Redactor Task for Visual Studio

redact_vscode.py

import json

def load_config(config_file):
    with open(config_file, 'r') as file:
        return json.load(file)

def redact_pii(file_path, config_file='redaction_config.json'):
    config = load_config(config_file)

    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()

    # Apply ignore patterns before redaction
    for pattern in config['ignore_patterns']:
        content = re.sub(pattern['regexp'], pattern['replace_with'], content)

    # Analyze and anonymize (after applying ignore patterns)
    results = analyzer.analyze(text=content, entities=["PHONE_NUMBER", "EMAIL_ADDRESS", "PERSON"], language='en')
    redacted_content = anonymizer.anonymize(text=content, analyzer_results=results)

    # Save redacted content
    with open(file_path, 'w', encoding='utf-8') as file:
        file.write(redacted_content)
    print(f"Redacted file saved at {file_path}")

redaction_config.json

{
    "ignore_patterns": [
        {
            "regexp": "\\bexample.com\\b",
            "replace_with": "example.com"
        },
        {
            "regexp": "\\b(?:specificString|testAccount)\\b",
            "replace_with": ""
        }
    ]
}

tasks.json

{
    "version": "2.0.0",
    "tasks": [
        {
            "label": "Redact PII in open file",
            "type": "shell",
            "command": "python",
            "args": [
                "${workspaceFolder}/redact_vscode.py"
            ],
            "problemMatcher": [],
            "options": {
                "env": {
                    "OPEN_FILE_PATH": "${file}"
                }
            },
            "group": {
                "kind": "build",
                "isDefault": true
            }
        }
    ]
}