Fetch the source path and query URL-encoded, not joined as text (closes #288)

The source URL was built by joining the decoded path and query as
text, so a space in the query reached the upstream raw and failed with
502, 100%25.png made a URL Go could not parse and answered 401, and
%20 and %2520 fetched the same path under different cache keys. The
source URL is now built with net/url, so each decoded path and query is
one upstream request matching its signature and cache key; the query
encodes the characters a browser encodes, ' included. The generator page
compares what pixa would fetch with the URL as entered, and answers 400
with the URL to use when they differ, or for a user name and password
or a .. segment.

Model: opus-5-5

internal/handlers/auth.go

@@ -9,7 +9,9 @@ import (
 	"math"
 	"net/http"
 	"net/url"
+	"slices"
 	"strconv"
+	"strings"
 	"time"
 
 	"sneak.berlin/go/pixa/internal/clientip"
@@ -133,6 +135,16 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 			return
 		}
 
+		// /v1/image/ refuses a ".." segment in the source path, and so does
+		// the generator. The path is decoded, so %2e%2e counts too
+		if slices.Contains(strings.Split(parsed.Path, "/"), "..") {
+			s.renderGeneratorWithForm(w, r,
+				"Source URL path cannot hold a .. segment", r.Form,
+				http.StatusBadRequest)
+
+			return
+		}
+
 		payload, expiresAt, ttl, err := buildGeneratePayload(parsed, r.Form)
 		if err != nil {
 			s.renderGeneratorWithForm(w, r, err.Error(), r.Form,
@@ -141,6 +153,19 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 			return
 		}
 
+		// The image URL must fetch the source URL as it was written
+		sourceRequest := payload.ToImageRequest()
+		sourceRequest.AllowHTTP = s.config.AllowHTTP
+		fetchURL := sourceRequest.SourceURL()
+
+		if !fetchedAsWritten(parsed, fetchURL) {
+			s.renderGeneratorWithForm(w, r, "Source URL cannot be fetched as "+
+				"written: pixa would fetch "+fetchURL,
+				r.Form, http.StatusBadRequest)
+
+			return
+		}
+
 		// Generate encrypted token
 		token, err := s.encGen.Generate(payload)
 		if err != nil {
@@ -173,6 +198,29 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 	}
 }
 
+// fetchedAsWritten reports whether fetchURL, the URL pixa fetches for an
+// image URL made from the source URL source, is source as it was written,
+// apart from the scheme, which the token does not keep. It is not when source
+// holds a user name and password, which the token does not keep either, or a
+// "?" with no query after it. The token keeps the source path decoded and
+// pixa fetches it percent-encoded again, so a path written another way, such
+// as with %2F, is fetched as another path. url.URL keeps the path as written
+// in RawPath when it is not the decoded path percent-encoded again.
+// EscapedPath ignores RawPath when it also holds a character net/url encodes,
+// such as a space, so RawPath is compared itself.
+func fetchedAsWritten(source *url.URL, fetchURL string) bool {
+	writtenPath := source.RawPath
+	if writtenPath == "" {
+		writtenPath = source.EscapedPath()
+	}
+
+	fetched, err := url.Parse(fetchURL)
+
+	return err == nil && source.User == nil && !source.ForceQuery &&
+		fetched.EscapedPath() == writtenPath &&
+		fetched.RawQuery == source.RawQuery
+}
+
 // buildGeneratePayload parses the numeric form fields and assembles the
 // encrypted URL payload. ttl=0 means never expires (ExpiresAt stays 0). A
 // non-numeric or out-of-range width, height, quality or ttl, or an

internal/imgcache/imgcache.go

@@ -5,6 +5,7 @@ import (
 	"context"
 	"errors"
 	"io"
+	"net/url"
 	"time"
 )
 
@@ -86,9 +87,11 @@ func ValidateImageRequest(req *ImageRequest) error {
 type ImageRequest struct {
 	// SourceHost is the origin host (e.g., "cdn.example.com")
 	SourceHost string
-	// SourcePath is the path on the origin (e.g., "/photos/cat.jpg")
+	// SourcePath is the path on the origin with its percent-escapes decoded,
+	// as url.URL's Path holds it (e.g., "/photos/my cat.jpg")
 	SourcePath string
-	// SourceQuery is the optional query string for the origin URL
+	// SourceQuery is the optional query string for the origin URL as the URL
+	// writes it, percent-escapes included, as url.URL's RawQuery holds it
 	SourceQuery string
 	// Size is the requested output dimensions
 	Size Size
@@ -107,20 +110,25 @@ type ImageRequest struct {
 	AllowHTTP bool
 }
 
-// SourceURL returns the full upstream URL to fetch.
-// Uses http:// scheme when AllowHTTP is true, otherwise https://.
+// SourceURL returns the full upstream URL to fetch: the source path
+// percent-encoded again, as net/url writes a path, so each source path is one
+// upstream path, and the source query as it is, with the characters
+// escapeQuery encodes percent-encoded. Uses http:// scheme when AllowHTTP is
+// true, otherwise https://.
 func (r *ImageRequest) SourceURL() string {
 	scheme := "https"
 	if r.AllowHTTP {
 		scheme = "http"
 	}
 
-	url := scheme + "://" + r.SourceHost + r.SourcePath
-	if r.SourceQuery != "" {
-		url += "?" + r.SourceQuery
+	sourceURL := url.URL{
+		Scheme:   scheme,
+		Host:     r.SourceHost,
+		Path:     r.SourcePath,
+		RawQuery: escapeQuery(r.SourceQuery),
 	}
 
