fix(newznab): make indexer book categories configurable (#1214)

Newznab searches hardcoded category 7000 for ebooks and 3030 for
audiobooks,
so indexers using custom IDs returned no results or the wrong ones. Add
NEWZNAB_EBOOK_CATEGORIES and NEWZNAB_AUDIOBOOK_CATEGORIES (tag lists,
defaulting to 7000 and 3030) and resolve the search categories from
config.

Values are parsed leniently — list or comma/whitespace separated,
non-numeric
entries skipped, duplicates dropped — and fall back to the standard IDs
when
empty, so a cleared field can't silently widen the search to every
category.
NEWZNAB_AUTO_EXPAND remains the way to do that on purpose.

Results carrying a custom ID outside the standard 7000-7999 / 3030
ranges were
typed as "other", which routed custom-category audiobooks as ebooks.
Trust the
searched content type when a result carries a category we explicitly
asked for.

Also drop the unused NEWZNAB_BOOKS / NEWZNAB_AUDIOBOOKS constants from
api.py —
a third copy of the same hardcoding.

Closes #1208

docs/environment-variables.md

@@ -1304,6 +1304,8 @@ Apply per-indexer seed time and ratio preferences from Prowlarr when sending tor
 | `NEWZNAB_ENABLED` | Enable searching for books via a Newznab-compatible indexer | boolean | `false` |
 | `NEWZNAB_URL` | Base URL of your Newznab indexer or aggregator | string | _none_ |
 | `NEWZNAB_API_KEY` | Your Newznab API key (leave blank if not required) | string (secret) | _none_ |
+| `NEWZNAB_EBOOK_CATEGORIES` | Newznab category IDs searched for ebooks. Most indexers use the standard 7000, but some use custom IDs. Leave empty to use 7000. | string (comma-separated) | `7000` |
+| `NEWZNAB_AUDIOBOOK_CATEGORIES` | Newznab category IDs searched for audiobooks. Most indexers use the standard 3030, but some use custom IDs. Leave empty to use 3030. | string (comma-separated) | `3030` |
 | `NEWZNAB_AUTO_EXPAND` | Automatically retry search without category filtering if no results are found | boolean | `false` |
 
 <details>
@@ -1337,6 +1339,24 @@ Your Newznab API key (leave blank if not required)
 - **Type:** string (secret)
 - **Default:** _none_
 
+#### `NEWZNAB_EBOOK_CATEGORIES`
+
+**Ebook Categories**
+
+Newznab category IDs searched for ebooks. Most indexers use the standard 7000, but some use custom IDs. Leave empty to use 7000.
+
+- **Type:** string (comma-separated)
+- **Default:** `7000`
+
+#### `NEWZNAB_AUDIOBOOK_CATEGORIES`
+
+**Audiobook Categories**
+
+Newznab category IDs searched for audiobooks. Most indexers use the standard 3030, but some use custom IDs. Leave empty to use 3030.
+
+- **Type:** string (comma-separated)
+- **Default:** `3030`
+
 #### `NEWZNAB_AUTO_EXPAND`
 
 **Auto-expand search on no results**

shelfmark/release_sources/newznab/api.py

@@ -14,10 +14,6 @@ from shelfmark.release_sources.prowlarr.torznab import parse_torznab_xml
 
 logger = setup_logger(__name__)
 
-# Newznab standard book category IDs
-NEWZNAB_BOOKS = 7000
-NEWZNAB_AUDIOBOOKS = 3030
-
 
 class NewznabClient:
     """Client for any Newznab-compatible indexer API."""

shelfmark/release_sources/newznab/settings.py

@@ -8,6 +8,7 @@ from shelfmark.core.settings_registry import (
     HeadingField,
     PasswordField,
     SettingsField,
+    TagListField,
     TextField,
     register_settings,
 )
@@ -86,6 +87,30 @@ def newznab_config_settings() -> list[SettingsField]:
             callback=_test_newznab_connection,
             show_when={"field": "NEWZNAB_ENABLED", "value": True},
         ),
+        TagListField(
+            key="NEWZNAB_EBOOK_CATEGORIES",
+            label="Ebook Categories",
+            description=(
+                "Newznab category IDs searched for ebooks. Most indexers use the standard 7000, "
+                "but some use custom IDs. Leave empty to use 7000."
+            ),
+            placeholder="7000",
+            default=["7000"],
+            normalize_urls=False,
+            show_when={"field": "NEWZNAB_ENABLED", "value": True},
+        ),
+        TagListField(
+            key="NEWZNAB_AUDIOBOOK_CATEGORIES",
+            label="Audiobook Categories",
+            description=(
+                "Newznab category IDs searched for audiobooks. Most indexers use the standard "
+                "3030, but some use custom IDs. Leave empty to use 3030."
+            ),
+            placeholder="3030",
+            default=["3030"],
+            normalize_urls=False,
+            show_when={"field": "NEWZNAB_ENABLED", "value": True},
+        ),
         CheckboxField(
             key="NEWZNAB_AUTO_EXPAND",
             label="Auto-expand search on no results",

shelfmark/release_sources/newznab/source.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import re
 import time
 from typing import TYPE_CHECKING, ClassVar
 
