编译自：http://www.aosabook.org/en/500L/a-python-interpreter-written-in-python.html 作者：Taavi Burns 翻译：鸿 如有翻译问题或建议，请公众号留言
Byterun
Byterun中有四种对象：
- VirtualMachine类，它是最高级别结构，拥有frame的call stack，并且包含指令到操作的映射。
- Frame类。每个Frame实例都有一个代码对象并管理一些其他必要的状态标识，例如全局和本地命名空间，以及调用frame的引用以及执行的最后一个字节码。
- Function类，用来代替真正的Python函数。调用函数会在解释器中创建一个新frame。
- Block类，它包含了block的三个属性。
The VirtualMachine Class
在程序运行时，只会创建一次VirtualMachine实例，这是因为只有一个Python解释器。 VirtualMachine存储着call stack，异常状态以及在frame之间的返回值。执行代码的入口是run_code方法，它将已经编译的代码对象作为参数。刚开始就会设置和运行一个frame。 这个frame可能会创建其他frame; 当第一个frame返回时，程序执行结束。
代码语言：javascript复制class VirtualMachineError(Exception):
pass
class VirtualMachine(object):
def __init__(self):
self.frames = [] # The call stack of frames.
self.frame = None # The current frame.
self.return_value = None
self.last_exception = None
def run_code(self, code, global_names=None, local_names=None):
""" An entry point to execute code using the virtual machine."""
frame = self.make_frame(code, global_names=global_names,
local_names=local_names)
self.run_frame(frame)The Frame Class
frame类只是属性的集合。这些属性包括由编译器创建的代码对象; 本地，全局和内置命名空间; 对前一个frame的引用、data stack、block stack。
代码语言：javascript复制class Frame(object):
def __init__(self, code_obj, global_names, local_names, prev_frame):
self.code_obj = code_obj
self.global_names = global_names
self.local_names = local_names
self.prev_frame = prev_frame
self.stack = []
if prev_frame:
self.builtin_names = prev_frame.builtin_names
else:
self.builtin_names = local_names['__builtins__']
if hasattr(self.builtin_names, '__dict__'):
self.builtin_names = self.builtin_names.__dict__
self.last_instruction = 0
self.block_stack = []现在增加对frame的操作到虚拟机。这里有三个有关frame的辅助函数：一个用于创建新的frame，另外两个用于在frame stacke上推入和弹出frame。 第四个函数run_frame执行frame类的主要工作。
代码语言：javascript复制class VirtualMachine(object):
[... snip ...]
# Frame manipulation
def make_frame(self, code, callargs={}, global_names=None, local_names=None):
if global_names is not None and local_names is not None:
local_names = global_names
elif self.frames:
global_names = self.frame.global_names
local_names = {}
else:
global_names = local_names = {
'__builtins__': __builtins__,
'__name__': '__main__',
'__doc__': None,
'__package__': None,
}
local_names.update(callargs)
frame = Frame(code, global_names, local_names, self.frame)
return frame
def push_frame(self, frame):
self.frames.append(frame)
self.frame = frame
def pop_frame(self):
self.frames.pop()
if self.frames:
self.frame = self.frames[-1]
else:
self.frame = None
def run_frame(self):
pass
# we'll come back to this shortlyThe Function Class
函数对象的实现需要注意的是调用函数（使用call方法）会创建一个新的Frame对象并开始运行它。
代码语言：javascript复制class Function(object):
"""
Create a realistic function object, defining the things the interpreter expects.
"""
__slots__ = [
'func_code', 'func_name', 'func_defaults', 'func_globals',
'func_locals', 'func_dict', 'func_closure',
'__name__', '__dict__', '__doc__',
'_vm', '_func',
]
def __init__(self, name, code, globs, defaults, closure, vm):
"""You don't need to follow this closely to understand the interpreter."""
self._vm = vm
self.func_code = code
self.func_name = self.__name__ = name or code.co_name
self.func_defaults = tuple(defaults)
self.func_globals = globs
self.func_locals = self._vm.frame.f_locals
self.__dict__ = {}
self.func_closure = closure
self.__doc__ = code.co_consts[0] if code.co_consts else None
# Sometimes, we need a real Python function. This is for that.
kw = {
'argdefs': self.func_defaults,
}
if closure:
kw['closure'] = tuple(make_cell(0) for _ in closure)
self._func = types.FunctionType(code, globs, **kw)
def __call__(self, *args, **kwargs):
"""When calling a Function, make a new frame and run it."""
callargs = inspect.getcallargs(self._func, *args, **kwargs)
# Use callargs to provide a mapping of arguments: values to pass into the new
# frame.
frame = self._vm.make_frame(
self.func_code, callargs, self.func_globals, {}
)
return self._vm.run_frame(frame)
def make_cell(value):
"""Create a real Python closure and grab a cell."""
# Thanks to Alex Gaynor for help with this bit of twistiness.
fn = (lambda x: lambda: x)(value)
return fn.__closure__[0]回到VirtualMachine实例，再增加一些函数操作函数对象：
代码语言：javascript复制class VirtualMachine(object):
[... snip ...]
