Update for 2.9 release.

Filenames slugification

README.md

@@ -6,16 +6,22 @@ actually a comic 2 epub converter that every ereader owner can happily use**_.
 
 It can also optionally optimize images by applying a number of transformations.
 
+### 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 _readers_.  
+If you want to read some comments over *Amazon's kc2* you can take a look at [this](http://www.mobileread.com/forums/showthread.php?t=207461&page=7#96) and [that](http://www.mobileread.com/forums/showthread.php?t=211047) threads on Mobileread.  
+_kc2_ in no way is a replacement for **KCC** so you can be quite confident we'll going to carry on developing our little monster ;)  
+
 ## BINARY RELEASES
 You can find the latest released binary at the following links:  
-- OS X: [https://dl.dropbox.com/u/16806101/KindleComicConverter_osx_2.8.zip](https://dl.dropbox.com/u/16806101/KindleComicConverter_osx_2.8.zip)
-- Win64: [https://dl.dropbox.com/u/16806101/KindleComicConverter_win-amd64_2.8.zip](https://dl.dropbox.com/u/16806101/KindleComicConverter_win-amd64_2.7.zip)
-- Win32: [http://pawelj.vulturis.eu/Shared/KindleComicConverter_win-x86_2.8.zip](http://pawelj.vulturis.eu/Shared/KindleComicConverter_win-x86_2.8.zip) *(thanks to [AcidWeb](https://github.com/AcidWeb))*
+- OS X: [https://dl.dropbox.com/u/16806101/KindleComicConverter_osx_2.9.zip](https://dl.dropbox.com/u/16806101/KindleComicConverter_osx_2.9.zip)
+- Win64: [https://dl.dropbox.com/u/16806101/KindleComicConverter_win-amd64_2.9.zip](https://dl.dropbox.com/u/16806101/KindleComicConverter_win-amd64_2.9.zip)
+- Win32: [http://pawelj.vulturis.eu/Shared/KindleComicConverter_win-x86_2.9.zip](http://pawelj.vulturis.eu/Shared/KindleComicConverter_win-x86_2.9.zip) *(thanks to [AcidWeb](https://github.com/AcidWeb))*
 - Linux: Just download sourcecode and launch `python kcc.py` *(Provided you have Python and Pillow installed)*
 
 ## INPUT FORMATS
 `kcc` can understand and convert, at the moment, the following file types:
-- PNG, JPG
+- PNG, JPG, GIF, TIFF, BMP
 - Folders
 - CBZ, ZIP
 - CBR, RAR *(With `unrar` executable)*
@@ -51,6 +57,7 @@ Options:
   -t TITLE, --title=TITLE
                         Comic title [Default=filename]
   -m, --manga-style     Manga style (Right-to-left reading and splitting) [Default=False]
+  -c, --cbz-output      Outputs a CBZ archive and does not generate EPUB
   --nopanelviewhq       Disable high quality Panel View [Default=False]
   --noprocessing        Do not apply image preprocessing (Page splitting and optimizations) [Default=True]
   --forcepng            Create PNG files instead JPEG (For non-Kindle devices) [Default=False]
@@ -62,7 +69,7 @@ Options:
   --nosplitrotate       Disable splitting and rotation [Default=False]
   --nocutpagenumbers    Do not try to cut page numbering on images [Default=True]
   -o OUTPUT, --output=OUTPUT
-                        Output generated EPUB to specified directory or file
+                        Output generated file (EPUB or CBZ) to specified directory or file
   -v, --verbose         Verbose output [Default=False]
 ```
 
@@ -121,8 +128,13 @@ The app relies and includes the following scripts/binaries:
         Rewrite of Landscape Mode support (huge readability improvement for KPW)  
         Upscale use now BILINEAR method  
         Added generic CSS file  
-        Optimized archive extraction for zip/rar files (#40) 
-        
+        Optimized archive extraction for zip/rar files (#40)  
+  - 2.9: Added support for generating a plain CBZ (skipping all the EPUB/Mobi generation) (#45)  
+        Prevent output file overwriting the source one: if a duplicate name is detected, append _kcc to the name  
+        Rarfile library updated to 2.6  
+        Added GIF, TIFF and BMP to supported formats (#42)  
+        Filenames slugifications (#28, #31, #9, #8)
+
 
 ## COPYRIGHT
 

kcc.py

