weircon-random-proxy/service/main_test.go

package main

import (
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"
	"time"
)

func TestStripIdentifying(t *testing.T) {
	h := http.Header{}

	// Headers that MUST be removed before the request reaches the target.
	removed := []string{
		"X-Weircon-Random-Ip",
		"X-Weircon-Proxy-Id",
		"X-Forwarded-For",
		"X-Forwarded-Host",
		"X-Forwarded-Proto",
		"X-Forwarded-Port",
		"X-Forwarded-Custom-Vendor", // caught by prefix sweep
		"X-Real-Ip",
		"Forwarded",
		"Via",
		"Cf-Connecting-Ip",
		"True-Client-Ip",
		"Fastly-Client-Ip",
		"X-Original-Forwarded-For",
		"X-Client-Ip",
		"X-Weircon-Anything-New", // caught by prefix sweep
		"From",
		"Sec-Ch-Ua",
		"Sec-Ch-Ua-Platform",
	}
	for _, k := range removed {
		h.Set(k, "leak")
	}

	// Headers a crawler legitimately sets — these MUST survive untouched.
	kept := map[string]string{
		"User-Agent":      "my-crawler/1.0",
		"Cookie":          "session=abc",
		"Accept":          "text/html",
		"Accept-Language": "en-US",
		"Referer":         "https://example.com",
		"X-Forward":       "not-a-forwarding-header", // does not match "X-Forwarded" prefix
	}
	for k, v := range kept {
		h.Set(k, v)
	}

	stripIdentifying(h)

	for _, k := range removed {
		if got := h.Get(k); got != "" {
			t.Errorf("expected %q to be stripped, still present: %q", k, got)
		}
	}
	for k, want := range kept {
		if got := h.Get(k); got != want {
			t.Errorf("expected %q to survive as %q, got %q", k, want, got)
		}
	}
}

func TestAnonymizeOverridesUserAgent(t *testing.T) {
	for _, ua := range []string{"crawlkit-roles", "python-requests/2.32", "Go-http-client/1.1", ""} {
		h := http.Header{}
		if ua != "" {
			h.Set("User-Agent", ua)
		}
		h.Set("X-Forwarded-For", "10.0.0.1")
		anonymize(h, defaultUserAgent)
		if got := h.Values("User-Agent"); len(got) != 1 || got[0] != defaultUserAgent {
			t.Errorf("caller UA %q: outbound User-Agent = %q, want only the browser UA", ua, got)
		}
		if h.Get("X-Forwarded-For") != "" {
			t.Errorf("anonymize must still strip forwarding headers")
		}
	}
}

func TestDefaultUserAgentIsBrowser(t *testing.T) {
	if !strings.HasPrefix(defaultUserAgent, "Mozilla/5.0 (") || !strings.Contains(defaultUserAgent, "Firefox/") {
		t.Errorf("default UA should be a plain Firefox string, got %q", defaultUserAgent)
	}
}

// End to end: what the TARGET receives when a careless client goes through the
// full handler. This is the no-leak contract, not just the helper.
func TestHandlerTargetSeesOnlyBrowser(t *testing.T) {
	var got http.Header
	target := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		got = r.Header.Clone()
	}))
	defer target.Close()

	cfg := Config{UserAgent: defaultUserAgent}
	mgr := newProxyManager(1, 0, 0, time.Minute)
	h := newHandler(cfg, []*http.Transport{{}}, mgr)

	req := httptest.NewRequest(http.MethodGet, "/", nil)
	req.Header.Set("X-Weircon-Random-Ip", "secret-key")
	req.Header.Set("X-Weircon-Random-Ip-Redirect", target.URL+"/x")
	req.Header.Set("User-Agent", "crawlkit-roles")
	req.Header.Set("From", "someone@example.com")
	req.Header.Set("X-Forwarded-For", "192.168.10.144")
	req.Header.Set("X-Real-Ip", "192.168.10.144")
	req.Header.Set("Sec-Ch-Ua", `"Chromium";v="125"`)
	rec := httptest.NewRecorder()
	h.ServeHTTP(rec, req)

	if rec.Code != http.StatusOK {
		t.Fatalf("status %d: %s", rec.Code, rec.Body.String())
	}
	if ua := got.Values("User-Agent"); len(ua) != 1 || ua[0] != defaultUserAgent {
		t.Errorf("target saw User-Agent %q", ua)
	}
	for k, v := range got {
		lk := strings.ToLower(k + ":" + strings.Join(v, ","))
		for _, bad := range []string{"weircon", "crawlkit", "secret-key", "192.168.", "example.com", "forwarded", "sec-ch-ua", "from:"} {
			if strings.Contains(lk, bad) {
				t.Errorf("target saw identifying header %s: %v", k, v)
			}
		}
	}
}