tools v1.6

Kindle_Mobi_Tools/lib/mobidedrm.py

@@ -26,263 +26,275 @@
 #         Also now handles encrypted files that don't need a specific PID.
 #  0.11 - use autoflushed stdout and proper return values
 #  0.12 - Fix for problems with metadata import as Calibre plugin, report errors
+#  0.13 - Formatting fixes: retabbed file, removed trailing whitespace
+#         and extra blank lines, converted CR/LF pairs at ends of each line,
+#         and other cosmetic fixes.
+#  0.14 - Working out when the extra data flags are present has been problematic
+#         Versions 7 through 9 have tried to tweak the conditions, but have been
+#         only partially successful. Closer examination of lots of sample
+#         files reveals that a confusin has arisen because trailing data entries
+#         are not encrypted, but it turns out that the multibyte entries
+#         in utf8 file are encrypted. (Although neither kind gets compressed.)
+#         This knowledge leads to a simplification of the test for the 
+#         trailing data byte flags - version 5 and higher AND header size >= 0xE4. 
 
-class Unbuffered:
-	def __init__(self, stream):
-		self.stream = stream
-	def write(self, data):
-		self.stream.write(data)
-		self.stream.flush()
-	def __getattr__(self, attr):
-		return getattr(self.stream, attr)
+__version__ = '0.14'
 
 import sys
-sys.stdout=Unbuffered(sys.stdout)
+import struct
+import binascii
 
-import struct,binascii
+class Unbuffered:
+    def __init__(self, stream):
+        self.stream = stream
+    def write(self, data):
+        self.stream.write(data)
+        self.stream.flush()
+    def __getattr__(self, attr):
+        return getattr(self.stream, attr)
 
 class DrmException(Exception):
-	pass
+    pass
 
-#implementation of Pukall Cipher 1
+# Implementation of Pukall Cipher 1
 def PC1(key, src, decryption=True):
-	sum1 = 0;
-	sum2 = 0;
-	keyXorVal = 0;
-	if len(key)!=16:
-		print "Bad key length!"
-		return None
-	wkey = []
-	for i in xrange(8):
-		wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
+    sum1 = 0;
+    sum2 = 0;
+    keyXorVal = 0;
+    if len(key)!=16:
+        print "Bad key length!"
+        return None
+    wkey = []
+    for i in xrange(8):
+        wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
 
-	dst = ""
-	for i in xrange(len(src)):
-		temp1 = 0;
-		byteXorVal = 0;
-		for j in xrange(8):
-			temp1 ^= wkey[j]
-			sum2  = (sum2+j)*20021 + sum1
-			sum1  = (temp1*346)&0xFFFF
-			sum2  = (sum2+sum1)&0xFFFF
-			temp1 = (temp1*20021+1)&0xFFFF
-			byteXorVal ^= temp1 ^ sum2
-		curByte = ord(src[i])
-		if not decryption:
-			keyXorVal = curByte * 257;
-		curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
-		if decryption:
-			keyXorVal = curByte * 257;
-		for j in xrange(8):
-			wkey[j] ^= keyXorVal;
-		dst+=chr(curByte)
-	return dst
+    dst = ""
+    for i in xrange(len(src)):
+        temp1 = 0;
+        byteXorVal = 0;
+        for j in xrange(8):
+            temp1 ^= wkey[j]
+            sum2  = (sum2+j)*20021 + sum1
+            sum1  = (temp1*346)&0xFFFF
+            sum2  = (sum2+sum1)&0xFFFF
+            temp1 = (temp1*20021+1)&0xFFFF
+            byteXorVal ^= temp1 ^ sum2
+        curByte = ord(src[i])
+        if not decryption:
+            keyXorVal = curByte * 257;
+        curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
+        if decryption:
+            keyXorVal = curByte * 257;
+        for j in xrange(8):
+            wkey[j] ^= keyXorVal;
+        dst+=chr(curByte)
+    return dst
 
 def checksumPid(s):
-	letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
-	crc = (~binascii.crc32(s,-1))&0xFFFFFFFF 
-	crc = crc ^ (crc >> 16)
-	res = s
-	l = len(letters)
-	for i in (0,1):
-		b = crc & 0xff
-		pos = (b // l) ^ (b % l)
-		res += letters[pos%l]
-		crc >>= 8
-	return res
+    letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
+    crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
+    crc = crc ^ (crc >> 16)
+    res = s
+    l = len(letters)
+    for i in (0,1):
+        b = crc & 0xff
+        pos = (b // l) ^ (b % l)
+        res += letters[pos%l]
+        crc >>= 8
+    return res
 
 def getSizeOfTrailingDataEntries(ptr, size, flags):
-	def getSizeOfTrailingDataEntry(ptr, size):
-		bitpos, result = 0, 0
-		if size <= 0:
-			return result
-		while True:
-			v = ord(ptr[size-1])
-			result |= (v & 0x7F) << bitpos
-			bitpos += 7
-			size -= 1
-			if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
-				return result
-	num = 0
-	testflags = flags >> 1
-	while testflags:
-		if testflags & 1:
-			num += getSizeOfTrailingDataEntry(ptr, size - num)
-		testflags >>= 1
-	if flags & 1:
-		num += (ord(ptr[size - num - 1]) & 0x3) + 1
-	return num
+    def getSizeOfTrailingDataEntry(ptr, size):
+        bitpos, result = 0, 0
+        if size <= 0:
+            return result
+        while True:
+            v = ord(ptr[size-1])
+            result |= (v & 0x7F) << bitpos
+            bitpos += 7
+            size -= 1
+            if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
+                return result
+    num = 0
+    testflags = flags >> 1
+    while testflags:
+        if testflags & 1:
+            num += getSizeOfTrailingDataEntry(ptr, size - num)
+        testflags >>= 1
+    # Multibyte data, if present, is included in the encryption, so
+    # we do not need to check the low bit.
+    # if flags & 1:
+    #    num += (ord(ptr[size - num - 1]) & 0x3) + 1
+    return num
 
 class DrmStripper:
-	def loadSection(self, section):	
-		if (section + 1 == self.num_sections):
-			endoff = len(self.data_file)
-		else:
-			endoff = self.sections[section + 1][0]
-		off = self.sections[section][0]
-		return self.data_file[off:endoff]
+    def loadSection(self, section):
+        if (section + 1 == self.num_sections):
+            endoff = len(self.data_file)
+        else:
+            endoff = self.sections[section + 1][0]
+        off = self.sections[section][0]
+        return self.data_file[off:endoff]
 
