Backup_Repos/beets
1
0
Fork 0
mirror of https://github.com/beetbox/beets.git synced 2025-12-06 16:42:42 +01:00
Code Issues Projects Releases Wiki Activity

Include class name in the log messages

Browse source
This commit is contained in:
Šarūnas Nejus 2024-09-06 07:35:24 +01:00
parent 283c513c72
commit cb29605bfd
No known key found for this signature in database
GPG key ID: DD28F6704DBE3435
2 changed files with 64 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

113
beetsplug/lyrics.py
View file

@ -28,8 +28,8 @@ from contextlib import contextmanager, suppress
from dataclasses import dataclass from dataclasses import dataclass
from functools import cached_property, partial, total_ordering from functools import cached_property, partial, total_ordering
from http import HTTPStatus from http import HTTPStatus
from typing import TYPE_CHECKING, ClassVar, Iterable, Iterator from typing import TYPE_CHECKING, Any, ClassVar, Iterable, Iterator
from urllib.parse import quote, urlparse from urllib.parse import quote, urlencode, urlparse
import requests import requests
from typing_extensions import TypedDict from typing_extensions import TypedDict
@ -58,6 +58,8 @@ try:
except ImportError: except ImportError:
HAS_LANGDETECT = False HAS_LANGDETECT = False
JSONDict = dict[str, Any]
DIV_RE = re.compile(r"<(/?)div>?", re.I) DIV_RE = re.compile(r"<(/?)div>?", re.I)
COMMENT_RE = re.compile(r"<!--.*-->", re.S) COMMENT_RE = re.compile(r"<!--.*-->", re.S)
TAG_RE = re.compile(r"<[^>]*>") TAG_RE = re.compile(r"<[^>]*>")
@ -258,14 +260,37 @@ else:
class RequestHandler: class RequestHandler:
_log: beets.logging.Logger _log: beets.logging.Logger
def fetch_text(self, url: str, **kwargs) -> str: def debug(self, message: str, *args) -> None:
"""Log a debug message with the class name."""
self._log.debug(f"{self.__class__.__name__}: {message}", *args)
def info(self, message: str, *args) -> None:
"""Log an info message with the class name."""
self._log.info(f"{self.__class__.__name__}: {message}", *args)
def warn(self, message: str, *args) -> None:
"""Log warning with the class name."""
self._log.warning(f"{self.__class__.__name__}: {message}", *args)
@staticmethod
def format_url(url: str, params: JSONDict | None) -> str:
if not params:
return url
return f"{url}?{urlencode(params)}"
def fetch_text(
self, url: str, params: JSONDict | None = None, **kwargs
) -> str:
"""Return text / HTML data from the given URL.""" """Return text / HTML data from the given URL."""
self._log.debug("Fetching HTML from {}", url) url = self.format_url(url, params)
self.debug("Fetching HTML from {}", url)
return r_session.get(url, **kwargs).text return r_session.get(url, **kwargs).text
def fetch_json(self, url: str, **kwargs): def fetch_json(self, url: str, params: JSONDict | None = None, **kwargs):
"""Return JSON data from the given URL.""" """Return JSON data from the given URL."""
self._log.debug("Fetching JSON from {}", url) url = self.format_url(url, params)
self.debug("Fetching JSON from {}", url)
return r_session.get(url, **kwargs).json() return r_session.get(url, **kwargs).json()
@contextmanager @contextmanager
@ -273,9 +298,9 @@ class RequestHandler:
try: try:
yield yield
except requests.JSONDecodeError: except requests.JSONDecodeError:
self._log.warning("Could not decode response JSON data") self.warn("Could not decode response JSON data")
except requests.RequestException as exc: except requests.RequestException as exc:
self._log.warning("Request error: {}", exc) self.warn("Request error: {}", exc)
class Backend(RequestHandler): class Backend(RequestHandler):
@ -377,10 +402,6 @@ class LRCLib(Backend):
GET_URL = f"{BASE_URL}/get" GET_URL = f"{BASE_URL}/get"
SEARCH_URL = f"{BASE_URL}/search" SEARCH_URL = f"{BASE_URL}/search"
def warn(self, message: str, *args) -> None:
"""Log a warning message with the class name."""
