// Package textutil holds small text helpers shared across the ingestion
// service.
package textutil

import "unicode/utf8"

// Ellipsis marks a value that was cut short.
const Ellipsis = "…"

// Truncate shortens s to at most limit CHARACTERS, appending an ellipsis when
// anything was dropped.
//
// It exists because four call sites did `s[:limit] + "…"` (#93). Both halves
// of that are byte operations: len() counts bytes and a slice cuts bytes, so
// on Swedish text — where å ä ö are two bytes and an em dash is three — the
// cut lands mid-character and leaves an orphaned lead byte. The result is
// invalid UTF-8.
//
// That failed loudly in exactly one place, wiki/index.md, which is written
// raw to disk and then rejected by every strict decoder. The other three fed
// MCP responses, where encoding/json silently substitutes U+FFFD — so those
// had been quietly eating the last character of truncated excerpts with no
// error anywhere.
//
// The marker is appended only when content was actually dropped: an ellipsis
// on complete text is a lie about the content.
func Truncate(s string, limit int) string {
	if limit <= 0 {
		return ""
	}
	if utf8.RuneCountInString(s) <= limit {
		return s
	}

	// Walk runes rather than converting to []rune: the input can be a whole
	// note body, and this runs on the read path.
	count := 0
	for i := range s {
		if count == limit {
			return s[:i] + Ellipsis
		}
		count++
	}
	return s + Ellipsis
}