From 15099fc4fff9437da9104f67c33e4a92ed15a76f Mon Sep 17 00:00:00 2001
From: itsme <itsme@xs4all.nl>
Date: Wed, 7 Jul 2021 01:55:05 +0200
Subject: CroStru record structure now seems to be mostly decoded

---
 crodump.py | 81 ++++++++++++++++++++++++++++++++++++++------------------------
 1 file changed, 50 insertions(+), 31 deletions(-)

diff --git a/crodump.py b/crodump.py
index 1ba7e5e..7a9d9f3 100644
--- a/crodump.py
+++ b/crodump.py
@@ -9,7 +9,15 @@ python3 crodump.py crodump chechnya_proverki_ul_2012
 python3 crodump.py kodump -s 6   -o 0x4cc9 -e 0x5d95 chechnya_proverki_ul_2012/CroStru.dat
 """
 
+def toout(args, data):
+    """ return either ascdump or hexdump """
+    if args.ascdump:
+        return asasc(data)
+    else:
+        return tohex(data)
+
 def enumunreferenced(ranges, filesize):
+    """ from a list of used ranges and the filesize, enumerate the list of unused ranges """
     o = 0
     for start, end, desc in sorted(ranges):
         if start > o:
@@ -19,6 +27,7 @@ def enumunreferenced(ranges, filesize):
         yield o, filesize-o
 
 class Datafile:
+    """ Represent a single .dat with it's .tad index file """
     def __init__(self, dat, tad):
         self.dat = dat
         self.tad = tad
@@ -39,7 +48,7 @@ class Datafile:
         self.dat.seek(ofs)
         return self.dat.read(size)
 
-    def dump(self, args, dokodecode=False, plainbytes=0):
+    def dump(self, args, nodecode=False):
         print("tadhdr: %08x %08x" % tuple(self.tadhdr))
         ranges = []
         for i, (ofs, ln, chk) in enumerate(self.tadidx):
@@ -50,30 +59,45 @@ class Datafile:
 
             ln &= 0xFFFFFFF
             dat = self.readdata(ofs, ln)
+            ranges.append((ofs, ofs+ln, "item #%d" % i))
             plain = b''
-            decrypted = ' '
-            if dokodecode and not args.nokod:
-                pb = plainbytes if flags else 8
-                plain = dat[:pb]
-                dat = kodecode(i+1, dat[pb:])
-                decrypted = '*' if flags else '+'
-            if args.ascdump:
-                print("%5d: %08x-%08x: (%02x:%08x) %s %s%s" % (i, ofs, ofs+ln, flags, chk, tohex(plain), decrypted, asasc(dat)))
+            decflag = ' '
+            infostr = ""
+            tail = b''
+            if not nodecode and not flags:
+                extofs, extlen = struct.unpack("<LL", dat[:8])
+                infostr = "%08x;%08x" % (extofs, extlen)
+                encdat = dat[8:]
+                while len(encdat)<extlen:
+                    dat = self.readdata(extofs, 0x200)
+                    ranges.append((extofs, extofs+0x200, "item #%d ext" % i))
+                    extofs, = struct.unpack("<L", dat[:4])
+                    infostr += ";%08x" % (extofs)
+                    encdat += dat[4:]
+                tail = encdat[extlen:]
+                encdat = encdat[:extlen]
+                decflag = '+'
             else:
-                print("%5d: %08x-%08x: (%02x:%08x) %s %s%s" % (i, ofs, ofs+ln, flags, chk, tohex(plain), decrypted, tohex(dat)))
-            ranges.append((ofs, ofs+ln, "item #%d" % i))
+                encdat = dat
+                decflag = '*'
+
+            if nodecode:
+                decdat = encdat
+                decflag = ' '
+            else:
+                decdat = kodecode(i+1, encdat)
+
+            print("%5d: %08x-%08x: (%02x:%08x) %s %s%s %s" % (i, ofs, ofs+ln, flags, chk, infostr, decflag, toout(args, decdat), tohex(tail)))
 
         if args.verbose:
             # output parts not referenced in the .tad file.
             for o, l in enumunreferenced(ranges, self.datsize):
                 dat = self.readdata(o, l)
-                if args.ascdump:
-                    print("%08x-%08x: %s" % (o, o+l, asasc(dat)))
-                else:
-                    print("%08x-%08x: %s" % (o, o+l, tohex(dat)))
+                print("%08x-%08x: %s" % (o, o+l, toout(args, dat)))
 
 
 class Database:
+    """ represent the entire database, consisting of stru, index and bank files """
     def __init__(self, dbdir):
         self.dbdir = dbdir
 
@@ -114,22 +138,12 @@ def decode_kod(args, data):
         # explicitly specified shift.
         for s in range(256):
             enc = incdata(data, s)
-            if args.ascdump:
-                print("%02x: %s" % (s, asasc(enc)))
-            else:
-                print("%02x: %s" % (s, tohex(enc)))
-
-
-
+            print("%02x: %s" % (s, toout(args, enc)))
     else:
         # output with all possible 'shift' values.
         for s in range(256):
             enc = kodecode(s, data)
-            if args.ascdump:
-                print("%02x: %s" % (s, asasc(enc)))
-            else:
-                print("%02x: %s" % (s, tohex(enc)))
-
+            print("%02x: %s" % (s, toout(args, enc)))
 
 
 def kod_hexdump(args):
@@ -145,6 +159,10 @@ def kod_hexdump(args):
 
     if args.filename:
         with open(args.filename, "rb") as fh:
+            if args.length is None:
+                fh.seek(0, io.SEEK_END)
+                filesize = fh.tell()
+                args.length = filesize-args.offset
             fh.seek(args.offset)
             data = fh.read(args.length)
             decode_kod(args, data)
@@ -158,22 +176,23 @@ def kod_hexdump(args):
 
 
 def cro_dump(args):
+    """ handle 'crodump' subcommand """
     db = Database(args.dbdir)
 
     if db.stru:
         print("stru")
-        db.stru.dump(args, dokodecode=True)
+        db.stru.dump(args)
     if args.struonly:
         return
     if db.index:
         print("index")
-        db.index.dump(args)
+        db.index.dump(args, nodecode=True)
     if db.bank:
         print("bank")
-        db.bank.dump(args)
+        db.bank.dump(args, nodecode=True)
     if db.sys:
         print("sys")
-        db.sys.dump(args, dokodecode=True, plainbytes=8)
+        db.sys.dump(args)
 
 
 def main():
-- 
cgit v1.2.3