Document how a source query goes into an image URL, and accept it (closes #255)

The README gave no way to put a source URL's query into a signed image
URL, and GenerateSignedURL built one that failed: the route parsed
chi's wildcard, which keeps the path as the client wrote it, so one
%2F, %3B or %2C left the %3F undecoded and the signature failed. The
route now parses the decoded path, GenerateSignedURL writes Go's own
encoding of it, and the README says the ? before the query, any ? in it
and every % must be percent-encoded, with a signed example. The path
traversal check no longer reads the query and accepts a literal %, while
a double-encoded .. stays refused. A percent-escape in a source path is
now decoded once.

Model: opus-5-5

internal/handlers/image.go

@@ -9,7 +9,6 @@ import (
 	"strconv"
 	"time"
 
-	"github.com/go-chi/chi/v5"
 	"github.com/go-chi/chi/v5/middleware"
 	"sneak.berlin/go/pixa/internal/encurl"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
@@ -80,20 +79,21 @@ func (s *Handlers) HandleRobotsTxt() http.HandlerFunc {
 	}
 }
 
-// parseImageRequest parses the wildcard path and query parameters into
+// parseImageRequest parses the image URL's path and query parameters into
 // an ImageRequest. On invalid input it writes an error response and
 // returns false.
 func (s *Handlers) parseImageRequest(
 	w http.ResponseWriter, r *http.Request,
 ) (*imgcache.ImageRequest, bool) {
-	// Get the wildcard path from chi
-	pathParam := chi.URLParam(r, "*")
-
-	// Parse the URL path
-	parsed, err := imgcache.ParseImagePath(pathParam)
+	// The path is parsed decoded once, as r.URL.Path holds it, and not from
+	// chi's wildcard: chi routes on the path as the client wrote it whenever
+	// that is not Go's own encoding of it, so its wildcard would still hold
+	// the %3F before a source query when, say, a "/" in the query is written
+	// as %2F
+	parsed, err := imgcache.ParseImageURL(r.URL.Path)
 	if err != nil {
 		s.log.Warn("failed to parse image URL",
-			"path", pathParam,
+			"path", r.URL.Path,
 			"error", err,
 		)
 		s.respondError(w, "invalid image URL: "+err.Error(), http.StatusBadRequest)