@@ -16,7 +16,7 @@
 # TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
 # PERFORMANCE OF THIS SOFTWARE.
 #
-__version__ = '2.8'
+__version__ = '2.9'
 __license__ = 'ISC'
 __copyright__ = '2012-2013, Ciro Mattia Gonano <ciromattia@gmail.com>'
 __docformat__ = 'restructuredtext en'

kcc/comic2ebook.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+# -*- coding: utf-8 -*-
 #
 # Copyright (c) 2012 Ciro Mattia Gonano <ciromattia@gmail.com>
 #
@@ -16,7 +17,7 @@
 # TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
 # PERFORMANCE OF THIS SOFTWARE.
 #
-__version__ = '2.8'
+__version__ = '2.9'
 __license__ = 'ISC'
 __copyright__ = '2012-2013, Ciro Mattia Gonano <ciromattia@gmail.com>'
 __docformat__ = 'restructuredtext en'
@@ -128,7 +129,7 @@ def buildNCX(dstdir, title, chapters):
     f = open(ncxfile, "w")
     f.writelines(["<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
                   "<!DOCTYPE ncx PUBLIC \"-//NISO//DTD ncx 2005-1//EN\" ",
-                  "http://www.daisy.org/z3986/2005/ncx-2005-1.dtd\">\n",
+                  "\"http://www.daisy.org/z3986/2005/ncx-2005-1.dtd\">\n",
                   "<ncx version=\"2005-1\" xml:lang=\"en-US\" xmlns=\"http://www.daisy.org/z3986/2005/ncx/\">\n",
                   "<head>\n",
                   "<meta name=\"dtb:uid\" content=\"015ffaec-9340-42f8-b163-a0c5ab7d0611\"/>\n",
@@ -276,6 +277,10 @@ def getImageFileName(imgfile):
     if filename[0].startswith('.') or\
             (filename[1].lower() != '.png' and
              filename[1].lower() != '.jpg' and
+             filename[1].lower() != '.gif' and
+             filename[1].lower() != '.tif' and
+             filename[1].lower() != '.tiff' and
+             filename[1].lower() != '.bmp' and
              filename[1].lower() != '.jpeg'):
         return None
     return filename
@@ -356,6 +361,7 @@ def genEpubStruct(path):
     chapterlist = []
     cover = None
     _, deviceres, _, _, panelviewsize = image.ProfileData.Profiles[options.profile]
+    sanitizeTree(os.path.join(path, 'OEBPS', 'Images'))
     os.mkdir(os.path.join(path, 'OEBPS', 'Text'))
     f = open(os.path.join(path, 'OEBPS', 'Text', 'style.css'), 'w')
     #DON'T COMPRESS CSS. KINDLE WILL FAIL TO PARSE IT.
@@ -535,6 +541,36 @@ def getWorkFolder(afile):
     return path
 
 
+def slugify(value):
+    """
+    Normalizes string, converts to lowercase, removes non-alpha characters,
+    and converts spaces to hyphens.
+    """
+    import unicodedata
+    value = unicodedata.normalize('NFKD', unicode(value, 'latin1')).encode('ascii', 'ignore')
+    value = re.sub('[^\w\s\.-]', '', value).strip().lower()
+    value = re.sub('[-\.\s]+', '-', value)
+    value = re.sub(r'([0-9]+)', r'00000\1', value)
+    value = re.sub(r'0*([0-9]{6,})', r'\1', value)
+    return value
+
+
+def sanitizeTree(filetree):
+    for root, dirs, files in os.walk(filetree):
+        for name in files:
+            if name.startswith('.') or name.lower() == 'thumbs.db':
+                os.remove(os.path.join(root, name))
+            else:
+                splitname = os.path.splitext(name)
+                os.rename(os.path.join(root, name),
+                          os.path.join(root, slugify(splitname[0]) + splitname[1]))
+        for name in dirs:
+            if name.startswith('.'):
+                os.remove(os.path.join(root, name))
+            else:
+                os.rename(os.path.join(root, name), os.path.join(root, slugify(name)))
+
+
 def Copyright():
     print ('comic2ebook v%(__version__)s. '
            'Written 2012 by Ciro Mattia Gonano.' % globals())
@@ -542,7 +578,6 @@ def Copyright():
 
 def Usage():
     print "Generates HTML, NCX and OPF for a Comic ebook from a bunch of images."
