Levyraati26_go/lyrics.go

package main

import (
	"context"
	"encoding/json"
	"fmt"
	"io"
	"log/slog"
	"net/http"
	"net/url"
	"regexp"
	"sort"
	"strconv"
	"strings"
	"time"
)

// LRCLIB is a community lyrics database with no API key. It is treated exactly like ffmpeg and
// yt-dlp: an outside thing with a timeout, allowed to fail, never blocking anything.
// A var rather than a const so tests can point it at a local server instead of the real service.
var lrclibBase = "https://lrclib.net/api"

const (
	// Identifies the client and nothing else. No URL, no host, no version: this app is private,
	// and a third party's logs are not the place to learn where it lives.
	lrclibAgent  = "levyraati"
	lyricsTimout = 10 * time.Second
)

type lrclibResult struct {
	TrackName    string  `json:"trackName"`
	ArtistName   string  `json:"artistName"`
	Duration     float64 `json:"duration"`
	Instrumental bool    `json:"instrumental"`
	PlainLyrics  string  `json:"plainLyrics"`
	SyncedLyrics string  `json:"syncedLyrics"`
}

// best returns the synced version when there is one — timestamps are what make the scroll possible
// later, and plain text is the fallback rather than the goal.
func (r lrclibResult) best() string {
	if r.SyncedLyrics != "" {
		return r.SyncedLyrics
	}
	return r.PlainLyrics
}

var lyricsClient = &http.Client{Timeout: lyricsTimout}

// LRC timestamps are stored, because the highlight needs them, and stripped for reading, because
// nobody wants to read [00:11.74] at the start of every line.
var lrcStamp = regexp.MustCompile(`^(\[\d{1,2}:\d{2}(?:[.:]\d{1,3})?\]\s*)+`)

// A line of synced lyrics: the seconds it starts at, and the words.
type lyricLine struct {
	At   float64
	Text string
}

var lrcOne = regexp.MustCompile(`\[(\d{1,2}):(\d{2})(?:[.:](\d{1,3}))?\]`)

// parseLRC returns nil for plain text, which is the signal to scroll continuously instead of
// highlighting: a line-by-line highlight on guessed timings makes every second of drift read as a
// bug.
func parseLRC(s string) []lyricLine {
	if !strings.HasPrefix(strings.TrimSpace(s), "[") {
		return nil
	}
	var out []lyricLine
	for _, raw := range strings.Split(s, "\n") {
		stamps := lrcOne.FindAllStringSubmatch(raw, -1)
		if len(stamps) == 0 {
			continue
		}
		text := strings.TrimSpace(lrcStamp.ReplaceAllString(raw, ""))
		// One line can carry several timestamps when a refrain repeats.
		for _, m := range stamps {
			min, _ := strconv.Atoi(m[1])
			sec, _ := strconv.Atoi(m[2])
			at := float64(min*60 + sec)
			if m[3] != "" {
				frac, _ := strconv.Atoi(m[3])
				switch len(m[3]) {
				case 1:
					at += float64(frac) / 10
				case 2:
					at += float64(frac) / 100
				default:
					at += float64(frac) / 1000
				}
			}
			out = append(out, lyricLine{At: at, Text: text})
		}
	}
	sort.Slice(out, func(i, j int) bool { return out[i].At < out[j].At })
	return out
}

func stripLRC(s string) string {
	if !strings.HasPrefix(strings.TrimSpace(s), "[") {
		return s
	}
	lines := strings.Split(s, "\n")
	for i, line := range lines {
		lines[i] = strings.TrimRight(lrcStamp.ReplaceAllString(line, ""), " ")
	}
	return strings.Join(lines, "\n")
}

func lrclibGet(ctx context.Context, path string, q url.Values) ([]byte, error) {
	ctx, cancel := context.WithTimeout(ctx, lyricsTimout)
	defer cancel()

	req, err := http.NewRequestWithContext(ctx, "GET", lrclibBase+path+"?"+q.Encode(), nil)
	if err != nil {
		return nil, err
	}
	req.Header.Set("User-Agent", lrclibAgent)
	resp, err := lyricsClient.Do(req)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()
	if resp.StatusCode != http.StatusOK {
		return nil, fmt.Errorf("lrclib %s: %s", path, resp.Status)
	}
	return io.ReadAll(io.LimitReader(resp.Body, 1<<20))
}

