CXML_decompiler.py

#!python2
#ps4 related changes -oct0xor
 
import sys, os, struct
 
from io import BytesIO
from pprint import pprint
 
def read_cstring(f):
	bytes = []
	while True:
		byte = f.read(1)
		if byte == b'\x00':
			break
		elif byte == '':
			raise EOFError()
		else:
			bytes.append(byte)
	return b''.join(bytes)
 
def check_file_magic(f, expected_magic):
	old_offset = f.tell()
	try:
		magic = f.read(len(expected_magic))
	except:
		return False
	finally:
		f.seek(old_offset)
	return magic == expected_magic
 
script_file_name = os.path.split(sys.argv[0])[1]
script_file_base = os.path.splitext(script_file_name)[0]
 
if len(sys.argv) < 2:
	print('CXML decompiler (c) flatz')
	print('Usage: {0} <cxml file> <xml file>'.format(script_file_name))
	sys.exit()
 
ENDIANNESS = '<'
 
def write_raw(f, data):
	if type(data) == str:
		f.write(data)
	elif type(data) == unicode:
		f.write(data.decode('utf-8'))
	else:
		f.write(data)
def write_indent(f, depth):
	write_raw(f, '\t' * depth)
def write_line(f, data):
	write_raw(f, data)
	write_raw(f, '\n')
 
INT_FMT = ENDIANNESS + 'i'
FLOAT_FMT = ENDIANNESS + 'f'
STRING_FMT = ENDIANNESS + 'ii'
INT_ARRAY_FMT = ENDIANNESS + 'ii'
FLOAT_ARRAY_FMT = ENDIANNESS + 'ii'
FILE_FMT = ENDIANNESS + 'ii'
ID_FMT = ENDIANNESS + 'i'
ID_REF_FMT = ENDIANNESS + 'i'
 
class Attribute(object):
	HEADER_FMT = ENDIANNESS + 'ii'
	HEADER_SIZE = struct.calcsize(HEADER_FMT)
	SIZE = HEADER_SIZE + max(struct.calcsize(INT_FMT), struct.calcsize(FLOAT_FMT), struct.calcsize(STRING_FMT), struct.calcsize(INT_ARRAY_FMT), struct.calcsize(FLOAT_ARRAY_FMT), struct.calcsize(FILE_FMT), struct.calcsize(ID_FMT), struct.calcsize(ID_REF_FMT))
 
	TYPE_NONE = 0
	TYPE_INT = 1
	TYPE_FLOAT = 2
	TYPE_STRING = 3
	TYPE_INT_ARRAY = 4
	TYPE_FLOAT_ARRAY = 5
	TYPE_UNK1 = 6
	TYPE_ID = 7
	TYPE_FILE = 8
	TYPE_ID_REF = 9
	TYPE_UNK2 = 11

	def __init__(self, element):
		self.element = element
		self.start = None
		self.name = None
		self.type = None
		self.offset = None
		self.length = None
		self.value = None
 
	def load(self, f):
		self.start = f.tell()
		data = f.read(self.HEADER_SIZE)
		self.name, self.type = struct.unpack(self.HEADER_FMT, data)
		data = f.read(self.SIZE - self.HEADER_SIZE)

		if self.type == self.TYPE_NONE:
			pass
		elif self.type == self.TYPE_INT:
			self.value, = struct.unpack(INT_FMT, data[:struct.calcsize(INT_FMT)])
		elif self.type == self.TYPE_FLOAT:
			self.value, = struct.unpack(FLOAT_FMT, data[:struct.calcsize(FLOAT_FMT)])
		elif self.type == self.TYPE_STRING:
			self.offset, self.length = struct.unpack(STRING_FMT, data[:struct.calcsize(STRING_FMT)])
		elif self.type == self.TYPE_INT_ARRAY:
			self.offset, self.length = struct.unpack(INT_ARRAY_FMT, data[:struct.calcsize(INT_ARRAY_FMT)])
		elif self.type == self.TYPE_FLOAT_ARRAY:
			self.offset, self.length = struct.unpack(FLOAT_ARRAY_FMT, data[:struct.calcsize(FLOAT_ARRAY_FMT)])
		elif self.type == self.TYPE_UNK1:
			self.offset, self.length = struct.unpack(FILE_FMT, data[:struct.calcsize(FILE_FMT)])
		elif self.type == self.TYPE_ID:
			self.offset, = struct.unpack(ID_FMT, data[:struct.calcsize(ID_FMT)])
		elif self.type == self.TYPE_ID_REF:
			self.offset, = struct.unpack(ID_REF_FMT, data[:struct.calcsize(ID_REF_FMT)])
		elif self.type == self.TYPE_FILE:
			self.offset, self.length = struct.unpack(FILE_FMT, data[:struct.calcsize(FILE_FMT)])
		elif self.type == self.TYPE_UNK2:
			self.value, = struct.unpack(INT_FMT, data[:struct.calcsize(INT_FMT)])

