Escape : and % in the signed and cached path and query (closes #247)

The signed data and the cache key joined host, path and query with ":" and no escaping, so path /a:b with no query and path /a with query b: gave the same string: a URL signed for https://h/a:b verified for https://h/a?b:, and the two shared a cached image. Both now write each % in the path and the query as %25 and each : as %3A before joining them. The host never holds / and the path always starts with /, so the joined string reads back one way only. A path and query holding neither character are signed and keyed as before, so the existing known-answer vectors and the README example are unchanged; new vectors cover the escaped cases. Signature Specification in README.md states the escaping.

Model: opus-5-5

internal/imgcache/storage.go

@@ -10,6 +10,7 @@ import (
 	"log/slog"
 	"os"
 	"path/filepath"
+	"strings"
 	"time"
 )
 
@@ -371,11 +372,13 @@ func HashPath(path string) PathHash {
 
 // CacheKey generates a unique key for a request variant.
 // Format: sha256(host:path:query:width:height:format:quality:fit_mode)
+// The path and query go through escapePercentAndColon, so that a ":" in
+// either cannot be taken for the one between them.
 func CacheKey(req *ImageRequest) VariantKey {
 	data := fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%s",
 		req.SourceHost,
-		req.SourcePath,
-		req.SourceQuery,
+		escapePercentAndColon(req.SourcePath),
+		escapePercentAndColon(req.SourceQuery),
 		req.Size.Width,
 		req.Size.Height,
 		req.Format,
@@ -387,6 +390,14 @@ func CacheKey(req *ImageRequest) VariantKey {
 	return VariantKey(hex.EncodeToString(h[:]))
 }
 
+// escapePercentAndColon returns s with each "%" written as "%25" and each
+// ":" as "%3A", so that the result holds no ":".
+func escapePercentAndColon(s string) string {
+	s = strings.ReplaceAll(s, "%", "%25")
+
+	return strings.ReplaceAll(s, ":", "%3A")
+}
+
 // VariantStorage handles key-based file storage for processed image variants.
 // Files are stored at: <basedir>/<ab>/<cd>/<cache_key>
 // Metadata is stored at: <basedir>/<ab>/<cd>/<cache_key>.meta

internal/imgcache/storage_internal_test.go

@@ -407,6 +407,62 @@ func TestCacheKey(t *testing.T) {
 	}
 }
 
+// TestCacheKey_ColonOrPercentInPathOrQuery checks that two different source
+// URLs whose path or query holds ":" or "%" get different keys.
+func TestCacheKey_ColonOrPercentInPathOrQuery(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name          string
+		path1, query1 string
+		path2, query2 string
+	}{
+		{
+			name:  "colon moved from path to query",
+			path1: "/a:b", query1: "",
+			path2: "/a", query2: "b:",
+		},
+		{
+			name:  "colon in path and its percent-encoding",
+			path1: "/a:b", query1: "",
+			path2: "/a%3Ab", query2: "",
+		},
+	}
+
+	for _, tt := range cases {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			key1 := CacheKey(&ImageRequest{
+				SourceHost:  testHostCDN,
+				SourcePath:  tt.path1,
+				SourceQuery: tt.query1,
+				Size:        Size{Width: 800, Height: 600},
+				Format:      FormatWebP,
+				Quality:     85,
+				FitMode:     FitCover,
+			})
+			key2 := CacheKey(&ImageRequest{
+				SourceHost:  testHostCDN,
+				SourcePath:  tt.path2,
+				SourceQuery: tt.query2,
+				Size:        Size{Width: 800, Height: 600},
+				Format:      FormatWebP,
+				Quality:     85,
+				FitMode:     FitCover,
+			})
+
+			t.Logf("CacheKey() of path %q query %q = %s", tt.path1, tt.query1, key1)
+			t.Logf("CacheKey() of path %q query %q = %s", tt.path2, tt.query2, key2)
+
+			if key1 == key2 {
+				t.Errorf("CacheKey() gave path %q query %q and path %q query %q "+
+					"the same key", tt.path1, tt.query1, tt.path2, tt.query2)
+			}
+		})
+	}
+}
+
 // TestVariantStorage_StoreLogsFailedMetaWrite verifies that a .meta write
 // that fails is logged at warn and the store still succeeds.
 func TestVariantStorage_StoreLogsFailedMetaWrite(t *testing.T) {

