Maniacs_Mansion/MealQuest
11
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Record site-name provenance instead of inferring it from the name's shape
CI / ci (push) Successful in 8m11s
Details

Browse Source 
Recipe extraction no longer falls back to the URL's host: a stored
recipes.site_name is now always a name the page gave (publisher or
og:site_name), and null when it named none. dinners.SourceOf is the one
documented rule for every fetched recipe's source: the page's name is
shown as it stands; otherwise the site is named by the link's host only
when the link itself is shown as free of secrets, else null. The recipe
detail, idea results and the recipe-candidate offer endpoint all apply
it; candidates no longer carry an extraction-time hostname fallback, so
their site_name is nullable (frontend updated to match).

Migration 0020 clears host-shaped site names (dotted host names, IP
addresses) stored before the change, in recipes and in legacy idea job
results, so already-stored rows read under the same rule.

Maestro 966066e3-0e25-4b8b-9bb0-0694c47c9106

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
dev_agent
2026-10-11 10:02:44 -04:00
co-authored by Claude Opus 5.5
parent d182349646
commit 267d0be4a6
18 changed files with 360 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/store/migrate_test.go
+80 -4
View File
@@ -2,6 +2,7 @@ package store
import (
"context"
"fmt"
"io/fs"
"reflect"
"slices"
@@ -176,8 +177,8 @@ func TestMigrateEmbeddedMigrations(t *testing.T) {
if err := Migrate(context.Background(), s.Writer, migrations.FS); err != nil {
t.Fatal(err)
}
if got := versions(migrationRows(t, s)); got != "0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed" {
t.Errorf("versions = %q, want 0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed", got)
if got := versions(migrationRows(t, s)); got != "0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed,0020_site_name_from_page" {
t.Errorf("versions = %q, want 0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed,0020_site_name_from_page", got)
}
}
@@ -197,8 +198,8 @@ func TestMigrateBootstrapThenEmbeddedInitApplies(t *testing.T) {
if err := Migrate(ctx, s.Writer, migrations.FS); err != nil {
t.Fatal(err)
}
if got := versions(migrationRows(t, s)); got != "0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed" {
t.Errorf("versions = %q, want 0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed", got)
if got := versions(migrationRows(t, s)); got != "0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed,0020_site_name_from_page" {
t.Errorf("versions = %q, want 0000_bootstrap,0001_init,0002_household_settings_updated_by,0003_jobs_status,0004_ai_provider_presets,0005_ai_provider_xai,0006_ai_runs_status,0007_recipe_grounding,0008_dinner_recipe_url,0009_dinner_grounding_error,0010_dinner_grounding_revision,0011_ground_dinner_job_revision,0012_suggestion_name,0013_week_plan_revision,0014_rotation_review_name,0015_google_reconnect_required,0016_shopping_list_untitled,0017_shopping_list_chat_send_unconfirmed,0020_site_name_from_page", got)
}
if !tableExists(t, s, "dinners") {
t.Error("table from 0001_init was not created")
@@ -922,3 +923,78 @@ func TestMigrateShoppingListChatSendUnconfirmed(t *testing.T) {
t.Errorf("shopping list after 0017 = %s, want %s", got, want)
}
}
// TestMigrateSiteNameFromPage applies 0020 over recipes and idea job
// results stored when a page naming no site was stored under its host: a
// stored name that could be a host — a dotted host name or an IP address —
// is cleared, so every stored name is one a page gave; any other name,
// including a dotted one with spaces, is kept, as is everything else in
// the rows.
func TestMigrateSiteNameFromPage(t *testing.T) {
ctx := context.Background()
s := openTestStore(t)
migrateBefore(t, s, "0020")
sites := []struct {
stored, want any
}{
{"private-token.example.com", nil},
{"Food.com", nil},
{"203.0.113.7", nil},
{"2001:db8::1", nil},
{"Curry House", "Curry House"},
{"Delish", "Delish"},
{"Mr. Food Test Kitchen", "Mr. Food Test Kitchen"},
{nil, nil},
}
for i, c := range sites {
if _, err := s.Writer.ExecContext(ctx, `INSERT INTO recipes (id, source_url, site_name, title, raw_jsonld, fetched_at, created_at, updated_at)
VALUES (?, ?, ?, 'Stew', '{}', 'f', 'c', 'u')`, fmt.Sprintf("recipe-%d", i), fmt.Sprintf("https://r%d.example/stew", i), c.stored); err != nil {
t.Fatal(err)
}
}
const (
legacy = `{"stage":"done","ideas":[{"name":"A","site_name":"query-host.example","source_url":"https://query-host.example/a?t=1"},{"name":"B","site_name":"Curry House","source_url":"https://b.example/b"},{"name":"C","site_name":null,"source_url":null}],"dropped":1}`
cleaned = `{"stage":"done","ideas":[{"name":"A","site_name":null,"source_url":"https://query-host.example/a?t=1"},{"name":"B","site_name":"Curry House","source_url":"https://b.example/b"},{"name":"C","site_name":null,"source_url":null}],"dropped":1}`
other = `{"ideas":[{"site_name":"host.example"}]}`
)
for _, j := range [][3]string{
{"job-ideas", "ideas_from_ingredients", legacy},
{"job-quick", "quick_ideas", legacy},
{"job-other", "ground_dinner", other},
{"job-empty", "quick_ideas", `{"stage":"searching","ideas":[]}`},
} {
if _, err := s.Writer.ExecContext(ctx, `INSERT INTO jobs (id, kind, status, payload, result, created_at, updated_at)
VALUES (?, ?, 'succeeded', '{}', ?, 'c', 'u')`, j[0], j[1], j[2]); err != nil {
t.Fatal(err)
}
}
if _, err := s.Writer.ExecContext(ctx, `INSERT INTO jobs (id, kind, status, payload, created_at, updated_at)
VALUES ('job-running', 'quick_ideas', 'running', '{}', 'c', 'u')`); err != nil {
t.Fatal(err)
}
if err := Migrate(ctx, s.Writer, migrations.FS); err != nil {
t.Fatal(err)
}
for i, c := range sites {
var got any
var title string
if err := s.Reader.QueryRowContext(ctx, `SELECT site_name, title FROM recipes WHERE id = ?`, fmt.Sprintf("recipe-%d", i)).Scan(&got, &title); err != nil {
t.Fatal(err)
}
if got != c.want || title != "Stew" {
t.Errorf("recipe stored with site_name %v: site_name %v, title %q after 0020; want %v, Stew", c.stored, got, title, c.want)
}
}
for id, want := range map[string]any{"job-ideas": cleaned, "job-quick": cleaned, "job-other": other,
"job-empty": `{"stage":"searching","ideas":[]}`, "job-running": nil} {
var got any
if err := s.Reader.QueryRowContext(ctx, `SELECT result FROM jobs WHERE id = ?`, id).Scan(&got); err != nil {
t.Fatal(err)
}
if got != want {
t.Errorf("%s result after 0020 = %v, want %v", id, got, want)
}
}
}