Merge pull request 'feat(translation): per-field language detection for mixed-language posts' (#205) from dev into main

backend/app/tasks/translation.py

@@ -250,29 +250,39 @@ def _summary(status: str, translated: int, scanned: int) -> str:
     return f"translated={translated} scanned={scanned}"
 
 
+def _translate_field(text: str, base_url: str, target: str):
+    """Translate ONE field independently. Returns (translated, source_lang,
+    engine_version), or (None, None, None) when there's nothing to store — empty
+    text, already the target language, or a passthrough (engine "none"). Per-field
+    (not aggregate first-item) detection so a non-English description still gets
+    translated when the title is already English (mixed-language posts)."""
+    if not text:
+        return None, None, None
+    res = ic.translate([text], base_url=base_url, target=target)
+    detected = res["detected_lang"] or target
+    if detected == target or res["engine"] == "none":
+        return None, None, None
+    return res["translations"][0], detected, res["engine_version"]
+
+
 def _translate_one(session, post, base_url: str, target: str) -> int:
-    """Translate one post's title/description in place. Returns 1 if it stored a
-    translation, 0 for passthrough/empty (which still marks the post handled)."""
+    """Translate a post's title/description in place, each field independently.
+    Returns 1 if it stored at least one translation, 0 when the post is all
+    passthrough/empty (still marks it handled so the sweep won't revisit it)."""
     title = (post.post_title or "").strip()
     desc = (html_to_plain(post.description) if post.description else "") or ""
     desc = desc.strip()
-    fields: list[tuple[str, str]] = []
-    if title:
-        fields.append(("title", title))
-    if desc:
-        fields.append(("desc", desc))
-    if not fields:
-        post.translated_source_lang = target   # nothing to translate → handled
+    title_tr, title_lang, title_ev = _translate_field(title, base_url, target)
+    desc_tr, desc_lang, desc_ev = _translate_field(desc, base_url, target)
+    if title_tr is None and desc_tr is None:
+        # Nothing non-target (or nothing to translate) → handled, store nothing.
+        post.translated_source_lang = target
         return 0
-    res = ic.translate([t for _, t in fields], base_url=base_url, target=target)
-    detected = res["detected_lang"] or target
-    if detected == target or res["engine"] == "none":
-        post.translated_source_lang = target   # already target language → handled
-        return 0
-    by_field = {f: res["translations"][i] for i, (f, _) in enumerate(fields)}
-    post.post_title_translated = by_field.get("title")
-    post.description_translated = by_field.get("desc")
-    post.translated_source_lang = detected
-    post.translation_engine_version = res["engine_version"]
+    post.post_title_translated = title_tr
+    post.description_translated = desc_tr
+    # Source lang = whichever field was actually non-target (for a mixed post,
+    # the translated field's language, not the already-English one).
+    post.translated_source_lang = title_lang or desc_lang
+    post.translation_engine_version = title_ev or desc_ev
     post.translated_at = datetime.now(UTC)
     return 1

tests/test_translate_posts.py

@@ -115,6 +115,35 @@ def test_translate_posts_passthrough_english_marks_handled(db_sync, monkeypatch)
     assert p.post_title_translated is None       # ...but nothing to show
 
 
+def test_translate_posts_mixed_language_translates_nonenglish_field(db_sync, monkeypatch):
+    # English title + Japanese description: the description is still translated
+    # even though the title is already English (per-field detection, not the old
+    # aggregate first-item bail). Source lang comes from the translated field.
+    _patch(monkeypatch, db_sync)
+    monkeypatch.setattr("backend.app.tasks.translation.ic.health", lambda *a, **k: True)
+
+    def fake_translate(texts, **k):
+        t = texts[0]
+        if t.isascii():   # already English → passthrough
+            return {"translations": [t], "detected_lang": "en",
+                    "engine": "none", "engine_version": None}
+        return {"translations": [f"EN:{t}"], "detected_lang": "ja",
+                "engine": "llm", "engine_version": "v9"}
+
+    monkeypatch.setattr("backend.app.tasks.translation.ic.translate", fake_translate)
+    a = _artist(db_sync)
+    p = _post(db_sync, a.id, title="hello", desc="ねこ")
+    _enable(db_sync)
+    db_sync.commit()
+
+    assert "translated=1" in translate_posts()
+    db_sync.refresh(p)
+    assert p.post_title_translated is None          # English title untouched
+    assert p.description_translated == "EN:ねこ"      # Japanese desc translated
+    assert p.translated_source_lang == "ja"          # from the translated field
+    assert p.translation_engine_version == "v9"
+
+
 def test_translate_posts_disabled_is_noop(db_sync, monkeypatch):
     _patch(monkeypatch, db_sync)
     a = _artist(db_sync)