| """create portable serialized representations of Python objects. |
| |
| See module cPickle for a (much) faster implementation. |
| See module copy_reg for a mechanism for registering custom picklers. |
| |
| Classes: |
| |
| Pickler |
| Unpickler |
| |
| Functions: |
| |
| dump(object, file) |
| dumps(object) -> string |
| load(file) -> object |
| loads(string) -> object |
| |
| Misc variables: |
| |
| __ version__ |
| format_version |
| compatible_formats |
| |
| """ |
| |
| __version__ = "1.9" # Code version |
| |
| from types import * |
| from copy_reg import dispatch_table, safe_constructors |
| import string, marshal |
| |
| format_version = "1.2" # File format version we write |
| compatible_formats = ["1.0", "1.1"] # Old format versions we can read |
| |
| mdumps = marshal.dumps |
| mloads = marshal.loads |
| |
| PicklingError = "pickle.PicklingError" |
| UnpicklingError = "pickle.UnpicklingError" |
| |
| MARK = '(' |
| STOP = '.' |
| POP = '0' |
| POP_MARK = '1' |
| DUP = '2' |
| FLOAT = 'F' |
| INT = 'I' |
| BININT = 'J' |
| BININT1 = 'K' |
| LONG = 'L' |
| BININT2 = 'M' |
| NONE = 'N' |
| PERSID = 'P' |
| BINPERSID = 'Q' |
| REDUCE = 'R' |
| STRING = 'S' |
| BINSTRING = 'T' |
| SHORT_BINSTRING = 'U' |
| APPEND = 'a' |
| BUILD = 'b' |
| GLOBAL = 'c' |
| DICT = 'd' |
| EMPTY_DICT = '}' |
| APPENDS = 'e' |
| GET = 'g' |
| BINGET = 'h' |
| INST = 'i' |
| LONG_BINGET = 'j' |
| LIST = 'l' |
| EMPTY_LIST = ']' |
| OBJ = 'o' |
| PUT = 'p' |
| BINPUT = 'q' |
| LONG_BINPUT = 'r' |
| SETITEM = 's' |
| TUPLE = 't' |
| EMPTY_TUPLE = ')' |
| SETITEMS = 'u' |
| |
| class Pickler: |
| |
| def __init__(self, file, bin = 0): |
| self.write = file.write |
| self.memo = {} |
| self.bin = bin |
| |
| def dump(self, object): |
| self.save(object) |
| self.write(STOP) |
| |
| def dump_special(self, callable, args, state = None): |
| if type(args) is not TupleType and args is not None: |
| raise PicklingError, "Second argument to dump_special " \ |
| "must be a tuple" |
| |
| self.save_reduce(callable, args, state) |
| self.write(STOP) |
| |
| def put(self, i): |
| if (self.bin): |
| s = mdumps(i)[1:] |
| if (i < 256): |
| return BINPUT + s[0] |
| |
| return LONG_BINPUT + s |
| |
| return PUT + `i` + '\n' |
| |
| def get(self, i): |
| if (self.bin): |
| s = mdumps(i)[1:] |
| |
| if (i < 256): |
| return BINGET + s[0] |
| |
| return LONG_BINGET + s |
| |
| return GET + `i` + '\n' |
| |
| def save(self, object, pers_save = 0): |
| memo = self.memo |
| |
| if (not pers_save): |
| pid = self.persistent_id(object) |
| if (pid is not None): |
| self.save_pers(pid) |
| return |
| |
| d = id(object) |
| |
| t = type(object) |
| |
| if ((t is TupleType) and (len(object) == 0)): |
| if (self.bin): |
| self.save_empty_tuple(object) |
| else: |
| self.save_tuple(object) |
| return |
| |
| if memo.has_key(d): |
| self.write(self.get(memo[d][0])) |
| return |
| |
| try: |
| f = self.dispatch[t] |
| except KeyError: |
| pid = self.inst_persistent_id(object) |
| if pid is not None: |
| self.save_pers(pid) |
| return |
| |
| try: |
| reduce = dispatch_table[t] |
| except KeyError: |
| try: |
| reduce = object.__reduce__ |
| except AttributeError: |
| raise PicklingError, \ |
| "can't pickle %s objects" % `t.__name__` |
