def readFromStream(stream, pdf):
idnum = b_("")
while True:
tok = stream.read(1)
if not tok:
# stream has truncated prematurely
raise PdfStreamError("Stream has ended unexpectedly")
if tok.isspace():
break
idnum += tok
generation = b_("")
while True:
tok = stream.read(1)
if not tok:
# stream has truncated prematurely
raise PdfStreamError("Stream has ended unexpectedly")
if tok.isspace():
break
generation += tok
r = stream.read(1)
if r != b_("R"):
raise utils.PdfReadError(
"Error reading indirect object reference at byte %s" %
utils.hexStr(stream.tell()))
return IndirectObject(int(idnum), int(generation), pdf)
def readFromStream(stream, pdf):
idnum = b_("")
while True:
tok = stream.read(1)
if tok.isspace():
break
idnum += tok
generation = b_("")
while True:
tok = stream.read(1)
if tok.isspace():
break
generation += tok
r = stream.read(1)
if r != b_("R"):
raise utils.PdfReadError(
"Error reading indirect object reference at byte %s" %
utils.hexStr(stream.tell()))
return IndirectObject(int(idnum), int(generation), pdf)
def readFromStream(stream, pdf):
idnum = b_("")
while True:
tok = stream.read(1)
if tok.isspace():
break
idnum += tok
generation = b_("")
while True:
tok = stream.read(1)
if tok.isspace():
break
generation += tok
r = stream.read(1)
if r != b_("R"):
raise utils.PdfReadError(
"Error reading indirect object reference at byte %s" %
utils.hexStr(stream.tell()))
return IndirectObject(int(idnum), int(generation), pdf)
def readFromStream(stream, pdf):
debug = False
tmp = stream.read(2)
if tmp != b_("<<"):
raise utils.PdfReadError, \
("Dictionary read error at byte %s: stream must begin with '<<'" % utils.hexStr(stream.tell()))
data = {}
while True:
tok = readNonWhitespace(stream)
if tok == b_('\x00'):
continue
if not tok:
# stream has truncated prematurely
raise PdfStreamError("Stream has ended unexpectedly")
if debug: print "Tok:",tok
if tok == b_(">"):
stream.read(1)
break
stream.seek(-1, 1)
key = readObject(stream, pdf)
tok = readNonWhitespace(stream)
stream.seek(-1, 1)
value = readObject(stream, pdf)
if not data.has_key(key):
data[key] = value
pos = stream.tell()
s = readNonWhitespace(stream)
if s == b_('s') and stream.read(5) == b_('tream'):
eol = stream.read(1)
# odd PDF file output has spaces after 'stream' keyword but before EOL.
# patch provided by Danial Sandler
while eol == b_(' '):
eol = stream.read(1)
assert eol in (b_("\n"), b_("\r"))
if eol == b_("\r"):
# read \n after
if stream.read(1) != '\n':
stream.seek(-1, 1)
# this is a stream object, not a dictionary
assert data.has_key("/Length")
length = data["/Length"]
if debug: print data
if isinstance(length, IndirectObject):
t = stream.tell()
length = pdf.getObject(length)
stream.seek(t, 0)
data["__streamdata__"] = stream.read(length)
if debug: print "here"
#if debug: print debugging.printAsHex(data["__streamdata__"])
e = readNonWhitespace(stream)
ndstream = stream.read(8)
if (e + ndstream) != b_("endstream"):
# (sigh) - the odd PDF file has a length that is too long, so
# we need to read backwards to find the "endstream" ending.
# ReportLab (unknown version) generates files with this bug,
# and Python users into PDF files tend to be our audience.
# we need to do this to correct the streamdata and chop off
# an extra character.
pos = stream.tell()
stream.seek(-10, 1)
end = stream.read(9)
if end == b_("endstream"):
# we found it by looking back one character further.
data["__streamdata__"] = data["__streamdata__"][:-1]
else:
if pdf.strict == False:
warnings.warn("Ignoring missing endstream. This could affect PDF output.")
