Update the mask dict helper

It now goes recursive, is case insenstivie for keys and mask keys requests
Checks not for equal but for start/end or inside with edge character set

pytests added
This commit is contained in:
Clemens Schwaighofer
2025-07-17 14:37:07 +09:00
parent 472d3495b5
commit 280e5fa861
4 changed files with 403 additions and 26 deletions

View File

@@ -3,26 +3,36 @@ Dict helpers
"""
from typing import Any
from typing import TypeAlias, Union, Dict, List, Any, cast
# definitions for the mask run below
MaskableValue: TypeAlias = Union[str, int, float, bool, None]
NestedDict: TypeAlias = Dict[str, Union[MaskableValue, List[Any], 'NestedDict']]
ProcessableValue: TypeAlias = Union[MaskableValue, List[Any], NestedDict]
def mask(
data_set: dict[str, str],
data_set: dict[str, Any],
mask_keys: list[str] | None = None,
mask_str: str = "***",
mask_str_edges: str = '_',
skip: bool = False
) -> dict[str, str]:
) -> dict[str, Any]:
"""
mask data for output
Checks if mask_keys list exist in any key in the data set either from the start or at the end
Use the mask_str_edges to define how searches inside a string should work. Default it must start
and end with '_', remove to search string in string
Arguments:
data_set {dict[str, str]} -- _description_
Keyword Arguments:
mask_keys {list[str] | None} -- _description_ (default: {None})
mask_str {str} -- _description_ (default: {"***"})
skip {bool} -- _description_ (default: {False})
mask_str_edges {str} -- _description_ (default: {"_"})
skip {bool} -- if set to true skip (default: {False})
Returns:
dict[str, str] -- _description_
@@ -30,29 +40,46 @@ def mask(
if skip is True:
return data_set
if mask_keys is None:
mask_keys = ["password", "secret"]
mask_keys = ["encryption", "password", "secret"]
else:
# make sure it is lower case
mask_keys = [mask_key.lower() for mask_key in mask_keys]
def should_mask_key(key: str) -> bool:
"""Check if a key should be masked"""
__key_lower = key.lower()
return any(
__key_lower.startswith(mask_key) or
__key_lower.endswith(mask_key) or
f"{mask_str_edges}{mask_key}{mask_str_edges}" in __key_lower
for mask_key in mask_keys
)
def mask_recursive(obj: ProcessableValue) -> ProcessableValue:
"""Recursively mask values in nested structures"""
if isinstance(obj, dict):
return {
key: mask_value(value) if should_mask_key(key) else mask_recursive(value)
for key, value in obj.items()
}
if isinstance(obj, list):
return [mask_recursive(item) for item in obj]
return obj
def mask_value(value: Any) -> Any:
"""Handle masking based on value type"""
if isinstance(value, list):
# Mask each individual value in the list
return [mask_str for _ in cast('list[Any]', value)]
if isinstance(value, dict):
# Recursively process the dictionary instead of masking the whole thing
return mask_recursive(cast('ProcessableValue', value))
# Mask primitive values
return mask_str
return {
key: mask_str
if any(key.startswith(mask_key) or key.endswith(mask_key) for mask_key in mask_keys) else value
key: mask_value(value) if should_mask_key(key) else mask_recursive(value)
for key, value in data_set.items()
}
def set_entry(dict_set: dict[str, Any], key: str, value_set: Any) -> dict[str, Any]:
"""
set a new entry in the dict set
Arguments:
key {str} -- _description_
dict_set {dict[str, Any]} -- _description_
value_set {Any} -- _description_
Returns:
dict[str, Any] -- _description_
"""
if not dict_set.get(key):
dict_set[key] = {}
dict_set[key] = value_set
return dict_set
# __END__