SpiderFoot automates OSINT for threat intelligence and mapping your attack surface.
Python attacksurfacecticybersecurityfootprintinghackinginformation-gatheringinformation-securityinfosecintelligence-gatheringosintosint-frameworkosint-reconnaissanceosint-toolpentestingpythonreconsecurity-toolsthreat-intelligencethreatintel
Replaced use of metapdf with PyPDF2.
Steve87af0d2cde95
diff --git a/LICENSE.tp b/LICENSE.tpindex 4fbd8853..3f98a6f1 100644--- a/LICENSE.tp+++ b/LICENSE.tp@@ -99,17 +99,6 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS INTHE SOFTWARE.-License for metapdf:-====================-Copyright (c) 2012 Ali Anari--Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:--The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.--THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.--License for ispell dictionary files:=====================================Ispell can be found at http://fmg-www.cs.ucla.edu/geoff/ispell.html.@@ -236,3 +225,38 @@ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISINGFROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHERDEALINGS IN THE SOFTWARE.+++License for PyPDF2:+====================++Copyright (c) 2006-2008, Mathieu Fenniak+Some contributions copyright (c) 2007, Ashish Kulkarni <[email protected]>+Some contributions copyright (c) 2014, Steve Witham <[email protected]>++All rights reserved.++Redistribution and use in source and binary forms, with or without+modification, are permitted provided that the following conditions are+met:++* Redistributions of source code must retain the above copyright notice,+this list of conditions and the following disclaimer.+* Redistributions in binary form must reproduce the above copyright notice,+this list of conditions and the following disclaimer in the documentation+and/or other materials provided with the distribution.+* The name of the author may not be used to endorse or promote products+derived from this software without specific prior written permission.++THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+POSSIBILITY OF SUCH DAMAGE.+diff --git a/ext/PyPDF2/__init__.py b/ext/PyPDF2/__init__.pynew file mode 100755index 00000000..f458c0ea--- /dev/null+++ b/ext/PyPDF2/__init__.py@@ -0,0 +1,5 @@+from .pdf import PdfFileReader, PdfFileWriter+from .merger import PdfFileMerger+from .pagerange import PageRange, parse_filename_page_ranges+from ._version import __version__+__all__ = ["pdf", "PdfFileMerger"]diff --git a/ext/PyPDF2/_version.py b/ext/PyPDF2/_version.pynew file mode 100755index 00000000..5fc7041e--- /dev/null+++ b/ext/PyPDF2/_version.py@@ -0,0 +1 @@+__version__ = '1.26.0'diff --git a/ext/PyPDF2/filters.py b/ext/PyPDF2/filters.pynew file mode 100755index 00000000..3717fd4c--- /dev/null+++ b/ext/PyPDF2/filters.py@@ -0,0 +1,362 @@+# vim: sw=4:expandtab:foldmethod=marker+#+# Copyright (c) 2006, Mathieu Fenniak+# All rights reserved.+#+# Redistribution and use in source and binary forms, with or without+# modification, are permitted provided that the following conditions are+# met:+#+# * Redistributions of source code must retain the above copyright notice,+# this list of conditions and the following disclaimer.+# * Redistributions in binary form must reproduce the above copyright notice,+# this list of conditions and the following disclaimer in the documentation+# and/or other materials provided with the distribution.+# * The name of the author may not be used to endorse or promote products+# derived from this software without specific prior written permission.+#+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+# POSSIBILITY OF SUCH DAMAGE.+++"""+Implementation of stream filters for PDF.+"""+__author__ = "Mathieu Fenniak"+__author_email__ = "[email protected]"++from .utils import PdfReadError, ord_, chr_+from sys import version_info+if version_info < ( 3, 0 ):+ from cStringIO import StringIO+else:+ from io import StringIO+ import struct++try:+ import zlib++ def decompress(data):+ return zlib.decompress(data)++ def compress(data):+ return zlib.compress(data)++except ImportError:+ # Unable to import zlib. Attempt to use the System.IO.Compression+ # library from the .NET framework. (IronPython only)+ import System+ from System import IO, Collections, Array++ def _string_to_bytearr(buf):+ retval = Array.CreateInstance(System.Byte, len(buf))+ for i in range(len(buf)):+ retval[i] = ord(buf[i])+ return retval++ def _bytearr_to_string(bytes):+ retval = ""+ for i in range(bytes.Length):+ retval += chr(bytes[i])+ return retval++ def _read_bytes(stream):+ ms = IO.MemoryStream()+ buf = Array.CreateInstance(System.Byte, 2048)+ while True:+ bytes = stream.Read(buf, 0, buf.Length)+ if bytes == 0:+ break+ else:+ ms.Write(buf, 0, bytes)+ retval = ms.ToArray()+ ms.Close()+ return retval++ def decompress(data):+ bytes = _string_to_bytearr(data)+ ms = IO.MemoryStream()+ ms.Write(bytes, 0, bytes.Length)+ ms.Position = 0 # fseek 0+ gz = IO.Compression.DeflateStream(ms, IO.Compression.CompressionMode.Decompress)+ bytes = _read_bytes(gz)+ retval = _bytearr_to_string(bytes)+ gz.Close()+ return retval++ def compress(data):+ bytes = _string_to_bytearr(data)+ ms = IO.MemoryStream()+ gz = IO.Compression.DeflateStream(ms, IO.Compression.CompressionMode.Compress, True)+ gz.Write(bytes, 0, bytes.Length)+ gz.Close()+ ms.Position = 0 # fseek 0+ bytes = ms.ToArray()+ retval = _bytearr_to_string(bytes)+ ms.Close()+ return retval+++class FlateDecode(object):+ def decode(data, decodeParms):+ data = decompress(data)+ predictor = 1+ if decodeParms:+ try:+ predictor = decodeParms.get("/Predictor", 1)+ except AttributeError:+ pass # usually an array with a null object was read++ # predictor 1 == no predictor+ if predictor != 1:+ columns = decodeParms["/Columns"]+ # PNG prediction:+ if predictor >= 10 and predictor <= 15:+ output = StringIO()+ # PNG prediction can vary from row to row+ rowlength = columns + 1+ assert len(data) % rowlength == 0+ prev_rowdata = (0,) * rowlength+ for row in range(len(data) // rowlength):+ rowdata = [ord_(x) for x in data[(row*rowlength):((row+1)*rowlength)]]+ filterByte = rowdata[0]+ if filterByte == 0:+ pass+ elif filterByte == 1:+ for i in range(2, rowlength):+ rowdata[i] = (rowdata[i] + rowdata[i-1]) % 256+ elif filterByte == 2:+ for i in range(1, rowlength):+ rowdata[i] = (rowdata[i] + prev_rowdata[i]) % 256+ else:+ # unsupported PNG filter+ raise PdfReadError("Unsupported PNG filter %r" % filterByte)+ prev_rowdata = rowdata+ output.write(''.join([chr(x) for x in rowdata[1:]]))+ data = output.getvalue()+ else:+ # unsupported predictor+ raise PdfReadError("Unsupported flatedecode predictor %r" % predictor)+ return data+ decode = staticmethod(decode)++ def encode(data):+ return compress(data)+ encode = staticmethod(encode)+++class ASCIIHexDecode(object):+ def decode(data, decodeParms=None):+ retval = ""+ char = ""+ x = 0+ while True:+ c = data[x]+ if c == ">":+ break+ elif c.isspace():+ x += 1+ continue+ char += c+ if len(char) == 2:+ retval += chr(int(char, base=16))+ char = ""+ x += 1+ assert char == ""+ return retval+ decode = staticmethod(decode)+++class LZWDecode(object):+ """Taken from:+ http://www.java2s.com/Open-Source/Java-Document/PDF/PDF-Renderer/com/sun/pdfview/decode/LZWDecode.java.htm+ """+ class decoder(object):+ def __init__(self, data):+ self.STOP=257+ self.CLEARDICT=256+ self.data=data+ self.bytepos=0+ self.bitpos=0+ self.dict=[""]*4096+ for i in range(256):+ self.dict[i]=chr(i)+ self.resetDict()++ def resetDict(self):+ self.dictlen=258+ self.bitspercode=9++ def nextCode(self):+ fillbits=self.bitspercode+ value=0+ while fillbits>0 :+ if self.bytepos >= len(self.data):+ return -1+ nextbits=ord(self.data[self.bytepos])+ bitsfromhere=8-self.bitpos+ if bitsfromhere>fillbits:+ bitsfromhere=fillbits+ value |= (((nextbits >> (8-self.bitpos-bitsfromhere)) &+ (0xff >> (8-bitsfromhere))) <<+ (fillbits-bitsfromhere))+ fillbits -= bitsfromhere+ self.bitpos += bitsfromhere+ if self.bitpos >=8:+ self.bitpos=0+ self.bytepos = self.bytepos+1+ return value++ def decode(self):+ """ algorithm derived from:+ http://www.rasip.fer.hr/research/compress/algorithms/fund/lz/lzw.html+ and the PDFReference+ """+ cW = self.CLEARDICT;+ baos=""+ while True:+ pW = cW;+ cW = self.nextCode();+ if cW == -1:+ raise PdfReadError("Missed the stop code in LZWDecode!")+ if cW == self.STOP:+ break;+ elif cW == self.CLEARDICT:+ self.resetDict();+ elif pW == self.CLEARDICT:+ baos+=self.dict[cW]+ else:+ if cW < self.dictlen:+ baos += self.dict[cW]+ p=self.dict[pW]+self.dict[cW][0]+ self.dict[self.dictlen]=p+ self.dictlen+=1+ else:+ p=self.dict[pW]+self.dict[pW][0]+ baos+=p+ self.dict[self.dictlen] = p;+ self.dictlen+=1+ if (self.dictlen >= (1 << self.bitspercode) - 1 and+ self.bitspercode < 12):+ self.bitspercode+=1+ return baos++ @staticmethod+ def decode(data,decodeParams=None):+ return LZWDecode.decoder(data).decode()+++class ASCII85Decode(object):+ def decode(data, decodeParms=None):+ if version_info < ( 3, 0 ):+ retval = ""+ group = []+ x = 0+ hitEod = False+ # remove all whitespace from data+ data = [y for y in data if not (y in ' \n\r\t')]+ while not hitEod:+ c = data[x]+ if len(retval) == 0 and c == "<" and data[x+1] == "~":+ x += 2+ continue+ #elif c.isspace():+ # x += 1+ # continue+ elif c == 'z':+ assert len(group) == 0+ retval += '\x00\x00\x00\x00'+ x += 1+ continue+ elif c == "~" and data[x+1] == ">":+ if len(group) != 0:+ # cannot have a final group of just 1 char+ assert len(group) > 1+ cnt = len(group) - 1+ group += [ 85, 85, 85 ]+ hitEod = cnt+ else:+ break+ else:+ c = ord(c) - 33+ assert c >= 0 and c < 85+ group += [ c ]+ if len(group) >= 5:+ b = group[0] * (85**4) + \+ group[1] * (85**3) + \+ group[2] * (85**2) + \+ group[3] * 85 + \+ group[4]+ assert b < (2**32 - 1)+ c4 = chr((b >> 0) % 256)+ c3 = chr((b >> 8) % 256)+ c2 = chr((b >> 16) % 256)+ c1 = chr(b >> 24)+ retval += (c1 + c2 + c3 + c4)+ if hitEod:+ retval = retval[:-4+hitEod]+ group = []+ x += 1+ return retval+ else:+ if isinstance(data, str):+ data = data.encode('ascii')+ n = b = 0+ out = bytearray()+ for c in data:+ if ord('!') <= c and c <= ord('u'):+ n += 1+ b = b*85+(c-33)+ if n == 5:+ out += struct.pack(b'>L',b)+ n = b = 0+ elif c == ord('z'):+ assert n == 0+ out += b'\0\0\0\0'+ elif c == ord('~'):+ if n:+ for _ in range(5-n):+ b = b*85+84+ out += struct.pack(b'>L',b)[:n-1]+ break+ return bytes(out)+ decode = staticmethod(decode)+++def decodeStreamData(stream):+ from .generic import NameObject+ filters = stream.get("/Filter", ())+ if len(filters) and not isinstance(filters[0], NameObject):+ # we have a single filter instance+ filters = (filters,)+ data = stream._data+ # If there is not data to decode we should not try to decode the data.+ if data:+ for filterType in filters:+ if filterType == "/FlateDecode" or filterType == "/Fl":+ data = FlateDecode.decode(data, stream.get("/DecodeParms"))+ elif filterType == "/ASCIIHexDecode" or filterType == "/AHx":+ data = ASCIIHexDecode.decode(data)+ elif filterType == "/LZWDecode" or filterType == "/LZW":+ data = LZWDecode.decode(data, stream.get("/DecodeParms"))+ elif filterType == "/ASCII85Decode" or filterType == "/A85":+ data = ASCII85Decode.decode(data)+ elif filterType == "/Crypt":+ decodeParams = stream.get("/DecodeParams", {})+ if "/Name" not in decodeParams and "/Type" not in decodeParams:+ pass+ else:+ raise NotImplementedError("/Crypt filter with /Name or /Type not supported yet")+ else:+ # unsupported filter+ raise NotImplementedError("unsupported filter %s" % filterType)+ return datadiff --git a/ext/PyPDF2/generic.py b/ext/PyPDF2/generic.pynew file mode 100755index 00000000..c4332297--- /dev/null+++ b/ext/PyPDF2/generic.py@@ -0,0 +1,1226 @@+# vim: sw=4:expandtab:foldmethod=marker+#+# Copyright (c) 2006, Mathieu Fenniak+# All rights reserved.+#+# Redistribution and use in source and binary forms, with or without+# modification, are permitted provided that the following conditions are+# met:+#+# * Redistributions of source code must retain the above copyright notice,+# this list of conditions and the following disclaimer.+# * Redistributions in binary form must reproduce the above copyright notice,+# this list of conditions and the following disclaimer in the documentation+# and/or other materials provided with the distribution.+# * The name of the author may not be used to endorse or promote products+# derived from this software without specific prior written permission.+#+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+# POSSIBILITY OF SUCH DAMAGE.+++"""+Implementation of generic PDF objects (dictionary, number, string, and so on)+"""+__author__ = "Mathieu Fenniak"+__author_email__ = "[email protected]"++import re+from .utils import readNonWhitespace, RC4_encrypt, skipOverComment+from .utils import b_, u_, chr_, ord_+from .utils import PdfStreamError+import warnings+from . import filters+from . import utils+import decimal+import codecs+import sys+#import debugging++ObjectPrefix = b_('/<[tf(n%')+NumberSigns = b_('+-')+IndirectPattern = re.compile(b_(r"(\d+)\s+(\d+)\s+R[^a-zA-Z]"))+++def readObject(stream, pdf):+ tok = stream.read(1)+ stream.seek(-1, 1) # reset to start+ idx = ObjectPrefix.find(tok)+ if idx == 0:+ # name object+ return NameObject.readFromStream(stream, pdf)+ elif idx == 1:+ # hexadecimal string OR dictionary+ peek = stream.read(2)+ stream.seek(-2, 1) # reset to start+ if peek == b_('<<'):+ return DictionaryObject.readFromStream(stream, pdf)+ else:+ return readHexStringFromStream(stream)+ elif idx == 2:+ # array object+ return ArrayObject.readFromStream(stream, pdf)+ elif idx == 3 or idx == 4:+ # boolean object+ return BooleanObject.readFromStream(stream)+ elif idx == 5:+ # string object+ return readStringFromStream(stream)+ elif idx == 6:+ # null object+ return NullObject.readFromStream(stream)+ elif idx == 7:+ # comment+ while tok not in (b_('\r'), b_('\n')):+ tok = stream.read(1)+ tok = readNonWhitespace(stream)+ stream.seek(-1, 1)+ return readObject(stream, pdf)+ else:+ # number object OR indirect reference+ if tok in NumberSigns:+ # number+ return NumberObject.readFromStream(stream)+ peek = stream.read(20)+ stream.seek(-len(peek), 1) # reset to start+ if IndirectPattern.match(peek) != None:+ return IndirectObject.readFromStream(stream, pdf)+ else:+ return NumberObject.readFromStream(stream)+++class PdfObject(object):+ def getObject(self):+ """Resolves indirect references."""+ return self+++class NullObject(PdfObject):+ def writeToStream(self, stream, encryption_key):+ stream.write(b_("null"))++ def readFromStream(stream):+ nulltxt = stream.read(4)+ if nulltxt != b_("null"):+ raise utils.PdfReadError("Could not read Null object")+ return NullObject()+ readFromStream = staticmethod(readFromStream)+++class BooleanObject(PdfObject):+ def __init__(self, value):+ self.value = value++ def writeToStream(self, stream, encryption_key):+ if self.value:+ stream.write(b_("true"))+ else:+ stream.write(b_("false"))++ def readFromStream(stream):+ word = stream.read(4)+ if word == b_("true"):+ return BooleanObject(True)+ elif word == b_("fals"):+ stream.read(1)+ return BooleanObject(False)+ else:+ raise utils.PdfReadError('Could not read Boolean object')+ readFromStream = staticmethod(readFromStream)+++class ArrayObject(list, PdfObject):+ def writeToStream(self, stream, encryption_key):+ stream.write(b_("["))+ for data in self:+ stream.write(b_(" "))+ data.writeToStream(stream, encryption_key)+ stream.write(b_(" ]"))++ def readFromStream(stream, pdf):+ arr = ArrayObject()+ tmp = stream.read(1)+ if tmp != b_("["):+ raise utils.PdfReadError("Could not read array")+ while True:+ # skip leading whitespace+ tok = stream.read(1)+ while tok.isspace():+ tok = stream.read(1)+ stream.seek(-1, 1)+ # check for array ending+ peekahead = stream.read(1)+ if peekahead == b_("]"):+ break+ stream.seek(-1, 1)+ # read and append obj+ arr.append(readObject(stream, pdf))+ return arr+ readFromStream = staticmethod(readFromStream)+++class IndirectObject(PdfObject):+ def __init__(self, idnum, generation, pdf):+ self.idnum = idnum+ self.generation = generation+ self.pdf = pdf++ def getObject(self):+ return self.pdf.getObject(self).getObject()++ def __repr__(self):+ return "IndirectObject(%r, %r)" % (self.idnum, self.generation)++ def __eq__(self, other):+ return (+ other != None and+ isinstance(other, IndirectObject) and+ self.idnum == other.idnum and+ self.generation == other.generation and+ self.pdf is other.pdf+ )++ def __ne__(self, other):+ return not self.