def decompress_stream(self, key):
"""
Decompress compressed object Streams.
"""
self.key = key
#print "++++++++++++ decompressing stream +++++++++++++++++++++++++" ,key
try:
data = self.objects[self.key]
start = data.find("stream")
end = data.find("endstream")
self.buff = data[start + 6:].strip()
if len(self.buff) < 2: return
self.methods = self.get_compMethod(key, data)
self.data = self.buff.strip()
for self.method in self.methods:
#print self.method
if 'fl' == self.method.lower():
self.data = decompress(self.data)
if 'ascii85decode' == self.method.lower():
self.data = ascii85decode(self.data)
if 'asciihexdecode' == self.method.lower():
self.data = asciihexdecode(self.data)
if 'lzwdecode' == self.method.lower():
self.data = lzwdecode(self.data)
if len(self.methods) == 0:
self.handle_evasion(key, data[:start])
except Exception, err:
pass
def decode(self):
assert self.data is None and self.rawdata is not None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if isinstance(f, PDFObjRef):
filters += f.resolve()
continue
params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error, e:
if STRICT:
raise PDFException('Invalid zlib bytes: %r, %r' % (e, data))
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
def decode(self):
assert self.data is None and self.rawdata is not None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if isinstance(f, PDFObjRef):
filters += f.resolve()
continue
params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error, e:
if STRICT:
raise PDFException('Invalid zlib bytes: %r, %r' %
(e, data))
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
def decode(self):
assert self.data is None and self.rawdata != None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error:
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
elif f in LITERALS_ASCII85_DECODE:
data = ascii85decode(data)
elif f in LITERALS_ASCIIHEX_DECODE:
data = asciihexdecode(data)
elif f in LITERALS_RUNLENGTH_DECODE:
data = rldecode(data)
elif f in LITERALS_CCITTFAX_DECODE:
#data = ccittfaxdecode(data)
raise PDFNotImplementedError('Unsupported filter: %r' % f)
elif f == LITERAL_CRYPT:
# not yet..
raise PDFNotImplementedError('/Crypt filter is unsupported')
else:
raise PDFNotImplementedError('Unsupported filter: %r' % f)
# apply predictors
params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
if 'Predictor' in params and 'Columns' in params:
pred = int_value(params['Predictor'])
columns = int_value(params['Columns'])
if pred:
if pred != 12:
raise PDFNotImplementedError(
'Unsupported predictor: %r' % pred)
buf = ''
ent0 = '\x00' * columns
for i in xrange(0, len(data), columns + 1):
pred = data[i]
ent1 = data[i + 1:i + 1 + columns]
if pred == '\x02':
ent1 = ''.join(
chr((ord(a) + ord(b)) & 255)
for (a, b) in zip(ent0, ent1))
buf += ent1
ent0 = ent1
data = buf
self.data = data
self.rawdata = None
return
def decode(self):
assert self.data is None and self.rawdata is not None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data, self.attrs)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error as e:
if STRICT:
raise PDFException('Invalid zlib bytes: %r, %r' % (e, data))
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
elif f in LITERALS_ASCII85_DECODE:
data = ascii85decode(data)
elif f in LITERALS_ASCIIHEX_DECODE:
data = asciihexdecode(data)
elif f in LITERALS_RUNLENGTH_DECODE:
data = rldecode(data)
elif f in LITERALS_CCITTFAX_DECODE:
data = ccittfaxdecode(data, params)
elif f in LITERALS_DCT_DECODE:
# This is probably a JPG stream - it does not need to be decoded twice.
# Just return the stream to the user.
pass
elif f == LITERAL_CRYPT:
# not yet..
raise PDFNotImplementedError('/Crypt filter is unsupported')
else:
raise PDFNotImplementedError('Unsupported filter: %r' % f)
# apply predictors
if 'Predictor' in params:
pred = int_value(params['Predictor'])
if pred == 1:
# no predictor
pass
elif 10 <= pred:
# PNG predictor
colors = int_value(params.get('Colors', 1))
columns = int_value(params.get('Columns', 1))
bitspercomponent = int_value(params.get('BitsPerComponent', 8))
data = apply_png_predictor(pred, colors, columns, bitspercomponent, data)
else:
raise PDFNotImplementedError('Unsupported predictor: %r' % pred)
self.data = data
self.rawdata = None
return
def decode(self):
assert self.data is None and self.rawdata != None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error as e:
if STRICT:
raise PDFException("Invalid zlib bytes: %r, %r" % (e, data))
data = ""
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
elif f in LITERALS_ASCII85_DECODE:
data = ascii85decode(data)
elif f in LITERALS_ASCIIHEX_DECODE:
data = asciihexdecode(data)
elif f in LITERALS_RUNLENGTH_DECODE:
data = rldecode(data)
elif f in LITERALS_CCITTFAX_DECODE:
# data = ccittfaxdecode(data)
raise PDFNotImplementedError("Unsupported filter: %r" % f)
elif f == LITERAL_CRYPT:
# not yet..
raise PDFNotImplementedError("/Crypt filter is unsupported")
else:
raise PDFNotImplementedError("Unsupported filter: %r" % f)
# apply predictors
params = self.get_any(("DP", "DecodeParms", "FDecodeParms"), {})
if "Predictor" in params and "Columns" in params:
pred = int_value(params["Predictor"])
columns = int_value(params["Columns"])
if pred:
if pred != 12:
raise PDFNotImplementedError("Unsupported predictor: %r" % pred)
buf = ""
ent0 = "\x00" * columns
for i in xrange(0, len(data), columns + 1):
pred = data[i]
ent1 = data[i + 1 : i + 1 + columns]
if pred == "\x02":
ent1 = "".join(chr((ord(a) + ord(b)) & 255) for (a, b) in zip(ent0, ent1))
buf += ent1
ent0 = ent1
data = buf
self.data = data
self.rawdata = None
return
def decode(self):
assert self.data is None and self.rawdata != None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error:
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
elif f in LITERALS_ASCII85_DECODE:
data = ascii85decode(data)
elif f in LITERALS_ASCIIHEX_DECODE:
data = asciihexdecode(data)
elif f in LITERALS_RUNLENGTH_DECODE:
data = rldecode(data)
elif f in LITERALS_CCITTFAX_DECODE:
#data = ccittfaxdecode(data)
raise PDFNotImplementedError('Unsupported filter: %r' % f)
elif f == LITERAL_CRYPT:
# not yet..
raise PDFNotImplementedError('/Crypt filter is unsupported')
else:
raise PDFNotImplementedError('Unsupported filter: %r' % f)
# apply predictors
params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
if 'Predictor' in params and 'Columns' in params:
pred = int_value(params['Predictor'])
columns = int_value(params['Columns'])
if pred:
if pred != 12:
raise PDFNotImplementedError('Unsupported predictor: %r' % pred)
buf = ''
ent0 = '\x00' * columns
for i in xrange(0, len(data), columns+1):
pred = data[i]
ent1 = data[i+1:i+1+columns]
if pred == '\x02':
ent1 = ''.join( chr((ord(a)+ord(b)) & 255) for (a,b) in zip(ent0,ent1) )
buf += ent1
ent0 = ent1
data = buf
self.data = data
self.rawdata = None
return
def lzwDecode(stream, parameters):
'''
Method to decode streams using the LZW algorithm
@param stream: A PDF stream
@return: A tuple (status,statusContent), where statusContent is the decoded PDF stream in case status = 0 or an error in case status = -1
'''
decodedStream = ''
try:
decodedStream = lzw.lzwdecode(stream)
except:
return (-1, 'Error decompressing string')
if parameters == None or parameters == {}:
return (0, decodedStream)
else:
if parameters.has_key('/Predictor'):
predictor = parameters['/Predictor'].getRawValue()
else:
predictor = 1
# Columns = number of samples per row
if parameters.has_key('/Columns'):
