Spaces:
Running
on
T4
Running
on
T4
| # Book_Ingestion_Lib.py | |
| ######################################### | |
| # Library to hold functions for ingesting book files.# | |
| # | |
| #################### | |
| # Function List | |
| # | |
| # 1. ingest_text_file(file_path, title=None, author=None, keywords=None): | |
| # 2. | |
| # | |
| # | |
| #################### | |
| # Import necessary libraries | |
| import os | |
| import re | |
| from datetime import datetime | |
| import logging | |
| # Import Local | |
| from SQLite_DB import add_media_with_keywords | |
| ####################################################################################################################### | |
| # Function Definitions | |
| # | |
| # Ingest a text file into the database with Title/Author/Keywords | |
| def extract_epub_metadata(content): | |
| title_match = re.search(r'Title:\s*(.*?)\n', content) | |
| author_match = re.search(r'Author:\s*(.*?)\n', content) | |
| title = title_match.group(1) if title_match else None | |
| author = author_match.group(1) if author_match else None | |
| return title, author | |
| def ingest_text_file(file_path, title=None, author=None, keywords=None): | |
| try: | |
| with open(file_path, 'r', encoding='utf-8') as file: | |
| content = file.read() | |
| # Check if it's a converted epub and extract metadata if so | |
| if 'epub_converted' in (keywords or ''): | |
| extracted_title, extracted_author = extract_epub_metadata(content) | |
| title = title or extracted_title | |
| author = author or extracted_author | |
| # If title is still not provided, use the filename without extension | |
| if not title: | |
| title = os.path.splitext(os.path.basename(file_path))[0] | |
| # If author is still not provided, set it to 'Unknown' | |
| if not author: | |
| author = 'Unknown' | |
| # If keywords are not provided, use a default keyword | |
| if not keywords: | |
| keywords = 'text_file,epub_converted' | |
| else: | |
| keywords = f'text_file,epub_converted,{keywords}' | |
| # Add the text file to the database | |
| add_media_with_keywords( | |
| url=file_path, | |
| title=title, | |
| media_type='document', | |
| content=content, | |
| keywords=keywords, | |
| prompt='No prompt for text files', | |
| summary='No summary for text files', | |
| transcription_model='None', | |
| author=author, | |
| ingestion_date=datetime.now().strftime('%Y-%m-%d') | |
| ) | |
| return f"Text file '{title}' by {author} ingested successfully." | |
| except Exception as e: | |
| logging.error(f"Error ingesting text file: {str(e)}") | |
| return f"Error ingesting text file: {str(e)}" | |
| def ingest_folder(folder_path, keywords=None): | |
| results = [] | |
| for filename in os.listdir(folder_path): | |
| if filename.lower().endswith('.txt'): | |
| file_path = os.path.join(folder_path, filename) | |
| result = ingest_text_file(file_path, keywords=keywords) | |
| results.append(result) | |