Add highly experimental U8 handling module

.gitignore

@@ -161,9 +161,10 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
 
-# Allows me to keep TMD files in my repository folder for testing without accidentally publishing them
+# Relevant files that are used for testing libWiiPy's features.
 *.tmd
 *.wad
+*.arc
 out_prod/
 remakewad.pl
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "libWiiPy"
-version = "0.2.3"
+version = "0.3.0"
 authors = [
     { name="NinjaCheetah", email="ninjacheetah@ncxprogramming.com" },
     { name="Lillian Skinner", email="lillian@randommeaninglesscharacters.com" }

src/libWiiPy/__init__.py

@@ -11,3 +11,4 @@ from .title import *
 from .tmd import *
 from .wad import *
 from .nus import *
+from .u8 import *

src/libWiiPy/types.py

@@ -1,6 +1,6 @@
 # "types.py" from libWiiPy by NinjaCheetah & Contributors
 # https://github.com/NinjaCheetah/libWiiPy
-
+from builtins import type
 from dataclasses import dataclass
 
 
@@ -14,21 +14,21 @@ class ContentRecord:
     Attributes
     ----------
     content_id : int
-        ID of the content.
+        The unique ID of the content.
     index : int
-        Index of the content in the list of contents.
+        The index of this content in the content records.
     content_type : int
         The type of the content.
     content_size : int
-        The size of the content.
+        The size of the content when decrypted.
     content_hash
         The SHA-1 hash of the decrypted content.
     """
-    content_id: int  # The unique ID of the content.
-    index: int  # The index of this content in the content record.
+    content_id: int
+    index: int
     content_type: int  # Type of content, possible values of: 0x0001: Normal, 0x4001: DLC, 0x8001: Shared.
-    content_size: int  # Size of the content when decrypted.
-    content_hash: bytes  # SHA-1 hash of the content when decrypted.
+    content_size: int
+    content_hash: bytes
 
 
 @dataclass
@@ -50,3 +50,27 @@ class TitleLimit:
     limit_type: int
     # The maximum value of the limit applied.
     maximum_usage: int
+
+
+@dataclass
+class U8Node:
+    """
+    A U8Node object that contains the data of a single node in a U8 file header. Each node keeps track of whether this
+    node is for a file or directory, the offset of the name of the file/directory, the offset of the data for the file/
+    directory, and the size of the data.
+
+    Attributes
+    ----------
+    type : int
+        Whether this node refers to a file or a directory. Either 0x0000 for files, or 0x0100 for directories.
+    name_offset : int
+        The offset of the name of the file/directory this node refers to.
+    data_offset : int
+        The offset of the data for the file/directory this node refers to.
+    size : int
+        The size of the data for this node.
+    """
+    type: int
+    name_offset: int
+    data_offset: int
+    size: int