self._log.warning(f"{self.__class__.__name__}: {message}", *args)
def fetch_candidates( def fetch_candidates(
self, artist: str, title: str, album: str, length: int self, artist: str, title: str, album: str, length: int
) -> Iterator[list[LRCLibItem]]: ) -> Iterator[list[LRCLibItem]]:
@ -415,13 +436,12 @@ class LRCLib(Backend):
"""Fetch lyrics text for the given song data.""" """Fetch lyrics text for the given song data."""
evaluate_item = partial(LRCLyrics.make, target_duration=length) evaluate_item = partial(LRCLyrics.make, target_duration=length)
try: for group in self.fetch_candidates(artist, title, album, length):
for group in self.fetch_candidates(artist, title, album, length): candidates = [evaluate_item(item) for item in group]
candidates = [evaluate_item(item) for item in group] if item := self.pick_best_match(candidates):
if item := self.pick_best_match(candidates): return item.get_text(self.config["synced"])
return item.get_text(self.config["synced"])
except StopIteration: return None
return None
class DirectBackend(Backend): class DirectBackend(Backend):
@ -463,9 +483,7 @@ class MusiXmatch(DirectBackend):
html = self.fetch_text(url) html = self.fetch_text(url)
if "We detected that your IP is blocked" in html: if "We detected that your IP is blocked" in html:
self._log.warning( self.warn("Failed: Blocked IP address")
"we are blocked at MusixMatch: url %s failed" % url
)
return None return None
html_parts = html.split('<p class="mxm-lyrics__content') html_parts = html.split('<p class="mxm-lyrics__content')
# Sometimes lyrics come in 2 or more parts # Sometimes lyrics come in 2 or more parts
@ -507,7 +525,7 @@ class SearchBackend(Backend):
if math.isclose(max_dist, self.dist_thresh, abs_tol=0.4): if math.isclose(max_dist, self.dist_thresh, abs_tol=0.4):
# log out the candidate that did not make it but was close. # log out the candidate that did not make it but was close.
# This may show a matching candidate with some noise in the name # This may show a matching candidate with some noise in the name
self._log.debug( self.debug(
"({}, {}) does not match ({}, {}) but dist was close: {:.2f}", "({}, {}) does not match ({}, {}) but dist was close: {:.2f}",
artist, artist,
title, title,
@ -542,9 +560,6 @@ class Genius(SearchBackend):
then attempt to scrape that url for the lyrics. then attempt to scrape that url for the lyrics.
""" """
json = self._search(artist, title) json = self._search(artist, title)
if not json:
self._log.debug("Genius API request returned invalid JSON")
return None
check = partial(self.check_match, artist, title) check = partial(self.check_match, artist, title)
for hit in json["response"]["hits"]: for hit in json["response"]["hits"]:
@ -588,7 +603,7 @@ class Genius(SearchBackend):
lyrics_divs = soup.find_all("div", {"data-lyrics-container": True}) lyrics_divs = soup.find_all("div", {"data-lyrics-container": True})
if not lyrics_divs: if not lyrics_divs:
self._log.debug("Received unusual song page html") self.debug("Received unusual song page html")
return self._try_extracting_lyrics_from_non_data_lyrics_container( return self._try_extracting_lyrics_from_non_data_lyrics_container(
soup soup
) )
@ -611,10 +626,10 @@ class Genius(SearchBackend):
class_=re.compile("LyricsPlaceholder__Message"), class_=re.compile("LyricsPlaceholder__Message"),
string="This song is an instrumental", string="This song is an instrumental",
): ):