__eq__(other)++ def writeToStream(self, stream, encryption_key):+ stream.write(b_("%s %s R" % (self.idnum, self.generation)))++ 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():+ if not generation:+ continue+ break+ generation += tok+ r = readNonWhitespace(stream)+ 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)+ readFromStream = staticmethod(readFromStream)+++class FloatObject(decimal.Decimal, PdfObject):+ def __new__(cls, value="0", context=None):+ try:+ return decimal.Decimal.__new__(cls, utils.str_(value), context)+ except:+ return decimal.Decimal.__new__(cls, str(value))++ def __repr__(self):+ if self == self.to_integral():+ return str(self.quantize(decimal.Decimal(1)))+ else:+ # Standard formatting adds useless extraneous zeros.+ o = "%.5f" % self+ # Remove the zeros.+ while o and o[-1] == '0':+ o = o[:-1]+ return o++ def as_numeric(self):+ return float(b_(repr(self)))++ def writeToStream(self, stream, encryption_key):+ stream.write(b_(repr(self)))+++class NumberObject(int, PdfObject):+ NumberPattern = re.compile(b_('[^+-.0-9]'))+ ByteDot = b_(".")++ def __new__(cls, value):+ val = int(value)+ try:+ return int.__new__(cls, val)+ except OverflowError:+ return int.__new__(cls, 0)++ def as_numeric(self):+ return int(b_(repr(self)))++ def writeToStream(self, stream, encryption_key):+ stream.write(b_(repr(self)))++ def readFromStream(stream):+ num = utils.readUntilRegex(stream, NumberObject.NumberPattern)+ if num.find(NumberObject.ByteDot) != -1:+ return FloatObject(num)+ else:+ return NumberObject(num)+ readFromStream = staticmethod(readFromStream)+++##+# Given a string (either a "str" or "unicode"), create a ByteStringObject or a+# TextStringObject to represent the string.+def createStringObject(string):+ if isinstance(string, utils.string_type):+ return TextStringObject(string)+ elif isinstance(string, utils.bytes_type):+ try:+ if string.startswith(codecs.BOM_UTF16_BE):+ retval = TextStringObject(string.decode("utf-16"))+ retval.autodetect_utf16 = True+ return retval+ else:+ # This is probably a big performance hit here, but we need to+ # convert string objects into the text/unicode-aware version if+ # possible... and the only way to check if that's possible is+ # to try. Some strings are strings, some are just byte arrays.+ retval = TextStringObject(decode_pdfdocencoding(string))+ retval.autodetect_pdfdocencoding = True+ return retval+ except UnicodeDecodeError:+ return ByteStringObject(string)+ else:+ raise TypeError("createStringObject should have str or unicode arg")+++def readHexStringFromStream(stream):+ stream.read(1)+ txt = ""+ x = b_("")+ while True:+ tok = readNonWhitespace(stream)+ if not tok:+ # stream has truncated prematurely+ raise PdfStreamError("Stream has ended unexpectedly")+ if tok == b_(">"):+ break+ x += tok+ if len(x) == 2:+ txt += chr(int(x, base=16))+ x = b_("")+ if len(x) == 1:+ x += b_("0")+ if len(x) == 2:+ txt += chr(int(x, base=16))+ return createStringObject(b_(txt))+++def readStringFromStream(stream):+ tok = stream.read(1)+ parens = 1+ txt = b_("")+ while True:+ tok = stream.read(1)+ if not tok:+ # stream has truncated prematurely+ raise PdfStreamError("Stream has ended unexpectedly")+ if tok == b_("("):+ parens += 1+ elif tok == b_(")"):+ parens -= 1+ if parens == 0:+ break+ elif tok == b_("\\"):+ tok = stream.read(1)+ if tok == b_("n"):+ tok = b_("\n")+ elif tok == b_("r"):+ tok = b_("\r")+ elif tok == b_("t"):+ tok = b_("\t")+ elif tok == b_("b"):+ tok = b_("\b")+ elif tok == b_("f"):+ tok = b_("\f")+ elif tok == b_("c"):+ tok = b_("\c")+ elif tok == b_("("):+ tok = b_("(")+ elif tok == b_(")"):+ tok = b_(")")+ elif tok == b_("/"):+ tok = b_("/")+ elif tok == b_("\\"):+ tok = b_("\\")+ elif tok in (b_(" "), b_("/"), b_("%"), b_("<"), b_(">"), b_("["),+ b_("]"), b_("#"), b_("_"), b_("&"), b_('$')):+ # odd/unnessecary escape sequences we have encountered+ tok = b_(tok)+ elif tok.isdigit():+ # "The number ddd may consist of one, two, or three+ # octal digits; high-order overflow shall be ignored.+ # Three octal digits shall be used, with leading zeros+ # as needed, if the next character of the string is also+ # a digit." (PDF reference 7.3.4.2, p 16)+ for i in range(2):+ ntok = stream.read(1)+ if ntok.isdigit():+ tok += ntok+ else:+ break+ tok = b_(chr(int(tok, base=8)))+ elif tok in b_("\n\r"):+ # This case is hit when a backslash followed by a line+ # break occurs. If it's a multi-char EOL, consume the+ # second character:+ tok = stream.read(1)+ if not tok in b_("\n\r"):+ stream.seek(-1, 1)+ # Then don't add anything to the actual string, since this+ # line break was escaped:+ tok = b_('')+ else:+ raise utils.PdfReadError(r"Unexpected escaped string: %s" % tok)+ txt += tok+ return createStringObject(txt)+++##+# Represents a string object where the text encoding could not be determined.+# This occurs quite often, as the PDF spec doesn't provide an alternate way to+# represent strings -- for example, the encryption data stored in files (like+# /O) is clearly not text, but is still stored in a "String" object.+class ByteStringObject(utils.bytes_type, PdfObject):++ ##+ # For compatibility with TextStringObject.original_bytes. This method+ # returns self.+ original_bytes = property(lambda self: self)++ def writeToStream(self, stream, encryption_key):+ bytearr = self+ if encryption_key:+ bytearr = RC4_encrypt(encryption_key, bytearr)+ stream.write(b_("<"))+ stream.write(utils.hexencode(bytearr))+ stream.write(b_(">"))+++##+# Represents a string object that has been decoded into a real unicode string.+# If read from a PDF document, this string appeared to match the+# PDFDocEncoding, or contained a UTF-16BE BOM mark to cause UTF-16 decoding to+# occur.+class TextStringObject(utils.string_type, PdfObject):+ autodetect_pdfdocencoding = False+ autodetect_utf16 = False++ ##+ # It is occasionally possible that a text string object gets created where+ # a byte string object was expected due to the autodetection mechanism --+ # if that occurs, this "original_bytes" property can be used to+ # back-calculate what the original encoded bytes were.+ original_bytes = property(lambda self: self.get_original_bytes())++ def get_original_bytes(self):+ # We're a text string object, but the library is trying to get our raw+ # bytes. This can happen if we auto-detected this string as text, but+ # we were wrong. It's pretty common. Return the original bytes that+ # would have been used to create this object, based upon the autodetect+ # method.+ if self.autodetect_utf16:+ return codecs.BOM_UTF16_BE + self.encode("utf-16be")+ elif self.autodetect_pdfdocencoding:+ return encode_pdfdocencoding(self)+ else:+ raise Exception("no information about original bytes")++ def writeToStream(self, stream, encryption_key):+ # Try to write the string out as a PDFDocEncoding encoded string. It's+ # nicer to look at in the PDF file. Sadly, we take a performance hit+ # here for trying...+ try:+ bytearr = encode_pdfdocencoding(self)+ except UnicodeEncodeError:+ bytearr = codecs.BOM_UTF16_BE + self.encode("utf-16be")+ if encryption_key:+ bytearr = RC4_encrypt(encryption_key, bytearr)+ obj = ByteStringObject(bytearr)+ obj.writeToStream(stream, None)+ else:+ stream.write(b_("("))+ for c in bytearr:+ if not chr_(c).isalnum() and c != b_(' '):+ stream.write(b_("\\%03o" % ord_(c)))+ else:+ stream.write(b_(chr_(c)))+ stream.write(b_(")"))+++class NameObject(str, PdfObject):+ delimiterPattern = re.compile(b_(r"\s+|[\(\)<>\[\]{}/%]"))+ surfix = b_("/")++ def writeToStream(self, stream, encryption_key):+ stream.write(b_(self))++ def readFromStream(stream, pdf):+ debug = False+ if debug: print((stream.tell()))+ name = stream.read(1)+ if name != NameObject.surfix:+ raise utils.PdfReadError("name read error")+ name += utils.readUntilRegex(stream, NameObject.delimiterPattern,+ ignore_eof=True)+ if debug: print(name)+ try:+ return NameObject(name.decode('utf-8'))+ except (UnicodeEncodeError, UnicodeDecodeError) as e:+ # Name objects should represent irregular characters+ # with a '#' followed by the symbol's hex number+ if not pdf.strict:+ warnings.warn("Illegal character in Name Object", utils.PdfReadWarning)+ return NameObject(name)+ else:+ raise utils.PdfReadError("Illegal character in Name Object")++ readFromStream = staticmethod(readFromStream)+++class DictionaryObject(dict, PdfObject):+ def raw_get(self, key):+ return dict.__getitem__(self, key)++ def __setitem__(self, key, value):+ if not isinstance(key, PdfObject):+ raise ValueError("key must be PdfObject")+ if not isinstance(value, PdfObject):+ raise ValueError("value must be PdfObject")+ return dict.__setitem__(self, key, value)++ def setdefault(self, key, value=None):+ if not isinstance(key, PdfObject):+ raise ValueError("key must be PdfObject")+ if not isinstance(value, PdfObject):+ raise ValueError("value must be PdfObject")+ return dict.setdefault(self, key, value)++ def __getitem__(self, key):+ return dict.__getitem__(self, key).getObject()++ ##+ # Retrieves XMP (Extensible Metadata Platform) data relevant to the+ # this object, if available.+ # <p>+ # Stability: Added in v1.12, will exist for all future v1.x releases.+ # @return Returns a {@link #xmp.XmpInformation XmlInformation} instance+ # that can be used to access XMP metadata from the document. Can also+ # return None if no metadata was found on the document root.+ def getXmpMetadata(self):+ metadata = self.get("/Metadata", None)+ if metadata == None:+ return None+ metadata = metadata.getObject()+ from . import xmp+ if not isinstance(metadata, xmp.XmpInformation):+ metadata = xmp.XmpInformation(metadata)+ self[NameObject("/Metadata")] = metadata+ return metadata++ ##+ # Read-only property that accesses the {@link+ # #DictionaryObject.getXmpData getXmpData} function.+ # <p>+ # Stability: Added in v1.12, will exist for all future v1.x releases.+ xmpMetadata = property(lambda self: self.getXmpMetadata(), None, None)++ def writeToStream(self, stream, encryption_key):+ stream.write(b_("<<\n"))+ for key, value in list(self.items()):+ key.writeToStream(stream, encryption_key)+ stream.write(b_(" "))+ value.writeToStream(stream, encryption_key)+ stream.write(b_("\n"))+ stream.write(b_(">>"))++ 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+ elif tok == b_('%'):+ stream.seek(-1, 1)+ skipOverComment(stream)+ 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.get(key):+ data[key] = value+ elif pdf.strict:+ # multiple definitions of key not permitted+ raise utils.PdfReadError("Multiple definitions in dictionary at byte %s for key %s" \+ % (utils.hexStr(stream.tell()), key))+ else:+ warnings.warn("Multiple definitions in dictionary at byte %s for key %s" \+ % (utils.hexStr(stream.tell()), key), utils.PdfReadWarning)++ 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) != b_('\n'):+ stream.seek(-1, 1)+ # this is a stream object, not a dictionary+ assert "/Length" in data+ 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(binascii.hexlify(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 "__streamdata__" in data:+ return StreamObject.initializeFromDictionary(data)+ else:+ retval = DictionaryObject()+ retval.update(data)+ return retval+ readFromStream = staticmethod(readFromStream)+++class TreeObject(DictionaryObject):+ def __init__(self):+ DictionaryObject.__init__(self)++ def hasChildren(self):+ return '/First' in self++ def __iter__(self):+ return self.children()++ def children(self):+ if not self.hasChildren():+ raise StopIteration++ child = self['/First']+ while True:+ yield child+ if child == self['/Last']:+ raise StopIteration+ child = child['/Next']++ def addChild(self, child, pdf):+ childObj = child.getObject()+ child = pdf.getReference(childObj)+ assert isinstance(child, IndirectObject)++ if '/First' not in self:+ self[NameObject('/First')] = child+ self[NameObject('/Count')] = NumberObject(0)+ prev = None+ else:+ prev = self['/Last']++ self[NameObject('/Last')] = child+ self[NameObject('/Count')] = NumberObject(self[NameObject('/Count')] + 1)++ if prev:+ prevRef = pdf.getReference(prev)+ assert isinstance(prevRef, IndirectObject)+ childObj[NameObject('/Prev')] = prevRef+ prev[NameObject('/Next')] = child++ parentRef = pdf.getReference(self)+ assert isinstance(parentRef, IndirectObject)+ childObj[NameObject('/Parent')] = parentRef++ def removeChild(self, child):+ childObj = child.getObject()++ if NameObject('/Parent') not in childObj:+ raise ValueError("Removed child does not appear to be a tree item")+ elif childObj[NameObject('/Parent')] != self:+ raise ValueError("Removed child is not a member of this tree")++ found = False+ prevRef = None+ prev = None+ curRef = self[NameObject('/First')]+ cur = curRef.getObject()+ lastRef = self[NameObject('/Last')]+ last = lastRef.getObject()+ while cur != None:+ if cur == childObj:+ if prev == None:+ if NameObject('/Next') in cur:+ # Removing first tree node+ nextRef = cur[NameObject('/Next')]+ next = nextRef.getObject()+ del next[NameObject('/Prev')]+ self[NameObject('/First')] = nextRef+ self[NameObject('/Count')] = self[NameObject('/Count')] - 1++ else:+ # Removing only tree node+ assert self[NameObject('/Count')] == 1+ del self[NameObject('/Count')]+ del self[NameObject('/First')]+ if NameObject('/Last') in self:+ del self[NameObject('/Last')]+ else:+ if NameObject('/Next') in cur:+ # Removing middle tree node+ nextRef = cur[NameObject('/Next')]+ next = nextRef.getObject()+ next[NameObject('/Prev')] = prevRef+ prev[NameObject('/Next')] = nextRef+ self[NameObject('/Count')] = self[NameObject('/Count')] - 1+ else:+ # Removing last tree node+ assert cur == last+ del prev[NameObject('/Next')]+ self[NameObject('/Last')] = prevRef+ self[NameObject('/Count')] = self[NameObject('/Count')] - 1+ found = True+ break++ prevRef = curRef+ prev = cur+ if NameObject('/Next') in cur:+ curRef = cur[NameObject('/Next')]+ cur = curRef.getObject()+ else:+ curRef = None+ cur = None++ if not found:+ raise ValueError("Removal couldn't find item in tree")++ del childObj[NameObject('/Parent')]+ if NameObject('/Next') in childObj:+ del childObj[NameObject('/Next')]+ if NameObject('/Prev') in childObj:+ del childObj[NameObject('/Prev')]++ def emptyTree(self):+ for child in self:+ childObj = child.getObject()+ del childObj[NameObject('/Parent')]+ if NameObject('/Next') in childObj:+ del childObj[NameObject('/Next')]+ if NameObject('/Prev') in childObj:+ del childObj[NameObject('/Prev')]++ if NameObject('/Count') in self:+ del self[NameObject('/Count')]+ if NameObject('/First') in self:+ del self[NameObject('/First')]+ if NameObject('/Last') in self:+ del self[NameObject('/Last')]+++class StreamObject(DictionaryObject):+ def __init__(self):+ self._data = None+ self.decodedSelf = None++ def writeToStream(self, stream, encryption_key):+ self[NameObject("/Length")] = NumberObject(len(self._data))+ DictionaryObject.writeToStream(self, stream, encryption_key)+ del self["/Length"]+ stream.write(b_("\nstream\n"))+ data = self._data+ if encryption_key:+ data = RC4_encrypt(encryption_key, data)+ stream.write(data)+ stream.write(b_("\nendstream"))++ def initializeFromDictionary(data):+ if "/Filter" in data:+ retval = EncodedStreamObject()+ else:+ retval = DecodedStreamObject()+ retval._data = data["__streamdata__"]+ del data["__streamdata__"]+ del data["/Length"]+ retval.update(data)+ return retval+ initializeFromDictionary = staticmethod(initializeFromDictionary)++ def flateEncode(self):+ if "/Filter" in self:+ f = self["/Filter"]+ if isinstance(f, ArrayObject):+ f.insert(0, NameObject("/FlateDecode"))+ else:+ newf = ArrayObject()+ newf.append(NameObject("/FlateDecode"))+ newf.append(f)+ f = newf+ else:+ f = NameObject("/FlateDecode")+ retval = EncodedStreamObject()+ retval[NameObject("/Filter")] = f+ retval._data = filters.FlateDecode.encode(self._data)+ return retval+++class DecodedStreamObject(StreamObject):+ def getData(self):+ return self._data++ def setData(self, data):+ self._data = data+++class EncodedStreamObject(StreamObject):+ def __init__(self):+ self.decodedSelf = None++ def getData(self):+ if self.decodedSelf:+ # cached version of decoded object+ return self.decodedSelf.getData()+ else:+ # create decoded object+ decoded = DecodedStreamObject()++ decoded._data = filters.decodeStreamData(self)+ for key, value in list(self.items()):+ if not key in ("/Length", "/Filter", "/DecodeParms"):+ decoded[key] = value+ self.decodedSelf = decoded+ return decoded._data++ def setData(self, data):+ raise utils.PdfReadError("Creating EncodedStreamObject is not currently supported")+++class RectangleObject(ArrayObject):+ """+ This class is used to represent *page boxes* in PyPDF2. These boxes include:++ * :attr:`artBox <PyPDF2.pdf.PageObject.artBox>`+ * :attr:`bleedBox <PyPDF2.pdf.PageObject.bleedBox>`+ * :attr:`cropBox <PyPDF2.pdf.PageObject.cropBox>`+ * :attr:`mediaBox <PyPDF2.pdf.PageObject.mediaBox>`+ * :attr:`trimBox <PyPDF2.pdf.PageObject.trimBox>`+ """+ def __init__(self, arr):+ # must have four points+ assert len(arr) == 4+ # automatically convert arr[x] into NumberObject(arr[x]) if necessary+ ArrayObject.