Add beets==2 and drop beets<1.5 support, improve catalognum, albumtypes parsing

.githooks/post-commit

@@ -1,43 +1,68 @@
-#!/bin/bash
+#!/bin/zsh
+# Run tests across all test files, and report what has changed in a pretty way.
+# Test metadata files are stored in $TEST_FILES_DIR (./jsons) directory: those
+# are JSON files that contain Bandcamp release metadata.
+#
+# You can use 'url2json -s <release-url>' to create such testing file for your
+# release of choice.
+# It extracts the relevant metadata saves it in './jsons' directory under
+# the filename that resembles that release URL (where slashes are replaced by
+# underscores).
 
-TESTS_DIR=lib_tests
+setopt extendedglob nullglob
+zmodload zsh/mapfile
+autoload -Uz zmv
 
-[ "$(git branch --show-current)" = dev ] || exit
+TESTS_DIR=lib_tests
 
-commit=$(git rev-parse --short HEAD)
-previous_commit=$(git rev-parse --short HEAD~1)
+[[ -d .git/rebase-merge ]] || [[ $(git branch --show-current) == dev ]] || exit
 
-[[ -e $TESTS_DIR/$previous_commit ]] || exit
+commit=$(git show --no-patch --format='%h %s')
+after=${${=commit}[1]}
+message=${commit#$after }
+if git diff --quiet HEAD~1..HEAD ./beetsplug; then
+  print "$after: Source code has not changed, bye: $message"
+  exit
+fi
 
-git diff --quiet HEAD~1..HEAD ./beetsplug
-committed_source_code=$?
-git diff --quiet ./beetsplug
-dirty_worktree=$?
+if [[ -d .git/rebase-merge ]]; then
+  results=(${(f@)${mapfile[.git/rebase-merge/done]%$'\n'}})
+  current_commit=(${=results[-1]})
+  action=$current_commit[1]
+  rebase_head=${current_commit[2]:0:7}
 
-if ((!committed_source_code)); then
-  cp -r "$TESTS_DIR/$previous_commit" "$TESTS_DIR/$commit"
-  cp "$TESTS_DIR/album-$previous_commit" "$TESTS_DIR/album-$commit"
-  cp "$TESTS_DIR/tracks-$previous_commit" "$TESTS_DIR/tracks-$commit"
-  exit
+  if [[ $action =~ (fixup|squash) ]]; then
+    print "Skipping commit rewrite: $message"
+    exit
+  fi
+  if [[ -d $TESTS_DIR/$rebase_head ]]; then
+    if [[ ! -s .git/rebase-merge/git-rebase-todo ]] && ( (( ${#${(M)${results}:#*(edit|fixup|squash)*}} )) || (( ! ${#${(M)${results}:#*reword*}} )) ); then
+      print "Current (latest) commit, testing against REBASE_HEAD $rebase_head to synchronise results: $message"
+      before=$rebase_head
+    else
+      zmv $TESTS_DIR/'(*)'$rebase_head $TESTS_DIR/'${1}'$after
+      if git diff --quiet $rebase_head..$after ./beetsplug; then
+        print "No source code changes in comparison to $rebase_head: $message"
+        exit
+      else
+        print "Testing previous against new commit: $message"
+      fi
+    fi
+  else
+    print "Results from base commit $rebase_head do not exist, testing against last commit $before: $message"
+  fi
+else
+  print "Testing previous against new commit: $message"
 fi
 
-cp -r "$TESTS_DIR/$previous_commit" "$TESTS_DIR/$commit"
-((dirty_worktree)) && git stash
-pytest -p no:randomly -k 'lib and file' -s -n 4 --base "$previous_commit" --target "$commit"
-((dirty_worktree)) && git stash pop
-
-jq '[(input_filename | sub(".*/"; "")), if .name then {before: .} else {after: .} end]' jsons/* "$TESTS_DIR/$commit"/*.json |
-  jq -s '
-    group_by(.[0]) | 
-    map(
-      [.[][1]] | 
-      add | 
-      select(.after.album) | 
-      "\(.before.name) -> \(.after.album)"
-    ) | 
-    sort | 
-    unique[]' -r >"$TESTS_DIR/album-$commit"
-jq '(.tracks//[]) | map(if .track_alt then "\(.track_alt). " else "" end + .artist + " - " + .title)[]' "$TESTS_DIR/$commit"/*.json -r >"$TESTS_DIR/tracks-$commit"
-
-git diff --unified=0 --no-index --color-words "$TESTS_DIR/album-$previous_commit" "$TESTS_DIR/album-$commit"
-git diff --unified=0 --no-index --color-words "$TESTS_DIR/tracks-$previous_commit" "$TESTS_DIR/tracks-$commit"
+(( $#before )) || {
+  folders=(lib_tests/^[a-z]##(/:t))
+  pat="^(${(j:|:)folders})"
+  before=($(git log main~3..HEAD~ --format=%h ./beetsplug | grep -E $pat -m1))
+}
+
+git diff --quiet ./beetsplug
+dirty_worktree=$?
+(( dirty_worktree )) && git stash
+./test_lib $before $after
+(( dirty_worktree )) && git stash pop --quiet

