Spaces:
Running
Running
| import logging | |
| import json | |
| import os | |
| import re | |
| from deep_translator import GoogleTranslator | |
| from gematria import calculate_gematria | |
| import math | |
| import csv | |
| # Configure the logger | |
| # You can uncomment the next line to enable debugging logs | |
| # logging.basicConfig(level=logging.DEBUG, format='%(levelname)s:%(message)s') | |
| logger = logging.getLogger(__name__) | |
| def process_json_files(start=40, end=66, step=1, rounds="1", length=0, tlang="en", strip_spaces=True, | |
| strip_in_braces=True, strip_diacritics=True, translate=False): | |
| """ | |
| Process a CSV file containing biblical texts and perform various text manipulations. | |
| Parameters: | |
| - start (int): Starting book number. | |
| - end (int): Ending book number. | |
| - step (int): Step value for character selection. | |
| - rounds (str): Comma-separated string of round values (can include floats). | |
| - length (int): Maximum length of the result text. | |
| - tlang (str): Target language for translation. | |
| - strip_spaces (bool): Whether to remove spaces from the text. | |
| - strip_in_braces (bool): Whether to remove text within braces. | |
| - strip_diacritics (bool): Whether to remove diacritics from the text. | |
| - translate (bool): Whether to translate the result text. | |
| Returns: | |
| - list: A list of dictionaries containing processed data or error messages. | |
| """ | |
| file_name = "texts/bible/OpenGNT_version3_3.csv" | |
| translator = GoogleTranslator(source='auto', target=tlang) if translate else None | |
| results = [] | |
| # Dictionary for the 27 books of the New Testament (English names) | |
| nt_books = { | |
| 40: "Matthew", | |
| 41: "Mark", | |
| 42: "Luke", | |
| 43: "John", | |
| 44: "Acts", | |
| 45: "Romans", | |
| 46: "1 Corinthians", | |
| 47: "2 Corinthians", | |
| 48: "Galatians", | |
| 49: "Ephesians", | |
| 50: "Philippians", | |
| 51: "Colossians", | |
| 52: "1 Thessalonians", | |
| 53: "2 Thessalonians", | |
| 54: "1 Timothy", | |
| 55: "2 Timothy", | |
| 56: "Titus", | |
| 57: "Philemon", | |
| 58: "Hebrews", | |
| 59: "James", | |
| 60: "1 Peter", | |
| 61: "2 Peter", | |
| 62: "1 John", | |
| 63: "2 John", | |
| 64: "3 John", | |
| 65: "Jude", | |
| 66: "Revelation" | |
| } | |
| try: | |
| with open(file_name, 'r', encoding='utf-8') as file: | |
| reader = csv.DictReader(file, delimiter='\t') | |
| book_texts = {} | |
| current_book = None | |
| for row_num, row in enumerate(reader, start=1): | |
| try: | |
| # Parse the book number from '〔Book｜Chapter｜Verse〕' field | |
| book_field = row['〔Book｜Chapter｜Verse〕'] | |
| book_str = book_field.split('｜')[0] # e.g., '〔40' | |
| book_num_str = book_str.lstrip('〔') # Remove leading '〔' | |
| book = int(book_num_str) | |
| if book < start or book > end: | |
| continue | |
| if current_book != book: | |
| current_book = book | |
| book_texts[book] = "" | |
| # Parse the Greek text from '〔OGNTk｜OGNTu｜OGNTa｜lexeme｜rmac｜sn〕' field | |
| greek_field = row['〔OGNTk｜OGNTu｜OGNTa｜lexeme｜rmac｜sn〕'] | |
| # Extract the first part before '〔' and split by '｜' | |
| if '〔' in greek_field: | |
| greek_text = greek_field.split('〔')[1] | |
| greek_text = greek_text.split('｜')[0] | |
| else: | |
| greek_text = greek_field.split('｜')[0] | |
| book_texts[book] += greek_text + " " | |
| except (KeyError, IndexError, ValueError) as e: | |
| logger.error(f"Error parsing row {row_num}: {e}") | |
| continue # Skip this row and continue | |
| for book, full_text in book_texts.items(): | |
| logger.debug(f"Processing book {book}") | |
| clean_text = full_text | |
| if strip_in_braces: | |
| clean_text = re.sub(r"\[.*?\]|\{.*?\}|\<.*?\>", "", clean_text, flags=re.DOTALL) | |
| if strip_diacritics: | |
| # Adjusted regex for Greek diacritics | |
| clean_text = re.sub(r"[^\u0370-\u03FF\u1F00-\u1FFF ]+", "", clean_text) | |
| # Optionally, remove specific diacritics or punctuation if needed | |
| # clean_text = re.sub(r'[additional patterns]', '', clean_text) | |
