Files
streamrip-go/internal/provider/soundcloud/client.go
T
JorenandClaude Opus 5 201aa5daa7 fix: database migration, config validation and provider client defects
Completes the correctness pass.

Download database migration no longer destroys dedupe state
  The pre-source-column migration carried every legacy row over with
  source='' and then dropped downloads_legacy, while IsDownloaded matched
  source exactly. The result was that every previously recorded download
  looked new, the user silently re-downloaded their whole library, and the
  original rows were gone. Now the file is copied to <path>.bak-<unixtime>
  first, downloads_legacy is kept, and IsDownloaded falls back to the
  sourceless rows (over-matching across sources costs a skipped re-download,
  which is the cheaper error). Schema state is tracked in PRAGMA user_version
  so later migrations can be ordered explicitly. Databases already migrated by
  the old code are detected on open.

  Also enables WAL and a 10s busy_timeout and caps the pool at one connection,
  so a concurrent reader no longer gets SQLITE_BUSY with no retry, and builds
  the DSN through url.URL so a path containing '?' is not parsed as query
  parameters.

--quality now applies to every source
  applyGlobalConfigOverrides set only qobuz, tidal, deezer and soundcloud, so
  `rip -q 4 url <beatport-url>` was a silent no-op even though
  qualityForSource reads Yandex and Beatport. All six are set, with the
  per-source floor applied and reported rather than silently ignored.

config: validation and a fixed reset
  Load checked nothing but misc.version, so a negative max_connections or a
  bogus conversion codec was accepted and only surfaced mid-rip. Adds
  Validate() covering per-source quality ranges, max_connections,
  requests_per_minute and truncate_to, and normalizes the conversion codec
  from the file through the same path as --codec. `config reset` assigned one
  value to both Config.File and Config.Session, so their Secrets slices shared
  a backing array; it now takes separate copies.

  Tests cover the shipped defaults and config.toml.example, which is how the
  over-strict artwork max-width bound in the first draft was caught: -1 is the
  documented "do not downscale" sentinel.

soundcloud: use the shared HTTP client
  It was the only provider constructing its own http.Client, so it silently
  ignored downloads.verify_ssl and max_connections and bypassed the transport
  that redacts credentials from -vv logs. It also had no rate limiter at all.

qobuz: mobile fallback could not download a long track
  http.Client.Timeout bounds the whole request including the body read, so the
  30s API client aborted any track that took longer than 30s to stream. The
  body copy now uses a no-timeout client, as internal/download already does.

qobuz: HKDF no longer fails silently
  hexDecodeOrNil discarded its error, so a non-hex app secret keyed HKDF on
  nil, derived a wrong KEK and produced silently corrupt audio instead of an
  error.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-10-03 16:58:59 +02:00

