cpython/Lib/collections.py
Raymond Hettinger b3a65f8d19 Move UserString to collections.
Removed decode() method.  Added isidentifier() and format() methods.
Drop MutableUserString class.
2008-02-21 22:11:37 +00:00

421 lines
17 KiB
Python

__all__ = ['deque', 'defaultdict', 'namedtuple', 'UserDict']
# For bootstrapping reasons, the collection ABCs are defined in _abcoll.py.
# They should however be considered an integral part of collections.py.
from _abcoll import *
import _abcoll
__all__ += _abcoll.__all__
from _collections import deque, defaultdict
from operator import itemgetter as _itemgetter
from keyword import iskeyword as _iskeyword
import sys as _sys
################################################################################
### namedtuple
################################################################################
def namedtuple(typename, field_names, verbose=False):
"""Returns a new subclass of tuple with named fields.
>>> Point = namedtuple('Point', 'x y')
>>> Point.__doc__ # docstring for the new class
'Point(x, y)'
>>> p = Point(11, y=22) # instantiate with positional args or keywords
>>> p[0] + p[1] # indexable like a plain tuple
33
>>> x, y = p # unpack like a regular tuple
>>> x, y
(11, 22)
>>> p.x + p.y # fields also accessable by name
33
>>> d = p._asdict() # convert to a dictionary
>>> d['x']
11
>>> Point(**d) # convert from a dictionary
Point(x=11, y=22)
>>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
Point(x=100, y=22)
"""
# Parse and validate the field names. Validation serves two purposes,
# generating informative error messages and preventing template injection attacks.
if isinstance(field_names, str):
field_names = field_names.replace(',', ' ').split() # names separated by whitespace and/or commas
field_names = tuple(field_names)
for name in (typename,) + field_names:
if not all(c.isalnum() or c=='_' for c in name):
raise ValueError('Type names and field names can only contain alphanumeric characters and underscores: %r' % name)
if _iskeyword(name):
raise ValueError('Type names and field names cannot be a keyword: %r' % name)
if name[0].isdigit():
raise ValueError('Type names and field names cannot start with a number: %r' % name)
seen_names = set()
for name in field_names:
if name.startswith('_'):
raise ValueError('Field names cannot start with an underscore: %r' % name)
if name in seen_names:
raise ValueError('Encountered duplicate field name: %r' % name)
seen_names.add(name)
# Create and fill-in the class template
numfields = len(field_names)
argtxt = repr(field_names).replace("'", "")[1:-1] # tuple repr without parens or quotes
reprtxt = ', '.join('%s=%%r' % name for name in field_names)
dicttxt = ', '.join('%r: t[%d]' % (name, pos) for pos, name in enumerate(field_names))
template = '''class %(typename)s(tuple):
'%(typename)s(%(argtxt)s)' \n
__slots__ = () \n
_fields = %(field_names)r \n
def __new__(cls, %(argtxt)s):
return tuple.__new__(cls, (%(argtxt)s)) \n
@classmethod
def _make(cls, iterable, new=tuple.__new__, len=len):
'Make a new %(typename)s object from a sequence or iterable'
result = new(cls, iterable)
if len(result) != %(numfields)d:
raise TypeError('Expected %(numfields)d arguments, got %%d' %% len(result))
return result \n
def __repr__(self):
return '%(typename)s(%(reprtxt)s)' %% self \n
def _asdict(t):
'Return a new dict which maps field names to their values'
return {%(dicttxt)s} \n
def _replace(self, **kwds):
'Return a new %(typename)s object replacing specified fields with new values'
result = self._make(map(kwds.pop, %(field_names)r, self))
if kwds:
raise ValueError('Got unexpected field names: %%r' %% kwds.keys())
return result \n\n''' % locals()
for i, name in enumerate(field_names):
template += ' %s = property(itemgetter(%d))\n' % (name, i)
if verbose:
print(template)
# Execute the template string in a temporary namespace
namespace = dict(itemgetter=_itemgetter)
try:
exec(template, namespace)
except SyntaxError as e:
raise SyntaxError(e.msg + ':\n' + template) from e
result = namespace[typename]
