sync

type Crawler struct {
	// contains filtered or unexported fields
}

type CrawlerOption func(*Crawler)

type FileManifest struct {
	FileID       string    `json:"file_id"`
	ParentPageID string    `json:"parent_page_id"`
	DownloadedAt time.Time `json:"downloaded_at"`
}

type FileRegistry struct {
	ID         string    `json:"id"`         // File ID extracted from S3 URL
	FilePath   string    `json:"file_path"`  // Local file path (directory + name)
	SourceURL  string    `json:"source_url"` // Original S3 URL
	LastSynced time.Time `json:"last_synced"`
}

type FolderInfo struct {
	Name          string
	RootPages     int
	TotalPages    int
	OrphanedPages int
	Pages         []*PageInfo
}

type FolderStatus struct {
	Name        string
	PageCount   int
	RootPages   int
	LastSynced  *time.Time
	QueuedPages int
}

type PageInfo struct {
	ID         string
	Title      string
	Path       string
	LastSynced time.Time
	IsRoot     bool
	IsOrphaned bool
	ParentID   string
	Children   []*PageInfo
}

type PageRegistry struct {
	ID          string    `json:"id"`
	Type        string    `json:"type"` // "page" or "database"
	Folder      string    `json:"folder"`
	FilePath    string    `json:"file_path"`
	Title       string    `json:"title"`
	LastEdited  time.Time `json:"last_edited"`
	LastSynced  time.Time `json:"last_synced"`
	IsRoot      bool      `json:"is_root"`
	ParentID    string    `json:"parent_id,omitempty"`
	Children    []string  `json:"children,omitempty"`
	ContentHash string    `json:"content_hash,omitempty"`
}

type PullOptions struct {
	Folder   string        // Filter to specific folder (empty = all folders)
	Since    time.Duration // Override for cutoff time (0 = use LastPullTime)
	MaxPages int           // Maximum number of pages to queue (0 = unlimited)
	All      bool          // Include pages not yet tracked
	DryRun   bool          // Preview without modifying
	Verbose  bool          // Show detailed output
}

type PullResult struct {
	PagesFound   int
	PagesQueued  int
	PagesSkipped int
	NewPages     int
	UpdatedPages int
	CutoffTime   time.Time
}

type QueueCallback func() error

type QueueInfo struct {
	Folder    string
	Type      string
	PageCount int
	QueueFile string
}

type State struct {
	Version          int        `json:"version"`
	Folders          []string   `json:"folders"`
	LastPullTime     *time.Time `json:"last_pull_time,omitempty"`
	OldestPullResult *time.Time `json:"oldest_pull_result,omitempty"` // Oldest page seen in last pull
}

type StatusInfo struct {
	FolderCount    int
	TotalPages     int
	TotalRootPages int
	QueueEntries   []*QueueInfo
	Folders        map[string]*FolderStatus
}