lastgenre: Whitelist/Tree fixes; Default aliases

- Fixes some inconsistencies in spelling in the data files we ship with
  the plugin as well as adds some new genres to both files that seem to
  be returned often by last.fm.
  - For some changes the default aliases feature helps to streamline
    inconsistencies that come from last.fm already.
- The default aliases file that ships with beets
  - Tests fixes that prove that most of the alias normalization patterns
    work as they are supposed to.

Co-authored-by: Šarūnas Nejus <snejus@protonmail.com>

beetsplug/lastgenre/aliases.yaml

@@ -0,0 +1,72 @@
+# Ampersands / Delimiters
+drum and bass:
+    - d(rum)?[ &n/]*b(ass)?
+r&b:
+    - r(hythm)?[ &n/]*b(lues)?
+rock and roll:
+    - rock[- ‐'&n/]*roll
+
+# Hyphenation
+\1-\2:
+    - ([ckj])[- ]*(pop)
+    - (j)[- ]*(rock)
+    - (post)[- ]*(\w+)
+    - (g?lo)[- ]*(fi)
+    - ([pg])[- ]*(funk)
+    - (synth)[- ]*(pop)
+avant-garde:
+    - avant[- ]*(garde?)?
+
+# Adding space
+\1 \2:
+    - (nu)[ -]*(disco|jazz|metal|soul)
+    - (dark)[ -]*(wave)
+    - (blues|folk|indie|gothic|progressive|alternative|punk)[ -]*(rock)
+    - (ska)[ -]*(jazz)
+    - (synth)[- ]*(funk)
+    - (glitch|hip|trip)y?(?:[ -]*hip)?[ -]*(hop)
+
+# Removing delimiters
+\1\2:
+    - (synth)[- ]*(wave)
+    - (psy)[ -]*(trance)
+    - (chill)[ -]*(out)
+
+# Old School spellings: old-school death metal, oldschool hip-hop, old-skool-jungle/-hardcore
+old school death metal:
+    - old[ -]*(?:school|skool)[ -]+death[ -]*metal
+old school hip hop:
+    - old[ -]*(?:school|skool)[ -]+hip[ -]*hop
+old school \1:
+    - old[ -]*(?:school|skool)[ -]+(\w+)
+
+# Terminology / Synonyms
+electronic:
+    - electronic music
+world music:
+    - world
+downtempo:
+    - down[ -]*beat
+shoegaze:
+    - shoegaz(e?r?|ing)
+footwork:
+    - (chicago )?footwork( music)?
+juke:
+    - (chicago )?juke( music| house)?
+
+# Compound genres
+alternative rock:
+    - alt[ -]*rock
+# negative lookahead avoids matching 'gothic metal'
+gothic rock:
+    - goth(?!ic)([ -]*rock)?
+# avoids matching 'progressive metal'
+progressive rock:
+    - prog([ -]*rock)?
+punk rock:
+    - punk
+# psy folk, psych-pop, psychedelic-rock, psychedelic soul, but not psychedelic (standalone)
+psychedelic \1:
+    - psy(?:ch(?:edelic)?)?[ -]*(folk|pop|rock|soul)
+dixieland:
+    - dixieland[ -]*jazz

beetsplug/lastgenre/genres-tree.yaml

@@ -257,6 +257,7 @@
         - broken beat
         - florida breaks
         - nu skool breaks
+        - breaks
     - chiptune:
         - bitpop
         - game boy music
@@ -268,12 +269,12 @@
         - disco polo
             - euro disco
         - italo disco
-        - nu-disco
+        - nu disco
         - space disco
     - downtempo:
         - acid jazz
         - balearic beat
-        - chill out
+        - chillout
         - dub music
         - dubtronica
         - ethnic electronica
@@ -293,7 +294,7 @@
         - jungle:
             - darkside jungle
             - ragga jungle
-            - oldschool jungle
+            - old school jungle
         - raggacore
         - sambass
         - techstep
@@ -327,7 +328,7 @@
         - indietronica
         - new rave
         - space rock
-        - synthpop
+        - synth-pop
         - synthpunk
     - electronica:
         - berlin school
@@ -358,6 +359,7 @@
         - happy hardcore
         - hardstyle
         - jumpstyle
+        - old school hardcore
         - makina
         - speedcore
         - terrorcore
@@ -426,6 +428,7 @@
         - dub techno
         - free tekno
         - ghettotech
+        - industrial techno
         - minimal
         - nortec
         - schranz
@@ -437,9 +440,10 @@
         - acid trance
         - classic trance
         - dream trance
-        - goa trance:
+        - psytrance:
             - dark psytrance
             - full on
+            - goa trance
             - psybreaks
             - psyprog
             - suomisaundi
@@ -492,8 +496,8 @@
     - gangsta rap
     - glitch hop
     - golden age hip hop
+    - hardcore hip hop
     - hip hop soul
-    - hip pop
     - hyphy
     - industrial hip hop
     - instrumental hip hop
@@ -620,11 +624,13 @@
     - turkish pop
     - vispop
     - wonky pop
-- rhythm and blues:
+- r&b:
     - funk:
         - deep funk
         - go-go
         - p-funk
+        - synth funk
+            - minneapolis sound
     - soul:
         - blue-eyed soul
         - neo soul
@@ -670,6 +676,7 @@
             - death/doom
             - goregrind
             - melodic death metal
+            - old school death metal
             - technical death metal
         - doom metal:
             - epic doom metal
@@ -708,6 +715,7 @@
         - traditional heavy metal
     - math rock
     - new wave:
+        - synthwave
         - world fusion
     - paisley underground
     - pop rock
@@ -786,7 +794,7 @@
     - chanson
     - canción de autor
     - nueva canción
-- world:
+- world music:
     - world dub
     - world fusion
     - worldbeat