internal/handlers/image_signature_internal_test.go

@@ -169,3 +169,166 @@ func TestHandleImage_InvalidExp_Returns400(t *testing.T) {
 		})
 	}
 }
+
+// TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies sends URLs built
+// by the service's signed-URL generator for source URLs with a query to the
+// route, through a chi router: chi routes on the path as the client wrote it
+// whenever that is not Go's own encoding of it. A 502 means the signature
+// passed, so the route read the source path and query that were signed.
+func TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name  string
+		query string
+	}{
+		{"slash and colon", "url=https://origin.example.com/cat.jpg"},
+		{"semicolon", "a=1;b=2"},
+		{"comma", "crop=0,0,50,50"},
+		{"equals and ampersand", "a=1&b=2"},
+		{"percent-escape", "name=my%20cat"},
+		{"question mark", "next=/a?b=1"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			fix := setupTestHandler(t)
+
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
+				SourceHost:  signedHost,
+				SourcePath:  photoPath,
+				SourceQuery: tt.query,
+				Size:        imgcache.Size{Width: 50, Height: 50},
+				Format:      imgcache.FormatJPEG,
+			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
+
+			status := getImage(t, fix, signedURL)
+			if status != http.StatusBadGateway {
+				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
+			}
+		})
+	}
+}
+
+// TestHandleImage_SourceQueryEncodedAnyWay signs one source URL with a query
+// and writes it into the image URL in ways the README allows: the "?" before
+// the query and each "%" in it percent-encoded, and every other character as
+// itself or percent-encoded. A 502 means the signature passed.
+func TestHandleImage_SourceQueryEncodedAnyWay(t *testing.T) {
+	t.Parallel()
+
+	expires := time.Now().Add(time.Hour)
+	signer := signature.New("test-signing-key-must-be-32-chars")
+	sig := signer.Sign(&signature.Request{
+		SourceHost:  signedHost,
+		SourcePath:  photoPath,
+		SourceQuery: "url=https://origin.example.com/my%20cat.jpg",
+		Width:       50,
+		Height:      50,
+		Format:      string(imgcache.FormatJPEG),
+		Quality:     85,
+		FitMode:     string(imgcache.FitCover),
+		Expires:     expires,
+	})
+
+	tests := []struct {
+		name         string
+		writtenQuery string
+	}{
+		{"only ? and % encoded",
+			"%3Furl=https://origin.example.com/my%2520cat.jpg"},
+		{"every reserved character encoded",
+			"%3Furl%3Dhttps%3A%2F%2Forigin.example.com%2Fmy%2520cat.jpg"},
+		{"lower-case hex digits",
+			"%3furl=https://origin.example.com/my%2520cat.jpg"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			target := fmt.Sprintf("/v1/image/%s%s%s/50x50.jpeg?sig=%s&exp=%d",
+				signedHost, photoPath, tt.writtenQuery, sig, expires.Unix())
+
+			status := getImage(t, setupTestHandler(t), target)
+			if status != http.StatusBadGateway {
+				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
+			}
+		})
+	}
+}
+
+// TestHandleImage_SourceURLHoldingPercent25Verifies signs a source path and a
+// source query that each hold %25, the percent-escape of a literal "%", and
+// sends each to the route written as the README says, with that "%" written as
+// %25, and as GenerateSignedURL writes it. A 502 means the signature passed.
+func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name        string
+		sourcePath  string
+		sourceQuery string
+		// writtenPathAndQuery is the source path and query as the README says
+		// to write them into the image URL
+		writtenPathAndQuery string
+	}{
+		{"path", "/sale/50%25off.jpg", "", "/sale/50%2525off.jpg"},
+		{"query", photoPath, "discount=50%25", photoPath + "%3Fdiscount=50%2525"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name+" written by the README rule", func(t *testing.T) {
+			t.Parallel()
+
+			expires := time.Now().Add(time.Hour)
+			signer := signature.New("test-signing-key-must-be-32-chars")
+			sig := signer.Sign(&signature.Request{
+				SourceHost:  signedHost,
+				SourcePath:  tt.sourcePath,
+				SourceQuery: tt.sourceQuery,
+				Width:       50,
+				Height:      50,
+				Format:      string(imgcache.FormatJPEG),
+				Quality:     85,
+				FitMode:     string(imgcache.FitCover),
+				Expires:     expires,
+			})
+
+			target := fmt.Sprintf("/v1/image/%s%s/50x50.jpeg?sig=%s&exp=%d",
+				signedHost, tt.writtenPathAndQuery, sig, expires.Unix())
+
+			status := getImage(t, setupTestHandler(t), target)
+			if status != http.StatusBadGateway {
+				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
+			}
+		})
+
+		t.Run(tt.name+" written by GenerateSignedURL", func(t *testing.T) {
+			t.Parallel()
+
+			fix := setupTestHandler(t)
+
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
+				SourceHost:  signedHost,
+				SourcePath:  tt.sourcePath,
+				SourceQuery: tt.sourceQuery,
+				Size:        imgcache.Size{Width: 50, Height: 50},
+				Format:      imgcache.FormatJPEG,
+			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
+
+			status := getImage(t, fix, signedURL)
+			if status != http.StatusBadGateway {
+				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
+			}
+		})
+	}
+}

internal/imgcache/urlparser.go

@@ -47,6 +47,9 @@ func ValidateDimension(name string, value int) error {
 var sizeFormatRegex = regexp.MustCompile(
 	`^(\d+)x(\d+)(?:\.(\w+))?$|^(orig)(?:\.(\w+))?$`)
 
+// percentEscapeRegex matches one percent-escape, such as "%2e"
+var percentEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}`)
+
 // ParsedURL contains the parsed components of an image proxy URL.
 type ParsedURL struct {
 	// Host is the source origin host (e.g., "cdn.example.com")
@@ -61,9 +64,8 @@ type ParsedURL struct {
 	Format ImageFormat
 }
 
-// ParseImagePath parses the path captured by chi's wildcard:
-// <host>/<path>/<size>.<format>, or <host>/<path>/<size> for JPEG XL
-// This is the primary entry point when using chi routing.
+// ParseImagePath parses an image URL's path after /v1/image/, decoded once:
+// <host>/<path>/<size>.<format>, or <host>/<path>/<size> for JPEG XL.
 // Examples:
 //   - cdn.example.com/photos/cat.jpg/800x600.webp
 //   - cdn.example.com/photos/cat.jpg/0x0.jpeg
@@ -79,9 +81,10 @@ func ParseImagePath(path string) (*ParsedURL, error) {
 	return parseImageComponents(path)
 }
 