| else: |
| tup = reduce() |
| else: |
| tup = reduce(object) |
| |
| if type(tup) is StringType: |
| self.save_global(object, tup) |
| return |
| |
| if (type(tup) is not TupleType): |
| raise PicklingError, "Value returned by %s must be a " \ |
| "tuple" % reduce |
| |
| l = len(tup) |
| |
| if ((l != 2) and (l != 3)): |
| raise PicklingError, "tuple returned by %s must contain " \ |
| "only two or three elements" % reduce |
| |
| callable = tup[0] |
| arg_tup = tup[1] |
| |
| if (l > 2): |
| state = tup[2] |
| else: |
| state = None |
| |
| if type(arg_tup) is not TupleType and arg_tup is not None: |
| raise PicklingError, "Second element of tuple returned " \ |
| "by %s must be a tuple" % reduce |
| |
| self.save_reduce(callable, arg_tup, state) |
| memo_len = len(memo) |
| self.write(self.put(memo_len)) |
| memo[d] = (memo_len, object) |
| return |
| |
| f(self, object) |
| |
| def persistent_id(self, object): |
| return None |
| |
| def inst_persistent_id(self, object): |
| return None |
| |
| def save_pers(self, pid): |
| if (not self.bin): |
| self.write(PERSID + str(pid) + '\n') |
| else: |
| self.save(pid, 1) |
| self.write(BINPERSID) |
| |
| def save_reduce(self, callable, arg_tup, state = None): |
| write = self.write |
| save = self.save |
| |
| save(callable) |
| save(arg_tup) |
| write(REDUCE) |
| |
| if (state is not None): |
| save(state) |
| write(BUILD) |
| |
| dispatch = {} |
| |
| def save_none(self, object): |
| self.write(NONE) |
| dispatch[NoneType] = save_none |
| |
| def save_int(self, object): |
| if (self.bin): |
| i = mdumps(object)[1:] |
| if (i[-2:] == '\000\000'): |
| if (i[-3] == '\000'): |
| self.write(BININT1 + i[:-3]) |
| return |
| |
| self.write(BININT2 + i[:-2]) |
| return |
| |
| self.write(BININT + i) |
| else: |
| self.write(INT + `object` + '\n') |
| dispatch[IntType] = save_int |
| |
| def save_long(self, object): |
| self.write(LONG + `object` + '\n') |
| dispatch[LongType] = save_long |
| |
| def save_float(self, object): |
| self.write(FLOAT + `object` + '\n') |
| dispatch[FloatType] = save_float |
| |
| def save_string(self, object): |
| d = id(object) |
| memo = self.memo |
| |
| if (self.bin): |
| l = len(object) |
| s = mdumps(l)[1:] |
| if (l < 256): |
| self.write(SHORT_BINSTRING + s[0] + object) |
| else: |
| self.write(BINSTRING + s + object) |
| else: |
| self.write(STRING + `object` + '\n') |
| |
| memo_len = len(memo) |
| self.write(self.put(memo_len)) |
| memo[d] = (memo_len, object) |
| dispatch[StringType] = save_string |
| |
| def save_tuple(self, object): |
| |
| write = self.write |
| save = self.save |
| memo = self.memo |
| |
| d = id(object) |
| |
| write(MARK) |
| |
| for element in object: |
| save(element) |
| |
| if (len(object) and memo.has_key(d)): |
| if (self.bin): |
| write(POP_MARK + self.get(memo[d][0])) |
| return |
| |
| write(POP * (len(object) + 1) + self.get(mem[d][0])) |
| return |
| |
| memo_len = len(memo) |
| self.write(TUPLE + self.put(memo_len)) |
| memo[d] = (memo_len, object) |
| dispatch[TupleType] = save_tuple |
| |
| def save_empty_tuple(self, object): |
| self.write(EMPTY_TUPLE) |
| |
| def save_list(self, object): |
| d = id(object) |
| |
| write = self.write |
