rproxy and servewaf replace the one-process smallwebwaf (closes #172, closes #165)

`smallwebwaf` with no command now prints the commands and exits with status 2.
The image runs rproxy, or servewaf with SMALLWEBWAF_COMMAND=servewaf. The
passing-on code, its settings and its log fields and metric go. internal/proxy
keeps the checks, answers, reports and own endpoints; its tests run through the
real rproxy. The documents describe the pair.

Judgement call: clients.json keeps token_refused, since state files refuse unknown fields.
Deviation: script/gitea-requests sets SWWAF_LOG_REQUEST_HEADERS, to label requests.
Partially verified: make example-app and make gitea-requests never built the image, as Ubuntu's snapshot service answered 5xx.

Model: opus-5-5

internal/proxy/proxy_test.go

@@ -5,6 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"io"
+	"log/slog"
 	"maps"
 	"net"
 	"net/http"
@@ -19,73 +20,68 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/proxy"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+	"sneak.berlin/go/smallwebwaf/internal/rproxy"
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 )
 
 const (
-	// shortTimeout is what a test sets a timeout to, to see it run out.
-	// It starts before the test has set up its case, such as an upgrade
-	// or the app's buffers filling, so it is as long as the hold-up of the
-	// test process that wantTimedOut allows: a shorter one can run out
-	// first on a busy host.
-	shortTimeout = waitLimit / 2
-	// longTimeoutSetting is a timeout that does not run out in a test.
-	longTimeoutSetting = "1m"
 	// waitLimit bounds how long a test waits for what should happen.
 	waitLimit = 10 * time.Second
 	// pollInterval is how often a test looks for a log line.
 	pollInterval = 10 * time.Millisecond
-	// localhost is where every test server listens, and so the address
-	// smallwebwaf sees each test's requests come from.
+	// localhost is where every test server listens, and so the address rproxy
+	// sees each test's requests come from.
 	localhost = "127.0.0.1"
 	// requestType is the type that marks a request log line.
 	requestType = "request"
-	// protocol is the protocol of every test's requests.
+	// protocol is the protocol of every question.
 	protocol = "HTTP/1.1"
+	// trustLocalhost trusts the address every test connects from, and a
+	// network for proxies in front of it.
+	trustLocalhost = localhost + "/32,10.0.0.0/8"
+	// appHost is the host every test asks for.
+	appHost = "app.example"
+	// client is the client's address, as a proxy names it.
+	client = "203.0.113.9"
+	// forwardedFor is the header that lists the client and its proxies,
+	// and forwardedProto the one that gives the scheme the client used.
+	forwardedFor   = "X-Forwarded-For"
+	forwardedProto = "X-Forwarded-Proto"
+	// secure is the scheme a client reached traefik with, and plain the one
+	// rproxy serves.
+	secure = "https"
+	plain  = "http"
 )
 
