refactored code and added tests, stemming not functioning

deutsche_stopwoerter.txt

@@ -0,0 +1,232 @@
+aber
+alle
+allem
+allen
+aller
+alles
+als
+also
+am
+an
+ander
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+auch
+auf
+aus
+bei
+bin
+bis
+bist
+da
+damit
+dann
+das
+dasselbe
+dazu
+daß
+dein
+deine
+deinem
+deinen
+deiner
+deines
+dem
+demselben
+den
+denn
+denselben
+der
+derer
+derselbe
+derselben
+des
+desselben
+dessen
+dich
+die
+dies
+diese
+dieselbe
+dieselben
+diesem
+diesen
+dieser
+dieses
+dir
+doch
+dort
+du
+durch
+ein
+eine
+einem
+einen
+einer
+eines
+einig
+einige
+einigem
+einigen
+einiger
+einiges
+einmal
+er
+es
+etwas
+euch
+euer
+eure
+eurem
+euren
+eurer
+eures
+für
+gegen
+gewesen
+hab
+habe
+haben
+hat
+hatte
+hatten
+hier
+hin
+hinter
+ich
+ihm
+ihn
+ihnen
+ihr
+ihre
+ihrem
+ihren
+ihrer
+ihres
+im
+in
+indem
+ins
+ist
+jede
+jedem
+jeden
+jeder
+jedes
+jene
+jenem
+jenen
+jener
+jenes
+jetzt
+kann
+kein
+keine
+keinem
+keinen
+keiner
+keines
+können
+könnte
+machen
+man
+manche
+manchem
+manchen
+mancher
+manches
+mein
+meine
+meinem
+meinen
+meiner
+meines
+mich
+mir
+mit
+muss
+musste
+nach
+nicht
+nichts
+noch
+nun
+nur
+ob
+oder
+ohne
+sehr
+sein
+seine
+seinem
+seinen
+seiner
+seines
+selbst
+sich
+sie
+sind
+so
+solche
+solchem
+solchen
+solcher
+solches
+soll
+sollte
+sondern
+sonst
+um
+und
+uns
+unser
+unsere
+unserem
+unseren
+unserer
+unseres
+unter
+viel
+vom
+von
+vor
+war
+waren
+warst
+was
+weg
+weil
+weiter
+welche
+welchem
+welchen
+welcher
+welches
+wenn
+werde
+werden
+wie
+wieder
+will
+wir
+wird
+wirst
+wo
+wollen
+wollte
+während
+würde
+würden
+zu
+zum
+zur
+zwar
+zwischen
+über

pom.xml

@@ -39,6 +39,18 @@
         <artifactId>lucene-analysis-common</artifactId>
         <version>9.9.2</version>
     </dependency>
+    <dependency>
+        <groupId>junit</groupId>
+        <artifactId>junit</artifactId>
+        <version>4.13.2</version>
+        <scope>test</scope>
+    </dependency>
+    <dependency>
+        <groupId>org.junit.jupiter</groupId>
+        <artifactId>junit-jupiter</artifactId>
+        <version>RELEASE</version>
+        <scope>test</scope>
+    </dependency>
 </dependencies>
 
     <properties>

src/main/java/domain/TextProcessing.java

@@ -67,11 +67,6 @@ public class TextProcessing {
         return "Nothing found!";
     }
 
-//    public String fileToTextString(File path, String format) {
-//        String text = formatToText(path, format);
-//        return text;
-//    }
-
     public void textToSetStopwords(Map<String, Integer> words) {
         Set<String> stopwords = new HashSet<>();
         for (Map.Entry<String, Integer> entry : words.entrySet()) {
@@ -99,9 +94,9 @@ public class TextProcessing {
     public Map<String, Integer> sortList(Map<String, Integer> unsortedMap) {
         List<Map.Entry<String, Integer>> entryList = new ArrayList<>(unsortedMap.entrySet());
 
-        entryList.sort((e1, e2) -> e2.getValue().compareTo(e1.getValue())); //Ki erstellte Zeile
+        entryList.sort((e1, e2) -> e2.getValue().compareTo(e1.getValue())); //KI erstellte Zeile
 
-        Map<String, Integer> sortedMap = new TreeMap<>();
+        Map<String, Integer> sortedMap = new LinkedHashMap<>();
         for (Map.Entry<String, Integer> entry : entryList) {
             sortedMap.put(entry.getKey(), entry.getValue());
         }
@@ -143,6 +138,22 @@ public class TextProcessing {
         return words;
     }
 
