コード例 #1
0
ファイル: mobi_header.py プロジェクト: junk2ool/azw2zip
 def getSizeOfTrailingDataEntry(data):
     num = 0
     for v in data[-4:]:
         if bord(v) & 0x80:
             num = 0
         num = (num << 7) | (bord(v) & 0x7f)
     return num
コード例 #2
0
ファイル: mobi_sectioner.py プロジェクト: junk2ool/azw2zip
def describe(data):
    txtans = ''
    hexans = hexlify(data)
    for i in data:
        if bord(i) < 32 or bord(i) > 127:
            txtans += '?'
        else:
            txtans += bchar(i).decode('latin-1')
    return '"' + txtans + '"' + ' 0x' + hexans
コード例 #3
0
ファイル: epub_utils.py プロジェクト: robyscar/sigil
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:]
コード例 #4
0
ファイル: epub_utils.py プロジェクト: CedarLogic/Sigil
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:]
コード例 #5
0
ファイル: mobi_index.py プロジェクト: junk2ool/azw2zip
 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
コード例 #6
0
ファイル: mobi_utils.py プロジェクト: junk2ool/azw2zip
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:]
コード例 #7
0
ファイル: mobi_index.py プロジェクト: junk2ool/azw2zip
def getTagMap(controlByteCount, tagTable, entryData, startPos, endPos):
    '''
    Create a map of tags and values from the given byte section.

    @param controlByteCount: The number of control bytes.
    @param tagTable: The tag table.
    @param entryData: The data to process.
    @param startPos: The starting position in entryData.
    @param endPos: The end position in entryData or None if it is unknown.
    @return: Hashmap of tag and list of values.
    '''
    tags = []
    tagHashMap = {}
    controlByteIndex = 0
    dataStart = startPos + controlByteCount

    for tag, valuesPerEntry, mask, endFlag in tagTable:
        if endFlag == 0x01:
            controlByteIndex += 1
            continue
        cbyte = ord(entryData[startPos + controlByteIndex:startPos +
                              controlByteIndex + 1])
        if 0:
            print("Control Byte Index %0x , Control Byte Value %0x" %
                  (controlByteIndex, cbyte))

        value = ord(entryData[startPos + controlByteIndex:startPos +
                              controlByteIndex + 1]) & mask
        if value != 0:
            if value == mask:
                if countSetBits(mask) > 1:
                    # If all bits of masked value are set and the mask has more than one bit, a variable width value
                    # will follow after the control bytes which defines the length of bytes (NOT the value count!)
                    # which will contain the corresponding variable width values.
                    consumed, value = getVariableWidthValue(
                        entryData, dataStart)
                    dataStart += consumed
                    tags.append((tag, None, value, valuesPerEntry))
                else:
                    tags.append((tag, 1, None, valuesPerEntry))
            else:
                # Shift bits to get the masked value.
                while mask & 0x01 == 0:
                    mask = mask >> 1
                    value = value >> 1
                tags.append((tag, value, None, valuesPerEntry))
    for tag, valueCount, valueBytes, valuesPerEntry in tags:
        values = []
        if valueCount is not None:
            # Read valueCount * valuesPerEntry variable width values.
            for _ in range(valueCount):
                for _ in range(valuesPerEntry):
                    consumed, data = getVariableWidthValue(
                        entryData, dataStart)
                    dataStart += consumed
                    values.append(data)
        else:
            # Convert valueBytes to variable width values.
            totalConsumed = 0
            while totalConsumed < valueBytes:
                # Does this work for valuesPerEntry != 1?
                consumed, data = getVariableWidthValue(entryData, dataStart)
                dataStart += consumed
                totalConsumed += consumed
                values.append(data)
            if totalConsumed != valueBytes:
                print("Error: Should consume %s bytes, but consumed %s" %
                      (valueBytes, totalConsumed))
        tagHashMap[tag] = values
    # Test that all bytes have been processed if endPos is given.
    if endPos is not None and dataStart != endPos:
        # The last entry might have some zero padding bytes, so complain only if non zero bytes are left.
        for char in entryData[dataStart:endPos]:
            if bord(char) != 0:
                print("Warning: There are unprocessed index bytes left: %s" %
                      toHex(entryData[dataStart:endPos]))
                if 0:
                    print("controlByteCount: %s" % controlByteCount)
                    print("tagTable: %s" % tagTable)
                    print("data: %s" % toHex(entryData[startPos:endPos]))
                    print("tagHashMap: %s" % tagHashMap)
                break

    return tagHashMap