| save = self.save |
| memo = self.memo |
| |
| if (self.bin): |
| write(EMPTY_LIST) |
| else: |
| write(MARK + LIST) |
| |
| memo_len = len(memo) |
| write(self.put(memo_len)) |
| memo[d] = (memo_len, object) |
| |
| using_appends = (self.bin and (len(object) > 1)) |
| |
| if (using_appends): |
| write(MARK) |
| |
| for element in object: |
| save(element) |
| |
| if (not using_appends): |
| write(APPEND) |
| |
| if (using_appends): |
| write(APPENDS) |
| dispatch[ListType] = save_list |
| |
| def save_dict(self, object): |
| d = id(object) |
| |
| write = self.write |
| save = self.save |
| memo = self.memo |
| |
| if (self.bin): |
| write(EMPTY_DICT) |
| else: |
| write(MARK + DICT) |
| |
| memo_len = len(memo) |
| self.write(self.put(memo_len)) |
| memo[d] = (memo_len, object) |
| |
| using_setitems = (self.bin and (len(object) > 1)) |
| |
| if (using_setitems): |
| write(MARK) |
| |
| items = object.items() |
| for key, value in items: |
| save(key) |
| save(value) |
| |
| if (not using_setitems): |
| write(SETITEM) |
| |
| if (using_setitems): |
| write(SETITEMS) |
| |
| dispatch[DictionaryType] = save_dict |
| |
| def save_inst(self, object): |
| d = id(object) |
| cls = object.__class__ |
| |
| memo = self.memo |
| write = self.write |
| save = self.save |
| |
| if hasattr(object, '__getinitargs__'): |
| args = object.__getinitargs__() |
| len(args) # XXX Assert it's a sequence |
| _keep_alive(args, memo) |
| else: |
| args = () |
| |
| write(MARK) |
| |
| if (self.bin): |
| save(cls) |
| |
| for arg in args: |
| save(arg) |
| |
| memo_len = len(memo) |
| if (self.bin): |
| write(OBJ + self.put(memo_len)) |
| else: |
| write(INST + cls.__module__ + '\n' + cls.__name__ + '\n' + |
| self.put(memo_len)) |
| |
| memo[d] = (memo_len, object) |
| |
| try: |
| getstate = object.__getstate__ |
| except AttributeError: |
| stuff = object.__dict__ |
| else: |
| stuff = getstate() |
| _keep_alive(stuff, memo) |
| save(stuff) |
| write(BUILD) |
| dispatch[InstanceType] = save_inst |
| |
| def save_global(self, object, name = None): |
| write = self.write |
| memo = self.memo |
| |
| if (name is None): |
| name = object.__name__ |
| |
| try: |
| module = object.__module__ |
| except AttributeError: |
| module = whichmodule(object, name) |
| |
| memo_len = len(memo) |
| write(GLOBAL + module + '\n' + name + '\n' + |
| self.put(memo_len)) |
| memo[id(object)] = (memo_len, object) |
| dispatch[ClassType] = save_global |
| dispatch[FunctionType] = save_global |
| dispatch[BuiltinFunctionType] = save_global |
| |
| |
| def _keep_alive(x, memo): |
| """Keeps a reference to the object x in the memo. |
| |
| Because we remember objects by their id, we have |
| to assure that possibly temporary objects are kept |
| alive by referencing them. |
| We store a reference at the id of the memo, which should |
| normally not be used unless someone tries to deepcopy |
| the memo itself... |
| """ |
| try: |
| memo[id(memo)].append(x) |
| except KeyError: |
| # aha, this is the first one :-) |
| memo[id(memo)]=[x] |
| |
| |
| classmap = {} |
| |
| # This is no longer used to find classes, but still for functions |
| def whichmodule(cls, clsname): |
| """Figure out the module in which a class occurs. |
