Initial commit: RE tooling and docs for The I of the Dragon localization/HD

2026-09-20 09:57:07 +08:00
commit caf7376019
26 changed files with 1624 additions and 0 deletions
@@ -0,0 +1,62 @@
+import os, sys, collections, math
+
+base = r"F:\steam\steamapps\common\The I of the Dragon\Data\Misc"
+files = ["Fonts.dat", "UnitDescription.dat", "AIDescription.dat"]
+
+def printable_ratio(b):
+    if not b: return 0
+    return sum(1 for x in b if 32 <= x < 127) / len(b)
+
+def score_text(b):
+    # rough score: printable ratio + bonus for common english words
+    r = printable_ratio(b)
+    sample = bytes(b)
+    kw = 0
+    for w in [b"Char", b"Code", b"Font", b"SpaceWidth", b".tga", b"Shrift", b"Distance", b"Id", b"String"]:
+        kw += sample.count(w)
+    return r, kw
+
+for f in files:
+    p = os.path.join(base, f)
+    data = open(p, "rb").read()
+    print("="*70)
+    print(f, "size", len(data))
+    print("first 32:", data[:32].hex(" "))
+
+    # 1) single-byte xor
+    best = []
+    for k in range(256):
+        dec = bytes(x ^ k for x in data)
+        r, kw = score_text(dec)
+        best.append((kw, r, k, dec[:80]))
+    best.sort(key=lambda t: (-t[0], -t[1]))
+    print("-- best single-byte XOR by keyword --")
+    for kw, r, k, s in best[:5]:
+        print(f"  k=0x{k:02X} kw={kw} pr={r:.3f} {s!r}")
+
+    # 2) additive / subtractive
+    best = []
+    for k in range(256):
+        dec = bytes((x - k) & 0xFF for x in data)
+        r, kw = score_text(dec)
+        best.append((kw, r, k, dec[:80]))
+    best.sort(key=lambda t: (-t[0], -t[1]))
+    print("-- best subtract key --")
+    for kw, r, k, s in best[:3]:
+        print(f"  k=0x{k:02X} kw={kw} pr={r:.3f} {s!r}")
+
+    # 3) repeating-key XOR, key length 2..64, derive key from space frequency
+    print("-- repeating-key XOR (key from most-common byte == space) --")
+    results = []
+    for L in range(2, 65):
+        key = bytearray()
+        for r in range(L):
+            col = data[r::L]
+            c = collections.Counter(col).most_common(1)[0][0]
+            key.append(c ^ 0x20)
+        dec = bytes(x ^ key[i % L] for i, x in enumerate(data))
+        rr, kw = score_text(dec)
+        results.append((kw, rr, L, bytes(key), dec[:80]))
+    results.sort(key=lambda t: (-t[0], -t[1]))
+    for kw, rr, L, key, s in results[:6]:
+        print(f"  L={L:2d} key={key.hex()} kw={kw} pr={rr:.3f} {s!r}")