yambs (Yet Another MusicBrainz Seeder)

Build Status

yambs is a command-line program for seeding edits to the MusicBrainz music database.

It can simplify adding multiple standalone recordings: given a CSV or TSV file describing recordings, yambs can open the Add standalone recording page for each with various fields pre-filled. The Add artist, Add event, Add label, Add place, Add release group, Add series, and Add work pages can be seeded in a similar manner.

yambs can also read key=value lines from text files to seed the Add release page, and it can use Bandcamp, Qobuz, and Tidal album pages, Soundcloud song pages, Metal Archives album, artist, and band pages, and local MP3 files or RSS feeds to seed edits too.

There's a web frontend that can be used to add releases from online sources or entities from text files at yambs.erat.org.

Installation

To compile and install the yambs executable, install Go and run the following command:

go install ./cmd/yambs

If the account that you will use to run the yambs executable does not have access to the Google Cloud Translation API (used to detect releases' languages and scripts), you can supply the nogcp build tag to avoid attempting to connect to the service:

go install -tags nogcp ./cmd/yambs

Prebuilt executables are also available.

Usage

Usage: yambs [flag]... <FILE/URL>
Seeds MusicBrainz edits.
 -action value
 	Action to perform with seed URLs (open, print, serve, write) (default open)
 -addr string
 	Address to listen on for -action=serve (default "localhost:8999")
 -charset string
 	Charset for text input if not UTF-8 (IANA or MIME, e.g. "ISO-8859-1" or "latin1")
 -country string
 	Country code for querying Tidal API (ISO 3166, e.g. "US" or "DE"; "XW" for all)
 -edit-release-recordings string
 	Release MBID or URL whose recordings will be edited
 -fields string
 	Comma-separated fields for CSV/TSV columns (e.g. "artist,name,length")
 -format value
 	Format for text input (csv, keyval, tsv) (default tsv)
 -list-fields
 	Print available fields for -type and exit
 -merge-ranges string
 	Colon-separated list of comma-separated custom ranges for merging (e.g. "1-4,6-10:1-9")
 -merge-release-recordings string
 	Comma-separated release MBIDs or URLs whose recordings will be merged
 -modify-data value
 	Comma-separated modifications for online data (extract-artists, punctuation, remove-parens, split-artists, standalone-recording)
 -server string
 	MusicBrainz server hostname (default "musicbrainz.org")
 -set value
 	Set a field for all entities (e.g. "edit_note=from https://www.example.org")
 -timeout duration
 	Timeout for generating edits (e.g. "30s" or "2m")
 -type value
 	Entity type for text or MP3 input (artist, event, label, place, recording, release, release-group, series, work)
 -verbose
 	Enable verbose logging
 -version
 	Print the version and exit

yambs reads the supplied file or URL (or stdin if no positional argument is supplied) and performs the action specified by the -action flag:

• open: Open edits in a browser using a temporary file.
• print: Write edit links to stdout (only possible for recordings).
• serve: Open edits in a browser using a short-lived webserver launched at -addr (useful if you're running yambs in a container).
• write: Write a webpage containing the edits to stdout.

If you supply a URL, yambs will fetch and parse it.

If you supply a filename, you should also pass the -type, -format, -fields, and -set flags to tell yambs how to interpret the file.

Examples

To add multiple non-album recordings for a single artist, you can run a command like the following:

yambs \
 -type recording \
 -format tsv \
 -fields name,length,edit_note \
 -set artist=7e84f845-ac16-41fe-9ff8-df12eb32af55 \
 -set url0_url=https://www.example.org/ \
 -set url0_type=255 \
 <recordings.tsv

with a recordings.tsv file like the following (with tab characters between the fields):

Song #1	4:35	info from https://example.org/song1.html
Song #2	53234.35	info from https://example.org/song2.html

The recordings' names, lengths, and edit notes will be read from the TSV file, and the -set artist=... flag sets all recordings' artist field to the specified artist.

Likewise, the -set url0_... flags add a URL relationship to each recording. seed/enums.go enumerates the different link types that can be specified between entities; 255 corresponds to LinkType_DownloadForFree_Recording_URL.

To edit existing recordings, specify their MBIDs via the mbid field:

yambs \
 -type recording \
 -format csv \
 -fields mbid,name \
 <recordings.csv

recordings.csv:

c55e74ff-bd7d-40ff-a591-c6993c59bda8,Sgt. Pepper’s Lonely Hearts Club Band...

Note that this example uses the csv format rather than tsv.

As a convenience, you can generate edits for all of the recordings associated with a release by passing the release’s MBID via the -edit-release-recordings flag:

yambs \
 -edit-release-recordings cf731f61-d8ba-438a-b346-644456fd27e2 \
 -set 'disambiguation=live, 2008年12月07日: Rose Garden, Portland, OR, USA' \
 -set 'edit_note=update for https://musicbrainz.org/doc/Style/Recording#Live_recordings'

yambs \
 -edit-release-recordings 6d71e03a-a7d6-4c4d-a645-b279b8a07b77 \
 -set 'artist0_mbid=2fcffd9a-f02a-4a2c-8085-6257f918949d' \
 -set 'artist0_credited=Pau Casals' \
 -set 'edit_note=[Style/Classical/Recording_Artist]'

This is equivalent to passing -fields mbid and supplying the recording MBIDs as input.

More-complicated artist credits can also be assigned:

yambs \
 -type recording \
 -format tsv
 -fields ... \
 -set artist0_mbid=1a054dd8-c5fa-40b6-9397-61c26b0185d4 \
 -set artist0_credited=virt \
 -set 'artist0_join= & ' \
 -set artist1_name=Rush \
 ...

