codex 1.5.12__py3-none-any.whl → 1.5.13a0__py3-none-any.whl

codex/views/browser/filters/search.py

@@ -1,56 +1,144 @@
 """Search Filters Methods."""
 
+from dataclasses import dataclass
+from time import time
+
 from django.db.models import Q
 
 from codex._vendor.haystack.query import SearchQuerySet
 from codex.logger.logging import get_logger
 from codex.models import Comic
+from codex.settings.settings import DEBUG
+from codex.views.browser.const import MAX_OBJ_PER_PAGE
 
 LOG = get_logger(__name__)
 
 
+@dataclass
+class SearchScores:
+    """Search Scores for annotation."""
+
+    scores: tuple[tuple[int, float], ...] = ()
+    scored_pks: tuple[int, ...] = ()
+    prev_pks: tuple[int, ...] = ()
+    next_pks: tuple[int, ...] = ()
+
+
 class SearchFilterMixin:
     """Search Filters Methods."""
 
-    def get_search_scores(self) -> dict | None:
+    def _get_binary_search_scores(self, sqs):
+        """Get search scores for choices and metadata."""
+        sqs = sqs.values_list("pk", flat=True)
+        search_results_limit = self.params.get(  # type: ignore
+            "search_results_limit",
+            MAX_OBJ_PER_PAGE,  # type: ignore
+        )
+        if search_results_limit:
+            sqs = sqs[:search_results_limit]  # type: ignore
+        return tuple(sqs)
+
+    def _get_browser_search_scores(self, sqs):
+        """Get search scores for the browser cards."""
+        page = self.kwargs.get("page", 1)  # type: ignore
+        search_results_limit = self.params.get(  # type: ignore
+            "search_results_limit",
+            MAX_OBJ_PER_PAGE,  # type: ignore
+        )
+        if search_results_limit:
+            offset = 0
+            limit = search_results_limit
+        else:
+            offset = max(0, (page - 1) * MAX_OBJ_PER_PAGE)  # type: ignore
+            limit = offset + MAX_OBJ_PER_PAGE  # type: ignore
+
+        if DEBUG:
+            LOG.debug(
+                f"searching... {page=} page_{offset=} page_{limit=} {search_results_limit=}"
+            )
+
+        scores_pairs = []
+        prev_pks = []
+        next_pks = []
+
+        if DEBUG:
+            start_time = time()
+        scores_values = sqs.values_list("pk", "score")
+        if search_results_limit:
+            scores_values = scores_values[:limit]
+        for index, pair in enumerate(scores_values):
+            if index < offset:
+                prev_pks.append(pair[0])
+            elif index > limit:
+                next_pks.append(pair[0])
+            else:
+                scores_pairs.append(pair)
+
+        if DEBUG:
+            LOG.debug(
+                f"search {time() - start_time}s"  # type: ignore
+                f" {len(scores_pairs)=} {len(prev_pks)=} {len(next_pks)=}"
+            )
+
+        return tuple(scores_pairs), tuple(prev_pks), tuple(next_pks)
+
+    def get_search_scores(self, binary=False) -> SearchScores | None:
         """Perform the search and return the scores as a dict."""
-        search_scores = {}
         text = self.params.get("q", "")  # type: ignore
         if not text:
-            # for opds 2
-            text = self.params.get("query", "")  # type: ignore
-        text = text.strip()
-        if not text:
-            return search_scores
+            return None
 
-        sqs = SearchQuerySet().auto_query(text)
-        comic_scores = sqs.values("pk", "score")
+        scores_pairs = ()
+        scored_pks = ()
+        prev_pks = ()
+        next_pks = ()
         try:
-            for comic_score in comic_scores:
-                search_scores[comic_score["pk"]] = comic_score["score"]
+            sqs = SearchQuerySet()
+            sqs = sqs.auto_query(text)  # .filter(score__gt=0.0)
+            if binary:
+                scored_pks = self._get_binary_search_scores(sqs)
+            else:
+                scores_pairs, prev_pks, next_pks = self._get_browser_search_scores(sqs)
+
         except MemoryError:
             LOG.warning("Search engine needs more memory, results truncated.")
         except Exception:
-            LOG.exception("While Searching")
-        if not search_scores:
-            return None
-        return search_scores
+            LOG.exception("Getting Search Scores")
+        return SearchScores(scores_pairs, scored_pks, prev_pks, next_pks)
 