beetsplug/lastgenre/genres.txt

@@ -1,5 +1,5 @@
 2 tone
-2-step garage
+2-step
 4-beat
 4x4 garage
 8-bit
@@ -12,10 +12,12 @@ acid rock
 acoustic music
 acousticana
 adult contemporary music
+african
 african popular music
 african rumba
 afrobeat
 aleatoric music
+alternative
 alternative country
 alternative dance
 alternative hip hop
@@ -112,7 +114,7 @@ blue-eyed soul
 bluegrass
 blues
 blues ballad
-blues-rock
+blues rock
 boogie
 boogie woogie
 boogie-woogie
@@ -123,6 +125,7 @@ brazilian jazz
 breakbeat
 breakbeat hardcore
 breakcore
+breaks
 breton music
 brill building pop
 britfunk
@@ -227,6 +230,7 @@ chicano rap
 chicha
 chicken scratch
 children's music
+chill
 chillout
 chillwave
 chimurenga
@@ -234,6 +238,7 @@ chinese music
 chinese pop
 chinese rock
 chip music
+chiptune
 cho-kantrum
 chongak
 chopera
@@ -336,7 +341,6 @@ dabka
 dadra
 daina
 dalauna
-dance
 dance music
 dance-pop
 dance-punk
@@ -349,10 +353,10 @@ danza
 danzón
 dark ambient
 dark cabaret
+dark wave
 dark pop
 darkcore
 darkstep
-darkwave
 de ascultat la servici
 de codru
 de dragoste
@@ -395,7 +399,6 @@ disney pop
 diva house
 divine rock
 dixieland
-dixieland jazz
 djambadon
 djent
 dodompa
@@ -415,6 +418,7 @@ drone metal
 drone music
 dronology
 drum and bass
+drumfunk
 dub
 dub house
 dubanguthu
@@ -497,6 +501,7 @@ folk pop
 folk punk
 folk rock
 folktronica
+footwork
 forró
 franco-country
 freak-folk
@@ -518,6 +523,7 @@ full on
 funaná
 funeral doom
 funk
+funk / soul
 funk metal
 funk rock
 funkcore
@@ -679,6 +685,7 @@ impressionist music
 improvisational
 incidental music
 indian pop
+indie
 indie folk
 indie music
 indie pop
@@ -688,12 +695,13 @@ indo jazz
 indo rock
 indonesian pop
 indoyíftika
+industrial
 industrial death metal
 industrial hip hop
 industrial metal
-industrial music
 industrial musical
 industrial rock
+industrial techno
 instrumental rock
 intelligent dance music
 international latin
@@ -755,6 +763,8 @@ jtek
 jug band
 jujitsu
 juju
+juke
+juke/footwork
 juke joint blues
 jump blues
 jumpstyle
@@ -968,6 +978,7 @@ min'yo
 mineras
 mini compas
 mini-jazz
+minimal
 minimal techno
 minimalist music
 minimalist trance
@@ -1063,7 +1074,7 @@ nintendocore
 nisiótika
 no wave
 noh
-noise music
+noise
 noise pop
 noise rock
 nongak
@@ -1074,6 +1085,7 @@ nortec
 norteño
 northern soul
 nota
+nu disco
 nu jazz
 nu metal
 nu soul
@@ -1083,7 +1095,10 @@ nyatiti
 néo kýma
 obscuro
 oi!
+old school death metal
+old school hardcore
 old school hip hop
+old school jungle
 old-time
 oldies
 olonkho
@@ -1190,11 +1205,13 @@ progressive trance
 progressive thrash metal
 protopunk
 psych folk
+psychedelic folk
 psychedelic music
 psychedelic pop
 psychedelic rock
-psychedelic trance
+psychedelic soul
 psychobilly
+psytrance
 punk blues
 punk cabaret
 punk jazz
@@ -1249,8 +1266,7 @@ renaissance music
 requiem
 rhapsody
 rhyming spiritual
-rhythm & blues
-rhythm and blues
+r&b
 ricercar
 riot grrrl
 rock
@@ -1314,6 +1330,7 @@ shabad
 shalako
 shan'ge
 shango
+shangaan electro
 shape note
 shibuya-kei
 shidaiqu
@@ -1328,8 +1345,10 @@ sica
 siguiriyas
 silat
 sinawi
+singer-songwriter
 situational
 ska
+ska jazz
 ska punk
 skacore
 skald
@@ -1406,9 +1425,11 @@ symphonic metal
 symphonic poem
 symphonic rock
 symphony
+synth-pop
+synth funk
 synthcore
-synthpop
 synthpunk
+synthwave
 t'ong guitar
 taarab
 tai tu
@@ -1454,6 +1475,7 @@ tinga
 tinku
 toeshey
 togaku
+trad
 trad jazz
 traditional bluegrass
 traditional heavy metal