-    print "Optimized for creating MOBI files to be read on Kindle Paperwhite."
     parser.print_help()
 
 
@@ -556,6 +591,8 @@ def main(argv=None):
                       help="Comic title [Default=filename]")
     parser.add_option("-m", "--manga-style", action="store_true", dest="righttoleft", default=False,
                       help="Manga style (Right-to-left reading and splitting) [Default=False]")
+    parser.add_option("-c", "--cbz-output", action="store_true", dest="cbzoutput", default=False,
+                      help="Outputs a CBZ archive and does not generate EPUB")
     parser.add_option("--nopanelviewhq", action="store_true", dest="nopanelviewhq", default=False,
                       help="Disable high quality Panel View [Default=False]")
     parser.add_option("--noprocessing", action="store_false", dest="imgproc", default=True,
@@ -578,7 +615,7 @@ def main(argv=None):
     parser.add_option("--nocutpagenumbers", action="store_false", dest="cutpagenumbers", default=True,
                       help="Do not try to cut page numbering on images [Default=True]")
     parser.add_option("-o", "--output", action="store", dest="output", default=None,
-                      help="Output generated EPUB to specified directory or file")
+                      help="Output generated file (EPUB or CBZ) to specified directory or file")
     parser.add_option("-v", "--verbose", action="store_true", dest="verbose", default=False,
                       help="Verbose output [Default=False]")
     options, args = parser.parse_args(argv)
@@ -593,25 +630,40 @@ def main(argv=None):
     if options.imgproc:
         print "Processing images..."
         dirImgProcess(path + "/OEBPS/Images/")
-    print "\nCreating ePub structure..."
-    genEpubStruct(path)
-    # actually zip the ePub
-    if options.output is not None:
-        if options.output.endswith('.epub'):
-            epubpath = os.path.abspath(options.output)
-        elif os.path.isdir(args[0]):
-            epubpath = os.path.abspath(options.output) + "/" + os.path.basename(args[0]) + '.epub'
-        else:
-            epubpath = os.path.abspath(options.output) + "/" \
-                + os.path.basename(os.path.splitext(args[0])[0]) + '.epub'
-    elif os.path.isdir(args[0]):
-        epubpath = args[0] + '.epub'
+    if options.cbzoutput:
+        # if CBZ output wanted, compress all images and return filepath
+        print "\nCreating CBZ file..."
+        filepath = getOutputFilename(args[0], options.output, '.cbz')
+        make_archive(path + '_comic', 'zip', path + '/OEBPS/Images')
     else:
-        epubpath = os.path.splitext(args[0])[0] + '.epub'
-    make_archive(path + '_comic', 'zip', path)
-    move(path + '_comic.zip', epubpath)
+        print "\nCreating ePub structure..."