src/libWiiPy/u8.py

@@ -0,0 +1,83 @@
+# "u8.py" from libWiiPy by NinjaCheetah & Contributors
+# https://github.com/NinjaCheetah/libWiiPy
+#
+# See https://wiibrew.org/wiki/U8_archive for details about the U8 archive format
+
+import io
+import binascii
+from typing import List
+from .types import U8Node
+
+
+class U8Archive:
+    def __init__(self):
+        """
+        A U8 object that allows for extracting and packing U8 archives.
+
+        Attributes
+        ----------
+        """
+        self.u8_magic = b''
+        self.root_node_offset = 0  # Offset of the root node, which will always be 0x20.
+        self.header_size = 0  # The size of the U8 header.
+        self.data_offset = 0  # The offset of the data, which is root_node_offset + header_size, aligned to 0x40.
+        self.header_padding = b''
+        self.root_node = U8Node
+        self.u8_node_list: List[U8Node] = []  # All the nodes in the header of a U8 file.
+        self.file_name_list: List[str] = []
+        self.u8_file_data_list: List[bytes] = []
+        self.u8_file_structure = dict
+
+    def load(self, u8_data: bytes) -> None:
+        """
+        Loads raw U8 data into a new U8 object. This allows for extracting the file and updating its contents.
+
+        Parameters
+        ----------
+        u8_data : bytes
+            The data for the U8 file to load.
+        """
+        with io.BytesIO(u8_data) as u8_data:
+            # Read the first 4 bytes of the file to ensure that it's a U8 archive.
+            u8_data.seek(0x0)
+            self.u8_magic = u8_data.read(4)
+            if self.u8_magic != b'\x55\xAA\x38\x2D':
+                raise TypeError("This is not a valid U8 archive!")
+            self.root_node_offset = int(binascii.hexlify(u8_data.read(4)), 16)
+            self.header_size = int(binascii.hexlify(u8_data.read(4)), 16)
+            self.data_offset = int(binascii.hexlify(u8_data.read(4)), 16)
+            self.header_padding = u8_data.read(16)
+            root_node_type = int.from_bytes(u8_data.read(2))
+            root_node_name_offset = int.from_bytes(u8_data.read(2))
+            root_node_data_offset = int.from_bytes(u8_data.read(4))
+            root_node_size = int.from_bytes(u8_data.read(4))
+            self.root_node = U8Node(root_node_type, root_node_name_offset, root_node_data_offset, root_node_size)
+            self.u8_node_list.append(self.root_node)
+            # Iterate over the number of nodes that the root node lists, minus one since the count includes itself.
+            for node in range(self.root_node.size - 1):
+                node_type = int.from_bytes(u8_data.read(2))
+                node_name_offset = int.from_bytes(u8_data.read(2))
+                node_data_offset = int.from_bytes(u8_data.read(4))
+                node_size = int.from_bytes(u8_data.read(4))
+                self.u8_node_list.append(U8Node(node_type, node_name_offset, node_data_offset, node_size))
+            # Iterate over all loaded nodes and create a list of file names.
+            name_base_offset = u8_data.tell()
+            for node in self.u8_node_list:
+                u8_data.seek(name_base_offset + node.name_offset)
+                name_bin = b''
+                while name_bin[-1:] != b'\x00':
+                    name_bin += u8_data.read(1)
+                name_bin = name_bin[:-1]
+                name = str(name_bin.decode())
+                self.file_name_list.append(name)
+                if node.type == 0:
+                    u8_data.seek(node.data_offset)
+                    self.u8_file_data_list.append(u8_data.read(node.size))
+                else:
+                    self.u8_file_data_list.append(b'')
+            # This does nothing for now.
+            next_dir = 0
+            for node in range(len(self.u8_node_list)):
+                if self.u8_node_list[node].type == 256 and node != 0:
+                    next_dir = self.u8_node_list[node].size
+

src/libWiiPy/wad.py

@@ -49,7 +49,7 @@ class WAD:
         self.wad_content_data: bytes = b''
         self.wad_meta_data: bytes = b''
 
-    def load(self, wad_data) -> None:
+    def load(self, wad_data: bytes) -> None:
         """
         Loads raw WAD data and sets all attributes of the WAD object. This allows for manipulating an already
         existing WAD file.
@@ -57,7 +57,7 @@ class WAD:
         Parameters
         ----------
         wad_data : bytes
-            The data for the WAD you wish to load.
+            The data for the WAD file to load.
         """
         with io.BytesIO(wad_data) as wad_data:
             # Read the first 8 bytes of the file to ensure that it's a WAD. Has two possible valid values for the two
@@ -67,7 +67,7 @@ class WAD:
             wad_magic_hex = binascii.hexlify(wad_magic_bin)
             wad_magic = str(wad_magic_hex.decode())
             if wad_magic != "0000002049730000" and wad_magic != "0000002069620000":
-                raise TypeError("This does not appear to be a valid WAD file.")
+                raise TypeError("This is not a valid WAD file!")
             # ====================================================================================
             # Get the sizes of each data region contained within the WAD.
             # ====================================================================================