-	def patch(self, off, new):	
-		self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
+    def patch(self, off, new):
+        self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
 
-	def patchSection(self, section, new, in_off = 0):
-		if (section + 1 == self.num_sections):
-			endoff = len(self.data_file)
-		else:
-			endoff = self.sections[section + 1][0]
-		off = self.sections[section][0]
-		assert off + in_off + len(new) <= endoff
-		self.patch(off + in_off, new)
+    def patchSection(self, section, new, in_off = 0):
+        if (section + 1 == self.num_sections):
+            endoff = len(self.data_file)
+        else:
+            endoff = self.sections[section + 1][0]
+        off = self.sections[section][0]
+        assert off + in_off + len(new) <= endoff
+        self.patch(off + in_off, new)
 
-	def parseDRM(self, data, count, pid):
-		pid = pid.ljust(16,'\0')
-		keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
-		temp_key = PC1(keyvec1, pid, False)
-		temp_key_sum = sum(map(ord,temp_key)) & 0xff
-		found_key = None
-		for i in xrange(count):
-			verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-			cookie = PC1(temp_key, cookie)
-			ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-			if verification == ver and cksum == temp_key_sum and (flags & 0x1F) == 1:
-				found_key = finalkey
-				break
-		if not found_key:
-			# Then try the default encoding that doesn't require a PID
-			temp_key = keyvec1
-			temp_key_sum = sum(map(ord,temp_key)) & 0xff
-			for i in xrange(count):
-				verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
-				cookie = PC1(temp_key, cookie)
-				ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
-				if verification == ver and cksum == temp_key_sum:
-					found_key = finalkey
-					break
-		return found_key		
+    def parseDRM(self, data, count, pid):
+        pid = pid.ljust(16,'\0')
+        keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
+        temp_key = PC1(keyvec1, pid, False)
+        temp_key_sum = sum(map(ord,temp_key)) & 0xff
+        found_key = None
+        for i in xrange(count):
+            verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
+            cookie = PC1(temp_key, cookie)
+            ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
+            if verification == ver and cksum == temp_key_sum and (flags & 0x1F) == 1:
+                found_key = finalkey
+                break
+        if not found_key:
+            # Then try the default encoding that doesn't require a PID
+            temp_key = keyvec1
+            temp_key_sum = sum(map(ord,temp_key)) & 0xff
+            for i in xrange(count):
+                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
+                cookie = PC1(temp_key, cookie)
+                ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
+                if verification == ver and cksum == temp_key_sum:
+                    found_key = finalkey
+                    break
+        return found_key
 
+    def __init__(self, data_file, pid):
+        if checksumPid(pid[0:-2]) != pid:
+            raise DrmException("invalid PID checksum")
+        pid = pid[0:-2]
 
-	def __init__(self, data_file, pid):
+        self.data_file = data_file
+        header = data_file[0:72]
+        if header[0x3C:0x3C+8] != 'BOOKMOBI':
+            raise DrmException("invalid file format")
+        self.num_sections, = struct.unpack('>H', data_file[76:78])
 
-		if checksumPid(pid[0:-2]) != pid:
-			raise DrmException("invalid PID checksum")
-		pid = pid[0:-2]
-		
-		self.data_file = data_file
-		header = data_file[0:72]
-		if header[0x3C:0x3C+8] != 'BOOKMOBI':
-			raise DrmException("invalid file format")
-		self.num_sections, = struct.unpack('>H', data_file[76:78])
+        self.sections = []
+        for i in xrange(self.num_sections):
+            offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', data_file[78+i*8:78+i*8+8])
+            flags, val = a1, a2<<16|a3<<8|a4
+            self.sections.append( (offset, flags, val) )
 
-		self.sections = []
-		for i in xrange(self.num_sections):
-			offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', data_file[78+i*8:78+i*8+8])
-			flags, val = a1, a2<<16|a3<<8|a4
-			self.sections.append( (offset, flags, val) )
+        sect = self.loadSection(0)
+        records, = struct.unpack('>H', sect[0x8:0x8+2])
+        mobi_length, = struct.unpack('>L',sect[0x14:0x18])
+        mobi_version, = struct.unpack('>L',sect[0x68:0x6C])
+        extra_data_flags = 0
+        print "MOBI header length = %d" %mobi_length
+        print "MOBI header version = %d" %mobi_version
+        if (mobi_length >= 0xE4) and (mobi_version >= 5):
+            extra_data_flags, = struct.unpack('>H', sect[0xF2:0xF4])
+            print "Extra Data Flags = %d" %extra_data_flags
 
