An answer from the app without a Content-Type reaches the client without one (closes #127)

Go's server adds a Content-Type it guesses from the body when the
response's headers have no Content-Type key, which happened to some
of the app's answers and not others, as the first part of the body or
the headers went out first. When the app sends none, smallwebwaf now
sets the key with no value on the client's response, which sends none.

Model: opus-5-5

README.md

@@ -96,11 +96,14 @@ in `bin/state` unless `SWWAF_STATE_DIR` is set, and the default rule file of
 ## What it does so far
 
 - Passes each request to the app and the app's answer back unchanged: method,
-  path, query, headers, body and status. Bodies stream through in both
+  path, query, headers, body and status. The one exception is a path starting
-  directions and are never held whole in memory, but for the part of a request
+  with `//` that holds a character Go escapes, such as `|`: Go cannot send it as
-  body the Core Rule Set reads, at most `SWWAF_WAF_BODY_LIMIT` and one byte
+  it is, and the app receives it decoded and escaped again, `%2F` as `/`. Bodies
-  more, which is held until the app is sent it. A WebSocket, or any other
+  stream through in both directions and are never held whole in memory, but for
-  upgraded connection, passes through, and the timeouts do not cut it.
+  the part of a request body the Core Rule Set reads, at most
+  `SWWAF_WAF_BODY_LIMIT` and one byte more, which is held until the app is sent
+  it. A WebSocket, or any other upgraded connection, passes through, and the
+  timeouts do not cut it.
 - Works out the client's address. A TCP peer outside `SWWAF_TRUSTED_PROXIES` is
   the client, and the forwarded headers it sends are replaced, not passed on.
   For a peer inside it, `X-Forwarded-For` is read from the right, and the first

internal/proxy/coreruleset.go

@@ -23,7 +23,7 @@ import (
 // limit while the Core Rule Set reads it, which it notes nothing of.
 func (rq *request) checkCoreRuleSet() string {
 	cfg := rq.h.config
-	if cfg.WAFMode == config.WAFModeOff || pathExempt(rq.in.URL, cfg.WAFExemptPaths) {
+	if cfg.WAFMode == config.WAFModeOff || pathExempt(rq.in, cfg.WAFExemptPaths) {
 		return ""
 	}
 

internal/proxy/passthrough_test.go

@@ -74,6 +74,47 @@ func TestPassesRequestAndAnswerUnchanged(t *testing.T) {
 	wantRequestFields(t, line, addr, len(requestBody), len(answerBody))
 }
 
+func TestPassesThePathAsSent(t *testing.T) {
+	t.Parallel()
+
+	for _, path := range []string{
+		// An encoded slash and a character Go escapes: |, ^, and é sent
+		// as its UTF-8 bytes.
+		"/a%2Fb|c", "/feat%2Fx/file^1", "/x%2Fy/café",
+		// A path starting with //, which Go would send as a scheme and
+		// host if it were put in URL.Opaque.
+		"//a%2Fb",
+	} {
+		t.Run(path, func(t *testing.T) {
+			t.Parallel()
+
+			saw := make(chan string, 1)
+			app := startApp(t, func(_ http.ResponseWriter, r *http.Request) {
+				saw <- r.RequestURI
+			})
+			addr, out := startProxy(t, app.URL, nil)
+
+			conn := dial(t, addr)
+			send(t, conn, "GET "+path+"?q=1 HTTP/1.1\r\nHost: "+appHost+"\r\n\r\n")
+
+			got := readResponse(t, conn)
+			if got.status != http.StatusOK {
+				t.Fatalf("status %d, want %d", got.status, http.StatusOK)
+			}
+
+			target := <-saw
+			if target != path+"?q=1" {
+				t.Errorf("app saw %s, want %s", target, path+"?q=1")
+			}
+
+			line := out.requestLine(t)
+			if line.Path != path {
+				t.Errorf("log line has path %s, want %s", line.Path, path)
+			}
+		})
+	}
+}
+
 // wantAppSaw checks that the app received the test's request unchanged.
 func wantAppSaw(t *testing.T, saw appSaw, body []byte) {
 	t.Helper()
@@ -168,18 +209,13 @@ func TestAddsNoContentTypeTheAppDidNotSend(t *testing.T) {
 	})
 	addr, _ := startProxy(t, app.URL, nil)
 
-	// Go's server guesses a Content-Type for an answer without one only
+	got := get(t, addr, "/")
-	// when the first part of the body goes out with the headers, which
+	if got.header.Values("Content-Type") != nil {
-	// happens to some answers and not others: the test asks many times.
+		t.Errorf("client got Content-Type %q, want none",
-	for range 50 {
+			got.header.Get("Content-Type"))
-		got := get(t, addr, "/")
-		if got.header.Values("Content-Type") != nil {
-			t.Fatalf("client got Content-Type %q, want none",
-				got.header.Get("Content-Type"))
-		}
 	}
 
-	got := get(t, addr, "/typed")
+	got = get(t, addr, "/typed")
 	if got.header.Get("Content-Type") != typed {
 		t.Errorf("client got Content-Type %q, want %q",
 			got.header.Get("Content-Type"), typed)

internal/proxy/ratelimits_test.go

@@ -185,6 +185,9 @@ func TestRateLimitCountsPathsThatAreNotExempt(t *testing.T) {
 		"/assets/x%2Fy",
 		"/assets/x%2fy",
 		`/assets/x\y`,
+		// The same with a character Go escapes, |, for which Go's
+		// URL.EscapedPath gives /assets/x/y%7Cz, with no encoded slash.
+		"/assets/x%2Fy|z",
 	} {
 		t.Run(sent, func(t *testing.T) {
 			t.Parallel()

internal/proxy/request.go

@@ -8,7 +8,6 @@ import (
 	"net/http/httptrace"
 	"net/http/httputil"
 	"net/netip"
-	"net/url"
 	"os"
 	"slices"
 	"strings"
@@ -22,6 +21,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/lookup"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
+	"sneak.berlin/go/smallwebwaf/internal/rules"
 )
 
