package services

import "strings"

// Smart genre selection for sidecar/embedded metadata (A2c plan §2.5).
//
// Sources arrive as comma-blobs ("Epic, Action & Adventure, Military,
// Sword & Sorcery" — one Audible genre string), media-format noise
// ("Audiobook"), or maximally generic tags ("Fiction"). This is a
// deterministic ranked rule set — no network, no guessing service:
//
//  1. split candidate strings on , ; /
//  2. alias-map to canonical genres
//  3. discard demoted (format/edition) tokens — they never win
//  4. most specific (longest) canonical hit wins; "Fiction" is last resort
//  5. every candidate (split parts included) still lands in tags, so
//     filtering keeps full coverage even when the genre column holds one

var genreAliases = map[string]string{
	"sci-fi": "science fiction", "scifi": "science fiction", "sf": "science fiction",
	"sff": "science fiction", "sci fi": "science fiction",
	"speculative fiction": "science fiction",
	" detectives":         "mystery", "detective": "mystery",
	"whodunnit": "mystery", "whodunit": "mystery",
	"adventure fiction":    "action & adventure",
	"action and adventure": "action & adventure",
	"ya":                   "young adult",
	"mg":                   "middle grade",
	"graphic novel":        "graphic novels",
	"coming of age":        "coming of age",
	"coming-of-age":        "coming of age",
	"histfiction":          "historical fiction",
	"epic":                 "epic fantasy",
	"high fantasy":         "epic fantasy",
	"military scifi":       "military science fiction",
	"military sf":          "military science fiction",
	"space opera":          "space opera",
	"post apocalyptic":     "post-apocalyptic",
	"self help":            "self-help",
	"sci_fi":               "science fiction",
}

// canonicalGenres is the known-genre set (lowercase). A candidate that
// normalizes to one of these wins the `genre` column; longest match beats
// shorter (Sword & Sorcery > Fiction).
var canonicalGenres = map[string]bool{
	"fiction": true, "nonfiction": true, "literary fiction": true,
	"classics": true, "poetry": true, "short stories": true,
	"anthology": true, "coming of age": true, "satire": true, "humor": true,
	"fantasy": true, "epic fantasy": true, "sword & sorcery": true,
	"dark fantasy": true, "urban fantasy": true, "paranormal": true,
	"paranormal romance": true, "high fantasy": true, "fairy tales": true,
	"mythology": true, "folklore": true,
	"science fiction": true, "space opera": true, "cyberpunk": true,
	"military science fiction": true, "dystopian": true,
	"post-apocalyptic": true, "apocalyptic": true, "time travel": true,
	"alternate history": true, "first contact": true, "steampunk": true,
	"litrpg": true, "progression fantasy": true,
	"historical fiction": true, "alternate world": true,
	"romance": true, "contemporary romance": true, "historical romance": true,
	"mystery": true, "cozy mystery": true, "crime": true, "true crime": true,
	"police procedural": true, "noir": true, "hardboiled": true,
	"thriller": true, "suspense": true, "espionage": true, "horror": true,
	"gothic": true, "supernatural": true,
	"action & adventure": true, "adventure": true, "western": true,
	"military": true, "war": true,
	"biography": true, "autobiography": true, "memoir": true,
	"history": true, "science": true, "philosophy": true,
	"psychology": true, "self-help": true, "business": true,
	"economics": true, "politics": true, "religion": true,
	"spirituality": true, "travel": true, "cooking": true, "food": true,
	"health": true, "fitness": true, "sports": true, "music": true,
	"art": true, "photography": true, "education": true, "reference": true,
	"young adult": true, "middle grade": true, "children's": true,
	"comics": true, "graphic novels": true, "manga": true,
	"legal": true, "medical": true,
}

// genreDemoted never wins the genre column — media formats and editions,
// not genres. They still pass through to tags.
var genreDemoted = map[string]bool{
	"audiobook": true, "unabridged": true, "abridged": true,
	"dramatization": true, "dramatized": true, "audio drama": true,
}

// splitGenreCandidates splits compound genre strings ("Epic, Action &
// Adventure" — one Audible blob) into individual candidates.
func splitGenreCandidates(genres []string) []string {
	var out []string
	for _, g := range genres {
		for _, part := range strings.Split(g, ",") {
			for _, p := range strings.Split(part, ";") {
				for _, piece := range strings.Split(p, "/") {
					t := strings.TrimSpace(piece)
					if t != "" {
						out = append(out, t)
					}
				}
			}
		}
	}
	return out
}

// pickSmartGenre chooses the best genre from candidate strings. Returns the
// winner ("" when there are no candidates) and the full candidate list for
// the tags array.
func pickSmartGenre(genres []string) (genre string, all []string) {
	all = splitGenreCandidates(genres)
	best := ""
	bestLen := -1
	for _, c := range all {
		lower := strings.ToLower(strings.TrimSpace(c))
		if lower == "" || genreDemoted[lower] {
			continue
		}
		if genreAliases[lower] != "" {
			lower = genreAliases[lower]
		}
		if !canonicalGenres[lower] {
			continue
		}
		// Specificity: the longest canonical form wins; earlier candidates
		// win ties (source order is provider significance).
		if len(lower) > bestLen {
			best = lower
			bestLen = len(lower)
		}
	}
	if best != "" {
		return best, all
	}
	// No lexicon hit: fall back to the first non-demoted candidate verbatim
	// (display honesty over false taxonomy), "" when only noise existed.
	for _, c := range all {
		lower := strings.ToLower(strings.TrimSpace(c))
		if lower != "" && !genreDemoted[lower] {
			return strings.TrimSpace(c), all
		}
	}
	return "", all
}