-    def _get_search_query_filter(self, model, search_scores: dict):
+    def _get_search_query_filter(
+        self,
+        model,
+        search_scores: SearchScores,
+    ):
         """Get the search filter and scores."""
-        prefix = "" if model == Comic else self.rel_prefix  # type: ignore
-        rel = prefix + "pk__in"
-        query_dict = {rel: search_scores.keys()}
-        return Q(**query_dict)
+        if search_scores.scores:
+            query = Q(search_score__gt=0.0)
+        else:
+            prefix = "" if model == Comic else self.rel_prefix  # type: ignore
+            rel = prefix + "pk__in"
+            query_dict = {rel: search_scores.scored_pks}
+            query = Q(**query_dict)
+        return query
 
-    def get_search_filter(self, model, search_scores: dict):
+    def apply_search_filter(
+        self,
+        qs,
+        model,
+        search_scores: SearchScores | None,
+    ):
         """Preparse search, search and return the filter and scores."""
-        search_filter = Q()
         try:
             if search_scores:
-                # Query haystack
                 search_filter = self._get_search_query_filter(model, search_scores)
-        except Exception as exc:
-            LOG.warning(exc)
+                qs = qs.filter(search_filter)
+        except Exception:
+            LOG.exception("Creating the search filter")
+
+        return qs
 
-        return search_filter
+    def apply_binary_search_filter(self, qs):
+        """Apply scoreless search filter for choices & metadata."""
+        search_scores = self.get_search_scores(binary=True)
+        model = self.model  # type: ignore
+        return self.apply_search_filter(qs, model, search_scores)

codex/views/browser/metadata.py

@@ -97,7 +97,7 @@ class MetadataView(BrowserAnnotationsView):
         if not self.is_model_comic:
             size_func = self.get_aggregate_func(self.model, "size")
             qs = qs.annotate(size=size_func)
-        return self.annotate_common_aggregates(qs, self.model, {})
+        return self.annotate_common_aggregates(qs, self.model, None)
 
     def _annotate_values_and_fks(self, qs, simple_qs):
         """Annotate comic values and comic foreign key values."""
@@ -242,13 +242,11 @@ class MetadataView(BrowserAnnotationsView):
         if self.model is None:
             raise NotFound(detail=f"Cannot get metadata for {self.group=}")
 
-        search_scores: dict | None = self.get_search_scores()
-        if search_scores is None:
-            self._raise_not_found()
-        object_filter = self.get_query_filters_without_group(self.model, search_scores)  # type: ignore
+        object_filter = self.get_query_filters_without_group(self.model)
         pk = self.kwargs["pk"]
         qs = self.model.objects.filter(object_filter, pk=pk)
-
+        if self.model != Comic:
+            qs = self.apply_binary_search_filter(qs)
         qs = self._annotate_aggregates(qs)
         simple_qs = qs
 

codex/views/error.py

@@ -7,15 +7,19 @@ from rest_framework.views import exception_handler
 
 from codex.exceptions import SeeOtherRedirectError
 
+_OPDS_PREFIX = "opds/v"
+
 
 def codex_exception_handler(exc, context):
     """Assume OPDS clients want redirects instead of errors."""
     response = None
     request = context.get("request")
-    opds_start = reverse("opds:start")
-    if request.path.startswith(opds_start):
+    if _OPDS_PREFIX in request.path:
+        name = "opds:v2:feed" if _OPDS_PREFIX + "2" in request.path else "opds:v1:feed"
+        opds_start = reverse(name)
+
         if isinstance(exc, SeeOtherRedirectError):
-            response = exc.get_response("opds:v1:browser")
+            response = exc.get_response(opds_start)
         elif hasattr(exc, "status_code") and exc.status_code in (
             status.HTTP_400_BAD_REQUEST,
             status.HTTP_404_NOT_FOUND,