| # Normalize spaces | |
| clean_text = clean_text.replace("\n\n ", " ") | |
| clean_text = clean_text.replace("\n", " ") | |
| clean_text = re.sub(r'\s+', ' ', clean_text).strip() | |
| if strip_spaces: | |
| clean_text = clean_text.replace(" ", "") | |
| text_length = len(clean_text) | |
| logger.debug(f"Clean text for book {book}: Length = {text_length}") | |
| if text_length == 0: | |
| logger.warning(f"No text available for book {book} after cleaning.") | |
| continue # Skip processing if there's no text | |
| try: | |
| rounds_list = list(map(float, rounds.split(','))) # Allow floats | |
| except ValueError as e: | |
| logger.error(f"Invalid rounds parameter: {e}") | |
| return [{"error": f"Invalid rounds parameter: {e}"}] | |
| result_text = "" | |
| for r in rounds_list: | |
| abs_r = abs(r) | |
| # Determine the number of full passes and the remainder. | |
| full_passes = math.floor(abs_r) | |
| remainder = abs_r - full_passes | |
| # Base number of characters per pass | |
| base_chars = text_length // step | |
| if base_chars == 0: | |
| if abs_r > 1: # Changed from >=1 to >1 | |
| # When step > text_length and rounds >1, pick 1 character per full pass | |
| chars_per_full_pass = 1 | |
| logger.debug(f"Book {book}: step > text_length ({step} > {text_length}), selecting 1 character per full pass.") | |
| else: | |
| # No characters to pick | |
| chars_per_full_pass = 0 | |
| logger.debug(f"Book {book}: step > text_length ({step} > {text_length}) and rounds <=1, no characters selected.") | |
| # For remainder, since base_chars=0, no remainder characters | |
| chars_for_remainder = 0 | |
| else: | |
| # Normal case | |
| chars_per_full_pass = base_chars | |
| chars_for_remainder = math.floor(base_chars * remainder) # Partial pass | |
| logger.debug(f"Book {book}: Normal case, chars_per_full_pass = {chars_per_full_pass}, chars_for_remainder = {chars_for_remainder}") | |
| if r > 0: | |
| current_index = (step - 1) % text_length | |
| direction = 1 | |
| else: | |
| current_index = (text_length - step) % text_length | |
| direction = -1 | |
| pass_result = "" | |
| # Full passes, keep only the last pass | |
| for pass_num in range(1, full_passes + 1): | |
| current_pass_chars = "" | |
| for _ in range(chars_per_full_pass): | |
| if chars_per_full_pass == 0: | |
| break | |
| current_pass_chars += clean_text[current_index] | |
| current_index = (current_index + direction * step) % text_length | |
| # Keep only the last full pass | |
| if pass_num == full_passes: | |
| pass_result = current_pass_chars | |
| logger.debug(f"Book {book}: Pass {pass_num}, pass_result = {pass_result}") | |
| # Remainder pass for fractional rounds | |
| if remainder > 0 and chars_for_remainder > 0: | |
| current_pass_chars = "" | |
| for _ in range(chars_for_remainder): | |
| current_pass_chars += clean_text[current_index] | |
| current_index = (current_index + direction * step) % text_length | |
| pass_result += current_pass_chars | |
| logger.debug(f"Book {book}: Remainder pass_result = {pass_result}") | |
| # Handle cases where step > text_length and chars_per_full_pass=1 | |
| if base_chars == 0 and chars_per_full_pass == 1 and full_passes > 0: | |
| # pass_result already contains the last character picked | |
| pass | |
| elif base_chars == 0 and chars_per_full_pass == 0 and full_passes > 0: | |
| # When no characters are picked, skip appending | |
| pass | |
| result_text += pass_result | |
| logger.debug(f"Result text for book {book}: {result_text}") | |
| if length != 0: | |
| result_text = result_text[:length] | |
| logger.debug(f"Book {book}: Result text truncated to length {length}.") | |
| # Translate the result text if required | |
| try: | |
| translated_text = translator.translate(result_text) if translator and result_text else "" | |
| except Exception as e: | |
| logger.error(f"Book {book}: Translation error: {e}") | |
| translated_text = "" | |
| # Calculate the Gematria sum | |
| try: | |
| result_sum = calculate_gematria(result_text) | |
| except Exception as e: | |
