Pythonプログラムの実行手順を下から簡単に分析する

  # Python3.4 
  >>> import dis 
  >>> f = lambda x: x + 3 
  >>> for i in dis.Bytecode(f.__code__): print (i) 
  ... 
  Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='x',    argrepr='x', offset=0, starts_line=1, is_jump_target=False) 
  Instruction(opname='LOAD_CONST', opcode=100, arg=1, argval=3,    argrepr='3', offset=3, starts_line=None, is_jump_target=False) 
  Instruction(opname='BINARY_ADD', opcode=23, arg=None,      argval=None, argrepr='', offset=6, starts_line=None,   is_jump_target=False) 
  Instruction(opname='RETURN_VALUE', opcode=83, arg=None,    argval=None, argrepr='', offset=7, starts_line=None,  is_jump_target=False) 

  class MutableCodeObject(object): 
    args_name = ("co_argcount", "co_kwonlyargcount", "co_nlocals", "co_stacksize", "co_flags", "co_code", 
           "co_consts", "co_names", "co_varnames",   "co_filename", "co_name", "co_firstlineno", 
            "co_lnotab", "co_freevars", "co_cellvars") 

    def __init__(self, initial_code): 
      self.initial_code = initial_code 
      for attr_name in self.args_name: 
        attr = getattr(self.initial_code, attr_name) 
        if isinstance(attr, tuple): 
          attr = list(attr) 
        setattr(self, attr_name, attr) 

    def get_code(self): 
      args = [] 
      for attr_name in self.args_name: 
        attr = getattr(self, attr_name) 
        if isinstance(attr, list): 
          attr = tuple(attr) 
        args.append(attr) 
      return self.initial_code.__class__(*args) 

  >>> x = lambda y : 2 
  >>> m = MutableCodeObject(x.__code__) 
  >>> m 
   
  >>> m.co_consts 
  [None, 2] 
  >>> m.co_consts[1] = '3' 
  >>> m.co_name = 'truc' 
  >>> m.get_code() 
  ", line 1> 

  from new_code import MutableCodeObject 

  def op_target(*args): 
    print("WOOT") 
    print("op_target called with args ".format(args)) 

  def nop(): 
    pass 

  new_nop_code = MutableCodeObject(nop.__code__) 
  new_nop_code.co_code = b"\x00" + new_nop_code.co_code[0:3] + b"\x00" + new_nop_code.co_code[-1:] 
  new_nop_code.co_stacksize += 3 

  nop.__code__ = new_nop_code.get_code() 

  import dis 
  dis.dis(nop) 
  nop() 


  # Don't forget that ./python is our custom Python implementing    DEBUG_OP 
  hakril@computer ~/python/CPython3.5 % ./python proof.py 
   8      0 <0> 
         1 LOAD_CONST        0 (None) 
         4 <0> 
         5 RETURN_VALUE 
  WOOT 
  op_target called with args )> 
  WOOT 
  op_target called with args )> 

  def add_debug_op_everywhere(code_obj): 
     # We get every instruction offset in the code object 
    offsets = [instr.offset for instr in dis.Bytecode(code_obj)]  
    # And insert a DEBUG_OP at every offset 
    return insert_op_debug_list(code_obj, offsets) 

  def insert_op_debug_list(code, offsets): 
     # We insert the DEBUG_OP one by one 
    for nb, off in enumerate(sorted(offsets)): 
      # Need to ajust the offsets by the number of opcodes     already inserted before 
      # That's why we sort our offsets! 
      code = insert_op_debug(code, off + nb) 
    return code 

  # Last problem: what does insert_op_debug looks like? 

  # Helper 
  def bytecode_to_string(bytecode): 
    if bytecode.arg is not None: 
      return struct.pack(" offset: 
          res_codestring +=   bytecode_to_string(DummyInstr(instr.opcode, instr.arg + 1)) 
          continue 
      res_codestring += bytecode_to_string(instr) 
    # replace_bytecode just replaces the original code co_code 
    return replace_bytecode(code, res_codestring) 

 >>> def lol(x): 
  ...   for i in range(10): 
  ...     if x == i: 
  ...       break 

  >>> dis.dis(lol) 
  101      0 SETUP_LOOP       36 (to 39) 
         3 LOAD_GLOBAL       0 (range) 
         6 LOAD_CONST        1 (10) 
         9 CALL_FUNCTION      1 (1 positional, 0  keyword pair) 
         12 GET_ITER 
      >>  13 FOR_ITER        22 (to 38) 
         16 STORE_FAST        1 (i) 

  102     19 LOAD_FAST        0 (x) 
         22 LOAD_FAST        1 (i) 
         25 COMPARE_OP        2 (==) 
         28 POP_JUMP_IF_FALSE    13 

