Expose all available voices from both TTS engines via the /api/voices endpoint. AudioPlayer and profile voice-selector now group voices by engine and show a labelled optgroup. Voice type carries an engine field so the chapter-reader can route synthesis to the correct backend.
1193 lines
41 KiB
Go
1193 lines
41 KiB
Go
package backend
|
|
|
|
// handlers.go — all HTTP request handlers for the backend server.
|
|
//
|
|
// Handler naming mirrors the route table in server.go:
|
|
// handleScrapeCatalogue, handleScrapeBook, handleScrapeBookRange
|
|
// handleScrapeStatus, handleScrapeTasks
|
|
// handleBrowse, handleSearch
|
|
// handleGetRanking, handleGetCover
|
|
// handleBookPreview, handleChapterText, handleChapterTextPreview, handleChapterMarkdown, handleReindex
|
|
// handleAudioGenerate, handleAudioStatus, handleAudioProxy
|
|
// handleVoices
|
|
// handlePresignChapter, handlePresignAudio, handlePresignVoiceSample
|
|
// handlePresignAvatarUpload, handlePresignAvatar
|
|
// handleGetProgress, handleSetProgress, handleDeleteProgress
|
|
//
|
|
// Key design choices vs. old scraper:
|
|
// - POST /scrape* creates a PocketBase task record and returns 202 with the
|
|
// task_id — it does NOT run the orchestrator inline.
|
|
// - POST /api/audio creates a PocketBase audio task and returns 202 — the
|
|
// runner binary executes TTS generation asynchronously.
|
|
// - GET /api/audio/status polls PocketBase for the task record status.
|
|
// - GET /api/audio-proxy reads the completed audio object from MinIO via a
|
|
// presigned URL redirect (the runner has already uploaded the bytes).
|
|
// - GET /api/browse and /api/search fetch novelfire.net live (no MinIO cache).
|
|
// - GET /api/cover redirects to the source cover URL live.
|
|
// - GET /api/ranking reads from the PocketBase ranking collection (populated
|
|
// by the runner after each catalogue scrape).
|
|
// - GET /api/book-preview returns stored data when in library, or enqueues a
|
|
// scrape task and returns 202 when not. The backend never scrapes directly.
|
|
// - GET /api/chapter-text-preview scrapes a chapter live from novelfire.net
|
|
// directly (no runner task, no store writes). Used for unscraped books.
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"net/url"
|
|
"regexp"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/libnovel/backend/internal/domain"
|
|
"github.com/libnovel/backend/internal/kokoro"
|
|
"github.com/libnovel/backend/internal/meili"
|
|
"github.com/libnovel/backend/internal/novelfire/htmlutil"
|
|
"github.com/libnovel/backend/internal/pockettts"
|
|
"github.com/libnovel/backend/internal/scraper"
|
|
)
|
|
|
|
const (
|
|
novelFireBase = "https://novelfire.net"
|
|
novelFireDomain = "novelfire.net"
|
|
)
|
|
|
|
// ── Scrape task creation ───────────────────────────────────────────────────────
|
|
|
|
// handleScrapeCatalogue handles POST /scrape.
|
|
// Creates a "catalogue" scrape task in PocketBase and returns 202 with the task ID.
|
|
func (s *Server) handleScrapeCatalogue(w http.ResponseWriter, r *http.Request) {
|
|
taskID, err := s.deps.Producer.CreateScrapeTask(r.Context(), "catalogue", "", 0, 0)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleScrapeCatalogue: CreateScrapeTask failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to create task")
|
|
return
|
|
}
|
|
writeJSON(w, http.StatusAccepted, map[string]string{"task_id": taskID, "status": "accepted"})
|
|
}
|
|
|
|
// handleScrapeBook handles POST /scrape/book.
|
|
// Body: {"url": "https://novelfire.net/book/..."}
|
|
func (s *Server) handleScrapeBook(w http.ResponseWriter, r *http.Request) {
|
|
var body struct {
|
|
URL string `json:"url"`
|
|
}
|
|
if err := json.NewDecoder(r.Body).Decode(&body); err != nil || body.URL == "" {
|
|
jsonError(w, http.StatusBadRequest, `request body must be JSON with "url" field`)
|
|
return
|
|
}
|
|
taskID, err := s.deps.Producer.CreateScrapeTask(r.Context(), "book", body.URL, 0, 0)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleScrapeBook: CreateScrapeTask failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to create task")
|
|
return
|
|
}
|
|
writeJSON(w, http.StatusAccepted, map[string]string{"task_id": taskID, "status": "accepted"})
|
|
}
|
|
|
|
// handleScrapeBookRange handles POST /scrape/book/range.
|
|
// Body: {"url": "...", "from": N, "to": M}
|
|
func (s *Server) handleScrapeBookRange(w http.ResponseWriter, r *http.Request) {
|
|
var body struct {
|
|
URL string `json:"url"`
|
|
From int `json:"from"`
|
|
To int `json:"to"`
|
|
}
|
|
if err := json.NewDecoder(r.Body).Decode(&body); err != nil || body.URL == "" {
|
|
jsonError(w, http.StatusBadRequest, `request body must be JSON with "url" field`)
|
|
return
|
|
}
|
|
taskID, err := s.deps.Producer.CreateScrapeTask(r.Context(), "book_range", body.URL, body.From, body.To)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleScrapeBookRange: CreateScrapeTask failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to create task")
|
|
return
|
|
}
|
|
writeJSON(w, http.StatusAccepted, map[string]string{"task_id": taskID, "status": "accepted"})
|
|
}
|
|
|
|
// handleCancelTask handles POST /api/cancel-task/{id}.
|
|
// Transitions a pending task (scrape or audio) to status=cancelled.
|
|
// Returns 404 if the task does not exist, 409 if it cannot be cancelled
|
|
// (e.g. already running/done).
|
|
func (s *Server) handleCancelTask(w http.ResponseWriter, r *http.Request) {
|
|
id := r.PathValue("id")
|
|
if id == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing task id")
|
|
return
|
|
}
|
|
if err := s.deps.Producer.CancelTask(r.Context(), id); err != nil {
|
|
s.deps.Log.Warn("handleCancelTask: CancelTask failed", "id", id, "err", err)
|
|
jsonError(w, http.StatusConflict, "could not cancel task: "+err.Error())
|
|
return
|
|
}
|
|
writeJSON(w, http.StatusOK, map[string]string{"status": "cancelled", "id": id})
|
|
}
|
|
|
|
// ── Scrape task status / history ───────────────────────────────────────────────
|
|
|
|
// handleScrapeStatus handles GET /api/scrape/status.