-		sect = self.loadSection(0)
-		records, = struct.unpack('>H', sect[0x8:0x8+2])
-		mobi_length, = struct.unpack('>L',sect[0x14:0x18])
-		mobi_version, = struct.unpack('>L',sect[0x68:0x6C])
-		extra_data_flags = 0
-		print "MOBI header length = %d" %mobi_length
-		print "MOBI header version = %d" %mobi_version
-		if (mobi_length >= 0xE4) and (mobi_version > 5):
-			extra_data_flags, = struct.unpack('>H', sect[0xF2:0xF4])
-			print "Extra Data Flags = %d" %extra_data_flags
+        crypto_type, = struct.unpack('>H', sect[0xC:0xC+2])
+        if crypto_type == 0:
+            print "This book is not encrypted."
+        else:
+            if crypto_type == 1:
+                raise DrmException("cannot decode Mobipocket encryption type 1")
+            if crypto_type != 2:
+                raise DrmException("unknown encryption type: %d" % crypto_type)
 
+            # calculate the keys
+            drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', sect[0xA8:0xA8+16])
+            if drm_count == 0:
+                raise DrmException("no PIDs found in this file")
+            found_key = self.parseDRM(sect[drm_ptr:drm_ptr+drm_size], drm_count, pid)
+            if not found_key:
+                raise DrmException("no key found. maybe the PID is incorrect")
 
-		crypto_type, = struct.unpack('>H', sect[0xC:0xC+2])
-		if crypto_type == 0:
-			print "This book is not encrypted."
-		else:
-			if crypto_type == 1:
-				raise DrmException("cannot decode Mobipocket encryption type 1")
-			if crypto_type != 2:
-				raise DrmException("unknown encryption type: %d" % crypto_type)
-	
-			# calculate the keys
-			drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', sect[0xA8:0xA8+16])
-			if drm_count == 0:
-				raise DrmException("no PIDs found in this file")
-			found_key = self.parseDRM(sect[drm_ptr:drm_ptr+drm_size], drm_count, pid)
-			if not found_key:
-				raise DrmException("no key found. maybe the PID is incorrect")
-	
-			# kill the drm keys
-			self.patchSection(0, "\0" * drm_size, drm_ptr)
-			# kill the drm pointers
-			self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
-			# clear the crypto type
-			self.patchSection(0, "\0" * 2, 0xC)
-	
-			# decrypt sections
-			print "Decrypting. Please wait...",
-			for i in xrange(1, records+1):
-				data = self.loadSection(i)
-				extra_size = getSizeOfTrailingDataEntries(data, len(data), extra_data_flags)
-				# print "record %d, extra_size %d" %(i,extra_size)
-				self.patchSection(i, PC1(found_key, data[0:len(data) - extra_size]))
-		print "done"
-	def getResult(self):
-		return self.data_file
+            # kill the drm keys
+            self.patchSection(0, "\0" * drm_size, drm_ptr)
+            # kill the drm pointers
+            self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
+            # clear the crypto type
+            self.patchSection(0, "\0" * 2, 0xC)
+
+            # decrypt sections
+            print "Decrypting. Please wait...",
+            for i in xrange(1, records+1):
+                data = self.loadSection(i)
+                extra_size = getSizeOfTrailingDataEntries(data, len(data), extra_data_flags)
+                # print "record %d, extra_size %d" %(i,extra_size)
+                self.patchSection(i, PC1(found_key, data[0:len(data) - extra_size]))
+        print "done"
+
+    def getResult(self):
+        return self.data_file
 
 if not __name__ == "__main__":
-	from calibre.customize import FileTypePlugin
+    from calibre.customize import FileTypePlugin
 
-	class MobiDeDRM(FileTypePlugin):
+    class MobiDeDRM(FileTypePlugin):
+        name                = 'MobiDeDRM' # Name of the plugin
+        description         = 'Removes DRM from secure Mobi files'
+        supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
+        author              = 'The Dark Reverser' # The author of this plugin
+        version             = (0, 1, 4)   # The version number of this plugin
+        file_types          = set(['prc','mobi','azw']) # The file types that this plugin will be applied to
+        on_import           = True # Run this plugin during the import
 
-		name                = 'MobiDeDRM' # Name of the plugin
-		description         = 'Removes DRM from secure Mobi files'
-		supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
-		author              = 'The Dark Reverser' # The author of this plugin
-		version             = (0, 1, 2)   # The version number of this plugin
-		file_types          = set(['prc','mobi','azw']) # The file types that this plugin will be applied to
-		on_import           = True # Run this plugin during the import
+        def run(self, path_to_ebook):
+            from calibre.gui2 import is_ok_to_use_qt
+            from PyQt4.Qt import QMessageBox
+            PID = self.site_customization
+            data_file = file(path_to_ebook, 'rb').read()
+            ar = PID.split(',')
+            for i in ar:
+                try:
+                    unlocked_file = DrmStripper(data_file, i).getResult()
+                except DrmException:
+                    # ignore the error
+                    pass
+                else:
+                    of = self.temporary_file('.mobi')
+                    of.write(unlocked_file)
+                    of.close()
+                    return of.name
+            if is_ok_to_use_qt():
+                d = QMessageBox(QMessageBox.Warning, "MobiDeDRM Plugin", "Couldn't decode: %s\n\nImporting encrypted version." % path_to_ebook)
+                d.show()
+                d.raise_()
+                d.exec_()
+            return path_to_ebook
 
