Files
silo-server/internal/api/handlers/admin_match_test.go
c75c519e3d fix(metadata): stop manual rematch from resurrecting recorded stale IDs (#276)
* fix(metadata): stop manual rematch from resurrecting recorded stale IDs

The Apply Match flow (ModeIdentify) re-injected durable provider IDs into
the identify request without checking stale_media_ids, so a known-dead
tmdb ID rode along, 404ed again during the Phase-2 fetch, and was
re-recorded with a fresh last_seen_at — the item never left the Stale
External IDs list and jumped back to the top after every rematch.

Filter recorded-stale IDs out of the injected durable set in
prepareProcessRequest. Caller-supplied IDs are untouched, so an admin
deliberately re-selecting a previously-stale ID still retries it (which
is also why the ModeIdentify suppression guard in processInternal stays).

Fixes #268

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(metadata): normalize provider-id keys so stale-ID suppression can't be bypassed by casing

Review on PR #276 flagged that suppressRecordedStaleProviderIDs lowercases
and trims the stored stale row's provider before looking it up in the
incoming map, while the map keys are used verbatim, and that
HandleApplyItemMatch passes req.ProviderIDs from the JSON body straight
into metadata.Process without the normalization the search endpoint
applies. A caller-supplied key like "TMDB" or " tmdb " therefore defeated
the suppression. The same normalization gap was previously flagged on
PR #182.

Fix both layers:
- HandleApplyItemMatch now runs req.ProviderIDs through
  normalizeMatchProviderIDs (same semantics as the search endpoint) and
  returns 400 when no non-blank entries remain, mirroring the existing
  empty-map rejection.
- suppressRecordedStaleProviderIDs now indexes the incoming map by
  normalized key and deletes the matching original keys, so suppression
  is robust regardless of caller casing or padding.

Adds regression tests at both layers: a metadata-level case where the
durable row arrives as "TMDB " while the stale row records "tmdb", and
handler-level cases asserting apply normalizes keys/values and rejects
all-blank provider-id maps.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com>
2026-07-02 14:07:34 -04:00

