Revert "huge speed optimization on HDD by removing md5 (#845)"

This reverts commit 01625904d1.

.travis.yml

@@ -1,30 +0,0 @@
-matrix:
-  include:
-  - os: osx
-    language: generic
-    osx_image: xcode11.1
-
-before_install:
-- pip3 install --upgrade pip setuptools wheel
-
-install:
-- pip3 install -r requirements.txt
-- pip3 install certifi https://github.com/pyinstaller/pyinstaller/archive/develop.zip
-- npm install -g appdmg
-
-script: python3 setup.py build_binary
-
-before_deploy:
-- shopt -s extglob
-- rm -r dist/!(*.deb|*.dmg)
-
-deploy:
-  provider: gcs
-  access_key_id: GOOG1EC62457RKUYFR2TIZUWV4EFSV2EP5LVLPPFXUAKADWJFDYPFW63BQSLA
-  secret_access_key:
-    secure: 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
-  bucket: kcc-deploy
-  local-dir: dist
-  skip_cleanup: true
-  on:
-    repo: AcidWeb/KCC

LICENSE.txt

@@ -1,8 +1,9 @@
 ISC LICENSE
 
-Copyright (c) 2012-2014 Ciro Mattia Gonano <ciromattia@gmail.com>
+Copyright (c) 2012-2025 Ciro Mattia Gonano <ciromattia@gmail.com>
 Copyright (c) 2013-2019 Paweł Jastrzębski <pawelj@iosphe.re>
-Copyright (c) 2021-2023 Darodi
+Copyright (c) 2021-2023 Darodi (https://github.com/darodi)
+Copyright (c) 2023-2025 Alex Xu (https://github.com/axu2)
 
 Permission to use, copy, modify, and/or distribute this software for
 any purpose with or without fee is hereby granted, provided that the

README.md

@@ -11,6 +11,8 @@ It was initially developed for Kindle but since version 4.6 it outputs valid EPU
 actually a comic/manga to EPUB converter that every e-reader owner can happily use**_.
 It can also optionally optimize images by applying a number of transformations.
 
+![image](https://github.com/user-attachments/assets/36ad2131-6677-4559-bd6f-314a90c27218)
+
 ### A word of warning
 **KCC** _is not_ [Amazon's Kindle Comic Creator](http://www.amazon.com/gp/feature.html?ie=UTF8&docId=1001103761) nor is in any way endorsed by Amazon.
 Amazon's tool is for comic publishers and involves a lot of manual effort, while **KCC** is for comic/manga readers.
@@ -319,5 +321,5 @@ The app relies and includes the following scripts:
 Please check [wiki page](https://github.com/ciromattia/kcc/wiki/Known-issues).
 
 ## COPYRIGHT
-Copyright (c) 2012-2023 Ciro Mattia Gonano, Paweł Jastrzębski and Darodi.
+Copyright (c) 2012-2025 Ciro Mattia Gonano, Paweł Jastrzębski, Darodi and Alex Xu.
 **KCC** is released under ISC LICENSE; see [LICENSE.txt](./LICENSE.txt) for further details.

appveyor.yml

@@ -1,14 +0,0 @@
-environment:
-  PYTHON: "C:\\Python37-x64"
-
-install:
-  - set PATH="%PYTHON%\\Scripts";%PATH%
-  - "%PYTHON%\\python.exe -m pip install --upgrade pip setuptools wheel"
-  - "%PYTHON%\\python.exe -m pip install -r requirements.txt"
-  - "%PYTHON%\\python.exe -m pip install certifi https://github.com/pyinstaller/pyinstaller/archive/develop.zip"
-
-build_script:
-    - "%PYTHON%\\python.exe setup.py build_binary"
-
-artifacts:
-  - path: dist\KCC*

kindlecomicconverter/comic2ebook.py

@@ -40,7 +40,7 @@ from subprocess import STDOUT, PIPE
 from psutil import virtual_memory, disk_usage
 from html import escape as hescape
 
-from .shared import available_archive_tools, getImageFileName, walkSort, walkLevel, sanitizeTrace, subprocess_run
+from .shared import available_archive_tools, md5Checksum, getImageFileName, walkSort, walkLevel, sanitizeTrace, subprocess_run
 from . import comic2panel
 from . import image
 from . import comicarchive
@@ -78,6 +78,7 @@ def main(argv=None):
 
 
 def buildHTML(path, imgfile, imgfilepath):
+    imgfilepath = md5Checksum(imgfilepath)
     filename = getImageFileName(imgfile)
     deviceres = options.profileData[1]
     if not options.noprocessing and "Rotated" in options.imgMetadata[imgfilepath]:
@@ -424,6 +425,7 @@ def buildOPF(dstdir, title, filelist, cover=None):
                   "</container>"])
     f.close()
 
