lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-04-05 20:55:01 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

New GetText() option: NegativeGapAsWhitespace

Browse Source 
When parsing PDF files with tables containing multiple lines in a cell or "merged" cells, the separate words can appear out of horizontal order. This option can better predict the spaces between the words.
This commit is contained in:
Kizaemon 2024-12-08 21:28:47 +09:00 committed by BobLd
parent 97ae62ce6f
commit a2ae1f16d6
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/UglyToad.PdfPig.DocumentLayoutAnalysis/TextExtractor/ContentOrderTextExtractor.cs
View File

@ -110,6 +110,11 @@
{
var gap = letter.StartBaseLine.X - previous.EndBaseLine.X;
if (options.NegativeGapAsWhitespace)
{
gap = Math.Abs(gap);
}
if (WhitespaceSizeStatistics.IsProbablyWhitespace(gap, previous))
{
sb.Append(" ");
@ -178,6 +183,13 @@
/// character. Default <see langword="false"/>.
/// </summary>
public bool ReplaceWhitespaceWithSpace { get; set; }
/// <summary>
/// When parsing PDF files with tables containing multiple lines in a cell or "merged" cells,
/// the separate words can appear out of horizontal order. This option can better predict the
// spaces between the words. Default <see langword="false"/>.
/// </summary>
public bool NegativeGapAsWhitespace { get; set; }
}
}
}