import logging
logger = logging.getLogger(__name__)

import json
import os
import re
from deep_translator import GoogleTranslator
from gematria import calculate_gematria
import math

def process_json_files(start=1, end=10, step=1, rounds="1", length=0, tlang="en", strip_spaces=True,
                       strip_in_braces=True, strip_diacritics=True, average_compile=False, translate=False):
    base_path = "texts/rigveda"
    translator = GoogleTranslator(source='ne', target=tlang)
    results = []

    for i in range(start, end + 1):
        file_name = f"{base_path}/rigveda_mandala_{i:02}.json"
        #file_name = f"{base_path}/mahabharata_book_{i:02}.json"
        try:
            with open(file_name, 'r', encoding='utf-8') as file:
                data = json.load(file)
                # Concatenate all suktas for the current book
                full_text = ""
                for sukta in data:
                    full_text += sukta["text"] + " "  # Add a space between suktas

                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'[^\u0900-\u097F\s]', '', clean_text)  # Keep only Devanagari and whitespace
                    clean_text = re.sub(r'[\u0951-\u0954\u0964\u0965]+', '', clean_text)  # Remove pitch marks, Danda, Double Danda
                    clean_text = re.sub(r'[०१२३४५६७८९]+', '', clean_text)  # Remove Devanagari digits
                    clean_text = clean_text.replace(":", "")  # Remove colons
                    clean_text = clean_text.replace("?", "")  # Remove question marks
                    clean_text = clean_text.replace("!", "")  # Remove exclamation marks
                    # Add any other characters to remove here, e.g.:
                    clean_text = clean_text.replace("-", "") 
                    clean_text = clean_text.replace("'", "")
                    # ...


                clean_text = clean_text.replace("\n\n              ", " ")
                clean_text = clean_text.replace("\n", " ")
                clean_text = re.sub(r'\s+', ' ', clean_text)  # Condense multiple spaces


                if strip_spaces:
                    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 j in range(len(keys) - 1): # Changed i to j to avoid conflict with outer loop
                        result_text = average_gematria(selected_characters_per_round[keys[j]],
                                                        selected_characters_per_round[keys[j + 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 and translate else ""

                if result_text:
                    results.append({
                        "book": f"Rigveda {i}.",
                        "title": f"Mandala {i}",
                        "result_text": result_text,
                        "result_sum": calculate_gematria(result_text),
                        "translated_text": translated_text,
                        "source_language": "sa",
                    })

        except (FileNotFoundError, json.JSONDecodeError, KeyError) as e:
            results.append({"error": f"Error processing {file_name}: {e}"})

    return results