# Data stack manipulation
def top(self):
return self.frame.stack[-1]
def pop(self):
return self.frame.stack.pop()
def push(self, *vals):
self.frame.stack.extend(vals)
def popn(self, n):
"""Pop a number of values from the value stack.
A list of `n` values is returned, the deepest value first.
"""
if n:
ret = self.frame.stack[-n:]
self.frame.stack[-n:] = []
return ret
else:
return []首先，parse_byte_and_args获取一个字节码，检查它是否有参数，如果有，则解析该参数。此方法还会更新frame的last_instruction属性。如果没有参数的话，单个指令是一个字节，有一个参数是三个字节，它们的最后两个字节是参数。每条指令参数的含义取决于它是哪一条指令。例如，对于POP_JUMP_IF_FALSE，指令参数是跳转目标。对于BUILD_LIST，指令是列表中元素的数量。LOAD_CONST，指令参数是常量列表的索引。
代码语言：javascript复制class VirtualMachine(object):
[... snip ...]
def parse_byte_and_args(self):
f = self.frame
opoffset = f.last_instruction
byteCode = f.code_obj.co_code[opoffset]
f.last_instruction = 1
byte_name = dis.opname[byteCode]
if byteCode >= dis.HAVE_ARGUMENT:
# index into the bytecode
arg = f.code_obj.co_code[f.last_instruction:f.last_instruction 2]
f.last_instruction = 2 # advance the instruction pointer
arg_val = arg[0] (arg[1] * 256)
if byteCode in dis.hasconst: # Look up a constant
arg = f.code_obj.co_consts[arg_val]
elif byteCode in dis.hasname: # Look up a name
arg = f.code_obj.co_names[arg_val]
elif byteCode in dis.haslocal: # Look up a local name
arg = f.code_obj.co_varnames[arg_val]
elif byteCode in dis.hasjrel: # Calculate a relative jump
arg = f.last_instruction arg_val
else:
arg = arg_val
argument = [arg]
else:
argument = []
return byte_name, argument下一个方法是dispatch，查找给定的指令对应的操作并执行。 在CPython解释器中是通过一个超过1500行的switch语句完成的！但是这次为每个字节名称定义一个方法，然后使用getattr来查找它。
代码语言：javascript复制class VirtualMachine(object):
[... snip ...]
def dispatch(self, byte_name, argument):
""" Dispatch by bytename to the corresponding methods.
Exceptions are caught and set on the virtual machine."""
# When later unwinding the block stack,
# we need to keep track of why we are doing it.
why = None
try:
bytecode_fn = getattr(self, 'byte_%s' % byte_name, None)
if bytecode_fn is None:
if byte_name.startswith('UNARY_'):
self.unaryOperator(byte_name[6:])
elif byte_name.startswith('BINARY_'):
self.binaryOperator(byte_name[7:])
else:
raise VirtualMachineError(
"unsupported bytecode type: %s" % byte_name
)
else:
why = bytecode_fn(*argument)
except:
# deal with exceptions encountered while executing the op.
self.last_exception = sys.exc_info()[:2] (None,)
why = 'exception'
return why
def run_frame(self, frame):
"""Run a frame until it returns (somehow).
Exceptions are raised, the return value is returned.
"""
self.push_frame(frame)
while True:
byte_name, arguments = self.parse_byte_and_args()
why = self.dispatch(byte_name, arguments)
# Deal with any block management we need to do
while why and frame.block_stack:
why = self.manage_block_stack(why)
if why:
break
self.pop_frame()
if why == 'exception':
exc, val, tb = self.last_exception
e = exc(val)
e.__traceback__ = tb
raise e
return self.return_valueThe Block Class
block类用于某些类型的流量控制，特别是异常处理和循环。block类负责在操作完成时确保data stack处于适当的状态。为了跟踪额外的信息，解释器会设置一个标志来表示其状态。这个标志是一个叫做why的变量，有着None或字符串“continue”，“break”，“exception”或“return”。表示block stack和data stack应该执行什么样的操作。
代码语言：javascript复制Block = collections.namedtuple("Block", "type, handler, stack_height")
class VirtualMachine(object):
[... snip ...]
# Block stack manipulation
def push_block(self, b_type, handler=None):
stack_height = len(self.frame.stack)
self.frame.block_stack.append(Block(b_type, handler, stack_height))
def pop_block(self):
return self.frame.block_stack.pop()
def unwind_block(self, block):
"""Unwind the values on the data stack corresponding to a given block."""
if block.type == 'except-handler':
# The exception itself is on the stack as type, value, and traceback.
offset = 3
else:
offset = 0
while len(self.frame.stack) > block.level offset:
self.pop()
if block.type == 'except-handler':
traceback, value, exctype = self.popn(3)
self.last_exception = exctype, value, traceback
def manage_block_stack(self, why):
""" """
frame = self.frame
block = frame.block_stack[-1]
if block.type == 'loop' and why == 'continue':
self.jump(self.return_value)
why = None
return why
self.pop_block()
self.unwind_block(block)
if block.type == 'loop' and why == 'break':
why = None
self.jump(block.handler)
return why
if (block.type in ['setup-except', 'finally'] and why == 'exception'):
self.push_block('except-handler')
exctype, value, tb = self.last_exception
self.push(tb, value, exctype)
self.push(tb, value, exctype) # yes, twice
why = None
self.jump(block.handler)
return why
elif block.type == 'finally':
if why in ('return', 'continue'):
self.push(self.return_value)
self.push(why)
why = None
self.jump(block.handler)
return why
return why
The Instructions下面就是几十种字节码方法。更多的请去GitHub去找：
代码语言：javascript复制class VirtualMachine(object):
[... snip ...]
