From 78354933d9b09489b1a8044c0224dea5d70d601d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joe=20K=C3=BCng?= <kuengjoe@students.zhaw.ch>
Date: Tue, 5 Nov 2024 10:54:44 +0100
Subject: [PATCH] add ExtractTextBlocks

---
 capzlog-ExtractDataFromPDF/ExtractText.cs | 32 +++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 capzlog-ExtractDataFromPDF/ExtractText.cs

diff --git a/capzlog-ExtractDataFromPDF/ExtractText.cs b/capzlog-ExtractDataFromPDF/ExtractText.cs
new file mode 100644
index 0000000..245c3ea
--- /dev/null
+++ b/capzlog-ExtractDataFromPDF/ExtractText.cs
@@ -0,0 +1,32 @@
+using UglyToad.PdfPig;
+using UglyToad.PdfPig.DocumentLayoutAnalysis;
+using UglyToad.PdfPig.DocumentLayoutAnalysis.PageSegmenter;
+using UglyToad.PdfPig.DocumentLayoutAnalysis.ReadingOrderDetector;
+using UglyToad.PdfPig.DocumentLayoutAnalysis.WordExtractor;
+
+namespace capzlog_ExtractDataFromPDF;
+
+public class ExtractText
+{
+    public IEnumerable<TextBlock> ExtractTextBlocks(PdfDocument document, int pageNumber)
+    {
+        if (pageNumber < 1 || pageNumber > document.NumberOfPages)
+        {
+            throw new ArgumentOutOfRangeException(nameof(pageNumber), "Page number is out of range.");
+        }
+        
+        var page = document.GetPage(pageNumber);
+
+        var letters = page.Letters;
+        var wordExtractor = NearestNeighbourWordExtractor.Instance;
+
+        var words = wordExtractor.GetWords(letters);
+                
+        var pageSegmenter = DocstrumBoundingBoxes.Instance;
+
+        var textBlocks = pageSegmenter.GetBlocks(words);
+                
+        var readingOrder = UnsupervisedReadingOrderDetector.Instance;
+        return readingOrder.Get(textBlocks);
+    }
+}
\ No newline at end of file