test/plugins/test_lastgenre.py

@@ -1039,17 +1039,20 @@ class TestAliases:
         [
             ("dnb", "drum and bass"),
             ("drum n bass", "drum and bass"),
-            ("r&b", "rhythm and blues"),
-            ("rnb", "rhythm and blues"),
+            ("r&b", "r&b"),
+            ("rnb", "r&b"),
             ("rock & roll", "rock and roll"),
             ("rock'n'roll", "rock and roll"),
             ("kpop", "k-pop"),
+            ("k -pop", "k-pop"),
             ("j rock", "j-rock"),
             ("post rock", "post-rock"),
             ("lofi", "lo-fi"),
             ("lo fi", "lo-fi"),
             ("p funk", "p-funk"),
-            ("synth pop", "synthpop"),
+            ("synth funk", "synth funk"),
+            ("synth pop", "synth-pop"),
+            ("synth-wave", "synthwave"),
             ("avantgarde", "avant-garde"),
             ("avant gard", "avant-garde"),
             ("nu-jazz", "nu jazz"),
@@ -1059,11 +1062,11 @@ class TestAliases:
             ("nu - disco", "nu disco"),
             ("electronic music", "electronic"),
             ("world", "world music"),
-            ("chill", "chillout"),
+            ("chill", "chill"),
             ("chill out", "chillout"),
             ("chill-out", "chillout"),
-            ("dark wave", "darkwave"),
-            ("dark-wave", "darkwave"),
+            ("dark wave", "dark wave"),
+            ("dark-wave", "dark wave"),
             ("blues rock", "blues rock"),
             ("blues-rock", "blues rock"),
             ("folk-rock", "folk rock"),
@@ -1072,17 +1075,29 @@ class TestAliases:
             ("shoegazing", "shoegaze"),
             ("hip-hop", "hip hop"),
             ("triphop", "trip hop"),
-            ("alt", "alternative rock"),
+            ("punk", "punk rock"),
+            ("alt", "alt"),
             ("alt rock", "alternative rock"),
-            ("alternative", "alternative rock"),
+            ("alternative", "alternative"),
             ("goth", "gothic rock"),
             ("goth rock", "gothic rock"),
             ("gothic rock", "gothic rock"),
             ("prog", "progressive rock"),
             ("prog rock", "progressive rock"),
             ("progressive rock", "progressive rock"),
-            ("trad", "traditional folk"),
-            ("traditional", "traditional folk"),
+            ("trad", "trad"),
+            ("traditional", "traditional"),
+            ("indie", "indie"),
+            ("indie rock", "indie rock"),
+            ("juke/footwork", "juke/footwork"),
+            ("Funk / Soul", "funk / soul"),
+            ("psy-trance", "psytrance"),
+            ("psy rock", "psychedelic rock"),
+            ("psych-pop", "psychedelic pop"),
+            ("disney", "disney"),
+            ("old-school death-metal", "old school death metal"),
+            ("old-skool-hip-hop", "old school hip hop"),
+            ("old school-jungle", "old school jungle"),
         ],
     )
     def test_default_alias_patterns(self, config, input_genre, expected_genre):