add(metadata): filter audible results by library language

README.md

@@ -23,6 +23,10 @@ docker compose up -d --build
 | `WORDARR_DOWNLOAD_DIR` | `/mnt/downloads` | Gescannter Download-Ordner |
 | `WORDARR_CONFIG_DIR` | `/config` | Ablage der SQLite-DB |
 
+## Sprachen
+
+Jede Library kann eine **Sprache** tragen (`Deutsch`/`Englisch`, Default: egal). Audible liefert zu jedem Titel die Sprache mit, deshalb zeigt die Suche für eine englische Library nur englische Ausgaben und für eine deutsche nur deutsche — praktisch, wenn dieselbe Reihe in beiden Sprachen in getrennten Libraries liegt (*A Song of Ice and Fire* vs. *Das Lied von Eis und Feuer*). Gesucht wird dann auch auf dem passenden Marktplatz (`audible.com` bzw. `audible.de`), was die Trefferqualität deutlich hebt. Im Tab *Suche* lässt sich die Sprache zusätzlich frei filtern; im Import-Dialog kommt sie automatisch aus der gewählten Ziel-Library.
+
 ## Namensschemata
 
 Pro Library konfigurierbar (Tab *Libraries*), Platzhalter: `{Author}` `{Authors}` `{Title}` `{Year}` `{Series}` `{Volume}`.

static/app.js

@@ -2,6 +2,7 @@ const $ = (sel) => document.querySelector(sel);
 const $$ = (sel) => document.querySelectorAll(sel);
 
 let libraries = [];
+const LANGUAGE_NAMES = { german: "Deutsch", english: "Englisch" };
 
 async function api(path, opts = {}) {
   const resp = await fetch(path, {
@@ -93,6 +94,7 @@ async function loadLibraries() {
       (l) => `<tr>
         <td>${esc(l.name)}</td><td>${esc(l.media_type)}</td><td>${esc(l.root_path)}</td>
         <td class="mono">${esc(l.folder_template)}</td><td class="mono">${esc(l.file_template)}</td>
+        <td>${l.language ? esc(LANGUAGE_NAMES[l.language] || l.language) : "—"}</td>
         <td class="row">
           <button class="secondary" data-edit-lib="${l.id}">Bearbeiten</button>
           <button class="danger" data-del-lib="${l.id}">Löschen</button>
@@ -127,6 +129,7 @@ function startLibraryEdit(id) {
   form.root_path.value = lib.root_path;
   form.folder_template.value = lib.folder_template;
   form.file_template.value = lib.file_template;
+  form.language.value = lib.language || "";
   form.dataset.editId = lib.id;
   $("#lib-form-title").textContent = `Library „${lib.name}“ bearbeiten`;
   $("#lib-form-submit").textContent = "Speichern";
@@ -199,7 +202,10 @@ $("#search-form").addEventListener("submit", async (e) => {
   searchBtn.disabled = true;
   searchBtn.innerHTML = '<span class="spinner"></span> Suche…';
   try {
-    const results = await api(`/api/search?media_type=${type}&q=${encodeURIComponent(q)}`);
+    const language = $("#search-language").value;
+    const results = await api(
+      `/api/search?media_type=${type}&q=${encodeURIComponent(q)}&language=${language}`
+    );
     if (!results.length) {
       box.innerHTML = `<p class='muted'>${EMPTY_HINTS[type]}</p>`;
       return;
@@ -214,7 +220,7 @@ $("#search-form").addEventListener("submit", async (e) => {
             <span>${esc(r.authors)}</span>
             ${r.narrator ? `<span class="muted">🎙 ${esc(r.narrator)}</span>` : ""}
             ${r.series && r.media_type ? `<span class="muted">📚 ${esc(r.series)}${r.volume != null ? " #" + r.volume : ""}</span>` : ""}
-            <span class="muted">${r.year ?? ""} ${r.external_id ? "· " + esc(r.external_id) : ""}</span>
+            <span class="muted">${r.year ?? ""} ${r.language ? "· " + esc(LANGUAGE_NAMES[r.language] || r.language) : ""} ${r.external_id ? "· " + esc(r.external_id) : ""}</span>
             ${type === "comic" ? `<input type="number" min="0" placeholder="Band" class="volume" data-vol="${i}">` : ""}
             <div class="row">
               <select data-lib="${i}">${opts || "<option value=''>— keine Library —</option>"}</select>
@@ -955,8 +961,12 @@ async function runQuickSearch() {
   const box = $("#quick-results");
   box.innerHTML = "<p class='muted'>Suche läuft…</p>";
   try {
+    // the target library decides the language: an "english" library should not
+    // offer the German edition of the same book
+    const lib = libraries.find((l) => String(l.id) === $("#quick-library").value);
     const results = await api(
-      `/api/search?media_type=${item.media_type}&q=${encodeURIComponent($("#quick-q").value)}`
+      `/api/search?media_type=${item.media_type}&q=${encodeURIComponent($("#quick-q").value)}` +
+        `&language=${lib?.language || ""}`
     );
     if (!results.length) {
       box.innerHTML = `<p class='muted'>${EMPTY_HINTS[item.media_type]}</p>`;
@@ -970,6 +980,7 @@ async function runQuickSearch() {
           r.narrator ? "🎙 " + r.narrator : "",
           r.series ? `📚 ${r.series}${r.volume != null ? " #" + r.volume : ""}` : "",
           r.year ?? "",
+          LANGUAGE_NAMES[r.language] || r.language,
         ].filter(Boolean).map(esc).join(" · ");
         return `<div class="card">
           ${r.cover_url ? `<img src="${esc(r.cover_url)}" alt="" loading="lazy">` : '<div class="nocover">?</div>'}

