ED3 Script Test

# -*- coding: utf-8 -*-
import os

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

def is_jis_char(s):
    if len(s) != 2: #If it's not a string of length 2, then...
        return False
    try:            #Python error handling
        if len(s.decode('cp932')) != 1: #For example, 2 ascii characters will be length 2
            return False                #Two bytes that decode to a SHIFT-JIS character will be length 1
    except UnicodeDecodeError:  #The string couldn't be decoded
        return False            #Not a SHIFT-JIS character
    return True                 #It is a SHIFT-JIS character

def decode_string(s):
    mode = True
    s1 = u'｡､･ｦｧｨｩｪｫｬｭｮｯｰｱｲｳｴｵｶｷｸｹｺｻｼｽｾｿﾀﾁﾂﾃﾄﾅﾆﾇﾈﾉﾊﾋﾌﾍﾎﾏﾐﾑﾒﾓﾔﾕﾖﾗﾘﾙﾚﾛﾜﾝﾞﾟ'
    s2 = u'。、Xをぁぃぅぇぉゃゅょっーあいうえおかきくけこさしすせそたちつてと\
なにぬねのはひふへほまみむめもやゆよらりるれろわんXX'
    s3 = u'。、Xヲァィゥェォャュョッーアイウエオカキクケコサシスセソタチツテト\
ナニヌネノハヒフヘホマミムメモヤユヨラリルレロワンXX'
    t = zip(s1,s2,s3) #Put 'em, togther, whatdayya got? :)
    sd = ''
    pos = 0
    while pos < len(s):
        if ord(s[pos]) == 0xA2: #Set hiragana flag
            mode = False
            pos += 1
        elif ord(s[pos]) == 0xA3: #Set katakana flag, the default
            mode = True
            pos += 1
        elif ord(s[pos]) == 1: #Linebreak, not sure
            sd += '\n'
            pos += 1
        elif ord(s[pos]) == 2: #Delay, not sure
            sd += 'delay'
            pos += 1
        elif ord(s[pos]) == 3:
            sd += 'Unknown Opcode 03'
            pos += 1
        elif ord(s[pos]) == 4:
            sd += 'Unknown Opcode 04'
            pos += 1
        elif ord(s[pos]) == 5:
            sd += 'Unknown Opcode 05'
            pos += 1
        elif ord(s[pos]) == 6:
            sd += 'Unknown Opcode 06'
            pos += 1
        elif ord(s[pos]) == 0x14:
            sd += 'Unknown Opcode 14'
            pos += 1
        elif ord(s[pos]) >= 0x20 and ord(s[pos]) < 0x7F: #ASCII
            sd += s[pos]
            pos += 1
        elif pos < len(s) - 1 and is_jis_char(s[pos:pos+2]): #SHIFT-JIS char, double-byte
            sd += s[pos:pos+2]
            pos += 2
        elif unicode(s[pos],'cp932') in s1:     #SHIFT-JIS char, single-byte
            for x, y, z in t:
                if unicode(s[pos],'cp932') == x:
                    if mode == True:
                        sd += y.encode('cp932')
                    else:
                        sd += z.encode('cp932')
                    pos += 1
                    break
        else:
            print 'Unknown character.'
            print pos
            return sd
    return sd


filedata = get_data('crap2.dat')
pos = 0x4e0
opcodes = ('\x00\x0f','\x04\x0f')
while True:
    r = []
    for op in opcodes:
        r.append(filedata.find(op,pos))
    pos = min(r) + 2
    print hex(pos)
    if pos == 1:
        break
    endpos = filedata.find('\x00', pos)
    s = filedata[pos:endpos]
    sd = decode_string(s)
    print sd.decode('cp932')
    pos = endpos