@@ -39,15 +40,92 @@ from shelfmark.release_sources.prowlarr.source import (
 
 logger = setup_logger(__name__)
 
-# Newznab category IDs
-_AUDIOBOOK_CATS = [3030]
-_BOOK_CATS = [7000]
+# Standard Newznab category IDs, used when the indexer's categories aren't configured.
+_DEFAULT_AUDIOBOOK_CATS = [3030]
+_DEFAULT_BOOK_CATS = [7000]
 
 # Reuse the same timeout constant as Prowlarr.
 NEWZNAB_SEARCH_TIMEOUT_SECONDS = _SEARCH_TIMEOUT
 
 
-def _newznab_result_to_release(result: dict, content_type: str = "ebook") -> Release:
+def _parse_category_ids(raw: object) -> list[int]:
+    """Parse a configured category setting into Newznab category IDs.
+
+    Accepts a list of values or a comma/whitespace separated string. Entries that
+    aren't positive integers are skipped, and duplicates are dropped.
+    """
+    if raw is None:
+        return []
+
+    values = list(raw) if isinstance(raw, (list, tuple)) else [raw]
+
+    category_ids: list[int] = []
+    for value in values:
+        for token in re.split(r"[,\s]+", str(value).strip()):
+            if not token:
+                continue
+            try:
+                category_id = int(token)
+            except ValueError:
+                logger.warning("Newznab: ignoring invalid category ID '%s'", token)
+                continue
+            if category_id > 0 and category_id not in category_ids:
+                category_ids.append(category_id)
+
+    return category_ids
+
+
+def _configured_categories(content_type: str) -> list[int]:
+    """Return the categories to search for a content type, falling back to defaults."""
+    if content_type == "audiobook":
+        key, defaults = "NEWZNAB_AUDIOBOOK_CATEGORIES", _DEFAULT_AUDIOBOOK_CATS
+    else:
+        key, defaults = "NEWZNAB_EBOOK_CATEGORIES", _DEFAULT_BOOK_CATS
+
+    return _parse_category_ids(config.get(key, None)) or list(defaults)
+
+
+def _result_category_ids(categories: object) -> set[int]:
+    """Extract numeric category IDs from a result's categories field."""
+    if not isinstance(categories, (list, tuple)):
+        return set()
+
+    category_ids: set[int] = set()
+    for cat in categories:
+        raw = cat.get("id") if isinstance(cat, dict) else cat
+        try:
+            category_ids.add(int(raw))  # type: ignore[arg-type]
+        except TypeError, ValueError:
+            continue
+    return category_ids
+
+
+def _resolve_content_type(
+    categories: object,
+    content_type: str,
+    searched_categories: list[int] | None,
+) -> str:
+    """Resolve a result's content type, honouring custom indexer categories.
+
+    Indexers using non-standard IDs (e.g. 7100 for ebooks) fall outside the standard
+    ranges, so trust the searched content type when the result carries a category we
+    explicitly asked for.
+    """
+    detected = _detect_content_type_from_categories(categories, content_type)
+    if (
+        detected == "other"
+        and searched_categories
+        and _result_category_ids(categories) & set(searched_categories)
+    ):
+        return "audiobook" if content_type == "audiobook" else "book"
+    return detected
+
+
+def _newznab_result_to_release(
+    result: dict,
+    content_type: str = "ebook",
+    searched_categories: list[int] | None = None,
+) -> Release:
     """Convert a parsed Newznab XML result dict to a Release object."""
     raw_title = result.get("title", "Unknown")
     size_bytes = result.get("size")
@@ -125,7 +203,7 @@ def _newznab_result_to_release(result: dict, content_type: str = "ebook") -> Rel
         indexer=indexer,
         seeders=seeders if is_torrent else None,
         peers=peers_display,
-        content_type=_detect_content_type_from_categories(categories, content_type),
+        content_type=_resolve_content_type(categories, content_type, searched_categories),
         extra={
             "publish_date": result.get("publishDate"),
             "categories": categories,
@@ -230,12 +308,7 @@ class NewznabSource(ReleaseSource):
             return []
 
         # Category selection — omit categories when expanding search
-        if expand_search:
-            categories = None
-        elif content_type == "audiobook":
-            categories = [3030]
-        else:
-            categories = [7000]
+        categories = None if expand_search else _configured_categories(content_type)
 
         auto_expand = config.get("NEWZNAB_AUTO_EXPAND", False)
         deadline = time.monotonic() + NEWZNAB_SEARCH_TIMEOUT_SECONDS
@@ -283,7 +356,7 @@ class NewznabSource(ReleaseSource):
             logger.exception("Newznab search failed")
             return []
 