|
|
// Returns the most recent scrape task status (or {"running":false} if none).
|
|
func (s *Server) handleScrapeStatus(w http.ResponseWriter, r *http.Request) {
|
|
tasks, err := s.deps.TaskReader.ListScrapeTasks(r.Context())
|
|
if err != nil {
|
|
s.deps.Log.Error("handleScrapeStatus: ListScrapeTasks failed", "err", err)
|
|
writeJSON(w, 0, map[string]bool{"running": false})
|
|
return
|
|
}
|
|
running := false
|
|
for _, t := range tasks {
|
|
if t.Status == domain.TaskStatusRunning || t.Status == domain.TaskStatusPending {
|
|
running = true
|
|
break
|
|
}
|
|
}
|
|
writeJSON(w, 0, map[string]bool{"running": running})
|
|
}
|
|
|
|
// handleScrapeTasks handles GET /api/scrape/tasks.
|
|
// Returns all scrape task records from PocketBase, newest first.
|
|
func (s *Server) handleScrapeTasks(w http.ResponseWriter, r *http.Request) {
|
|
tasks, err := s.deps.TaskReader.ListScrapeTasks(r.Context())
|
|
if err != nil {
|
|
s.deps.Log.Error("handleScrapeTasks: ListScrapeTasks failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to list tasks")
|
|
return
|
|
}
|
|
if tasks == nil {
|
|
tasks = []domain.ScrapeTask{}
|
|
}
|
|
writeJSON(w, 0, tasks)
|
|
}
|
|
|
|
// ── Browse & search ────────────────────────────────────────────────────────────
|
|
|
|
// NovelListing represents a single novel entry from the novelfire browse/search page.
|
|
type NovelListing struct {
|
|
Slug string `json:"slug"`
|
|
Title string `json:"title"`
|
|
Cover string `json:"cover"`
|
|
Rank string `json:"rank"`
|
|
Rating string `json:"rating"`
|
|
Chapters string `json:"chapters"`
|
|
URL string `json:"url"`
|
|
}
|
|
|
|
// handleSearch handles GET /api/search.
|
|
// Query params: q (min 2 chars), source ("local"|"remote"|"all", default "all")
|
|
//
|
|
// Local search is powered by Meilisearch when configured; falls back to a
|
|
// substring match against PocketBase book records otherwise.
|
|
func (s *Server) handleSearch(w http.ResponseWriter, r *http.Request) {
|
|
q := r.URL.Query().Get("q")
|
|
if len([]rune(q)) < 2 {
|
|
jsonError(w, http.StatusBadRequest, "query must be at least 2 characters")
|
|
return
|
|
}
|
|
|
|
source := r.URL.Query().Get("source")
|
|
if source == "" {
|
|
source = "all"
|
|
}
|
|
|
|
ctx, cancel := context.WithTimeout(r.Context(), 20*time.Second)
|
|
defer cancel()
|
|
|
|
var localResults, remoteResults []NovelListing
|
|
|
|
// Local search: Meilisearch → PocketBase substring fallback
|
|
if source == "local" || source == "all" {
|
|
meiliBooks, meiliErr := s.deps.SearchIndex.Search(ctx, q, 50)
|
|
if meiliErr == nil && len(meiliBooks) > 0 {
|
|
for _, b := range meiliBooks {
|
|
localResults = append(localResults, NovelListing{
|
|
Slug: b.Slug,
|
|
Title: b.Title,
|
|
Cover: b.Cover,
|
|
URL: b.SourceURL,
|
|
})
|
|
}
|
|
} else {
|
|
// Fallback: substring match against PocketBase
|
|
books, err := s.deps.BookReader.ListBooks(ctx)
|
|
if err != nil {
|
|
s.deps.Log.Warn("search: ListBooks failed", "err", err)
|
|
} else {
|
|
qLower := strings.ToLower(q)
|
|
for _, b := range books {
|
|
if strings.Contains(strings.ToLower(b.Title), qLower) ||
|
|
strings.Contains(strings.ToLower(b.Author), qLower) {
|
|
localResults = append(localResults, NovelListing{
|
|
Slug: b.Slug,
|
|
Title: b.Title,
|
|
Cover: b.Cover,
|
|
URL: b.SourceURL,
|
|
})
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Remote search (novelfire.net)
|
|
if source == "remote" || source == "all" {
|
|
searchURL := novelFireBase + "/search?keyword=" + url.QueryEscape(q)
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
|
|
if err == nil {
|
|
req.Header.Set("User-Agent", "Mozilla/5.0 (compatible; libnovel-backend/2)")
|
|
req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
|
|
if resp, fetchErr := http.DefaultClient.Do(req); fetchErr == nil {
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode == http.StatusOK {
|
|
parsed, _ := parseBrowsePage(resp.Body)
|
|
remoteResults = parsed
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Merge: local first, de-duplicate remote
|
|
localSlugs := make(map[string]bool, len(localResults))
|
|
for _, item := range localResults {
|
|
localSlugs[item.Slug] = true
|
|
}
|
|
combined := make([]NovelListing, 0, len(localResults)+len(remoteResults))
|
|
combined = append(combined, localResults...)
|
|
for _, item := range remoteResults {
|
|
if !localSlugs[item.Slug] {
|
|
combined = append(combined, item)
|
|
}
|
|
}
|
|
|
|
writeJSON(w, 0, map[string]any{
|
|
"results": combined,
|
|
"local_count": len(localResults),
|
|
"remote_count": len(remoteResults),
|
|
})
|
|
}
|
|
|
|
// ── Ranking ────────────────────────────────────────────────────────────────────
|
|
|
|
// handleGetRanking handles GET /api/ranking.
|
|
// Returns all ranking items sorted by rank ascending.
|
|
func (s *Server) handleGetRanking(w http.ResponseWriter, r *http.Request) {
|
|
items, err := s.deps.RankingStore.ReadRankingItems(r.Context())
|
|
if err != nil {
|
|
s.deps.Log.Error("handleGetRanking: ReadRankingItems failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to read ranking")
|
|
return
|
|
}
|
|
if items == nil {
|
|
items = []domain.RankingItem{}
|
|
}
|
|
writeJSON(w, 0, items)
|
|
}
|
|
|
|
// handleGetCover handles GET /api/cover/{domain}/{slug}.