544 lines
16 KiB
Go

package soundcloud
import (
"context"
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"net/url"
"os/exec"
"regexp"
"strings"
"sync"
"time"
"streamrip-go/internal/config"
"streamrip-go/internal/jsonutil"
"streamrip-go/internal/netutil"
"streamrip-go/internal/provider"
"streamrip-go/internal/ratelimit"
)
var errUnsupportedMediaType = errors.New("unsupported soundcloud media type")
var soundcloudSearchBaseURL = "https://soundcloud.com"
type commandRunner func(ctx context.Context, name string, args ...string) ([]byte, error)
type Client struct {
cfg *config.Config
bin string
run commandRunner
http *http.Client
limiter *ratelimit.Limiter
mu sync.Mutex
cache map[string]map[string]any
// authMu guards loggedIn. Kept separate from mu, which guards cache, so a
// cache operation can never block a login check.
authMu sync.Mutex
loggedIn bool
}
func New(cfg *config.Config) *Client {
return &Client{
cfg: cfg,
bin: "yt-dlp",
run: runCommand,
// Use the shared constructor like every other provider: rolling our own
// client here meant soundcloud silently ignored downloads.verify_ssl and
// downloads.max_connections, and bypassed the transport that logs
// requests at -vv with credentials redacted.
http: netutil.NewHTTPClient(20*time.Second, cfg.Session.Downloads.VerifySSL, cfg.Session.Downloads.MaxConnections),
limiter: ratelimit.New(cfg.Session.Downloads.RequestsPerMinute),
cache: map[string]map[string]any{},
}
}
func (c *Client) Source() string {
return "soundcloud"
}
func (c *Client) LoggedIn() bool {
c.authMu.Lock()
defer c.authMu.Unlock()
return c.loggedIn
}
func (c *Client) Login(context.Context) error {
if _, err := exec.LookPath(c.bin); err != nil {
return fmt.Errorf("yt-dlp is required for soundcloud downloads/search. install it and ensure it is in $PATH (e.g. pipx install yt-dlp): %w", err)
}
c.authMu.Lock()
defer c.authMu.Unlock()
c.loggedIn = true
return nil
}
func (c *Client) Search(ctx context.Context, mediaType, query string, limit int) ([]map[string]any, error) {
if !c.LoggedIn() {
return nil, errors.New("soundcloud client not logged in")
}
if limit <= 0 {
limit = 20
}
if mediaType == "track" {
return c.searchTracks(ctx, query, limit)
}
if mediaType == "playlist" {
return c.searchPlaylists(ctx, query, limit)
}
return nil, fmt.Errorf("%w: %s", errUnsupportedMediaType, mediaType)
}
func (c *Client) searchTracks(ctx context.Context, query string, limit int) ([]map[string]any, error) {
target := fmt.Sprintf("scsearch%d:%s", limit, query)
b, err := c.run(ctx, c.bin, "-J", "--flat-playlist", "--skip-download", "--no-warnings", target)
if err != nil {
return nil, err
}
root, err := parseJSONMap(b)
if err != nil {
return nil, err
}
entries := asAnySlice(root["entries"])
if len(entries) == 0 {
return []map[string]any{}, nil
}
items := make([]any, 0, len(entries))
for _, e := range entries {
m, ok := e.(map[string]any)
if !ok {
continue
}
id := canonicalSoundcloudURL(m)
if id == "" {
continue
}
artist := strings.TrimSpace(jsonutil.StringFromAny(m["uploader"]))
if artist == "" {
artist = strings.TrimSpace(jsonutil.StringFromAny(m["channel"]))
}
artistID := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(m["uploader_id"]), jsonutil.StringFromAny(m["channel_id"])))
item := map[string]any{
"id": id,
"title": jsonutil.StringFromAny(m["title"]),
"artist": map[string]any{
"name": artist,
},
}
if artistID != "" {
item["artist"] = map[string]any{"name": artist, "id": artistID}
}
if trackID := strings.TrimSpace(jsonutil.StringFromAny(m["id"])); trackID != "" {
item["source_track_id"] = trackID
}
items = append(items, item)
}
return []map[string]any{{"items": items}}, nil
}
func (c *Client) searchPlaylists(ctx context.Context, query string, limit int) ([]map[string]any, error) {
searchURL := strings.TrimSuffix(soundcloudSearchBaseURL, "/") + "/search/sets?q=" + url.QueryEscape(query)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
