Pythonの__xxx__の集計
(追記、まとめはこちら Pythonの__xxx__まとめ)
Python2.7.3のコードから__xxx__の形の文字列が何回でてくるかを集計した。まずは*.cと*.hの中を集計したもの。C言語レベルで使われている物もまざっている。__LP64__とか__GNUC__とか。Pythonコードに対する集計はこのリストの下。
__doc__ 1278 __LP64__ 317 __in_len__ 206 __in__ 183 __UNUSED__ 180 __len__ 169 __attribute__ 77 __dict__ 74 __init__ 70 __format__ 68 __reduce__ 62 __out__ 61 __GNUC__ 55 __new__ 51 __name__ 49 __APPLE__ 48 __builtin__ 41 __class__ 40 __error__ 40 __mode__ 36 __CYGWIN__ 34 __getitem__ 34 __LINE__ 34 __main__ 31 __bases__ 30 __ppc64__ 29 __FILE__ 28 __x86_64__ 27 __sizeof__ 26 __asm__ 25 __module__ 25 __del__ 25 __BORLANDC__ 25 __ppc__ 25 __builtins__ 23 __contains__ 22 __SH4__ 21 __setstate__ 21 __FreeBSD__ 21 __BEOS__ 20 __i386__ 20 __NetBSD__ 19 __buf__ 18 __trunc__ 17 __int__ 15 __str__ 15 __cmp__ 15 __call__ 15 __getattr__ 15 __length_hint__ 15 __coerce__ 15 __version__ 15 __eq__ 14 __QNX__ 14 __enter__ 13 __exit__ 13 __file__ 13 __getstate__ 13 __copy__ 13 __import__ 13 __path__ 12 __delitem__ 12 __setitem__ 12 __mul__ 12 __future__ 12 __WATCOMC__ 12 __index__ 12 __pow__ 11 __hash__ 11 __SI__ 10 __DI__ 10 __s390x__ 10 __abstractmethods__ 9 __unicode__ 9 __getslice__ 9 __getnewargs__ 9 __members__ 9 __self__ 9 __reduce_ex__ 9 __add__ 9 __delattr__ 8 __setattr__ 8 __weakref__ 8 __STDC__ 8 __HI__ 8 __repr__ 8 __QI__ 8 __package__ 8 __newobj__ 8 __reversed__ 7 __nonzero__ 7 __LITTLE_ENDIAN__ 7 __setslice__ 7 __getattribute__ 7 __OpenBSD__ 7 __slots__ 7 __methods__ 7 __delslice__ 7 __getinitargs__ 7 __lt__ 6 __LONG_LONG_MAX__ 6 __unused__ 6 __proc__ 6 __ne__ 6 __missing__ 6 __rpow__ 6 __iter__ 6 __subclasscheck__ 6 __DragonFly__ 6 __TURBOC__ 6 __GNUC_MINOR__ 6 __dir__ 6 __CHAR_UNSIGNED__ 5 __get__ 5 __deepcopy__ 5 __gt__ 5 __iadd__ 5 __MVS__ 5 __instancecheck__ 5 __osf__ 5 __setformat__ 5 ___hello__ 5 __imul__ 5 __le__ 5 __ge__ 5 __ipow__ 5 __debug__ 5 __ctypes_from_outparam__ 4 __volatile__ 4 __MWERKS__ 4 __oct__ 4 __CRIS__ 4 __long__ 4 __SC__ 4 __all__ 4 __rmul__ 4 __complex__ 4 __hex__ 4 __delete__ 4 __float__ 4 __set__ 4 __abs__ 4 __invert__ 4 __OS400__ 4 __IBMC__ 4 __ctype_be__ 4 __getformat__ 4 __visibility__ 4 __pos__ 4 __STDC_VERSION__ 4 __GLIBC__ 4 __ctype_le__ 4 __neg__ 4 __irshift__ 3 __stderr__ 3 __rshift__ 3 __alignof__ 3 __getinitargs___ 3 __dict___ 3 __amigaos4__ 3 __metaclass__ 3 __MyCompanyName__ 3 __truediv__ 3 __STDC_SECURE_LIB__ 3 __imod__ 3 __stdout__ 3 __iand__ 3 __MIPSEB__ 3 __idiv__ 3 __ifloordiv__ 3 __main___ 3 __name___ 3 _____ 3 __xor__ 3 __ior__ 3 __and__ 3 __func__ 3 __loader__ 3 __ilshift__ 3 __class___ 3 __ixor__ 3 __isub__ 3 __author__ 3 __lshift__ 3 __mod__ 3 __itruediv__ 3 __about__ 3 __floordiv__ 3 __sub__ 3 __radd__ 3 __OS2__ 3 __or__ 3 __FRV_FDPIC__ 3 __stdin__ 3 __BUILTIN___ 3 __div__ 3 __NO_FPRS__ 3 __LDBL_MANT_DIG__ 2 __ror__ 2 __HOS_AIX__ 2 __objclass__ 2 __rdiv__ 2 __code__ 2 __powerpc64__ 2 __linux__ 2 __TOS_OS2__ 2 __LCC__ 2 __FLAT__ 2 __defaults__ 2 __reduce___ 2 __LONG_DOUBLE_128__ 2 __BIG_ENDIAN__ 2 __TIME__ 2 __rsub__ 2 __rrshift__ 2 __rlshift__ 2 __MACTYPES__ 2 __WIN32__ 2 __SMALL__ 2 __rmod__ 2 __warningregistry__ 2 __conform__ 2 __phello__ 2 __MSDOS__ 2 __getstate___ 2 __excepthook__ 2 __rxor__ 2 __MACH__ 2 __divmod__ 2 __386__ 2 __reduce_ex___ 2 __VERSION__ 2 __subclasses__ 2 __foo__ 2 __INSURE__ 2 __rand__ 2 ___subclasscheck__ 2 __alloc__ 2 __________________________________ 2 __SCO_VERSION__ 2 __exit__doc__ 2 ______ 2 __rdivmod__ 2 __hello__ 2 __USLC__ 2 __isdir__doc__ 2 __rtruediv__ 2 __itemsize__ 2 __name__doc__ 2 __adapt__ 2 __MEDIUM__ 2 ___instancecheck__ 2 ___init__ 2 ___import__ 2 __PROC__ 2 __alpha__ 2 __MINGW32__ 2 __arch64__ 2 __rfloordiv__ 2 __DATE__ 2 __setstate___ 2 __displayhook__ 2 __powerpc__ 2 ___new__ 2 __IBMCPP__ 2 __concat__ 1 __HITACHI__ 1 __noinline__ 1 __builtin___ 1 __hppa__ 1 __inv__ 1 __COMPACT__ 1 ______________________________________________________________ 1 __gnu_linux__ 1 __iconcat__ 1 __weakrefoffset__ 1 __id__ 1 __copyright__ 1 ______________________ 1 __subclasshook__ 1 __basicsize__ 1 __EXTENSIONS__ 1 __repeat__ 1 __whatever__ 1 __deprecated__ 1 __mro__ 1 __next__ 1 __64BIT__ 1 __DJGPP__ 1 __lltrace__ 1 _______________________________________________________________________ 1 __not__ 1 __________________________________________________________________ 1 _______________________________ 1 __sun__ 1 __LARGE__ 1 __flags__ 1 __EMX__ 1 __KAME__ 1 __closure__ 1 ___main__ 1 __hpux__ 1 __slotnames__ 1 __irepeat__ 1 __svr4__ 1 __digital__ 1 __xx__ 1 ____________ 1 __base__ 1 __rtems__ 1 __ELF__ 1 __globals__ 1 __unix__ 1 __dictoffset__ 1 __MULTI__ 1 __self_class__ 1 ________ 1 __thisclass__ 1 __FUNCTION__ 1 __OPTIMIZE__ 1 _________ 1
py
一方で*.pyに対して同じ事をやったものはこちら。こっちのほうが期待していたものに近いな。コンストラクタ__init__が一番多く、ライブラリとしてインポートされたかスクリプトとして実行されたかを判断するのに使う__name__と__main__のセットが次に多い(__name__の方が600件ほど多いってことはそれ以外の使い方をしているケースが600件あるってことだな)
あるインスタンスがどのクラスであるか(__class__)や、そのインスタンスがどんなメンバを持っているか(__dict__)は、Pythonを学び始めの人にすぐ必要にはならないかなぁ。
__init__ 3058 __name__ 1729 __main__ 1191 __class__ 564 __dict__ 524 __repr__ 392 __getitem__ 378 __file__ 341 __all__ 299 __doc__ 255 __str__ 217 __iter__ 206 __hash__ 195 __len__ 175 __slots__ 175 __builtin__ 166 __eq__ 164 __call__ 161 __new__ 160 __cmp__ 157 __future__ 157 __del__ 154 __exit__ 150 __setitem__ 148 __getattr__ 138 __contains__ 133 __format__ 131 __import__ 125 __enter__ 119 __version__ 112 __add__ 107 __metaclass__ 101 __module__ 100 __bases__ 95 __debug__ 83 __delitem__ 82 __path__ 81 __setstate__ 70 __get__ 66 __mod__ 60 __int__ 58 __ne__ 58 __reduce__ 58 __coerce__ 57 __getattribute__ 57 __mul__ 55 __builtins__ 52 __setattr__ 50 __revision__ 48 __lt__ 47 __loader__ 47 __float__ 47 __getstate__ 45 __getslice__ 45 __mro__ 45 __sub__ 43 __nonzero__ 41 __package__ 40 __c__ 40 __b__ 40 __unicode__ 40 __le__ 40 __a__ 40 __missing__ 39 __test__ 39 __stderr__ 35 __gt__ 35 __complex__ 35 __floordiv__ 35 __radd__ 35 __index__ 35 __next__ 34 __out__ 33 __ge__ 33 __rmul__ 32 __ctype_be__ 32 __ctype_le__ 32 __setslice__ 31 __iadd__ 31 __author__ 30 __long__ 29 __truediv__ 29 __pow__ 28 __div__ 28 __weakref__ 26 __attribute__ 26 __rfloordiv__ 25 __set__ 25 __getformat__ 24 __imul__ 23 __aepack__ 23 __warningregistry__ 23 __code__ 22 __rsub__ 22 __stdout__ 21 __rpow__ 