|
|
// Serves the cover image directly from MinIO when available; falls back to a
|
|
// redirect to the novelfire CDN when the cover has not yet been downloaded.
|
|
func (s *Server) handleGetCover(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
if slug == "" {
|
|
http.Error(w, "missing slug", http.StatusBadRequest)
|
|
return
|
|
}
|
|
|
|
// Fast path: serve from MinIO if the cover has been downloaded.
|
|
if s.deps.CoverStore != nil {
|
|
data, ct, ok, err := s.deps.CoverStore.GetCover(r.Context(), slug)
|
|
if err != nil {
|
|
s.deps.Log.Warn("handleGetCover: GetCover error", "slug", slug, "err", err)
|
|
}
|
|
if ok && len(data) > 0 {
|
|
if ct == "" {
|
|
ct = "image/jpeg"
|
|
}
|
|
w.Header().Set("Content-Type", ct)
|
|
w.Header().Set("Cache-Control", "public, max-age=86400")
|
|
_, _ = w.Write(data)
|
|
return
|
|
}
|
|
}
|
|
|
|
// Fallback: redirect to the CDN. The caller sees a working image; the
|
|
// cover will be populated on the next catalogue refresh run.
|
|
coverURL := fmt.Sprintf("https://cdn.novelfire.net/covers/%s.jpg", slug)
|
|
http.Redirect(w, r, coverURL, http.StatusFound)
|
|
}
|
|
|
|
// ── Preview (live scrape, no store writes) ─────────────────────────────────────
|
|
|
|
// handleBookPreview handles GET /api/book-preview/{slug}.
|
|
//
|
|
// If the book is already in the library (PocketBase), returns its metadata and
|
|
// chapter index immediately (200).
|
|
//
|
|
// If the book is not yet in the library, enqueues a "book" scrape task and
|
|
// returns 202 Accepted with the task_id. The runner will scrape the book
|
|
// asynchronously; the client should poll GET /api/scrape/status or
|
|
// GET /api/scrape/tasks to detect completion, then re-request this endpoint.
|
|
//
|
|
// The backend never scrapes directly — all scraping is the runner's job.
|
|
func (s *Server) handleBookPreview(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
if slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing slug")
|
|
return
|
|
}
|
|
|
|
ctx := r.Context()
|
|
|
|
meta, inLib, err := s.deps.BookReader.ReadMetadata(ctx, slug)
|
|
if err != nil {
|
|
s.deps.Log.Warn("book-preview: ReadMetadata failed", "slug", slug, "err", err)
|
|
inLib = false
|
|
}
|
|
|
|
if inLib {
|
|
// Fast path: book is already scraped — return stored data.
|
|
chapters, cerr := s.deps.BookReader.ListChapters(ctx, slug)
|
|
if cerr != nil {
|
|
s.deps.Log.Warn("book-preview: ListChapters failed", "slug", slug, "err", cerr)
|
|
}
|
|
writeJSON(w, 0, map[string]any{
|
|
"in_lib": true,
|
|
"meta": meta,
|
|
"chapters": chapters,
|
|
})
|
|
return
|
|
}
|
|
|
|
// Book not in library — enqueue a range scrape task for the first 20 chapters
|
|
// so the user can start reading quickly. Remaining chapters can be scraped
|
|
// later via the book detail page or the admin scrape panel.
|
|
bookURL := r.URL.Query().Get("source_url")
|
|
if bookURL == "" {
|
|
bookURL = fmt.Sprintf("%s/book/%s", novelFireBase, slug)
|
|
}
|
|
|
|
const previewFrom, previewTo = 1, 20
|
|
taskID, err := s.deps.Producer.CreateScrapeTask(ctx, "book_range", bookURL, previewFrom, previewTo)
|
|
if err != nil {
|
|
s.deps.Log.Error("book-preview: CreateScrapeTask failed", "slug", slug, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to enqueue scrape task")
|
|
return
|
|
}
|
|
|
|
s.deps.Log.Info("book-preview: enqueued range scrape task", "slug", slug, "task_id", taskID,
|
|
"from", previewFrom, "to", previewTo)
|
|
writeJSON(w, http.StatusAccepted, map[string]any{
|
|
"in_lib": false,
|
|
"task_id": taskID,
|
|
"message": fmt.Sprintf("scraping first %d chapters; poll /api/scrape/tasks for completion", previewTo),
|
|
})
|
|
}
|
|
|
|
// ── Chapter text ───────────────────────────────────────────────────────────────
|
|
|
|
// handleChapterText handles GET /api/chapter-text/{slug}/{n}.
|
|
// Returns plain text (markdown stripped) of a stored chapter.
|
|
func (s *Server) handleChapterText(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 {
|
|
http.NotFound(w, r)
|
|
return
|
|
}
|
|
raw, err := s.deps.BookReader.ReadChapter(r.Context(), slug, n)
|
|
if err != nil {
|
|
http.NotFound(w, r)
|
|
return
|
|
}
|
|
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
|
|
w.Header().Set("Cache-Control", "no-store")
|
|
fmt.Fprint(w, stripMarkdown(raw))
|
|
}
|
|
|
|
// handleChapterMarkdown handles GET /api/chapter-markdown/{slug}/{n}.
|
|
//
|
|
// Returns the raw markdown content of a stored chapter directly from MinIO.
|
|
// This is used by the SvelteKit UI as a simpler alternative to presign+fetch:
|
|
// it avoids the need for the SvelteKit server to reach MinIO directly, and
|
|
// gives a clean 404 when the chapter has not been scraped yet.
|
|
func (s *Server) handleChapterMarkdown(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 || slug == "" {
|
|
http.Error(w, `{"error":"invalid params"}`, http.StatusBadRequest)
|
|
return
|
|
}
|
|
raw, err := s.deps.BookReader.ReadChapter(r.Context(), slug, n)
|
|
if err != nil {
|
|
s.deps.Log.Warn("chapter-markdown: not found in MinIO", "slug", slug, "n", n, "err", err)
|
|
http.Error(w, `{"error":"chapter not found"}`, http.StatusNotFound)
|
|
return
|
|
}
|
|
w.Header().Set("Content-Type", "text/markdown; charset=utf-8")
|
|
w.Header().Set("Cache-Control", "no-store")
|
|
fmt.Fprint(w, raw)
|
|
}
|
|
|
|
// handleChapterTextPreview handles GET /api/chapter-text-preview/{slug}/{n}.
