XingfenD/book-comic-library
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(cbz): adapt reader to real archive structure — PageIndex skips macOS junk (__MACOSX/ and ._ AppleDouble were polluting pages with 163-byte blacks), pages endpoint derives chapters[{title,start}] from folder layout, imageless zip now lands state=error instead of an empty reader, CbzReader gains 目录 sidebar + prev/next chapter (TextReader pattern, rd-* classes); pagesidx cache key bumped for one-time invalidation; e2e on 311MB 調教開關：第二季.zip: 15048→7524 real pages, 52 chapters, all JPEGs

Browse Source
This commit is contained in:
XingfenD
2026-09-08 00:22:13 +08:00
parent 7d650107d2
commit b8da9fd92e
9 changed files with 216 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/cmd/webui/handlers/content.go
+44 -2
View File
@@ -4,6 +4,7 @@ import (
"fmt"
"net/http"
"os"
"path"
"path/filepath"
"strconv"
"strings"
@@ -118,7 +119,7 @@ func (h *H) openBook(c *gin.Context, b store.Book, root string) (*os.File, int64
func (h *H) pageIndex(c *gin.Context, b store.Book, root string) ([]string, error) {
hash := bookfile.Hash(b.FileSize, b.ModTS)
key := fmt.Sprintf("pagesidx:%d:%s", b.ID, hash)
key := fmt.Sprintf("pagesidx2:%d:%s", b.ID, hash) // 前缀换代 = 索引逻辑变更时一次性作废旧缓存
if v, ok := h.rdb.Get(c, key); ok && v != "" {
return strings.Split(v, "\n"), nil
}
@@ -158,7 +159,48 @@ func (h *H) PagesCount(c *gin.Context) {
err(c, http.StatusUnprocessableEntity, "broken", e.Error())
return
}
c.JSON(http.StatusOK, gin.H{"count": len(idx)})
c.JSON(http.StatusOK, gin.H{"count": len(idx), "chapters": chaptersOf(idx)})
}
type cbzChapter struct {
Title string `json:"title"`
Start int `json:"start"`
}
// chaptersOf 页索引已自然序排列,按父目录分组:每个新目录开一章,标题取目录名;扁平包或只有一组返回 nil
func chaptersOf(idx []string) []cbzChapter {
type grp struct {
dir string
start int
}
var grps []grp
last := "\x00"
for i, n := range idx {
d := path.Dir(n)
if d == last {
continue
}
last = d
if d == "." { // 根目录散页不开章
continue
}
grps = append(grps, grp{d, i})
}
if len(grps) < 2 {
return nil
}
titles := make(map[string]int)
out := make([]cbzChapter, len(grps))
for i, g := range grps {
out[i] = cbzChapter{Title: path.Base(g.dir), Start: g.start}
titles[out[i].Title]++
}
for i, g := range grps { // 同名目录(不同父级)撞车 → 用全路径消歧
if titles[out[i].Title] > 1 {
out[i].Title = g.dir
}
}
return out
}
func (h *H) Page(c *gin.Context) {
backend/cmd/webui/handlers/content_test.go
+72
View File
@@ -1,6 +1,8 @@
package handlers_test
import (
"archive/zip"
"bytes"
"context"
"encoding/json"
"net/http"
@@ -103,6 +105,76 @@ func TestPages(t *testing.T) {
}
}
func zipTo(t *testing.T, path string, kv map[string]string) {
t.Helper()
os.MkdirAll(filepath.Dir(path), 0o755)
buf := &bytes.Buffer{}
zw := zip.NewWriter(buf)
for n, v := range kv {
w, err := zw.Create(n)
if err != nil {
t.Fatal(err)
}
w.Write([]byte(v))
}
zw.Close()
os.WriteFile(path, buf.Bytes(), 0o644)
}
func TestPagesChaptersAndNoImageZip(t *testing.T) {
st, sc, h, booksDir := setupAPI(t)
tok := adminToken(t, h)
lib, root := newLibrary(t, st, h, tok, booksDir, "ch")
zipTo(t, filepath.Join(root, "show.cbz"), map[string]string{
"第2季/第2話/0001.jpg": "IMG2",
"第2季/第1話/0001.jpg": "IMG1a",
"第2季/第1話/._0001.jpg": "junk",
"__MACOSX/第2季/._0001.jpg": "junk",
})
zipTo(t, filepath.Join(root, "videos.zip"), map[string]string{"ep/01.mkv": "x"})
scanNow(t, sc, lib)
bookID := func(q string) string {
w := do(h, "GET", "/api/books?q="+q, tok, nil)
var bs []map[string]any
json.Unmarshal(w.Body.Bytes(), &bs)
if len(bs) != 1 {
t.Fatalf("q=%s books: %s", q, w.Body)
}
return itoa(bs[0]["id"])
}
