Files
minstrel/internal/library/mbids_test.go
T
bvandeusen cc12ab7e96 fix(server/m7-382): strip NUL bytes from MBIDs before persist
Follow-up to 947f944. With the dhowden/tag/mbz extractor now correctly
matching ID3v2 TXXX frames, mbid backfill started rejecting every row
with "invalid byte sequence for encoding UTF8: 0x00 (SQLSTATE 22021)".

Cause: dhowden's readTextWithDescrFrame (id3v2frames.go:454) — the path
that decodes TXXX text — does NOT strip the trailing/embedded NUL bytes
that ID3v2.4 uses as frame terminator and multi-value separator. Unlike
readTFrame, which does (line 313). So a TXXX:MusicBrainz Album Id of
"abc-123\x00" comes back to us verbatim, and Postgres refuses to store
NULs in text columns.

cleanMBID splits on NUL and returns the first non-empty segment, which
also handles the multi-value case (collaboration artist IDs are
NUL-separated; Minstrel uses the primary for MBCAA, so first wins).

Tests cover the trailing-NUL, multi-value, and all-NUL paths.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 21:35:01 -04:00

166 lines
5.1 KiB
Go

package library
import (
"testing"
"github.com/dhowden/tag"
)
// stubMeta is a minimal tag.Metadata used to feed the dhowden mbz extractor
// the same Raw()/Format() shape its real parsers produce. The other interface
// methods return zero values — the extractor only branches on Format and
// iterates Raw().
type stubMeta struct {
format tag.Format
raw map[string]interface{}
}
func (s stubMeta) Format() tag.Format { return s.format }
func (s stubMeta) FileType() tag.FileType { return tag.UnknownFileType }
func (s stubMeta) Title() string { return "" }
func (s stubMeta) Album() string { return "" }
func (s stubMeta) Artist() string { return "" }
func (s stubMeta) AlbumArtist() string { return "" }
func (s stubMeta) Composer() string { return "" }
func (s stubMeta) Year() int { return 0 }
func (s stubMeta) Genre() string { return "" }
func (s stubMeta) Track() (int, int) { return 0, 0 }
func (s stubMeta) Disc() (int, int) { return 0, 0 }
func (s stubMeta) Picture() *tag.Picture { return nil }
func (s stubMeta) Lyrics() string { return "" }
func (s stubMeta) Comment() string { return "" }
func (s stubMeta) Raw() map[string]interface{} { return s.raw }
func TestExtractMBIDs_Vorbis(t *testing.T) {
// dhowden lowercases all Vorbis comment keys at parse time.
m := stubMeta{
format: tag.VORBIS,
raw: map[string]interface{}{
"musicbrainz_albumid": "abc",
"musicbrainz_artistid": "def",
},
}
a, ar := extractMBIDs(m)
if a != "abc" || ar != "def" {
t.Errorf("got (%q, %q), want (\"abc\", \"def\")", a, ar)
}
}
func TestExtractMBIDs_ID3v2(t *testing.T) {
// dhowden stores TXXX frames under bare "TXXX"/"TXXX_N" keys with
// *tag.Comm values whose Description holds the Picard tag name.
m := stubMeta{
format: tag.ID3v2_4,
raw: map[string]interface{}{
"TXXX": &tag.Comm{
Description: "MusicBrainz Album Id",
Text: "abc-123",
},
"TXXX_0": &tag.Comm{
Description: "MusicBrainz Artist Id",
Text: "def-456",
},
},
}
a, ar := extractMBIDs(m)
if a != "abc-123" || ar != "def-456" {
t.Errorf("got (%q, %q), want (\"abc-123\", \"def-456\")", a, ar)
}
}
func TestExtractMBIDs_MP4(t *testing.T) {
// dhowden stores freeform iTunes atoms under their bare sub-name.
// mbz.Extract maps the human-readable form back to its lowercase key.
m := stubMeta{
format: tag.MP4,
raw: map[string]interface{}{
"MusicBrainz Album Id": "abc",
"MusicBrainz Artist Id": "def",
},
}
a, ar := extractMBIDs(m)
if a != "abc" || ar != "def" {
t.Errorf("got (%q, %q), want (\"abc\", \"def\")", a, ar)
}
}
func TestExtractMBIDs_MissingTagsReturnEmpty(t *testing.T) {
m := stubMeta{format: tag.VORBIS, raw: map[string]interface{}{}}
a, ar := extractMBIDs(m)
if a != "" || ar != "" {
t.Errorf("got (%q, %q), want empty", a, ar)
}
}
func TestExtractMBIDs_VorbisUppercaseKeysMiss(t *testing.T) {
// Regression guard: real dhowden never produces uppercase Vorbis
// keys. If a future change starts looking up "MUSICBRAINZ_ALBUMID"
// directly, this test must keep returning empty so we don't
// silently re-introduce the v0 bug where every album skipped.
m := stubMeta{
format: tag.VORBIS,
raw: map[string]interface{}{
"MUSICBRAINZ_ALBUMID": "wrong-case",
"MUSICBRAINZ_ARTISTID": "wrong-case",
},
}
a, ar := extractMBIDs(m)
if a != "" || ar != "" {
t.Errorf("uppercase Vorbis keys must not match dhowden output; got (%q, %q)", a, ar)
}
}
func TestExtractMBIDs_ID3v2StripsTrailingNUL(t *testing.T) {
// dhowden's readTextWithDescrFrame leaves the ID3v2.4 frame-
// terminator NUL on TXXX values. Postgres rejects NULs in text
// columns (SQLSTATE 22021), so we must strip them.
m := stubMeta{
format: tag.ID3v2_4,
raw: map[string]interface{}{
"TXXX": &tag.Comm{
Description: "MusicBrainz Album Id",
Text: "abc-123\x00",
},
"TXXX_0": &tag.Comm{
Description: "MusicBrainz Artist Id",
Text: "def-456\x00",
},
},
}
a, ar := extractMBIDs(m)
if a != "abc-123" || ar != "def-456" {
t.Errorf("got (%q, %q), want trailing NUL stripped", a, ar)
}
}
func TestExtractMBIDs_ID3v2MultiValueTakesFirst(t *testing.T) {
// Some Picard configs emit multi-value TXXX:MusicBrainz Artist Id
// for collaborations, NUL-separated. Minstrel uses the primary
// release artist for MBCAA, so first wins.
m := stubMeta{
format: tag.ID3v2_4,
raw: map[string]interface{}{
"TXXX": &tag.Comm{
Description: "MusicBrainz Artist Id",
Text: "primary-mbid\x00collab-mbid",
},
},
}
_, ar := extractMBIDs(m)
if ar != "primary-mbid" {
t.Errorf("got %q, want %q", ar, "primary-mbid")
}
}
func TestCleanMBID_OnlyNULReturnsEmpty(t *testing.T) {
// Defensive: a TXXX value that is purely NULs (or empty after
// trimming) must round-trip to empty so the caller skips the row
// instead of writing a NUL-only string to Postgres.
if got := cleanMBID("\x00\x00"); got != "" {
t.Errorf("got %q, want empty", got)
}
if got := cleanMBID(""); got != "" {
t.Errorf("got %q, want empty", got)
}
}