| |
| Search sys.modules for the module. |
| Cache in classmap. |
| Return a module name. |
| If the class cannot be found, return __main__. |
| """ |
| if classmap.has_key(cls): |
| return classmap[cls] |
| import sys |
| |
| for name, module in sys.modules.items(): |
| if name != '__main__' and \ |
| hasattr(module, clsname) and \ |
| getattr(module, clsname) is cls: |
| break |
| else: |
| name = '__main__' |
| classmap[cls] = name |
| return name |
| |
| |
| class Unpickler: |
| |
| def __init__(self, file): |
| self.readline = file.readline |
| self.read = file.read |
| self.memo = {} |
| |
| def load(self): |
| self.mark = ['spam'] # Any new unique object |
| self.stack = [] |
| self.append = self.stack.append |
| read = self.read |
| dispatch = self.dispatch |
| try: |
| while 1: |
| key = read(1) |
| dispatch[key](self) |
| except STOP, value: |
| return value |
| |
| def marker(self): |
| stack = self.stack |
| mark = self.mark |
| k = len(stack)-1 |
| while stack[k] is not mark: k = k-1 |
| return k |
| |
| dispatch = {} |
| |
| def load_eof(self): |
| raise EOFError |
| dispatch[''] = load_eof |
| |
| def load_persid(self): |
| pid = self.readline()[:-1] |
| self.append(self.persistent_load(pid)) |
| dispatch[PERSID] = load_persid |
| |
| def load_binpersid(self): |
| stack = self.stack |
| |
| pid = stack[-1] |
| del stack[-1] |
| |
| self.append(self.persistent_load(pid)) |
| dispatch[BINPERSID] = load_binpersid |
| |
| def load_none(self): |
| self.append(None) |
| dispatch[NONE] = load_none |
| |
| def load_int(self): |
| self.append(string.atoi(self.readline()[:-1])) |
| dispatch[INT] = load_int |
| |
| def load_binint(self): |
| self.append(mloads('i' + self.read(4))) |
| dispatch[BININT] = load_binint |
| |
| def load_binint1(self): |
| self.append(mloads('i' + self.read(1) + '\000\000\000')) |
| dispatch[BININT1] = load_binint1 |
| |
| def load_binint2(self): |
| self.append(mloads('i' + self.read(2) + '\000\000')) |
| dispatch[BININT2] = load_binint2 |
| |
| def load_long(self): |
| self.append(string.atol(self.readline()[:-1], 0)) |
| dispatch[LONG] = load_long |
| |
| def load_float(self): |
| self.append(string.atof(self.readline()[:-1])) |
| dispatch[FLOAT] = load_float |
| |
| def load_string(self): |
| self.append(eval(self.readline()[:-1], |
| {'__builtins__': {}})) # Let's be careful |
| dispatch[STRING] = load_string |
| |
| def load_binstring(self): |
| len = mloads('i' + self.read(4)) |
| self.append(self.read(len)) |
| dispatch[BINSTRING] = load_binstring |
| |
| def load_short_binstring(self): |
| len = mloads('i' + self.read(1) + '\000\000\000') |
| self.append(self.read(len)) |
| dispatch[SHORT_BINSTRING] = load_short_binstring |
| |
| def load_tuple(self): |
| k = self.marker() |
| self.stack[k:] = [tuple(self.stack[k+1:])] |
| dispatch[TUPLE] = load_tuple |
| |
| def load_empty_tuple(self): |
| self.stack.append(()) |
| dispatch[EMPTY_TUPLE] = load_empty_tuple |
| |
| def load_empty_list(self): |
| self.stack.append([]) |
| dispatch[EMPTY_LIST] = load_empty_list |
| |
| def load_empty_dictionary(self): |
| self.stack.append({}) |
| dispatch[EMPTY_DICT] = load_empty_dictionary |
| |
| def load_list(self): |
| k = self.marker() |
