Check cached file sizes at startup, not per request (closes #252)

Lookup and LookupSource are as on next again: requests compare no
sizes and a hit reads no extra row. The reconciliation pass, at startup
and every five minutes, compares each cached source and variant file
with the size its row records and removes one that is empty or of
another size, with its rows and a warning naming the file; an empty
variant file without a row is removed rather than adopted. Source,
variant and .meta files all go through writeFileSynced (temp file,
sync, rename, directory sync), the .meta file before the variant, and
a failed directory sync removes the renamed file.

#252

Model: opus-5-5

README.md

@@ -427,11 +427,8 @@ HMAC-SHA256(secret, "host:path:query:width:height:format:expiration:quality:fit"
 Where:
 
 - `host` — source origin hostname (e.g. `cdn.example.com`)
-- `path` — source path (e.g. `/photos/cat.jpg`), with each `%` written as `%25`
-  and each `:` as `%3A`, so `/photos/a:b.jpg` is signed as `/photos/a%3Ab.jpg`
-- `query` — source query string, empty string if none, with `%` and `:` written
-  as in `path`; neither then holds a `:`, so path `/a:b` with no query and path
-  `/a` with query `b:` are signed differently
+- `path` — source path (e.g. `/photos/cat.jpg`)
+- `query` — source query string, empty string if none
 - `width` — requested width in pixels, `0` for original
 - `height` — requested height in pixels, `0` for original
 - `format` — output format, one of those listed under Routes, with `original`

TODO.md

@@ -30,14 +30,6 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
-- 2026-10-15 a `:` in the source path or query no longer moves where the path
-  ends and the query begins (closes #247): the signed data and the cache key
-  joined host, path and query with `:` and no escaping, so a URL signed for
-  `https://h/a:b` verified for `https://h/a?b:`; the two also shared a cache
-  key, and whichever was fetched first was served for both. In both, the path
-  and the query now have each `%` written as `%25` and each `:` as `%3A`; a path
-  and query holding neither are signed and keyed as before. Signature
-  Specification in `README.md` says so.
 - 2026-10-15 a cached file left empty or partial is no longer served, or fetched
   again on every request (closes #252). Source and transformed image files, and
   each transformed image's `.meta` file, are synced to disk before they are
@@ -58,24 +50,6 @@ P2: security: per-origin rate limiting
   commented entry under `example.com`. Getting Started and "Running under upaas"
   in `README.md` say that every image on an allowlisted host is served without a
   signature, so an allowlisted host must be one the operator controls.
-- 2026-10-15 a chunked upstream body of exactly `upstream_max_response_size`
-  bytes is accepted (closes #248): once the limit was used up, the fetcher's
-  next read refused the body without looking for its end. Go's HTTP client
-  returns the end of a body sent with a `Content-Length` together with its last
-  bytes, but the end of a chunked body can come in a later read, so such a body
-  was refused after it had been downloaded whole, and the image routes
-  answered 500. Once the limit is used up, the fetcher now reads one more byte:
-  if the body has ended it is accepted, and if there is more it is refused with
-  `ErrResponseTooLarge`, as before.
-- 2026-10-15 a cached file left empty or partial is no longer served, or fetched
-  again on every request (closes #252). Source and transformed image files are
-  synced to disk before they are renamed into place, and their directory after.
-  A request that finds a cached source or transformed image whose file is empty,
-  or not the size the database records for it, removes it with a log line naming
-  it, and fetches the source or converts the image again. Storing a source over
-  a file of another size replaces that file. A source that fails to decode is
-  not removed for that alone: a damaged upstream image would then be fetched on
-  every request.
 - 2026-10-13 `fit=outside` no longer makes an output above 8192 on a side
   (closes #257): it scales the image to cover the requested size, and the side
   scaled past that size was held to no maximum, so `1x8192?fit=outside` of a

internal/httpfetcher/fetch_internal_test.go

@@ -9,7 +9,6 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"slices"
-	"strconv"
 	"strings"
 	"sync"
 	"testing"
@@ -298,139 +297,6 @@ func TestFetchMaxResponseSizeEnforced(t *testing.T) {
 	}
 }
 
