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.
@@ -68,9 +70,11 @@ If you have issues detecting it, get stuck on the MOBI conversion step, or use L
 
 ### 7-Zip
 
-This is only required for certain files and advanced features. 
+This is optional but will make conversions much faster.
 
-KCC will ask you to install if needed. 
+This is required for certain files and advanced features. 
+
+KCC will ask you to install if needed.
 
 Refer to the wiki to install: https://github.com/ciromattia/kcc/wiki/Installation#7-zip
 
@@ -317,5 +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/KCC_gui.py

@@ -37,7 +37,7 @@ from packaging.version import Version
 from raven import Client
 from tempfile import gettempdir
 
-from .shared import HTMLStripper, sanitizeTrace, walkLevel, subprocess_run
+from .shared import HTMLStripper, available_archive_tools, sanitizeTrace, walkLevel, subprocess_run
 from . import __version__
 from . import comic2ebook
 from . import metadata
@@ -317,13 +317,8 @@ class WorkerThread(QThread):
                 GUI.progress.content = ''
                 self.errors = True
                 _, _, traceback = sys.exc_info()
-                if len(err.args) == 1:
-                    MW.showDialog.emit("Error during conversion %s:\n\n%s\n\nTraceback:\n%s"
-                                       % (jobargv[-1], str(err), sanitizeTrace(traceback)), 'error')
-                else:
-                    MW.showDialog.emit("Error during conversion %s:\n\n%s\n\nTraceback:\n%s"
-                                       % (jobargv[-1], str(err.args[0]), err.args[1]), 'error')
-                    GUI.sentry.extra_context({'realTraceback': err.args[1]})
+                MW.showDialog.emit("Error during conversion %s:\n\n%s\n\nTraceback:\n%s"
+                                   % (jobargv[-1], str(err), sanitizeTrace(traceback)), 'error')
                 if ' is corrupted.' not in str(err):
                     GUI.sentry.captureException()
                 MW.addMessage.emit('Error during conversion! Please consult '
@@ -1071,19 +1066,12 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
             self.addMessage('Since you are a new user of <b>KCC</b> please see few '
                             '<a href="https://github.com/ciromattia/kcc/wiki/Important-tips">important tips</a>.',
                             'info')
-        try:
-            subprocess_run(['tar'], stdout=PIPE, stderr=STDOUT)
-            self.tar = True
-        except FileNotFoundError:
-            self.tar = False
-        try:
-            subprocess_run(['7z'], stdout=PIPE, stderr=STDOUT)
-            self.sevenzip = True
-        except FileNotFoundError:
-            self.sevenzip = False
-            if not self.tar:
-                self.addMessage('<a href="https://github.com/ciromattia/kcc#7-zip">Install 7z (link)</a>'
-                                ' to enable CBZ/CBR/ZIP/etc processing.', 'warning')
+        
+        self.tar = 'tar' in available_archive_tools()
+        self.sevenzip = '7z' in available_archive_tools()
+        if not any([self.tar, self.sevenzip]):
+            self.addMessage('<a href="https://github.com/ciromattia/kcc#7-zip">Install 7z (link)</a>'
+                            ' to enable CBZ/CBR/ZIP/etc processing.', 'warning')
         self.detectKindleGen(True)
 
         APP.messageFromOtherInstance.connect(self.handleMessage)

kindlecomicconverter/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '7.2.3'
+__version__ = '7.3.0'
 __license__ = 'ISC'
 __copyright__ = '2012-2022, Ciro Mattia Gonano <ciromattia@gmail.com>, Pawel Jastrzebski <pawelj@iosphe.re>, darodi'
 __docformat__ = 'restructuredtext en'

kindlecomicconverter/comic2ebook.py

@@ -23,7 +23,7 @@ import pathlib
 import re
 import sys
 from argparse import ArgumentParser
-from time import strftime, gmtime
+from time import perf_counter, strftime, gmtime
 from copy import copy
 from glob import glob, escape
 from re import sub
@@ -33,14 +33,14 @@ from tempfile import mkdtemp, gettempdir, TemporaryFile
 from shutil import move, copytree, rmtree, copyfile
 from multiprocessing import Pool
 from uuid import uuid4
-from natsort import os_sorted
+from natsort import os_sort_keygen
 from slugify import slugify as slugify_ext
 from PIL import Image, ImageFile
 from subprocess import STDOUT, PIPE
 from psutil import virtual_memory, disk_usage
 from html import escape as hescape
 
-from .shared import md5Checksum, 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
@@ -51,7 +51,7 @@ from . import kindle
 from . import __version__
 
 ImageFile.LOAD_TRUNCATED_IMAGES = True
-
+OS_SORT_KEY = os_sort_keygen()
 
 def main(argv=None):
     global options
@@ -790,12 +790,16 @@ def getPanelViewSize(deviceres, size):
 
 def sanitizeTree(filetree):
     chapterNames = {}
-    for root, dirs, files in os.walk(filetree, False):
-        for i, name in enumerate(os_sorted(files)):
+    page = 1
+    for root, dirs, files in os.walk(filetree):
+        dirs.sort(key=OS_SORT_KEY)
+        files.sort(key=OS_SORT_KEY)
+        for name in files:
             splitname = os.path.splitext(name)
 