| self.stack[k:] = [self.stack[k+1:]] |
| dispatch[LIST] = load_list |
| |
| def load_dict(self): |
| k = self.marker() |
| d = {} |
| items = self.stack[k+1:] |
| for i in range(0, len(items), 2): |
| key = items[i] |
| value = items[i+1] |
| d[key] = value |
| self.stack[k:] = [d] |
| dispatch[DICT] = load_dict |
| |
| def load_inst(self): |
| k = self.marker() |
| args = tuple(self.stack[k+1:]) |
| del self.stack[k:] |
| module = self.readline()[:-1] |
| name = self.readline()[:-1] |
| klass = self.find_class(module, name) |
| instantiated = 0 |
| if (not args and type(klass) is ClassType and |
| not hasattr(klass, "__getinitargs__")): |
| try: |
| value = _EmptyClass() |
| value.__class__ = klass |
| except RuntimeError: |
| # In restricted execution, assignment to inst.__class__ is |
| # prohibited |
| pass |
| if not instantiated: |
| value = apply(klass, args) |
| self.append(value) |
| dispatch[INST] = load_inst |
| |
| def load_obj(self): |
| stack = self.stack |
| k = self.marker() |
| klass = stack[k + 1] |
| del stack[k + 1] |
| args = tuple(stack[k + 1:]) |
| del stack[k:] |
| instantiated = 0 |
| if (not args and type(klass) is ClassType and |
| not hasattr(klass, "__getinitargs__")): |
| try: |
| value = _EmptyClass() |
| value.__class__ = klass |
| instantiated = 1 |
| except RuntimeError: |
| # In restricted execution, assignment to inst.__class__ is |
| # prohibited |
| pass |
| if not instantiated: |
| value = apply(klass, args) |
| self.append(value) |
| dispatch[OBJ] = load_obj |
| |
| def load_global(self): |
| module = self.readline()[:-1] |
| name = self.readline()[:-1] |
| klass = self.find_class(module, name) |
| self.append(klass) |
| dispatch[GLOBAL] = load_global |
| |
| def find_class(self, module, name): |
| env = {} |
| |
| try: |
| exec 'from %s import %s' % (module, name) in env |
| except ImportError: |
| raise SystemError, \ |
| "Failed to import class %s from module %s" % \ |
| (name, module) |
| klass = env[name] |
| return klass |
| |
| def load_reduce(self): |
| stack = self.stack |
| |
| callable = stack[-2] |
| arg_tup = stack[-1] |
| del stack[-2:] |
| |
| if type(callable) is not ClassType: |
| if not safe_constructors.has_key(callable): |
| try: |
| safe = callable.__safe_for_unpickling__ |
| except AttributeError: |
| safe = None |
| |
| if (not safe): |
| raise UnpicklingError, "%s is not safe for " \ |
| "unpickling" % callable |
| |
| if arg_tup is None: |
| value = callable.__basicnew__() |
| else: |
| value = apply(callable, arg_tup) |
| self.append(value) |
| dispatch[REDUCE] = load_reduce |
| |
| def load_pop(self): |
| del self.stack[-1] |
| dispatch[POP] = load_pop |
| |
| def load_pop_mark(self): |
| k = self.marker() |
| del self.stack[k:] |
| dispatch[POP_MARK] = load_pop_mark |
| |
| def load_dup(self): |
| self.append(stack[-1]) |
| dispatch[DUP] = load_dup |
| |
| def load_get(self): |
| self.append(self.memo[self.readline()[:-1]]) |
| dispatch[GET] = load_get |
| |
| def load_binget(self): |
| i = mloads('i' + self.read(1) + '\000\000\000') |
| self.append(self.memo[`i`]) |
| dispatch[BINGET] = load_binget |
| |
| def load_long_binget(self): |
| i = mloads('i' + self.read(4)) |
| self.append(self.memo[`i`]) |