+        genEpubStruct(path)
+        # actually zip the ePub
+        filepath = getOutputFilename(args[0], options.output, '.epub')
+        make_archive(path + '_comic', 'zip', path)
+    move(path + '_comic.zip', filepath)
     rmtree(path)
-    return epubpath
+    return filepath
+
+
+def getOutputFilename(srcpath, wantedname, ext):
+    if not ext.startswith('.'):
+        ext = '.' + ext
+    if wantedname is not None:
+        if wantedname.endswith(ext):
+            filename = os.path.abspath(wantedname)
+        elif os.path.isdir(srcpath):
+            filename = os.path.abspath(options.output) + "/" + os.path.basename(srcpath) + ext
+        else:
+            filename = os.path.abspath(options.output) + "/" \
+                       + os.path.basename(os.path.splitext(srcpath)[0]) + ext
+    elif os.path.isdir(srcpath):
+        filename = srcpath + ext
+    else:
+        filename = os.path.splitext(srcpath)[0] + ext
+    if os.path.isfile(filename):
+        filename = os.path.splitext(filename)[0] + '_kcc' + ext
+    return filename
 
 
 def checkOptions():

kcc/gui.py

@@ -93,31 +93,33 @@ class MainWindow:
 
         self.options = {
             'Aepub_only': IntVar(None, 0),
-            'Bmangastyle': IntVar(None, 0),
-            'Cnopanelviewhq': IntVar(None, 0),
-            'Dimage_preprocess': IntVar(None, 0),
-            'Eforcepng': IntVar(None, 0),
-            'Fimage_gamma': DoubleVar(None, 0.0),
-            'Gimage_upscale': IntVar(None, 0),
-            'Himage_stretch': IntVar(None, 0),
-            'Iblack_borders': IntVar(None, 0),
-            'Jrotate': IntVar(None, 0),
-            'Knosplitrotate': IntVar(None, 0),
-            'Lcut_page_numbers': IntVar(None, 0)
+            'Bcbz_only': IntVar(None, 0),
+            'Cmangastyle': IntVar(None, 0),
+            'Dnopanelviewhq': IntVar(None, 0),
+            'Eimage_preprocess': IntVar(None, 0),
+            'Fforcepng': IntVar(None, 0),
+            'Gimage_gamma': DoubleVar(None, 0.0),
+            'Himage_upscale': IntVar(None, 0),
+            'Iimage_stretch': IntVar(None, 0),
+            'Jblack_borders': IntVar(None, 0),
+            'Krotate': IntVar(None, 0),
+            'Lnosplitrotate': IntVar(None, 0),
+            'Mcut_page_numbers': IntVar(None, 0)
         }
         self.optionlabels = {
             'Aepub_only': "Generate EPUB only",
-            'Bmangastyle': "Manga mode",
-            'Cnopanelviewhq': "Disable high quality Panel View",
-            'Dimage_preprocess': "Disable image optimizations",
-            'Eforcepng': "Create PNG files instead JPEG",
-            'Fimage_gamma': "Custom gamma correction",
-            'Gimage_upscale': "Allow image upscaling",
-            'Himage_stretch': "Stretch images",
-            'Iblack_borders': "Use black borders",
-            'Jrotate': "Rotate images instead splitting them",
-            'Knosplitrotate': "Disable splitting and rotation",
-            'Lcut_page_numbers': "Disable page numbers cutting"
+            'Bcbz_only': "Generate CBZ only (skip EPUB/Mobi generation)",
+            'Cmangastyle': "Manga mode",
+            'Dnopanelviewhq': "Disable high quality Panel View",
+            'Eimage_preprocess': "Disable image optimizations",
+            'Fforcepng': "Create PNG files instead of JPEG",
+            'Gimage_gamma': "Custom gamma correction",
+            'Himage_upscale': "Allow image upscaling",
+            'Iimage_stretch': "Stretch images",
+            'Jblack_borders': "Use black borders (instead of white ones)",
+            'Krotate': "Rotate images (instead of splitting them)",
+            'Lnosplitrotate': "Disable both splitting and rotation",
+            'Mcut_page_numbers': "Disable page numbers cutting"
         }
         self.optionsButtons = {}
         for key in sorted(self.options):
@@ -162,28 +164,30 @@ class MainWindow:
             return
         profilekey = ProfileData.ProfileLabels[self.profile.get()]
         argv = ["-p", profilekey]
-        if self.options['Bmangastyle'].get() == 1:
+        if self.options['Bcbz_only'].get() == 1:
+            argv.append("-c")
