import numpy as np
import os

def get_unique_chars(file_path):
    """
    Reads a wafer map file and returns all unique characters found,
    excluding whitespace.
    """
    unique_chars = set()
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            lines = file.readlines()
            # Filter out empty lines before calculating max_length
            non_empty_lines = [line.strip() for line in lines if line.strip()]
            if not non_empty_lines:
                return []
            
            max_length = max(len(line) for line in non_empty_lines)

            for line in non_empty_lines:
                # Process only lines that have the max length
                if len(line) == max_length:
                    for char in line:
                        if char != ' ':
                            unique_chars.add(char)
        return sorted(list(unique_chars))
    except Exception as e:
        print(f"Error reading unique chars: {e}")
        return []

def read_wafer_map(file_path, char_to_bin_mapping):
    """
    Reads a wafer map file and converts it to a numerical numpy array based on
    the provided character-to-bin mapping.
    """
    wafer_map = []
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            lines = file.readlines()
            non_empty_lines = [line.strip() for line in lines if line.strip()]
            if not non_empty_lines:
                return np.array([])

            max_length = max(len(line) for line in non_empty_lines)

            for line in non_empty_lines:
                # Pad the line to ensure uniform length for all processed rows
                padded_line = line.ljust(max_length, ' ')
                row = [char_to_bin_mapping.get(char, -1) for char in padded_line]
                wafer_map.append(row)
        
        return np.array(wafer_map)
    except Exception as e:
        print(f"Error reading wafer map: {e}")
        return np.array([])

def save_wafer_map(wafer_map, bin_to_char_mapping, file_path):
    """
    Saves the numerical wafer map back to a character-based file.
    """
    with open(file_path, 'w', encoding='utf-8') as file:
        for row in wafer_map:
            file.write(''.join([bin_to_char_mapping.get(int(bin_code), ' ') for bin_code in row]) + '\n')