mirror of
https://github.com/navidrome/navidrome.git
synced 2026-08-31 07:30:32 +00:00
f853ca604a
* refactor(model): extract canonical 128-bit base62 id codec * feat(model): generate random ids as canonical 128-bit base62 values * feat(scanner): emit legacy PIDs in canonical base62 encoding * feat(db): add id canonicalization transform for the uniform-ids migration * feat(db): migrate all ids to canonical 128-bit base62 encoding * fix(db): canonicalize ids in junction tables and JSON columns * chore(jellyfin): update id-family notes for uniform canonical ids * test(ids): harden codec input contract and migration edge coverage * refactor(model): use log.Fatal for Encode128 contract guard per project convention * fix(db): force full rescan after id migration for legacy PID configs * test(db): guard id-column inventory against schema drift * refactor(ids): compile-time Encode128 contract and unified column rewrite helper * refactor(db): apply review feedback to id migration Filter empty strings in collectColumn's SQL, reuse a prepared statement for rewriteColumn updates, and clarify the legacy ID functions' comment now that they emit the canonical encoding. * feat(auth): split session and public-link JWT secrets, rotating sessions on id migration * test(subsonic): initialize public token secret in helpers suite The suite sets auth.TokenAuth directly instead of calling auth.Init, so the new PublicTokenAuth was nil whenever Ginkgo's spec order ran a helpers spec before any spec that calls auth.Init, panicking in publicurl.ImageURL. * refactor(db): inline canonicalID into its only consumer, the uniform-ids migration * refactor(model): rename Encode128/Decode128 to Encode/Decode With every id now exactly 128 bits, the width suffix is redundant; the package-qualified id.Encode/id.Decode carries the same information. * test(db): make the id-columns guard classify JSON columns too The guard only inspected columns named id/pid/*_id, so it could not see ids embedded in JSON. Widen it to *_ids and to every JSON column, and drive the "covered" set from a new embeddedIDColumns list instead of the inline calls in the migration. Every JSON column the schema has now carries a verdict. The four denormalized caches -- media_file/album.participants, media_file/album.tags, album.folder_ids and artist.similar_artists -- hold only artist, tag and folder ids. Those all come from id.NewHash, whose 22-char base62 encoding of a 128-bit MD5 is already in canonical range, so canonicalID is the identity on them and the migration correctly leaves them alone. A new codec test pins that invariant, since the exemptions depend on it. Verified on a copy of a 727MB/96k-track production database: canonicalizing those four columns changed zero rows, and artist, tag and folder ids were themselves unchanged by the migration (only media_file ids moved, 95108 of 96666).
48 lines
2.0 KiB
Go
48 lines
2.0 KiB
Go
package migrations
|
|
|
|
import (
|
|
"strings"
|
|
|
|
"github.com/navidrome/navidrome/model/id"
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
var _ = Describe("canonicalID", func() {
|
|
DescribeTable("transforms each historical id shape",
|
|
func(in, want string) {
|
|
Expect(canonicalID(in)).To(Equal(want))
|
|
},
|
|
Entry("hash-family id (fits 128 bits) is kept", "5cLJPkLA5DK2BADhoeotPk", "5cLJPkLA5DK2BADhoeotPk"),
|
|
Entry("overflowing random id is remapped via md5", "zzzzzzzzzzzzzzzzzzzzzz", "3LyqmwQBm5IRqlVjNYASwb"),
|
|
Entry("legacy 32-hex is re-encoded value-preserving", "e3b7fc2ae9447bbec37a13bf916e3cf6", "6VHl3uR4kss6sUPKA8Cwnk"),
|
|
Entry("playlist uuid is re-encoded value-preserving", "f47ac10b-58cc-4372-a567-0e02b2c3d479", "7rke2SAWaicSeSYzkhww6R"),
|
|
Entry("empty string passes through", "", ""),
|
|
Entry("share id (10 chars) passes through", "aB3xY9kQz1", "aB3xY9kQz1"),
|
|
Entry("truncated Finamp id (16 chars) passes through", "0123456789abcdef", "0123456789abcdef"),
|
|
Entry("22 chars with non-base62 char passes through", "!!!!!!!!!!!!!!!!!!!!!!", "!!!!!!!!!!!!!!!!!!!!!!"),
|
|
Entry("32 chars non-hex passes through", "zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz", "zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz"),
|
|
Entry("36 chars without uuid dashes passes through", "000000000000000000000000000000000000", "000000000000000000000000000000000000"),
|
|
)
|
|
|
|
// The exemptions for participants/tags/folder_ids/similar_artists rest on this invariant.
|
|
It("is the identity on every NewHash id", func() {
|
|
for _, parts := range [][]string{
|
|
{""}, {"a"}, {"The Beatles"}, {"genre", "electronic"},
|
|
{"/music/Artist/Album", "1"}, {strings.Repeat("x", 500)},
|
|
} {
|
|
h := id.NewHash(parts...)
|
|
Expect(h).To(HaveLen(22))
|
|
Expect(canonicalID(h)).To(Equal(h), "NewHash(%v) = %q was rewritten", parts, h)
|
|
}
|
|
})
|
|
|
|
It("is idempotent for every shape", func() {
|
|
for _, s := range []string{"5cLJPkLA5DK2BADhoeotPk", "zzzzzzzzzzzzzzzzzzzzzz",
|
|
"e3b7fc2ae9447bbec37a13bf916e3cf6", "f47ac10b-58cc-4372-a567-0e02b2c3d479"} {
|
|
once := canonicalID(s)
|
|
Expect(canonicalID(once)).To(Equal(once))
|
|
}
|
|
})
|
|
})
|