From 0299895869be5bdbbb858fe5e13de4207dbd6be2 Mon Sep 17 00:00:00 2001
From: Steppenstreuner <jazz.h@gmx.net>
Date: Fri, 28 Aug 2026 13:37:33 +0200
Subject: [PATCH] add(chore): bulk requests

---
 static/app.js               | 43 ++++++++++++++++++++++++++-----------
 static/index.html           | 11 ++++++++++
 tests/test_import_flow.py   | 28 ++++++++++++++++++++++++
 tests/test_matcher.py       | 13 ++++++++++-
 wordarr/api/imports.py      |  4 ++--
 wordarr/api/requests.py     | 40 ++++++++++++++++++++++++++++++++++
 wordarr/importer/matcher.py | 15 ++++++++++++-
 wordarr/importer/scanner.py |  8 ++++---
 8 files changed, 143 insertions(+), 19 deletions(-)

diff --git a/static/app.js b/static/app.js
index d5969ca..fef8863 100644
--- a/static/app.js
+++ b/static/app.js
@@ -182,18 +182,36 @@ $("#manual-form").addEventListener("submit", async (e) => {
   const data = Object.fromEntries(new FormData(e.target));
   if (!data.library_id) { toast("Keine Library gewählt", true); return; }
   try {
-    await api("/api/requests", {
-      method: "POST",
-      body: JSON.stringify({
-        library_id: parseInt(data.library_id),
-        title: data.title, authors: data.authors, series: data.series,
-        external_id: data.external_id,
-        year: data.year ? parseInt(data.year) : null,
-        volume: data.volume ? parseInt(data.volume) : null,
-      }),
-    });
+    if (data.volume_to) {
+      if (!data.volume) {
+        toast("Für Bulk bitte Start-Band angeben", true);
+        return;
+      }
+      const created = await api("/api/requests/bulk", {
+        method: "POST",
+        body: JSON.stringify({
+          library_id: parseInt(data.library_id),
+          series: data.series || data.title, authors: data.authors,
+          volume_from: parseInt(data.volume),
+          volume_to: parseInt(data.volume_to),
+          year: data.year ? parseInt(data.year) : null,
+        }),
+      });
+      toast(`${created.length} Anfragen angelegt`);
+    } else {
+      await api("/api/requests", {
+        method: "POST",
+        body: JSON.stringify({
+          library_id: parseInt(data.library_id),
+          title: data.title, authors: data.authors, series: data.series,
+          external_id: data.external_id,
+          year: data.year ? parseInt(data.year) : null,
+          volume: data.volume ? parseInt(data.volume) : null,
+        }),
+      });
+      toast("Anfrage angelegt");
+    }
     e.target.reset();
-    toast("Anfrage angelegt");
   } catch (err) { toast(err.message, true); }
 });
 
