mirror of
https://github.com/ivuorinen/monolog-gdpr-filter.git
synced 2026-03-13 19:01:27 +00:00
feat: add advanced architecture, documentation, and coverage improvements (#65)
* fix(style): resolve PHPCS line-length warnings in source files * fix(style): resolve PHPCS line-length warnings in test files * feat(audit): add structured audit logging with ErrorContext and AuditContext - ErrorContext: standardized error information with sensitive data sanitization - AuditContext: structured context for audit entries with operation types - StructuredAuditLogger: enhanced audit logger wrapper with timing support * feat(recovery): add recovery mechanism for failed masking operations - FailureMode enum: FAIL_OPEN, FAIL_CLOSED, FAIL_SAFE modes - RecoveryStrategy interface and RecoveryResult value object - RetryStrategy: exponential backoff with configurable attempts - FallbackMaskStrategy: type-aware fallback values * feat(strategies): add CallbackMaskingStrategy for custom masking logic - Wraps custom callbacks as MaskingStrategy implementations - Factory methods: constant(), hash(), partial() for common use cases - Supports exact match and prefix match for field paths * docs: add framework integration guides and examples - symfony-integration.md: Symfony service configuration and Monolog setup - psr3-decorator.md: PSR-3 logger decorator pattern implementation - framework-examples.md: CakePHP, CodeIgniter 4, Laminas, Yii2, PSR-15 - docker-development.md: Docker development environment guide * chore(docker): add Docker development environment - Dockerfile: PHP 8.2-cli-alpine with Xdebug for coverage - docker-compose.yml: development services with volume mounts * feat(demo): add interactive GDPR pattern tester playground - PatternTester.php: pattern testing utility with strategy support - index.php: web API endpoint with JSON response handling - playground.html: interactive web interface for testing patterns * docs(todo): update with completed medium priority items - Mark all PHPCS warnings as fixed (81 → 0) - Document new Audit and Recovery features - Update test count to 1,068 tests with 2,953 assertions - Move remaining items to low priority * feat: add advanced architecture, documentation, and coverage improvements - Add architecture improvements: - ArrayAccessorInterface and DotArrayAccessor for decoupled array access - MaskingOrchestrator for single-responsibility masking coordination - GdprProcessorBuilder for fluent configuration - MaskingPluginInterface and AbstractMaskingPlugin for plugin architecture - PluginAwareProcessor for plugin hook execution - AuditLoggerFactory for instance-based audit logger creation - Add advanced features: - SerializedDataProcessor for handling print_r/var_export/serialize output - KAnonymizer with GeneralizationStrategy for GDPR k-anonymity - RetentionPolicy for configurable data retention periods - StreamingProcessor for memory-efficient large log processing - Add comprehensive documentation: - docs/performance-tuning.md - benchmarking, optimization, caching - docs/troubleshooting.md - common issues and solutions - docs/logging-integrations.md - ELK, Graylog, Datadog, etc. - docs/plugin-development.md - complete plugin development guide - Improve test coverage (84.41% → 85.07%): - ConditionalRuleFactoryInstanceTest (100% coverage) - GdprProcessorBuilderEdgeCasesTest (100% coverage) - StrategyEdgeCasesTest for ReDoS detection and type parsing - 78 new tests, 119 new assertions - Update TODO.md with current statistics: - 141 PHP files, 1,346 tests, 85.07% line coverage * chore: tests, update actions, sonarcloud issues * chore: rector * fix: more sonarcloud fixes * chore: more fixes * refactor: copilot review fix * chore: rector
This commit is contained in:
GitHub
48
src/Anonymization/GeneralizationStrategy.php
Normal file
48
src/Anonymization/GeneralizationStrategy.php
Normal file
@@ -0,0 +1,48 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace Ivuorinen\MonologGdprFilter\Anonymization;
|
||||
|
||||
/**
|
||||
* Represents a generalization strategy for k-anonymity.
