Add native extension analysis

README.md

@@ -38,7 +38,7 @@ ranked := dependents.Rank(kept, 10, nil)
 
 `DefaultScore` favors source references and tests after checkout analysis. Callers can pass another `ScoreFunc` to `Rank`, so security exposure and contract-test selection can use different policies.
 
-`Analyze` accepts any `Checkout`. `CloneCheckout` uses a direct checkout and supports full history for Hyrum, while `CacheCheckout` copies from a persistent `git-pkgs/clone` cache for Scrutineer. A caller that supplies `Workdir` or sets `Keep` receives the checkout path on each analyzed candidate for follow-up work.
+`Analyze` accepts any `Checkout`. `CloneCheckout` uses a direct checkout and supports full history for Hyrum, while `CacheCheckout` copies from a persistent `git-pkgs/clone` cache for Scrutineer. A caller that supplies `Workdir` or sets `Keep` receives the checkout path on each analyzed candidate for follow-up work. Set `DetectNativeExtensions` to record native-extension toolchains and their build commands, including Maturin, napi-rs, Neon, rb-sys, Rustler, and setuptools-rust.
 
 After analysis, `FilterOptions.RequireTests` and `RequireImports` reproduce the contract-test eligibility used by downstream. Scrutineer can require upstream references without excluding repositories that have no conventional test files.
 

analyze.go

@@ -9,10 +9,12 @@ import (
 	"io/fs"
 	"os"
 	"path/filepath"
+	"sort"
 	"strings"
 	"sync"
 
 	"github.com/git-pkgs/brief"
+	"github.com/git-pkgs/brief/detect"
 	"github.com/git-pkgs/brief/kb"
 )
 
@@ -23,10 +25,11 @@ const (
 
 // AnalyzeOptions controls checkout analysis.
 type AnalyzeOptions struct {
-	Upstreams []string
-	Workdir   string
-	Checkout  Checkout
-	Keep      bool
+	Upstreams              []string
+	Workdir                string
+	Checkout               Checkout
+	Keep                   bool
+	DetectNativeExtensions bool
 }
 
 // AnalysisFailure records one candidate that could not be checked out or
@@ -85,6 +88,13 @@ func Analyze(ctx context.Context, candidates []Candidate, opts AnalyzeOptions) (
 			result.Failures = append(result.Failures, AnalysisFailure{Repository: candidate.Repository, Err: err})
 			continue
 		}
+		if opts.DetectNativeExtensions {
+			analysis.NativeExtensions, err = detectNativeExtensions(destination)
+			if err != nil {
+				result.Failures = append(result.Failures, AnalysisFailure{Repository: candidate.Repository, Err: err})
+				continue
+			}
+		}
 		candidate.Analysis = analysis
 		candidate.Analyzed = true
 		candidate.Commit = commit
@@ -150,9 +160,13 @@ func candidateDirectory(repository string) string {
 	return hex.EncodeToString(sum[:])
 }
 
+var loadKnowledge = sync.OnceValues(func() (*kb.KnowledgeBase, error) {
+	return kb.Load(brief.KnowledgeFS)
+})
+
 var testDirs = sync.OnceValue(func() map[string]bool {
-	dirs := map[string]bool{}
-	knowledge, err := kb.Load(brief.KnowledgeFS)
+	dirs := make(map[string]bool)
+	knowledge, err := loadKnowledge()
 	if err != nil {
 		return dirs
 	}
@@ -162,6 +176,31 @@ var testDirs = sync.OnceValue(func() map[string]bool {
 	return dirs
 })
 
+func detectNativeExtensions(root string) ([]NativeExtension, error) {
+	knowledge, err := loadKnowledge()
+	if err != nil {
+		return nil, err
+	}
+	report, err := detect.New(knowledge, root).Run()
+	if err != nil {
+		return nil, err
+	}
+
+	detections := report.Tools["native_extension"]
+	extensions := make([]NativeExtension, 0, len(detections))
+	for _, detection := range detections {
+		extension := NativeExtension{Name: detection.Name}
+		if detection.Command != nil {
+			extension.BuildCommand = detection.Command.Run
+		}
+		extensions = append(extensions, extension)
+	}
+	sort.Slice(extensions, func(i, j int) bool {
+		return extensions[i].Name < extensions[j].Name
+	})
+	return extensions, nil
+}
+
 func isTestFile(base string) bool {
 	stem, extension, ok := strings.Cut(base, ".")
 	if !ok {

analyze_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"os"
 	"path/filepath"
+	"reflect"
 	"strings"
 	"testing"
 )
@@ -71,7 +72,7 @@ func TestAnalyzeDirectorySkipsSymlinks(t *testing.T) {
 	if err != nil {
 		t.Fatalf("AnalyzeDirectory: %v", err)
 	}
-	if got != (Analysis{}) {
+	if !reflect.DeepEqual(got, Analysis{}) {
 		t.Errorf("analysis = %+v, want symlink excluded", got)
 	}
 }
@@ -105,7 +106,7 @@ func TestAnalyzeKeepsFailuresAndPersistentDirectories(t *testing.T) {
 		t.Fatalf("result = %+v", result)
 	}
 	good := result.Candidates[0]
-	if !good.Analyzed || good.Commit != "abc123" || good.Analysis != (Analysis{TestFiles: 1, ImportFiles: 1}) {
+	if !good.Analyzed || good.Commit != "abc123" || !reflect.DeepEqual(good.Analysis, Analysis{TestFiles: 1, ImportFiles: 1}) {
 		t.Errorf("good candidate = %+v", good)
 	}
 	if good.Directory == "" {
@@ -125,6 +126,53 @@ func TestAnalyzeKeepsFailuresAndPersistentDirectories(t *testing.T) {
 	}
 }
 
