dulwich/dulwich/_compat.py

# _compat.py -- For dealing with python2.4 oddness
# Copyright (C) 2008 Canonical Ltd.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; version 2
# of the License or (at your option) a later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
# MA  02110-1301, USA.

"""Misc utilities to work with python <2.6.

These utilities can all be deleted when dulwich decides it wants to stop
support for python <2.6.
"""
try:
    import hashlib
except ImportError:
    import sha

try:
    from urlparse import parse_qs
except ImportError:
    from cgi import parse_qs

try:
    from os import SEEK_CUR, SEEK_END
except ImportError:
    SEEK_CUR = 1
    SEEK_END = 2

import struct


class defaultdict(dict):
    """A python 2.4 equivalent of collections.defaultdict."""

    def __init__(self, default_factory=None, *a, **kw):
        if (default_factory is not None and
            not hasattr(default_factory, '__call__')):
            raise TypeError('first argument must be callable')
        dict.__init__(self, *a, **kw)
        self.default_factory = default_factory

    def __getitem__(self, key):
        try:
            return dict.__getitem__(self, key)
        except KeyError:
            return self.__missing__(key)

    def __missing__(self, key):
        if self.default_factory is None:
            raise KeyError(key)
        self[key] = value = self.default_factory()
        return value

    def __reduce__(self):
        if self.default_factory is None:
            args = tuple()
        else:
            args = self.default_factory,
        return type(self), args, None, None, self.items()

    def copy(self):
        return self.__copy__()

    def __copy__(self):
        return type(self)(self.default_factory, self)

    def __deepcopy__(self, memo):
        import copy
        return type(self)(self.default_factory,
                          copy.deepcopy(self.items()))
    def __repr__(self):
        return 'defaultdict(%s, %s)' % (self.default_factory,
                                        dict.__repr__(self))


def make_sha(source=''):
    """A python2.4 workaround for the sha/hashlib module fiasco."""
    try:
        return hashlib.sha1(source)
    except NameError:
        sha1 = sha.sha(source)
        return sha1


def unpack_from(fmt, buf, offset=0):
    """A python2.4 workaround for struct missing unpack_from."""
    try:
        return struct.unpack_from(fmt, buf, offset)
    except AttributeError:
        b = buf[offset:offset+struct.calcsize(fmt)]
        return struct.unpack(fmt, b)


try:
    from itertools import permutations
except ImportError:
    # Implementation of permutations from Python 2.6 documentation:
    # http://docs.python.org/2.6/library/itertools.html#itertools.permutations
    # Copyright (c) 2001-2010 Python Software Foundation; All Rights Reserved
    # Modified syntax slightly to run under Python 2.4.
    def permutations(iterable, r=None):
        # permutations('ABCD', 2) --> AB AC AD BA BC BD CA CB CD DA DB DC
        # permutations(range(3)) --> 012 021 102 120 201 210
        pool = tuple(iterable)
        n = len(pool)
        if r is None:
            r = n
        if r > n:
            return
        indices = range(n)
        cycles = range(n, n-r, -1)
        yield tuple(pool[i] for i in indices[:r])
        while n:
            for i in reversed(range(r)):
                cycles[i] -= 1
                if cycles[i] == 0:
                    indices[i:] = indices[i+1:] + indices[i:i+1]
                    cycles[i] = n - i
                else:
                    j = cycles[i]
                    indices[i], indices[-j] = indices[-j], indices[i]
                    yield tuple(pool[i] for i in indices[:r])
                    break
            else:
                return


try:
    all = all
except NameError:
    # Implementation of permutations from Python 2.6 documentation:
    # http://docs.python.org/2.6/library/functions.html#all
    # Copyright (c) 2001-2010 Python Software Foundation; All Rights Reserved
    # Licensed under the Python Software Foundation License.
    def all(iterable):
        for element in iterable:
            if not element:
                return False
        return True


try:
    from collections import namedtuple
except ImportError:
    # Recipe for namedtuple from http://code.activestate.com/recipes/500261/
    # Copyright (c) 2007 Python Software Foundation; All Rights Reserved
    # Licensed under the Python Software Foundation License.
    from operator import itemgetter as _itemgetter
    from keyword import iskeyword as _iskeyword
    import sys as _sys

    def namedtuple(typename, field_names, verbose=False, rename=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, basestring):
            field_names = field_names.replace(',', ' ').split() # names separated by whitespace and/or commas
        field_names = tuple(map(str, field_names))
        if rename:
            names = list(field_names)
            seen = set()
            for i, name in enumerate(names):
                if (not min(c.isalnum() or c=='_' for c in name) or _iskeyword(name)
                    or not name or name[0].isdigit() or name.startswith('_')
                    or name in seen):
                        names[i] = '_%d' % i
                seen.add(name)
            field_names = tuple(names)
        for name in (typename,) + field_names:
            if not min(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('_') and not rename:
                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)
        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(self):
            'Return a new dict which maps field names to their values'
            return dict(zip(self._fields, self)) \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
        def __getnewargs__(self):
            return tuple(self) \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, __name__='namedtuple_%s' % typename,
                         _property=property, _tuple=tuple)
        try:
            exec template in namespace
        except SyntaxError, e:
            raise SyntaxError(e.message + ':\n' + template)
        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) or sys._getframe is not
        # defined for arguments greater than 0 (IronPython).
        try:
            result.__module__ = _sys._getframe(1).f_globals.get('__name__', '__main__')
        except (AttributeError, ValueError):
            pass

        return result