Fetch the source path and query URL-encoded, not joined as text (closes #288) #289

Merged
clawbot merged 4 commits from issue-288-encode-source-url into next 2026-10-16 03:31:16 +02:00
Showing only changes of commit 5bfec71b61 - Show all commits
+63 -26
View File
@@ -157,10 +157,11 @@ func postGenerate(
}
// TestImageURLFetchesItsSourcePathAndQuery requests image URLs whose source
// query holds a space and whose source path holds a "%", each 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.
// 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()
@@ -174,6 +175,8 @@ func TestImageURLFetchesItsSourcePathAndQuery(t *testing.T) {
}{
{"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},
}
@@ -305,30 +308,64 @@ func TestGeneratedURLFetchesTheSourceURLAsEntered(t *testing.T) {
}
}
// TestGeneratorRefusesSourceURLItWouldFetchAnotherWay submits a source URL
// whose path holds %2F. pixa keeps the path decoded and would fetch it with a
// "/" there, which is another URL, so the generator page answers 400, shows
// the URL pixa would fetch, and makes no encrypted URL.
func TestGeneratorRefusesSourceURLItWouldFetchAnotherWay(t *testing.T) {
// 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()
s, _, _ := startImageProxy(t, startRecordingUpstream(t).Server)
rec := postGenerate(t, s, "https://"+upstreamHost+"/a%2Fb.png")
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")
}
// The test config sets allow_http, so pixa would fetch over plain HTTP
fetchURL := "http://" + upstreamHost + "/a/b.png"
if !strings.Contains(body, fetchURL) {
t.Errorf("the page does not show the URL pixa would fetch, %s; body %s",
fetchURL, body)
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)
}
})
}
}