423 lines
13 KiB
Go

package handlers
import (
"bytes"
"context"
"encoding/json"
"fmt"
"net/http"
"net/http/httptest"
"testing"
"github.com/go-chi/chi/v5"
"github.com/Silo-Server/silo-server/internal/metadata"
"github.com/Silo-Server/silo-server/internal/models"
)
// --- Fakes ---
type fakeMatchItemLookup struct {
items map[string]*models.MediaItem
}
func (f *fakeMatchItemLookup) GetByID(_ context.Context, contentID string) (*models.MediaItem, error) {
if item, ok := f.items[contentID]; ok {
return item, nil
}
return nil, fmt.Errorf("item not found: %s", contentID)
}
type fakeMatchFolderLookup struct {
folders map[string]int
folderIDs map[string][]int
}
func (f *fakeMatchFolderLookup) GetFolderIDForItem(_ context.Context, contentID string) (int, error) {
if fid, ok := f.folders[contentID]; ok {
return fid, nil
}
return 0, fmt.Errorf("no folder for %s", contentID)
}
func (f *fakeMatchFolderLookup) GetFolderIDsForItem(_ context.Context, contentID string) ([]int, error) {
if ids, ok := f.folderIDs[contentID]; ok {
return ids, nil
}
if fid, ok := f.folders[contentID]; ok {
return []int{fid}, nil
}
return nil, fmt.Errorf("no folders for %s", contentID)
}
type fakeMatchMetadataService struct {
searchResults []metadata.MatchCandidate
searchErr error
processResult *metadata.ProcessResult
processErr error
lastProcess metadata.ProcessRequest
}
func (f *fakeMatchMetadataService) SearchAndNormalize(_ context.Context, _ metadata.SearchQuery, _ int) ([]metadata.MatchCandidate, error) {
return f.searchResults, f.searchErr
}
func (f *fakeMatchMetadataService) Process(_ context.Context, req metadata.ProcessRequest) (*metadata.ProcessResult, error) {
f.lastProcess = req
return f.processResult, f.processErr
}
// --- Helpers ---
func buildMatchRouter(h *AdminMatchHandler) *chi.Mux {
r := chi.NewRouter()
r.Post("/admin/items/{id}/match/search", h.HandleSearchItemMatchCandidates)
r.Post("/admin/items/{id}/match/apply", h.HandleApplyItemMatch)
return r
}
// --- Tests ---
func TestAdminMatchSearch_ReturnsCandidatesArray(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-1": {ContentID: "item-1", Title: "The Matrix", Year: 1999, Type: "movie"},
},
}
folders := &fakeMatchFolderLookup{
folders: map[string]int{"item-1": 10},
}
metaSvc := &fakeMatchMetadataService{
searchResults: []metadata.MatchCandidate{
{
Title: "The Matrix",
Year: 1999,
ContentType: "movie",
ProviderIDs: map[string]string{"tmdb": "603", "imdb": "tt0133093"},
Sources: []string{"tmdb"},
AgreementHints: []string{"agreed_by_tmdb_and_tvdb"},
},
{
Title: "The Matrix Reloaded",
Year: 2003,
ContentType: "movie",
ProviderIDs: map[string]string{"tmdb": "604"},
Sources: []string{"tmdb"},
},
},
}
h := NewAdminMatchHandler(items, folders, metaSvc)
router := buildMatchRouter(h)
body, _ := json.Marshal(matchSearchRequest{Title: "The Matrix"})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-1/match/search", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", rec.Code, rec.Body.String())
}
var resp matchSearchResponse
if err := json.NewDecoder(rec.Body).Decode(&resp); err != nil {
t.Fatalf("decoding response: %v", err)
}
if len(resp.Candidates) != 2 {
t.Fatalf("expected 2 candidates, got %d", len(resp.Candidates))
}
// Verify candidate structure.
c0 := resp.Candidates[0]
if c0.Title != "The Matrix" {
t.Errorf("expected title 'The Matrix', got %q", c0.Title)
}
if c0.ProviderIDs["tmdb"] != "603" {
t.Errorf("expected tmdb=603, got %q", c0.ProviderIDs["tmdb"])
}
if len(c0.AgreementHints) != 1 || c0.AgreementHints[0] != "agreed_by_tmdb_and_tvdb" {
t.Errorf("expected agreement_hints, got %v", c0.AgreementHints)
}
}
func TestAdminMatchSearch_ItemNotFound(t *testing.T) {
items := &fakeMatchItemLookup{items: map[string]*models.MediaItem{}}
h := NewAdminMatchHandler(items, nil, &fakeMatchMetadataService{})
router := buildMatchRouter(h)
body, _ := json.Marshal(matchSearchRequest{Title: "foo"})
