Files
wfrp-4e-de/python/find_translated_scripts.py
2025-05-15 23:03:43 +02:00

101 lines
4.5 KiB
Python

# -*- coding: utf-8 -*-
import os
import difflib
import chardet
import shutil
import urllib.parse
def normalize_line(line):
return line.strip()
def detect_encoding(file_path):
with open(file_path, "rb") as f:
raw_data = f.read()
result = chardet.detect(raw_data)
return result['encoding'] if result['encoding'] else 'utf-8'
def convert_to_utf8(file_path):
# Erkenne das aktuelle Encoding
encoding = detect_encoding(file_path)
if encoding.lower() == 'utf-8':
return file_path # Keine Konvertierung notwendig
# Konvertiere die Datei nach UTF-8
utf8_path = file_path + ".utf8"
with open(file_path, "rb") as f:
content = f.read().decode(encoding, errors="replace")
with open(utf8_path, "w", encoding="utf-8") as f:
f.write(content)
# Originaldatei löschen und umbenennen
print(f"Konvertiert: {file_path} ({encoding}) -> {utf8_path}")
os.remove(file_path)
shutil.move(utf8_path, file_path)
return file_path
def find_translated_files(original_folder, modified_folder, output_file):
original_files = {f for f in os.listdir(original_folder) if f.endswith(".js")}
modified_files = {f for f in os.listdir(modified_folder) if f.endswith(".js")}
common_files = original_files.intersection(modified_files)
translated_files = []
total_differences = 0
with open(output_file, "w", encoding="utf-8") as f:
for file_name in sorted(common_files):
original_path = os.path.abspath(os.path.join(original_folder, file_name))
modified_path = os.path.abspath(os.path.join(modified_folder, file_name))
# Dateien in UTF-8 konvertieren, falls notwendig
original_utf8 = convert_to_utf8(original_path)
modified_utf8 = convert_to_utf8(modified_path)
try:
with open(original_utf8, "r", encoding="utf-8") as orig_file, \
open(modified_utf8, "r", encoding="utf-8") as mod_file:
original_lines = [normalize_line(line) for line in orig_file if normalize_line(line)]
modified_lines = [normalize_line(line) for line in mod_file if normalize_line(line)]
diff = list(difflib.unified_diff(original_lines, modified_lines,
fromfile=original_path,
tofile=modified_path,
lineterm=""))
if diff:
num_changes = sum(1 for line in diff if line.startswith(("-", "+")) and not line.startswith(("---", "+++")))
translated_files.append((file_name, num_changes, original_path, modified_path))
total_differences += num_changes
# VS Code Diff Link erzeugen (absoluter Pfad, URL-enkodiert)
encoded_orig = urllib.parse.quote(original_path)
encoded_mod = urllib.parse.quote(modified_path)
vscode_diff_link = f"vscode://file/{encoded_orig}:0?diff={encoded_mod}:0"
# Header und Unterschiede in die Ausgabedatei schreiben
f.write(f"📝 Unterschiede in [{file_name}]({vscode_diff_link}) ({num_changes} Änderungen):\n")
f.write("\n".join(diff) + "\n\n")
except Exception as e:
print(f"Fehler beim Verarbeiten von {file_name}: {e}")
# Zusammenfassung am Ende der Datei hinzufügen (sortiert)
f.write("\n🔎 Zusammenfassung der Unterschiede (nach Anzahl der Änderungen sortiert):\n")
for file_name, count, orig_path, mod_path in sorted(translated_files, key=lambda x: x[1], reverse=True):
encoded_orig = urllib.parse.quote(orig_path)
encoded_mod = urllib.parse.quote(mod_path)
vscode_diff_link = f"vscode://file/{encoded_orig}:0?diff={encoded_mod}:0"
f.write(f"- [{file_name}]({vscode_diff_link}): {count} Änderungen\n")
f.write(f"\n📊 Gesamtanzahl der Änderungen: {total_differences}\n")
print(f"Prüfung abgeschlossen. {len(translated_files)} übersetzte Dateien gefunden.")
print(f"Ergebnis gespeichert in: {output_file}")
# Beispielpfade (kannst du anpassen)
original_folder = "original_scripts"
modified_folder = "modified_scripts"
output_file = "scripts_with_translation.md"
find_translated_files(original_folder, modified_folder, output_file)