Country allow and deny lists, looked up through GeoJS (closes #44)

SWWAF_DENIED_COUNTRIES and SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES refuse a
request with 403 before its body is read or rate-limited, logged as
country_denied. internal/lookup asks GeoJS only while a list is set, 200
clients per request, one at a time, keeping answers 7 days. Failures, a
redirect or an answer leaving an address out included, are logged without
addresses; GeoJS is then left alone a second, doubling to five minutes.
Private, loopback and link-local clients are never sent.

Deviation, per the issue: no SWWAF_LOOKUP_SOURCE or SWWAF_LOOKUP_TIMEOUT; 403, not SWWAF_BAN_RESPONSE.
Deviation: GeoJS's country endpoint, not geo.json.
Judgement call: an IPv6 /64 is asked about by its first address; at most 10,000 clients wait.
Judgement call: config.go lists the ISO 3166-1 codes; no widely used library holds them.

Model: opus-5-5

internal/proxy/countries_test.go

@@ -0,0 +1,267 @@
+package proxy_test
+
+import (
+	"encoding/json"
+	"maps"
+	"net/http"
+	"net/http/httptest"
+	"slices"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+)
+
+// The clients the stand-in for GeoJS knows about.
+const (
+	// fromDE is placed in Germany.
+	fromDE = client
+	// fromKP is placed in North Korea.
+	fromKP = "198.51.100.7"
+	// unplaced cannot be placed in any country.
+	unplaced = "192.0.2.1"
+)
+
+func TestCountryLists(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name    string
+		env     map[string]string
+		refused []string
+	}{
+		{"denied", map[string]string{deniedCountries: "kp"}, []string{fromKP}},
+		{
+			"exclusively allowed", map[string]string{allowedCountries: "DE"},
+			[]string{fromKP, unplaced},
+		},
+		{
+			"both", map[string]string{deniedCountries: "kp", allowedCountries: "de,fr"},
+			[]string{fromKP, unplaced},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			var calls atomic.Int32
+
+			app := startApp(t, func(http.ResponseWriter, *http.Request) {
+				calls.Add(1)
+			})
+			geojsURL, _ := startGeoJS(t)
+			env := map[string]string{trustedProxies: trustLocalhost}
+			maps.Copy(env, tc.env)
+			addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, env)
+
+			for i, sent := range []struct{ client, country string }{
+				{fromDE, "DE"}, {fromKP, "KP"}, {unplaced, ""},
+			} {
+				req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
+				req.Header.Set(forwardedFor, sent.client)
+				got := do(t, req)
+
+				line := out.requestLines(t, i+1)[i]
+				if line.Country != sent.country {
+					t.Errorf("log line has country %q, want %q", line.Country, sent.country)
+				}
+
+				if slices.Contains(tc.refused, sent.client) {
+					wantStatus(t, got, http.StatusForbidden)
+					wantLine(t, line, http.StatusForbidden, requestlog.ActionCountryDenied)
+				} else {
+					wantStatus(t, got, http.StatusOK)
+					wantLine(t, line, http.StatusOK, requestlog.ActionForward)
+				}
+			}
+
+			if int(calls.Load()) != 3-len(tc.refused) {
+				t.Errorf("the app was called %d times, want %d",
+					calls.Load(), 3-len(tc.refused))
+			}
+		})
+	}
+}
+
+func TestCountryRefusalComesBeforeTheBody(t *testing.T) {
+	t.Parallel()
+
+	var calls atomic.Int32
+
+	app := startApp(t, func(http.ResponseWriter, *http.Request) {
+		calls.Add(1)
+	})
+	geojsURL, _ := startGeoJS(t)
+	addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, map[string]string{
+		trustedProxies:  trustLocalhost,
+		deniedCountries: "kp",
+	})
+
+	req := newRequest(t, http.MethodPost, addr, "/", strings.NewReader("a body"))
+	req.Header.Set(forwardedFor, fromKP)
+	wantStatus(t, do(t, req), http.StatusForbidden)
+
+	line := out.requestLine(t)
+	wantLine(t, line, http.StatusForbidden, requestlog.ActionCountryDenied)
+
+	if line.RequestBytes != 0 {
+		t.Errorf("log line has request_bytes %d, want 0", line.RequestBytes)
+	}
+
+	if calls.Load() != 0 {
+		t.Errorf("the app was called %d times, want none", calls.Load())
+	}
+}
+
+func TestRequestRefusedByCountryIsNotCounted(t *testing.T) {
+	t.Parallel()
+