| dispatch[LONG_BINGET] = load_long_binget |
| |
| def load_put(self): |
| self.memo[self.readline()[:-1]] = self.stack[-1] |
| dispatch[PUT] = load_put |
| |
| def load_binput(self): |
| i = mloads('i' + self.read(1) + '\000\000\000') |
| self.memo[`i`] = self.stack[-1] |
| dispatch[BINPUT] = load_binput |
| |
| def load_long_binput(self): |
| i = mloads('i' + self.read(4)) |
| self.memo[`i`] = self.stack[-1] |
| dispatch[LONG_BINPUT] = load_long_binput |
| |
| def load_append(self): |
| stack = self.stack |
| value = stack[-1] |
| del stack[-1] |
| list = stack[-1] |
| list.append(value) |
| dispatch[APPEND] = load_append |
| |
| def load_appends(self): |
| stack = self.stack |
| mark = self.marker() |
| list = stack[mark - 1] |
| for i in range(mark + 1, len(stack)): |
| list.append(stack[i]) |
| |
| del stack[mark:] |
| dispatch[APPENDS] = load_appends |
| |
| def load_setitem(self): |
| stack = self.stack |
| value = stack[-1] |
| key = stack[-2] |
| del stack[-2:] |
| dict = stack[-1] |
| dict[key] = value |
| dispatch[SETITEM] = load_setitem |
| |
| def load_setitems(self): |
| stack = self.stack |
| mark = self.marker() |
| dict = stack[mark - 1] |
| for i in range(mark + 1, len(stack), 2): |
| dict[stack[i]] = stack[i + 1] |
| |
| del stack[mark:] |
| dispatch[SETITEMS] = load_setitems |
| |
| def load_build(self): |
| stack = self.stack |
| value = stack[-1] |
| del stack[-1] |
| inst = stack[-1] |
| try: |
| setstate = inst.__setstate__ |
| except AttributeError: |
| try: |
| inst.__dict__.update(value) |
| except RuntimeError: |
| # XXX In restricted execution, the instance's __dict__ is not |
| # accessible. Use the old way of unpickling the instance |
| # variables. This is a semantic different when unpickling in |
| # restricted vs. unrestricted modes. |
| for k, v in value.items(): |
| setattr(inst, k, v) |
| else: |
| setstate(value) |
| dispatch[BUILD] = load_build |
| |
| def load_mark(self): |
| self.append(self.mark) |
| dispatch[MARK] = load_mark |
| |
| def load_stop(self): |
| value = self.stack[-1] |
| del self.stack[-1] |
| raise STOP, value |
| dispatch[STOP] = load_stop |
| |
| # Helper class for load_inst/load_obj |
| |
| class _EmptyClass: |
| pass |
| |
| # Shorthands |
| |
| from StringIO import StringIO |
| |
| def dump(object, file, bin = 0): |
| Pickler(file, bin).dump(object) |
| |
| def dumps(object, bin = 0): |
| file = StringIO() |
| Pickler(file, bin).dump(object) |
| return file.getvalue() |
| |
| def load(file): |
| return Unpickler(file).load() |
| |
| def loads(str): |
| file = StringIO(str) |
| return Unpickler(file).load() |
| |
| |
| # The rest is used for testing only |
| |
| class C: |
| def __cmp__(self, other): |
| return cmp(self.__dict__, other.__dict__) |
| |
| def test(): |
| fn = 'out' |
| c = C() |
| c.foo = 1 |
| c.bar = 2 |
| x = [0, 1, 2, 3] |
| y = ('abc', 'abc', c, c) |
| x.append(y) |
| x.append(y) |
| x.append(5) |
| f = open(fn, 'w') |
| F = Pickler(f) |
| F.dump(x) |
| f.close() |
| f = open(fn, 'r') |
| U = Unpickler(f) |
| x2 = U.load() |
| print x |
| print x2 |
| print x == x2 |
| print map(id, x) |
| print map(id, x2) |
| print F.memo |
| print U.memo |
| |
| if __name__ == '__main__': |
| test() |