-// shortTimeoutSetting is shortTimeout as a setting's value.
-//
-//nolint:gochecknoglobals // a constant cannot call String
-var shortTimeoutSetting = shortTimeout.String()
-
 // The settings the tests set.
 const (
-	clientRequestTimeout    = "SWWAF_CLIENT_REQUEST_TIMEOUT"
-	clientHeaderMaxBytes    = "SWWAF_CLIENT_REQUEST_HEADER_MAX_BYTES"
-	clientIdleTimeout       = "SWWAF_CLIENT_IDLE_TIMEOUT"
-	clientResponseTimeout   = "SWWAF_CLIENT_RESPONSE_TIMEOUT"
-	upstreamRequestTimeout  = "SWWAF_UPSTREAM_REQUEST_TIMEOUT"
-	upstreamResponseTimeout = "SWWAF_UPSTREAM_RESPONSE_TIMEOUT"
-	mode                    = "SWWAF_MODE"
-	requestMaxBytes         = "SWWAF_REQUEST_MAX_BYTES"
-	responseMaxBytes        = "SWWAF_RESPONSE_MAX_BYTES"
-	trustedProxies          = "SWWAF_TRUSTED_PROXIES"
-	ipv6GroupPrefix         = "SWWAF_IPV6_GROUP_PREFIX"
-	maxTrackedClients       = "SWWAF_MAX_TRACKED_CLIENTS"
-	allowNets               = "SWWAF_ALLOW_NETS"
-	rateLimitExemptNets     = "SWWAF_RATE_LIMIT_EXEMPT_NETS"
-	denyNets                = "SWWAF_DENY_NETS"
-	rateLimitPerMinute      = "SWWAF_RATE_LIMIT_PER_MINUTE"
-	rateLimitPerDay         = "SWWAF_RATE_LIMIT_PER_DAY"
-	rateLimitExemptPaths    = "SWWAF_RATE_LIMIT_EXEMPT_PATHS"
-	lookupSource            = "SWWAF_LOOKUP_SOURCE"
-	lookupDBPath            = "SWWAF_LOOKUP_DB_PATH"
-	lookupTimeout           = "SWWAF_LOOKUP_TIMEOUT"
-	addLookupHeaders        = "SWWAF_ADD_LOOKUP_HEADERS"
-	deniedCountries         = "SWWAF_DENIED_COUNTRIES"
-	allowedCountries        = "SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES"
-	banResponse             = "SWWAF_BAN_RESPONSE"
-	limitBanDuration        = "SWWAF_LIMIT_BAN_DURATION"
-	limitBanRepeatWindow    = "SWWAF_LIMIT_BAN_REPEAT_WINDOW"
-	maxBanDuration          = "SWWAF_MAX_BAN_DURATION"
-	maxBans                 = "SWWAF_MAX_BANS"
-	banScopeV4Prefix        = "SWWAF_BAN_SCOPE_V4_PREFIX"
-	instanceName            = "SWWAF_INSTANCE_NAME"
-	logRequestHeaders       = "SWWAF_LOG_REQUEST_HEADERS"
-	attackBanDuration       = "SWWAF_ATTACK_BAN_DURATION"
-	rulesDir                = "SWWAF_RULES_DIR"
-	wafMode                 = "SWWAF_WAF_MODE"
+	mode                 = "SWWAF_MODE"
+	trustedProxies       = "SWRP_TRUSTED_PROXIES"
+	ipv6GroupPrefix      = "SWWAF_IPV6_GROUP_PREFIX"
+	maxTrackedClients    = "SWWAF_MAX_TRACKED_CLIENTS"
+	allowNets            = "SWWAF_ALLOW_NETS"
+	rateLimitExemptNets  = "SWWAF_RATE_LIMIT_EXEMPT_NETS"
+	denyNets             = "SWWAF_DENY_NETS"
+	rateLimitPerMinute   = "SWWAF_RATE_LIMIT_PER_MINUTE"
+	rateLimitPerDay      = "SWWAF_RATE_LIMIT_PER_DAY"
+	rateLimitExemptPaths = "SWWAF_RATE_LIMIT_EXEMPT_PATHS"
+	lookupSource         = "SWWAF_LOOKUP_SOURCE"
+	lookupDBPath         = "SWWAF_LOOKUP_DB_PATH"
+	lookupTimeout        = "SWWAF_LOOKUP_TIMEOUT"
+	addLookupHeaders     = "SWWAF_ADD_LOOKUP_HEADERS"
+	deniedCountries      = "SWWAF_DENIED_COUNTRIES"
+	allowedCountries     = "SWWAF_EXCLUSIVELY_ALLOWED_COUNTRIES"
+	banResponse          = "SWWAF_BAN_RESPONSE"
+	limitBanDuration     = "SWWAF_LIMIT_BAN_DURATION"
+	limitBanRepeatWindow = "SWWAF_LIMIT_BAN_REPEAT_WINDOW"
+	maxBanDuration       = "SWWAF_MAX_BAN_DURATION"
+	maxBans              = "SWWAF_MAX_BANS"
+	banScopeV4Prefix     = "SWWAF_BAN_SCOPE_V4_PREFIX"
+	instanceName         = "SWWAF_INSTANCE_NAME"
+	logRequestHeaders    = "SWWAF_LOG_REQUEST_HEADERS"
+	attackBanDuration    = "SWWAF_ATTACK_BAN_DURATION"
+	rulesDir             = "SWWAF_RULES_DIR"
+	wafMode              = "SWWAF_WAF_MODE"
 )
 