-// fetchWithMaxResponseSize serves handler as the fake upstream and fetches
-// its /image route with MaxResponseSize set to maxResponseSize.
-func fetchWithMaxResponseSize(
-	t *testing.T,
-	maxResponseSize int64,
-	handler http.HandlerFunc,
-) *FetchResult {
-	t.Helper()
-
-	srv := httptest.NewServer(handler)
-	t.Cleanup(srv.Close)
-
-	cfg := DefaultConfig()
-	cfg.MaxResponseSize = maxResponseSize
-
-	f, _ := newServerFetcher(t, srv, cfg)
-
-	res := fetchImage(t, f, "/image")
-	t.Cleanup(func() { _ = res.Content.Close() })
-
-	return res
-}
-
-// TestFetchContentLengthBodyAtMaxResponseSize checks that a body sent with a
-// Content-Length is read whole at exactly MaxResponseSize bytes and refused
-// at one byte more.
-func TestFetchContentLengthBodyAtMaxResponseSize(t *testing.T) {
-	t.Parallel()
-
-	const maxResponseSize = 8
-
-	for _, tc := range []struct {
-		size    int
-		wantErr error
-	}{
-		{maxResponseSize, nil},
-		{maxResponseSize + 1, ErrResponseTooLarge},
-	} {
-		t.Run(strconv.Itoa(tc.size)+" bytes", func(t *testing.T) {
-			t.Parallel()
-
-			body := strings.Repeat("x", tc.size)
-
-			res := fetchWithMaxResponseSize(t, maxResponseSize,
-				func(w http.ResponseWriter, _ *http.Request) {
-					w.Header().Set("Content-Type", contentTypeJPEG)
-					w.Header().Set("Content-Length", strconv.Itoa(tc.size))
-					_, _ = io.WriteString(w, body)
-				})
-
-			if res.ContentLength != int64(tc.size) {
-				t.Fatalf("ContentLength = %d, want %d", res.ContentLength, tc.size)
-			}
-
-			data, err := io.ReadAll(res.Content)
-			t.Logf("body of %d bytes: read %d, error %v", tc.size, len(data), err)
-
-			if !errors.Is(err, tc.wantErr) {
-				t.Fatalf("read error = %v, want %v", err, tc.wantErr)
-			}
-
-			if err == nil && string(data) != body {
-				t.Errorf("read %q, want %q", data, body)
-			}
-		})
-	}
-}
-
-// TestFetchChunkedBodyAtMaxResponseSize checks that a chunked body is read
-// whole at exactly MaxResponseSize bytes and refused at one byte more. The
-// upstream sends the end of the body only once the test has read
-// MaxResponseSize bytes, so the read after them comes before the end of the
-// body has arrived, as it can from a real upstream.
-func TestFetchChunkedBodyAtMaxResponseSize(t *testing.T) {
-	t.Parallel()
-
-	const maxResponseSize = 8
-
-	for _, tc := range []struct {
-		size    int
-		wantErr error
-	}{
-		{maxResponseSize, nil},
-		{maxResponseSize + 1, ErrResponseTooLarge},
-	} {
-		t.Run(strconv.Itoa(tc.size)+" bytes", func(t *testing.T) {
-			t.Parallel()
-
-			body := strings.Repeat("x", tc.size)
-			endBody := make(chan struct{})
-
-			res := fetchWithMaxResponseSize(t, maxResponseSize,
-				func(w http.ResponseWriter, r *http.Request) {
-					w.Header().Set("Content-Type", contentTypeJPEG)
-					_, _ = io.WriteString(w, body)
-					// With no Content-Length, flushing sends the body
-					// chunked; its end is sent when the handler returns.
-					_ = http.NewResponseController(w).Flush()
-
-					select {
-					case <-endBody:
-					case <-r.Context().Done():
-					}
-				})
-
-			if res.ContentLength != -1 {
-				t.Fatalf("ContentLength = %d, want -1 (chunked)", res.ContentLength)
-			}
-
-			head := make([]byte, maxResponseSize)
-
-			_, err := io.ReadFull(res.Content, head)
-			if err != nil {
-				t.Fatalf("read the first %d bytes: %v", maxResponseSize, err)
-			}
-
-			close(endBody)
-
-			rest, err := io.ReadAll(res.Content)
-			data := string(head) + string(rest)
-			t.Logf("body of %d bytes: read %d, error %v", tc.size, len(data), err)
-
-			if !errors.Is(err, tc.wantErr) {
-				t.Fatalf("read error = %v, want %v", err, tc.wantErr)
-			}
-
-			if err == nil && data != body {
-				t.Errorf("read %q, want %q", data, body)
-			}
-		})
-	}
-}
-
 func TestFetchSemaphoreReleasedOnError(t *testing.T) {
 	t.Parallel()
 

