From b4abbf82823179fd2efe40c671c459b11e3eaa2b Mon Sep 17 00:00:00 2001
From: Daniel Fromm <3015351@stud.hs-mannheim.de>
Date: Tue, 29 Apr 2025 15:05:24 +0200
Subject: [PATCH 1/2] adding KI Code for FileChooser PDF
---
pom.xml | 8 +++++++
src/main/java/domain/FileManager.java | 32 +++++++++++++++++++--------
2 files changed, 31 insertions(+), 9 deletions(-)
diff --git a/pom.xml b/pom.xml
index 138cc1d..52adb1c 100644
--- a/pom.xml
+++ b/pom.xml
@@ -8,6 +8,14 @@
PR2WordCloud
1.0-SNAPSHOT
+
+
+ org.apache.pdfbox
+ pdfbox
+ 2.0.29
+
+
+
23
23
diff --git a/src/main/java/domain/FileManager.java b/src/main/java/domain/FileManager.java
index 031497a..8609475 100644
--- a/src/main/java/domain/FileManager.java
+++ b/src/main/java/domain/FileManager.java
@@ -1,5 +1,7 @@
package domain;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.text.PDFTextStripper;
import javax.swing.*;
import javax.swing.filechooser.FileNameExtensionFilter;
import java.io.File;
@@ -7,17 +9,29 @@ import java.io.File;
public class FileManager {
public void loadFile() {
- JFileChooser fileChooser = new JFileChooser();
- fileChooser.setFileFilter(new FileNameExtensionFilter("PDF Files", "pdf"));
+ try{
+ JFileChooser fileChooser = new JFileChooser();
+ fileChooser.setFileFilter(new FileNameExtensionFilter("PDF Files", "pdf"));
- int result = fileChooser.showOpenDialog(null);
+ int result = fileChooser.showOpenDialog(null);
- if (result == JFileChooser.APPROVE_OPTION) {
- File selectedFile = fileChooser.getSelectedFile();
- System.out.println("Ausgewählte Datei: " + selectedFile.getAbsolutePath());
- // Hier kannst du die Datei weiterverarbeiten
- } else {
- System.out.println("Dateiauswahl abgebrochen.");
+ if (result == JFileChooser.APPROVE_OPTION) {
+ File selectedFile = fileChooser.getSelectedFile();
+ System.out.println("Ausgewählte Datei: " + selectedFile.getAbsolutePath());
+ // Hier kannst du die Datei weiterverarbeiten
+
+ try (PDDocument document = PDDocument.load(selectedFile)) {
+ PDFTextStripper pdfStripper = new PDFTextStripper();
+ String text = pdfStripper.getText(document);
+ System.out.println(text);
+ }
+ }
+ else {
+ System.out.println("Dateiauswahl abgebrochen.");
+ }
+
+ } catch (Exception e) {
+ e.printStackTrace();
}
}
From 21546dd91d0631db7db94ea2cbe3010c7073061b Mon Sep 17 00:00:00 2001
From: Daniel Fromm <3015351@stud.hs-mannheim.de>
Date: Tue, 29 Apr 2025 16:11:26 +0200
Subject: [PATCH 2/2] solved errors. in Filechooser and PDFTextstripper
---
src/main/java/domain/FileManager.java | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/src/main/java/domain/FileManager.java b/src/main/java/domain/FileManager.java
index 8609475..8c563e2 100644
--- a/src/main/java/domain/FileManager.java
+++ b/src/main/java/domain/FileManager.java
@@ -18,12 +18,15 @@ public class FileManager {
if (result == JFileChooser.APPROVE_OPTION) {
File selectedFile = fileChooser.getSelectedFile();
System.out.println("Ausgewählte Datei: " + selectedFile.getAbsolutePath());
- // Hier kannst du die Datei weiterverarbeiten
try (PDDocument document = PDDocument.load(selectedFile)) {
PDFTextStripper pdfStripper = new PDFTextStripper();
String text = pdfStripper.getText(document);
- System.out.println(text);
+ String regex = "[,\\s\\.:/]";
+ String[] words = text.split(regex);
+ for(String word : words) {
+ System.out.println(word);
+ }
}
}
else {