Judge Dredd: Dredd Vs. Death Extractors

parseSound.py

import os
from struct import *
import struct

def bread(filename):
	with open(filename, 'rb') as f:
		return f.read(-1)

def parseSoundFile(filename):
	byteData = bread(filename)
	byteData = byteData[36:]
	print(f"Extracting files from: {filename}")
	bTest = False
	while byteData[0:4] != b'':
		index = 0
		while(chr(byteData[index]) != '\\'): index += 1

		totalReadData = 0
		wavName = ""

		while(byteData[index] != 0):
			wavName += chr(byteData[index])
			index += 1

		# For SOME reason there's just a .INI file in this exact same file, for now we just return
		if(".wav" not in wavName): 
			byteData = byteData[index:]
			bTest = True
			continue

		while(byteData[index] == 0): index += 1
		totalReadData += index
		wavName = "./extract" + wavName.replace("\\","/")

		print(f"Reading .WAV: {wavName}")
		byteData = byteData[totalReadData:]


		fileLength = struct.unpack('<I', byteData[4:8])[0]

		print(f".WAV Length: {fileLength}")
		if not(os.path.exists(os.path.dirname(wavName))): os.makedirs(os.path.dirname(wavName))

		outputFile = open(wavName, 'wb+')
		outputFile.write(byteData[0:fileLength+4])

		byteData = byteData[fileLength+4+32:]

parseSoundFile("./MPSnds.asr")
parseSoundFile("./en_gmsnd.asr")

parseText.py

import os
from struct import *
import struct

magic = b'ASURA	 '

def bread(filename):
	with open(filename, 'rb') as f:
		bdata = []
		while True:
			bytes = f.read(1)
			if bytes == b'':
				break
			else:
				bdata.append(struct.unpack('b', bytes)[0]) # 1byte
	hdata = [hex(x) for x in bdata]
	return struct.pack("b"*len(bdata), *bdata), hdata

def parseFile(filename):
	outputFile = open(filename + ".txt", 'w+', encoding="utf-16-be")
	byteData = bread(filename)[0]

	magicNumber = byteData[0:8]
	print(f"Magic: {magicNumber}")
	if(magicNumber != b'Asura   '): return "Magic Number does not match..."

	fileType = byteData[8:12]
	print(f"File Type: {fileType} ({chr(fileType[0])})")

	if(fileType[1:] == b'TXT'):
		# Handle the byte skipping
		if(chr(fileType[0]) == 'L' or chr(fileType[0]) == 'H'): byteData = byteData[28:]
		elif(chr(fileType[0]) == 'P'): byteData = byteData[44:]

		print("\n")
		i = 0
		# Read strings until we're at the end of file (aka just 16 (or 9 if its an HTXT) NULL bytes)
		while (byteData != b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'):
			if(fileType == b'HTXT' and byteData[0:10] == b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'): break
			if(fileType == b'HTXT'):
				print(f"String {hex(byteData[0])}")
				byteData = byteData[4:]
			consumed = 0
			stringLength = struct.unpack('H', byteData[0:2])[0]
			print(f"Test: {[hex(x) for x in byteData[0:10]]}")
			print(f"Parsing string of length: {hex(stringLength)} ({stringLength * 2})")
			byteData = byteData[3:]
			consumed += 1

			output = byteData[:stringLength*2].decode('utf-16-be').rstrip('\x00')

			print(f"Total String: \"{output}\"")
			outputFile.write(output + "\n")
			consumed += (stringLength * 2)
			print(f"Complete reading string #{i}")
			print(f"Consumed {consumed} bytes...\n")
			# For some reason the HTXT files have a few extra bytes in between each string
			byteData = byteData[consumed:]
			i += 1
	return f"Done parsing: {filename}"


print(parseFile("English.asr"))
print(parseFile("./l_text/names/n_En.asr"))
print(parseFile("./l_text/control/c_En.asr"))
print(parseFile("./l_text/scripted/s_En.asr"))
print(parseFile("./l_text/tannoy/t_En.asr"))
print(parseFile("./CSText/CS_En.asr"))