columns = parameters['/Columns'].getRawValue()
else:
columns = 1
# Colors = number of components per sample
if parameters.has_key('/Colors'):
colors = parameters['/Colors'].getRawValue()
if colors < 1:
colors = 1
else:
colors = 1
# BitsPerComponent: number of bits per color component
if parameters.has_key('/BitsPerComponent'):
bits = parameters['/BitsPerComponent'].getRawValue()
if bits not in [1, 2, 4, 8, 16]:
bits = 8
else:
bits = 8
if parameters.has_key('/EarlyChange'):
earlyChange = parameters['/EarlyChange'].getRawValue()
else:
earlyChange = 1
if predictor != None and predictor != 1:
ret = post_prediction(decodedStream, predictor, columns, colors,
bits)
return ret
else:
return (0, decodedStream)
def lzwDecode(stream, parameters):
'''
Method to decode streams using the LZW algorithm
@param stream: A PDF stream
@return: A tuple (status,statusContent), where statusContent is the decoded PDF stream in case status = 0 or an error in case status = -1
'''
decodedStream = ''
try:
decodedStream = lzw.lzwdecode(stream)
except:
return (-1,'Error decompressing string')
if parameters == None or parameters == {}:
return (0,decodedStream)
else:
if parameters.has_key('/Predictor'):
predictor = parameters['/Predictor'].getRawValue()
else:
predictor = 1
# Columns = number of samples per row
if parameters.has_key('/Columns'):
columns = parameters['/Columns'].getRawValue()
else:
columns = 1
# Colors = number of components per sample
if parameters.has_key('/Colors'):
colors = parameters['/Colors'].getRawValue()
if colors < 1:
colors = 1
else:
colors = 1
# BitsPerComponent: number of bits per color component
if parameters.has_key('/BitsPerComponent'):
bits = parameters['/BitsPerComponent'].getRawValue()
if bits not in [1,2,4,8,16]:
bits = 8
else:
bits = 8
if parameters.has_key('/EarlyChange'):
earlyChange = parameters['/EarlyChange'].getRawValue()
else:
earlyChange = 1
if predictor != None and predictor != 1:
ret = post_prediction(decodedStream, predictor, columns, colors, bits)
return ret
else:
return (0,decodedStream)
def lzwDecode(stream, parameters):
"""
Method to decode streams using the LZW algorithm
@param stream: A PDF stream
@return: A tuple (status,statusContent), where statusContent is the decoded PDF stream in case status = 0 or an error in case status = -1
"""
decodedStream = ""
try:
decodedStream = lzw.lzwdecode(stream)
except:
return (-1, "Error decompressing string")
if parameters == None or parameters == {}:
return (0, decodedStream)
else:
if "/Predictor" in parameters:
predictor = parameters["/Predictor"].getRawValue()
else:
predictor = 1
# Columns = number of samples per row
if "/Columns" in parameters:
columns = parameters["/Columns"].getRawValue()
else:
columns = 1
# Colors = number of components per sample
if "/Colors" in parameters:
colors = parameters["/Colors"].getRawValue()
if colors < 1:
colors = 1
else:
colors = 1
# BitsPerComponent: number of bits per color component
if "/BitsPerComponent" in parameters:
bits = parameters["/BitsPerComponent"].getRawValue()
if bits not in [1, 2, 4, 8, 16]:
bits = 8
else:
bits = 8
if "/EarlyChange" in parameters:
earlyChange = parameters["/EarlyChange"].getRawValue()
else:
earlyChange = 1
if predictor != None and predictor != 1:
ret = post_prediction(decodedStream, predictor, columns, colors, bits)
return ret
else:
return (0, decodedStream)
def decode(self):
assert self.data is None and self.rawdata != None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error, e:
if STRICT:
raise PDFException('Invalid zlib bytes: %r, %r' % (e, data))
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
def decode(self):
assert self.data is None and self.rawdata != None
data = self.rawdata
if self.decipher:
# Handle encryption
data = self.decipher(self.objid, self.genno, data)
filters = self.get_filters()
if not filters:
self.data = data
self.rawdata = None
return
for f in filters:
if f in LITERALS_FLATE_DECODE:
# will get errors if the document is encrypted.
try:
data = zlib.decompress(data)
except zlib.error, e:
if STRICT:
raise PDFException('Invalid zlib bytes: %r, %r' %
(e, data))
data = ''
elif f in LITERALS_LZW_DECODE:
data = lzwdecode(data)
def getdictionary(file, followlinks=False):
# sequence of key - object pairs, of which at least the key is a /name (without slash)
# it may be followed by a stream, which is encapsulated by the words "stream" and "endstream"
# TODO: handling of specific keys and return values (Length, Size): from global to variables to returns from this function (as this function may be called recursively)
# TODO: the stream itself needs to be checked "in the context to which it is referred to"
global globaldictvaluesize # TODO: from global variable to return'd value from this function
vprint("[DICT]", 2, '')
getkey = ""
getobject = ""
dictionary = {}
while getkey != '>' and getobject != '>':
getkey = readobject(file)
getobject = readobject(file, getkey in followlinkslist)
dictionary[getkey] = getobject
nword, nnword = getnexttwowords(file)
if nword == 'stream':
#TODO: followsymlinks handling in case stream can have symlinks
length = num(dictionary.get("Length"))
getword(
file
) # actually read the word 'stream' (including trailing delimiter)
file.seek(-1, 1) #stream follows after 'stream\r\n' or 'stream\n'
if ord(nextchar(file)) == 13: # \r
file.read(2) # read 'stream\r\n'
else:
file.read(1) # read 'stream\n'
stream = file.read(length)
vprint(" ", 2)
vprint("[STREAM] " + str(length) + " bytes", 2)
if "Filter" in list(dictionary.keys()):
filterlist = dictionary.get("Filter")
if isinstance(filterlist, str):
filterlist = [filterlist]
for streamfilter in list(filterlist):
vprint("[DECODE]: " + streamfilter + " ", 2, '')
if streamfilter == "FlateDecode":
#TODO: Predictor filters not implemented yet, see getxrefstream(). It is possible we encounter an xrefstream as we might not explicitly have searched and parsed one.
try:
stream = zlib.decompress(stream)
vprint(makeprintable(stream), 3)
except:
try:
vprint(
"zlib error; streamlength: " +
str(len(stream)) + ", firstbyte: " +
str(stream[0]) + ", lastbyte: " +
str(stream[len(stream) - 1]) +
", ZLIB runtime version: " +
zlib.ZLIB_RUNTIME_VERSION, 2)
except:
vprint("No return stream given by zlib", 2)
elif streamfilter == 'ASCII85Decode':
stream = ascii85decode(stream)
elif streamfilter == 'LZWDecode':
stream = lzwdecode(stream)
# elif streamfilter == 'CCITTFaxDecode':
# vprint("[FILTER]: "+streamfilter,3)
# ccittfaxdecode(stream) #TODO: needs additional arguments
elif streamfilter == '/':
pass
else:
vprint(
"Filter not implemented: " + streamfilter +
", found in object: " + str(currentobject[0]) + " " +
str(currentobject[1]), 1)
# TODO: use counttable instead to give list of unimplemented filters with objects at the end of the scan.
# TODO: need to break here if multiple compressions are used of which one fails to prevent error out.
getword(file) # the word endstream
vprint("[STREAM: end]", 2)
if dictionary.get("Type") == "XRef":
vprint("[XRef]", 2)
dictionary["Stream"] = stream
elif dictionary.get("Type") == "ObjStm":
vprint("[STREAM]: open ObjStm", 2)
f = open(".pdfaudit", "w+b")
f.write(stream)
f.write(bytearray([13, 13, 13]))
f.seek(0)
iterateobjstm(f, num(dictionary.get("N")))
f.close()
#TODO: delete file
vprint("[STREAM]: close ObjStm", 2)
else:
dictionary["Stream"] = stream.decode('utf-8', 'ignore')
#TODO: followsymlinks handling in case stream can have symlinks
vprint("[DICT: end]", 2, '')
checkdictionary(dictionary)
return dictionary # TODO: check if we can return more here