From 19344c50d505fbcb0c59f92a9033de43dfcd122b Mon Sep 17 00:00:00 2001
From: Yavin7 <morgan07kelley@gmail.com>
Date: Thu, 18 Sep 2025 22:53:57 -0600
Subject: [PATCH] Added a notes file Updated header parsing, and replaced the
 endian with little instead of big, because the files are def little endian

---
 main.py   | 24 +++++++++++++-----------
 notes.txt | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+), 11 deletions(-)
 create mode 100644 notes.txt

diff --git a/main.py b/main.py
index 606c9ab..eb85a65 100644
--- a/main.py
+++ b/main.py
@@ -12,7 +12,7 @@ class BZZCompressor:
         # read the input file
         try:
             with open(f"{input_file_path}/{input_file}", "rb") as infile:
-                temp = bitarray(endian="big")
+                temp = bitarray(endian="little")
                 temp.fromfile(infile)
 
                 data = temp.tobytes()
@@ -30,13 +30,9 @@ class BZZCompressor:
         ##############################################################################
 
         # This is always 1, 0, 0, 0. so I'm just having fun
-        bzz_version = f"v{data[0]}.{data[1]}.{data[2]}.{data[3]}"
-        game_id = "".join([str(int(bin(item)[2:], 2)) for item in data[4:8]])
-
-        num_files = 0
-
-        for item in data[8:12]:
-            num_files += int(bin(item)[2:].zfill(8), 2)
+        bzz_version = int.from_bytes(data[0:4], "little")
+        game_id = int.from_bytes(data[4:8], "little")
+        num_files = int.from_bytes(data[8:12], "little")
 
         print(f"BZZ Version: {bzz_version}")
         print(f"Game ID: {game_id}")
@@ -48,9 +44,15 @@ class BZZCompressor:
             tmp = (i) * 12
             files.append(
                 {
-                    "pt_a": data[12 + tmp : 12 + tmp + 4],
-                    "pt_b": data[12 + tmp + 4 : 12 + tmp + 8],
-                    "pt_c": data[12 + tmp + 8 : 12 + tmp + 12],
+                    "pt_a": hex(
+                        int.from_bytes(data[12 + tmp : 12 + tmp + 4], "little")
+                    ),
+                    "pt_b": hex(
+                        int.from_bytes(data[12 + tmp + 4 : 12 + tmp + 8], "little")
+                    ),
+                    "pt_c": hex(
+                        int.from_bytes(data[12 + tmp + 8 : 12 + tmp + 12], "little")
+                    ),
                 }
             )
 
diff --git a/notes.txt b/notes.txt
new file mode 100644
index 0000000..544c4ad
--- /dev/null
+++ b/notes.txt
@@ -0,0 +1,50 @@
+Conclusions based on the data below:
+1. It looks like the Part A is the file's type
+2. It looks like Part C - Part B is 1 more than the length of the 0-padding between files
+  note: I don't know why they didn't just write the file's size here, it would've saved on space
+3. PS1 developers were madlads
+
+
+Header:
+Header Data Start:  0x00
+Header Data End:    0x2F
+0 Padding Start:    0x30
+0 Padding End:      0x7FB
+Checksum Start:     0x7FC
+Checksum End:       0x7FF
+
+File 1:
+Part A:             0x1
+Part B:             0x8fc
+Part C:             0x1000
+C - B = 0x704
+
+Data Start:         0x800
+Data End:           0x10F9
+0 Padding Start:    0x10FA
+0 Padding End:      0x17FF
+End - Start = 0x705
+
+File 2:
+Part A:             0x3
+Part B:             0xE240
+Part C:             0xE800
+C - B = 0x5C0
+
+Data Start:         0x1800
+Data End:           0xFA3F
+0 Padding Start:    0xFA40
+0 Padding End:      0xFFFF
+0 Padding End - Start = 0x5BF
+
+File 3:
+Part A:             0x4
+Part B:             0xD450
+Part C:             0xD800
+C - B = 0x3B0
+
+Data Start:         0x10000
+Data End:           0x1D44F
+0 Padding Start:    0x1D450
+0 Padding End:      0x1D7FF
+End - Start = 3AF
\ No newline at end of file