Psst.. new poll here.
[email protected] web/email now available. Want one? Go here.
Cannot use outlook/hotmail/live here to register as they blocking our mail servers. #microsoftdeez
Obey the Epel!
Paste
Pasted as Java by kasun ( 13 years ago )
else if (userPath.equals("/topkphrases")) {
byte[] b = null;
try {
b = getBLOB("2");
} catch (Exception ex) {
Logger.getLogger(ControlerServelet.class.getName()).log(Level.SEVERE, null, ex);
}
ArrayList<String> sentenceList = new ArrayList<String>();
Line------>(ControlerServelet.java:585) sentenceList=pdfDocToSentence(b);
request.setAttribute("allphrases", sentenceList);
}
public ArrayList<String> txtDocToSentence(String paragraph) {
// This option shows loading and sentence-segment and tokenizing
// a file using DocumentPreprocessor
ArrayList<String> sentenceList = new ArrayList<String>();
Reader reader = new StringReader(paragraph);
for (List<HasWord> sentence : new DocumentPreprocessor(reader)) {
sentenceList.add(sentence.toString());
}
return sentenceList;
}
public ArrayList<String> pdfDocToSentence(byte[] buf ) throws IOException {
PDFParser parser;
String parsedText;
PDFTextStripper pdfStripper;
PDDocument pdDoc = null ;
COSDocument cosDoc = null ;
try {
parser = new PDFParser(new ByteArrayInputStream(buf));
// parser = new PDFParser(new FileInputStream(f));
} catch (Exception e) {
// System.out.println("Unable to open PDF Parser.");
return null;
}
{
try {
parser.parse();
cosDoc = parser.getDocument();
pdfStripper = new PDFTextStripper();
pdDoc = new PDDocument(cosDoc);
parsedText = pdfStripper.getText(pdDoc);
//System.out.println("An exception occured in parsing the PDF Document.");
} catch (Exception e) {
try {
if (cosDoc != null) cosDoc.close();
if (pdDoc != null) pdDoc.close();
} catch (Exception e1) {
}
return null;
}
finally{
Line-->(ControlerServelet.java:755) cosDoc.close();
pdDoc.close();
}
}
if (parsedText == null) {
//System.out.println("PDF to Text Conversion failed.");
}
return txtDocToSentence(parsedText);
}
Revise this Paste
Parent: 47395