if err != nil {
return nil, err
}
req.Header.Set("User-Agent", "Mozilla/5.0")
if c.limiter != nil {
if err = c.limiter.Wait(ctx); err != nil {
return nil, err
}
}
resp, err := c.http.Do(req)
if err != nil {
return nil, err
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return nil, fmt.Errorf("soundcloud playlist search failed: status=%d", resp.StatusCode)
}
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, err
}
re := regexp.MustCompile(`/(?:[A-Za-z0-9._-]+)/sets/(?:[A-Za-z0-9._%~-]+)`)
paths := re.FindAllString(string(body), -1)
if len(paths) == 0 {
return []map[string]any{}, nil
}
seen := map[string]struct{}{}
items := make([]any, 0, limit)
for _, path := range paths {
if _, ok := seen[path]; ok {
continue
}
seen[path] = struct{}{}
playlistURL := "https://soundcloud.com" + path
info, infoErr := c.playlistInfo(ctx, playlistURL)
if infoErr != nil {
continue
}
title := strings.TrimSpace(jsonutil.StringFromAny(info["title"]))
if title == "" {
title = strings.Trim(strings.ReplaceAll(path, "/", " "), " ")
}
artist := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(info["uploader"]), jsonutil.StringFromAny(info["channel"])))
artistID := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(info["uploader_id"]), jsonutil.StringFromAny(info["channel_id"])))
trackCount := 0
if entries := asAnySlice(info["entries"]); len(entries) > 0 {
trackCount = len(entries)
}
canonical := jsonutil.FirstNonEmpty(canonicalSoundcloudURL(info), playlistURL)
item := map[string]any{
"id": canonical,
"title": title,
"tracks_count": trackCount,
"artist": map[string]any{"name": artist},
}
if artistID != "" {
item["artist"] = map[string]any{"name": artist, "id": artistID}
}
if pid := strings.TrimSpace(jsonutil.StringFromAny(info["id"])); pid != "" {
item["source_playlist_id"] = pid
}
if thumb := strings.TrimSpace(jsonutil.StringFromAny(info["thumbnail"])); thumb != "" {
item["image"] = soundcloudImageMap(thumb)
}
items = append(items, item)
if len(items) >= limit {
break
}
}
if len(items) == 0 {
return []map[string]any{}, nil
}
return []map[string]any{{"items": items}}, nil
}
func (c *Client) GetMetadata(ctx context.Context, item, mediaType string) (map[string]any, error) {
if !c.LoggedIn() {
return nil, errors.New("soundcloud client not logged in")
}
switch mediaType {
case "track":
info, err := c.trackInfo(ctx, item)
if err != nil {
return nil, err
}
return trackMetadataFromInfo(item, info), nil
case "playlist":
root, err := c.playlistInfo(ctx, item)
if err != nil {
return nil, err
}
tracks := make([]any, 0)
for i, raw := range asAnySlice(root["entries"]) {
entry, ok := raw.(map[string]any)
if !ok {
continue
}
id := canonicalSoundcloudURL(entry)
if id == "" {
continue
}
track := map[string]any{"id": id}
if trackID := strings.TrimSpace(jsonutil.StringFromAny(entry["id"])); trackID != "" {
track["source_track_id"] = trackID
}
if title := strings.TrimSpace(jsonutil.StringFromAny(entry["title"])); title != "" {
track["title"] = title
}
if artist := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(entry["uploader"]), jsonutil.StringFromAny(entry["channel"]))); artist != "" {
artistMap := map[string]any{"name": artist}
if artistID := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(entry["uploader_id"]), jsonutil.StringFromAny(entry["channel_id"]))); artistID != "" {
artistMap["id"] = artistID
}
track["artist"] = artistMap
}
track["track_number"] = i + 1
tracks = append(tracks, track)
}
name := strings.TrimSpace(jsonutil.StringFromAny(root["title"]))
if name == "" {
name = "SoundCloud Playlist"
}
meta := map[string]any{
"id": jsonutil.FirstNonEmpty(canonicalSoundcloudURL(root), item),
"name": name,
"description": strings.TrimSpace(jsonutil.StringFromAny(root["description"])),
"tracks": map[string]any{"items": tracks},
}