pass
else:
if debug: print "E", e, ndstream, debugging.toHex(end)
stream.seek(pos, 0)
raise utils.PdfReadError, \
("Unable to find 'endstream' marker after stream at byte %s." % utils.hexStr(stream.tell()))
else:
stream.seek(pos, 0)
if data.has_key("__streamdata__"):
return StreamObject.initializeFromDictionary(data)
else:
retval = DictionaryObject()
retval.update(data)
return retval
def readFromStream(stream, pdf):
idnum = b_("")
while True:
tok = stream.read(1)
if not tok:
# stream has truncated prematurely
raise PdfStreamError("Stream has ended unexpectedly")
if tok.isspace():
break
idnum += tok
generation = b_("")
while True:
tok = stream.read(1)
if not tok:
# stream has truncated prematurely
raise PdfStreamError("Stream has ended unexpectedly")
if tok.isspace():
break
generation += tok
r = stream.read(1)
if r != b_("R"):
raise utils.PdfReadError("Error reading indirect object reference at byte %s" % utils.hexStr(stream.tell()))
return IndirectObject(int(idnum), int(generation), pdf)
def readFromStream(stream, pdf):
debug = False
tmp = stream.read(2)
if tmp != b_("<<"):
raise utils.PdfReadError, \
("Dictionary read error at byte %s: stream must begin with '<<'" % utils.hexStr(stream.tell()))
data = {}
while True:
tok = readNonWhitespace(stream)
if debug: print "Tok:", tok
if tok == b_(">"):
stream.read(1)
break
stream.seek(-1, 1)
key = readObject(stream, pdf)
tok = readNonWhitespace(stream)
stream.seek(-1, 1)
value = readObject(stream, pdf)
if data.has_key(key):
# multiple definitions of key not permitted
raise utils.PdfReadError, ("Multiple definitions in dictionary at byte %s for key %s" \
% (utils.hexStr(stream.tell()), key))
data[key] = value
pos = stream.tell()
s = readNonWhitespace(stream)
if s == b_('s') and stream.read(5) == b_('tream'):
eol = stream.read(1)
# odd PDF file output has spaces after 'stream' keyword but before EOL.
# patch provided by Danial Sandler
while eol == b_(' '):
eol = stream.read(1)
assert eol in (b_("\n"), b_("\r"))
if eol == b_("\r"):
# read \n after
stream.read(1)
# this is a stream object, not a dictionary
assert data.has_key("/Length")
length = data["/Length"]
if debug: print data
if isinstance(length, IndirectObject):
t = stream.tell()
length = pdf.getObject(length)
stream.seek(t, 0)
data["__streamdata__"] = stream.read(length)
if debug: print "here"
#if debug: print debugging.printAsHex(data["__streamdata__"])
e = readNonWhitespace(stream)
ndstream = stream.read(8)
if (e + ndstream) != b_("endstream"):
# (sigh) - the odd PDF file has a length that is too long, so
# we need to read backwards to find the "endstream" ending.
# ReportLab (unknown version) generates files with this bug,
# and Python users into PDF files tend to be our audience.
# we need to do this to correct the streamdata and chop off
# an extra character.
pos = stream.tell()
stream.seek(-10, 1)
end = stream.read(9)
if end == b_("endstream"):
# we found it by looking back one character further.
data["__streamdata__"] = data["__streamdata__"][:-1]
else:
# if debug: print "E", e, ndstream, debugging.toHex(end)
stream.seek(pos, 0)
raise utils.PdfReadError, \
("Unable to find 'endstream' marker after stream at byte %s." % utils.hexStr(stream.tell()))
else:
stream.seek(pos, 0)
if data.has_key("__streamdata__"):
return StreamObject.initializeFromDictionary(data)
else:
retval = DictionaryObject()
retval.update(data)
return retval
def readFromStream(stream, pdf):
debug = False
tmp = stream.read(2)
if tmp != "<<":
raise utils.PdfReadError, (
"Dictionary read error at byte %s: stream must begin with '<<'" % utils.hexStr(stream.tell())
)
data = {}
while True:
tok = readNonWhitespace(stream)
if debug:
print "Tok:", tok
if tok == ">":
stream.read(1)
break
stream.seek(-1, 1)
key = readObject(stream, pdf)
tok = readNonWhitespace(stream)
stream.seek(-1, 1)
value = readObject(stream, pdf)
if data.has_key(key):
# multiple definitions of key not permitted
raise utils.PdfReadError, (
"Multiple definitions in dictionary at byte %s for key %s" % (utils.hexStr(stream.tell()), key)
)
data[key] = value
pos = stream.tell()
s = readNonWhitespace(stream)
if s == "s" and stream.read(5) == "tream":
eol = stream.read(1)