__init__(self, [self.ensureIsNumber(x) for x in arr])++ def ensureIsNumber(self, value):+ if not isinstance(value, (NumberObject, FloatObject)):+ value = FloatObject(value)+ return value++ def __repr__(self):+ return "RectangleObject(%s)" % repr(list(self))++ def getLowerLeft_x(self):+ return self[0]++ def getLowerLeft_y(self):+ return self[1]++ def getUpperRight_x(self):+ return self[2]++ def getUpperRight_y(self):+ return self[3]++ def getUpperLeft_x(self):+ return self.getLowerLeft_x()++ def getUpperLeft_y(self):+ return self.getUpperRight_y()++ def getLowerRight_x(self):+ return self.getUpperRight_x()++ def getLowerRight_y(self):+ return self.getLowerLeft_y()++ def getLowerLeft(self):+ return self.getLowerLeft_x(), self.getLowerLeft_y()++ def getLowerRight(self):+ return self.getLowerRight_x(), self.getLowerRight_y()++ def getUpperLeft(self):+ return self.getUpperLeft_x(), self.getUpperLeft_y()++ def getUpperRight(self):+ return self.getUpperRight_x(), self.getUpperRight_y()++ def setLowerLeft(self, value):+ self[0], self[1] = [self.ensureIsNumber(x) for x in value]++ def setLowerRight(self, value):+ self[2], self[1] = [self.ensureIsNumber(x) for x in value]++ def setUpperLeft(self, value):+ self[0], self[3] = [self.ensureIsNumber(x) for x in value]++ def setUpperRight(self, value):+ self[2], self[3] = [self.ensureIsNumber(x) for x in value]++ def getWidth(self):+ return self.getUpperRight_x() - self.getLowerLeft_x()++ def getHeight(self):+ return self.getUpperRight_y() - self.getLowerLeft_y()++ lowerLeft = property(getLowerLeft, setLowerLeft, None, None)+ """+ Property to read and modify the lower left coordinate of this box+ in (x,y) form.+ """+ lowerRight = property(getLowerRight, setLowerRight, None, None)+ """+ Property to read and modify the lower right coordinate of this box+ in (x,y) form.+ """+ upperLeft = property(getUpperLeft, setUpperLeft, None, None)+ """+ Property to read and modify the upper left coordinate of this box+ in (x,y) form.+ """+ upperRight = property(getUpperRight, setUpperRight, None, None)+ """+ Property to read and modify the upper right coordinate of this box+ in (x,y) form.+ """+++class Field(TreeObject):+ """+ A class representing a field dictionary. This class is accessed through+ :meth:`getFields()<PyPDF2.PdfFileReader.getFields>`+ """+ def __init__(self, data):+ DictionaryObject.__init__(self)+ attributes = ("/FT", "/Parent", "/Kids", "/T", "/TU", "/TM", "/Ff",+ "/V", "/DV", "/AA")+ for attr in attributes:+ try:+ self[NameObject(attr)] = data[attr]+ except KeyError:+ pass++ fieldType = property(lambda self: self.get("/FT"))+ """+ Read-only property accessing the type of this field.+ """++ parent = property(lambda self: self.get("/Parent"))+ """+ Read-only property accessing the parent of this field.+ """++ kids = property(lambda self: self.get("/Kids"))+ """+ Read-only property accessing the kids of this field.+ """++ name = property(lambda self: self.get("/T"))+ """+ Read-only property accessing the name of this field.+ """++ altName = property(lambda self: self.get("/TU"))+ """+ Read-only property accessing the alternate name of this field.+ """++ mappingName = property(lambda self: self.get("/TM"))+ """+ Read-only property accessing the mapping name of this field. This+ name is used by PyPDF2 as a key in the dictionary returned by+ :meth:`getFields()<PyPDF2.PdfFileReader.getFields>`+ """++ flags = property(lambda self: self.get("/Ff"))+ """+ Read-only property accessing the field flags, specifying various+ characteristics of the field (see Table 8.70 of the PDF 1.7 reference).+ """++ value = property(lambda self: self.get("/V"))+ """+ Read-only property accessing the value of this field. Format+ varies based on field type.+ """++ defaultValue = property(lambda self: self.get("/DV"))+ """+ Read-only property accessing the default value of this field.+ """++ additionalActions = property(lambda self: self.get("/AA"))+ """+ Read-only property accessing the additional actions dictionary.+ This dictionary defines the field's behavior in response to trigger events.+ See Section 8.5.2 of the PDF 1.7 reference.+ """+++class Destination(TreeObject):+ """+ A class representing a destination within a PDF file.+ See section 8.2.1 of the PDF 1.6 reference.++ :param str title: Title of this destination.+ :param int page: Page number of this destination.+ :param str typ: How the destination is displayed.+ :param args: Additional arguments may be necessary depending on the type.+ :raises PdfReadError: If destination type is invalid.++ Valid ``typ`` arguments (see PDF spec for details):+ /Fit No additional arguments+ /XYZ [left] [top] [zoomFactor]+ /FitH [top]+ /FitV [left]+ /FitR [left] [bottom] [right] [top]+ /FitB No additional arguments+ /FitBH [top]+ /FitBV [left]+ """+ def __init__(self, title, page, typ, *args):+ DictionaryObject.__init__(self)+ self[NameObject("/Title")] = title+ self[NameObject("/Page")] = page+ self[NameObject("/Type")] = typ++ # from table 8.2 of the PDF 1.7 reference.+ if typ == "/XYZ":+ (self[NameObject("/Left")], self[NameObject("/Top")],+ self[NameObject("/Zoom")]) = args+ elif typ == "/FitR":+ (self[NameObject("/Left")], self[NameObject("/Bottom")],+ self[NameObject("/Right")], self[NameObject("/Top")]) = args+ elif typ in ["/FitH", "/FitBH"]:+ self[NameObject("/Top")], = args+ elif typ in ["/FitV", "/FitBV"]:+ self[NameObject("/Left")], = args+ elif typ in ["/Fit", "/FitB"]:+ pass+ else:+ raise utils.PdfReadError("Unknown Destination Type: %r" % typ)++ def getDestArray(self):+ return ArrayObject([self.raw_get('/Page'), self['/Type']] + [self[x] for x in ['/Left', '/Bottom', '/Right', '/Top', '/Zoom'] if x in self])++ def writeToStream(self, stream, encryption_key):+ stream.write(b_("<<\n"))+ key = NameObject('/D')+ key.writeToStream(stream, encryption_key)+ stream.write(b_(" "))+ value = self.getDestArray()+ value.writeToStream(stream, encryption_key)++ key = NameObject("/S")+ key.writeToStream(stream, encryption_key)+ stream.write(b_(" "))+ value = NameObject("/GoTo")+ value.writeToStream(stream, encryption_key)++ stream.write(b_("\n"))+ stream.write(b_(">>"))++ title = property(lambda self: self.get("/Title"))+ """+ Read-only property accessing the destination title.++ :rtype: str+ """++ page = property(lambda self: self.get("/Page"))+ """+ Read-only property accessing the destination page number.++ :rtype: int+ """++ typ = property(lambda self: self.get("/Type"))+ """+ Read-only property accessing the destination type.++ :rtype: str+ """++ zoom = property(lambda self: self.get("/Zoom", None))+ """+ Read-only property accessing the zoom factor.++ :rtype: int, or ``None`` if not available.+ """++ left = property(lambda self: self.get("/Left", None))+ """+ Read-only property accessing the left horizontal coordinate.++ :rtype: int, or ``None`` if not available.+ """++ right = property(lambda self: self.get("/Right", None))+ """+ Read-only property accessing the right horizontal coordinate.++ :rtype: int, or ``None`` if not available.+ """++ top = property(lambda self: self.get("/Top", None))+ """+ Read-only property accessing the top vertical coordinate.++ :rtype: int, or ``None`` if not available.+ """++ bottom = property(lambda self: self.get("/Bottom", None))+ """+ Read-only property accessing the bottom vertical coordinate.++ :rtype: int, or ``None`` if not available.+ """+++class Bookmark(Destination):+ def writeToStream(self, stream, encryption_key):+ stream.write(b_("<<\n"))+ for key in [NameObject(x) for x in ['/Title', '/Parent', '/First', '/Last', '/Next', '/Prev'] if x in self]:+ key.writeToStream(stream, encryption_key)+ stream.write(b_(" "))+ value = self.raw_get(key)+ value.writeToStream(stream, encryption_key)+ stream.write(b_("\n"))+ key = NameObject('/Dest')+ key.writeToStream(stream, encryption_key)+ stream.write(b_(" "))+ value = self.getDestArray()+ value.writeToStream(stream, encryption_key)+ stream.write(b_("\n"))+ stream.write(b_(">>"))+++def encode_pdfdocencoding(unicode_string):+ retval = b_('')+ for c in unicode_string:+ try:+ retval += b_(chr(_pdfDocEncoding_rev[c]))+ except KeyError:+ raise UnicodeEncodeError("pdfdocencoding", c, -1, -1,+ "does not exist in translation table")+ return retval+++def decode_pdfdocencoding(byte_array):+ retval = u_('')+ for b in byte_array:+ c = _pdfDocEncoding[ord_(b)]+ if c == u_('\u0000'):+ raise UnicodeDecodeError("pdfdocencoding", utils.barray(b), -1, -1,+ "does not exist in translation table")+ retval += c+ return retval++_pdfDocEncoding = (+ u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'),+ u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'),+ u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'), u_('\u0000'),+ u_('\u02d8'), u_('\u02c7'), u_('\u02c6'), u_('\u02d9'), u_('\u02dd'), u_('\u02db'), u_('\u02da'), u_('\u02dc'),+ u_('\u0020'), u_('\u0021'), u_('\u0022'), u_('\u0023'), u_('\u0024'), u_('\u0025'), u_('\u0026'), u_('\u0027'),+ u_('\u0028'), u_('\u0029'), u_('\u002a'), u_('\u002b'), u_('\u002c'), u_('\u002d'), u_('\u002e'), u_('\u002f'),+ u_('\u0030'), u_('\u0031'), u_('\u0032'), u_('\u0033'), u_('\u0034'), u_('\u0035'), u_('\u0036'), u_('\u0037'),+ u_('\u0038'), u_('\u0039'), u_('\u003a'), u_('\u003b'), u_('\u003c'), u_('\u003d'), u_('\u003e'), u_('\u003f'),+ u_('\u0040'), u_('\u0041'), u_('\u0042'), u_('\u0043'), u_('\u0044'), u_('\u0045'), u_('\u0046'), u_('\u0047'),+ u_('\u0048'), u_('\u0049'), u_('\u004a'), u_('\u004b'), u_('\u004c'), u_('\u004d'), u_('\u004e'), u_('\u004f'),+ u_('\u0050'), u_('\u0051'), u_('\u0052'), u_('\u0053'), u_('\u0054'), u_('\u0055'), u_('\u0056'), u_('\u0057'),+ u_('\u0058'), u_('\u0059'), u_('\u005a'), u_('\u005b'), u_('\u005c'), u_('\u005d'), u_('\u005e'), u_('\u005f'),+ u_('\u0060'), u_('\u0061'), u_('\u0062'), u_('\u0063'), u_('\u0064'), u_('\u0065'), u_('\u0066'), u_('\u0067'),+ u_('\u0068'), u_('\u0069'), u_('\u006a'), u_('\u006b'), u_('\u006c'), u_('\u006d'), u_('\u006e'), u_('\u006f'),+ u_('\u0070'), u_('\u0071'), u_('\u0072'), u_('\u0073'), u_('\u0074'), u_('\u0075'), u_('\u0076'), u_('\u0077'),+ u_('\u0078'), u_('\u0079'), u_('\u007a'), u_('\u007b'), u_('\u007c'), u_('\u007d'), u_('\u007e'), u_('\u0000'),+ u_('\u2022'), u_('\u2020'), u_('\u2021'), u_('\u2026'), u_('\u2014'), u_('\u2013'), u_('\u0192'), u_('\u2044'),+ u_('\u2039'), u_('\u203a'), u_('\u2212'), u_('\u2030'), u_('\u201e'), u_('\u201c'), u_('\u201d'), u_('\u2018'),+ u_('\u2019'), u_('\u201a'), u_('\u2122'), u_('\ufb01'), u_('\ufb02'), u_('\u0141'), u_('\u0152'), u_('\u0160'),+ u_('\u0178'), u_('\u017d'), u_('\u0131'), u_('\u0142'), u_('\u0153'), u_('\u0161'), u_('\u017e'), u_('\u0000'),+ u_('\u20ac'), u_('\u00a1'), u_('\u00a2'), u_('\u00a3'), u_('\u00a4'), u_('\u00a5'), u_('\u00a6'), u_('\u00a7'),+ u_('\u00a8'), u_('\u00a9'), u_('\u00aa'), u_('\u00ab'), u_('\u00ac'), u_('\u0000'), u_('\u00ae'), u_('\u00af'),+ u_('\u00b0'), u_('\u00b1'), u_('\u00b2'), u_('\u00b3'), u_('\u00b4'), u_('\u00b5'), u_('\u00b6'), u_('\u00b7'),+ u_('\u00b8'), u_('\u00b9'), u_('\u00ba'), u_('\u00bb'), u_('\u00bc'), u_('\u00bd'), u_('\u00be'), u_('\u00bf'),+ u_('\u00c0'), u_('\u00c1'), u_('\u00c2'), u_('\u00c3'), u_('\u00c4'), u_('\u00c5'), u_('\u00c6'), u_('\u00c7'),+ u_('\u00c8'), u_('\u00c9'), u_('\u00ca'), u_('\u00cb'), u_('\u00cc'), u_('\u00cd'), u_('\u00ce'), u_('\u00cf'),+ u_('\u00d0'), u_('\u00d1'), u_('\u00d2'), u_('\u00d3'), u_('\u00d4'), u_('\u00d5'), u_('\u00d6'), u_('\u00d7'),+ u_('\u00d8'), u_('\u00d9'), u_('\u00da'), u_('\u00db'), u_('\u00dc'), u_('\u00dd'), u_('\u00de'), u_('\u00df'),+ u_('\u00e0'), u_('\u00e1'), u_('\u00e2'), u_('\u00e3'), u_('\u00e4'), u_('\u00e5'), u_('\u00e6'), u_('\u00e7'),+ u_('\u00e8'), u_('\u00e9'), u_('\u00ea'), u_('\u00eb'), u_('\u00ec'), u_('\u00ed'), u_('\u00ee'), u_('\u00ef'),+ u_('\u00f0'), u_('\u00f1'), u_('\u00f2'), u_('\u00f3'), u_('\u00f4'), u_('\u00f5'), u_('\u00f6'), u_('\u00f7'),+ u_('\u00f8'), u_('\u00f9'), u_('\u00fa'), u_('\u00fb'), u_('\u00fc'), u_('\u00fd'), u_('\u00fe'), u_('\u00ff')+)++assert len(_pdfDocEncoding) == 256++_pdfDocEncoding_rev = {}+for i in range(256):+ char = _pdfDocEncoding[i]+ if char == u_("\u0000"):+ continue+ assert char not in _pdfDocEncoding_rev+ _pdfDocEncoding_rev[char] = idiff --git a/ext/PyPDF2/merger.py b/ext/PyPDF2/merger.pynew file mode 100755index 00000000..27702add--- /dev/null+++ b/ext/PyPDF2/merger.py@@ -0,0 +1,553 @@+# vim: sw=4:expandtab:foldmethod=marker+#+# Copyright (c) 2006, Mathieu Fenniak+# All rights reserved.+#+# Redistribution and use in source and binary forms, with or without+# modification, are permitted provided that the following conditions are+# met:+#+# * Redistributions of source code must retain the above copyright notice,+# this list of conditions and the following disclaimer.+# * Redistributions in binary form must reproduce the above copyright notice,+# this list of conditions and the following disclaimer in the documentation+# and/or other materials provided with the distribution.+# * The name of the author may not be used to endorse or promote products+# derived from this software without specific prior written permission.+#+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+# POSSIBILITY OF SUCH DAMAGE.++from .generic import *+from .utils import isString, str_+from .pdf import PdfFileReader, PdfFileWriter+from .pagerange import PageRange+from sys import version_info+if version_info < ( 3, 0 ):+ from cStringIO import StringIO+ StreamIO = StringIO+else:+ from io import BytesIO+ from io import FileIO as file+ StreamIO = BytesIO+++class _MergedPage(object):+ """+ _MergedPage is used internally by PdfFileMerger to collect necessary+ information on each page that is being merged.+ """+ def __init__(self, pagedata, src, id):+ self.src = src+ self.pagedata = pagedata+ self.out_pagedata = None+ self.id = id+++class PdfFileMerger(object):+ """+ Initializes a PdfFileMerger object. PdfFileMerger merges multiple PDFs+ into a single PDF. It can concatenate, slice, insert, or any combination+ of the above.++ See the functions :meth:`merge()<merge>` (or :meth:`append()<append>`)+ and :meth:`write()<write>` for usage information.++ :param bool strict: Determines whether user should be warned of all+ problems and also causes some correctable problems to be fatal.+ Defaults to ``True``.+ """++ def __init__(self, strict=True):+ self.inputs = []+ self.pages = []+ self.output = PdfFileWriter()+ self.bookmarks = []+ self.named_dests = []+ self.id_count = 0+ self.strict = strict++ def merge(self, position, fileobj, bookmark=None, pages=None, import_bookmarks=True):+ """+ Merges the pages from the given file into the output file at the+ specified page number.++ :param int position: The *page number* to insert this file. File will+ be inserted after the given number.++ :param fileobj: A File Object or an object that supports the standard read+ and seek methods similar to a File Object. Could also be a+ string representing a path to a PDF file.