		return True

	def get_unk1(self):
		return self.offset, self.length

	def get_unk2(self):
		return self.value
 
	def get_name(self):
		return self.element.document.get_string(self.name)
 
	def get_int(self):
		if self.type != self.TYPE_INT:
			return None
		return self.value
 
	def get_float(self):
		if self.type != self.TYPE_FLOAT:
			return None
		return self.value
 
	def get_string(self):
		if self.type != self.TYPE_STRING:
			return None
		value = self.element.document.get_string(self.offset)
		if len(value) != self.length:
			return None
		return value
 
	def get_int_array(self):
		if self.type != self.TYPE_INT_ARRAY:
			return None
		value = self.element.document.get_int_array(self.offset, self.length)
		if len(value) != self.length:
			return None
		return value
 
	def get_float_array(self):
		if self.type != self.TYPE_FLOAT_ARRAY:
			return None
		value = self.element.document.get_float_array(self.offset, self.length)
		if len(value) != self.length:
			return None
		return value
 
	def get_file(self):
		if self.type != self.TYPE_FILE:
			return None
		value = self.element.document.get_file(self.offset, self.length)
		return value
 
	def get_id(self):
		if self.type != self.TYPE_ID:
			return None
		id = self.element.document.get_id_string(self.offset)
		return id
 
	def get_id_ref(self):
		if self.type != self.TYPE_ID_REF:
			return None
		id = self.element.document.get_id_string(self.offset)
		element = Element(self.element.document)
		return [id, element]
 
	def dump(self, f, depth):
		pass
		#print('  ' * depth + 'Attribute:' + 'name:{0} type:{1}'.format(self.name, self.type), end='\n', file=f)
 
class Element(object):
	HEADER_FMT = ENDIANNESS + 'iiiiiii'
	SIZE = struct.calcsize(HEADER_FMT)
 
	TAG_NAME = 0
	ATTR_NUM = 1
	PARENT = 2
	PREV = 3
	NEXT = 4
	FIRST_CHILD = 5
	LAST_CHILD = 6
 
	def __init__(self, document):
		self.document = document
		self.start = None
		self.name = None
		self.num_attributes = None
		self.parent = None
		self.prev = None
		self.next = None
		self.first_child = None
		self.last_child = None
 
	def load(self, f):
		self.start = f.tell()
		self.name, self.num_attributes, self.parent, self.prev, self.next, self.first_child, self.last_child = struct.unpack(self.HEADER_FMT, f.read(self.SIZE))
		return True
 
	def get_name(self):
		return self.document.get_string(self.name)
 
	def get_attribute(self, index):
		if index < 0 or index >= self.num_attributes:
			return None
		offset = self.start + Element.SIZE + index * Attribute.SIZE
		if not is_valid_attribute(self.document, offset):
			return None
		attribute = Attribute(self)
		f = BytesIO(self.document.tree_bin)
		f.seek(offset)
		attribute.load(f)
		return attribute
 
	def get_parent(self):
		if not is_valid_element(self.document, self.parent):
			return None
		element = Element(self.document)
		f = BytesIO(self.document.tree_bin)
		f.seek(parent)
		element.load(f)
		return element
 
	def get_first_child(self):
		if not is_valid_element(self.document, self.first_child):
			return None
		element = Element(self.document)
		f = BytesIO(self.document.tree_bin)
		f.seek(self.first_child)
		element.load(f)
		return element
 
	def get_last_child(self):
		if not is_valid_element(self.document, self.last_child):
			return None
		element = Element(self.document)
		f = BytesIO(self.document.tree_bin)
		f.seek(self.last_child)
		element.load(f)
		return element
 
	def get_prev_sibling(self):
		if not is_valid_element(self.document, self.prev):
			return None
		element = Element(self.document)
		f = BytesIO(self.document.tree_bin)
		f.seek(self.prev)
		element.load(f)
		return element
 
	def get_next_sibling(self):
		if not is_valid_element(self.document, self.next):
			return None
		element = Element(self.document)
		f = BytesIO(self.document.tree_bin)
		f.seek(self.next)
		element.load(f)
		return element
 