+//    public Map<String, Integer> stemming(Map<String, Integer> wordList) {
+//        Map<String, Integer> wordCounts = new HashMap<>();
+//        GermanStemmer stemmer = new GermanStemmer();
+//
+//        for (String key : wordList.keySet()) {
+//            char[] wordChars = key.toCharArray();
+//            int length = stemmer.stem(wordChars, wordChars.length); // Stemming durchführen
+//            String stemmedWord = new String(wordChars, 0, length); // Gestemmtes Wort extrahieren
+//
+//            if (stemmedWord != null && !stemmedWord.isBlank()) {
+//                wordCounts.merge(stemmedWord, wordList.get(key), Integer::sum);
+//            }
+//        }
+//        return wordCounts;
+//    }
+
     public void setStemming(boolean stemming) {
         this.stemming = stemming;
     }
@@ -150,19 +161,4 @@ public class TextProcessing {
     public void setMaxWords(int maxWords) {
         this.maxWords = maxWords;
     }
-
-
-
-//    public Map<String, Integer> stemming(Map<String, Integer> wordList) {
-//        Map<String, Integer> wordCounts = new HashMap<>();
-//        GermanStemmer stemmer = new GermanStemmer();
-//
-//        for (String key: wordList.keySet()) {
-//            String stemmedWord = stemmer.stemWord(key);
-//            if (stemmedWord != null) {
-//                wordCounts.merge(stemmedWord, 1, Integer::sum);
-//            }
-//        }
-//        return wordCounts;
-//    }
 }

src/main/java/domain/WordCloudCreator.java

@@ -4,8 +4,8 @@ import java.io.*;
 import java.util.Map;
 
 public class WordCloudCreator {
+    private int maxFontSize = 70;
 
-    //AI Method but mit massive changes
     public boolean insertWordsIntoTemplate(Map<String, Integer> wordMap) {
         File templateFile = new File("wordcloud.html"); // Template in project directory
         File outputFile = new File("createdHTML.html"); // Output in project directory
@@ -23,14 +23,14 @@ public class WordCloudCreator {
             while ((line = reader.readLine()) != null) {
                 htmlContent.append(line).append("\n");
             }
-
+//AI generated lines below
-            // Generate clickable word entries with font size based on frequency
+            // Generated clickable word entries with font size based on frequency
             StringBuilder wordEntries = new StringBuilder();
             int id = 1;
             for (Map.Entry<String, Integer> entry : wordMap.entrySet()) {
                 String word = entry.getKey();
                 int frequency = entry.getValue();
-                int fontSize = (int) ((float) 12 + frequency * 1.5); // Example: Base size 10px, increase by 2px per frequency
+                int fontSize = Math.min(10 + frequency * 2, maxFontSize); // Example: Base size 10px, increase by 2px per frequency
                 wordEntries.append(String.format(
                         "<span id=\"%d\" class=\"wrd\" style=\"font-size:%dpx;\">" +
                                 "<a href=\"https://www.google.com/search?q=%s\" target=\"_blank\">%s</a>" +
@@ -50,10 +50,11 @@ public class WordCloudCreator {
             // Write the updated HTML to the output file
             writer.write(updatedHtml);
             System.out.println("Output file 'output.html' created successfully!");
+            return true;
 
         } catch (IOException e) {
             throw new RuntimeException("Error processing HTML template", e);
         }
-        return true;
+
     }
 }

src/main/java/facade/WordCloudManager.java

@@ -20,12 +20,8 @@ public class WordCloudManager {
     public boolean loadFile() {
         fl.loadFileGUI();
         if (fl.getFilePath().length() > 0) {
-            System.out.println(fl.getFilePath());
-            System.out.println(fl.getStopwordsPath());
             return true;
         } else {
-            System.out.println(fl.getFilePath());
-            System.out.println(fl.getStopwordsPath());
             return false;
         }
     }

src/main/java/tui/TUI.java

@@ -51,7 +51,7 @@ public class TUI {
     public void fileMenu() {
         while(fMenu) {
             System.out.println("(0) Load Stopwords\n(1) Add to Stopwords\n(2) Set Max Words in HTML\n" +
-                    "(3) Stemming? (only German available)\n(4) Create WordCloud\n(5) Exit FileMenu");
+                    "(3) Stemming? (only German available)\n(4) Create WordCloud and Exit");
             option = Integer.parseInt(scan.nextLine());
             switch(option) {
                 case (0):
@@ -88,19 +88,15 @@ public class TUI {
                     }
                     break;
                 case(4):
-                    //Create WordCloud
+                    //Create WordCloud and exit program
                     if(wcm.createWordCloud()) {
-                        System.out.println("HTML File created!");
+                        System.out.println("HTML File created!\n");
-                        fMenu = false;
-                    }
-                    else {
-                        System.out.println("HTML FIle not created!");
-                    }
-                    break;
-                case(5):
-                    //Exit Filemenu
                         fMenu = false;
                         System.out.println("Close Program!");
+                    }
+                    else {
+                        System.out.println("HTML FIle not created!\n");
+                    }
                     break;
             }
         }