 // flushAfterEachWrite has ReverseProxy pass on each part of the app's
@@ -137,7 +137,7 @@ func (h *handler) newRequest(w http.ResponseWriter, r *http.Request) *request {
 			Method:           r.Method,
 			Scheme:           scheme(r, peerTrusted),
 			Host:             r.Host,
-			Path:             r.URL.EscapedPath(),
+			Path:             rules.Path(r),
 			Query:            r.URL.RawQuery,
 			Protocol:         r.Proto,
 			Referer:          r.Referer(),
@@ -284,7 +284,7 @@ func (rq *request) checkClient(ctx context.Context) string {
 	}
 
 	rq.counted = !isInside(rq.client, cfg.RateLimitExemptNets) &&
-		!pathExempt(rq.in.URL, cfg.RateLimitExemptPaths)
+		!pathExempt(rq.in, cfg.RateLimitExemptPaths)
 	if rq.counted {
 		rq.limitPercent, rq.bytesPercent = rq.limitPercentages()
 		rq.line.LimitPercent, rq.line.LimitPercentSetting = rq.limitPercent.logged()
@@ -307,7 +307,7 @@ func (rq *request) checkClient(ctx context.Context) string {
 	return rq.checkCoreRuleSet()
 }
 
-// pathExempt reports whether a request for u is exempt under prefixes,
+// pathExempt reports whether r is exempt under prefixes,
 // SWWAF_RATE_LIMIT_EXEMPT_PATHS or SWWAF_WAF_EXEMPT_PATHS: whether its
 // path as sent, the path the app receives, not percent-decoded, starts
 // with one of prefixes, so that /%61ssets/x is not under /assets/ for an
@@ -316,10 +316,9 @@ func (rq *request) checkClient(ctx context.Context) string {
 // encoded slash (%2F or %2f), never is, since an app may act on it as a
 // path outside every prefix: /assets/..%2Flogin as /login, or /assets%2Fx
 // as one path segment, as Go's router does.
-func pathExempt(u *url.URL, prefixes []string) bool {
+func pathExempt(r *http.Request, prefixes []string) bool {
-	decoded := u.Path
+	decoded := r.URL.Path
-	// EscapedPath is the path as the app receives it, not decoded.
+	sent := rules.Path(r)
-	sent := u.EscapedPath()
 
 	if strings.Contains(decoded, "..") || strings.Contains(decoded, `\`) ||
 		strings.Contains(strings.ToLower(sent), "%2f") {
@@ -375,6 +374,17 @@ func (rq *request) rewrite(pr *httputil.ProxyRequest) {
 	// ReverseProxy drops query parameters it cannot parse; the app gets
 	// the query as the client sent it.
 	pr.Out.URL.RawQuery = pr.In.URL.RawQuery
+	// ReverseProxy sends the path URL.EscapedPath gives, which, for a path
+	// holding a character Go escapes, such as |, is the whole path decoded
+	// and escaped again, %2F turned into /. Opaque is sent as it is, so the
+	// app gets the path as the client sent it. Left out are a target that
+	// is no path, such as *, and a path starting with //, which Go would
+	// send in Opaque as a scheme and host.
+	path := rules.Path(pr.In)
+	if strings.HasPrefix(path, "/") && !strings.HasPrefix(path, "//") {
+		pr.Out.URL.Opaque = path
+	}
+
 	setForwardedHeaders(pr.In, pr.Out, rq.peer, rq.peerTrusted)
 	pr.Out.Header.Set(requestIDHeader, rq.line.RequestID)
 	pr.Out.Header.Del(asnHeader)

internal/proxy/request_internal_test.go

@@ -0,0 +1,55 @@
+package proxy
+
+import (
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/config"
+)
+
+func TestAnAnswerWithoutAContentTypeGetsNone(t *testing.T) {
+	t.Parallel()
+
+	srv := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			rq := &request{
+				h:   &handler{config: &config.Config{}},
+				out: &responseWriter{ResponseWriter: w},
+			}
+			app := &http.Response{
+				StatusCode: http.StatusOK,
+				Header:     http.Header{},
+				Body:       http.NoBody,
+			}
+
+			err := rq.modifyResponse(app)
+			if err != nil {
+				t.Errorf("modifyResponse: %v", err)
+			}
+
+			// The headers go out with this, the first part of the body,
+			// which Go's server would guess a Content-Type from.
+			_, _ = io.WriteString(w, "<!doctype html><title>page</title>")
+		}))
+	t.Cleanup(srv.Close)
+
+	req, err := http.NewRequestWithContext(t.Context(), http.MethodGet, srv.URL,
+		http.NoBody)
+	if err != nil {
+		t.Fatalf("new request: %v", err)
+	}
+
+	res, err := srv.Client().Do(req)
+	if err != nil {
+		t.Fatalf("get: %v", err)
+	}
+
+	_ = res.Body.Close()
+
+	if res.Header.Values("Content-Type") != nil {
+		t.Errorf("client got Content-Type %q, want none",
+			res.Header.Get("Content-Type"))
+	}
+}