# For pickling to work, the __module__ variable needs to be set to the frame
# where the named tuple is created. Bypass this step in enviroments where
# sys._getframe is not defined (Jython for example).
if hasattr(_sys, '_getframe'):
result.__module__ = _sys._getframe(1).f_globals['__name__']
return result
################################################################################
### UserDict
################################################################################
class UserDict(MutableMapping):
# Start by filling-out the abstract methods
def __init__(self, dict=None, **kwargs):
self.data = {}
if dict is not None:
self.update(dict)
if len(kwargs):
self.update(kwargs)
def __len__(self): return len(self.data)
def __getitem__(self, key):
if key in self.data:
return self.data[key]
if hasattr(self.__class__, "__missing__"):
return self.__class__.__missing__(self, key)
raise KeyError(key)
def __setitem__(self, key, item): self.data[key] = item
def __delitem__(self, key): del self.data[key]
def __iter__(self):
return iter(self.data)
# Modify __contains__ to work correctly when __missing__ is present
def __contains__(self, key):
return key in self.data
# Now, add the methods in dicts but not in MutableMapping
def __repr__(self): return repr(self.data)
def copy(self):
if self.__class__ is UserDict:
return UserDict(self.data.copy())
import copy
data = self.data
try:
self.data = {}
c = copy.copy(self)
finally:
self.data = data
c.update(self)
return c
@classmethod
def fromkeys(cls, iterable, value=None):
d = cls()
for key in iterable:
d[key] = value
return d
################################################################################
### UserList
################################################################################
class UserList(MutableSequence):
"""A more or less complete user-defined wrapper around list objects."""
def __init__(self, initlist=None):
self.data = []
if initlist is not None:
# XXX should this accept an arbitrary sequence?
if type(initlist) == type(self.data):
self.data[:] = initlist
elif isinstance(initlist, UserList):
self.data[:] = initlist.data[:]
else:
self.data = list(initlist)
def __repr__(self): return repr(self.data)
def __lt__(self, other): return self.data < self.__cast(other)
def __le__(self, other): return self.data <= self.__cast(other)
def __eq__(self, other): return self.data == self.__cast(other)
def __ne__(self, other): return self.data != self.__cast(other)
def __gt__(self, other): return self.data > self.__cast(other)
def __ge__(self, other): return self.data >= self.__cast(other)
def __cast(self, other):
return other.data if isinstance(other, UserList) else other
def __cmp__(self, other):
return cmp(self.data, self.__cast(other))
def __contains__(self, item): return item in self.data
def __len__(self): return len(self.data)
def __getitem__(self, i): return self.data[i]
def __setitem__(self, i, item): self.data[i] = item
def __delitem__(self, i): del self.data[i]
def __add__(self, other):
if isinstance(other, UserList):
return self.__class__(self.data + other.data)
elif isinstance(other, type(self.data)):
return self.__class__(self.data + other)
return self.__class__(self.data + list(other))
def __radd__(self, other):
if isinstance(other, UserList):
return self.__class__(other.data + self.data)
elif isinstance(other, type(self.data)):
return self.__class__(other + self.data)
return self.__class__(list(other) + self.data)
def __iadd__(self, other):
if isinstance(other, UserList):
self.data += other.data
elif isinstance(other, type(self.data)):
self.data += other
else:
self.data += list(other)
return self
def __mul__(self, n):
return self.__class__(self.data*n)
__rmul__ = __mul__
def __imul__(self, n):
self.data *= n
return self
def append(self, item): self.data.append(item)
def insert(self, i, item): self.data.insert(i, item)
def pop(self, i=-1): return self.data.pop(i)
def remove(self, item): self.data.remove(item)
def count(self, item): return self.data.count(item)
def index(self, item, *args): return self.data.index(item, *args)
def reverse(self): self.data.reverse()
def sort(self, *args, **kwds): self.data.sort(*args, **kwds)
def extend(self, other):
if isinstance(other, UserList):
self.data.extend(other.data)
else:
self.data.extend(other)
################################################################################
### UserString
################################################################################
class UserString(Sequence):
def __init__(self, seq):
if isinstance(seq, str):
self.data = seq
elif isinstance(seq, UserString):
self.data = seq.data[:]
else:
self.data = str(seq)
def __str__(self): return str(self.data)
def __repr__(self): return repr(self.data)
def __int__(self): return int(self.data)
def __long__(self): return int(self.data)
def __float__(self): return float(self.data)
def __complex__(self): return complex(self.data)
def __hash__(self): return hash(self.data)
def __eq__(self, string):
if isinstance(string, UserString):
return self.data == string.data
return self.data == string
def __ne__(self, string):
if isinstance(string, UserString):
return self.data != string.data
return self.data != string
def __lt__(self, string):
if isinstance(string, UserString):
return self.data < string.data
return self.data < string
def __le__(self, string):
if isinstance(string, UserString):
return self.data <= string.data
return self.data <= string
def __gt__(self, string):
if isinstance(string, UserString):
return self.data > string.data
return self.data > string
def __ge__(self, string):
if isinstance(string, UserString):
return self.data >= string.data
return self.data >= string
def __contains__(self, char):
if isinstance(char, UserString):
char = char.data
return char in self.data
def __len__(self): return len(self.data)
def __getitem__(self, index): return self.__class__(self.data[index])
def __add__(self, other):
if isinstance(other, UserString):
return self.__class__(self.data + other.data)
elif isinstance(other, str):
return self.__class__(self.data + other)
return self.__class__(self.data + str(other))
def __radd__(self, other):
if isinstance(other, str):
return self.__class__(other + self.data)
return self.__class__(str(other) + self.data)
def __mul__(self, n):
return self.__class__(self.data*n)
__rmul__ = __mul__
def __mod__(self, args):
return self.__class__(self.data % args)
# the following methods are defined in alphabetical order:
def capitalize(self): return self.__class__(self.data.capitalize())
def center(self, width, *args):
return self.__class__(self.data.center(width, *args))
def count(self, sub, start=0, end=_sys.maxsize):
if isinstance(sub, UserString):
sub = sub.data
return self.data.count(sub, start, end)
def encode(self, encoding=None, errors=None): # XXX improve this?
if encoding:
if errors:
return self.__class__(self.data.encode(encoding, errors))
return self.__class__(self.data.encode(encoding))
return self.__class__(self.data.encode())
def endswith(self, suffix, start=0, end=_sys.maxsize):
return self.data.endswith(suffix, start, end)
def expandtabs(self, tabsize=8):
return self.__class__(self.data.expandtabs(tabsize))
def find(self, sub, start=0, end=_sys.maxsize):
if isinstance(sub, UserString):
sub = sub.data
return self.data.find(sub, start, end)
def format(self, *args, **kwds):
return self.data.format(*args, **kwds)
def index(self, sub, start=0, end=_sys.maxsize):
return self.data.index(sub, start, end)
def isalpha(self): return self.data.isalpha()
def isalnum(self): return self.data.isalnum()
def isdecimal(self): return self.data.isdecimal()
def isdigit(self): return self.data.isdigit()
def isidentifier(self): return self.data.isidentifier()
def islower(self): return self.data.islower()
def isnumeric(self): return self.data.isnumeric()
def isspace(self): return self.data.isspace()
def istitle(self): return self.data.istitle()
def isupper(self): return self.data.isupper()
def join(self, seq): return self.data.join(seq)
def ljust(self, width, *args):
return self.__class__(self.data.ljust(width, *args))
def lower(self): return self.__class__(self.data.lower())
def lstrip(self, chars=None): return self.__class__(self.data.lstrip(chars))
def partition(self, sep):
return self.data.partition(sep)
def replace(self, old, new, maxsplit=-1):
if isinstance(old, UserString):
old = old.data
if isinstance(new, UserString):
new = new.data
return self.__class__(self.data.replace(old, new, maxsplit))
def rfind(self, sub, start=0, end=_sys.maxsize):
return self.data.rfind(sub, start, end)
def rindex(self, sub, start=0, end=_sys.maxsize):
return self.data.rindex(sub, start, end)
def rjust(self, width, *args):
return self.__class__(self.data.rjust(width, *args))
def rpartition(self, sep):
return self.data.rpartition(sep)
def rstrip(self, chars=None):
return self.__class__(self.data.rstrip(chars))
def split(self, sep=None, maxsplit=-1):
return self.data.split(sep, maxsplit)
def rsplit(self, sep=None, maxsplit=-1):
return self.data.rsplit(sep, maxsplit)
def splitlines(self, keepends=0): return self.data.splitlines(keepends)
def startswith(self, prefix, start=0, end=_sys.maxsize):
return self.data.startswith(prefix, start, end)
def strip(self, chars=None): return self.__class__(self.data.strip(chars))
def swapcase(self): return self.__class__(self.data.swapcase())
def title(self): return self.__class__(self.data.title())
def translate(self, *args):
return self.__class__(self.data.translate(*args))
def upper(self): return self.__class__(self.data.upper())
def zfill(self, width): return self.__class__(self.data.zfill(width))
################################################################################
### Simple tests
################################################################################
if __name__ == '__main__':
# verify that instances can be pickled
from pickle import loads, dumps
Point = namedtuple('Point', 'x, y', True)
p = Point(x=10, y=20)
assert p == loads(dumps(p))
# test and demonstrate ability to override methods
class Point(namedtuple('Point', 'x y')):
__slots__ = ()
@property
def hypot(self):
return (self.x ** 2 + self.y ** 2) ** 0.5
def __str__(self):
return 'Point: x=%6.3f y=%6.3f hypot=%6.3f' % (self.x, self.y, self.hypot)
for p in Point(3, 4), Point(14, 5/7.):
print (p)
class Point(namedtuple('Point', 'x y')):
'Point class with optimized _make() and _replace() without error-checking'
__slots__ = ()
_make = classmethod(tuple.__new__)
def _replace(self, _map=map, **kwds):
return self._make(_map(kwds.get, ('x', 'y'), self))
print(Point(11, 22)._replace(x=100))
Point3D = namedtuple('Point3D', Point._fields + ('z',))
print(Point3D.__doc__)
import doctest
TestResults = namedtuple('TestResults', 'failed attempted')
print(TestResults(*doctest.testmod()))