storage: add upload_files table and UploadRepo

Add the upload_files SQLite table and UploadRepo CRUD methods (Create/Get/List/Delete). The table stores file_id, name, size, sha256, and uploaded_at as a queryable index. The .meta.json sidecar remains the source of truth for uploads; the DB is only an index for admin visibility. On startup the next commit will backfill any pre-existing sidecars into this table. Tests cover Create/Get/List/Delete round-trip, name search filtering, descending time ordering, and limit defaults/cap. Co-Authored-By: Claude <noreply@anthropic.com>
2026-07-14 11:21:38 +08:00
parent 4af166ea48
commit 1796b5b872
3 changed files with 318 additions and 0 deletions
@@ -38,6 +38,15 @@ CREATE TABLE IF NOT EXISTS audit_log (
  details     TEXT
 );
 CREATE INDEX IF NOT EXISTS idx_audit_ts ON audit_log(timestamp DESC);
+
+CREATE TABLE IF NOT EXISTS upload_files (
+  file_id      TEXT PRIMARY KEY,
+  name         TEXT NOT NULL,
+  size         INTEGER NOT NULL,
+  sha256       TEXT NOT NULL,
+  uploaded_at  INTEGER NOT NULL
+);
+CREATE INDEX IF NOT EXISTS idx_uploads_ts ON upload_files(uploaded_at DESC);
 `

 // DB is the storage handle.
@@ -0,0 +1,147 @@
+package storage
+
+import (
+	"context"
+	"database/sql"
+	"errors"
+	"fmt"
+	"strings"
+	"time"
+)
+
+// UploadMeta is the database index record for an uploaded file.
+//
+// The .meta.json sidecar remains the source of truth; this struct is the
+// queryable mirror used by the admin UI.
+type UploadMeta struct {
+	FileID     string
+	Name       string
+	Size       int64
+	SHA256     string
+	UploadedAt time.Time
+}
+
+// UploadRepo provides CRUD operations for upload file index records.
+type UploadRepo struct {
+	db *DB
+}
+
+// Uploads returns a repository bound to this DB handle.
+func (d *DB) Uploads() *UploadRepo {
+	return &UploadRepo{db: d}
+}
+
+// Create inserts a new upload index record. Timestamps are stored as Unix
+// nanoseconds for stable ORDER BY semantics.
+func (r *UploadRepo) Create(ctx context.Context, fileID, name string, size int64, sha256Hex string, uploadedAt time.Time) error {
+	_, err := r.db.sqlDB.ExecContext(ctx, `
+		INSERT INTO upload_files (file_id, name, size, sha256, uploaded_at)
+		VALUES (?, ?, ?, ?, ?)`,
+		fileID, name, size, sha256Hex, uploadedAt.UnixNano(),
+	)
+	if err != nil {
+		if strings.Contains(err.Error(), "UNIQUE constraint failed") {
+			return fmt.Errorf("storage: create upload %s: primary key conflict: %w", fileID, err)
+		}
+		return fmt.Errorf("storage: create upload %s: %w", fileID, err)
+	}
+	return nil
+}
+
+// Get retrieves an upload index record by file_id. If the record does not
+// exist, it returns ErrNotFound.
+func (r *UploadRepo) Get(ctx context.Context, fileID string) (UploadMeta, error) {
+	row := r.db.sqlDB.QueryRowContext(ctx, `
+		SELECT file_id, name, size, sha256, uploaded_at
+		FROM upload_files
+		WHERE file_id = ?`, fileID)
+
+	m, err := scanUpload(row.Scan)
+	if errors.Is(err, sql.ErrNoRows) {
+		return UploadMeta{}, ErrNotFound
+	}
+	if err != nil {
+		return UploadMeta{}, fmt.Errorf("storage: get upload %s: %w", fileID, err)
+	}
+	return m, nil
+}
+
+// List returns upload index records ordered by uploaded_at descending.
+//
+// If search is non-empty, name is filtered with a case-insensitive LIKE.
+// A limit of zero or less falls back to 100; values above 500 are capped.
+func (r *UploadRepo) List(ctx context.Context, search string, limit int) ([]UploadMeta, error) {
+	if limit <= 0 {
+		limit = 100
+	}
+	if limit > 500 {
+		limit = 500
+	}
+
+	var rows *sql.Rows
+	var err error
+	if search != "" {
+		rows, err = r.db.sqlDB.QueryContext(ctx, `
+			SELECT file_id, name, size, sha256, uploaded_at
+			FROM upload_files
+			WHERE name LIKE ?
