package classes

import (
	"bytes"
	"fmt"
	"regexp"
	"strings"

	"github.com/yuin/goldmark"
	"github.com/yuin/goldmark/extension"
	"github.com/yuin/goldmark/parser"
)

var (
	markdownEngine = goldmark.New(
		goldmark.WithExtensions(extension.Footnote, extension.Table),
		goldmark.WithParserOptions(parser.WithAttribute()),
	)

	markdownUnsafeTag    = regexp.MustCompile(`(?i)<(?:script|iframe|object|embed)\b`)
	markdownEventHandler = regexp.MustCompile(`(?i)\son[a-z]+\s*=`)
	markdownDangerousURL = regexp.MustCompile(`(?i)(?:javascript|vbscript|data):`)
)

// FormatHTML converts journal post markdown to stored HTML using goldmark
// footnote, table, and attribute extensions, then the same rejectUnsafe gate
// as cabana.RenderMarkdown. It does not call cabana.RenderMarkdown.
func FormatHTML(src string) (string, error) {
	var buf bytes.Buffer
	if err := markdownEngine.Convert([]byte(strings.TrimSpace(src)), &buf); err != nil {
		return "", fmt.Errorf("journal: markdown: %w", err)
	}
	html := buf.String()
	if err := rejectUnsafe(html); err != nil {
		return "", err
	}
	return html, nil
}

// CheckHTML applies the FormatHTML safety gate to HTML that is stored as is,
// such as category content. It refuses raw script, iframe, object and embed
// tags, event handler attributes and javascript, vbscript or data URL schemes.
func CheckHTML(html string) error {
	return rejectUnsafe(html)
}

func rejectUnsafe(html string) error {
	if markdownUnsafeTag.MatchString(html) {
		return fmt.Errorf("journal: rendered HTML contains raw unsafe tags")
	}
	if markdownEventHandler.MatchString(html) {
		return fmt.Errorf("journal: rendered HTML contains event handlers")
	}
	if markdownDangerousURL.MatchString(html) {
		return fmt.Errorf("journal: rendered HTML contains a dangerous URL scheme")
	}
	return nil
}