+	// The stand-in for GeoJS fails until placing is set, and then places
+	// every address in Germany.
+	var placing atomic.Bool
+
+	geojs := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			if !placing.Load() {
+				w.WriteHeader(http.StatusServiceUnavailable)
+
+				return
+			}
+
+			answer := []map[string]string{{"ip": r.URL.Query().Get("ip"), "country": "DE"}}
+
+			err := json.NewEncoder(w).Encode(answer)
+			if err != nil {
+				http.Error(w, err.Error(), http.StatusInternalServerError)
+			}
+		}))
+	t.Cleanup(geojs.Close)
+
+	app := startApp(t, func(http.ResponseWriter, *http.Request) {})
+	addr, _ := startProxyWithGeoJS(t, app.URL, geojs.URL, map[string]string{
+		trustedProxies:     trustLocalhost,
+		allowedCountries:   "de",
+		rateLimitPerMinute: "1",
+	})
+
+	request := func() answer {
+		req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
+		req.Header.Set(forwardedFor, fromDE)
+
+		return do(t, req)
+	}
+
+	// While GeoJS fails, the client's country cannot be found, and its
+	// request is refused.
+	wantStatus(t, request(), http.StatusForbidden)
+
+	// Once GeoJS places it, a second after the failure, its requests are let
+	// through. No refused one was counted, so the first let through is
+	// within the limit of one a minute.
+	placing.Store(true)
+
+	deadline := time.Now().Add(waitLimit)
+	got := request()
+
+	for got.status == http.StatusForbidden && time.Now().Before(deadline) {
+		time.Sleep(pollInterval)
+
+		got = request()
+	}
+
+	wantStatus(t, got, http.StatusOK)
+}
+
+func TestCountryNotLookedUpWithoutAListOrForAPrivateAddress(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		name    string
+		env     map[string]string
+		clients []string // "" sends no X-Forwarded-For: the client is 127.0.0.1
+	}{
+		{"no country list is set", nil, []string{fromKP, fromDE}},
+		{
+			"private, loopback and link-local addresses",
+			map[string]string{allowedCountries: "de"},
+			[]string{"10.0.0.5", "192.168.1.9", "fd00::5", "", "169.254.0.9", "fe80::9"},
+		},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			app := startApp(t, func(http.ResponseWriter, *http.Request) {})
+			geojsURL, asked := startGeoJS(t)
+			env := map[string]string{trustedProxies: trustLocalhost}
+			maps.Copy(env, tc.env)
+			addr, out := startProxyWithGeoJS(t, app.URL, geojsURL, env)
+
+			for i, sent := range tc.clients {
+				req := newRequest(t, http.MethodGet, addr, "/", http.NoBody)
+				if sent != "" {
+					req.Header.Set(forwardedFor, sent)
+				}
+
+				wantStatus(t, do(t, req), http.StatusOK)
+
+				line := out.requestLines(t, i+1)[i]
+				wantLine(t, line, http.StatusOK, requestlog.ActionForward)
+
+				country, present := line.fields["country"]
+				if !present || country != "" {
+					t.Errorf("log line for %q has country %v, want an empty one",
+						line.ClientIP, country)
+				}
+			}
+
+			if len(asked()) != 0 {
+				t.Errorf("GeoJS was asked about %v, want nothing", asked())
+			}
+		})
+	}
+}
+
+// startGeoJS starts a stand-in for GeoJS, which places fromDE and fromKP
+// and no other address. It returns its URL, and what returns the
+// addresses it has been asked about.
+func startGeoJS(t *testing.T) (string, func() []string) {
+	t.Helper()
+
+	places := map[string]string{fromDE: "DE", fromKP: "KP"}
+
+	var asked struct {
+		mu    sync.Mutex
+		addrs []string
+	}
+
+	geojs := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			addrs := strings.Split(r.URL.Query().Get("ip"), ",")
+
+			asked.mu.Lock()
+			asked.addrs = append(asked.addrs, addrs...)
+			asked.mu.Unlock()
+
+			answers := make([]map[string]string, 0, len(addrs))
+			for _, addr := range addrs {
+				answers = append(answers, map[string]string{
+					"ip": addr, "country": places[addr],
+				})
+			}
+
+			err := json.NewEncoder(w).Encode(answers)
+			if err != nil {
+				http.Error(w, err.Error(), http.StatusInternalServerError)
+			}
+		}))
+	t.Cleanup(geojs.Close)
+
+	return geojs.URL, func() []string {
+		asked.mu.Lock()
+		defer asked.mu.Unlock()
+
+		return slices.Clone(asked.addrs)
+	}
+}