  103     31 BREAK_LOOP 
         32 JUMP_ABSOLUTE      13 
         35 JUMP_ABSOLUTE      13 
      >>  38 POP_BLOCK 
      >>  39 LOAD_CONST        0 (None) 
         42 RETURN_VALUE 
  >>> lol.__code__ = transform_code(lol.__code__,    add_debug_op_everywhere, add_stacksize=3) 


  >>> dis.dis(lol) 
  101      0 <0> 
         1 SETUP_LOOP       50 (to 54) 
         4 <0> 
         5 LOAD_GLOBAL       0 (range) 
         8 <0> 
         9 LOAD_CONST        1 (10) 
         12 <0> 
         13 CALL_FUNCTION      1 (1 positional, 0  keyword pair) 
         16 <0> 
         17 GET_ITER 
      >>  18 <0> 

  102     19 FOR_ITER        30 (to 52) 
         22 <0> 
         23 STORE_FAST        1 (i) 
         26 <0> 
         27 LOAD_FAST        0 (x) 
         30 <0> 

  103     31 LOAD_FAST        1 (i) 
         34 <0> 
         35 COMPARE_OP        2 (==) 
         38 <0> 
         39 POP_JUMP_IF_FALSE    18 
         42 <0> 
         43 BREAK_LOOP 
         44 <0> 
         45 JUMP_ABSOLUTE      18 
         48 <0> 
         49 JUMP_ABSOLUTE      18 
      >>  52 <0> 
         53 POP_BLOCK 
      >>  54 <0> 
         55 LOAD_CONST        0 (None) 
         58 <0> 
         59 RETURN_VALUE 

   # Setup the simplest handler EVER 
  >>> def op_target(stack, frame): 
  ...   print (stack) 

  # GO 
  >>> lol(2) 
  [] 
  [] 
  [] 
  [10, ] 
  [range(0, 10)] 
  [] 
  [0, ] 
  [] 
  [2, ] 
  [0, 2, ] 
  [False, ] 
  [] 
  [1, ] 
  [] 
  [2, ] 
  [1, 2, ] 
  [False, ] 
  [] 
  [2, ] 
  [] 
  [2, ] 
  [2, 2, ] 
  [True, ] 
  [] 
  [] 
  [None] 

 def op_target(l, f, exc=None): 
    if op_target.callback is not None: 
      op_target.callback(l, f, exc) 

  class Trace: 
    def __init__(self, func): 
      self.func = func 

    def call(self, *args, **kwargs): 
       self.add_func_to_trace(self.func) 
      # Activate Trace callback for the func call 
      op_target.callback = self.callback 
      try: 
        res = self.func(*args, **kwargs) 
      except Exception as e: 
        res = e 
      op_target.callback = None 
      return res 

    def add_func_to_trace(self, f): 
      # Is it code? is it already transformed? 
      if not hasattr(f ,"op_debug") and hasattr(f, "__code__"): 
        f.__code__ = transform_code(f.__code__,  transform=add_everywhere, add_stacksize=ADD_STACK) 
        f.__globals__['op_target'] = op_target 
        f.op_debug = True 

    def do_auto_follow(self, stack, frame): 
      # Nothing fancy: FrameAnalyser is just the wrapper that gives the next executed instruction 
      next_instr = FrameAnalyser(frame).next_instr() 
      if "CALL" in next_instr.opname: 
        arg = next_instr.arg 
        f_index = (arg & 0xff) + (2 * (arg >> 8)) 
        called_func = stack[f_index] 

        # If call target is not traced yet: do it 
        if not hasattr(called_func, "op_debug"): 
          self.add_func_to_trace(called_func) 

 class DummyTrace(Trace): 
    def __init__(self, func): 
      self.func = func 
      self.data = collections.OrderedDict() 
      self.last_frame = None 
      self.known_frame = [] 
      self.report = [] 

    def callback(self, stack, frame, exc): 
       if frame not in self.known_frame: 
        self.known_frame.append(frame) 
        self.report.append(" === Entering New Frame {0} ({1})   ===".format(frame.f_code.co_name, id(frame))) 
        self.last_frame = frame 
      if frame != self.last_frame: 
        self.report.append(" === Returning to Frame {0}   {1}===".format(frame.f_code.co_name, id(frame))) 
        self.last_frame = frame 

      self.report.append(str(stack)) 
      instr = FrameAnalyser(frame).next_instr() 
      offset = str(instr.offset).rjust(8) 
      opname = str(instr.opname).ljust(20) 
      arg = str(instr.arg).ljust(10) 
      self.report.append("{0} {1} {2} {3}".format(offset,  opname, arg, instr.argval)) 
      self.do_auto_follow(stack, frame) 

    def do_report(self): 
      print("
".join(self.report))