+func TestAnalyzeDetectsNativeExtensions(t *testing.T) {
+	checkout := CheckoutFunc(func(_ context.Context, _ string, destination string) (string, error) {
+		writeTree(t, destination, map[string]string{
+			"Cargo.toml": `[package]
+name = "native-package"
+version = "0.1.0"
+
+[dependencies]
+rb-sys = "0.9"
+`,
+			"Gemfile": `source "https://rubygems.org"
+gem "rb_sys"
+`,
+			"pyproject.toml": `[build-system]
+requires = ["maturin>=1.0,<2.0"]
+build-backend = "maturin"
+
+[project]
+name = "native-package"
+version = "0.1.0"
+
+[tool.maturin]
+bindings = "pyo3"
+`,
+		})
+		return "abc123", nil
+	})
+
+	result, err := Analyze(context.Background(), []Candidate{{Repository: "https://example.com/native"}}, AnalyzeOptions{
+		Checkout:               checkout,
+		DetectNativeExtensions: true,
+	})
+	if err != nil {
+		t.Fatalf("Analyze: %v", err)
+	}
+	if len(result.Failures) != 0 {
+		t.Fatalf("failures = %+v", result.Failures)
+	}
+	want := []NativeExtension{
+		{Name: "Maturin", BuildCommand: "maturin develop"},
+		{Name: "rb-sys", BuildCommand: "bundle exec rake compile"},
+	}
+	if got := result.Candidates[0].Analysis.NativeExtensions; !reflect.DeepEqual(got, want) {
+		t.Errorf("native extensions = %+v, want %+v", got, want)
+	}
+}
+
 func TestAnalyzeStopsOnCancellation(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()

candidate.go

@@ -68,10 +68,17 @@ type Relationship struct {
 	Dependent PackageRef
 }
 
-// Analysis contains checkout-derived ranking signals.
+// NativeExtension describes a detected native-extension toolchain.
+type NativeExtension struct {
+	Name         string
+	BuildCommand string
+}
+
+// Analysis contains checkout-derived ranking signals and integrations.
 type Analysis struct {
-	TestFiles   int
-	ImportFiles int
+	TestFiles        int
+	ImportFiles      int
+	NativeExtensions []NativeExtension
 }
 
 // Candidate is one repository containing packages that depend on one or more

go.mod

@@ -3,27 +3,42 @@ module github.com/git-pkgs/dependents
 go 1.26
 
 require (
-	github.com/git-pkgs/brief v0.9.4
-	github.com/git-pkgs/clone v0.2.1
+	github.com/git-pkgs/brief v0.10.0
+	github.com/git-pkgs/clone v0.3.0
 	github.com/git-pkgs/enrichment v0.6.5
 )
 
 require (
 	github.com/BurntSushi/toml v1.6.0 // indirect
 	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
+	github.com/bazelbuild/buildtools v0.0.0-20260716142318-04cf7de1434f // indirect
+	github.com/bmatcuk/doublestar/v4 v4.10.0 // indirect
+	github.com/cyphar/filepath-securejoin v0.6.1 // indirect
 	github.com/ecosyste-ms/ecosystems-go v0.4.0 // indirect
-	github.com/git-pkgs/magic v0.1.0 // indirect
+	github.com/git-pkgs/licensecheck v0.4.1 // indirect
+	github.com/git-pkgs/magic v0.2.0 // indirect
+	github.com/git-pkgs/manifests v0.8.0 // indirect
 	github.com/git-pkgs/packageurl-go v0.3.1 // indirect
-	github.com/git-pkgs/pom v0.1.5 // indirect
-	github.com/git-pkgs/purl v0.1.15 // indirect
-	github.com/git-pkgs/registries v0.6.4 // indirect
-	github.com/git-pkgs/spdx v0.3.0 // indirect
-	github.com/git-pkgs/vers v0.3.0 // indirect
+	github.com/git-pkgs/pom v0.1.6 // indirect
+	github.com/git-pkgs/purl v0.1.16 // indirect
+	github.com/git-pkgs/registries v0.7.0 // indirect
+	github.com/git-pkgs/spdx v0.3.1 // indirect
+	github.com/git-pkgs/vers v0.3.1 // indirect
 	github.com/git-pkgs/vulns v0.2.1 // indirect
 	github.com/github/go-spdx/v2 v2.7.0 // indirect
+	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
+	github.com/go-git/go-billy/v5 v5.9.1 // indirect
+	github.com/go-git/go-git/v5 v5.19.2 // indirect
 	github.com/google/uuid v1.6.0 // indirect
+	github.com/jbenet/go-context v0.0.0-20150711004518-d14ea06fba99 // indirect
+	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
 	github.com/oapi-codegen/nullable v1.2.0 // indirect
 	github.com/oapi-codegen/runtime v1.6.0 // indirect
 	github.com/package-url/packageurl-go v0.1.6 // indirect
 	github.com/pandatix/go-cvss v0.6.2 // indirect
+	github.com/pjbgf/sha1cd v0.6.0 // indirect
+	golang.org/x/net v0.56.0 // indirect
+	golang.org/x/sys v0.47.0 // indirect
+	gopkg.in/warnings.v0 v0.1.2 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 )