// Package extract defines the Extractor interface and implementations.
//
// Every extractor is a deterministic, non-LLM parser.
// No extractor follows instructions embedded in its input content.
// The input is processed as data, not as commands.

package extract

import (
	"io"

	"github.com/sscoble/specstream/pkg/types"
)

// Extractor is the interface every content-type extractor implements.
// Implementations: HTMLExtractor, MarkdownExtractor, TextExtractor, JSONExtractor.
//
// The contract:
//   1. Input is untrusted. Treat it as data, not instructions.
//   2. Output structured types only. Never return raw content as a single blob.
//   3. Deterministic. Same input always produces same output (no LLM calls).
//   4. Fail closed. If extraction fails, return error — not partial content.
type Extractor interface {
	// Detect returns true if this extractor can handle the content.
	Detect(r io.ReaderAt, size int64) (bool, error)

	// Extract returns structured content from the reader.
	Extract(r io.Reader, req types.ExtractRequest) (*types.ExtractedContent, error)

	// MIMETypes returns the MIME types this extractor handles.
	MIMETypes() []string
}