+			ORDER BY uploaded_at DESC
+			LIMIT ?`,
+			"%"+search+"%", limit,
+		)
+	} else {
+		rows, err = r.db.sqlDB.QueryContext(ctx, `
+			SELECT file_id, name, size, sha256, uploaded_at
+			FROM upload_files
+			ORDER BY uploaded_at DESC
+			LIMIT ?`, limit)
+	}
+	if err != nil {
+		return nil, fmt.Errorf("storage: list uploads: %w", err)
+	}
+	defer rows.Close()
+
+	var out []UploadMeta
+	for rows.Next() {
+		m, err := scanUpload(rows.Scan)
+		if err != nil {
+			return nil, fmt.Errorf("storage: list uploads: %w", err)
+		}
+		out = append(out, m)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("storage: list uploads: %w", err)
+	}
+	if out == nil {
+		// Force empty slice (not null) in JSON.
+		out = []UploadMeta{}
+	}
+	return out, nil
+}
+
+// Delete removes an upload index record by file_id. If the record does not
+// exist, it returns ErrNotFound.
+func (r *UploadRepo) Delete(ctx context.Context, fileID string) error {
+	res, err := r.db.sqlDB.ExecContext(ctx, `DELETE FROM upload_files WHERE file_id = ?`, fileID)
+	if err != nil {
+		return fmt.Errorf("storage: delete upload %s: %w", fileID, err)
+	}
+	n, err := res.RowsAffected()
+	if err != nil {
+		return fmt.Errorf("storage: delete upload %s: rows affected: %w", fileID, err)
+	}
+	if n == 0 {
+		return ErrNotFound
+	}
+	return nil
+}
+
+func scanUpload(scan scanFunc) (UploadMeta, error) {
+	var m UploadMeta
+	var uploadedAt int64
+	if err := scan(&m.FileID, &m.Name, &m.Size, &m.SHA256, &uploadedAt); err != nil {
+		return UploadMeta{}, err
+	}
+	m.UploadedAt = time.Unix(0, uploadedAt)
+	return m, nil
+}
@@ -0,0 +1,162 @@
+package storage
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"testing"
+	"time"
+)
+
+func newUploadRepo(t *testing.T) *UploadRepo {
+	t.Helper()
+	db, err := Open(":memory:")
+	if err != nil {
+		t.Fatalf("Open in-memory db: %v", err)
+	}
+	t.Cleanup(func() { _ = db.Close() })
+	return db.Uploads()
+}
+
+func assertUploadEqual(t *testing.T, got, want UploadMeta) {
+	t.Helper()
+	if got.FileID != want.FileID {
+		t.Errorf("FileID: got %q, want %q", got.FileID, want.FileID)
+	}
+	if got.Name != want.Name {
+		t.Errorf("Name: got %q, want %q", got.Name, want.Name)
+	}
+	if got.Size != want.Size {
+		t.Errorf("Size: got %d, want %d", got.Size, want.Size)
+	}
+	if got.SHA256 != want.SHA256 {
+		t.Errorf("SHA256: got %q, want %q", got.SHA256, want.SHA256)
+	}
+	if !got.UploadedAt.Equal(want.UploadedAt) {
+		t.Errorf("UploadedAt: got %v, want %v", got.UploadedAt, want.UploadedAt)
+	}
+}
+
+func TestUploadRepo_CreateGetListDelete(t *testing.T) {
+	repo := newUploadRepo(t)
+	ctx := context.Background()
+	uploadedAt := time.Unix(0, time.Now().UnixNano())
+	want := UploadMeta{
+		FileID:     "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
+		Name:       "report.csv",
+		Size:       42,
+		SHA256:     "deadbeef",
+		UploadedAt: uploadedAt,
+	}
+	if err := repo.Create(ctx, want.FileID, want.Name, want.Size, want.SHA256, want.UploadedAt); err != nil {
+		t.Fatalf("Create: %v", err)
+	}
+	got, err := repo.Get(ctx, want.FileID)
+	if err != nil {
+		t.Fatalf("Get: %v", err)
+	}
+	assertUploadEqual(t, got, want)
+	if err := repo.Create(ctx, want.FileID, "other", 1, "abcd", time.Now()); err == nil {
+		t.Errorf("duplicate Create succeeded, want error")
