translations: make sure we do not re-translate

Author: snejus

beetsplug/lyrics.py

@@ -733,6 +733,7 @@ def scrape(cls, html: str) -> str | None:
 class Translator(RequestHandler):
     TRANSLATE_URL = "https://api.cognitive.microsofttranslator.com/translate"
     LINE_PARTS_RE = re.compile(r"^(\[\d\d:\d\d.\d\d\]|) *(.*)$")
+    remove_translations = partial(re.compile(r" / [^\n]+").sub, "")
 
     _log: beets.logging.Logger
     api_key: str
@@ -802,21 +803,33 @@ def append_translations(self, lines: Iterable[str]) -> list[str]:
     def translate(self, new_lyrics: str, old_lyrics: str) -> str:
         """Translate the given lyrics to the target language.
 
+        Check old lyrics for existing translations and return them if their
+        original text matches the new lyrics. This is to avoid translating
+        the same lyrics multiple times.
+
         If the lyrics are already in the target language or not in any of
         of the source languages (if configured), they are returned as is.
 
         The footer with the source URL is preserved, if present.
         """
+        if (
+            " / " in old_lyrics
+            and self.remove_translations(old_lyrics) == new_lyrics
+        ):
+            self.info("🔵 Translations already exist")
+            return old_lyrics
+
         lyrics_language = langdetect.detect(new_lyrics)
         if lyrics_language != self.to_lang and (
             not self.from_langs or lyrics_language in self.from_langs
         ):
             lyrics, *url = new_lyrics.split("\n\nSource: ")
             with self.handle_request():
                 translated_lines = self.append_translations(lyrics.splitlines())
+                self.info("🟢 Translated lyrics to {}", self.to_lang.upper())
                 return "\n\nSource: ".join(["\n".join(translated_lines), *url])
 
-        return lyrics
+        return new_lyrics
 
 
 @dataclass
@@ -1052,12 +1065,7 @@ def add_item_lyrics(self, item: Item, write: bool) -> None:
         if lyrics := self.find_lyrics(item):
             self.info("🟢 Found lyrics: {0}", item)
             if translator := self.translator:
-                initial_lyrics = lyrics
-                if (lyrics := translator.translate(lyrics)) != initial_lyrics:
-                    self.info(
-                        "🟢 Added translation to {}",
-                        self.config["translate_to"].get().upper(),
-                    )
+                lyrics = translator.translate(lyrics, item.lyrics)
         else:
             self.info("🔴 Lyrics not found: {}", item)
             lyrics = self.config["fallback"].get()

test/plugins/test_lyrics.py

@@ -560,7 +560,7 @@ def callback(request, _):
         requests_mock.post(lyrics.Translator.TRANSLATE_URL, json=callback)
 
     @pytest.mark.parametrize(
-        "initial_lyrics, expected",
+        "new_lyrics, old_lyrics, expected",
         [
             pytest.param(
                 """
@@ -569,6 +569,7 @@ def callback(request, _):
                 My body wouldn't let me hide it (Hide it)
                 No matter what, I wouldn't fold (Wouldn't fold, wouldn't fold)
                 Ridin' through the thunder, lightnin'""",
+                "",
                 """
                 [Refrain: Doja Cat] / [Refrain : Doja Cat]
                 Hard for me to let you go (Let you go, let you go) / Difficile pour moi de te laisser partir (Te laisser partir, te laisser partir)
@@ -584,6 +585,7 @@ def callback(request, _):
                 [00:01.00] Some more synced lyrics
 
                 Source: https://lrclib.net/api/123""",
+                "",
                 """
                 [00:00.00] Some synced lyrics / Quelques paroles synchronisées
                 [00:00:50]
@@ -592,14 +594,20 @@ def callback(request, _):
                 Source: https://lrclib.net/api/123""",  # noqa: E501
                 id="synced",
             ),
+            pytest.param(
+                "Some lyrics",
+                "Some lyrics / Some translation",
+                "Some lyrics / Some translation",
+                id="already translated",
+            ),
         ],
     )
-    def test_translate(self, initial_lyrics, expected):
+    def test_translate(self, new_lyrics, old_lyrics, expected):
         plugin = lyrics.LyricsPlugin()
         bing = lyrics.Translator(plugin._log, "123", ["en"], "fr")
 
         assert bing.translate(
-            textwrap.dedent(initial_lyrics)
+            textwrap.dedent(new_lyrics), old_lyrics
         ) == textwrap.dedent(expected)