++ :param str bookmark: Optionally, you may specify a bookmark to be applied at+ the beginning of the included file by supplying the text of the bookmark.++ :param pages: can be a :ref:`Page Range <page-range>` or a ``(start, stop[, step])`` tuple+ to merge only the specified range of pages from the source+ document into the output document.++ :param bool import_bookmarks: You may prevent the source document's bookmarks+ from being imported by specifying this as ``False``.+ """++ # This parameter is passed to self.inputs.append and means+ # that the stream used was created in this method.+ my_file = False++ # If the fileobj parameter is a string, assume it is a path+ # and create a file object at that location. If it is a file,+ # copy the file's contents into a BytesIO (or StreamIO) stream object; if+ # it is a PdfFileReader, copy that reader's stream into a+ # BytesIO (or StreamIO) stream.+ # If fileobj is none of the above types, it is not modified+ decryption_key = None+ if isString(fileobj):+ fileobj = file(fileobj, 'rb')+ my_file = True+ elif isinstance(fileobj, file):+ fileobj.seek(0)+ filecontent = fileobj.read()+ fileobj = StreamIO(filecontent)+ my_file = True+ elif isinstance(fileobj, PdfFileReader):+ orig_tell = fileobj.stream.tell()+ fileobj.stream.seek(0)+ filecontent = StreamIO(fileobj.stream.read())+ fileobj.stream.seek(orig_tell) # reset the stream to its original location+ fileobj = filecontent+ if hasattr(fileobj, '_decryption_key'):+ decryption_key = fileobj._decryption_key+ my_file = True++ # Create a new PdfFileReader instance using the stream+ # (either file or BytesIO or StringIO) created above+ pdfr = PdfFileReader(fileobj, strict=self.strict)+ if decryption_key is not None:+ pdfr._decryption_key = decryption_key++ # Find the range of pages to merge.+ if pages == None:+ pages = (0, pdfr.getNumPages())+ elif isinstance(pages, PageRange):+ pages = pages.indices(pdfr.getNumPages())+ elif not isinstance(pages, tuple):+ raise TypeError('"pages" must be a tuple of (start, stop[, step])')++ srcpages = []+ if bookmark:+ bookmark = Bookmark(TextStringObject(bookmark), NumberObject(self.id_count), NameObject('/Fit'))++ outline = []+ if import_bookmarks:+ outline = pdfr.getOutlines()+ outline = self._trim_outline(pdfr, outline, pages)++ if bookmark:+ self.bookmarks += [bookmark, outline]+ else:+ self.bookmarks += outline++ dests = pdfr.namedDestinations+ dests = self._trim_dests(pdfr, dests, pages)+ self.named_dests += dests++ # Gather all the pages that are going to be merged+ for i in range(*pages):+ pg = pdfr.getPage(i)++ id = self.id_count+ self.id_count += 1++ mp = _MergedPage(pg, pdfr, id)++ srcpages.append(mp)++ self._associate_dests_to_pages(srcpages)+ self._associate_bookmarks_to_pages(srcpages)++ # Slice to insert the pages at the specified position+ self.pages[position:position] = srcpages++ # Keep track of our input files so we can close them later+ self.inputs.append((fileobj, pdfr, my_file))++ def append(self, fileobj, bookmark=None, pages=None, import_bookmarks=True):+ """+ Identical to the :meth:`merge()<merge>` method, but assumes you want to concatenate+ all pages onto the end of the file instead of specifying a position.++ :param fileobj: A File Object or an object that supports the standard read+ and seek methods similar to a File Object. Could also be a+ string representing a path to a PDF file.++ :param str bookmark: Optionally, you may specify a bookmark to be applied at+ the beginning of the included file by supplying the text of the bookmark.++ :param pages: can be a :ref:`Page Range <page-range>` or a ``(start, stop[, step])`` tuple+ to merge only the specified range of pages from the source+ document into the output document.++ :param bool import_bookmarks: You may prevent the source document's bookmarks+ from being imported by specifying this as ``False``.+ """++ self.merge(len(self.pages), fileobj, bookmark, pages, import_bookmarks)++ def write(self, fileobj):+ """+ Writes all data that has been merged to the given output file.++ :param fileobj: Output file. Can be a filename or any kind of+ file-like object.+ """+ my_file = False+ if isString(fileobj):+ fileobj = file(fileobj, 'wb')+ my_file = True++ # Add pages to the PdfFileWriter+ # The commented out line below was replaced with the two lines below it to allow PdfFileMerger to work with PyPdf 1.13+ for page in self.pages:+ self.output.addPage(page.pagedata)+ page.out_pagedata = self.output.getReference(self.output._pages.getObject()["/Kids"][-1].getObject())+ #idnum = self.output._objects.index(self.output._pages.getObject()["/Kids"][-1].getObject()) + 1+ #page.out_pagedata = IndirectObject(idnum, 0, self.output)++ # Once all pages are added, create bookmarks to point at those pages+ self._write_dests()+ self._write_bookmarks()++ # Write the output to the file+ self.output.write(fileobj)++ if my_file:+ fileobj.close()++ def close(self):+ """+ Shuts all file descriptors (input and output) and clears all memory+ usage.+ """+ self.pages = []+ for fo, pdfr, mine in self.inputs:+ if mine:+ fo.close()++ self.inputs = []+ self.output = None++ def addMetadata(self, infos):+ """+ Add custom metadata to the output.++ :param dict infos: a Python dictionary where each key is a field+ and each value is your new metadata.+ Example: ``{u'/Title': u'My title'}``+ """+ self.output.addMetadata(infos)++ def setPageLayout(self, layout):+ """+ Set the page layout++ :param str layout: The page layout to be used++ Valid layouts are:+ /NoLayout Layout explicitly not specified+ /SinglePage Show one page at a time+ /OneColumn Show one column at a time+ /TwoColumnLeft Show pages in two columns, odd-numbered pages on the left+ /TwoColumnRight Show pages in two columns, odd-numbered pages on the right+ /TwoPageLeft Show two pages at a time, odd-numbered pages on the left+ /TwoPageRight Show two pages at a time, odd-numbered pages on the right+ """+ self.output.setPageLayout(layout)++ def setPageMode(self, mode):+ """+ Set the page mode.++ :param str mode: The page mode to use.++ Valid modes are:+ /UseNone Do not show outlines or thumbnails panels+ /UseOutlines Show outlines (aka bookmarks) panel+ /UseThumbs Show page thumbnails panel+ /FullScreen Fullscreen view+ /UseOC Show Optional Content Group (OCG) panel+ /UseAttachments Show attachments panel+ """+ self.output.setPageMode(mode)++ def _trim_dests(self, pdf, dests, pages):+ """+ Removes any named destinations that are not a part of the specified+ page set.+ """+ new_dests = []+ prev_header_added = True+ for k, o in list(dests.items()):+ for j in range(*pages):+ if pdf.getPage(j).getObject() == o['/Page'].getObject():+ o[NameObject('/Page')] = o['/Page'].getObject()+ assert str_(k) == str_(o['/Title'])+ new_dests.append(o)+ break+ return new_dests++ def _trim_outline(self, pdf, outline, pages):+ """+ Removes any outline/bookmark entries that are not a part of the+ specified page set.+ """+ new_outline = []+ prev_header_added = True+ for i, o in enumerate(outline):+ if isinstance(o, list):+ sub = self._trim_outline(pdf, o, pages)+ if sub:+ if not prev_header_added:+ new_outline.append(outline[i-1])+ new_outline.append(sub)+ else:+ prev_header_added = False+ for j in range(*pages):+ if pdf.getPage(j).getObject() == o['/Page'].getObject():+ o[NameObject('/Page')] = o['/Page'].getObject()+ new_outline.append(o)+ prev_header_added = True+ break+ return new_outline++ def _write_dests(self):+ dests = self.named_dests++ for v in dests:+ pageno = None+ pdf = None+ if '/Page' in v:+ for i, p in enumerate(self.pages):+ if p.id == v['/Page']:+ v[NameObject('/Page')] = p.out_pagedata+ pageno = i+ pdf = p.src+ break+ if pageno != None:+ self.output.addNamedDestinationObject(v)++ def _write_bookmarks(self, bookmarks=None, parent=None):++ if bookmarks == None:+ bookmarks = self.bookmarks++ last_added = None+ for b in bookmarks:+ if isinstance(b, list):+ self._write_bookmarks(b, last_added)+ continue++ pageno = None+ pdf = None+ if '/Page' in b:+ for i, p in enumerate(self.pages):+ if p.id == b['/Page']:+ #b[NameObject('/Page')] = p.out_pagedata+ args = [NumberObject(p.id), NameObject(b['/Type'])]+ #nothing more to add+ #if b['/Type'] == '/Fit' or b['/Type'] == '/FitB'+ if b['/Type'] == '/FitH' or b['/Type'] == '/FitBH':+ if '/Top' in b and not isinstance(b['/Top'], NullObject):+ args.append(FloatObject(b['/Top']))+ else:+ args.append(FloatObject(0))+ del b['/Top']+ elif b['/Type'] == '/FitV' or b['/Type'] == '/FitBV':+ if '/Left' in b and not isinstance(b['/Left'], NullObject):+ args.append(FloatObject(b['/Left']))+ else:+ args.append(FloatObject(0))+ del b['/Left']+ elif b['/Type'] == '/XYZ':+ if '/Left' in b and not isinstance(b['/Left'], NullObject):+ args.append(FloatObject(b['/Left']))+ else:+ args.append(FloatObject(0))+ if '/Top' in b and not isinstance(b['/Top'], NullObject):+ args.append(FloatObject(b['/Top']))+ else:+ args.append(FloatObject(0))+ if '/Zoom' in b and not isinstance(b['/Zoom'], NullObject):+ args.append(FloatObject(b['/Zoom']))+ else:+ args.append(FloatObject(0))+ del b['/Top'], b['/Zoom'], b['/Left']+ elif b['/Type'] == '/FitR':+ if '/Left' in b and not isinstance(b['/Left'], NullObject):+ args.append(FloatObject(b['/Left']))+ else:+ args.append(FloatObject(0))+ if '/Bottom' in b and not isinstance(b['/Bottom'], NullObject):+ args.append(FloatObject(b['/Bottom']))+ else:+ args.append(FloatObject(0))+ if '/Right' in b and not isinstance(b['/Right'], NullObject):+ args.append(FloatObject(b['/Right']))+ else:+ args.append(FloatObject(0))+ if '/Top' in b and not isinstance(b['/Top'], NullObject):+ args.append(FloatObject(b['/Top']))+ else:+ args.append(FloatObject(0))+ del b['/Left'], b['/Right'], b['/Bottom'], b['/Top']++ b[NameObject('/A')] = DictionaryObject({NameObject('/S'): NameObject('/GoTo'), NameObject('/D'): ArrayObject(args)})++ pageno = i+ pdf = p.src+ break+ if pageno != None:+ del b['/Page'], b['/Type']+ last_added = self.output.addBookmarkDict(b, parent)++ def _associate_dests_to_pages(self, pages):+ for nd in self.named_dests:+ pageno = None+ np = nd['/Page']++ if isinstance(np, NumberObject):+ continue++ for p in pages:+ if np.getObject() == p.pagedata.getObject():+ pageno = p.id++ if pageno != None:+ nd[NameObject('/Page')] = NumberObject(pageno)+ else:+ raise ValueError("Unresolved named destination '%s'" % (nd['/Title'],))++ def _associate_bookmarks_to_pages(self, pages, bookmarks=None):+ if bookmarks == None:+ bookmarks = self.bookmarks++ for b in bookmarks:+ if isinstance(b, list):+ self._associate_bookmarks_to_pages(pages, b)+ continue++ pageno = None+ bp = b['/Page']++ if isinstance(bp, NumberObject):+ continue++ for p in pages:+ if bp.getObject() == p.pagedata.getObject():+ pageno = p.id++ if pageno != None:+ b[NameObject('/Page')] = NumberObject(pageno)+ else:+ raise ValueError("Unresolved bookmark '%s'" % (b['/Title'],))++ def findBookmark(self, bookmark, root=None):+ if root == None:+ root = self.bookmarks++ for i, b in enumerate(root):+ if isinstance(b, list):+ res = self.findBookmark(bookmark, b)+ if res:+ return [i] + res+ elif b == bookmark or b['/Title'] == bookmark:+ return [i]++ return None++ def addBookmark(self, title, pagenum, parent=None):+ """+ Add a bookmark to this PDF file.++ :param str title: Title to use for this bookmark.+ :param int pagenum: Page number this bookmark will point to.+ :param parent: A reference to a parent bookmark to create nested+ bookmarks.+ """+ if parent == None:+ iloc = [len(self.bookmarks)-1]+ elif isinstance(parent, list):+ iloc = parent+ else:+ iloc = self.findBookmark(parent)++ dest = Bookmark(TextStringObject(title), NumberObject(pagenum), NameObject('/FitH'), NumberObject(826))++ if parent == None:+ self.bookmarks.append(dest)+ else:+ bmparent = self.bookmarks+ for i in iloc[:-1]:+ bmparent = bmparent[i]+ npos = iloc[-1]+1+ if npos < len(bmparent) and isinstance(bmparent[npos], list):+ bmparent[npos].append(dest)+ else:+ bmparent.insert(npos, [dest])+ return dest++ def addNamedDestination(self, title, pagenum):+ """+ Add a destination to the output.++ :param str title: Title to use+ :param int pagenum: Page number this destination points at.+ """++ dest = Destination(TextStringObject(title), NumberObject(pagenum), NameObject('/FitH'), NumberObject(826))+ self.named_dests.append(dest)+++class OutlinesObject(list):+ def __init__(self, pdf, tree, parent=None):+ list.__init__(self)+ self.tree = tree+ self.pdf = pdf+ self.parent = parent++ def remove(self, index):+ obj = self[index]+ del self[index]+ self.tree.removeChild(obj)++ def add(self, title, pagenum):+ pageRef = self.pdf.getObject(self.pdf._pages)['/Kids'][pagenum]+ action = DictionaryObject()+ action.update({+ NameObject('/D') : ArrayObject([pageRef, NameObject('/FitH'), NumberObject(826)]),+ NameObject('/S') : NameObject('/GoTo')+ })+ actionRef = self.pdf._addObject(action)+ bookmark = TreeObject()++ bookmark.update({+ NameObject('/A'): actionRef,+ NameObject('/Title'): createStringObject(title),+ })++ self.pdf._addObject(bookmark)++ self.tree.addChild(bookmark)++ def removeAll(self):+ for child in [x for x in self.tree.children()]:+ self.tree.removeChild(child)+ self.pop()diff --git a/ext/PyPDF2/pagerange.py b/ext/PyPDF2/pagerange.pynew file mode 100755index 00000000..ce96ec5f--- /dev/null+++ b/ext/PyPDF2/pagerange.py@@ -0,0 +1,152 @@+#!/usr/bin/env python+"""+Representation and utils for ranges of PDF file pages.++Copyright (c) 2014, Steve Witham <[email protected]>.+All rights reserved. This software is available under a BSD license;+see https://github.com/mstamy2/PyPDF2/blob/master/LICENSE+"""++import re+from .utils import isString++_INT_RE = r"(0|-?[1-9]\d*)" # A decimal int, don't allow "-0".+PAGE_RANGE_RE = "^({int}|({int}?(:{int}?(:{int}?)?)))$".format(int=_INT_RE)+# groups: 12 34 5 6 7 8+++class ParseError(Exception):+ pass+++PAGE_RANGE_HELP = """Remember, page indices start with zero.+ Page range expression examples:+ : all pages. -1 last page.+ 22 just the 23rd page. :-1 all but the last page.+ 0:3 the first three pages. -2 second-to-last page.+ :3 the first three pages. -2: last two pages.+ 5: from the sixth page onward. -3:-1 third & second to last.+ The third, "stride" or "step" number is also recognized.+ ::2 0 2 4 ... to the end. 3:0:-1 3 2 1 but not 0.+ 1:10:2 1 3 5 7 9 2::-1 2 1 0.+ ::-1 all pages in reverse order.+"""+++class PageRange(object):+ """+ A slice-like representation of a range of page indices,+ i.e. page numbers, only starting at zero.+ The syntax is like what you would put between brackets [ ].+ The slice is one of the few Python types that can't be subclassed,+ but this class converts to and from slices, and allows similar use.+ o PageRange(str) parses a string representing a page range.+ o PageRange(slice) directly "imports" a slice.+ o to_slice() gives the equivalent slice.+ o str() and repr() allow printing.+ o indices(n) is like slice.indices(n).+ """++ def __init__(self, arg):+ """+ Initialize with either a slice -- giving the equivalent page range,+ or a PageRange object -- making a copy,+ or a string like+ "int", "[int]:[int]" or "[int]:[int]:[int]",+ where the brackets indicate optional ints.+ {page_range_help}+ Note the difference between this notation and arguments to slice():+ slice(3) means the first three pages;+ PageRange("3") means the range of only the fourth page.+ However PageRange(slice(3)) means the first three pages.+ """+ if isinstance(arg, slice):+ self._slice = arg+ return++ if isinstance(arg, PageRange):+ self._slice = arg.to_slice()+ return++ m = isString(arg) and re.match(PAGE_RANGE_RE, arg)+ if not m:+ raise ParseError(arg)+ elif m.group(2):+ # Special case: just an int means a range of one page.+ start = int(m.group(2))+ stop = start + 1 if start != -1 else None+ self._slice = slice(start, stop)+ else:+ self._slice = slice(*[int(g) if g else None+ for g in m.group(4, 6, 8)])++ # Just formatting this when there is __doc__ for __init__+ if __init__.__doc__:+ __init__.__doc__ = __init__.__doc__.format(page_range_help=PAGE_RANGE_HELP)++ @staticmethod+ def valid(input):+ """ True if input is a valid initializer for a PageRange. """+ return isinstance(input, slice) or \+ isinstance(input, PageRange) or \+ (isString(input)+ and bool(re.match(PAGE_RANGE_RE, input)))++ def to_slice(self):+ """ Return the slice equivalent of this page range. """+ return self._slice++ def __str__(self):+ """ A string like "1:2:3". """+ s = self._slice+ if s.step == None:+ if s.start != None and s.stop == s.start + 1:+ return str(s.start)++ indices = s.start, s.stop+ else:+ indices = s.start, s.stop, s.step+ return ':'.join("" if i == None else str(i) for i in indices)++ def __repr__(self):+ """ A string like "PageRange('1:2:3')". """+ return "PageRange(" + repr(str(self)) + ")"++ def indices(self, n):+ """+ n is the length of the list of pages to choose from.+ Returns arguments for range(). See help(slice.indices).+ """+ return self._slice.indices(n)+++PAGE_RANGE_ALL = PageRange(":") # The range of all pages.+++def parse_filename_page_ranges(args):+ """+ Given a list of filenames and page ranges, return a list of+ (filename, page_range) pairs.+ First arg must be a filename; other ags are filenames, page-range+ expressions, slice objects, or PageRange objects.+ A filename not followed by a page range indicates all pages of the file.+ """+ pairs = []+ pdf_filename = None+ did_page_range = False+ for arg in args + [None]:+ if PageRange.valid(arg):+ if not pdf_filename:+ raise ValueError("The first argument must be a filename, " \+ "not a page range.")++ pairs.append( (pdf_filename, PageRange(arg)) )+ did_page_range = True+ else:+ # New filename or end of list--do all of the previous file?+ if pdf_filename and not did_page_range:+ pairs.append( (pdf_filename, PAGE_RANGE_ALL) )++ pdf_filename = arg+ did_page_range = False+ return pairsdiff --git a/ext/PyPDF2/pdf.py b/ext/PyPDF2/pdf.pynew file mode 100755index 00000000..9979414f--- /dev/null+++ b/ext/PyPDF2/pdf.py@@ -0,0 +1,3004 @@+# -*- coding: utf-8 -*-+#+# vim: sw=4:expandtab:foldmethod=marker+#+# Copyright (c) 2006, Mathieu Fenniak+# Copyright (c) 2007, Ashish Kulkarni <[email protected]>+#+# All rights reserved.+#+# Redistribution and use in source and binary forms, with or without+# modification, are permitted provided that the following conditions are+# met:+#+# * Redistributions of source code must retain the above copyright notice,+# this list of conditions and the following disclaimer.+# * Redistributions in binary form must reproduce the above copyright notice,+# this list of conditions and the following disclaimer in the documentation+# and/or other materials provided with the distribution.+# * The name of the author may not be used to endorse or promote products+# derived from this software without specific prior written permission.+#+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+# POSSIBILITY OF SUCH DAMAGE.++"""+A pure-Python PDF library with an increasing number of capabilities.+See README for links to FAQ, documentation, homepage, etc.+"""++__author__ = "Mathieu Fenniak"+__author_email__ = "[email protected]"++__maintainer__ = "Phaseit, Inc."+__maintainer_email = "[email protected]"++import string+import math+import struct+import sys+import uuid+from sys import version_info+if version_info < ( 3, 0 ):+ from cStringIO import StringIO+else:+ from io import StringIO++if version_info < ( 3, 0 ):+ BytesIO = StringIO+else:+ from io import BytesIO++from . import filters+from . import utils+import warnings+import codecs+from .generic import *+from .utils import readNonWhitespace, readUntilWhitespace, ConvertFunctionsToVirtualList+from .utils import isString, b_, u_, ord_, chr_, str_, formatWarning++if version_info < ( 2, 4 ):+ from sets import ImmutableSet as frozenset++if version_info < ( 2, 5 ):+ from md5 import md5+else:+ from hashlib import md5+import uuid+++class PdfFileWriter(object):+ """+ This class supports writing PDF files out, given pages produced by another+ class (typically :class:`PdfFileReader<PdfFileReader>`).+ """+ def __init__(self):+ self._header = b_("%PDF-1.3")+ self._objects = [] # array of indirect objects++ # The root of our page tree node.+ pages = DictionaryObject()+ pages.update({+ NameObject("/Type"): NameObject("/Pages"),+ NameObject("/Count"): NumberObject(0),+ NameObject("/Kids"): ArrayObject(),+ })+ self._pages = self._addObject(pages)++ # info object+ info = DictionaryObject()+ info.update({+ NameObject("/Producer"): createStringObject(codecs.BOM_UTF16_BE + u_("PyPDF2").encode('utf-16be'))+ })+ self._info = self._addObject(info)++ # root object+ root = DictionaryObject()+ root.update({+ NameObject("/Type"): NameObject("/Catalog"),+ NameObject("/Pages"): self._pages,+ })+ self._root = None+ self._root_object = root++ def _addObject(self, obj):+ self._objects.append(obj)+ return IndirectObject(len(self._objects), 0, self)++ def getObject(self, ido):+ if ido.pdf != self:+ raise ValueError("pdf must be self")+ return self._objects[ido.idnum - 1]++ def _addPage(self, page, action):+ assert page["/Type"] == "/Page"+ page[NameObject("/Parent")] = self._pages+ page = self._addObject(page)+ pages = self.getObject(self._pages)+ action(pages["/Kids"], page)+ pages[NameObject("/Count")] = NumberObject(pages["/Count"] + 1)++ def addPage(self, page):+ """+ Adds a page to this PDF file. The page is usually acquired from a+ :class:`PdfFileReader<PdfFileReader>` instance.++ :param PageObject page: The page to add to the document. Should be+ an instance of :class:`PageObject<PyPDF2.pdf.PageObject>`+ """+ self._addPage(page, list.append)++ def insertPage(self, page, index=0):+ """+ Insert a page in this PDF file. The page is usually acquired from a+ :class:`PdfFileReader<PdfFileReader>` instance.++ :param PageObject page: The page to add to the document. This+ argument should be an instance of :class:`PageObject<pdf.PageObject>`.+ :param int index: Position at which the page will be inserted.+ """+ self._addPage(page, lambda l, p: l.insert(index, p))++ def getPage(self, pageNumber):+ """+ Retrieves a page by number from this PDF file.++ :param int pageNumber: The page number to retrieve+ (pages begin at zero)+ :return: the page at the index given by *pageNumber*+ :rtype: :class:`PageObject<pdf.PageObject>`+ """+ pages = self.getObject(self._pages)+ # XXX: crude hack+ return pages["/Kids"][pageNumber].getObject()++ def getNumPages(self):+ """+ :return: the number of pages.+ :rtype: int+ """+ pages = self.getObject(self._pages)+ return int(pages[NameObject("/Count")])++ def addBlankPage(self, width=None, height=None):+ """+ Appends a blank page to this PDF file and returns it. If no page size+ is specified, use the size of the last page.++ :param float width: The width of the new page expressed in default user+ space units.+ :param float height: The height of the new page expressed in default+ user space units.+ :return: the newly appended page+ :rtype: :class:`PageObject<PyPDF2.pdf.PageObject>`+ :raises PageSizeNotDefinedError: if width and height are not defined+ and previous page does not exist.+ """+ page = PageObject.createBlankPage(self, width, height)+ self.addPage(page)+ return page++ def insertBlankPage(self, width=None, height=None, index=0):+ """+ Inserts a blank page to this PDF file and returns it. If no page size+ is specified, use the size of the last page.++ :param float width: The width of the new page expressed in default user+ space units.+ :param float height: The height of the new page expressed in default+ user space units.+ :param int index: Position to add the page.+ :return: the newly appended page+ :rtype: :class:`PageObject<PyPDF2.pdf.PageObject>`+ :raises PageSizeNotDefinedError: if width and height are not defined+ and previous page does not exist.+ """+ if width is None or height is None and \+ (self.getNumPages() - 1) >= index:+ oldpage = self.getPage(index)+ width = oldpage.mediaBox.getWidth()+ height = oldpage.mediaBox.getHeight()+ page = PageObject.createBlankPage(self, width, height)+ self.insertPage(page, index)+ return page++ def addJS(self, javascript):+ """+ Add Javascript which will launch upon opening this PDF.++ :param str javascript: Your Javascript.++ >>> output.addJS("this.print({bUI:true,bSilent:false,bShrinkToFit:true});")+ # Example: This will launch the print window when the PDF is opened.+ """+ js = DictionaryObject()+ js.update({+ NameObject("/Type"): NameObject("/Action"),+ NameObject("/S"): NameObject("/JavaScript"),+ NameObject("/JS"): NameObject("(%s)" % javascript)+ })+ js_indirect_object = self._addObject(js)++ # We need a name for parameterized javascript in the pdf file, but it can be anything.+ js_string_name = str(uuid.uuid4())++ js_name_tree = DictionaryObject()+ js_name_tree.update({+ NameObject("/JavaScript"): DictionaryObject({+ NameObject("/Names"): ArrayObject([createStringObject(js_string_name), js_indirect_object])+ })+ })+ self._addObject(js_name_tree)++ self._root_object.update({+ NameObject("/OpenAction"): js_indirect_object,+ NameObject("/Names"): js_name_tree+ })++ def addAttachment(self, fname, fdata):+ """+ Embed a file inside the PDF.++ :param str fname: The filename to display.+ :param str fdata: The data in the file.++ Reference:+ https://www.adobe.com/content/dam/Adobe/en/devnet/acrobat/pdfs/PDF32000_2008.pdf+ Section 7.11.3+ """++ # We need 3 entries:+ # * The file's data+ # * The /Filespec entry+ # * The file's name, which goes in the Catalog+++ # The entry for the file+ """ Sample:+ 8 0 obj+ <<+ /Length 12+ /Type /EmbeddedFile+ >>+ stream+ Hello world!+ endstream+ endobj+ """+ file_entry = DecodedStreamObject()+ file_entry.setData(fdata)+ file_entry.update({+ NameObject("/Type"): NameObject("/EmbeddedFile")+ })++ # The Filespec entry+ """ Sample:+ 7 0 obj+ <<+ /Type /Filespec+ /F (hello.txt)+ /EF << /F 8 0 R >>+ >>+ """+ efEntry = DictionaryObject()+ efEntry.update({ NameObject("/F"):file_entry })++ filespec = DictionaryObject()+ filespec.update({+ NameObject("/Type"): NameObject("/Filespec"),+ NameObject("/F"): createStringObject(fname), # Perhaps also try TextStringObject+ NameObject("/EF"): efEntry+ })++ # Then create the entry for the root, as it needs a reference to the Filespec+ """ Sample:+ 1 0 obj+ <<+ /Type /Catalog+ /Outlines 2 0 R+ /Pages 3 0 R+ /Names << /EmbeddedFiles << /Names [(hello.txt) 7 0 R] >> >>+ >>+ endobj++ """+ embeddedFilesNamesDictionary = DictionaryObject()+ embeddedFilesNamesDictionary.update({+ NameObject("/Names"): ArrayObject([createStringObject(fname), filespec])+ })++ embeddedFilesDictionary = DictionaryObject()+ embeddedFilesDictionary.update({+ NameObject("/EmbeddedFiles"): embeddedFilesNamesDictionary+ })+ # Update the root+ self._root_object.update({+ NameObject("/Names"): embeddedFilesDictionary+ })++ def appendPagesFromReader(self, reader, after_page_append=None):+ """+ Copy pages from reader to writer. Includes an optional callback parameter+ which is invoked after pages are appended to the writer.++ :param reader: a PdfFileReader object from which to copy page+ annotations to this writer object. The writer's annots+ will then be updated+ :callback after_page_append (function): Callback function that is invoked after+ each page is appended to the writer. Callback signature:++ :param writer_pageref (PDF page reference): Reference to the page+ appended to the writer.+ """+ # Get page count from writer and reader+ reader_num_pages = reader.getNumPages()+ writer_num_pages = self.getNumPages()++ # Copy pages from reader to writer+ for rpagenum in range(0, reader_num_pages):+ reader_page = reader.getPage(rpagenum)+ self.addPage(reader_page)+ writer_page = self.getPage(writer_num_pages+rpagenum)+ # Trigger callback, pass writer page as parameter+ if callable(after_page_append): after_page_append(writer_page)++ def updatePageFormFieldValues(self, page, fields):+ '''+ Update the form field values for a given page from a fields dictionary.+ Copy field texts and values from fields to page.++ :param page: Page reference from PDF writer where the annotations+ and field data will be updated.+ :param fields: a Python dictionary of field names (/T) and text+ values (/V)+ '''+ # Iterate through pages, update field values+ for j in range(0, len(page['/Annots'])):+ writer_annot = page['/Annots'][j].getObject()+ for field in fields:+ if writer_annot.get('/T') == field:+ writer_annot.update({+ NameObject("/V"): TextStringObject(fields[field])+ })++ def cloneReaderDocumentRoot(self, reader):+ '''+ Copy the reader document root to the writer.++ :param reader: PdfFileReader from the document root should be copied.+ :callback after_page_append+ '''+ self._root_object = reader.trailer['/Root']++ def cloneDocumentFromReader(self, reader, after_page_append=None):+ '''+ Create a copy (clone) of a document from a PDF file reader++ :param reader: PDF file reader instance from which the clone+ should be created.+ :callback after_page_append (function): Callback function that is invoked after+ each page is appended to the writer. Signature includes a reference to the+ appended page (delegates to appendPagesFromReader). Callback signature:++ :param writer_pageref (PDF page reference): Reference to the page just+ appended to the document.+ '''+ self.cloneReaderDocumentRoot(reader)+ self.appendPagesFromReader(reader, after_page_append)++ def encrypt(self, user_pwd, owner_pwd = None, use_128bit = True):+ """+ Encrypt this PDF file with the PDF Standard encryption handler.++ :param str user_pwd: The "user password", which allows for opening+ and reading the PDF file with the restrictions provided.+ :param str owner_pwd: The "owner password", which allows for+ opening the PDF files without any restrictions. By default,+ the owner password is the same as the user password.+ :param bool use_128bit: flag as to whether to use 128bit+ encryption. When false, 40bit encryption will be used. By default,+ this flag is on.+ """+ import time, random+ if owner_pwd == None:+ owner_pwd = user_pwd+ if use_128bit:+ V = 2+ rev = 3+ keylen = int(128 / 8)+ else:+ V = 1+ rev = 2+ keylen = int(40 / 8)+ # permit everything:+ P = -1+ O = ByteStringObject(_alg33(owner_pwd, user_pwd, rev, keylen))+ ID_1 = ByteStringObject(md5(b_(repr(time.time()))).digest())+ ID_2 = ByteStringObject(md5(b_(repr(random.random()))).digest())+ self._ID = ArrayObject((ID_1, ID_2))+ if rev == 2:+ U, key = _alg34(user_pwd, O, P, ID_1)+ else:+ assert rev == 3+ U, key = _alg35(user_pwd, rev, keylen, O, P, ID_1, False)+ encrypt = DictionaryObject()+ encrypt[NameObject("/Filter")] = NameObject("/Standard")+ encrypt[NameObject("/V")] = NumberObject(V)+ if V == 2:+ encrypt[NameObject("/Length")] = NumberObject(keylen * 8)+ encrypt[NameObject("/R")] = NumberObject(rev)+ encrypt[NameObject("/O")] = ByteStringObject(O)+ encrypt[NameObject("/U")] = ByteStringObject(U)+ encrypt[NameObject("/P")] = NumberObject(P)+ self._encrypt = self._addObject(encrypt)+ self._encrypt_key = key++ def write(self, stream):+ """+ Writes the collection of pages added to this object out as a PDF file.++ :param stream: An object to write the file to. The object must support+ the write method and the tell method, similar to a file object.+ """+ if hasattr(stream, 'mode') and 'b' not in stream.mode:+ warnings.warn("File <%s> to write to is not in binary mode. It may not be written to correctly." % stream.name)+ debug = False+ import struct++ if not self._root:+ self._root = self._addObject(self._root_object)++ externalReferenceMap = {}++ # PDF objects sometimes have circular references to their /Page objects+ # inside their object tree (for example, annotations). Those will be+ # indirect references to objects that we've recreated in this PDF. To+ # address this problem, PageObject's store their original object+ # reference number, and we add it to the external reference map before+ # we sweep for indirect references. This forces self-page-referencing+ # trees to reference the correct new object location, rather than+ # copying in a new copy of the page object.+ for objIndex in range(len(self._objects)):+ obj = self._objects[objIndex]+ if isinstance(obj, PageObject) and obj.indirectRef != None:+ data = obj.indirectRef+ if data.pdf not in externalReferenceMap:+ externalReferenceMap[data.pdf] = {}+ if data.generation not in externalReferenceMap[data.pdf]:+ externalReferenceMap[data.pdf][data.generation] = {}+ externalReferenceMap[data.pdf][data.generation][data.idnum] = IndirectObject(objIndex + 1, 0, self)++ self.stack = []+ if debug: print(("ERM:", externalReferenceMap, "root:", self._root))+ self._sweepIndirectReferences(externalReferenceMap, self._root)+ del self.stack++ # Begin writing:+ object_positions = []+ stream.write(self._header + b_("\n"))+ for i in range(len(self._objects)):+ idnum = (i + 1)+ obj = self._objects[i]+ object_positions.append(stream.tell())+ stream.write(b_(str(idnum) + " 0 obj\n"))+ key = None+ if hasattr(self, "_encrypt") and idnum != self._encrypt.idnum:+ pack1 = struct.pack("<i", i + 1)[:3]+ pack2 = struct.pack("<i", 0)[:2]+ key = self._encrypt_key + pack1 + pack2+ assert len(key) == (len(self._encrypt_key) + 5)+ md5_hash = md5(key).digest()+ key = md5_hash[:min(16, len(self._encrypt_key) + 5)]+ obj.writeToStream(stream, key)+ stream.write(b_("\nendobj\n"))++ # xref table+ xref_location = stream.tell()+ stream.write(b_("xref\n"))+ stream.write(b_("0 %s\n" % (len(self._objects) + 1)))+ stream.write(b_("%010d %05d f \n" % (0, 65535)))+ for offset in object_positions:+ stream.write(b_("%010d %05d n \n" % (offset, 0)))++ # trailer+ stream.write(b_("trailer\n"))+ trailer = DictionaryObject()+ trailer.update({+ NameObject("/Size"): NumberObject(len(self._objects) + 1),+ NameObject("/Root"): self._root,+ NameObject("/Info"): self._info,+ })+ if hasattr(self, "_ID"):+ trailer[NameObject("/ID")] = self._ID+ if hasattr(self, "_encrypt"):+ trailer[NameObject("/Encrypt")] = self._encrypt+ trailer.writeToStream(stream, None)++ # eof+ stream.write(b_("\nstartxref\n%s\n%%%%EOF\n" % (xref_location)))++ def addMetadata(self, infos):+ """+ Add custom metadata to the output.++ :param dict infos: a Python dictionary where each key is a field+ and each value is your new metadata.+ """+ args = {}+ for key, value in list(infos.items()):+ args[NameObject(key)] = createStringObject(value)+ self.getObject(self._info).update(args)++ def _sweepIndirectReferences(self, externMap, data):+ debug = False+ if debug: print((data, "TYPE", data.__class__.__name__))+ if isinstance(data, DictionaryObject):+ for key, value in list(data.items()):+ origvalue = value+ value = self._sweepIndirectReferences(externMap, value)+ if isinstance(value, StreamObject):+ # a dictionary value is a stream. streams must be indirect+ # objects, so we need to change this value.+ value = self._addObject(value)+ data[key] = value+ return data+ elif isinstance(data, ArrayObject):+ for i in range(len(data)):+ value = self._sweepIndirectReferences(externMap, data[i])+ if isinstance(value, StreamObject):+ # an array value is a stream. streams must be indirect+ # objects, so we need to change this value+ value = self._addObject(value)+ data[i] = value+ return data+ elif isinstance(data, IndirectObject):+ # internal indirect references are fine+ if data.pdf == self:+ if data.idnum in self.stack:+ return data+ else:+ self.stack.append(data.idnum)+ realdata = self.getObject(data)+ self._sweepIndirectReferences(externMap, realdata)+ return data+ else:+ newobj = externMap.get(data.pdf, {}).get(data.generation, {}).get(data.idnum, None)+ if newobj == None:+ try:+ newobj = data.pdf.getObject(data)+ self._objects.append(None) # placeholder+ idnum = len(self._objects)+ newobj_ido = IndirectObject(idnum, 0, self)+ if data.pdf not in externMap:+ externMap[data.pdf] = {}+ if data.generation not in externMap[data.pdf]:+ externMap[data.pdf][data.generation] = {}+ externMap[data.pdf][data.generation][data.idnum] = newobj_ido+ newobj = self._sweepIndirectReferences(externMap, newobj)+ self._objects[idnum-1] = newobj+ return newobj_ido+ except ValueError:+ # Unable to resolve the Object, returning NullObject instead.+ return NullObject()+ return newobj+ else:+ return data++ def getReference(self, obj):+ idnum = self._objects.index(obj) + 1+ ref = IndirectObject(idnum, 0, self)+ assert ref.getObject() == obj+ return ref++ def getOutlineRoot(self):+ if '/Outlines' in self._root_object:+ outline = self._root_object['/Outlines']+ idnum = self._objects.index(outline) + 1+ outlineRef = IndirectObject(idnum, 0, self)+ assert outlineRef.getObject() == outline+ else:+ outline = TreeObject()+ outline.update({ })+ outlineRef = self._addObject(outline)+ self._root_object[NameObject('/Outlines')] = outlineRef++ return outline++ def getNamedDestRoot(self):+ if '/Names' in self._root_object and isinstance(self._root_object['/Names'], DictionaryObject):+ names = self._root_object['/Names']+ idnum = self._objects.index(names) + 1+ namesRef = IndirectObject(idnum, 0, self)+ assert namesRef.getObject() == names+ if '/Dests' in names and isinstance(names['/Dests'], DictionaryObject):+ dests = names['/Dests']+ idnum = self._objects.index(dests) + 1+ destsRef = IndirectObject(idnum, 0, self)+ assert destsRef.getObject() == dests+ if '/Names' in dests:+ nd = dests['/Names']+ else:+ nd = ArrayObject()+ dests[NameObject('/Names')] = nd+ else:+ dests = DictionaryObject()+ destsRef = self._addObject(dests)+ names[NameObject('/Dests')] = destsRef+ nd = ArrayObject()+ dests[NameObject('/Names')] = nd++ else:+ names = DictionaryObject()+ namesRef = self._addObject(names)+ self._root_object[NameObject('/Names')] = namesRef+ dests = DictionaryObject()+ destsRef = self._addObject(dests)+ names[NameObject('/Dests')] = destsRef+ nd = ArrayObject()+ dests[NameObject('/Names')] = nd++ return nd++ def addBookmarkDestination(self, dest, parent=None):+ destRef = self._addObject(dest)++ outlineRef = self.getOutlineRoot()++ if parent == None:+ parent = outlineRef++ parent = parent.getObject()+ #print parent.__class__.__name__+ parent.addChild(destRef, self)++ return destRef++ def addBookmarkDict(self, bookmark, parent=None):+ bookmarkObj = TreeObject()+ for k, v in list(bookmark.items()):+ bookmarkObj[NameObject(str(k))] = v+ bookmarkObj.update(bookmark)++ if '/A' in bookmark:+ action = DictionaryObject()+ for k, v in list(bookmark['/A'].items()):+ action[NameObject(str(k))] = v+ actionRef = self._addObject(action)+ bookmarkObj[NameObject('/A')] = actionRef++ bookmarkRef = self._addObject(bookmarkObj)++ outlineRef = self.getOutlineRoot()++ if parent == None:+ parent = outlineRef++ parent = parent.getObject()+ parent.addChild(bookmarkRef, self)++ return bookmarkRef++ def addBookmark(self, title, pagenum, parent=None, color=None, bold=False, italic=False, fit='/Fit', *args):+ """+ Add a bookmark to this PDF file.++ :param str title: Title to use for this bookmark.+ :param int pagenum: Page number this bookmark will point to.+ :param parent: A reference to a parent bookmark to create nested+ bookmarks.+ :param tuple color: Color of the bookmark as a red, green, blue tuple+ from 0.0 to 1.0+ :param bool bold: Bookmark is bold+ :param bool italic: Bookmark is italic+ :param str fit: The fit of the destination page. See+ :meth:`addLink()<addLink>` for details.+ """+ pageRef = self.getObject(self._pages)['/Kids'][pagenum]+ action = DictionaryObject()+ zoomArgs = []+ for a in args:+ if a is not None:+ zoomArgs.append(NumberObject(a))+ else:+ zoomArgs.append(NullObject())+ dest = Destination(NameObject("/"+title + " bookmark"), pageRef, NameObject(fit), *zoomArgs)+ destArray = dest.getDestArray()+ action.update({+ NameObject('/D') : destArray,+ NameObject('/S') : NameObject('/GoTo')+ })+ actionRef = self._addObject(action)++ outlineRef = self.getOutlineRoot()++ if parent == None:+ parent = outlineRef++ bookmark = TreeObject()++ bookmark.update({+ NameObject('/A'): actionRef,+ NameObject('/Title'): createStringObject(title),+ })++ if color is not None:+ bookmark.update({NameObject('/C'): ArrayObject([FloatObject(c) for c in color])})++ format = 0+ if italic:+ format += 1+ if bold:+ format += 2+ if format:+ bookmark.update({NameObject('/F'): NumberObject(format)})++ bookmarkRef = self._addObject(bookmark)++ parent = parent.getObject()+ parent.addChild(bookmarkRef, self)++ return bookmarkRef++ def addNamedDestinationObject(self, dest):+ destRef = self._addObject(dest)++ nd = self.getNamedDestRoot()+ nd.extend([dest['/Title'], destRef])++ return destRef++ def addNamedDestination(self, title, pagenum):+ pageRef = self.getObject(self._pages)['/Kids'][pagenum]+ dest = DictionaryObject()+ dest.update({+ NameObject('/D') : ArrayObject([pageRef, NameObject('/FitH'), NumberObject(826)]),+ NameObject('/S') : NameObject('/GoTo')+ })++ destRef = self._addObject(dest)+ nd = self.getNamedDestRoot()++ nd.extend([title, destRef])++ return destRef++ def removeLinks(self):+ """+ Removes links and annotations from this output.+ """+ pages = self.getObject(self._pages)['/Kids']+ for page in pages:+ pageRef = self.getObject(page)+ if "/Annots" in pageRef:+ del pageRef['/Annots']++ def removeImages(self, ignoreByteStringObject=False):+ """+ Removes images from this output.++ :param bool ignoreByteStringObject: optional parameter+ to ignore ByteString Objects.+ """+ pages = self.getObject(self._pages)['/Kids']+ for j in range(len(pages)):+ page = pages[j]+ pageRef = self.getObject(page)+ content = pageRef['/Contents'].getObject()+ if not isinstance(content, ContentStream):+ content = ContentStream(content, pageRef)++ _operations = []+ seq_graphics = False+ for operands, operator in content.operations:+ if operator == b_('Tj'):+ text = operands[0]+ if ignoreByteStringObject:+ if not isinstance(text, TextStringObject):+ operands[0] = TextStringObject()+ elif operator == b_("'"):+ text = operands[0]+ if ignoreByteStringObject:+ if not isinstance(text, TextStringObject):+ operands[0] = TextStringObject()+ elif operator == b_('"'):+ text = operands[2]+ if ignoreByteStringObject:+ if not isinstance(text, TextStringObject):+ operands[2] = TextStringObject()+ elif operator == b_("TJ"):+ for i in range(len(operands[0])):+ if ignoreByteStringObject:+ if not isinstance(operands[0][i], TextStringObject):+ operands[0][i] = TextStringObject()++ if operator == b_('q'):+ seq_graphics = True+ if operator == b_('Q'):+ seq_graphics = False+ if seq_graphics:+ if operator in [b_('cm'), b_('w'), b_('J'), b_('j'), b_('M'), b_('d'), b_('ri'), b_('i'),+ b_('gs'), b_('W'), b_('b'), b_('s'), b_('S'), b_('f'), b_('F'), b_('n'), b_('m'), b_('l'),+ b_('c'), b_('v'), b_('y'), b_('h'), b_('B'), b_('Do'), b_('sh')]:+ continue+ if operator == b_('re'):+ continue+ _operations.append((operands, operator))++ content.operations = _operations+ pageRef.__setitem__(NameObject('/Contents'), content)++ def removeText(self, ignoreByteStringObject=False):+ """+ Removes images from this output.++ :param bool ignoreByteStringObject: optional parameter+ to ignore ByteString Objects.+ """+ pages = self.getObject(self._pages)['/Kids']+ for j in range(len(pages)):+ page = pages[j]+ pageRef = self.getObject(page)+ content = pageRef['/Contents'].getObject()+ if not isinstance(content, ContentStream):+ content = ContentStream(content, pageRef)+ for operands,operator in content.operations:+ if operator == b_('Tj'):+ text = operands[0]+ if not ignoreByteStringObject:+ if isinstance(text, TextStringObject):+ operands[0] = TextStringObject()+ else:+ if isinstance(text, TextStringObject) or \+ isinstance(text, ByteStringObject):+ operands[0] = TextStringObject()+ elif operator == b_("'"):+ text = operands[0]+ if not ignoreByteStringObject:+ if isinstance(text, TextStringObject):+ operands[0] = TextStringObject()+ else:+ if isinstance(text, TextStringObject) or \+ isinstance(text, ByteStringObject):+ operands[0] = TextStringObject()+ elif operator == b_('"'):+ text = operands[2]+ if not ignoreByteStringObject:+ if isinstance(text, TextStringObject):+ operands[2] = TextStringObject()+ else:+ if isinstance(text, TextStringObject) or \+ isinstance(text, ByteStringObject):+ operands[2] = TextStringObject()+ elif operator == b_("TJ"):+ for i in range(len(operands[0])):+ if not ignoreByteStringObject:+ if isinstance(operands[0][i], TextStringObject):+ operands[0][i] = TextStringObject()+ else:+ if isinstance(operands[0][i], TextStringObject) or \+ isinstance(operands[0][i], ByteStringObject):+ operands[0][i] = TextStringObject()++ pageRef.__setitem__(NameObject('/Contents'), content)++ def addLink(self, pagenum, pagedest, rect, border=None, fit='/Fit', *args):+ """+ Add an internal link from a rectangular area to the specified page.++ :param int pagenum: index of the page on which to place the link.+ :param int pagedest: index of the page to which the link should go.+ :param rect: :class:`RectangleObject<PyPDF2.generic.RectangleObject>` or array of four+ integers specifying the clickable rectangular area+ ``[xLL, yLL, xUR, yUR]``, or string in the form ``"[ xLL yLL xUR yUR ]"``.+ :param border: if provided, an array describing border-drawing+ properties. See the PDF spec for details. No border will be+ drawn if this argument is omitted.+ :param str fit: Page fit or 'zoom' option (see below). Additional arguments may need+ to be supplied. Passing ``None`` will be read as a null value for that coordinate.++ Valid zoom arguments (see Table 8.2 of the PDF 1.7 reference for details):+ /Fit No additional arguments+ /XYZ [left] [top] [zoomFactor]+ /FitH [top]+ /FitV [left]+ /FitR [left] [bottom] [right] [top]+ /FitB No additional arguments+ /FitBH [top]+ /FitBV [left]+ """++ pageLink = self.getObject(self._pages)['/Kids'][pagenum]+ pageDest = self.getObject(self._pages)['/Kids'][pagedest] #TODO: switch for external link+ pageRef = self.getObject(pageLink)++ if border is not None:+ borderArr = [NameObject(n) for n in border[:3]]+ if len(border) == 4:+ dashPattern = ArrayObject([NameObject(n) for n in border[3]])+ borderArr.append(dashPattern)+ else:+ borderArr = [NumberObject(0)] * 3++ if isString(rect):+ rect = NameObject(rect)+ elif isinstance(rect, RectangleObject):+ pass+ else:+ rect = RectangleObject(rect)++ zoomArgs = []+ for a in args:+ if a is not None:+ zoomArgs.append(NumberObject(a))+ else:+ zoomArgs.append(NullObject())+ dest = Destination(NameObject("/LinkName"), pageDest, NameObject(fit), *zoomArgs) #TODO: create a better name for the link+ destArray = dest.getDestArray()++ lnk = DictionaryObject()+ lnk.update({+ NameObject('/Type'): NameObject('/Annot'),+ NameObject('/Subtype'): NameObject('/Link'),+ NameObject('/P'): pageLink,+ NameObject('/Rect'): rect,+ NameObject('/Border'): ArrayObject(borderArr),+ NameObject('/Dest'): destArray+ })+ lnkRef = self._addObject(lnk)++ if "/Annots" in pageRef:+ pageRef['/Annots'].append(lnkRef)+ else:+ pageRef[NameObject('/Annots')] = ArrayObject([lnkRef])++ _valid_layouts = ['/NoLayout', '/SinglePage', '/OneColumn', '/TwoColumnLeft', '/TwoColumnRight', '/TwoPageLeft', '/TwoPageRight']++ def getPageLayout(self):+ """+ Get the page layout.+ See :meth:`setPageLayout()<PdfFileWriter.setPageLayout>` for a description of valid layouts.++ :return: Page layout currently being used.+ :rtype: str, None if not specified+ """+ try:+ return self._root_object['/PageLayout']+ except KeyError:+ return None++ def setPageLayout(self, layout):+ """+ Set the page layout++ :param str layout: The page layout to be used++ Valid layouts are:+ /NoLayout Layout explicitly not specified+ /SinglePage Show one page at a time+ /OneColumn Show one column at a time+ /TwoColumnLeft Show pages in two columns, odd-numbered pages on the left+ /TwoColumnRight Show pages in two columns, odd-numbered pages on the right+ /TwoPageLeft Show two pages at a time, odd-numbered pages on the left+ /TwoPageRight Show two pages at a time, odd-numbered pages on the right+ """+ if not isinstance(layout, NameObject):+ if layout not in self._valid_layouts:+ warnings.warn("Layout should be one of: {}".format(', '.join(self._valid_layouts)))+ layout = NameObject(layout)+ self._root_object.update({NameObject('/PageLayout'): layout})++ pageLayout = property(getPageLayout, setPageLayout)+ """Read and write property accessing the :meth:`getPageLayout()<PdfFileWriter.getPageLayout>`+ and :meth:`setPageLayout()<PdfFileWriter.setPageLayout>` methods."""