filesystem

type Config struct {
	Extractors []Extractor
	ScanRoots  []*scalibrfs.ScanRoot
	// Optional: Individual files to extract inventory from. If specified, the
	// extractors will only look at these files during the filesystem traversal.
	// Note that these are not relative to the ScanRoots and thus need to be
	// sub-directories of one of the ScanRoots.
	PathsToExtract []string
	// Optional: If true, only the files in the top-level directories in PathsToExtract are
	// extracted and sub-directories are ignored.
	IgnoreSubDirs bool
	// Optional: Directories that the file system walk should ignore.
	// Note that these are not relative to the ScanRoots and thus need to be
	// sub-directories of one of the ScanRoots.
	// TODO(b/279413691): Also skip local paths, e.g. "Skip all .git dirs"
	DirsToSkip []string
	// Optional: If the regex matches a directory, it will be skipped.
	SkipDirRegex *regexp.Regexp
	// Optional: If the regex matches a glob, it will be skipped.
	SkipDirGlob glob.Glob
	// Optional: Skip files declared in .gitignore files in source repos.
	UseGitignore bool
	// Optional: stats allows to enter a metric hook. If left nil, no metrics will be recorded.
	Stats stats.Collector
	// Optional: Whether to read symlinks.
	ReadSymlinks bool
	// Optional: Limit for visited inodes. If 0, no limit is applied.
	MaxInodes int
	// Optional: Files larger than this size in bytes are skipped. If 0, no limit is applied.
	MaxFileSize int
	// Optional: By default, inventories stores a path relative to the scan root. If StoreAbsolutePath
	// is set, the absolute path is stored instead.
	StoreAbsolutePath bool
	// Optional: If true, print a detailed analysis of the duration of each extractor.
	PrintDurationAnalysis bool
	// Optional: If true, fail the scan if any permission errors are encountered.
	ErrorOnFSErrors bool
}

type Extractor interface {
	extractor.Extractor
	// FileRequired should return true if the file described by path and file info is
	// relevant for the extractor.
	// Note that the plugin doesn't traverse the filesystem itself but relies on the core
	// library for that.
	FileRequired(api FileAPI) bool
	// Extract extracts inventory data relevant for the extractor from a given file.
	Extract(ctx context.Context, input *ScanInput) (inventory.Inventory, error)
}

type FileAPI interface {
	// Stat returns the file info for the file.
	Stat() (fs.FileInfo, error)
	Path() string
}

type ScanInput struct {
	// FS for file access. This is rooted at Root.
	FS scalibrfs.FS
	// The path of the file to extract, relative to Root.
	Path string
	// The root directory where the extraction file walking started from.
	Root string
	Info fs.FileInfo
	// A reader for accessing contents of the file.
	// Note that the file is closed by the core library, not the plugin.
	Reader io.Reader
}