|
|
//
|
|
// Fetches a chapter live from novelfire.net and returns its plain text without
|
|
// writing anything to PocketBase or MinIO. This is the preview path used when
|
|
// a chapter has not yet been scraped into the library.
|
|
//
|
|
// Optional query params:
|
|
//
|
|
// chapter_url — the canonical chapter URL (preferred over constructing one)
|
|
// title — hint for the chapter title (used when the page title is empty)
|
|
//
|
|
// Response: {"slug":string,"number":int,"title":string,"text":string,"url":string}
|
|
func (s *Server) handleChapterTextPreview(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 || slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "invalid slug or chapter number")
|
|
return
|
|
}
|
|
|
|
// Determine the chapter URL to fetch.
|
|
chapterURL := r.URL.Query().Get("chapter_url")
|
|
if chapterURL == "" {
|
|
// Best-effort: novelfire chapter URLs follow /book/{slug}/chapter-{n}
|
|
chapterURL = fmt.Sprintf("%s/book/%s/chapter-%d", novelFireBase, slug, n)
|
|
}
|
|
|
|
titleHint := r.URL.Query().Get("title")
|
|
|
|
ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
|
|
defer cancel()
|
|
|
|
// Fetch the chapter page.
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, chapterURL, nil)
|
|
if err != nil {
|
|
s.deps.Log.Error("chapter-text-preview: build request failed", "url", chapterURL, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to build request")
|
|
return
|
|
}
|
|
req.Header.Set("User-Agent", "Mozilla/5.0 (compatible; libnovel-backend/2)")
|
|
req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
|
|
|
|
resp, err := http.DefaultClient.Do(req)
|
|
if err != nil {
|
|
s.deps.Log.Warn("chapter-text-preview: fetch failed", "url", chapterURL, "err", err)
|
|
jsonError(w, http.StatusBadGateway, "failed to fetch chapter")
|
|
return
|
|
}
|
|
defer resp.Body.Close()
|
|
|
|
if resp.StatusCode == http.StatusNotFound {
|
|
jsonError(w, http.StatusNotFound, "chapter not found")
|
|
return
|
|
}
|
|
if resp.StatusCode != http.StatusOK {
|
|
body, _ := io.ReadAll(io.LimitReader(resp.Body, 512))
|
|
s.deps.Log.Warn("chapter-text-preview: upstream error",
|
|
"url", chapterURL, "status", resp.StatusCode, "body_snippet", string(body))
|
|
jsonError(w, http.StatusBadGateway, fmt.Sprintf("upstream returned %d", resp.StatusCode))
|
|
return
|
|
}
|
|
|
|
bodyBytes, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
s.deps.Log.Error("chapter-text-preview: read body failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to read response")
|
|
return
|
|
}
|
|
|
|
// Parse HTML and extract the #content node.
|
|
root, err := htmlutil.ParseHTML(string(bodyBytes))
|
|
if err != nil {
|
|
s.deps.Log.Error("chapter-text-preview: html parse failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to parse chapter HTML")
|
|
return
|
|
}
|
|
|
|
container := htmlutil.FindFirst(root, scraper.Selector{ID: "content"})
|
|
if container == nil {
|
|
s.deps.Log.Warn("chapter-text-preview: #content not found", "url", chapterURL)
|
|
jsonError(w, http.StatusNotFound, "chapter content not found on page")
|
|
return
|
|
}
|
|
|
|
markdownText := htmlutil.NodeToMarkdown(container)
|
|
plainText := stripMarkdown(markdownText)
|
|
|
|
// Extract the chapter title from the page <title> or <h1> if not hinted.
|
|
chapterTitle := titleHint
|
|
if chapterTitle == "" {
|
|
// Try <h1 class="chapter-title"> first, then <h2 class="chapter-title">
|
|
for _, tag := range []string{"h1", "h2", "h3"} {
|
|
if node := htmlutil.FindFirst(root, scraper.Selector{Tag: tag, Class: "chapter-title"}); node != nil {
|
|
chapterTitle = strings.TrimSpace(htmlutil.TextContent(node))
|
|
break
|
|
}
|
|
}
|
|
}
|
|
if chapterTitle == "" {
|
|
chapterTitle = fmt.Sprintf("Chapter %d", n)
|
|
}
|
|
|
|
writeJSON(w, 0, map[string]any{
|
|
"slug": slug,
|
|
"number": n,
|
|
"title": chapterTitle,
|
|
"text": plainText,
|
|
"url": chapterURL,
|
|
})
|
|
}
|
|
|
|
// handleReindex handles POST /api/reindex/{slug}.
|
|
// Rebuilds the chapters_idx PocketBase collection for a book from MinIO objects.
|
|
func (s *Server) handleReindex(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
if slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing slug")
|
|
return
|
|
}
|
|
|
|
count, err := s.deps.BookReader.ReindexChapters(r.Context(), slug)
|
|
if err != nil {
|
|
s.deps.Log.Error("reindex failed", "slug", slug, "indexed", count, "err", err)
|
|
writeJSON(w, http.StatusInternalServerError, map[string]any{
|
|
"error": err.Error(),
|
|
"indexed": count,
|
|
})
|
|
return
|
|
}
|
|
|
|
s.deps.Log.Info("reindex complete", "slug", slug, "indexed", count)
|
|
writeJSON(w, 0, map[string]any{"slug": slug, "indexed": count})
|
|
}
|
|
|
|
// ── Audio ──────────────────────────────────────────────────────────────────────
|
|
|
|
// handleAudioGenerate handles POST /api/audio/{slug}/{n}.
|
|
// Creates an audio_jobs task in PocketBase (runner executes asynchronously).
|
|
// Returns 200 immediately if audio already exists in MinIO.
|
|
// Returns 202 with the task_id if a new task was created.
|
|
func (s *Server) handleAudioGenerate(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 {
|
|
jsonError(w, http.StatusBadRequest, "invalid chapter")
|
|
return
|
|
}
|
|
|
|
voice := s.cfg.DefaultVoice
|
|
var body struct {
|
|
Voice string `json:"voice"`
|
|
}
|
|
if r.Body != nil {
|
|
_ = json.NewDecoder(r.Body).Decode(&body)
|
|
}
|
|
if body.Voice != "" {
|
|
voice = body.Voice
|
|
}
|
|
|
|
cacheKey := fmt.Sprintf("%s/%d/%s", slug, n, voice)
|
|
|
|
// Fast path: audio already in MinIO
|
|
audioKey := s.deps.AudioStore.AudioObjectKey(slug, n, voice)
|
|
if s.deps.AudioStore.AudioExists(r.Context(), audioKey) {
|
|
proxyURL := fmt.Sprintf("/api/audio-proxy/%s/%d?voice=%s", slug, n, voice)
|
|
writeJSON(w, 0, map[string]string{"url": proxyURL, "status": "done"})
|
|
return
|
|
}
|
|
|
|
// Check if a task is already pending/running
|
|
task, found, _ := s.deps.TaskReader.GetAudioTask(r.Context(), cacheKey)
|
|
if found && (task.Status == domain.TaskStatusPending || task.Status == domain.TaskStatusRunning) {
|
|
writeJSON(w, http.StatusAccepted, map[string]string{
|
|
"task_id": task.ID,
|
|
"status": string(task.Status),
|
|
})
|
|
return
|
|
}
|
|
|
|
// Create a new audio task
|
|
taskID, err := s.deps.Producer.CreateAudioTask(r.Context(), slug, n, voice)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleAudioGenerate: CreateAudioTask failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "failed to create audio task")
|
|
return
|
|
}
|
|
|
|
writeJSON(w, http.StatusAccepted, map[string]string{
|
|
"task_id": taskID,
|
|
"status": "pending",
|
|
})
|
|
}
|
|
|
|
// handleAudioStatus handles GET /api/audio/status/{slug}/{n}.
|
|
// Polls PocketBase for the audio task status.
|
|
// Query params: voice (optional, defaults to DefaultVoice)
|
|
func (s *Server) handleAudioStatus(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 || slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "invalid params")
|
|
return
|
|
}
|
|
|
|
voice := r.URL.Query().Get("voice")
|
|
if voice == "" {
|
|
voice = s.cfg.DefaultVoice
|
|
}
|
|
|
|
// Fast path: audio exists in MinIO
|
|
audioKey := s.deps.AudioStore.AudioObjectKey(slug, n, voice)
|
|
if s.deps.AudioStore.AudioExists(r.Context(), audioKey) {
|
|
proxyURL := fmt.Sprintf("/api/audio-proxy/%s/%d?voice=%s", slug, n, voice)
|
|
writeJSON(w, 0, map[string]string{
|
|
"status": "done",
|
|
"url": proxyURL,
|
|
})
|
|
return
|
|
}
|
|
|
|
cacheKey := fmt.Sprintf("%s/%d/%s", slug, n, voice)
|
|
task, found, _ := s.deps.TaskReader.GetAudioTask(r.Context(), cacheKey)
|
|
if !found {
|
|
writeJSON(w, 0, map[string]string{"status": "idle"})
|
|
return
|
|
}
|
|
|
|
resp := map[string]string{
|
|
"status": string(task.Status),
|
|
"task_id": task.ID,
|
|
}
|
|
if task.Status == domain.TaskStatusFailed && task.ErrorMessage != "" {
|
|
resp["error"] = task.ErrorMessage
|
|
}
|
|
writeJSON(w, 0, resp)
|
|
}
|
|
|
|
// handleAudioProxy handles GET /api/audio-proxy/{slug}/{n}.
|
|
// Redirects to a presigned MinIO URL for the generated audio object.
|
|
// Query params: voice (optional, defaults to DefaultVoice)
|
|
func (s *Server) handleAudioProxy(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 {
|
|
http.NotFound(w, r)
|
|
return
|
|
}
|
|
|
|
voice := r.URL.Query().Get("voice")
|
|
if voice == "" {
|
|
voice = s.cfg.DefaultVoice
|
|
}
|
|
|
|
audioKey := s.deps.AudioStore.AudioObjectKey(slug, n, voice)
|
|
if !s.deps.AudioStore.AudioExists(r.Context(), audioKey) {
|
|
http.Error(w, "audio not generated yet", http.StatusNotFound)
|
|
return
|
|
}
|
|
|
|
presignURL, err := s.deps.PresignStore.PresignAudio(r.Context(), audioKey, 1*time.Hour)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleAudioProxy: PresignAudio failed", "slug", slug, "n", n, "err", err)
|
|
http.Error(w, "presign failed", http.StatusInternalServerError)
|
|
return
|
|
}
|
|
|
|
http.Redirect(w, r, presignURL, http.StatusFound)
|
|
}
|
|
|
|
// ── Voices ─────────────────────────────────────────────────────────────────────
|
|
|
|
// handleVoices handles GET /api/voices.
|
|
// Returns {"voices": [...]} — merged list from Kokoro and pocket-tts.
|
|
func (s *Server) handleVoices(w http.ResponseWriter, r *http.Request) {
|
|
writeJSON(w, 0, map[string]any{"voices": s.voices(r.Context())})
|
|
}
|
|
|
|
// ── Presigned URLs ─────────────────────────────────────────────────────────────
|
|
|
|
// handlePresignChapter handles GET /api/presign/chapter/{slug}/{n}.
|
|
func (s *Server) handlePresignChapter(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 || slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "invalid params")
|
|
return
|
|
}
|
|
|
|
u, err := s.deps.PresignStore.PresignChapter(r.Context(), slug, n, 15*time.Minute)
|
|
if err != nil {
|
|
s.deps.Log.Error("presign chapter failed", "slug", slug, "n", n, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "presign failed")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"url": u})
|
|
}
|
|
|
|
// handlePresignAudio handles GET /api/presign/audio/{slug}/{n}.
|
|
// Query params: voice (optional)
|
|
func (s *Server) handlePresignAudio(w http.ResponseWriter, r *http.Request) {
|
|
slug := r.PathValue("slug")
|
|
n, err := strconv.Atoi(r.PathValue("n"))
|
|
if err != nil || n < 1 || slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "invalid params")
|
|
return
|
|
}
|
|
|
|
voice := r.URL.Query().Get("voice")
|
|
if voice == "" {
|
|
voice = s.cfg.DefaultVoice
|
|
}
|
|
|
|
key := s.deps.AudioStore.AudioObjectKey(slug, n, voice)
|
|
if !s.deps.AudioStore.AudioExists(r.Context(), key) {
|
|
http.NotFound(w, r)
|
|
return
|
|
}
|
|
|
|
u, err := s.deps.PresignStore.PresignAudio(r.Context(), key, 1*time.Hour)
|
|
if err != nil {
|
|
s.deps.Log.Error("presign audio failed", "slug", slug, "n", n, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "presign failed")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"url": u})
|
|
}
|
|
|
|
// voiceSampleText is the phrase synthesised for every voice sample.
|
|
const voiceSampleText = "Hello! This is a preview of what I sound like. I hope you enjoy listening to your stories with my voice."
|
|
|
|
// handlePresignVoiceSample handles GET /api/presign/voice-sample/{voice}.
|
|
// If the sample has not been generated yet it synthesises it on the fly via
|
|
// the appropriate TTS engine (Kokoro for kokoro voices, pocket-tts for
|
|
// pocket-tts voices), stores the result in MinIO, and returns the presigned URL.
|
|
func (s *Server) handlePresignVoiceSample(w http.ResponseWriter, r *http.Request) {
|
|
voice := r.PathValue("voice")
|
|
if voice == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing voice")
|
|
return
|
|
}
|
|
|
|
key := kokoro.VoiceSampleKey(voice)
|
|
|
|
// Generate sample on demand when it is not in MinIO yet.
|
|
if !s.deps.AudioStore.AudioExists(r.Context(), key) {
|
|
s.deps.Log.Info("generating voice sample on demand", "voice", voice)
|
|
|
|
var (
|
|
mp3 []byte
|
|
err error
|
|
)
|
|
if pockettts.IsPocketTTSVoice(voice) {
|
|
if s.deps.PocketTTS == nil {
|
|
jsonError(w, http.StatusServiceUnavailable, "pocket-tts not configured")
|
|
return
|
|
}
|
|
mp3, err = s.deps.PocketTTS.GenerateAudio(r.Context(), voiceSampleText, voice)
|
|
} else {
|
|
mp3, err = s.deps.Kokoro.GenerateAudio(r.Context(), voiceSampleText, voice)
|
|
}
|
|
if err != nil {
|
|
s.deps.Log.Error("voice sample generation failed", "voice", voice, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "voice sample generation failed")
|
|
return
|
|
}
|
|
if err := s.deps.AudioStore.PutAudio(r.Context(), key, mp3); err != nil {
|
|
s.deps.Log.Error("voice sample upload failed", "voice", voice, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "voice sample upload failed")
|
|
return
|
|
}
|
|
}
|
|
|
|
u, err := s.deps.PresignStore.PresignAudio(r.Context(), key, 1*time.Hour)
|
|
if err != nil {
|
|
s.deps.Log.Error("presign voice sample failed", "voice", voice, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "presign failed")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"url": u})
|
|
}
|
|
|
|
// handleAvatarUpload handles PUT /api/avatar-upload/{userId}.
|
|
// The request body must be the raw image bytes; Content-Type must be
|
|
// image/jpeg, image/png, or image/webp.
|
|
//
|
|
// This endpoint is called by the SvelteKit server (not the browser directly),
|
|
// so MinIO credentials and internal networking are not a concern.
|
|
//
|
|
// Returns: { "key": "<objectKey>" }
|
|
func (s *Server) handleAvatarUpload(w http.ResponseWriter, r *http.Request) {
|
|
userID := r.PathValue("userId")
|
|
if userID == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing userId")
|
|
return
|
|
}
|
|
|
|
ct := r.Header.Get("Content-Type")
|
|
var ext string
|
|
switch {
|
|
case strings.HasPrefix(ct, "image/jpeg"):
|
|
ext = "jpg"
|
|
case strings.HasPrefix(ct, "image/png"):
|
|
ext = "png"
|
|
case strings.HasPrefix(ct, "image/webp"):
|
|
ext = "webp"
|
|
default:
|
|
jsonError(w, http.StatusBadRequest, "unsupported content-type; use image/jpeg, image/png, or image/webp")
|
|
return
|
|
}
|
|
|
|
const maxSize = 5 << 20 // 5 MiB
|
|
data, err := io.ReadAll(io.LimitReader(r.Body, maxSize+1))
|
|
if err != nil {
|
|
jsonError(w, http.StatusBadRequest, "failed to read body")
|
|
return
|
|
}
|
|
if len(data) > maxSize {
|
|
jsonError(w, http.StatusRequestEntityTooLarge, "image too large (max 5 MiB)")
|
|
return
|
|
}
|
|
if len(data) == 0 {
|
|
jsonError(w, http.StatusBadRequest, "empty body")
|
|
return
|
|
}
|
|
|
|
key, err := s.deps.PresignStore.PutAvatar(r.Context(), userID, ext, ct, data)
|
|
if err != nil {
|
|
s.deps.Log.Error("avatar upload failed", "userId", userID, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "upload failed")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"key": key})
|
|
}
|
|
|
|
// handlePresignAvatarUpload handles GET /api/presign/avatar-upload/{userId}.
|
|
// Query params: ext (jpg|png|webp, defaults to jpg)
|
|
func (s *Server) handlePresignAvatarUpload(w http.ResponseWriter, r *http.Request) {
|
|
userID := r.PathValue("userId")
|
|
if userID == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing userId")
|
|
return
|
|
}
|
|
|
|
ext := r.URL.Query().Get("ext")
|
|
switch ext {
|
|
case "jpg", "jpeg":
|
|
ext = "jpg"
|
|
case "png":
|
|
ext = "png"
|
|
case "webp":
|
|
ext = "webp"
|
|
default:
|
|
ext = "jpg"
|
|
}
|
|
|
|
uploadURL, key, err := s.deps.PresignStore.PresignAvatarUpload(r.Context(), userID, ext)
|
|
if err != nil {
|
|
s.deps.Log.Error("presign avatar upload failed", "userId", userID, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "presign failed")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"upload_url": uploadURL, "key": key})
|
|
}
|
|
|
|
// handlePresignAvatar handles GET /api/presign/avatar/{userId}.
