github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-28 06:48:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

langchain-experimental: Add allow_list support in experimental/data_anonymizer (#11597)

Browse Source 
- **Description:** Add allow_list support in langchain experimental
data-anonymizer package
  - **Issue:** no
  - **Dependencies:** no
  - **Tag maintainer:** @hwchase17
  - **Twitter handle:**
This commit is contained in:
Suresh Kumar Ponnusamy
2023-10-12 03:20:41 +05:30
committed by GitHub
parent 2363c02cf3
commit 70f7558db2
4 changed files with 55 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
libs/experimental/langchain_experimental/data_anonymizer/presidio.py
View File

@@ -139,7 +139,12 @@ class PresidioAnonymizerBase(AnonymizerBase):
class PresidioAnonymizer(PresidioAnonymizerBase):
def _anonymize(self, text: str, language: Optional[str] = None) -> str:
def _anonymize(
self,
text: str,
language: Optional[str] = None,
allow_list: Optional[List[str]] = None,
) -> str:
"""Anonymize text.
Each PII entity is replaced with a fake value.
Each time fake values will be different, as they are generated randomly.
@@ -172,6 +177,7 @@ class PresidioAnonymizer(PresidioAnonymizerBase):
text,
entities=self.analyzed_fields,
language=language,
allow_list=allow_list,
)
filtered_analyzer_results = (
@@ -226,7 +232,12 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
for key, inner_dict in self.deanonymizer_mapping.items()
}
def _anonymize(self, text: str, language: Optional[str] = None) -> str:
def _anonymize(
self,
text: str,
language: Optional[str] = None,
allow_list: Optional[List[str]] = None,
) -> str:
"""Anonymize text.
Each PII entity is replaced with a fake value.
Each time fake values will be different, as they are generated randomly.
@@ -261,6 +272,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
text,
entities=self.analyzed_fields,
language=language,
allow_list=allow_list,
)
filtered_analyzer_results = (