Implement: US: Book Search and Discovery (#13)

Reviewed and merged by Reid (Hermes Reviewer)

Co-authored-by: crisleo-hermes <hermes@codescripters.org>
Co-committed-by: crisleo-hermes <hermes@codescripters.org>

backend/apps/books/views.py

@@ -1,3 +1,6 @@
+from __future__ import annotations
+
+import logging
 from typing import Any
 
 from django.db.models import QuerySet, Q
@@ -9,13 +12,16 @@ from rest_framework.permissions import AllowAny, IsAuthenticated
 from rest_framework.request import Request
 from rest_framework.response import Response
 
-from apps.books.models import Book, EBook, ReadingProgress, ReadingSettings
+from apps.books.models import Book, BookChapter, EBook, ReadingProgress, ReadingSettings
 from apps.books.serializers import (
     BookDetailSerializer, BookListSerializer, BookSerializer,
-    EBookDetailSerializer, EBookListSerializer, EBookUploadSerializer,
+    BookChapterSerializer, EBookContentSerializer, EBookDetailSerializer,
+    EBookListSerializer, EBookTocSerializer, EBookUploadSerializer,
     ReadingProgressSerializer, ReadingSettingsSerializer,
 )
 
+logger = logging.getLogger(__name__)
+
 
 class BookViewSet(viewsets.ModelViewSet):
     queryset = Book.objects.all()
@@ -63,8 +69,10 @@ class EBookViewSet(viewsets.ModelViewSet):
     def get_serializer_class(self):
         if self.action == "create":
             return EBookUploadSerializer
-        if self.action == "list":
+        if self.action in ("list",):
             return EBookListSerializer
+        if self.action in ("toc",):
+            return BookChapterSerializer
         return EBookDetailSerializer
 
     def get_queryset(self):
@@ -82,6 +90,135 @@ class EBookViewSet(viewsets.ModelViewSet):
         serializer.save()
         return Response(serializer.data)
 
+    @action(detail=True, methods=["post"])
+    def process(self, request: Request, pk: int | None = None) -> Response:
+        """Trigger e-book processing: metadata extraction, TOC building, page counting."""
+        ebook = self.get_object()
+        if not ebook.file:
+            return Response({"error": "No file found for this e-book."}, status=status.HTTP_400_BAD_REQUEST)
+
+        try:
+            from apps.books.services import process_ebook
+
+            file_path = ebook.file.path
+            result = process_ebook(file_path, original_filename=ebook.filename())
+
+            # Update ebook with extracted data
+            ebook.format = result.get("format", ebook.format)
+            ebook.page_count = result.get("page_count", 0)
+            ebook.metadata_json = result.get("metadata", {})
+            ebook.save(update_fields=["format", "page_count", "metadata_json", "updated_at"])
+
+            # Store chapters in DB
+            raw_toc: list[dict[str, Any]] = result.get("toc", [])
+            BookChapter.objects.filter(ebook=ebook).delete()
+            _store_chapters(ebook, raw_toc)
+
+            return Response({
+                "format": ebook.format,
+                "page_count": ebook.page_count,
+                "metadata": ebook.metadata_json,
+                "toc_count": len(raw_toc),
+                "status": "processed",
+            })
+        except Exception as exc:
+            logger.exception("Failed to process ebook %s", ebook.id)
+            return Response({"error": f"Processing failed: {exc}"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+
+    @action(detail=True, methods=["get"])
+    def toc(self, request: Request, pk: int | None = None) -> Response:
+        """Return hierarchical table of contents."""
+        ebook = self.get_object()
+        chapters = BookChapter.objects.filter(ebook=ebook).order_by("index").select_related("ebook")
+        serializer = BookChapterSerializer(chapters, many=True)
+        return Response({
+            "chapters": serializer.data,
+            "format": ebook.format,
+            "page_count": ebook.page_count,
+        })
+
+    @action(detail=True, methods=["get"])
+    def content(self, request: Request, pk: int | None = None) -> Response:
+        """Return paginated content for a given page number.
+
+        Query params:
+            page (int): page/chapter index to fetch (1-indexed, default: 1)
+        """
+        ebook = self.get_object()
+        page = max(1, int(request.query_params.get("page", 1)))
+
+        chapters = list(BookChapter.objects.filter(ebook=ebook).order_by("index").select_related("ebook"))
+        total_pages = len(chapters) or ebook.page_count or 1
+
+        chapter: BookChapter | None = None
+        chapter_title = ""
+        content_html = ""
+
+        if chapters and 0 <= page - 1 < len(chapters):
+            ch = chapters[page - 1]
+            chapter_title = ch.title
+            content_html = _fetch_chapter_content(ebook, ch)
+
+        serializer = EBookContentSerializer(data={
+            "page": page,
+            "total_pages": total_pages,
+            "content": content_html,
+            "chapter_title": chapter_title,
+            "format": ebook.format,
+        })
+        serializer.is_valid(raise_exception=True)
+        return Response(serializer.data)
+
+
+def _store_chapters(ebook: EBook, toc: list[dict[str, Any]], parent_index: int = 0) -> None:
+    """Recursively store TOC entries as BookChapter records."""
+    for idx, entry in enumerate(toc):
+        BookChapter.objects.create(
+            ebook=ebook,
+            title=entry.get("title", "Untitled"),
+            index=parent_index + idx,
+            href=entry.get("href", ""),
+            children=entry.get("children", []),
+        )
+        children = entry.get("children", [])
+        if children:
+            _store_chapters(ebook, children, parent_index + idx + 1)
+
+
+def _fetch_chapter_content(ebook: EBook, chapter: BookChapter) -> str:
+    """Fetch HTML content for a chapter from the e-book file."""
+    if ebook.format == "epub":
+        return _fetch_epub_chapter_content(ebook.file.path, chapter)
+    return ""
+
+
+def _fetch_epub_chapter_content(file_path: str, chapter: BookChapter) -> str:
+    """Extract HTML content of a specific EPUB chapter by href."""
+    try:
+        from ebooklib import epub
+        from bs4 import BeautifulSoup
+    except ImportError:
+        return ""
+
+    try:
+        book = epub.read_epub(file_path)
+        href = chapter.href or ""
+        # Find the item by href
+        for item in book.get_items():
+            item_name = item.get_name() or ""
+            if href and (item_name.endswith(href) or href.endswith(item_name)):
+                content = item.get_content()
+                soup = BeautifulSoup(content, "html.parser")
+                # Clean up — remove body/html/head wrappers, keep inner content
+                body = soup.find("body")
+                if body:
+                    return str(body)
+                return str(soup)
+        return ""
+    except Exception:
+        logger.exception("Failed to fetch EPUB chapter content for %s", chapter.href)
+        return ""
+
 
 class ReadingSettingsViewSet(viewsets.GenericViewSet):
     permission_classes = [IsAuthenticated]