+	}
+	list, err := repo.List(ctx, "", 100)
+	if err != nil {
+		t.Fatalf("List: %v", err)
+	}
+	if len(list) != 1 {
+		t.Fatalf("List len: got %d, want 1", len(list))
+	}
+	assertUploadEqual(t, list[0], want)
+	if err := repo.Delete(ctx, want.FileID); err != nil {
+		t.Fatalf("Delete: %v", err)
+	}
+	if _, err := repo.Get(ctx, want.FileID); !errors.Is(err, ErrNotFound) {
+		t.Fatalf("Get after Delete: got %v, want ErrNotFound", err)
+	}
+	if err := repo.Delete(ctx, want.FileID); !errors.Is(err, ErrNotFound) {
+		t.Fatalf("Delete again: got %v, want ErrNotFound", err)
+	}
+}
+
+func TestUploadRepo_ListOrderAndSearch(t *testing.T) {
+	repo := newUploadRepo(t)
+	ctx := context.Background()
+	base := time.Unix(0, time.Now().UnixNano())
+	records := []UploadMeta{
+		{FileID: "00000000000000000000000000000001", Name: "alpha.csv", Size: 1, SHA256: "a", UploadedAt: base.Add(-2 * time.Hour)},
+		{FileID: "00000000000000000000000000000002", Name: "beta.log", Size: 2, SHA256: "b", UploadedAt: base.Add(-1 * time.Hour)},
+		{FileID: "00000000000000000000000000000003", Name: "gamma.csv", Size: 3, SHA256: "c", UploadedAt: base},
+	}
+	for _, r := range records {
+		if err := repo.Create(ctx, r.FileID, r.Name, r.Size, r.SHA256, r.UploadedAt); err != nil {
+			t.Fatalf("Create %s: %v", r.FileID, err)
+		}
+	}
+	all, err := repo.List(ctx, "", 100)
+	if err != nil {
+		t.Fatalf("List: %v", err)
+	}
+	if len(all) != 3 {
+		t.Fatalf("List len: got %d, want 3", len(all))
+	}
+	wantOrder := []string{"00000000000000000000000000000003", "00000000000000000000000000000002", "00000000000000000000000000000001"}
+	for i, id := range wantOrder {
+		if all[i].FileID != id {
+			t.Errorf("List order[%d]: got %q, want %q", i, all[i].FileID, id)
+		}
+	}
+	csv, err := repo.List(ctx, "csv", 100)
+	if err != nil {
+		t.Fatalf("List search: %v", err)
+	}
+	if len(csv) != 2 {
+		t.Fatalf("search csv len: got %d, want 2", len(csv))
+	}
+	if csv[0].Name != "gamma.csv" || csv[1].Name != "alpha.csv" {
+		t.Errorf("search csv order: got %v", []string{csv[0].Name, csv[1].Name})
+	}
+	beta, err := repo.List(ctx, "beta", 100)
+	if err != nil {
+		t.Fatalf("List search beta: %v", err)
+	}
+	if len(beta) != 1 || beta[0].Name != "beta.log" {
+		t.Errorf("search beta: got %+v", beta)
+	}
+}
+
+func TestUploadRepo_ListLimitCap(t *testing.T) {
+	repo := newUploadRepo(t)
+	ctx := context.Background()
+	base := time.Unix(0, time.Now().UnixNano())
+	for i := 0; i < 10; i++ {
+		id := fmt.Sprintf("%032d", i)
+		if err := repo.Create(ctx, id, "x", int64(i), "h", base.Add(time.Duration(i)*time.Second)); err != nil {
+			t.Fatalf("Create %d: %v", i, err)
+		}
+	}
+	list, err := repo.List(ctx, "", 0)
+	if err != nil {
+		t.Fatalf("List default limit: %v", err)
+	}
+	// Default limit is 100 but only 10 rows exist.
+	if len(list) != 10 {
+		t.Errorf("default limit: got %d, want 10", len(list))
+	}
+
+	list, err = repo.List(ctx, "", 501)
+	if err != nil {
+		t.Fatalf("List cap: %v", err)
+	}
+	if len(list) != 10 {
+		t.Errorf("cap limit: got %d, want 10", len(list))
+	}
+
+	// Explicit small limit is respected.
+	list, err = repo.List(ctx, "", 3)
+	if err != nil {
+		t.Fatalf("List small limit: %v", err)
+	}
+	if len(list) != 3 {
+		t.Errorf("small limit: got %d, want 3", len(list))
+	}
+}