req := httptest.NewRequest(http.MethodPost, "/admin/items/nonexistent/match/search", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusNotFound {
t.Fatalf("expected 404, got %d: %s", rec.Code, rec.Body.String())
}
}
func TestAdminMatchSearch_FallsBackToItemMetadata(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-2": {ContentID: "item-2", Title: "Inception", Year: 2010, Type: "movie"},
},
}
var capturedQuery metadata.SearchQuery
metaSvc := &fakeMatchMetadataService{
searchResults: []metadata.MatchCandidate{},
}
// Wrap to capture the query.
captureSvc := &capturingMetadataService{
inner: metaSvc,
}
h := NewAdminMatchHandler(items, nil, captureSvc)
router := buildMatchRouter(h)
// Send empty title/year -- handler should use item's metadata.
body, _ := json.Marshal(matchSearchRequest{})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-2/match/search", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", rec.Code, rec.Body.String())
}
capturedQuery = captureSvc.lastQuery
if capturedQuery.Title != "Inception" {
t.Errorf("expected title fallback to 'Inception', got %q", capturedQuery.Title)
}
if capturedQuery.Year != 2010 {
t.Errorf("expected year fallback to 2010, got %d", capturedQuery.Year)
}
}
func TestAdminMatchSearch_AcceptsGenericProviderIDsAndLibraryID(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"ebook-1": {ContentID: "ebook-1", Title: "Example Book", Year: 2024, Type: "ebook"},
},
}
folders := &fakeMatchFolderLookup{
folderIDs: map[string][]int{"ebook-1": {7, 8}},
}
captureSvc := &capturingMetadataService{
inner: &fakeMatchMetadataService{searchResults: []metadata.MatchCandidate{}},
}
h := NewAdminMatchHandler(items, folders, captureSvc)
router := buildMatchRouter(h)
libraryID := 8
body, _ := json.Marshal(matchSearchRequest{
ProviderIDs: map[string]string{
" ISBN ": " 9780000000001 ",
"goodreads": " ",
},
TmdbID: "12345",
LibraryID: &libraryID,
})
req := httptest.NewRequest(http.MethodPost, "/admin/items/ebook-1/match/search", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", rec.Code, rec.Body.String())
}
if captureSvc.lastFolderID != 8 {
t.Fatalf("folderID = %d, want 8", captureSvc.lastFolderID)
}
if captureSvc.lastQuery.ContentType != "ebook" {
t.Fatalf("ContentType = %q, want ebook", captureSvc.lastQuery.ContentType)
}
if got := captureSvc.lastQuery.ProviderIDs["isbn"]; got != "9780000000001" {
t.Fatalf("ProviderIDs[isbn] = %q, want 9780000000001", got)
}
if got := captureSvc.lastQuery.ProviderIDs["tmdb"]; got != "12345" {
t.Fatalf("ProviderIDs[tmdb] = %q, want 12345", got)
}
if _, ok := captureSvc.lastQuery.ProviderIDs["goodreads"]; ok {
t.Fatalf("blank provider IDs should be ignored, got %v", captureSvc.lastQuery.ProviderIDs)
}
}
func TestAdminMatchApply_PreservesContentID(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-3": {ContentID: "item-3", Title: "Interstellar", Year: 2014, Type: "movie"},
},
}
metaSvc := &fakeMatchMetadataService{
processResult: &metadata.ProcessResult{
ContentID: "item-3",
Updated: true,
},
}
h := NewAdminMatchHandler(items, nil, metaSvc)
router := buildMatchRouter(h)
body, _ := json.Marshal(matchApplyRequest{
ProviderIDs: map[string]string{"tmdb": "157336"},
})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-3/match/apply", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", rec.Code, rec.Body.String())
}
var resp matchApplyResponse
if err := json.NewDecoder(rec.Body).Decode(&resp); err != nil {
t.Fatalf("decoding response: %v", err)
}
// The original content_id must be preserved (not replaced with a new ID).
if resp.ContentID != "item-3" {
t.Errorf("expected content_id 'item-3' preserved, got %q", resp.ContentID)
}
if !resp.Updated {
t.Error("expected updated=true")
}
// Verify the Process call used ModeIdentify with the original content_id.
if metaSvc.lastProcess.ContentID != "item-3" {
t.Errorf("expected Process called with content_id 'item-3', got %q", metaSvc.lastProcess.ContentID)
