public Task <File> Convert(string path)
{
return(Task.Run(() =>
{
var file = new File
{
Path = path,
Mime = "application/pdf"
};
using (var document = new PdfDocument(new PdfReader(path)))
{
int numOfPages = document.GetNumberOfPages();
var listener = new FilteredEventListener();
var extractionStrategy = listener
.AttachEventListener(new LocationTextExtractionStrategy());
var processor = new PdfCanvasProcessor(listener);
var content = new StringBuilder();
for (int i = 1; i <= numOfPages; i++)
{
processor.ProcessPageContent(document.GetPage(i));
content.Append(extractionStrategy.GetResultantText());
processor.Reset();
}
file.Content = content.ToString();
}
return file;
}));
}
/// <summary>
/// Parsing data from Oy axis
/// </summary>
/// <param name="page">Data of page</param>
/// <returns>data of Oy axis</returns>
internal StringBuilder ParsingOyAxis(PdfPage page)
{
// temp variable
Rectangle readBox;
TextRegionEventFilter readText;
FilteredEventListener listener;
LocationTextExtractionStrategy extractor;
PdfCanvasProcessor parser;
string[] lines;
StringBuilder result = new StringBuilder();
// area limit for read
readBox = new Rectangle(Margin.Left, Margin.Bottom + 60, 20,
page.GetPageSize().GetHeight() - Margin.Bottom - 160);
readText = new TextRegionEventFilter(readBox);
listener = new FilteredEventListener();
// create a text extraction renderer
extractor = listener
.AttachEventListener(new LocationTextExtractionStrategy(),
readText);
lock (block)
{
(parser = new PdfCanvasProcessor(listener))
.ProcessPageContent(page);
parser.Reset();
}
// read every line (row)
lines = extractor
.GetResultantText()
.Split('\n');
foreach (string line in lines)
{
if (!string.IsNullOrEmpty(line.Trim()))
{
result.AppendLine(line);
}
}
TextExtractionStrategy strategy =
listener.AttachEventListener(new TextExtractionStrategy(), readText);
lock (block)
{
(parser = new PdfCanvasProcessor(listener))
.ProcessPageContent(page);
parser.Reset();
}
PositionOyAxis = strategy.TextResult.ToArray();
return(result);
}
/// <summary>
/// Parsing columns name
/// </summary>
/// <param name="page">Data of page</param>
/// <returns>names of columns from page</returns>
internal StringBuilder ParsingColumns(PdfPage page)
{
// temp variable
Rectangle readBox;
TextRegionEventFilter readText;
FilteredEventListener listener;
LocationTextExtractionStrategy extractor;
PdfCanvasProcessor parser;
string[] lines;
StringBuilder result = new StringBuilder();
// area limit for read
readBox = new Rectangle(Margin.Left,
page.GetPageSize().GetHeight() - Margin.Top - 70,
(page.GetPageSize().GetWidth() - Margin.Right) / 4, 10);
readText = new TextRegionEventFilter(readBox);
listener = new FilteredEventListener();
// create a text extraction renderer
extractor = listener
.AttachEventListener(new LocationTextExtractionStrategy(),
readText);
lock (block)
{
(parser = new PdfCanvasProcessor(listener))
.ProcessPageContent(page);
parser.Reset();
}
// read every line (row)
lines = extractor.GetResultantText()
.Split('\n');
foreach (string line in lines)
{
result.AppendLine(line);
}
return(result);
}