// fetchLyrics tries the exact match first — artist, track and duration within LRCLIB's ±2 s — and
// falls back to a search, which is what saves songs whose tags are close but not exact. Returns an
// empty string when nothing matches, which is a normal outcome rather than an error.
func fetchLyrics(ctx context.Context, title, artist string, seconds int) (string, error) {
	title, artist = strings.TrimSpace(title), strings.TrimSpace(artist)
	if title == "" {
		return "", nil // nothing to match on; the submitter has not named it yet
	}

	if artist != "" && seconds > 0 {
		body, err := lrclibGet(ctx, "/get", url.Values{
			"track_name":  {title},
			"artist_name": {artist},
			"duration":    {fmt.Sprint(seconds)},
		})
		if err == nil {
			var res lrclibResult
			if json.Unmarshal(body, &res) == nil && !res.Instrumental {
				if l := res.best(); l != "" {
					return l, nil
				}
			}
		}
	}

	// Looser: let LRCLIB do the matching on a free-text query.
	q := title
	if artist != "" {
		q = artist + " " + title
	}
	body, err := lrclibGet(ctx, "/search", url.Values{"q": {q}})
	if err != nil {
		return "", err
	}
	var results []lrclibResult
	if err := json.Unmarshal(body, &results); err != nil {
		return "", err
	}
	for _, res := range results {
		if res.Instrumental {
			continue
		}
		// A duration within 5 s is the strongest signal we have that it is the same recording.
		if seconds > 0 && res.Duration > 0 && abs(int(res.Duration)-seconds) > 5 {
			continue
		}
		if l := res.best(); l != "" {
			return l, nil
		}
	}
	return "", nil
}

func abs(n int) int {
	if n < 0 {
		return -n
	}
	return n
}

// --- the button on the waiting page ---

// Suggests lyrics for whatever title and artist are currently typed, and never overwrites what the
// submitter has already put in the field — the response fills the textarea, and they can accept it,
// edit it or clear it.
func (a *app) suggestLyrics(w http.ResponseWriter, r *http.Request) {
	s := a.loadSubmission(w, r)
	if s == nil {
		return
	}
	title := clean(r.FormValue("title"), maxTitle)
	artist := clean(r.FormValue("artist"), maxArtist)
	if title == "" {
		title, artist = s.Title, s.Artist
	}

	seconds := 0
	if meta, err := probe(r.Context(), s.TmpPath); err == nil {
		seconds = int(meta.Duration.Seconds())
	}

	lyrics, err := fetchLyrics(r.Context(), title, artist, seconds)
	if err != nil {
		slog.Warn("lyrics lookup", "ctx", "submissions", "error", err, "submission", s.ID)
	}

	// Keep whatever the submitter already typed: a suggestion never overwrites their own words.
	if existing := cleanLyrics(r.FormValue("lyrics")); existing != "" {
		lyrics = existing
	}

	w.Header().Set("Content-Type", "text/html; charset=utf-8")
	data := map[string]any{
		"ID": s.ID, "Lyrics": lyrics, "Found": lyrics != "", "Searched": true,
	}
	if err := pages["submission.html"].ExecuteTemplate(w, "lyricsfield", data); err != nil {
		slog.Error("render lyrics field", "ctx", "submissions", "error", err)
	}
}

// Called from the conversion worker: one automatic attempt, best effort, and only when the
// submitter has not already pasted something.
func (a *app) autoFetchLyrics(ctx context.Context, subID int64, title, artist string, seconds int) {
	if title == "" {
		return
	}
	lyrics, err := fetchLyrics(ctx, title, artist, seconds)
	if err != nil {
		slog.Warn("lyrics lookup", "ctx", "submissions", "error", err, "submission", subID)
		return
	}
	if lyrics == "" {
		return
	}
	tag, err := a.pool.Exec(ctx,
		`update submissions set lyrics = $2 where id = $1 and lyrics is null`,
		subID, cleanLyrics(lyrics))
	if err != nil {
		slog.Error("save lyrics", "ctx", "submissions", "error", err, "submission", subID)
		return
	}
	if tag.RowsAffected() > 0 {
		slog.Info("lyrics found", "ctx", "submissions", "submission", subID)
	}
}