JDM170/deezspot-spotizerr-dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #9 from lexitronic/fix-track-matching

Browse Source 
Use `rapidfuzz` instead of `difflib`, use `_remove_parentheses()` during ISRC search, remove redundant `title_match` entries.
This commit is contained in:
Spotizerr
2025-08-19 19:53:38 -06:00
committed by GitHub
parent d81c57e357 5886904a72
commit cd16cbabf3
2 changed files with 10 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
deezspot/deezloader/__init__.py
View File

@@ -47,7 +47,6 @@ from deezspot.libutils.others_settings import (
)
from deezspot.libutils.logging_utils import ProgressReporter, logger, report_progress
import requests
from difflib import SequenceMatcher
from deezspot.models.callback.callbacks import (
trackCallbackObject,
@@ -64,14 +63,14 @@ from deezspot.models.callback.album import albumObject as albumCbObject
from deezspot.models.callback.playlist import playlistObject as playlistCbObject
from deezspot.models.callback.common import IDs
from deezspot.models.callback.user import userObject
from rapidfuzz import fuzz
def _sim(a: str, b: str) -> float:
a = (a or '').strip().lower()
b = (b or '').strip().lower()
if not a or not b:
return 0.0
return SequenceMatcher(None, a, b).ratio()
return fuzz.partial_ratio(a, b) / 100
# Clean for searching on Deezer
def _remove_parentheses(string: str) -> str:
@@ -438,8 +437,8 @@ class DeeLogin:
dz_json = dz
tn = (dz_json.get('track_position') or dz_json.get('track_number') or 0)
title_match = max(
_sim(spo_title, dz_json.get('title', '')),
_sim(spo_title, dz_json.get('title_short', '')),
_sim(_remove_parentheses(spo_title), _remove_parentheses(dz_json.get('title', ''))),
_sim(_remove_parentheses(spo_title), _remove_parentheses(dz_json.get('title_short', '')))
)
album_match = _sim(spo_album_title, (dz_json.get('album') or {}).get('title', ''))
t_isrc = (dz_json.get('isrc') or '').upper()
@@ -460,15 +459,11 @@ class DeeLogin:
candidates = []
for cand in candidates:
title_match_1 = max(
_sim(spo_title, dz_json.get('title', '')),
_sim(spo_title, dz_json.get('title_short', ''))
title_match = max(
_sim(_remove_parentheses(spo_title), _remove_parentheses(cand.get('title', ''))),
_sim(_remove_parentheses(spo_title), _remove_parentheses(cand.get('title_short', '')))
)
title_match_2 = max(
_sim(_remove_parentheses(spo_title), _remove_parentheses(dz_json.get('title', ''))),
_sim(_remove_parentheses(spo_title), _remove_parentheses(dz_json.get('title_short', '')))
)
if max(title_match_1, title_match_2) < 0.90:
if title_match < 0.90:
continue
c_id = cand.get('id')
if not c_id:

3
setup.py
View File

@@ -27,6 +27,7 @@ setup(
"fastapi==0.116.1",
"uvicorn[standard]==0.35.0",
"spotipy-anon==1.5.2",
"librespot-spotizerr==0.3.0"
"librespot-spotizerr==0.3.0",
"rapidfuzz"
],
)