codex/views/opds/v1/feed.py

@@ -12,6 +12,7 @@ from codex.serializers.opds.v1 import (
     OPDS1TemplateSerializer,
 )
 from codex.views.browser.browser import BrowserView
+from codex.views.browser.const import MAX_OBJ_PER_PAGE
 from codex.views.const import FALSY
 from codex.views.opds.const import BLANK_TITLE, MimeType
 from codex.views.opds.v1.entry.data import OPDS1EntryData
@@ -107,7 +108,7 @@ class OPDS1FeedView(CodexXMLTemplateView, LinksMixin):
         """Return opensearch:itemsPerPage."""
         try:
             if self.params.get("q"):
-                return self.MAX_OBJ_PER_PAGE
+                return MAX_OBJ_PER_PAGE
         except Exception:
             LOG.exception("Getting OPDS v1 items per page")
 

codex/views/opds/v2/feed.py

@@ -11,6 +11,7 @@ from codex.logger.logging import get_logger
 from codex.models import AdminFlag
 from codex.serializers.opds.v2 import OPDS2FeedSerializer
 from codex.views.browser.browser import BrowserView
+from codex.views.browser.const import MAX_OBJ_PER_PAGE
 from codex.views.const import FALSY
 from codex.views.opds.const import BLANK_TITLE
 from codex.views.opds.v2.const import (
@@ -175,14 +176,11 @@ class OPDS2FeedView(PublicationMixin, TopLinksMixin):
         """Get the browser page and serialize it for this subclass."""
         group = self.kwargs.get("group")
         if group in ("f", "a"):
-            self.acquisition_groups = frozenset()
-        else:
-            self.acquisition_groups = frozenset(self.valid_nav_groups[-2:])
-        if group == "a":
             pk = self.kwargs["pk"]
             self.is_opds_2_acquisition = bool(pk)
         else:
-            self.is_opds_2_acquisition = group in self.acquisition_groups
+            acquisition_groups = frozenset(self.valid_nav_groups[-2:])
+            self.is_opds_2_acquisition = group in acquisition_groups
         self.is_opds_metadata = (
             self.request.query_params.get("opdsMetadata", "").lower() not in FALSY
         )
@@ -202,7 +200,7 @@ class OPDS2FeedView(PublicationMixin, TopLinksMixin):
                 "metadata": {
                     "title": title,
                     "number_of_items": number_of_items,
-                    "items_per_page": self.MAX_OBJ_PER_PAGE,
+                    "items_per_page": MAX_OBJ_PER_PAGE,
                     "current_page": self.kwargs.get("page"),
                 },
                 "links": self.get_links(browser_page["up_route"]),

codex/views/opds/v2/publications.py

@@ -144,8 +144,10 @@ class PublicationMixin(LinksMixin):
 
         download_mime_type = MimeType.FILE_TYPE_MAP.get(obj.file_type, MimeType.OCTET)
         self_kwargs = {"group": "c", "pk": obj.pk, "page": 1}
-        self_href_data = HrefData(self_kwargs, absolute_query_params=True)
-        self_link_data = LinkData(Rel.SELF, self_href_data, mime_type=MimeType.OPDS_PUB)
+
+        # This would be for comic streaming which is not supported by OPDS 2 yet?
+        # self_href_data = HrefData(self_kwargs, absolute_query_params=True)
+        # self_link_data = LinkData(Rel.SELF, self_href_data, mime_type=MimeType.OPDS_PUB)
 
         alt_kwargs = self_kwargs
         alt_href_data = HrefData(
@@ -168,7 +170,8 @@ class PublicationMixin(LinksMixin):
             mime_type=download_mime_type,
         )
         links = [
-            self.link(self_link_data),
+            # Comic streaming link (unsupported)
+            # self.link(self_link_data),
             self.link(alt_link_data),
             self.link(acq_link_data),
         ]

codex/views/session.py

@@ -105,6 +105,7 @@ class BrowserSessionViewBase(SessionViewBaseBase):
             "order_reverse": False,
             "q": DEFAULTS["q"],
             "route": DEFAULTS["route"],
+            "search_results_limit": DEFAULTS["searchResultsLimit"],
             "show": DEFAULTS["show"],
             "twenty_four_hour_time": False,
             "top_group": DEFAULTS["topGroup"],

