lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-09-20 03:17:57 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Implement DuplicateOverlappingTextProcessor

Browse Source
This commit is contained in:
BobLd
2020-06-25 15:00:20 +01:00
parent 091c17bdf8
commit fe8bc0e5be
1 changed files with 73 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
src/UglyToad.PdfPig.DocumentLayoutAnalysis/DuplicateOverlappingTextProcessor.cs Normal file
View File

@@ -0,0 +1,73 @@
namespace UglyToad.PdfPig.DocumentLayoutAnalysis
{
using System.Collections.Generic;
using System.Linq;
using UglyToad.PdfPig.Content;
/// <summary>
/// Checks if each letter is a duplicate and overlaps any other letter and remove the duplicate. Duplicate overlapping letters might be used to simulate bold.
/// <para>Logic inspired from PdfBox's PDFTextStripper class.</para>
/// </summary>
public static class DuplicateOverlappingTextProcessor
{
/// <summary>
/// Checks if each letter is a duplicate and overlaps any other letter and remove the duplicate. Duplicate overlapping letters might be used to simulate bold.
/// <para>Logic inspired from PdfBox's PDFTextStripper class.</para>
/// </summary>
/// <param name="letters">Letters to be processed.</param>
/// <returns>Letters with no duplicate overlapping.</returns>
public static IReadOnlyList<Letter> Get(IEnumerable<Letter> letters)
{
if (letters?.Any() != true)
{
return letters?.ToList();
}
var queue = new Queue<Letter>(letters);
var cleanLetters = new List<Letter>() { queue.Dequeue() }; // dequeue the first letter
while (queue.Count > 0)
{
var letter = queue.Dequeue();
bool addLetter = true;
var duplicates = cleanLetters.Where(l => l.Value.Equals(letter.Value) && l.FontName.Equals(letter.FontName)); // do other checks?
if (duplicates.Any())
{
double tolerance = letter.GlyphRectangle.Width / (letter.Value.Length == 0 ? 1 : letter.Value.Length) / 3.0;
double minX = letter.GlyphRectangle.BottomLeft.X - tolerance;
double maxX = letter.GlyphRectangle.BottomLeft.X + tolerance;
double minY = letter.GlyphRectangle.BottomLeft.Y - tolerance;
double maxY = letter.GlyphRectangle.BottomLeft.Y + tolerance;
var duplicatesOverlapping = duplicates.FirstOrDefault(l => minX <= l.GlyphRectangle.BottomLeft.X &&
maxX >= l.GlyphRectangle.BottomLeft.X &&
minY <= l.GlyphRectangle.BottomLeft.Y &&
maxY >= l.GlyphRectangle.BottomLeft.Y);
if (duplicatesOverlapping != default)
{
// duplicate overlapping letter was found, keeping the existing one and not adding this one.
addLetter = false;
}
}
if (addLetter)
{
cleanLetters.Add(letter);
}
else
{
// TODO: update font details to bold
// TODO: need to update the bounding box
// TODO: need to update bottom left/right
// TODO: need to update width
// update textSequence?
}
}
return cleanLetters;
}
}
}