|
||||
*
|
||||
* @api
|
||||
*/
|
||||
final class GeneralizationStrategy
|
||||
{
|
||||
/**
|
||||
* @var callable(mixed):string
|
||||
*/
|
||||
private $generalizer;
|
||||
|
||||
/**
|
||||
* @param callable(mixed):string $generalizer Function that generalizes a value
|
||||
* @param string $type Type identifier for the strategy
|
||||
*/
|
||||
public function __construct(
|
||||
callable $generalizer,
|
||||
private readonly string $type = 'custom'
|
||||
) {
|
||||
$this->generalizer = $generalizer;
|
||||
}
|
||||
|
||||
/**
|
||||
* Apply the generalization to a value.
|
||||
*
|
||||
* @param mixed $value The value to generalize
|
||||
* @return string The generalized value
|
||||
*/
|
||||
public function generalize(mixed $value): string
|
||||
{
|
||||
return ($this->generalizer)($value);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the strategy type.
|
||||
*/
|
||||
public function getType(): string
|
||||
{
|
||||
return $this->type;
|
||||
}
|
||||
}
|
||||
212
src/Anonymization/KAnonymizer.php
Normal file
212
src/Anonymization/KAnonymizer.php
Normal file
@@ -0,0 +1,212 @@
|
||||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
namespace Ivuorinen\MonologGdprFilter\Anonymization;
|
||||
|
||||
/**
|
||||
* K-Anonymity implementation for GDPR compliance.
|
||||
*
|
||||
* K-anonymity is a privacy model ensuring that each record in a dataset
|
||||
* is indistinguishable from at least k-1 other records with respect to
|
||||
* certain identifying attributes (quasi-identifiers).
|
||||
*
|
||||
* Common use cases:
|
||||
* - Age generalization (25 -> "20-29")
|
||||
* - Location generalization (specific address -> region)
|
||||
* - Date generalization (specific date -> month/year)
|
||||
*
|
||||
* @api
|
||||
*/
|
||||
final class KAnonymizer
|
||||
{
|
||||
/**
|
||||
* @var array<string,GeneralizationStrategy>
|
||||
*/
|
||||
private array $strategies = [];
|
||||
|
||||
/**
|
||||
* @var callable(string,mixed,mixed):void|null
|
||||
*/
|
||||
private $auditLogger;
|
||||
|
||||
/**
|
||||
* @param callable(string,mixed,mixed):void|null $auditLogger Optional audit logger
|
||||
*/
|
||||
public function __construct(?callable $auditLogger = null)
|
||||
{
|
||||
$this->auditLogger = $auditLogger;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a generalization strategy for a field.
|
||||
*/
|
||||
public function registerStrategy(string $field, GeneralizationStrategy $strategy): self
|
||||
{
|
||||
$this->strategies[$field] = $strategy;
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register an age generalization strategy.
|
||||
*
|
||||
* @param int $rangeSize Size of age ranges (e.g., 10 for 20-29, 30-39)
|
||||
*/
|
||||
public function registerAgeStrategy(string $field, int $rangeSize = 10): self
|
||||
{
|
||||
$this->strategies[$field] = new GeneralizationStrategy(
|
||||
static function (mixed $value) use ($rangeSize): string {
|
||||
$age = (int) $value;
|
||||
$lowerBound = (int) floor($age / $rangeSize) * $rangeSize;
|
||||
$upperBound = $lowerBound + $rangeSize - 1;
|
||||
return "{$lowerBound}-{$upperBound}";
|
||||
},
|
||||
'age'
|
||||
);
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a date generalization strategy.
|
||||
*
|
||||
* @param string $precision 'year', 'month', 'quarter'
|
||||
*/
|
||||
public function registerDateStrategy(string $field, string $precision = 'month'): self
|
||||
{
|
||||
$this->strategies[$field] = new GeneralizationStrategy(
|
||||
static function (mixed $value) use ($precision): string {
|
||||
if (!$value instanceof \DateTimeInterface) {
|
||||
$value = new \DateTimeImmutable((string) $value);
|
||||
}
|
||||
|
||||
return match ($precision) {
|
||||
'year' => $value->format('Y'),
|
||||
'quarter' => $value->format('Y') . '-Q' . (int) ceil((int) $value->format('n') / 3),
|
||||
default => $value->format('Y-m'),
|
||||
};
|
||||
},
|
||||
'date'
|
||||
);
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a location/ZIP code generalization strategy.
