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._-]*)*`)

// maxEntityReferences caps how many names one utterance may send to Nexus. The
// cap is not about correctness, it is about one turn not fanning out into a
// dozen HTTP calls when the utterance is a paragraph of English.
const maxEntityReferences = 4

// 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
}

// entityReferences returns the names Nexus is asked to resolve, in the order
// they were said.
//
// Normally there is one, and it is the router's Text slot — 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. 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.
//
// What this does NOT do is pick. It used to return the longest run, and length
// is a guess: "перезапусти nginx на muzick-indexer" has two names in it and the
// longer one is not reliably the target. Nexus owns which names it knows
// (docs/ecosystem.md — ambiguous resolution asks the owner, it does not pick),
// so every run goes over and Nexus answers. Two runs that both resolve are a
// clarify, not a coin toss.
func entityReferences(dec router.Decision) []string {
	text := dec.Slots.Text
	if hasLatin(text) || !hasLatin(dec.Utterance) {
		return []string{text}
	}
	var refs []string
	seen := map[string]bool{}
	for _, m := range latinRun.FindAllString(dec.Utterance, -1) {
		m = strings.TrimSpace(m)
		// A single stray letter is not a name.
		if len(m) < 2 {
			continue
		}
		key := strings.ToLower(m)
		if seen[key] {
			continue
		}
		seen[key] = true
		refs = append(refs, m)
		if len(refs) == maxEntityReferences {
			break
		}
	}
	if len(refs) == 0 {
		return []string{text}
	}
	return refs
}