Return the recipe source url when it is verifiably free of secrets
The dinner detail API now sends source.url when the stored recipe link
is https to a host with no userinfo, no query (not even a bare "?") and
no fragment (not even a bare "#"), and a port the client can parse;
otherwise source.url is null. The rule matches sourceUrl() in
web/src/dinners/detail.ts, so the recipe screen links "Recipe from
{site}" in a new tab for a safe link and shows plain text otherwise.
The site-name protection in pageSiteName is unchanged.
Task: c1a97243-3e41-42fc-a1a0-1ac684ccb463
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -58,15 +58,16 @@ type Ingredient struct {
|
||||
RawText string `json:"raw_text"`
|
||||
}
|
||||
|
||||
// Source is the site a recipe was fetched from. It has no url: the page's
|
||||
// link, pasted or offered as a candidate, may carry a personal token, and
|
||||
// no stored link can be shown to be free of one, so like a dinner's
|
||||
// recipe_url and a candidate's page it never leaves the server. SiteName
|
||||
// is the name the page itself gives its site, and null when it gives none
|
||||
// or the stored name could have come from a link (see pageSiteName), so a
|
||||
// client shows "Recipe from {site}" only when SiteName is not null.
|
||||
// Source is the site a recipe was fetched from. SiteName is the name the
|
||||
// page itself gives its site, and null when it gives none or the stored
|
||||
// name could have come from a link (see pageSiteName), so a client shows
|
||||
// "Recipe from {site}" only when SiteName is not null. URL is the page's
|
||||
// link only when it is verifiably free of secrets (see safeSourceURL), and
|
||||
// null otherwise: a link pasted or offered as a candidate may carry a
|
||||
// personal token, so a client links the credit only when URL is not null.
|
||||
type Source struct {
|
||||
SiteName *string `json:"site_name"`
|
||||
URL *string `json:"url"`
|
||||
}
|
||||
|
||||
// Get returns dinner id with its recipe and the reason it was suggested,
|
||||
@@ -149,7 +150,7 @@ func readRecipe(ctx context.Context, q *db.Queries, recipeID string, d *Detail)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
d.Source = &Source{SiteName: site}
|
||||
d.Source = &Source{SiteName: site, URL: safeSourceURL(rec.SourceUrl)}
|
||||
}
|
||||
ings, err := q.ListRecipeIngredients(ctx, recipeID)
|
||||
if err != nil {
|
||||
@@ -209,6 +210,28 @@ func pageSiteName(stored sql.NullString, sourceURL string) (*string, error) {
|
||||
return &name, nil
|
||||
}
|
||||
|
||||
// safeSourceURL is sourceURL when it is verifiably free of secrets — an
|
||||
// https link to a host, with no user or password, no query (not even a
|
||||
// bare "?") and no fragment (not even a bare "#") — else nil. Those are
|
||||
// the places a link carries a token; a link failing any check, or not
|
||||
// parsing, is withheld rather than trimmed, since a trimmed link is not the
|
||||
// page the recipe came from. The client (sourceUrl in
|
||||
// web/src/dinners/detail.ts) refuses any other link, so the port must also
|
||||
// be one it parses.
|
||||
func safeSourceURL(sourceURL string) *string {
|
||||
u, err := url.Parse(sourceURL)
|
||||
if err != nil || u.Scheme != "https" || u.Opaque != "" || u.Host == "" || u.User != nil ||
|
||||
u.RawQuery != "" || u.ForceQuery || u.Fragment != "" || strings.Contains(sourceURL, "#") {
|
||||
return nil
|
||||
}
|
||||
if port := u.Port(); port != "" {
|
||||
if n, err := strconv.ParseUint(port, 10, 16); err != nil || n == 0 {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
return &sourceURL
|
||||
}
|
||||
|
||||
// duplicatePosition is the error for two recipe items of kind at position.
|
||||
// Position is the only record of recipe order, and the id that breaks the
|
||||
// tie says nothing about it, so a recipe with a duplicate is refused rather
|
||||
|
||||
@@ -112,6 +112,45 @@ func TestPageSiteNameWithholdsHosts(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestSafeSourceURLOnlyWithoutSecrets: a recipe link is shown only when it
|
||||
// is https to a host with no user, password, query or fragment, each of
|
||||
// which can carry a token; any other link, or one that does not parse, is
|
||||
// withheld whole.
|
||||
func TestSafeSourceURLOnlyWithoutSecrets(t *testing.T) {
|
||||
t.Parallel()
|
||||
for _, link := range []string{
|
||||
"https://www.example.com/recipes/chicken-curry",
|
||||
"https://example.com",
|
||||
"https://example.com:8443/stew/",
|
||||
} {
|
||||
if got := dinners.SafeSourceURL(link); got == nil || *got != link {
|
||||
t.Errorf("SafeSourceURL(%q) = %v, want the link", link, deref(got))
|
||||
}
|
||||
}
|
||||
for _, link := range []string{
|
||||
"https://example.com/curry?access_token=query-token",
|
||||
"https://example.com/curry?",
|
||||
"https://user:password@example.com/curry",
|
||||
"https://token@example.com/curry",
|
||||
"https://@example.com/curry",
|
||||
"http://example.com/curry",
|
||||
"https://example.com/curry#token=fragment-token",
|
||||
"https://example.com/curry#",
|
||||
"ftp://example.com/curry",
|
||||
"https:example.com/curry",
|
||||
"https:///curry",
|
||||
"https://example.com:99999/curry",
|
||||
"https://example.com:0/curry",
|
||||
"//example.com/curry",
|
||||
"https://secret-token\x7f.example/%zz",
|
||||
"",
|
||||
} {
|
||||
if got := dinners.SafeSourceURL(link); got != nil {
|
||||
t.Errorf("SafeSourceURL(%q) = %q, want nil", link, *got)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func deref(s *string) any {
|
||||
if s == nil {
|
||||
return nil
|
||||
|
||||
@@ -74,3 +74,6 @@ func (s *Service) RunGroundJob(ctx context.Context, p GroundJob) (string, error)
|
||||
|
||||
// PageSiteName is pageSiteName.
|
||||
var PageSiteName = pageSiteName
|
||||
|
||||
// SafeSourceURL is safeSourceURL.
|
||||
var SafeSourceURL = safeSourceURL
|
||||
|
||||
Reference in New Issue
Block a user