+        if self.options['Cmangastyle'].get() == 1:
             argv.append("-m")
-        if self.options['Cnopanelviewhq'].get() == 1:
+        if self.options['Dnopanelviewhq'].get() == 1:
             argv.append("--nopanelviewhq")
-        if self.options['Dimage_preprocess'].get() == 1:
+        if self.options['Eimage_preprocess'].get() == 1:
             argv.append("--noprocessing")
-        if self.options['Eforcepng'].get() == 1:
+        if self.options['Fforcepng'].get() == 1:
             argv.append("--forcepng")
-        if self.options['Fimage_gamma'].get() != 0.0:
+        if self.options['Gimage_gamma'].get() != 0.0:
             argv.append("--gamma")
-            argv.append(self.options['Fimage_gamma'].get())
-        if self.options['Gimage_upscale'].get() == 1:
+            argv.append(self.options['Gimage_gamma'].get())
+        if self.options['Himage_upscale'].get() == 1:
             argv.append("--upscale")
-        if self.options['Himage_stretch'].get() == 1:
+        if self.options['Iimage_stretch'].get() == 1:
             argv.append("--stretch")
-        if self.options['Iblack_borders'].get() == 1:
+        if self.options['Jblack_borders'].get() == 1:
             argv.append("--blackborders")
-        if self.options['Jrotate'].get() == 1:
+        if self.options['Krotate'].get() == 1:
             argv.append("--rotate")
-        if self.options['Knosplitrotate'].get() == 1:
+        if self.options['Lnosplitrotate'].get() == 1:
             argv.append("--nosplitrotate")
-        if self.options['Lcut_page_numbers'].get() == 1:
+        if self.options['Mcut_page_numbers'].get() == 1:
             argv.append("--nocutpagenumbers")
         errors = False
         left_files = len(self.filelist)
@@ -207,7 +211,7 @@ class MainWindow:
                                                     (subargv[-1], str(err), traceback.format_tb(traceback_)))
                 errors = True
                 continue
-            if self.options['Aepub_only'].get() == 0:
+            if self.options['Aepub_only'].get() == 0 and self.options['Bcbz_only'].get() == 0:
                 try:
                     if os.path.getsize(epub_path) > 314572800:
                         # do not call kindlegen if source is bigger than 300MB

kcc/rarfile.py

@@ -1,6 +1,6 @@
 # rarfile.py
 #
-# Copyright (c) 2005-2012  Marko Kreen <markokr@gmail.com>
+# Copyright (c) 2005-2013  Marko Kreen <markokr@gmail.com>
 #
 # Permission to use, copy, modify, and/or distribute this software for any
 # purpose with or without fee is hereby granted, provided that the above
@@ -17,7 +17,7 @@
 r"""RAR archive reader.
 
 This is Python module for Rar archive reading.  The interface
-is made as zipfile like as possible.
+is made as :mod:`zipfile`-like as possible.
 
 Basic logic:
  - Parse archive structure with Python.
@@ -34,7 +34,17 @@ Example::
     for f in rf.infolist():
         print f.filename, f.file_size
         if f.filename == 'README':
-            print rf.read(f)
+            print(rf.read(f))
+
+Archive files can also be accessed via file-like object returned
+by :meth:`RarFile.open`::
+
+    import rarfile
+
+    with rarfile.RarFile('archive.rar') as rf:
+        with rf.open('README') as f:
+            for ln in f:
+                print(ln.strip())
 
 There are few module-level parameters to tune behaviour,
 here they are with defaults, and reason to change it::
@@ -64,7 +74,7 @@ For more details, refer to source.
 
 """
 
-__version__ = '2.5'
+__version__ = '2.6'
 
 # export only interesting items
 __all__ = ['is_rarfile', 'RarInfo', 'RarFile', 'RarExtFile']
@@ -148,45 +158,45 @@ except ImportError:
 ## Module configuration.  Can be tuned after importing.
 ##
 
-# default fallback charset
+#: default fallback charset
 DEFAULT_CHARSET = "windows-1252"
 
-# list of encodings to try, with fallback to DEFAULT_CHARSET if none succeed
+#: list of encodings to try, with fallback to DEFAULT_CHARSET if none succeed
 TRY_ENCODINGS = ('utf8', 'utf-16le')
 
-# 'unrar', 'rar' or full path to either one
+#: 'unrar', 'rar' or full path to either one
 UNRAR_TOOL = "unrar"
 
-# Command line args to use for opening file for reading.
+#: Command line args to use for opening file for reading.
 OPEN_ARGS = ('p', '-inul')
 
-# Command line args to use for extracting file to disk.
+#: Command line args to use for extracting file to disk.
 EXTRACT_ARGS = ('x', '-y', '-idq')
 
-# args for testrar()
+#: args for testrar()
 TEST_ARGS = ('t', '-idq')
 
-# whether to speed up decompression by using tmp archive
+#: whether to speed up decompression by using tmp archive
 USE_EXTRACT_HACK = 1
 
-# limit the filesize for tmp archive usage
+#: limit the filesize for tmp archive usage
 HACK_SIZE_LIMIT = 20*1024*1024
 
-# whether to parse file/archive comments.
+#: whether to parse file/archive comments.
 NEED_COMMENTS = 1
 
-# whether to convert comments to unicode strings
+#: whether to convert comments to unicode strings
 UNICODE_COMMENTS = 0
 
-# When RAR is corrupt, stopping on bad header is better
-# On unknown/misparsed RAR headers reporting is better
+#: When RAR is corrupt, stopping on bad header is better
+#: On unknown/misparsed RAR headers reporting is better
 REPORT_BAD_HEADER = 0
 
-# Convert RAR time tuple into datetime() object
+#: Convert RAR time tuple into datetime() object
 USE_DATETIME = 0
 
-# Separator for path name components.  RAR internally uses '\\'.
-# Use '/' to be similar with zipfile.
+#: Separator for path name components.  RAR internally uses '\\'.
+#: Use '/' to be similar with zipfile.
 PATH_SEP = '\\'
 
 ##
@@ -337,49 +347,57 @@ def is_rarfile(fn):
 
 
 class RarInfo(object):
-    '''An entry in rar archive.
-    
-    @ivar filename:
-        File name with relative path.
-        Default path separator is '/', to change set rarfile.PATH_SEP.
-        Always unicode string.
-    @ivar date_time:
-        Modification time, tuple of (year, month, day, hour, minute, second).
-        Or datetime() object if USE_DATETIME is set.
-    @ivar file_size:
-        Uncompressed size.
-    @ivar compress_size:
-        Compressed size.
-    @ivar compress_type:
-        Compression method: 0x30 - 0x35.
-    @ivar extract_version:
-        Minimal Rar version needed for decompressing.
-    @ivar host_os:
-        Host OS type, one of RAR_OS_* constants.
-    @ivar mode:
-        File attributes. May be either dos-style or unix-style, depending on host_os.
-    @ivar CRC:
-        CRC-32 of uncompressed file, unsigned int.
-    @ivar volume:
-        Volume nr, starting from 0.
-    @ivar volume_file:
-        Volume file name, where file starts.
-    @ivar type:
-        One of RAR_BLOCK_* types.  Only entries with type==RAR_BLOCK_FILE are shown in .infolist().
-    @ivar flags:
-        For files, RAR_FILE_* bits.
-    @ivar comment:
-        File comment (unicode string or None).
+    r'''An entry in rar archive.
 
-    @ivar mtime:
-        Optional time field: Modification time, with float seconds.
-        Same as .date_time but with more precision.
-    @ivar ctime:
-        Optional time field: creation time, with float seconds.
-    @ivar atime:
-        Optional time field: last access time, with float seconds.
-    @ivar arctime:
-        Optional time field: archival time, with float seconds.
+    :mod:`zipfile`-compatible fields:
+    
+        filename
+            File name with relative path.
+            Default path separator is '\\', to change set rarfile.PATH_SEP.
+            Always unicode string.
+        date_time
+            Modification time, tuple of (year, month, day, hour, minute, second).
+            Or datetime() object if USE_DATETIME is set.
+        file_size
+            Uncompressed size.
+        compress_size
+            Compressed size.
+        CRC
+            CRC-32 of uncompressed file, unsigned int.
+        comment
+            File comment.  Byte string or None.  Use UNICODE_COMMENTS
+            to get automatic decoding to unicode.
+        volume
+            Volume nr, starting from 0.