-	return url
+	return sourceURL.String()
 }
 
 // ImageResponse represents a processed image ready to serve

internal/imgcache/urlparser.go

@@ -51,6 +51,13 @@ var sizeFormatRegex = regexp.MustCompile(
 // percentEscapeRegex matches one percent-escape, such as "%2e"
 var percentEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}`)
 
+// queryEscapeRegex matches a percent-escape, or one character that a browser
+// percent-encodes in the query of an http or https URL: one outside the
+// printable ASCII characters "!" to "~", such as a space, a control character
+// or a character outside ASCII, or one of `"#'<>`. A "%" that does not begin a
+// percent-escape matches too.
+var queryEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}|[^!-~]|["#'<>%]`)
+
 // hostRegex matches the forms the host of an image URL may take: a host name
 // or an IPv4 address (letters, digits, "-", "_" and "."), or an IPv6 address
 // in brackets (hex digits, ":" and "."), either one optionally followed by ":"
@@ -179,9 +186,12 @@ func parseImageComponents(remainder string) (*ParsedURL, error) {
 			`%w: the source path or query holds a "#"`, ErrInvalidPath)
 	}
 
-	// Extract query string if present in path
+	// Extract query string if present in path. It is the source URL's query
+	// as that URL writes it. A character a URL's query cannot hold as it is,
+	// such as a space written %20 in the image URL, is percent-encoded here,
+	// so the query is signed and cached as it is sent upstream
 	if qIndex := strings.Index(path, "?"); qIndex != -1 {
-		query = path[qIndex+1:]
+		query = escapeQuery(path[qIndex+1:])
 		path = path[:qIndex]
 	}
 
@@ -270,6 +280,20 @@ func decodePercentEscapes(s string) string {
 	})
 }
 
+// escapeQuery returns a source query as a URL's query holds it: each
+// character that queryEscapeRegex names, such as a space, percent-encoded,
+// and the rest, the query's percent-escapes included, kept as they are. The
+// result is unchanged by a second escapeQuery.
+func escapeQuery(query string) string {
+	return queryEscapeRegex.ReplaceAllStringFunc(query, func(match string) string {
+		if percentEscapeRegex.MatchString(match) {
+			return match
+		}
+
+		return url.PathEscape(match)
+	})
+}
+
 // parseSizeFormat parses strings like "800x600.webp", "orig.png" or "800x600"
 func parseSizeFormat(s string) (Size, ImageFormat, error) {
 	matches := sizeFormatRegex.FindStringSubmatch(s)

internal/server/source_url_internal_test.go

@@ -0,0 +1,371 @@
+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, written percent-encoded, or a "'", and whose source
+// path holds a "%", 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 and the "'" written %27, as a browser
+// writes them in a query.
+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"},
+		{"apostrophe in the query", "/photo.png%3Fname=it's",
+			"/photo.png?name=it%27s"},
+		{"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)
+			}
+		})
+	}
+}
+
+// TestGeneratorRefusesSourceURLItCannotFetchAsWritten submits source URLs the
+// generator page must make no encrypted URL for, and checks that it answers
+// 400 and shows why. pixa keeps the source path decoded and fetches it
+// percent-encoded again, so a path holding %2F would be fetched with a "/"
+// there, whatever else the path holds. pixa sends no user name or password,
+// and no "?" with no query after it. For these the page shows the URL pixa
+// would fetch. A source path holding a ".." segment is refused, as
+// /v1/image/ refuses it.
+func TestGeneratorRefusesSourceURLItCannotFetchAsWritten(t *testing.T) {
+	t.Parallel()
+
+	// The test config sets allow_http, so pixa would fetch over plain HTTP
+	const fetchedFrom = "http://" + upstreamHost
+
+	tests := []struct {
+		name string
+		// sourceURL is the source URL after "https://"
+		sourceURL string
+		// wantShown is what the page must show: the URL pixa would fetch, or
+		// why it makes no encrypted URL
+		wantShown string
+	}{
+		{"encoded slash", upstreamHost + "/a%2Fb.png",
+			fetchedFrom + "/a/b.png"},
+		{"encoded slash and a space", upstreamHost + "/a%2Fb c.png",
+			fetchedFrom + "/a/b%20c.png"},
+		{"encoded slash and a bar", upstreamHost + "/a%2Fb|c.png",
+			fetchedFrom + "/a/b%7Cc.png"},
+		{"encoded slash and a letter outside ASCII", upstreamHost + "/café%2Fx.png",
+			fetchedFrom + "/caf%C3%A9/x.png"},
+		{"user name and password", "user:pass@" + upstreamHost + "/a.png",
+			fetchedFrom + "/a.png"},
+		{"question mark with no query", upstreamHost + "/a.png?",
+			fetchedFrom + "/a.png"},
+		{"two-dot segment", upstreamHost + "/a/../b.png",
+			"cannot hold a .. segment"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			s, _, _ := startImageProxy(t, startRecordingUpstream(t).Server)
+
+			rec := postGenerate(t, s, "https://"+tt.sourceURL)
+			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")
+			}
+
+			if !strings.Contains(body, tt.wantShown) {
+				t.Errorf("the page does not show %s; body %s", tt.wantShown, body)
+			}
+		})
+	}
+}