(Note that repeated fields are 0-indexed.)

The keyval format can be used to seed a single entity across multiple lines:

yambs -type release -format keyval <release.txt

release.txt:

title=Some Album
artist0_name=Some Artist
types=Album,Soundtrack
status=Official
packaging=Jewel Case
language=eng
script=Latn
event0_date=2021年05月15日
event0_country=XW
medium0_format=CD
medium0_track0_title=First Track
medium0_track0_length=3:45.04
medium0_track1_title=Second Track
medium1_format=CD
medium1_track0_title=First Track on Second Disc
url0_url=https://www.example.org/
url0_type=75
edit_note=https://www.example.org

seed/enums.go shows that the url0_type=75 line corresponds to LinkType_DownloadForFree_Release_URL.

If you'd like to bulk-add LinkType_Published_Label_Release (ID 362) relationships between the existing label 02442aba and releases 43bcfb95 and a9d8b538, you can set the mbid field to edit the label and seed the new relationships:

yambs -type label -format keyval <label.txt

label.txt:

mbid=02442aba-cf00-445c-877e-f0eaa504d8c2
rel0_target=43bcfb95-f26c-4f8d-84f8-7b2ac5b8ab72
rel0_type=362
rel1_target=a9d8b538-c20a-4025-aea1-5530d616a20a
rel1_type=362

Pass the -list-fields flag to list all available fields for a given entity type:

yambs -type artist -list-fields
yambs -type event -list-fields
yambs -type label -list-fields
yambs -type place -list-fields
yambs -type recording -list-fields
yambs -type release -list-fields
yambs -type release-group -list-fields
yambs -type series -list-fields
yambs -type work -list-fields

Acceptable values for various fields are listed in seed/enums.go, which is automatically generated from t/sql/initial.sql in the musicbrainz-server repository.

A column in an input file can be assigned to multiple fields by supplying slash-separated field names. For example, -fields name,url0_url/edit_note,length maps the first column to field name, the second column to fields url0_url and edit_note, and the third column to field length.

A column can be skipped by passing an empty field name. For example, -fields name,,length maps the first column to field name, skips the second column, and maps the third column to length.

You can pass Bandcamp, Qobuz, or Tidal album URLs to seed release edits:

yambs https://austinwintory.bandcamp.com/album/journey

yambs https://www.qobuz.com/us-en/album/the-dark-side-of-the-moon-pink-floyd/xggxq5w5dmljb

yambs https://tidal.com/browse/album/55391786

The page that is opened will include a link to the album's highest-resolution cover art to make it easier to add in a followup edit.

If you pass a Bandcamp track URL that isn't part of an album, an edit to add it as a single will be created:

yambs https://caribouband.bandcamp.com/track/tin

You can pass the path to a local MP3 file to use it to seed a (single) release or standalone recording edit:

yambs \
 -type recording \
 -set artist=7e84f845-ac16-41fe-9ff8-df12eb32af55 \
 -set edit_note='from artist-provided MP3 at https://www.example.org/song.mp3' \
 /path/to/a/song.mp3

If the MP3 file contains embedded images, they will be extracted to temporary files so they can be added as cover art.

You can also pass the path to a local RSS feed (e.g. for a podcast) and use it to either seed a separate release (per the broadcast programs guidelines) or a standalone recording for each item:

yambs \
 -type release \
 -set artist0_name='Podcast Host' \
 -set edit_note='from https://www.example.org/feed.xml' \
 /path/to/a/feed.xml

You can generate edits to merge all of the recordings between two or more releases by passing a comma-separated list of release MBIDs or URLs via the -merge-release-recordings flag:

yambs -merge-release-recordings 7cce69ab-08b2-48ba-93f0-0ba458d98adc,a7c74fca-9392-4fc8-9aac-a8e122dbbfa8

The recording merge edits must be opened and submitted one at a time (due to the MusicBrainz website maintaining its own internal queue of entities to merge).

By default, the releases must have the same number of tracks. You can additionally pass the -merge-ranges flag to specify a colon-separated list of per-release comma-separated track ranges. For example, -merge-ranges 1-4,7-9,5:1-8 will merge:

• tracks 1-4 from the first release with tracks 1-4 from the second
• track 7 from the first release with track 5 from the second
• track 8 from the first release with track 6 from the second
• track 9 from the first release with track 7 from the second
• track 5 from the first release with track 8 from the second

There's also a yambsd executable that exposes most of the same functionality through a webpage (with some limits to avoid abuse).

Why?

There are a bunch of MusicBrainz userscripts that run in the browser with the help of an extension like Tampermonkey to seed edits. They're well-tested, so why not just use them instead of writing a new thing?

Well, at first I was adding a bunch of standalone recordings that I'd downloaded from random musicians' homepages. I couldn't find any userscripts to help with that, since the main focus seems to be seeding releases from major websites. I ended up hacking together a shell script to generate URLs that would seed my edits, but I figured it'd be nice to have something more robust and convenient to use next time.

I had also been using the bandcamp_importer.user.js userscript to import releases from Bandcamp, but I'm nervous about using extensions like Tampermonkey that require permission to modify data on all sites. I'm not so worried about malice on the part of extension or userscript developers, but I have no idea about their security practices and I'm fearful of attackers compromising their computers and uploading malicious versions of their code.

I created a separate browser profile that I could use to run Tampermonkey without exposing any of my (non-MusicBrainz) credentials, but using it was a pain, so I decided to add Bandcamp support to this codebase as well since that's where I get most of my music.

Further reading

• "Release Editor Seeding" documentation
• Release seeding example
• "Seeding Recordings" thread