             # file needs kcc at front AND back to avoid renaming issues
-            slugified = f'kcc-{i:04}'
+            slugified = f'kcc-{page:04}'
+            page += 1
             for suffix in '-KCC', '-KCC-A', '-KCC-B', '-KCC-C':
                 if splitname[0].endswith(suffix):
                     slugified += suffix.lower()
@@ -805,7 +809,7 @@ def sanitizeTree(filetree):
             key = os.path.join(root, name)
             if key != newKey:
                 os.replace(key, newKey)
-        for name in dirs:
+        for i, name in enumerate(dirs):
             tmpName = name
             slugified = slugify(name)
             while os.path.exists(os.path.join(root, slugified)) and name.upper() != slugified.upper():
@@ -815,6 +819,7 @@ def sanitizeTree(filetree):
             key = os.path.join(root, name)
             if key != newKey:
                 os.replace(key, newKey)
+                dirs[i] = newKey
     return chapterNames
 
 
@@ -946,17 +951,27 @@ def slugify(value):
 
 
 def makeZIP(zipfilename, basedir, isepub=False):
+    start = perf_counter()
     zipfilename = os.path.abspath(zipfilename) + '.zip'
-    zipOutput = ZipFile(zipfilename, 'w', ZIP_DEFLATED)
-    if isepub:
-        zipOutput.writestr('mimetype', 'application/epub+zip', ZIP_STORED)
-    for dirpath, _, filenames in os.walk(basedir):
-        for name in filenames:
-            path = os.path.normpath(os.path.join(dirpath, name))
-            aPath = os.path.normpath(os.path.join(dirpath.replace(basedir, ''), name))
-            if os.path.isfile(path):
-                zipOutput.write(path, aPath)
-    zipOutput.close()
+    if '7z' in available_archive_tools():
+        if isepub:
+            mimetypeFile = open(os.path.join(basedir, 'mimetype'), 'w')
+            mimetypeFile.write('application/epub+zip')
+            mimetypeFile.close()
+        subprocess_run(['7z', 'a', '-tzip', zipfilename, os.path.join(basedir, "*")], capture_output=True, check=True)
+    else:
+        zipOutput = ZipFile(zipfilename, 'w', ZIP_DEFLATED)
+        if isepub:
+            zipOutput.writestr('mimetype', 'application/epub+zip', ZIP_STORED)
+        for dirpath, _, filenames in os.walk(basedir):
+            for name in filenames:
+                path = os.path.normpath(os.path.join(dirpath, name))
+                aPath = os.path.normpath(os.path.join(dirpath.replace(basedir, ''), name))
+                if os.path.isfile(path):
+                    zipOutput.write(path, aPath)
+        zipOutput.close()
+    end = perf_counter()
+    print(f"makeZIP time: {end - start} seconds")
     return zipfilename
 
 
@@ -1131,9 +1146,7 @@ def checkTools(source):
     source = source.upper()
     if source.endswith('.CB7') or source.endswith('.7Z') or source.endswith('.RAR') or source.endswith('.CBR') or \
             source.endswith('.ZIP') or source.endswith('.CBZ'):
-        try:
-            subprocess_run(['7z'], stdout=PIPE, stderr=STDOUT)
-        except FileNotFoundError:
+        if '7z' not in available_archive_tools():
             print('ERROR: 7z is missing!')
             sys.exit(1)
     if options.format == 'MOBI':
@@ -1163,6 +1176,7 @@ def checkPre(source):
 
 
 def makeBook(source, qtgui=None):
+    start = perf_counter()
     global GUI
     GUI = qtgui
     if GUI:
@@ -1265,6 +1279,8 @@ def makeBook(source, qtgui=None):
         elif os.path.isdir(source):
             rmtree(source)
 
+    end = perf_counter()
+    print(f"makeBook: {end - start} seconds")
     return filepath
 
 

kindlecomicconverter/shared.py

@@ -18,6 +18,7 @@
 # PERFORMANCE OF THIS SOFTWARE.
 #
 
+from functools import lru_cache
 import os
 from hashlib import md5
 from html.parser import HTMLParser
@@ -137,6 +138,19 @@ def dependencyCheck(level):
         print('ERROR: ' + ', '.join(missing) + ' is not installed!')
         sys.exit(1)
 
+@lru_cache
+def available_archive_tools():
+    available = []
+
+    for tool in ['tar', '7z', 'unar', 'unrar']:
+        try:
+            subprocess_run([tool], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+            available.append(tool)
+        except FileNotFoundError:
+            pass
+    
+    return available
+
 def subprocess_run(command, **kwargs):
     if (os.name == 'nt'):
         kwargs.setdefault('creationflags', subprocess.CREATE_NO_WINDOW)