private string GetPdfText(PageData pageData, PdfTextSpan textSpan)
{
var result = new byte[(textSpan.Length + 1) * 2];
NativeMethods.FPDFText_GetText(pageData.TextPage, textSpan.Offset, textSpan.Length, result);
return(FPDFEncoding.GetString(result, 0, textSpan.Length * 2));
}
public IList <PdfRectangle> GetTextBounds(PdfTextSpan textSpan)
{
using (var pageData = new PageData(_document, _form, textSpan.Page))
{
return(GetTextBounds(pageData.TextPage, textSpan.Page, textSpan.Offset, textSpan.Length));
}
}
public string GetPdfText(PdfTextSpan textSpan)
{
using (var pageData = new PageData(_document, _form, textSpan.Page))
{
return(GetPdfText(pageData, textSpan));
}
}
public string GetPdfText(PdfTextSpan textSpan)
{
var pageData = GetPageData(_document, _form, textSpan.Page);
{
return(GetPdfText(pageData, textSpan));
}
}
public bool GetWordAtPosition(PdfPoint location, double xTolerance, double yTolerance, out PdfTextSpan span)
{
var index = GetCharIndexAtPos(location, xTolerance, yTolerance);
if (index < 0)
{
span = default(PdfTextSpan);
return(false);
}
var baseCharacter = GetCharacter(location.Page, index);
if (IsWordSeparator(baseCharacter))
{
span = default(PdfTextSpan);
return(false);
}
int start = index, end = index;
for (int i = index - 1; i >= 0; i--)
{
var c = GetCharacter(location.Page, i);
if (IsWordSeparator(c))
{
break;
}
start = i;
}
var count = CountChars(location.Page);
for (int i = index + 1; i < count; i++)
{
var c = GetCharacter(location.Page, i);
if (IsWordSeparator(c))
{
break;
}
end = i;
}
span = new PdfTextSpan(location.Page, start, end - start);
return(true);
bool IsWordSeparator(char c)
{
return(char.IsSeparator(c) || char.IsPunctuation(c) || char.IsControl(c) || char.IsWhiteSpace(c) || c == '\r' || c == '\n');
}
}
private string GetPdfText(PageData pageData, PdfTextSpan textSpan)
{
// NOTE: The count parameter in FPDFText_GetText seems to include the null terminator, even though the documentation does not specify this.
// So to read 40 characters, we need to allocate 82 bytes (2 for the terminator), and request 41 characters from GetText.
// The return value also includes the terminator (which is documented)
var result = new byte[(textSpan.Length + 1) * 2];
int count = NativeMethods.FPDFText_GetText(pageData.TextPage, textSpan.Offset, textSpan.Length + 1, result);
if (count <= 0)
{
return(string.Empty);
}
return(FPDFEncoding.GetString(result, 0, (count - 1) * 2));
}
private string GetPdfText(PageData pageData, PdfTextSpan textSpan)
{
var result = new byte[(textSpan.Length + 1) * 2];
NativeMethods.FPDFText_GetText(pageData.TextPage, textSpan.Offset, textSpan.Length, result);
string s = FPDFEncoding.GetString(result, 0, textSpan.Length * 2);
string az = "QWERTYUIOPASDFGHJKLZXCVBNMqwertyuiopasdfghjklzxcvbnm0123456789";
s = s.Replace('\0', ' ');
string[] a = s.Split(new char[] { ' ', '\n' });
string si = a[0];
for (int i = 1; i < a.Length; i++)
{
string it = a[i];
if (it.Trim().Length == 1)
{
if (az.IndexOf(it) == -1)
{
si += ' ' + it;
}
else
{
if (i < a.Length && a[i + 1].Trim().Length == 1)
{
si = si.Trim() + ' ' + it + a[i + 1].Trim();
i++;
}
else
{
si = si.Trim() + it;
}
}
}
else
{
si += ' ' + it + ' ';
}
}
si = si.Replace("\r", "\r\n").Trim();
return(si);
}
public IList <PdfRectangle> GetTextBounds(PdfTextSpan textSpan)
{
var result = new List <PdfRectangle>();
var pageData = GetPageData(_document, _form, textSpan.Page);
{
int rect_count = NativeMethods.FPDFText_CountRects(pageData.TextPage, textSpan.Offset, textSpan.Length);
for (int i = 0; i < rect_count; i++)
{
NativeMethods.FPDFText_GetRect(pageData.TextPage, i, out var left, out var top, out var right, out var bottom);
RectangleF bounds = new RectangleF((float)left, (float)top, (float)(right - left), (float)(bottom - top));
result.Add(new PdfRectangle(textSpan.Page, bounds));
}
return(result);
}
}
public string GetPdfText(PdfTextSpan textSpan)
{
return(GetPdfText(GetPageData(textSpan.Page), textSpan));
}
public IList <PdfRectangle> GetTextBounds(PdfTextSpan textSpan)
{
return(GetTextBounds(GetPageData(textSpan.Page).TextPage, textSpan.Page, textSpan.Offset, textSpan.Length));
}
public PdfMatch(string text, PdfTextSpan textSpan, int page)
{
Text = text;
TextSpan = textSpan;
Page = page;
}
/// <summary>
/// Get the full word at or nearby a specific position
/// </summary>
/// <param name="location">The location to inspect</param>
/// <param name="xTolerance">An x-axis tolerance value for character hit detection, in point unit.</param>
/// <param name="yTolerance">A y-axis tolerance value for character hit detection, in point unit.</param>
/// <param name="span">The location of the found word, if any</param>
/// <returns>A value indicating whether a word was found at the specified location</returns>
public bool GetWordAtPosition(PdfPoint location, double xTolerance, double yTolerance, out PdfTextSpan span)
{
return(_file.GetWordAtPosition(location, xTolerance, yTolerance, out span));
}
/// <summary>
/// Get all bounding rectangles for the text span.
/// </summary>
/// <description>
/// The algorithm used to get the bounding rectangles tries to join
/// adjacent character bounds into larger rectangles.
/// </description>
/// <param name="textSpan">The span to get the bounding rectangles for.</param>
/// <returns>The bounding rectangles.</returns>
public IList <PdfRectangle> GetTextBounds(PdfTextSpan textSpan)
{
return(_file.GetTextBounds(textSpan));
}
/// <summary>
/// Get all text matching the text span.
/// </summary>
/// <param name="textSpan">The span to get the text for.</param>
/// <returns>The text matching the span.</returns>
public string GetPdfText(PdfTextSpan textSpan)
{
return(_file.GetPdfText(textSpan));
}
public IList <PdfRectangle> GetTextBounds(PdfTextSpan textSpan)
{
return(Document.GetTextBounds(textSpan));
}
public string GetPdfText(PdfTextSpan textSpan)
{
return(Document.GetPdfText(textSpan));
}
