Spaces:
Sleeping
Sleeping
| 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" | |
| translator = GoogleTranslator(source='auto', target=tlang) | |
| results = [] | |
| for i in range(start, end + 1): | |
| file_name = f"{base_path}/{i:02}.json" | |
| try: | |
| with open(file_name, 'r', encoding='utf-8') as file: | |
| data = json.load(file) | |
| text_blocks = data["text"] | |
| full_text = "" | |
| for block in text_blocks: | |
| full_text += ' '.join(block) | |
| clean_text = full_text | |
| if strip_in_braces: | |
| clean_text = re.sub(r"\[.*?\]", "", clean_text, flags=re.DOTALL) | |
| if strip_diacritics: | |
| clean_text = re.sub(r"[^\u05D0-\u05EA ]+", "", clean_text) | |
| if not spaces_include: | |
| clean_text = clean_text.replace(" ", "") | |
| if length != 0: | |
| selected_characters = clean_text[step - 1::step][:length] | |
| else: | |
| selected_characters = clean_text[step - 1::step] # If length is 0, select all characters from step | |
| translated_text = translator.translate(''.join(selected_characters)) | |
| if selected_characters != "": | |
| results.append({ | |
| "book": i, | |
| "title": data["title"], | |
| "original_text": selected_characters, | |
| "translated_text": translated_text | |
| }) | |
| except FileNotFoundError: | |
| results.append({"error": f"File {file_name} not found."}) | |
| except json.JSONDecodeError: | |
| results.append({"error": f"File {file_name} could not be read as JSON."}) | |
| except KeyError: | |
| results.append({"error": f"Expected key 'text' is missing in {file_name}."}) | |
| return results | |