|
|
func (s *Server) handlePresignAvatar(w http.ResponseWriter, r *http.Request) {
|
|
userID := r.PathValue("userId")
|
|
if userID == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing userId")
|
|
return
|
|
}
|
|
|
|
u, found, err := s.deps.PresignStore.PresignAvatarURL(r.Context(), userID)
|
|
if err != nil {
|
|
s.deps.Log.Error("presign avatar failed", "userId", userID, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "presign failed")
|
|
return
|
|
}
|
|
if !found {
|
|
http.NotFound(w, r)
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{"url": u})
|
|
}
|
|
|
|
// ── Progress ───────────────────────────────────────────────────────────────────
|
|
|
|
// handleGetProgress handles GET /api/progress.
|
|
// Returns {"slug": chapterNum, "slug_ts": timestampMs, ...}
|
|
func (s *Server) handleGetProgress(w http.ResponseWriter, r *http.Request) {
|
|
sid := ensureSession(w, r)
|
|
entries, err := s.deps.ProgressStore.AllProgress(r.Context(), sid)
|
|
if err != nil {
|
|
s.deps.Log.Error("AllProgress failed", "err", err)
|
|
entries = nil
|
|
}
|
|
|
|
progress := make(map[string]any, len(entries)*2)
|
|
for _, p := range entries {
|
|
progress[p.Slug] = p.Chapter
|
|
progress[p.Slug+"_ts"] = p.UpdatedAt.UnixMilli()
|
|
}
|
|
writeJSON(w, 0, progress)
|
|
}
|
|
|
|
// handleSetProgress handles POST /api/progress/{slug}.
|
|
// Body: {"chapter": N}
|
|
func (s *Server) handleSetProgress(w http.ResponseWriter, r *http.Request) {
|
|
sid := ensureSession(w, r)
|
|
slug := r.PathValue("slug")
|
|
if slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing slug")
|
|
return
|
|
}
|
|
|
|
var body struct {
|
|
Chapter int `json:"chapter"`
|
|
}
|
|
if err := json.NewDecoder(r.Body).Decode(&body); err != nil || body.Chapter < 1 {
|
|
jsonError(w, http.StatusBadRequest, "invalid body")
|
|
return
|
|
}
|
|
|
|
p := domain.ReadingProgress{
|
|
Slug: slug,
|
|
Chapter: body.Chapter,
|
|
UpdatedAt: time.Now(),
|
|
}
|
|
if err := s.deps.ProgressStore.SetProgress(r.Context(), sid, p); err != nil {
|
|
s.deps.Log.Error("SetProgress failed", "slug", slug, "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "store error")
|
|
return
|
|
}
|
|
writeJSON(w, 0, map[string]string{})
|
|
}
|
|
|
|
// handleDeleteProgress handles DELETE /api/progress/{slug}.
|
|
func (s *Server) handleDeleteProgress(w http.ResponseWriter, r *http.Request) {
|
|
sid := ensureSession(w, r)
|
|
slug := r.PathValue("slug")
|
|
if slug == "" {
|
|
jsonError(w, http.StatusBadRequest, "missing slug")
|
|
return
|
|
}
|
|
|
|
if err := s.deps.ProgressStore.DeleteProgress(r.Context(), sid, slug); err != nil {
|
|
s.deps.Log.Error("DeleteProgress failed", "slug", slug, "err", err)
|
|
// non-fatal
|
|
}
|
|
writeJSON(w, 0, map[string]string{})
|
|
}
|
|
|
|
// ── Catalogue (Meilisearch-backed browse + search) ────────────────────────────
|
|
|
|
// handleCatalogue handles GET /api/catalogue.
|
|
//
|
|
// Provides unified browse + search over the locally-indexed book catalogue
|
|
// via Meilisearch. Unlike /api/browse this never fetches novelfire.net live —
|
|
// it is entirely served from the Meilisearch index populated by the runner.
|
|
//
|
|
// Query params:
|
|
//
|
|
// q — full-text search query (optional)
|
|
// genre — genre filter, e.g. "fantasy" or "all" (default "all")
|
|
// status — status filter: "ongoing", "completed", or "all" (default "all")
|
|
// sort — "popular" (default) | "new" | "top-rated" | "rank"
|
|
// page — 1-indexed page number (default 1)
|
|
// limit — items per page (default 20, max 100)
|
|
func (s *Server) handleCatalogue(w http.ResponseWriter, r *http.Request) {
|
|
q := r.URL.Query()
|
|
|
|
genre := q.Get("genre")
|
|
if genre == "" {
|
|
genre = "all"
|
|
}
|
|
status := q.Get("status")
|
|
if status == "" {
|
|
status = "all"
|
|
}
|
|
sort := q.Get("sort")
|
|
if sort == "" {
|
|
sort = "popular"
|
|
}
|
|
|
|
page, _ := strconv.Atoi(q.Get("page"))
|
|
if page <= 0 {
|
|
page = 1
|
|
}
|
|
limit, _ := strconv.Atoi(q.Get("limit"))
|
|
if limit <= 0 {
|
|
limit = 20
|
|
}
|
|
if limit > 100 {
|
|
limit = 100
|
|
}
|
|
|
|
cq := meili.CatalogueQuery{
|
|
Q: q.Get("q"),
|
|
Genre: genre,
|
|
Status: status,
|
|
Sort: sort,
|
|
Page: page,
|
|
Limit: limit,
|
|
}
|
|
|
|
books, total, facets, err := s.deps.SearchIndex.Catalogue(r.Context(), cq)
|
|
if err != nil {
|
|
s.deps.Log.Error("handleCatalogue: Catalogue query failed", "err", err)
|
|
jsonError(w, http.StatusInternalServerError, "search failed")
|
|
return
|
|
}
|
|
|
|
hasNext := int64(page*limit) < total
|
|
|
|
w.Header().Set("Cache-Control", "public, max-age=60")
|
|
writeJSON(w, 0, map[string]any{
|
|
"books": books,
|
|
"page": page,
|
|
"limit": limit,
|
|
"total": total,
|
|
"has_next": hasNext,
|
|
"facets": map[string]any{
|
|
"genres": facets.Genres,
|
|
"statuses": facets.Statuses,
|
|
},
|
|
})
|
|
}
|
|
|
|
// ── Browse page parsing helpers ────────────────────────────────────────────────
|
|
|
|
// fetchBrowsePage fetches pageURL and parses NovelListings from the HTML.
