Backup_Repos/beets
1
0
Fork 0
mirror of https://github.com/beetbox/beets.git synced 2025-12-06 08:39:17 +01:00
Code Issues Projects Releases Wiki Activity

translations: use a more distinctive separator

Browse source 
I found that the translator would sometimes replace the pipe character
with another symbol (maybe it got confused thinking the character is
part of the text?).

Added spaces around the pipe to make it more clear that it's definitely
the separator.
This commit is contained in:
Šarūnas Nejus 2025-01-13 01:48:29 +00:00
parent 43032f7bc7
commit b713d72612
No known key found for this signature in database
GPG key ID: DD28F6704DBE3435
2 changed files with 14 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
beetsplug/lyrics.py
View file

@ -744,6 +744,7 @@ class Google(SearchBackend):
class Translator(RequestHandler): class Translator(RequestHandler):
TRANSLATE_URL = "https://api.cognitive.microsofttranslator.com/translate" TRANSLATE_URL = "https://api.cognitive.microsofttranslator.com/translate"
LINE_PARTS_RE = re.compile(r"^(\[\d\d:\d\d.\d\d\]|) *(.*)$") LINE_PARTS_RE = re.compile(r"^(\[\d\d:\d\d.\d\d\]|) *(.*)$")
SEPARATOR = " | "
remove_translations = partial(re.compile(r" / [^\n]+").sub, "") remove_translations = partial(re.compile(r" / [^\n]+").sub, "")
_log: Logger _log: Logger
@ -773,14 +774,16 @@ class Translator(RequestHandler):
map the translations back to the original texts. map the translations back to the original texts.
""" """
unique_texts = list(dict.fromkeys(texts)) unique_texts = list(dict.fromkeys(texts))
text = self.SEPARATOR.join(unique_texts)
data: list[TranslatorAPI.Response] = self.post_json( data: list[TranslatorAPI.Response] = self.post_json(
self.TRANSLATE_URL, self.TRANSLATE_URL,
headers={"Ocp-Apim-Subscription-Key": self.api_key}, headers={"Ocp-Apim-Subscription-Key": self.api_key},
json=[{"text": "|".join(unique_texts)}], json=[{"text": text}],
params={"api-version": "3.0", "to": self.to_language}, params={"api-version": "3.0", "to": self.to_language},
) )
translations = data[0]["translations"][0]["text"].split("|") translated_text = data[0]["translations"][0]["text"]
translations = translated_text.split(self.SEPARATOR)
trans_by_text = dict(zip(unique_texts, translations)) trans_by_text = dict(zip(unique_texts, translations))
return list(zip(texts, (trans_by_text.get(t, "") for t in texts))) return list(zip(texts, (trans_by_text.get(t, "") for t in texts)))

18
test/plugins/test_lyrics.py
View file

@ -554,23 +554,23 @@ class TestTranslation:
if b"Refrain" in request.body: if b"Refrain" in request.body:
translations = ( translations = (
"" ""
"|[Refrain : Doja Cat]" " | [Refrain : Doja Cat]"
"|Difficile pour moi de te laisser partir (Te laisser partir, te laisser partir)" # noqa: E501 " | Difficile pour moi de te laisser partir (Te laisser partir, te laisser partir)" # noqa: E501
"|Mon corps ne me laissait pas le cacher (Cachez-le)" " | Mon corps ne me laissait pas le cacher (Cachez-le)"
"|Quoi qu’il arrive, je ne plierais pas (Ne plierait pas, ne plierais pas)" # noqa: E501 " | Quoi qu’il arrive, je ne plierais pas (Ne plierait pas, ne plierais pas)" # noqa: E501
"|Chevauchant à travers le tonnerre, la foudre" " | Chevauchant à travers le tonnerre, la foudre"
) )
elif b"00:00.00" in request.body: elif b"00:00.00" in request.body:
translations = ( translations = (
"" ""
"|[00:00.00] Quelques paroles synchronisées" " | [00:00.00] Quelques paroles synchronisées"
"|[00:01.00] Quelques paroles plus synchronisées" " | [00:01.00] Quelques paroles plus synchronisées"
) )
else: else:
translations = ( translations = (
"" ""
"|Quelques paroles synchronisées" " | Quelques paroles synchronisées"
"|Quelques paroles plus synchronisées" " | Quelques paroles plus synchronisées"
) )
return [ return [