}
if metaSvc.lastProcess.Mode != metadata.ModeIdentify {
t.Errorf("expected ModeIdentify, got %d", metaSvc.lastProcess.Mode)
}
if metaSvc.lastProcess.ProviderIDs["tmdb"] != "157336" {
t.Errorf("expected provider_ids tmdb=157336, got %v", metaSvc.lastProcess.ProviderIDs)
}
}
func TestAdminMatchApply_RequiresProviderIDs(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-4": {ContentID: "item-4", Title: "Test", Type: "movie"},
},
}
h := NewAdminMatchHandler(items, nil, &fakeMatchMetadataService{})
router := buildMatchRouter(h)
body, _ := json.Marshal(matchApplyRequest{ProviderIDs: map[string]string{}})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-4/match/apply", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusBadRequest {
t.Fatalf("expected 400 for empty provider_ids, got %d: %s", rec.Code, rec.Body.String())
}
}
func TestAdminMatchApply_NormalizesProviderIDKeys(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-5": {ContentID: "item-5", Title: "Test", Type: "movie"},
},
}
metaSvc := &fakeMatchMetadataService{
processResult: &metadata.ProcessResult{ContentID: "item-5", Updated: true},
}
h := NewAdminMatchHandler(items, nil, metaSvc)
router := buildMatchRouter(h)
body, _ := json.Marshal(matchApplyRequest{
ProviderIDs: map[string]string{
" TMDB ": " 157336 ",
"blank": " ",
},
})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-5/match/apply", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", rec.Code, rec.Body.String())
}
if got := metaSvc.lastProcess.ProviderIDs["tmdb"]; got != "157336" {
t.Errorf("Process provider_ids[tmdb] = %q, want 157336 (keys/values must be normalized)", got)
}
if _, ok := metaSvc.lastProcess.ProviderIDs[" TMDB "]; ok {
t.Errorf("Process received raw key %q, want normalized keys only: %v", " TMDB ", metaSvc.lastProcess.ProviderIDs)
}
if _, ok := metaSvc.lastProcess.ProviderIDs["blank"]; ok {
t.Errorf("blank provider IDs should be dropped, got %v", metaSvc.lastProcess.ProviderIDs)
}
}
func TestAdminMatchApply_RejectsAllBlankProviderIDs(t *testing.T) {
items := &fakeMatchItemLookup{
items: map[string]*models.MediaItem{
"item-6": {ContentID: "item-6", Title: "Test", Type: "movie"},
},
}
h := NewAdminMatchHandler(items, nil, &fakeMatchMetadataService{})
router := buildMatchRouter(h)
body, _ := json.Marshal(matchApplyRequest{
ProviderIDs: map[string]string{"tmdb": " ", " ": "123"},
})
req := httptest.NewRequest(http.MethodPost, "/admin/items/item-6/match/apply", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusBadRequest {
t.Fatalf("expected 400 for all-blank provider_ids, got %d: %s", rec.Code, rec.Body.String())
}
}
func TestAdminMatchApply_ItemNotFound(t *testing.T) {
items := &fakeMatchItemLookup{items: map[string]*models.MediaItem{}}
h := NewAdminMatchHandler(items, nil, &fakeMatchMetadataService{})
router := buildMatchRouter(h)
body, _ := json.Marshal(matchApplyRequest{ProviderIDs: map[string]string{"tmdb": "123"}})
req := httptest.NewRequest(http.MethodPost, "/admin/items/nonexistent/match/apply", bytes.NewReader(body))
req.Header.Set("Content-Type", "application/json")
rec := httptest.NewRecorder()
router.ServeHTTP(rec, req)
if rec.Code != http.StatusNotFound {
t.Fatalf("expected 404, got %d: %s", rec.Code, rec.Body.String())
}
}
// capturingMetadataService wraps a fake to capture the query passed to SearchAndNormalize.
type capturingMetadataService struct {
inner *fakeMatchMetadataService
lastQuery metadata.SearchQuery
lastFolderID int
}
func (c *capturingMetadataService) SearchAndNormalize(ctx context.Context, query metadata.SearchQuery, folderID int) ([]metadata.MatchCandidate, error) {
c.lastQuery = query
c.lastFolderID = folderID
return c.inner.SearchAndNormalize(ctx, query, folderID)
}
func (c *capturingMetadataService) Process(ctx context.Context, req metadata.ProcessRequest) (*metadata.ProcessResult, error) {
return c.inner.Process(ctx, req)
}