pycをみる

ここを読んだときのメモ。 struct.unpackに渡すフォーマットがLじゃなくてiだってだけの話。おいらの環境が６４bitだからかな。

マジック + CRLF + datetime(epock) + marshalled object

である。pickleじゃなくてmarshallな理由はこの辺:

The entire rest of the file is just the output of marshal.dump of the code object that results from compiling the source file. Marshal is like pickle, in that it serializes Python objects. It has different goals than pickle, though. Where pickle is meant to produce version-independent serialization suitable for persistence, marshal is meant for short-lived serialized objects, so its representation can change with each Python version. Also, pickle is designed to work properly for user-defined types, while marshal handles the complexities of Python internal types. The one we care about in particular here is the code object.

import dis, marshal, struct, sys, time, types
    
MAGICLENGTH = 4
DATELENGTH = 4
        
def show_file(fname):
    f = open(fname, "rb")
    magic = f.read(MAGICLENGTH)
    moddate = f.read(DATELENGTH)
    modtime = time.asctime(time.localtime(struct.unpack('i', moddate)[0]))
    print "magic %s" % (magic.encode('hex'))
    print "moddate %s (%s)" % (moddate.encode('hex'), modtime)
    code = marshal.load(f)
    show_code(code)
        
def show_code(code, indent=''):
    print "%scode" % indent
    indent += '   '
    print "%sargcount %d" % (indent, code.co_argcount)
    print "%snlocals %d" % (indent, code.co_nlocals)
    print "%sstacksize %d" % (indent, code.co_stacksize)
    print "%sflags %04x" % (indent, code.co_flags)
    show_hex("code", code.co_code, indent=indent)
    dis.disassemble(code)
    print "%sconsts" % indent
    for const in code.co_consts:
        if type(const) == types.CodeType:
            show_code(const, indent+'   ')
        else:
            print "   %s%r" % (indent, const)
    print "%snames %r" % (indent, code.co_names)
    print "%svarnames %r" % (indent, code.co_varnames)
    print "%sfreevars %r" % (indent, code.co_freevars)
    print "%scellvars %r" % (indent, code.co_cellvars)
    print "%sfilename %r" % (indent, code.co_filename)
    print "%sname %r" % (indent, code.co_name)
    print "%sfirstlineno %d" % (indent, code.co_firstlineno)
    show_hex("lnotab", code.co_lnotab, indent=indent)
    
def show_hex(label, h, indent): 
    h = h.encode('hex')
    if len(h) < 60:
        print "%s%s %s" % (indent, label, h)
    else:
        print "%s%s" % (indent, label)
        for i in range(0, len(h), 60):
            print "%s   %s" % (indent, h[i:i+60])
        
show_file(sys.argv[1])