+
+    RAR-specific fields:
+
+        compress_type
+            Compression method: 0x30 - 0x35.
+        extract_version
+            Minimal Rar version needed for decompressing.
+        host_os
+            Host OS type, one of RAR_OS_* constants.
+        mode
+            File attributes. May be either dos-style or unix-style, depending on host_os.
+        volume_file
+            Volume file name, where file starts.
+        mtime
+            Optional time field: Modification time, with float seconds.
+            Same as .date_time but with more precision.
+        ctime
+            Optional time field: creation time, with float seconds.
+        atime
+            Optional time field: last access time, with float seconds.
+        arctime
+            Optional time field: archival time, with float seconds.
+
+    Internal fields:
+
+        type
+            One of RAR_BLOCK_* types.  Only entries with type==RAR_BLOCK_FILE are shown in .infolist().
+        flags
+            For files, RAR_FILE_* bits.
     '''
 
     __slots__ = (
@@ -433,19 +451,27 @@ class RarInfo(object):
 
 class RarFile(object):
     '''Parse RAR structure, provide access to files in archive.
-
-    @ivar comment:
-        Archive comment (unicode string or None).
     '''
 
+    #: Archive comment.  Byte string or None.  Use UNICODE_COMMENTS
+    #: to get automatic decoding to unicode.
+    comment = None
+
     def __init__(self, rarfile, mode="r", charset=None, info_callback=None, crc_check = True):
         """Open and parse a RAR archive.
         
-        @param rarfile: archive file name
-        @param mode: only 'r' is supported.
-        @param charset: fallback charset to use, if filenames are not already Unicode-enabled.
-        @param info_callback: debug callback, gets to see all archive entries.
-        @param crc_check: set to False to disable CRC checks
+        Parameters:
+
+            rarfile
+                archive file name
+            mode
+                only 'r' is supported.
+            charset
+                fallback charset to use, if filenames are not already Unicode-enabled.
+            info_callback
+                debug callback, gets to see all archive entries.
+            crc_check
+                set to False to disable CRC checks
         """
         self.rarfile = rarfile
         self.comment = None
@@ -457,6 +483,7 @@ class RarFile(object):
         self._needs_password = False
         self._password = None
         self._crc_check = crc_check
+        self._vol_list = []
 
         self._main = None
 
@@ -489,6 +516,14 @@ class RarFile(object):
         '''Return RarInfo objects for all files/directories in archive.'''
         return self._info_list
 
+    def volumelist(self):
+        '''Returns filenames of archive volumes.
+
+        In case of single-volume archive, the list contains
+        just the name of main archive file.
+        '''
+        return self._vol_list
+
     def getinfo(self, fname):
         '''Return RarInfo for file.'''
 
@@ -510,7 +545,8 @@ class RarFile(object):
                 raise NoRarEntry("No such file: "+fname)
 
     def open(self, fname, mode = 'r', psw = None):
-        '''Return open file object, where the data can be read.
+        '''Returns file-like object (:class:`RarExtFile`),
+        from where the data can be read.
         
         The object implements io.RawIOBase interface, so it can
         be further wrapped with io.BufferedReader and io.TextIOWrapper.
@@ -522,9 +558,14 @@ class RarFile(object):
         uncompressed files, on compressed files the seeking is implemented
         by reading ahead and/or restarting the decompression.
 
-        @param fname: file name or RarInfo instance.
-        @param mode: must be 'r'
-        @param psw: password to use for extracting.
+        Parameters:
+
+            fname
+                file name or RarInfo instance.
+            mode
+                must be 'r'
+            psw
+                password to use for extracting.
         '''
 
         if mode != 'r':
@@ -571,8 +612,12 @@ class RarFile(object):
         
         For longer files using .open() may be better idea.
 
-        @param fname: filename or RarInfo instance
-        @param psw: password to use for extracting.
+        Parameters:
+
+            fname
+                filename or RarInfo instance
+            psw
+                password to use for extracting.
         """
 
         f = self.open(fname, 'r', psw)
@@ -593,9 +638,14 @@ class RarFile(object):
     def extract(self, member, path=None, pwd=None):
         """Extract single file into current directory.