|
|
func (s *Server) fetchBrowsePage(ctx context.Context, pageURL string) ([]NovelListing, bool, error) {
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, pageURL, nil)
|
|
if err != nil {
|
|
return nil, false, fmt.Errorf("build request: %w", err)
|
|
}
|
|
req.Header.Set("User-Agent", "Mozilla/5.0 (compatible; libnovel-backend/2)")
|
|
req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
|
|
req.Header.Set("Accept-Language", "en-US,en;q=0.9")
|
|
|
|
resp, err := http.DefaultClient.Do(req)
|
|
if err != nil {
|
|
return nil, false, fmt.Errorf("fetch %s: %w", pageURL, err)
|
|
}
|
|
defer resp.Body.Close()
|
|
|
|
if resp.StatusCode != http.StatusOK {
|
|
_, _ = io.Copy(io.Discard, resp.Body)
|
|
return nil, false, fmt.Errorf("upstream returned %d", resp.StatusCode)
|
|
}
|
|
|
|
novels, hasNext := parseBrowsePage(resp.Body)
|
|
return novels, hasNext, nil
|
|
}
|
|
|
|
// parseBrowsePage parses a novelfire HTML body and returns novel listings.
|
|
// It uses a simple string-scanning approach to avoid importing golang.org/x/net/html
|
|
// in this package (that dependency is only in internal/novelfire).
|
|
func parseBrowsePage(r io.Reader) ([]NovelListing, bool) {
|
|
data, err := io.ReadAll(r)
|
|
if err != nil {
|
|
return nil, false
|
|
}
|
|
body := string(data)
|
|
|
|
var novels []NovelListing
|
|
hasNext := false
|
|
|
|
// Detect "next page" link
|
|
if strings.Contains(body, `rel="next"`) ||
|
|
strings.Contains(body, `aria-label="Next"`) ||
|
|
strings.Contains(body, `class="next"`) {
|
|
hasNext = true
|
|
}
|
|
|
|
// Extract novel slugs and titles using simple regex patterns.
|
|
// novelfire.net novel items: <li class="novel-item">...</li>
|
|
// Each contains an anchor like <a href="/book/{slug}">
|
|
slugRe := regexp.MustCompile(`href="/book/([^/"]+)"`)
|
|
titleRe := regexp.MustCompile(`class="novel-title[^"]*"[^>]*>([^<]+)<`)
|
|
coverRe := regexp.MustCompile(`data-src="(https?://[^"]+)"`)
|
|
|
|
slugMatches := slugRe.FindAllStringSubmatch(body, -1)
|
|
titleMatches := titleRe.FindAllStringSubmatch(body, -1)
|
|
coverMatches := coverRe.FindAllStringSubmatch(body, -1)
|
|
|
|
seen := make(map[string]bool)
|
|
for i, sm := range slugMatches {
|
|
slug := sm[1]
|
|
if seen[slug] {
|
|
continue
|
|
}
|
|
seen[slug] = true
|
|
|
|
novel := NovelListing{
|
|
Slug: slug,
|
|
URL: novelFireBase + "/book/" + slug,
|
|
}
|
|
if i < len(titleMatches) {
|
|
novel.Title = strings.TrimSpace(titleMatches[i][1])
|
|
}
|
|
if i < len(coverMatches) {
|
|
novel.Cover = coverMatches[i][1]
|
|
}
|
|
if novel.Title != "" {
|
|
novels = append(novels, novel)
|
|
}
|
|
}
|
|
|
|
return novels, hasNext
|
|
}
|
|
|
|
// ── Markdown stripping ─────────────────────────────────────────────────────────
|
|
|
|
// stripMarkdown removes common markdown syntax from src, returning plain text.
|
|
func stripMarkdown(src string) string {
|
|
src = regexp.MustCompile(`(?m)^#{1,6}\s+`).ReplaceAllString(src, "")
|
|
src = regexp.MustCompile(`\*{1,3}|_{1,3}`).ReplaceAllString(src, "")
|
|
src = regexp.MustCompile("(?s)```.*?```").ReplaceAllString(src, "")
|
|
src = regexp.MustCompile("`[^`]*`").ReplaceAllString(src, "")
|
|
src = regexp.MustCompile(`\[([^\]]+)\]\([^)]+\)`).ReplaceAllString(src, "$1")
|
|
src = regexp.MustCompile(`!\[[^\]]*\]\([^)]+\)`).ReplaceAllString(src, "")
|
|
src = regexp.MustCompile(`(?m)^>\s?`).ReplaceAllString(src, "")
|
|
src = regexp.MustCompile(`(?m)^[-*_]{3,}\s*$`).ReplaceAllString(src, "")
|
|
src = regexp.MustCompile(`\n{3,}`).ReplaceAllString(src, "\n\n")
|
|
return strings.TrimSpace(src)
|
|
}
|
|
|
|
// ── Hardcoded Kokoro voice fallback ───────────────────────────────────────────
|
|
|
|
// kokoroVoiceIDs is the built-in fallback list of Kokoro voice IDs used when
|
|
// the Kokoro service is unavailable.
|
|
var kokoroVoiceIDs = []string{
|
|
// American English
|
|
"af_alloy", "af_aoede", "af_bella", "af_heart", "af_jadzia",
|
|
"af_jessica", "af_kore", "af_nicole", "af_nova", "af_river",
|
|
"af_sarah", "af_sky",
|
|
"am_adam", "am_echo", "am_eric", "am_fenrir", "am_liam",
|
|
"am_michael", "am_onyx", "am_puck",
|
|
// British English
|
|
"bf_alice", "bf_emma", "bf_lily",
|
|
"bm_daniel", "bm_fable", "bm_george", "bm_lewis",
|
|
// Spanish
|
|
"ef_dora", "em_alex",
|
|
// French
|
|
"ff_siwis",
|
|
// Hindi
|
|
"hf_alpha", "hf_beta", "hm_omega", "hm_psi",
|
|
// Italian
|
|
"if_sara", "im_nicola",
|
|
// Japanese
|
|
"jf_alpha", "jf_gongitsune", "jf_nezumi", "jf_tebukuro", "jm_kumo",
|
|
// Portuguese
|
|
"pf_dora", "pm_alex",
|
|
// Chinese
|
|
"zf_xiaobei", "zf_xiaoni", "zf_xiaoxiao", "zf_xiaoyi",
|
|
"zm_yunjian", "zm_yunxi", "zm_yunxia", "zm_yunyang",
|
|
}
|