Bump to 9.4.3

* remove corrupt image checking

Removed image verification step before copying the image.

* Update image.py

.github/workflows/package-linux.yml

@@ -68,7 +68,7 @@ jobs:
       if: startsWith(github.ref, 'refs/tags/')
       with:
         prerelease: true
-        generate_release_notes: true
+        generate_release_notes: false
         files: |
           LICENSE.txt
           *.AppImage*

.github/workflows/package-macos.yml

@@ -89,7 +89,7 @@ jobs:
         if: startsWith(github.ref, 'refs/tags/')
         with:
           prerelease: true
-          generate_release_notes: true
+          generate_release_notes: false
           files: |
             dist/*.dmg
       - name: Clean up keychain and provisioning profile

.github/workflows/package-osx-legacy.yml

@@ -60,7 +60,7 @@ jobs:
         if: startsWith(github.ref, 'refs/tags/')
         with:
           prerelease: true
-          generate_release_notes: true
+          generate_release_notes: false
           files: |
             LICENSE.txt
             dist/*.dmg

.github/workflows/package-windows.yml

@@ -73,6 +73,6 @@ jobs:
         if: startsWith(github.ref, 'refs/tags/')
         with:
           prerelease: true
-          generate_release_notes: true
+          generate_release_notes: false
           files: |
             dist/*.exe

.github/workflows/package-windows7.yml

@@ -55,6 +55,6 @@ jobs:
         if: startsWith(github.ref, 'refs/tags/')
         with:
           prerelease: true
-          generate_release_notes: true
+          generate_release_notes: false
           files: |
             dist/*.exe

README.md

@@ -14,6 +14,8 @@ with proper fixed layout support.
 Supported input formats include JPG/PNG image files in folders, archives, or PDFs.
 Supported output formats include MOBI/AZW3, EPUB, KEPUB, CBZ, and PDF.
 
+**WARNING**: Kindle Scribe 2025 support may not be possible. Does not work well currently.
+
 **NEW**: PDF output is now supported for direct conversion to reMarkable devices! 
 When using a reMarkable profile (Rmk1, Rmk2, RmkPP), the format automatically defaults to PDF 
 for optimal compatibility with your device's native PDF reader.
@@ -238,6 +240,7 @@ MAIN:
 
 PROCESSING:
   -n, --noprocessing    Do not modify image and ignore any profile or processing option
+  --pdfextract          Use legacy PDF image extraction method from KCC 8 and earlier.
   -u, --upscale         Resize images smaller than device's resolution
   -s, --stretch         Stretch images to device's resolution
   -r SPLITTER, --splitter SPLITTER

gui/KCC.ui

@@ -896,6 +896,18 @@ Higher values are larger and higher quality, and may resolve blank page issues.<
          </property>
         </widget>
        </item>
+       <item row="9" column="0">
+        <widget class="QCheckBox" name="pdfExtractBox">
+         <property name="toolTip">
+          <string>Use the PDF image extraction method from KCC 8 and earlier.
+
+Useful for really weird PDFs.</string>
+         </property>
+         <property name="text">
+          <string>PDF Legacy Extract</string>
+         </property>
+        </widget>
+       </item>
       </layout>
      </widget>
     </item>

kindlecomicconverter/KCC_gui.py

@@ -327,6 +327,8 @@ class WorkerThread(QThread):
             options.maximizestrips = True
         if GUI.disableProcessingBox.isChecked():
             options.noprocessing = True
+        if GUI.pdfExtractBox.isChecked():
+            options.pdfextract = True
         if GUI.metadataTitleBox.checkState() == Qt.CheckState.PartiallyChecked:
             options.metadatatitle = 1
         elif GUI.metadataTitleBox.checkState() == Qt.CheckState.Checked:
@@ -1032,6 +1034,7 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
                                            'colorBox': GUI.colorBox.checkState(),
                                            'eraseRainbowBox': GUI.eraseRainbowBox.checkState(),
                                            'disableProcessingBox': GUI.disableProcessingBox.checkState(),
+                                           'pdfExtractBox': GUI.pdfExtractBox.checkState(),
                                            'metadataTitleBox': GUI.metadataTitleBox.checkState(),
                                            'mozJpegBox': GUI.mozJpegBox.checkState(),
                                            'jpegQualityBox': GUI.jpegQualityBox.checkState(),
@@ -1195,6 +1198,9 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
             "Kindle 1920x1920": {
                 'PVOptions': True, 'ForceExpert': False, 'DefaultFormat': 0, 'DefaultUpscale': False, 'ForceColor': False, 'Label': 'KS1920',
             },
+            "Kindle 1240x1860": {
+                'PVOptions': True, 'ForceExpert': False, 'DefaultFormat': 0, 'DefaultUpscale': False, 'ForceColor': False, 'Label': 'KS1240',
+            },
             "Kindle Scribe 1/2": {
                 'PVOptions': True, 'ForceExpert': False, 'DefaultFormat': 0, 'DefaultUpscale': False, 'ForceColor': False, 'Label': 'KS',
             },
@@ -1304,6 +1310,7 @@ class KCCGUI(KCC_ui.Ui_mainWindow):
             "Separator",
             "Kindle 1920x1920",
             "Kindle 1860x1920",
+            "Kindle 1240x1860",
             "Kindle 8/10",
             "Kindle Oasis 8",
             "Kindle Paperwhite 7/10",

kindlecomicconverter/KCC_ui.py

@@ -462,6 +462,11 @@ class Ui_mainWindow(object):
 
         self.gridLayout_2.addWidget(self.jpegQualityBox, 8, 0, 1, 1)
 