if pid := strings.TrimSpace(jsonutil.StringFromAny(root["id"])); pid != "" {
meta["source_playlist_id"] = pid
}
if artist := strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(root["uploader"]), jsonutil.StringFromAny(root["channel"]))); artist != "" {
meta["artist"] = map[string]any{"name": artist}
}
if thumb := strings.TrimSpace(jsonutil.StringFromAny(root["thumbnail"])); thumb != "" {
meta["image"] = soundcloudImageMap(thumb)
}
if entries := asAnySlice(root["entries"]); len(entries) > 0 {
meta["tracks_count"] = len(entries)
}
return meta, nil
default:
return nil, fmt.Errorf("%w: %s", errUnsupportedMediaType, mediaType)
}
}
func (c *Client) GetDownloadable(ctx context.Context, item string, _ int) (*provider.Downloadable, error) {
if !c.LoggedIn() {
return nil, errors.New("soundcloud client not logged in")
}
info, err := c.trackInfo(ctx, item)
if err != nil {
return nil, err
}
streamURL := strings.TrimSpace(jsonutil.StringFromAny(info["url"]))
if streamURL == "" {
return nil, errors.New("yt-dlp output missing url (track may be unavailable or region-restricted)")
}
ext := strings.TrimSpace(jsonutil.StringFromAny(info["ext"]))
if ext == "" {
ext = "m4a"
}
return &provider.Downloadable{URL: streamURL, Extension: ext, Source: "soundcloud", Audio: soundcloudAudioProfile(ext)}, nil
}
func (c *Client) Close() error {
return nil
}
func soundcloudAudioProfile(ext string) provider.AudioProfile {
switch strings.ToLower(strings.TrimSpace(ext)) {
case "mp3":
return provider.AudioProfile{Container: "MP3", Codec: "MP3", Quality: "LOSSY", BitDepth: 16, SamplingRate: "44.1"}
case "flac":
return provider.AudioProfile{Container: "FLAC", Codec: "FLAC", Quality: "LOSSLESS", BitDepth: 16, SamplingRate: "44.1"}
case "m4a", "aac":
return provider.AudioProfile{Container: "M4A", Codec: "AAC", Quality: "LOSSY", BitDepth: 16, SamplingRate: "44.1"}
default:
container := strings.ToUpper(strings.TrimSpace(ext))
if container == "" {
container = "M4A"
}
return provider.AudioProfile{Container: container, Codec: container, Quality: "LOSSY", BitDepth: 16, SamplingRate: "44.1"}
}
}
func (c *Client) trackInfo(ctx context.Context, item string) (map[string]any, error) {
if strings.TrimSpace(item) == "" {
return nil, errors.New("empty soundcloud item")
}
c.mu.Lock()
if cached, ok := c.cache[item]; ok {
copied := cloneMap(cached)
c.mu.Unlock()
return copied, nil
}
c.mu.Unlock()
b, err := c.run(ctx, c.bin, "-J", "--no-playlist", "--skip-download", "--no-warnings", item)
if err != nil {
return nil, err
}
info, err := parseJSONMap(b)
if err != nil {
return nil, err
}
canonical := canonicalSoundcloudURL(info)
c.mu.Lock()
c.cache[item] = cloneMap(info)
if canonical != "" {
c.cache[canonical] = cloneMap(info)
}
c.mu.Unlock()
return info, nil
}
func (c *Client) playlistInfo(ctx context.Context, item string) (map[string]any, error) {
b, err := c.run(ctx, c.bin, "-J", "--flat-playlist", "--skip-download", "--no-warnings", item)
if err != nil {
return nil, err
}
return parseJSONMap(b)
}
func trackMetadataFromInfo(id string, info map[string]any) map[string]any {
canonicalID := jsonutil.FirstNonEmpty(canonicalSoundcloudURL(info), id)
publisher := jsonutil.NestedMap(info, "publisher_metadata")
title := strings.TrimSpace(jsonutil.StringFromAny(info["title"]))
if title == "" {
title = canonicalID
}
albumTitle := strings.TrimSpace(jsonutil.StringFromAny(publisher["album_title"]))
if albumTitle == "" {
albumTitle = strings.TrimSpace(jsonutil.StringFromAny(info["album"]))
}
if albumTitle == "" {
albumTitle = title
}
artistName := strings.TrimSpace(jsonutil.StringFromAny(info["artist"]))
if artistName == "" {
artistName = strings.TrimSpace(jsonutil.StringFromAny(publisher["artist"]))
}
if artistName == "" {
artistName = strings.TrimSpace(jsonutil.StringFromAny(info["uploader"]))
}
if artistName == "" {
artistName = strings.TrimSpace(jsonutil.StringFromAny(info["channel"]))
}
