filesystem

type Config struct {
	Extractors []Extractor
	ScanRoot   string
	FS         fs.FS
	// 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 ScanRoot and thus need to be in
	// sub-directories of ScanRoot.
	FilesToExtract []string
	// Optional: Directories that the file system walk should ignore.
	// Note that these are not relative to ScanRoot and thus need to be
	// sub-directories of ScanRoot.
	// 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: 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
}

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

type ScanInput struct {
	// The path of the file to extract, relative to ScanRoot.
	Path string
	// The root directory where the extraction file walking started from.
	ScanRoot 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
	// Stats collector to export stats internally from a plugin.
	Stats stats.Collector
}