static/index.html

@@ -30,6 +30,11 @@
             <option value="audiobook">Audiobook</option>
             <option value="comic">Comic/Manga</option>
           </select>
+          <select id="search-language" title="Nur Audiobooks: Sprache der Ausgabe">
+            <option value="">Alle Sprachen</option>
+            <option value="german">Deutsch</option>
+            <option value="english">Englisch</option>
+          </select>
           <input id="search-q" placeholder="Titel, Autor oder ISBN…" required />
           <button type="submit" id="search-btn">Suchen</button>
           <button type="button" id="manual-btn" class="secondary">
@@ -237,6 +242,7 @@
                 <th>Pfad</th>
                 <th>Ordner-Schema</th>
                 <th>Datei-Schema</th>
+                <th>Sprache</th>
                 <th></th>
               </tr>
             </thead>
@@ -267,6 +273,11 @@
             name="file_template"
             placeholder="Datei-Schema (optional)"
             class="wide" />
+          <select name="language" title="Sprache der Ausgaben in dieser Library — filtert die Audible-Suche">
+            <option value="">Sprache: egal</option>
+            <option value="german">Deutsch</option>
+            <option value="english">Englisch</option>
+          </select>
           <button type="submit" id="lib-form-submit">Anlegen</button>
           <button type="button" id="lib-form-cancel" class="secondary" hidden>
             Abbrechen

tests/test_import_flow.py

@@ -647,3 +647,43 @@ def test_append_without_the_flag_is_still_refused(client):
     assert not res["ok"]
     assert "bereits importiert" in res["error"]
     assert (second / "c.mp3").exists()
+
+
+def test_library_language_round_trip(client):
+    lib = client.post("/api/libraries", json={
+        "name": "english", "media_type": "audiobook",
+        "root_path": str(client.tmp_path / "en"), "language": "english",
+    }).json()
+    assert lib["language"] == "english"
+    assert client.get("/api/libraries").json()[0]["language"] == "english"
+
+    # libraries without a language keep working and stay unrestricted
+    other = client.post("/api/libraries", json={
+        "name": "adults", "media_type": "audiobook",
+        "root_path": str(client.tmp_path / "de"),
+    }).json()
+    assert other["language"] == ""
+
+    updated = client.put(f"/api/libraries/{other['id']}", json={
+        "name": "adults", "media_type": "audiobook",
+        "root_path": str(client.tmp_path / "de"), "language": "german",
+    }).json()
+    assert updated["language"] == "german"
+
+
+def test_search_passes_language_to_the_provider(client, monkeypatch):
+    from wordarr.metadata.base import MetadataResult
+    seen = {}
+
+    async def fake(query, language=""):
+        seen["query"], seen["language"] = query, language
+        return [MetadataResult(media_type="audiobook", title="A Game of Thrones",
+                               language="english")]
+
+    monkeypatch.setitem(
+        __import__("wordarr.metadata", fromlist=["PROVIDERS"]).PROVIDERS, "audiobook", fake)
+    res = client.get("/api/search", params={
+        "media_type": "audiobook", "q": "Game of Thrones", "language": "english",
+    }).json()
+    assert seen == {"query": "Game of Thrones", "language": "english"}
+    assert res[0]["language"] == "english"

wordarr/api/libraries.py

@@ -15,6 +15,7 @@ class LibraryIn(BaseModel):
     root_path: str
     folder_template: str | None = None
     file_template: str | None = None
+    language: str = ""  # "german" / "english" - filters the Audible search
 
 
 class LibraryOut(LibraryIn):
@@ -44,6 +45,7 @@ def create_library(data: LibraryIn, session: Session = Depends(get_session)):
         root_path=data.root_path,
         folder_template=data.folder_template or defaults["folder"],
         file_template=data.file_template or defaults["file"],
+        language=data.language,
     )
     session.add(lib)
     session.commit()
@@ -62,6 +64,7 @@ def update_library(library_id: int, data: LibraryIn, session: Session = Depends(
     lib.root_path = data.root_path
     lib.folder_template = data.folder_template or defaults["folder"]
     lib.file_template = data.file_template or defaults["file"]
+    lib.language = data.language
     session.commit()
     return lib
 

wordarr/api/search.py

@@ -7,12 +7,12 @@ router = APIRouter(prefix="/api/search", tags=["search"])
 
