pixa/internal/server/source_url_internal_test.go

package server

import (
	"net/http"
	"net/http/httptest"
	"net/url"
	"regexp"
	"slices"
	"strings"
	"sync"
	"testing"

	"sneak.berlin/go/pixa/internal/imgcache"
	"sneak.berlin/go/pixa/internal/session"
)

// percentSignPath is a source path holding a "%", which a URL writes %25.
const percentSignPath = "/100%25.png"

// generateFormPattern extracts the CSRF token rendered into the generator
// page's form.
var generateFormPattern = regexp.MustCompile(
	`(?s)action="/generate".*?name="gorilla\.csrf\.Token" value="([^"]+)"`)

// generatedURLPattern extracts the path of the encrypted URL the generator
// page shows.
var generatedURLPattern = regexp.MustCompile(`value="[^"]*(/v1/e/[^"]+)"`)

// recordingUpstream is a test upstream that answers every request with a PNG
// and records the request target, the path and query as sent, of each request
// it receives.
type recordingUpstream struct {
	*httptest.Server

	mu       sync.Mutex
	received []string
}

// startRecordingUpstream starts a recordingUpstream, which is closed when the
// test ends.
func startRecordingUpstream(t *testing.T) *recordingUpstream {
	t.Helper()

	source := encodeTestPNG(t, 64, 48)
	upstream := &recordingUpstream{}

	upstream.Server = httptest.NewServer(http.HandlerFunc(
		func(w http.ResponseWriter, r *http.Request) {
			upstream.mu.Lock()
			upstream.received = append(upstream.received, r.RequestURI)
			upstream.mu.Unlock()

			w.Header().Set("Content-Type", "image/png")
			_, _ = w.Write(source)
		}))
	t.Cleanup(upstream.Close)

	return upstream
}

// requestTargets returns the request targets the upstream has received, in
// the order it received them.
func (u *recordingUpstream) requestTargets() []string {
	u.mu.Lock()
	defer u.mu.Unlock()

	return slices.Clone(u.received)
}

// pageOrigin is the origin of the login and generator pages below, opened
// over HTTPS; httptest gives every request the host example.com.
const pageOrigin = "https://example.com"

// openRoot sends GET / to s over HTTPS, with cookie when it is not nil, and
// returns the page: the login page, or the generator page for a login session.
func openRoot(
	t *testing.T, s *Server, cookie *http.Cookie,
) *httptest.ResponseRecorder {
	t.Helper()

	req := httptest.NewRequestWithContext(t.Context(), http.MethodGet,
		pageOrigin+"/", nil)
	if cookie != nil {
		req.AddCookie(cookie)
	}

	page := httptest.NewRecorder()
	s.ServeHTTP(page, req)

	return page
}

// submitForm posts form to path on s as a browser submits it from page over
// HTTPS: with the CSRF token tokenPattern finds in page, the cookies page set,
// cookie when it is not nil, and a Referer naming the page, which pixa needs
// while debug is off, as it is in startImageProxy's config.
func submitForm(
	t *testing.T, s *Server, page *httptest.ResponseRecorder,
	tokenPattern *regexp.Regexp, path string, form url.Values,
	cookie *http.Cookie,
) *httptest.ResponseRecorder {
	t.Helper()

	match := tokenPattern.FindStringSubmatch(page.Body.String())
	if match == nil {
		t.Fatalf("the page has no form for %s with a CSRF token", path)
	}

	form.Set("gorilla.csrf.Token", match[1])

	req := httptest.NewRequestWithContext(t.Context(), http.MethodPost,
		pageOrigin+path, strings.NewReader(form.Encode()))
	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
	req.Header.Set("Referer", pageOrigin+"/")

	for _, c := range page.Result().Cookies() {
		req.AddCookie(c)
	}

	if cookie != nil {
		req.AddCookie(cookie)
	}

	rec := httptest.NewRecorder()
	s.ServeHTTP(rec, req)

	return rec
}

// postGenerate logs in to s with the signing key, submits the generator page's
// form with sourceURL, and returns the response.
func postGenerate(
	t *testing.T, s *Server, sourceURL string,
) *httptest.ResponseRecorder {
	t.Helper()

	login := submitForm(t, s, openRoot(t, s, nil), csrfFieldPattern, "/",
		url.Values{"key": {testSigningKey}}, nil)

	var sessionCookie *http.Cookie

	for _, c := range login.Result().Cookies() {
		if c.Name == session.CookieName {
			sessionCookie = c
		}
	}

	if sessionCookie == nil {
		t.Fatalf("logging in answered %d and set no session cookie", login.Code)
	}

	rec := submitForm(t, s, openRoot(t, s, sessionCookie), generateFormPattern,
		"/generate", url.Values{"url": {sourceURL}}, sessionCookie)
	t.Logf("POST /generate with url %s: %d", sourceURL, rec.Code)

	return rec
}

// TestImageURLFetchesItsSourcePathAndQuery requests image URLs whose source
// query holds a space and whose source path holds a "%", each written
// percent-encoded, and checks the one request the upstream receives: the
// source path percent-encoded again, and the source query with the space
// written %20.
func TestImageURLFetchesItsSourcePathAndQuery(t *testing.T) {
	t.Parallel()

	tests := []struct {
		name string
		// pathAndQuery is the source path and query as the image URL writes
		// them
		pathAndQuery string
		// wantRequest is the path and query the upstream must receive
		wantRequest string
	}{
		{"space in the query", "/photo.png%3Fname=my%20cat",
			"/photo.png?name=my%20cat"},
		{"percent sign in the path", percentSignPath, percentSignPath},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			upstream := startRecordingUpstream(t)
			s, _, _ := startImageProxy(t, upstream.Server)

			getImage(t, s, "/v1/image/"+upstreamHost+tt.pathAndQuery+"/orig.png")

			got := upstream.requestTargets()
			t.Logf("upstream received %q", got)

			if !slices.Equal(got, []string{tt.wantRequest}) {
				t.Errorf("upstream received %q, want [%q]", got, tt.wantRequest)
			}
		})
	}
}

