From 59857d117359544d936ba7f4836fb752a03b5a20 Mon Sep 17 00:00:00 2001
From: Daniel Fromm <3015351@stud.hs-mannheim.de>
Date: Tue, 13 May 2025 01:16:01 +0200
Subject: [PATCH] some refactoring and cleared a bug with PDFDocument file
 opening warning

---
 src/main/java/domain/FileLoader.java       |  1 +
 src/main/java/domain/TextProcessing.java   | 13 ++++++++++---
 src/main/java/domain/URLContentLoader.java |  1 +
 src/main/java/domain/WordCloudCreator.java |  3 ++-
 src/main/java/tui/TUI.java                 |  5 +++--
 5 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/src/main/java/domain/FileLoader.java b/src/main/java/domain/FileLoader.java
index 1a33927..6e852eb 100644
--- a/src/main/java/domain/FileLoader.java
+++ b/src/main/java/domain/FileLoader.java
@@ -41,6 +41,7 @@ public class FileLoader {
         }
     }
 
+    //detect format from file for further processing
     public String getFileFormat(File path) {
         String fileName = path.getName();
         String fileFormat = fileName.contains(".") ? fileName.substring(fileName.lastIndexOf(".") + 1) : "";
diff --git a/src/main/java/domain/TextProcessing.java b/src/main/java/domain/TextProcessing.java
index 4f6c788..cd1499f 100644
--- a/src/main/java/domain/TextProcessing.java
+++ b/src/main/java/domain/TextProcessing.java
@@ -24,6 +24,7 @@ public class TextProcessing {
     private int maxWords = 0;
     private Set<String> stopwordList = new HashSet<>();
 
+    //Extract text from file with supported format
     public String formatToText(File file, String format) {
         StringBuilder text = new StringBuilder();
         try {
@@ -38,9 +39,10 @@ public class TextProcessing {
                         }
                         return text.toString();
                     case "pdf":
-                        PDDocument document = PDDocument.load(file);
-                        PDFTextStripper pdfStripper = new PDFTextStripper();
-                        return pdfStripper.getText(document);
+                        try (PDDocument document = PDDocument.load(file)) {
+                            PDFTextStripper pdfStripper = new PDFTextStripper();
+                            return pdfStripper.getText(document);
+                        }
 
                     case "docx":
                         XWPFDocument officeDocument = new XWPFDocument(new FileInputStream(file));
@@ -67,6 +69,7 @@ public class TextProcessing {
         return text.toString();
     }
 
+    //Set stopwords in list
     public void textToSetStopwords(Map<String, Integer> words) {
         Set<String> stopwords = new HashSet<>();
         for (Map.Entry<String, Integer> entry : words.entrySet()) {
@@ -75,10 +78,12 @@ public class TextProcessing {
         stopwordList.addAll(stopwords);
     }
 
+    //Set stopword in list
     public void addToStopWords(String stopword) {
         stopwordList.add(stopword);
     }
 
+    //Set maxwords for html
     public Map<String, Integer> maxShowWords(Map<String, Integer> words, int maxWords) {
         HashMap <String, Integer> cuttedHashmap = new HashMap<>();
         int index = maxWords;
@@ -91,6 +96,7 @@ public class TextProcessing {
         return cuttedHashmap;
     }
 
+    //Sort List for cutting the map with words
     public Map<String, Integer> sortList(Map<String, Integer> unsortedMap) {
         List<Map.Entry<String, Integer>> entryList = new ArrayList<>(unsortedMap.entrySet());
 
@@ -103,6 +109,7 @@ public class TextProcessing {
         return sortedMap;
     }
 
+    //tokenizing, stemming, lowercasing, stopwordfiltering Method Apachi Lucene
     public Map<String, Integer> tokenizingFile(String text) {
         Map<String, Integer> words = new HashMap<>();
 
diff --git a/src/main/java/domain/URLContentLoader.java b/src/main/java/domain/URLContentLoader.java
index c448989..b0599fb 100644
--- a/src/main/java/domain/URLContentLoader.java
+++ b/src/main/java/domain/URLContentLoader.java
@@ -9,6 +9,7 @@ import java.net.URL;
 public class URLContentLoader {
     private String urlPath;
 
+    //extract Content from URL
     public String loadURLContent() {
         StringBuilder text = new StringBuilder();
         try {
diff --git a/src/main/java/domain/WordCloudCreator.java b/src/main/java/domain/WordCloudCreator.java
index 8929e8d..931d67a 100644
--- a/src/main/java/domain/WordCloudCreator.java
+++ b/src/main/java/domain/WordCloudCreator.java
@@ -6,6 +6,7 @@ import java.util.Map;
 public class WordCloudCreator {
     private int maxFontSize = 70;
 
+    //Create html file with clickable words
     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
@@ -28,7 +29,7 @@ public class WordCloudCreator {
                 int frequency = entry.getValue();
                 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;\">" +
+                        "<span id=\"%d\" class=\"wrd\" style=\"font-size:%dpx; margin-right:10px\">" +
                                 "<a href=\"https://www.google.com/search?q=%s\" target=\"_blank\">%s</a>" +
                                 "</span>\n",
                         id++, fontSize, word, word
diff --git a/src/main/java/tui/TUI.java b/src/main/java/tui/TUI.java
index 8d0b176..28f1877 100644
--- a/src/main/java/tui/TUI.java
+++ b/src/main/java/tui/TUI.java
@@ -64,7 +64,7 @@ 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 not functioning!\n(4) Create WordCloud and Exit");
+                    "(3) Activate German stemming\n(4) Create WordCloud and Exit");
             option = Integer.parseInt(scan.nextLine());
             switch(option) {
                 case (0):
@@ -74,7 +74,8 @@ public class TUI {
                             System.out.println("File loaded successful!\n");
                         }
                         else{
-                            System.out.println("Cannot load one more File!\n");
+                            System.out.println("Cannot load one more File! Please use for more stopwords words " +
+                                    "menu option (1).\n");
                         }
                     }
                     else {