 // off is the value that switches a setting off.
@@ -179,6 +175,73 @@ func (o *output) requestLine(t *testing.T) logLine {
 	return o.requestLines(t, 1)[0]
 }
 
+// endedLines waits for count requests that went through rproxy, or to servewaf's
+// own endpoints, to have ended, and returns the last log line of each, in the
+// order servewaf took them. A question's last line is the one its report writes.
+func (o *output) endedLines(t *testing.T, count int) []logLine {
+	t.Helper()
+
+	deadline := time.Now().Add(waitLimit)
+	for time.Now().Before(deadline) {
+		found := o.lastLines(t)
+
+		ended := len(found) >= count
+		for _, line := range found[:min(count, len(found))] {
+			if line.ServeWAFLine == requestlog.ServeWAFLineDecision {
+				ended = false
+			}
+		}
+
+		if ended {
+			return found
+		}
+
+		time.Sleep(pollInterval)
+	}
+
+	t.Fatalf("fewer than %d requests have ended after %s", count, waitLimit)
+
+	return nil
+}
+
+// lastLines returns the last request log line written so far of each request,
+// in the order servewaf took them.
+func (o *output) lastLines(t *testing.T) []logLine {
+	t.Helper()
+
+	var found []logLine
+
+	places := map[string]int{}
+
+	for _, fields := range o.lines(t) {
+		if fields["type"] != requestType {
+			continue
+		}
+
+		line := decodeLine(t, fields)
+
+		place, seen := places[line.RequestID]
+		if seen {
+			found[place] = line
+
+			continue
+		}
+
+		places[line.RequestID] = len(found)
+		found = append(found, line)
+	}
+
+	return found
+}
+
+// endedLine waits for a test's one request to have ended, and returns its last
+// log line.
+func (o *output) endedLine(t *testing.T) logLine {
+	t.Helper()
+
+	return o.endedLines(t, 1)[0]
+}
+
 // decodeLine reads a request log line's fields into a logLine.
 func decodeLine(t *testing.T, fields map[string]any) logLine {
 	t.Helper()
@@ -198,7 +261,7 @@ func decodeLine(t *testing.T, fields map[string]any) logLine {
 	return line
 }
 
-// startApp starts app as the app smallwebwaf passes requests to.
+// startApp starts app as the app rproxy passes requests to.
 func startApp(t *testing.T, app http.HandlerFunc) *httptest.Server {
 	t.Helper()
 
@@ -208,9 +271,9 @@ func startApp(t *testing.T, app http.HandlerFunc) *httptest.Server {
 	return server
 }
 
-// startProxy starts smallwebwaf in front of the app at appURL, with the
-// settings in env on top of the defaults, and returns where it listens and
-// what it writes.
+// startProxy starts servewaf, and rproxy in front of the app at appURL, each with
+// the settings in env on top of the defaults, and returns where rproxy listens
+// and what servewaf writes.
 func startProxy(t *testing.T, appURL string, env map[string]string) (string, *output) {
 	t.Helper()
 
