Spaces:
Running
Running
| import json | |
| import os | |
| import re | |
| from deep_translator import GoogleTranslator | |
| def process_json_files(start, end, step, length=0, tlang="en", spaces_include=False, strip_in_braces=True, strip_diacritics=True): | |
| base_path = "texts" # Angepasster Pfad zum Verzeichnis der Dateien | |
| print(f"\nAnalyzing Books from {start} to {end}, step: {step}, length (0 is inf): {length}, \ninclude spaces: {spaces_include}, strip text in braces: {strip_in_braces}, strip diacritics: {strip_diacritics}") | |
| translator = GoogleTranslator(source='auto', target=tlang) # Setze den Übersetzer | |
| rc = 0 | |
| for i in range(start, end + 1): | |
| file_name = f"{base_path}/{i:02}.json" # Format file names, e.g., 01, 02, ..., 39 | |
| try: | |
| with open(file_name, 'r', encoding='utf-8') as file: | |
| data = json.load(file) | |
| text_blocks = data["text"] | |
| # Combine all lines in a book into a single string | |
| full_text = "" | |
| for block in text_blocks: | |
| for line in block: | |
| full_text += line | |
| #print(full_text) | |
| clean_text = full_text | |
| if strip_in_braces: | |
| clean_text = re.sub(r"\[.*?\]", "", clean_text, flags=re.DOTALL) | |
| else: | |
| clean_text = clean_text.replace("[", "").replace("]", "") | |
| if strip_diacritics: | |
| clean_text = re.sub(r"[^\u05D0-\u05EA ]+", "", clean_text) # Präzisiert auf U+05D0 bis U+05EA und " " | |
| if not spaces_include: | |
| clean_text = clean_text.replace(" ", "") # Remove spaces | |
| if " " in clean_text: | |
| print("Error: there are still spaces in the text") | |
| else: | |
| clean_text = clean_text.replace(" ", " ") # Remove spaces | |
| clean_text = clean_text.replace(" ", " ") # Remove spaces | |
| clean_text = clean_text.replace(" ", " ") # Remove spaces | |
| if " " in clean_text: | |
| print("Error: there are still double spaces in the text") | |
| #print(clean_text) | |
| if length != 0: | |
| selected_characters = clean_text[step - 1::step][:length] # Start at n-th character and select every nth character | |
| else: | |
| selected_characters = clean_text[step - 1::step] # Start at n-th character and select every nth character | |
| # Übersetzen des extrahierten Texts | |
| translated_text = translator.translate(''.join(selected_characters)) | |
| if selected_characters != "": | |
| rc += 1 | |
| print("\n" + str(rc) + ". Result, " + "Book "+ str(i) + " - " + data["title"] + "\n") | |
| print(f"HE:==> {selected_characters}") | |
| print(f"{tlang.upper()}:==> {translated_text}") # Output results or further processing | |
| except FileNotFoundError: | |
| print(f"File {file_name} not found.") | |
| except json.JSONDecodeError: | |
| print(f"File {file_name} could not be read as JSON.") | |
| except KeyError: | |
| print(f"Expected key 'text' is missing in {file_name}.") | |
| # Beispiel: n = 3, Dateien von 01 bis 39 | |
| process_json_files(start=1, end=1, step=6, length=1, tlang="en", spaces_include=False, strip_in_braces=True, strip_diacritics=True) | |
| print("\n ^^ Test: this output should be with any parameters: HE:==> ת") | |
| process_json_files(start=1, end=39, step=8240, tlang="en", spaces_include=False, strip_in_braces=True, strip_diacritics=True) | |