         
-        @param member: filename or RarInfo instance
-        @param path: optional destination path
-        @param pwd: optional password to use
+        Parameters:
+
+            member
+                filename or RarInfo instance
+            path
+                optional destination path
+            pwd
+                optional password to use
         """
         if isinstance(member, RarInfo):
             fname = member.filename
@@ -606,9 +656,14 @@ class RarFile(object):
     def extractall(self, path=None, members=None, pwd=None):
         """Extract all files into current directory.
         
-        @param path: optional destination path
-        @param members: optional filename or RarInfo instance list to extract
-        @param pwd: optional password to use
+        Parameters:
+
+            path
+                optional destination path
+            members
+                optional filename or RarInfo instance list to extract
+            pwd
+                optional password to use
         """
         fnlist = []
         if members is not None:
@@ -693,6 +748,7 @@ class RarFile(object):
         more_vols = 0
         endarc = 0
         volfile = self.rarfile
+        self._vol_list = [self.rarfile]
         while 1:
             if endarc:
                 h = None    # don't read past ENDARC
@@ -707,6 +763,7 @@ class RarFile(object):
                     self._fd = fd
                     more_vols = 0
                     endarc = 0
+                    self._vol_list.append(volfile)
                     continue
                 break
             h.volume = volume
@@ -1210,7 +1267,7 @@ class UnicodeFilename:
 
 
 class RarExtFile(RawIOBase):
-    """Base class for 'file-like' object that RarFile.open() returns.
+    """Base class for file-like object that :meth:`RarFile.open` returns.
 
     Provides public methods and common crc checking.
 
@@ -1218,13 +1275,15 @@ class RarExtFile(RawIOBase):
      - no short reads - .read() and .readinfo() read as much as requested.
      - no internal buffer, use io.BufferedReader for that.
 
-    @ivar name:
-      filename of the archive entry.
+    If :mod:`io` module is available (Python 2.6+, 3.x), then this calls
+    will inherit from :class:`io.RawIOBase` class.  This makes line-based
+    access available: :meth:`RarExtFile.readline` and ``for ln in f``.
     """
 
-    def __init__(self, rf, inf):
-        """Fill common fields"""
+    #: Filename of the archive entry
+    name = None
 
+    def __init__(self, rf, inf):
         RawIOBase.__init__(self)
 
         # standard io.* properties
@@ -1325,7 +1384,13 @@ class RarExtFile(RawIOBase):
         return self.inf.file_size - self.remain
 
     def seek(self, ofs, whence = 0):
-        """Seek in data."""
+        """Seek in data.
+        
+        On uncompressed files, the seeking works by actual
+        seeks so it's fast.  On compresses files its slow
+        - forward seeking happends by reading ahead,
+        backwards by re-opening and decompressing from the start.
+        """
 
         # disable crc check when seeking
         self.crc_check = 0
@@ -1374,8 +1439,17 @@ class RarExtFile(RawIOBase):
         """Returns True"""
         return True
 
+    def writable(self):
+        """Returns False.
+        
+        Writing is not supported."""
+        return False
+
     def seekable(self):
-        """Returns True"""
+        """Returns True.
+        
+        Seeking is supported, although it's slow on compressed files.
+        """
         return True
 
     def readall(self):

setup.py

@@ -15,7 +15,7 @@ use_setuptools()
 import sys
 
 NAME = "KindleComicConverter"
-VERSION = "2.8"
+VERSION = "2.9"
 MAIN = "kcc.py"
 
 includefiles = ['README.md', 'MANIFEST.in', 'LICENSE.txt', 'comic2ebook.ico', 'comic2ebook.icns']

setup_console.py

@@ -10,7 +10,7 @@ sys.path.insert(0, 'kcc')
 
 setup(
     name = "KindleComicConverter",
-    version = "2.8",
+    version = "2.9",
     author = "Ciro Mattia Gonano",
     author_email = "ciromattia@gmail.com",
     description = "A tool to convert comics (CBR/CBZ/PDFs/image folders) to MOBI.",