Nayuta Script Dump v1.5

# v1.5: Add 0xC1 opcode
# v1.4: Correct error in 41 opcode dumping
# v1.3: Change the way 35 opcodes dump
# v1.2: Previous version wasn't dumping all the text
#       Added opcodes 6B, BC and 35...should be working now
# v1.1: Previous version wasn't dumping all the text
#       Added opcodes 3F, 40 and 06...should be working now
# Dump Nayuta no Kiseki script file
# Usage is python script.py mp_0000
# Where mp_0000.bin is the file you want to dump
# mp_0000.data is the output file (in this example), tab-separated
import os
import struct
import sys

def get_data(filename):
    totalbytes = os.path.getsize(filename)
    infile = open(filename, 'rb')
    totalfiledata = infile.read(totalbytes)
    infile.close()
    return totalfiledata

def myprogram(filename):
    C1num = 0
    filedata = get_data(filename + '.orig')

    # Analyze header -> store in indexdata
    pos = 0x18
    EOF = struct.unpack('<I',filedata[pos + 0x24:pos+ 0x28])[0]

    indexdata = []
    flag = False
    while pos < EOF:
        addr = struct.unpack('<I',filedata[pos + 0x24:pos+ 0x28])[0]
        if flag:
            #Start address and end address are stored
            indexdata.append([name, addrold, addr])
        else:
            flag = True
        name = filedata[pos:filedata.find('\x00',pos)]
        addrold = addr
        pos += 0x28
    indexdata.append([name, addr, len(filedata)])

    output = filename + "\n"
    for name, addr, endaddr in indexdata:
        data = filedata[addr:endaddr]
        pos = 0
        addrs = []
        opcodelist = ('\x41\x80\xDD\x82','\x98\x80\xDF\x82',
                      '\x07\x80\xDF\x82','\x3F\x80\xDF\x82','\x40\x80\xDF\x82',
                      '\x06\x80\xDF\x82',
                      '\xC9\x80\xDD\x82\x01\x00\x00\x00\xDF\x82',
                      '\xCE\x80\xDD\x82',
                      '\x36\x80\xDD\x82',
                      '\xBC\x80\xDF\x82','\x6B\x80\xDF\x82',
                      '\xC1\x80\xE0\x82')
        for opcode in opcodelist:
            pos = -1
            while True:
                pos = data.find(opcode,pos + 1)
                if pos == -1:
                    break
                addrs.append(addr + pos)

        output += name + '\n'
        for addr in sorted(addrs):
            if ord(filedata[addr]) == 0x41:
                output += hex(addr) + '\t' + '0x41' + '\t' + 'System' + '\t'
                pos = addr + 0x16
                for x in range(10):
                    datalen = ord(filedata[pos])
                    pos += 4
                    text = filedata[pos:pos + datalen]
                    output += text + '\n' + '\t'*3
                    pos += datalen + 2
                output = output[:-3]
            elif ord(filedata[addr]) in (0x98,0x40):
                opcode = hex(ord(filedata[addr]))
                pos = addr + 4
                datalen = ord(filedata[pos])
                pos += 4
                text = filedata[pos:pos + datalen]
                output += hex(addr) + '\t' + opcode + '\t' + text + '\t'
                pos += datalen + 2
                for x in range(3):
                    datalen = ord(filedata[pos])
                    pos += 4
                    text = filedata[pos:pos + datalen]
                    output += text + '\n' + '\t'*3
                    pos += datalen + 2
                output = output[:-3]
            elif ord(filedata[addr]) == 0x07:
                output += hex(addr) + '\t' + '0x07' + '\t' + 'System' + '\t'
                pos = addr + 4
                datalen = ord(filedata[pos])
                pos += 4
                text = filedata[pos:pos + datalen]
                while '\\n' in text:
                    output += text[:text.find('\\n')] + '\n' + '\t'*3
                    text = text[text.find('\\n') + 2:]
                output += text + '\n'
            elif ord(filedata[addr]) in (0x3F,0xC9,0xCE):
                output += hex(addr) + '\t' + hex(ord(filedata[addr])) + '\t'
                if ord(filedata[addr]) == 0xCE:
                    output += 'Obj.' + '\t'
                else:
                    output += '\t'
                if ord(filedata[addr]) == 0x3F:
                    pos = addr + 4
                else:
                    pos = addr + 10
                datalen = ord(filedata[pos])
                pos += 4
                text = filedata[pos:pos + datalen]
                output += text + '\n'
            elif ord(filedata[addr]) == 0x06:
                pos = addr + 4
                output += hex(addr) + '\t' + '0x06'
                for x in range(2):
                    datalen = ord(filedata[pos])
                    pos += 4
                    text = filedata[pos:pos + datalen]
                    output += '\t' + text
                    pos += datalen + 2
                output += '\n'
            elif ord(filedata[addr]) == 0x36:
                pos = addr + 10
                datalen = struct.unpack('<I',filedata[pos:pos+4])[0]
                pos += 4
                output += hex(addr) + '\t' + '0x36' + '\t' + 'Choice' + '\t' + filedata[pos:pos+datalen] + '\n'
            elif ord(filedata[addr]) in (0xBC,0x6B):
                pos = addr + 2
                datalen = struct.unpack('<I',filedata[pos+2:pos+6])[0]
                pos += 6
                text = filedata[pos:pos + datalen]
                output += hex(addr) + '\t' + hex(ord(filedata[addr])) + '\t' \
                          + text + '\t'
                pos += datalen + 8
                val = struct.unpack('<I',filedata[pos:pos+4])[0]
                if val == 0x0:
                    text = 'Question'
                elif val == 0x2:
                    text = 'Exclamation'
                elif val == 0x10:
                    text = 'Sweatdrop'
                elif val == 0x14:
                    text = 'Coldsweat'
                elif val == 0x18:
                    text = 'Ellipsis'
                elif val == 0x27:
                    text = 'Surprise'
                elif val == 0x39:
                    text = 'Discovery/Findout'
                else:
                    text = 'Unknown value %s.' % str(val)
                output += text + '\n'
            elif ord(filedata[addr]) == 0xC1:
                C1num += 1
                pos = addr + 2
                for x in range(3):
                    pos += 2
                    datalen = struct.unpack('<I',filedata[pos:pos+4])[0]
                    pos += datalen + 4
                pos += 2
                datalen = struct.unpack('<I',filedata[pos:pos+4])[0]
                pos += 4
                text = filedata[pos:pos+datalen]
                output += '\t'.join((hex(addr),hex(ord(filedata[addr])),'System',
                                   text)) + '\n'
            else:
                print 'Unknown opcode %s at address %s.' % \
                      (filedata[addr].encode('hex'),hex(addr))

    outfile = open(filename + '.data','wb')
    outfile.write(output)
    outfile.close()
    print '%d C1 opcodes.' % C1num

if __name__ == '__main__':
##    for testing in IDLE
##    sys.argv.append('mp_0110')
    myprogram(sys.argv[1])