My hexdump in Python

hexdump.py

"""
hexdump in python

`python hexdump.py -h` to see usage
"""

from typing import *

CONTROL_CHARACTERS_REPRESENTATION_IN_CONTROL_PICTURE: Final[dict[int, str]] = {
	0: '\N{Symbol For Null}',
	1: '\N{Symbol For Start of Heading}',
	2: '\N{Symbol For Start of Text}',
	3: '\N{Symbol For End of Text}',
	4: '\N{Symbol For End of Transmission}',
	5: '\N{Symbol For Enquiry}',
	6: '\N{Symbol For Acknowledge}',
	7: '\N{Symbol For Bell}',
	8: '\N{Symbol For Backspace}',
	9: '\N{Symbol For Horizontal Tabulation}',
	10: '\N{Symbol For Line Feed}',
	11: '\N{Symbol For Vertical Tabulation}',
	12: '\N{Symbol For Form Feed}',
	13: '\N{Symbol For Carriage Return}',
	14: '\N{Symbol For Shift Out}',
	15: '\N{Symbol For Shift In}',
	16: '\N{Symbol For Data Link Escape}',
	17: '\N{Symbol For Device Control One}',
	18: '\N{Symbol For Device Control Two}',
	19: '\N{Symbol For Device Control Three}',
	20: '\N{Symbol For Device Control Four}',
	21: '\N{Symbol For Negative Acknowledge}',
	22: '\N{Symbol For Synchronous Idle}',
	23: '\N{Symbol For End of Transmission Block}',
	24: '\N{Symbol For Cancel}',
	25: '\N{Symbol For End of Medium}',
	26: '\N{Symbol For Substitute}',
	27: '\N{Symbol For Escape}',
	28: '\N{Symbol For File Separator}',
	29: '\N{Symbol For Group Separator}',
	30: '\N{Symbol For Record Separator}',
	31: '\N{Symbol For Unit Separator}',
	127: '\N{Symbol For Delete}',
}


def hexdump(filepath: str, use_control_picture: bool = False) -> None:
	"""
	Print the file in a hexadecimal way -- with some more information.
	
	It just does `open(filepath, 'rb')` to open the file.
	
	:param filepath: The same rule of doing `open(filepath)` in Python.
	:param use_control_picture: Use Unicode Control Pictures to represent ASCII control characters.
	:return: None, it just prints.
	"""
	
	# Expected output:
	# [00000] 0000:  00 00 00 00 00 00 00 00    00 00 00 00 00 00 00 00  |................|
	
	with open(filepath, 'rb') as file:
		byte_count: int = 0
		row_flag: bool = True
		print()
		print('    Offset                            Byte                               ASCII')
		print('  Dec    Hex   0  1  2  3  4  5  6  7     8  9  A  B  C  D  E  F    0123456789ABCDEF')
		print('-' * 85)
		while row_flag:
			print(f"[{byte_count:0>5}] {hex(byte_count)[2:].upper():0>4}:  ", end='')
			row_in_ascii: str = ''
			for i in range(16):
				byte = file.read(1)
				if byte == b'':
					# Just hard-code, I don't want any trouble :(
					space_table: list[int] = [52, 49, 46, 43, 40, 37, 34, 31, 25, 22, 19, 16, 13, 10, 7, 4]
					print(" " * space_table[byte_count % 16], end='')
					row_flag = False
					break
				byte_count += 1
				print(byte.hex().upper(),
				      end=(' ' if byte_count % 8 != 0 else ('  ' if byte_count % 16 == 0 else '    ')))
				byte_as_int: int = int.from_bytes(byte)
				if 32 <= byte_as_int <= 126:  # Printable characters
					row_in_ascii += chr(byte_as_int)
				elif byte_as_int <= 127:  # Control characters
					if use_control_picture:
						row_in_ascii += CONTROL_CHARACTERS_REPRESENTATION_IN_CONTROL_PICTURE[byte_as_int]
					else:
						row_in_ascii += '.'
				else:
					row_in_ascii += '.'
			if row_in_ascii:
				print(f"|{row_in_ascii}|")
		if byte_count % 16 != 0:
			print(f"[{byte_count:0>5}] {hex(byte_count)[2:].upper():0>4}:")
	print()


if __name__ == '__main__':
	import argparse
	
	parser = argparse.ArgumentParser(description='Generate hex dump of a file')
	parser.add_argument('file', help='file path')
	parser.add_argument('-c', '--control-picture',
	                    help='use Unicode control pictures to represent ASCII control characters',
	                    action='store_true')
	args = parser.parse_args()
	hexdump(filepath=args.file,
	        use_control_picture=args.control_picture,
	        )