Files
keyhunter/pkg/providers/registry.go
salvacybersec 45ee2f8f53 test(05-03): add failing tests for VerifyAll worker pool
- TestVerifyAll_MultipleFindings: 5 findings via 3-worker pool
- TestVerifyAll_MissingProvider: unknown provider yields StatusUnknown
- TestVerifyAll_ContextCancellation: cancellation closes channel early
- Add providers.NewRegistryFromProviders test helper
2026-04-05 15:48:46 +03:00

91 lines
2.5 KiB
Go

package providers
import (
"fmt"
ahocorasick "github.com/petar-dambovaliev/aho-corasick"
)
// Registry is the in-memory store of all loaded provider definitions.
// It is initialized once at startup and is safe for concurrent reads.
type Registry struct {
providers []Provider
index map[string]int // name -> slice index
ac ahocorasick.AhoCorasick // pre-built automaton for keyword pre-filter
}
// NewRegistry loads all embedded provider YAML files, validates them, builds the
// Aho-Corasick automaton from all provider keywords, and returns the Registry.
func NewRegistry() (*Registry, error) {
providers, err := loadProviders()
if err != nil {
return nil, fmt.Errorf("loading providers: %w", err)
}
index := make(map[string]int, len(providers))
var keywords []string
for i, p := range providers {
index[p.Name] = i
keywords = append(keywords, p.Keywords...)
}
builder := ahocorasick.NewAhoCorasickBuilder(ahocorasick.Opts{DFA: true})
ac := builder.Build(keywords)
return &Registry{
providers: providers,
index: index,
ac: ac,
}, nil
}
// NewRegistryFromProviders builds a Registry from an explicit slice of providers
// without touching the embedded YAML files. Intended for tests that need a
// minimal registry with synthetic providers.
func NewRegistryFromProviders(ps []Provider) *Registry {
index := make(map[string]int, len(ps))
var keywords []string
for i, p := range ps {
index[p.Name] = i
keywords = append(keywords, p.Keywords...)
}
builder := ahocorasick.NewAhoCorasickBuilder(ahocorasick.Opts{DFA: true})
ac := builder.Build(keywords)
return &Registry{providers: ps, index: index, ac: ac}
}
// List returns all loaded providers.
func (r *Registry) List() []Provider {
return r.providers
}
// Get returns a provider by name and a boolean indicating whether it was found.
func (r *Registry) Get(name string) (Provider, bool) {
idx, ok := r.index[name]
if !ok {
return Provider{}, false
}
return r.providers[idx], true
}
// Stats returns aggregate statistics about the loaded providers.
func (r *Registry) Stats() RegistryStats {
stats := RegistryStats{
Total: len(r.providers),
ByTier: make(map[int]int),
ByConfidence: make(map[string]int),
}
for _, p := range r.providers {
stats.ByTier[p.Tier]++
for _, pat := range p.Patterns {
stats.ByConfidence[pat.Confidence]++
}
}
return stats
}
// AC returns the pre-built Aho-Corasick automaton for keyword pre-filtering.
func (r *Registry) AC() ahocorasick.AhoCorasick {
return r.ac
}