bookhoard/internal/services/media_scanner_manifest_test.go

package services

// Unit tests for the sidecar manifest ladder (faceted plan Part 2 §3):
// stat-pair fast compare, hash-based repoint reconciliation, and the
// change verdicts. Real files only where the hash compare needs them.

import (
	"os"
	"path/filepath"
	"testing"
	"time"
)

func TestDecodeSidecarManifest(t *testing.T) {
	if decodeSidecarManifest(nil) != nil {
		t.Error("NULL manifest decodes to nil (backfill territory)")
	}
	if decodeSidecarManifest([]byte("{not json")) != nil {
		t.Error("corrupt manifest decodes to nil (self-healing backfill)")
	}
	m := decodeSidecarManifest([]byte(`{"v":1,"entries":[{"n":"metadata.opf","s":10,"m":100,"h":"abc"}]}`))
	if m == nil || len(m.Entries) != 1 || m.Entries[0].Sha != "abc" {
		t.Errorf("valid manifest round-trip failed: %+v", m)
	}
}

// TestStatSidecarManifestSentinelNames pins the Phase 6 name derivation
// for folder books: the manifest must stat exactly the names the
// extractor consumes through the sentinel (metadata sidecars + the
// standard cover set) — never the directory's own basename (the
// extractor's basename-pattern covers resolve against the sentinel's
// basename, which generates no candidates).
func TestStatSidecarManifestSentinelNames(t *testing.T) {
	dir := t.TempDir()
	write := func(name string) {
		t.Helper()
		if err := os.WriteFile(filepath.Join(dir, name), []byte("x"), 0o644); err != nil {
			t.Fatal(err)
		}
	}
	write("metadata.json")
	write("cover.jpg")
	write(filepath.Base(dir) + ".jpg") // extractor never reads this
	sentinel := filepath.Join(dir, ".audiobook-root")

	m := statSidecarManifest(sentinel, dir)
	if m == nil {
		t.Fatal("manifest must stat, not nil")
	}
	seen := map[string]bool{}
	for _, e := range m.Entries {
		seen[e.Name] = true
	}
	if !seen["metadata.json"] || !seen["cover.jpg"] {
		t.Errorf("extractor-consumed sidecars missing from manifest: %v", seen)
	}
	if seen[filepath.Base(dir)+".jpg"] {
		t.Errorf("directory-basename cover must not be tracked (extractor ignores it): %v", seen)
	}
	for name := range seen {
		if name == ".audiobook-root.jpg" {
			t.Errorf("sentinel-basename candidates must not appear (they cannot exist): %v", seen)
		}
	}
}

func TestReconcileSidecarManifest(t *testing.T) {
	dir := t.TempDir()
	write := func(name, content string) {
		t.Helper()
		if err := os.WriteFile(filepath.Join(dir, name), []byte(content), 0644); err != nil {
			t.Fatal(err)
		}
	}

	// The book: one hashed sidecar + one size-only cover.
	write("metadata.opf", `<opf>original content</opf>`)
	originalSha, err := sha256File(filepath.Join(dir, "metadata.opf"))
	if err != nil {
		t.Fatal(err)
	}
	write("cover.jpg", "coverbytes")
	// stored is seeded exactly the way production backfill does: a real
	// stat pass + hash fill. Hand-built fake mtimes would drift on the
	// first compare (real files' mtimes never equal a constant).
	stored := hashSidecarManifest("book.epub", dir, statSidecarManifest(filepath.Join(dir, "book.epub"), dir))

	stat := func() *sidecarManifest {
		m := statSidecarManifest(filepath.Join(dir, "book.epub"), dir)
		if m == nil || len(m.Entries) < 2 {
			t.Fatalf("stat manifest should find both sidecars, got %+v", m)
		}
		return m
	}

	// Stat pairs identical → unchanged, zero reads, nothing to store.
	fresh, changed := reconcileSidecarManifest(dir, stored, stat())
	if changed || fresh != nil {
		t.Errorf("identical stats must be unchanged, got changed=%v fresh=%v", changed, fresh)
	}

	// Repoint: mtime drifts, content identical → reconciled fresh
	// manifest with the refreshed stat pair and the KEPT hash, no change.
	if err := os.Chtimes(filepath.Join(dir, "metadata.opf"), time.Now(), time.Now().Add(time.Minute)); err != nil {
		t.Fatal(err)
	}
	fresh, changed = reconcileSidecarManifest(dir, stored, stat())
	if changed {
		t.Error("mtime drift with identical content is repoint reconciliation, not a change")
	}
	if fresh == nil || len(fresh.Entries) != 2 {
		t.Fatalf("repoint must produce a refreshed manifest, got %+v", fresh)
	}
	if fresh.Entries[0].Sha != originalSha {
		t.Error("repointed entry keeps its stored hash")
	}
	if fresh.Entries[0].MTime == stored.Entries[0].MTime {
		t.Error("repointed entry refreshes its stat pair")
	}

	// Same-size edit: drift + hash differs → changed.
	write("metadata.opf", `<opf>mutated XYY content</opf>`) // +1 byte, and hash differs
	_, changed = reconcileSidecarManifest(dir, stored, stat())
	if !changed {
		t.Error("content drift must be a change")
	}

	// Same-LENGTH edit (the size-only detection blind spot) → changed.
	write("metadata.opf", `<opf>original Xontent</opf>`)
	_, changed = reconcileSidecarManifest(dir, stored, stat())
	if !changed {
		t.Error("same-size content drift must be a change (hash compare)")
	}

	// New sidecar appears → changed.
	write("metadata.json", `{"title":"X"}`)
	_, changed = reconcileSidecarManifest(dir, stored, stat())
	if !changed {
		t.Error("an appearing sidecar must be a change")
	}

	// Sidecar vanishes AND everything else returns to the stored state
	// (opf restored; its mtime drifts but the hash proves equality) →
	// the manifest reconciles, not a change.
	if err := os.Remove(filepath.Join(dir, "metadata.json")); err != nil {
		t.Fatal(err)
	}
	write("metadata.opf", `<opf>original content</opf>`)
	fresh, changed = reconcileSidecarManifest(dir, stored, stat())
	if changed {
		t.Errorf("returning to the stored state is not a change: %+v", fresh)
	}
	if fresh == nil || len(fresh.Entries) != 2 {
		t.Errorf("reconciled manifest covers both sidecars: %+v", fresh)
	}
}

// An unhashable drift (a stored entry with no baseline hash — legacy
// or partially-written manifest) is a change: the manifest cannot prove
// content equality for it.
func TestReconcileUnhashableDrift(t *testing.T) {
	dir := t.TempDir()
	stored := &sidecarManifest{Version: 1, Entries: []manifestSidecar{
		{Name: "cover.jpg", Size: 10, MTime: 1000},
	}}
	computed := &sidecarManifest{Version: 1, Entries: []manifestSidecar{
		{Name: "cover.jpg", Size: 11, MTime: 1001},
	}}
	fresh, changed := reconcileSidecarManifest(dir, stored, computed)
	if !changed {
		t.Error("stat drift without a stored baseline hash must be a change")
	}
	if fresh != nil {
		t.Error("a change never returns a fresh manifest (caller builds one)")
	}
}