bencharb

/*
QUERY Apple Messages sqlite database 
at ~/Library/Messages/chat.db
*/

select 
  datetime(m.date + strftime('%s','2001-01-01'), 'unixepoch', 'localtime') as dt
, m.text
, c.chat_identifier

bencharb

// Utilities

var td_mill = {
	second: 1000
}
td_mill.minute = td_mill.second * 60; 
td_mill.hour = td_mill.minute * 60; 
td_mill.day = td_mill.hour * 24; 

bencharb

'''
Transform Bank of America PDF text into tables. 

Example: 
python parse_boa_statements.py test/joint_dump.txt test/pers_dump.txt --output test/combined.csv

Example of original PDF text (copy/pasted from PDF):
    MISTER NAME | Account # 999 99999 9999  | November 24, 2015 to December 24, 2015
    Your checking account
    Page 3 of 4

bencharb

import os
import datetime
import time
import shove

SEC = 1
MIN = SEC * 60
HOUR = MIN * 60
DAY = HOUR * 24

bencharb

'''
Move a file to a backup, if the file exists. If context manager statement fails, then restore the backup.
'''

class FakeException(Exception):
    pass

def create_backup_path(path, backup_ext='.bak'):
    backup_path = path
    while backup_path == path or os.path.exists(backup_path):

bencharb

import string
import re
import jinja2

def split_many(astring, *split_on_chars, **kwargs):
    """
    Split a string on many values.

    :param split_on_chars: string to split
    :type split_on_chars: basestring

bencharb

import string
import re
import jinja2

acceptable_punc = set('#$._-')

all_punctuation = set(string.punctuation)

ignore_punc = all_punctuation.difference(acceptable_punc)

bencharb

def get_dependencies(node, edges_list, depth=0):
    if depth > len(edges_list):
        raise Exception('Circular dependency somewhere.')
    seen_nodes = set()
    for from_node, to_node in edges_list:
        if from_node == node:
            seen_nodes.add(from_node)
            if to_node in seen_nodes:
                continue
            yield to_node

bencharb

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)
def iterable_paths(o, level=0):
    if is_dict(o):
        seqs = []
        for k, v in o.iteritems():

bencharb

import collections
import operator
import json

def merge_dicts(dicts=None, create_key_func=None):
    """ Efficiently sort and merge different dictionary collections """
    sort_keys = collections.defaultdict(list)
    for dct_ix, dcts in enumerate(dicts):
        for record_ix, record in enumerate(dcts):
            sortkey = create_key_func(record)