	def dump(self, f, depth):
		write_indent(f, depth)
		name = self.get_name()
		write_raw(f, '<' + name)
		for i in range(self.num_attributes):
			attribute = self.get_attribute(i)
			if attribute is None:
				return False
			write_raw(f, ' {0}='.format(attribute.get_name()))

			if attribute.type == Attribute.TYPE_NONE:
				write_raw(f, '\"null\"')
			elif attribute.type == Attribute.TYPE_INT:
				write_raw(f, '\"{0}\"'.format(attribute.get_int()))
			elif attribute.type == Attribute.TYPE_FLOAT:
				write_raw(f, '\"{0}\"'.format(attribute.get_float()))
			elif attribute.type == Attribute.TYPE_STRING:
				write_raw(f, '\"{0}\"'.format(attribute.get_string()))
			elif attribute.type == Attribute.TYPE_INT_ARRAY:
				write_raw(f, '\"')
				array = attribute.get_int_array()
				array_length = len(array)
				for j in range(array_length):
					write_raw(f, '{0}'.format(array[j]))
					if j + 1 < array_length:
						write_raw(f, ',')
				write_raw(f, '\"')
			elif attribute.type == Attribute.TYPE_FLOAT_ARRAY:
				write_raw(f, '\"')
				array = attribute.get_float_array()
				array_length = len(array)
				for j in range(array_length):
					write_raw(f, '{0}'.format(array[j]))
					if j + 1 < array_length:
						write_raw(f, ',')
				write_raw(f, '\"')
			elif attribute.type == Attribute.TYPE_FILE:
				file_name = '{0}_0x{1:08X}.bin'.format(self.document.file_prefix, attribute.offset)
				file_data = attribute.get_file()
				with open(file_name, 'wb') as of:
					of.write(file_data)
				write_raw(f, '\"{0}\"'.format(file_name))
			elif attribute.type == Attribute.TYPE_ID:
				write_raw(f, '\"{0}\"'.format(attribute.get_id()))
			elif attribute.type == Attribute.TYPE_ID_REF:
				id_entity = attribute.get_id_ref()
				write_raw(f, '\"{0}\"'.format(id_entity[0]))

			elif attribute.type == Attribute.TYPE_UNK1:
				offset, length = attribute.get_unk1()
				write_raw(f, '\"{0}, {1}\"'.format(offset, length))

			elif attribute.type == Attribute.TYPE_UNK2:
				write_raw(f, '\"{0}\"'.format(attribute.get_unk2()))

		child_element = self.get_first_child()
		if not child_element is None:
			write_raw(f, '>\n')
			while not child_element is None:
				child_element.dump(f, depth + 1)
				child_element = child_element.get_next_sibling()
			write_indent(f, depth)
			write_raw(f, '</' + name + '>\n')
		else:
			write_raw(f, ' />\n')
 
def is_valid_element(document, offset):
	if offset < 0 or offset + Element.SIZE > document.tree_size:
		return False
	element = Element(document)
	f = BytesIO(document.tree_bin)
	f.seek(offset)
	element.load(f)
	if element.num_attributes < 0 or offset + Element.SIZE + element.num_attributes * Attribute.SIZE > document.tree_size:
		return False
	return True
 
def is_valid_attribute(document, offset):
	if offset < 0 or offset + Attribute.SIZE > document.tree_size:
		return False
	return True
 
class Document(object):
	HEADER_FMT = ENDIANNESS + '4siiiiiiiiiiiiiiiiiii'
	HEADER_SIZE = struct.calcsize(HEADER_FMT)
 
	def __init__(self, file_prefix=''):
		self.file_prefix = file_prefix
		self.magic = None
		self.version = None
		self.tree_offset = None
		self.tree_size = None
		self.id_table_offset = None
		self.id_table_size = None
		self.idhashtable_offset = None
		self.idhashtable_size = None
		self.string_table_offset = None
		self.string_table_size = None
		self.wstringtable_offset = None
		self.wstringtable_size = None
		self.hashtable_offset = None
		self.hashtable_size = None
		self.int_array_table_offset = None
		self.int_array_table_size = None
		self.float_array_table_offset = None
		self.float_array_table_size = None
		self.file_table_offset = None
		self.file_table_size = None

		self.tree_bin = None
		self.id_table_bin = None
		self.idhashtable_bin = None
		self.string_table_bin = None
		self.wstringtable_bin = None
		self.hashtable_bin = None