@@ -230,10 +293,10 @@ func startProxyWithGeoJS(
 }
 
 // startProxyWithClock is startProxyWithGeoJS with requests counted and
-// bans made by the time now tells, and returns the server as well. Unless
-// env sets SWWAF_RULES_DIR, it is an empty directory, of no rules, and
-// unless it sets SWWAF_INSTANCE_NAME, that is app, the label instance of
-// every metric.
+// bans made by the time now tells, and returns servewaf's server as well, whose
+// Addr is where servewaf listens. Unless env sets SWWAF_RULES_DIR, it is an empty
+// directory, of no rules, and unless it sets SWWAF_INSTANCE_NAME, that is app,
+// the label instance of every metric.
 func startProxyWithClock(
 	t *testing.T, appURL, geojsURL string, now func() time.Time,
 	env map[string]string,
@@ -246,14 +309,70 @@ func startProxyWithClock(
 }
 
 // startProxyWithAlerts is startProxyWithClock, and returns the queue of
-// the alerts the proxy raises as well, as newProxy makes them.
+// the alerts servewaf raises as well, as newServeWAF makes them.
 func startProxyWithAlerts(
 	t *testing.T, appURL, geojsURL string, now func() time.Time,
 	env map[string]string,
 ) (string, *output, *proxy.Server, *alerts.Queue) {
 	t.Helper()
 
-	server, out, alertQueue := newProxy(t, appURL, geojsURL, now, env)
+	server, out, alertQueue := newServeWAF(t, geojsURL, now, env)
+	serve(t, server)
+
+	return startRProxy(t, server.Addr, appURL, env), out, server, alertQueue
+}
+
+// serve serves server on a port of its own until the test ends, and sets its
+// Addr to where it listens.
+func serve(t *testing.T, server *proxy.Server) {
+	t.Helper()
+
+	listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+
+	server.Addr = listener.Addr().String()
+
+	go func() {
+		_ = server.Serve(listener)
+	}()
+
+	t.Cleanup(func() {
+		_ = server.Close()
+	})
+}
+
+// startRProxy starts rproxy in front of the app at appURL, asking the servewaf
+// at serveWAFAddr, with the settings in env on top of the defaults, and returns
+// where it listens. What it writes is dropped. SWRP_TIMEOUT_MS is a minute unless
+// env sets it, so that on a busy host SWRP_DEFAULT_DISPOSITION does not decide.
+func startRProxy(
+	t *testing.T, serveWAFAddr, appURL string, env map[string]string,
+) string {
+	t.Helper()
+
+	settings := map[string]string{
+		"SWRP_WAF_BACKEND":  "http://" + serveWAFAddr,
+		"SWRP_UPSTREAM_URL": appURL,
+		"SWRP_TIMEOUT_MS":   "60000",
+	}
+	maps.Copy(settings, env)
+
+	cfg, err := config.RProxyFromEnvironment(func(name string) (string, bool) {
+		value, ok := settings[name]
+
+		return value, ok
+	})
+	if err != nil {
+		t.Fatalf("settings %v: %v", settings, err)
+	}
+
+	server := rproxy.New(rproxy.Params{
+		Config:     cfg,
+		RequestLog: io.Discard,
+		ProcessLog: requestlog.NewProcessLogger(io.Discard, "rproxy", slog.LevelInfo),
+	})
 
 	listener, err := (&net.ListenConfig{}).Listen(t.Context(), "tcp", localhost+":0")
 	if err != nil {
@@ -268,38 +387,35 @@ func startProxyWithAlerts(
 		_ = server.Close()
 	})
 
-	return listener.Addr().String(), out, server, alertQueue
+	return listener.Addr().String()
 }
 