| logger.error(f"Book {book}: Gematria calculation error: {e}") | |
| result_sum = None | |
| if result_text: | |
| result = { | |
| 'book': f"Bible {book}.", | |
| 'title': nt_books.get(book, "Unknown Book"), | |
| 'result_text': result_text, | |
| 'result_sum': result_sum, | |
| 'translated_text': translated_text, | |
| 'source_language': 'el' | |
| } | |
| results.append(result) | |
| except FileNotFoundError: | |
| logger.error(f"File {file_name} not found.") | |
| results.append({"error": f"File {file_name} not found."}) | |
| except Exception as e: | |
| logger.error(f"An unexpected error occurred: {e}") | |
| results.append({"error": f"An unexpected error occurred: {e}"}) | |
| return results if results else None | |
| # Tests | |
| test_results = [ | |
| (process_json_files(40,40,386,rounds="1,0.5,-1,-0.5"), "τωιεοννναυοοαμπυρααυοιξοηαϲοιιωομκνοοουομρυοιεχοοδεαλαννοτοκϲααυϲϲτεαδαϲαιεευαιηαεηαμαλκμαιακιγνμυνετνυυθθεγιεδρεαοαντηοκεοατϲνπναολαεοοφεηεϲωμκουμερρυοϲαοοαϲλτιηιωδυνϲυτυιχοονεαηωντολθβοτεαιαυοηετιτεαννυεινϲεενωκωξρυρηρνϲξεαγεαϲατωιεοννναυοοαμπυρααυοιξοηαϲοιιωομκνοοουομρυοιεχοοδεαλαννοτοκϲααυϲϲτεαδαϲαιεευαιηαεηαμαλκμαιακιγνμυνετνυυθθεγιεδρεαοϲτοαϲωθειιυνδνδξλονυταολαϲαττμτννοερτεοροανιεκτεεαιιϲωεαμϲωικμτποκϲϲιορϲπμοκαιουτωτδοωαξεαγωεφτωυπμαλυττταεομττλυαεπατονεαξτομυχαωηνυοβωπτυυκξαπιτααπυενεροοτϲαααυηοανηλταιθεαντινοιλκιβπγοδαιοηωαδαετακυϲοηυουαυνωαεαοττυαεεωτανεκβγεϲτοαϲωθειιυνδνδξλονυταολαϲαττμτννοερτεοροανιεκτεεαιιϲωεαμϲωικμτποκϲϲιορϲπμοκαιουτωτδοωαξεαγωεφτωυπμαλυττταεομττλυαε"), | |
| (process_json_files(40,40,386,rounds="1,-1"), "τωιεοννναυοοαμπυρααυοιξοηαϲοιιωομκνοοουομρυοιεχοοδεαλαννοτοκϲααυϲϲτεαδαϲαιεευαιηαεηαμαλκμαιακιγνμυνετνυυθθεγιεδρεαοαντηοκεοατϲνπναολαεοοφεηεϲωμκουμερρυοϲαοοαϲλτιηιωδυνϲυτυιχοονεαηωντολθβοτεαιαυοηετιτεαννυεινϲεενωκωξρυρηρνϲξεαγεαϲαϲτοαϲωθειιυνδνδξλονυταολαϲαττμτννοερτεοροανιεκτεεαιιϲωεαμϲωικμτποκϲϲιορϲπμοκαιουτωτδοωαξεαγωεφτωυπμαλυττταεομττλυαεπατονεαξτομυχαωηνυοβωπτυυκξαπιτααπυενεροοτϲαααυηοανηλταιθεαντινοιλκιβπγοδαιοηωαδαετακυϲοηυουαυνωαεαοττυαεεωτανεκβγε"), | |
| #(process_json_files(1, 1, 21, rounds="3", length=0), ""), | |
| #(process_json_files(1, 1, 22, rounds="1", length=0), ""), | |
| #(process_json_files(1, 1, 22, rounds="3", length=0), ""), | |
| #(process_json_files(1, 1, 23, rounds="3", length=0), ""), | |
| #(process_json_files(1, 1, 11, rounds="1", length=0), ""), | |
| #(process_json_files(1, 1, 2, rounds="1", length=0), ""), | |
| #(process_json_files(1, 1, 23, rounds="1", length=0), None), # Expect None, when no results | |
| #(process_json_files(1, 1, 23, rounds="-1", length=0), None), # Expect None, when no results | |
| #(process_json_files(1, 1, 22, rounds="-1", length=0), ""), | |
| #(process_json_files(1, 1, 22, rounds="-2", length=0), ""), | |
| #(process_json_files(1, 1, 1, rounds="-1", length=0), ""), # Reversed Hebrew alphabet | |
| #(process_json_files(1, 1, 1, rounds="1,-1", length=0), ""), # Combined rounds | |
| #(process_json_files(1, 1, 22, rounds="1,-1", length=0, average_compile=True), ""), # average compile test (400+1) / 2 = math.ceil(200.5)=201=200+1="רא" | |
| ] | |
| all_tests_passed = True | |
| for result, expected in test_results: | |
| if expected is None: # Check if no result is expected | |
| if not result: | |
| logger.warning(f"Test passed: Expected no results, got no results.") | |
| else: | |
| logger.error(f"Test failed: Expected no results, but got: {result}") | |
| all_tests_passed = False | |
| else: | |
| # Check if result is not empty before accessing elements | |
| if result: | |
| result_text = result[0]['result_text'] | |
| if result_text == expected: | |
| logger.warning(f"Test passed: Expected '{expected}', got '{result_text}'") | |
| else: | |
| logger.error(f"Test failed: Expected '{expected}', but got '{result_text}'") | |
| all_tests_passed = False | |
| else: | |
| logger.error(f"Test failed: Expected '{expected}', but got no results") | |
| all_tests_passed = False | |
| if all_tests_passed: | |
| logger.info("All round tests passed.") | |