base

type ContentExtractor func(ctx context.Context, r io.Reader) (string, error)

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

type Parser interface {
	// ParseStream reads from an io.Reader and streams parsed Document objects.
	// This ensures O(1) memory complexity for handling massive files (e.g., 2GB logs).
	ParseStream(ctx context.Context, r io.Reader, metadata map[string]any) (<-chan *core.Document, error)

	// GetSupportedTypes returns the file extensions or MIME types this parser supports.
	GetSupportedTypes() []string
}

type Triple struct {
	Subject     string `json:"subject"`
	Predicate   string `json:"predicate"`
	Object      string `json:"object"`
	SubjectType string `json:"subject_type"`
	ObjectType  string `json:"object_type"`
}

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