public bool PdfContains(string text)
{
var buf = new StringBuilder();
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
var streamBytes = pdfReader.GetPageContent(1);
var tokenizer = new PrTokeniser(new RandomAccessFileOrArray(streamBytes));
var stringsList = new List <string>();
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
stringsList.Add(tokenizer.StringValue);
_output.WriteLine(stringsList.Last());
var currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.UTF8, Encoding.UTF8, Encoding.UTF8.GetBytes(tokenizer.StringValue)));
_output.WriteLine(currentText);
}
}
tokenizer.Close();
}
pdfReader.Close();
//if (stringsList.Contains(text))
// eturn true;
return(false);
}
public IActionResult PostearDoc(IFormFile file)
{
string texto;
if (file.ContentType == "application/pdf")
{
using (MemoryStream ms = new MemoryStream())
{
file.CopyTo(ms);
byte[] que = ms.ToArray();
PdfReader pdfReader = new PdfReader(que);
byte[] contenidoPageUno = pdfReader.GetPageContent(1);
PrTokeniser tokenizer = new PrTokeniser(new RandomAccessFileOrArray(contenidoPageUno));
List <string> strList = new List <string>();
texto = String.Empty;
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
strList.Add(tokenizer.StringValue);
texto = texto + tokenizer.StringValue;
}
}
pdfReader.Close();
}
}
else
{
XWPFDocument doc = new XWPFDocument(file.OpenReadStream());
XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
texto = extractor.Text;
}
return(Json(new { texto }));
}
public void Verify_Issue42_CanBe_Processed()
{
var inPdfFile = TestUtils.GetPdfsPath("issue42.pdf");
var reader = new PdfReader(inPdfFile);
var content = reader.GetPageContent(1);
var tokenizer = new PrTokeniser(new RandomAccessFileOrArray(content));
var stringsList = new List <string>();
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
stringsList.Add(tokenizer.StringValue);
}
}
reader.Close();
Assert.IsTrue(stringsList.Contains("demonstration"));
}
public void Test_Extract_Text()
{
var pdfFile = createSamplePdfFile();
var reader = new PdfReader(pdfFile);
var streamBytes = reader.GetPageContent(1);
var tokenizer = new PrTokeniser(new RandomAccessFileOrArray(streamBytes));
var stringsList = new List <string>();
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
stringsList.Add(tokenizer.StringValue);
}
}
reader.Close();
Assert.IsTrue(stringsList.Contains("Hello DNT!"));
}
public static string Extract(string path)
{
var reader = new PdfReader(path);
var sb = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
var streamBytes = reader.GetPageContent(i);
var tokenizer = new PrTokeniser(new RandomAccessFileOrArray(streamBytes));
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
var currentText = tokenizer.StringValue;
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
sb.Append(tokenizer.StringValue + " ");
}
}
}
return(sb.ToString());
}
private void ExtractData()
{
var state = State.Stop;
var reader = new PdfReader(_pdfReceipt.OpenReadStream());
var streamBytes = reader.GetPageContent(1);
var tokenizer = new PrTokeniser(new RandomAccessFileOrArray(streamBytes));
int num = 1;
var pdfReceiptItem = new PdfReceiptItemDto();
bool isFirstWordTaken = false;
while (tokenizer.NextToken())
{
if (tokenizer.TokenType == PrTokeniser.TK_STRING)
{
var currentText = tokenizer.StringValue;
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default,
Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
Console.WriteLine(currentText);
//GetLocation
if (!isFirstWordTaken && !string.IsNullOrWhiteSpace(currentText))
{
_location = currentText;
isFirstWordTaken = true;
}
//GetDate
if (currentText.Contains("Dato:"))
{
var formatted = GetFormattedDateString(currentText.Remove(0, 6));
_date = DateTime.Parse(formatted);
}
//GetReceiptItem
if (state == State.Start)
{
//navn 1 -> antal 2 -> pris 3 -> reset
switch (num)
{
case 1:
//name
pdfReceiptItem.Name = currentText;
if (currentText == "Rabat")
{
pdfReceiptItem.IsDiscount = true;
}
num++;
break;
case 2:
//antal
var countParsed = double.TryParse(currentText, out double count);
if (countParsed)
{
pdfReceiptItem.Count = (int)count;
num++;
}
break;
case 3:
var priceParsed = double.TryParse(currentText, out double price);
if (priceParsed)
{
pdfReceiptItem.Price = price;
_pdfReceiptItems.Add(pdfReceiptItem);
pdfReceiptItem = new PdfReceiptItemDto();
}
num = 1;
break;
}
}
//setState
if (currentText == "Pris")
{
state = State.Start;
}
//end
else if (currentText == "I alt inkl. moms")
{
break;
}
}
}
}
/// <summary>
/// Uses <see cref="iTextSharp"/> library to extract plaintext
/// from pdf file.
/// </summary>
/// <param name="pathToPdf">Path to PDF file</param>
/// <returns>Plaintext string</returns>
public static string GetPlainText(string pathToPdf)
{
var pdf = new PdfReader(pathToPdf);
//string builder for output
var sb = new StringBuilder();
//go page-by-page
for (var i = 1; i < pdf.NumberOfPages; i++)
{
var streamBytes = pdf.GetPageContent(i);
var tokeniser = new PrTokeniser(new RandomAccessFileOrArray(streamBytes));
while (tokeniser.NextToken())
{
switch (tokeniser.TokenType)
{
//string tokens seem to encompass everything we're interested in
case PrTokeniser.TK_STRING:
sb.Append(tokeniser.StringValue);
break;
//todo:find consistent way of parsing newlines
//newline tokens. Seem to be inconsistent, hacky to
//add new cases as seen but works for now.
case PrTokeniser.TK_NUMBER:
if (tokeniser.StringValue.Equals("-1.159"))
{
sb.Append(Environment.NewLine);
}
break;
case PrTokeniser.TK_OTHER:
if (tokeniser.StringValue.Equals("BDC"))
{
sb.Append(Environment.NewLine);
}
break;
// // these are apparently the newline tokens. Results in LOTS of newlines which breaks parsing
// switch (tokeniser.StringValue)
// {
// // case "ET":
// case "TD":
// case "Td":
// //case "Tm":
// //case "T*":
// //sb.Append(Environment.NewLine);
// sb.Append($"[{tokeniser.StringValue}]");
// break;
// default:
// break;
// }
// break;
// ReSharper disable once RedundantEmptySwitchSection - keep for debugging
default:
//if (Debugger.IsAttached) { sb.Append($"[{tokeniser.TokenType}-{tokeniser.StringValue}]"); }
break;
}
}
// add newline between pages
sb.AppendLine();
//ignore latter sections
if (sb.ToString().Contains("ANNEX II"))
{
break;
}
}
//close reader
pdf.Close();
return(sb.ToString());
}