internal/httpfetcher/httpfetcher.go

@@ -660,33 +660,14 @@ func dialSSRFSafe(
 	return nil, fmt.Errorf("%w to %s", errConnectFailed, host)
 }
 
-// limitedReader wraps a reader and refuses a body longer than remaining
-// bytes with ErrResponseTooLarge. remaining goes below 0 once the body is
-// found to be longer.
+// limitedReader wraps a reader and limits the number of bytes read.
 type limitedReader struct {
 	reader    io.Reader
 	remaining int64
 }
 
-// Read reads at most the remaining bytes. Once they are read, it reads one
-// more byte to tell the end of the body from more data: at the end it
-// returns the wrapped reader's error, io.EOF; with more data it returns
-// ErrResponseTooLarge, as does every later Read.
 func (r *limitedReader) Read(p []byte) (int, error) {
-	if r.remaining < 0 {
-		return 0, ErrResponseTooLarge
-	}
-
-	if r.remaining == 0 {
-		var extra [1]byte
-
-		n, err := r.reader.Read(extra[:])
-		r.remaining -= int64(n)
-
-		if n == 0 {
-			return 0, err
-		}
-
+	if r.remaining <= 0 {
 		return 0, ErrResponseTooLarge
 	}
 

internal/imgcache/storage.go

@@ -10,7 +10,6 @@ import (
 	"log/slog"
 	"os"
 	"path/filepath"
-	"strings"
 	"time"
 )
 
@@ -405,13 +404,11 @@ 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,
-		escapePercentAndColon(req.SourcePath),
-		escapePercentAndColon(req.SourceQuery),
+		req.SourcePath,
+		req.SourceQuery,
 		req.Size.Width,
 		req.Size.Height,
 		req.Format,
@@ -423,14 +420,6 @@ 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

@@ -407,62 +407,6 @@ 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

@@ -1,113 +0,0 @@
-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

@@ -10,7 +10,6 @@ import (
 	"fmt"
 	"net/url"
 	"strconv"
-	"strings"
 	"time"
 )
 
@@ -155,17 +154,15 @@ func (s *Signer) GenerateSignedURL(
 
 // buildSignatureData creates the string to be signed.
 // Format: "host:path:query:width:height:format:expiration:quality:fit"
-// 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.
+// 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.
 func (s *Signer) buildSignatureData(req *Request) string {
 	return fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%d:%s",
 		req.SourceHost,
-		escapePercentAndColon(req.SourcePath),
-		escapePercentAndColon(req.SourceQuery),
+		req.SourcePath,
+		req.SourceQuery,
 		req.Width,
 		req.Height,
 		req.Format,
@@ -175,14 +172,6 @@ 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 == "" {