		self.int_array_table_bin = None
		self.float_array_table_bin = None
		self.file_table_bin = None
		self.root = None
 
	def get_document_element(self):
		if not is_valid_element(self, 0):
			return None
		element = Element(self)
		f = BytesIO(self.tree_bin)
		element.load(f)
		return element
 
	def get_id_string(self, offset):
		if offset < 0 or offset >= self.id_table_size:
			return None
		f = BytesIO(self.id_table_bin)
		f.seek(offset)
		entity_offset, = struct.unpack(INT_FMT, f.read(struct.calcsize(INT_FMT)))
		return read_cstring(f)
 
	def get_string(self, offset):
		if offset < 0 or offset >= self.string_table_size:
			return None
		f = BytesIO(self.string_table_bin)
		f.seek(offset)
		return read_cstring(f)
 
	def get_int_array(self, offset, length):
		if offset < 0 or (offset + length) * struct.calcsize(INT_FMT) > self.int_array_table_size:
			return None
		f = BytesIO(self.int_array_table_bin)
		f.seek(offset * struct.calcsize(INT_FMT))
		array = []
		for i in range(length):
			value, = struct.unpack(INT_FMT, f.read(struct.calcsize(INT_FMT)))
			array.append(value)
		return array
 
	def get_float_array(self, offset, length):
		if offset < 0 or (offset + length) * struct.calcsize(FLOAT_FMT) > self.float_array_table_size:
			return None
		f = BytesIO(self.float_array_table_bin)
		f.seek(offset * struct.calcsize(FLOAT_FMT))
		array = []
		for i in range(length):
			value, = struct.unpack(FLOAT_FMT, f.read(struct.calcsize(FLOAT_FMT)))
			array.append(value)
		return array
 
	def get_file(self, offset, length):
		if offset < 0 or offset + length > self.file_table_size:
			return None
		return self.file_table_bin[offset:offset + length]
 
	def load(self, f):
		self.magic, self.version, self.tree_offset, self.tree_size, self.id_table_offset, self.id_table_size, self.idhashtable_offset, self.idhashtable_size, self.string_table_offset, self.string_table_size, self.wstringtable_offset, self.wstringtable_size, self.hashtable_offset, self.hashtable_size, self.int_array_table_offset, self.int_array_table_size, self.float_array_table_offset, self.float_array_table_size, self.file_table_offset, self.file_table_size = struct.unpack(self.HEADER_FMT, f.read(self.HEADER_SIZE))
		f.seek(self.tree_offset)
		self.tree_bin = f.read(self.tree_size)
		f.seek(self.id_table_offset)
		self.id_table_bin = f.read(self.id_table_size)
		f.seek(self.idhashtable_offset)
		self.idhashtable_bin = f.read(self.idhashtable_size)
		f.seek(self.string_table_offset)
		self.string_table_bin = f.read(self.string_table_size)
		f.seek(self.wstringtable_offset)
		self.wstringtable_bin = f.read(self.wstringtable_size)
		f.seek(self.hashtable_offset)
		self.hashtable_bin = f.read(self.hashtable_size)
		f.seek(self.int_array_table_offset)
		self.int_array_table_bin = f.read(self.int_array_table_size)
		f.seek(self.float_array_table_offset)
		self.float_array_table_bin = f.read(self.float_array_table_size)
		f.seek(self.file_table_offset)
		self.file_table_bin = f.read(self.file_table_size)
		self.root = self.get_document_element()

		return True
 
	def check(self, f):
		return check_file_magic(f, 'CXML')
 
	def dump(self, f=sys.stdout, depth=0):
		if self.root is None:
			return
		self.root.dump(f, depth)
 
if len(sys.argv) < 3:
	print('error: insufficient options specified')
	sys.exit()
 
cxml_file_path = sys.argv[1]
if not os.path.isfile(cxml_file_path):
	print('error: invalid cxml file specified')
	sys.exit()
xml_file_path = sys.argv[2]
if os.path.exists(xml_file_path) and not os.path.isfile(xml_file_path):
	print('error: invalid xml file specified')
	sys.exit()
	 
cxml_file_base = os.path.splitext(cxml_file_path)[0]
document = Document(cxml_file_base)
with open(cxml_file_path, 'rb') as f:
	#if not document.check(f):
	#	print 'error: invalid CXML file format'
	#	sys.exit()
	document.load(f)
	
with open(xml_file_path, 'wb') as f:
	write_raw(f, '<?xml version="1.0" encoding="utf-8"?>\n')
	document.dump(f)