser to use, later
* JREs seem to have a default set internally. It seems to be the case
* that in 1.4 org.apache.crimson.parser.XMLReaderImpl is always
* available.
*/
String jre_version = System.getProperty("java.version");
if (jre_version.startsWith("1.4")) {
System.setProperty("org.xml.sax.driver", "org.apache.crimson.parser.XMLReaderImpl");
}
TET tet = null;
try {
tet = new TET();
/* This is where input files live. Adjust as necessary. */
ServletContext context = getServletContext();
final String datapath = context.getRealPath("/WEB-INF/data");
final String cmappath = context.getRealPath("/WEB-INF/resource/cmap");
/** Global option list */
final String globaloptlist = "searchpath={{" + datapath + "} {" + cmappath + "}}";
tet.set_option(globaloptlist);
final String tetmlname = infile + ".tetml";
final String docoptlist =
(inmemory ? "tetml={}" : "tetml={filename={" + tetmlname + "}}") + " " + basedocoptlist;
if (inmemory) {
writer.println("Processing TETML output for document \"" + infile + "\" in memory...");
} else {
writer.println(
"Extracting TETML for document \"" + infile + "\" to file \"" + tetmlname + "\"...");
}
final int doc = tet.open_document(infile, docoptlist);
if (doc == -1) {
writer.println(
"Error " + tet.get_errnum() + " in " + tet.get_apiname() + "(): " + tet.get_errmsg());
tet.delete();
return;
}
final int n_pages = (int) tet.pcos_get_number(doc, "length:pages");
/*
* Loop over pages in the document;
*/
for (int pageno = 0; pageno <= n_pages; ++pageno) {
tet.process_page(doc, pageno, pageoptlist);
}
/*
* This could be combined with the last page-related call.
*/
tet.process_page(doc, 0, "tetml={trailer}");
if (inmemory) {
/*
* Get the XML document as a byte array.
*/
final byte[] tetml = tet.get_xml_data(doc, "");
if (tetml == null) {
writer.println("tetml: couldn't retrieve XML data");
return;
}
/*
* Process the in-memory XML document to print out some
* information that is extracted with the sax_handler class.
*/
XMLReader reader = XMLReaderFactory.createXMLReader();
reader.setContentHandler(new sax_handler(writer));
reader.parse(new InputSource(new ByteArrayInputStream(tetml)));
writer.println("Found " + word_count + " words in document");
}
tet.close_document(doc);
} catch (TETException e) {
writer.println(
"Error " + e.get_errnum() + " in " + e.get_apiname() + "(): " + e.get_errmsg());
} catch (Exception e) {
e.printStackTrace(writer);
} finally {
writer.println("</pre>");
writer.println("</body>");
writer.println("</html>");
writer.close();
if (tet != null) {
tet.delete();
}
}
}
/**
* Process a single page of text.
*
* @param tet TET object
* @param doc TET document handle
* @param pageno Page to process
* @throws TETException An error occurred in the TET API
*/
private void process_page(TET tet, final int doc, int pageno) throws TETException {
final int page = tet.open_page(doc, pageno, PAGE_OPTLIST);
if (page == -1) {
System.err.println(
"Error " + tet.get_errnum() + " in " + tet.get_apiname() + "(): " + tet.get_errmsg());
} else {
/*
* Fetch the text word-wise.
*/
for (String text = tet.get_text(page); text != null; text = tet.get_text(page)) {
/*
* Only include words that start with a letter.
*/
if (Character.isLetter(text.charAt(0))) {
if (LOWERCASE_WORDS) {
text = text.toLowerCase();
}
Integer value = (Integer) wordCounters.get(text);
if (value != null) {
// Increment counter
value = new Integer(value.intValue() + 1);
} else {
// Initialize with first counted word
value = new Integer(1);
}
wordCounters.put(text, value);
}
}
if (tet.get_errnum() != 0) {
System.err.println(
"Error " + tet.get_errnum() + " in " + tet.get_apiname() + "(): " + tet.get_errmsg());
}
tet.close_page(page);
}
}
