Files
keyhunter/pkg/recon/sources/maven.go
salvacybersec 23613150f6 feat(13-02): implement MavenSource and NuGetSource with tests
- MavenSource queries Maven Central Solr API for provider keyword matches
- NuGetSource queries NuGet gallery search API with projectUrl fallback
- Both sources: httptest fixtures, ctx cancellation, metadata tests
2026-04-06 12:52:27 +03:00

119 lines
2.9 KiB
Go

package sources
import (
"context"
"encoding/json"
"fmt"
"net/http"
"net/url"
"time"
"golang.org/x/time/rate"
"github.com/salvacybersec/keyhunter/pkg/providers"
"github.com/salvacybersec/keyhunter/pkg/recon"
)
// MavenSource searches Maven Central for artifacts matching provider keywords.
// Maven Central exposes a Solr-based JSON search API that requires no
// authentication.
type MavenSource struct {
BaseURL string
Registry *providers.Registry
Limiters *recon.LimiterRegistry
Client *Client
}
// Compile-time assertion that MavenSource satisfies recon.ReconSource.
var _ recon.ReconSource = (*MavenSource)(nil)
func (s *MavenSource) Name() string { return "maven" }
func (s *MavenSource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
func (s *MavenSource) Burst() int { return 2 }
func (s *MavenSource) RespectsRobots() bool { return false }
// Enabled always returns true: Maven Central requires no credentials.
func (s *MavenSource) Enabled(_ recon.Config) bool { return true }
// Sweep queries Maven Central's Solr search for each provider keyword and
// emits a Finding per matching artifact.
func (s *MavenSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
base := s.BaseURL
if base == "" {
base = "https://search.maven.org"
}
client := s.Client
if client == nil {
client = NewClient()
}
queries := BuildQueries(s.Registry, "maven")
if len(queries) == 0 {
return nil
}
for _, q := range queries {
if err := ctx.Err(); err != nil {
return err
}
if s.Limiters != nil {
if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
return err
}
}
endpoint := fmt.Sprintf("%s/solrsearch/select?q=%s&rows=20&wt=json",
base, url.QueryEscape(q))
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
if err != nil {
return fmt.Errorf("maven: build request: %w", err)
}
req.Header.Set("Accept", "application/json")
resp, err := client.Do(ctx, req)
if err != nil {
continue // non-fatal: skip keyword on HTTP error
}
var parsed mavenSearchResponse
decErr := json.NewDecoder(resp.Body).Decode(&parsed)
_ = resp.Body.Close()
if decErr != nil {
continue
}
for _, doc := range parsed.Response.Docs {
if err := ctx.Err(); err != nil {
return err
}
src := fmt.Sprintf("https://search.maven.org/artifact/%s/%s/%s/jar",
doc.Group, doc.Artifact, doc.LatestVersion)
select {
case out <- recon.Finding{
Source: src,
SourceType: "recon:maven",
Confidence: "low",
DetectedAt: time.Now(),
}:
case <-ctx.Done():
return ctx.Err()
}
}
}
return nil
}
type mavenSearchResponse struct {
Response mavenResponseBody `json:"response"`
}
type mavenResponseBody struct {
Docs []mavenDoc `json:"docs"`
}
type mavenDoc struct {
Group string `json:"g"`
Artifact string `json:"a"`
LatestVersion string `json:"latestVersion"`
}