src/test/java/FileLoaderTest.java

@@ -0,0 +1,23 @@
+import domain.FileLoader;
+import org.junit.jupiter.api.Test;
+import java.io.File;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+class FileLoaderTest {
+
+    @Test
+    void testGetFileFormat_knownFormats() {
+        FileLoader loader = new FileLoader();
+        assertEquals("txt", loader.getFileFormat(new File("test.txt")));
+        assertEquals("pdf", loader.getFileFormat(new File("test.pdf")));
+        assertEquals("docx", loader.getFileFormat(new File("test.docx")));
+        assertEquals("pptx", loader.getFileFormat(new File("test.pptx")));
+    }
+
+    @Test
+    void testGetFileFormat_unknownFormat() {
+        FileLoader loader = new FileLoader();
+        assertEquals("File format not supported", loader.getFileFormat(new File("test.xyz")));
+    }
+}

src/test/java/TextProcessingTest.java

@@ -0,0 +1,68 @@
+import domain.TextProcessing;
+import org.junit.jupiter.api.Test;
+
+import java.util.*;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+class TextProcessingTest {
+
+    @Test
+    void testAddToStopWords() {
+        TextProcessing tp = new TextProcessing();
+        tp.addToStopWords("der");
+        assertTrue(tp.tokenizingFile("Der Hund ist groß.").containsKey("hund"));
+        assertFalse(tp.tokenizingFile("Der Hund ist groß.").containsKey("der"));
+    }
+
+    @Test
+    void testSortList() {
+        TextProcessing tp = new TextProcessing();
+        Map<String, Integer> input = Map.of("a", 1, "b", 3, "c", 2);
+        List<Integer> values = new ArrayList<>(tp.sortList(input).values());
+        assertEquals(List.of(3, 2, 1), values);
+    }
+
+    @Test
+    void testMaxShowWords() {
+        TextProcessing tp = new TextProcessing();
+        Map<String, Integer> input = new LinkedHashMap<>();
+        input.put("eins", 1);
+        input.put("zwei", 2);
+        input.put("drei", 3);
+
+        Map<String, Integer> result = tp.maxShowWords(input, 2);
+        assertEquals(2, result.size());
+    }
+
+    @Test
+    void testAddStopWordsIndividuallyAndAsList() {
+        TextProcessing tp = new TextProcessing();
+
+        tp.addToStopWords("der");
+        tp.addToStopWords("die");
+        tp.addToStopWords("das");
+
+        assertTrue(tp.tokenizingFile("Der Hund ist groß.").containsKey("hund"));
+        assertFalse(tp.tokenizingFile("Der Hund ist groß.").containsKey("der"));
+        assertFalse(tp.tokenizingFile("Die Katze ist klein.").containsKey("die"));
+
+        Map<String, Integer> stopwordMap = Map.of("und", 1, "oder", 1, "aber", 1);
+        tp.textToSetStopwords(stopwordMap);
+
+        assertFalse(tp.tokenizingFile("Und der Hund ist groß.").containsKey("und"));
+        assertFalse(tp.tokenizingFile("Oder die Katze ist klein.").containsKey("oder"));
+        assertFalse(tp.tokenizingFile("Aber das Haus ist alt.").containsKey("aber"));
+    }
+
+//    @Test
+//    void testStemming() {
+//        TextProcessing tp = new TextProcessing();
+//        Map<String, Integer> input = new HashMap<>();
+//        input.put("gegangen", 1);
+//        input.put("geht", 1);
+//
+//        Map<String, Integer> result = tp.stemming(input);
+//        assertFalse(result.isEmpty());
+//    }
+}

src/test/java/WordCloudCreatorTest.java

@@ -0,0 +1,30 @@
+import domain.WordCloudCreator;
+import org.junit.jupiter.api.Test;
+
+import java.io.File;
+import java.io.FileWriter;
+import java.io.IOException;
+import java.util.Map;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+class WordCloudCreatorTest {
+
+    @Test
+    void testInsertWordsIntoTemplate_success() throws IOException {
+        // Prepare a simple HTML template with placeholder
+        File template = new File("wordcloud.html");
+        try (FileWriter fw = new FileWriter(template)) {
+            fw.write("<html><body><!-- TODO: Hier die generierten Tags einsetzen --></body></html>");
+        }
+
+        WordCloudCreator creator = new WordCloudCreator();
+        Map<String, Integer> words = Map.of("Test", 3, "Java", 2);
+
+        assertTrue(creator.insertWordsIntoTemplate(words));
+
+        File output = new File("createdHTML.html");
+        assertTrue(output.exists());
+        assertTrue(output.length() > 0);
+    }
+}

wordcloud.html

@@ -0,0 +1 @@
+<html><body><!-- TODO: Hier die generierten Tags einsetzen --></body></html>