francois/DeDRM_tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tools v5.0

Browse Source 
Introduction of alfcrypto library for speed
Reorganisation of archive plugins,apps,other
This commit is contained in:
Apprentice Alf
2012-03-06 18:24:28 +00:00
parent 882edb6c69
commit 07e532f59c
112 changed files with 11472 additions and 5177 deletions
Download Patch File Download Diff File Expand all files Collapse all files

167
Other_Tools/KindleBooks/lib/convert2xml.py
View File

@@ -23,7 +23,7 @@ from struct import unpack
class TpzDRMError(Exception):
pass
# Get a 7 bit encoded number from string. The most
# Get a 7 bit encoded number from string. The most
# significant byte comes first and has the high bit (8th) set
def readEncodedNumber(file):
@@ -32,57 +32,57 @@ def readEncodedNumber(file):
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)
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):
if (len(c) == 0):
return None
data = ord(c)
datax = (datax <<7) + (data & 0x7F)
data = datax
data = datax
if flag:
data = -data
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]
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
@@ -97,9 +97,9 @@ def readString(file):
sv = file.read(stringLength)
if (len(sv) != stringLength):
return ""
return unpack(str(stringLength)+"s",sv)[0]
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
@@ -265,6 +265,8 @@ class PageParser(object):
'paragraph.gridSize' : (1, 'scalar_number', 0, 0),
'paragraph.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridEndCenter' : (1, 'scalar_number', 0, 0),
'word_semantic' : (1, 'snippets', 1, 1),
@@ -284,6 +286,8 @@ class PageParser(object):
'_span.gridSize' : (1, 'scalar_number', 0, 0),
'_span.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
'_span.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'_span.gridEndCenter' : (1, 'scalar_number', 0, 0),
'span' : (1, 'snippets', 1, 0),
'span.firstWord' : (1, 'scalar_number', 0, 0),
@@ -291,6 +295,8 @@ class PageParser(object):
'span.gridSize' : (1, 'scalar_number', 0, 0),
'span.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
'span.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'span.gridEndCenter' : (1, 'scalar_number', 0, 0),
'extratokens' : (1, 'snippets', 1, 0),
'extratokens.type' : (1, 'scalar_text', 0, 0),
@@ -376,14 +382,14 @@ class PageParser(object):
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
# 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):
@@ -416,7 +422,7 @@ class PageParser(object):
return result
# process the next tag token, recursively handling subtags,
# process the next tag token, recursively handling subtags,
# arguments, and commands
def procToken(self, token):
@@ -438,7 +444,7 @@ class PageParser(object):
if known_token :
# handle subtags if present
# handle subtags if present
subtagres = []
if (splcase == 1):
# this type of tag uses of escape marker 0x74 indicate subtag count
@@ -447,7 +453,7 @@ class PageParser(object):
subtags = 1
num_args = 0
if (subtags == 1):
if (subtags == 1):
ntags = readEncodedNumber(self.fo)
if self.debug : print 'subtags: ' + token + ' has ' + str(ntags)
for j in xrange(ntags):
@@ -478,7 +484,7 @@ class PageParser(object):
return result
# all tokens that need to be processed should be in the hash
# table if it may indicate a problem, either new token
# table if it may indicate a problem, either new token
# or an out of sync condition
else:
result = []
@@ -530,7 +536,7 @@ class PageParser(object):
# 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
# 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
@@ -549,7 +555,7 @@ class PageParser(object):
return result
# add full tag path to injected snippets
def updateName(self, tag, prefix):
name = tag[0]
@@ -577,7 +583,7 @@ class PageParser(object):
argtype = tag[2]
argList = tag[3]
nsubtagList = []
if len(argList) > 0 :
if len(argList) > 0 :
for j in argList:
asnip = self.snippetList[j]
aso, atag = self.injectSnippets(asnip)
@@ -609,65 +615,70 @@ class PageParser(object):
nodename = fullpathname.pop()
ilvl = len(fullpathname)
indent = ' ' * (3 * ilvl)
result = indent + '<' + nodename + '>'
rlst = []
rlst.append(indent + '<' + nodename + '>')
if len(argList) > 0:
argres = ''
alst = []
for j in argList:
if (argtype == 'text') or (argtype == 'scalar_text') :
argres += j + '|'
alst.append(j + '|')
else :
argres += str(j) + ','
alst.append(str(j) + ',')
argres = "".join(alst)
argres = argres[0:-1]
if argtype == 'snippets' :
result += 'snippets:' + argres
rlst.append('snippets:' + argres)
else :
result += argres
rlst.append(argres)
if len(subtagList) > 0 :
result += '\n'
rlst.append('\n')
for j in subtagList:
if len(j) > 0 :
result += self.formatTag(j)
result += indent + '</' + nodename + '>\n'
rlst.append(self.formatTag(j))
rlst.append(indent + '</' + nodename + '>\n')
else:
result += '</' + nodename + '>\n'
return result
rlst.append('</' + nodename + '>\n')
return "".join(rlst)
# flatten tag
# flatten tag
def flattenTag(self, node):
name = node[0]
subtagList = node[1]
argtype = node[2]
argList = node[3]
result = name
rlst = []
rlst.append(name)
if (len(argList) > 0):
argres = ''
alst = []
for j in argList:
if (argtype == 'text') or (argtype == 'scalar_text') :
argres += j + '|'
alst.append(j + '|')
else :
argres += str(j) + '|'
alst.append(str(j) + '|')
argres = "".join(alst)
argres = argres[0:-1]
if argtype == 'snippets' :
result += '.snippets=' + argres
rlst.append('.snippets=' + argres)
else :
result += '=' + argres
result += '\n'
rlst.append('=' + argres)
rlst.append('\n')
for j in subtagList:
if len(j) > 0 :
result += self.flattenTag(j)
return result
rlst.append(self.flattenTag(j))
return "".join(rlst)
# reduce create xml output
def formatDoc(self, flat_xml):
result = ''
rlst = []
for j in self.doc :
if len(j) > 0:
if flat_xml:
result += self.flattenTag(j)
rlst.append(self.flattenTag(j))
else:
result += self.formatTag(j)
rlst.append(self.formatTag(j))
result = "".join(rlst)
if self.debug : print result
return result
@@ -712,7 +723,7 @@ class PageParser(object):
first_token = None
v = self.getNext()
if (v == None):
if (v == None):
break
if (v == 0x72):
@@ -723,7 +734,7 @@ class PageParser(object):
self.doc.append(tag)
else:
if self.debug:
print "Main Loop: Unknown value: %x" % v
print "Main Loop: Unknown value: %x" % v
if (v == 0):
if (self.peek(1) == 0x5f):
skip = self.fo.read(1)
@@ -776,7 +787,7 @@ def usage():
#
# Main
#
#
def main(argv):
dictFile = ""
@@ -797,11 +808,11 @@ def main(argv):
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)
sys.exit(2)
for o, a in opts:
if o =="-d":
debug=True