Spaces:
Sleeping
Sleeping
File size: 6,041 Bytes
6fad24e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | from presidio_analyzer import AnalyzerEngine
from presidio_anonymizer import AnonymizerEngine, DeanonymizeEngine, OperatorConfig
from presidio_anonymizer.operators import Operator, OperatorType
from typing import Dict
from pprint import pprint
# text = "Peter gave his book to Heidi which later gave it to Nicole. Peter lives in London and Nicole lives in Tashkent."
# print("original text:")
# pprint(text)
# analyzer = AnalyzerEngine()
# analyzer_results = analyzer.analyze(text=text, language="en")
# # print("analyzer results:")
# # pprint(analyzer_results)
class InstanceCounterAnonymizer(Operator):
"""
Anonymizer which replaces the entity value
with an instance counter per entity.
"""
REPLACING_FORMAT = "<{entity_type}_{index}>"
def operate(self, text: str, params: Dict = None) -> str:
"""Anonymize the input text."""
entity_type: str = params["entity_type"]
# entity_mapping is a dict of dicts containing mappings per entity type
entity_mapping: Dict[Dict:str] = params["entity_mapping"]
entity_mapping_for_type = entity_mapping.get(entity_type)
if not entity_mapping_for_type:
new_text = self.REPLACING_FORMAT.format(
entity_type=entity_type, index=0
)
entity_mapping[entity_type] = {}
else:
if text in entity_mapping_for_type:
return entity_mapping_for_type[text]
previous_index = self._get_last_index(entity_mapping_for_type)
new_text = self.REPLACING_FORMAT.format(
entity_type=entity_type, index=previous_index + 1
)
entity_mapping[entity_type][text] = new_text
return new_text
@staticmethod
def _get_last_index(entity_mapping_for_type: Dict) -> int:
"""Get the last index for a given entity type."""
def get_index(value: str) -> int:
return int(value.split("_")[-1][:-1])
indices = [get_index(v) for v in entity_mapping_for_type.values()]
return max(indices)
def validate(self, params: Dict = None) -> None:
"""Validate operator parameters."""
if "entity_mapping" not in params:
raise ValueError("An input Dict called `entity_mapping` is required.")
if "entity_type" not in params:
raise ValueError("An entity_type param is required.")
def operator_name(self) -> str:
return "entity_counter"
def operator_type(self) -> OperatorType:
return OperatorType.Anonymize
# Create Anonymizer engine and add the custom anonymizer
# anonymizer_engine = AnonymizerEngine()
# anonymizer_engine.add_anonymizer(InstanceCounterAnonymizer)
# # Create a mapping between entity types and counters
# entity_mapping = dict()
# # Anonymize the text
# anonymized_result = anonymizer_engine.anonymize(
# text,
# analyzer_results,
# {
# "DEFAULT": OperatorConfig(
# "entity_counter", {"entity_mapping": entity_mapping}
# )
# },
# )
# print(anonymized_result.text)
# pprint(entity_mapping, indent=2)
# class InstanceCounterDeanonymizer(Operator):
# """
# Deanonymizer which replaces the unique identifier
# with the original text.
# """
# def operate(self, text: str, params: Dict = None) -> str:
# """Anonymize the input text."""
# entity_type: str = params["entity_type"]
# # entity_mapping is a dict of dicts containing mappings per entity type
# entity_mapping: Dict[Dict:str] = params["entity_mapping"]
# if entity_type not in entity_mapping:
# raise ValueError(f"Entity type {entity_type} not found in entity mapping!")
# if text not in entity_mapping[entity_type].values():
# raise ValueError(f"Text {text} not found in entity mapping for entity type {entity_type}!")
# return self._find_key_by_value(entity_mapping[entity_type], text)
# @staticmethod
# def _find_key_by_value(entity_mapping, value):
# for key, val in entity_mapping.items():
# if val == value:
# return key
# return None
# def validate(self, params: Dict = None) -> None:
# """Validate operator parameters."""
# if "entity_mapping" not in params:
# raise ValueError("An input Dict called `entity_mapping` is required.")
# if "entity_type" not in params:
# raise ValueError("An entity_type param is required.")
# def operator_name(self) -> str:
# return "entity_counter_deanonymizer"
# def operator_type(self) -> OperatorType:
# return OperatorType.Deanonymize
# # Create Anonymizer engine and add the custom anonymizer
# anonymizer_engine = AnonymizerEngine()
# anonymizer_engine.add_anonymizer(InstanceCounterAnonymizer)
# # Create a mapping between entity types and counters
# entity_mapping = dict()
# # Anonymize the text
# text = "Peter gave his book to Heidi which later gave it to Nicole. Peter lives in London and Nicole lives in Tashkent."
# print("original text:")
# pprint(text)
# analyzer = AnalyzerEngine()
# analyzer_results = analyzer.analyze(text=text, language="en")
# print("analyzer results:")
# pprint(analyzer_results)
# anonymized_result = anonymizer_engine.anonymize(
# text,
# analyzer_results,
# {
# "DEFAULT": OperatorConfig(
# "entity_counter", {"entity_mapping": entity_mapping}
# )
# },
# )
# print(anonymized_result)
# deanonymizer_engine = DeanonymizeEngine()
# deanonymizer_engine.add_deanonymizer(InstanceCounterDeanonymizer)
# deanonymized = deanonymizer_engine.deanonymize(
# anonymized_result.text,
# anonymized_result.items,
# {"DEFAULT": OperatorConfig("entity_counter_deanonymizer",
# params={"entity_mapping": entity_mapping})}
# )
# print("anonymized text:")
# pprint(anonymized_result.text)
# print("de-anonymized text:")
# pprint(deanonymized.text) |