+
 def buildEPUB(path, chapternames, tomenumber, ischunked):
     filelist = []
     chapterlist = []
@@ -504,7 +506,6 @@ def buildEPUB(path, chapternames, tomenumber, ischunked):
                       "display: none;\n",
                       "}\n"])
     f.close()
-    build_html_start = perf_counter()
     for dirpath, dirnames, filenames in os.walk(os.path.join(path, 'OEBPS', 'Images')):
         chapter = False
         dirnames, filenames = walkSort(dirnames, filenames)
@@ -514,12 +515,10 @@ def buildEPUB(path, chapternames, tomenumber, ischunked):
                                      'cover' + getImageFileName(afile)[1])
                 options.covers.append((image.Cover(os.path.join(dirpath, afile), cover, options,
                                                    tomenumber), options.uuid))
-            if not chapter:
-                chapterlist.append((dirpath.replace('Images', 'Text'), afile))
-                chapter = True
             filelist.append(buildHTML(dirpath, afile, os.path.join(dirpath, afile)))
-    build_html_end = perf_counter()
-    print(f"buildHTML: {build_html_end - build_html_start} seconds")
+            if not chapter:
+                chapterlist.append((dirpath.replace('Images', 'Text'), filelist[-1][1]))
+                chapter = True
     # Overwrite chapternames if tree is flat and ComicInfo.xml has bookmarks
     if not chapternames and options.chapters and not ischunked:
         chapterlist = []
@@ -567,13 +566,10 @@ def imgDirectoryProcessing(path):
     if GUI:
         GUI.progressBarTick.emit(str(pagenumber))
     if len(work) > 0:
-        img_processing_start = perf_counter()
         for i in work:
             workerPool.apply_async(func=imgFileProcessing, args=(i,), callback=imgFileProcessingTick)
         workerPool.close()
         workerPool.join()
-        img_processing_end = perf_counter()
-        print(f"imgFileProcessing: {img_processing_end - img_processing_start} seconds")
         if GUI and not GUI.conversionAlive:
             rmtree(os.path.join(path, '..', '..'), True)
             raise UserWarning("Conversion interrupted.")
@@ -813,7 +809,6 @@ def sanitizeTree(filetree):
             key = os.path.join(root, name)
             if key != newKey:
                 os.replace(key, newKey)
-                options.imgMetadata[newKey] = options.imgMetadata.pop(key)
         for i, name in enumerate(dirs):
             tmpName = name
             slugified = slugify(name)
@@ -825,10 +820,6 @@ def sanitizeTree(filetree):
             if key != newKey:
                 os.replace(key, newKey)
                 dirs[i] = newKey
-                existingImgPathKeys = list(options.imgMetadata.keys())
-                for imgPath in existingImgPathKeys:
-                    if imgPath.startswith(key):
-                        options.imgMetadata[newKey + imgPath.removeprefix(key)] = options.imgMetadata.pop(imgPath)
     return chapterNames
 
 

kindlecomicconverter/image.py

@@ -22,6 +22,7 @@ import io
 import os
 import mozjpeg_lossless_optimization
 from PIL import Image, ImageOps, ImageStat, ImageChops, ImageFilter
+from .shared import md5Checksum
 from .page_number_crop_alg import get_bbox_crop_margin_page_number, get_bbox_crop_margin
 from .inter_panel_crop_alg import crop_empty_inter_panel
 
@@ -320,7 +321,7 @@ class ComicPage:
                             output_jpeg_file.write(output_jpeg_bytes)
                 else:
                     self.image.save(self.targetPath, 'JPEG', optimize=1, quality=85)
-            return [self.targetPath, flags, self.orgPath]
+            return [md5Checksum(self.targetPath), flags, self.orgPath]
         except IOError as err:
             raise RuntimeError('Cannot save image. ' + str(err))
 

kindlecomicconverter/shared.py

@@ -75,6 +75,16 @@ def walkLevel(some_dir, level=1):
             del dirs[:]
 
 
+def md5Checksum(fpath):
+    with open(fpath, 'rb') as fh:
+        m = md5()
+        while True:
+            data = fh.read(8192)
+            if not data:
+                break
+            m.update(data)
+        return m.hexdigest()
+
 
 def sanitizeTrace(traceback):
     return ''.join(format_tb(traceback))\