 
 @router.get("", response_model=list[MetadataResult])
-async def search(media_type: str, q: str):
+async def search(media_type: str, q: str, language: str = ""):
     provider = PROVIDERS.get(media_type)
     if not provider:
         raise HTTPException(400, f"invalid media_type: {media_type}")
     try:
-        return await provider(q)
+        return await provider(q, language)
     except Exception as exc:
         raise HTTPException(502, f"metadata provider error: {exc}")
 

wordarr/db.py

@@ -19,6 +19,9 @@ class Library(Base):
     root_path: Mapped[str] = mapped_column(String)
     folder_template: Mapped[str] = mapped_column(String)
     file_template: Mapped[str] = mapped_column(String)
+    # audible language of this library's editions ("english", "german", …).
+    # empty means no restriction.
+    language: Mapped[str] = mapped_column(String, default="")
 
     requests: Mapped[list["BookRequest"]] = relationship(back_populates="library")
 
@@ -58,9 +61,13 @@ def init_db(db_path=None):
     Base.metadata.create_all(_engine)
     # lightweight migration: create_all doesn't add new columns to existing tables
     with _engine.begin() as conn:
-        cols = [row[1] for row in conn.exec_driver_sql("PRAGMA table_info(requests)")]
+        def add_column(table: str, column: str, ddl: str) -> None:
-        if "narrator" not in cols:
+            cols = [row[1] for row in conn.exec_driver_sql(f"PRAGMA table_info({table})")]
-            conn.exec_driver_sql("ALTER TABLE requests ADD COLUMN narrator VARCHAR NOT NULL DEFAULT ''")
+            if column not in cols:
+                conn.exec_driver_sql(f"ALTER TABLE {table} ADD COLUMN {ddl}")
+
+        add_column("requests", "narrator", "narrator VARCHAR NOT NULL DEFAULT ''")
+        add_column("libraries", "language", "language VARCHAR NOT NULL DEFAULT ''")
     SessionLocal = sessionmaker(bind=_engine, expire_on_commit=False)
     return _engine
 

wordarr/metadata/anilist.py

@@ -17,7 +17,8 @@ query ($search: String) {
 """
 
 
-async def search(query: str) -> list[MetadataResult]:
+async def search(query: str, language: str = "") -> list[MetadataResult]:
+    # language is an Audible concept; AniList results carry no usable language tag
     async with httpx.AsyncClient(timeout=15) as client:
         resp = await client.post(
             "https://graphql.anilist.co",

wordarr/metadata/audible.py

@@ -7,6 +7,9 @@ from .base import MetadataResult
 
 # Comma-separated marketplace TLDs, first entries rank first in the results.
 REGIONS = [r.strip() for r in os.environ.get("WORDARR_AUDIBLE_REGIONS", "de,com").split(",")]
+# a marketplace ranks its own language first, so searching for an English
+# edition works much better on .com than on .de - and vice versa
+LANGUAGE_REGIONS = {"english": ["com", "co.uk"], "german": ["de"]}
 
 RESPONSE_GROUPS = "media,contributors,product_desc,product_attrs,series"
 PAGE_SIZE = 50
@@ -56,6 +59,7 @@ def _to_result(p: dict) -> MetadataResult:
         title=p.get("title", ""),
         authors=", ".join(a.get("name", "") for a in p.get("authors") or []),
         narrator=", ".join(n.get("name", "") for n in p.get("narrators") or []),
+        language=(p.get("language") or "").lower(),
         series=first.get("title", ""),
         series_id=first.get("asin", ""),
         volume=volume,
@@ -65,10 +69,11 @@ def _to_result(p: dict) -> MetadataResult:
     )
 
 
-async def search(query: str) -> list[MetadataResult]:
+async def search(query: str, language: str = "") -> list[MetadataResult]:
+    regions = LANGUAGE_REGIONS.get(language, REGIONS)
     async with httpx.AsyncClient(timeout=15) as client:
         region_results = await asyncio.gather(
-            *(_query(client, tld, query) for tld in REGIONS)
+            *(_query(client, tld, query) for tld in regions)
         )
 
     results = []
@@ -80,6 +85,9 @@ async def search(query: str) -> list[MetadataResult]:
                 continue
             seen_asins.add(asin)
             results.append(_to_result(p))
+    if language:
+        # keep entries whose language is unknown, drop the ones we know differ
+        results = [r for r in results if r.language in ("", language)]
     return results
 
 

wordarr/metadata/base.py

@@ -8,6 +8,7 @@ class MetadataResult(BaseModel):
     narrator: str = ""
     external_id: str = ""
     year: int | None = None
+    language: str = ""  # audible: "english", "german", …
     series: str = ""
     series_id: str = ""
     volume: int | None = None

wordarr/metadata/openlibrary.py

@@ -7,7 +7,8 @@ from .base import MetadataResult
 _ISBN = re.compile(r"^(97[89])?\d{9}[\dXx]$")
 
 
-async def search(query: str) -> list[MetadataResult]:
+async def search(query: str, language: str = "") -> list[MetadataResult]:
+    # language is an Audible concept; Open Library results carry no usable language tag
     query = query.strip()
     isbn = query.replace("-", "").replace(" ", "")
     async with httpx.AsyncClient(timeout=15) as client: