parent
38eabe7612
commit
a7856f5c32
@ -0,0 +1,458 @@
|
||||
#! /usr/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# ineptkey.pyw, version 5
|
||||
# Copyright © 2009-2010 i♥cabbages
|
||||
|
||||
# Released under the terms of the GNU General Public Licence, version 3 or
|
||||
# later. <http://www.gnu.org/licenses/>
|
||||
|
||||
# Windows users: Before running this program, you must first install Python 2.6
|
||||
# from <http://www.python.org/download/> and PyCrypto from
|
||||
# <http://www.voidspace.org.uk/python/modules.shtml#pycrypto> (make certain
|
||||
# to install the version for Python 2.6). Then save this script file as
|
||||
# ineptkey.pyw and double-click on it to run it. It will create a file named
|
||||
# adeptkey.der in the same directory. This is your ADEPT user key.
|
||||
#
|
||||
# Mac OS X users: Save this script file as ineptkey.pyw. You can run this
|
||||
# program from the command line (pythonw ineptkey.pyw) or by double-clicking
|
||||
# it when it has been associated with PythonLauncher. It will create a file
|
||||
# named adeptkey.der in the same directory. This is your ADEPT user key.
|
||||
|
||||
# Revision history:
|
||||
# 1 - Initial release, for Adobe Digital Editions 1.7
|
||||
# 2 - Better algorithm for finding pLK; improved error handling
|
||||
# 3 - Rename to INEPT
|
||||
# 4 - Series of changes by joblack (and others?) --
|
||||
# 4.1 - quick beta fix for ADE 1.7.2 (anon)
|
||||
# 4.2 - added old 1.7.1 processing
|
||||
# 4.3 - better key search
|
||||
# 4.4 - Make it working on 64-bit Python
|
||||
# 5 - Clean up and improve 4.x changes;
|
||||
# Clean up and merge OS X support by unknown
|
||||
# 5.1 - add support for using OpenSSL on Windows in place of PyCrypto
|
||||
# 5.2 - added support for output of key to a particular file
|
||||
|
||||
"""
|
||||
Retrieve Adobe ADEPT user key.
|
||||
"""
|
||||
|
||||
from __future__ import with_statement
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
|
||||
import sys
|
||||
import os
|
||||
import struct
|
||||
import Tkinter
|
||||
import Tkconstants
|
||||
import tkMessageBox
|
||||
import traceback
|
||||
|
||||
class ADEPTError(Exception):
|
||||
pass
|
||||
|
||||
if sys.platform.startswith('win'):
|
||||
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
|
||||
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
|
||||
string_at, Structure, c_void_p, cast, c_size_t, memmove, CDLL, c_int, \
|
||||
c_long, c_ulong
|
||||
|
||||
from ctypes.wintypes import LPVOID, DWORD, BOOL
|
||||
import _winreg as winreg
|
||||
|
||||
def _load_crypto_libcrypto():
|
||||
from ctypes.util import find_library
|
||||
libcrypto = find_library('libeay32')
|
||||
if libcrypto is None:
|
||||
raise ADEPTError('libcrypto not found')
|
||||
libcrypto = CDLL(libcrypto)
|
||||
AES_MAXNR = 14
|
||||
c_char_pp = POINTER(c_char_p)
|
||||
c_int_p = POINTER(c_int)
|
||||
class AES_KEY(Structure):
|
||||
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
|
||||
('rounds', c_int)]
|
||||
AES_KEY_p = POINTER(AES_KEY)
|
||||
|
||||
def F(restype, name, argtypes):
|
||||
func = getattr(libcrypto, name)
|
||||
func.restype = restype
|
||||
func.argtypes = argtypes
|
||||
return func
|
||||
|
||||
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
|
||||
[c_char_p, c_int, AES_KEY_p])
|
||||
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
|
||||
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
|
||||
c_int])
|
||||
class AES(object):
|
||||
def __init__(self, userkey):
|
||||
self._blocksize = len(userkey)
|
||||
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
|
||||
raise ADEPTError('AES improper key used')
|
||||
key = self._key = AES_KEY()
|
||||
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
|
||||
if rv < 0:
|
||||
raise ADEPTError('Failed to initialize AES key')
|
||||
def decrypt(self, data):
|
||||
out = create_string_buffer(len(data))
|
||||
iv = ("\x00" * self._blocksize)
|
||||
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
|
||||
if rv == 0:
|
||||
raise ADEPTError('AES decryption failed')
|
||||
return out.raw
|
||||
return AES
|
||||
|
||||
def _load_crypto_pycrypto():
|
||||
from Crypto.Cipher import AES as _AES
|
||||
class AES(object):
|
||||
def __init__(self, key):
|
||||
self._aes = _AES.new(key, _AES.MODE_CBC)
|
||||
def decrypt(self, data):
|
||||
return self._aes.decrypt(data)
|
||||
return AES
|
||||
|
||||
def _load_crypto():
|
||||
AES = None
|
||||
for loader in (_load_crypto_libcrypto, _load_crypto_pycrypto):
|
||||
try:
|
||||
AES = loader()
|
||||
break
|
||||
except (ImportError, ADEPTError):
|
||||
pass
|
||||
return AES
|
||||
|
||||
AES = _load_crypto()
|
||||
|
||||
|
||||
DEVICE_KEY_PATH = r'Software\Adobe\Adept\Device'
|
||||
PRIVATE_LICENCE_KEY_PATH = r'Software\Adobe\Adept\Activation'
|
||||
|
||||
MAX_PATH = 255
|
||||
|
||||
kernel32 = windll.kernel32
|
||||
advapi32 = windll.advapi32
|
||||
crypt32 = windll.crypt32
|
||||
|
||||
def GetSystemDirectory():
|
||||
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
|
||||
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
|
||||
GetSystemDirectoryW.restype = c_uint
|
||||
def GetSystemDirectory():
|
||||
buffer = create_unicode_buffer(MAX_PATH + 1)
|
||||
GetSystemDirectoryW(buffer, len(buffer))
|
||||
return buffer.value
|
||||
return GetSystemDirectory
|
||||
GetSystemDirectory = GetSystemDirectory()
|
||||
|
||||
def GetVolumeSerialNumber():
|
||||
GetVolumeInformationW = kernel32.GetVolumeInformationW
|
||||
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
|
||||
POINTER(c_uint), POINTER(c_uint),
|
||||
POINTER(c_uint), c_wchar_p, c_uint]
|
||||
GetVolumeInformationW.restype = c_uint
|
||||
def GetVolumeSerialNumber(path):
|
||||
vsn = c_uint(0)
|
||||
GetVolumeInformationW(
|
||||
path, None, 0, byref(vsn), None, None, None, 0)
|
||||
return vsn.value
|
||||
return GetVolumeSerialNumber
|
||||
GetVolumeSerialNumber = GetVolumeSerialNumber()
|
||||
|
||||
def GetUserName():
|
||||
GetUserNameW = advapi32.GetUserNameW
|
||||
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
|
||||
GetUserNameW.restype = c_uint
|
||||
def GetUserName():
|
||||
buffer = create_unicode_buffer(32)
|
||||
size = c_uint(len(buffer))
|
||||
while not GetUserNameW(buffer, byref(size)):
|
||||
buffer = create_unicode_buffer(len(buffer) * 2)
|
||||
size.value = len(buffer)
|
||||
return buffer.value.encode('utf-16-le')[::2]
|
||||
return GetUserName
|
||||
GetUserName = GetUserName()
|
||||
|
||||
PAGE_EXECUTE_READWRITE = 0x40
|
||||
MEM_COMMIT = 0x1000
|
||||
MEM_RESERVE = 0x2000
|
||||
|
||||
def VirtualAlloc():
|
||||
_VirtualAlloc = kernel32.VirtualAlloc
|
||||
_VirtualAlloc.argtypes = [LPVOID, c_size_t, DWORD, DWORD]
|
||||
_VirtualAlloc.restype = LPVOID
|
||||
def VirtualAlloc(addr, size, alloctype=(MEM_COMMIT | MEM_RESERVE),
|
||||
protect=PAGE_EXECUTE_READWRITE):
|
||||
return _VirtualAlloc(addr, size, alloctype, protect)
|
||||
return VirtualAlloc
|
||||
VirtualAlloc = VirtualAlloc()
|
||||
|
||||
MEM_RELEASE = 0x8000
|
||||
|
||||
def VirtualFree():
|
||||
_VirtualFree = kernel32.VirtualFree
|
||||
_VirtualFree.argtypes = [LPVOID, c_size_t, DWORD]
|
||||
_VirtualFree.restype = BOOL
|
||||
def VirtualFree(addr, size=0, freetype=MEM_RELEASE):
|
||||
return _VirtualFree(addr, size, freetype)
|
||||
return VirtualFree
|
||||
VirtualFree = VirtualFree()
|
||||
|
||||
class NativeFunction(object):
|
||||
def __init__(self, restype, argtypes, insns):
|
||||
self._buf = buf = VirtualAlloc(None, len(insns))
|
||||
memmove(buf, insns, len(insns))
|
||||
ftype = CFUNCTYPE(restype, *argtypes)
|
||||
self._native = ftype(buf)
|
||||
|
||||
def __call__(self, *args):
|
||||
return self._native(*args)
|
||||
|
||||
def __del__(self):
|
||||
if self._buf is not None:
|
||||
VirtualFree(self._buf)
|
||||
self._buf = None
|
||||
|
||||
if struct.calcsize("P") == 4:
|
||||
CPUID0_INSNS = (
|
||||
"\x53" # push %ebx
|
||||
"\x31\xc0" # xor %eax,%eax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x8b\x44\x24\x08" # mov 0x8(%esp),%eax
|
||||
"\x89\x18" # mov %ebx,0x0(%eax)
|
||||
"\x89\x50\x04" # mov %edx,0x4(%eax)
|
||||
"\x89\x48\x08" # mov %ecx,0x8(%eax)
|
||||
"\x5b" # pop %ebx
|
||||
"\xc3" # ret
|
||||
)
|
||||
CPUID1_INSNS = (
|
||||
"\x53" # push %ebx
|
||||
"\x31\xc0" # xor %eax,%eax
|
||||
"\x40" # inc %eax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x5b" # pop %ebx
|
||||
"\xc3" # ret
|
||||
)
|
||||
else:
|
||||
CPUID0_INSNS = (
|
||||
"\x49\x89\xd8" # mov %rbx,%r8
|
||||
"\x49\x89\xc9" # mov %rcx,%r9
|
||||
"\x48\x31\xc0" # xor %rax,%rax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x4c\x89\xc8" # mov %r9,%rax
|
||||
"\x89\x18" # mov %ebx,0x0(%rax)
|
||||
"\x89\x50\x04" # mov %edx,0x4(%rax)
|
||||
"\x89\x48\x08" # mov %ecx,0x8(%rax)
|
||||
"\x4c\x89\xc3" # mov %r8,%rbx
|
||||
"\xc3" # retq
|
||||
)
|
||||
CPUID1_INSNS = (
|
||||
"\x53" # push %rbx
|
||||
"\x48\x31\xc0" # xor %rax,%rax
|
||||
"\x48\xff\xc0" # inc %rax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x5b" # pop %rbx
|
||||
"\xc3" # retq
|
||||
)
|
||||
|
||||
def cpuid0():
|
||||
_cpuid0 = NativeFunction(None, [c_char_p], CPUID0_INSNS)
|
||||
buf = create_string_buffer(12)
|
||||
def cpuid0():
|
||||
_cpuid0(buf)
|
||||
return buf.raw
|
||||
return cpuid0
|
||||
cpuid0 = cpuid0()
|
||||
|
||||
cpuid1 = NativeFunction(c_uint, [], CPUID1_INSNS)
|
||||
|
||||
class DataBlob(Structure):
|
||||
_fields_ = [('cbData', c_uint),
|
||||
('pbData', c_void_p)]
|
||||
DataBlob_p = POINTER(DataBlob)
|
||||
|
||||
def CryptUnprotectData():
|
||||
_CryptUnprotectData = crypt32.CryptUnprotectData
|
||||
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
|
||||
c_void_p, c_void_p, c_uint, DataBlob_p]
|
||||
_CryptUnprotectData.restype = c_uint
|
||||
def CryptUnprotectData(indata, entropy):
|
||||
indatab = create_string_buffer(indata)
|
||||
indata = DataBlob(len(indata), cast(indatab, c_void_p))
|
||||
entropyb = create_string_buffer(entropy)
|
||||
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
|
||||
outdata = DataBlob()
|
||||
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
|
||||
None, None, 0, byref(outdata)):
|
||||
raise ADEPTError("Failed to decrypt user key key (sic)")
|
||||
return string_at(outdata.pbData, outdata.cbData)
|
||||
return CryptUnprotectData
|
||||
CryptUnprotectData = CryptUnprotectData()
|
||||
|
||||
def retrieve_key(keypath):
|
||||
if AES is None:
|
||||
tkMessageBox.showerror(
|
||||
"ADEPT Key",
|
||||
"This script requires PyCrypto or OpenSSL which must be installed "
|
||||
"separately. Read the top-of-script comment for details.")
|
||||
return False
|
||||
root = GetSystemDirectory().split('\\')[0] + '\\'
|
||||
serial = GetVolumeSerialNumber(root)
|
||||
vendor = cpuid0()
|
||||
signature = struct.pack('>I', cpuid1())[1:]
|
||||
user = GetUserName()
|
||||
entropy = struct.pack('>I12s3s13s', serial, vendor, signature, user)
|
||||
cuser = winreg.HKEY_CURRENT_USER
|
||||
try:
|
||||
regkey = winreg.OpenKey(cuser, DEVICE_KEY_PATH)
|
||||
except WindowsError:
|
||||
raise ADEPTError("Adobe Digital Editions not activated")
|
||||
device = winreg.QueryValueEx(regkey, 'key')[0]
|
||||
keykey = CryptUnprotectData(device, entropy)
|
||||
userkey = None
|
||||
try:
|
||||
plkroot = winreg.OpenKey(cuser, PRIVATE_LICENCE_KEY_PATH)
|
||||
except WindowsError:
|
||||
raise ADEPTError("Could not locate ADE activation")
|
||||
for i in xrange(0, 16):
|
||||
try:
|
||||
plkparent = winreg.OpenKey(plkroot, "%04d" % (i,))
|
||||
except WindowsError:
|
||||
break
|
||||
ktype = winreg.QueryValueEx(plkparent, None)[0]
|
||||
if ktype != 'credentials':
|
||||
continue
|
||||
for j in xrange(0, 16):
|
||||
try:
|
||||
plkkey = winreg.OpenKey(plkparent, "%04d" % (j,))
|
||||
except WindowsError:
|
||||
break
|
||||
ktype = winreg.QueryValueEx(plkkey, None)[0]
|
||||
if ktype != 'privateLicenseKey':
|
||||
continue
|
||||
userkey = winreg.QueryValueEx(plkkey, 'value')[0]
|
||||
break
|
||||
if userkey is not None:
|
||||
break
|
||||
if userkey is None:
|
||||
raise ADEPTError('Could not locate privateLicenseKey')
|
||||
userkey = userkey.decode('base64')
|
||||
aes = AES(keykey)
|
||||
userkey = aes.decrypt(userkey)
|
||||
userkey = userkey[26:-ord(userkey[-1])]
|
||||
with open(keypath, 'wb') as f:
|
||||
f.write(userkey)
|
||||
return True
|
||||
|
||||
elif sys.platform.startswith('darwin'):
|
||||
import xml.etree.ElementTree as etree
|
||||
import Carbon.File
|
||||
import Carbon.Folder
|
||||
import Carbon.Folders
|
||||
import MacOS
|
||||
|
||||
ACTIVATION_PATH = 'Adobe/Digital Editions/activation.dat'
|
||||
NSMAP = {'adept': 'http://ns.adobe.com/adept',
|
||||
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
|
||||
|
||||
def find_folder(domain, dtype):
|
||||
try:
|
||||
fsref = Carbon.Folder.FSFindFolder(domain, dtype, False)
|
||||
return Carbon.File.pathname(fsref)
|
||||
except MacOS.Error:
|
||||
return None
|
||||
|
||||
def find_app_support_file(subpath):
|
||||
dtype = Carbon.Folders.kApplicationSupportFolderType
|
||||
for domain in Carbon.Folders.kUserDomain, Carbon.Folders.kLocalDomain:
|
||||
path = find_folder(domain, dtype)
|
||||
if path is None:
|
||||
continue
|
||||
path = os.path.join(path, subpath)
|
||||
if os.path.isfile(path):
|
||||
return path
|
||||
return None
|
||||
|
||||
def retrieve_key(keypath):
|
||||
actpath = find_app_support_file(ACTIVATION_PATH)
|
||||
if actpath is None:
|
||||
raise ADEPTError("Could not locate ADE activation")
|
||||
tree = etree.parse(actpath)
|
||||
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
|
||||
expr = '//%s/%s' % (adept('credentials'), adept('privateLicenseKey'))
|
||||
userkey = tree.findtext(expr)
|
||||
userkey = userkey.decode('base64')
|
||||
userkey = userkey[26:]
|
||||
with open(keypath, 'wb') as f:
|
||||
f.write(userkey)
|
||||
return True
|
||||
|
||||
elif sys.platform.startswith('cygwin'):
|
||||
def retrieve_key(keypath):
|
||||
tkMessageBox.showerror(
|
||||
"ADEPT Key",
|
||||
"This script requires a Windows-native Python, and cannot be run "
|
||||
"under Cygwin. Please install a Windows-native Python and/or "
|
||||
"check your file associations.")
|
||||
return False
|
||||
|
||||
else:
|
||||
def retrieve_key(keypath):
|
||||
tkMessageBox.showerror(
|
||||
"ADEPT Key",
|
||||
"This script only supports Windows and Mac OS X. For Linux "
|
||||
"you should be able to run ADE and this script under Wine (with "
|
||||
"an appropriate version of Windows Python installed).")
|
||||
return False
|
||||
|
||||
class ExceptionDialog(Tkinter.Frame):
|
||||
def __init__(self, root, text):
|
||||
Tkinter.Frame.__init__(self, root, border=5)
|
||||
label = Tkinter.Label(self, text="Unexpected error:",
|
||||
anchor=Tkconstants.W, justify=Tkconstants.LEFT)
|
||||
label.pack(fill=Tkconstants.X, expand=0)
|
||||
self.text = Tkinter.Text(self)
|
||||
self.text.pack(fill=Tkconstants.BOTH, expand=1)
|
||||
self.text.insert(Tkconstants.END, text)
|
||||
|
||||
def cli_main(argv=sys.argv):
|
||||
keypath = argv[1]
|
||||
try:
|
||||
success = retrieve_key(keypath)
|
||||
except ADEPTError, e:
|
||||
print "Key generation Error: " + str(e)
|
||||
return 1
|
||||
except Exception, e:
|
||||
print "General Error: " + str(e)
|
||||
return 1
|
||||
if not success:
|
||||
return 1
|
||||
return 0
|
||||
|
||||
def main(argv=sys.argv):
|
||||
root = Tkinter.Tk()
|
||||
root.withdraw()
|
||||
progname = os.path.basename(argv[0])
|
||||
keypath = 'adeptkey.der'
|
||||
success = False
|
||||
try:
|
||||
success = retrieve_key(keypath)
|
||||
except ADEPTError, e:
|
||||
tkMessageBox.showerror("ADEPT Key", "Error: " + str(e))
|
||||
except Exception:
|
||||
root.wm_state('normal')
|
||||
root.title('ADEPT Key')
|
||||
text = traceback.format_exc()
|
||||
ExceptionDialog(root, text).pack(fill=Tkconstants.BOTH, expand=1)
|
||||
root.mainloop()
|
||||
if not success:
|
||||
return 1
|
||||
tkMessageBox.showinfo(
|
||||
"ADEPT Key", "Key successfully retrieved to %s" % (keypath))
|
||||
return 0
|
||||
|
||||
if __name__ == '__main__':
|
||||
if len(sys.argv) > 1:
|
||||
sys.exit(cli_main())
|
||||
sys.exit(main())
|
@ -0,0 +1,151 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class PParser(object):
|
||||
def __init__(self, gd, flatxml):
|
||||
self.gd = gd
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.temp = []
|
||||
foo = self.getData('page.h') or self.getData('book.h')
|
||||
self.ph = foo[0]
|
||||
foo = self.getData('page.w') or self.getData('book.w')
|
||||
self.pw = foo[0]
|
||||
self.gx = self.getData('info.glyph.x')
|
||||
self.gy = self.getData('info.glyph.y')
|
||||
self.gid = self.getData('info.glyph.glyphID')
|
||||
def getData(self, path):
|
||||
result = None
|
||||
cnt = len(self.flatdoc)
|
||||
for j in xrange(cnt):
|
||||
item = self.flatdoc[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getDataTemp(self, path):
|
||||
result = None
|
||||
cnt = len(self.temp)
|
||||
for j in xrange(cnt):
|
||||
item = self.temp[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
self.temp.pop(j)
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getImages(self):
|
||||
result = []
|
||||
self.temp = self.flatdoc
|
||||
while (self.getDataTemp('img') != None):
|
||||
h = self.getDataTemp('img.h')[0]
|
||||
w = self.getDataTemp('img.w')[0]
|
||||
x = self.getDataTemp('img.x')[0]
|
||||
y = self.getDataTemp('img.y')[0]
|
||||
src = self.getDataTemp('img.src')[0]
|
||||
result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
|
||||
return result
|
||||
def getGlyphs(self):
|
||||
result = []
|
||||
if (self.gid != None) and (len(self.gid) > 0):
|
||||
glyphs = []
|
||||
for j in set(self.gid):
|
||||
glyphs.append(j)
|
||||
glyphs.sort()
|
||||
for gid in glyphs:
|
||||
id='id="gl%d"' % gid
|
||||
path = self.gd.lookup(id)
|
||||
if path:
|
||||
result.append(id + ' ' + path)
|
||||
return result
|
||||
|
||||
|
||||
def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
|
||||
ml = ''
|
||||
pp = PParser(gdict, flat_xml)
|
||||
ml += '<?xml version="1.0" standalone="no"?>\n'
|
||||
if (raw):
|
||||
ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
|
||||
ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
else:
|
||||
ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
ml += '<script><![CDATA[\n'
|
||||
ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
|
||||
ml += 'var dpi=%d;\n' % scaledpi
|
||||
if (counter) :
|
||||
ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
|
||||
if (counter < numfiles-1) :
|
||||
ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
|
||||
ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
|
||||
ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
|
||||
ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
|
||||
ml += 'function setsize(){var svg=document.getElementById("svgimg");var prev=document.getElementById("prevsvg");var next=document.getElementById("nextsvg");var width=(pw/dpi)+"in";var height=(ph/dpi)+"in";svg.setAttribute("width",width);svg.setAttribute("height",height);prev.setAttribute("height",height);prev.setAttribute("width","50px");next.setAttribute("height",height);next.setAttribute("width","50px");}\n'
|
||||
ml += 'function ppage(){window.location.href=prevpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'function npage(){window.location.href=nextpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'var gt=gd();if(gt>0){dpi=gt;}\n'
|
||||
ml += 'window.onload=setsize;\n'
|
||||
ml += ']]></script>\n'
|
||||
ml += '</head>\n'
|
||||
ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
|
||||
ml += '<div style="white-space:nowrap;">\n'
|
||||
if (counter == 0) :
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else:
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
|
||||
if (pp.gid != None):
|
||||
ml += '<defs>\n'
|
||||
gdefs = pp.getGlyphs()
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ml += gdefs[j]
|
||||
ml += '</defs>\n'
|
||||
img = pp.getImages()
|
||||
if (img != None):
|
||||
for j in xrange(0,len(img)):
|
||||
ml += img[j]
|
||||
if (pp.gid != None):
|
||||
for j in xrange(0,len(pp.gid)):
|
||||
ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
|
||||
if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
|
||||
ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content. (gensvg.py)</text>\n'
|
||||
if (raw) :
|
||||
ml += '</svg>'
|
||||
else :
|
||||
ml += '</svg></a>\n'
|
||||
if (counter == numfiles - 1) :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '</div>\n'
|
||||
ml += '<div><a href="javascript:zoomin();">zoom in</a> - <a href="javascript:zoomout();">zoom out</a></div>\n'
|
||||
ml += '</body>\n'
|
||||
ml += '</html>\n'
|
||||
return ml
|
||||
|
@ -0,0 +1,561 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
# local support routines
|
||||
import convert2xml
|
||||
import flatxml2html
|
||||
import flatxml2svg
|
||||
import stylexml2css
|
||||
|
||||
|
||||
# Get a 7 bit encoded number from a file
|
||||
def readEncodedNumber(file):
|
||||
flag = False
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
# Get a length prefixed string from the file
|
||||
def lengthPrefixString(data):
|
||||
return encodeNumber(len(data))+data
|
||||
|
||||
def readString(file):
|
||||
stringLength = readEncodedNumber(file)
|
||||
if (stringLength == None):
|
||||
return None
|
||||
sv = file.read(stringLength)
|
||||
if (len(sv) != stringLength):
|
||||
return ""
|
||||
return unpack(str(stringLength)+"s",sv)[0]
|
||||
|
||||
def getMetaArray(metaFile):
|
||||
# parse the meta file
|
||||
result = {}
|
||||
fo = file(metaFile,'rb')
|
||||
size = readEncodedNumber(fo)
|
||||
for i in xrange(size):
|
||||
tag = readString(fo)
|
||||
value = readString(fo)
|
||||
result[tag] = value
|
||||
# print tag, value
|
||||
fo.close()
|
||||
return result
|
||||
|
||||
|
||||
# dictionary of all text strings by index value
|
||||
class Dictionary(object):
|
||||
def __init__(self, dictFile):
|
||||
self.filename = dictFile
|
||||
self.size = 0
|
||||
self.fo = file(dictFile,'rb')
|
||||
self.stable = []
|
||||
self.size = readEncodedNumber(self.fo)
|
||||
for i in xrange(self.size):
|
||||
self.stable.append(self.escapestr(readString(self.fo)))
|
||||
self.pos = 0
|
||||
def escapestr(self, str):
|
||||
str = str.replace('&','&')
|
||||
str = str.replace('<','<')
|
||||
str = str.replace('>','>')
|
||||
str = str.replace('=','=')
|
||||
return str
|
||||
def lookup(self,val):
|
||||
if ((val >= 0) and (val < self.size)) :
|
||||
self.pos = val
|
||||
return self.stable[self.pos]
|
||||
else:
|
||||
print "Error - %d outside of string table limits" % val
|
||||
sys.exit(-1)
|
||||
def getSize(self):
|
||||
return self.size
|
||||
def getPos(self):
|
||||
return self.pos
|
||||
|
||||
|
||||
class PageDimParser(object):
|
||||
def __init__(self, flatxml):
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
# find tag if within pos to end inclusive
|
||||
def findinDoc(self, tagpath, pos, end) :
|
||||
result = None
|
||||
docList = self.flatdoc
|
||||
cnt = len(docList)
|
||||
if end == -1 :
|
||||
end = cnt
|
||||
else:
|
||||
end = min(cnt,end)
|
||||
foundat = -1
|
||||
for j in xrange(pos, end):
|
||||
item = docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=')
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
result = argres
|
||||
foundat = j
|
||||
break
|
||||
return foundat, result
|
||||
def process(self):
|
||||
(pos, sph) = self.findinDoc('page.h',0,-1)
|
||||
(pos, spw) = self.findinDoc('page.w',0,-1)
|
||||
if (sph == None): sph = '-1'
|
||||
if (spw == None): spw = '-1'
|
||||
return sph, spw
|
||||
|
||||
def getPageDim(flatxml):
|
||||
# create a document parser
|
||||
dp = PageDimParser(flatxml)
|
||||
(ph, pw) = dp.process()
|
||||
return ph, pw
|
||||
|
||||
class GParser(object):
|
||||
def __init__(self, flatxml):
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.dpi = 1440
|
||||
self.gh = self.getData('info.glyph.h')
|
||||
self.gw = self.getData('info.glyph.w')
|
||||
self.guse = self.getData('info.glyph.use')
|
||||
if self.guse :
|
||||
self.count = len(self.guse)
|
||||
else :
|
||||
self.count = 0
|
||||
self.gvtx = self.getData('info.glyph.vtx')
|
||||
self.glen = self.getData('info.glyph.len')
|
||||
self.gdpi = self.getData('info.glyph.dpi')
|
||||
self.vx = self.getData('info.vtx.x')
|
||||
self.vy = self.getData('info.vtx.y')
|
||||
self.vlen = self.getData('info.len.n')
|
||||
if self.vlen :
|
||||
self.glen.append(len(self.vlen))
|
||||
elif self.glen:
|
||||
self.glen.append(0)
|
||||
if self.vx :
|
||||
self.gvtx.append(len(self.vx))
|
||||
elif self.gvtx :
|
||||
self.gvtx.append(0)
|
||||
def getData(self, path):
|
||||
result = None
|
||||
cnt = len(self.flatdoc)
|
||||
for j in xrange(cnt):
|
||||
item = self.flatdoc[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name == path):
|
||||
result = argres
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getGlyphDim(self, gly):
|
||||
maxh = (self.gh[gly] * self.dpi) / self.gdpi[gly]
|
||||
maxw = (self.gw[gly] * self.dpi) / self.gdpi[gly]
|
||||
return maxh, maxw
|
||||
def getPath(self, gly):
|
||||
path = ''
|
||||
if (gly < 0) or (gly >= self.count):
|
||||
return path
|
||||
tx = self.vx[self.gvtx[gly]:self.gvtx[gly+1]]
|
||||
ty = self.vy[self.gvtx[gly]:self.gvtx[gly+1]]
|
||||
p = 0
|
||||
for k in xrange(self.glen[gly], self.glen[gly+1]):
|
||||
if (p == 0):
|
||||
zx = tx[0:self.vlen[k]+1]
|
||||
zy = ty[0:self.vlen[k]+1]
|
||||
else:
|
||||
zx = tx[self.vlen[k-1]+1:self.vlen[k]+1]
|
||||
zy = ty[self.vlen[k-1]+1:self.vlen[k]+1]
|
||||
p += 1
|
||||
j = 0
|
||||
while ( j < len(zx) ):
|
||||
if (j == 0):
|
||||
# Start Position.
|
||||
path += 'M %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly])
|
||||
elif (j <= len(zx)-3):
|
||||
# Cubic Bezier Curve
|
||||
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[j+2] * self.dpi / self.gdpi[gly], zy[j+2] * self.dpi / self.gdpi[gly])
|
||||
j += 2
|
||||
elif (j == len(zx)-2):
|
||||
# Cubic Bezier Curve to Start Position
|
||||
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
||||
j += 1
|
||||
elif (j == len(zx)-1):
|
||||
# Quadratic Bezier Curve to Start Position
|
||||
path += 'Q %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
||||
|
||||
j += 1
|
||||
path += 'z'
|
||||
return path
|
||||
|
||||
|
||||
|
||||
# dictionary of all text strings by index value
|
||||
class GlyphDict(object):
|
||||
def __init__(self):
|
||||
self.gdict = {}
|
||||
def lookup(self, id):
|
||||
# id='id="gl%d"' % val
|
||||
if id in self.gdict:
|
||||
return self.gdict[id]
|
||||
return None
|
||||
def addGlyph(self, val, path):
|
||||
id='id="gl%d"' % val
|
||||
self.gdict[id] = path
|
||||
|
||||
|
||||
def generateBook(bookDir, raw, fixedimage):
|
||||
# sanity check Topaz file extraction
|
||||
if not os.path.exists(bookDir) :
|
||||
print "Can not find directory with unencrypted book"
|
||||
return 1
|
||||
|
||||
dictFile = os.path.join(bookDir,'dict0000.dat')
|
||||
if not os.path.exists(dictFile) :
|
||||
print "Can not find dict0000.dat file"
|
||||
return 1
|
||||
|
||||
pageDir = os.path.join(bookDir,'page')
|
||||
if not os.path.exists(pageDir) :
|
||||
print "Can not find page directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
imgDir = os.path.join(bookDir,'img')
|
||||
if not os.path.exists(imgDir) :
|
||||
print "Can not find image directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
glyphsDir = os.path.join(bookDir,'glyphs')
|
||||
if not os.path.exists(glyphsDir) :
|
||||
print "Can not find glyphs directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
metaFile = os.path.join(bookDir,'metadata0000.dat')
|
||||
if not os.path.exists(metaFile) :
|
||||
print "Can not find metadata0000.dat in unencrypted book"
|
||||
return 1
|
||||
|
||||
svgDir = os.path.join(bookDir,'svg')
|
||||
if not os.path.exists(svgDir) :
|
||||
os.makedirs(svgDir)
|
||||
|
||||
xmlDir = os.path.join(bookDir,'xml')
|
||||
if not os.path.exists(xmlDir) :
|
||||
os.makedirs(xmlDir)
|
||||
|
||||
otherFile = os.path.join(bookDir,'other0000.dat')
|
||||
if not os.path.exists(otherFile) :
|
||||
print "Can not find other0000.dat in unencrypted book"
|
||||
return 1
|
||||
|
||||
print "Updating to color images if available"
|
||||
spath = os.path.join(bookDir,'color_img')
|
||||
dpath = os.path.join(bookDir,'img')
|
||||
filenames = os.listdir(spath)
|
||||
filenames = sorted(filenames)
|
||||
for filename in filenames:
|
||||
imgname = filename.replace('color','img')
|
||||
sfile = os.path.join(spath,filename)
|
||||
dfile = os.path.join(dpath,imgname)
|
||||
imgdata = file(sfile,'rb').read()
|
||||
file(dfile,'wb').write(imgdata)
|
||||
|
||||
print "Creating cover.jpg"
|
||||
isCover = False
|
||||
cpath = os.path.join(bookDir,'img')
|
||||
cpath = os.path.join(cpath,'img0000.jpg')
|
||||
if os.path.isfile(cpath):
|
||||
cover = file(cpath, 'rb').read()
|
||||
cpath = os.path.join(bookDir,'cover.jpg')
|
||||
file(cpath, 'wb').write(cover)
|
||||
isCover = True
|
||||
|
||||
|
||||
print 'Processing Dictionary'
|
||||
dict = Dictionary(dictFile)
|
||||
|
||||
print 'Processing Meta Data and creating OPF'
|
||||
meta_array = getMetaArray(metaFile)
|
||||
|
||||
xname = os.path.join(xmlDir, 'metadata.xml')
|
||||
metastr = ''
|
||||
for key in meta_array:
|
||||
metastr += '<meta name="' + key + '" content="' + meta_array[key] + '" />\n'
|
||||
file(xname, 'wb').write(metastr)
|
||||
|
||||
print 'Processing StyleSheet'
|
||||
# get some scaling info from metadata to use while processing styles
|
||||
fontsize = '135'
|
||||
if 'fontSize' in meta_array:
|
||||
fontsize = meta_array['fontSize']
|
||||
|
||||
# also get the size of a normal text page
|
||||
spage = '1'
|
||||
if 'firstTextPage' in meta_array:
|
||||
spage = meta_array['firstTextPage']
|
||||
pnum = int(spage)
|
||||
|
||||
# get page height and width from first text page for use in stylesheet scaling
|
||||
pname = 'page%04d.dat' % (pnum + 1)
|
||||
fname = os.path.join(pageDir,pname)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
(ph, pw) = getPageDim(flat_xml)
|
||||
if (ph == '-1') or (ph == '0') : ph = '11000'
|
||||
if (pw == '-1') or (pw == '0') : pw = '8500'
|
||||
|
||||
# print ' ', 'other0000.dat'
|
||||
xname = os.path.join(bookDir, 'style.css')
|
||||
flat_xml = convert2xml.fromData(dict, otherFile)
|
||||
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
|
||||
file(xname, 'wb').write(cssstr)
|
||||
xname = os.path.join(xmlDir, 'other0000.xml')
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
|
||||
|
||||
print 'Processing Glyphs'
|
||||
gd = GlyphDict()
|
||||
filenames = os.listdir(glyphsDir)
|
||||
filenames = sorted(filenames)
|
||||
glyfname = os.path.join(svgDir,'glyphs.svg')
|
||||
glyfile = open(glyfname, 'w')
|
||||
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
|
||||
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
|
||||
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
|
||||
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
|
||||
glyfile.write('<defs>\n')
|
||||
counter = 0
|
||||
for filename in filenames:
|
||||
# print ' ', filename
|
||||
print '.',
|
||||
fname = os.path.join(glyphsDir,filename)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
||||
|
||||
gp = GParser(flat_xml)
|
||||
for i in xrange(0, gp.count):
|
||||
path = gp.getPath(i)
|
||||
maxh, maxw = gp.getGlyphDim(i)
|
||||
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
|
||||
glyfile.write(fullpath)
|
||||
gd.addGlyph(counter * 256 + i, fullpath)
|
||||
counter += 1
|
||||
glyfile.write('</defs>\n')
|
||||
glyfile.write('</svg>\n')
|
||||
glyfile.close()
|
||||
print " "
|
||||
|
||||
# start up the html
|
||||
htmlFileName = "book.html"
|
||||
htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
htmlstr += '<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n'
|
||||
htmlstr += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n'
|
||||
htmlstr += '<head>\n'
|
||||
htmlstr += '<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n'
|
||||
htmlstr += '<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n'
|
||||
htmlstr += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
|
||||
htmlstr += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
|
||||
htmlstr += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
|
||||
htmlstr += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
|
||||
htmlstr += '<link href="style.css" rel="stylesheet" type="text/css" />\n'
|
||||
htmlstr += '</head>\n<body>\n'
|
||||
|
||||
print 'Processing Pages'
|
||||
# Books are at 1440 DPI. This is rendering at twice that size for
|
||||
# readability when rendering to the screen.
|
||||
scaledpi = 1440.0
|
||||
|
||||
svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
|
||||
svgindex += '<head>\n'
|
||||
svgindex += '<title>' + meta_array['Title'] + '</title>\n'
|
||||
svgindex += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
|
||||
svgindex += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
|
||||
svgindex += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
|
||||
svgindex += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
|
||||
svgindex += '</head>\n'
|
||||
svgindex += '<body>\n'
|
||||
|
||||
filenames = os.listdir(pageDir)
|
||||
filenames = sorted(filenames)
|
||||
numfiles = len(filenames)
|
||||
counter = 0
|
||||
|
||||
for filename in filenames:
|
||||
# print ' ', filename
|
||||
print ".",
|
||||
|
||||
fname = os.path.join(pageDir,filename)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
||||
|
||||
# first get the html
|
||||
htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
|
||||
|
||||
# now get the svg image of the page
|
||||
svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
|
||||
|
||||
if (raw) :
|
||||
pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
|
||||
svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
|
||||
else :
|
||||
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
|
||||
svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
|
||||
|
||||
|
||||
pfile.write(svgxml)
|
||||
pfile.close()
|
||||
|
||||
counter += 1
|
||||
|
||||
print " "
|
||||
|
||||
# finish up the html string and output it
|
||||
htmlstr += '</body>\n</html>\n'
|
||||
file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
|
||||
|
||||
# finish up the svg index string and output it
|
||||
svgindex += '</body>\n</html>\n'
|
||||
file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
|
||||
|
||||
# build the opf file
|
||||
opfname = os.path.join(bookDir, 'book.opf')
|
||||
opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
opfstr += '<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n'
|
||||
# adding metadata
|
||||
opfstr += ' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:title>' + meta_array['Title'] + '</dc:title>\n'
|
||||
opfstr += ' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n'
|
||||
opfstr += ' <dc:language>en</dc:language>\n'
|
||||
opfstr += ' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n'
|
||||
if isCover:
|
||||
opfstr += ' <meta name="cover" content="bookcover"/>\n'
|
||||
opfstr += ' </metadata>\n'
|
||||
opfstr += '<manifest>\n'
|
||||
opfstr += ' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
|
||||
opfstr += ' <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
|
||||
# adding image files to manifest
|
||||
filenames = os.listdir(imgDir)
|
||||
filenames = sorted(filenames)
|
||||
for filename in filenames:
|
||||
imgname, imgext = os.path.splitext(filename)
|
||||
if imgext == '.jpg':
|
||||
imgext = 'jpeg'
|
||||
if imgext == '.svg':
|
||||
imgext = 'svg+xml'
|
||||
opfstr += ' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n'
|
||||
if isCover:
|
||||
opfstr += ' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n'
|
||||
opfstr += '</manifest>\n'
|
||||
# adding spine
|
||||
opfstr += '<spine>\n <itemref idref="book" />\n</spine>\n'
|
||||
if isCover:
|
||||
opfstr += ' <guide>\n'
|
||||
opfstr += ' <reference href="cover.jpg" type="cover" title="Cover"/>\n'
|
||||
opfstr += ' </guide>\n'
|
||||
opfstr += '</package>\n'
|
||||
file(opfname, 'wb').write(opfstr)
|
||||
|
||||
print 'Processing Complete'
|
||||
|
||||
return 0
|
||||
|
||||
def usage():
|
||||
print "genbook.py generates a book from the extract Topaz Files"
|
||||
print "Usage:"
|
||||
print " genbook.py [-r] [-h [--fixed-image] <bookDir> "
|
||||
print " "
|
||||
print "Options:"
|
||||
print " -h : help - print this usage message"
|
||||
print " -r : generate raw svg files (not wrapped in xhtml)"
|
||||
print " --fixed-image : genearate any Fixed Area as an svg image in the html"
|
||||
print " "
|
||||
|
||||
|
||||
def main(argv):
|
||||
bookDir = ''
|
||||
|
||||
if len(argv) == 0:
|
||||
argv = sys.argv
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(argv[1:], "rh:",["fixed-image"])
|
||||
|
||||
except getopt.GetoptError, err:
|
||||
print str(err)
|
||||
usage()
|
||||
return 1
|
||||
|
||||
if len(opts) == 0 and len(args) == 0 :
|
||||
usage()
|
||||
return 1
|
||||
|
||||
raw = 0
|
||||
fixedimage = False
|
||||
for o, a in opts:
|
||||
if o =="-h":
|
||||
usage()
|
||||
return 0
|
||||
if o =="-r":
|
||||
raw = 1
|
||||
if o =="--fixed-image":
|
||||
fixedimage = True
|
||||
|
||||
bookDir = args[0]
|
||||
|
||||
rv = generateBook(bookDir, raw, fixedimage)
|
||||
return rv
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main(''))
|
@ -0,0 +1,312 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
from __future__ import with_statement
|
||||
import sys
|
||||
import os, csv
|
||||
import binascii
|
||||
import zlib
|
||||
import re
|
||||
from struct import pack, unpack, unpack_from
|
||||
|
||||
class DrmException(Exception):
|
||||
pass
|
||||
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
global charMap2
|
||||
global charMap3
|
||||
global charMap4
|
||||
|
||||
if sys.platform.startswith('win'):
|
||||
from k4pcutils import openKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
|
||||
if sys.platform.startswith('darwin'):
|
||||
from k4mutils import openKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
|
||||
|
||||
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
|
||||
charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
|
||||
charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
|
||||
|
||||
# crypto digestroutines
|
||||
import hashlib
|
||||
|
||||
def MD5(message):
|
||||
ctx = hashlib.md5()
|
||||
ctx.update(message)
|
||||
return ctx.digest()
|
||||
|
||||
def SHA1(message):
|
||||
ctx = hashlib.sha1()
|
||||
ctx.update(message)
|
||||
return ctx.digest()
|
||||
|
||||
|
||||
# Encode the bytes in data with the characters in map
|
||||
def encode(data, map):
|
||||
result = ""
|
||||
for char in data:
|
||||
value = ord(char)
|
||||
Q = (value ^ 0x80) // len(map)
|
||||
R = value % len(map)
|
||||
result += map[Q]
|
||||
result += map[R]
|
||||
return result
|
||||
|
||||
# Hash the bytes in data and then encode the digest with the characters in map
|
||||
def encodeHash(data,map):
|
||||
return encode(MD5(data),map)
|
||||
|
||||
# Decode the string in data with the characters in map. Returns the decoded bytes
|
||||
def decode(data,map):
|
||||
result = ""
|
||||
for i in range (0,len(data)-1,2):
|
||||
high = map.find(data[i])
|
||||
low = map.find(data[i+1])
|
||||
if (high == -1) or (low == -1) :
|
||||
break
|
||||
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
|
||||
result += pack("B",value)
|
||||
return result
|
||||
|
||||
|
||||
# Parse the Kindle.info file and return the records as a list of key-values
|
||||
def parseKindleInfo(kInfoFile):
|
||||
DB = {}
|
||||
infoReader = openKindleInfo(kInfoFile)
|
||||
infoReader.read(1)
|
||||
data = infoReader.read()
|
||||
if sys.platform.startswith('win'):
|
||||
items = data.split('{')
|
||||
else :
|
||||
items = data.split('[')
|
||||
for item in items:
|
||||
splito = item.split(':')
|
||||
DB[splito[0]] =splito[1]
|
||||
return DB
|
||||
|
||||
# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). Return the decoded and decrypted record
|
||||
def getKindleInfoValueForHash(hashedKey):
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
global charMap2
|
||||
encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
|
||||
if sys.platform.startswith('win'):
|
||||
return CryptUnprotectData(encryptedValue,"")
|
||||
else:
|
||||
cleartext = CryptUnprotectData(encryptedValue)
|
||||
return decode(cleartext, charMap1)
|
||||
|
||||
# Get a record from the Kindle.info file for the string in "key" (plaintext). Return the decoded and decrypted record
|
||||
def getKindleInfoValueForKey(key):
|
||||
global charMap2
|
||||
return getKindleInfoValueForHash(encodeHash(key,charMap2))
|
||||
|
||||
# Find if the original string for a hashed/encoded string is known. If so return the original string othwise return an empty string.
|
||||
def findNameForHash(hash):
|
||||
global charMap2
|
||||
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
|
||||
result = ""
|
||||
for name in names:
|
||||
if hash == encodeHash(name, charMap2):
|
||||
result = name
|
||||
break
|
||||
return result
|
||||
|
||||
# Print all the records from the kindle.info file (option -i)
|
||||
def printKindleInfo():
|
||||
for record in kindleDatabase:
|
||||
name = findNameForHash(record)
|
||||
if name != "" :
|
||||
print (name)
|
||||
print ("--------------------------")
|
||||
else :
|
||||
print ("Unknown Record")
|
||||
print getKindleInfoValueForHash(record)
|
||||
print "\n"
|
||||
|
||||
#
|
||||
# PID generation routines
|
||||
#
|
||||
|
||||
# Returns two bit at offset from a bit field
|
||||
def getTwoBitsFromBitField(bitField,offset):
|
||||
byteNumber = offset // 4
|
||||
bitPosition = 6 - 2*(offset % 4)
|
||||
return ord(bitField[byteNumber]) >> bitPosition & 3
|
||||
|
||||
# Returns the six bits at offset from a bit field
|
||||
def getSixBitsFromBitField(bitField,offset):
|
||||
offset *= 3
|
||||
value = (getTwoBitsFromBitField(bitField,offset) <<4) + (getTwoBitsFromBitField(bitField,offset+1) << 2) +getTwoBitsFromBitField(bitField,offset+2)
|
||||
return value
|
||||
|
||||
# 8 bits to six bits encoding from hash to generate PID string
|
||||
def encodePID(hash):
|
||||
global charMap3
|
||||
PID = ""
|
||||
for position in range (0,8):
|
||||
PID += charMap3[getSixBitsFromBitField(hash,position)]
|
||||
return PID
|
||||
|
||||
# Encryption table used to generate the device PID
|
||||
def generatePidEncryptionTable() :
|
||||
table = []
|
||||
for counter1 in range (0,0x100):
|
||||
value = counter1
|
||||
for counter2 in range (0,8):
|
||||
if (value & 1 == 0) :
|
||||
value = value >> 1
|
||||
else :
|
||||
value = value >> 1
|
||||
value = value ^ 0xEDB88320
|
||||
table.append(value)
|
||||
return table
|
||||
|
||||
# Seed value used to generate the device PID
|
||||
def generatePidSeed(table,dsn) :
|
||||
value = 0
|
||||
for counter in range (0,4) :
|
||||
index = (ord(dsn[counter]) ^ value) &0xFF
|
||||
value = (value >> 8) ^ table[index]
|
||||
return value
|
||||
|
||||
# Generate the device PID
|
||||
def generateDevicePID(table,dsn,nbRoll):
|
||||
global charMap4
|
||||
seed = generatePidSeed(table,dsn)
|
||||
pidAscii = ""
|
||||
pid = [(seed >>24) &0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF,(seed>>24) & 0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF]
|
||||
index = 0
|
||||
for counter in range (0,nbRoll):
|
||||
pid[index] = pid[index] ^ ord(dsn[counter])
|
||||
index = (index+1) %8
|
||||
for counter in range (0,8):
|
||||
index = ((((pid[counter] >>5) & 3) ^ pid[counter]) & 0x1f) + (pid[counter] >> 7)
|
||||
pidAscii += charMap4[index]
|
||||
return pidAscii
|
||||
|
||||
def crc32(s):
|
||||
return (~binascii.crc32(s,-1))&0xFFFFFFFF
|
||||
|
||||
# convert from 8 digit PID to 10 digit PID with checksum
|
||||
def checksumPid(s):
|
||||
global charMap4
|
||||
crc = crc32(s)
|
||||
crc = crc ^ (crc >> 16)
|
||||
res = s
|
||||
l = len(charMap4)
|
||||
for i in (0,1):
|
||||
b = crc & 0xff
|
||||
pos = (b // l) ^ (b % l)
|
||||
res += charMap4[pos%l]
|
||||
crc >>= 8
|
||||
return res
|
||||
|
||||
|
||||
# old kindle serial number to fixed pid
|
||||
def pidFromSerial(s, l):
|
||||
global charMap4
|
||||
crc = crc32(s)
|
||||
arr1 = [0]*l
|
||||
for i in xrange(len(s)):
|
||||
arr1[i%l] ^= ord(s[i])
|
||||
crc_bytes = [crc >> 24 & 0xff, crc >> 16 & 0xff, crc >> 8 & 0xff, crc & 0xff]
|
||||
for i in xrange(l):
|
||||
arr1[i] ^= crc_bytes[i&3]
|
||||
pid = ""
|
||||
for i in xrange(l):
|
||||
b = arr1[i] & 0xff
|
||||
pid+=charMap4[(b >> 7) + ((b >> 5 & 3) ^ (b & 0x1f))]
|
||||
return pid
|
||||
|
||||
|
||||
# Parse the EXTH header records and use the Kindle serial number to calculate the book pid.
|
||||
def getKindlePid(pidlst, rec209, token, serialnum):
|
||||
|
||||
if rec209 != None:
|
||||
# Compute book PID
|
||||
pidHash = SHA1(serialnum+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# compute fixed pid for old pre 2.5 firmware update pid as well
|
||||
bookPID = pidFromSerial(serialnum, 7) + "*"
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
return pidlst
|
||||
|
||||
|
||||
# Parse the EXTH header records and parse the Kindleinfo
|
||||
# file to calculate the book pid.
|
||||
|
||||
def getK4Pids(pidlst, rec209, token, kInfoFile=None):
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
kindleDatabase = None
|
||||
try:
|
||||
kindleDatabase = parseKindleInfo(kInfoFile)
|
||||
except Exception, message:
|
||||
print(message)
|
||||
pass
|
||||
|
||||
if kindleDatabase == None :
|
||||
return pidlst
|
||||
|
||||
# Get the Mazama Random number
|
||||
MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
|
||||
|
||||
# Get the HDD serial
|
||||
encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
|
||||
|
||||
# Get the current user name
|
||||
encodedUsername = encodeHash(GetUserName(),charMap1)
|
||||
|
||||
# concat, hash and encode to calculate the DSN
|
||||
DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
|
||||
|
||||
# Compute the device PID (for which I can tell, is used for nothing).
|
||||
table = generatePidEncryptionTable()
|
||||
devicePID = generateDevicePID(table,DSN,4)
|
||||
devicePID = checksumPid(devicePID)
|
||||
pidlst.append(devicePID)
|
||||
|
||||
# Compute book PID
|
||||
if rec209 == None:
|
||||
print "\nNo EXTH record type 209 - Perhaps not a K4 file?"
|
||||
return pidlst
|
||||
|
||||
# Get the kindle account token
|
||||
kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
|
||||
|
||||
# book pid
|
||||
pidHash = SHA1(DSN+kindleAccountToken+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# variant 1
|
||||
pidHash = SHA1(kindleAccountToken+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# variant 2
|
||||
pidHash = SHA1(DSN+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
return pidlst
|
||||
|
||||
def getPidList(md1, md2, k4, pids, serials, kInfoFiles):
|
||||
pidlst = []
|
||||
if k4:
|
||||
pidlst = getK4Pids(pidlst, md1, md2)
|
||||
for infoFile in kInfoFiles:
|
||||
pidlst = getK4Pids(pidlst, md1, md2, infoFile)
|
||||
for serialnum in serials:
|
||||
pidlst = getKindlePid(pidlst, md1, md2, serialnum)
|
||||
for pid in pids:
|
||||
pidlst.append(pid)
|
||||
return pidlst
|
@ -0,0 +1,434 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
import os, csv, getopt
|
||||
import zlib, zipfile, tempfile, shutil
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
class TpzDRMError(Exception):
|
||||
pass
|
||||
|
||||
# local support routines
|
||||
import kgenpids
|
||||
import genbook
|
||||
#
|
||||
# Utility routines
|
||||
#
|
||||
|
||||
# Get a 7 bit encoded number from file
|
||||
def bookReadEncodedNumber(fo):
|
||||
flag = False
|
||||
data = ord(fo.read(1))
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
data = ord(fo.read(1))
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
data = ord(fo.read(1))
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
# Get a length prefixed string from file
|
||||
def bookReadString(fo):
|
||||
stringLength = bookReadEncodedNumber(fo)
|
||||
return unpack(str(stringLength)+"s",fo.read(stringLength))[0]
|
||||
|
||||
#
|
||||
# crypto routines
|
||||
#
|
||||
|
||||
# Context initialisation for the Topaz Crypto
|
||||
def topazCryptoInit(key):
|
||||
ctx1 = 0x0CAFFE19E
|
||||
for keyChar in key:
|
||||
keyByte = ord(keyChar)
|
||||
ctx2 = ctx1
|
||||
ctx1 = ((((ctx1 >>2) * (ctx1 >>7))&0xFFFFFFFF) ^ (keyByte * keyByte * 0x0F902007)& 0xFFFFFFFF )
|
||||
return [ctx1,ctx2]
|
||||
|
||||
# decrypt data with the context prepared by topazCryptoInit()
|
||||
def topazCryptoDecrypt(data, ctx):
|
||||
ctx1 = ctx[0]
|
||||
ctx2 = ctx[1]
|
||||
plainText = ""
|
||||
for dataChar in data:
|
||||
dataByte = ord(dataChar)
|
||||
m = (dataByte ^ ((ctx1 >> 3) &0xFF) ^ ((ctx2<<3) & 0xFF)) &0xFF
|
||||
ctx2 = ctx1
|
||||
ctx1 = (((ctx1 >> 2) * (ctx1 >> 7)) &0xFFFFFFFF) ^((m * m * 0x0F902007) &0xFFFFFFFF)
|
||||
plainText += chr(m)
|
||||
return plainText
|
||||
|
||||
# Decrypt data with the PID
|
||||
def decryptRecord(data,PID):
|
||||
ctx = topazCryptoInit(PID)
|
||||
return topazCryptoDecrypt(data, ctx)
|
||||
|
||||
# Try to decrypt a dkey record (contains the bookPID)
|
||||
def decryptDkeyRecord(data,PID):
|
||||
record = decryptRecord(data,PID)
|
||||
fields = unpack("3sB8sB8s3s",record)
|
||||
if fields[0] != "PID" or fields[5] != "pid" :
|
||||
raise TpzDRMError("Didn't find PID magic numbers in record")
|
||||
elif fields[1] != 8 or fields[3] != 8 :
|
||||
raise TpzDRMError("Record didn't contain correct length fields")
|
||||
elif fields[2] != PID :
|
||||
raise TpzDRMError("Record didn't contain PID")
|
||||
return fields[4]
|
||||
|
||||
# Decrypt all dkey records (contain the book PID)
|
||||
def decryptDkeyRecords(data,PID):
|
||||
nbKeyRecords = ord(data[0])
|
||||
records = []
|
||||
data = data[1:]
|
||||
for i in range (0,nbKeyRecords):
|
||||
length = ord(data[0])
|
||||
try:
|
||||
key = decryptDkeyRecord(data[1:length+1],PID)
|
||||
records.append(key)
|
||||
except TpzDRMError:
|
||||
pass
|
||||
data = data[1+length:]
|
||||
if len(records) == 0:
|
||||
raise TpzDRMError("BookKey Not Found")
|
||||
return records
|
||||
|
||||
|
||||
class TopazBook:
|
||||
def __init__(self, filename, outdir):
|
||||
self.fo = file(filename, 'rb')
|
||||
self.outdir = outdir
|
||||
self.bookPayloadOffset = 0
|
||||
self.bookHeaderRecords = {}
|
||||
self.bookMetadata = {}
|
||||
self.bookKey = None
|
||||
magic = unpack("4s",self.fo.read(4))[0]
|
||||
if magic != 'TPZ0':
|
||||
raise TpzDRMError("Parse Error : Invalid Header, not a Topaz file")
|
||||
self.parseTopazHeaders()
|
||||
self.parseMetadata()
|
||||
|
||||
def parseTopazHeaders(self):
|
||||
def bookReadHeaderRecordData():
|
||||
# Read and return the data of one header record at the current book file position
|
||||
# [[offset,decompressedLength,compressedLength],...]
|
||||
nbValues = bookReadEncodedNumber(self.fo)
|
||||
values = []
|
||||
for i in range (0,nbValues):
|
||||
values.append([bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo)])
|
||||
return values
|
||||
def parseTopazHeaderRecord():
|
||||
# Read and parse one header record at the current book file position and return the associated data
|
||||
# [[offset,decompressedLength,compressedLength],...]
|
||||
if ord(self.fo.read(1)) != 0x63:
|
||||
raise TpzDRMError("Parse Error : Invalid Header")
|
||||
tag = bookReadString(self.fo)
|
||||
record = bookReadHeaderRecordData()
|
||||
return [tag,record]
|
||||
nbRecords = bookReadEncodedNumber(self.fo)
|
||||
for i in range (0,nbRecords):
|
||||
result = parseTopazHeaderRecord()
|
||||
# print result[0], result[1]
|
||||
self.bookHeaderRecords[result[0]] = result[1]
|
||||
if ord(self.fo.read(1)) != 0x64 :
|
||||
raise TpzDRMError("Parse Error : Invalid Header")
|
||||
self.bookPayloadOffset = self.fo.tell()
|
||||
|
||||
def parseMetadata(self):
|
||||
# Parse the metadata record from the book payload and return a list of [key,values]
|
||||
self.fo.seek(self.bookPayloadOffset + self.bookHeaderRecords["metadata"][0][0])
|
||||
tag = bookReadString(self.fo)
|
||||
if tag != "metadata" :
|
||||
raise TpzDRMError("Parse Error : Record Names Don't Match")
|
||||
flags = ord(self.fo.read(1))
|
||||
nbRecords = ord(self.fo.read(1))
|
||||
for i in range (0,nbRecords) :
|
||||
record = [bookReadString(self.fo), bookReadString(self.fo)]
|
||||
self.bookMetadata[record[0]] = record[1]
|
||||
return self.bookMetadata
|
||||
|
||||
def getPIDMetaInfo(self):
|
||||
keysRecord = None
|
||||
KeysRecordRecord = None
|
||||
if 'keys' in self.bookMetadata:
|
||||
keysRecord = self.bookMetadata['keys']
|
||||
keysRecordRecord = self.bookMetadata[keysRecord]
|
||||
return keysRecord, keysRecordRecord
|
||||
|
||||
def getBookTitle(self):
|
||||
title = ''
|
||||
if 'Title' in self.bookMetadata:
|
||||
title = self.bookMetadata['Title']
|
||||
return title
|
||||
|
||||
def setBookKey(self, key):
|
||||
self.bookKey = key
|
||||
|
||||
def getBookPayloadRecord(self, name, index):
|
||||
# Get a record in the book payload, given its name and index.
|
||||
# decrypted and decompressed if necessary
|
||||
encrypted = False
|
||||
compressed = False
|
||||
try:
|
||||
recordOffset = self.bookHeaderRecords[name][index][0]
|
||||
except:
|
||||
raise TpzDRMError("Parse Error : Invalid Record, record not found")
|
||||
|
||||
self.fo.seek(self.bookPayloadOffset + recordOffset)
|
||||
|
||||
tag = bookReadString(self.fo)
|
||||
if tag != name :
|
||||
raise TpzDRMError("Parse Error : Invalid Record, record name doesn't match")
|
||||
|
||||
recordIndex = bookReadEncodedNumber(self.fo)
|
||||
if recordIndex < 0 :
|
||||
encrypted = True
|
||||
recordIndex = -recordIndex -1
|
||||
|
||||
if recordIndex != index :
|
||||
raise TpzDRMError("Parse Error : Invalid Record, index doesn't match")
|
||||
|
||||
if (self.bookHeaderRecords[name][index][2] > 0):
|
||||
compressed = True
|
||||
record = self.fo.read(self.bookHeaderRecords[name][index][2])
|
||||
else:
|
||||
record = self.fo.read(self.bookHeaderRecords[name][index][1])
|
||||
|
||||
if encrypted:
|
||||
if self.bookKey:
|
||||
ctx = topazCryptoInit(self.bookKey)
|
||||
record = topazCryptoDecrypt(record,ctx)
|
||||
else :
|
||||
raise TpzDRMError("Error: Attempt to decrypt without bookKey")
|
||||
|
||||
if compressed:
|
||||
record = zlib.decompress(record)
|
||||
|
||||
return record
|
||||
|
||||
def processBook(self, pidlst):
|
||||
raw = 0
|
||||
fixedimage=True
|
||||
try:
|
||||
keydata = self.getBookPayloadRecord('dkey', 0)
|
||||
except TpzDRMError, e:
|
||||
print "no dkey record found, book may not be encrypted"
|
||||
print "attempting to extrct files without a book key"
|
||||
self.createBookDirectory()
|
||||
self.extractFiles()
|
||||
print "Successfully Extracted Topaz contents"
|
||||
rv = genbook.generateBook(self.outdir, raw, fixedimage)
|
||||
if rv == 0:
|
||||
print "\nBook Successfully generated"
|
||||
return rv
|
||||
|
||||
# try each pid to decode the file
|
||||
bookKey = None
|
||||
for pid in pidlst:
|
||||
# use 8 digit pids here
|
||||
pid = pid[0:8]
|
||||
print "\nTrying: ", pid
|
||||
bookKeys = []
|
||||
data = keydata
|
||||
try:
|
||||
bookKeys+=decryptDkeyRecords(data,pid)
|
||||
except TpzDRMError, e:
|
||||
pass
|
||||
else:
|
||||
bookKey = bookKeys[0]
|
||||
print "Book Key Found!"
|
||||
break
|
||||
|
||||
if not bookKey:
|
||||
raise TpzDRMError('Decryption Unsucessful; No valid pid found')
|
||||
|
||||
self.setBookKey(bookKey)
|
||||
self.createBookDirectory()
|
||||
self.extractFiles()
|
||||
print "Successfully Extracted Topaz contents"
|
||||
rv = genbook.generateBook(self.outdir, raw, fixedimage)
|
||||
if rv == 0:
|
||||
print "\nBook Successfully generated"
|
||||
return rv
|
||||
|
||||
def createBookDirectory(self):
|
||||
outdir = self.outdir
|
||||
# create output directory structure
|
||||
if not os.path.exists(outdir):
|
||||
os.makedirs(outdir)
|
||||
destdir = os.path.join(outdir,'img')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'color_img')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'page')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'glyphs')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
|
||||
def extractFiles(self):
|
||||
outdir = self.outdir
|
||||
for headerRecord in self.bookHeaderRecords:
|
||||
name = headerRecord
|
||||
if name != "dkey" :
|
||||
ext = '.dat'
|
||||
if name == 'img' : ext = '.jpg'
|
||||
if name == 'color' : ext = '.jpg'
|
||||
print "\nProcessing Section: %s " % name
|
||||
for index in range (0,len(self.bookHeaderRecords[name])) :
|
||||
fnum = "%04d" % index
|
||||
fname = name + fnum + ext
|
||||
destdir = outdir
|
||||
if name == 'img':
|
||||
destdir = os.path.join(outdir,'img')
|
||||
if name == 'color':
|
||||
destdir = os.path.join(outdir,'color_img')
|
||||
if name == 'page':
|
||||
destdir = os.path.join(outdir,'page')
|
||||
if name == 'glyphs':
|
||||
destdir = os.path.join(outdir,'glyphs')
|
||||
outputFile = os.path.join(destdir,fname)
|
||||
print ".",
|
||||
record = self.getBookPayloadRecord(name,index)
|
||||
if record != '':
|
||||
file(outputFile, 'wb').write(record)
|
||||
print " "
|
||||
|
||||
|
||||
def zipUpDir(myzip, tempdir,localname):
|
||||
currentdir = tempdir
|
||||
if localname != "":
|
||||
currentdir = os.path.join(currentdir,localname)
|
||||
list = os.listdir(currentdir)
|
||||
for file in list:
|
||||
afilename = file
|
||||
localfilePath = os.path.join(localname, afilename)
|
||||
realfilePath = os.path.join(currentdir,file)
|
||||
if os.path.isfile(realfilePath):
|
||||
myzip.write(realfilePath, localfilePath)
|
||||
elif os.path.isdir(realfilePath):
|
||||
zipUpDir(myzip, tempdir, localfilePath)
|
||||
|
||||
|
||||
def usage(progname):
|
||||
print "Removes DRM protection from Topaz ebooks and extract the contents"
|
||||
print "Usage:"
|
||||
print " %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir> " % progname
|
||||
|
||||
|
||||
# Main
|
||||
def main(argv=sys.argv):
|
||||
progname = os.path.basename(argv[0])
|
||||
k4 = False
|
||||
pids = []
|
||||
serials = []
|
||||
kInfoFiles = []
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
|
||||
except getopt.GetoptError, err:
|
||||
print str(err)
|
||||
usage(progname)
|
||||
return 1
|
||||
if len(args)<2:
|
||||
usage(progname)
|
||||
return 1
|
||||
|
||||
for o, a in opts:
|
||||
if o == "-k":
|
||||
if a == None :
|
||||
print "Invalid parameter for -k"
|
||||
return 1
|
||||
kInfoFiles.append(a)
|
||||
if o == "-p":
|
||||
if a == None :
|
||||
print "Invalid parameter for -p"
|
||||
return 1
|
||||
pids = a.split(',')
|
||||
if o == "-s":
|
||||
if a == None :
|
||||
print "Invalid parameter for -s"
|
||||
return 1
|
||||
serials = a.split(',')
|
||||
k4 = True
|
||||
|
||||
infile = args[0]
|
||||
outdir = args[1]
|
||||
|
||||
if not os.path.isfile(infile):
|
||||
print "Input File Does Not Exist"
|
||||
return 1
|
||||
|
||||
bookname = os.path.splitext(os.path.basename(infile))[0]
|
||||
tempdir = tempfile.mkdtemp()
|
||||
|
||||
tb = TopazBook(infile, tempdir)
|
||||
title = tb.getBookTitle()
|
||||
print "Processing Book: ", title
|
||||
keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
|
||||
pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles)
|
||||
|
||||
try:
|
||||
tb.processBook(pidlst)
|
||||
except TpzDRMError, e:
|
||||
print str(e)
|
||||
print " Creating DeBug Full Zip Archive of Book"
|
||||
zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
|
||||
myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
zipUpDir(myzip, tempdir, '')
|
||||
myzip.close()
|
||||
return 1
|
||||
|
||||
print " Creating HTML ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
|
||||
myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
|
||||
myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
|
||||
if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
|
||||
myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
|
||||
myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
|
||||
zipUpDir(myzip1, tempdir, 'img')
|
||||
myzip1.close()
|
||||
|
||||
print " Creating SVG ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
|
||||
myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
|
||||
zipUpDir(myzip2, tempdir, 'svg')
|
||||
zipUpDir(myzip2, tempdir, 'img')
|
||||
myzip2.close()
|
||||
|
||||
print " Creating XML ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
|
||||
myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
targetdir = os.path.join(tempdir,'xml')
|
||||
zipUpDir(myzip3, targetdir, '')
|
||||
zipUpDir(myzip3, tempdir, 'img')
|
||||
myzip3.close()
|
||||
|
||||
shutil.rmtree(tempdir)
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
|
@ -0,0 +1,36 @@
|
||||
Inept PDF Plugin - ineptpdf_vXX_plugin.zip
|
||||
Requires Calibre version 0.6.44 or higher.
|
||||
|
||||
All credit given to IHeartCabbages for the original standalone scripts.
|
||||
I had the much easier job of converting them to a Calibre plugin.
|
||||
|
||||
This plugin is meant to decrypt Adobe Digital Edition PDFs that are protected with Adobe's Adept encryption. It is meant to function without having to install any dependencies... other than having Calibre installed, of course. It will still work if you have Python, PyCrypto and/or OpenSSL already installed, but they aren't necessary.
|
||||
|
||||
Installation:
|
||||
|
||||
Go to Calibre's Preferences page... click on the Plugins button. Use the file dialog button to select the plugin's zip file (ineptpdf_vXX_plugin.zip) and click the 'Add' button. you're done.
|
||||
|
||||
Configuration:
|
||||
|
||||
When first run, the plugin will attempt to find your Adobe Digital Editions installation (on Windows and Mac OS's). If successful, it will create an 'adeptkey.der' file and save it in Calibre's configuration directory. It will use that file on subsequent runs. If there are already '*.der' files in the directory, the plugin won't attempt to
|
||||
find the Adobe Digital Editions installation installation.
|
||||
|
||||
So if you have Adobe Digital Editions installation installed on the same machine as Calibre... you are ready to go. If not... keep reading.
|
||||
|
||||
If you already have keyfiles generated with I <3 Cabbages' ineptkey.pyw script, you can put those keyfiles in Calibre's configuration directory. The easiest way to find the correct directory is to go to Calibre's Preferences page... click on the 'Miscellaneous' button (looks like a gear), and then click the 'Open Calibre configuration directory' button. Paste your keyfiles in there. Just make sure that
|
||||
they have different names and are saved with the '.der' extension (like the ineptkey script produces). This directory isn't touched when upgrading Calibre, so it's quite safe to leave them there.
|
||||
|
||||
Since there is no Linux version of Adobe Digital Editions, Linux users will have to obtain a keyfile through other methods and put the file in Calibre's configuration directory.
|
||||
|
||||
All keyfiles with a '.der' extension found in Calibre's configuration directory will be used to attempt to decrypt a book.
|
||||
|
||||
** NOTE ** There is no plugin customization data for the Inept PDF plugin.
|
||||
|
||||
Troubleshooting:
|
||||
|
||||
If you find that it's not working for you (imported PDFs still have DRM), you can save a lot of time and trouble by trying to add the PDF to Calibre with the command line tools. This will print out a lot of helpful debugging info that can be copied into any online help requests. I'm going to ask you to do it first, anyway, so you might
|
||||
as well get used to it. ;)
|
||||
|
||||
Open a command prompt (terminal) and change to the directory where the ebook you're trying to import resides. Then type the command "calibredb add your_ebook.pdf". Don't type the quotes and obviously change the 'your_ebook.pdf' to whatever the filename of your book is. Copy the resulting output and paste it into any online help request you make.
|
||||
|
||||
** Note: the Mac version of Calibre doesn't install the command line tools by default. If you go to the 'Preferences' page and click on the miscellaneous button, you'll see the option to install the command line tools.
|
Binary file not shown.
@ -0,0 +1,31 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
|
||||
def load_pycrypto():
|
||||
try :
|
||||
from Crypto.Cipher import DES as _DES
|
||||
except:
|
||||
return None
|
||||
|
||||
class DES(object):
|
||||
def __init__(self, key):
|
||||
if len(key) != 8 :
|
||||
raise Error('DES improper key used')
|
||||
self.key = key
|
||||
self._des = _DES.new(key,_DES.MODE_ECB)
|
||||
def desdecrypt(self, data):
|
||||
return self._des.decrypt(data)
|
||||
def decrypt(self, data):
|
||||
if not data:
|
||||
return ''
|
||||
i = 0
|
||||
result = []
|
||||
while i < len(data):
|
||||
block = data[i:i+8]
|
||||
processed_block = self.desdecrypt(block)
|
||||
result.append(processed_block)
|
||||
i += 8
|
||||
return ''.join(result)
|
||||
return DES
|
||||
|
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@ -1,51 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Secret-key encryption algorithms.
|
||||
|
||||
Secret-key encryption algorithms transform plaintext in some way that
|
||||
is dependent on a key, producing ciphertext. This transformation can
|
||||
easily be reversed, if (and, hopefully, only if) one knows the key.
|
||||
|
||||
The encryption modules here all support the interface described in PEP
|
||||
272, "API for Block Encryption Algorithms".
|
||||
|
||||
If you don't know which algorithm to choose, use AES because it's
|
||||
standard and has undergone a fair bit of examination.
|
||||
|
||||
Crypto.Cipher.AES Advanced Encryption Standard
|
||||
Crypto.Cipher.ARC2 Alleged RC2
|
||||
Crypto.Cipher.ARC4 Alleged RC4
|
||||
Crypto.Cipher.Blowfish
|
||||
Crypto.Cipher.CAST
|
||||
Crypto.Cipher.DES The Data Encryption Standard. Very commonly used
|
||||
in the past, but today its 56-bit keys are too small.
|
||||
Crypto.Cipher.DES3 Triple DES.
|
||||
Crypto.Cipher.XOR The simple XOR cipher.
|
||||
"""
|
||||
|
||||
__all__ = ['AES', 'ARC2', 'ARC4',
|
||||
'Blowfish', 'CAST', 'DES', 'DES3',
|
||||
'XOR'
|
||||
]
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
|
@ -1,46 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Python Cryptography Toolkit
|
||||
|
||||
A collection of cryptographic modules implementing various algorithms
|
||||
and protocols.
|
||||
|
||||
Subpackages:
|
||||
Crypto.Cipher Secret-key encryption algorithms (AES, DES, ARC4)
|
||||
Crypto.Hash Hashing algorithms (MD5, SHA, HMAC)
|
||||
Crypto.Protocol Cryptographic protocols (Chaffing, all-or-nothing
|
||||
transform). This package does not contain any
|
||||
network protocols.
|
||||
Crypto.PublicKey Public-key encryption and signature algorithms
|
||||
(RSA, DSA)
|
||||
Crypto.Util Various useful modules and functions (long-to-string
|
||||
conversion, random number generation, number
|
||||
theoretic functions)
|
||||
"""
|
||||
|
||||
__all__ = ['Cipher', 'Hash', 'Protocol', 'PublicKey', 'Util']
|
||||
|
||||
__version__ = '2.3' # See also below and setup.py
|
||||
__revision__ = "$Id$"
|
||||
|
||||
# New software should look at this instead of at __version__ above.
|
||||
version_info = (2, 1, 0, 'final', 0) # See also above and setup.py
|
||||
|
@ -1,57 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# pct_warnings.py : PyCrypto warnings file
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
#
|
||||
# Base classes. All our warnings inherit from one of these in order to allow
|
||||
# the user to specifically filter them.
|
||||
#
|
||||
|
||||
class CryptoWarning(Warning):
|
||||
"""Base class for PyCrypto warnings"""
|
||||
|
||||
class CryptoDeprecationWarning(DeprecationWarning, CryptoWarning):
|
||||
"""Base PyCrypto DeprecationWarning class"""
|
||||
|
||||
class CryptoRuntimeWarning(RuntimeWarning, CryptoWarning):
|
||||
"""Base PyCrypto RuntimeWarning class"""
|
||||
|
||||
#
|
||||
# Warnings that we might actually use
|
||||
#
|
||||
|
||||
class RandomPool_DeprecationWarning(CryptoDeprecationWarning):
|
||||
"""Issued when Crypto.Util.randpool.RandomPool is instantiated."""
|
||||
|
||||
class ClockRewindWarning(CryptoRuntimeWarning):
|
||||
"""Warning for when the system clock moves backwards."""
|
||||
|
||||
class GetRandomNumber_DeprecationWarning(CryptoDeprecationWarning):
|
||||
"""Issued when Crypto.Util.number.getRandomNumber is invoked."""
|
||||
|
||||
# By default, we want this warning to be shown every time we compensate for
|
||||
# clock rewinding.
|
||||
import warnings as _warnings
|
||||
_warnings.filterwarnings('always', category=ClockRewindWarning, append=1)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
Binary file not shown.
Binary file not shown.
@ -1,51 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Secret-key encryption algorithms.
|
||||
|
||||
Secret-key encryption algorithms transform plaintext in some way that
|
||||
is dependent on a key, producing ciphertext. This transformation can
|
||||
easily be reversed, if (and, hopefully, only if) one knows the key.
|
||||
|
||||
The encryption modules here all support the interface described in PEP
|
||||
272, "API for Block Encryption Algorithms".
|
||||
|
||||
If you don't know which algorithm to choose, use AES because it's
|
||||
standard and has undergone a fair bit of examination.
|
||||
|
||||
Crypto.Cipher.AES Advanced Encryption Standard
|
||||
Crypto.Cipher.ARC2 Alleged RC2
|
||||
Crypto.Cipher.ARC4 Alleged RC4
|
||||
Crypto.Cipher.Blowfish
|
||||
Crypto.Cipher.CAST
|
||||
Crypto.Cipher.DES The Data Encryption Standard. Very commonly used
|
||||
in the past, but today its 56-bit keys are too small.
|
||||
Crypto.Cipher.DES3 Triple DES.
|
||||
Crypto.Cipher.XOR The simple XOR cipher.
|
||||
"""
|
||||
|
||||
__all__ = ['AES', 'ARC2', 'ARC4',
|
||||
'Blowfish', 'CAST', 'DES', 'DES3',
|
||||
'XOR'
|
||||
]
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
|
Binary file not shown.
@ -1,44 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Hashing algorithms
|
||||
|
||||
Hash functions take arbitrary strings as input, and produce an output
|
||||
of fixed size that is dependent on the input; it should never be
|
||||
possible to derive the input data given only the hash function's
|
||||
output. Hash functions can be used simply as a checksum, or, in
|
||||
association with a public-key algorithm, can be used to implement
|
||||
digital signatures.
|
||||
|
||||
The hashing modules here all support the interface described in PEP
|
||||
247, "API for Cryptographic Hash Functions".
|
||||
|
||||
Submodules:
|
||||
Crypto.Hash.HMAC RFC 2104: Keyed-Hashing for Message Authentication
|
||||
Crypto.Hash.MD2
|
||||
Crypto.Hash.MD4
|
||||
Crypto.Hash.MD5
|
||||
Crypto.Hash.RIPEMD160
|
||||
Crypto.Hash.SHA
|
||||
"""
|
||||
|
||||
__all__ = ['HMAC', 'MD2', 'MD4', 'MD5', 'RIPEMD', 'RIPEMD160', 'SHA', 'SHA256']
|
||||
__revision__ = "$Id$"
|
||||
|
@ -1,184 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# PublicKey/RSA.py : RSA public key primitive
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""RSA public-key cryptography algorithm."""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
__all__ = ['generate', 'construct', 'error']
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
from Crypto.PublicKey import _RSA, _slowmath, pubkey
|
||||
from Crypto import Random
|
||||
|
||||
try:
|
||||
from Crypto.PublicKey import _fastmath
|
||||
except ImportError:
|
||||
_fastmath = None
|
||||
|
||||
class _RSAobj(pubkey.pubkey):
|
||||
keydata = ['n', 'e', 'd', 'p', 'q', 'u']
|
||||
|
||||
def __init__(self, implementation, key):
|
||||
self.implementation = implementation
|
||||
self.key = key
|
||||
|
||||
def __getattr__(self, attrname):
|
||||
if attrname in self.keydata:
|
||||
# For backward compatibility, allow the user to get (not set) the
|
||||
# RSA key parameters directly from this object.
|
||||
return getattr(self.key, attrname)
|
||||
else:
|
||||
raise AttributeError("%s object has no %r attribute" % (self.__class__.__name__, attrname,))
|
||||
|
||||
def _encrypt(self, c, K):
|
||||
return (self.key._encrypt(c),)
|
||||
|
||||
def _decrypt(self, c):
|
||||
#(ciphertext,) = c
|
||||
(ciphertext,) = c[:1] # HACK - We should use the previous line
|
||||
# instead, but this is more compatible and we're
|
||||
# going to replace the Crypto.PublicKey API soon
|
||||
# anyway.
|
||||
return self.key._decrypt(ciphertext)
|
||||
|
||||
def _blind(self, m, r):
|
||||
return self.key._blind(m, r)
|
||||
|
||||
def _unblind(self, m, r):
|
||||
return self.key._unblind(m, r)
|
||||
|
||||
def _sign(self, m, K=None):
|
||||
return (self.key._sign(m),)
|
||||
|
||||
def _verify(self, m, sig):
|
||||
#(s,) = sig
|
||||
(s,) = sig[:1] # HACK - We should use the previous line instead, but
|
||||
# this is more compatible and we're going to replace
|
||||
# the Crypto.PublicKey API soon anyway.
|
||||
return self.key._verify(m, s)
|
||||
|
||||
def has_private(self):
|
||||
return self.key.has_private()
|
||||
|
||||
def size(self):
|
||||
return self.key.size()
|
||||
|
||||
def can_blind(self):
|
||||
return True
|
||||
|
||||
def can_encrypt(self):
|
||||
return True
|
||||
|
||||
def can_sign(self):
|
||||
return True
|
||||
|
||||
def publickey(self):
|
||||
return self.implementation.construct((self.key.n, self.key.e))
|
||||
|
||||
def __getstate__(self):
|
||||
d = {}
|
||||
for k in self.keydata:
|
||||
try:
|
||||
d[k] = getattr(self.key, k)
|
||||
except AttributeError:
|
||||
pass
|
||||
return d
|
||||
|
||||
def __setstate__(self, d):
|
||||
if not hasattr(self, 'implementation'):
|
||||
self.implementation = RSAImplementation()
|
||||
t = []
|
||||
for k in self.keydata:
|
||||
if not d.has_key(k):
|
||||
break
|
||||
t.append(d[k])
|
||||
self.key = self.implementation._math.rsa_construct(*tuple(t))
|
||||
|
||||
def __repr__(self):
|
||||
attrs = []
|
||||
for k in self.keydata:
|
||||
if k == 'n':
|
||||
attrs.append("n(%d)" % (self.size()+1,))
|
||||
elif hasattr(self.key, k):
|
||||
attrs.append(k)
|
||||
if self.has_private():
|
||||
attrs.append("private")
|
||||
return "<%s @0x%x %s>" % (self.__class__.__name__, id(self), ",".join(attrs))
|
||||
|
||||
class RSAImplementation(object):
|
||||
def __init__(self, **kwargs):
|
||||
# 'use_fast_math' parameter:
|
||||
# None (default) - Use fast math if available; Use slow math if not.
|
||||
# True - Use fast math, and raise RuntimeError if it's not available.
|
||||
# False - Use slow math.
|
||||
use_fast_math = kwargs.get('use_fast_math', None)
|
||||
if use_fast_math is None: # Automatic
|
||||
if _fastmath is not None:
|
||||
self._math = _fastmath
|
||||
else:
|
||||
self._math = _slowmath
|
||||
|
||||
elif use_fast_math: # Explicitly select fast math
|
||||
if _fastmath is not None:
|
||||
self._math = _fastmath
|
||||
else:
|
||||
raise RuntimeError("fast math module not available")
|
||||
|
||||
else: # Explicitly select slow math
|
||||
self._math = _slowmath
|
||||
|
||||
self.error = self._math.error
|
||||
|
||||
# 'default_randfunc' parameter:
|
||||
# None (default) - use Random.new().read
|
||||
# not None - use the specified function
|
||||
self._default_randfunc = kwargs.get('default_randfunc', None)
|
||||
self._current_randfunc = None
|
||||
|
||||
def _get_randfunc(self, randfunc):
|
||||
if randfunc is not None:
|
||||
return randfunc
|
||||
elif self._current_randfunc is None:
|
||||
self._current_randfunc = Random.new().read
|
||||
return self._current_randfunc
|
||||
|
||||
def generate(self, bits, randfunc=None, progress_func=None):
|
||||
rf = self._get_randfunc(randfunc)
|
||||
obj = _RSA.generate_py(bits, rf, progress_func) # TODO: Don't use legacy _RSA module
|
||||
key = self._math.rsa_construct(obj.n, obj.e, obj.d, obj.p, obj.q, obj.u)
|
||||
return _RSAobj(self, key)
|
||||
|
||||
def construct(self, tup):
|
||||
key = self._math.rsa_construct(*tup)
|
||||
return _RSAobj(self, key)
|
||||
|
||||
_impl = RSAImplementation()
|
||||
generate = _impl.generate
|
||||
construct = _impl.construct
|
||||
error = _impl.error
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
||||
|
@ -1,95 +0,0 @@
|
||||
#
|
||||
# RSA.py : RSA encryption/decryption
|
||||
#
|
||||
# Part of the Python Cryptography Toolkit
|
||||
#
|
||||
# Written by Andrew Kuchling, Paul Swartz, and others
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
#
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
from Crypto.PublicKey import pubkey
|
||||
from Crypto.Util import number
|
||||
|
||||
def generate_py(bits, randfunc, progress_func=None):
|
||||
"""generate(bits:int, randfunc:callable, progress_func:callable)
|
||||
|
||||
Generate an RSA key of length 'bits', using 'randfunc' to get
|
||||
random data and 'progress_func', if present, to display
|
||||
the progress of the key generation.
|
||||
"""
|
||||
obj=RSAobj()
|
||||
obj.e = 65537L
|
||||
|
||||
# Generate the prime factors of n
|
||||
if progress_func:
|
||||
progress_func('p,q\n')
|
||||
p = q = 1L
|
||||
while number.size(p*q) < bits:
|
||||
# Note that q might be one bit longer than p if somebody specifies an odd
|
||||
# number of bits for the key. (Why would anyone do that? You don't get
|
||||
# more security.)
|
||||
#
|
||||
# Note also that we ensure that e is coprime to (p-1) and (q-1).
|
||||
# This is needed for encryption to work properly, according to the 1997
|
||||
# paper by Robert D. Silverman of RSA Labs, "Fast generation of random,
|
||||
# strong RSA primes", available at
|
||||
# http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.17.2713&rep=rep1&type=pdf
|
||||
# Since e=65537 is prime, it is sufficient to check that e divides
|
||||
# neither (p-1) nor (q-1).
|
||||
p = 1L
|
||||
while (p - 1) % obj.e == 0:
|
||||
if progress_func:
|
||||
progress_func('p\n')
|
||||
p = pubkey.getPrime(bits/2, randfunc)
|
||||
q = 1L
|
||||
while (q - 1) % obj.e == 0:
|
||||
if progress_func:
|
||||
progress_func('q\n')
|
||||
q = pubkey.getPrime(bits - (bits/2), randfunc)
|
||||
|
||||
# p shall be smaller than q (for calc of u)
|
||||
if p > q:
|
||||
(p, q)=(q, p)
|
||||
obj.p = p
|
||||
obj.q = q
|
||||
|
||||
if progress_func:
|
||||
progress_func('u\n')
|
||||
obj.u = pubkey.inverse(obj.p, obj.q)
|
||||
obj.n = obj.p*obj.q
|
||||
|
||||
if progress_func:
|
||||
progress_func('d\n')
|
||||
obj.d=pubkey.inverse(obj.e, (obj.p-1)*(obj.q-1))
|
||||
|
||||
assert bits <= 1+obj.size(), "Generated key is too small"
|
||||
|
||||
return obj
|
||||
|
||||
class RSAobj(pubkey.pubkey):
|
||||
|
||||
def size(self):
|
||||
"""size() : int
|
||||
Return the maximum number of bits that can be handled by this key.
|
||||
"""
|
||||
return number.size(self.n) - 1
|
||||
|
@ -1,37 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Public-key encryption and signature algorithms.
|
||||
|
||||
Public-key encryption uses two different keys, one for encryption and
|
||||
one for decryption. The encryption key can be made public, and the
|
||||
decryption key is kept private. Many public-key algorithms can also
|
||||
be used to sign messages, and some can *only* be used for signatures.
|
||||
|
||||
Crypto.PublicKey.DSA Digital Signature Algorithm. (Signature only)
|
||||
Crypto.PublicKey.ElGamal (Signing and encryption)
|
||||
Crypto.PublicKey.RSA (Signing, encryption, and blinding)
|
||||
Crypto.PublicKey.qNEW (Signature only)
|
||||
|
||||
"""
|
||||
|
||||
__all__ = ['RSA', 'DSA', 'ElGamal', 'qNEW']
|
||||
__revision__ = "$Id$"
|
||||
|
@ -1,134 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# PubKey/RSA/_slowmath.py : Pure Python implementation of the RSA portions of _fastmath
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Pure Python implementation of the RSA-related portions of Crypto.PublicKey._fastmath."""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
__all__ = ['rsa_construct']
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
from Crypto.Util.number import size, inverse
|
||||
|
||||
class error(Exception):
|
||||
pass
|
||||
|
||||
class _RSAKey(object):
|
||||
def _blind(self, m, r):
|
||||
# compute r**e * m (mod n)
|
||||
return m * pow(r, self.e, self.n)
|
||||
|
||||
def _unblind(self, m, r):
|
||||
# compute m / r (mod n)
|
||||
return inverse(r, self.n) * m % self.n
|
||||
|
||||
def _decrypt(self, c):
|
||||
# compute c**d (mod n)
|
||||
if not self.has_private():
|
||||
raise TypeError("No private key")
|
||||
return pow(c, self.d, self.n) # TODO: CRT exponentiation
|
||||
|
||||
def _encrypt(self, m):
|
||||
# compute m**d (mod n)
|
||||
return pow(m, self.e, self.n)
|
||||
|
||||
def _sign(self, m): # alias for _decrypt
|
||||
if not self.has_private():
|
||||
raise TypeError("No private key")
|
||||
return self._decrypt(m)
|
||||
|
||||
def _verify(self, m, sig):
|
||||
return self._encrypt(sig) == m
|
||||
|
||||
def has_private(self):
|
||||
return hasattr(self, 'd')
|
||||
|
||||
def size(self):
|
||||
"""Return the maximum number of bits that can be encrypted"""
|
||||
return size(self.n) - 1
|
||||
|
||||
def rsa_construct(n, e, d=None, p=None, q=None, u=None):
|
||||
"""Construct an RSAKey object"""
|
||||
assert isinstance(n, long)
|
||||
assert isinstance(e, long)
|
||||
assert isinstance(d, (long, type(None)))
|
||||
assert isinstance(p, (long, type(None)))
|
||||
assert isinstance(q, (long, type(None)))
|
||||
assert isinstance(u, (long, type(None)))
|
||||
obj = _RSAKey()
|
||||
obj.n = n
|
||||
obj.e = e
|
||||
if d is not None: obj.d = d
|
||||
if p is not None: obj.p = p
|
||||
if q is not None: obj.q = q
|
||||
if u is not None: obj.u = u
|
||||
return obj
|
||||
|
||||
class _DSAKey(object):
|
||||
def size(self):
|
||||
"""Return the maximum number of bits that can be encrypted"""
|
||||
return size(self.p) - 1
|
||||
|
||||
def has_private(self):
|
||||
return hasattr(self, 'x')
|
||||
|
||||
def _sign(self, m, k): # alias for _decrypt
|
||||
# SECURITY TODO - We _should_ be computing SHA1(m), but we don't because that's the API.
|
||||
if not self.has_private():
|
||||
raise TypeError("No private key")
|
||||
if not (1L < k < self.q):
|
||||
raise ValueError("k is not between 2 and q-1")
|
||||
inv_k = inverse(k, self.q) # Compute k**-1 mod q
|
||||
r = pow(self.g, k, self.p) % self.q # r = (g**k mod p) mod q
|
||||
s = (inv_k * (m + self.x * r)) % self.q
|
||||
return (r, s)
|
||||
|
||||
def _verify(self, m, r, s):
|
||||
# SECURITY TODO - We _should_ be computing SHA1(m), but we don't because that's the API.
|
||||
if not (0 < r < self.q) or not (0 < s < self.q):
|
||||
return False
|
||||
w = inverse(s, self.q)
|
||||
u1 = (m*w) % self.q
|
||||
u2 = (r*w) % self.q
|
||||
v = (pow(self.g, u1, self.p) * pow(self.y, u2, self.p) % self.p) % self.q
|
||||
return v == r
|
||||
|
||||
def dsa_construct(y, g, p, q, x=None):
|
||||
assert isinstance(y, long)
|
||||
assert isinstance(g, long)
|
||||
assert isinstance(p, long)
|
||||
assert isinstance(q, long)
|
||||
assert isinstance(x, (long, type(None)))
|
||||
obj = _DSAKey()
|
||||
obj.y = y
|
||||
obj.g = g
|
||||
obj.p = p
|
||||
obj.q = q
|
||||
if x is not None: obj.x = x
|
||||
return obj
|
||||
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
||||
|
@ -1,192 +0,0 @@
|
||||
#
|
||||
# pubkey.py : Internal functions for public key operations
|
||||
#
|
||||
# Part of the Python Cryptography Toolkit
|
||||
#
|
||||
# Written by Andrew Kuchling, Paul Swartz, and others
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
#
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
import types, warnings
|
||||
from Crypto.Util.number import *
|
||||
|
||||
# Basic public key class
|
||||
class pubkey:
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def __getstate__(self):
|
||||
"""To keep key objects platform-independent, the key data is
|
||||
converted to standard Python long integers before being
|
||||
written out. It will then be reconverted as necessary on
|
||||
restoration."""
|
||||
d=self.__dict__
|
||||
for key in self.keydata:
|
||||
if d.has_key(key): d[key]=long(d[key])
|
||||
return d
|
||||
|
||||
def __setstate__(self, d):
|
||||
"""On unpickling a key object, the key data is converted to the big
|
||||
number representation being used, whether that is Python long
|
||||
integers, MPZ objects, or whatever."""
|
||||
for key in self.keydata:
|
||||
if d.has_key(key): self.__dict__[key]=bignum(d[key])
|
||||
|
||||
def encrypt(self, plaintext, K):
|
||||
"""encrypt(plaintext:string|long, K:string|long) : tuple
|
||||
Encrypt the string or integer plaintext. K is a random
|
||||
parameter required by some algorithms.
|
||||
"""
|
||||
wasString=0
|
||||
if isinstance(plaintext, types.StringType):
|
||||
plaintext=bytes_to_long(plaintext) ; wasString=1
|
||||
if isinstance(K, types.StringType):
|
||||
K=bytes_to_long(K)
|
||||
ciphertext=self._encrypt(plaintext, K)
|
||||
if wasString: return tuple(map(long_to_bytes, ciphertext))
|
||||
else: return ciphertext
|
||||
|
||||
def decrypt(self, ciphertext):
|
||||
"""decrypt(ciphertext:tuple|string|long): string
|
||||
Decrypt 'ciphertext' using this key.
|
||||
"""
|
||||
wasString=0
|
||||
if not isinstance(ciphertext, types.TupleType):
|
||||
ciphertext=(ciphertext,)
|
||||
if isinstance(ciphertext[0], types.StringType):
|
||||
ciphertext=tuple(map(bytes_to_long, ciphertext)) ; wasString=1
|
||||
plaintext=self._decrypt(ciphertext)
|
||||
if wasString: return long_to_bytes(plaintext)
|
||||
else: return plaintext
|
||||
|
||||
def sign(self, M, K):
|
||||
"""sign(M : string|long, K:string|long) : tuple
|
||||
Return a tuple containing the signature for the message M.
|
||||
K is a random parameter required by some algorithms.
|
||||
"""
|
||||
if (not self.has_private()):
|
||||
raise TypeError('Private key not available in this object')
|
||||
if isinstance(M, types.StringType): M=bytes_to_long(M)
|
||||
if isinstance(K, types.StringType): K=bytes_to_long(K)
|
||||
return self._sign(M, K)
|
||||
|
||||
def verify (self, M, signature):
|
||||
"""verify(M:string|long, signature:tuple) : bool
|
||||
Verify that the signature is valid for the message M;
|
||||
returns true if the signature checks out.
|
||||
"""
|
||||
if isinstance(M, types.StringType): M=bytes_to_long(M)
|
||||
return self._verify(M, signature)
|
||||
|
||||
# alias to compensate for the old validate() name
|
||||
def validate (self, M, signature):
|
||||
warnings.warn("validate() method name is obsolete; use verify()",
|
||||
DeprecationWarning)
|
||||
|
||||
def blind(self, M, B):
|
||||
"""blind(M : string|long, B : string|long) : string|long
|
||||
Blind message M using blinding factor B.
|
||||
"""
|
||||
wasString=0
|
||||
if isinstance(M, types.StringType):
|
||||
M=bytes_to_long(M) ; wasString=1
|
||||
if isinstance(B, types.StringType): B=bytes_to_long(B)
|
||||
blindedmessage=self._blind(M, B)
|
||||
if wasString: return long_to_bytes(blindedmessage)
|
||||
else: return blindedmessage
|
||||
|
||||
def unblind(self, M, B):
|
||||
"""unblind(M : string|long, B : string|long) : string|long
|
||||
Unblind message M using blinding factor B.
|
||||
"""
|
||||
wasString=0
|
||||
if isinstance(M, types.StringType):
|
||||
M=bytes_to_long(M) ; wasString=1
|
||||
if isinstance(B, types.StringType): B=bytes_to_long(B)
|
||||
unblindedmessage=self._unblind(M, B)
|
||||
if wasString: return long_to_bytes(unblindedmessage)
|
||||
else: return unblindedmessage
|
||||
|
||||
|
||||
# The following methods will usually be left alone, except for
|
||||
# signature-only algorithms. They both return Boolean values
|
||||
# recording whether this key's algorithm can sign and encrypt.
|
||||
def can_sign (self):
|
||||
"""can_sign() : bool
|
||||
Return a Boolean value recording whether this algorithm can
|
||||
generate signatures. (This does not imply that this
|
||||
particular key object has the private information required to
|
||||
to generate a signature.)
|
||||
"""
|
||||
return 1
|
||||
|
||||
def can_encrypt (self):
|
||||
"""can_encrypt() : bool
|
||||
Return a Boolean value recording whether this algorithm can
|
||||
encrypt data. (This does not imply that this
|
||||
particular key object has the private information required to
|
||||
to decrypt a message.)
|
||||
"""
|
||||
return 1
|
||||
|
||||
def can_blind (self):
|
||||
"""can_blind() : bool
|
||||
Return a Boolean value recording whether this algorithm can
|
||||
blind data. (This does not imply that this
|
||||
particular key object has the private information required to
|
||||
to blind a message.)
|
||||
"""
|
||||
return 0
|
||||
|
||||
# The following methods will certainly be overridden by
|
||||
# subclasses.
|
||||
|
||||
def size (self):
|
||||
"""size() : int
|
||||
Return the maximum number of bits that can be handled by this key.
|
||||
"""
|
||||
return 0
|
||||
|
||||
def has_private (self):
|
||||
"""has_private() : bool
|
||||
Return a Boolean denoting whether the object contains
|
||||
private components.
|
||||
"""
|
||||
return 0
|
||||
|
||||
def publickey (self):
|
||||
"""publickey(): object
|
||||
Return a new key object containing only the public information.
|
||||
"""
|
||||
return self
|
||||
|
||||
def __eq__ (self, other):
|
||||
"""__eq__(other): 0, 1
|
||||
Compare us to other for equality.
|
||||
"""
|
||||
return self.__getstate__() == other.__getstate__()
|
||||
|
||||
def __ne__ (self, other):
|
||||
"""__ne__(other): 0, 1
|
||||
Compare us to other for inequality.
|
||||
"""
|
||||
return not self.__eq__(other)
|
@ -1,139 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# FortunaAccumulator.py : Fortuna's internal accumulator
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
from binascii import b2a_hex
|
||||
import time
|
||||
import warnings
|
||||
|
||||
from Crypto.pct_warnings import ClockRewindWarning
|
||||
import SHAd256
|
||||
|
||||
import FortunaGenerator
|
||||
|
||||
class FortunaPool(object):
|
||||
"""Fortuna pool type
|
||||
|
||||
This object acts like a hash object, with the following differences:
|
||||
|
||||
- It keeps a count (the .length attribute) of the number of bytes that
|
||||
have been added to the pool
|
||||
- It supports a .reset() method for in-place reinitialization
|
||||
- The method to add bytes to the pool is .append(), not .update().
|
||||
"""
|
||||
|
||||
digest_size = SHAd256.digest_size
|
||||
|
||||
def __init__(self):
|
||||
self.reset()
|
||||
|
||||
def append(self, data):
|
||||
self._h.update(data)
|
||||
self.length += len(data)
|
||||
|
||||
def digest(self):
|
||||
return self._h.digest()
|
||||
|
||||
def hexdigest(self):
|
||||
return b2a_hex(self.digest())
|
||||
|
||||
def reset(self):
|
||||
self._h = SHAd256.new()
|
||||
self.length = 0
|
||||
|
||||
def which_pools(r):
|
||||
"""Return a list of pools indexes (in range(32)) that are to be included during reseed number r.
|
||||
|
||||
According to _Practical Cryptography_, chapter 10.5.2 "Pools":
|
||||
|
||||
"Pool P_i is included if 2**i is a divisor of r. Thus P_0 is used
|
||||
every reseed, P_1 every other reseed, P_2 every fourth reseed, etc."
|
||||
"""
|
||||
# This is a separate function so that it can be unit-tested.
|
||||
assert r >= 1
|
||||
retval = []
|
||||
mask = 0
|
||||
for i in range(32):
|
||||
# "Pool P_i is included if 2**i is a divisor of [reseed_count]"
|
||||
if (r & mask) == 0:
|
||||
retval.append(i)
|
||||
else:
|
||||
break # optimization. once this fails, it always fails
|
||||
mask = (mask << 1) | 1L
|
||||
return retval
|
||||
|
||||
class FortunaAccumulator(object):
|
||||
|
||||
min_pool_size = 64 # TODO: explain why
|
||||
reseed_interval = 0.100 # 100 ms TODO: explain why
|
||||
|
||||
def __init__(self):
|
||||
self.reseed_count = 0
|
||||
self.generator = FortunaGenerator.AESGenerator()
|
||||
self.last_reseed = None
|
||||
|
||||
# Initialize 32 FortunaPool instances.
|
||||
# NB: This is _not_ equivalent to [FortunaPool()]*32, which would give
|
||||
# us 32 references to the _same_ FortunaPool instance (and cause the
|
||||
# assertion below to fail).
|
||||
self.pools = [FortunaPool() for i in range(32)] # 32 pools
|
||||
assert(self.pools[0] is not self.pools[1])
|
||||
|
||||
def random_data(self, bytes):
|
||||
current_time = time.time()
|
||||
if self.last_reseed > current_time:
|
||||
warnings.warn("Clock rewind detected. Resetting last_reseed.", ClockRewindWarning)
|
||||
self.last_reseed = None
|
||||
if (self.pools[0].length >= self.min_pool_size and
|
||||
(self.last_reseed is None or
|
||||
current_time > self.last_reseed + self.reseed_interval)):
|
||||
self._reseed(current_time)
|
||||
# The following should fail if we haven't seeded the pool yet.
|
||||
return self.generator.pseudo_random_data(bytes)
|
||||
|
||||
def _reseed(self, current_time=None):
|
||||
if current_time is None:
|
||||
current_time = time.time()
|
||||
seed = []
|
||||
self.reseed_count += 1
|
||||
self.last_reseed = current_time
|
||||
for i in which_pools(self.reseed_count):
|
||||
seed.append(self.pools[i].digest())
|
||||
self.pools[i].reset()
|
||||
|
||||
seed = "".join(seed)
|
||||
self.generator.reseed(seed)
|
||||
|
||||
def add_random_event(self, source_number, pool_number, data):
|
||||
assert 1 <= len(data) <= 32
|
||||
assert 0 <= source_number <= 255
|
||||
assert 0 <= pool_number <= 31
|
||||
self.pools[pool_number].append(chr(source_number))
|
||||
self.pools[pool_number].append(chr(len(data)))
|
||||
self.pools[pool_number].append(data)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,128 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# FortunaGenerator.py : Fortuna's internal PRNG
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
import struct
|
||||
|
||||
from Crypto.Util.number import ceil_shift, exact_log2, exact_div
|
||||
from Crypto.Util import Counter
|
||||
from Crypto.Cipher import AES
|
||||
|
||||
import SHAd256
|
||||
|
||||
class AESGenerator(object):
|
||||
"""The Fortuna "generator"
|
||||
|
||||
This is used internally by the Fortuna PRNG to generate arbitrary amounts
|
||||
of pseudorandom data from a smaller amount of seed data.
|
||||
|
||||
The output is generated by running AES-256 in counter mode and re-keying
|
||||
after every mebibyte (2**16 blocks) of output.
|
||||
"""
|
||||
|
||||
block_size = AES.block_size # output block size in octets (128 bits)
|
||||
key_size = 32 # key size in octets (256 bits)
|
||||
|
||||
# Because of the birthday paradox, we expect to find approximately one
|
||||
# collision for every 2**64 blocks of output from a real random source.
|
||||
# However, this code generates pseudorandom data by running AES in
|
||||
# counter mode, so there will be no collisions until the counter
|
||||
# (theoretically) wraps around at 2**128 blocks. Thus, in order to prevent
|
||||
# Fortuna's pseudorandom output from deviating perceptibly from a true
|
||||
# random source, Ferguson and Schneier specify a limit of 2**16 blocks
|
||||
# without rekeying.
|
||||
max_blocks_per_request = 2**16 # Allow no more than this number of blocks per _pseudo_random_data request
|
||||
|
||||
_four_kiblocks_of_zeros = "\0" * block_size * 4096
|
||||
|
||||
def __init__(self):
|
||||
self.counter = Counter.new(nbits=self.block_size*8, initial_value=0, little_endian=True)
|
||||
self.key = None
|
||||
|
||||
# Set some helper constants
|
||||
self.block_size_shift = exact_log2(self.block_size)
|
||||
assert (1 << self.block_size_shift) == self.block_size
|
||||
|
||||
self.blocks_per_key = exact_div(self.key_size, self.block_size)
|
||||
assert self.key_size == self.blocks_per_key * self.block_size
|
||||
|
||||
self.max_bytes_per_request = self.max_blocks_per_request * self.block_size
|
||||
|
||||
def reseed(self, seed):
|
||||
if self.key is None:
|
||||
self.key = "\0" * self.key_size
|
||||
self._set_key(SHAd256.new(self.key + seed).digest())
|
||||
self.counter() # increment counter
|
||||
assert len(self.key) == self.key_size
|
||||
|
||||
def pseudo_random_data(self, bytes):
|
||||
assert bytes >= 0
|
||||
|
||||
num_full_blocks = bytes >> 20
|
||||
remainder = bytes & ((1<<20)-1)
|
||||
|
||||
retval = []
|
||||
for i in xrange(num_full_blocks):
|
||||
retval.append(self._pseudo_random_data(1<<20))
|
||||
retval.append(self._pseudo_random_data(remainder))
|
||||
|
||||
return "".join(retval)
|
||||
|
||||
def _set_key(self, key):
|
||||
self.key = key
|
||||
self._cipher = AES.new(key, AES.MODE_CTR, counter=self.counter)
|
||||
|
||||
def _pseudo_random_data(self, bytes):
|
||||
if not (0 <= bytes <= self.max_bytes_per_request):
|
||||
raise AssertionError("You cannot ask for more than 1 MiB of data per request")
|
||||
|
||||
num_blocks = ceil_shift(bytes, self.block_size_shift) # num_blocks = ceil(bytes / self.block_size)
|
||||
|
||||
# Compute the output
|
||||
retval = self._generate_blocks(num_blocks)[:bytes]
|
||||
|
||||
# Switch to a new key to avoid later compromises of this output (i.e.
|
||||
# state compromise extension attacks)
|
||||
self._set_key(self._generate_blocks(self.blocks_per_key))
|
||||
|
||||
assert len(retval) == bytes
|
||||
assert len(self.key) == self.key_size
|
||||
|
||||
return retval
|
||||
|
||||
def _generate_blocks(self, num_blocks):
|
||||
if self.key is None:
|
||||
raise AssertionError("generator must be seeded before use")
|
||||
assert 0 <= num_blocks <= self.max_blocks_per_request
|
||||
retval = []
|
||||
for i in xrange(num_blocks >> 12): # xrange(num_blocks / 4096)
|
||||
retval.append(self._cipher.encrypt(self._four_kiblocks_of_zeros))
|
||||
remaining_bytes = (num_blocks & 4095) << self.block_size_shift # (num_blocks % 4095) * self.block_size
|
||||
retval.append(self._cipher.encrypt(self._four_kiblocks_of_zeros[:remaining_bytes]))
|
||||
return "".join(retval)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,88 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# Random/Fortuna/SHAd256.py : SHA_d-256 hash function implementation
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""\
|
||||
SHA_d-256 hash function implementation.
|
||||
|
||||
This module should comply with PEP 247.
|
||||
"""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['new', 'digest_size']
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
from binascii import b2a_hex
|
||||
|
||||
from Crypto.Hash import SHA256
|
||||
|
||||
assert SHA256.digest_size == 32
|
||||
|
||||
class _SHAd256(object):
|
||||
"""SHA-256, doubled.
|
||||
|
||||
Returns SHA-256(SHA-256(data)).
|
||||
"""
|
||||
|
||||
digest_size = SHA256.digest_size
|
||||
|
||||
_internal = object()
|
||||
|
||||
def __init__(self, internal_api_check, sha256_hash_obj):
|
||||
if internal_api_check is not self._internal:
|
||||
raise AssertionError("Do not instantiate this class directly. Use %s.new()" % (__name__,))
|
||||
self._h = sha256_hash_obj
|
||||
|
||||
# PEP 247 "copy" method
|
||||
def copy(self):
|
||||
"""Return a copy of this hashing object"""
|
||||
return _SHAd256(SHAd256._internal, self._h.copy())
|
||||
|
||||
# PEP 247 "digest" method
|
||||
def digest(self):
|
||||
"""Return the hash value of this object as a binary string"""
|
||||
retval = SHA256.new(self._h.digest()).digest()
|
||||
assert len(retval) == 32
|
||||
return retval
|
||||
|
||||
# PEP 247 "hexdigest" method
|
||||
def hexdigest(self):
|
||||
"""Return the hash value of this object as a (lowercase) hexadecimal string"""
|
||||
retval = b2a_hex(self.digest())
|
||||
assert len(retval) == 64
|
||||
return retval
|
||||
|
||||
# PEP 247 "update" method
|
||||
def update(self, data):
|
||||
self._h.update(data)
|
||||
|
||||
# PEP 247 module-level "digest_size" variable
|
||||
digest_size = _SHAd256.digest_size
|
||||
|
||||
# PEP 247 module-level "new" function
|
||||
def new(data=""):
|
||||
"""Return a new SHAd256 hashing object"""
|
||||
return _SHAd256(_SHAd256._internal, SHA256.new(data))
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,40 +0,0 @@
|
||||
#
|
||||
# Random/OSRNG/__init__.py : Platform-independent OS RNG API
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Provides a platform-independent interface to the random number generators
|
||||
supplied by various operating systems."""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
import os
|
||||
|
||||
if os.name == 'posix':
|
||||
from Crypto.Random.OSRNG.posix import new
|
||||
elif os.name == 'nt':
|
||||
from Crypto.Random.OSRNG.nt import new
|
||||
elif hasattr(os, 'urandom'):
|
||||
from Crypto.Random.OSRNG.fallback import new
|
||||
else:
|
||||
raise ImportError("Not implemented")
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,46 +0,0 @@
|
||||
#
|
||||
# Random/OSRNG/fallback.py : Fallback entropy source for systems with os.urandom
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['PythonOSURandomRNG']
|
||||
|
||||
import os
|
||||
|
||||
from rng_base import BaseRNG
|
||||
|
||||
class PythonOSURandomRNG(BaseRNG):
|
||||
|
||||
name = "<os.urandom>"
|
||||
|
||||
def __init__(self):
|
||||
self._read = os.urandom
|
||||
BaseRNG.__init__(self)
|
||||
|
||||
def _close(self):
|
||||
self._read = None
|
||||
|
||||
def new(*args, **kwargs):
|
||||
return PythonOSURandomRNG(*args, **kwargs)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,74 +0,0 @@
|
||||
#
|
||||
# Random/OSRNG/nt.py : OS entropy source for MS Windows
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['WindowsRNG']
|
||||
|
||||
import winrandom
|
||||
from rng_base import BaseRNG
|
||||
|
||||
class WindowsRNG(BaseRNG):
|
||||
|
||||
name = "<CryptGenRandom>"
|
||||
|
||||
def __init__(self):
|
||||
self.__winrand = winrandom.new()
|
||||
BaseRNG.__init__(self)
|
||||
|
||||
def flush(self):
|
||||
"""Work around weakness in Windows RNG.
|
||||
|
||||
The CryptGenRandom mechanism in some versions of Windows allows an
|
||||
attacker to learn 128 KiB of past and future output. As a workaround,
|
||||
this function reads 128 KiB of 'random' data from Windows and discards
|
||||
it.
|
||||
|
||||
For more information about the weaknesses in CryptGenRandom, see
|
||||
_Cryptanalysis of the Random Number Generator of the Windows Operating
|
||||
System_, by Leo Dorrendorf and Zvi Gutterman and Benny Pinkas
|
||||
http://eprint.iacr.org/2007/419
|
||||
"""
|
||||
if self.closed:
|
||||
raise ValueError("I/O operation on closed file")
|
||||
data = self.__winrand.get_bytes(128*1024)
|
||||
assert (len(data) == 128*1024)
|
||||
BaseRNG.flush(self)
|
||||
|
||||
def _close(self):
|
||||
self.__winrand = None
|
||||
|
||||
def _read(self, N):
|
||||
# Unfortunately, research shows that CryptGenRandom doesn't provide
|
||||
# forward secrecy and fails the next-bit test unless we apply a
|
||||
# workaround, which we do here. See http://eprint.iacr.org/2007/419
|
||||
# for information on the vulnerability.
|
||||
self.flush()
|
||||
data = self.__winrand.get_bytes(N)
|
||||
self.flush()
|
||||
return data
|
||||
|
||||
def new(*args, **kwargs):
|
||||
return WindowsRNG(*args, **kwargs)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,86 +0,0 @@
|
||||
#
|
||||
# Random/OSRNG/rng_base.py : Base class for OSRNG
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
class BaseRNG(object):
|
||||
|
||||
def __init__(self):
|
||||
self.closed = False
|
||||
self._selftest()
|
||||
|
||||
def __del__(self):
|
||||
self.close()
|
||||
|
||||
def _selftest(self):
|
||||
# Test that urandom can return data
|
||||
data = self.read(16)
|
||||
if len(data) != 16:
|
||||
raise AssertionError("read truncated")
|
||||
|
||||
# Test that we get different data every time (if we don't, the RNG is
|
||||
# probably malfunctioning)
|
||||
data2 = self.read(16)
|
||||
if data == data2:
|
||||
raise AssertionError("OS RNG returned duplicate data")
|
||||
|
||||
# PEP 343: Support for the "with" statement
|
||||
def __enter__(self):
|
||||
pass
|
||||
def __exit__(self):
|
||||
"""PEP 343 support"""
|
||||
self.close()
|
||||
|
||||
def close(self):
|
||||
if not self.closed:
|
||||
self._close()
|
||||
self.closed = True
|
||||
|
||||
def flush(self):
|
||||
pass
|
||||
|
||||
def read(self, N=-1):
|
||||
"""Return N bytes from the RNG."""
|
||||
if self.closed:
|
||||
raise ValueError("I/O operation on closed file")
|
||||
if not isinstance(N, (long, int)):
|
||||
raise TypeError("an integer is required")
|
||||
if N < 0:
|
||||
raise ValueError("cannot read to end of infinite stream")
|
||||
elif N == 0:
|
||||
return ""
|
||||
data = self._read(N)
|
||||
if len(data) != N:
|
||||
raise AssertionError("%s produced truncated output (requested %d, got %d)" % (self.name, N, len(data)))
|
||||
return data
|
||||
|
||||
def _close(self):
|
||||
raise NotImplementedError("child class must implement this")
|
||||
|
||||
def _read(self, N):
|
||||
raise NotImplementedError("child class must implement this")
|
||||
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
Binary file not shown.
@ -1,213 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Random/_UserFriendlyRNG.py : A user-friendly random number generator
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
import os
|
||||
import threading
|
||||
import struct
|
||||
import time
|
||||
from math import floor
|
||||
|
||||
from Crypto.Random import OSRNG
|
||||
from Crypto.Random.Fortuna import FortunaAccumulator
|
||||
|
||||
class _EntropySource(object):
|
||||
def __init__(self, accumulator, src_num):
|
||||
self._fortuna = accumulator
|
||||
self._src_num = src_num
|
||||
self._pool_num = 0
|
||||
|
||||
def feed(self, data):
|
||||
self._fortuna.add_random_event(self._src_num, self._pool_num, data)
|
||||
self._pool_num = (self._pool_num + 1) & 31
|
||||
|
||||
class _EntropyCollector(object):
|
||||
|
||||
def __init__(self, accumulator):
|
||||
self._osrng = OSRNG.new()
|
||||
self._osrng_es = _EntropySource(accumulator, 255)
|
||||
self._time_es = _EntropySource(accumulator, 254)
|
||||
self._clock_es = _EntropySource(accumulator, 253)
|
||||
|
||||
def reinit(self):
|
||||
# Add 256 bits to each of the 32 pools, twice. (For a total of 16384
|
||||
# bits collected from the operating system.)
|
||||
for i in range(2):
|
||||
block = self._osrng.read(32*32)
|
||||
for p in range(32):
|
||||
self._osrng_es.feed(block[p*32:(p+1)*32])
|
||||
block = None
|
||||
self._osrng.flush()
|
||||
|
||||
def collect(self):
|
||||
# Collect 64 bits of entropy from the operating system and feed it to Fortuna.
|
||||
self._osrng_es.feed(self._osrng.read(8))
|
||||
|
||||
# Add the fractional part of time.time()
|
||||
t = time.time()
|
||||
self._time_es.feed(struct.pack("@I", int(2**30 * (t - floor(t)))))
|
||||
|
||||
# Add the fractional part of time.clock()
|
||||
t = time.clock()
|
||||
self._clock_es.feed(struct.pack("@I", int(2**30 * (t - floor(t)))))
|
||||
|
||||
|
||||
class _UserFriendlyRNG(object):
|
||||
|
||||
def __init__(self):
|
||||
self.closed = False
|
||||
self._fa = FortunaAccumulator.FortunaAccumulator()
|
||||
self._ec = _EntropyCollector(self._fa)
|
||||
self.reinit()
|
||||
|
||||
def reinit(self):
|
||||
"""Initialize the random number generator and seed it with entropy from
|
||||
the operating system.
|
||||
"""
|
||||
self._pid = os.getpid()
|
||||
self._ec.reinit()
|
||||
|
||||
def close(self):
|
||||
self.closed = True
|
||||
self._osrng = None
|
||||
self._fa = None
|
||||
|
||||
def flush(self):
|
||||
pass
|
||||
|
||||
def read(self, N):
|
||||
"""Return N bytes from the RNG."""
|
||||
if self.closed:
|
||||
raise ValueError("I/O operation on closed file")
|
||||
if not isinstance(N, (long, int)):
|
||||
raise TypeError("an integer is required")
|
||||
if N < 0:
|
||||
raise ValueError("cannot read to end of infinite stream")
|
||||
|
||||
# Collect some entropy and feed it to Fortuna
|
||||
self._ec.collect()
|
||||
|
||||
# Ask Fortuna to generate some bytes
|
||||
retval = self._fa.random_data(N)
|
||||
|
||||
# Check that we haven't forked in the meantime. (If we have, we don't
|
||||
# want to use the data, because it might have been duplicated in the
|
||||
# parent process.
|
||||
self._check_pid()
|
||||
|
||||
# Return the random data.
|
||||
return retval
|
||||
|
||||
def _check_pid(self):
|
||||
# Lame fork detection to remind developers to invoke Random.atfork()
|
||||
# after every call to os.fork(). Note that this check is not reliable,
|
||||
# since process IDs can be reused on most operating systems.
|
||||
#
|
||||
# You need to do Random.atfork() in the child process after every call
|
||||
# to os.fork() to avoid reusing PRNG state. If you want to avoid
|
||||
# leaking PRNG state to child processes (for example, if you are using
|
||||
# os.setuid()) then you should also invoke Random.atfork() in the
|
||||
# *parent* process.
|
||||
if os.getpid() != self._pid:
|
||||
raise AssertionError("PID check failed. RNG must be re-initialized after fork(). Hint: Try Random.atfork()")
|
||||
|
||||
|
||||
class _LockingUserFriendlyRNG(_UserFriendlyRNG):
|
||||
def __init__(self):
|
||||
self._lock = threading.Lock()
|
||||
_UserFriendlyRNG.__init__(self)
|
||||
|
||||
def close(self):
|
||||
self._lock.acquire()
|
||||
try:
|
||||
return _UserFriendlyRNG.close(self)
|
||||
finally:
|
||||
self._lock.release()
|
||||
|
||||
def reinit(self):
|
||||
self._lock.acquire()
|
||||
try:
|
||||
return _UserFriendlyRNG.reinit(self)
|
||||
finally:
|
||||
self._lock.release()
|
||||
|
||||
def read(self, bytes):
|
||||
self._lock.acquire()
|
||||
try:
|
||||
return _UserFriendlyRNG.read(self, bytes)
|
||||
finally:
|
||||
self._lock.release()
|
||||
|
||||
class RNGFile(object):
|
||||
def __init__(self, singleton):
|
||||
self.closed = False
|
||||
self._singleton = singleton
|
||||
|
||||
# PEP 343: Support for the "with" statement
|
||||
def __enter__(self):
|
||||
"""PEP 343 support"""
|
||||
def __exit__(self):
|
||||
"""PEP 343 support"""
|
||||
self.close()
|
||||
|
||||
def close(self):
|
||||
# Don't actually close the singleton, just close this RNGFile instance.
|
||||
self.closed = True
|
||||
self._singleton = None
|
||||
|
||||
def read(self, bytes):
|
||||
if self.closed:
|
||||
raise ValueError("I/O operation on closed file")
|
||||
return self._singleton.read(bytes)
|
||||
|
||||
def flush(self):
|
||||
if self.closed:
|
||||
raise ValueError("I/O operation on closed file")
|
||||
|
||||
_singleton_lock = threading.Lock()
|
||||
_singleton = None
|
||||
def _get_singleton():
|
||||
global _singleton
|
||||
_singleton_lock.acquire()
|
||||
try:
|
||||
if _singleton is None:
|
||||
_singleton = _LockingUserFriendlyRNG()
|
||||
return _singleton
|
||||
finally:
|
||||
_singleton_lock.release()
|
||||
|
||||
def new():
|
||||
return RNGFile(_get_singleton())
|
||||
|
||||
def reinit():
|
||||
_get_singleton().reinit()
|
||||
|
||||
def get_random_bytes(n):
|
||||
"""Return the specified number of cryptographically-strong random bytes."""
|
||||
return _get_singleton().read(n)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,43 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Random/__init__.py : PyCrypto random number generation
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['new']
|
||||
|
||||
import OSRNG
|
||||
import _UserFriendlyRNG
|
||||
|
||||
def new(*args, **kwargs):
|
||||
"""Return a file-like object that outputs cryptographically random bytes."""
|
||||
return _UserFriendlyRNG.new(*args, **kwargs)
|
||||
|
||||
def atfork():
|
||||
"""Call this whenever you call os.fork()"""
|
||||
_UserFriendlyRNG.reinit()
|
||||
|
||||
def get_random_bytes(n):
|
||||
"""Return the specified number of cryptographically-strong random bytes."""
|
||||
return _UserFriendlyRNG.get_random_bytes(n)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,143 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Random/random.py : Strong alternative for the standard 'random' module
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""A cryptographically strong version of Python's standard "random" module."""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['StrongRandom', 'getrandbits', 'randrange', 'randint', 'choice', 'shuffle', 'sample']
|
||||
|
||||
from Crypto import Random
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
class StrongRandom(object):
|
||||
def __init__(self, rng=None, randfunc=None):
|
||||
if randfunc is None and rng is None:
|
||||
self._randfunc = None
|
||||
elif randfunc is not None and rng is None:
|
||||
self._randfunc = randfunc
|
||||
elif randfunc is None and rng is not None:
|
||||
self._randfunc = rng.read
|
||||
else:
|
||||
raise ValueError("Cannot specify both 'rng' and 'randfunc'")
|
||||
|
||||
def getrandbits(self, k):
|
||||
"""Return a python long integer with k random bits."""
|
||||
if self._randfunc is None:
|
||||
self._randfunc = Random.new().read
|
||||
mask = (1L << k) - 1
|
||||
return mask & bytes_to_long(self._randfunc(ceil_div(k, 8)))
|
||||
|
||||
def randrange(self, *args):
|
||||
"""randrange([start,] stop[, step]):
|
||||
Return a randomly-selected element from range(start, stop, step)."""
|
||||
if len(args) == 3:
|
||||
(start, stop, step) = args
|
||||
elif len(args) == 2:
|
||||
(start, stop) = args
|
||||
step = 1
|
||||
elif len(args) == 1:
|
||||
(stop,) = args
|
||||
start = 0
|
||||
step = 1
|
||||
else:
|
||||
raise TypeError("randrange expected at most 3 arguments, got %d" % (len(args),))
|
||||
if (not isinstance(start, (int, long))
|
||||
or not isinstance(stop, (int, long))
|
||||
or not isinstance(step, (int, long))):
|
||||
raise TypeError("randrange requires integer arguments")
|
||||
if step == 0:
|
||||
raise ValueError("randrange step argument must not be zero")
|
||||
|
||||
num_choices = ceil_div(stop - start, step)
|
||||
if num_choices < 0:
|
||||
num_choices = 0
|
||||
if num_choices < 1:
|
||||
raise ValueError("empty range for randrange(%r, %r, %r)" % (start, stop, step))
|
||||
|
||||
# Pick a random number in the range of possible numbers
|
||||
r = num_choices
|
||||
while r >= num_choices:
|
||||
r = self.getrandbits(size(num_choices))
|
||||
|
||||
return start + (step * r)
|
||||
|
||||
def randint(self, a, b):
|
||||
"""Return a random integer N such that a <= N <= b."""
|
||||
if not isinstance(a, (int, long)) or not isinstance(b, (int, long)):
|
||||
raise TypeError("randint requires integer arguments")
|
||||
N = self.randrange(a, b+1)
|
||||
assert a <= N <= b
|
||||
return N
|
||||
|
||||
def choice(self, seq):
|
||||
"""Return a random element from a (non-empty) sequence.
|
||||
|
||||
If the seqence is empty, raises IndexError.
|
||||
"""
|
||||
if len(seq) == 0:
|
||||
raise IndexError("empty sequence")
|
||||
return seq[self.randrange(len(seq))]
|
||||
|
||||
def shuffle(self, x):
|
||||
"""Shuffle the sequence in place."""
|
||||
# Make a (copy) of the list of objects we want to shuffle
|
||||
items = list(x)
|
||||
|
||||
# Choose a random item (without replacement) until all the items have been
|
||||
# chosen.
|
||||
for i in xrange(len(x)):
|
||||
p = self.randint(len(items))
|
||||
x[i] = items[p]
|
||||
del items[p]
|
||||
|
||||
def sample(self, population, k):
|
||||
"""Return a k-length list of unique elements chosen from the population sequence."""
|
||||
|
||||
num_choices = len(population)
|
||||
if k > num_choices:
|
||||
raise ValueError("sample larger than population")
|
||||
|
||||
retval = []
|
||||
selected = {} # we emulate a set using a dict here
|
||||
for i in xrange(k):
|
||||
r = None
|
||||
while r is None or r in selected:
|
||||
r = self.randrange(num_choices)
|
||||
retval.append(population[r])
|
||||
selected[r] = 1
|
||||
return retval
|
||||
|
||||
_r = StrongRandom()
|
||||
getrandbits = _r.getrandbits
|
||||
randrange = _r.randrange
|
||||
randint = _r.randint
|
||||
choice = _r.choice
|
||||
shuffle = _r.shuffle
|
||||
sample = _r.sample
|
||||
|
||||
# These are at the bottom to avoid problems with recursive imports
|
||||
from Crypto.Util.number import ceil_div, bytes_to_long, long_to_bytes, size
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,61 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# Util/Counter.py : Fast counter for use with CTR-mode ciphers
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
from Crypto.Util import _counter
|
||||
import struct
|
||||
|
||||
# Factory function
|
||||
def new(nbits, prefix="", suffix="", initial_value=1, overflow=0, little_endian=False, allow_wraparound=False, disable_shortcut=False):
|
||||
# TODO: Document this
|
||||
|
||||
# Sanity-check the message size
|
||||
(nbytes, remainder) = divmod(nbits, 8)
|
||||
if remainder != 0:
|
||||
# In the future, we might support arbitrary bit lengths, but for now we don't.
|
||||
raise ValueError("nbits must be a multiple of 8; got %d" % (nbits,))
|
||||
if nbytes < 1:
|
||||
raise ValueError("nbits too small")
|
||||
elif nbytes > 0xffff:
|
||||
raise ValueError("nbits too large")
|
||||
|
||||
initval = _encode(initial_value, nbytes, little_endian)
|
||||
if little_endian:
|
||||
return _counter._newLE(str(prefix), str(suffix), initval, allow_wraparound=allow_wraparound, disable_shortcut=disable_shortcut)
|
||||
else:
|
||||
return _counter._newBE(str(prefix), str(suffix), initval, allow_wraparound=allow_wraparound, disable_shortcut=disable_shortcut)
|
||||
|
||||
def _encode(n, nbytes, little_endian=False):
|
||||
retval = []
|
||||
n = long(n)
|
||||
for i in range(nbytes):
|
||||
if little_endian:
|
||||
retval.append(chr(n & 0xff))
|
||||
else:
|
||||
retval.insert(0, chr(n & 0xff))
|
||||
n >>= 8
|
||||
return "".join(retval)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,36 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Miscellaneous modules
|
||||
|
||||
Contains useful modules that don't belong into any of the
|
||||
other Crypto.* subpackages.
|
||||
|
||||
Crypto.Util.number Number-theoretic functions (primality testing, etc.)
|
||||
Crypto.Util.randpool Random number generation
|
||||
Crypto.Util.RFC1751 Converts between 128-bit keys and human-readable
|
||||
strings of words.
|
||||
|
||||
"""
|
||||
|
||||
__all__ = ['randpool', 'RFC1751', 'number', 'strxor']
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
Binary file not shown.
@ -1,117 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# Util/_number_new.py : utility functions
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
## NOTE: Do not import this module directly. Import these functions from Crypto.Util.number.
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = ['ceil_shift', 'ceil_div', 'floor_div', 'exact_log2', 'exact_div']
|
||||
|
||||
from Crypto.Util.python_compat import *
|
||||
|
||||
def ceil_shift(n, b):
|
||||
"""Return ceil(n / 2**b) without performing any floating-point or division operations.
|
||||
|
||||
This is done by right-shifting n by b bits and incrementing the result by 1
|
||||
if any '1' bits were shifted out.
|
||||
"""
|
||||
if not isinstance(n, (int, long)) or not isinstance(b, (int, long)):
|
||||
raise TypeError("unsupported operand type(s): %r and %r" % (type(n).__name__, type(b).__name__))
|
||||
|
||||
assert n >= 0 and b >= 0 # I haven't tested or even thought about negative values
|
||||
mask = (1L << b) - 1
|
||||
if n & mask:
|
||||
return (n >> b) + 1
|
||||
else:
|
||||
return n >> b
|
||||
|
||||
def ceil_div(a, b):
|
||||
"""Return ceil(a / b) without performing any floating-point operations."""
|
||||
|
||||
if not isinstance(a, (int, long)) or not isinstance(b, (int, long)):
|
||||
raise TypeError("unsupported operand type(s): %r and %r" % (type(a).__name__, type(b).__name__))
|
||||
|
||||
(q, r) = divmod(a, b)
|
||||
if r:
|
||||
return q + 1
|
||||
else:
|
||||
return q
|
||||
|
||||
def floor_div(a, b):
|
||||
if not isinstance(a, (int, long)) or not isinstance(b, (int, long)):
|
||||
raise TypeError("unsupported operand type(s): %r and %r" % (type(a).__name__, type(b).__name__))
|
||||
|
||||
(q, r) = divmod(a, b)
|
||||
return q
|
||||
|
||||
def exact_log2(num):
|
||||
"""Find and return an integer i >= 0 such that num == 2**i.
|
||||
|
||||
If no such integer exists, this function raises ValueError.
|
||||
"""
|
||||
|
||||
if not isinstance(num, (int, long)):
|
||||
raise TypeError("unsupported operand type: %r" % (type(num).__name__,))
|
||||
|
||||
n = long(num)
|
||||
if n <= 0:
|
||||
raise ValueError("cannot compute logarithm of non-positive number")
|
||||
|
||||
i = 0
|
||||
while n != 0:
|
||||
if (n & 1) and n != 1:
|
||||
raise ValueError("No solution could be found")
|
||||
i += 1
|
||||
n >>= 1
|
||||
i -= 1
|
||||
|
||||
assert num == (1L << i)
|
||||
return i
|
||||
|
||||
def exact_div(p, d, allow_divzero=False):
|
||||
"""Find and return an integer n such that p == n * d
|
||||
|
||||
If no such integer exists, this function raises ValueError.
|
||||
|
||||
Both operands must be integers.
|
||||
|
||||
If the second operand is zero, this function will raise ZeroDivisionError
|
||||
unless allow_divzero is true (default: False).
|
||||
"""
|
||||
|
||||
if not isinstance(p, (int, long)) or not isinstance(d, (int, long)):
|
||||
raise TypeError("unsupported operand type(s): %r and %r" % (type(p).__name__, type(d).__name__))
|
||||
|
||||
if d == 0 and allow_divzero:
|
||||
n = 0
|
||||
if p != n * d:
|
||||
raise ValueError("No solution could be found")
|
||||
else:
|
||||
(n, r) = divmod(p, d)
|
||||
if r != 0:
|
||||
raise ValueError("No solution could be found")
|
||||
|
||||
assert p == n * d
|
||||
return n
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,250 +0,0 @@
|
||||
#
|
||||
# number.py : Number-theoretic functions
|
||||
#
|
||||
# Part of the Python Cryptography Toolkit
|
||||
#
|
||||
# Written by Andrew M. Kuchling, Barry A. Warsaw, and others
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
#
|
||||
|
||||
__revision__ = "$Id$"
|
||||
|
||||
bignum = long
|
||||
try:
|
||||
from Crypto.PublicKey import _fastmath
|
||||
except ImportError:
|
||||
_fastmath = None
|
||||
|
||||
# New functions
|
||||
from _number_new import *
|
||||
|
||||
# Commented out and replaced with faster versions below
|
||||
## def long2str(n):
|
||||
## s=''
|
||||
## while n>0:
|
||||
## s=chr(n & 255)+s
|
||||
## n=n>>8
|
||||
## return s
|
||||
|
||||
## import types
|
||||
## def str2long(s):
|
||||
## if type(s)!=types.StringType: return s # Integers will be left alone
|
||||
## return reduce(lambda x,y : x*256+ord(y), s, 0L)
|
||||
|
||||
def size (N):
|
||||
"""size(N:long) : int
|
||||
Returns the size of the number N in bits.
|
||||
"""
|
||||
bits, power = 0,1L
|
||||
while N >= power:
|
||||
bits += 1
|
||||
power = power << 1
|
||||
return bits
|
||||
|
||||
def getRandomNumber(N, randfunc=None):
|
||||
"""getRandomNumber(N:int, randfunc:callable):long
|
||||
Return a random N-bit number.
|
||||
|
||||
If randfunc is omitted, then Random.new().read is used.
|
||||
|
||||
NOTE: Confusingly, this function does NOT return N random bits; It returns
|
||||
a random N-bit number, i.e. a random number between 2**(N-1) and (2**N)-1.
|
||||
|
||||
This function is for internal use only and may be renamed or removed in
|
||||
the future.
|
||||
"""
|
||||
if randfunc is None:
|
||||
_import_Random()
|
||||
randfunc = Random.new().read
|
||||
|
||||
S = randfunc(N/8)
|
||||
odd_bits = N % 8
|
||||
if odd_bits != 0:
|
||||
char = ord(randfunc(1)) >> (8-odd_bits)
|
||||
S = chr(char) + S
|
||||
value = bytes_to_long(S)
|
||||
value |= 2L ** (N-1) # Ensure high bit is set
|
||||
assert size(value) >= N
|
||||
return value
|
||||
|
||||
def GCD(x,y):
|
||||
"""GCD(x:long, y:long): long
|
||||
Return the GCD of x and y.
|
||||
"""
|
||||
x = abs(x) ; y = abs(y)
|
||||
while x > 0:
|
||||
x, y = y % x, x
|
||||
return y
|
||||
|
||||
def inverse(u, v):
|
||||
"""inverse(u:long, u:long):long
|
||||
Return the inverse of u mod v.
|
||||
"""
|
||||
u3, v3 = long(u), long(v)
|
||||
u1, v1 = 1L, 0L
|
||||
while v3 > 0:
|
||||
q=u3 / v3
|
||||
u1, v1 = v1, u1 - v1*q
|
||||
u3, v3 = v3, u3 - v3*q
|
||||
while u1<0:
|
||||
u1 = u1 + v
|
||||
return u1
|
||||
|
||||
# Given a number of bits to generate and a random generation function,
|
||||
# find a prime number of the appropriate size.
|
||||
|
||||
def getPrime(N, randfunc=None):
|
||||
"""getPrime(N:int, randfunc:callable):long
|
||||
Return a random N-bit prime number.
|
||||
|
||||
If randfunc is omitted, then Random.new().read is used.
|
||||
"""
|
||||
if randfunc is None:
|
||||
_import_Random()
|
||||
randfunc = Random.new().read
|
||||
|
||||
number=getRandomNumber(N, randfunc) | 1
|
||||
while (not isPrime(number, randfunc=randfunc)):
|
||||
number=number+2
|
||||
return number
|
||||
|
||||
def isPrime(N, randfunc=None):
|
||||
"""isPrime(N:long, randfunc:callable):bool
|
||||
Return true if N is prime.
|
||||
|
||||
If randfunc is omitted, then Random.new().read is used.
|
||||
"""
|
||||
_import_Random()
|
||||
if randfunc is None:
|
||||
randfunc = Random.new().read
|
||||
|
||||
randint = StrongRandom(randfunc=randfunc).randint
|
||||
|
||||
if N == 1:
|
||||
return 0
|
||||
if N in sieve:
|
||||
return 1
|
||||
for i in sieve:
|
||||
if (N % i)==0:
|
||||
return 0
|
||||
|
||||
# Use the accelerator if available
|
||||
if _fastmath is not None:
|
||||
return _fastmath.isPrime(N)
|
||||
|
||||
# Compute the highest bit that's set in N
|
||||
N1 = N - 1L
|
||||
n = 1L
|
||||
while (n<N):
|
||||
n=n<<1L
|
||||
n = n >> 1L
|
||||
|
||||
# Rabin-Miller test
|
||||
for c in sieve[:7]:
|
||||
a=long(c) ; d=1L ; t=n
|
||||
while (t): # Iterate over the bits in N1
|
||||
x=(d*d) % N
|
||||
if x==1L and d!=1L and d!=N1:
|
||||
return 0 # Square root of 1 found
|
||||
if N1 & t:
|
||||
d=(x*a) % N
|
||||
else:
|
||||
d=x
|
||||
t = t >> 1L
|
||||
if d!=1L:
|
||||
return 0
|
||||
return 1
|
||||
|
||||
# Small primes used for checking primality; these are all the primes
|
||||
# less than 256. This should be enough to eliminate most of the odd
|
||||
# numbers before needing to do a Rabin-Miller test at all.
|
||||
|
||||
sieve=[2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37, 41, 43, 47, 53, 59,
|
||||
61, 67, 71, 73, 79, 83, 89, 97, 101, 103, 107, 109, 113, 127,
|
||||
131, 137, 139, 149, 151, 157, 163, 167, 173, 179, 181, 191, 193,
|
||||
197, 199, 211, 223, 227, 229, 233, 239, 241, 251]
|
||||
|
||||
# Improved conversion functions contributed by Barry Warsaw, after
|
||||
# careful benchmarking
|
||||
|
||||
import struct
|
||||
|
||||
def long_to_bytes(n, blocksize=0):
|
||||
"""long_to_bytes(n:long, blocksize:int) : string
|
||||
Convert a long integer to a byte string.
|
||||
|
||||
If optional blocksize is given and greater than zero, pad the front of the
|
||||
byte string with binary zeros so that the length is a multiple of
|
||||
blocksize.
|
||||
"""
|
||||
# after much testing, this algorithm was deemed to be the fastest
|
||||
s = ''
|
||||
n = long(n)
|
||||
pack = struct.pack
|
||||
while n > 0:
|
||||
s = pack('>I', n & 0xffffffffL) + s
|
||||
n = n >> 32
|
||||
# strip off leading zeros
|
||||
for i in range(len(s)):
|
||||
if s[i] != '\000':
|
||||
break
|
||||
else:
|
||||
# only happens when n == 0
|
||||
s = '\000'
|
||||
i = 0
|
||||
s = s[i:]
|
||||
# add back some pad bytes. this could be done more efficiently w.r.t. the
|
||||
# de-padding being done above, but sigh...
|
||||
if blocksize > 0 and len(s) % blocksize:
|
||||
s = (blocksize - len(s) % blocksize) * '\000' + s
|
||||
return s
|
||||
|
||||
def bytes_to_long(s):
|
||||
"""bytes_to_long(string) : long
|
||||
Convert a byte string to a long integer.
|
||||
|
||||
This is (essentially) the inverse of long_to_bytes().
|
||||
"""
|
||||
acc = 0L
|
||||
unpack = struct.unpack
|
||||
length = len(s)
|
||||
if length % 4:
|
||||
extra = (4 - length % 4)
|
||||
s = '\000' * extra + s
|
||||
length = length + extra
|
||||
for i in range(0, length, 4):
|
||||
acc = (acc << 32) + unpack('>I', s[i:i+4])[0]
|
||||
return acc
|
||||
|
||||
# For backwards compatibility...
|
||||
import warnings
|
||||
def long2str(n, blocksize=0):
|
||||
warnings.warn("long2str() has been replaced by long_to_bytes()")
|
||||
return long_to_bytes(n, blocksize)
|
||||
def str2long(s):
|
||||
warnings.warn("str2long() has been replaced by bytes_to_long()")
|
||||
return bytes_to_long(s)
|
||||
|
||||
def _import_Random():
|
||||
# This is called in a function instead of at the module level in order to avoid problems with recursive imports
|
||||
global Random, StrongRandom
|
||||
from Crypto import Random
|
||||
from Crypto.Random.random import StrongRandom
|
||||
|
@ -1,84 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Util/python_compat.py : Compatibility code for old versions of Python
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Compatibility code for old versions of Python
|
||||
|
||||
Currently, this just defines:
|
||||
- True and False
|
||||
- object
|
||||
- isinstance
|
||||
"""
|
||||
|
||||
__revision__ = "$Id$"
|
||||
__all__ = []
|
||||
|
||||
import sys
|
||||
import __builtin__
|
||||
|
||||
# 'True' and 'False' aren't defined in Python 2.1. Define them.
|
||||
try:
|
||||
True, False
|
||||
except NameError:
|
||||
(True, False) = (1, 0)
|
||||
__all__ += ['True', 'False']
|
||||
|
||||
# New-style classes were introduced in Python 2.2. Defining "object" in Python
|
||||
# 2.1 lets us use new-style classes in versions of Python that support them,
|
||||
# while still maintaining backward compatibility with old-style classes
|
||||
try:
|
||||
object
|
||||
except NameError:
|
||||
class object: pass
|
||||
__all__ += ['object']
|
||||
|
||||
# Starting with Python 2.2, isinstance allows a tuple for the second argument.
|
||||
# Also, builtins like "tuple", "list", "str", "unicode", "int", and "long"
|
||||
# became first-class types, rather than functions. We want to support
|
||||
# constructs like:
|
||||
# isinstance(x, (int, long))
|
||||
# So we hack it for Python 2.1.
|
||||
try:
|
||||
isinstance(5, (int, long))
|
||||
except TypeError:
|
||||
__all__ += ['isinstance']
|
||||
_builtin_type_map = {
|
||||
tuple: type(()),
|
||||
list: type([]),
|
||||
str: type(""),
|
||||
unicode: type(u""),
|
||||
int: type(0),
|
||||
long: type(0L),
|
||||
}
|
||||
def isinstance(obj, t):
|
||||
if not __builtin__.isinstance(t, type(())):
|
||||
# t is not a tuple
|
||||
return __builtin__.isinstance(obj, _builtin_type_map.get(t, t))
|
||||
else:
|
||||
# t is a tuple
|
||||
for typ in t:
|
||||
if __builtin__.isinstance(obj, _builtin_type_map.get(typ, typ)):
|
||||
return True
|
||||
return False
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
@ -1,46 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
"""Python Cryptography Toolkit
|
||||
|
||||
A collection of cryptographic modules implementing various algorithms
|
||||
and protocols.
|
||||
|
||||
Subpackages:
|
||||
Crypto.Cipher Secret-key encryption algorithms (AES, DES, ARC4)
|
||||
Crypto.Hash Hashing algorithms (MD5, SHA, HMAC)
|
||||
Crypto.Protocol Cryptographic protocols (Chaffing, all-or-nothing
|
||||
transform). This package does not contain any
|
||||
network protocols.
|
||||
Crypto.PublicKey Public-key encryption and signature algorithms
|
||||
(RSA, DSA)
|
||||
Crypto.Util Various useful modules and functions (long-to-string
|
||||
conversion, random number generation, number
|
||||
theoretic functions)
|
||||
"""
|
||||
|
||||
__all__ = ['Cipher', 'Hash', 'Protocol', 'PublicKey', 'Util']
|
||||
|
||||
__version__ = '2.3' # See also below and setup.py
|
||||
__revision__ = "$Id$"
|
||||
|
||||
# New software should look at this instead of at __version__ above.
|
||||
version_info = (2, 1, 0, 'final', 0) # See also above and setup.py
|
||||
|
@ -1,57 +0,0 @@
|
||||
# -*- coding: ascii -*-
|
||||
#
|
||||
# pct_warnings.py : PyCrypto warnings file
|
||||
#
|
||||
# Written in 2008 by Dwayne C. Litzenberger <dlitz@dlitz.net>
|
||||
#
|
||||
# ===================================================================
|
||||
# The contents of this file are dedicated to the public domain. To
|
||||
# the extent that dedication to the public domain is not available,
|
||||
# everyone is granted a worldwide, perpetual, royalty-free,
|
||||
# non-exclusive license to exercise all rights associated with the
|
||||
# contents of this file for any purpose whatsoever.
|
||||
# No rights are reserved.
|
||||
#
|
||||
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
# SOFTWARE.
|
||||
# ===================================================================
|
||||
|
||||
#
|
||||
# Base classes. All our warnings inherit from one of these in order to allow
|
||||
# the user to specifically filter them.
|
||||
#
|
||||
|
||||
class CryptoWarning(Warning):
|
||||
"""Base class for PyCrypto warnings"""
|
||||
|
||||
class CryptoDeprecationWarning(DeprecationWarning, CryptoWarning):
|
||||
"""Base PyCrypto DeprecationWarning class"""
|
||||
|
||||
class CryptoRuntimeWarning(RuntimeWarning, CryptoWarning):
|
||||
"""Base PyCrypto RuntimeWarning class"""
|
||||
|
||||
#
|
||||
# Warnings that we might actually use
|
||||
#
|
||||
|
||||
class RandomPool_DeprecationWarning(CryptoDeprecationWarning):
|
||||
"""Issued when Crypto.Util.randpool.RandomPool is instantiated."""
|
||||
|
||||
class ClockRewindWarning(CryptoRuntimeWarning):
|
||||
"""Warning for when the system clock moves backwards."""
|
||||
|
||||
class GetRandomNumber_DeprecationWarning(CryptoDeprecationWarning):
|
||||
"""Issued when Crypto.Util.number.getRandomNumber is invoked."""
|
||||
|
||||
# By default, we want this warning to be shown every time we compensate for
|
||||
# clock rewinding.
|
||||
import warnings as _warnings
|
||||
_warnings.filterwarnings('always', category=ClockRewindWarning, append=1)
|
||||
|
||||
# vim:set ts=4 sw=4 sts=4 expandtab:
|
Binary file not shown.
@ -0,0 +1,346 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
"""
|
||||
Retrieve Adobe ADEPT user key.
|
||||
"""
|
||||
|
||||
from __future__ import with_statement
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
|
||||
import sys
|
||||
import os
|
||||
import struct
|
||||
from calibre.constants import iswindows, isosx
|
||||
|
||||
class ADEPTError(Exception):
|
||||
pass
|
||||
|
||||
if iswindows:
|
||||
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
|
||||
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
|
||||
string_at, Structure, c_void_p, cast, c_size_t, memmove, CDLL, c_int, \
|
||||
c_long, c_ulong
|
||||
|
||||
from ctypes.wintypes import LPVOID, DWORD, BOOL
|
||||
import _winreg as winreg
|
||||
|
||||
def _load_crypto_libcrypto():
|
||||
from ctypes.util import find_library
|
||||
libcrypto = find_library('libeay32')
|
||||
if libcrypto is None:
|
||||
raise ADEPTError('libcrypto not found')
|
||||
libcrypto = CDLL(libcrypto)
|
||||
AES_MAXNR = 14
|
||||
c_char_pp = POINTER(c_char_p)
|
||||
c_int_p = POINTER(c_int)
|
||||
class AES_KEY(Structure):
|
||||
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
|
||||
('rounds', c_int)]
|
||||
AES_KEY_p = POINTER(AES_KEY)
|
||||
|
||||
def F(restype, name, argtypes):
|
||||
func = getattr(libcrypto, name)
|
||||
func.restype = restype
|
||||
func.argtypes = argtypes
|
||||
return func
|
||||
|
||||
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
|
||||
[c_char_p, c_int, AES_KEY_p])
|
||||
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
|
||||
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
|
||||
c_int])
|
||||
class AES(object):
|
||||
def __init__(self, userkey):
|
||||
self._blocksize = len(userkey)
|
||||
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
|
||||
raise ADEPTError('AES improper key used')
|
||||
key = self._key = AES_KEY()
|
||||
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
|
||||
if rv < 0:
|
||||
raise ADEPTError('Failed to initialize AES key')
|
||||
def decrypt(self, data):
|
||||
out = create_string_buffer(len(data))
|
||||
iv = ("\x00" * self._blocksize)
|
||||
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
|
||||
if rv == 0:
|
||||
raise ADEPTError('AES decryption failed')
|
||||
return out.raw
|
||||
return AES
|
||||
|
||||
def _load_crypto_pycrypto():
|
||||
from Crypto.Cipher import AES as _AES
|
||||
class AES(object):
|
||||
def __init__(self, key):
|
||||
self._aes = _AES.new(key, _AES.MODE_CBC)
|
||||
def decrypt(self, data):
|
||||
return self._aes.decrypt(data)
|
||||
return AES
|
||||
|
||||
def _load_crypto():
|
||||
AES = None
|
||||
for loader in (_load_crypto_libcrypto, _load_crypto_pycrypto):
|
||||
try:
|
||||
AES = loader()
|
||||
break
|
||||
except (ImportError, ADEPTError):
|
||||
pass
|
||||
return AES
|
||||
|
||||
AES = _load_crypto()
|
||||
|
||||
|
||||
DEVICE_KEY_PATH = r'Software\Adobe\Adept\Device'
|
||||
PRIVATE_LICENCE_KEY_PATH = r'Software\Adobe\Adept\Activation'
|
||||
|
||||
MAX_PATH = 255
|
||||
|
||||
kernel32 = windll.kernel32
|
||||
advapi32 = windll.advapi32
|
||||
crypt32 = windll.crypt32
|
||||
|
||||
def GetSystemDirectory():
|
||||
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
|
||||
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
|
||||
GetSystemDirectoryW.restype = c_uint
|
||||
def GetSystemDirectory():
|
||||
buffer = create_unicode_buffer(MAX_PATH + 1)
|
||||
GetSystemDirectoryW(buffer, len(buffer))
|
||||
return buffer.value
|
||||
return GetSystemDirectory
|
||||
GetSystemDirectory = GetSystemDirectory()
|
||||
|
||||
def GetVolumeSerialNumber():
|
||||
GetVolumeInformationW = kernel32.GetVolumeInformationW
|
||||
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
|
||||
POINTER(c_uint), POINTER(c_uint),
|
||||
POINTER(c_uint), c_wchar_p, c_uint]
|
||||
GetVolumeInformationW.restype = c_uint
|
||||
def GetVolumeSerialNumber(path):
|
||||
vsn = c_uint(0)
|
||||
GetVolumeInformationW(
|
||||
path, None, 0, byref(vsn), None, None, None, 0)
|
||||
return vsn.value
|
||||
return GetVolumeSerialNumber
|
||||
GetVolumeSerialNumber = GetVolumeSerialNumber()
|
||||
|
||||
def GetUserName():
|
||||
GetUserNameW = advapi32.GetUserNameW
|
||||
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
|
||||
GetUserNameW.restype = c_uint
|
||||
def GetUserName():
|
||||
buffer = create_unicode_buffer(32)
|
||||
size = c_uint(len(buffer))
|
||||
while not GetUserNameW(buffer, byref(size)):
|
||||
buffer = create_unicode_buffer(len(buffer) * 2)
|
||||
size.value = len(buffer)
|
||||
return buffer.value.encode('utf-16-le')[::2]
|
||||
return GetUserName
|
||||
GetUserName = GetUserName()
|
||||
|
||||
PAGE_EXECUTE_READWRITE = 0x40
|
||||
MEM_COMMIT = 0x1000
|
||||
MEM_RESERVE = 0x2000
|
||||
|
||||
def VirtualAlloc():
|
||||
_VirtualAlloc = kernel32.VirtualAlloc
|
||||
_VirtualAlloc.argtypes = [LPVOID, c_size_t, DWORD, DWORD]
|
||||
_VirtualAlloc.restype = LPVOID
|
||||
def VirtualAlloc(addr, size, alloctype=(MEM_COMMIT | MEM_RESERVE),
|
||||
protect=PAGE_EXECUTE_READWRITE):
|
||||
return _VirtualAlloc(addr, size, alloctype, protect)
|
||||
return VirtualAlloc
|
||||
VirtualAlloc = VirtualAlloc()
|
||||
|
||||
MEM_RELEASE = 0x8000
|
||||
|
||||
def VirtualFree():
|
||||
_VirtualFree = kernel32.VirtualFree
|
||||
_VirtualFree.argtypes = [LPVOID, c_size_t, DWORD]
|
||||
_VirtualFree.restype = BOOL
|
||||
def VirtualFree(addr, size=0, freetype=MEM_RELEASE):
|
||||
return _VirtualFree(addr, size, freetype)
|
||||
return VirtualFree
|
||||
VirtualFree = VirtualFree()
|
||||
|
||||
class NativeFunction(object):
|
||||
def __init__(self, restype, argtypes, insns):
|
||||
self._buf = buf = VirtualAlloc(None, len(insns))
|
||||
memmove(buf, insns, len(insns))
|
||||
ftype = CFUNCTYPE(restype, *argtypes)
|
||||
self._native = ftype(buf)
|
||||
|
||||
def __call__(self, *args):
|
||||
return self._native(*args)
|
||||
|
||||
def __del__(self):
|
||||
if self._buf is not None:
|
||||
VirtualFree(self._buf)
|
||||
self._buf = None
|
||||
|
||||
if struct.calcsize("P") == 4:
|
||||
CPUID0_INSNS = (
|
||||
"\x53" # push %ebx
|
||||
"\x31\xc0" # xor %eax,%eax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x8b\x44\x24\x08" # mov 0x8(%esp),%eax
|
||||
"\x89\x18" # mov %ebx,0x0(%eax)
|
||||
"\x89\x50\x04" # mov %edx,0x4(%eax)
|
||||
"\x89\x48\x08" # mov %ecx,0x8(%eax)
|
||||
"\x5b" # pop %ebx
|
||||
"\xc3" # ret
|
||||
)
|
||||
CPUID1_INSNS = (
|
||||
"\x53" # push %ebx
|
||||
"\x31\xc0" # xor %eax,%eax
|
||||
"\x40" # inc %eax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x5b" # pop %ebx
|
||||
"\xc3" # ret
|
||||
)
|
||||
else:
|
||||
CPUID0_INSNS = (
|
||||
"\x49\x89\xd8" # mov %rbx,%r8
|
||||
"\x49\x89\xc9" # mov %rcx,%r9
|
||||
"\x48\x31\xc0" # xor %rax,%rax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x4c\x89\xc8" # mov %r9,%rax
|
||||
"\x89\x18" # mov %ebx,0x0(%rax)
|
||||
"\x89\x50\x04" # mov %edx,0x4(%rax)
|
||||
"\x89\x48\x08" # mov %ecx,0x8(%rax)
|
||||
"\x4c\x89\xc3" # mov %r8,%rbx
|
||||
"\xc3" # retq
|
||||
)
|
||||
CPUID1_INSNS = (
|
||||
"\x53" # push %rbx
|
||||
"\x48\x31\xc0" # xor %rax,%rax
|
||||
"\x48\xff\xc0" # inc %rax
|
||||
"\x0f\xa2" # cpuid
|
||||
"\x5b" # pop %rbx
|
||||
"\xc3" # retq
|
||||
)
|
||||
|
||||
def cpuid0():
|
||||
_cpuid0 = NativeFunction(None, [c_char_p], CPUID0_INSNS)
|
||||
buf = create_string_buffer(12)
|
||||
def cpuid0():
|
||||
_cpuid0(buf)
|
||||
return buf.raw
|
||||
return cpuid0
|
||||
cpuid0 = cpuid0()
|
||||
|
||||
cpuid1 = NativeFunction(c_uint, [], CPUID1_INSNS)
|
||||
|
||||
class DataBlob(Structure):
|
||||
_fields_ = [('cbData', c_uint),
|
||||
('pbData', c_void_p)]
|
||||
DataBlob_p = POINTER(DataBlob)
|
||||
|
||||
def CryptUnprotectData():
|
||||
_CryptUnprotectData = crypt32.CryptUnprotectData
|
||||
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
|
||||
c_void_p, c_void_p, c_uint, DataBlob_p]
|
||||
_CryptUnprotectData.restype = c_uint
|
||||
def CryptUnprotectData(indata, entropy):
|
||||
indatab = create_string_buffer(indata)
|
||||
indata = DataBlob(len(indata), cast(indatab, c_void_p))
|
||||
entropyb = create_string_buffer(entropy)
|
||||
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
|
||||
outdata = DataBlob()
|
||||
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
|
||||
None, None, 0, byref(outdata)):
|
||||
raise ADEPTError("Failed to decrypt user key key (sic)")
|
||||
return string_at(outdata.pbData, outdata.cbData)
|
||||
return CryptUnprotectData
|
||||
CryptUnprotectData = CryptUnprotectData()
|
||||
|
||||
def retrieve_key():
|
||||
if AES is None:
|
||||
tkMessageBox.showerror(
|
||||
"ADEPT Key",
|
||||
"This script requires PyCrypto or OpenSSL which must be installed "
|
||||
"separately. Read the top-of-script comment for details.")
|
||||
return False
|
||||
root = GetSystemDirectory().split('\\')[0] + '\\'
|
||||
serial = GetVolumeSerialNumber(root)
|
||||
vendor = cpuid0()
|
||||
signature = struct.pack('>I', cpuid1())[1:]
|
||||
user = GetUserName()
|
||||
entropy = struct.pack('>I12s3s13s', serial, vendor, signature, user)
|
||||
cuser = winreg.HKEY_CURRENT_USER
|
||||
try:
|
||||
regkey = winreg.OpenKey(cuser, DEVICE_KEY_PATH)
|
||||
except WindowsError:
|
||||
raise ADEPTError("Adobe Digital Editions not activated")
|
||||
device = winreg.QueryValueEx(regkey, 'key')[0]
|
||||
keykey = CryptUnprotectData(device, entropy)
|
||||
userkey = None
|
||||
try:
|
||||
plkroot = winreg.OpenKey(cuser, PRIVATE_LICENCE_KEY_PATH)
|
||||
except WindowsError:
|
||||
raise ADEPTError("Could not locate ADE activation")
|
||||
for i in xrange(0, 16):
|
||||
try:
|
||||
plkparent = winreg.OpenKey(plkroot, "%04d" % (i,))
|
||||
except WindowsError:
|
||||
break
|
||||
ktype = winreg.QueryValueEx(plkparent, None)[0]
|
||||
if ktype != 'credentials':
|
||||
continue
|
||||
for j in xrange(0, 16):
|
||||
try:
|
||||
plkkey = winreg.OpenKey(plkparent, "%04d" % (j,))
|
||||
except WindowsError:
|
||||
break
|
||||
ktype = winreg.QueryValueEx(plkkey, None)[0]
|
||||
if ktype != 'privateLicenseKey':
|
||||
continue
|
||||
userkey = winreg.QueryValueEx(plkkey, 'value')[0]
|
||||
break
|
||||
if userkey is not None:
|
||||
break
|
||||
if userkey is None:
|
||||
raise ADEPTError('Could not locate privateLicenseKey')
|
||||
userkey = userkey.decode('base64')
|
||||
aes = AES(keykey)
|
||||
userkey = aes.decrypt(userkey)
|
||||
userkey = userkey[26:-ord(userkey[-1])]
|
||||
return userkey
|
||||
|
||||
else:
|
||||
|
||||
import xml.etree.ElementTree as etree
|
||||
import subprocess
|
||||
|
||||
NSMAP = {'adept': 'http://ns.adobe.com/adept',
|
||||
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
|
||||
|
||||
def findActivationDat():
|
||||
home = os.getenv('HOME')
|
||||
cmdline = 'find "' + home + '/Library/Application Support/Adobe/Digital Editions" -name "activation.dat"'
|
||||
cmdline = cmdline.encode(sys.getfilesystemencoding())
|
||||
p2 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
|
||||
out1, out2 = p2.communicate()
|
||||
reslst = out1.split('\n')
|
||||
cnt = len(reslst)
|
||||
for j in xrange(cnt):
|
||||
resline = reslst[j]
|
||||
pp = resline.find('activation.dat')
|
||||
if pp >= 0:
|
||||
ActDatPath = resline
|
||||
break
|
||||
if os.path.exists(ActDatPath):
|
||||
return ActDatPath
|
||||
return None
|
||||
|
||||
def retrieve_key():
|
||||
actpath = findActivationDat()
|
||||
if actpath is None:
|
||||
raise ADEPTError("Could not locate ADE activation")
|
||||
tree = etree.parse(actpath)
|
||||
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
|
||||
expr = '//%s/%s' % (adept('credentials'), adept('privateLicenseKey'))
|
||||
userkey = tree.findtext(expr)
|
||||
userkey = userkey.decode('base64')
|
||||
userkey = userkey[26:]
|
||||
return userkey
|
File diff suppressed because it is too large
Load Diff
Binary file not shown.
Binary file not shown.
@ -0,0 +1,817 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
# For use with Topaz Scripts Version 2.6
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
# Get a 7 bit encoded number from string. The most
|
||||
# significant byte comes first and has the high bit (8th) set
|
||||
|
||||
def readEncodedNumber(file):
|
||||
flag = False
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
|
||||
# returns a binary string that encodes a number into 7 bits
|
||||
# most significant byte first which has the high bit set
|
||||
|
||||
def encodeNumber(number):
|
||||
result = ""
|
||||
negative = False
|
||||
flag = 0
|
||||
|
||||
if number < 0 :
|
||||
number = -number + 1
|
||||
negative = True
|
||||
|
||||
while True:
|
||||
byte = number & 0x7F
|
||||
number = number >> 7
|
||||
byte += flag
|
||||
result += chr(byte)
|
||||
flag = 0x80
|
||||
if number == 0 :
|
||||
if (byte == 0xFF and negative == False) :
|
||||
result += chr(0x80)
|
||||
break
|
||||
|
||||
if negative:
|
||||
result += chr(0xFF)
|
||||
|
||||
return result[::-1]
|
||||
|
||||
|
||||
|
||||
# create / read a length prefixed string from the file
|
||||
|
||||
def lengthPrefixString(data):
|
||||
return encodeNumber(len(data))+data
|
||||
|
||||
def readString(file):
|
||||
stringLength = readEncodedNumber(file)
|
||||
if (stringLength == None):
|
||||
return ""
|
||||
sv = file.read(stringLength)
|
||||
if (len(sv) != stringLength):
|
||||
return ""
|
||||
return unpack(str(stringLength)+"s",sv)[0]
|
||||
|
||||
|
||||
# convert a binary string generated by encodeNumber (7 bit encoded number)
|
||||
# to the value you would find inside the page*.dat files to be processed
|
||||
|
||||
def convert(i):
|
||||
result = ''
|
||||
val = encodeNumber(i)
|
||||
for j in xrange(len(val)):
|
||||
c = ord(val[j:j+1])
|
||||
result += '%02x' % c
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# the complete string table used to store all book text content
|
||||
# as well as the xml tokens and values that make sense out of it
|
||||
|
||||
class Dictionary(object):
|
||||
def __init__(self, dictFile):
|
||||
self.filename = dictFile
|
||||
self.size = 0
|
||||
self.fo = file(dictFile,'rb')
|
||||
self.stable = []
|
||||
self.size = readEncodedNumber(self.fo)
|
||||
for i in xrange(self.size):
|
||||
self.stable.append(self.escapestr(readString(self.fo)))
|
||||
self.pos = 0
|
||||
|
||||
def escapestr(self, str):
|
||||
str = str.replace('&','&')
|
||||
str = str.replace('<','<')
|
||||
str = str.replace('>','>')
|
||||
str = str.replace('=','=')
|
||||
return str
|
||||
|
||||
def lookup(self,val):
|
||||
if ((val >= 0) and (val < self.size)) :
|
||||
self.pos = val
|
||||
return self.stable[self.pos]
|
||||
else:
|
||||
print "Error - %d outside of string table limits" % val
|
||||
sys.exit(-1)
|
||||
|
||||
def getSize(self):
|
||||
return self.size
|
||||
|
||||
def getPos(self):
|
||||
return self.pos
|
||||
|
||||
def dumpDict(self):
|
||||
for i in xrange(self.size):
|
||||
print "%d %s %s" % (i, convert(i), self.stable[i])
|
||||
return
|
||||
|
||||
# parses the xml snippets that are represented by each page*.dat file.
|
||||
# also parses the other0.dat file - the main stylesheet
|
||||
# and information used to inject the xml snippets into page*.dat files
|
||||
|
||||
class PageParser(object):
|
||||
def __init__(self, filename, dict, debug, flat_xml):
|
||||
self.fo = file(filename,'rb')
|
||||
self.id = os.path.basename(filename).replace('.dat','')
|
||||
self.dict = dict
|
||||
self.debug = debug
|
||||
self.flat_xml = flat_xml
|
||||
self.tagpath = []
|
||||
self.doc = []
|
||||
self.snippetList = []
|
||||
|
||||
|
||||
# hash table used to enable the decoding process
|
||||
# This has all been developed by trial and error so it may still have omissions or
|
||||
# contain errors
|
||||
# Format:
|
||||
# tag : (number of arguments, argument type, subtags present, special case of subtags presents when escaped)
|
||||
|
||||
token_tags = {
|
||||
'x' : (1, 'scalar_number', 0, 0),
|
||||
'y' : (1, 'scalar_number', 0, 0),
|
||||
'h' : (1, 'scalar_number', 0, 0),
|
||||
'w' : (1, 'scalar_number', 0, 0),
|
||||
'firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'lastWord' : (1, 'scalar_number', 0, 0),
|
||||
'rootID' : (1, 'scalar_number', 0, 0),
|
||||
'stemID' : (1, 'scalar_number', 0, 0),
|
||||
'type' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'info' : (0, 'number', 1, 0),
|
||||
|
||||
'info.word' : (0, 'number', 1, 1),
|
||||
'info.word.ocrText' : (1, 'text', 0, 0),
|
||||
'info.word.firstGlyph' : (1, 'raw', 0, 0),
|
||||
'info.word.lastGlyph' : (1, 'raw', 0, 0),
|
||||
'info.word.bl' : (1, 'raw', 0, 0),
|
||||
'info.word.link_id' : (1, 'number', 0, 0),
|
||||
|
||||
'glyph' : (0, 'number', 1, 1),
|
||||
'glyph.x' : (1, 'number', 0, 0),
|
||||
'glyph.y' : (1, 'number', 0, 0),
|
||||
'glyph.glyphID' : (1, 'number', 0, 0),
|
||||
|
||||
'dehyphen' : (0, 'number', 1, 1),
|
||||
'dehyphen.rootID' : (1, 'number', 0, 0),
|
||||
'dehyphen.stemID' : (1, 'number', 0, 0),
|
||||
'dehyphen.stemPage' : (1, 'number', 0, 0),
|
||||
'dehyphen.sh' : (1, 'number', 0, 0),
|
||||
|
||||
'links' : (0, 'number', 1, 1),
|
||||
'links.page' : (1, 'number', 0, 0),
|
||||
'links.rel' : (1, 'number', 0, 0),
|
||||
'links.row' : (1, 'number', 0, 0),
|
||||
'links.title' : (1, 'text', 0, 0),
|
||||
'links.href' : (1, 'text', 0, 0),
|
||||
'links.type' : (1, 'text', 0, 0),
|
||||
|
||||
'paraCont' : (0, 'number', 1, 1),
|
||||
'paraCont.rootID' : (1, 'number', 0, 0),
|
||||
'paraCont.stemID' : (1, 'number', 0, 0),
|
||||
'paraCont.stemPage' : (1, 'number', 0, 0),
|
||||
|
||||
'paraStems' : (0, 'number', 1, 1),
|
||||
'paraStems.stemID' : (1, 'number', 0, 0),
|
||||
|
||||
'wordStems' : (0, 'number', 1, 1),
|
||||
'wordStems.stemID' : (1, 'number', 0, 0),
|
||||
|
||||
'empty' : (1, 'snippets', 1, 0),
|
||||
|
||||
'page' : (1, 'snippets', 1, 0),
|
||||
'page.pageid' : (1, 'scalar_text', 0, 0),
|
||||
'page.pagelabel' : (1, 'scalar_text', 0, 0),
|
||||
'page.type' : (1, 'scalar_text', 0, 0),
|
||||
'page.h' : (1, 'scalar_number', 0, 0),
|
||||
'page.w' : (1, 'scalar_number', 0, 0),
|
||||
'page.startID' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'group' : (1, 'snippets', 1, 0),
|
||||
'group.type' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'region' : (1, 'snippets', 1, 0),
|
||||
'region.type' : (1, 'scalar_text', 0, 0),
|
||||
'region.x' : (1, 'scalar_number', 0, 0),
|
||||
'region.y' : (1, 'scalar_number', 0, 0),
|
||||
'region.h' : (1, 'scalar_number', 0, 0),
|
||||
'region.w' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'empty_text_region' : (1, 'snippets', 1, 0),
|
||||
|
||||
'img' : (1, 'snippets', 1, 0),
|
||||
'img.x' : (1, 'scalar_number', 0, 0),
|
||||
'img.y' : (1, 'scalar_number', 0, 0),
|
||||
'img.h' : (1, 'scalar_number', 0, 0),
|
||||
'img.w' : (1, 'scalar_number', 0, 0),
|
||||
'img.src' : (1, 'scalar_number', 0, 0),
|
||||
'img.color_src' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'paragraph' : (1, 'snippets', 1, 0),
|
||||
'paragraph.class' : (1, 'scalar_text', 0, 0),
|
||||
'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'paragraph.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'word_semantic' : (1, 'snippets', 1, 1),
|
||||
'word_semantic.type' : (1, 'scalar_text', 0, 0),
|
||||
'word_semantic.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'word_semantic.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'word' : (1, 'snippets', 1, 0),
|
||||
'word.type' : (1, 'scalar_text', 0, 0),
|
||||
'word.class' : (1, 'scalar_text', 0, 0),
|
||||
'word.firstGlyph' : (1, 'scalar_number', 0, 0),
|
||||
'word.lastGlyph' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'_span' : (1, 'snippets', 1, 0),
|
||||
'_span.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'-span.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'span' : (1, 'snippets', 1, 0),
|
||||
'span.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'span.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'extratokens' : (1, 'snippets', 1, 0),
|
||||
'extratokens.type' : (1, 'scalar_text', 0, 0),
|
||||
'extratokens.firstGlyph' : (1, 'scalar_number', 0, 0),
|
||||
'extratokens.lastGlyph' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'glyph.h' : (1, 'number', 0, 0),
|
||||
'glyph.w' : (1, 'number', 0, 0),
|
||||
'glyph.use' : (1, 'number', 0, 0),
|
||||
'glyph.vtx' : (1, 'number', 0, 1),
|
||||
'glyph.len' : (1, 'number', 0, 1),
|
||||
'glyph.dpi' : (1, 'number', 0, 0),
|
||||
'vtx' : (0, 'number', 1, 1),
|
||||
'vtx.x' : (1, 'number', 0, 0),
|
||||
'vtx.y' : (1, 'number', 0, 0),
|
||||
'len' : (0, 'number', 1, 1),
|
||||
'len.n' : (1, 'number', 0, 0),
|
||||
|
||||
'book' : (1, 'snippets', 1, 0),
|
||||
'version' : (1, 'snippets', 1, 0),
|
||||
'version.FlowEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.FlowEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.Schema_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.Schema_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.Topaz_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.WordDetailEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.WordDetailEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.ZoneEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.ZoneEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.chapterheaders' : (1, 'scalar_text', 0, 0),
|
||||
'version.creation_date' : (1, 'scalar_text', 0, 0),
|
||||
'version.header_footer' : (1, 'scalar_text', 0, 0),
|
||||
'version.init_from_ocr' : (1, 'scalar_text', 0, 0),
|
||||
'version.letter_insertion' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_convert' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_reflow' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_transform' : (1, 'scalar_text', 0, 0),
|
||||
'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),
|
||||
'style._tag' : (1, 'scalar_text', 0, 0),
|
||||
'style.type' : (1, 'scalar_text', 0, 0),
|
||||
'style._parent_type' : (1, 'scalar_text', 0, 0),
|
||||
'style.class' : (1, 'scalar_text', 0, 0),
|
||||
'style._after_class' : (1, 'scalar_text', 0, 0),
|
||||
'rule' : (1, 'snippets', 1, 0),
|
||||
'rule.attr' : (1, 'scalar_text', 0, 0),
|
||||
'rule.value' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'original' : (0, 'number', 1, 1),
|
||||
'original.pnum' : (1, 'number', 0, 0),
|
||||
'original.pid' : (1, 'text', 0, 0),
|
||||
'pages' : (0, 'number', 1, 1),
|
||||
'pages.ref' : (1, 'number', 0, 0),
|
||||
'pages.id' : (1, 'number', 0, 0),
|
||||
'startID' : (0, 'number', 1, 1),
|
||||
'startID.page' : (1, 'number', 0, 0),
|
||||
'startID.id' : (1, 'number', 0, 0),
|
||||
|
||||
}
|
||||
|
||||
|
||||
# full tag path record keeping routines
|
||||
def tag_push(self, token):
|
||||
self.tagpath.append(token)
|
||||
def tag_pop(self):
|
||||
if len(self.tagpath) > 0 :
|
||||
self.tagpath.pop()
|
||||
def tagpath_len(self):
|
||||
return len(self.tagpath)
|
||||
def get_tagpath(self, i):
|
||||
cnt = len(self.tagpath)
|
||||
if i < cnt : result = self.tagpath[i]
|
||||
for j in xrange(i+1, cnt) :
|
||||
result += '.' + self.tagpath[j]
|
||||
return result
|
||||
|
||||
|
||||
# list of absolute command byte values values that indicate
|
||||
# various types of loop meachanisms typically used to generate vectors
|
||||
|
||||
cmd_list = (0x76, 0x76)
|
||||
|
||||
# peek at and return 1 byte that is ahead by i bytes
|
||||
def peek(self, aheadi):
|
||||
c = self.fo.read(aheadi)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
self.fo.seek(-aheadi,1)
|
||||
c = c[-1:]
|
||||
return ord(c)
|
||||
|
||||
|
||||
# get the next value from the file being processed
|
||||
def getNext(self):
|
||||
nbyte = self.peek(1);
|
||||
if (nbyte == None):
|
||||
return None
|
||||
val = readEncodedNumber(self.fo)
|
||||
return val
|
||||
|
||||
|
||||
# format an arg by argtype
|
||||
def formatArg(self, arg, argtype):
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
result = self.dict.lookup(arg)
|
||||
elif (argtype == 'raw') or (argtype == 'number') or (argtype == 'scalar_number') :
|
||||
result = arg
|
||||
elif (argtype == 'snippets') :
|
||||
result = arg
|
||||
else :
|
||||
print "Error Unknown argtype %s" % argtype
|
||||
sys.exit(-2)
|
||||
return result
|
||||
|
||||
|
||||
# process the next tag token, recursively handling subtags,
|
||||
# arguments, and commands
|
||||
def procToken(self, token):
|
||||
|
||||
known_token = False
|
||||
self.tag_push(token)
|
||||
|
||||
if self.debug : print 'Processing: ', self.get_tagpath(0)
|
||||
cnt = self.tagpath_len()
|
||||
for j in xrange(cnt):
|
||||
tkn = self.get_tagpath(j)
|
||||
if tkn in self.token_tags :
|
||||
num_args = self.token_tags[tkn][0]
|
||||
argtype = self.token_tags[tkn][1]
|
||||
subtags = self.token_tags[tkn][2]
|
||||
splcase = self.token_tags[tkn][3]
|
||||
ntags = -1
|
||||
known_token = True
|
||||
break
|
||||
|
||||
if known_token :
|
||||
|
||||
# handle subtags if present
|
||||
subtagres = []
|
||||
if (splcase == 1):
|
||||
# this type of tag uses of escape marker 0x74 indicate subtag count
|
||||
if self.peek(1) == 0x74:
|
||||
skip = readEncodedNumber(self.fo)
|
||||
subtags = 1
|
||||
num_args = 0
|
||||
|
||||
if (subtags == 1):
|
||||
ntags = readEncodedNumber(self.fo)
|
||||
if self.debug : print 'subtags: ' + token + ' has ' + str(ntags)
|
||||
for j in xrange(ntags):
|
||||
val = readEncodedNumber(self.fo)
|
||||
subtagres.append(self.procToken(self.dict.lookup(val)))
|
||||
|
||||
# arguments can be scalars or vectors of text or numbers
|
||||
argres = []
|
||||
if num_args > 0 :
|
||||
firstarg = self.peek(1)
|
||||
if (firstarg in self.cmd_list) and (argtype != 'scalar_number') and (argtype != 'scalar_text'):
|
||||
# single argument is a variable length vector of data
|
||||
arg = readEncodedNumber(self.fo)
|
||||
argres = self.decodeCMD(arg,argtype)
|
||||
else :
|
||||
# num_arg scalar arguments
|
||||
for i in xrange(num_args):
|
||||
argres.append(self.formatArg(readEncodedNumber(self.fo), argtype))
|
||||
|
||||
# build the return tag
|
||||
result = []
|
||||
tkn = self.get_tagpath(0)
|
||||
result.append(tkn)
|
||||
result.append(subtagres)
|
||||
result.append(argtype)
|
||||
result.append(argres)
|
||||
self.tag_pop()
|
||||
return result
|
||||
|
||||
# all tokens that need to be processed should be in the hash
|
||||
# table if it may indicate a problem, either new token
|
||||
# or an out of sync condition
|
||||
else:
|
||||
result = []
|
||||
if (self.debug):
|
||||
print 'Unknown Token:', token
|
||||
self.tag_pop()
|
||||
return result
|
||||
|
||||
|
||||
# special loop used to process code snippets
|
||||
# it is NEVER used to format arguments.
|
||||
# builds the snippetList
|
||||
def doLoop72(self, argtype):
|
||||
cnt = readEncodedNumber(self.fo)
|
||||
if self.debug :
|
||||
result = 'Set of '+ str(cnt) + ' xml snippets. The overall structure \n'
|
||||
result += 'of the document is indicated by snippet number sets at the\n'
|
||||
result += 'end of each snippet. \n'
|
||||
print result
|
||||
for i in xrange(cnt):
|
||||
if self.debug: print 'Snippet:',str(i)
|
||||
snippet = []
|
||||
snippet.append(i)
|
||||
val = readEncodedNumber(self.fo)
|
||||
snippet.append(self.procToken(self.dict.lookup(val)))
|
||||
self.snippetList.append(snippet)
|
||||
return
|
||||
|
||||
|
||||
|
||||
# general loop code gracisouly submitted by "skindle" - thank you!
|
||||
def doLoop76Mode(self, argtype, cnt, mode):
|
||||
result = []
|
||||
adj = 0
|
||||
if mode & 1:
|
||||
adj = readEncodedNumber(self.fo)
|
||||
mode = mode >> 1
|
||||
x = []
|
||||
for i in xrange(cnt):
|
||||
x.append(readEncodedNumber(self.fo) - adj)
|
||||
for i in xrange(mode):
|
||||
for j in xrange(1, cnt):
|
||||
x[j] = x[j] + x[j - 1]
|
||||
for i in xrange(cnt):
|
||||
result.append(self.formatArg(x[i],argtype))
|
||||
return result
|
||||
|
||||
|
||||
# dispatches loop commands bytes with various modes
|
||||
# The 0x76 style loops are used to build vectors
|
||||
|
||||
# This was all derived by trial and error and
|
||||
# new loop types may exist that are not handled here
|
||||
# since they did not appear in the test cases
|
||||
|
||||
def decodeCMD(self, cmd, argtype):
|
||||
if (cmd == 0x76):
|
||||
|
||||
# loop with cnt, and mode to control loop styles
|
||||
cnt = readEncodedNumber(self.fo)
|
||||
mode = readEncodedNumber(self.fo)
|
||||
|
||||
if self.debug : print 'Loop for', cnt, 'with mode', mode, ': '
|
||||
return self.doLoop76Mode(argtype, cnt, mode)
|
||||
|
||||
if self.dbug: print "Unknown command", cmd
|
||||
result = []
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# add full tag path to injected snippets
|
||||
def updateName(self, tag, prefix):
|
||||
name = tag[0]
|
||||
subtagList = tag[1]
|
||||
argtype = tag[2]
|
||||
argList = tag[3]
|
||||
nname = prefix + '.' + name
|
||||
nsubtaglist = []
|
||||
for j in subtagList:
|
||||
nsubtaglist.append(self.updateName(j,prefix))
|
||||
ntag = []
|
||||
ntag.append(nname)
|
||||
ntag.append(nsubtaglist)
|
||||
ntag.append(argtype)
|
||||
ntag.append(argList)
|
||||
return ntag
|
||||
|
||||
|
||||
|
||||
# perform depth first injection of specified snippets into this one
|
||||
def injectSnippets(self, snippet):
|
||||
snipno, tag = snippet
|
||||
name = tag[0]
|
||||
subtagList = tag[1]
|
||||
argtype = tag[2]
|
||||
argList = tag[3]
|
||||
nsubtagList = []
|
||||
if len(argList) > 0 :
|
||||
for j in argList:
|
||||
asnip = self.snippetList[j]
|
||||
aso, atag = self.injectSnippets(asnip)
|
||||
atag = self.updateName(atag, name)
|
||||
nsubtagList.append(atag)
|
||||
argtype='number'
|
||||
argList=[]
|
||||
if len(nsubtagList) > 0 :
|
||||
subtagList.extend(nsubtagList)
|
||||
tag = []
|
||||
tag.append(name)
|
||||
tag.append(subtagList)
|
||||
tag.append(argtype)
|
||||
tag.append(argList)
|
||||
snippet = []
|
||||
snippet.append(snipno)
|
||||
snippet.append(tag)
|
||||
return snippet
|
||||
|
||||
|
||||
|
||||
# format the tag for output
|
||||
def formatTag(self, node):
|
||||
name = node[0]
|
||||
subtagList = node[1]
|
||||
argtype = node[2]
|
||||
argList = node[3]
|
||||
fullpathname = name.split('.')
|
||||
nodename = fullpathname.pop()
|
||||
ilvl = len(fullpathname)
|
||||
indent = ' ' * (3 * ilvl)
|
||||
result = indent + '<' + nodename + '>'
|
||||
if len(argList) > 0:
|
||||
argres = ''
|
||||
for j in argList:
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
argres += j + '|'
|
||||
else :
|
||||
argres += str(j) + ','
|
||||
argres = argres[0:-1]
|
||||
if argtype == 'snippets' :
|
||||
result += 'snippets:' + argres
|
||||
else :
|
||||
result += argres
|
||||
if len(subtagList) > 0 :
|
||||
result += '\n'
|
||||
for j in subtagList:
|
||||
if len(j) > 0 :
|
||||
result += self.formatTag(j)
|
||||
result += indent + '</' + nodename + '>\n'
|
||||
else:
|
||||
result += '</' + nodename + '>\n'
|
||||
return result
|
||||
|
||||
|
||||
# flatten tag
|
||||
def flattenTag(self, node):
|
||||
name = node[0]
|
||||
subtagList = node[1]
|
||||
argtype = node[2]
|
||||
argList = node[3]
|
||||
result = name
|
||||
if (len(argList) > 0):
|
||||
argres = ''
|
||||
for j in argList:
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
argres += j + '|'
|
||||
else :
|
||||
argres += str(j) + '|'
|
||||
argres = argres[0:-1]
|
||||
if argtype == 'snippets' :
|
||||
result += '.snippets=' + argres
|
||||
else :
|
||||
result += '=' + argres
|
||||
result += '\n'
|
||||
for j in subtagList:
|
||||
if len(j) > 0 :
|
||||
result += self.flattenTag(j)
|
||||
return result
|
||||
|
||||
|
||||
# reduce create xml output
|
||||
def formatDoc(self, flat_xml):
|
||||
result = ''
|
||||
for j in self.doc :
|
||||
if len(j) > 0:
|
||||
if flat_xml:
|
||||
result += self.flattenTag(j)
|
||||
else:
|
||||
result += self.formatTag(j)
|
||||
if self.debug : print result
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# main loop - parse the page.dat files
|
||||
# to create structured document and snippets
|
||||
|
||||
# FIXME: value at end of magic appears to be a subtags count
|
||||
# but for what? For now, inject an 'info" tag as it is in
|
||||
# every dictionary and seems close to what is meant
|
||||
# The alternative is to special case the last _ "0x5f" to mean something
|
||||
|
||||
def process(self):
|
||||
|
||||
# peek at the first bytes to see what type of file it is
|
||||
magic = self.fo.read(9)
|
||||
if (magic[0:1] == 'p') and (magic[2:9] == 'marker_'):
|
||||
first_token = 'info'
|
||||
elif (magic[0:1] == 'p') and (magic[2:9] == '__PAGE_'):
|
||||
skip = self.fo.read(2)
|
||||
first_token = 'info'
|
||||
elif (magic[0:1] == 'p') and (magic[2:8] == '_PAGE_'):
|
||||
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(-9,1)
|
||||
|
||||
|
||||
# main loop to read and build the document tree
|
||||
while True:
|
||||
|
||||
if first_token != None :
|
||||
# use "inserted" first token 'info' for page and glyph files
|
||||
tag = self.procToken(first_token)
|
||||
if len(tag) > 0 :
|
||||
self.doc.append(tag)
|
||||
first_token = None
|
||||
|
||||
v = self.getNext()
|
||||
if (v == None):
|
||||
break
|
||||
|
||||
if (v == 0x72):
|
||||
self.doLoop72('number')
|
||||
elif (v > 0) and (v < self.dict.getSize()) :
|
||||
tag = self.procToken(self.dict.lookup(v))
|
||||
if len(tag) > 0 :
|
||||
self.doc.append(tag)
|
||||
else:
|
||||
if self.debug:
|
||||
print "Main Loop: Unknown value: %x" % v
|
||||
if (v == 0):
|
||||
if (self.peek(1) == 0x5f):
|
||||
skip = self.fo.read(1)
|
||||
first_token = 'info'
|
||||
|
||||
# now do snippet injection
|
||||
if len(self.snippetList) > 0 :
|
||||
if self.debug : print 'Injecting Snippets:'
|
||||
snippet = self.injectSnippets(self.snippetList[0])
|
||||
snipno = snippet[0]
|
||||
tag_add = snippet[1]
|
||||
if self.debug : print self.formatTag(tag_add)
|
||||
if len(tag_add) > 0:
|
||||
self.doc.append(tag_add)
|
||||
|
||||
# handle generation of xml output
|
||||
xmlpage = self.formatDoc(self.flat_xml)
|
||||
|
||||
return xmlpage
|
||||
|
||||
|
||||
def fromData(dict, fname):
|
||||
flat_xml = True
|
||||
debug = False
|
||||
pp = PageParser(fname, dict, debug, flat_xml)
|
||||
xmlpage = pp.process()
|
||||
return xmlpage
|
||||
|
||||
def getXML(dict, fname):
|
||||
flat_xml = False
|
||||
debug = False
|
||||
pp = PageParser(fname, dict, debug, flat_xml)
|
||||
xmlpage = pp.process()
|
||||
return xmlpage
|
||||
|
||||
def usage():
|
||||
print 'Usage: '
|
||||
print ' convert2xml.py dict0000.dat infile.dat '
|
||||
print ' '
|
||||
print ' Options:'
|
||||
print ' -h print this usage help message '
|
||||
print ' -d turn on debug output to check for potential errors '
|
||||
print ' --flat-xml output the flattened xml page description only '
|
||||
print ' '
|
||||
print ' This program will attempt to convert a page*.dat file or '
|
||||
print ' glyphs*.dat file, using the dict0000.dat file, to its xml description. '
|
||||
print ' '
|
||||
print ' Use "cmbtc_dump.py" first to unencrypt, uncompress, and dump '
|
||||
print ' the *.dat files from a Topaz format e-book.'
|
||||
|
||||
#
|
||||
# Main
|
||||
#
|
||||
|
||||
def main(argv):
|
||||
dictFile = ""
|
||||
pageFile = ""
|
||||
debug = False
|
||||
flat_xml = False
|
||||
printOutput = False
|
||||
if len(argv) == 0:
|
||||
printOutput = True
|
||||
argv = sys.argv
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(argv[1:], "hd", ["flat-xml"])
|
||||
|
||||
except getopt.GetoptError, err:
|
||||
|
||||
# print help information and exit:
|
||||
print str(err) # will print something like "option -a not recognized"
|
||||
usage()
|
||||
sys.exit(2)
|
||||
|
||||
if len(opts) == 0 and len(args) == 0 :
|
||||
usage()
|
||||
sys.exit(2)
|
||||
|
||||
for o, a in opts:
|
||||
if o =="-d":
|
||||
debug=True
|
||||
if o =="-h":
|
||||
usage()
|
||||
sys.exit(0)
|
||||
if o =="--flat-xml":
|
||||
flat_xml = True
|
||||
|
||||
dictFile, pageFile = args[0], args[1]
|
||||
|
||||
# read in the string table dictionary
|
||||
dict = Dictionary(dictFile)
|
||||
# dict.dumpDict()
|
||||
|
||||
# create a page parser
|
||||
pp = PageParser(pageFile, dict, debug, flat_xml)
|
||||
|
||||
xmlpage = pp.process()
|
||||
|
||||
if printOutput:
|
||||
print xmlpage
|
||||
return 0
|
||||
|
||||
return xmlpage
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main(''))
|
@ -0,0 +1,706 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
# For use with Topaz Scripts Version 2.6
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import math
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class DocParser(object):
|
||||
def __init__(self, flatxml, classlst, fileid, bookDir, gdict, fixedimage):
|
||||
self.id = os.path.basename(fileid).replace('.dat','')
|
||||
self.svgcount = 0
|
||||
self.docList = flatxml.split('\n')
|
||||
self.docSize = len(self.docList)
|
||||
self.classList = {}
|
||||
self.bookDir = bookDir
|
||||
self.gdict = gdict
|
||||
tmpList = classlst.split('\n')
|
||||
for pclass in tmpList:
|
||||
if pclass != '':
|
||||
# remove the leading period from the css name
|
||||
cname = pclass[1:]
|
||||
self.classList[cname] = True
|
||||
self.fixedimage = fixedimage
|
||||
self.ocrtext = []
|
||||
self.link_id = []
|
||||
self.link_title = []
|
||||
self.link_page = []
|
||||
self.link_href = []
|
||||
self.link_type = []
|
||||
self.dehyphen_rootid = []
|
||||
self.paracont_stemid = []
|
||||
self.parastems_stemid = []
|
||||
|
||||
|
||||
def getGlyph(self, gid):
|
||||
result = ''
|
||||
id='id="gl%d"' % gid
|
||||
return self.gdict.lookup(id)
|
||||
|
||||
def glyphs_to_image(self, glyphList):
|
||||
|
||||
def extract(path, key):
|
||||
b = path.find(key) + len(key)
|
||||
e = path.find(' ',b)
|
||||
return int(path[b:e])
|
||||
|
||||
svgDir = os.path.join(self.bookDir,'svg')
|
||||
|
||||
imgDir = os.path.join(self.bookDir,'img')
|
||||
imgname = self.id + '_%04d.svg' % self.svgcount
|
||||
imgfile = os.path.join(imgDir,imgname)
|
||||
|
||||
# get glyph information
|
||||
gxList = self.getData('info.glyph.x',0,-1)
|
||||
gyList = self.getData('info.glyph.y',0,-1)
|
||||
gidList = self.getData('info.glyph.glyphID',0,-1)
|
||||
|
||||
gids = []
|
||||
maxws = []
|
||||
maxhs = []
|
||||
xs = []
|
||||
ys = []
|
||||
gdefs = []
|
||||
|
||||
# get path defintions, positions, dimensions for ecah glyph
|
||||
# that makes up the image, and find min x and min y to reposition origin
|
||||
minx = -1
|
||||
miny = -1
|
||||
for j in glyphList:
|
||||
gid = gidList[j]
|
||||
gids.append(gid)
|
||||
|
||||
xs.append(gxList[j])
|
||||
if minx == -1: minx = gxList[j]
|
||||
else : minx = min(minx, gxList[j])
|
||||
|
||||
ys.append(gyList[j])
|
||||
if miny == -1: miny = gyList[j]
|
||||
else : miny = min(miny, gyList[j])
|
||||
|
||||
path = self.getGlyph(gid)
|
||||
gdefs.append(path)
|
||||
|
||||
maxws.append(extract(path,'width='))
|
||||
maxhs.append(extract(path,'height='))
|
||||
|
||||
|
||||
# change the origin to minx, miny and calc max height and width
|
||||
maxw = maxws[0] + xs[0] - minx
|
||||
maxh = maxhs[0] + ys[0] - miny
|
||||
for j in xrange(0, len(xs)):
|
||||
xs[j] = xs[j] - minx
|
||||
ys[j] = ys[j] - miny
|
||||
maxw = max( maxw, (maxws[j] + xs[j]) )
|
||||
maxh = max( maxh, (maxhs[j] + ys[j]) )
|
||||
|
||||
# open the image file for output
|
||||
ifile = open(imgfile,'w')
|
||||
ifile.write('<?xml version="1.0" standalone="no"?>\n')
|
||||
ifile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
|
||||
ifile.write('<svg width="%dpx" height="%dpx" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (math.floor(maxw/10), math.floor(maxh/10), maxw, maxh))
|
||||
ifile.write('<defs>\n')
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ifile.write(gdefs[j])
|
||||
ifile.write('</defs>\n')
|
||||
for j in xrange(0,len(gids)):
|
||||
ifile.write('<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (gids[j], xs[j], ys[j]))
|
||||
ifile.write('</svg>')
|
||||
ifile.close()
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
# return tag at line pos in document
|
||||
def lineinDoc(self, pos) :
|
||||
if (pos >= 0) and (pos < self.docSize) :
|
||||
item = self.docList[pos]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
return name, argres
|
||||
|
||||
|
||||
# find tag in doc if within pos to end inclusive
|
||||
def findinDoc(self, tagpath, pos, end) :
|
||||
result = None
|
||||
if end == -1 :
|
||||
end = self.docSize
|
||||
else:
|
||||
end = min(self.docSize, end)
|
||||
foundat = -1
|
||||
for j in xrange(pos, end):
|
||||
item = self.docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
result = argres
|
||||
foundat = j
|
||||
break
|
||||
return foundat, result
|
||||
|
||||
|
||||
# return list of start positions for the tagpath
|
||||
def posinDoc(self, tagpath):
|
||||
startpos = []
|
||||
pos = 0
|
||||
res = ""
|
||||
while res != None :
|
||||
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
|
||||
if res != None :
|
||||
startpos.append(foundpos)
|
||||
pos = foundpos + 1
|
||||
return startpos
|
||||
|
||||
|
||||
# returns a vector of integers for the tagpath
|
||||
def getData(self, tagpath, pos, end):
|
||||
argres=[]
|
||||
(foundat, argt) = self.findinDoc(tagpath, pos, end)
|
||||
if (argt != None) and (len(argt) > 0) :
|
||||
argList = argt.split('|')
|
||||
argres = [ int(strval) for strval in argList]
|
||||
return argres
|
||||
|
||||
|
||||
# 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
|
||||
# from a base class (but then not actually provide all of these _reclustereed
|
||||
# classes in the stylesheet!
|
||||
|
||||
# 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
|
||||
baseclass = ''
|
||||
# graphic is the base class for captions
|
||||
if nclass.find('cl-cap-') >=0 :
|
||||
classres = 'graphic' + ' '
|
||||
else :
|
||||
# strip to find baseclass
|
||||
p = nclass.find('_')
|
||||
if p > 0 :
|
||||
baseclass = nclass[0:p]
|
||||
if baseclass in self.classList:
|
||||
classres += baseclass + ' '
|
||||
classres += nclass
|
||||
nclass = classres
|
||||
return nclass
|
||||
|
||||
|
||||
# develop a sorted description of the starting positions of
|
||||
# groups and regions on the page, as well as the page type
|
||||
def PageDescription(self):
|
||||
|
||||
def compare(x, y):
|
||||
(xtype, xval) = x
|
||||
(ytype, yval) = y
|
||||
if xval > yval:
|
||||
return 1
|
||||
if xval == yval:
|
||||
return 0
|
||||
return -1
|
||||
|
||||
result = []
|
||||
(pos, pagetype) = self.findinDoc('page.type',0,-1)
|
||||
|
||||
groupList = self.posinDoc('page.group')
|
||||
groupregionList = self.posinDoc('page.group.region')
|
||||
pageregionList = self.posinDoc('page.region')
|
||||
# integrate into one list
|
||||
for j in groupList:
|
||||
result.append(('grpbeg',j))
|
||||
for j in groupregionList:
|
||||
result.append(('gregion',j))
|
||||
for j in pageregionList:
|
||||
result.append(('pregion',j))
|
||||
result.sort(compare)
|
||||
|
||||
# insert group end and page end indicators
|
||||
inGroup = False
|
||||
j = 0
|
||||
while True:
|
||||
if j == len(result): break
|
||||
rtype = result[j][0]
|
||||
rval = result[j][1]
|
||||
if not inGroup and (rtype == 'grpbeg') :
|
||||
inGroup = True
|
||||
j = j + 1
|
||||
elif inGroup and (rtype in ('grpbeg', 'pregion')):
|
||||
result.insert(j,('grpend',rval))
|
||||
inGroup = False
|
||||
else:
|
||||
j = j + 1
|
||||
if inGroup:
|
||||
result.append(('grpend',-1))
|
||||
result.append(('pageend', -1))
|
||||
return pagetype, result
|
||||
|
||||
|
||||
|
||||
# build a description of the paragraph
|
||||
def getParaDescription(self, start, end, regtype):
|
||||
|
||||
result = []
|
||||
|
||||
# paragraph
|
||||
(pos, pclass) = self.findinDoc('paragraph.class',start,end)
|
||||
|
||||
pclass = self.getClass(pclass)
|
||||
|
||||
# build up a description of the paragraph in result and return it
|
||||
# first check for the basic - all words paragraph
|
||||
(pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
|
||||
(pos, slast) = self.findinDoc('paragraph.lastWord',start,end)
|
||||
if (sfirst != None) and (slast != None) :
|
||||
first = int(sfirst)
|
||||
last = int(slast)
|
||||
|
||||
makeImage = (regtype == 'vertical') or (regtype == 'table')
|
||||
if self.fixedimage:
|
||||
makeImage = makeImage or (regtype == 'fixed')
|
||||
|
||||
if (pclass != None):
|
||||
makeImage = makeImage or (pclass.find('.inverted') >= 0)
|
||||
if self.fixedimage :
|
||||
makeImage = makeImage or (pclass.find('cl-f-') >= 0)
|
||||
|
||||
if not makeImage :
|
||||
# standard all word paragraph
|
||||
for wordnum in xrange(first, last):
|
||||
result.append(('ocr', wordnum))
|
||||
return pclass, result
|
||||
|
||||
# convert paragraph to svg image
|
||||
# translate first and last word into first and last glyphs
|
||||
# and generate inline image and include it
|
||||
glyphList = []
|
||||
firstglyphList = self.getData('word.firstGlyph',0,-1)
|
||||
gidList = self.getData('info.glyph.glyphID',0,-1)
|
||||
firstGlyph = firstglyphList[first]
|
||||
if last < len(firstglyphList):
|
||||
lastGlyph = firstglyphList[last]
|
||||
else :
|
||||
lastGlyph = len(gidList)
|
||||
for glyphnum in xrange(firstGlyph, lastGlyph):
|
||||
glyphList.append(glyphnum)
|
||||
# include any extratokens if they exist
|
||||
(pos, sfg) = self.findinDoc('extratokens.firstGlyph',start,end)
|
||||
(pos, slg) = self.findinDoc('extratokens.lastGlyph',start,end)
|
||||
if (sfg != None) and (slg != None):
|
||||
for glyphnum in xrange(int(sfg), int(slg)):
|
||||
glyphList.append(glyphnum)
|
||||
num = self.svgcount
|
||||
self.glyphs_to_image(glyphList)
|
||||
self.svgcount += 1
|
||||
result.append(('svg', num))
|
||||
return pclass, result
|
||||
|
||||
# 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
|
||||
|
||||
# need to parse this type line by line
|
||||
line = start + 1
|
||||
word_class = ''
|
||||
|
||||
# if end is -1 then we must search to end of document
|
||||
if end == -1 :
|
||||
end = self.docSize
|
||||
|
||||
# seems some xml has last* coming before first* so we have to
|
||||
# handle any order
|
||||
sp_first = -1
|
||||
sp_last = -1
|
||||
|
||||
gl_first = -1
|
||||
gl_last = -1
|
||||
|
||||
ws_first = -1
|
||||
ws_last = -1
|
||||
|
||||
word_class = ''
|
||||
|
||||
while (line < end) :
|
||||
|
||||
(name, argres) = self.lineinDoc(line)
|
||||
|
||||
if name.endswith('span.firstWord') :
|
||||
sp_first = int(argres)
|
||||
|
||||
elif name.endswith('span.lastWord') :
|
||||
sp_last = int(argres)
|
||||
|
||||
elif name.endswith('word.firstGlyph') :
|
||||
gl_first = int(argres)
|
||||
|
||||
elif name.endswith('word.lastGlyph') :
|
||||
gl_last = int(argres)
|
||||
|
||||
elif name.endswith('word_semantic.firstWord'):
|
||||
ws_first = int(argres)
|
||||
|
||||
elif name.endswith('word_semantic.lastWord'):
|
||||
ws_last = int(argres)
|
||||
|
||||
elif name.endswith('word.class'):
|
||||
(cname, space) = argres.split('-',1)
|
||||
if space == '' : space = '0'
|
||||
if (cname == 'spaceafter') and (int(space) > 0) :
|
||||
word_class = 'sa'
|
||||
|
||||
elif name.endswith('word.img.src'):
|
||||
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))
|
||||
sp_first = -1
|
||||
sp_last = -1
|
||||
|
||||
if (gl_first != -1) and (gl_last != -1):
|
||||
glyphList = []
|
||||
for glyphnum in xrange(gl_first, gl_last):
|
||||
glyphList.append(glyphnum)
|
||||
num = self.svgcount
|
||||
self.glyphs_to_image(glyphList)
|
||||
self.svgcount += 1
|
||||
result.append(('svg', num))
|
||||
gl_first = -1
|
||||
gl_last = -1
|
||||
|
||||
if (ws_first != -1) and (ws_last != -1):
|
||||
for wordnum in xrange(ws_first, ws_last):
|
||||
result.append(('ocr', wordnum))
|
||||
ws_first = -1
|
||||
ws_last = -1
|
||||
|
||||
line += 1
|
||||
|
||||
return pclass, result
|
||||
|
||||
|
||||
def buildParagraph(self, pclass, pdesc, type, regtype) :
|
||||
parares = ''
|
||||
sep =''
|
||||
|
||||
classres = ''
|
||||
if pclass :
|
||||
classres = ' class="' + pclass + '"'
|
||||
|
||||
br_lb = (regtype == 'fixed') or (regtype == 'chapterheading') or (regtype == 'vertical')
|
||||
|
||||
handle_links = len(self.link_id) > 0
|
||||
|
||||
if (type == 'full') or (type == 'begin') :
|
||||
parares += '<p' + classres + '>'
|
||||
|
||||
if (type == 'end'):
|
||||
parares += ' '
|
||||
|
||||
lstart = len(parares)
|
||||
|
||||
cnt = len(pdesc)
|
||||
|
||||
for j in xrange( 0, cnt) :
|
||||
|
||||
(wtype, num) = pdesc[j]
|
||||
|
||||
if wtype == 'ocr' :
|
||||
word = self.ocrtext[num]
|
||||
sep = ' '
|
||||
|
||||
if handle_links:
|
||||
link = self.link_id[num]
|
||||
if (link > 0):
|
||||
linktype = self.link_type[link-1]
|
||||
title = self.link_title[link-1]
|
||||
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 = ''
|
||||
|
||||
if word == '_lb_':
|
||||
if ((num-1) in self.dehyphen_rootid ) or handle_links:
|
||||
word = ''
|
||||
sep = ''
|
||||
elif br_lb :
|
||||
word = '<br />\n'
|
||||
sep = ''
|
||||
else :
|
||||
word = '\n'
|
||||
sep = ''
|
||||
|
||||
if num in self.dehyphen_rootid :
|
||||
word = word[0:-1]
|
||||
sep = ''
|
||||
|
||||
parares += word + sep
|
||||
|
||||
elif wtype == 'img' :
|
||||
sep = ''
|
||||
parares += '<img src="img/img%04d.jpg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
elif wtype == 'imgsa' :
|
||||
sep = ' '
|
||||
parares += '<img src="img/img%04d.jpg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
elif wtype == 'svg' :
|
||||
sep = ''
|
||||
parares += '<img src="img/' + self.id + '_%04d.svg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
if len(sep) > 0 : parares = parares[0:-1]
|
||||
if (type == 'full') or (type == 'end') :
|
||||
parares += '</p>'
|
||||
return parares
|
||||
|
||||
|
||||
|
||||
# walk the document tree collecting the information needed
|
||||
# to build an html page using the ocrText
|
||||
|
||||
def process(self):
|
||||
|
||||
htmlpage = ''
|
||||
|
||||
# get the ocr text
|
||||
(pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
|
||||
if argres : self.ocrtext = argres.split('|')
|
||||
|
||||
# get information to dehyphenate the text
|
||||
self.dehyphen_rootid = self.getData('info.dehyphen.rootID',0,-1)
|
||||
|
||||
# determine if first paragraph is continued from previous page
|
||||
(pos, self.parastems_stemid) = self.findinDoc('info.paraStems.stemID',0,-1)
|
||||
first_para_continued = (self.parastems_stemid != None)
|
||||
|
||||
# determine if last paragraph is continued onto the next page
|
||||
(pos, self.paracont_stemid) = self.findinDoc('info.paraCont.stemID',0,-1)
|
||||
last_para_continued = (self.paracont_stemid != None)
|
||||
|
||||
# collect link ids
|
||||
self.link_id = self.getData('info.word.link_id',0,-1)
|
||||
|
||||
# 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 :
|
||||
self.link_title = argres.split('|')
|
||||
else:
|
||||
self.link_title.append('')
|
||||
|
||||
# get a descriptions of the starting points of the regions
|
||||
# and groups on the page
|
||||
(pagetype, pageDesc) = self.PageDescription()
|
||||
regcnt = len(pageDesc) - 1
|
||||
|
||||
anchorSet = False
|
||||
breakSet = False
|
||||
inGroup = False
|
||||
|
||||
# process each region on the page and convert what you can to html
|
||||
|
||||
for j in xrange(regcnt):
|
||||
|
||||
(etype, start) = pageDesc[j]
|
||||
(ntype, end) = pageDesc[j+1]
|
||||
|
||||
|
||||
# set anchor for link target on this page
|
||||
if not anchorSet and not first_para_continued:
|
||||
htmlpage += '<div style="visibility: hidden; height: 0; width: 0;" id="'
|
||||
htmlpage += self.id + '" title="pagetype_' + pagetype + '"></div>\n'
|
||||
anchorSet = True
|
||||
|
||||
# handle groups of graphics with text captions
|
||||
if (etype == 'grpbeg'):
|
||||
(pos, grptype) = self.findinDoc('group.type', start, end)
|
||||
if grptype != None:
|
||||
if grptype == 'graphic':
|
||||
gcstr = ' class="' + grptype + '"'
|
||||
htmlpage += '<div' + gcstr + '>'
|
||||
inGroup = True
|
||||
|
||||
elif (etype == 'grpend'):
|
||||
if inGroup:
|
||||
htmlpage += '</div>\n'
|
||||
inGroup = False
|
||||
|
||||
else:
|
||||
(pos, regtype) = self.findinDoc('region.type',start,end)
|
||||
|
||||
if regtype == 'graphic' :
|
||||
(pos, simgsrc) = self.findinDoc('img.src',start,end)
|
||||
if simgsrc:
|
||||
if inGroup:
|
||||
htmlpage += '<img src="img/img%04d.jpg" alt="" />' % int(simgsrc)
|
||||
else:
|
||||
htmlpage += '<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc)
|
||||
|
||||
elif regtype == 'chapterheading' :
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
if not breakSet:
|
||||
htmlpage += '<div style="page-break-after: always;"> </div>\n'
|
||||
breakSet = True
|
||||
tag = 'h1'
|
||||
if pclass and (len(pclass) >= 7):
|
||||
if pclass[3:7] == 'ch1-' : tag = 'h1'
|
||||
if pclass[3:7] == 'ch2-' : tag = 'h2'
|
||||
if pclass[3:7] == 'ch3-' : tag = 'h3'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
else:
|
||||
htmlpage += '<' + tag + '>'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
|
||||
elif (regtype == 'text') or (regtype == 'fixed') or (regtype == 'insert') or (regtype == 'listitem'):
|
||||
ptype = 'full'
|
||||
# check to see if this is a continution from the previous page
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
if pclass and (len(pclass) >= 6) and (ptype == 'full'):
|
||||
tag = 'p'
|
||||
if pclass[3:6] == 'h1-' : tag = 'h4'
|
||||
if pclass[3:6] == 'h2-' : tag = 'h5'
|
||||
if pclass[3:6] == 'h3-' : tag = 'h6'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
else :
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
elif (regtype == 'tocentry') :
|
||||
ptype = 'full'
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
|
||||
elif (regtype == 'vertical') or (regtype == 'table') :
|
||||
ptype = 'full'
|
||||
if inGroup:
|
||||
ptype = 'middle'
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start, end, regtype)
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
|
||||
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 ' Making region type', regtype,
|
||||
(pos, temp) = self.findinDoc('paragraph',start,end)
|
||||
(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
|
||||
if first_para_continued :
|
||||
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'
|
||||
if pclass[3:6] == 'h2-' : tag = 'h5'
|
||||
if pclass[3:6] == 'h3-' : tag = 'h6'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
else :
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
else :
|
||||
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)
|
||||
|
||||
|
||||
if last_para_continued :
|
||||
if htmlpage[-4:] == '</p>':
|
||||
htmlpage = htmlpage[0:-4]
|
||||
last_para_continued = False
|
||||
|
||||
return htmlpage
|
||||
|
||||
|
||||
|
||||
def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
|
||||
# create a document parser
|
||||
dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
|
||||
htmlpage = dp.process()
|
||||
return htmlpage
|
@ -0,0 +1,151 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class PParser(object):
|
||||
def __init__(self, gd, flatxml):
|
||||
self.gd = gd
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.temp = []
|
||||
foo = self.getData('page.h') or self.getData('book.h')
|
||||
self.ph = foo[0]
|
||||
foo = self.getData('page.w') or self.getData('book.w')
|
||||
self.pw = foo[0]
|
||||
self.gx = self.getData('info.glyph.x')
|
||||
self.gy = self.getData('info.glyph.y')
|
||||
self.gid = self.getData('info.glyph.glyphID')
|
||||
def getData(self, path):
|
||||
result = None
|
||||
cnt = len(self.flatdoc)
|
||||
for j in xrange(cnt):
|
||||
item = self.flatdoc[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getDataTemp(self, path):
|
||||
result = None
|
||||
cnt = len(self.temp)
|
||||
for j in xrange(cnt):
|
||||
item = self.temp[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
self.temp.pop(j)
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getImages(self):
|
||||
result = []
|
||||
self.temp = self.flatdoc
|
||||
while (self.getDataTemp('img') != None):
|
||||
h = self.getDataTemp('img.h')[0]
|
||||
w = self.getDataTemp('img.w')[0]
|
||||
x = self.getDataTemp('img.x')[0]
|
||||
y = self.getDataTemp('img.y')[0]
|
||||
src = self.getDataTemp('img.src')[0]
|
||||
result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
|
||||
return result
|
||||
def getGlyphs(self):
|
||||
result = []
|
||||
if (self.gid != None) and (len(self.gid) > 0):
|
||||
glyphs = []
|
||||
for j in set(self.gid):
|
||||
glyphs.append(j)
|
||||
glyphs.sort()
|
||||
for gid in glyphs:
|
||||
id='id="gl%d"' % gid
|
||||
path = self.gd.lookup(id)
|
||||
if path:
|
||||
result.append(id + ' ' + path)
|
||||
return result
|
||||
|
||||
|
||||
def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
|
||||
ml = ''
|
||||
pp = PParser(gdict, flat_xml)
|
||||
ml += '<?xml version="1.0" standalone="no"?>\n'
|
||||
if (raw):
|
||||
ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
|
||||
ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
else:
|
||||
ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
ml += '<script><![CDATA[\n'
|
||||
ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
|
||||
ml += 'var dpi=%d;\n' % scaledpi
|
||||
if (counter) :
|
||||
ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
|
||||
if (counter < numfiles-1) :
|
||||
ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
|
||||
ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
|
||||
ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
|
||||
ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
|
||||
ml += 'function setsize(){var svg=document.getElementById("svgimg");var prev=document.getElementById("prevsvg");var next=document.getElementById("nextsvg");var width=(pw/dpi)+"in";var height=(ph/dpi)+"in";svg.setAttribute("width",width);svg.setAttribute("height",height);prev.setAttribute("height",height);prev.setAttribute("width","50px");next.setAttribute("height",height);next.setAttribute("width","50px");}\n'
|
||||
ml += 'function ppage(){window.location.href=prevpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'function npage(){window.location.href=nextpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'var gt=gd();if(gt>0){dpi=gt;}\n'
|
||||
ml += 'window.onload=setsize;\n'
|
||||
ml += ']]></script>\n'
|
||||
ml += '</head>\n'
|
||||
ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
|
||||
ml += '<div style="white-space:nowrap;">\n'
|
||||
if (counter == 0) :
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else:
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
|
||||
if (pp.gid != None):
|
||||
ml += '<defs>\n'
|
||||
gdefs = pp.getGlyphs()
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ml += gdefs[j]
|
||||
ml += '</defs>\n'
|
||||
img = pp.getImages()
|
||||
if (img != None):
|
||||
for j in xrange(0,len(img)):
|
||||
ml += img[j]
|
||||
if (pp.gid != None):
|
||||
for j in xrange(0,len(pp.gid)):
|
||||
ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
|
||||
if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
|
||||
ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content. (gensvg.py)</text>\n'
|
||||
if (raw) :
|
||||
ml += '</svg>'
|
||||
else :
|
||||
ml += '</svg></a>\n'
|
||||
if (counter == numfiles - 1) :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '</div>\n'
|
||||
ml += '<div><a href="javascript:zoomin();">zoom in</a> - <a href="javascript:zoomout();">zoom out</a></div>\n'
|
||||
ml += '</body>\n'
|
||||
ml += '</html>\n'
|
||||
return ml
|
||||
|
@ -0,0 +1,561 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
# local support routines
|
||||
import convert2xml
|
||||
import flatxml2html
|
||||
import flatxml2svg
|
||||
import stylexml2css
|
||||
|
||||
|
||||
# Get a 7 bit encoded number from a file
|
||||
def readEncodedNumber(file):
|
||||
flag = False
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
# Get a length prefixed string from the file
|
||||
def lengthPrefixString(data):
|
||||
return encodeNumber(len(data))+data
|
||||
|
||||
def readString(file):
|
||||
stringLength = readEncodedNumber(file)
|
||||
if (stringLength == None):
|
||||
return None
|
||||
sv = file.read(stringLength)
|
||||
if (len(sv) != stringLength):
|
||||
return ""
|
||||
return unpack(str(stringLength)+"s",sv)[0]
|
||||
|
||||
def getMetaArray(metaFile):
|
||||
# parse the meta file
|
||||
result = {}
|
||||
fo = file(metaFile,'rb')
|
||||
size = readEncodedNumber(fo)
|
||||
for i in xrange(size):
|
||||
tag = readString(fo)
|
||||
value = readString(fo)
|
||||
result[tag] = value
|
||||
# print tag, value
|
||||
fo.close()
|
||||
return result
|
||||
|
||||
|
||||
# dictionary of all text strings by index value
|
||||
class Dictionary(object):
|
||||
def __init__(self, dictFile):
|
||||
self.filename = dictFile
|
||||
self.size = 0
|
||||
self.fo = file(dictFile,'rb')
|
||||
self.stable = []
|
||||
self.size = readEncodedNumber(self.fo)
|
||||
for i in xrange(self.size):
|
||||
self.stable.append(self.escapestr(readString(self.fo)))
|
||||
self.pos = 0
|
||||
def escapestr(self, str):
|
||||
str = str.replace('&','&')
|
||||
str = str.replace('<','<')
|
||||
str = str.replace('>','>')
|
||||
str = str.replace('=','=')
|
||||
return str
|
||||
def lookup(self,val):
|
||||
if ((val >= 0) and (val < self.size)) :
|
||||
self.pos = val
|
||||
return self.stable[self.pos]
|
||||
else:
|
||||
print "Error - %d outside of string table limits" % val
|
||||
sys.exit(-1)
|
||||
def getSize(self):
|
||||
return self.size
|
||||
def getPos(self):
|
||||
return self.pos
|
||||
|
||||
|
||||
class PageDimParser(object):
|
||||
def __init__(self, flatxml):
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
# find tag if within pos to end inclusive
|
||||
def findinDoc(self, tagpath, pos, end) :
|
||||
result = None
|
||||
docList = self.flatdoc
|
||||
cnt = len(docList)
|
||||
if end == -1 :
|
||||
end = cnt
|
||||
else:
|
||||
end = min(cnt,end)
|
||||
foundat = -1
|
||||
for j in xrange(pos, end):
|
||||
item = docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=')
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
result = argres
|
||||
foundat = j
|
||||
break
|
||||
return foundat, result
|
||||
def process(self):
|
||||
(pos, sph) = self.findinDoc('page.h',0,-1)
|
||||
(pos, spw) = self.findinDoc('page.w',0,-1)
|
||||
if (sph == None): sph = '-1'
|
||||
if (spw == None): spw = '-1'
|
||||
return sph, spw
|
||||
|
||||
def getPageDim(flatxml):
|
||||
# create a document parser
|
||||
dp = PageDimParser(flatxml)
|
||||
(ph, pw) = dp.process()
|
||||
return ph, pw
|
||||
|
||||
class GParser(object):
|
||||
def __init__(self, flatxml):
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.dpi = 1440
|
||||
self.gh = self.getData('info.glyph.h')
|
||||
self.gw = self.getData('info.glyph.w')
|
||||
self.guse = self.getData('info.glyph.use')
|
||||
if self.guse :
|
||||
self.count = len(self.guse)
|
||||
else :
|
||||
self.count = 0
|
||||
self.gvtx = self.getData('info.glyph.vtx')
|
||||
self.glen = self.getData('info.glyph.len')
|
||||
self.gdpi = self.getData('info.glyph.dpi')
|
||||
self.vx = self.getData('info.vtx.x')
|
||||
self.vy = self.getData('info.vtx.y')
|
||||
self.vlen = self.getData('info.len.n')
|
||||
if self.vlen :
|
||||
self.glen.append(len(self.vlen))
|
||||
elif self.glen:
|
||||
self.glen.append(0)
|
||||
if self.vx :
|
||||
self.gvtx.append(len(self.vx))
|
||||
elif self.gvtx :
|
||||
self.gvtx.append(0)
|
||||
def getData(self, path):
|
||||
result = None
|
||||
cnt = len(self.flatdoc)
|
||||
for j in xrange(cnt):
|
||||
item = self.flatdoc[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name == path):
|
||||
result = argres
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getGlyphDim(self, gly):
|
||||
maxh = (self.gh[gly] * self.dpi) / self.gdpi[gly]
|
||||
maxw = (self.gw[gly] * self.dpi) / self.gdpi[gly]
|
||||
return maxh, maxw
|
||||
def getPath(self, gly):
|
||||
path = ''
|
||||
if (gly < 0) or (gly >= self.count):
|
||||
return path
|
||||
tx = self.vx[self.gvtx[gly]:self.gvtx[gly+1]]
|
||||
ty = self.vy[self.gvtx[gly]:self.gvtx[gly+1]]
|
||||
p = 0
|
||||
for k in xrange(self.glen[gly], self.glen[gly+1]):
|
||||
if (p == 0):
|
||||
zx = tx[0:self.vlen[k]+1]
|
||||
zy = ty[0:self.vlen[k]+1]
|
||||
else:
|
||||
zx = tx[self.vlen[k-1]+1:self.vlen[k]+1]
|
||||
zy = ty[self.vlen[k-1]+1:self.vlen[k]+1]
|
||||
p += 1
|
||||
j = 0
|
||||
while ( j < len(zx) ):
|
||||
if (j == 0):
|
||||
# Start Position.
|
||||
path += 'M %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly])
|
||||
elif (j <= len(zx)-3):
|
||||
# Cubic Bezier Curve
|
||||
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[j+2] * self.dpi / self.gdpi[gly], zy[j+2] * self.dpi / self.gdpi[gly])
|
||||
j += 2
|
||||
elif (j == len(zx)-2):
|
||||
# Cubic Bezier Curve to Start Position
|
||||
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
||||
j += 1
|
||||
elif (j == len(zx)-1):
|
||||
# Quadratic Bezier Curve to Start Position
|
||||
path += 'Q %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
|
||||
|
||||
j += 1
|
||||
path += 'z'
|
||||
return path
|
||||
|
||||
|
||||
|
||||
# dictionary of all text strings by index value
|
||||
class GlyphDict(object):
|
||||
def __init__(self):
|
||||
self.gdict = {}
|
||||
def lookup(self, id):
|
||||
# id='id="gl%d"' % val
|
||||
if id in self.gdict:
|
||||
return self.gdict[id]
|
||||
return None
|
||||
def addGlyph(self, val, path):
|
||||
id='id="gl%d"' % val
|
||||
self.gdict[id] = path
|
||||
|
||||
|
||||
def generateBook(bookDir, raw, fixedimage):
|
||||
# sanity check Topaz file extraction
|
||||
if not os.path.exists(bookDir) :
|
||||
print "Can not find directory with unencrypted book"
|
||||
return 1
|
||||
|
||||
dictFile = os.path.join(bookDir,'dict0000.dat')
|
||||
if not os.path.exists(dictFile) :
|
||||
print "Can not find dict0000.dat file"
|
||||
return 1
|
||||
|
||||
pageDir = os.path.join(bookDir,'page')
|
||||
if not os.path.exists(pageDir) :
|
||||
print "Can not find page directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
imgDir = os.path.join(bookDir,'img')
|
||||
if not os.path.exists(imgDir) :
|
||||
print "Can not find image directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
glyphsDir = os.path.join(bookDir,'glyphs')
|
||||
if not os.path.exists(glyphsDir) :
|
||||
print "Can not find glyphs directory in unencrypted book"
|
||||
return 1
|
||||
|
||||
metaFile = os.path.join(bookDir,'metadata0000.dat')
|
||||
if not os.path.exists(metaFile) :
|
||||
print "Can not find metadata0000.dat in unencrypted book"
|
||||
return 1
|
||||
|
||||
svgDir = os.path.join(bookDir,'svg')
|
||||
if not os.path.exists(svgDir) :
|
||||
os.makedirs(svgDir)
|
||||
|
||||
xmlDir = os.path.join(bookDir,'xml')
|
||||
if not os.path.exists(xmlDir) :
|
||||
os.makedirs(xmlDir)
|
||||
|
||||
otherFile = os.path.join(bookDir,'other0000.dat')
|
||||
if not os.path.exists(otherFile) :
|
||||
print "Can not find other0000.dat in unencrypted book"
|
||||
return 1
|
||||
|
||||
print "Updating to color images if available"
|
||||
spath = os.path.join(bookDir,'color_img')
|
||||
dpath = os.path.join(bookDir,'img')
|
||||
filenames = os.listdir(spath)
|
||||
filenames = sorted(filenames)
|
||||
for filename in filenames:
|
||||
imgname = filename.replace('color','img')
|
||||
sfile = os.path.join(spath,filename)
|
||||
dfile = os.path.join(dpath,imgname)
|
||||
imgdata = file(sfile,'rb').read()
|
||||
file(dfile,'wb').write(imgdata)
|
||||
|
||||
print "Creating cover.jpg"
|
||||
isCover = False
|
||||
cpath = os.path.join(bookDir,'img')
|
||||
cpath = os.path.join(cpath,'img0000.jpg')
|
||||
if os.path.isfile(cpath):
|
||||
cover = file(cpath, 'rb').read()
|
||||
cpath = os.path.join(bookDir,'cover.jpg')
|
||||
file(cpath, 'wb').write(cover)
|
||||
isCover = True
|
||||
|
||||
|
||||
print 'Processing Dictionary'
|
||||
dict = Dictionary(dictFile)
|
||||
|
||||
print 'Processing Meta Data and creating OPF'
|
||||
meta_array = getMetaArray(metaFile)
|
||||
|
||||
xname = os.path.join(xmlDir, 'metadata.xml')
|
||||
metastr = ''
|
||||
for key in meta_array:
|
||||
metastr += '<meta name="' + key + '" content="' + meta_array[key] + '" />\n'
|
||||
file(xname, 'wb').write(metastr)
|
||||
|
||||
print 'Processing StyleSheet'
|
||||
# get some scaling info from metadata to use while processing styles
|
||||
fontsize = '135'
|
||||
if 'fontSize' in meta_array:
|
||||
fontsize = meta_array['fontSize']
|
||||
|
||||
# also get the size of a normal text page
|
||||
spage = '1'
|
||||
if 'firstTextPage' in meta_array:
|
||||
spage = meta_array['firstTextPage']
|
||||
pnum = int(spage)
|
||||
|
||||
# get page height and width from first text page for use in stylesheet scaling
|
||||
pname = 'page%04d.dat' % (pnum + 1)
|
||||
fname = os.path.join(pageDir,pname)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
(ph, pw) = getPageDim(flat_xml)
|
||||
if (ph == '-1') or (ph == '0') : ph = '11000'
|
||||
if (pw == '-1') or (pw == '0') : pw = '8500'
|
||||
|
||||
# print ' ', 'other0000.dat'
|
||||
xname = os.path.join(bookDir, 'style.css')
|
||||
flat_xml = convert2xml.fromData(dict, otherFile)
|
||||
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
|
||||
file(xname, 'wb').write(cssstr)
|
||||
xname = os.path.join(xmlDir, 'other0000.xml')
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
|
||||
|
||||
print 'Processing Glyphs'
|
||||
gd = GlyphDict()
|
||||
filenames = os.listdir(glyphsDir)
|
||||
filenames = sorted(filenames)
|
||||
glyfname = os.path.join(svgDir,'glyphs.svg')
|
||||
glyfile = open(glyfname, 'w')
|
||||
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
|
||||
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
|
||||
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
|
||||
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
|
||||
glyfile.write('<defs>\n')
|
||||
counter = 0
|
||||
for filename in filenames:
|
||||
# print ' ', filename
|
||||
print '.',
|
||||
fname = os.path.join(glyphsDir,filename)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
||||
|
||||
gp = GParser(flat_xml)
|
||||
for i in xrange(0, gp.count):
|
||||
path = gp.getPath(i)
|
||||
maxh, maxw = gp.getGlyphDim(i)
|
||||
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
|
||||
glyfile.write(fullpath)
|
||||
gd.addGlyph(counter * 256 + i, fullpath)
|
||||
counter += 1
|
||||
glyfile.write('</defs>\n')
|
||||
glyfile.write('</svg>\n')
|
||||
glyfile.close()
|
||||
print " "
|
||||
|
||||
# start up the html
|
||||
htmlFileName = "book.html"
|
||||
htmlstr = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
htmlstr += '<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n'
|
||||
htmlstr += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n'
|
||||
htmlstr += '<head>\n'
|
||||
htmlstr += '<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n'
|
||||
htmlstr += '<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n'
|
||||
htmlstr += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
|
||||
htmlstr += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
|
||||
htmlstr += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
|
||||
htmlstr += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
|
||||
htmlstr += '<link href="style.css" rel="stylesheet" type="text/css" />\n'
|
||||
htmlstr += '</head>\n<body>\n'
|
||||
|
||||
print 'Processing Pages'
|
||||
# Books are at 1440 DPI. This is rendering at twice that size for
|
||||
# readability when rendering to the screen.
|
||||
scaledpi = 1440.0
|
||||
|
||||
svgindex = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
svgindex += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
svgindex += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >'
|
||||
svgindex += '<head>\n'
|
||||
svgindex += '<title>' + meta_array['Title'] + '</title>\n'
|
||||
svgindex += '<meta name="Author" content="' + meta_array['Authors'] + '" />\n'
|
||||
svgindex += '<meta name="Title" content="' + meta_array['Title'] + '" />\n'
|
||||
svgindex += '<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n'
|
||||
svgindex += '<meta name="GUID" content="' + meta_array['GUID'] + '" />\n'
|
||||
svgindex += '</head>\n'
|
||||
svgindex += '<body>\n'
|
||||
|
||||
filenames = os.listdir(pageDir)
|
||||
filenames = sorted(filenames)
|
||||
numfiles = len(filenames)
|
||||
counter = 0
|
||||
|
||||
for filename in filenames:
|
||||
# print ' ', filename
|
||||
print ".",
|
||||
|
||||
fname = os.path.join(pageDir,filename)
|
||||
flat_xml = convert2xml.fromData(dict, fname)
|
||||
|
||||
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
|
||||
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
|
||||
|
||||
# first get the html
|
||||
htmlstr += flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
|
||||
|
||||
# now get the svg image of the page
|
||||
svgxml = flatxml2svg.convert2SVG(gd, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi)
|
||||
|
||||
if (raw) :
|
||||
pfile = open(os.path.join(svgDir,filename.replace('.dat','.svg')), 'w')
|
||||
svgindex += '<a href="svg/page%04d.svg">Page %d</a>\n' % (counter, counter)
|
||||
else :
|
||||
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % counter), 'w')
|
||||
svgindex += '<a href="svg/page%04d.xhtml">Page %d</a>\n' % (counter, counter)
|
||||
|
||||
|
||||
pfile.write(svgxml)
|
||||
pfile.close()
|
||||
|
||||
counter += 1
|
||||
|
||||
print " "
|
||||
|
||||
# finish up the html string and output it
|
||||
htmlstr += '</body>\n</html>\n'
|
||||
file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
|
||||
|
||||
# finish up the svg index string and output it
|
||||
svgindex += '</body>\n</html>\n'
|
||||
file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
|
||||
|
||||
# build the opf file
|
||||
opfname = os.path.join(bookDir, 'book.opf')
|
||||
opfstr = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
opfstr += '<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n'
|
||||
# adding metadata
|
||||
opfstr += ' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n'
|
||||
opfstr += ' <dc:title>' + meta_array['Title'] + '</dc:title>\n'
|
||||
opfstr += ' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n'
|
||||
opfstr += ' <dc:language>en</dc:language>\n'
|
||||
opfstr += ' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n'
|
||||
if isCover:
|
||||
opfstr += ' <meta name="cover" content="bookcover"/>\n'
|
||||
opfstr += ' </metadata>\n'
|
||||
opfstr += '<manifest>\n'
|
||||
opfstr += ' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n'
|
||||
opfstr += ' <item id="stylesheet" href="style.css" media-type="text.css"/>\n'
|
||||
# adding image files to manifest
|
||||
filenames = os.listdir(imgDir)
|
||||
filenames = sorted(filenames)
|
||||
for filename in filenames:
|
||||
imgname, imgext = os.path.splitext(filename)
|
||||
if imgext == '.jpg':
|
||||
imgext = 'jpeg'
|
||||
if imgext == '.svg':
|
||||
imgext = 'svg+xml'
|
||||
opfstr += ' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n'
|
||||
if isCover:
|
||||
opfstr += ' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n'
|
||||
opfstr += '</manifest>\n'
|
||||
# adding spine
|
||||
opfstr += '<spine>\n <itemref idref="book" />\n</spine>\n'
|
||||
if isCover:
|
||||
opfstr += ' <guide>\n'
|
||||
opfstr += ' <reference href="cover.jpg" type="cover" title="Cover"/>\n'
|
||||
opfstr += ' </guide>\n'
|
||||
opfstr += '</package>\n'
|
||||
file(opfname, 'wb').write(opfstr)
|
||||
|
||||
print 'Processing Complete'
|
||||
|
||||
return 0
|
||||
|
||||
def usage():
|
||||
print "genbook.py generates a book from the extract Topaz Files"
|
||||
print "Usage:"
|
||||
print " genbook.py [-r] [-h [--fixed-image] <bookDir> "
|
||||
print " "
|
||||
print "Options:"
|
||||
print " -h : help - print this usage message"
|
||||
print " -r : generate raw svg files (not wrapped in xhtml)"
|
||||
print " --fixed-image : genearate any Fixed Area as an svg image in the html"
|
||||
print " "
|
||||
|
||||
|
||||
def main(argv):
|
||||
bookDir = ''
|
||||
|
||||
if len(argv) == 0:
|
||||
argv = sys.argv
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(argv[1:], "rh:",["fixed-image"])
|
||||
|
||||
except getopt.GetoptError, err:
|
||||
print str(err)
|
||||
usage()
|
||||
return 1
|
||||
|
||||
if len(opts) == 0 and len(args) == 0 :
|
||||
usage()
|
||||
return 1
|
||||
|
||||
raw = 0
|
||||
fixedimage = False
|
||||
for o, a in opts:
|
||||
if o =="-h":
|
||||
usage()
|
||||
return 0
|
||||
if o =="-r":
|
||||
raw = 1
|
||||
if o =="--fixed-image":
|
||||
fixedimage = True
|
||||
|
||||
bookDir = args[0]
|
||||
|
||||
rv = generateBook(bookDir, raw, fixedimage)
|
||||
return rv
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main(''))
|
@ -0,0 +1,312 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
from __future__ import with_statement
|
||||
import sys
|
||||
import os, csv
|
||||
import binascii
|
||||
import zlib
|
||||
import re
|
||||
from struct import pack, unpack, unpack_from
|
||||
|
||||
class DrmException(Exception):
|
||||
pass
|
||||
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
global charMap2
|
||||
global charMap3
|
||||
global charMap4
|
||||
|
||||
if sys.platform.startswith('win'):
|
||||
from k4pcutils import openKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
|
||||
if sys.platform.startswith('darwin'):
|
||||
from k4mutils import openKindleInfo, CryptUnprotectData, GetUserName, GetVolumeSerialNumber, charMap2
|
||||
|
||||
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
|
||||
charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
|
||||
charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
|
||||
|
||||
# crypto digestroutines
|
||||
import hashlib
|
||||
|
||||
def MD5(message):
|
||||
ctx = hashlib.md5()
|
||||
ctx.update(message)
|
||||
return ctx.digest()
|
||||
|
||||
def SHA1(message):
|
||||
ctx = hashlib.sha1()
|
||||
ctx.update(message)
|
||||
return ctx.digest()
|
||||
|
||||
|
||||
# Encode the bytes in data with the characters in map
|
||||
def encode(data, map):
|
||||
result = ""
|
||||
for char in data:
|
||||
value = ord(char)
|
||||
Q = (value ^ 0x80) // len(map)
|
||||
R = value % len(map)
|
||||
result += map[Q]
|
||||
result += map[R]
|
||||
return result
|
||||
|
||||
# Hash the bytes in data and then encode the digest with the characters in map
|
||||
def encodeHash(data,map):
|
||||
return encode(MD5(data),map)
|
||||
|
||||
# Decode the string in data with the characters in map. Returns the decoded bytes
|
||||
def decode(data,map):
|
||||
result = ""
|
||||
for i in range (0,len(data)-1,2):
|
||||
high = map.find(data[i])
|
||||
low = map.find(data[i+1])
|
||||
if (high == -1) or (low == -1) :
|
||||
break
|
||||
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
|
||||
result += pack("B",value)
|
||||
return result
|
||||
|
||||
|
||||
# Parse the Kindle.info file and return the records as a list of key-values
|
||||
def parseKindleInfo(kInfoFile):
|
||||
DB = {}
|
||||
infoReader = openKindleInfo(kInfoFile)
|
||||
infoReader.read(1)
|
||||
data = infoReader.read()
|
||||
if sys.platform.startswith('win'):
|
||||
items = data.split('{')
|
||||
else :
|
||||
items = data.split('[')
|
||||
for item in items:
|
||||
splito = item.split(':')
|
||||
DB[splito[0]] =splito[1]
|
||||
return DB
|
||||
|
||||
# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). Return the decoded and decrypted record
|
||||
def getKindleInfoValueForHash(hashedKey):
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
global charMap2
|
||||
encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
|
||||
if sys.platform.startswith('win'):
|
||||
return CryptUnprotectData(encryptedValue,"")
|
||||
else:
|
||||
cleartext = CryptUnprotectData(encryptedValue)
|
||||
return decode(cleartext, charMap1)
|
||||
|
||||
# Get a record from the Kindle.info file for the string in "key" (plaintext). Return the decoded and decrypted record
|
||||
def getKindleInfoValueForKey(key):
|
||||
global charMap2
|
||||
return getKindleInfoValueForHash(encodeHash(key,charMap2))
|
||||
|
||||
# Find if the original string for a hashed/encoded string is known. If so return the original string othwise return an empty string.
|
||||
def findNameForHash(hash):
|
||||
global charMap2
|
||||
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
|
||||
result = ""
|
||||
for name in names:
|
||||
if hash == encodeHash(name, charMap2):
|
||||
result = name
|
||||
break
|
||||
return result
|
||||
|
||||
# Print all the records from the kindle.info file (option -i)
|
||||
def printKindleInfo():
|
||||
for record in kindleDatabase:
|
||||
name = findNameForHash(record)
|
||||
if name != "" :
|
||||
print (name)
|
||||
print ("--------------------------")
|
||||
else :
|
||||
print ("Unknown Record")
|
||||
print getKindleInfoValueForHash(record)
|
||||
print "\n"
|
||||
|
||||
#
|
||||
# PID generation routines
|
||||
#
|
||||
|
||||
# Returns two bit at offset from a bit field
|
||||
def getTwoBitsFromBitField(bitField,offset):
|
||||
byteNumber = offset // 4
|
||||
bitPosition = 6 - 2*(offset % 4)
|
||||
return ord(bitField[byteNumber]) >> bitPosition & 3
|
||||
|
||||
# Returns the six bits at offset from a bit field
|
||||
def getSixBitsFromBitField(bitField,offset):
|
||||
offset *= 3
|
||||
value = (getTwoBitsFromBitField(bitField,offset) <<4) + (getTwoBitsFromBitField(bitField,offset+1) << 2) +getTwoBitsFromBitField(bitField,offset+2)
|
||||
return value
|
||||
|
||||
# 8 bits to six bits encoding from hash to generate PID string
|
||||
def encodePID(hash):
|
||||
global charMap3
|
||||
PID = ""
|
||||
for position in range (0,8):
|
||||
PID += charMap3[getSixBitsFromBitField(hash,position)]
|
||||
return PID
|
||||
|
||||
# Encryption table used to generate the device PID
|
||||
def generatePidEncryptionTable() :
|
||||
table = []
|
||||
for counter1 in range (0,0x100):
|
||||
value = counter1
|
||||
for counter2 in range (0,8):
|
||||
if (value & 1 == 0) :
|
||||
value = value >> 1
|
||||
else :
|
||||
value = value >> 1
|
||||
value = value ^ 0xEDB88320
|
||||
table.append(value)
|
||||
return table
|
||||
|
||||
# Seed value used to generate the device PID
|
||||
def generatePidSeed(table,dsn) :
|
||||
value = 0
|
||||
for counter in range (0,4) :
|
||||
index = (ord(dsn[counter]) ^ value) &0xFF
|
||||
value = (value >> 8) ^ table[index]
|
||||
return value
|
||||
|
||||
# Generate the device PID
|
||||
def generateDevicePID(table,dsn,nbRoll):
|
||||
global charMap4
|
||||
seed = generatePidSeed(table,dsn)
|
||||
pidAscii = ""
|
||||
pid = [(seed >>24) &0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF,(seed>>24) & 0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF]
|
||||
index = 0
|
||||
for counter in range (0,nbRoll):
|
||||
pid[index] = pid[index] ^ ord(dsn[counter])
|
||||
index = (index+1) %8
|
||||
for counter in range (0,8):
|
||||
index = ((((pid[counter] >>5) & 3) ^ pid[counter]) & 0x1f) + (pid[counter] >> 7)
|
||||
pidAscii += charMap4[index]
|
||||
return pidAscii
|
||||
|
||||
def crc32(s):
|
||||
return (~binascii.crc32(s,-1))&0xFFFFFFFF
|
||||
|
||||
# convert from 8 digit PID to 10 digit PID with checksum
|
||||
def checksumPid(s):
|
||||
global charMap4
|
||||
crc = crc32(s)
|
||||
crc = crc ^ (crc >> 16)
|
||||
res = s
|
||||
l = len(charMap4)
|
||||
for i in (0,1):
|
||||
b = crc & 0xff
|
||||
pos = (b // l) ^ (b % l)
|
||||
res += charMap4[pos%l]
|
||||
crc >>= 8
|
||||
return res
|
||||
|
||||
|
||||
# old kindle serial number to fixed pid
|
||||
def pidFromSerial(s, l):
|
||||
global charMap4
|
||||
crc = crc32(s)
|
||||
arr1 = [0]*l
|
||||
for i in xrange(len(s)):
|
||||
arr1[i%l] ^= ord(s[i])
|
||||
crc_bytes = [crc >> 24 & 0xff, crc >> 16 & 0xff, crc >> 8 & 0xff, crc & 0xff]
|
||||
for i in xrange(l):
|
||||
arr1[i] ^= crc_bytes[i&3]
|
||||
pid = ""
|
||||
for i in xrange(l):
|
||||
b = arr1[i] & 0xff
|
||||
pid+=charMap4[(b >> 7) + ((b >> 5 & 3) ^ (b & 0x1f))]
|
||||
return pid
|
||||
|
||||
|
||||
# Parse the EXTH header records and use the Kindle serial number to calculate the book pid.
|
||||
def getKindlePid(pidlst, rec209, token, serialnum):
|
||||
|
||||
if rec209 != None:
|
||||
# Compute book PID
|
||||
pidHash = SHA1(serialnum+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# compute fixed pid for old pre 2.5 firmware update pid as well
|
||||
bookPID = pidFromSerial(serialnum, 7) + "*"
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
return pidlst
|
||||
|
||||
|
||||
# Parse the EXTH header records and parse the Kindleinfo
|
||||
# file to calculate the book pid.
|
||||
|
||||
def getK4Pids(pidlst, rec209, token, kInfoFile=None):
|
||||
global kindleDatabase
|
||||
global charMap1
|
||||
kindleDatabase = None
|
||||
try:
|
||||
kindleDatabase = parseKindleInfo(kInfoFile)
|
||||
except Exception, message:
|
||||
print(message)
|
||||
pass
|
||||
|
||||
if kindleDatabase == None :
|
||||
return pidlst
|
||||
|
||||
# Get the Mazama Random number
|
||||
MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
|
||||
|
||||
# Get the HDD serial
|
||||
encodedSystemVolumeSerialNumber = encodeHash(GetVolumeSerialNumber(),charMap1)
|
||||
|
||||
# Get the current user name
|
||||
encodedUsername = encodeHash(GetUserName(),charMap1)
|
||||
|
||||
# concat, hash and encode to calculate the DSN
|
||||
DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
|
||||
|
||||
# Compute the device PID (for which I can tell, is used for nothing).
|
||||
table = generatePidEncryptionTable()
|
||||
devicePID = generateDevicePID(table,DSN,4)
|
||||
devicePID = checksumPid(devicePID)
|
||||
pidlst.append(devicePID)
|
||||
|
||||
# Compute book PID
|
||||
if rec209 == None:
|
||||
print "\nNo EXTH record type 209 - Perhaps not a K4 file?"
|
||||
return pidlst
|
||||
|
||||
# Get the kindle account token
|
||||
kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
|
||||
|
||||
# book pid
|
||||
pidHash = SHA1(DSN+kindleAccountToken+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# variant 1
|
||||
pidHash = SHA1(kindleAccountToken+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
# variant 2
|
||||
pidHash = SHA1(DSN+rec209+token)
|
||||
bookPID = encodePID(pidHash)
|
||||
bookPID = checksumPid(bookPID)
|
||||
pidlst.append(bookPID)
|
||||
|
||||
return pidlst
|
||||
|
||||
def getPidList(md1, md2, k4, pids, serials, kInfoFiles):
|
||||
pidlst = []
|
||||
if k4:
|
||||
pidlst = getK4Pids(pidlst, md1, md2)
|
||||
for infoFile in kInfoFiles:
|
||||
pidlst = getK4Pids(pidlst, md1, md2, infoFile)
|
||||
for serialnum in serials:
|
||||
pidlst = getKindlePid(pidlst, md1, md2, serialnum)
|
||||
for pid in pids:
|
||||
pidlst.append(pid)
|
||||
return pidlst
|
@ -0,0 +1,243 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
# For use with Topaz Scripts Version 2.6
|
||||
|
||||
import csv
|
||||
import sys
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class DocParser(object):
|
||||
def __init__(self, flatxml, fontsize, ph, pw):
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.fontsize = int(fontsize)
|
||||
self.ph = int(ph) * 1.0
|
||||
self.pw = int(pw) * 1.0
|
||||
|
||||
stags = {
|
||||
'paragraph' : 'p',
|
||||
'graphic' : '.graphic'
|
||||
}
|
||||
|
||||
attr_val_map = {
|
||||
'hang' : 'text-indent: ',
|
||||
'indent' : 'text-indent: ',
|
||||
'line-space' : 'line-height: ',
|
||||
'margin-bottom' : 'margin-bottom: ',
|
||||
'margin-left' : 'margin-left: ',
|
||||
'margin-right' : 'margin-right: ',
|
||||
'margin-top' : 'margin-top: ',
|
||||
'space-after' : 'padding-bottom: ',
|
||||
}
|
||||
|
||||
attr_str_map = {
|
||||
'align-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
|
||||
'align-left' : 'text-align: left;',
|
||||
'align-right' : 'text-align: right;',
|
||||
'align-justify' : 'text-align: justify;',
|
||||
'display-inline' : 'display: inline;',
|
||||
'pos-left' : 'text-align: left;',
|
||||
'pos-right' : 'text-align: right;',
|
||||
'pos-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
|
||||
}
|
||||
|
||||
|
||||
# find tag if within pos to end inclusive
|
||||
def findinDoc(self, tagpath, pos, end) :
|
||||
result = None
|
||||
docList = self.flatdoc
|
||||
cnt = len(docList)
|
||||
if end == -1 :
|
||||
end = cnt
|
||||
else:
|
||||
end = min(cnt,end)
|
||||
foundat = -1
|
||||
for j in xrange(pos, end):
|
||||
item = docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
result = argres
|
||||
foundat = j
|
||||
break
|
||||
return foundat, result
|
||||
|
||||
|
||||
# return list of start positions for the tagpath
|
||||
def posinDoc(self, tagpath):
|
||||
startpos = []
|
||||
pos = 0
|
||||
res = ""
|
||||
while res != None :
|
||||
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
|
||||
if res != None :
|
||||
startpos.append(foundpos)
|
||||
pos = foundpos + 1
|
||||
return startpos
|
||||
|
||||
|
||||
def process(self):
|
||||
|
||||
classlst = ''
|
||||
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')
|
||||
stylecnt = len(styleList)
|
||||
styleList.append(-1)
|
||||
|
||||
# process each style converting what you can
|
||||
|
||||
for j in xrange(stylecnt):
|
||||
start = styleList[j]
|
||||
end = styleList[j+1]
|
||||
|
||||
(pos, tag) = self.findinDoc('style._tag',start,end)
|
||||
if tag == None :
|
||||
(pos, tag) = self.findinDoc('style.type',start,end)
|
||||
|
||||
# Is this something we know how to convert to css
|
||||
if tag in self.stags :
|
||||
|
||||
# get the style class
|
||||
(pos, sclass) = self.findinDoc('style.class',start,end)
|
||||
if sclass != None:
|
||||
sclass = sclass.replace(' ','-')
|
||||
sclass = '.cl-' + sclass.lower()
|
||||
else :
|
||||
sclass = ''
|
||||
|
||||
# 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 = ''
|
||||
|
||||
cssargs = {}
|
||||
|
||||
while True :
|
||||
|
||||
(pos1, attr) = self.findinDoc('style.rule.attr', start, end)
|
||||
(pos2, val) = self.findinDoc('style.rule.value', start, end)
|
||||
|
||||
if attr == None : break
|
||||
|
||||
if (attr == 'display') or (attr == 'pos') or (attr == 'align'):
|
||||
# handle text based attributess
|
||||
attr = attr + '-' + val
|
||||
if attr in self.attr_str_map :
|
||||
cssargs[attr] = (self.attr_str_map[attr], '')
|
||||
else :
|
||||
# handle value based attributes
|
||||
if attr in self.attr_val_map :
|
||||
name = self.attr_val_map[attr]
|
||||
if attr in ('margin-bottom', 'margin-top', 'space-after') :
|
||||
scale = self.ph
|
||||
elif attr in ('margin-right', 'indent', 'margin-left', 'hang') :
|
||||
scale = self.pw
|
||||
elif attr == 'line-space':
|
||||
scale = self.fontsize * 2.0
|
||||
|
||||
if not ((attr == 'hang') and (int(val) == 0)) :
|
||||
pv = float(val)/scale
|
||||
cssargs[attr] = (self.attr_val_map[attr], pv)
|
||||
keep = True
|
||||
|
||||
start = max(pos1, pos2) + 1
|
||||
|
||||
# disable all of the after class tags until I figure out how to handle them
|
||||
if aftclass != "" : keep = False
|
||||
|
||||
if keep :
|
||||
# make sure line-space does not go below 100% or above 300% since
|
||||
# it can be wacky in some styles
|
||||
if 'line-space' in cssargs:
|
||||
seg = cssargs['line-space'][0]
|
||||
val = cssargs['line-space'][1]
|
||||
if val < 1.0: val = 1.0
|
||||
if val > 3.0: val = 3.0
|
||||
del cssargs['line-space']
|
||||
cssargs['line-space'] = (self.attr_val_map['line-space'], val)
|
||||
|
||||
|
||||
# handle modifications for css style hanging indents
|
||||
if 'hang' in cssargs:
|
||||
hseg = cssargs['hang'][0]
|
||||
hval = cssargs['hang'][1]
|
||||
del cssargs['hang']
|
||||
cssargs['hang'] = (self.attr_val_map['hang'], -hval)
|
||||
mval = 0
|
||||
mseg = 'margin-left: '
|
||||
mval = hval
|
||||
if 'margin-left' in cssargs:
|
||||
mseg = cssargs['margin-left'][0]
|
||||
mval = cssargs['margin-left'][1]
|
||||
if mval < 0: mval = 0
|
||||
mval = hval + mval
|
||||
cssargs['margin-left'] = (mseg, mval)
|
||||
if 'indent' in cssargs:
|
||||
del cssargs['indent']
|
||||
|
||||
cssline = sclass + ' { '
|
||||
for key in iter(cssargs):
|
||||
mseg = cssargs[key][0]
|
||||
mval = cssargs[key][1]
|
||||
if mval == '':
|
||||
cssline += mseg + ' '
|
||||
else :
|
||||
aseg = mseg + '%.1f%%;' % (mval * 100.0)
|
||||
cssline += aseg + ' '
|
||||
|
||||
cssline += '}'
|
||||
|
||||
if sclass != '' :
|
||||
classlst += sclass + '\n'
|
||||
|
||||
# handle special case of paragraph class used inside chapter heading
|
||||
# and non-chapter headings
|
||||
if sclass != '' :
|
||||
ctype = sclass[4:7]
|
||||
if ctype == 'ch1' :
|
||||
csspage += 'h1' + cssline + '\n'
|
||||
if ctype == 'ch2' :
|
||||
csspage += 'h2' + cssline + '\n'
|
||||
if ctype == 'ch3' :
|
||||
csspage += 'h3' + cssline + '\n'
|
||||
if ctype == 'h1-' :
|
||||
csspage += 'h4' + cssline + '\n'
|
||||
if ctype == 'h2-' :
|
||||
csspage += 'h5' + cssline + '\n'
|
||||
if ctype == 'h3_' :
|
||||
csspage += 'h6' + cssline + '\n'
|
||||
|
||||
if cssline != ' { }':
|
||||
csspage += self.stags[tag] + cssline + '\n'
|
||||
|
||||
|
||||
return csspage, classlst
|
||||
|
||||
|
||||
|
||||
def convert2CSS(flatxml, fontsize, ph, pw):
|
||||
|
||||
print ' ', 'Using font size:',fontsize
|
||||
print ' ', 'Using page height:', ph
|
||||
print ' ', 'Using page width:', pw
|
||||
|
||||
# create a document parser
|
||||
dp = DocParser(flatxml, fontsize, ph, pw)
|
||||
|
||||
csspage = dp.process()
|
||||
|
||||
return csspage
|
@ -0,0 +1,434 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
import os, csv, getopt
|
||||
import zlib, zipfile, tempfile, shutil
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
class TpzDRMError(Exception):
|
||||
pass
|
||||
|
||||
# local support routines
|
||||
import kgenpids
|
||||
import genbook
|
||||
#
|
||||
# Utility routines
|
||||
#
|
||||
|
||||
# Get a 7 bit encoded number from file
|
||||
def bookReadEncodedNumber(fo):
|
||||
flag = False
|
||||
data = ord(fo.read(1))
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
data = ord(fo.read(1))
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
data = ord(fo.read(1))
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
# Get a length prefixed string from file
|
||||
def bookReadString(fo):
|
||||
stringLength = bookReadEncodedNumber(fo)
|
||||
return unpack(str(stringLength)+"s",fo.read(stringLength))[0]
|
||||
|
||||
#
|
||||
# crypto routines
|
||||
#
|
||||
|
||||
# Context initialisation for the Topaz Crypto
|
||||
def topazCryptoInit(key):
|
||||
ctx1 = 0x0CAFFE19E
|
||||
for keyChar in key:
|
||||
keyByte = ord(keyChar)
|
||||
ctx2 = ctx1
|
||||
ctx1 = ((((ctx1 >>2) * (ctx1 >>7))&0xFFFFFFFF) ^ (keyByte * keyByte * 0x0F902007)& 0xFFFFFFFF )
|
||||
return [ctx1,ctx2]
|
||||
|
||||
# decrypt data with the context prepared by topazCryptoInit()
|
||||
def topazCryptoDecrypt(data, ctx):
|
||||
ctx1 = ctx[0]
|
||||
ctx2 = ctx[1]
|
||||
plainText = ""
|
||||
for dataChar in data:
|
||||
dataByte = ord(dataChar)
|
||||
m = (dataByte ^ ((ctx1 >> 3) &0xFF) ^ ((ctx2<<3) & 0xFF)) &0xFF
|
||||
ctx2 = ctx1
|
||||
ctx1 = (((ctx1 >> 2) * (ctx1 >> 7)) &0xFFFFFFFF) ^((m * m * 0x0F902007) &0xFFFFFFFF)
|
||||
plainText += chr(m)
|
||||
return plainText
|
||||
|
||||
# Decrypt data with the PID
|
||||
def decryptRecord(data,PID):
|
||||
ctx = topazCryptoInit(PID)
|
||||
return topazCryptoDecrypt(data, ctx)
|
||||
|
||||
# Try to decrypt a dkey record (contains the bookPID)
|
||||
def decryptDkeyRecord(data,PID):
|
||||
record = decryptRecord(data,PID)
|
||||
fields = unpack("3sB8sB8s3s",record)
|
||||
if fields[0] != "PID" or fields[5] != "pid" :
|
||||
raise TpzDRMError("Didn't find PID magic numbers in record")
|
||||
elif fields[1] != 8 or fields[3] != 8 :
|
||||
raise TpzDRMError("Record didn't contain correct length fields")
|
||||
elif fields[2] != PID :
|
||||
raise TpzDRMError("Record didn't contain PID")
|
||||
return fields[4]
|
||||
|
||||
# Decrypt all dkey records (contain the book PID)
|
||||
def decryptDkeyRecords(data,PID):
|
||||
nbKeyRecords = ord(data[0])
|
||||
records = []
|
||||
data = data[1:]
|
||||
for i in range (0,nbKeyRecords):
|
||||
length = ord(data[0])
|
||||
try:
|
||||
key = decryptDkeyRecord(data[1:length+1],PID)
|
||||
records.append(key)
|
||||
except TpzDRMError:
|
||||
pass
|
||||
data = data[1+length:]
|
||||
if len(records) == 0:
|
||||
raise TpzDRMError("BookKey Not Found")
|
||||
return records
|
||||
|
||||
|
||||
class TopazBook:
|
||||
def __init__(self, filename, outdir):
|
||||
self.fo = file(filename, 'rb')
|
||||
self.outdir = outdir
|
||||
self.bookPayloadOffset = 0
|
||||
self.bookHeaderRecords = {}
|
||||
self.bookMetadata = {}
|
||||
self.bookKey = None
|
||||
magic = unpack("4s",self.fo.read(4))[0]
|
||||
if magic != 'TPZ0':
|
||||
raise TpzDRMError("Parse Error : Invalid Header, not a Topaz file")
|
||||
self.parseTopazHeaders()
|
||||
self.parseMetadata()
|
||||
|
||||
def parseTopazHeaders(self):
|
||||
def bookReadHeaderRecordData():
|
||||
# Read and return the data of one header record at the current book file position
|
||||
# [[offset,decompressedLength,compressedLength],...]
|
||||
nbValues = bookReadEncodedNumber(self.fo)
|
||||
values = []
|
||||
for i in range (0,nbValues):
|
||||
values.append([bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo)])
|
||||
return values
|
||||
def parseTopazHeaderRecord():
|
||||
# Read and parse one header record at the current book file position and return the associated data
|
||||
# [[offset,decompressedLength,compressedLength],...]
|
||||
if ord(self.fo.read(1)) != 0x63:
|
||||
raise TpzDRMError("Parse Error : Invalid Header")
|
||||
tag = bookReadString(self.fo)
|
||||
record = bookReadHeaderRecordData()
|
||||
return [tag,record]
|
||||
nbRecords = bookReadEncodedNumber(self.fo)
|
||||
for i in range (0,nbRecords):
|
||||
result = parseTopazHeaderRecord()
|
||||
# print result[0], result[1]
|
||||
self.bookHeaderRecords[result[0]] = result[1]
|
||||
if ord(self.fo.read(1)) != 0x64 :
|
||||
raise TpzDRMError("Parse Error : Invalid Header")
|
||||
self.bookPayloadOffset = self.fo.tell()
|
||||
|
||||
def parseMetadata(self):
|
||||
# Parse the metadata record from the book payload and return a list of [key,values]
|
||||
self.fo.seek(self.bookPayloadOffset + self.bookHeaderRecords["metadata"][0][0])
|
||||
tag = bookReadString(self.fo)
|
||||
if tag != "metadata" :
|
||||
raise TpzDRMError("Parse Error : Record Names Don't Match")
|
||||
flags = ord(self.fo.read(1))
|
||||
nbRecords = ord(self.fo.read(1))
|
||||
for i in range (0,nbRecords) :
|
||||
record = [bookReadString(self.fo), bookReadString(self.fo)]
|
||||
self.bookMetadata[record[0]] = record[1]
|
||||
return self.bookMetadata
|
||||
|
||||
def getPIDMetaInfo(self):
|
||||
keysRecord = None
|
||||
KeysRecordRecord = None
|
||||
if 'keys' in self.bookMetadata:
|
||||
keysRecord = self.bookMetadata['keys']
|
||||
keysRecordRecord = self.bookMetadata[keysRecord]
|
||||
return keysRecord, keysRecordRecord
|
||||
|
||||
def getBookTitle(self):
|
||||
title = ''
|
||||
if 'Title' in self.bookMetadata:
|
||||
title = self.bookMetadata['Title']
|
||||
return title
|
||||
|
||||
def setBookKey(self, key):
|
||||
self.bookKey = key
|
||||
|
||||
def getBookPayloadRecord(self, name, index):
|
||||
# Get a record in the book payload, given its name and index.
|
||||
# decrypted and decompressed if necessary
|
||||
encrypted = False
|
||||
compressed = False
|
||||
try:
|
||||
recordOffset = self.bookHeaderRecords[name][index][0]
|
||||
except:
|
||||
raise TpzDRMError("Parse Error : Invalid Record, record not found")
|
||||
|
||||
self.fo.seek(self.bookPayloadOffset + recordOffset)
|
||||
|
||||
tag = bookReadString(self.fo)
|
||||
if tag != name :
|
||||
raise TpzDRMError("Parse Error : Invalid Record, record name doesn't match")
|
||||
|
||||
recordIndex = bookReadEncodedNumber(self.fo)
|
||||
if recordIndex < 0 :
|
||||
encrypted = True
|
||||
recordIndex = -recordIndex -1
|
||||
|
||||
if recordIndex != index :
|
||||
raise TpzDRMError("Parse Error : Invalid Record, index doesn't match")
|
||||
|
||||
if (self.bookHeaderRecords[name][index][2] > 0):
|
||||
compressed = True
|
||||
record = self.fo.read(self.bookHeaderRecords[name][index][2])
|
||||
else:
|
||||
record = self.fo.read(self.bookHeaderRecords[name][index][1])
|
||||
|
||||
if encrypted:
|
||||
if self.bookKey:
|
||||
ctx = topazCryptoInit(self.bookKey)
|
||||
record = topazCryptoDecrypt(record,ctx)
|
||||
else :
|
||||
raise TpzDRMError("Error: Attempt to decrypt without bookKey")
|
||||
|
||||
if compressed:
|
||||
record = zlib.decompress(record)
|
||||
|
||||
return record
|
||||
|
||||
def processBook(self, pidlst):
|
||||
raw = 0
|
||||
fixedimage=True
|
||||
try:
|
||||
keydata = self.getBookPayloadRecord('dkey', 0)
|
||||
except TpzDRMError, e:
|
||||
print "no dkey record found, book may not be encrypted"
|
||||
print "attempting to extrct files without a book key"
|
||||
self.createBookDirectory()
|
||||
self.extractFiles()
|
||||
print "Successfully Extracted Topaz contents"
|
||||
rv = genbook.generateBook(self.outdir, raw, fixedimage)
|
||||
if rv == 0:
|
||||
print "\nBook Successfully generated"
|
||||
return rv
|
||||
|
||||
# try each pid to decode the file
|
||||
bookKey = None
|
||||
for pid in pidlst:
|
||||
# use 8 digit pids here
|
||||
pid = pid[0:8]
|
||||
print "\nTrying: ", pid
|
||||
bookKeys = []
|
||||
data = keydata
|
||||
try:
|
||||
bookKeys+=decryptDkeyRecords(data,pid)
|
||||
except TpzDRMError, e:
|
||||
pass
|
||||
else:
|
||||
bookKey = bookKeys[0]
|
||||
print "Book Key Found!"
|
||||
break
|
||||
|
||||
if not bookKey:
|
||||
raise TpzDRMError('Decryption Unsucessful; No valid pid found')
|
||||
|
||||
self.setBookKey(bookKey)
|
||||
self.createBookDirectory()
|
||||
self.extractFiles()
|
||||
print "Successfully Extracted Topaz contents"
|
||||
rv = genbook.generateBook(self.outdir, raw, fixedimage)
|
||||
if rv == 0:
|
||||
print "\nBook Successfully generated"
|
||||
return rv
|
||||
|
||||
def createBookDirectory(self):
|
||||
outdir = self.outdir
|
||||
# create output directory structure
|
||||
if not os.path.exists(outdir):
|
||||
os.makedirs(outdir)
|
||||
destdir = os.path.join(outdir,'img')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'color_img')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'page')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
destdir = os.path.join(outdir,'glyphs')
|
||||
if not os.path.exists(destdir):
|
||||
os.makedirs(destdir)
|
||||
|
||||
def extractFiles(self):
|
||||
outdir = self.outdir
|
||||
for headerRecord in self.bookHeaderRecords:
|
||||
name = headerRecord
|
||||
if name != "dkey" :
|
||||
ext = '.dat'
|
||||
if name == 'img' : ext = '.jpg'
|
||||
if name == 'color' : ext = '.jpg'
|
||||
print "\nProcessing Section: %s " % name
|
||||
for index in range (0,len(self.bookHeaderRecords[name])) :
|
||||
fnum = "%04d" % index
|
||||
fname = name + fnum + ext
|
||||
destdir = outdir
|
||||
if name == 'img':
|
||||
destdir = os.path.join(outdir,'img')
|
||||
if name == 'color':
|
||||
destdir = os.path.join(outdir,'color_img')
|
||||
if name == 'page':
|
||||
destdir = os.path.join(outdir,'page')
|
||||
if name == 'glyphs':
|
||||
destdir = os.path.join(outdir,'glyphs')
|
||||
outputFile = os.path.join(destdir,fname)
|
||||
print ".",
|
||||
record = self.getBookPayloadRecord(name,index)
|
||||
if record != '':
|
||||
file(outputFile, 'wb').write(record)
|
||||
print " "
|
||||
|
||||
|
||||
def zipUpDir(myzip, tempdir,localname):
|
||||
currentdir = tempdir
|
||||
if localname != "":
|
||||
currentdir = os.path.join(currentdir,localname)
|
||||
list = os.listdir(currentdir)
|
||||
for file in list:
|
||||
afilename = file
|
||||
localfilePath = os.path.join(localname, afilename)
|
||||
realfilePath = os.path.join(currentdir,file)
|
||||
if os.path.isfile(realfilePath):
|
||||
myzip.write(realfilePath, localfilePath)
|
||||
elif os.path.isdir(realfilePath):
|
||||
zipUpDir(myzip, tempdir, localfilePath)
|
||||
|
||||
|
||||
def usage(progname):
|
||||
print "Removes DRM protection from Topaz ebooks and extract the contents"
|
||||
print "Usage:"
|
||||
print " %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir> " % progname
|
||||
|
||||
|
||||
# Main
|
||||
def main(argv=sys.argv):
|
||||
progname = os.path.basename(argv[0])
|
||||
k4 = False
|
||||
pids = []
|
||||
serials = []
|
||||
kInfoFiles = []
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
|
||||
except getopt.GetoptError, err:
|
||||
print str(err)
|
||||
usage(progname)
|
||||
return 1
|
||||
if len(args)<2:
|
||||
usage(progname)
|
||||
return 1
|
||||
|
||||
for o, a in opts:
|
||||
if o == "-k":
|
||||
if a == None :
|
||||
print "Invalid parameter for -k"
|
||||
return 1
|
||||
kInfoFiles.append(a)
|
||||
if o == "-p":
|
||||
if a == None :
|
||||
print "Invalid parameter for -p"
|
||||
return 1
|
||||
pids = a.split(',')
|
||||
if o == "-s":
|
||||
if a == None :
|
||||
print "Invalid parameter for -s"
|
||||
return 1
|
||||
serials = a.split(',')
|
||||
k4 = True
|
||||
|
||||
infile = args[0]
|
||||
outdir = args[1]
|
||||
|
||||
if not os.path.isfile(infile):
|
||||
print "Input File Does Not Exist"
|
||||
return 1
|
||||
|
||||
bookname = os.path.splitext(os.path.basename(infile))[0]
|
||||
tempdir = tempfile.mkdtemp()
|
||||
|
||||
tb = TopazBook(infile, tempdir)
|
||||
title = tb.getBookTitle()
|
||||
print "Processing Book: ", title
|
||||
keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
|
||||
pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles)
|
||||
|
||||
try:
|
||||
tb.processBook(pidlst)
|
||||
except TpzDRMError, e:
|
||||
print str(e)
|
||||
print " Creating DeBug Full Zip Archive of Book"
|
||||
zipname = os.path.join(outdir, bookname + '_debug' + '.zip')
|
||||
myzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
zipUpDir(myzip, tempdir, '')
|
||||
myzip.close()
|
||||
return 1
|
||||
|
||||
print " Creating HTML ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_nodrm' + '.zip')
|
||||
myzip1 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
myzip1.write(os.path.join(tempdir,'book.html'),'book.html')
|
||||
myzip1.write(os.path.join(tempdir,'book.opf'),'book.opf')
|
||||
if os.path.isfile(os.path.join(tempdir,'cover.jpg')):
|
||||
myzip1.write(os.path.join(tempdir,'cover.jpg'),'cover.jpg')
|
||||
myzip1.write(os.path.join(tempdir,'style.css'),'style.css')
|
||||
zipUpDir(myzip1, tempdir, 'img')
|
||||
myzip1.close()
|
||||
|
||||
print " Creating SVG ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
|
||||
myzip2 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
myzip2.write(os.path.join(tempdir,'index_svg.xhtml'),'index_svg.xhtml')
|
||||
zipUpDir(myzip2, tempdir, 'svg')
|
||||
zipUpDir(myzip2, tempdir, 'img')
|
||||
myzip2.close()
|
||||
|
||||
print " Creating XML ZIP Archive"
|
||||
zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
|
||||
myzip3 = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
|
||||
targetdir = os.path.join(tempdir,'xml')
|
||||
zipUpDir(myzip3, targetdir, '')
|
||||
zipUpDir(myzip3, tempdir, 'img')
|
||||
myzip3.close()
|
||||
|
||||
shutil.rmtree(tempdir)
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main())
|
||||
|
@ -0,0 +1,59 @@
|
||||
KindleBooks (Originally called K4MobiDeDRM and Topaz_Tools)
|
||||
|
||||
This tools combines functionality of MobiDeDRM with that of K4PCDeDRM, K4MDeDRM, and K4DeDRM. Effectively, it provides one-stop shopping for all your Mobipocket, Kindle for iPhone/iPad/iPodTouch, Kindle for PC, and Kindle for Mac needs and should work for both Mobi and Topaz ebooks.
|
||||
|
||||
Preliminary Steps:
|
||||
|
||||
1. Make sure you have Python 2.X installed (32 bit) and properly set as part of your SYSTEM PATH environment variable (On Windows I recommend ActiveState's ActivePython. See their web pages for instructions on how to install and how to properly set your PATH). On Mac OSX 10.6 everything you need is already installed.
|
||||
|
||||
|
||||
****
|
||||
Please Note: If you a happy user of MobiDeDRM, K4DeDRM, K4PCDeDRM, or K4MUnswindle, please continue to use these programs as there is no additional capability provided by this tool over the others. In the long run, if you have problems with any of those tools, you might want to try this one as it will continue under development eventually replacing all of those tools.
|
||||
****
|
||||
|
||||
Instructions:
|
||||
|
||||
1. double-click on KindleBooks.pyw
|
||||
|
||||
2. In the window that opens:
|
||||
hit the first '...' button to locate your DRM Kindle-style ebook
|
||||
|
||||
3. Then hit the second '...' button to select an output directory for the unlocked file
|
||||
|
||||
4. If you have multiple Kindle.Info files and would like to use one specific one, please hit the third "...' button to select it. Note, if you only have one Kindle.Info file (like most users) this can and should be left blank.
|
||||
|
||||
5. Then add in any PIDs you need from KindleV1, Kindle for iPhone/iPad/iPodTouch, or other single PID devices to the provided box as a comma separated list of 10 digit PID numbers. If this is a Kindle for Mac or a Kindle for PC book then you can leave this box blank
|
||||
|
||||
|
||||
6. If you have standalone Kindles, add in any 16 digit Serial Numbers as a comma separated list. If this is a Kindle for Mac or a Kindle for PC book then you can leave this box blank
|
||||
|
||||
7. hit the 'Start' button
|
||||
|
||||
After a short delay, you should see progress in the Conversion Log window indicating is the unlocking was a success or failure.
|
||||
|
||||
|
||||
|
||||
If your book was a normal Mobi style ebook:
|
||||
If successful, you should see a "_nodrm" named version Mobi ebook.
|
||||
If not please examine the Conversion Log window for any errors.
|
||||
|
||||
|
||||
|
||||
If your book was actually a Topaz book:
|
||||
|
||||
Please note that Topaz is most similar to a poor man's image only PDF in style. It has glyphs and x,y positions, ocrText used just for searching, that describe the image each page all encoded into a binary xml-like set of files.
|
||||
|
||||
If successful, you will have 3 zip archives created.
|
||||
|
||||
1. The first is BOOKNAME_nodrm.zip.
|
||||
You can import this into calibre as is or unzip it and edit the book.html file you find inside. To create the book.html, Amazon's ocrText is combined with other information to recreate as closely as possible what the original book looked like. Unfortunately most bolding, italics is lost. Also, Amazon's ocrText can be absolutely horrible at times. Much work will be needed to clean up and correct Topaz books.
|
||||
|
||||
2. The second is BOOKNAME_SVG.zip
|
||||
You can also import this into calibre or unzip it and open the indexsvg.xhtml file in any good Browser (Safari, Firefox, etc). This zip contains a set of svg images (one for each pages is created) and it shows the page exactly how it appeared. This zip can be used to create an image only pdf file via post conversion.
|
||||
|
||||
3. The third is BOOKNAME_XML.zip
|
||||
This is a zip archive of the decrypted and translated xml-like descriptions of each page and can be archived/saved in case later code can do a better job converting these files. These are exactly what a Topaz books guts are. You should take a look at them in any text editor to see what they look like.
|
||||
|
||||
If the Topaz book conversion is not successful, a large _DEBUG.zip archive of all of the pieces is created and this can examined along with the Conversion Log window contents to determine the cause of the error and hopefully get it fixed in the next release.
|
||||
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,817 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
# For use with Topaz Scripts Version 2.6
|
||||
|
||||
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)
|
||||
|
||||
import sys
|
||||
sys.stdout=Unbuffered(sys.stdout)
|
||||
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
# Get a 7 bit encoded number from string. The most
|
||||
# significant byte comes first and has the high bit (8th) set
|
||||
|
||||
def readEncodedNumber(file):
|
||||
flag = False
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
|
||||
if data == 0xFF:
|
||||
flag = True
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
|
||||
if data >= 0x80:
|
||||
datax = (data & 0x7F)
|
||||
while data >= 0x80 :
|
||||
c = file.read(1)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
data = ord(c)
|
||||
datax = (datax <<7) + (data & 0x7F)
|
||||
data = datax
|
||||
|
||||
if flag:
|
||||
data = -data
|
||||
return data
|
||||
|
||||
|
||||
# returns a binary string that encodes a number into 7 bits
|
||||
# most significant byte first which has the high bit set
|
||||
|
||||
def encodeNumber(number):
|
||||
result = ""
|
||||
negative = False
|
||||
flag = 0
|
||||
|
||||
if number < 0 :
|
||||
number = -number + 1
|
||||
negative = True
|
||||
|
||||
while True:
|
||||
byte = number & 0x7F
|
||||
number = number >> 7
|
||||
byte += flag
|
||||
result += chr(byte)
|
||||
flag = 0x80
|
||||
if number == 0 :
|
||||
if (byte == 0xFF and negative == False) :
|
||||
result += chr(0x80)
|
||||
break
|
||||
|
||||
if negative:
|
||||
result += chr(0xFF)
|
||||
|
||||
return result[::-1]
|
||||
|
||||
|
||||
|
||||
# create / read a length prefixed string from the file
|
||||
|
||||
def lengthPrefixString(data):
|
||||
return encodeNumber(len(data))+data
|
||||
|
||||
def readString(file):
|
||||
stringLength = readEncodedNumber(file)
|
||||
if (stringLength == None):
|
||||
return ""
|
||||
sv = file.read(stringLength)
|
||||
if (len(sv) != stringLength):
|
||||
return ""
|
||||
return unpack(str(stringLength)+"s",sv)[0]
|
||||
|
||||
|
||||
# convert a binary string generated by encodeNumber (7 bit encoded number)
|
||||
# to the value you would find inside the page*.dat files to be processed
|
||||
|
||||
def convert(i):
|
||||
result = ''
|
||||
val = encodeNumber(i)
|
||||
for j in xrange(len(val)):
|
||||
c = ord(val[j:j+1])
|
||||
result += '%02x' % c
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# the complete string table used to store all book text content
|
||||
# as well as the xml tokens and values that make sense out of it
|
||||
|
||||
class Dictionary(object):
|
||||
def __init__(self, dictFile):
|
||||
self.filename = dictFile
|
||||
self.size = 0
|
||||
self.fo = file(dictFile,'rb')
|
||||
self.stable = []
|
||||
self.size = readEncodedNumber(self.fo)
|
||||
for i in xrange(self.size):
|
||||
self.stable.append(self.escapestr(readString(self.fo)))
|
||||
self.pos = 0
|
||||
|
||||
def escapestr(self, str):
|
||||
str = str.replace('&','&')
|
||||
str = str.replace('<','<')
|
||||
str = str.replace('>','>')
|
||||
str = str.replace('=','=')
|
||||
return str
|
||||
|
||||
def lookup(self,val):
|
||||
if ((val >= 0) and (val < self.size)) :
|
||||
self.pos = val
|
||||
return self.stable[self.pos]
|
||||
else:
|
||||
print "Error - %d outside of string table limits" % val
|
||||
sys.exit(-1)
|
||||
|
||||
def getSize(self):
|
||||
return self.size
|
||||
|
||||
def getPos(self):
|
||||
return self.pos
|
||||
|
||||
def dumpDict(self):
|
||||
for i in xrange(self.size):
|
||||
print "%d %s %s" % (i, convert(i), self.stable[i])
|
||||
return
|
||||
|
||||
# parses the xml snippets that are represented by each page*.dat file.
|
||||
# also parses the other0.dat file - the main stylesheet
|
||||
# and information used to inject the xml snippets into page*.dat files
|
||||
|
||||
class PageParser(object):
|
||||
def __init__(self, filename, dict, debug, flat_xml):
|
||||
self.fo = file(filename,'rb')
|
||||
self.id = os.path.basename(filename).replace('.dat','')
|
||||
self.dict = dict
|
||||
self.debug = debug
|
||||
self.flat_xml = flat_xml
|
||||
self.tagpath = []
|
||||
self.doc = []
|
||||
self.snippetList = []
|
||||
|
||||
|
||||
# hash table used to enable the decoding process
|
||||
# This has all been developed by trial and error so it may still have omissions or
|
||||
# contain errors
|
||||
# Format:
|
||||
# tag : (number of arguments, argument type, subtags present, special case of subtags presents when escaped)
|
||||
|
||||
token_tags = {
|
||||
'x' : (1, 'scalar_number', 0, 0),
|
||||
'y' : (1, 'scalar_number', 0, 0),
|
||||
'h' : (1, 'scalar_number', 0, 0),
|
||||
'w' : (1, 'scalar_number', 0, 0),
|
||||
'firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'lastWord' : (1, 'scalar_number', 0, 0),
|
||||
'rootID' : (1, 'scalar_number', 0, 0),
|
||||
'stemID' : (1, 'scalar_number', 0, 0),
|
||||
'type' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'info' : (0, 'number', 1, 0),
|
||||
|
||||
'info.word' : (0, 'number', 1, 1),
|
||||
'info.word.ocrText' : (1, 'text', 0, 0),
|
||||
'info.word.firstGlyph' : (1, 'raw', 0, 0),
|
||||
'info.word.lastGlyph' : (1, 'raw', 0, 0),
|
||||
'info.word.bl' : (1, 'raw', 0, 0),
|
||||
'info.word.link_id' : (1, 'number', 0, 0),
|
||||
|
||||
'glyph' : (0, 'number', 1, 1),
|
||||
'glyph.x' : (1, 'number', 0, 0),
|
||||
'glyph.y' : (1, 'number', 0, 0),
|
||||
'glyph.glyphID' : (1, 'number', 0, 0),
|
||||
|
||||
'dehyphen' : (0, 'number', 1, 1),
|
||||
'dehyphen.rootID' : (1, 'number', 0, 0),
|
||||
'dehyphen.stemID' : (1, 'number', 0, 0),
|
||||
'dehyphen.stemPage' : (1, 'number', 0, 0),
|
||||
'dehyphen.sh' : (1, 'number', 0, 0),
|
||||
|
||||
'links' : (0, 'number', 1, 1),
|
||||
'links.page' : (1, 'number', 0, 0),
|
||||
'links.rel' : (1, 'number', 0, 0),
|
||||
'links.row' : (1, 'number', 0, 0),
|
||||
'links.title' : (1, 'text', 0, 0),
|
||||
'links.href' : (1, 'text', 0, 0),
|
||||
'links.type' : (1, 'text', 0, 0),
|
||||
|
||||
'paraCont' : (0, 'number', 1, 1),
|
||||
'paraCont.rootID' : (1, 'number', 0, 0),
|
||||
'paraCont.stemID' : (1, 'number', 0, 0),
|
||||
'paraCont.stemPage' : (1, 'number', 0, 0),
|
||||
|
||||
'paraStems' : (0, 'number', 1, 1),
|
||||
'paraStems.stemID' : (1, 'number', 0, 0),
|
||||
|
||||
'wordStems' : (0, 'number', 1, 1),
|
||||
'wordStems.stemID' : (1, 'number', 0, 0),
|
||||
|
||||
'empty' : (1, 'snippets', 1, 0),
|
||||
|
||||
'page' : (1, 'snippets', 1, 0),
|
||||
'page.pageid' : (1, 'scalar_text', 0, 0),
|
||||
'page.pagelabel' : (1, 'scalar_text', 0, 0),
|
||||
'page.type' : (1, 'scalar_text', 0, 0),
|
||||
'page.h' : (1, 'scalar_number', 0, 0),
|
||||
'page.w' : (1, 'scalar_number', 0, 0),
|
||||
'page.startID' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'group' : (1, 'snippets', 1, 0),
|
||||
'group.type' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'region' : (1, 'snippets', 1, 0),
|
||||
'region.type' : (1, 'scalar_text', 0, 0),
|
||||
'region.x' : (1, 'scalar_number', 0, 0),
|
||||
'region.y' : (1, 'scalar_number', 0, 0),
|
||||
'region.h' : (1, 'scalar_number', 0, 0),
|
||||
'region.w' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'empty_text_region' : (1, 'snippets', 1, 0),
|
||||
|
||||
'img' : (1, 'snippets', 1, 0),
|
||||
'img.x' : (1, 'scalar_number', 0, 0),
|
||||
'img.y' : (1, 'scalar_number', 0, 0),
|
||||
'img.h' : (1, 'scalar_number', 0, 0),
|
||||
'img.w' : (1, 'scalar_number', 0, 0),
|
||||
'img.src' : (1, 'scalar_number', 0, 0),
|
||||
'img.color_src' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'paragraph' : (1, 'snippets', 1, 0),
|
||||
'paragraph.class' : (1, 'scalar_text', 0, 0),
|
||||
'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'paragraph.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'word_semantic' : (1, 'snippets', 1, 1),
|
||||
'word_semantic.type' : (1, 'scalar_text', 0, 0),
|
||||
'word_semantic.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'word_semantic.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'word' : (1, 'snippets', 1, 0),
|
||||
'word.type' : (1, 'scalar_text', 0, 0),
|
||||
'word.class' : (1, 'scalar_text', 0, 0),
|
||||
'word.firstGlyph' : (1, 'scalar_number', 0, 0),
|
||||
'word.lastGlyph' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'_span' : (1, 'snippets', 1, 0),
|
||||
'_span.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'-span.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'span' : (1, 'snippets', 1, 0),
|
||||
'span.firstWord' : (1, 'scalar_number', 0, 0),
|
||||
'span.lastWord' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'extratokens' : (1, 'snippets', 1, 0),
|
||||
'extratokens.type' : (1, 'scalar_text', 0, 0),
|
||||
'extratokens.firstGlyph' : (1, 'scalar_number', 0, 0),
|
||||
'extratokens.lastGlyph' : (1, 'scalar_number', 0, 0),
|
||||
|
||||
'glyph.h' : (1, 'number', 0, 0),
|
||||
'glyph.w' : (1, 'number', 0, 0),
|
||||
'glyph.use' : (1, 'number', 0, 0),
|
||||
'glyph.vtx' : (1, 'number', 0, 1),
|
||||
'glyph.len' : (1, 'number', 0, 1),
|
||||
'glyph.dpi' : (1, 'number', 0, 0),
|
||||
'vtx' : (0, 'number', 1, 1),
|
||||
'vtx.x' : (1, 'number', 0, 0),
|
||||
'vtx.y' : (1, 'number', 0, 0),
|
||||
'len' : (0, 'number', 1, 1),
|
||||
'len.n' : (1, 'number', 0, 0),
|
||||
|
||||
'book' : (1, 'snippets', 1, 0),
|
||||
'version' : (1, 'snippets', 1, 0),
|
||||
'version.FlowEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.FlowEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.Schema_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.Schema_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.Topaz_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.WordDetailEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.WordDetailEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.ZoneEdit_1_id' : (1, 'scalar_text', 0, 0),
|
||||
'version.ZoneEdit_1_version' : (1, 'scalar_text', 0, 0),
|
||||
'version.chapterheaders' : (1, 'scalar_text', 0, 0),
|
||||
'version.creation_date' : (1, 'scalar_text', 0, 0),
|
||||
'version.header_footer' : (1, 'scalar_text', 0, 0),
|
||||
'version.init_from_ocr' : (1, 'scalar_text', 0, 0),
|
||||
'version.letter_insertion' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_convert' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_reflow' : (1, 'scalar_text', 0, 0),
|
||||
'version.xmlinj_transform' : (1, 'scalar_text', 0, 0),
|
||||
'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),
|
||||
'style._tag' : (1, 'scalar_text', 0, 0),
|
||||
'style.type' : (1, 'scalar_text', 0, 0),
|
||||
'style._parent_type' : (1, 'scalar_text', 0, 0),
|
||||
'style.class' : (1, 'scalar_text', 0, 0),
|
||||
'style._after_class' : (1, 'scalar_text', 0, 0),
|
||||
'rule' : (1, 'snippets', 1, 0),
|
||||
'rule.attr' : (1, 'scalar_text', 0, 0),
|
||||
'rule.value' : (1, 'scalar_text', 0, 0),
|
||||
|
||||
'original' : (0, 'number', 1, 1),
|
||||
'original.pnum' : (1, 'number', 0, 0),
|
||||
'original.pid' : (1, 'text', 0, 0),
|
||||
'pages' : (0, 'number', 1, 1),
|
||||
'pages.ref' : (1, 'number', 0, 0),
|
||||
'pages.id' : (1, 'number', 0, 0),
|
||||
'startID' : (0, 'number', 1, 1),
|
||||
'startID.page' : (1, 'number', 0, 0),
|
||||
'startID.id' : (1, 'number', 0, 0),
|
||||
|
||||
}
|
||||
|
||||
|
||||
# full tag path record keeping routines
|
||||
def tag_push(self, token):
|
||||
self.tagpath.append(token)
|
||||
def tag_pop(self):
|
||||
if len(self.tagpath) > 0 :
|
||||
self.tagpath.pop()
|
||||
def tagpath_len(self):
|
||||
return len(self.tagpath)
|
||||
def get_tagpath(self, i):
|
||||
cnt = len(self.tagpath)
|
||||
if i < cnt : result = self.tagpath[i]
|
||||
for j in xrange(i+1, cnt) :
|
||||
result += '.' + self.tagpath[j]
|
||||
return result
|
||||
|
||||
|
||||
# list of absolute command byte values values that indicate
|
||||
# various types of loop meachanisms typically used to generate vectors
|
||||
|
||||
cmd_list = (0x76, 0x76)
|
||||
|
||||
# peek at and return 1 byte that is ahead by i bytes
|
||||
def peek(self, aheadi):
|
||||
c = self.fo.read(aheadi)
|
||||
if (len(c) == 0):
|
||||
return None
|
||||
self.fo.seek(-aheadi,1)
|
||||
c = c[-1:]
|
||||
return ord(c)
|
||||
|
||||
|
||||
# get the next value from the file being processed
|
||||
def getNext(self):
|
||||
nbyte = self.peek(1);
|
||||
if (nbyte == None):
|
||||
return None
|
||||
val = readEncodedNumber(self.fo)
|
||||
return val
|
||||
|
||||
|
||||
# format an arg by argtype
|
||||
def formatArg(self, arg, argtype):
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
result = self.dict.lookup(arg)
|
||||
elif (argtype == 'raw') or (argtype == 'number') or (argtype == 'scalar_number') :
|
||||
result = arg
|
||||
elif (argtype == 'snippets') :
|
||||
result = arg
|
||||
else :
|
||||
print "Error Unknown argtype %s" % argtype
|
||||
sys.exit(-2)
|
||||
return result
|
||||
|
||||
|
||||
# process the next tag token, recursively handling subtags,
|
||||
# arguments, and commands
|
||||
def procToken(self, token):
|
||||
|
||||
known_token = False
|
||||
self.tag_push(token)
|
||||
|
||||
if self.debug : print 'Processing: ', self.get_tagpath(0)
|
||||
cnt = self.tagpath_len()
|
||||
for j in xrange(cnt):
|
||||
tkn = self.get_tagpath(j)
|
||||
if tkn in self.token_tags :
|
||||
num_args = self.token_tags[tkn][0]
|
||||
argtype = self.token_tags[tkn][1]
|
||||
subtags = self.token_tags[tkn][2]
|
||||
splcase = self.token_tags[tkn][3]
|
||||
ntags = -1
|
||||
known_token = True
|
||||
break
|
||||
|
||||
if known_token :
|
||||
|
||||
# handle subtags if present
|
||||
subtagres = []
|
||||
if (splcase == 1):
|
||||
# this type of tag uses of escape marker 0x74 indicate subtag count
|
||||
if self.peek(1) == 0x74:
|
||||
skip = readEncodedNumber(self.fo)
|
||||
subtags = 1
|
||||
num_args = 0
|
||||
|
||||
if (subtags == 1):
|
||||
ntags = readEncodedNumber(self.fo)
|
||||
if self.debug : print 'subtags: ' + token + ' has ' + str(ntags)
|
||||
for j in xrange(ntags):
|
||||
val = readEncodedNumber(self.fo)
|
||||
subtagres.append(self.procToken(self.dict.lookup(val)))
|
||||
|
||||
# arguments can be scalars or vectors of text or numbers
|
||||
argres = []
|
||||
if num_args > 0 :
|
||||
firstarg = self.peek(1)
|
||||
if (firstarg in self.cmd_list) and (argtype != 'scalar_number') and (argtype != 'scalar_text'):
|
||||
# single argument is a variable length vector of data
|
||||
arg = readEncodedNumber(self.fo)
|
||||
argres = self.decodeCMD(arg,argtype)
|
||||
else :
|
||||
# num_arg scalar arguments
|
||||
for i in xrange(num_args):
|
||||
argres.append(self.formatArg(readEncodedNumber(self.fo), argtype))
|
||||
|
||||
# build the return tag
|
||||
result = []
|
||||
tkn = self.get_tagpath(0)
|
||||
result.append(tkn)
|
||||
result.append(subtagres)
|
||||
result.append(argtype)
|
||||
result.append(argres)
|
||||
self.tag_pop()
|
||||
return result
|
||||
|
||||
# all tokens that need to be processed should be in the hash
|
||||
# table if it may indicate a problem, either new token
|
||||
# or an out of sync condition
|
||||
else:
|
||||
result = []
|
||||
if (self.debug):
|
||||
print 'Unknown Token:', token
|
||||
self.tag_pop()
|
||||
return result
|
||||
|
||||
|
||||
# special loop used to process code snippets
|
||||
# it is NEVER used to format arguments.
|
||||
# builds the snippetList
|
||||
def doLoop72(self, argtype):
|
||||
cnt = readEncodedNumber(self.fo)
|
||||
if self.debug :
|
||||
result = 'Set of '+ str(cnt) + ' xml snippets. The overall structure \n'
|
||||
result += 'of the document is indicated by snippet number sets at the\n'
|
||||
result += 'end of each snippet. \n'
|
||||
print result
|
||||
for i in xrange(cnt):
|
||||
if self.debug: print 'Snippet:',str(i)
|
||||
snippet = []
|
||||
snippet.append(i)
|
||||
val = readEncodedNumber(self.fo)
|
||||
snippet.append(self.procToken(self.dict.lookup(val)))
|
||||
self.snippetList.append(snippet)
|
||||
return
|
||||
|
||||
|
||||
|
||||
# general loop code gracisouly submitted by "skindle" - thank you!
|
||||
def doLoop76Mode(self, argtype, cnt, mode):
|
||||
result = []
|
||||
adj = 0
|
||||
if mode & 1:
|
||||
adj = readEncodedNumber(self.fo)
|
||||
mode = mode >> 1
|
||||
x = []
|
||||
for i in xrange(cnt):
|
||||
x.append(readEncodedNumber(self.fo) - adj)
|
||||
for i in xrange(mode):
|
||||
for j in xrange(1, cnt):
|
||||
x[j] = x[j] + x[j - 1]
|
||||
for i in xrange(cnt):
|
||||
result.append(self.formatArg(x[i],argtype))
|
||||
return result
|
||||
|
||||
|
||||
# dispatches loop commands bytes with various modes
|
||||
# The 0x76 style loops are used to build vectors
|
||||
|
||||
# This was all derived by trial and error and
|
||||
# new loop types may exist that are not handled here
|
||||
# since they did not appear in the test cases
|
||||
|
||||
def decodeCMD(self, cmd, argtype):
|
||||
if (cmd == 0x76):
|
||||
|
||||
# loop with cnt, and mode to control loop styles
|
||||
cnt = readEncodedNumber(self.fo)
|
||||
mode = readEncodedNumber(self.fo)
|
||||
|
||||
if self.debug : print 'Loop for', cnt, 'with mode', mode, ': '
|
||||
return self.doLoop76Mode(argtype, cnt, mode)
|
||||
|
||||
if self.dbug: print "Unknown command", cmd
|
||||
result = []
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# add full tag path to injected snippets
|
||||
def updateName(self, tag, prefix):
|
||||
name = tag[0]
|
||||
subtagList = tag[1]
|
||||
argtype = tag[2]
|
||||
argList = tag[3]
|
||||
nname = prefix + '.' + name
|
||||
nsubtaglist = []
|
||||
for j in subtagList:
|
||||
nsubtaglist.append(self.updateName(j,prefix))
|
||||
ntag = []
|
||||
ntag.append(nname)
|
||||
ntag.append(nsubtaglist)
|
||||
ntag.append(argtype)
|
||||
ntag.append(argList)
|
||||
return ntag
|
||||
|
||||
|
||||
|
||||
# perform depth first injection of specified snippets into this one
|
||||
def injectSnippets(self, snippet):
|
||||
snipno, tag = snippet
|
||||
name = tag[0]
|
||||
subtagList = tag[1]
|
||||
argtype = tag[2]
|
||||
argList = tag[3]
|
||||
nsubtagList = []
|
||||
if len(argList) > 0 :
|
||||
for j in argList:
|
||||
asnip = self.snippetList[j]
|
||||
aso, atag = self.injectSnippets(asnip)
|
||||
atag = self.updateName(atag, name)
|
||||
nsubtagList.append(atag)
|
||||
argtype='number'
|
||||
argList=[]
|
||||
if len(nsubtagList) > 0 :
|
||||
subtagList.extend(nsubtagList)
|
||||
tag = []
|
||||
tag.append(name)
|
||||
tag.append(subtagList)
|
||||
tag.append(argtype)
|
||||
tag.append(argList)
|
||||
snippet = []
|
||||
snippet.append(snipno)
|
||||
snippet.append(tag)
|
||||
return snippet
|
||||
|
||||
|
||||
|
||||
# format the tag for output
|
||||
def formatTag(self, node):
|
||||
name = node[0]
|
||||
subtagList = node[1]
|
||||
argtype = node[2]
|
||||
argList = node[3]
|
||||
fullpathname = name.split('.')
|
||||
nodename = fullpathname.pop()
|
||||
ilvl = len(fullpathname)
|
||||
indent = ' ' * (3 * ilvl)
|
||||
result = indent + '<' + nodename + '>'
|
||||
if len(argList) > 0:
|
||||
argres = ''
|
||||
for j in argList:
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
argres += j + '|'
|
||||
else :
|
||||
argres += str(j) + ','
|
||||
argres = argres[0:-1]
|
||||
if argtype == 'snippets' :
|
||||
result += 'snippets:' + argres
|
||||
else :
|
||||
result += argres
|
||||
if len(subtagList) > 0 :
|
||||
result += '\n'
|
||||
for j in subtagList:
|
||||
if len(j) > 0 :
|
||||
result += self.formatTag(j)
|
||||
result += indent + '</' + nodename + '>\n'
|
||||
else:
|
||||
result += '</' + nodename + '>\n'
|
||||
return result
|
||||
|
||||
|
||||
# flatten tag
|
||||
def flattenTag(self, node):
|
||||
name = node[0]
|
||||
subtagList = node[1]
|
||||
argtype = node[2]
|
||||
argList = node[3]
|
||||
result = name
|
||||
if (len(argList) > 0):
|
||||
argres = ''
|
||||
for j in argList:
|
||||
if (argtype == 'text') or (argtype == 'scalar_text') :
|
||||
argres += j + '|'
|
||||
else :
|
||||
argres += str(j) + '|'
|
||||
argres = argres[0:-1]
|
||||
if argtype == 'snippets' :
|
||||
result += '.snippets=' + argres
|
||||
else :
|
||||
result += '=' + argres
|
||||
result += '\n'
|
||||
for j in subtagList:
|
||||
if len(j) > 0 :
|
||||
result += self.flattenTag(j)
|
||||
return result
|
||||
|
||||
|
||||
# reduce create xml output
|
||||
def formatDoc(self, flat_xml):
|
||||
result = ''
|
||||
for j in self.doc :
|
||||
if len(j) > 0:
|
||||
if flat_xml:
|
||||
result += self.flattenTag(j)
|
||||
else:
|
||||
result += self.formatTag(j)
|
||||
if self.debug : print result
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# main loop - parse the page.dat files
|
||||
# to create structured document and snippets
|
||||
|
||||
# FIXME: value at end of magic appears to be a subtags count
|
||||
# but for what? For now, inject an 'info" tag as it is in
|
||||
# every dictionary and seems close to what is meant
|
||||
# The alternative is to special case the last _ "0x5f" to mean something
|
||||
|
||||
def process(self):
|
||||
|
||||
# peek at the first bytes to see what type of file it is
|
||||
magic = self.fo.read(9)
|
||||
if (magic[0:1] == 'p') and (magic[2:9] == 'marker_'):
|
||||
first_token = 'info'
|
||||
elif (magic[0:1] == 'p') and (magic[2:9] == '__PAGE_'):
|
||||
skip = self.fo.read(2)
|
||||
first_token = 'info'
|
||||
elif (magic[0:1] == 'p') and (magic[2:8] == '_PAGE_'):
|
||||
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(-9,1)
|
||||
|
||||
|
||||
# main loop to read and build the document tree
|
||||
while True:
|
||||
|
||||
if first_token != None :
|
||||
# use "inserted" first token 'info' for page and glyph files
|
||||
tag = self.procToken(first_token)
|
||||
if len(tag) > 0 :
|
||||
self.doc.append(tag)
|
||||
first_token = None
|
||||
|
||||
v = self.getNext()
|
||||
if (v == None):
|
||||
break
|
||||
|
||||
if (v == 0x72):
|
||||
self.doLoop72('number')
|
||||
elif (v > 0) and (v < self.dict.getSize()) :
|
||||
tag = self.procToken(self.dict.lookup(v))
|
||||
if len(tag) > 0 :
|
||||
self.doc.append(tag)
|
||||
else:
|
||||
if self.debug:
|
||||
print "Main Loop: Unknown value: %x" % v
|
||||
if (v == 0):
|
||||
if (self.peek(1) == 0x5f):
|
||||
skip = self.fo.read(1)
|
||||
first_token = 'info'
|
||||
|
||||
# now do snippet injection
|
||||
if len(self.snippetList) > 0 :
|
||||
if self.debug : print 'Injecting Snippets:'
|
||||
snippet = self.injectSnippets(self.snippetList[0])
|
||||
snipno = snippet[0]
|
||||
tag_add = snippet[1]
|
||||
if self.debug : print self.formatTag(tag_add)
|
||||
if len(tag_add) > 0:
|
||||
self.doc.append(tag_add)
|
||||
|
||||
# handle generation of xml output
|
||||
xmlpage = self.formatDoc(self.flat_xml)
|
||||
|
||||
return xmlpage
|
||||
|
||||
|
||||
def fromData(dict, fname):
|
||||
flat_xml = True
|
||||
debug = False
|
||||
pp = PageParser(fname, dict, debug, flat_xml)
|
||||
xmlpage = pp.process()
|
||||
return xmlpage
|
||||
|
||||
def getXML(dict, fname):
|
||||
flat_xml = False
|
||||
debug = False
|
||||
pp = PageParser(fname, dict, debug, flat_xml)
|
||||
xmlpage = pp.process()
|
||||
return xmlpage
|
||||
|
||||
def usage():
|
||||
print 'Usage: '
|
||||
print ' convert2xml.py dict0000.dat infile.dat '
|
||||
print ' '
|
||||
print ' Options:'
|
||||
print ' -h print this usage help message '
|
||||
print ' -d turn on debug output to check for potential errors '
|
||||
print ' --flat-xml output the flattened xml page description only '
|
||||
print ' '
|
||||
print ' This program will attempt to convert a page*.dat file or '
|
||||
print ' glyphs*.dat file, using the dict0000.dat file, to its xml description. '
|
||||
print ' '
|
||||
print ' Use "cmbtc_dump.py" first to unencrypt, uncompress, and dump '
|
||||
print ' the *.dat files from a Topaz format e-book.'
|
||||
|
||||
#
|
||||
# Main
|
||||
#
|
||||
|
||||
def main(argv):
|
||||
dictFile = ""
|
||||
pageFile = ""
|
||||
debug = False
|
||||
flat_xml = False
|
||||
printOutput = False
|
||||
if len(argv) == 0:
|
||||
printOutput = True
|
||||
argv = sys.argv
|
||||
|
||||
try:
|
||||
opts, args = getopt.getopt(argv[1:], "hd", ["flat-xml"])
|
||||
|
||||
except getopt.GetoptError, err:
|
||||
|
||||
# print help information and exit:
|
||||
print str(err) # will print something like "option -a not recognized"
|
||||
usage()
|
||||
sys.exit(2)
|
||||
|
||||
if len(opts) == 0 and len(args) == 0 :
|
||||
usage()
|
||||
sys.exit(2)
|
||||
|
||||
for o, a in opts:
|
||||
if o =="-d":
|
||||
debug=True
|
||||
if o =="-h":
|
||||
usage()
|
||||
sys.exit(0)
|
||||
if o =="--flat-xml":
|
||||
flat_xml = True
|
||||
|
||||
dictFile, pageFile = args[0], args[1]
|
||||
|
||||
# read in the string table dictionary
|
||||
dict = Dictionary(dictFile)
|
||||
# dict.dumpDict()
|
||||
|
||||
# create a page parser
|
||||
pp = PageParser(pageFile, dict, debug, flat_xml)
|
||||
|
||||
xmlpage = pp.process()
|
||||
|
||||
if printOutput:
|
||||
print xmlpage
|
||||
return 0
|
||||
|
||||
return xmlpage
|
||||
|
||||
if __name__ == '__main__':
|
||||
sys.exit(main(''))
|
@ -0,0 +1,706 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
# For use with Topaz Scripts Version 2.6
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import math
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class DocParser(object):
|
||||
def __init__(self, flatxml, classlst, fileid, bookDir, gdict, fixedimage):
|
||||
self.id = os.path.basename(fileid).replace('.dat','')
|
||||
self.svgcount = 0
|
||||
self.docList = flatxml.split('\n')
|
||||
self.docSize = len(self.docList)
|
||||
self.classList = {}
|
||||
self.bookDir = bookDir
|
||||
self.gdict = gdict
|
||||
tmpList = classlst.split('\n')
|
||||
for pclass in tmpList:
|
||||
if pclass != '':
|
||||
# remove the leading period from the css name
|
||||
cname = pclass[1:]
|
||||
self.classList[cname] = True
|
||||
self.fixedimage = fixedimage
|
||||
self.ocrtext = []
|
||||
self.link_id = []
|
||||
self.link_title = []
|
||||
self.link_page = []
|
||||
self.link_href = []
|
||||
self.link_type = []
|
||||
self.dehyphen_rootid = []
|
||||
self.paracont_stemid = []
|
||||
self.parastems_stemid = []
|
||||
|
||||
|
||||
def getGlyph(self, gid):
|
||||
result = ''
|
||||
id='id="gl%d"' % gid
|
||||
return self.gdict.lookup(id)
|
||||
|
||||
def glyphs_to_image(self, glyphList):
|
||||
|
||||
def extract(path, key):
|
||||
b = path.find(key) + len(key)
|
||||
e = path.find(' ',b)
|
||||
return int(path[b:e])
|
||||
|
||||
svgDir = os.path.join(self.bookDir,'svg')
|
||||
|
||||
imgDir = os.path.join(self.bookDir,'img')
|
||||
imgname = self.id + '_%04d.svg' % self.svgcount
|
||||
imgfile = os.path.join(imgDir,imgname)
|
||||
|
||||
# get glyph information
|
||||
gxList = self.getData('info.glyph.x',0,-1)
|
||||
gyList = self.getData('info.glyph.y',0,-1)
|
||||
gidList = self.getData('info.glyph.glyphID',0,-1)
|
||||
|
||||
gids = []
|
||||
maxws = []
|
||||
maxhs = []
|
||||
xs = []
|
||||
ys = []
|
||||
gdefs = []
|
||||
|
||||
# get path defintions, positions, dimensions for ecah glyph
|
||||
# that makes up the image, and find min x and min y to reposition origin
|
||||
minx = -1
|
||||
miny = -1
|
||||
for j in glyphList:
|
||||
gid = gidList[j]
|
||||
gids.append(gid)
|
||||
|
||||
xs.append(gxList[j])
|
||||
if minx == -1: minx = gxList[j]
|
||||
else : minx = min(minx, gxList[j])
|
||||
|
||||
ys.append(gyList[j])
|
||||
if miny == -1: miny = gyList[j]
|
||||
else : miny = min(miny, gyList[j])
|
||||
|
||||
path = self.getGlyph(gid)
|
||||
gdefs.append(path)
|
||||
|
||||
maxws.append(extract(path,'width='))
|
||||
maxhs.append(extract(path,'height='))
|
||||
|
||||
|
||||
# change the origin to minx, miny and calc max height and width
|
||||
maxw = maxws[0] + xs[0] - minx
|
||||
maxh = maxhs[0] + ys[0] - miny
|
||||
for j in xrange(0, len(xs)):
|
||||
xs[j] = xs[j] - minx
|
||||
ys[j] = ys[j] - miny
|
||||
maxw = max( maxw, (maxws[j] + xs[j]) )
|
||||
maxh = max( maxh, (maxhs[j] + ys[j]) )
|
||||
|
||||
# open the image file for output
|
||||
ifile = open(imgfile,'w')
|
||||
ifile.write('<?xml version="1.0" standalone="no"?>\n')
|
||||
ifile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
|
||||
ifile.write('<svg width="%dpx" height="%dpx" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (math.floor(maxw/10), math.floor(maxh/10), maxw, maxh))
|
||||
ifile.write('<defs>\n')
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ifile.write(gdefs[j])
|
||||
ifile.write('</defs>\n')
|
||||
for j in xrange(0,len(gids)):
|
||||
ifile.write('<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (gids[j], xs[j], ys[j]))
|
||||
ifile.write('</svg>')
|
||||
ifile.close()
|
||||
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
# return tag at line pos in document
|
||||
def lineinDoc(self, pos) :
|
||||
if (pos >= 0) and (pos < self.docSize) :
|
||||
item = self.docList[pos]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
return name, argres
|
||||
|
||||
|
||||
# find tag in doc if within pos to end inclusive
|
||||
def findinDoc(self, tagpath, pos, end) :
|
||||
result = None
|
||||
if end == -1 :
|
||||
end = self.docSize
|
||||
else:
|
||||
end = min(self.docSize, end)
|
||||
foundat = -1
|
||||
for j in xrange(pos, end):
|
||||
item = self.docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
result = argres
|
||||
foundat = j
|
||||
break
|
||||
return foundat, result
|
||||
|
||||
|
||||
# return list of start positions for the tagpath
|
||||
def posinDoc(self, tagpath):
|
||||
startpos = []
|
||||
pos = 0
|
||||
res = ""
|
||||
while res != None :
|
||||
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
|
||||
if res != None :
|
||||
startpos.append(foundpos)
|
||||
pos = foundpos + 1
|
||||
return startpos
|
||||
|
||||
|
||||
# returns a vector of integers for the tagpath
|
||||
def getData(self, tagpath, pos, end):
|
||||
argres=[]
|
||||
(foundat, argt) = self.findinDoc(tagpath, pos, end)
|
||||
if (argt != None) and (len(argt) > 0) :
|
||||
argList = argt.split('|')
|
||||
argres = [ int(strval) for strval in argList]
|
||||
return argres
|
||||
|
||||
|
||||
# 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
|
||||
# from a base class (but then not actually provide all of these _reclustereed
|
||||
# classes in the stylesheet!
|
||||
|
||||
# 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
|
||||
baseclass = ''
|
||||
# graphic is the base class for captions
|
||||
if nclass.find('cl-cap-') >=0 :
|
||||
classres = 'graphic' + ' '
|
||||
else :
|
||||
# strip to find baseclass
|
||||
p = nclass.find('_')
|
||||
if p > 0 :
|
||||
baseclass = nclass[0:p]
|
||||
if baseclass in self.classList:
|
||||
classres += baseclass + ' '
|
||||
classres += nclass
|
||||
nclass = classres
|
||||
return nclass
|
||||
|
||||
|
||||
# develop a sorted description of the starting positions of
|
||||
# groups and regions on the page, as well as the page type
|
||||
def PageDescription(self):
|
||||
|
||||
def compare(x, y):
|
||||
(xtype, xval) = x
|
||||
(ytype, yval) = y
|
||||
if xval > yval:
|
||||
return 1
|
||||
if xval == yval:
|
||||
return 0
|
||||
return -1
|
||||
|
||||
result = []
|
||||
(pos, pagetype) = self.findinDoc('page.type',0,-1)
|
||||
|
||||
groupList = self.posinDoc('page.group')
|
||||
groupregionList = self.posinDoc('page.group.region')
|
||||
pageregionList = self.posinDoc('page.region')
|
||||
# integrate into one list
|
||||
for j in groupList:
|
||||
result.append(('grpbeg',j))
|
||||
for j in groupregionList:
|
||||
result.append(('gregion',j))
|
||||
for j in pageregionList:
|
||||
result.append(('pregion',j))
|
||||
result.sort(compare)
|
||||
|
||||
# insert group end and page end indicators
|
||||
inGroup = False
|
||||
j = 0
|
||||
while True:
|
||||
if j == len(result): break
|
||||
rtype = result[j][0]
|
||||
rval = result[j][1]
|
||||
if not inGroup and (rtype == 'grpbeg') :
|
||||
inGroup = True
|
||||
j = j + 1
|
||||
elif inGroup and (rtype in ('grpbeg', 'pregion')):
|
||||
result.insert(j,('grpend',rval))
|
||||
inGroup = False
|
||||
else:
|
||||
j = j + 1
|
||||
if inGroup:
|
||||
result.append(('grpend',-1))
|
||||
result.append(('pageend', -1))
|
||||
return pagetype, result
|
||||
|
||||
|
||||
|
||||
# build a description of the paragraph
|
||||
def getParaDescription(self, start, end, regtype):
|
||||
|
||||
result = []
|
||||
|
||||
# paragraph
|
||||
(pos, pclass) = self.findinDoc('paragraph.class',start,end)
|
||||
|
||||
pclass = self.getClass(pclass)
|
||||
|
||||
# build up a description of the paragraph in result and return it
|
||||
# first check for the basic - all words paragraph
|
||||
(pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
|
||||
(pos, slast) = self.findinDoc('paragraph.lastWord',start,end)
|
||||
if (sfirst != None) and (slast != None) :
|
||||
first = int(sfirst)
|
||||
last = int(slast)
|
||||
|
||||
makeImage = (regtype == 'vertical') or (regtype == 'table')
|
||||
if self.fixedimage:
|
||||
makeImage = makeImage or (regtype == 'fixed')
|
||||
|
||||
if (pclass != None):
|
||||
makeImage = makeImage or (pclass.find('.inverted') >= 0)
|
||||
if self.fixedimage :
|
||||
makeImage = makeImage or (pclass.find('cl-f-') >= 0)
|
||||
|
||||
if not makeImage :
|
||||
# standard all word paragraph
|
||||
for wordnum in xrange(first, last):
|
||||
result.append(('ocr', wordnum))
|
||||
return pclass, result
|
||||
|
||||
# convert paragraph to svg image
|
||||
# translate first and last word into first and last glyphs
|
||||
# and generate inline image and include it
|
||||
glyphList = []
|
||||
firstglyphList = self.getData('word.firstGlyph',0,-1)
|
||||
gidList = self.getData('info.glyph.glyphID',0,-1)
|
||||
firstGlyph = firstglyphList[first]
|
||||
if last < len(firstglyphList):
|
||||
lastGlyph = firstglyphList[last]
|
||||
else :
|
||||
lastGlyph = len(gidList)
|
||||
for glyphnum in xrange(firstGlyph, lastGlyph):
|
||||
glyphList.append(glyphnum)
|
||||
# include any extratokens if they exist
|
||||
(pos, sfg) = self.findinDoc('extratokens.firstGlyph',start,end)
|
||||
(pos, slg) = self.findinDoc('extratokens.lastGlyph',start,end)
|
||||
if (sfg != None) and (slg != None):
|
||||
for glyphnum in xrange(int(sfg), int(slg)):
|
||||
glyphList.append(glyphnum)
|
||||
num = self.svgcount
|
||||
self.glyphs_to_image(glyphList)
|
||||
self.svgcount += 1
|
||||
result.append(('svg', num))
|
||||
return pclass, result
|
||||
|
||||
# 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
|
||||
|
||||
# need to parse this type line by line
|
||||
line = start + 1
|
||||
word_class = ''
|
||||
|
||||
# if end is -1 then we must search to end of document
|
||||
if end == -1 :
|
||||
end = self.docSize
|
||||
|
||||
# seems some xml has last* coming before first* so we have to
|
||||
# handle any order
|
||||
sp_first = -1
|
||||
sp_last = -1
|
||||
|
||||
gl_first = -1
|
||||
gl_last = -1
|
||||
|
||||
ws_first = -1
|
||||
ws_last = -1
|
||||
|
||||
word_class = ''
|
||||
|
||||
while (line < end) :
|
||||
|
||||
(name, argres) = self.lineinDoc(line)
|
||||
|
||||
if name.endswith('span.firstWord') :
|
||||
sp_first = int(argres)
|
||||
|
||||
elif name.endswith('span.lastWord') :
|
||||
sp_last = int(argres)
|
||||
|
||||
elif name.endswith('word.firstGlyph') :
|
||||
gl_first = int(argres)
|
||||
|
||||
elif name.endswith('word.lastGlyph') :
|
||||
gl_last = int(argres)
|
||||
|
||||
elif name.endswith('word_semantic.firstWord'):
|
||||
ws_first = int(argres)
|
||||
|
||||
elif name.endswith('word_semantic.lastWord'):
|
||||
ws_last = int(argres)
|
||||
|
||||
elif name.endswith('word.class'):
|
||||
(cname, space) = argres.split('-',1)
|
||||
if space == '' : space = '0'
|
||||
if (cname == 'spaceafter') and (int(space) > 0) :
|
||||
word_class = 'sa'
|
||||
|
||||
elif name.endswith('word.img.src'):
|
||||
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))
|
||||
sp_first = -1
|
||||
sp_last = -1
|
||||
|
||||
if (gl_first != -1) and (gl_last != -1):
|
||||
glyphList = []
|
||||
for glyphnum in xrange(gl_first, gl_last):
|
||||
glyphList.append(glyphnum)
|
||||
num = self.svgcount
|
||||
self.glyphs_to_image(glyphList)
|
||||
self.svgcount += 1
|
||||
result.append(('svg', num))
|
||||
gl_first = -1
|
||||
gl_last = -1
|
||||
|
||||
if (ws_first != -1) and (ws_last != -1):
|
||||
for wordnum in xrange(ws_first, ws_last):
|
||||
result.append(('ocr', wordnum))
|
||||
ws_first = -1
|
||||
ws_last = -1
|
||||
|
||||
line += 1
|
||||
|
||||
return pclass, result
|
||||
|
||||
|
||||
def buildParagraph(self, pclass, pdesc, type, regtype) :
|
||||
parares = ''
|
||||
sep =''
|
||||
|
||||
classres = ''
|
||||
if pclass :
|
||||
classres = ' class="' + pclass + '"'
|
||||
|
||||
br_lb = (regtype == 'fixed') or (regtype == 'chapterheading') or (regtype == 'vertical')
|
||||
|
||||
handle_links = len(self.link_id) > 0
|
||||
|
||||
if (type == 'full') or (type == 'begin') :
|
||||
parares += '<p' + classres + '>'
|
||||
|
||||
if (type == 'end'):
|
||||
parares += ' '
|
||||
|
||||
lstart = len(parares)
|
||||
|
||||
cnt = len(pdesc)
|
||||
|
||||
for j in xrange( 0, cnt) :
|
||||
|
||||
(wtype, num) = pdesc[j]
|
||||
|
||||
if wtype == 'ocr' :
|
||||
word = self.ocrtext[num]
|
||||
sep = ' '
|
||||
|
||||
if handle_links:
|
||||
link = self.link_id[num]
|
||||
if (link > 0):
|
||||
linktype = self.link_type[link-1]
|
||||
title = self.link_title[link-1]
|
||||
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 = ''
|
||||
|
||||
if word == '_lb_':
|
||||
if ((num-1) in self.dehyphen_rootid ) or handle_links:
|
||||
word = ''
|
||||
sep = ''
|
||||
elif br_lb :
|
||||
word = '<br />\n'
|
||||
sep = ''
|
||||
else :
|
||||
word = '\n'
|
||||
sep = ''
|
||||
|
||||
if num in self.dehyphen_rootid :
|
||||
word = word[0:-1]
|
||||
sep = ''
|
||||
|
||||
parares += word + sep
|
||||
|
||||
elif wtype == 'img' :
|
||||
sep = ''
|
||||
parares += '<img src="img/img%04d.jpg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
elif wtype == 'imgsa' :
|
||||
sep = ' '
|
||||
parares += '<img src="img/img%04d.jpg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
elif wtype == 'svg' :
|
||||
sep = ''
|
||||
parares += '<img src="img/' + self.id + '_%04d.svg" alt="" />' % num
|
||||
parares += sep
|
||||
|
||||
if len(sep) > 0 : parares = parares[0:-1]
|
||||
if (type == 'full') or (type == 'end') :
|
||||
parares += '</p>'
|
||||
return parares
|
||||
|
||||
|
||||
|
||||
# walk the document tree collecting the information needed
|
||||
# to build an html page using the ocrText
|
||||
|
||||
def process(self):
|
||||
|
||||
htmlpage = ''
|
||||
|
||||
# get the ocr text
|
||||
(pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
|
||||
if argres : self.ocrtext = argres.split('|')
|
||||
|
||||
# get information to dehyphenate the text
|
||||
self.dehyphen_rootid = self.getData('info.dehyphen.rootID',0,-1)
|
||||
|
||||
# determine if first paragraph is continued from previous page
|
||||
(pos, self.parastems_stemid) = self.findinDoc('info.paraStems.stemID',0,-1)
|
||||
first_para_continued = (self.parastems_stemid != None)
|
||||
|
||||
# determine if last paragraph is continued onto the next page
|
||||
(pos, self.paracont_stemid) = self.findinDoc('info.paraCont.stemID',0,-1)
|
||||
last_para_continued = (self.paracont_stemid != None)
|
||||
|
||||
# collect link ids
|
||||
self.link_id = self.getData('info.word.link_id',0,-1)
|
||||
|
||||
# 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 :
|
||||
self.link_title = argres.split('|')
|
||||
else:
|
||||
self.link_title.append('')
|
||||
|
||||
# get a descriptions of the starting points of the regions
|
||||
# and groups on the page
|
||||
(pagetype, pageDesc) = self.PageDescription()
|
||||
regcnt = len(pageDesc) - 1
|
||||
|
||||
anchorSet = False
|
||||
breakSet = False
|
||||
inGroup = False
|
||||
|
||||
# process each region on the page and convert what you can to html
|
||||
|
||||
for j in xrange(regcnt):
|
||||
|
||||
(etype, start) = pageDesc[j]
|
||||
(ntype, end) = pageDesc[j+1]
|
||||
|
||||
|
||||
# set anchor for link target on this page
|
||||
if not anchorSet and not first_para_continued:
|
||||
htmlpage += '<div style="visibility: hidden; height: 0; width: 0;" id="'
|
||||
htmlpage += self.id + '" title="pagetype_' + pagetype + '"></div>\n'
|
||||
anchorSet = True
|
||||
|
||||
# handle groups of graphics with text captions
|
||||
if (etype == 'grpbeg'):
|
||||
(pos, grptype) = self.findinDoc('group.type', start, end)
|
||||
if grptype != None:
|
||||
if grptype == 'graphic':
|
||||
gcstr = ' class="' + grptype + '"'
|
||||
htmlpage += '<div' + gcstr + '>'
|
||||
inGroup = True
|
||||
|
||||
elif (etype == 'grpend'):
|
||||
if inGroup:
|
||||
htmlpage += '</div>\n'
|
||||
inGroup = False
|
||||
|
||||
else:
|
||||
(pos, regtype) = self.findinDoc('region.type',start,end)
|
||||
|
||||
if regtype == 'graphic' :
|
||||
(pos, simgsrc) = self.findinDoc('img.src',start,end)
|
||||
if simgsrc:
|
||||
if inGroup:
|
||||
htmlpage += '<img src="img/img%04d.jpg" alt="" />' % int(simgsrc)
|
||||
else:
|
||||
htmlpage += '<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc)
|
||||
|
||||
elif regtype == 'chapterheading' :
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
if not breakSet:
|
||||
htmlpage += '<div style="page-break-after: always;"> </div>\n'
|
||||
breakSet = True
|
||||
tag = 'h1'
|
||||
if pclass and (len(pclass) >= 7):
|
||||
if pclass[3:7] == 'ch1-' : tag = 'h1'
|
||||
if pclass[3:7] == 'ch2-' : tag = 'h2'
|
||||
if pclass[3:7] == 'ch3-' : tag = 'h3'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
else:
|
||||
htmlpage += '<' + tag + '>'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
|
||||
elif (regtype == 'text') or (regtype == 'fixed') or (regtype == 'insert') or (regtype == 'listitem'):
|
||||
ptype = 'full'
|
||||
# check to see if this is a continution from the previous page
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
if pclass and (len(pclass) >= 6) and (ptype == 'full'):
|
||||
tag = 'p'
|
||||
if pclass[3:6] == 'h1-' : tag = 'h4'
|
||||
if pclass[3:6] == 'h2-' : tag = 'h5'
|
||||
if pclass[3:6] == 'h3-' : tag = 'h6'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
else :
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
elif (regtype == 'tocentry') :
|
||||
ptype = 'full'
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
|
||||
elif (regtype == 'vertical') or (regtype == 'table') :
|
||||
ptype = 'full'
|
||||
if inGroup:
|
||||
ptype = 'middle'
|
||||
if first_para_continued :
|
||||
ptype = 'end'
|
||||
first_para_continued = False
|
||||
(pclass, pdesc) = self.getParaDescription(start, end, regtype)
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
|
||||
|
||||
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 ' Making region type', regtype,
|
||||
(pos, temp) = self.findinDoc('paragraph',start,end)
|
||||
(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
|
||||
if first_para_continued :
|
||||
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'
|
||||
if pclass[3:6] == 'h2-' : tag = 'h5'
|
||||
if pclass[3:6] == 'h3-' : tag = 'h6'
|
||||
htmlpage += '<' + tag + ' class="' + pclass + '">'
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, 'middle', regtype)
|
||||
htmlpage += '</' + tag + '>'
|
||||
else :
|
||||
htmlpage += self.buildParagraph(pclass, pdesc, ptype, regtype)
|
||||
else :
|
||||
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)
|
||||
|
||||
|
||||
if last_para_continued :
|
||||
if htmlpage[-4:] == '</p>':
|
||||
htmlpage = htmlpage[0:-4]
|
||||
last_para_continued = False
|
||||
|
||||
return htmlpage
|
||||
|
||||
|
||||
|
||||
def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
|
||||
# create a document parser
|
||||
dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
|
||||
htmlpage = dp.process()
|
||||
return htmlpage
|
@ -0,0 +1,151 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
class PParser(object):
|
||||
def __init__(self, gd, flatxml):
|
||||
self.gd = gd
|
||||
self.flatdoc = flatxml.split('\n')
|
||||
self.temp = []
|
||||
foo = self.getData('page.h') or self.getData('book.h')
|
||||
self.ph = foo[0]
|
||||
foo = self.getData('page.w') or self.getData('book.w')
|
||||
self.pw = foo[0]
|
||||
self.gx = self.getData('info.glyph.x')
|
||||
self.gy = self.getData('info.glyph.y')
|
||||
self.gid = self.getData('info.glyph.glyphID')
|
||||
def getData(self, path):
|
||||
result = None
|
||||
cnt = len(self.flatdoc)
|
||||
for j in xrange(cnt):
|
||||
item = self.flatdoc[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getDataTemp(self, path):
|
||||
result = None
|
||||
cnt = len(self.temp)
|
||||
for j in xrange(cnt):
|
||||
item = self.temp[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argt) = item.split('=')
|
||||
argres = argt.split('|')
|
||||
else:
|
||||
name = item
|
||||
argres = []
|
||||
if (name.endswith(path)):
|
||||
result = argres
|
||||
self.temp.pop(j)
|
||||
break
|
||||
if (len(argres) > 0) :
|
||||
for j in xrange(0,len(argres)):
|
||||
argres[j] = int(argres[j])
|
||||
return result
|
||||
def getImages(self):
|
||||
result = []
|
||||
self.temp = self.flatdoc
|
||||
while (self.getDataTemp('img') != None):
|
||||
h = self.getDataTemp('img.h')[0]
|
||||
w = self.getDataTemp('img.w')[0]
|
||||
x = self.getDataTemp('img.x')[0]
|
||||
y = self.getDataTemp('img.y')[0]
|
||||
src = self.getDataTemp('img.src')[0]
|
||||
result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
|
||||
return result
|
||||
def getGlyphs(self):
|
||||
result = []
|
||||
if (self.gid != None) and (len(self.gid) > 0):
|
||||
glyphs = []
|
||||
for j in set(self.gid):
|
||||
glyphs.append(j)
|
||||
glyphs.sort()
|
||||
for gid in glyphs:
|
||||
id='id="gl%d"' % gid
|
||||
path = self.gd.lookup(id)
|
||||
if path:
|
||||
result.append(id + ' ' + path)
|
||||
return result
|
||||
|
||||
|
||||
def convert2SVG(gdict, flat_xml, counter, numfiles, svgDir, raw, meta_array, scaledpi):
|
||||
ml = ''
|
||||
pp = PParser(gdict, flat_xml)
|
||||
ml += '<?xml version="1.0" standalone="no"?>\n'
|
||||
if (raw):
|
||||
ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
|
||||
ml += '<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1)
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
else:
|
||||
ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (counter, meta_array['Title'],meta_array['Authors'])
|
||||
ml += '<script><![CDATA[\n'
|
||||
ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
|
||||
ml += 'var dpi=%d;\n' % scaledpi
|
||||
if (counter) :
|
||||
ml += 'var prevpage="page%04d.xhtml";\n' % (counter - 1)
|
||||
if (counter < numfiles-1) :
|
||||
ml += 'var nextpage="page%04d.xhtml";\n' % (counter + 1)
|
||||
ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
|
||||
ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
|
||||
ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
|
||||
ml += 'function setsize(){var svg=document.getElementById("svgimg");var prev=document.getElementById("prevsvg");var next=document.getElementById("nextsvg");var width=(pw/dpi)+"in";var height=(ph/dpi)+"in";svg.setAttribute("width",width);svg.setAttribute("height",height);prev.setAttribute("height",height);prev.setAttribute("width","50px");next.setAttribute("height",height);next.setAttribute("width","50px");}\n'
|
||||
ml += 'function ppage(){window.location.href=prevpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'function npage(){window.location.href=nextpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'var gt=gd();if(gt>0){dpi=gt;}\n'
|
||||
ml += 'window.onload=setsize;\n'
|
||||
ml += ']]></script>\n'
|
||||
ml += '</head>\n'
|
||||
ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
|
||||
ml += '<div style="white-space:nowrap;">\n'
|
||||
if (counter == 0) :
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else:
|
||||
ml += '<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph)
|
||||
if (pp.gid != None):
|
||||
ml += '<defs>\n'
|
||||
gdefs = pp.getGlyphs()
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ml += gdefs[j]
|
||||
ml += '</defs>\n'
|
||||
img = pp.getImages()
|
||||
if (img != None):
|
||||
for j in xrange(0,len(img)):
|
||||
ml += img[j]
|
||||
if (pp.gid != None):
|
||||
for j in xrange(0,len(pp.gid)):
|
||||
ml += '<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j])
|
||||
if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
|
||||
ml += '<text x="10" y="10" font-family="Helvetica" font-size="100" stroke="black">This page intentionally left blank.</text>\n<text x="10" y="110" font-family="Helvetica" font-size="50" stroke="black">Until this notice unintentionally gave it content. (gensvg.py)</text>\n'
|
||||
if (raw) :
|
||||
ml += '</svg>'
|
||||
else :
|
||||
ml += '</svg></a>\n'
|
||||
if (counter == numfiles - 1) :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n'
|
||||
else :
|
||||
ml += '<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n'
|
||||
ml += '</div>\n'
|
||||
ml += '<div><a href="javascript:zoomin();">zoom in</a> - <a href="javascript:zoomout();">zoom out</a></div>\n'
|
||||
ml += '</body>\n'
|
||||
ml += '</html>\n'
|
||||
return ml
|
||||
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue