DATA_A = "2021Census_T24A_AUST_LGA.csv"
DATA_B = "2021Census_T24B_AUST_LGA.csv"
DATA_C = "2021Census_T24C_AUST_LGA.csv"
DATA_D = "2021Census_T24D_AUST_LGA.csv"

DATA_A = "2021Census_T24A_AUST_STE.csv"
DATA_B = "2021Census_T24B_AUST_STE.csv"
# Merge files into list of unique cells
def merge_file_parts(filenames):
    merged_file = []
    for file_index in range(len(filenames)):
        file = open(filenames[file_index], "r").readlines()
        # Split the row into columns
        for row in range(len(file)):
            cols_in_row = file[row].split(",")
            # Remove any newlines from cells
            for column in range(len(cols_in_row)):
                cols_in_row[column] = cols_in_row[column].strip()
            file[row] = cols_in_row
        # The FIRST file in the list (DATA_A)
        if file_index == 0:
            # `merged_file` is empty, this is the first file we are processing
            merged_file = file
        else:
            for row in range(len(file)):
                # Extend with everything in row except state codes
                merged_file[row].extend(file[row][1:])
    return merged_file

# First step: clean & merge data from multiple files

print(categories)

# print(categories)
parts = merge_file_parts([DATA_A, DATA_B])
print(parts[-2])