+        self.pdfExtractBox = QCheckBox(self.optionWidget)
+        self.pdfExtractBox.setObjectName(u"pdfExtractBox")
+
+        self.gridLayout_2.addWidget(self.pdfExtractBox, 9, 0, 1, 1)
+
 
         self.gridLayout.addWidget(self.optionWidget, 5, 0, 1, 2)
 
@@ -733,6 +738,12 @@ class Ui_mainWindow(object):
 "Higher values are larger and higher quality, and may resolve blank page issues.", None))
 #endif // QT_CONFIG(tooltip)
         self.jpegQualityBox.setText(QCoreApplication.translate("mainWindow", u"Custom JPEG Quality", None))
+#if QT_CONFIG(tooltip)
+        self.pdfExtractBox.setToolTip(QCoreApplication.translate("mainWindow", u"Use the PDF image extraction method from KCC 8 and earlier.\n"
+"\n"
+"Useful for really weird PDFs.", None))
+#endif // QT_CONFIG(tooltip)
+        self.pdfExtractBox.setText(QCoreApplication.translate("mainWindow", u"PDF Legacy Extract", None))
         self.gammaLabel.setText(QCoreApplication.translate("mainWindow", u"Gamma: Auto", None))
         self.jpegQualityLabel.setText(QCoreApplication.translate("mainWindow", u"JPEG Quality:", None))
     # retranslateUi

kindlecomicconverter/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '9.4.2'
+__version__ = '9.4.3'
 __license__ = 'ISC'
 __copyright__ = '2012-2022, Ciro Mattia Gonano <ciromattia@gmail.com>, Pawel Jastrzebski <pawelj@iosphe.re>, darodi'
 __docformat__ = 'restructuredtext en'

kindlecomicconverter/comic2ebook.py

@@ -48,6 +48,7 @@ from .comicarchive import SEVENZIP, available_archive_tools
 from . import comic2panel
 from . import image
 from . import comicarchive
+from . import pdfjpgextract
 from . import dualmetafix
 from . import metadata
 from . import kindle
@@ -800,9 +801,7 @@ def extract_page(vector):
             if len(image_list) > 1:
                 raise UserWarning("mupdf_pdf_extract_page_image() function can be used only with single image pages.")
             if not image_list:
-                width, height = int(page.rect.width), int(page.rect.height)
-                blank_page = Image.new("RGB", (width, height), "white")
-                blank_page.save(output_path)
+                continue
             else:
                 xref = image_list[0][0]
                 d = doc.extract_image(xref)
@@ -854,6 +853,7 @@ def mupdf_pdf_process_pages_parallel(filename, output_dir, target_height):
 def getWorkFolder(afile, workdir=None):
     if not workdir:
         workdir = mkdtemp('', 'KCC-')
+        # workdir = mkdtemp('', 'KCC-', os.path.dirname(afile))
         fullPath = os.path.join(workdir, 'OEBPS', 'Images')
     else:
         fullPath = workdir
@@ -875,6 +875,12 @@ def getWorkFolder(afile, workdir=None):
                 os.makedirs(fullPath)
             path = workdir
             sanitizePermissions(path)
+            if options.pdfextract:
+                pdf = pdfjpgextract.PdfJpgExtract(afile, fullPath)
+                njpg = pdf.extract()
+                if njpg == 0:
+                    raise UserWarning("Failed to extract images from PDF file.")
+                return workdir
             target_height = options.profileData[1][1]
             if options.cropping == 1:
                 target_height = target_height + target_height*0.20 #Account for possible margin at the top and bottom
@@ -1066,7 +1072,7 @@ def removeNonImages(filetree):
         raise UserWarning('No images detected, nested archives are not supported.')
 