# odd PDF file output has spaces after 'stream' keyword but before EOL.
# patch provided by Danial Sandler
while eol == " ":
eol = stream.read(1)
assert eol in ("\n", "\r")
if eol == "\r":
# read \n after
stream.read(1)
# this is a stream object, not a dictionary
assert data.has_key("/Length")
length = data["/Length"]
if debug:
print data
if isinstance(length, IndirectObject):
t = stream.tell()
length = pdf.getObject(length)
stream.seek(t, 0)
data["__streamdata__"] = stream.read(length)
if debug:
print "here"
# if debug: print debugging.printAsHex(data["__streamdata__"])
e = readNonWhitespace(stream)
ndstream = stream.read(8)
if (e + ndstream) != "endstream":
# (sigh) - the odd PDF file has a length that is too long, so
# we need to read backwards to find the "endstream" ending.
# ReportLab (unknown version) generates files with this bug,
# and Python users into PDF files tend to be our audience.
# we need to do this to correct the streamdata and chop off
# an extra character.
pos = stream.tell()
stream.seek(-10, 1)
end = stream.read(9)
if end == "endstream":
# we found it by looking back one character further.
data["__streamdata__"] = data["__streamdata__"][:-1]
else:
# if debug: print "E", e, ndstream, debugging.toHex(end)
stream.seek(pos, 0)
raise utils.PdfReadError, (
"Unable to find 'endstream' marker after stream at byte %s." % utils.hexStr(stream.tell())
)
else:
stream.seek(pos, 0)
if data.has_key("__streamdata__"):
return StreamObject.initializeFromDictionary(data)
else:
retval = DictionaryObject()
retval.update(data)
return retval
def readFromStream(stream, pdf):
tmp = stream.read(2)
if tmp != b_("<<"):
raise utils.PdfReadError(
("Dictionary read error at byte %s: "
"stream must begin with '<<'" %
utils.hexStr(stream.tell())))
data = {}
while True:
tok = readNonWhitespace(stream)
if not tok:
# stream has truncated prematurely
raise utils.PdfStreamError("Stream has ended unexpectedly")
if tok == b_(">"):
stream.read(1)
break
stream.seek(-1, 1)
key = readObject(stream, pdf)
tok = readNonWhitespace(stream)
stream.seek(-1, 1)
value = readObject(stream, pdf)
if key in data:
# multiple definitions of key not permitted
raise utils.PdfReadError, ("Multiple definitions in "
"dictionary at byte %s for key %s"
% (utils.hexStr(stream.tell()),
key))
data[key] = value
pos = stream.tell()
s = readNonWhitespace(stream)
if s == b_('s') and stream.read(5) == b_('tream'):
eol = stream.read(1)
# odd PDF file output has spaces after 'stream'
# keyword but before EOL.
# patch provided by Danial Sandler
while eol == b_(' '):
eol = stream.read(1)
assert eol in (b_("\n"), b_("\r"))
if eol == b_("\r"):
# read \n after
if stream.read(1) != '\n':
stream.seek(-1, 1)
# this is a stream object, not a dictionary
assert "/Length" in data
length = data["/Length"]
if isinstance(length, IndirectObject):
t = stream.tell()
length = pdf.getObject(length)
stream.seek(t, 0)
data["__streamdata__"] = stream.read(length)
e = readNonWhitespace(stream)
ndstream = stream.read(8)
if (e + ndstream) != b_("endstream"):
# (sigh) - the odd PDF file has a length that is too long, so
# we need to read backwards to find the "endstream" ending.
# ReportLab (unknown version) generates files with this bug,
# and Python users into PDF files tend to be our audience.
# we need to do this to correct the streamdata and chop off
# an extra character.
pos = stream.tell()
stream.seek(-10, 1)
end = stream.read(9)
if end == b_("endstream"):
# we found it by looking back one character further.
data["__streamdata__"] = data["__streamdata__"][:-1]
else:
stream.seek(pos, 0)
raise utils.PdfReadError, \
("Unable to find 'endstream' marker after "
"stream at byte %s." % utils.hexStr(stream.tell()))
else:
stream.seek(pos, 0)
if "__streamdata__" in data:
return StreamObject.initializeFromDictionary(data)
else:
retval = DictionaryObject()
retval.update(data)
return retval