From 9c6c61ada9042a7c80eb7c51f8f411209857a809 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joe=20K=C3=BCng?= <kuengjoe@students.zhaw.ch>
Date: Wed, 6 Nov 2024 10:28:54 +0100
Subject: [PATCH] ExtractText implemented

---
 capzlog-ExtractDataFromPDF/ExtractText.cs     | 32 ----------------
 .../util/ExtractText.cs                       | 37 +++++++++++++++++++
 2 files changed, 37 insertions(+), 32 deletions(-)
 delete mode 100644 capzlog-ExtractDataFromPDF/ExtractText.cs
 create mode 100644 capzlog-ExtractDataFromPDF/util/ExtractText.cs

diff --git a/capzlog-ExtractDataFromPDF/ExtractText.cs b/capzlog-ExtractDataFromPDF/ExtractText.cs
deleted file mode 100644
index 245c3ea..0000000
--- a/capzlog-ExtractDataFromPDF/ExtractText.cs
+++ /dev/null
@@ -1,32 +0,0 @@
-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
diff --git a/capzlog-ExtractDataFromPDF/util/ExtractText.cs b/capzlog-ExtractDataFromPDF/util/ExtractText.cs
new file mode 100644
index 0000000..5f4a700
--- /dev/null
+++ b/capzlog-ExtractDataFromPDF/util/ExtractText.cs
@@ -0,0 +1,37 @@
+using UglyToad.PdfPig;
+using UglyToad.PdfPig.DocumentLayoutAnalysis.PageSegmenter;
+using UglyToad.PdfPig.DocumentLayoutAnalysis.WordExtractor;
+
+namespace capzlog_ExtractDataFromPDF;
+
+public class ExtractText
+{
+    public string 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 words = page.GetWords(NearestNeighbourWordExtractor.Instance);
+        
+        var blocks = DefaultPageSegmenter.Instance.GetBlocks(words);
+        
+        return blocks[0].Text;
+    }
+
+    public List<string> ExtractFirstLines(PdfDocument document)
+    {
+        List<string> firstLines = new List<string>();
+        for (int i = 1; i <= document.NumberOfPages; i++)
+        {
+            var page = document.GetPage(i);
+            var words = page.GetWords(NearestNeighbourWordExtractor.Instance);
+            var blocks = DefaultPageSegmenter.Instance.GetBlocks(words);
+            firstLines.Add(blocks[0].Text.Split("\n")[0]);;
+        }
+        return firstLines;
+    }
+}
\ No newline at end of file