// Package detector wraps the body-language detection used by the
// diplomail subsystem. The package exposes a narrow `LanguageDetector`
// interface so the implementation can be swapped without touching the
// callers; the default backed-by-whatlanggo detector handles 84
// natural languages and ships with the embedded statistical profiles.
//
// Detection happens only on the body. Subjects are short and
// frequently template-like ("Re: ..."), so detecting on them adds
// noise. The diplomail Service feeds the body, captures the BCP 47
// tag returned here, and stores it in `diplomail_messages.body_lang`.
package detector

import (
	"strings"
	"unicode/utf8"

	"github.com/abadojack/whatlanggo"
)

// Undetermined is the BCP 47 placeholder stored when detection cannot
// confidently identify a language (empty body, too-short body, mixed
// scripts the detector refuses to bet on).
const Undetermined = "und"

// LanguageDetector is the read-only surface diplomail consumes when
// it needs to label a message body. Detect must never panic and
// must never return an error: detection failure simply yields
// `Undetermined`.
type LanguageDetector interface {
	Detect(body string) string
}

// New returns the package-default detector backed by `whatlanggo`.
// The instance is safe for concurrent use; whatlanggo's `Detect`
// reads the embedded profiles without state mutation. Callers that
// want a fixed allow-list can build their own implementation around
// the same interface.
func New() LanguageDetector {
	return &whatlangDetector{}
}

type whatlangDetector struct{}

// minRunes is the lower bound on body length below which whatlanggo
// can flip between near-synonyms; for shorter bodies we return
// `Undetermined` and let the noop translator skip the slot. The
// value matches whatlanggo's documented "stable above ~25 runes"
// guidance.
const minRunes = 25

// Detect returns the BCP 47 tag for body, or `Undetermined` when the
// body is empty / too short / whatlanggo refuses to label it. The
// trim is applied so leading whitespace does not bias the script
// detector toward Latin. We deliberately do not gate on
// `info.IsReliable()` because the gate is too conservative for the
// short sentences typical of in-game mail; a misclassification only
// hurts the translation cache key, never correctness.
func (d *whatlangDetector) Detect(body string) string {
	body = strings.TrimSpace(body)
	if body == "" {
		return Undetermined
	}
	if utf8.RuneCountInString(body) < minRunes {
		return Undetermined
	}
	info := whatlanggo.Detect(body)
	tag := info.Lang.Iso6391()
	if tag == "" {
		return Undetermined
	}
	return tag
}

// NoopDetector returns the placeholder unconditionally. Used by
// tests and by Stage A code paths that predate the real detector.
type NoopDetector struct{}

// Detect always returns `Undetermined` regardless of input.
func (NoopDetector) Detect(string) string { return Undetermined }