Use of Splitter

dotnet 8.0.100

.vscode/format-report.json

@@ -0,0 +1 @@
+[]

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "[markdown]": {
+        "editor.wordWrap": "off"
+    }
+}

.vscode/tasks.json

@@ -0,0 +1,28 @@
+{
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "Build",
+            "command": "dotnet",
+            "type": "process",
+            "args": [
+                "build",
+                "/property:GenerateFullPaths=true",
+                "/consoleloggerparameters:NoSummary"
+            ],
+            "problemMatcher": "$msCompile"
+        },
+        {
+            "label": "Build Self",
+            "command": "dotnet",
+            "type": "process",
+            "args": [
+                "build",
+                "--runtime",
+                "win-x64",
+                "--self-contained"
+            ],
+            "problemMatcher": "$msCompile"
+        },
+    ]
+}

PDF-Text-Stripper.yml

@@ -23,7 +23,7 @@ steps:
     displayName: Configuration
 
   - script: |
-      set nugetSource=https://messa08ec.ec.local/v3/index.json
+      set nugetSource=https://eaf-prod.mes.infineon.com/v3/index.json
       echo %nugetSource%
       echo ##vso[task.setvariable variable=NugetSource;]%nugetSource%
       echo $(NugetSource)

PDF-Text-Stripper/PDF-Text-Stripper.csproj

@@ -8,7 +8,7 @@
     <PackageId>Infineon.Mesa.PDF.Text.Stripper</PackageId>
     <RuntimeIdentifier>win-x86</RuntimeIdentifier>
     <TargetFrameworks>net48</TargetFrameworks>
-    <Version>4.8.0.1</Version>
+    <Version>4.8.0.2</Version>
   </PropertyGroup>
   <ItemGroup Condition=" '$(TargetFramework)' == 'net48' ">
     <Reference Include="Microsoft.CSharp" />

PDF-Text-Stripper/Program.cs

@@ -5,19 +5,42 @@ using System.Linq;
 
 namespace PDF_Text_Stripper;
 
-internal class Program
+public class Program
 {
 
-    private static void PDFTextStripper(string file)
+    private static void PortableDocumentFormatWriteText(string sourceFileName)
     {
-        string altFileName = Path.ChangeExtension(file, ".txt");
-        if(File.Exists(altFileName))
-            File.Delete(altFileName);
-        org.apache.pdfbox.pdmodel.PDDocument pdfDocument = org.apache.pdfbox.pdmodel.PDDocument.load(file);
-        org.apache.pdfbox.util.PDFTextStripper stripper = new();
-        string text = stripper.getText(pdfDocument);
-        pdfDocument.close();
-        File.WriteAllText(altFileName, text);
+        object item;
+        string pageText;
+        string pagePDFFile;
+        string pageTextFile;
+        java.io.File file = new(sourceFileName);
+        org.apache.pdfbox.util.Splitter splitter = new();
+        string sourcePath = Path.GetDirectoryName(sourceFileName) ?? throw new Exception();
+        string sourceFileNameWithoutExtension = Path.GetFileNameWithoutExtension(sourceFileName);
+        org.apache.pdfbox.pdmodel.PDDocument pdDocument = org.apache.pdfbox.pdmodel.PDDocument.load(file);
+        java.util.List list = splitter.split(pdDocument);
+        java.util.ListIterator iterator = list.listIterator();
+        org.apache.pdfbox.util.PDFTextStripper dataStripper = new();
+        for (short i = 1; i < short.MaxValue; i++)
+        {
+            if (!iterator.hasNext())
+                break;
+            item = iterator.next();
+            pagePDFFile = string.Concat(sourcePath, @"\", sourceFileNameWithoutExtension, "_", i, ".pdf");
+            if (File.Exists(pagePDFFile))
+                File.Delete(pagePDFFile);
+            pageTextFile = Path.ChangeExtension(pagePDFFile, ".txt");
+            if (File.Exists(pageTextFile))
+                File.Delete(pageTextFile);
+            if (item is not org.apache.pdfbox.pdmodel.PDDocument pd)
+                continue;
+            pageText = dataStripper.getText(pd);
+            pd.save(pagePDFFile);
+            pd.close();
+            File.WriteAllText(pageTextFile, pageText);
+        }
+        pdDocument.close();
     }
 
     public static void Secondary(List<string> args)
@@ -28,7 +51,7 @@ internal class Program
         try
         {
             if (args.Any() && File.Exists(args[0]))
-                PDFTextStripper(args[0]);
+                PortableDocumentFormatWriteText(args[0]);
             else
                 throw new Exception(args[0]);
         }

global.json

@@ -1,6 +1,6 @@
 {
     "sdk": {
-      "version": "6.0.202"
+      "version": "8.0.100"
     }
   }