Get and put dictionaries (documents) from and to the filesystem.

document.py

#!/usr/bin/env python3
# -----------------------------------------------------------------------------
# Copyright (c) 2015, Heiko Möllerke
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
# -----------------------------------------------------------------------------

"""
=================================================
document.py
Store and retrieve dictionaries to and from files
=================================================
"""

import collections
import functools
import glob
import json
import os
import uuid


def get(base, identifier): # -> dict
    with open(_path(base, identifier), 'r', encoding='UTF-8') as fp:
        xm = json.load(fp)
        xm.update({_IDENTIFIER: identifier})
        return xm
    
def put(base, xm):
    if _IDENTIFIER not in xm: xm[_IDENTIFIER] = uuid.uuid4().hex
    with open(_path(base, xm[_IDENTIFIER]), 'w', encoding='UTF-8') as fp:
        # Ensure that no 'special' root-keys will be stored in the JSON-file:
        nonmeta = dict((k, v) for \
                                  k, v in xm.items() \
                                  if not k.startswith(_META_PREFIX))
        json.dump(nonmeta, fp, **_JSON_CONFIG)

def delete(base, xm):
    os.remove(_path(base, xm[_IDENTIFIER]))

def select(base, trait=lambda xm: True):
    filenames = glob.glob(os.path.join(base, '*{}'.format(_FILESUFFIX)))
    identifiers = [os.path.splitext(os.path.basename(e))[0] for e in filenames]
    return list(filter(trait, [get(base, e_) for e_ in identifiers]))

def functions(base):
    return collections.namedtuple('Storage', 'get put delete select')(
        *(functools.partial(f, base) for f in (get, put, delete, select))
    )

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Module specific (non API) constants and utility-functions
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

_JSON_CONFIG = {'indent': 2, 'ensure_ascii': False, 'sort_keys': True}
_META_PREFIX = '__'
_IDENTIFIER = _META_PREFIX + 'id'
_FILESUFFIX = '.txt'
    
def _path(base, identifier):
    """Returns the path aggregated from base and the given identifier."""
    return os.path.join(base, '{}{}'.format(identifier, _FILESUFFIX))

showcase_document.py

#!/usr/bin/env python3

import os
from pprint import pprint
import document

def main():
    # Some preparations:
    get, put, delete, select = document.functions(os.getcwd())
 
    # Create some example data:
    person = {'name': 'John', 'surname': 'Doe'}
    other = {'name': 'Johanna', 'surname': 'Doelyn'}
    rectangle = {'x': 10, 'y': 12, 'width': 42, 'height': 77}
    mistake = {'oops': 'FOO'}
    
    # Save them:
    put(person)
    put(other)
    put(rectangle)
    put(mistake)
    
    print('\n ---> Show them all:')
    pprint(select(), width=1)
 
    print('\n ---> Show persons only:')
    trait = lambda xm: 'name' in xm and 'surname' in xm
    pprint(select(trait=trait), width=1)
   
    print('\n ---> Give me only the ids from persons:')
    ids = select(trait=trait, map_=lambda xm: xm['__id'])
    pprint(ids, width=1)
    
    print('\n ---> Now get the persons:')
    persons = [get(e) for e in ids]
    pprint(persons, width=1)
    
    print('\n ---> Get rid of the mistake:')
    delete(mistake)
    
    print('\n ---> Show them all, again:')
    pprint(select(), width=1)
    
    print('\n ---> Get rid of them all')
    for e in select():
        delete(e)
    
if __name__ == '__main__':
    main()