// TestSourcePathsHoldingSpaceAndPercent20AreFetchedApart requests twice each
// of the source paths /my cat.png and /my%20cat.png, which the image URL
// writes my%20cat.png and my%2520cat.png. Each is fetched once, as a request
// of its own, and its second request is served from the cache.
func TestSourcePathsHoldingSpaceAndPercent20AreFetchedApart(t *testing.T) {
	t.Parallel()

	upstream := startRecordingUpstream(t)
	s, _, _ := startImageProxy(t, upstream.Server)

	imageURLs := []string{
		"/v1/image/" + upstreamHost + "/my%20cat.png/orig.png",
		"/v1/image/" + upstreamHost + "/my%2520cat.png/orig.png",
	}

	for _, imageURL := range imageURLs {
		getImage(t, s, imageURL)
	}

	for _, imageURL := range imageURLs {
		cacheStatus := getImage(t, s, imageURL).Header().Get("X-Pixa-Cache")
		if cacheStatus != string(imgcache.CacheHit) {
			t.Errorf("second GET %s: X-Pixa-Cache = %q, want HIT",
				imageURL, cacheStatus)
		}
	}

	got := upstream.requestTargets()
	t.Logf("upstream received %q", got)

	want := []string{"/my%20cat.png", "/my%2520cat.png"}
	if !slices.Equal(got, want) {
		t.Errorf("upstream received %q, want %q", got, want)
	}
}

// TestSourceQueryWrittenTwoWaysIsOneUpstreamRequest requests the source query
// name=my%20cat written as the README says, name=my%2520cat, and with the
// space written %20, name=my%20cat. Both are one source query: the upstream
// receives one request, and the second image URL is served from the cache.
func TestSourceQueryWrittenTwoWaysIsOneUpstreamRequest(t *testing.T) {
	t.Parallel()

	upstream := startRecordingUpstream(t)
	s, _, _ := startImageProxy(t, upstream.Server)

	getImage(t, s, "/v1/image/"+upstreamHost+"/photo.png%3Fname=my%2520cat/orig.png")

	second := getImage(t, s,
		"/v1/image/"+upstreamHost+"/photo.png%3Fname=my%20cat/orig.png")
	if got := second.Header().Get("X-Pixa-Cache"); got != string(imgcache.CacheHit) {
		t.Errorf("second X-Pixa-Cache = %q, want HIT", got)
	}

	got := upstream.requestTargets()
	t.Logf("upstream received %q", got)

	want := []string{"/photo.png?name=my%20cat"}
	if !slices.Equal(got, want) {
		t.Errorf("upstream received %q, want %q", got, want)
	}
}

// TestGeneratedURLFetchesTheSourceURLAsEntered makes an encrypted URL on the
// generator page for source URLs holding %20, %25 and %23 in the path or the
// query, requests it, and checks that the upstream receives the path and
// query exactly as entered.
func TestGeneratedURLFetchesTheSourceURLAsEntered(t *testing.T) {
	t.Parallel()

	// The names hold no "%": each test's state directory is named after it
	// and goes into the database URL, which decodes percent-escapes
	tests := []struct {
		name         string
		pathAndQuery string
	}{
		{"space in the path", "/my%20cat.png"},
		{"percent sign in the path", percentSignPath},
		{"number sign in the path", "/a%23b.png"},
		{"all three in the query", "/photo.png?name=my%20cat%25%23"},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			upstream := startRecordingUpstream(t)
			s, _, _ := startImageProxy(t, upstream.Server)

			rec := postGenerate(t, s, "https://"+upstreamHost+tt.pathAndQuery)

			match := generatedURLPattern.FindStringSubmatch(rec.Body.String())
			if rec.Code != http.StatusOK || match == nil {
				t.Fatalf("POST /generate: %d with no encrypted URL; body %s",
					rec.Code, rec.Body.String())
			}

			getImage(t, s, match[1])

			got := upstream.requestTargets()
			t.Logf("upstream received %q", got)

			if !slices.Equal(got, []string{tt.pathAndQuery}) {
				t.Errorf("upstream received %q, want [%q]", got, tt.pathAndQuery)
			}
		})
	}
}

// TestGeneratorRefusesSourceURLItWouldFetchAnotherWay submits a source URL
// whose path holds %2F. pixa keeps the path decoded and would fetch it with a
// "/" there, which is another URL, so the generator page answers 400, shows
// the URL pixa would fetch, and makes no encrypted URL.
func TestGeneratorRefusesSourceURLItWouldFetchAnotherWay(t *testing.T) {
	t.Parallel()

	s, _, _ := startImageProxy(t, startRecordingUpstream(t).Server)

	rec := postGenerate(t, s, "https://"+upstreamHost+"/a%2Fb.png")
	body := rec.Body.String()

	if rec.Code != http.StatusBadRequest {
		t.Errorf("status = %d, want %d", rec.Code, http.StatusBadRequest)
	}

	if strings.Contains(body, "/v1/e/") {
		t.Error("the page shows an encrypted URL")
	}

	// The test config sets allow_http, so pixa would fetch over plain HTTP
	fetchURL := "http://" + upstreamHost + "/a/b.png"
	if !strings.Contains(body, fetchURL) {
		t.Errorf("the page does not show the URL pixa would fetch, %s; body %s",
			fetchURL, body)
	}
}