-// ParseImageURL parses a full URL path like /v1/image/<host>/<path>/<size>.<format>,
-// or /v1/image/<host>/<path>/<size> for JPEG XL
-// Use ParseImagePath instead when working with chi's wildcard capture.
+// ParseImageURL parses an image URL's path, decoded once as r.URL.Path holds
+// it: /v1/image/<host>/<path>/<size>.<format>, or /v1/image/<host>/<path>/<size>
+// for JPEG XL. A source query follows the source path after a "?", which the
+// URL writes as %3F.
 func ParseImageURL(urlPath string) (*ParsedURL, error) {
 	// Remove the /v1/image/ prefix
 	const prefix = "/v1/image/"
@@ -100,12 +103,6 @@ func ParseImageURL(urlPath string) (*ParsedURL, error) {
 // parseImageComponents parses <host>/<path>/<size>.<format>, or
 // <host>/<path>/<size> for JPEG XL.
 func parseImageComponents(remainder string) (*ParsedURL, error) {
-	// Check for path traversal before any other processing
-	err := checkPathTraversal(remainder)
-	if err != nil {
-		return nil, err
-	}
-
 	// Find the last path segment, which holds "size" or "size.format"
 	lastSlash := strings.LastIndex(remainder, "/")
 	if lastSlash == -1 {
@@ -161,6 +158,13 @@ func parseImageComponents(remainder string) (*ParsedURL, error) {
 		path = path[:qIndex]
 	}
 
+	// The source query names no file on the upstream, so only the host and
+	// the source path are checked for path traversal
+	err = checkPathTraversal(host + path)
+	if err != nil {
+		return nil, err
+	}
+
 	// Ensure path starts with /
 	if !strings.HasPrefix(path, "/") {
 		path = "/" + path
@@ -186,12 +190,7 @@ func checkPathTraversal(path string) error {
 	// Decode multiple times to catch double-encoding
 	decoded := path
 	for range 3 {
-		newDecoded, err := url.PathUnescape(decoded)
-		if err != nil {
-			// Malformed encoding is suspicious
-			return ErrPathTraversal
-		}
-
+		newDecoded := decodePercentEscapes(decoded)
 		if newDecoded == decoded {
 			break
 		}
@@ -232,6 +231,18 @@ func checkPathTraversal(path string) error {
 	return nil
 }
 
+// decodePercentEscapes decodes every percent-escape in s, such as %2e, and
+// keeps a "%" that does not start one as it is, where url.PathUnescape would
+// refuse the whole string. A source path holding %25, a literal "%", has such
+// a "%" after one more decoding.
+func decodePercentEscapes(s string) string {
+	return percentEscapeRegex.ReplaceAllStringFunc(s, func(escape string) string {
+		decoded, _ := url.PathUnescape(escape)
+
+		return decoded
+	})
+}
+
 // parseSizeFormat parses strings like "800x600.webp", "orig.png" or "800x600"
 func parseSizeFormat(s string) (Size, ImageFormat, error) {
 	matches := sizeFormatRegex.FindStringSubmatch(s)

internal/imgcache/urlparser_internal_test.go

@@ -407,6 +407,71 @@ func TestParseImagePath_PathTraversal(t *testing.T) {
 	}
 }
 
+// TestParseImageURL_SourceURLHoldingPercent25 verifies that a source path and
+// a source query holding %25, the percent-escape of a literal "%", are
+// accepted as they are, although decoding them once more leaves a "%" that
+// does not start a percent-escape.
+func TestParseImageURL_SourceURLHoldingPercent25(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name  string
+		input string
+		want  *ParsedURL
+	}{
+		{
+			name:  "path",
+			input: "/v1/image/cdn.example.com/sale/50%25off.jpg/800x600.webp",
+			want: &ParsedURL{
+				Host: testHostCDN, Path: "/sale/50%25off.jpg",
+				Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
+			},
+		},
+		{
+			name:  "query",
+			input: "/v1/image/cdn.example.com/photos/cat.jpg?discount=50%25/800x600.webp",
+			want: &ParsedURL{
+				Host: testHostCDN, Path: testPathCat, Query: "discount=50%25",
+				Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			got, err := ParseImageURL(tt.input)
+			if err != nil {
+				t.Fatalf("ParseImageURL() unexpected error = %v", err)
+			}
+
+			assertParsedURL(t, got, tt.want)
+		})
+	}
+}
+
+// TestParseImageURL_DoubleEncodedTraversalNextToPercent verifies that a
+// double-encoded ".." is still refused when the path also holds a "%" that
+// does not start a percent-escape, either as written or after one more
+// decoding.
+func TestParseImageURL_DoubleEncodedTraversalNextToPercent(t *testing.T) {
+	t.Parallel()
+
+	for _, input := range []string{
+		"/v1/image/cdn.example.com/photos/%252e%252e/secret/50%25off.jpg/800x600.jpeg",
+		"/v1/image/cdn.example.com/photos/%252e%252e/secret/100%/800x600.jpeg",
+	} {
+		_, err := ParseImageURL(input)
+		t.Logf("ParseImageURL(%q) error = %v", input, err)
+
+		if !errors.Is(err, ErrPathTraversal) {
+			t.Errorf("ParseImageURL(%q) error = %v, want ErrPathTraversal",
+				input, err)
+		}
+	}
+}
+
 // errorIs checks if err matches target (handles wrapped errors).
 func errorIs(err, target error) bool {
 	if errors.Is(err, target) {