.github/workflows/build.yml

@@ -7,7 +7,7 @@ jobs:
       fail-fast: false
       matrix:
         python: ["3.8", "3.9", "3.10", "3.11", "3.12"]
-        beets: ["1.4.9", "1.5.0", "1.6.0"]
+        beets: ["1.5.0", "1.6.0", "2.0.0"]
     steps:
       - uses: actions/checkout@v4
         with:

.gitignore

@@ -7,5 +7,6 @@ dist
 htmls
 lib_tests
 reports
-jsons
+*jsons
 stubs
+singletons

CHANGELOG.md

@@ -1,7 +1,131 @@
-## Unreleased
+## [0.20.0] 2024-11-04
+
+### Removed
+
+- Drop support for `beets<1.5`.
+
+### Fixed
+
+- `album`:
+  - Keep remix artist in place within 'remix' parentheses, such as **Album (Artist
+    Remix)**.
+  - When a release has the same name as the album artist, do not clean/adjust it.
+  - Keep album artist in album when it is immediately followed by a dot.
+  - Do not remove **EP** or **LP** from the beginning of the album name.
+  - Remove **`V.A`** from the beginning of the album name, in the same way we remove
+    **`VA`**.
+  - Do not split album with a year range into `albumartist` and `album`.
+
+- cleanup:
+  - Remove **`(... preview)`**, **`free dl`**, **`Name Your Price:`**, **`just out!`**,
+    **`- Album`**, **`(Selected by ...)`** from album and track names.
+  - Remove unicode HTML whitespace from incoming data.
+
+- `albumtype`:
+  - Identify **LP** / **album** type from vinyl media descriptions.
+  - Remove some funky description parsing logic responsible for multiple **ep** false
+    positives.
+  - Resolve either **ep** or **lp** to add to `albumtypes`, and never both.
+  - Check for **single** album type (expecting a single track only) before anything else.
+
+- `artist`: handle remix releases with a single title and its remixes. Instead of trying
+  to determine the artist from the titles, detect such release and use the given album
+  artist.
+
+- `catalognum`:
+  - Fix false positives:
+    - Exclude very short matches like **OP-1**, **SK-1** and **BBC6**.
+    - Exclude label name, and label name without spaces.
+    - Exclude matches followed by a comma. This excludes many artists from release
+      descriptions that happen to have names that look like catalogue numbers.
+    - Exclude matches followed by a single quote. This used to wrongly match vinyl disc
+      titles like **LABEL 12** here: `LABEL 12'' Black Vinyl`.
+    - Prevent album artists becoming catalogue numbers.
+    - Remove pattern responsible for many false positives that contain a space, like
+      **DOOM 3**, **ONLY 1** and **NIGHT 3** etc.
+    - Do not any more assume that artist **[DRAKEN49]** is a catalogue number.
+    - Instead of using a pattern like `[A-Z]+-[0-9]+` _(more than one capital letter —
+      dash — more than one number)_, explicitly specify how many letters and numbers are
+      expected for the most common variations, like **TAR30**, **RM12012**, **HEY-101**
+      etc.
+
+- `media`: ignore subscription type Bandcamp media format which returns a duplicate
+  digital media.
+
+- `title`: 
+  - Remove track number from the beginning of the title more reliably.
+  - Remove label name from anywhere if it inside brackets or from the end of the title if
+    preceded by a dash or a colon.
+
+- `track`:
+  - `artist` / `title` / `track_alt`: Handle edge cases where `track_alt` is followed by a
+    single dash. Some instances were previously ignored.
+  - `artist` / `title` / `track_alt`: fix several artists and titles which had pieces
+    incorrectly identified as `track_alt`.
+  - `artist` / `title`: In releases where every track has the same title, check whether
+    this title may actually be the artist name. If so, move it to the artist field.
+  - `artist` / `title`: use characters **`[|-–—]`** explicitly for splitting artists and
+    titles.
+  - `artist` / `title`: recover some of the original titles which contain **`-`** and got
+    split into `artist` and `title`.
+  - Return an empty tracklist for [releases that have no tracks].
+
+[releases that have no tracks]: https://seagrave.bandcalmp.com/album/interlocked
 