self._log.debug("Detected instrumental") self.debug("Detected instrumental")
return INSTRUMENTAL_LYRICS return INSTRUMENTAL_LYRICS
else: else:
self._log.debug("Couldn't scrape page using known layouts") self.debug("Couldn't scrape page using known layouts")
return None return None
lyrics_div = verse_div.parent lyrics_div = verse_div.parent
@ -654,6 +669,8 @@ class Tekstowo(DirectBackend):
self.fetch_text(self.build_url(artist, title)) self.fetch_text(self.build_url(artist, title))
) )
return None
def extract_lyrics(self, html: str) -> str | None: def extract_lyrics(self, html: str) -> str | None:
html = _scrape_strip_cruft(html) html = _scrape_strip_cruft(html)
html = _scrape_merge_paragraphs(html) html = _scrape_merge_paragraphs(html)
@ -747,7 +764,7 @@ class Google(SearchBackend):
bad_triggers_occ = [] bad_triggers_occ = []
nb_lines = text.count("\n") nb_lines = text.count("\n")
if nb_lines <= 1: if nb_lines <= 1:
self._log.debug("Ignoring too short lyrics '{0}'", text) self.debug("Ignoring too short lyrics '{}'", text)
return False return False
elif nb_lines < 5: elif nb_lines < 5:
bad_triggers_occ.append("too_short") bad_triggers_occ.append("too_short")
@ -766,7 +783,7 @@ class Google(SearchBackend):
) )
if bad_triggers_occ: if bad_triggers_occ:
self._log.debug("Bad triggers detected: {0}", bad_triggers_occ) self.debug("Bad triggers detected: {}", bad_triggers_occ)
return len(bad_triggers_occ) < 2 return len(bad_triggers_occ) < 2
def slugify(self, text): def slugify(self, text):
@ -779,7 +796,7 @@ class Google(SearchBackend):
text = unicodedata.normalize("NFKD", text).encode("ascii", "ignore") text = unicodedata.normalize("NFKD", text).encode("ascii", "ignore")
text = str(re.sub(r"[-\s]+", " ", text.decode("utf-8"))) text = str(re.sub(r"[-\s]+", " ", text.decode("utf-8")))
except UnicodeDecodeError: except UnicodeDecodeError:
self._log.exception("Failing to normalize '{0}'", text) self.debug("Failed to normalize '{}'", text)
return text return text
BY_TRANS = ["by", "par", "de", "von"] BY_TRANS = ["by", "par", "de", "von"]
@ -831,7 +848,7 @@ class Google(SearchBackend):
continue continue
if self.is_lyrics(lyrics, artist): if self.is_lyrics(lyrics, artist):
self._log.debug("got lyrics from {0}", item["displayLink"]) self.debug("Got lyrics from {}", item["displayLink"])
return lyrics return lyrics
return None return None
@ -900,9 +917,7 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
# configuration includes `google`. This way, the source # configuration includes `google`. This way, the source
# is silent by default but can be enabled just by # is silent by default but can be enabled just by
# setting an API key. # setting an API key.
self._log.debug( self.debug("Disabling google source: " "no API key configured.")
"Disabling google source: " "no API key configured."
)
sources.remove("google") sources.remove("google")
self.config["bing_lang_from"] = [ self.config["bing_lang_from"] = [
@ -910,15 +925,14 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
] ]
if not HAS_LANGDETECT and self.config["bing_client_secret"].get(): if not HAS_LANGDETECT and self.config["bing_client_secret"].get():
self._log.warning( self.warn(
"To use bing translations, you need to " "To use bing translations, you need to install the langdetect "
"install the langdetect module. See the " "module. See the documentation for further details."
"documentation for further details."
