Recursively merging dictionaries with boltons.iterutils.remap. Useful for @hynek's configs. https://twitter.com/hynek/status/696720593002041345

remerge.py

"""
This is an extension of the technique first detailed here:

http://sedimental.org/remap.html#add_common_keys

In short, it calls remap on each container, back to front, using the accumulating
previous values as the default for the current iteration.
"""


from boltons.iterutils import remap, get_path, default_enter, default_visit

defaults = {'host': '127.0.0.1',
            'port': 8000,
            'endpoints': {'persistence': {'host': '127.0.0.1',
                                          'port': 8888},
                          'cache': {'host': '127.0.0.1',
                                    'port': 8889}},
            'owners': {'secondary': ['alice']},
            'zones': [{'a': 1}],
            'notes': ['this is the default']}


overlay = {'host': '127.0.0.1',
           'port': 8080,
           'endpoints': {'persistence': {'host': '10.2.2.2',
                                         'port': 5433}},
           'overlay_version': '5.0',
           'owners': {'primary': ['bob'], 'secondary': ['charles']},
           'zones': [{'a': 2}],
           'notes': ['this is the overlay']}


cache_host_override = {'endpoints': {'cache': {'host': '127.0.0.2'}}}


def remerge(target_list, sourced=False):
    """Takes a list of containers (e.g., dicts) and merges them using
    boltons.iterutils.remap. Containers later in the list take
    precedence (last-wins).

    By default, returns a new, merged top-level container. With the
    *sourced* option, `remerge` expects a list of (*name*, container*)
    pairs, and will return a source map: a dictionary mapping between
    path and the name of the container it came from.

    """

    if not sourced:
        target_list = [(id(t), t) for t in target_list]

    ret = None
    source_map = {}

    def remerge_enter(path, key, value):
        new_parent, new_items = default_enter(path, key, value)
        if ret and not path and key is None:
            new_parent = ret
        try:
            cur_val = get_path(ret, path + (key,))
        except KeyError:
            pass
        else:
            # TODO: type check?
            new_parent = cur_val

        if isinstance(value, list):
            # lists are purely additive. See https://github.com/mahmoud/boltons/issues/81
            new_parent.extend(value)
            new_items = []

        return new_parent, new_items

    for t_name, target in target_list:
        if sourced:
            def remerge_visit(path, key, value):
                source_map[path + (key,)] = t_name
                return True
        else:
            remerge_visit = default_visit

        ret = remap(target, enter=remerge_enter, visit=remerge_visit)

    if not sourced:
        return ret
    return ret, source_map


def main():
    from pprint import pprint

    merged, source_map = remerge([('defaults', defaults),
                                  ('overlay', overlay),
                                  ('cache_host_override', cache_host_override)],
                                 sourced=True)

    assert merged['host'] == '127.0.0.1'
    assert merged['port'] == 8080
    assert merged['endpoints']['persistence']['host'] == '10.2.2.2'
    assert merged['endpoints']['persistence']['port'] == 5433
    assert merged['endpoints']['cache']['host'] == '127.0.0.2'
    assert merged['endpoints']['cache']['port'] == 8889
    assert merged['overlay_version'] == '5.0'

    pprint(merged)
    print
    pprint(source_map)
    print(len(source_map), 'paths')


if __name__ == '__main__':
    main()

the_output.py

{'endpoints': {'cache': {'host': '127.0.0.2', 'port': 8889},
               'persistence': {'host': '10.2.2.2', 'port': 5433}},
 'host': '127.0.0.1',
 'notes': ['this is the default', 'this is the overlay'],
 'overlay_version': '5.0',
 'owners': {'primary': ['bob'], 'secondary': ['alice', 'charles']},
 'port': 8080,
 'zones': [{'a': 1}, {'a': 2}]}

{('endpoints',): 'cache_host_override',
 ('endpoints', 'cache'): 'cache_host_override',
 ('endpoints', 'cache', 'host'): 'cache_host_override',
 ('endpoints', 'cache', 'port'): 'defaults',
 ('endpoints', 'persistence'): 'overlay',
 ('endpoints', 'persistence', 'host'): 'overlay',
 ('endpoints', 'persistence', 'port'): 'overlay',
 ('host',): 'overlay',
 ('notes',): 'overlay',
 ('overlay_version',): 'overlay',
 ('owners',): 'overlay',
 ('owners', 'primary'): 'overlay',
 ('owners', 'secondary'): 'overlay',
 ('port',): 'overlay',
 ('zones',): 'overlay'}
(15, 'paths')