++ _valid_modes = ['/UseNone', '/UseOutlines', '/UseThumbs', '/FullScreen', '/UseOC', '/UseAttachments']++ def getPageMode(self):+ """+ Get the page mode.+ See :meth:`setPageMode()<PdfFileWriter.setPageMode>` for a description+ of valid modes.++ :return: Page mode currently being used.+ :rtype: str, None if not specified+ """+ try:+ return self._root_object['/PageMode']+ except KeyError:+ return None++ def setPageMode(self, mode):+ """+ Set the page mode.++ :param str mode: The page mode to use.++ Valid modes are:+ /UseNone Do not show outlines or thumbnails panels+ /UseOutlines Show outlines (aka bookmarks) panel+ /UseThumbs Show page thumbnails panel+ /FullScreen Fullscreen view+ /UseOC Show Optional Content Group (OCG) panel+ /UseAttachments Show attachments panel+ """+ if not isinstance(mode, NameObject):+ if mode not in self._valid_modes:+ warnings.warn("Mode should be one of: {}".format(', '.join(self._valid_modes)))+ mode = NameObject(mode)+ self._root_object.update({NameObject('/PageMode'): mode})++ pageMode = property(getPageMode, setPageMode)+ """Read and write property accessing the :meth:`getPageMode()<PdfFileWriter.getPageMode>`+ and :meth:`setPageMode()<PdfFileWriter.setPageMode>` methods."""+++class PdfFileReader(object):+ """+ Initializes a PdfFileReader object. This operation can take some time, as+ the PDF stream's cross-reference tables are read into memory.++ :param stream: A File object or an object that supports the standard read+ and seek methods similar to a File object. Could also be a+ string representing a path to a PDF file.+ :param bool strict: Determines whether user should be warned of all+ problems and also causes some correctable problems to be fatal.+ Defaults to ``True``.+ :param warndest: Destination for logging warnings (defaults to+ ``sys.stderr``).+ :param bool overwriteWarnings: Determines whether to override Python's+ ``warnings.py`` module with a custom implementation (defaults to+ ``True``).+ """+ def __init__(self, stream, strict=True, warndest = None, overwriteWarnings = True):+ if overwriteWarnings:+ # have to dynamically override the default showwarning since there are no+ # public methods that specify the 'file' parameter+ def _showwarning(message, category, filename, lineno, file=warndest, line=None):+ if file is None:+ file = sys.stderr+ try:+ file.write(formatWarning(message, category, filename, lineno, line))+ except IOError:+ pass+ warnings.showwarning = _showwarning+ self.strict = strict+ self.flattenedPages = None+ self.resolvedObjects = {}+ self.xrefIndex = 0+ self._pageId2Num = None # map page IndirectRef number to Page Number+ if hasattr(stream, 'mode') and 'b' not in stream.mode:+ warnings.warn("PdfFileReader stream/file object is not in binary mode. It may not be read correctly.", utils.PdfReadWarning)+ if isString(stream):+ fileobj = open(stream, 'rb')+ stream = BytesIO(b_(fileobj.read()))+ fileobj.close()+ self.read(stream)+ self.stream = stream++ self._override_encryption = False++ def getDocumentInfo(self):+ """+ Retrieves the PDF file's document information dictionary, if it exists.+ Note that some PDF files use metadata streams instead of docinfo+ dictionaries, and these metadata streams will not be accessed by this+ function.++ :return: the document information of this PDF file+ :rtype: :class:`DocumentInformation<pdf.DocumentInformation>` or ``None`` if none exists.+ """+ if "/Info" not in self.trailer:+ return None+ obj = self.trailer['/Info']+ retval = DocumentInformation()+ retval.update(obj)+ return retval++ documentInfo = property(lambda self: self.getDocumentInfo(), None, None)+ """Read-only property that accesses the :meth:`getDocumentInfo()<PdfFileReader.getDocumentInfo>` function."""++ def getXmpMetadata(self):+ """+ Retrieves XMP (Extensible Metadata Platform) data from the PDF document+ root.++ :return: a :class:`XmpInformation<xmp.XmpInformation>`+ instance that can be used to access XMP metadata from the document.+ :rtype: :class:`XmpInformation<xmp.XmpInformation>` or+ ``None`` if no metadata was found on the document root.+ """+ try:+ self._override_encryption = True+ return self.trailer["/Root"].getXmpMetadata()+ finally:+ self._override_encryption = False++ xmpMetadata = property(lambda self: self.getXmpMetadata(), None, None)+ """+ Read-only property that accesses the+ :meth:`getXmpMetadata()<PdfFileReader.getXmpMetadata>` function.+ """++ def getNumPages(self):+ """+ Calculates the number of pages in this PDF file.++ :return: number of pages+ :rtype: int+ :raises PdfReadError: if file is encrypted and restrictions prevent+ this action.+ """++ # Flattened pages will not work on an Encrypted PDF;+ # the PDF file's page count is used in this case. Otherwise,+ # the original method (flattened page count) is used.+ if self.isEncrypted:+ try:+ self._override_encryption = True+ self.decrypt('')+ return self.trailer["/Root"]["/Pages"]["/Count"]+ except:+ raise utils.PdfReadError("File has not been decrypted")+ finally:+ self._override_encryption = False+ else:+ if self.flattenedPages == None:+ self._flatten()+ return len(self.flattenedPages)++ numPages = property(lambda self: self.getNumPages(), None, None)+ """+ Read-only property that accesses the+ :meth:`getNumPages()<PdfFileReader.getNumPages>` function.+ """++ def getPage(self, pageNumber):+ """+ Retrieves a page by number from this PDF file.++ :param int pageNumber: The page number to retrieve+ (pages begin at zero)+ :return: a :class:`PageObject<pdf.PageObject>` instance.+ :rtype: :class:`PageObject<pdf.PageObject>`+ """+ ## ensure that we're not trying to access an encrypted PDF+ #assert not self.trailer.has_key("/Encrypt")+ if self.flattenedPages == None:+ self._flatten()+ return self.flattenedPages[pageNumber]++ namedDestinations = property(lambda self:+ self.getNamedDestinations(), None, None)+ """+ Read-only property that accesses the+ :meth:`getNamedDestinations()<PdfFileReader.getNamedDestinations>` function.+ """++ # A select group of relevant field attributes. For the complete list,+ # see section 8.6.2 of the PDF 1.7 reference.++ def getFields(self, tree = None, retval = None, fileobj = None):+ """+ Extracts field data if this PDF contains interactive form fields.+ The *tree* and *retval* parameters are for recursive use.++ :param fileobj: A file object (usually a text file) to write+ a report to on all interactive form fields found.+ :return: A dictionary where each key is a field name, and each+ value is a :class:`Field<PyPDF2.generic.Field>` object. By+ default, the mapping name is used for keys.+ :rtype: dict, or ``None`` if form data could not be located.+ """+ fieldAttributes = {"/FT" : "Field Type", "/Parent" : "Parent",+ "/T" : "Field Name", "/TU" : "Alternate Field Name",+ "/TM" : "Mapping Name", "/Ff" : "Field Flags",+ "/V" : "Value", "/DV" : "Default Value"}+ if retval == None:+ retval = {}+ catalog = self.trailer["/Root"]+ # get the AcroForm tree+ if "/AcroForm" in catalog:+ tree = catalog["/AcroForm"]+ else:+ return None+ if tree == None:+ return retval++ self._checkKids(tree, retval, fileobj)+ for attr in fieldAttributes:+ if attr in tree:+ # Tree is a field+ self._buildField(tree, retval, fileobj, fieldAttributes)+ break++ if "/Fields" in tree:+ fields = tree["/Fields"]+ for f in fields:+ field = f.getObject()+ self._buildField(field, retval, fileobj, fieldAttributes)++ return retval++ def _buildField(self, field, retval, fileobj, fieldAttributes):+ self._checkKids(field, retval, fileobj)+ try:+ key = field["/TM"]+ except KeyError:+ try:+ key = field["/T"]+ except KeyError:+ # Ignore no-name field for now+ return+ if fileobj:+ self._writeField(fileobj, field, fieldAttributes)+ fileobj.write("\n")+ retval[key] = Field(field)++ def _checkKids(self, tree, retval, fileobj):+ if "/Kids" in tree:+ # recurse down the tree+ for kid in tree["/Kids"]:+ self.getFields(kid.getObject(), retval, fileobj)++ def _writeField(self, fileobj, field, fieldAttributes):+ order = ["/TM", "/T", "/FT", "/Parent", "/TU", "/Ff", "/V", "/DV"]+ for attr in order:+ attrName = fieldAttributes[attr]+ try:+ if attr == "/FT":+ # Make the field type value more clear+ types = {"/Btn":"Button", "/Tx":"Text", "/Ch": "Choice",+ "/Sig":"Signature"}+ if field[attr] in types:+ fileobj.write(attrName + ": " + types[field[attr]] + "\n")+ elif attr == "/Parent":+ # Let's just write the name of the parent+ try:+ name = field["/Parent"]["/TM"]+ except KeyError:+ name = field["/Parent"]["/T"]+ fileobj.write(attrName + ": " + name + "\n")+ else:+ fileobj.write(attrName + ": " + str(field[attr]) + "\n")+ except KeyError:+ # Field attribute is N/A or unknown, so don't write anything+ pass++ def getFormTextFields(self):+ ''' Retrieves form fields from the document with textual data (inputs, dropdowns)+ '''+ # Retrieve document form fields+ formfields = self.getFields()+ return dict(+ (formfields[field]['/T'], formfields[field].get('/V')) for field in formfields \+ if formfields[field].get('/FT') == '/Tx'+ )++ def getNamedDestinations(self, tree=None, retval=None):+ """+ Retrieves the named destinations present in the document.++ :return: a dictionary which maps names to+ :class:`Destinations<PyPDF2.generic.Destination>`.+ :rtype: dict+ """+ if retval == None:+ retval = {}+ catalog = self.trailer["/Root"]++ # get the name tree+ if "/Dests" in catalog:+ tree = catalog["/Dests"]+ elif "/Names" in catalog:+ names = catalog['/Names']+ if "/Dests" in names:+ tree = names['/Dests']++ if tree == None:+ return retval++ if "/Kids" in tree:+ # recurse down the tree+ for kid in tree["/Kids"]:+ self.getNamedDestinations(kid.getObject(), retval)++ if "/Names" in tree:+ names = tree["/Names"]+ for i in range(0, len(names), 2):+ key = names[i].getObject()+ val = names[i+1].getObject()+ if isinstance(val, DictionaryObject) and '/D' in val:+ val = val['/D']+ dest = self._buildDestination(key, val)+ if dest != None:+ retval[key] = dest++ return retval++ outlines = property(lambda self: self.getOutlines(), None, None)+ """+ Read-only property that accesses the+ :meth:`getOutlines()<PdfFileReader.getOutlines>` function.+ """++ def getOutlines(self, node=None, outlines=None):+ """+ Retrieves the document outline present in the document.++ :return: a nested list of :class:`Destinations<PyPDF2.generic.Destination>`.+ """+ if outlines == None:+ outlines = []+ catalog = self.trailer["/Root"]++ # get the outline dictionary and named destinations+ if "/Outlines" in catalog:+ try:+ lines = catalog["/Outlines"]+ except utils.PdfReadError:+ # this occurs if the /Outlines object reference is incorrect+ # for an example of such a file, see https://unglueit-files.s3.amazonaws.com/ebf/7552c42e9280b4476e59e77acc0bc812.pdf+ # so continue to load the file without the Bookmarks+ return outlines++ if "/First" in lines:+ node = lines["/First"]+ self._namedDests = self.getNamedDestinations()++ if node == None:+ return outlines++ # see if there are any more outlines+ while True:+ outline = self._buildOutline(node)+ if outline:+ outlines.append(outline)++ # check for sub-outlines+ if "/First" in node:+ subOutlines = []+ self.getOutlines(node["/First"], subOutlines)+ if subOutlines:+ outlines.append(subOutlines)++ if "/Next" not in node:+ break+ node = node["/Next"]++ return outlines++ def _getPageNumberByIndirect(self, indirectRef):+ """Generate _pageId2Num"""+ if self._pageId2Num is None:+ id2num = {}+ for i, x in enumerate(self.pages):+ id2num[x.indirectRef.idnum] = i+ self._pageId2Num = id2num++ if isinstance(indirectRef, int):+ idnum = indirectRef+ else:+ idnum = indirectRef.idnum++ ret = self._pageId2Num.get(idnum, -1)+ return ret++ def getPageNumber(self, page):+ """+ Retrieve page number of a given PageObject++ :param PageObject page: The page to get page number. Should be+ an instance of :class:`PageObject<PyPDF2.pdf.PageObject>`+ :return: the page number or -1 if page not found+ :rtype: int+ """+ indirectRef = page.indirectRef+ ret = self._getPageNumberByIndirect(indirectRef)+ return ret++ def getDestinationPageNumber(self, destination):+ """+ Retrieve page number of a given Destination object++ :param Destination destination: The destination to get page number.+ Should be an instance of+ :class:`Destination<PyPDF2.pdf.Destination>`+ :return: the page number or -1 if page not found+ :rtype: int+ """+ indirectRef = destination.page+ ret = self._getPageNumberByIndirect(indirectRef)+ return ret++ def _buildDestination(self, title, array):+ page, typ = array[0:2]+ array = array[2:]+ return Destination(title, page, typ, *array)++ def _buildOutline(self, node):+ dest, title, outline = None, None, None++ if "/A" in node and "/Title" in node:+ # Action, section 8.5 (only type GoTo supported)+ title = node["/Title"]+ action = node["/A"]+ if action["/S"] == "/GoTo":+ dest = action["/D"]+ elif "/Dest" in node and "/Title" in node:+ # Destination, section 8.2.1+ title = node["/Title"]+ dest = node["/Dest"]++ # if destination found, then create outline+ if dest:+ if isinstance(dest, ArrayObject):+ outline = self._buildDestination(title, dest)+ elif isString(dest) and dest in self._namedDests:+ outline = self._namedDests[dest]+ outline[NameObject("/Title")] = title+ else:+ raise utils.PdfReadError("Unexpected destination %r" % dest)+ return outline++ pages = property(lambda self: ConvertFunctionsToVirtualList(self.getNumPages, self.getPage),+ None, None)+ """+ Read-only property that emulates a list based upon the+ :meth:`getNumPages()<PdfFileReader.getNumPages>` and+ :meth:`getPage()<PdfFileReader.getPage>` methods.+ """++ def getPageLayout(self):+ """+ Get the page layout.+ See :meth:`setPageLayout()<PdfFileWriter.setPageLayout>`+ for a description of valid layouts.++ :return: Page layout currently being used.+ :rtype: ``str``, ``None`` if not specified+ """+ try:+ return self.trailer['/Root']['/PageLayout']+ except KeyError:+ return None++ pageLayout = property(getPageLayout)+ """Read-only property accessing the+ :meth:`getPageLayout()<PdfFileReader.getPageLayout>` method."""++ def getPageMode(self):+ """+ Get the page mode.+ See :meth:`setPageMode()<PdfFileWriter.setPageMode>`+ for a description of valid modes.++ :return: Page mode currently being used.+ :rtype: ``str``, ``None`` if not specified+ """+ try:+ return self.trailer['/Root']['/PageMode']+ except KeyError:+ return None++ pageMode = property(getPageMode)+ """Read-only property accessing the+ :meth:`getPageMode()<PdfFileReader.getPageMode>` method."""++ def _flatten(self, pages=None, inherit=None, indirectRef=None):+ inheritablePageAttributes = (+ NameObject("/Resources"), NameObject("/MediaBox"),+ NameObject("/CropBox"), NameObject("/Rotate")+ )+ if inherit == None:+ inherit = dict()+ if pages == None:+ self.flattenedPages = []+ catalog = self.trailer["/Root"].getObject()+ pages = catalog["/Pages"].getObject()++ t = "/Pages"+ if "/Type" in pages:+ t = pages["/Type"]++ if t == "/Pages":+ for attr in inheritablePageAttributes:+ if attr in pages:+ inherit[attr] = pages[attr]+ for page in pages["/Kids"]:+ addt = {}+ if isinstance(page, IndirectObject):+ addt["indirectRef"] = page+ self._flatten(page.getObject(), inherit, **addt)+ elif t == "/Page":+ for attr, value in list(inherit.items()):+ # if the page has it's own value, it does not inherit the+ # parent's value:+ if attr not in pages:+ pages[attr] = value+ pageObj = PageObject(self, indirectRef)+ pageObj.update(pages)+ self.flattenedPages.append(pageObj)++ def _getObjectFromStream(self, indirectReference):+ # indirect reference to object in object stream+ # read the entire object stream into memory+ debug = False+ stmnum, idx = self.xref_objStm[indirectReference.idnum]+ if debug: print(("Here1: %s %s"%(stmnum, idx)))+ objStm = IndirectObject(stmnum, 0, self).getObject()+ if debug: print(("Here2: objStm=%s.. stmnum=%s data=%s"%(objStm, stmnum, objStm.getData())))+ # This is an xref to a stream, so its type better be a stream+ assert objStm['/Type'] == '/ObjStm'+ # /N is the number of indirect objects in the stream+ assert idx < objStm['/N']+ streamData = BytesIO(b_(objStm.getData()))+ for i in range(objStm['/N']):+ readNonWhitespace(streamData)+ streamData.seek(-1, 1)+ objnum = NumberObject.readFromStream(streamData)+ readNonWhitespace(streamData)+ streamData.seek(-1, 1)+ offset = NumberObject.readFromStream(streamData)+ readNonWhitespace(streamData)+ streamData.seek(-1, 1)+ if objnum != indirectReference.idnum:+ # We're only interested in one object+ continue+ if self.strict and idx != i:+ raise utils.PdfReadError("Object is in wrong index.")