 
-def sanitizeTree(filetree):
+def sanitizeTree(filetree, prefix='kcc'):
     chapterNames = {}
     page = 1
     cover_path = None
@@ -1076,7 +1082,7 @@ def sanitizeTree(filetree):
             _, ext = getImageFileName(name)
 
             # 9999 page limit
-            unique_name = f'kcc-{page:04}'
+            unique_name = f'{prefix}-{page:04}'
             page += 1
 
             newKey = os.path.join(root, unique_name + ext)
@@ -1342,6 +1348,8 @@ def makeParser():
 
     processing_options.add_argument("-n", "--noprocessing", action="store_true", dest="noprocessing", default=False,
                                     help="Do not modify image and ignore any profile or processing option")
+    processing_options.add_argument("--pdfextract", action="store_true", dest="pdfextract", default=False,
+                                    help="Use the legacy PDF image extraction method from KCC 8 and earlier")
     processing_options.add_argument("-u", "--upscale", action="store_true", dest="upscale", default=False,
                                     help="Resize images smaller than device's resolution")
     processing_options.add_argument("-s", "--stretch", action="store_true", dest="stretch", default=False,
@@ -1549,7 +1557,7 @@ def makeFusion(sources: List[str]):
         else:
             targetpath = fusion_path.joinpath(source_path.name)
         getWorkFolder(source, str(targetpath))
-        sanitizeTree(targetpath)
+        sanitizeTree(targetpath, prefix='fusion')
         # TODO: remove flattenTree when subchapters are supported
         flattenTree(targetpath)   
 

kindlecomicconverter/image.py

@@ -103,6 +103,7 @@ class ProfileData:
         'KPW5': ("Kindle Paperwhite 5/Signature Edition", (1236, 1648), Palette16, 1.0),
         'KS1860': ("Kindle 1860", (1860, 1920), Palette16, 1.0),
         'KS1920': ("Kindle 1920", (1920, 1920), Palette16, 1.0),
+        'KS1240': ("Kindle 1240", (1240, 1860), Palette16, 1.0),
         'KS': ("Kindle Scribe 1/2", (1860, 2480), Palette16, 1.0),
         'KCS': ("Kindle Colorsoft", (1264, 1680), Palette16, 1.0),
         'KS3': ("Kindle Scribe 3", (1986, 2648), Palette16, 1.0),
@@ -157,7 +158,7 @@ class ComicPageParser:
 
         # Detect corruption in source image, let caller catch any exceptions triggered.
         srcImgPath = os.path.join(source[0], source[1])
-        Image.open(srcImgPath).verify()
+        # Image.open(srcImgPath).verify()
         with Image.open(srcImgPath) as im:
             self.image = im.copy()
 

kindlecomicconverter/page_number_crop_alg.py

@@ -160,6 +160,8 @@ def ignore_pixels_near_edge(bw_img):
     for box in edge_bbox:
         edge = bw_img.crop(box)
         h = edge.histogram()
+        if not edge.height or not edge.width:
+            continue
         imperfections = h[255] / (edge.height * edge.width)
         if imperfections > 0 and imperfections < .02:
             bw_img.paste(im=0, box=box)

kindlecomicconverter/pdfjpgextract.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2012-2014 Ciro Mattia Gonano <ciromattia@gmail.com>
+# Copyright (c) 2013-2019 Pawel Jastrzebski <pawelj@iosphe.re>
+#
+# Based upon the code snippet by Ned Batchelder
+# (http://nedbatchelder.com/blog/200712/extracting_jpgs_from_pdfs.html)
+#
+# Permission to use, copy, modify, and/or distribute this software for
+# any purpose with or without fee is hereby granted, provided that the
+# above copyright notice and this permission notice appear in all
+# copies.
+#
+# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
+# WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
+# WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE
+# AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
+# DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA
+# OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+# PERFORMANCE OF THIS SOFTWARE.
+#
+
+import os
+
+# skip stray images a few pixels in size in some PDFs
+# typical images are many thousands in length
+# https://github.com/ciromattia/kcc/pull/546
+STRAY_IMAGE_LENGTH_THRESHOLD = 300
+
+
+class PdfJpgExtract:
+    def __init__(self, fname, fullPath):
+        self.fname = fname
+        self.path = fullPath
+
+    def getPath(self):
+        return self.path
+
+    def extract(self):
+        pdf = open(self.fname, "rb").read()
+        startmark = b"\xff\xd8"
+        startfix = 0
+        endmark = b"\xff\xd9"
+        endfix = 2
+        i = 0
+        njpg = 0
+        while True:
+            istream = pdf.find(b"stream", i)
+            if istream < 0:
+                break
+            istart = pdf.find(startmark, istream, istream + 20)
+            if istart < 0:
+                i = istream + 20
+                continue
+            iend = pdf.find(b"endstream", istart)
+            if iend < 0:
+                raise Exception("Didn't find end of stream!")
+            iend = pdf.find(endmark, iend - 20)
+            if iend < 0:
+                raise Exception("Didn't find end of JPG!")
+            istart += startfix
+            iend += endfix
+            i = iend
+
+            if iend - istart < STRAY_IMAGE_LENGTH_THRESHOLD:
+                continue
+
+            jpg = pdf[istart:iend]
+            jpgfile = open(os.path.join(self.path, "jpg%d.jpg" % njpg), "wb")
+            jpgfile.write(jpg)
+            jpgfile.close()
+            njpg += 1
+
+        return njpg