bencharb

class CappedDict(collections.OrderedDict):
    default_max_size = 50
    def __init__(self, *args, **kwargs):
        self.max_size = kwargs.pop('max_size', self.default_max_size)
        super(CappedDict, self).__init__(*args, **kwargs)
        
    def __setitem__(self, key, val):
        if key not in self:
            max_size = self.max_size-1  # so the dict is sized properly after adding a key
            self._prune_dict(max_size)

bencharb

class CappedDict(collections.OrderedDict):
    default_max_size = 50
    def __init__(self, *args, **kwargs):
        self.max_size = kwargs.pop('max_size', self.default_max_size)
        super(CappedDict, self).__init__(*args, **kwargs)
        
    def __setitem__(self, key, val):
        if key not in self:
            max_size = self.max_size-1  # so the dict is sized properly after adding a key
            self._prune_dict(max_size)

bencharb

thread_args = (func_arg, inner_func, (outer_func, outer_arg1, outer_arg2),)

functoolz.thread_first(*thread_args)
# expands to
# outer_func(inner_func(func_arg), outer_arg1, outer_arg2)

functoolz.thread_last(*thread_args)
# expands to
# outer_func(outer_arg1, outer_arg2, inner_func(func_arg))

bencharb

def group_sequential_numbers(data):
    # In [4]: list(group_sequential_numbers((2,3,4,5,5,66,6,7,7,7,8,8,99,9)))
    # Out[4]: [[2, 3, 4, 5], [5], [66], [6, 7], [7], [7, 8], [8], [99], [9]]
    from operator import itemgetter
    from itertools import groupby
    groups = []
    for k, g in groupby(enumerate(data), lambda (i,x):i-x):
         yield map(itemgetter(1), g)

bencharb

def get_arg_indexes(*args):
    # In [8]: get_arg_indexes('zero_and_three', 'one', 'two', 'zero_and_three', 'four_and_five','four_and_five')
    # Out[8]: {'four_and_five': [4, 5], 'one': [1], 'two': [2], 'zero_and_three': [0, 3]}
    return {k:[i for i, test_key in enumerate(keys) if test_key==k] for k in keys}

bencharb

def multi_delete(list_, *indexes):
    # http://stackoverflow.com/questions/497426/deleting-multiple-elements-from-a-list
    for index in sorted(list(indexes), reverse=True):
        del list_[index]
    return list_

def indices(lst, element):
    # http://stackoverflow.com/questions/6294179/how-to-find-all-occurrences-of-an-element-in-a-list
    result = []
    offset = -1

bencharb

def strip_bad_unicode(okay_unicode_string):
    return ''.join(map(lambda char: char.encode('latin1').decode('utf8', 'ignore'), okay_unicode_string))

bencharb

# -----------------
# MIXINS: FORCE BP MAPPERS TO WORK FOR US
# -----------------


class AllowMissingObjectAttrsMixin(object):
    def _getattr_inner(self, *args, **kwargs):
        try:
            return super(AllowMissingObjectAttrsMixin, self)._getattr_inner(*args, **kwargs)

bencharb

import csv

class PGCopyCSVSQLStatement(object):
    delimiter = ','
    template = "COPY {table_name}({column_sequence}) FROM STDIN WITH DELIMITER '{delimiter}' CSV {optional_header}"
    def __init__(self,
                 table_name=None,
                 column_sequence=None,
                 delimiter=',',
                 has_header=None,

bencharb

DEFAULT_DELIM = '.'
NOPREFIX_PREFIX = '__NOPREFIX__'

import itertools
import collections
def is_non_string_sequence(seq):
    return isinstance(seq, collections.Sequence) and not isinstance(seq, basestring)
def is_dict(d):
    return isinstance(d, collections.Mapping) or hasattr(d, 'iteritems') and not isinstance(d, basestring)