) )
self.backends = [ self.backends = [
self.SOURCE_BACKENDS[source](self.config, self._log) self.SOURCE_BACKENDS[s](self.config, self._log.getChild(s))
for source in sources for s in sources
] ]
def sanitize_bs_sources(self, sources): def sanitize_bs_sources(self, sources):
@ -949,8 +963,6 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
r = r_session.post(oauth_url, params=params) r = r_session.post(oauth_url, params=params)
return r.json()["access_token"] return r.json()["access_token"]
return None
def commands(self): def commands(self):
cmd = ui.Subcommand("lyrics", help="fetch song lyrics") cmd = ui.Subcommand("lyrics", help="fetch song lyrics")
cmd.parser.add_option( cmd.parser.add_option(
@ -1095,7 +1107,7 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
""" """
# Skip if the item already has lyrics. # Skip if the item already has lyrics.
if not force and item.lyrics: if not force and item.lyrics:
self._log.info("lyrics already present: {0}", item) self.info("Lyrics already present: {}", item)
return return
lyrics_matches = [] lyrics_matches = []
@ -1111,7 +1123,7 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
lyrics = "\n\n---\n\n".join(filter(None, lyrics_matches)) lyrics = "\n\n---\n\n".join(filter(None, lyrics_matches))
if lyrics: if lyrics:
self._log.info("fetched lyrics: {0}", item) self.info("Lyrics found: {}", item)
if HAS_LANGDETECT and self.config["bing_client_secret"].get(): if HAS_LANGDETECT and self.config["bing_client_secret"].get():
lang_from = langdetect.detect(lyrics) lang_from = langdetect.detect(lyrics)
if self.config["bing_lang_to"].get() != lang_from and ( if self.config["bing_lang_to"].get() != lang_from and (
@ -1122,7 +1134,7 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
lyrics, self.config["bing_lang_to"] lyrics, self.config["bing_lang_to"]
) )
else: else:
self._log.info("lyrics not found: {0}", item) self.info("Lyrics not found: {}", item)
fallback = self.config["fallback"].get() fallback = self.config["fallback"].get()
if fallback: if fallback:
lyrics = fallback lyrics = fallback
@ -1137,13 +1149,10 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
"""Fetch lyrics, trying each source in turn. Return a string or """Fetch lyrics, trying each source in turn. Return a string or
None if no lyrics were found. None if no lyrics were found.
""" """
self.info("Fetching lyrics for {} - {}", artist, title)
for backend in self.backends: for backend in self.backends:
with backend.handle_request(): with backend.handle_request():
if lyrics := backend.fetch(artist, title, *args): if lyrics := backend.fetch(artist, title, *args):
self._log.debug(
"got lyrics from backend: {0}",
backend.__class__.__name__,
)
return _scrape_strip_cruft(lyrics, True) return _scrape_strip_cruft(lyrics, True)
return None return None
@ -1152,7 +1161,7 @@ class LyricsPlugin(RequestHandler, plugins.BeetsPlugin):
from xml.etree import ElementTree from xml.etree import ElementTree
if not (token := self.bing_access_token): if not (token := self.bing_access_token):
self._log.warning( self.warn(
"Could not get Bing Translate API access token. " "Could not get Bing Translate API access token. "
"Check your 'bing_client_secret' password." "Check your 'bing_client_secret' password."
) )

6
test/plugins/test_lyrics.py
View file

@ -230,9 +230,9 @@ class TestLyricsPlugin(LyricsPluginMixin):
[ [
( (
{"status_code": HTTPStatus.BAD_GATEWAY}, {"status_code": HTTPStatus.BAD_GATEWAY},
r"lyrics: Request error: 502", r"LRCLib: Request error: 502",
), ),
({"text": "invalid"}, r"lyrics: Could not decode.*JSON"), ({"text": "invalid"}, r"LRCLib: Could not decode.*JSON"),
], ],
) )
def test_error_handling( def test_error_handling(
@ -243,7 +243,7 @@ class TestLyricsPlugin(LyricsPluginMixin):
request_kwargs, request_kwargs,
expected_log_match, expected_log_match,
): ):
"""Errors are logged with the plugin name.""" """Errors are logged with the backend name."""
requests_mock.get(lyrics.LRCLib.SEARCH_URL, **request_kwargs) requests_mock.get(lyrics.LRCLib.SEARCH_URL, **request_kwargs)
assert lyrics_plugin.get_lyrics("", "", "", 0.0) is None assert lyrics_plugin.get_lyrics("", "", "", 0.0) is None