def unpack(self, i):
o, p = b'', 0
while p < len(i):
# for python 3 must use slice since i[p] returns int while slice returns character
c = ord(i[p:p + 1])
p += 1
if (c >= 1 and c <= 8):
o += i[p:p + c]
p += c
elif (c < 128):
o += bchr(c)
elif (c >= 192):
o += b' ' + bchr(c ^ 128)
else:
if p < len(i):
c = (c << 8) | ord(i[p:p + 1])
p += 1
m = (c >> 3) & 0x07ff
n = (c & 7) + 3
if (m > n):
o += o[-m:n - m]
else:
for _ in range(n):
# because of completely ass-backwards decision by python mainters for python 3
# we must use slice for bytes as i[p] returns int while slice returns character
if m == 1:
o += o[-m:]
else:
o += o[-m:-m + 1]
return o
def Idpf_encryption_key(uid):
# remove whitespace changing nothing else
key = utf8_str(uid)
key = key.replace(bchr(x20), b'')
key = key.replace(bchr(x09), b'')
key = key.replace(bchr(x0d), b'')
key = key.replace(bchr(x0a), b'')
key = SHA1(key)
return key
def Idpf_encryption_key(uid):
# remove whitespace changing nothing else
key = utf8_str(uid)
key = key.replace(bchr(0x20),b'')
key = key.replace(bchr(0x09),b'')
key = key.replace(bchr(0x0d),b'')
key = key.replace(bchr(0x0a),b'')
key = SHA1(key)
return key
def Idpf_encryption_key(uid):
# remove whitespace changing nothing else
key = utf8_str(uid)
if key.startswith(b"urn:uuid:"):
key = key[9:]
key = key.replace(bchr(0x20),b'')
key = key.replace(bchr(0x09),b'')
key = key.replace(bchr(0x0d),b'')
key = key.replace(bchr(0x0a),b'')
key = SHA1(key)
return key
def Idpf_encryption_key(uid):
# remove whitespace changing nothing else
key = utf8_str(uid)
if key.startswith(b"urn:uuid:"):
key = key[9:]
key = key.replace(bchr(0x20), b'')
key = key.replace(bchr(0x09), b'')
key = key.replace(bchr(0x0d), b'')
key = key.replace(bchr(0x0a), b'')
key = SHA1(key)
return key
def Idpf_mangle_fonts(encryption_key, data):
if isinstance(data, text_type):
print('Error: font data must be a byte string')
crypt = data[:1040]
key = cycle(iter(map(bord, encryption_key)))
encrypt = b''.join([bchr(bord(x) ^ next(key)) for x in crypt])
return encrypt + data[1040:]
def Idpf_mangle_fonts(encryption_key, data):
if isinstance(data, text_type):
print('Error: font data must be a byte string')
crypt = data[:1040]
key = cycle(iter(map(bord, encryption_key)))
encrypt = b''.join([bchr(bord(x)^next(key)) for x in crypt])
return encrypt + data[1040:]
def getIndexData(self, idx, label="Unknown"):
sect = self.sect
outtbl = []
ctoc_text = {}
if idx != 0xffffffff:
sect.setsectiondescription(idx,
"{0} Main INDX section".format(label))
data = sect.loadSection(idx)
idxhdr, hordt1, hordt2 = self.parseINDXHeader(data)
IndexCount = idxhdr['count']
# handle the case of multiple sections used for CTOC
rec_off = 0
off = idx + IndexCount + 1
for j in range(idxhdr['nctoc']):
cdata = sect.loadSection(off + j)
sect.setsectiondescription(off + j,
label + ' CTOC Data ' + str(j))
ctocdict = self.readCTOC(cdata)
for k in ctocdict:
ctoc_text[k + rec_off] = ctocdict[k]
rec_off += 0x10000
tagSectionStart = idxhdr['len']
controlByteCount, tagTable = readTagSection(tagSectionStart, data)
if self.DEBUG:
print("ControlByteCount is", controlByteCount)
print("IndexCount is", IndexCount)
print("TagTable: %s" % tagTable)
for i in range(idx + 1, idx + 1 + IndexCount):
sect.setsectiondescription(
i, "{0} Extra {1:d} INDX section".format(label, i - idx))
data = sect.loadSection(i)
hdrinfo, ordt1, ordt2 = self.parseINDXHeader(data)
idxtPos = hdrinfo['start']
entryCount = hdrinfo['count']
if self.DEBUG:
print(idxtPos, entryCount)
# loop through to build up the IDXT position starts
idxPositions = []
for j in range(entryCount):
pos, = struct.unpack_from(b'>H', data,
idxtPos + 4 + (2 * j))
idxPositions.append(pos)
# The last entry ends before the IDXT tag (but there might be zero fill bytes we need to ignore!)
idxPositions.append(idxtPos)
# for each entry in the IDXT build up the tagMap and any associated text
for j in range(entryCount):
startPos = idxPositions[j]
endPos = idxPositions[j + 1]
textLength = ord(data[startPos:startPos + 1])
text = data[startPos + 1:startPos + 1 + textLength]
if hordt2 is not None:
text = b''.join(bchr(hordt2[bord(x)]) for x in text)
tagMap = getTagMap(controlByteCount, tagTable, data,
startPos + 1 + textLength, endPos)
outtbl.append([text, tagMap])
if self.DEBUG:
print(tagMap)
print(text)
return outtbl, ctoc_text
def mangle_fonts(encryption_key, data):
if isinstance(encryption_key, text_type):
encryption_key = encryption_key.encode('latin-1')
crypt = data[:1024]
key = cycle(iter(map(bord, encryption_key)))
# encrypt = ''.join([chr(ord(x)^key.next()) for x in crypt])
encrypt = b''.join([bchr(bord(x) ^ next(key)) for x in crypt])
return encrypt + data[1024:]
def applyInflectionRule(self, mainEntry, inflectionRuleData, start, end):
'''
Apply inflection rule.
@param mainEntry: The word to inflect.
@param inflectionRuleData: The inflection rules.
@param start: The start position of the inflection rule to use.
@param end: The end position of the inflection rule to use.
@return: The string with the inflected word or None if an error occurs.
'''
mode = -1
byteArray = array.array(array_format, mainEntry)
position = len(byteArray)
for charOffset in range(start, end):
char = inflectionRuleData[charOffset:charOffset + 1]
abyte = ord(char)
if abyte >= 0x0a and abyte <= 0x13:
# Move cursor backwards
offset = abyte - 0x0a
if mode not in [0x02, 0x03]:
mode = 0x02
position = len(byteArray)
position -= offset
elif abyte > 0x13:
if mode == -1:
print(
"Error: Unexpected first byte %i of inflection rule" %
abyte)
return None
elif position == -1:
print(
"Error: Unexpected first byte %i of inflection rule" %
abyte)
return None
else:
if mode == 0x01:
# Insert at word start
byteArray.insert(position, abyte)
position += 1
elif mode == 0x02:
# Insert at word end
byteArray.insert(position, abyte)
elif mode == 0x03:
# Delete at word end
position -= 1
deleted = byteArray.pop(position)
if bchr(deleted) != char:
if DEBUG_DICT:
print("0x03: %s %s %s %s" %
(mainEntry,
toHex(inflectionRuleData[start:end]),
char, bchr(deleted)))
print(
"Error: Delete operation of inflection rule failed"
)
return None
elif mode == 0x04:
# Delete at word start
deleted = byteArray.pop(position)
if bchr(deleted) != char:
if DEBUG_DICT:
print("0x03: %s %s %s %s" %
(mainEntry,
toHex(inflectionRuleData[start:end]),
char, bchr(deleted)))
print(
"Error: Delete operation of inflection rule failed"
)
return None
else:
print(
"Error: Inflection rule mode %x is not implemented"
% mode)
return None
elif abyte == 0x01:
# Insert at word start
if mode not in [0x01, 0x04]:
position = 0
mode = abyte
elif abyte == 0x02:
# Insert at word end
if mode not in [0x02, 0x03]:
position = len(byteArray)
mode = abyte
elif abyte == 0x03:
# Delete at word end
if mode not in [0x02, 0x03]:
position = len(byteArray)
mode = abyte
elif abyte == 0x04:
# Delete at word start
if mode not in [0x01, 0x04]:
position = 0
# Delete at word start
mode = abyte
else:
print("Error: Inflection rule mode %x is not implemented" %
abyte)
return None
return utf8_str(byteArray.tostring())
