refactor!: disk-first zero-copy architecture with file-to-file cwebp conversion

BREAKING CHANGE: Complete refactoring of the conversion pipeline.

- Replace in-memory Page/PageContainer with disk-based PageFile struct
- Extract archives to temp directory instead of loading into memory
- Use cwebp InputFile/OutputFile for zero-copy file-to-file conversion
- Use cwebp -crop for splitting (no Go-side image decode needed)
- Check if already converted before extracting (fast pre-check)
- Remove oliamb/cutter dependency (replaced by cwebp -crop)
- Remove page_container.go (no longer needed)
- Add comprehensive tests with improved coverage

Co-authored-by: Belphemur <197810+Belphemur@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-07-04 22:18:22 +00:00
committed by GitHub
co-authored by Belphemur
parent e87e73eb28
commit 164dc577b9
21 changed files with 1735 additions and 1386 deletions
+123 -55
View File
@@ -2,88 +2,102 @@ package cbz
import (
"archive/zip"
"bytes"
"fmt"
"github.com/belphemur/CBZOptimizer/v2/internal/manga"
"github.com/belphemur/CBZOptimizer/v2/internal/utils/errs"
"os"
"path/filepath"
"testing"
"time"
"github.com/belphemur/CBZOptimizer/v2/internal/manga"
"github.com/belphemur/CBZOptimizer/v2/internal/utils/errs"
)
func TestWriteChapterToCBZ(t *testing.T) {
currentTime := time.Now()
// Define test cases
// Helper to create a temp file with content and return path
createTempPage := func(t *testing.T, dir, content, ext string) string {
t.Helper()
f, err := os.CreateTemp(dir, "page-*"+ext)
if err != nil {
t.Fatal(err)
}
_, err = f.WriteString(content)
if err != nil {
_ = f.Close()
t.Fatal(err)
}
_ = f.Close()
return f.Name()
}
testCases := []struct {
name string
chapter *manga.Chapter
chapter func(t *testing.T, dir string) *manga.Chapter
expectedFiles []string
expectedComment string
}{
//test case where there is only one page and ComicInfo and the chapter is converted
{
name: "Single page, ComicInfo, converted",
chapter: &manga.Chapter{
Pages: []*manga.Page{
{
Index: 0,
Extension: ".jpg",
Contents: bytes.NewBuffer([]byte("image data")),
chapter: func(t *testing.T, dir string) *manga.Chapter {
return &manga.Chapter{
Pages: []*manga.PageFile{
{
Index: 0,
Extension: ".jpg",
FilePath: createTempPage(t, dir, "image data", ".jpg"),
},
},
},
ComicInfoXml: "<Series>Boundless Necromancer</Series>",
IsConverted: true,
ConvertedTime: currentTime,
ComicInfoXml: "<Series>Boundless Necromancer</Series>",
IsConverted: true,
ConvertedTime: currentTime,
}
},
expectedFiles: []string{"0000.jpg", "ComicInfo.xml"},
expectedComment: fmt.Sprintf("%s\nThis chapter has been converted by CBZOptimizer.", currentTime),
},
//test case where there is only one page and no
{
name: "Single page, no ComicInfo",
chapter: &manga.Chapter{
Pages: []*manga.Page{
{
Index: 0,
Extension: ".jpg",
Contents: bytes.NewBuffer([]byte("image data")),
chapter: func(t *testing.T, dir string) *manga.Chapter {
return &manga.Chapter{
Pages: []*manga.PageFile{
{
Index: 0,
Extension: ".jpg",
FilePath: createTempPage(t, dir, "image data", ".jpg"),
},
},
},
}
},
expectedFiles: []string{"0000.jpg"},
},
{
name: "Multiple pages with ComicInfo",
chapter: &manga.Chapter{
Pages: []*manga.Page{
{
Index: 0,
Extension: ".jpg",
Contents: bytes.NewBuffer([]byte("image data 1")),
chapter: func(t *testing.T, dir string) *manga.Chapter {
return &manga.Chapter{
Pages: []*manga.PageFile{
{Index: 0, Extension: ".jpg", FilePath: createTempPage(t, dir, "image data 1", ".jpg")},
{Index: 1, Extension: ".jpg", FilePath: createTempPage(t, dir, "image data 2", ".jpg")},
},
{
Index: 1,
Extension: ".jpg",
Contents: bytes.NewBuffer([]byte("image data 2")),
},
},
ComicInfoXml: "<Series>Boundless Necromancer</Series>",
