fuj-management/go/internal/domain/matching/name_variants.go

package matching

import (
	"fuj-management/go/internal/domain/czech"
	"regexp"
	"strings"
)

var (
	nicknameRe      = regexp.MustCompile(`\(([^)]+)\)`)
	nicknameStripRe = regexp.MustCompile(`\s*\([^)]*\)\s*`)
)

// BuildNameVariants returns searchable lowercase ASCII variants of a member name.
//
// Example: "František Vrbík (Štrúdl)" → ["frantisek vrbik", "strudl", "vrbik", "frantisek"]
//
// variants[0] is always the full normalized base name (no nickname). MatchMembers relies on
// this invariant for the exact short-circuit pass. Variants shorter than 3 characters are
// dropped.
//
// Ports legacy/scripts/match_payments.py _build_name_variants.
func BuildNameVariants(name string) []string {
	var nickname string
	if m := nicknameRe.FindStringSubmatch(name); m != nil {
		nickname = m[1]
	}

	base := strings.TrimSpace(nicknameStripRe.ReplaceAllString(name, " "))
	normalizedBase := czech.Normalize(base)
	normalizedNick := czech.Normalize(nickname)

	variants := []string{normalizedBase}
	if normalizedNick != "" {
		variants = append(variants, normalizedNick)
	}

	parts := strings.Fields(normalizedBase)
	if len(parts) >= 2 {
		variants = append(variants, parts[len(parts)-1]) // last name
		variants = append(variants, parts[0])            // first name
	}

	filtered := variants[:0]
	for _, v := range variants {
		if len(v) >= 3 {
			filtered = append(filtered, v)
		}
	}
	return filtered
}

// wordIn returns true if needle appears as a whole word in haystack.
// Both needle and haystack must already be ASCII-folded (via czech.Normalize).
func wordIn(needle, haystack string) bool {
	pattern := `\b` + regexp.QuoteMeta(needle) + `\b`
	matched, _ := regexp.MatchString(pattern, haystack)
	return matched
}