-// newProxy makes the server startProxyWithClock starts, without starting
-// it, and returns it, what it writes, and the queue of the alerts the
-// proxy raises, as the settings in env make it. No alert is sent from the
-// queue: they wait in it, for the test to look at. With no geojsURL, there
-// is no stand-in for GeoJS to look clients up at, and SWWAF_LOOKUP_SOURCE
-// is off unless env sets it. While it is file, the lookup database
-// SWWAF_LOOKUP_DB_PATH names is read. Clients are checked with AbuseIPDB
-// at abuseIPDBURL while env sets SWWAF_ABUSEIPDB_KEY. SWWAF_WAF_MODE is off
-// unless env sets it, so that only the tests of the Core Rule Set have
-// their requests inspected by it.
-func newProxy(
-	t *testing.T, appURL, geojsURL string, now func() time.Time,
-	env map[string]string,
+// newServeWAF makes servewaf's server, without starting it, and returns it, what
+// it writes, and the queue of the alerts it raises, as the settings in env make
+// it. No alert is sent from the queue: they wait in it, for the test to look at.
+// With no geojsURL, there is no stand-in for GeoJS to look clients up at, and
+// SWWAF_LOOKUP_SOURCE is off unless env sets it. While it is file, the lookup
+// database SWWAF_LOOKUP_DB_PATH names is read. Clients are checked with AbuseIPDB
+// at abuseIPDBURL while env sets SWWAF_ABUSEIPDB_KEY. SWWAF_WAF_MODE is off unless
+// env sets it, so that only the tests of the Core Rule Set have their requests
+// inspected by it.
+func newServeWAF(
+	t *testing.T, geojsURL string, now func() time.Time, env map[string]string,
 ) (*proxy.Server, *output, *alerts.Queue) {
 	t.Helper()
 
-	return newServerWith(t, proxy.New, appURL, geojsURL, now, env)
+	return newServeWAFWith(t, proxy.NewServeWAF, geojsURL, now, env)
 }
 
-// newServerWith is newProxy for the server build makes.
-func newServerWith(
+// newServeWAFWith is newServeWAF for the server build makes.
+func newServeWAFWith(
 	t *testing.T, build func(proxy.Params) *proxy.Server,
-	appURL, geojsURL string, now func() time.Time, env map[string]string,
+	geojsURL string, now func() time.Time, env map[string]string,
 ) (*proxy.Server, *output, *alerts.Queue) {
 	t.Helper()
 
 	settings := map[string]string{
-		"SWWAF_UPSTREAM_URL": appURL, rulesDir: t.TempDir(), instanceName: "app",
-		wafMode: off,
+		rulesDir: t.TempDir(), instanceName: "app", wafMode: off,
 	}
 	if geojsURL == "" {
 		settings[lookupSource] = off
@@ -391,7 +507,7 @@ func readAnswer(res *http.Response) answer {
 	return answer{status: res.StatusCode, header: res.Header, body: body, err: err}
 }
 
-// newRequest makes a request for path to smallwebwaf at addr.
+// newRequest makes a request for path to addr, where rproxy or servewaf listens.
 func newRequest(t *testing.T, method, addr, path string, body io.Reader) *http.Request {
 	t.Helper()
 
@@ -415,15 +531,15 @@ func do(t *testing.T, req *http.Request) answer {
 	return readAnswer(res)
 }
 
-// get sends a GET request for path to smallwebwaf at addr.
+// get sends a GET request for path to addr.
 func get(t *testing.T, addr, path string) answer {
 	t.Helper()
 
 	return do(t, newRequest(t, http.MethodGet, addr, path, http.NoBody))
 }
 
-// dial opens a connection to smallwebwaf at addr, for requests the HTTP
-// client cannot make, such as one that stops sending halfway.
+// dial opens a connection to addr, for requests the HTTP client cannot make,
+// such as one that stops sending halfway.
 func dial(t *testing.T, addr string) net.Conn {
 	t.Helper()
 
@@ -484,14 +600,3 @@ func wantStatus(t *testing.T, got answer, status int) {
 		t.Errorf("status %d, want %d", got.status, status)
 	}
 }
-
-// wantTimedOut checks that what began at start ended once shortTimeout
-// had run out, and not much later.
-func wantTimedOut(t *testing.T, start time.Time) {
-	t.Helper()
-
-	took := time.Since(start)
-	if took < shortTimeout || took > shortTimeout+waitLimit/2 {
-		t.Errorf("took %s, want %s", took, shortTimeout)
-	}
-}