ComicInfoXml: "<Series>Boundless Necromancer</Series>",
}
},
expectedFiles: []string{"0000.jpg", "0001.jpg", "ComicInfo.xml"},
},
{
name: "Split page",
chapter: &manga.Chapter{
Pages: []*manga.Page{
{
Index: 0,
Extension: ".jpg",
Contents: bytes.NewBuffer([]byte("split image data")),
IsSplitted: true,
SplitPartIndex: 1,
chapter: func(t *testing.T, dir string) *manga.Chapter {
return &manga.Chapter{
Pages: []*manga.PageFile{
{
Index: 0,
Extension: ".jpg",
FilePath: createTempPage(t, dir, "split image data", ".jpg"),
IsSplitted: true,
SplitPartIndex: 1,
},
},
},
}
},
expectedFiles: []string{"0000-01.jpg"},
},
@@ -91,33 +105,36 @@ func TestWriteChapterToCBZ(t *testing.T) {
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
// Create a temporary file for the .cbz output
// Create temp dir for page files
pageDir := t.TempDir()
chapter := tc.chapter(t, pageDir)
// Create temp file for output CBZ
tempFile, err := os.CreateTemp("", "*.cbz")
if err != nil {
t.Fatalf("Failed to create temporary file: %v", err)
}
_ = tempFile.Close()
defer errs.CaptureGeneric(&err, os.Remove, tempFile.Name(), "failed to remove temporary file")
// Write the chapter to the .cbz file
err = WriteChapterToCBZ(tc.chapter, tempFile.Name())
// Write chapter
err = WriteChapterToCBZ(chapter, tempFile.Name())
if err != nil {
t.Fatalf("Failed to write chapter to CBZ: %v", err)
}
// Open the .cbz file as a zip archive
// Verify the archive
r, err := zip.OpenReader(tempFile.Name())
if err != nil {
t.Fatalf("Failed to open CBZ file: %v", err)
}
defer errs.Capture(&err, r.Close, "failed to close CBZ file")
defer func() { _ = r.Close() }()
// Collect the names of the files in the archive
var filesInArchive []string
for _, f := range r.File {
filesInArchive = append(filesInArchive, f.Name)
}
// Check if all expected files are present
for _, expectedFile := range tc.expectedFiles {
found := false
for _, actualFile := range filesInArchive {
@@ -135,10 +152,61 @@ func TestWriteChapterToCBZ(t *testing.T) {
t.Errorf("Expected comment %s, but found %s", tc.expectedComment, r.Comment)
}
// Check if there are no unexpected files
if len(filesInArchive) != len(tc.expectedFiles) {
t.Errorf("Expected %d files, but found %d", len(tc.expectedFiles), len(filesInArchive))
t.Errorf("Expected %d files, but found %d: %v", len(tc.expectedFiles), len(filesInArchive), filesInArchive)
}
})
}
}
func TestWriteAndReadRoundTrip(t *testing.T) {
// Create a temp directory with page files
pageDir := t.TempDir()
// Create some page files
for i := 0; i < 3; i++ {
pagePath := filepath.Join(pageDir, fmt.Sprintf("%04d.jpg", i))
err := os.WriteFile(pagePath, []byte(fmt.Sprintf("image data %d", i)), 0644)
if err != nil {
t.Fatal(err)
}
}
// Create chapter
chapter := &manga.Chapter{
FilePath: "/test/chapter.cbz",
Pages: []*manga.PageFile{
{Index: 0, Extension: ".jpg", FilePath: filepath.Join(pageDir, "0000.jpg")},
{Index: 1, Extension: ".jpg", FilePath: filepath.Join(pageDir, "0001.jpg")},
{Index: 2, Extension: ".jpg", FilePath: filepath.Join(pageDir, "0002.jpg")},
},
ComicInfoXml: "<Series>Test Series</Series>",
}
chapter.SetConverted()
// Write to CBZ
outputPath := filepath.Join(t.TempDir(), "output.cbz")
err := WriteChapterToCBZ(chapter, outputPath)
if err != nil {
t.Fatalf("Failed to write chapter: %v", err)
}
// Read it back
loaded, err := LoadChapter(outputPath)
if err != nil {
t.Fatalf("Failed to load chapter: %v", err)
}
defer func() { _ = loaded.Cleanup() }()
if !loaded.IsConverted {
t.Error("Loaded chapter should be marked as converted")
}
if len(loaded.Pages) != 3 {
t.Errorf("Expected 3 pages, got %d", len(loaded.Pages))
}
if loaded.ComicInfoXml != "<Series>Test Series</Series>" {
t.Errorf("ComicInfoXml mismatch: %s", loaded.ComicInfoXml)
}
}