Getting an IncorrectFontUsageException (Document error: TJ operator without preceding Tf - no font set for the text segment) thrown when using page.Accept(TextAbsorber).
To reproduce, run the following code on the attached anthropic.pdf.zip (5.6 MB)
:
protected List<IText> GetTexts(Document pdfDocument, CancellationToken cancellationToken)
{
List<IText> list = new List<IText>();
int num = 1;
foreach (Page page in pdfDocument.Pages)
{
cancellationToken.ThrowIfCancellationRequested();
TextAbsorber textAbsorber = new TextAbsorber();
page.Accept(textAbsorber);
string text = textAbsorber.Text;
list.Add(new Text(num, text.Trim()));
num++;
}
return list;
}