implement switch case for textbuilding from pptx, docx, txt and add comments for Method loadFileGUI

pom.xml

@@ -14,6 +14,26 @@
         <artifactId>pdfbox</artifactId>
         <version>2.0.29</version>
     </dependency>
+    <dependency>
+        <groupId>org.apache.poi</groupId>
+        <artifactId>poi-ooxml</artifactId>
+        <version>5.2.3</version>
+    </dependency>
+    <dependency>
+        <groupId>org.apache.poi</groupId>
+        <artifactId>poi</artifactId>
+        <version>5.2.3</version>
+    </dependency>
+    <dependency>
+        <groupId>org.apache.xmlbeans</groupId>
+        <artifactId>xmlbeans</artifactId>
+        <version>5.1.1</version>
+    </dependency>
+    <dependency>
+        <groupId>org.apache.logging.log4j</groupId>
+        <artifactId>log4j-core</artifactId>
+        <version>2.18.0</version>
+    </dependency>
 </dependencies>
 
     <properties>

src/main/java/domain/FileLoader.java

@@ -14,14 +14,14 @@ public class FileLoader {
     public FileLoader() {
         this.inputFile = null;
     }
-
+    //KI erstellte Methode
     public File loadFileGUI() {
         try {
             JFileChooser fileChooser = new JFileChooser();
             fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("PDF Files", "pdf"));
-            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("Text Files", "txt"));
-            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("Word Documents", "docx"));
-            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("PowerPoint Presentations", "pptx"));
+            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("Text Files", "txt")); //selbst hinzugefügt
+            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("Word Documents", "docx")); //selbst hinzugefügt
+            fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("PowerPoint Presentations", "pptx")); //selbst hinzugefügt
             int result = fileChooser.showOpenDialog(null);
 
             if (result == JFileChooser.APPROVE_OPTION) {

src/main/java/domain/TextProcessing.java

@@ -2,6 +2,12 @@ package domain;
 
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+import org.apache.poi.xslf.usermodel.XMLSlideShow;
+import org.apache.poi.xslf.usermodel.XSLFSlide;
+import org.apache.poi.xslf.usermodel.XSLFShape;
+import org.apache.poi.xslf.usermodel.XSLFTextShape;
 
 import java.io.*;
 import java.util.HashMap;
@@ -9,31 +15,44 @@ import java.util.HashMap;
 public class TextProcessing {
 
     public String formatToText(File file, String format) {
-        PDDocument document;
         try {
+            StringBuilder text = new StringBuilder();
             if (file != null) {
                 switch (format) {
                     case "txt":
-
-                        break;
-
+                        FileReader fileReader = new FileReader(file);
+                        BufferedReader reader = new BufferedReader(fileReader);
+                        String line;
+                        while((line = reader.readLine()) != null) {
+                            text.append(line).append("\n");
+                        }
+                        return text.toString();
                     case "pdf":
-                        document = PDDocument.load(file);
+                        PDDocument document = PDDocument.load(file);
                         PDFTextStripper pdfStripper = new PDFTextStripper();
                         return pdfStripper.getText(document);
 
                     case "docx":
-
-                        break;
-
+                        XWPFDocument officeDocument = new XWPFDocument(new FileInputStream(file));
+                        for(XWPFParagraph paragraph : officeDocument.getParagraphs()) {
+                            text.append(paragraph.getText()).append("\n");
+                        }
+                        return text.toString();
                     case "pptx":
-
-                        break;
+                        XMLSlideShow ppt = new XMLSlideShow(new FileInputStream(file));
+                        for (XSLFSlide slide : ppt.getSlides()) {
+                            for (XSLFShape shape : slide.getShapes()) {
+                                if (shape instanceof XSLFTextShape) {
+                                    text.append(((XSLFTextShape) shape).getText()).append("\n");
+                                }
+                            }
+                        }
+                        return text.toString();
                 }
             }
         }
-        catch (IOException ex) {
-            throw new RuntimeException(ex);
+        catch (IOException e) {
+            throw new RuntimeException(e);
         }
         return "Nothing found!";
     }
@@ -53,18 +72,20 @@ public class TextProcessing {
     public HashMap tokenizingText(String text){
         HashMap<String, Integer> filteredWords = new HashMap<>();
         try {
+            if(!text.isEmpty()) {
                 //Tokenizing der Wörter
-                String splitter = "[,\\s\\.:/!§$%&/()=?+*~#.;_<>^°\"']";
+                String splitter = "[,\\s\\.:/!§$%&/()=?+*~#.;_<\\-–>^°\"']";
                 String[] textWords = text.split(splitter);
-                for(String word : textWords){
+                for (String word : textWords) {
                     if (filteredWords.containsKey(word)) {
                         filteredWords.compute(word, (k, counter) -> counter + 1);
-                    }
-                    else {
+                    } else {
                         filteredWords.put(word, 1);
                     }
                 }
-            } catch (Exception ex) {
+            }
+        }
+        catch (Exception ex) {
             throw new RuntimeException(ex);
         }
         return filteredWords;