public static String Extract(String sPattern, int iOffset, String sText) {
String sResult = "";
try {
Scanner document_scanner = new Scanner(sText);
int iCountOcurr = 0;
int iFirstLine = 0;
String sLine = "";
Boolean bReading = false;
Boolean bIsEmpty = true;
while (document_scanner.hasNext()) {
sLine = document_scanner.next();
/// Pattern detected
if (sLine.indexOf(sPattern) > -1) {
iCountOcurr++;
}
/// Number of pattern has been reached
if (iCountOcurr == iOffset) {
bReading = true;
}
if (bReading && bIsEmpty) {
if (iFirstLine != 0) {
/// Stop
if (sLine.indexOf(sStop) > -1) {
bReading = false;
bIsEmpty = false;
} else {
sResult += " " + sLine;
}
} else {
sResult += " " + sLine;
}
System.out.println("sResult:" + sResult + "\n");
iFirstLine++;
}
}
document_scanner.close();
// Print number of times the search pattern was found
// System.out.println("Found Input "+ iCountOcurr + " times");
} catch (Exception e) {
sResult = "Error buscar parrafo: " + e.getMessage();
}
return sResult;
}
@POST
@Consumes(MediaType.APPLICATION_JSON)
public String GetDocumentParagraph(InputStream incomingData) {
String output = "";
StringBuilder builder = new StringBuilder();
Calendar cal = Calendar.getInstance();
SimpleDateFormat sdf = new SimpleDateFormat("HH:mm:ss.SSS");
try {
// output += "Web Service Document ..." + sdf.format(cal.getTime()) +"<br>";
/// Reeading vars from JSON
/// ----------------------------------------------------------------------------------------
BufferedReader in = new BufferedReader(new InputStreamReader(incomingData));
String line = null;
while ((line = in.readLine()) != null) {
builder.append(line);
}
cal = Calendar.getInstance();
// output += "Json stream readed: " + sdf.format(cal.getTime()) + "<br>";
/// Reeading vars from JSON
/// ----------------------------------------------------------------------------------------
JSONObject jsonObject = new JSONObject(builder.toString());
String sUrl = jsonObject.getString("url");
String sPattern = jsonObject.getString("pattern");
int iOffset = jsonObject.getInt("offset");
sUrl = sUrl.replace('^', '"');
// output += "sUrl: " + sUrl + " <br>";
// output += "sPattern: " + sPattern + " <br>";
// output += "iOffset: " + iOffset + " <br>";
output += GetDocumentParagraph(sPattern, iOffset, sUrl);
} catch (Exception e) {
cal = Calendar.getInstance();
output += "Error: " + e.toString() + sdf.format(cal.getTime()) + "<br>";
}
// return HTTP response 200 in case of success
return output;
}
public static String GetText(String sUrl) {
String sRet = "";
try {
System.out.print(" Connecting to: " + sUrl + "... \n");
InputStream inputStream = new URL(sUrl).openStream();
System.out.print(" Stream readed from: " + sUrl + "\n");
HWPFDocument docx = new HWPFDocument(inputStream);
WordExtractor we = new WordExtractor(docx);
sRet = we.getText();
we.close();
} catch (Exception e) {
sRet = "Error al leer el archivo" + e.getMessage();
}
return sRet;
}