@@ -241,8 +259,9 @@ let missingReqs = [];
 $("#scan-btn").addEventListener("click", async () => {
   $("#scan-info").textContent = "Scanne…";
   try {
+    const split = $("#split-dirs").checked;
     const [scan, reqs] = await Promise.all([
-      api("/api/import/scan"),
+      api("/api/import/scan?split_dirs=" + split),
       api("/api/requests?status=missing"),
     ]);
     scanItems = scan.items;
diff --git a/static/index.html b/static/index.html
index e6462f1..57190c3 100644
--- a/static/index.html
+++ b/static/index.html
@@ -48,6 +48,13 @@
             <label>Autor(en) <input name="authors" /></label>
             <label>Serie <input name="series" /></label>
             <label>Band <input name="volume" type="number" min="0" /></label>
+            <label
+              >bis Band (Bulk, optional)
+              <input name="volume_to" type="number" min="0" />
+              <span class="muted"
+                >Legt pro Band/Folge eine Anfrage an, z.B. 1 bis 300</span
+              >
+            </label>
             <label>Jahr <input name="year" type="number" /></label>
             <label>ISBN/ID <input name="external_id" /></label>
             <label
@@ -84,6 +91,10 @@
       <section id="view-import" hidden>
         <div class="bar">
           <button id="scan-btn">Download-Ordner scannen</button>
+          <label class="muted"
+            ><input type="checkbox" id="split-dirs" /> Ordner als Einzeldateien
+            behandeln (z.B. Folgen-Sammlungen)</label
+          >
           <span id="scan-info" class="muted"></span>
         </div>
         <table id="import-table" hidden>
diff --git a/tests/test_import_flow.py b/tests/test_import_flow.py
index 09d5c0d..e07b010 100644
--- a/tests/test_import_flow.py
+++ b/tests/test_import_flow.py
@@ -106,3 +106,31 @@ def test_import_rejects_path_outside_download_dir(client):
         "path": str(outside), "is_dir": False, "files": [str(outside)], "request_id": req_id,
     }]})
     assert resp.json()["results"][0]["ok"] is False
+
+
+def test_bulk_requests_and_split_scan(client):
+    root = client.tmp_path / "library" / "audio"
+    lib_id = client.post("/api/libraries", json={
+        "name": "Hoerspiele", "media_type": "audiobook", "root_path": str(root),
+    }).json()["id"]
+    resp = client.post("/api/requests/bulk", json={
+        "library_id": lib_id, "series": "Die drei ???", "volume_from": 1, "volume_to": 3,
+    })
+    assert resp.status_code == 200
+    created = resp.json()
+    assert [r["title"] for r in created] == [
+        "Die drei ??? Folge 01", "Die drei ??? Folge 02", "Die drei ??? Folge 03",
+    ]
+
+    folder = client.downloads / "Die drei Fragezeichen Sammlung"
+    folder.mkdir()
+    for n in (1, 2, 3):
+        (folder / f"Die drei Fragezeichen - Folge {n:03d}.mp3").write_bytes(b"a")
+
+    # default scan: one audiobook unit; split scan: three individual files
+    assert len(client.get("/api/import/scan").json()["items"]) == 1
+    items = client.get("/api/import/scan", params={"split_dirs": "true"}).json()["items"]
+    assert len(items) == 3
+    by_name = {i["name"]: i["suggested_request_id"] for i in items}
+    expected = {f"Die drei Fragezeichen - Folge {n:03d}": created[n - 1]["id"] for n in (1, 2, 3)}
+    assert by_name == expected
diff --git a/tests/test_matcher.py b/tests/test_matcher.py
index e1663b4..cfacaae 100644
--- a/tests/test_matcher.py
+++ b/tests/test_matcher.py
@@ -4,7 +4,7 @@ from wordarr.importer.matcher import best_matches, normalize
 
 
 def req(id, title, authors="", media_type="ebook"):
-    return SimpleNamespace(id=id, title=title, authors=authors, media_type=media_type)
+    return SimpleNamespace(id=id, title=title, authors=authors, media_type=media_type, volume=None)
 
 
 def test_normalize():
@@ -36,3 +36,14 @@ def test_media_type_filter():
               "is_dir": False, "files": ["/d/dune.epub"]}]
     out = best_matches(items, requests)
     assert out[0]["suggested_request_id"] is None
+
+
+def test_volume_number_must_match():
+    r1 = req(1, "Die drei ??? Folge 001", "", media_type="audiobook")
+    r1.volume = 1
+    r123 = req(2, "Die drei ??? Folge 123", "", media_type="audiobook")
+    r123.volume = 123
+    items = [{"path": "/d/f.mp3", "name": "Die drei Fragezeichen - Folge 123 - Der Superpapagei",
+              "media_type": "audiobook", "is_dir": False, "files": ["/d/f.mp3"]}]
+    out = best_matches(items, [r1, r123])
+    assert out[0]["suggested_request_id"] == 2
diff --git a/wordarr/api/imports.py b/wordarr/api/imports.py
index e02d4e4..eb54ead 100644
--- a/wordarr/api/imports.py
+++ b/wordarr/api/imports.py
@@ -13,9 +13,9 @@ router = APIRouter(prefix="/api/import", tags=["import"])
 
 
 @router.get("/scan")
-def scan(session: Session = Depends(get_session)):
+def scan(split_dirs: bool = False, session: Session = Depends(get_session)):
     """Scan the download dir and suggest matches against open requests."""
-    items = scanner.scan(Path(config.DOWNLOAD_DIR))
+    items = scanner.scan(Path(config.DOWNLOAD_DIR), split_dirs=split_dirs)
     missing = session.scalars(
         select(BookRequest).where(BookRequest.status == "missing")
     ).all()
diff --git a/wordarr/api/requests.py b/wordarr/api/requests.py
index 883351c..d5f1409 100644
--- a/wordarr/api/requests.py
+++ b/wordarr/api/requests.py
@@ -61,6 +61,46 @@ def create_request(data: RequestIn, session: Session = Depends(get_session)):
     return _out(req)
 
 
+class BulkRequestIn(BaseModel):
+    library_id: int
+    series: str
+    authors: str = ""
+    volume_from: int
+    volume_to: int
+    year: int | None = None
+    cover_url: str = ""
+
+
+@router.post("/bulk", response_model=list[RequestOut])
+def create_bulk(data: BulkRequestIn, session: Session = Depends(get_session)):
+    lib = session.get(Library, data.library_id)
+    if not lib:
+        raise HTTPException(404, "library not found")
+    if data.volume_from > data.volume_to:
+        raise HTTPException(400, "volume_from must be <= volume_to")
+    if data.volume_to - data.volume_from > 999:
+        raise HTTPException(400, "at most 1000 requests per bulk call")
+    width = max(2, len(str(data.volume_to)))
+    reqs = []
+    for n in range(data.volume_from, data.volume_to + 1):
+        req = BookRequest(
+            media_type=lib.media_type,
+            library_id=lib.id,
+            title=f"{data.series} Folge {n:0{width}d}",
+            authors=data.authors,
+            series=data.series,
+            volume=n,
+            year=data.year,
+            cover_url=data.cover_url,
+        )
+        session.add(req)
+        reqs.append(req)
+    session.commit()
+    for r in reqs:
+        session.refresh(r)
+    return [_out(r) for r in reqs]
+
+
 @router.delete("/{request_id}")
 def delete_request(request_id: int, session: Session = Depends(get_session)):
     req = session.get(BookRequest, request_id)
diff --git a/wordarr/importer/matcher.py b/wordarr/importer/matcher.py
index 8c824da..c640aee 100644
--- a/wordarr/importer/matcher.py
+++ b/wordarr/importer/matcher.py
@@ -11,12 +11,25 @@ def normalize(s: str) -> str:
     return s.strip()
 
 
+def _numbers(s: str) -> set[int]:
+    return {int(n) for n in re.findall(r"\d+", s)}
+
+
 def score(item_name: str, request) -> float:
     target = normalize(f"{request.authors} {request.title}")
     name = normalize(item_name)
     s = fuzz.token_set_ratio(name, target)
     title_only = fuzz.token_set_ratio(name, normalize(request.title))
-    return max(s, title_only * 0.95)
+    result = max(s, title_only * 0.95)
+    # for numbered volumes/episodes the number must match, otherwise every
+    # episode of a series scores alike on the shared title tokens
+    if request.volume is not None:
+        nums = _numbers(item_name)
+        if request.volume in nums:
+            result = min(100.0, result + 5)
+        elif nums:
+            result = min(result, 40.0)
+    return result
 
 
 def best_matches(items: list[dict], requests) -> list[dict]:
diff --git a/wordarr/importer/scanner.py b/wordarr/importer/scanner.py
index d2250ed..37e9cf8 100644
--- a/wordarr/importer/scanner.py
+++ b/wordarr/importer/scanner.py
@@ -14,9 +14,11 @@ def media_type_for(ext: str) -> str | None:
     return None
 
 
-def scan(root: Path) -> list[dict]:
+def scan(root: Path, split_dirs: bool = False) -> list[dict]:
     """Scan the download dir. Returns items: single files, or a directory that is
-    an audiobook unit (contains >1 audio file and nothing but audio/junk)."""
+    an audiobook unit (contains >1 audio file and nothing but audio/junk).
+    With split_dirs=True every file is listed individually (e.g. for folders
+    holding many episodes of a series)."""
     items = []
     if not root.is_dir():
         return items
@@ -29,7 +31,7 @@ def scan(root: Path) -> list[dict]:
 
     def walk(d: Path):
         audio = audio_files(d)
-        if len(audio) > 1:
+        if len(audio) > 1 and not split_dirs:
             items.append({
                 "path": str(d),
                 "name": d.name,