-        results = [_newznab_result_to_release(r, content_type) for r in all_results]
+        results = [_newznab_result_to_release(r, content_type, categories) for r in all_results]
 
         if results:
             nzb_count = sum(1 for r in results if r.protocol == ReleaseProtocol.NZB)

tests/newznab/test_source.py

@@ -10,6 +10,7 @@ from shelfmark.release_sources import ReleaseProtocol
 from shelfmark.release_sources.newznab.source import (
     NewznabSource,
     _newznab_result_to_release,
+    _parse_category_ids,
 )
 
 # ── fixtures / helpers ─────────────────────────────────────────────────────────
@@ -100,6 +101,18 @@ class TestResultToRelease:
         r = _newznab_result_to_release(_make_result(categories=[]), "audiobook")
         assert r.content_type == "audiobook"
 
+    def test_custom_searched_category_treated_as_book(self):
+        r = _newznab_result_to_release(_make_result(categories=[8010]), "ebook", [8010])
+        assert r.content_type == "book"
+
+    def test_custom_searched_category_treated_as_audiobook(self):
+        r = _newznab_result_to_release(_make_result(categories=[{"id": 3040}]), "audiobook", [3040])
+        assert r.content_type == "audiobook"
+
+    def test_unsearched_out_of_range_category_stays_other(self):
+        r = _newznab_result_to_release(_make_result(categories=[2000]), "ebook", [8010])
+        assert r.content_type == "other"
+
     def test_freeleech_flag_detected_via_download_volume(self):
         r = _newznab_result_to_release(_make_result(downloadVolumeFactor=0.0))
         assert r.extra["freeleech"] is True
@@ -209,6 +222,31 @@ class TestIsAvailable:
         assert NewznabSource().is_available() is False
 
 
+# ── category parsing ───────────────────────────────────────────────────────────
+
+
+class TestParseCategoryIds:
+    def test_parses_list_of_strings(self):
+        assert _parse_category_ids(["7100", "7120"]) == [7100, 7120]
+
+    def test_parses_comma_separated_string(self):
+        assert _parse_category_ids("7100, 7120") == [7100, 7120]
+
+    def test_parses_comma_separated_entry_inside_list(self):
+        assert _parse_category_ids(["7100,7120", "8010"]) == [7100, 7120, 8010]
+
+    def test_drops_duplicates_and_keeps_order(self):
+        assert _parse_category_ids(["7120", "7100", "7120"]) == [7120, 7100]
+
+    def test_skips_non_numeric_and_non_positive_values(self):
+        assert _parse_category_ids(["books", "0", "-7000", "7100"]) == [7100]
+
+    def test_returns_empty_for_unset_or_blank(self):
+        assert _parse_category_ids(None) == []
+        assert _parse_category_ids([]) == []
+        assert _parse_category_ids("   ") == []
+
+
 # ── NewznabSource.search ───────────────────────────────────────────────────────
 
 
@@ -276,6 +314,44 @@ class TestSearch:
         _, kwargs = client.search.call_args
         assert kwargs["categories"] == [3030]
 
+    def test_searches_with_configured_ebook_categories(self, monkeypatch):
+        client = MagicMock()
+        client.search.return_value = []
+        src = self._patched_source(
+            monkeypatch, client, {"NEWZNAB_EBOOK_CATEGORIES": ["7100", "7120"]}
+        )
+        book = _make_book()
+        src.search(book, _make_plan(book), content_type="ebook")
+        _, kwargs = client.search.call_args
+        assert kwargs["categories"] == [7100, 7120]
+
+    def test_searches_with_configured_audiobook_categories(self, monkeypatch):
+        client = MagicMock()
+        client.search.return_value = []
+        src = self._patched_source(monkeypatch, client, {"NEWZNAB_AUDIOBOOK_CATEGORIES": "3040"})
+        book = _make_book()
+        src.search(book, _make_plan(book), content_type="audiobook")
+        _, kwargs = client.search.call_args
+        assert kwargs["categories"] == [3040]
+
+    def test_falls_back_to_default_when_categories_cleared(self, monkeypatch):
+        client = MagicMock()
+        client.search.return_value = []
+        src = self._patched_source(monkeypatch, client, {"NEWZNAB_EBOOK_CATEGORIES": []})
+        book = _make_book()
+        src.search(book, _make_plan(book), content_type="ebook")
+        _, kwargs = client.search.call_args
+        assert kwargs["categories"] == [7000]
+
+    def test_ebook_categories_do_not_affect_audiobook_search(self, monkeypatch):
+        client = MagicMock()
+        client.search.return_value = []
+        src = self._patched_source(monkeypatch, client, {"NEWZNAB_EBOOK_CATEGORIES": ["7100"]})
+        book = _make_book()
+        src.search(book, _make_plan(book), content_type="audiobook")
+        _, kwargs = client.search.call_args
+        assert kwargs["categories"] == [3030]
+
     def test_expand_search_removes_categories(self, monkeypatch):
         client = MagicMock()
         client.search.return_value = []