X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=dict_utils.py;h=573e683c1d84d2f0f11d18e61fa9f950f585e1c4;hb=a9bdfd8fc9f84b7b2c09a57cd12ba32259e84d1c;hp=b1464c6bb9967ce4efa48318a288babd0ff322e9;hpb=8d6abef443543013d7b37cda1375a28f040d24a6;p=python_utils.git diff --git a/dict_utils.py b/dict_utils.py index b1464c6..573e683 100644 --- a/dict_utils.py +++ b/dict_utils.py @@ -1,5 +1,9 @@ #!/usr/bin/env python3 +# © Copyright 2021-2022, Scott Gasch + +"""Helper functions for dealing with dictionaries.""" + from itertools import islice from typing import Any, Callable, Dict, Iterator, List, Tuple @@ -38,47 +42,60 @@ def shard(d: Dict[Any, Any], size: int) -> Iterator[Dict[Any, Any]]: """ Shards a dict into N subdicts which, together, contain all keys/values from the original unsharded dict. - """ items = d.items() for x in range(0, len(d), size): - yield {key: value for (key, value) in islice(items, x, x + size)} + yield dict(islice(items, x, x + size)) -def coalesce_by_creating_list(key, new_value, old_value): +def coalesce_by_creating_list(_, new_value, old_value): + """Helper for use with :meth:`coalesce` that creates a list on + collision.""" from list_utils import flatten return flatten([new_value, old_value]) def coalesce_by_creating_set(key, new_value, old_value): + """Helper for use with :meth:`coalesce` that creates a set on + collision.""" return set(coalesce_by_creating_list(key, new_value, old_value)) -def coalesce_last_write_wins(key, new_value, old_value): +def coalesce_last_write_wins(_, new_value, discarded_old_value): + """Helper for use with :meth:`coalsce` that klobbers the old + with the new one on collision.""" return new_value -def coalesce_first_write_wins(key, new_value, old_value): +def coalesce_first_write_wins(_, discarded_new_value, old_value): + """Helper for use with :meth:`coalsce` that preserves the old + value and discards the new one on collision.""" return old_value def raise_on_duplicated_keys(key, new_value, old_value): + """Helper for use with :meth:`coalesce` that raises an exception + when a collision is detected. + """ raise Exception(f'Key {key} is duplicated in more than one input dict.') def coalesce( inputs: Iterator[Dict[Any, Any]], *, - aggregation_function: Callable[[Any, Any], Any] = coalesce_by_creating_list, + aggregation_function: Callable[[Any, Any, Any], Any] = coalesce_by_creating_list, ) -> Dict[Any, Any]: """Merge N dicts into one dict containing the union of all keys / values in the input dicts. When keys collide, apply the aggregation_function which, by default, creates a list of values. - See also several other alternative functions for coalescing values - (coalesce_by_creating_set, coalesce_first_write_wins, - coalesce_last_write_wins, raise_on_duplicated_keys) or provide a - custom helper function. + See also several other alternative functions for coalescing values: + + * :meth:`coalesce_by_creating_set` + * :meth:`coalesce_first_write_wins` + * :meth:`coalesce_last_write_wins` + * :meth:`raise_on_duplicated_keys` + * or provive your own collision resolution code. >>> a = {'a': 1, 'b': 2} >>> b = {'b': 1, 'c': 2, 'd': 3} @@ -107,7 +124,7 @@ def coalesce( def item_with_max_value(d: Dict[Any, Any]) -> Tuple[Any, Any]: - """Returns the key and value with the max value in a dict. + """Returns the key and value of the item with the max value in a dict. >>> d = {'a': 1, 'b': 2, 'c': 3} >>> item_with_max_value(d) @@ -122,7 +139,7 @@ def item_with_max_value(d: Dict[Any, Any]) -> Tuple[Any, Any]: def item_with_min_value(d: Dict[Any, Any]) -> Tuple[Any, Any]: - """Returns the key and value with the min value in a dict. + """Returns the key and value of the item with the min value in a dict. >>> d = {'a': 1, 'b': 2, 'c': 3} >>> item_with_min_value(d) @@ -223,7 +240,7 @@ def dict_to_key_value_lists(d: Dict[Any, Any]) -> Tuple[List[Any], List[Any]]: ['scott', '555-1212', '123 main st.', '12345'] """ - r = ([], []) + r: Tuple[List[Any], List[Any]] = ([], []) for (k, v) in d.items(): r[0].append(k) r[1].append(v)