Withhold a site name that could be the recipe link's host

A page that names no site is stored under its host, which may be the
pasted link's (a token in a subdomain) or a redirect's. The dinner
detail now returns source.site_name only when the stored name could not
be a host: the link's own host, an IP address or a dotted host name is
withheld as null, so "Recipe from {site}" shows only real attribution.
The extractor's host fallback is shared as recipes.HostSiteName.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

internal/dinners/detail.go

@@ -5,7 +5,10 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
+	"net"
+	"net/url"
 	"strconv"
+	"strings"
 
 	"code.cubecraftlabs.com/Maniacs_Mansion/Meal-Quest/internal/db"
 	"code.cubecraftlabs.com/Maniacs_Mansion/Meal-Quest/internal/recipes"
@@ -59,7 +62,9 @@ type Ingredient struct {
 // 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 null when the page names no site.
+// 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.
 type Source struct {
 	SiteName *string `json:"site_name"`
 }
@@ -140,7 +145,11 @@ func readRecipe(ctx context.Context, q *db.Queries, recipeID string, d *Detail)
 		return fmt.Errorf("recipe %s: %w", recipeID, err)
 	}
 	if !IsManualRecipe(rec.SourceUrl) {
-		d.Source = &Source{SiteName: nullString(rec.SiteName)}
+		site, err := pageSiteName(rec.SiteName, rec.SourceUrl)
+		if err != nil {
+			return err
+		}
+		d.Source = &Source{SiteName: site}
 	}
 	ings, err := q.ListRecipeIngredients(ctx, recipeID)
 	if err != nil {
@@ -171,6 +180,35 @@ func readRecipe(ctx context.Context, q *db.Queries, recipeID string, d *Detail)
 	return nil
 }
 
+// pageSiteName is the stored site name of a recipe fetched from sourceURL
+// when it is one the page gave, else nil. A page that names no site is
+// stored under recipes.HostSiteName of the URL it was served from: the
+// pasted link's host, which may hold a personal token (a private
+// subdomain), or that of a page the link redirected to, which is not
+// stored. Nothing records which a stored name is, so any name that could
+// be a host — the link's own host, an IP address, or a dotted host name —
+// is treated as one and withheld. A site that names itself as a domain,
+// such as "Food.com", loses its attribution with them: a recipe with no
+// attribution is better than one that leaks a link.
+func pageSiteName(stored sql.NullString, sourceURL string) (*string, error) {
+	if !stored.Valid {
+		return nil, nil
+	}
+	link, err := url.Parse(sourceURL)
+	if err != nil {
+		// Not wrapped: url.Parse's error quotes the link.
+		return nil, errors.New("source url does not parse")
+	}
+	name := stored.String
+	if strings.EqualFold(name, recipes.HostSiteName(link)) || net.ParseIP(name) != nil {
+		return nil, nil
+	}
+	if u, err := url.Parse("https://" + name + "/"); err == nil && u.Host == name && strings.Contains(name, ".") {
+		return nil, nil
+	}
+	return &name, nil
+}
+
 // 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

internal/dinners/dinners_test.go

@@ -1,6 +1,7 @@
 package dinners_test
 
 import (
+	"database/sql"
 	"encoding/json"
 	"errors"
 	"strings"
@@ -74,3 +75,46 @@ func TestCreateRegularNeverNamesFromLink(t *testing.T) {
 	}
 	check("duplicate error", dup.Error())
 }
+
+// TestPageSiteNameWithholdsHosts: a stored site name that could be a host —
+// the link's own, in any case and without "www.", an IP address or a dotted
+// host name — is withheld; a name the page gave, dotless or with spaces, is
+// kept.
+func TestPageSiteNameWithholdsHosts(t *testing.T) {
+	t.Parallel()
+	const link = "https://www.TokenHost/recipes/stew"
+	for _, tc := range []struct {
+		stored string
+		valid  bool
+		want   *string
+	}{
+		{"", false, nil},
+		{"tokenhost", true, nil},
+		{"TOKENHOST", true, nil},
+		{"private-token.example.com", true, nil},
+		{"Food.com", true, nil},
+		{"203.0.113.7", true, nil},
+		{"2001:db8::1", true, nil},
+		{"Delish", true, ptr("Delish")},
+		{"Bon Appétit", true, ptr("Bon Appétit")},
+		{"Mr. Food Test Kitchen", true, ptr("Mr. Food Test Kitchen")},
+	} {
+		got, err := dinners.PageSiteName(sql.NullString{String: tc.stored, Valid: tc.valid}, link)
+		if err != nil {
+			t.Fatalf("PageSiteName(%q): %v", tc.stored, err)
+		}
+		if (got == nil) != (tc.want == nil) || (got != nil && *got != *tc.want) {
+			t.Errorf("PageSiteName(%q) = %v, want %v", tc.stored, deref(got), deref(tc.want))
+		}
+	}
+	if _, err := dinners.PageSiteName(sql.NullString{String: "Delish", Valid: true}, "https://secret-token\x7f.example/%zz"); err == nil || strings.Contains(err.Error(), "secret-token") {
+		t.Errorf("PageSiteName of an unparseable link: err = %v, want one not quoting the link", err)
+	}
+}
+
+func deref(s *string) any {
+	if s == nil {
+		return nil
+	}
+	return *s
+}

internal/dinners/export_test.go

@@ -71,3 +71,6 @@ func (s *Service) RunGroundJob(ctx context.Context, p GroundJob) (string, error)
 	r, err := s.runGroundJob(ctx, p, nil)
 	return r.GroundingStatus, err
 }
+
+// PageSiteName is pageSiteName.
+var PageSiteName = pageSiteName