import logging logger = logging.getLogger(__name__) import json import os import re from deep_translator import GoogleTranslator from gematria import calculate_gematria import math # Hebrew gematria values for relevant characters gematria_values = { 'א': 1, 'ב': 2, 'ג': 3, 'ד': 4, 'ה': 5, 'ו': 6, 'ז': 7, 'ח': 8, 'ט': 9, 'י': 10, 'כ': 20, 'ך': 500, 'ל': 30, 'מ': 40, 'ם': 600, 'נ': 50, 'ן': 700, 'ס': 60, 'ע': 70, 'פ': 80, 'ף': 800, 'צ': 90, 'ץ': 900, 'ק': 100, 'ר': 200, 'ש': 300, 'ת': 400 } # Reverse dictionary for converting gematria values back to Hebrew characters reverse_gematria_values = {v: k for k, v in gematria_values.items()} # Function to convert a Hebrew string to its gematria values def string_to_gematria(s): return [gematria_values.get(char, 0) for char in s] # Handle characters not in the dictionary # Function to convert a single gematria value to Hebrew characters def gematria_to_string(value): result = [] for val in sorted(reverse_gematria_values.keys(), reverse=True): while value >= val: result.append(reverse_gematria_values[val]) value -= val return ''.join(result) # Function to calculate the average gematria values of corresponding characters and convert them to Hebrew characters def average_gematria(str1, str2): # Convert strings to gematria values gematria1 = string_to_gematria(str1) gematria2 = string_to_gematria(str2) # Handle cases where strings have different lengths by padding with 0s max_len = max(len(gematria1), len(gematria2)) gematria1.extend([0] * (max_len - len(gematria1))) gematria2.extend([0] * (max_len - len(gematria2))) # Calculate the average of corresponding gematria values and apply math.ceil average_gematria_values = [math.ceil((g1 + g2) / 2) for g1, g2 in zip(gematria1, gematria2)] # Convert the average gematria values back to Hebrew characters return ''.join(gematria_to_string(val) for val in average_gematria_values) from deep_translator import GoogleTranslator import os import re import csv def process_json_files(start=1, end=66, step=1, rounds="1", length=0, tlang="en", strip_spaces=True, strip_in_braces=True, strip_diacritics=True, average_compile=False): file_name = "texts/bible/OpenGNT_version3_3.csv" translator = GoogleTranslator(source='auto', target=tlang) results = [] # Dictionary für die 27 Bücher des Neuen Testaments (Englische Namen) 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 in reader: book = int(row['〔Book｜Chapter｜Verse〕'].split('｜')[0][1:]) if book < start or book > end: continue if current_book != book: current_book = book book_texts[book] = "" greek_text = row['〔OGNTk｜OGNTu｜OGNTa｜lexeme｜rmac｜sn〕'] greek_text = greek_text.split('〔')[1] greek_text = greek_text.split('｜')[0] book_texts[book] += greek_text + " " 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: clean_text = re.sub(r"[^\u0370-\u03FF\u1F00-\u1FFF ]+", "", clean_text) if strip_spaces: clean_text = clean_text.replace(" ", "") else: clean_text = clean_text.replace(" ", " ") clean_text = clean_text.replace(" ", " ") clean_text = clean_text.replace(" ", " ") text_length = len(clean_text) selected_characters_per_round = {} for round_num in map(int, rounds.split(',')): if not (round_num == 1 and step > text_length) and not (round_num == -1 and step > text_length): if round_num > 0: current_position = step - 1 else: current_position = text_length - 1 if step == 1 else text_length - step completed_rounds = 0 selected_characters = "" while completed_rounds < abs(round_num): selected_characters += clean_text[current_position % text_length] current_position += step if round_num > 0 else -step if (round_num > 0 and current_position >= text_length * (completed_rounds + 1)) or \ (round_num < 0 and current_position < 0): completed_rounds += 1 selected_characters_per_round[round_num] = selected_characters if average_compile and len(selected_characters_per_round) > 1: result_text = "" keys = sorted(selected_characters_per_round.keys()) for i in range(len(keys) - 1): result_text = average_gematria(selected_characters_per_round[keys[i]], selected_characters_per_round[keys[i+1]]) else: result_text = ''.join(selected_characters_per_round.values()) if length != 0: result_text = result_text[:length] translated_text = translator.translate(result_text) if result_text else "" result_sum = calculate_gematria(result_text) if result_text: logger.debug(f"Result for book {book}: {result_text}") result = { 'book': f"Bible {book}.", # Use the correct 'book' variable 'title': nt_books.get(book, "Unknown Book"), # Get book name from dictionary 'result_text': result_text, 'result_sum': result_sum, # Make sure result_sum is calculated correctly 'translated_text': translated_text } results.append(result) except FileNotFoundError: results.append({"error": f"File {file_name} not found."}) return results # Tests test_results = [ #(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.info(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'] result_text = None if result_text == expected: logger.info(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.")