{codex-1.5.12.dist-info → codex-1.5.13a0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: codex
-Version: 1.5.12
+Version: 1.5.13a0
 Summary: A comic archive web server.
 Home-page: https://github.com/ajslater/codex
 License: GPL-3.0-only
@@ -30,6 +30,7 @@ Requires-Dist: case-converter (>=1.1.0,<2.0.0)
 Requires-Dist: channels (>=4.0.0,<5.0.0)
 Requires-Dist: comicbox[pdf] (>=1.1.4,<2.0.0)
 Requires-Dist: django (>=5.0.3,<6.0.0)
+Requires-Dist: django-cachalot (>=2.6.2,<3.0.0)
 Requires-Dist: django-cors-headers (>=4.0,<5.0)
 Requires-Dist: django-rest-registration (>=0.8.0,<0.9.0)
 Requires-Dist: django-vite (>=3.0.1,<4.0.0)
@@ -267,15 +268,29 @@ remove users to groups.
 Codex can make groups for libraries that exclude groups of users or exclude
 everyone and include only certain groups of users.
 
-### PDFs
+### PDF Metadata
 
-Codex only reads PDF metadata from the filename. If you decide to include PDFs
-in your comic library, I recommend taking time to rename your files so Codex can
-find some metadata. Codex recognizes several file naming schemes. This one has
-good results:
+Codex reads PDF metadata from the filename, PDF metadata fields and also many
+formats of common complex comic metadata if they are embedded in the PDF
+`keywords` field.
+
+If you decide to include PDFs in your comic library, I recommend taking time to
+rename your files so Codex can find some metadata. Codex recognizes several file
+naming schemes. This one has good results:
 
 `{series} v{volume} #{issue} {title} ({year}) {ignored}.pdf`
 
+Complex comic metadata, such as ComicInfo.xml, can be also be embedded in the
+keywords field by using the [comicbox](https://github.com/ajslater/comicbox)
+command line tool. Codex will read this data because it relies on comicbox
+internally. Not many people use comicbox or embedded metadata in PDFs in this
+fashion, so you likely won't find it unless you've added it yourself.
+
+### 🗝️ API with Key Access
+
+Codex has a limited number of API endpoints available with API Key Access. The
+API Key is available on the admin/stats tab.
+
 ## <a name="configuration">🎛️ Configuration</a>
 
 ### Config Dir
@@ -384,7 +399,7 @@ If you must run Codex in an admin restricted memory environment you might want
 to temporarily give Codex a lot of memory to run a very large import job and
 then restrict it for normal operation.
 
-## <a name="usage">📖 Usage</a>
+## <a name="use">📖 Use</a>
 
 ### 👤 Sessions & Accounts
 
@@ -395,11 +410,6 @@ To preserve these settings across browsers and after sessions expire, you may
 register an account with a username and password. You will have to contact your
 administrator to reset your password if you forget it.
 
-### 🗝️ API with Key Access
-
-Codex has a limited number of API endpoints available with API Key Access. The
-API Key is available on the admin/stats tab.
-
 ### ᯤ OPDS
 
 Codex supports OPDS syndication and OPDS streaming. You may find the OPDS url in
@@ -438,6 +448,7 @@ authentication. In that case the OPDS url will look like:
 - [OPDS-PSE 1.2](https://github.com/anansi-project/opds-pse/blob/master/v1.2.md)
 - [OPDS Authentication 1.0](https://drafts.opds.io/authentication-for-opds-1.0.html)
 - [OpenSearch 1.1](https://github.com/dewitt/opensearch)
+- [OPDS 2.0 (draft)](https://drafts.opds.io/opds-2.0.html)
 
 ## <a name="troubleshooting">🩺 Troubleshooting</a>