20 __in__ 20 __delattr__ 19 __or__ 19 __rdiv__ 17 __trunc__ 17 __and__ 17 __delslice__ 17 __reversed__ 16 __abs__ 16 __LINE__ 15 __reduce_ex__ 15 __setformat__ 15 __divmod__ 15 __subclasscheck__ 14 __rmod__ 14 __deepcopy__ 13 __getnewargs__ 13 __phello__ 13 __copy__ 13 __xor__ 13 __in_len__ 13 __getinitargs__ 13 __isub__ 12 __LP64__ 11 __iand__ 11 __credits__ 11 __GNUC__ 11 __self__ 11 __rtruediv__ 11 __CONCAT__ 11 __neg__ 11 __pos__ 10 __decimal_context__ 10 __abstractmethods__ 10 __newobj__ 10 __ior__ 10 __ixor__ 10 __delete__ 10 __trace_output__ 9 __date__ 9 __safe_for_unpickling__ 9 __spam__ 9 __GNUCLIKE___ 9 __methods__ 9 __annotations__ 9 __ipow__ 9 __ror__ 8 __rshift__ 8 __subclasshook__ 8 __rxor__ 8 __callable__ 8 __ifloordiv__ 8 __length_hint__ 8 __rdivmod__ 8 __isabstractmethod__ 8 __lshift__ 8 __rand__ 8 __idiv__ 8 __objclass__ 7 __irshift__ 7 __NETLIB_VERSION__ 7 __copyright__ 7 __instancecheck__ 7 __UNDEF__ 7 __rlshift__ 7 __op__ 7 __ispkg__ 7 __rop__ 7 __rrshift__ 7 __ilshift__ 7 __imod__ 7 __format_arg__ 6 __bool__ 6 __oct__ 6 __section__ 6 __attribute_format_arg__ 6 __importer__ 6 __itruediv__ 6 __aligned__ 6 __trace_call__ 6 __members__ 6 ____C__ 6 __GLIBC__ 6 __hello__ 6 __GLIBC_MINOR__ 6 __GNU_LIBRARY__ 5 __STDC_IEC_559__ 5 __error__ 5 __return__ 5 __hex__ 5 __subclasses__ 5 __invert__ 5 __STDC_IEC_559_COMPLEX__ 5 __26__ 5 __unittest_skip__ 5 __dir__ 5 __flags__ 5 __USER_LABEL_PREFIX__ 5 __helperinit__ 4 __bootstrap__ 4 ____________________________________________________________ 4 __stdin__ 4 __as_immutable__ 4 __kp__ 4 _____ 4 __setup__ 4 __func__ 4 __rawmain__ 4 __methodwrapper__ 4 __helper__ 4 __STDC_ISO_10646__ 3 __nonnull__ 3 __formalclass__ 3 ___str__ 3 __BIT_TYPES_DEFINED__ 3 __basicsize__ 3 __CC_SUPPORTS___ 3 __proc__ 3 __as_temporarily_immutable__ 3 __CC_SUPPORTS___INLINE__ 3 __alloc__ 3 __realdict__ 3 ______ 3 __rcmp__ 3 __runpy_pkg__ 3 __unittest_skip_why__ 3 __lock__ 3 __CC_SUPPORTS___FUNC__ 3 __pkgdir__ 2 __buf__ 2 __conform__ 2 __slotnames__ 2 __args__ 2 __test_name__ 2 __iop__ 2 __console__ 2 __temp__ 2 __subclass__ 2 __usergetattr__ 2 __value__ 2 __dummy__ 2 __attributes__ 2 __GL_GET_H__ 2 __subclassing__ 2 __meta_init__ 2 __klass__ 2 ___file__ 2 __sizeof__ 2 __not_mangled__ 2 __cause__ 2 __namespace__ 2 __parents_main__ 2 __displayhook__ 2 __iconcat__ 1 __docformat__ 1 __base__ 1 __xyz__ 1 __email__ 1 __cached__ 1 __ceil__ 1 __non__zero__ 1 __license__ 1 ____________________ 1 __excepthook__ 1 __traceback__ 1 ___contains__ 1 ___all__ 1 __dialog__ 1 __NETLIB_BASE_VERSION__ 1 __TABLE_NAMES__ 1 __irepeat__ 1 __class__with__dict__ 1 __about__ 1 __itemsize__ 1 _______________ 1 __inst__ 1 __context__ 1 __________________________ 1 __floor__ 1 __MSL__ 1 ________________________ 1 __exception__ 1 __foo__ 1 __status__ 1 __cvsid__ 1 __testdir__ 1 __x__ 1
import re import os from collections import Counter stat = Counter() for root, dirs, files in os.walk('.'): for f in files: if f.endswith('.py'): data = file(os.path.join(root, f)).read() words = re.findall("__\w+__", data) stat.update(words) for x in stat.most_common(): print "%s %d" % x
