From eb6a40b82cc5ff7b9b8efac5520bfee608b9ab7f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Joe=20K=C3=BCng?= <kuengjoe@students.zhaw.ch>
Date: Wed, 6 Nov 2024 10:30:03 +0100
Subject: [PATCH] work in progress program.cs

---
 capzlog-ExtractDataFromPDF/Program.cs         | 100 +++++++++++++++++-
 .../capzlog-ExtractDataFromPDF.csproj         |   7 ++
 2 files changed, 104 insertions(+), 3 deletions(-)

diff --git a/capzlog-ExtractDataFromPDF/Program.cs b/capzlog-ExtractDataFromPDF/Program.cs
index 8a84e20..ce41fd1 100644
--- a/capzlog-ExtractDataFromPDF/Program.cs
+++ b/capzlog-ExtractDataFromPDF/Program.cs
@@ -1,4 +1,98 @@
-// See https://aka.ms/new-console-template for more information
-using System;
+using System;
+using System.IO;
+using System.Text;
+using System.Text.RegularExpressions;
+using capzlog_ExtractDataFromPDF.pdfsharp;
+using iText.Kernel.Pdf.Canvas.Parser;
+using iText.Kernel.Pdf.Canvas.Parser.Listener;
+using UglyToad.PdfPig;
 
-Console.WriteLine("Hello, World!");
\ No newline at end of file
+
+namespace capzlog_ExtractDataFromPDF
+{
+    public class ParseCzech
+    {
+        public static readonly String DEST = "C:\\Users\\joeku\\RiderProjects\\capzlog-ExtractDataFromPDF\\text.txt";
+        public static readonly String SRC = "C:\\Users\\joeku\\RiderProjects\\capzlog-ExtractDataFromPDF\\Task 1 - Extract Data from a PDF File - Sample File.pdf";
+        public static void Main(String[] args)
+        {
+            using (var pdfDoc = PdfDocument.Open(SRC))
+            {
+                //Prova prova = new Prova();
+                //prova.ProvaRead(SRC);
+                
+                
+               
+               // var testoEstratto = EstraiTestoDaPosizione(SRC, pagina: 85, xMin: 400, yMin: 400, xMax: 800, yMax: 800);
+
+                //Console.WriteLine("Testo Estratto:");
+               // Console.WriteLine(testoEstratto);
+                
+                //EstraiCrewConRegex(SRC, 85);
+                
+                SinglePageReader reader = new SinglePageReader();
+                reader.GetCrewAndFlightAssignment(pdfDoc, 89);
+            }
+            
+            static string EstraiTestoDaPosizione(string filePath, int pagina, double xMin, double yMin, double xMax, double yMax)
+            {
+                using (PdfDocument pdf = PdfDocument.Open(filePath))
+                {
+                    var paginaPdf = pdf.GetPage(pagina);
+                    List<string> testoNellaZona = new List<string>();
+
+                    foreach (var parola in paginaPdf.GetWords())
+                    {
+                        var posizione = parola.BoundingBox;
+
+                        if (posizione.Left >= xMin && posizione.Right <= xMax &&
+                            posizione.Bottom >= yMin && posizione.Top <= yMax)
+                        {
+                            testoNellaZona.Add(parola.Text);
+                        }
+                    }
+
+                    return string.Join(" ", testoNellaZona);
+                }
+            }
+
+            static void EstraiCrewConRegex(string filePath, int pagina)
+            {
+                List<string> crew = new List<string>();
+                using (PdfDocument pdf = PdfDocument.Open(filePath))
+                {
+                    var paginaPdf = pdf.GetPage(pagina);
+                    string testo = paginaPdf.Text;
+
+                    // Regex per catturare ruolo, codice, nome e posizione in maniera compatta
+                    var regex = new Regex(@"\b(CMD|COP|CAB|SEN)\s(\w+)\s([A-Za-z]+\s[A-Za-z]+)\s(.+?)(?=\bCMD|\bCOP|\bCAB|\bSEN|Observer|Contacts|Crew|\Z)");
+
+                    foreach (Match match in regex.Matches(testo))
+                    {
+                        string ruolo = match.Groups[1].Value;
+                        string codice = match.Groups[2].Value;
+                        string nome = match.Groups[3].Value;
+                        string posizione = match.Groups[4].Value;
+
+                        crew.Add($"{ruolo} {codice} {nome} - {posizione}");
+                    }
+                }
+            }
+
+
+                        
+
+            //
+            
+            // reader.ReadPage(SRC, 85); // Read page 2 for example
+            //
+            //FileInfo file = new FileInfo(DEST);
+            //file.Directory.Create();
+
+            //new ParseCzech().ManipulatePdf(DEST);
+        }
+        
+        
+        
+    }
+}
\ No newline at end of file
diff --git a/capzlog-ExtractDataFromPDF/capzlog-ExtractDataFromPDF.csproj b/capzlog-ExtractDataFromPDF/capzlog-ExtractDataFromPDF.csproj
index c19000d..b97475e 100644
--- a/capzlog-ExtractDataFromPDF/capzlog-ExtractDataFromPDF.csproj
+++ b/capzlog-ExtractDataFromPDF/capzlog-ExtractDataFromPDF.csproj
@@ -8,4 +8,11 @@
         <Nullable>enable</Nullable>
     </PropertyGroup>
 
+    <ItemGroup>
+      <PackageReference Include="itext7" Version="8.0.5" />
+      <PackageReference Include="PdfPig" Version="0.1.9" />
+      <PackageReference Include="PDFsharp" Version="6.1.1" />
+      <PackageReference Include="PDFSharp.Extensions" Version="0.1.2.2" />
+    </ItemGroup>
+
 </Project>