Make one image URL per source on the generator page for host case and an empty path (closes #293) #294

Merged
clawbot merged 2 commits from issue-293-generator-canonical-source into next 2026-10-16 04:04:19 +02:00
4 changed files with 94 additions and 4 deletions
+5 -3
View File
@@ -473,9 +473,11 @@ nor change what it asks for.
`jxl` for a form with no format. `jxl` for a form with no format.
The token holds the source's host, path and query and the size, format, quality, The token holds the source's host, path and query and the size, format, quality,
fit and expiry, encrypted with a key derived from `signing_key`. The source fit and expiry, encrypted with a key derived from `signing_key`. The host is
URL's scheme is not kept: the image is fetched like any other (see Routes), and kept in lower case and an empty path as `/`, as for `/v1/image/`, so
the blocked networks still apply. `https://CDN.Example.com` and `https://cdn.example.com/` are one source image,
fetched and cached once. The source URL's scheme is not kept: the image is
fetched like any other (see Routes), and the blocked networks still apply.
How long the URL lasts is chosen on the page, from 1 minute to 1 year, or never. How long the URL lasts is chosen on the page, from 1 minute to 1 year, or never.
The expiry is fixed in the token when the URL is made and cannot be changed or The expiry is fixed in the token when the URL is made and cannot be changed or
+5
View File
@@ -30,6 +30,11 @@ P2: security: per-origin rate limiting
# Completed Steps # Completed Steps
- 2026-10-16 the generator page lower-cases the source host and writes an empty
source path as `/` before it makes the encrypted URL, as `/v1/image/` does
(closes #293). A host written in upper and in lower case, or a source URL with
no path and with the path `/`, made two cache keys and two upstream requests
for one image.
- 2026-10-16 the source URL a request fetches is built with `net/url` from the - 2026-10-16 the source URL a request fetches is built with `net/url` from the
source host, path and query, not joined as text (closes #288). The source source host, path and query, not joined as text (closes #288). The source
path, decoded, is fetched percent-encoded again, so `100%25.png` fetches path, decoded, is fetched percent-encoded again, so `100%25.png` fetches
+20 -1
View File
@@ -127,7 +127,7 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
sourceURL := r.FormValue("url") sourceURL := r.FormValue("url")
// Validate source URL // Validate source URL
parsed, err := url.Parse(sourceURL) parsed, err := parseSourceURL(sourceURL)
if err != nil || parsed.Host == "" { if err != nil || parsed.Host == "" {
s.renderGeneratorWithForm(w, r, "Invalid source URL", r.Form, s.renderGeneratorWithForm(w, r, "Invalid source URL", r.Form,
http.StatusBadRequest) http.StatusBadRequest)
@@ -198,6 +198,25 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
} }
} }
// parseSourceURL parses the source URL entered on the generator page with its
// host lower-cased and an empty path written as "/", as /v1/image/ reads a
// source URL, so that each spelling of one source URL makes one cache key and
// one upstream request.
func parseSourceURL(sourceURL string) (*url.URL, error) {
parsed, err := url.Parse(sourceURL)
if err != nil {
return nil, err
}
parsed.Host = strings.ToLower(parsed.Host)
if parsed.Path == "" {
parsed.Path = "/"
}
return parsed, nil
}
// fetchedAsWritten reports whether fetchURL, the URL pixa fetches for an // fetchedAsWritten reports whether fetchURL, the URL pixa fetches for an
// image URL made from the source URL source, is source as it was written, // 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 // apart from the scheme, which the token does not keep. It is not when source
@@ -308,6 +308,70 @@ func TestGeneratedURLFetchesTheSourceURLAsEntered(t *testing.T) {
} }
} }
// TestGeneratorMakesOneImageURLForTwoSpellingsOfASourceURL enters two
// spellings of one source URL on the generator page, requests the encrypted
// URL made for each, and checks that the upstream receives one request and
// that the second encrypted URL is served from the cache. One pair writes the
// host in upper and in lower case, which /v1/image/ lower-cases. The host is
// an IPv6 address, whose hex digits have letter case, because the fetcher
// would look a host name up in DNS. It has a port, as the fetcher refuses an
// IPv6 address written without one. The other pair is a source URL with no
// path and with the path "/", both of which fetch "/".
func TestGeneratorMakesOneImageURLForTwoSpellingsOfASourceURL(t *testing.T) {
t.Parallel()
tests := []struct {
name string
// sourceURLs are the two spellings, after "https://"
sourceURLs []string
// wantRequest is the path the upstream must receive
wantRequest string
}{
{"host in upper and in lower case",
[]string{"[2001:DB8::A]:8443/a.png", "[2001:db8::a]:8443/a.png"},
"/a.png"},
{"no path and the path written as a slash",
[]string{upstreamHost, upstreamHost + "/"}, "/"},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
t.Parallel()
upstream := startRecordingUpstream(t)
s, _, _ := startImageProxy(t, upstream.Server)
var imageURLs []string
for _, sourceURL := range tt.sourceURLs {
rec := postGenerate(t, s, "https://"+sourceURL)
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())
}
imageURLs = append(imageURLs, match[1])
}
getImage(t, s, imageURLs[0])
second := getImage(t, s, imageURLs[1])
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)
if !slices.Equal(got, []string{tt.wantRequest}) {
t.Errorf("upstream received %q, want [%q]", got, tt.wantRequest)
}
})
}
}
// TestGeneratorRefusesSourceURLItCannotFetchAsWritten submits source URLs the // TestGeneratorRefusesSourceURLItCannotFetchAsWritten submits source URLs the
// generator page must make no encrypted URL for, and checks that it answers // 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 // 400 and shows why. pixa keeps the source path decoded and fetches it