test(08-07): add dork count + uniqueness guardrail

- TestDorkCountGuardrail: enforces DORK-02 >=150 floor
- TestDorkCountPerSource: per-source minimums (github>=50, google>=30, shodan>=20, censys>=15, zoomeye/fofa/gitlab>=10, bing>=5)
- TestDorkCategoriesPresent: all 5 DORK-01 categories present
- TestDorkIDsUnique: no collisions across source files

pkg/dorks/count_test.go

@@ -0,0 +1,78 @@
+package dorks
+
+import "testing"
+
+// TestDorkCountGuardrail enforces the DORK-02 requirement that the embedded
+// corpus ships with at least 150 built-in dorks. If this test fails, a dork
+// file was removed or a YAML was broken — do not lower the threshold, restore
+// the missing dorks instead.
+func TestDorkCountGuardrail(t *testing.T) {
+	r, err := NewRegistry()
+	if err != nil {
+		t.Fatalf("NewRegistry: %v", err)
+	}
+	const minTotal = 150
+	if got := len(r.List()); got < minTotal {
+		t.Fatalf("dork count regression: got %d, want >= %d (see DORK-02)", got, minTotal)
+	}
+}
+
+// TestDorkCountPerSource enforces per-source minimums so a partial regression
+// (e.g. deleting all github dorks) is caught even if the total still clears
+// 150 via other sources.
+func TestDorkCountPerSource(t *testing.T) {
+	r, err := NewRegistry()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	minimums := map[string]int{
+		"github":  50,
+		"google":  30,
+		"shodan":  20,
+		"censys":  15,
+		"zoomeye": 10,
+		"fofa":    10,
+		"gitlab":  10,
+		"bing":    5,
+	}
+	stats := r.Stats()
+	for src, min := range minimums {
+		if stats.BySource[src] < min {
+			t.Errorf("source %s: got %d, want >= %d", src, stats.BySource[src], min)
+		}
+	}
+}
+
+// TestDorkCategoriesPresent guarantees every category in the DORK-01 schema
+// has at least one representative dork in the embedded corpus.
+func TestDorkCategoriesPresent(t *testing.T) {
+	r, err := NewRegistry()
+	if err != nil {
+		t.Fatal(err)
+	}
+	required := []string{"frontier", "specialized", "infrastructure", "emerging", "enterprise"}
+	stats := r.Stats()
+	for _, c := range required {
+		if stats.ByCategory[c] == 0 {
+			t.Errorf("category %q missing", c)
+		}
+	}
+}
+
+// TestDorkIDsUnique ensures no two dork files (across sources) use the same
+// ID. Duplicate IDs would cause the later entry to shadow the earlier one in
+// Registry.Get lookups.
+func TestDorkIDsUnique(t *testing.T) {
+	r, err := NewRegistry()
+	if err != nil {
+		t.Fatal(err)
+	}
+	seen := map[string]string{}
+	for _, d := range r.List() {
+		if existing, ok := seen[d.ID]; ok {
+			t.Errorf("duplicate dork id %q (second occurrence: %s, first: %s)", d.ID, d.Source, existing)
+		}
+		seen[d.ID] = d.Source
+	}
+}