APEX2Dump.py

# Wunkolo<wunkolo@gmail.com> - 8/3/2018
# Dumps the archive files for Avalanche's APEX Engine 2 ".tab/.arc" file pairs
# Drag this python script into your "theHunter Call of the Wild\archives_win64\"
# directory and run the script. It will create some worker threads and dump each
# archive into its own folder. Each dumped file will be named using its file
# identifier(a numerical hash of the actual filename). Other games such as
# Just Cause 3 were mistakingly shipped with a .txt file that paired each hash
# with a full filename but they fixed up theHunter so all we got to work
# with are numerical file IDs

import mmap
import os
import struct
from multiprocessing.dummy import Pool

class TABHeader:
	def __init__(self):
		self.Magic = 0
		self.VersionMajor = 0
		self.VersionMinor = 0
		self.Alignment = 0

class TABEntry:
	def __init__(self):
		self.FileNameCRC = 0
		self.FileOffset = 0
		self.FileSize = 0


def DumpArc(ArchiveIndex):
	TABFilename = "./game" + str(ArchiveIndex) + ".tab"
	ARCFilename = "./game" + str(ArchiveIndex) + ".arc"
	with open(TABFilename, "r") as TABFile, open(ARCFilename, "r") as ARCFile:
		TABMap = mmap.mmap(TABFile.fileno(), 0, access=mmap.ACCESS_READ)
		ARCMap = mmap.mmap(ARCFile.fileno(), 0, access=mmap.ACCESS_READ)
		CurHeader = TABHeader
		(CurHeader.Magic, CurHeader.VersionMajor, CurHeader.VersionMinor, CurHeader.Alignment) \
			= struct.unpack_from('<IHHI',TABMap,0)
		if CurHeader.Magic != 0x424154:
			# Invalid magic, probably not a .tab file
			return
		FileCount = (TABMap.size() - 0xC) // 0xC
		# Extract files
		CurDumpPath = "./game" + str(ArchiveIndex) + "/"
		if not os.path.exists(CurDumpPath):
			os.makedirs(CurDumpPath)
		# Parse file list
		for FileIndex in range(FileCount):
			CurEntry = TABEntry
			(CurEntry.FileNameCRC, CurEntry.FileOffset, CurEntry.FileSize) \
				= struct.unpack_from('<III',TABMap,0xC + FileIndex * 0xC)
			print("{}: CRC:{:08x} Offset:{:08X} Size:{:08X}".format(
					ArchiveIndex,
					CurEntry.FileNameCRC,
					CurEntry.FileOffset,
					CurEntry.FileSize
				)
			)
			with open(CurDumpPath + hex(CurEntry.FileNameCRC)[2:],"wb") as CurDumpFile:
				CurDumpFile.write(
					ARCMap[CurEntry.FileOffset:CurEntry.FileOffset + CurEntry.FileSize]
				)


workers = Pool(4)
workers.map(DumpArc,range(0,23))