internal/signature/escaping_test.go

@@ -0,0 +1,113 @@
+package signature_test
+
+import (
+	"errors"
+	"testing"
+	"time"
+
+	"sneak.berlin/go/pixa/internal/signature"
+)
+
+// TestSigner_Verify_ColonCannotMovePathQueryBoundary checks that a URL
+// signed for path "/a:b" with no query does not verify for path "/a" with
+// query "b:", a different resource on the same host.
+func TestSigner_Verify_ColonCannotMovePathQueryBoundary(t *testing.T) {
+	t.Parallel()
+
+	signer := signature.New(goldenSigningKey)
+
+	signed := &signature.Request{
+		SourceHost: testHost,
+		SourcePath: "/a:b",
+		Width:      800,
+		Height:     600,
+		Format:     testFormatWebP,
+		Quality:    85,
+		FitMode:    testFitCover,
+		Expires:    time.Now().Add(1 * time.Hour),
+	}
+	signed.Signature = signer.Sign(signed)
+
+	replayed := *signed
+	replayed.SourcePath = "/a"
+	replayed.SourceQuery = "b:"
+
+	t.Logf("signature for path %q query %q: %s",
+		signed.SourcePath, signed.SourceQuery, signed.Signature)
+	t.Logf("signature for path %q query %q: %s",
+		replayed.SourcePath, replayed.SourceQuery, signer.Sign(&replayed))
+
+	err := signer.Verify(&replayed)
+	if !errors.Is(err, signature.ErrInvalid) {
+		t.Errorf("Verify() of path %q query %q with the signature for "+
+			"path %q = %v, want %v",
+			replayed.SourcePath, replayed.SourceQuery, signed.SourcePath,
+			err, signature.ErrInvalid)
+	}
+}
+
+// TestSigner_EscapedGoldenVectors pins the signature of requests whose path
+// or query holds ":" or "%", which are signed with "%" written as "%25" and
+// ":" as "%3A". The expected values were computed once, outside pixa, from
+// the signed data in each comment.
+func TestSigner_EscapedGoldenVectors(t *testing.T) {
+	t.Parallel()
+
+	signer := signature.New(goldenSigningKey)
+
+	vectors := []struct {
+		name          string
+		path          string
+		query         string
+		wantSignature string
+	}{
+		{
+			name: "colon in path",
+			path: "/photos/a:b.jpg",
+			// Signed data:
+			// "cdn.example.com:/photos/a%3Ab.jpg::800:600:webp:1704067200:85:cover"
+			wantSignature: "WnEpZ7bQp1Zvw8WDatlj2vu-4wYKWE3BFBizV8m__6k=",
+		},
+		{
+			name:  "colon in query",
+			path:  testPath,
+			query: "t=1:2",
+			// Signed data:
+			// "cdn.example.com:/photos/cat.jpg:t=1%3A2:800:600:webp:1704067200:85:cover"
+			wantSignature: "85kRoN8hhr4cCUkEUjNvUsvVYKjYYfWdeffx5TjJjqA=",
+		},
+		{
+			name:  "percent in path and query",
+			path:  "/photos/a%20b.jpg",
+			query: "q=50%",
+			// Signed data:
+			// "cdn.example.com:/photos/a%2520b.jpg:q=50%25:800:600:webp:1704067200:85:cover"
+			wantSignature: "MjDiiRdgXMrsjqPMsENtD4aG1hp1e-a6zy67vKTX4CQ=",
+		},
+	}
+
+	for _, tt := range vectors {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			req := &signature.Request{
+				SourceHost:  testHost,
+				SourcePath:  tt.path,
+				SourceQuery: tt.query,
+				Width:       800,
+				Height:      600,
+				Format:      testFormatWebP,
+				Quality:     85,
+				FitMode:     testFitCover,
+				Expires:     time.Unix(goldenExpiresUnix, 0),
+			}
+
+			gotSignature := signer.Sign(req)
+			t.Logf("Sign() of path %q query %q = %s", tt.path, tt.query, gotSignature)
+
+			if gotSignature != tt.wantSignature {
+				t.Errorf("Sign() = %q, want %q", gotSignature, tt.wantSignature)
+			}
+		})
+	}
+}

internal/signature/signature.go

@@ -10,6 +10,7 @@ import (
 	"fmt"
 	"net/url"
 	"strconv"
+	"strings"
 	"time"
 )
 
@@ -154,15 +155,17 @@ func (s *Signer) GenerateSignedURL(
 
 // buildSignatureData creates the string to be signed.
 // Format: "host:path:query:width:height:format:expiration:quality:fit"
-// All components are used verbatim (exact match). No normalization,
-// suffix matching, or wildcard expansion is performed. Quality and fit
-// are the effective transform values, so replaying a signed URL with a
-// different quality or fit mode fails verification.
+// The path and query go through escapePercentAndColon, so that a ":" in
+// either cannot be taken for the one between them; every other component
+// is used verbatim. No normalization, suffix matching, or wildcard
+// expansion is performed. Quality and fit are the effective transform
+// values, so replaying a signed URL with a different quality or fit mode
+// fails verification.
 func (s *Signer) buildSignatureData(req *Request) string {
 	return fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%d:%s",
 		req.SourceHost,
-		req.SourcePath,
-		req.SourceQuery,
+		escapePercentAndColon(req.SourcePath),
+		escapePercentAndColon(req.SourceQuery),
 		req.Width,
 		req.Height,
 		req.Format,
@@ -172,6 +175,14 @@ func (s *Signer) buildSignatureData(req *Request) string {
 	)
 }
 
+// escapePercentAndColon returns s with each "%" written as "%25" and each
+// ":" as "%3A", so that the result holds no ":".
+func escapePercentAndColon(s string) string {
+	s = strings.ReplaceAll(s, "%", "%25")
+
+	return strings.ReplaceAll(s, ":", "%3A")
+}
+
 // ParseParams extracts signature and expiration from query parameters.
 func ParseParams(sig, expStr string) (string, time.Time, error) {
 	if expStr == "" {