cloud-reader/backend/apps/books/views.py

from __future__ import annotations

import logging
from typing import Any

from django.db.models import QuerySet, Q
from django_filters.rest_framework import DjangoFilterBackend
from rest_framework import parsers, permissions, status, viewsets
from rest_framework.decorators import action
from rest_framework.filters import OrderingFilter, SearchFilter
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, BookChapter, DownloadRecord, EBook, ReadingProgress
from apps.books.serializers import (
    BookChapterSerializer, BookDetailSerializer, BookListSerializer, BookSerializer,
    DownloadRecordSerializer, EBookContentSerializer, EBookDetailSerializer,
    EBookListSerializer, EBookTocSerializer, EBookUploadSerializer,
    ReadingProgressSerializer, StorageSummarySerializer,
)

logger = logging.getLogger(__name__)


class BookViewSet(viewsets.ModelViewSet):
    queryset = Book.objects.all()
    permission_classes = [IsAuthenticated]
    filter_backends = [DjangoFilterBackend, SearchFilter, OrderingFilter]
    filterset_fields = ["author", "genre", "reading_status"]
    search_fields = ["title", "author", "genre"]
    ordering_fields = ["title", "author", "genre", "created_at"]
    ordering = ["title"]

    def get_serializer_class(self):
        if self.action == "retrieve":
            return BookDetailSerializer
        if self.action == "list":
            return BookListSerializer
        return BookSerializer

    def get_queryset(self) -> QuerySet[Book]:
        qs = super().get_queryset()
        query = self.request.query_params.get("q", "").strip()
        if query:
            qs = qs.filter(Q(title__icontains=query) | Q(author__icontains=query) | Q(genre__icontains=query))
        return qs

    @action(detail=False, methods=["get"], permission_classes=[AllowAny])
    def genres(self, request: Request) -> Response:
        genre_list = Book.objects.values_list("genre", flat=True).distinct().order_by("genre")
        return Response([g for g in genre_list if g])

    @action(detail=False, methods=["get"], permission_classes=[AllowAny])
    def authors(self, request: Request) -> Response:
        author_list = Book.objects.values_list("author", flat=True).distinct().order_by("author")
        return Response([a for a in author_list if a])

    @action(detail=False, methods=["get"])
    def storage(self, request: Request) -> Response:
        """Return storage usage summary for the current user."""
        download_records = DownloadRecord.objects.filter(user=request.user).select_related("ebook")
        total_size = sum(r.file_size for r in download_records)
        ebook_list = [
            {"id": r.ebook.id, "title": r.ebook.title, "file_size": r.file_size}
            for r in download_records
        ]
        serializer = StorageSummarySerializer(data={
            "total_downloads": download_records.count(),
            "total_size_bytes": total_size,
            "ebooks": ebook_list,
        })
        serializer.is_valid(raise_exception=True)
        return Response(serializer.data)


class IsEBookOwner(permissions.BasePermission):
    def has_object_permission(self, request: Request, view: object, obj: EBook) -> bool:
        return obj.user == request.user


class EBookViewSet(viewsets.ModelViewSet):
    parser_classes = [parsers.MultiPartParser, parsers.FormParser, parsers.JSONParser]
    permission_classes = [IsAuthenticated, IsEBookOwner]

    def get_serializer_class(self):
        if self.action == "create":
            return EBookUploadSerializer
        if self.action in ("list",):
            return EBookListSerializer
        if self.action in ("toc",):
            return BookChapterSerializer
        return EBookDetailSerializer

    def get_queryset(self):
        return EBook.objects.filter(user=self.request.user).select_related("reading_progress", "user")

    @action(detail=True, methods=["get", "patch"])
    def progress(self, request: Request, pk: int | None = None) -> Response:
        ebook = self.get_object()
        progress_obj, _created = ReadingProgress.objects.get_or_create(user=request.user, ebook=ebook)
        if request.method == "GET":
            serializer = ReadingProgressSerializer(progress_obj)
            return Response(serializer.data)
        serializer = ReadingProgressSerializer(progress_obj, data=request.data, partial=True)
        serializer.is_valid(raise_exception=True)
        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)

    @action(detail=True, methods=["post"])
    def download(self, request: Request, pk: int | None = None) -> Response:
        """Track download of an e-book. Creates a DownloadRecord and returns file info."""
        ebook = self.get_object()
        if not ebook.file:
            return Response({"error": "No file found for this e-book."}, status=status.HTTP_400_BAD_REQUEST)

        download, created = DownloadRecord.objects.get_or_create(
            user=request.user,
            ebook=ebook,
            defaults={"file_size": ebook.file.size if ebook.file else 0},
        )
        if not created:
            download.file_size = ebook.file.size if ebook.file else 0
            download.save(update_fields=["file_size"])

        serializer = DownloadRecordSerializer(download, context={"request": request})
        return Response(serializer.data, status=status.HTTP_200_OK)

    @action(detail=False, methods=["get"])
    def downloads(self, request: Request) -> Response:
        """List all e-books the current user has downloaded."""
        records = DownloadRecord.objects.filter(user=request.user).select_related(
            "ebook", "ebook__reading_progress"
        ).prefetch_related("ebook__chapters")
        page = self.paginate_queryset(records)
        if page is not None:
            serializer = DownloadRecordSerializer(page, many=True, context={"request": request})
            return self.get_paginated_response(serializer.data)
        serializer = DownloadRecordSerializer(records, many=True, context={"request": request})
        return Response(serializer.data)

    @action(detail=False, methods=["delete"], url_path="downloads/(?P<download_pk>[^/.]+)")
    def delete_download(self, request: Request, download_pk: str | None = None) -> Response:
        """Delete a download record."""
        try:
            download = DownloadRecord.objects.get(pk=download_pk, user=request.user)
        except DownloadRecord.DoesNotExist:
            return Response({"error": "Download record not found."}, status=status.HTTP_404_NOT_FOUND)
        download.delete()
        return Response(status=status.HTTP_204_NO_CONTENT)


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 ""