package main

import (
	"regexp"
	"strings"
	"unicode"

	"github.com/kami/maven/internal/router"
)

// latinRun matches a run of Latin-script words — the shape a service, host or
// project name takes in a Russian sentence. Digits, dot, dash and underscore
// ride along because "muzick-indexer" and "nginx.conf" are one name, not two.
var latinRun = regexp.MustCompile(`[A-Za-z][A-Za-z0-9._-]*(?:\s+[A-Za-z][A-Za-z0-9._-]*)*`)

// hasLatin reports whether s carries a Latin letter.
func hasLatin(s string) bool {
	for _, r := range s {
		if unicode.In(r, unicode.Latin) {
			return true
		}
	}
	return false
}

// entityReferenceText is the name Nexus is asked to resolve.
//
// Normally that is the router's Text slot, which is the verb phrase the model
// wrote. But the resident model rewrites a Russian utterance as it routes, and
// on the way it transliterates: "перезапусти muzick indexer" came back as
// "перезагрузить музик индексер" (Vikunja #476). Nexus is then asked for a
// service nobody has ever named, so the act cannot resolve its target even
// with every gate open.
//
// The recovery is deliberately narrow. Only when the utterance holds a Latin
// run and the model's Text holds none has a name certainly been rewritten —
// then the longest Latin run in his own words is the reference. Anything else
// keeps the Text slot, so an English utterance and a Russian entity name are
// both untouched. Un-transliterating the Cyrillic back is not attempted: the
// surface form he said is right there, and guessing at a reverse mapping would
// invent a second name to be wrong about.
func entityReferenceText(dec router.Decision) string {
	text := dec.Slots.Text
	if hasLatin(text) || !hasLatin(dec.Utterance) {
		return text
	}
	longest := ""
	for _, m := range latinRun.FindAllString(dec.Utterance, -1) {
		if len(m) > len(longest) {
			longest = m
		}
	}
	longest = strings.TrimSpace(longest)
	// A single stray letter is not a name.
	if len(longest) < 2 {
		return text
	}
	return longest
}