cbzID := bookID("show")
w := do(h, "GET", "/api/books/"+cbzID+"/pages", tok, nil)
var pg struct {
Count int `json:"count"`
Chapters []struct {
Title string `json:"title"`
Start int `json:"start"`
} `json:"chapters"`
}
json.Unmarshal(w.Body.Bytes(), &pg)
if pg.Count != 2 || len(pg.Chapters) != 2 {
t.Fatalf("pages want 2/2ch got %s", w.Body)
}
if pg.Chapters[0].Title != "第1話" || pg.Chapters[0].Start != 0 || pg.Chapters[1].Start != 1 {
t.Fatalf("chapters: %s", w.Body)
}
ww := do(h, "GET", "/api/books/"+cbzID+"/pages/0", tok, nil)
if ww.Code != 200 || ww.Body.String() != "IMG1a" {
t.Fatalf("page0 must be real image (junk filtered): %d %s", ww.Code, ww.Body)
}
if ww := do(h, "GET", "/api/books/"+cbzID+"/pages/2", tok, nil); ww.Code != 404 {
t.Fatalf("junk-indexed page must be gone: %d", ww.Code)
}
// 无图 zip → state=error,而不是空白 reader
w = do(h, "GET", "/api/books/"+bookID("videos"), tok, nil)
var bk map[string]any
json.Unmarshal(w.Body.Bytes(), &bk)
if bk["state"] != "error" || !strings.Contains(bk["error"].(string), "no images") {
t.Fatalf("empty-image zip want error, got %s", w.Body)
}
}
func TestBrokenCBZ(t *testing.T) {
st, sc, h, booksDir := setupAPI(t)
atok := adminToken(t, h)
backend/internal/bookfile/zip.go
+11
View File
@@ -26,6 +26,14 @@ func isImage(name string) bool {
return false
}
// junkEntry: macOS 打包混入的资源叉垃圾(__MACOSX/ 目录与 ._* AppleDouble),不是页
func junkEntry(name string) bool {
if strings.HasPrefix(strings.ToLower(name), "__macosx/") {
return true
}
return strings.HasPrefix(path.Base(name), "._")
}
func PageIndex(f io.ReaderAt, size int64) ([]string, error) {
zr, err := zip.NewReader(f, size)
if err != nil {
@@ -36,6 +44,9 @@ func PageIndex(f io.ReaderAt, size int64) ([]string, error) {
if unsafeEntry(zf.Name) {
return nil, fmt.Errorf("%w: %s", ErrUnsafeZip, zf.Name)
}
if junkEntry(zf.Name) {
continue
}
if isImage(zf.Name) {
names = append(names, zf.Name)
}
backend/internal/bookfile/zip_test.go
+17
View File
@@ -38,6 +38,23 @@ func TestPageIndexSortAndFilter(t *testing.T) {
}
}
func TestPageIndexSkipsAppleDouble(t *testing.T) {
r := zipOf(t, "第2季/第2話/0001.jpg", "第2季/第1話/._0001.jpg", "__MACOSX/第2季/._0001.jpg", "第2季/第1話/0001.jpg", "._top.jpg")
idx, err := PageIndex(r, int64(r.Len()))
if err != nil {
t.Fatal(err)
}
want := []string{"第2季/第1話/0001.jpg", "第2季/第2話/0001.jpg"}
if len(idx) != len(want) {
t.Fatalf("got %v want %v", idx, want)
}
for i := range want {
if idx[i] != want[i] {
t.Fatalf("got %v want %v", idx, want)
}
}
}
func TestPageIndexRejectsSlip(t *testing.T) {
for _, bad := range []string{"../evil.jpg", "/etc/passwd.jpg", "a\\..\\b.jpg", "pag\ne.jpg", "pag\re.jpg"} {
r := zipOf(t, bad)
backend/internal/scanner/scanner.go
+7
View File
@@ -2,6 +2,7 @@ package scanner
import (
"context"
"errors"
"fmt"
"io"
"io/fs"
@@ -146,6 +147,9 @@ func (s *Scanner) add(ctx context.Context, libID int64, root, rel string, ds dis
idx, err := s.zipIndex(root, rel)
pageCount = len(idx)
idxErr = err
if idxErr == nil && pageCount == 0 { // 视频/文档 zip 不是漫画,空白 reader 没有意义
idxErr = errors.New("no images in archive")
}
}
id, err := s.st.InsertBook(ctx, libID, rel, titleOf(rel), format, ds.size, ds.modTS, pageCount)
if err != nil {
@@ -167,6 +171,9 @@ func (s *Scanner) update(ctx context.Context, libID, bookID int64, root, rel str
idx, err := s.zipIndex(root, rel)
pageCount = len(idx)
idxErr = err
if idxErr == nil && pageCount == 0 { // 视频/文档 zip 不是漫画,空白 reader 没有意义
idxErr = errors.New("no images in archive")
}
}
if err := s.st.UpdateBookFile(ctx, bookID, ds.size, ds.modTS, pageCount); err != nil {
log.Printf("scan: update %s: %v", rel, err)