|
||||
*
|
||||
* @param int $prefixLength Number of characters to keep
|
||||
*/
|
||||
public function registerLocationStrategy(string $field, int $prefixLength = 3): self
|
||||
{
|
||||
$this->strategies[$field] = new GeneralizationStrategy(
|
||||
static function (mixed $value) use ($prefixLength): string {
|
||||
$value = (string) $value;
|
||||
if (strlen($value) <= $prefixLength) {
|
||||
return $value;
|
||||
}
|
||||
return substr($value, 0, $prefixLength) . str_repeat('*', strlen($value) - $prefixLength);
|
||||
},
|
||||
'location'
|
||||
);
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a numeric range generalization strategy.
|
||||
*
|
||||
* @param int $rangeSize Size of numeric ranges
|
||||
*/
|
||||
public function registerNumericRangeStrategy(string $field, int $rangeSize = 10): self
|
||||
{
|
||||
$this->strategies[$field] = new GeneralizationStrategy(
|
||||
static function (mixed $value) use ($rangeSize): string {
|
||||
$num = (int) $value;
|
||||
$lowerBound = (int) floor($num / $rangeSize) * $rangeSize;
|
||||
$upperBound = $lowerBound + $rangeSize - 1;
|
||||
return "{$lowerBound}-{$upperBound}";
|
||||
},
|
||||
'numeric_range'
|
||||
);
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register a custom generalization strategy.
|
||||
*
|
||||
* @param callable(mixed):string $generalizer
|
||||
*/
|
||||
public function registerCustomStrategy(string $field, callable $generalizer): self
|
||||
{
|
||||
$this->strategies[$field] = new GeneralizationStrategy($generalizer, 'custom');
|
||||
return $this;
|
||||
}
|
||||
|
||||
/**
|
||||
* Anonymize a single record.
|
||||
*
|
||||
* @param array<string,mixed> $record The record to anonymize
|
||||
* @return array<string,mixed> The anonymized record
|
||||
*/
|
||||
public function anonymize(array $record): array
|
||||
{
|
||||
foreach ($this->strategies as $field => $strategy) {
|
||||
if (isset($record[$field])) {
|
||||
$original = $record[$field];
|
||||
$record[$field] = $strategy->generalize($original);
|
||||
|
||||
if ($this->auditLogger !== null && $record[$field] !== $original) {
|
||||
($this->auditLogger)(
|
||||
"k-anonymity.{$field}",
|
||||
$original,
|
||||
$record[$field]
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return $record;
|
||||
}
|
||||
|
||||
/**
|
||||
* Anonymize a batch of records.
|
||||
*
|
||||
* @param list<array<string,mixed>> $records
|
||||
* @return list<array<string,mixed>>
|
||||
*/
|
||||
public function anonymizeBatch(array $records): array
|
||||
{
|
||||
return array_map($this->anonymize(...), $records);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get registered strategies.
|
||||
*
|
||||
* @return array<string,GeneralizationStrategy>
|
||||
*/
|
||||
public function getStrategies(): array
|
||||
{
|
||||
return $this->strategies;
|
||||
}
|
||||
|
||||
/**
|
||||
* Set the audit logger.
|
||||
*
|
||||
* @param callable(string,mixed,mixed):void|null $auditLogger
|
||||
*/
|
||||
public function setAuditLogger(?callable $auditLogger): void
|
||||
{
|
||||
$this->auditLogger = $auditLogger;
|
||||
}
|
||||
|
||||
/**
|
||||
* Create a pre-configured anonymizer for common GDPR scenarios.
|
||||
*/
|
||||
public static function createGdprDefault(?callable $auditLogger = null): self
|
||||
{
|
||||
return (new self($auditLogger))
|
||||
->registerAgeStrategy('age')
|
||||
->registerDateStrategy('birth_date', 'year')
|
||||
->registerDateStrategy('created_at', 'month')
|
||||
->registerLocationStrategy('zip_code', 3)
|
||||
->registerLocationStrategy('postal_code', 3);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user