internal/signature/signature.go

@@ -126,31 +126,20 @@ func (s *Signer) GenerateSignedURL(
 		sizeStr = fmt.Sprintf("%dx%d", req.Width, req.Height)
 	}
 
-	// Build the path.
-	// When a source query is present, it is embedded as a path segment
-	// (e.g. /host/path?query/size.fmt) so that the URL parser can extract
-	// it from the last-slash split. The "?" inside a path segment is
-	// percent-encoded by clients but chi delivers it decoded, which is
-	// exactly what the URL parser expects.
-	var path string
+	// Build the path. A source query follows the source path after a "?".
+	// The image route reads the path decoded once, so the whole path is
+	// written in Go's own percent-encoding of a URL path, which writes "?"
+	// as %3F and "%" as %25, and leaves "/", ";", ",", "=" and "&" as they
+	// are.
+	sourcePathAndQuery := req.SourcePath
 	if req.SourceQuery != "" {
-		path = fmt.Sprintf("/v1/image/%s%s%%3F%s/%s.%s",
-			req.SourceHost,
-			req.SourcePath,
-			url.PathEscape(req.SourceQuery),
-			sizeStr,
-			req.Format,
-		)
-	} else {
-		path = fmt.Sprintf("/v1/image/%s%s/%s.%s",
-			req.SourceHost,
-			req.SourcePath,
-			sizeStr,
-			req.Format,
-		)
+		sourcePathAndQuery += "?" + req.SourceQuery
 	}
 
-	return path, sig, exp
+	unescapedPath := fmt.Sprintf("/v1/image/%s%s/%s.%s",
+		req.SourceHost, sourcePathAndQuery, sizeStr, req.Format)
+
+	return (&url.URL{Path: unescapedPath}).EscapedPath(), sig, exp
 }
 
 // buildSignatureData creates the string to be signed.

internal/signature/signature_test.go

@@ -475,6 +475,44 @@ func TestGenerateSignedURL_WithoutQueryString(t *testing.T) {
 	}
 }
 
+// TestGenerateSignedURL_ReadmeQueryExample checks the README's example of a
+// source URL with a query, the image at
+// https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg: its
+// signature with the README's key, and the path GenerateSignedURL writes for
+// it, with the "?" written as %3F and the "%" as %25.
+func TestGenerateSignedURL_ReadmeQueryExample(t *testing.T) {
+	t.Parallel()
+
+	signer := signature.New("example-signing-key-for-documentation")
+
+	req := signature.Request{
+		SourceHost:  testHost,
+		SourcePath:  "/img",
+		SourceQuery: "url=https://origin.example.com/my%20cat.jpg",
+		Width:       800,
+		Height:      600,
+		Format:      testFormatWebP,
+		Quality:     85,
+		FitMode:     testFitCover,
+		Expires:     time.Unix(1704067200, 0),
+	}
+
+	const wantSig = "37aFa9GSVCZM1kRY9SzMOk2fOg_M7Wt5gKNR4xM-FYA="
+
+	gotSig := signer.Sign(&req)
+	if gotSig != wantSig {
+		t.Errorf("Sign() = %q, want %q", gotSig, wantSig)
+	}
+
+	const wantPath = "/v1/image/cdn.example.com" +
+		"/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp"
+
+	gotPath, _, _ := signer.GenerateSignedURL(&req, time.Hour)
+	if gotPath != wantPath {
+		t.Errorf("GenerateSignedURL() path = %q, want %q", gotPath, wantPath)
+	}
+}
+
 func TestParseParams(t *testing.T) {
 	t.Parallel()