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

Fix issues in Advanced Example in README.md

Browse Source
This commit is contained in:
davebrokit 2024-06-23 10:31:47 +01:00 committed by BobLd
parent d2cae7985c
commit dc933aede9
1 changed files with 28 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
README.md
View File

@ -84,52 +84,52 @@ In this example a more advanced document extraction is performed. PdfDocumentBui
```cs
//using UglyToad.PdfPig;
//using UglyToad.PdfPig.DocumentLayoutAnalysis.PageSegmenter;
//using UglyToad.PdfPig.DocumentLayoutAnalysis.ReadingOrderDetector;
//using UglyToad.PdfPig.DocumentLayoutAnalysis.WordExtractor;
//using UglyToad.PdfPig.Fonts.Standard14Fonts;
//using UglyToad.PdfPig.Writer;
var sourcePdfPath = "";
var outputPath = "";
var pageNumber = 1;
using (var document = PdfDocument.Open(sourcePdfPath))
{
var builder = new PdfDocumentBuilder { };
PdfDocumentBuilder.AddedFont font = builder.AddStandard14Font(Standard14Font.Helvetica);
var pageBuilder = builder.AddPage(document, pageNumber);
pageBuilder.SetStrokeColor(0, 255, 0);
var page = document.GetPage(pageNumber);
foreach (var word in page.GetWords())
{
var builder = new PdfDocumentBuilder { };
PdfDocumentBuilder.AddedFont font = builder.AddStandard14Font(Standard14Font.Helvetica);
var pageBuilder = builder.AddPage(document, pageNumber);
pageBuilder.SetStrokeColor(0, 255, 0);
var page = document.GetPage(pageNumber);
var letters = page.Letters; // no preprocessing
var letters = page.Letters; // no preprocessing
// 1. Extract words
var wordExtractor = NearestNeighbourWordExtractor.Instance;
// 1. Extract words
var wordExtractor = NearestNeighbourWordExtractor.Instance;
var words = wordExtractor.GetWords(letters);
var words = wordExtractor.GetWords(letters);
// 2. Segment page
var pageSegmenter = DocstrumBoundingBoxes.Instance;
// 2. Segment page
var pageSegmenter = DocstrumBoundingBoxes.Instance;
var textBlocks = pageSegmenter.GetBlocks(words);
var textBlocks = pageSegmenter.GetBlocks(words);
// 3. Postprocessing
var readingOrder = UnsupervisedReadingOrderDetector.Instance;
var orderedTextBlocks = readingOrder.Get(textBlocks);
// 3. Postprocessing
var readingOrder = UnsupervisedReadingOrderDetector.Instance;
var orderedTextBlocks = readingOrder.Get(textBlocks);
// 4. Add debug info - Bounding boxes and reading order
foreach (var block in orderedTextBlocks)
{
var bbox = block.BoundingBox;
pageBuilder.DrawRectangle(bbox.BottomLeft, bbox.Width, bbox.Height);
pageBuilder.AddText(block.ReadingOrder.ToString(), 8, bbox, font);
}
}
// 4. Add debug info - Bounding boxes and reading order
foreach (var block in orderedTextBlocks)
{
var bbox = block.BoundingBox;
pageBuilder.DrawRectangle(bbox.BottomLeft, bbox.Width, bbox.Height);
pageBuilder.AddText(block.ReadingOrder.ToString(), 8, bbox.TopLeft, font);
}
// 5. Write result to a file
byte[] fileBytes = builder.Build();
File.WriteAllBytes(outputPath, fileBytes); // save to file
// 5. Write result to a file
byte[] fileBytes = builder.Build();
File.WriteAllBytes(outputPath, fileBytes); // save to file
}
```