## Stack manipulation
def byte_LOAD_CONST(self, const):
self.push(const)
def byte_POP_TOP(self):
self.pop()
## Names
def byte_LOAD_NAME(self, name):
frame = self.frame
if name in frame.f_locals:
val = frame.f_locals[name]
elif name in frame.f_globals:
val = frame.f_globals[name]
elif name in frame.f_builtins:
val = frame.f_builtins[name]
else:
raise NameError("name '%s' is not defined" % name)
self.push(val)
def byte_STORE_NAME(self, name):
self.frame.f_locals[name] = self.pop()
def byte_LOAD_FAST(self, name):
if name in self.frame.f_locals:
val = self.frame.f_locals[name]
else:
raise UnboundLocalError(
"local variable '%s' referenced before assignment" % name
)
self.push(val)
def byte_STORE_FAST(self, name):
self.frame.f_locals[name] = self.pop()
def byte_LOAD_GLOBAL(self, name):
f = self.frame
if name in f.f_globals:
val = f.f_globals[name]
elif name in f.f_builtins:
val = f.f_builtins[name]
else:
raise NameError("global name '%s' is not defined" % name)
self.push(val)
## Operators
BINARY_OPERATORS = {
'POWER': pow,
'MULTIPLY': operator.mul,
'FLOOR_DIVIDE': operator.floordiv,
'TRUE_DIVIDE': operator.truediv,
'MODULO': operator.mod,
'ADD': operator.add,
'SUBTRACT': operator.sub,
'SUBSCR': operator.getitem,
'LSHIFT': operator.lshift,
'RSHIFT': operator.rshift,
'AND': operator.and_,
'XOR': operator.xor,
'OR': operator.or_,
}
def binaryOperator(self, op):
x, y = self.popn(2)
self.push(self.BINARY_OPERATORS[op](x, y))
COMPARE_OPERATORS = [
operator.lt,
operator.le,
operator.eq,
operator.ne,
operator.gt,
operator.ge,
lambda x, y: x in y,
lambda x, y: x not in y,
lambda x, y: x is y,
lambda x, y: x is not y,
lambda x, y: issubclass(x, Exception) and issubclass(x, y),
]
def byte_COMPARE_OP(self, opnum):
x, y = self.popn(2)
self.push(self.COMPARE_OPERATORS[opnum](x, y))
## Attributes and indexing
def byte_LOAD_ATTR(self, attr):
obj = self.pop()
val = getattr(obj, attr)
self.push(val)
def byte_STORE_ATTR(self, name):
val, obj = self.popn(2)
setattr(obj, name, val)
## Building
def byte_BUILD_LIST(self, count):
elts = self.popn(count)
self.push(elts)
def byte_BUILD_MAP(self, size):
self.push({})
def byte_STORE_MAP(self):
the_map, val, key = self.popn(3)
the_map[key] = val
self.push(the_map)
def byte_LIST_APPEND(self, count):
val = self.pop()
the_list = self.frame.stack[-count] # peek
the_list.append(val)
## Jumps
def byte_JUMP_FORWARD(self, jump):
self.jump(jump)
def byte_JUMP_ABSOLUTE(self, jump):
self.jump(jump)
def byte_POP_JUMP_IF_TRUE(self, jump):
val = self.pop()
if val:
self.jump(jump)
def byte_POP_JUMP_IF_FALSE(self, jump):
val = self.pop()
if not val:
self.jump(jump)
## Blocks
def byte_SETUP_LOOP(self, dest):
self.push_block('loop', dest)
def byte_GET_ITER(self):
self.push(iter(self.pop()))
def byte_FOR_ITER(self, jump):
iterobj = self.top()
try:
v = next(iterobj)
self.push(v)
except StopIteration:
self.pop()
self.jump(jump)
def byte_BREAK_LOOP(self):
return 'break'
def byte_POP_BLOCK(self):
self.pop_block()
## Functions
def byte_MAKE_FUNCTION(self, argc):
name = self.pop()
code = self.pop()
defaults = self.popn(argc)
globs = self.frame.f_globals
fn = Function(name, code, globs, defaults, None, self)
self.push(fn)
def byte_CALL_FUNCTION(self, arg):
lenKw, lenPos = divmod(arg, 256) # KWargs not supported here
posargs = self.popn(lenPos)
func = self.pop()
frame = self.frame
retval = func(*posargs)
self.push(retval)
def byte_RETURN_VALUE(self):
self.return_value = self.pop()
return "return"
