4cdb68907e
Update utility modules: - File utilities with secure file operations - Environment pool with resource tracking - Error types with scheduler error categories - Logging with audit context support - Network/SSH with connection pooling - Privacy/PII handling with tenant boundaries - Resource manager with scheduler allocation - Security monitor with audit integration - Tracking plugins (MLflow, TensorBoard) with auth - Crypto signing with tenant keys - Database init with multi-user support
55 lines
1.5 KiB
Go
55 lines
1.5 KiB
Go
// Package privacy provides PII detection for narratives and annotations.
|
|
package privacy
|
|
|
|
import (
|
|
"regexp"
|
|
)
|
|
|
|
// piiPatterns contains regex patterns for detecting PII.
|
|
var piiPatterns = map[string]*regexp.Regexp{
|
|
"email": regexp.MustCompile(`\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b`),
|
|
"ssn": regexp.MustCompile(`\b\d{3}-\d{2}-\d{4}\b`),
|
|
"phone": regexp.MustCompile(`\b\d{3}-\d{3}-\d{4}\b`),
|
|
"credit_card": regexp.MustCompile(`\b(?:\d[ -]*?){13,16}\b`),
|
|
"ip_address": regexp.MustCompile(`\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b`),
|
|
}
|
|
|
|
// PIIFinding represents a detected PII instance.
|
|
type PIIFinding struct {
|
|
Type string `json:"type"`
|
|
Sample string `json:"sample"`
|
|
Position int `json:"position"`
|
|
Length int `json:"length"`
|
|
}
|
|
|
|
// DetectPII scans text for potential PII.
|
|
func DetectPII(text string) []PIIFinding {
|
|
var findings []PIIFinding
|
|
|
|
for piiType, pattern := range piiPatterns {
|
|
matches := pattern.FindAllStringIndex(text, -1)
|
|
for _, match := range matches {
|
|
findings = append(findings, PIIFinding{
|
|
Type: piiType,
|
|
Position: match[0],
|
|
Length: match[1] - match[0],
|
|
Sample: RedactSample(text[match[0]:match[1]]),
|
|
})
|
|
}
|
|
}
|
|
|
|
return findings
|
|
}
|
|
|
|
// HasPII returns true if text contains PII.
|
|
func HasPII(text string) bool {
|
|
return len(DetectPII(text)) > 0
|
|
}
|
|
|
|
// RedactSample creates a safe sample for reporting.
|
|
func RedactSample(match string) string {
|
|
if len(match) <= 4 {
|
|
return "[PII]"
|
|
}
|
|
return match[:2] + "..." + match[len(match)-2:]
|
|
}
|