 ### Added
-- Auto-Tagger: Wider search analogous to cli search query as a fallback for bad or missing meta data
+
+- Auto-Tagger: Wider search analogous to cli search query as a fallback for bad or missing
+  meta data.
+- Add artist list fields support for `beets==2.0.0`.
+
+### Updated
+
+- `album`:
+  - When album name is wrapped in brackets, **[ALBUM]**, keep the brackets in place.
+  - Uncover some release names in the description preceded by **Title :**.
+
+- `albumartist`:
+  - Remove notes about remixes, like **(incl. ABC remix)** and similar.
+
+- `albumtype`:
+  - Improve accuracy of identifying **EP** and **LP** release types from the description.
+  - Include **remix** albumtype to the release when remixed track count is one less than
+    the track count.
+  - Check album names that may end with **E.P.** instead of **EP**.
+
+- `catalognum`:
+  - Add support for new formats: **`UVB76-023`**, **`SOP 061-1233`**, **`a+w lp029`**,
+    **`SK11X015`**.
+  - Parse label-like catalogue numbers for singletons too.
+  - When searching for a catalogue number which is prefixed by the label name
+    1. Take two variations of the label name
+       1. Original one
+       2. Without **Records**, **Recordings**, **Productions**, **Music** endings
+    2. Form prefixes from each variation
+       1. The original variation
+       2. With punctuation and spaces removed
+       3. Its acronym when it has multiple words
+    3. Lastly, if the original label has multiple words, use the first word as another
+       possible prefix.
+
+    For example, for a label named **Diffuse Reality Records**, the plugin is able to
+    recognize the following catalogue numbers (case insensitively)
+    - **Diffuse Reality Records**001
+    - **DiffuseRealityRecords**001
+    - **DRR**001
+    - **Diffuse Reality**001
+    - **DiffuseReality**001
+    - **DR**001
+    - **Diffuse**001
+
+  - Parse catalogue number from the description when the header is followed by a hash
+    symbol, like **CAT#: ABC-123**.
+  - Properly catch catalogue number suffix **RP**.
+  - Relax the rule that looks for a catalogue number within brackets in the release title.
+
+- `track`:
+  - For tracks named like **[Remixer] - Artist - Title** move the remixer to the end:
+    **Artist - Title [Remixer]**.
 
 ## [0.19.3] 2024-10-17
 
@@ -12,7 +136,8 @@
 
 ### Fixed
 
-- `exclude_extra_fields`: A typo that prevented exclude configurations from being applied correctly
+- `exclude_extra_fields`: A typo that prevented exclude configurations from being applied
+  correctly
 
 ## [0.19.2] 2024-08-04
 
@@ -85,7 +210,6 @@
   - consider **with** and **w/** as markers for collaborating artists
   - remove **`bonus -`**
     - `Artist - Title (bonus - something)` -> **`Artist - Title (something)`**
-
 [album sent to us by the devil himself]: https://examine-archive.bandcamp.com/album/va-examine-archive-international-sampler-xmn01
 
 ## [0.17.2] 2023-08-09
@@ -1124,3 +1248,4 @@ Thanks @arogl for reporting each of the above!
 [0.19.1]: https://github.com/snejus/beetcamp/releases/tag/0.19.1
 [0.19.2]: https://github.com/snejus/beetcamp/releases/tag/0.19.2
 [0.19.3]: https://github.com/snejus/beetcamp/releases/tag/0.19.3
+[0.20.0]: https://github.com/snejus/beetcamp/releases/tag/0.20.0

beetsplug/bandcamp/__init__.py

@@ -21,10 +21,10 @@
 import logging
 import re
 from contextlib import contextmanager
-from functools import lru_cache, partial
+from functools import partial
 from itertools import chain
 from operator import itemgetter
-from typing import TYPE_CHECKING, Any, Dict, Iterable, Iterator, List, Literal, Sequence
+from typing import TYPE_CHECKING, Any, Dict, Iterable, Iterator, List, Literal
 
 from beets import IncludeLazyConfig, config, library, plugins
 
@@ -64,10 +64,10 @@ class BandcampRequestsHandler:
     _log: logging.Logger
     config: IncludeLazyConfig
 
-    def _exc(self, msg_template: str, *args: Sequence[str]) -> None:
+    def _exc(self, msg_template: str, *args: object) -> None:
         self._log.log(logging.WARNING, msg_template, *args, exc_info=True)
 
-    def _info(self, msg_template: str, *args: Sequence[str]) -> None:
+    def _info(self, msg_template: str, *args: object) -> None:
         self._log.log(logging.DEBUG, msg_template, *args, exc_info=False)
 
     def _get(self, url: str) -> str: