def retrieveCP(self, cp):
pos, compressed = self.__cpToOffset(cp)
if compressed:
return globals.encodeName(self.bytes[pos])
else:
return globals.encodeName(self.bytes[pos:pos + 2].decode('utf-16'),
lowOnly=True)
def retrieveCP(self, cp):
pos, compressed = self.__cpToOffset(cp)
if compressed:
return globals.encodeName(self.bytes[pos])
else:
try:
return globals.encodeName(self.bytes[pos:pos + 2].decode('utf-16'), lowOnly=True)
except UnicodeDecodeError:
reason = 'could not decode bytes in position %d-%d (%s-%s)' % (pos, pos + 1, hex(ord(self.bytes[pos])), hex(ord(self.bytes[pos + 1])))
print '<todo what="WordDocumentStream::retrieveCP(): %s"/>' % reason
return globals.encodeName(self.bytes[pos:pos + 2].decode('utf-16', errors="replace"), lowOnly=True)
def dump(self):
print '<%s type="CodePageString">' % self.name
self.printAndSet("Size", self.readuInt32())
bytes = []
for dummy in range(self.Size):
c = self.readuInt8()
if c == 0:
break
bytes.append(c)
codepage = self.parent.parent.getCodePage()
if (codepage is not None) and (codepage < 0):
codepage += 2**16 # signed -> unsigned
encoding = ""
# http://msdn.microsoft.com/en-us/goglobal/bb964654
if codepage == 1252:
encoding = "latin1"
elif codepage == 1250:
encoding = "latin2"
elif codepage == 65001:
# http://msdn.microsoft.com/en-us/library/windows/desktop/dd374130%28v=vs.85%29.aspx
encoding = "utf-8"
if len(encoding):
print '<Characters value="%s"/>' % globals.encodeName(
"".join(map(lambda c: chr(c), bytes)).decode(encoding),
lowOnly=True).encode('utf-8')
else:
print '<todo what="CodePageString::dump: unhandled codepage %s"/>' % codepage
print '</%s>' % self.name
def dump(self):
print '<%s type="CodePageString">' % self.name
self.printAndSet("Size", self.readuInt32())
bytes = []
for dummy in range(self.Size):
c = self.readuInt8()
if c == 0:
break
bytes.append(c)
codepage = self.parent.parent.getCodePage()
if (codepage is not None) and (codepage < 0):
codepage += 2 ** 16 # signed -> unsigned
encoding = ""
# http://msdn.microsoft.com/en-us/goglobal/bb964654
if codepage == 1252:
encoding = "latin1"
elif codepage == 1250:
encoding = "latin2"
elif codepage == 65001:
# http://msdn.microsoft.com/en-us/library/windows/desktop/dd374130%28v=vs.85%29.aspx
encoding = "utf-8"
if len(encoding):
print '<Characters value="%s"/>' % globals.encodeName("".join(map(lambda c: chr(c), bytes)).decode(encoding), lowOnly=True).encode('utf-8')
else:
print '<todo what="CodePageString::dump: unhandled codepage %s"/>' % codepage
print '</%s>' % self.name
def retrieveCP(self, cp):
pos, compressed = self.__cpToOffset(cp)
if compressed:
return globals.encodeName(self.bytes[pos])
else:
try:
return globals.encodeName(self.bytes[pos:pos +
2].decode('utf-16'),
lowOnly=True)
except UnicodeDecodeError:
reason = 'could not decode bytes in position %d-%d (%s-%s)' % (
pos, pos + 1, hex(ord(
self.bytes[pos])), hex(ord(self.bytes[pos + 1])))
print '<todo what="WordDocumentStream::retrieveCP(): %s"/>' % reason
return globals.encodeName(self.bytes[pos:pos + 2].decode(
'utf-16', errors="replace"),
lowOnly=True)
def __printDirHeader (self, direntry, byteLen):
dirname = direntry.Name
dirname = globals.encodeName(dirname)
print("")
print("="*globals.OutputWidth)
if direntry.isStorage():
print("%s (storage)"%dirname)
else:
print("%s (stream, size: %d bytes)"%(dirname, byteLen))
print("-"*globals.OutputWidth)
def __printDirHeader(self, direntry, byteLen):
dirname = direntry.Name
dirname = globals.encodeName(dirname)
print("")
print("=" * globals.OutputWidth)
if direntry.isStorage():
print("%s (storage)" % dirname)
else:
print("%s (stream, size: %d bytes)" % (dirname, byteLen))
print("-" * globals.OutputWidth)
def __addSiblings( self, entries, parent, child ):
# add left siblings
nextLeft = child.Entry.DirIDLeft
if ( nextLeft > 0 ):
newEntry = DirNode( entries[ nextLeft ] )
newEntry.HierachicalName = parent.HierachicalName + globals.encodeName( newEntry.Entry.Name )
if newEntry.Entry.DirIDRoot > 0:
newEntry.HierachicalName = newEntry.HierachicalName + '/'
self.__addSiblings( entries, parent, newEntry )
parent.Nodes.insert( 0, newEntry )
nextRight = child.Entry.DirIDRight
# add children to the right
if ( nextRight > 0 ):
newEntry = DirNode( entries[ nextRight ] )
newEntry.HierachicalName = parent.HierachicalName + globals.encodeName( newEntry.Entry.Name )
if newEntry.Entry.DirIDRoot > 0:
newEntry.HierachicalName = newEntry.HierachicalName + '/'
self.__addSiblings( entries, parent, newEntry )
parent.Nodes.append( newEntry )
def createDOM(self, wb):
nd = node.Element("external-sheet-cache")
# 1st char is always 0x1.
nd.setAttr("url", globals.encodeName(self.docURL[1:]))
for sheet in self.__sheets:
if sheet[1] == None:
continue
elem = sheet[1].createDOM(wb)
elem.setAttr("name", sheet[0])
nd.appendChild(elem)
return nd
def createDOM (self, wb):
nd = node.Element("external-sheet-cache")
# 1st char is always 0x1.
nd.setAttr("url", globals.encodeName(self.docURL[1:]))
for sheet in self.__sheets:
if sheet[1] == None:
continue
elem = sheet[1].createDOM(wb)
elem.setAttr("name", sheet[0])
nd.appendChild(elem)
return nd
def __buildTreeImpl(self, entries, parent ):
if ( parent.Entry.DirIDRoot > 0 ):
newEntry = DirNode( entries[ parent.Entry.DirIDRoot ] )
newEntry.HierachicalName = parent.HierachicalName + globals.encodeName( newEntry.Entry.Name )
if ( newEntry.Entry.DirIDRoot > 0 ):
newEntry.HierachicalName = newEntry.HierachicalName + '/'
self.__addSiblings( entries, parent, newEntry )
parent.Nodes.append( newEntry )
for child in parent.Nodes:
if child.Entry.DirIDRoot > 0:
self.__buildTreeImpl( entries, child )
def __getString(self, limit):
bytes = []
count = 0
pos = self.pos
while True:
if (limit is not None) and count == limit:
break
i = self.getuInt8(pos=pos)
pos += 1
j = self.getuInt8(pos=pos)
pos += 1
if i != 0 or j != 0:
bytes.append(i)
bytes.append(j)
else:
break
count += 1
return (self.quoteAttr(globals.encodeName(globals.getUTF8FromUTF16("".join(map(lambda x: chr(x), bytes))))), pos)
def __getString(self, limit):
bytes = []
count = 0
pos = self.pos
while True:
if (limit is not None) and count == limit:
break
i = self.getuInt8(pos=pos)
pos += 1
j = self.getuInt8(pos=pos)
pos += 1
if i != 0 or j != 0:
bytes.append(i)
bytes.append(j)
else:
break
count += 1
return (self.quoteAttr(globals.encodeName(globals.getUTF8FromUTF16("".join(map(lambda x: chr(x), bytes))))), pos)
def dump(self):
print '<dictionaryEntry offset="%s" index="%s">' % (self.pos,
self.index)
self.printAndSet("PropertyIdentifier", self.readuInt32())
self.printAndSet("Length", self.readuInt32())
bytes = []
for dummy in range(self.Length):
c = self.readuInt8()
if c == 0:
break
bytes.append(c)
# TODO support non-latin1
encoding = "latin1"
print '<Name value="%s"/>' % globals.encodeName(
"".join(map(lambda c: chr(c), bytes)).decode(encoding),
lowOnly=True).encode('utf-8')
print '</dictionaryEntry>'
self.parent.pos = self.pos
def dump(self):
print '<stream name="%s" size="%s"/>' % (self.quoteAttr(
globals.encodeName(self.name)), self.size)
def dump(self):
print '<stream name="%s" size="%s"/>' % (self.quoteAttr(globals.encodeName(self.name)), self.size)
def __printDirHeader(self, dirname, byteLen):
dirname = globals.encodeName(dirname)
print("")
print("=" * 68)
print("%s (size: %d bytes)" % (dirname, byteLen))
print("-" * 68)
def retrieveCP(self, cp):
pos, compressed = self.__cpToOffset(cp)
if compressed:
return globals.encodeName(self.bytes[pos])
else:
return globals.encodeName(self.bytes[pos:pos+2].decode('utf-16'), lowOnly = True)