Merge branch 'issue/18-19-20'

.github/workflows/build.yml

@@ -26,13 +26,12 @@ jobs:
       - name: Pytest
         run: |
           poetry run pytest
-          poetry run coverage xml
       - name: Flake8
         run: poetry run flake8 . --output-file flake.log  --exit-zero
       - name: Pylint
         run: poetry run pylint --output pylint.log --exit-zero beetsplug/**/*.py
       - name: SonarCloud Scan
-        uses: sonarsource/sonarcloud-github-action@master
+        uses: SonarSource/sonarcloud-github-action@master
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}

CHANGELOG.md

@@ -1,3 +1,27 @@
+## [0.10.1] 2021-09-13
+
+### Fixed
+
+- Fixed #18 by handling cases when a track duration is not given.
+- Fixed #19 where artist names like **SUNN O)))** would get incorrectly mistreated by
+  the album name cleanup logic due to multiple consecutive parentheses. The fix involved
+  adding some rules around it: they are now deduped _only if_
+
+  - they are preceded with a space
+  - or they enclose remix / edit info and are the last characters in the album name
+
+- Fixed #20 where dynamically obtained label names used in further REs caused `re.error`
+  since they were not appropriately escaped (for example, `label: /m\ records`).
+
+Thanks @arogl for reporting each of the above!
+
+- `album`: Keep label in the album name if it's immediately followed by an apostrophe. An
+  example scenario:
+  - `label: Mike`
+  - `album: Mike's Creations`
+
+[0.10.1]: https://github.com/snejus/beetcamp/releases/tag/0.10.1
+
 ## [0.10.0] 2021-09-10
 
 ### Fixed
@@ -47,6 +71,7 @@
   - Improved the way **Various Artists** are cleaned up when catalognum is available
 
 - `albumartist`:
+
   - If **various** is specified as the albumartist, make it **Various Artists**
   - When the label have set their name as the albumartist in every field, and if the
     actual albumartist could be inferred from the album name, use the inferred name.

beetsplug/bandcamp/__init__.py

@@ -29,7 +29,7 @@
 from beets import __version__, config, library, plugins
 from beets.autotag.hooks import AlbumInfo, TrackInfo
 from beets.importer import ImportTask
-from beetsplug import fetchart
+from beetsplug import fetchart  # type: ignore[attr-defined]
 
 from ._metaguru import DATA_SOURCE, DEFAULT_MEDIA, Metaguru, urlify
 
@@ -266,7 +266,7 @@ def handle(self, guru: Metaguru, attr: str, _id: str) -> Any:
         except (KeyError, ValueError, AttributeError):
             self._info("Failed obtaining {}", _id)
             return None
-        except Exception:
+        except Exception:  # pylint: disable=broad-except
             url = "https://github.com/snejus/beetcamp/issues/new"
             self._exc("Unexpected error obtaining {}, please report at {}", _id, url)
             return None

beetsplug/bandcamp/_metaguru.py

@@ -103,8 +103,10 @@ def parse_track_name(name: str, catalognum: str = "") -> Dict[str, Optional[str]
             track["track_alt"] = track_alt
             name = name.replace(track_alt, "")
 
+        # do not strip a period from the end since it could end with an abbrev
+        name = name.lstrip(".")
         # in most cases that's the delimiter between the artist and the title
-        parts = re.split(r"\s-\s|\s?-\s|\s-\s?", name.strip(",.- "))
+        parts = re.split(r"\s-\s|\s?-\s|\s-\s?", name.strip(",- "))
 
         # title is always given
         track["title"] = parts.pop(-1)
@@ -134,28 +136,36 @@ def parse_catalognum(album: str, disctitle: str, description: str, label: str) -
         3. Check whether label name is followed by numbers
         4. Check album name and disctitle using more flexible rules.
         """
+        label_excl: Tuple[Optional[Pattern], Optional[str]] = (None, None)
+        if label:
+            escaped = re.escape(label)
+            label_excl = (re.compile(rf"({escaped}\s?[0-9]+)"), album)
+
         for pattern, source in [
             (PATTERNS["desc_catalognum"], description),
             (PATTERNS["quick_catalognum"], album),
-            (rf"({label}\s?[0-9]+)", album) if label else (None, None),
+            label_excl,
             (PATTERNS["catalognum"], album),
             (PATTERNS["catalognum"], disctitle),
         ]:
             if not pattern:
                 continue
 
-            match = re.search(pattern, re.sub(PATTERNS["catalognum_excl"], "", source))
+            match = pattern.search(PATTERNS["catalognum_excl"].sub("", source))
             if match:
                 return match.groups()[0]
         return ""
 
     @staticmethod
     def get_duration(source: JSONDict) -> int:
-        return [
-            floor(x.get("value", 0))
+        prop = [
+            x.get("value") or 0
             for x in source.get("additionalProperty", [])
             if x.get("name") == "duration_secs"
-        ][0]
+        ]
+        if len(prop) == 1:
+            return floor(prop[0])
+        return 0
 
     @staticmethod
     def clean_name(name: str, *args: str, remove_extra: bool = False) -> str:
@@ -167,13 +177,16 @@ def clean_name(name: str, *args: str, remove_extra: bool = False) -> str:
         """
         # catalognum, album, albumartist
         for arg in args:
-            name = name.replace(arg, "")
+            arg = re.escape(arg)
+            name = re.sub(rf"{arg}((?=[^'])|$)", "", name)
 
         # redundant spaces, duoble quotes, parentheses
         for pat, repl in [
             (r"\s\s+", " "),
             (r"\(\s+|(- )?\(+", "("),
-            (r"\s+\)|\)+", ")"),
+            # Remove duplicate closing parens if they follow a space
+            # or enclose mix/edit info and are at the end
+            (r" \)+|(?<=(?i:.mix|edit))\)+$", ")"),
             (r'"', ""),
         ]:
             name = re.sub(pat, repl, name)
@@ -206,7 +219,7 @@ def clean_name(name: str, *args: str, remove_extra: bool = False) -> str:
         def clean(patstr: str, text: str) -> str:
             return re.sub(patstr, "", text)
 
-        return clean(empty_parens, clean(rubbish, name)).strip("/-|([. ") or default
+        return clean(empty_parens, clean(rubbish, name)).strip("/-|([ ") or default
 
     @staticmethod
     def _get_media_index(meta: JSONDict) -> JSONDict:
@@ -393,7 +406,7 @@ def tracks(self) -> List[JSONDict]:
                 index=index,
                 medium_index=index,
                 track_id=raw_item.get("@id"),
-                length=self.get_duration(raw_item),
+                length=self.get_duration(raw_item) or None,
                 **self.parse_track_name(name, catalognum),
             )
             track["artist"] = self.get_track_artist(

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "beetcamp"
-version = "0.10.0"
+version = "0.10.1"
 description = "Bandcamp autotagger source for beets (http://beets.io)."
 authors = ["Šarūnas Nejus <[email protected]>"]
 readme = "README.md"

setup.cfg

@@ -33,6 +33,7 @@ addopts =
 
 markers =
     need_connection: end-to-end tests that require internet connection
+    jsons: tests that compare parsed releases with json fixtures
     parsing: parsing tests
 
 testpaths =

tests/conftest.py

@@ -690,3 +690,65 @@ def edge_cases() -> ReleaseInfo:
         mediums=1,
     )
     return info
+
+
+@pytest.fixture
+def issues_18() -> ReleaseInfo:
+    albumartist = "General Dicon"
+    info = ReleaseInfo(
+        artist_id="https://54thregiment.bandcamp.com",
+        album_id="https://54thregiment.bandcamp.com/album/fall-in",
+        media="Digital Media",
+        disctitle=None,
+    )
+    tracks = [
+        ("54-regi", albumartist, "54 regi", None, None),
+        ("54-regi-2", albumartist, "54 regi", 227, None),
+        (
+            "mile-high-monsta-ft-nation",
+            albumartist,
+            "Mile high monsta ft.nation",
+            157,
+            None,
+        ),
+        ("pure-entertainment", albumartist, "Pure entertainment", 166, None),
+        ("smoke-interlude", albumartist, "Smoke interlude", 69, None),
+        (
+            "ganja-tune-ft-spellbinder",
+            albumartist,
+            "Ganja tune ft.spellbinder",
+            235,
+            None,
+        ),
+        ("war-ft-spellbinder", albumartist, "War ft.spellbinder", 203, None),
+        (
+            "w-m-m-a-where-my-money-ft-spellbinder",
+            albumartist,
+            "w.m.m.a(where my money @) ft.Spellbinder",
+            147,
+            None,
+        ),
+        ("due-time", albumartist, "Due time", 257, None),
+        ("hustle-aint-no-game", albumartist, "Hustle Ain't no game", 197, None),
+        (
+            "its-ova-ft-scrilla-scratch",
+            albumartist,
+            "It's ova ft. scrilla scratch",
+            201,
+            None,
+        ),
+        ("dont-stop-ft-spellbinder", albumartist, "Don't stop ft.Spellbinder", 244, None),
+    ]
+    info.set_albuminfo(
+        tracks,
+        album="FALL IN",
+        albumartist=albumartist,
+        albumtype="album",
+        catalognum="",
+        label="54th Regiment",
+        release_date=date(2011, 4, 20),
+        va=False,
+        country="US",
+        mediums=1,
+    )
+    return info