PHIS/filesearch.py

import os
import threading
import itertools
from tkinter import Tk, Label, Entry, Button, Text, filedialog

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()

def list_files(directory):
    files = []
    for root, dirs, filenames in os.walk(directory):
        # Versteckte Verzeichnisse ausschließen
        dirs[:] = [d for d in dirs if not d.startswith('.')]
        for filename in filenames:
            if filename.endswith(('.docx', '.pdf')):
                file_path = os.path.join(root, filename)
                files.append(file_path)
    return files  # Hier wurde die Einrückung korrigiert
def compare_with_openai(content, search_query):
    client = OpenAI(
        api_key=os.environ.get("OPENAI_API_KEY"),  # This is the default and can be omitted
    )
    try:
        chat_completion = client.chat.completions.create(
            messages=[
                {
                    "role": "user",
                    "content": f"Vergleiche den folgenden Text mit der Suchanfrage '{search_query}':\n\n{content[:1000]}...\n\nIst der Text relevant für die Suchanfrage? Antworte mit 'Ja' oder 'Nein'.",
                }
            ],
            model="gpt-4o-mini",
        )
        answer = chat_completion.choices[0].message.content.strip().lower()
        return "ja" in answer
    except Exception as e:
        print(f"Fehler bei der OpenAI-API-Anfrage: {e}")
        return False

def read_file_content(file_path):
    if file_path.endswith('.docx'):
        try:
            import docx
            doc = docx.Document(file_path)
            fullText = []
            for para in doc.paragraphs:
                fullText.append(para.text)
            return '\n'.join(fullText)
        except Exception as e:
            print(f"Fehler beim Lesen der DOCX-Datei {file_path}: {e}")
            return ''
    elif file_path.endswith('.pdf'):
        try:
            import PyPDF2
            with open(file_path, 'rb') as pdf_file:
                reader = PyPDF2.PdfReader(pdf_file)
                text = ''
                for page in reader.pages:
                    page_text = page.extract_text()
                    if page_text:
                        text += page_text
                return text
        except Exception as e:
            print(f"Fehler beim Lesen der PDF-Datei {file_path}: {e}")
        return ''
    else:
        return ''

def search_files_threaded():
    search_query = query_entry.get()
    directory = directory_entry.get()

    if not search_query:
        print("Keine Suchanfrage eingegeben.")
        root.after(0, stop_animation)
        return

    if not directory:
        print("Kein Verzeichnis eingegeben.")
        root.after(0, stop_animation)
        return

    if not os.path.exists(directory):
        print("Verzeichnis existiert nicht.")
        root.after(0, stop_animation)
        return

    files = list_files(directory)
    found_files = []

    for file_path in files:
        file_content = read_file_content(file_path)
        if file_content:
            if compare_with_openai(file_content, search_query):
                found_files.append(file_path)

    # Nach Abschluss der Suche GUI aktualisieren
    root.after(0, update_result_text, found_files)

def update_result_text(found_files):
    # Animation stoppen
    global searching
    searching = False
    animation_label.config(text="")

    result_text.delete(1.0, 'end')
    if found_files:
        result_text.insert('end', "Dateien relevant für die Suchanfrage:\n")
        for file in found_files:
            result_text.insert('end', file + '\n')
    else:
        result_text.insert('end', "Keine relevanten Dateien gefunden.")

def start_search():
    global searching
    if searching:
        print("Die Suche läuft bereits.")
        return
    searching = True
    result_text.delete(1.0, 'end')  # Ausgabefenster leeren
    animate()  # Animation starten
    threading.Thread(target=search_files_threaded).start()

def animate():
    if not searching:
        return
    next_frame = next(animation_frames)
    animation_label.config(text=f"Suche läuft... {next_frame}")
    root.after(200, animate)

def stop_animation():
    global searching
    searching = False
    animation_label.config(text="")

def select_directory():
    directory = filedialog.askdirectory()
    if directory:
        directory_entry.delete(0, 'end')
        directory_entry.insert(0, directory)

# GUI erstellen
root = Tk()
root.title("Dateisuche mit OpenAI")
root.geometry("600x500")

# Eingabefeld für die Suchanfrage
query_label = Label(root, text="Suchanfrage:")
query_label.pack(pady=5)
query_entry = Entry(root, width=50)
query_entry.pack(pady=5)

# Eingabefeld für das Verzeichnis
directory_label = Label(root, text="Verzeichnis:")
directory_label.pack(pady=5)
directory_entry = Entry(root, width=50)
directory_entry.pack(pady=5)

# Button zum Auswählen des Verzeichnisses
select_button = Button(root, text="Durchsuchen...", command=select_directory)
select_button.pack(pady=5)

# Suchbutton
search_button = Button(root, text="Suchen", command=start_search)
search_button.pack(pady=10)

# Animation Label
animation_label = Label(root, text="")
animation_label.pack(pady=5)

# Ergebnisanzeige
result_text = Text(root, height=15, width=70)
result_text.pack(pady=10)

# Animation initialisieren
animation_frames = itertools.cycle(['|', '/', '-', '\\'])
searching = False

root.mainloop()