-	
-		def run(self, path_to_ebook):
-			from calibre.gui2 import is_ok_to_use_qt
-			from PyQt4.Qt import QMessageBox
-			PID = self.site_customization
-			data_file = file(path_to_ebook, 'rb').read()
-			ar = PID.split(',')
-			for i in ar:
-				try:
-					unlocked_file = DrmStripper(data_file, i).getResult()
-				except DrmException:
-					# ignore the error
-					pass
-				else:
-					of = self.temporary_file('.mobi')
-					of.write(unlocked_file)
-					of.close()
-					return of.name
-			if is_ok_to_use_qt():
-				d = QMessageBox(QMessageBox.Warning, "MobiDeDRM Plugin", "Couldn't decode: %s\n\nImporting encrypted version." % path_to_ebook)
-				d.show()
-				d.raise_()
-				d.exec_()
-			return path_to_ebook
-
-		def customization_help(self, gui=False):
-			return 'Enter PID (separate multiple PIDs with comma)'
+        def customization_help(self, gui=False):
+            return 'Enter PID (separate multiple PIDs with comma)'
 
 if __name__ == "__main__":
-	print "MobiDeDrm v0.12. Copyright (c) 2008 The Dark Reverser"
-	if len(sys.argv)<4:
-		print "Removes protection from Mobipocket books"
-		print "Usage:"
-		print "  mobidedrm infile.mobi outfile.mobi (PID)"
-		sys.exit(1)
-	else:
-		infile = sys.argv[1]
-		outfile = sys.argv[2]
-		pid = sys.argv[3]
-		data_file = file(infile, 'rb').read()
-		try:
-			strippedFile = DrmStripper(data_file, pid)
-			file(outfile, 'wb').write(strippedFile.getResult())
-		except DrmException, e:
-			print "Error: %s" % e
-			sys.exit(1)
-	sys.exit(0)
+    sys.stdout=Unbuffered(sys.stdout)
+    print ('MobiDeDrm v%(__version__)s. '
+	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+    if len(sys.argv)<4:
+        print "Removes protection from Mobipocket books"
+        print "Usage:"
+        print "    %s <infile> <outfile> <PID>" % sys.argv[0]
+        sys.exit(1)
+    else:
+        infile = sys.argv[1]
+        outfile = sys.argv[2]
+        pid = sys.argv[3]
+        data_file = file(infile, 'rb').read()
+        try:
+            strippedFile = DrmStripper(data_file, pid)
+            file(outfile, 'wb').write(strippedFile.getResult())
+        except DrmException, e:
+            print "Error: %s" % e
+            sys.exit(1)
+    sys.exit(0)

Kindle_Mobi_Tools/unswindle/mobidedrm.py

@@ -0,0 +1,300 @@
+#!/usr/bin/python
+#
+# This is a python script. You need a Python interpreter to run it.
+# For example, ActiveState Python, which exists for windows.
+#
+# It can run standalone to convert files, or it can be installed as a
+# plugin for Calibre (http://calibre-ebook.com/about) so that
+# importing files with DRM 'Just Works'.
+#
+# To create a Calibre plugin, rename this file so that the filename
+# ends in '_plugin.py', put it into a ZIP file and import that Calibre
+# using its plugin configuration GUI.
+#
+# Changelog
+#  0.01 - Initial version
+#  0.02 - Huffdic compressed books were not properly decrypted
+#  0.03 - Wasn't checking MOBI header length
+#  0.04 - Wasn't sanity checking size of data record
+#  0.05 - It seems that the extra data flags take two bytes not four
+#  0.06 - And that low bit does mean something after all :-)
+#  0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
+#  0.08 - ...and also not in Mobi header version < 6
+#  0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
+#  0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
+#         import filter it works when importing unencrypted files.
+#         Also now handles encrypted files that don't need a specific PID.
+#  0.11 - use autoflushed stdout and proper return values
+#  0.12 - Fix for problems with metadata import as Calibre plugin, report errors
+#  0.13 - Formatting fixes: retabbed file, removed trailing whitespace
+#         and extra blank lines, converted CR/LF pairs at ends of each line,
+#         and other cosmetic fixes.
+#  0.14 - Working out when the extra data flags are present has been problematic
+#         Versions 7 through 9 have tried to tweak the conditions, but have been
+#         only partially successful. Closer examination of lots of sample
+#         files reveals that a confusin has arisen because trailing data entries
+#         are not encrypted, but it turns out that the multibyte entries
+#         in utf8 file are encrypted. (Although neither kind gets compressed.)
+#         This knowledge leads to a simplification of the test for the 
+#         trailing data byte flags - version 5 and higher AND header size >= 0xE4. 
+
+__version__ = '0.14'
+
+import sys
+import struct
+import binascii
+
+class Unbuffered:
+    def __init__(self, stream):
+        self.stream = stream
+    def write(self, data):
+        self.stream.write(data)
+        self.stream.flush()
+    def __getattr__(self, attr):
+        return getattr(self.stream, attr)
+
+class DrmException(Exception):
+    pass
+
+# Implementation of Pukall Cipher 1
+def PC1(key, src, decryption=True):
+    sum1 = 0;
+    sum2 = 0;
+    keyXorVal = 0;
+    if len(key)!=16:
+        print "Bad key length!"
+        return None
+    wkey = []
+    for i in xrange(8):
+        wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
+
+    dst = ""
+    for i in xrange(len(src)):
+        temp1 = 0;
+        byteXorVal = 0;
+        for j in xrange(8):
+            temp1 ^= wkey[j]
+            sum2  = (sum2+j)*20021 + sum1
+            sum1  = (temp1*346)&0xFFFF
+            sum2  = (sum2+sum1)&0xFFFF
+            temp1 = (temp1*20021+1)&0xFFFF
+            byteXorVal ^= temp1 ^ sum2
+        curByte = ord(src[i])
+        if not decryption:
+            keyXorVal = curByte * 257;
+        curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
+        if decryption:
+            keyXorVal = curByte * 257;
+        for j in xrange(8):
+            wkey[j] ^= keyXorVal;
+        dst+=chr(curByte)
+    return dst
+
+def checksumPid(s):
+    letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
+    crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
+    crc = crc ^ (crc >> 16)
+    res = s
+    l = len(letters)
+    for i in (0,1):
+        b = crc & 0xff
+        pos = (b // l) ^ (b % l)
+        res += letters[pos%l]
+        crc >>= 8
+    return res
+
+def getSizeOfTrailingDataEntries(ptr, size, flags):
+    def getSizeOfTrailingDataEntry(ptr, size):
+        bitpos, result = 0, 0
+        if size <= 0:
+            return result
+        while True:
+            v = ord(ptr[size-1])
+            result |= (v & 0x7F) << bitpos
+            bitpos += 7
+            size -= 1
+            if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
+                return result
+    num = 0
+    testflags = flags >> 1
+    while testflags:
+        if testflags & 1:
+            num += getSizeOfTrailingDataEntry(ptr, size - num)
+        testflags >>= 1
+    # Multibyte data, if present, is included in the encryption, so
+    # we do not need to check the low bit.
+    # if flags & 1:
+    #    num += (ord(ptr[size - num - 1]) & 0x3) + 1
+    return num
+
+class DrmStripper:
+    def loadSection(self, section):
+        if (section + 1 == self.num_sections):
+            endoff = len(self.data_file)
+        else:
+            endoff = self.sections[section + 1][0]
+        off = self.sections[section][0]
+        return self.data_file[off:endoff]
+
+    def patch(self, off, new):
+        self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
+
+    def patchSection(self, section, new, in_off = 0):
+        if (section + 1 == self.num_sections):
+            endoff = len(self.data_file)
+        else:
+            endoff = self.sections[section + 1][0]
+        off = self.sections[section][0]
+        assert off + in_off + len(new) <= endoff
+        self.patch(off + in_off, new)
+
+    def parseDRM(self, data, count, pid):
+        pid = pid.ljust(16,'\0')
+        keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
+        temp_key = PC1(keyvec1, pid, False)
+        temp_key_sum = sum(map(ord,temp_key)) & 0xff
+        found_key = None
+        for i in xrange(count):
+            verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
+            cookie = PC1(temp_key, cookie)
+            ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
+            if verification == ver and cksum == temp_key_sum and (flags & 0x1F) == 1:
+                found_key = finalkey
+                break
+        if not found_key:
+            # Then try the default encoding that doesn't require a PID
+            temp_key = keyvec1
+            temp_key_sum = sum(map(ord,temp_key)) & 0xff
+            for i in xrange(count):
+                verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
+                cookie = PC1(temp_key, cookie)
+                ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
+                if verification == ver and cksum == temp_key_sum:
+                    found_key = finalkey
+                    break
+        return found_key
+
+    def __init__(self, data_file, pid):
+        if checksumPid(pid[0:-2]) != pid:
+            raise DrmException("invalid PID checksum")
+        pid = pid[0:-2]
+
+        self.data_file = data_file
+        header = data_file[0:72]
+        if header[0x3C:0x3C+8] != 'BOOKMOBI':
+            raise DrmException("invalid file format")
+        self.num_sections, = struct.unpack('>H', data_file[76:78])
+
+        self.sections = []
+        for i in xrange(self.num_sections):
+            offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', data_file[78+i*8:78+i*8+8])
+            flags, val = a1, a2<<16|a3<<8|a4
+            self.sections.append( (offset, flags, val) )
+
+        sect = self.loadSection(0)
+        records, = struct.unpack('>H', sect[0x8:0x8+2])
+        mobi_length, = struct.unpack('>L',sect[0x14:0x18])
+        mobi_version, = struct.unpack('>L',sect[0x68:0x6C])
+        extra_data_flags = 0
+        print "MOBI header length = %d" %mobi_length
+        print "MOBI header version = %d" %mobi_version
+        if (mobi_length >= 0xE4) and (mobi_version >= 5):
+            extra_data_flags, = struct.unpack('>H', sect[0xF2:0xF4])
+            print "Extra Data Flags = %d" %extra_data_flags
+
+        crypto_type, = struct.unpack('>H', sect[0xC:0xC+2])
+        if crypto_type == 0:
+            print "This book is not encrypted."
+        else:
+            if crypto_type == 1:
+                raise DrmException("cannot decode Mobipocket encryption type 1")
+            if crypto_type != 2:
+                raise DrmException("unknown encryption type: %d" % crypto_type)
+
+            # calculate the keys
+            drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', sect[0xA8:0xA8+16])
+            if drm_count == 0:
+                raise DrmException("no PIDs found in this file")
+            found_key = self.parseDRM(sect[drm_ptr:drm_ptr+drm_size], drm_count, pid)
+            if not found_key:
+                raise DrmException("no key found. maybe the PID is incorrect")
+
+            # kill the drm keys
+            self.patchSection(0, "\0" * drm_size, drm_ptr)
+            # kill the drm pointers
+            self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
+            # clear the crypto type
+            self.patchSection(0, "\0" * 2, 0xC)
+
+            # decrypt sections
+            print "Decrypting. Please wait...",
+            for i in xrange(1, records+1):
+                data = self.loadSection(i)
+                extra_size = getSizeOfTrailingDataEntries(data, len(data), extra_data_flags)
+                # print "record %d, extra_size %d" %(i,extra_size)
+                self.patchSection(i, PC1(found_key, data[0:len(data) - extra_size]))
+        print "done"
+
+    def getResult(self):
+        return self.data_file
+
+if not __name__ == "__main__":
+    from calibre.customize import FileTypePlugin
+
+    class MobiDeDRM(FileTypePlugin):
+        name                = 'MobiDeDRM' # Name of the plugin
+        description         = 'Removes DRM from secure Mobi files'
+        supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
+        author              = 'The Dark Reverser' # The author of this plugin
+        version             = (0, 1, 4)   # The version number of this plugin
+        file_types          = set(['prc','mobi','azw']) # The file types that this plugin will be applied to
+        on_import           = True # Run this plugin during the import
+
+        def run(self, path_to_ebook):
+            from calibre.gui2 import is_ok_to_use_qt
+            from PyQt4.Qt import QMessageBox
+            PID = self.site_customization
+            data_file = file(path_to_ebook, 'rb').read()
+            ar = PID.split(',')
+            for i in ar:
+                try:
+                    unlocked_file = DrmStripper(data_file, i).getResult()
+                except DrmException:
+                    # ignore the error
+                    pass
+                else:
+                    of = self.temporary_file('.mobi')
+                    of.write(unlocked_file)
+                    of.close()
+                    return of.name
+            if is_ok_to_use_qt():
+                d = QMessageBox(QMessageBox.Warning, "MobiDeDRM Plugin", "Couldn't decode: %s\n\nImporting encrypted version." % path_to_ebook)
+                d.show()
+                d.raise_()
+                d.exec_()
+            return path_to_ebook
+
+        def customization_help(self, gui=False):
+            return 'Enter PID (separate multiple PIDs with comma)'
+
+if __name__ == "__main__":
+    sys.stdout=Unbuffered(sys.stdout)
+    print ('MobiDeDrm v%(__version__)s. '
+	   'Copyright 2008-2010 The Dark Reverser.' % globals())
+    if len(sys.argv)<4:
+        print "Removes protection from Mobipocket books"
+        print "Usage:"
+        print "    %s <infile> <outfile> <PID>" % sys.argv[0]
+        sys.exit(1)
+    else:
+        infile = sys.argv[1]
+        outfile = sys.argv[2]
+        pid = sys.argv[3]
+        data_file = file(infile, 'rb').read()
+        try:
+            strippedFile = DrmStripper(data_file, pid)
+            file(outfile, 'wb').write(strippedFile.getResult())
+        except DrmException, e:
+            print "Error: %s" % e
+            sys.exit(1)
+    sys.exit(0)

Topaz_Tools/lib/cmbtc_dump.py

@@ -1,5 +1,5 @@
 #! /usr/bin/python
-# For use in Topaz Scripts version 2.3
+# For use in Topaz Scripts version 2.6
 
 """
 

Topaz_Tools/lib/cmbtc_dump_nonK4PC.py

@@ -1,5 +1,5 @@
 #!/usr/bin/python
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 class Unbuffered:
     def __init__(self, stream):

Topaz_Tools/lib/convert2xml.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.4
+# For use with Topaz Scripts Version 2.6
 
 class Unbuffered:
     def __init__(self, stream):
@@ -315,6 +315,12 @@ class PageParser(object):
         'version.findlists'                : (1, 'scalar_text', 0, 0),
         'version.page_num'                 : (1, 'scalar_text', 0, 0),
         'version.page_type'                : (1, 'scalar_text', 0, 0),
+        'version.bad_text'                 : (1, 'scalar_text', 0, 0),
+        'version.glyph_mismatch'           : (1, 'scalar_text', 0, 0),
+        'version.margins'                  : (1, 'scalar_text', 0, 0),
+        'version.staggered_lines'          : (1, 'scalar_text', 0, 0),
+        'version.paragraph_continuation'   : (1, 'scalar_text', 0, 0),
+        'version.toc'                      : (1, 'scalar_text', 0, 0),
 
         'stylesheet'   : (1, 'snippets', 1, 0),
         'style'              : (1, 'snippets', 1, 0),
@@ -662,16 +668,19 @@ class PageParser(object):
     def process(self):
 
         # peek at the first bytes to see what type of file it is
-        magic = self.fo.read(11)
-        if (magic[0:1] == 'p') and (magic[2:10] == '__PAGE__'):
+        magic = self.fo.read(9)
+        if (magic[0:1] == 'p') and (magic[2:9] == 'marker_'):
             first_token = 'info'
-        elif (magic[0:1] == 'g') and (magic[2:11] == '__GLYPH__'):
-            skip = self.fo.read(1)
+        elif (magic[0:1] == 'p') and (magic[2:9] == '__PAGE_'):
+            skip = self.fo.read(2)
+            first_token = 'info'
+        elif (magic[0:1] == 'g') and (magic[2:9] == '__GLYPH'):
+            skip = self.fo.read(3)
             first_token = 'info'
         else :
             # other0.dat file
             first_token = None
-            self.fo.seek(-11,1)
+            self.fo.seek(-9,1)
 
 
         # main loop to read and build the document tree

Topaz_Tools/lib/decode_meta.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 import csv
 import sys

Topaz_Tools/lib/flatxml2html.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 import sys
 import csv
@@ -32,6 +32,8 @@ class DocParser(object):
         self.link_id = []
         self.link_title = []
         self.link_page = []
+        self.link_href = []
+        self.link_type = []
         self.dehyphen_rootid = []
         self.paracont_stemid = []
         self.parastems_stemid = []
@@ -197,6 +199,7 @@ class DocParser(object):
     # get the class
     def getClass(self, pclass):
         nclass = pclass
+
         # class names are an issue given topaz may start them with numerals (not allowed),
         # use a mix of cases (which cause some browsers problems), and actually
         # attach numbers after "_reclustered*" to the end to deal classeses that inherit
@@ -206,7 +209,10 @@ class DocParser(object):
         # so we clean this up by lowercasing, prepend 'cl-', and getting any baseclass
         # that exists in the stylesheet first, and then adding this specific class
         # after
+        
+        # also some class names have spaces in them so need to convert to dashes
         if nclass != None :
+            nclass = nclass.replace(' ','-')
             classres = ''
             nclass = nclass.lower()
             nclass = 'cl-' + nclass
@@ -334,7 +340,7 @@ class DocParser(object):
             result.append(('svg', num))
             return pclass, result
 
-        # this type of paragrph may be made up of multiple spans, inline 
+        # this type of paragraph may be made up of multiple spans, inline 
         # word monograms (images), and words with semantic meaning, 
         # plus glyphs used to form starting letter of first word
         
@@ -391,6 +397,9 @@ class DocParser(object):
                 result.append(('img' + word_class, int(argres)))
                 word_class = ''
 
+            elif name.endswith('region.img.src'):
+                result.append(('img' + word_class, int(argres)))
+
             if (sp_first != -1) and (sp_last != -1):
                 for wordnum in xrange(sp_first, sp_last):
                     result.append(('ocr', wordnum))
@@ -437,6 +446,8 @@ class DocParser(object):
         if (type == 'end'):
             parares += ' '
 
+        lstart = len(parares)
+
         cnt = len(pdesc)
 
         for j in xrange( 0, cnt) :
@@ -449,18 +460,28 @@ class DocParser(object):
 
                 if handle_links:
                     link = self.link_id[num]
-                    if (link > 0): 
+                    if (link > 0):
+                        linktype = self.link_type[link-1]
                         title = self.link_title[link-1]
-                        if (title == "") or (parares.rfind(title) < 0): 
-                            title='_link_'
-                        ptarget = self.link_page[link-1] - 1
-                        linkhtml = '<a href="#page%04d">' % ptarget
+                        if (title == "") or (parares.rfind(title) < 0):
+                            title=parares[lstart:]
+                        if linktype == 'external' :
+                            linkhref = self.link_href[link-1]
+                            linkhtml = '<a href="%s">' % linkhref
+                        else : 
+                            if len(self.link_page) >= link :
+                                ptarget = self.link_page[link-1] - 1
+                                linkhtml = '<a href="#page%04d">' % ptarget
+                            else :
+                                # just link to the current page
+                                linkhtml = '<a href="#' + self.id + '">'
                         linkhtml += title + '</a>'
                         pos = parares.rfind(title)
                         if pos >= 0:
                             parares = parares[0:pos] + linkhtml + parares[pos+len(title):]
                         else :
                             parares += linkhtml
+                        lstart = len(parares)
                         if word == '_link_' : word = ''
                     elif (link < 0) :
                         if word == '_link_' : word = ''
@@ -532,6 +553,14 @@ class DocParser(object):
         # collect link destination page numbers
         self.link_page = self.getData('info.links.page',0,-1)
 
+        # collect link types (container versus external)
+        (pos, argres) = self.findinDoc('info.links.type',0,-1)
+        if argres :  self.link_type = argres.split('|')
+
+        # collect link destinations
+        (pos, argres) = self.findinDoc('info.links.href',0,-1)
+        if argres :  self.link_href = argres.split('|')
+
         # collect link titles
         (pos, argres) = self.findinDoc('info.links.title',0,-1)
         if argres :
@@ -641,16 +670,18 @@ class DocParser(object):
                     htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
 
 
-                elif (regtype == 'synth_fcvr.center') or (regtype == 'synth_text.center'):
+                elif (regtype == 'synth_fcvr.center'):
                     (pos, simgsrc) = self.findinDoc('img.src',start,end)
                     if simgsrc:
                         htmlpage += '<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc)
 
                 else :
-                    print 'Warning: region type', regtype
+                    print '          Making region type', regtype,
                     (pos, temp) = self.findinDoc('paragraph',start,end)
-                    if pos != -1:
-                        print '   is a "text" region'
+                    (pos2, temp) = self.findinDoc('span',start,end)
+                    if pos != -1 or pos2 != -1:
+                        print ' a "text" region'
+                        orig_regtype = regtype
                         regtype = 'fixed'
                         ptype = 'full'
                         # check to see if this is a continution from the previous page
@@ -658,6 +689,11 @@ class DocParser(object):
                             ptype = 'end'
                             first_para_continued = False
                         (pclass, pdesc) = self.getParaDescription(start,end, regtype)
+                        if not pclass:
+                            if orig_regtype.endswith('.right')     : pclass = 'cl-right'
+                            elif orig_regtype.endswith('.center')  : pclass = 'cl-center'
+                            elif orig_regtype.endswith('.left')    : pclass = 'cl-left'
+                            elif orig_regtype.endswith('.justify') : pclass = 'cl-justify'
                         if pclass and (ptype == 'full') and (len(pclass) >= 6):
                             tag = 'p'
                             if pclass[3:6] == 'h1-' : tag = 'h4'
@@ -669,7 +705,7 @@ class DocParser(object):
                         else :
                             htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
                     else :
-                        print '    is a "graphic" region'
+                        print ' a "graphic" region'
                         (pos, simgsrc) = self.findinDoc('img.src',start,end)
                         if simgsrc:
                             htmlpage += '<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc)

Topaz_Tools/lib/genhtml.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 class Unbuffered:
     def __init__(self, stream):

Topaz_Tools/lib/gensvg.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 class Unbuffered:
     def __init__(self, stream):

Topaz_Tools/lib/genxml.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 class Unbuffered:
     def __init__(self, stream):

Topaz_Tools/lib/getpagedim.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 import csv
 import sys

Topaz_Tools/lib/stylexml2css.py

@@ -1,6 +1,6 @@
 #! /usr/bin/python
 # vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
-# For use with Topaz Scripts Version 2.3
+# For use with Topaz Scripts Version 2.6
 
 import csv
 import sys
@@ -85,7 +85,10 @@ class DocParser(object):
     def process(self):
 
         classlst = ''
-        csspage = ''
+        csspage = '.cl-center { text-align: center; margin-left: auto; margin-right: auto; }\n'
+        csspage += '.cl-right { text-align: right; }\n'
+        csspage += '.cl-left { text-align: left; }\n'
+        csspage += '.cl-justify { text-align: justify; }\n'
 
         # generate a list of each <style> starting point in the stylesheet
         styleList= self.posinDoc('book.stylesheet.style')
@@ -108,6 +111,7 @@ class DocParser(object):
                 # get the style class
                 (pos, sclass) = self.findinDoc('style.class',start,end)
                 if sclass != None:
+                    sclass = sclass.replace(' ','-')
                     sclass = '.cl-' + sclass.lower()
                 else : 
                     sclass = ''
@@ -115,6 +119,7 @@ class DocParser(object):
                 # check for any "after class" specifiers
                 (pos, aftclass) = self.findinDoc('style._after_class',start,end)
                 if aftclass != None:
+                    aftclass = aftclass.replace(' ','-')
                     aftclass = '.cl-' + aftclass.lower()
                 else : 
                     aftclass = ''
@@ -216,7 +221,8 @@ class DocParser(object):
                         if ctype == 'h3_' :
                             csspage += 'h6' + cssline + '\n'
 
-                    csspage += self.stags[tag] + cssline + '\n'
+                    if cssline != ' { }':
+                        csspage += self.stags[tag] + cssline + '\n'
 
                 
         return csspage, classlst

Topaz_Tools/lib/topaz-changes.txt

@@ -1,4 +1,18 @@
-Canges in 2.3
+Changes in this Version
+	- bug fix to prevent problems with sample books
+	modified version of patch submitted by that-guy
+
+Changes in 2.6
+	- fix for many additional version tags
+	- fixes to generate better links
+	- fixes to handle external links
+	- now handles new "marker" page .dat files
+	- improved special region handling
+	- properly handle class names with spaces
+	- handle default alignment for synthetic regions
+
+
+Changes in 2.3
        - fix for use with non-latin1 based systems (thank you Tedd)
        - fixes for out of order tokens in xml
 

eReader_Tools/lib/erdr2pml.py

@@ -53,8 +53,9 @@
 #  0.12 - Fix added to prevent lowercasing of image names when the pml code itself uses a different case in the link name.
 #  0.13 - change to unbuffered stdout for use with gui front ends
 #  0.14 - contributed enhancement to support --make-pmlz switch
+#  0.15 - enabled high-ascii to pml character encoding. DropBook now works on Mac.
 
-__version__='0.14'
+__version__='0.15'
 
 # Import Psyco if available
 try:
@@ -465,17 +466,6 @@ class EreaderProcessor(object):
         data = sect[62:]
         return sanitizeFileName(name), data
 
-    def cleanPML(self,pml):
-        # Update old \b font tag with correct \B bold font tag
-        pml2 = pml.replace('\\b', '\\B')
-        # Convert special characters to proper PML code.  High ASCII start at (\x82, \a130) and go up to (\xff, \a255)
-        for k in xrange(130,256):
-            # a2b_hex takes in a hexidecimal as a string and converts it 
-            # to a binary ascii code that we search and replace for
-            badChar=binascii.a2b_hex('%02x' % k)
-            pml2 = pml2.replace(badChar, '\\a%03d' % k)
-            #end for k
-        return pml2
 
     # def getChapterNamePMLOffsetData(self):
     #     cv = ''
@@ -564,6 +554,14 @@ class EreaderProcessor(object):
 
         return r
 
+def cleanPML(pml):
+	# Convert special characters to proper PML code.  High ASCII start at (\x80, \a128) and go up to (\xff, \a255)
+	pml2 = pml
+	for k in xrange(128,256):
+		badChar = chr(k)
+		pml2 = pml2.replace(badChar, '\\a%03d' % k)
+	return pml2
+
 def convertEreaderToPml(infile, name, cc, outdir):
     if not os.path.exists(outdir):
         os.makedirs(outdir)
@@ -585,7 +583,7 @@ def convertEreaderToPml(infile, name, cc, outdir):
     print "   Extracting pml"
     pml_string = er.getText()
     pmlfilename = bookname + ".pml"
-    file(os.path.join(outdir, pmlfilename),'wb').write(pml_string)
+    file(os.path.join(outdir, pmlfilename),'wb').write(cleanPML(pml_string))
 
     # bkinfo = er.getBookInfo()
     # if bkinfo != '':
@@ -677,7 +675,7 @@ def main(argv=None):
             search_time = end_time - start_time
             print 'elapsed time: %.2f seconds' % (search_time, ) 
             if make_pmlz :
-                print 'output in %s' % zipname
+                print 'output is %s' % zipname
             else :
                 print 'output in %s' % outdir 
             print "done"

eReader_Tools/lib/xpml2xhtml.py

@@ -30,8 +30,10 @@
 #  0.17 - add support for tidy.exe under windows
 #  0.18 - fix corner case of lines that start with \axxx or \Uxxxx tags
 #  0.19 - change to use auto flushed stdout, and use proper return values
+#  0.20 - properly handle T markup inside links
+#  0.21 - properly handle new sigil Chapter Breaks for 0.2X series and up
 
-__version__='0.19'
+__version__='0.21'
 
 class Unbuffered:
     def __init__(self, stream):
@@ -624,7 +626,7 @@ class PmlConverter(object):
 
                     if sigil_breaks:
                         if (len(final) - lastbreaksize) > 3000:
-                            final += '<div>\n   <hr class="sigilChapterBreak" />\n</div>\n'
+                            final += '<hr class="sigilChapterBreak" />\n'
                             lastbreaksize = len(final)
 
                     # now create new start tags for all tags that 
@@ -699,7 +701,7 @@ class PmlConverter(object):
                     self.skipNewLine()
 
                 elif cmd == 'T':
-                    if inBlock():
+                    if inBlock() or inLink() or inComment():
                         final += '<span style="margin-left: %s;">&nbsp;</span>' % attr
                     else:
                         final += '<p style="text-indent: %s;">' % attr