artistID := strings.TrimSpace(jsonutil.FirstNonEmpty(
jsonutil.StringFromAny(info["uploader_id"]),
jsonutil.StringFromAny(info["channel_id"]),
jsonutil.StringFromAny(jsonutil.NestedMap(info, "user")["id"]),
))
trackNum := jsonutil.IntFromAny(info["track_number"])
if trackNum <= 0 {
trackNum = 1
}
meta := map[string]any{
"id": canonicalID,
"title": title,
"track_number": trackNum,
"artist": map[string]any{"name": artistName, "id": artistID},
"performer": map[string]any{"name": artistName, "id": artistID},
"album": map[string]any{
"id": jsonutil.FirstNonEmpty(strings.TrimSpace(jsonutil.StringFromAny(info["album"])), canonicalID),
"title": albumTitle,
"artist": map[string]any{"name": artistName, "id": artistID},
},
"description": strings.TrimSpace(jsonutil.StringFromAny(info["description"])),
"genre": strings.TrimSpace(jsonutil.StringFromAny(info["genre"])),
"isrc": strings.TrimSpace(jsonutil.StringFromAny(info["isrc"])),
"label": strings.TrimSpace(jsonutil.FirstNonEmpty(jsonutil.StringFromAny(info["label"]), jsonutil.StringFromAny(info["label_name"]))),
"copyright": strings.TrimSpace(jsonutil.StringFromAny(publisher["p_line"])),
"release_date": strings.TrimSpace(jsonutil.FirstNonEmpty(
jsonutil.StringFromAny(info["created_at"]),
jsonutil.StringFromAny(info["release_date"]),
jsonutil.StringFromAny(info["upload_date"]),
)),
}
if trackID := strings.TrimSpace(jsonutil.StringFromAny(info["id"])); trackID != "" {
meta["source_track_id"] = trackID
}
if jsonutil.BoolFromAny(publisher["explicit"]) || jsonutil.IntFromAny(info["age_limit"]) >= 18 {
meta["explicit"] = true
}
if meta["release_date"] == "" {
delete(meta, "release_date")
}
if thumb := strings.TrimSpace(jsonutil.StringFromAny(info["thumbnail"])); thumb != "" {
meta["image"] = soundcloudImageMap(thumb)
}
if strings.TrimSpace(jsonutil.StringFromAny(info["album"])) == "" && strings.TrimSpace(jsonutil.StringFromAny(publisher["album_title"])) == "" {
meta["album"] = map[string]any{
"id": canonicalID,
"title": title,
"artist": map[string]any{"name": artistName, "id": artistID},
}
}
if durationSec := jsonutil.IntFromAny(info["duration"]); durationSec > 0 {
meta["duration"] = durationSec
}
return meta
}
func canonicalSoundcloudURL(info map[string]any) string {
for _, key := range []string{"webpage_url", "original_url", "url"} {
raw := strings.TrimSpace(jsonutil.StringFromAny(info[key]))
if raw == "" {
continue
}
u, err := url.Parse(raw)
if err != nil {
continue
}
host := strings.ToLower(strings.TrimPrefix(u.Host, "www."))
if host != "soundcloud.com" && !strings.HasSuffix(host, ".soundcloud.com") {
continue
}
u.Scheme = "https"
u.Host = "soundcloud.com"
u.RawQuery = ""
u.Fragment = ""
u.Path = strings.TrimSuffix(u.Path, "/")
if strings.TrimSpace(u.Path) == "" {
continue
}
return u.String()
}
return ""
}
func parseJSONMap(b []byte) (map[string]any, error) {
var out map[string]any
if err := json.Unmarshal(b, &out); err != nil {
return nil, err
}
if out == nil {
return nil, errors.New("empty json payload")
}
return out, nil
}
func cloneMap(in map[string]any) map[string]any {
out := make(map[string]any, len(in))
for k, v := range in {
out[k] = v
}
return out
}
func asAnySlice(v any) []any {
items, ok := v.([]any)
if !ok {
return nil
}
return items
}
func soundcloudImageMap(raw string) map[string]any {
base := strings.TrimSpace(raw)
if base == "" {
return map[string]any{}
}
large := strings.Replace(base, "-large.", "-t500x500.", 1)
if large == base {
large = strings.Replace(base, "large", "t500x500", 1)
}
return map[string]any{
"small": base,
"large": large,
"extralarge": large,
"original": large,
}
}
func runCommand(ctx context.Context, name string, args ...string) ([]byte, error) {
cmd := exec.CommandContext(ctx, name, args...)
b, err := cmd.CombinedOutput()
if err != nil {
return nil, fmt.Errorf("command %s failed: %w: %s", name, err, string(b))
}
return b, nil
}