bvandeusen
37b396a7e4
dhowden/tag's readTFrame splits ID3v2 null-separated multi-value text frames and rejoins them with the EMPTY string, so a file tagged "Alternative Rock" + "Rock" was stored as "Alternative RockRock". It also leaves bare numeric ID3v1 references unresolved, which is why the library showed genres like "4017" and "526617". This corrupted more than the browse axis added in #367: taste_profile.sql reads tracks.genre directly, so the welded tokens were entering the taste profile's tag vocabulary, and recommendation.sql/discover.sql were comparing them as single opaque tags. Genre counts were wrong everywhere. ffprobe is not a fix — ffmpeg's read_ttag calls decode_str once with no loop, keeping only the first value. Truncating multi-genre tags would blunt the similarity signal genre mainly feeds. So the TCON frame is now parsed directly (ID3v2.2/2.3/2.4, all four text encodings, per-frame and tag-level unsynchronisation, numeric and parenthesised ID3v1 references); everything else still comes from dhowden/tag. Values are stored ";"-delimited, which the read side already splits on, so no query changes. Existing rows are repaired without an operator-run rebuild: migration 0054 adds tracks.tag_read_version DEFAULT 0, below the scanner's current tagReadVersion, so the next scan re-reads tags it would otherwise skip on mtime. Such a re-read reuses the stored duration instead of re-running ffprobe, keeping a repair pass tag-read-bound rather than one fork+exec per file. Bumping the constant is how a future extraction fix reaches an existing library. Only ID3v2 is in scope — dhowden welds nowhere else. The Vorbis/MP4 repeated-field question is #2500, unproven and deliberately not built.
76 lines
2.2 KiB
Go
76 lines
2.2 KiB
Go
package recommendation
|
|
|
|
import (
|
|
"strings"
|
|
|
|
"github.com/jackc/pgx/v5/pgtype"
|
|
|
|
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
|
|
)
|
|
|
|
type SessionVector struct {
|
|
Seed bool `json:"seed"`
|
|
Artists []string `json:"artists"`
|
|
Tags map[string]int `json:"tags"`
|
|
RecentTrackIDs []string `json:"recent_track_ids"`
|
|
// DeviceClass is the current request's device (#1551), set by the radio
|
|
// handler from the user's latest play; drives the device dimension of the
|
|
// context-affinity term. Empty (omitted) for the daily mixes and for the
|
|
// snapshot stored on play_events, so it never narrows those.
|
|
DeviceClass string `json:"device_class,omitempty"`
|
|
}
|
|
|
|
func BuildSessionVector(priorTracks []dbq.Track) SessionVector {
|
|
v := SessionVector{
|
|
Seed: len(priorTracks) < 3,
|
|
Artists: []string{},
|
|
Tags: map[string]int{},
|
|
RecentTrackIDs: []string{},
|
|
}
|
|
seen := map[string]bool{}
|
|
for _, t := range priorTracks {
|
|
artistID := uuidString(t.ArtistID)
|
|
if !seen[artistID] {
|
|
seen[artistID] = true
|
|
v.Artists = append(v.Artists, artistID)
|
|
}
|
|
if t.Genre != nil && *t.Genre != "" {
|
|
for _, g := range splitGenres(*t.Genre) {
|
|
v.Tags[g]++
|
|
}
|
|
}
|
|
v.RecentTrackIDs = append(v.RecentTrackIDs, uuidString(t.ID))
|
|
}
|
|
return v
|
|
}
|
|
|
|
func uuidString(u pgtype.UUID) string {
|
|
if !u.Valid {
|
|
return ""
|
|
}
|
|
return u.String()
|
|
}
|
|
|
|
// splitGenres splits a track's denormalized genre string on the common
|
|
// multi-genre delimiters (`;`, `,`) used by various tag editors. Trims
|
|
// whitespace; drops empty fragments. Strings with no delimiter come back
|
|
// as a single-element slice.
|
|
//
|
|
// This comment used to blame concatenated inputs like
|
|
// "ElectronicComplextroGlitch Hop" on broken tag editors. They were ours: the
|
|
// scanner stored dhowden/tag's welded multi-value frames verbatim. Fixed in
|
|
// #2499 — the scanner now writes ";"-delimited values, so such tokens only
|
|
// survive on rows not yet re-scanned.
|
|
func splitGenres(s string) []string {
|
|
parts := strings.FieldsFunc(s, func(r rune) bool {
|
|
return r == ';' || r == ','
|
|
})
|
|
out := make([]string, 0, len(parts))
|
|
for _, p := range parts {
|
|
if p = strings.TrimSpace(p); p != "" {
|
|
out = append(out, p)
|
|
}
|
|
}
|
|
return out
|
|
}
|