+ streamData.seek(objStm['/First']+offset, 0)+ if debug:+ pos = streamData.tell()+ streamData.seek(0, 0)+ lines = streamData.readlines()+ for i in range(0, len(lines)):+ print((lines[i]))+ streamData.seek(pos, 0)+ try:+ obj = readObject(streamData, self)+ except utils.PdfStreamError as e:+ # Stream object cannot be read. Normally, a critical error, but+ # Adobe Reader doesn't complain, so continue (in strict mode?)+ e = sys.exc_info()[1]+ warnings.warn("Invalid stream (index %d) within object %d %d: %s" % \+ (i, indirectReference.idnum, indirectReference.generation, e), utils.PdfReadWarning)++ if self.strict:+ raise utils.PdfReadError("Can't read object stream: %s"%e)+ # Replace with null. Hopefully it's nothing important.+ obj = NullObject()+ return obj++ if self.strict: raise utils.PdfReadError("This is a fatal error in strict mode.")+ return NullObject()++ def getObject(self, indirectReference):+ debug = False+ if debug: print(("looking at:", indirectReference.idnum, indirectReference.generation))+ retval = self.cacheGetIndirectObject(indirectReference.generation,+ indirectReference.idnum)+ if retval != None:+ return retval+ if indirectReference.generation == 0 and \+ indirectReference.idnum in self.xref_objStm:+ retval = self._getObjectFromStream(indirectReference)+ elif indirectReference.generation in self.xref and \+ indirectReference.idnum in self.xref[indirectReference.generation]:+ start = self.xref[indirectReference.generation][indirectReference.idnum]+ if debug: print((" Uncompressed Object", indirectReference.idnum, indirectReference.generation, ":", start))+ self.stream.seek(start, 0)+ idnum, generation = self.readObjectHeader(self.stream)+ if idnum != indirectReference.idnum and self.xrefIndex:+ # Xref table probably had bad indexes due to not being zero-indexed+ if self.strict:+ raise utils.PdfReadError("Expected object ID (%d %d) does not match actual (%d %d); xref table not zero-indexed." \+ % (indirectReference.idnum, indirectReference.generation, idnum, generation))+ else: pass # xref table is corrected in non-strict mode+ elif idnum != indirectReference.idnum:+ # some other problem+ raise utils.PdfReadError("Expected object ID (%d %d) does not match actual (%d %d)." \+ % (indirectReference.idnum, indirectReference.generation, idnum, generation))+ assert generation == indirectReference.generation+ retval = readObject(self.stream, self)++ # override encryption is used for the /Encrypt dictionary+ if not self._override_encryption and self.isEncrypted:+ # if we don't have the encryption key:+ if not hasattr(self, '_decryption_key'):+ raise utils.PdfReadError("file has not been decrypted")+ # otherwise, decrypt here...+ import struct+ pack1 = struct.pack("<i", indirectReference.idnum)[:3]+ pack2 = struct.pack("<i", indirectReference.generation)[:2]+ key = self._decryption_key + pack1 + pack2+ assert len(key) == (len(self._decryption_key) + 5)+ md5_hash = md5(key).digest()+ key = md5_hash[:min(16, len(self._decryption_key) + 5)]+ retval = self._decryptObject(retval, key)+ else:+ warnings.warn("Object %d %d not defined."%(indirectReference.idnum,+ indirectReference.generation), utils.PdfReadWarning)+ #if self.strict:+ raise utils.PdfReadError("Could not find object.")+ self.cacheIndirectObject(indirectReference.generation,+ indirectReference.idnum, retval)+ return retval++ def _decryptObject(self, obj, key):+ if isinstance(obj, ByteStringObject) or isinstance(obj, TextStringObject):+ obj = createStringObject(utils.RC4_encrypt(key, obj.original_bytes))+ elif isinstance(obj, StreamObject):+ obj._data = utils.RC4_encrypt(key, obj._data)+ elif isinstance(obj, DictionaryObject):+ for dictkey, value in list(obj.items()):+ obj[dictkey] = self._decryptObject(value, key)+ elif isinstance(obj, ArrayObject):+ for i in range(len(obj)):+ obj[i] = self._decryptObject(obj[i], key)+ return obj++ def readObjectHeader(self, stream):+ # Should never be necessary to read out whitespace, since the+ # cross-reference table should put us in the right spot to read the+ # object header. In reality... some files have stupid cross reference+ # tables that are off by whitespace bytes.+ extra = False+ utils.skipOverComment(stream)+ extra |= utils.skipOverWhitespace(stream); stream.seek(-1, 1)+ idnum = readUntilWhitespace(stream)+ extra |= utils.skipOverWhitespace(stream); stream.seek(-1, 1)+ generation = readUntilWhitespace(stream)+ obj = stream.read(3)+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ if (extra and self.strict):+ #not a fatal error+ warnings.warn("Superfluous whitespace found in object header %s %s" % \+ (idnum, generation), utils.PdfReadWarning)+ return int(idnum), int(generation)++ def cacheGetIndirectObject(self, generation, idnum):+ debug = False+ out = self.resolvedObjects.get((generation, idnum))+ if debug and out: print(("cache hit: %d %d"%(idnum, generation)))+ elif debug: print(("cache miss: %d %d"%(idnum, generation)))+ return out++ def cacheIndirectObject(self, generation, idnum, obj):+ # return None # Sometimes we want to turn off cache for debugging.+ if (generation, idnum) in self.resolvedObjects:+ msg = "Overwriting cache for %s %s"%(generation, idnum)+ if self.strict: raise utils.PdfReadError(msg)+ else: warnings.warn(msg)+ self.resolvedObjects[(generation, idnum)] = obj+ return obj++ def read(self, stream):+ debug = False+ if debug: print(">>read", stream)+ # start at the end:+ stream.seek(-1, 2)+ if not stream.tell():+ raise utils.PdfReadError('Cannot read an empty file')+ last1K = stream.tell() - 1024 + 1 # offset of last 1024 bytes of stream+ line = b_('')+ while line[:5] != b_("%%EOF"):+ if stream.tell() < last1K:+ raise utils.PdfReadError("EOF marker not found")+ line = self.readNextEndLine(stream)+ if debug: print(" line:",line)++ # find startxref entry - the location of the xref table+ line = self.readNextEndLine(stream)+ try:+ startxref = int(line)+ except ValueError:+ # 'startxref' may be on the same line as the location+ if not line.startswith(b_("startxref")):+ raise utils.PdfReadError("startxref not found")+ startxref = int(line[9:].strip())+ warnings.warn("startxref on same line as offset")+ else:+ line = self.readNextEndLine(stream)+ if line[:9] != b_("startxref"):+ raise utils.PdfReadError("startxref not found")++ # read all cross reference tables and their trailers+ self.xref = {}+ self.xref_objStm = {}+ self.trailer = DictionaryObject()+ while True:+ # load the xref table+ stream.seek(startxref, 0)+ x = stream.read(1)+ if x == b_("x"):+ # standard cross-reference table+ ref = stream.read(4)+ if ref[:3] != b_("ref"):+ raise utils.PdfReadError("xref table read error")+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ firsttime = True; # check if the first time looking at the xref table+ while True:+ num = readObject(stream, self)+ if firsttime and num != 0:+ self.xrefIndex = num+ if self.strict:+ warnings.warn("Xref table not zero-indexed. ID numbers for objects will be corrected.", utils.PdfReadWarning)+ #if table not zero indexed, could be due to error from when PDF was created+ #which will lead to mismatched indices later on, only warned and corrected if self.strict=True+ firsttime = False+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ size = readObject(stream, self)+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ cnt = 0+ while cnt < size:+ line = stream.read(20)++ # It's very clear in section 3.4.3 of the PDF spec+ # that all cross-reference table lines are a fixed+ # 20 bytes (as of PDF 1.7). However, some files have+ # 21-byte entries (or more) due to the use of \r\n+ # (CRLF) EOL's. Detect that case, and adjust the line+ # until it does not begin with a \r (CR) or \n (LF).+ while line[0] in b_("\x0D\x0A"):+ stream.seek(-20 + 1, 1)+ line = stream.read(20)++ # On the other hand, some malformed PDF files+ # use a single character EOL without a preceeding+ # space. Detect that case, and seek the stream+ # back one character. (0-9 means we've bled into+ # the next xref entry, t means we've bled into the+ # text "trailer"):+ if line[-1] in b_("0123456789t"):+ stream.seek(-1, 1)++ offset, generation = line[:16].split(b_(" "))+ offset, generation = int(offset), int(generation)+ if generation not in self.xref:+ self.xref[generation] = {}+ if num in self.xref[generation]:+ # It really seems like we should allow the last+ # xref table in the file to override previous+ # ones. Since we read the file backwards, assume+ # any existing key is already set correctly.+ pass+ else:+ self.xref[generation][num] = offset+ cnt += 1+ num += 1+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ trailertag = stream.read(7)+ if trailertag != b_("trailer"):+ # more xrefs!+ stream.seek(-7, 1)+ else:+ break+ readNonWhitespace(stream)+ stream.seek(-1, 1)+ newTrailer = readObject(stream, self)+ for key, value in list(newTrailer.items()):+ if key not in self.trailer:+ self.trailer[key] = value+ if "/Prev" in newTrailer:+ startxref = newTrailer["/Prev"]+ else:+ break+ elif x.isdigit():+ # PDF 1.5+ Cross-Reference Stream+ stream.seek(-1, 1)+ idnum, generation = self.readObjectHeader(stream)+ xrefstream = readObject(stream, self)+ assert xrefstream["/Type"] == "/XRef"+ self.cacheIndirectObject(generation, idnum, xrefstream)+ streamData = BytesIO(b_(xrefstream.getData()))+ # Index pairs specify the subsections in the dictionary. If+ # none create one subsection that spans everything.+ idx_pairs = xrefstream.get("/Index", [0, xrefstream.get("/Size")])+ if debug: print(("read idx_pairs=%s"%list(self._pairs(idx_pairs))))+ entrySizes = xrefstream.get("/W")+ assert len(entrySizes) >= 3+ if self.strict and len(entrySizes) > 3:+ raise utils.PdfReadError("Too many entry sizes: %s" %entrySizes)++ def getEntry(i):+ # Reads the correct number of bytes for each entry. See the+ # discussion of the W parameter in PDF spec table 17.+ if entrySizes[i] > 0:+ d = streamData.read(entrySizes[i])+ return convertToInt(d, entrySizes[i])++ # PDF Spec Table 17: A value of zero for an element in the+ # W array indicates...the default value shall be used+ if i == 0: return 1 # First value defaults to 1+ else: return 0++ def used_before(num, generation):+ # We move backwards through the xrefs, don't replace any.+ return num in self.xref.get(generation, []) or \+ num in self.xref_objStm++ # Iterate through each subsection+ last_end = 0+ for start, size in self._pairs(idx_pairs):+ # The subsections must increase+ assert start >= last_end+ last_end = start + size+ for num in range(start, start+size):+ # The first entry is the type+ xref_type = getEntry(0)+ # The rest of the elements depend on the xref_type+ if xref_type == 0:+ # linked list of free objects+ next_free_object = getEntry(1)+ next_generation = getEntry(2)+ elif xref_type == 1:+ # objects that are in use but are not compressed+ byte_offset = getEntry(1)+ generation = getEntry(2)+ if generation not in self.xref:+ self.xref[generation] = {}+ if not used_before(num, generation):+ self.xref[generation][num] = byte_offset+ if debug: print(("XREF Uncompressed: %s %s"%(+ num, generation)))+ elif xref_type == 2:+ # compressed objects+ objstr_num = getEntry(1)+ obstr_idx = getEntry(2)+ generation = 0 # PDF spec table 18, generation is 0+ if not used_before(num, generation):+ if debug: print(("XREF Compressed: %s %s %s"%(+ num, objstr_num, obstr_idx)))+ self.xref_objStm[num] = (objstr_num, obstr_idx)+ elif self.strict:+ raise utils.PdfReadError("Unknown xref type: %s"%+ xref_type)++ trailerKeys = "/Root", "/Encrypt", "/Info", "/ID"+ for key in trailerKeys:+ if key in xrefstream and key not in self.trailer:+ self.trailer[NameObject(key)] = xrefstream.raw_get(key)+ if "/Prev" in xrefstream:+ startxref = xrefstream["/Prev"]+ else:+ break+ else:+ # bad xref character at startxref. Let's see if we can find+ # the xref table nearby, as we've observed this error with an+ # off-by-one before.+ stream.seek(-11, 1)+ tmp = stream.read(20)+ xref_loc = tmp.find(b_("xref"))+ if xref_loc != -1:+ startxref -= (10 - xref_loc)+ continue+ # No explicit xref table, try finding a cross-reference stream.+ stream.seek(startxref, 0)+ found = False+ for look in range(5):+ if stream.read(1).isdigit():+ # This is not a standard PDF, consider adding a warning+ startxref += look+ found = True+ break+ if found:+ continue+ # no xref table found at specified location+ raise utils.PdfReadError("Could not find xref table at specified location")+ #if not zero-indexed, verify that the table is correct; change it if necessary+ if self.xrefIndex and not self.strict:+ loc = stream.tell()+ for gen in self.xref:+ if gen == 65535: continue+ for id in self.xref[gen]:+ stream.seek(self.xref[gen][id], 0)+ try:+ pid, pgen = self.readObjectHeader(stream)+ except ValueError:+ break+ if pid == id - self.xrefIndex:+ self._zeroXref(gen)+ break+ #if not, then either it's just plain wrong, or the non-zero-index is actually correct+ stream.seek(loc, 0) #return to where it was++ def _zeroXref(self, generation):+ self.xref[generation] = dict( (k-self.xrefIndex, v) for (k, v) in list(self.xref[generation].items()) )++ def _pairs(self, array):+ i = 0+ while True:+ yield array[i], array[i+1]+ i += 2+ if (i+1) >= len(array):+ break++ def readNextEndLine(self, stream):+ debug = False+ if debug: print(">>readNextEndLine")+ line = b_("")+ while True:+ # Prevent infinite loops in malformed PDFs+ if stream.tell() == 0:+ raise utils.PdfReadError("Could not read malformed PDF file")+ x = stream.read(1)+ if debug: print((" x:", x, "%x"%ord(x)))+ if stream.tell() < 2:+ raise utils.PdfReadError("EOL marker not found")+ stream.seek(-2, 1)+ if x == b_('\n') or x == b_('\r'): ## \n = LF; \r = CR+ crlf = False+ while x == b_('\n') or x == b_('\r'):+ if debug:+ if ord(x) == 0x0D: print(" x is CR 0D")+ elif ord(x) == 0x0A: print(" x is LF 0A")+ x = stream.read(1)+ if x == b_('\n') or x == b_('\r'): # account for CR+LF+ stream.seek(-1, 1)+ crlf = True+ if stream.tell() < 2:+ raise utils.PdfReadError("EOL marker not found")+ stream.seek(-2, 1)+ stream.seek(2 if crlf else 1, 1) #if using CR+LF, go back 2 bytes, else 1+ break+ else:+ if debug: print(" x is neither")+ line = x + line+ if debug: print((" RNEL line:", line))+ if debug: print("leaving RNEL")+ return line++ def decrypt(self, password):+ """+ When using an encrypted / secured PDF file with the PDF Standard+ encryption handler, this function will allow the file to be decrypted.+ It checks the given password against the document's user password and+ owner password, and then stores the resulting decryption key if either+ password is correct.++ It does not matter which password was matched. Both passwords provide+ the correct decryption key that will allow the document to be used with+ this library.++ :param str password: The password to match.+ :return: ``0`` if the password failed, ``1`` if the password matched the user+ password, and ``2`` if the password matched the owner password.+ :rtype: int+ :raises NotImplementedError: if document uses an unsupported encryption+ method.+ """++ self._override_encryption = True+ try:+ return self._decrypt(password)+ finally:+ self._override_encryption = False++ def _decrypt(self, password):+ encrypt = self.trailer['/Encrypt'].getObject()+ if encrypt['/Filter'] != '/Standard':+ raise NotImplementedError("only Standard PDF encryption handler is available")+ if not (encrypt['/V'] in (1, 2)):+ raise NotImplementedError("only algorithm code 1 and 2 are supported")+ user_password, key = self._authenticateUserPassword(password)+ if user_password:+ self._decryption_key = key+ return 1+ else:+ rev = encrypt['/R'].getObject()+ if rev == 2:+ keylen = 5+ else:+ keylen = encrypt['/Length'].getObject() // 8+ key = _alg33_1(password, rev, keylen)+ real_O = encrypt["/O"].getObject()+ if rev == 2:+ userpass = utils.RC4_encrypt(key, real_O)+ else:+ val = real_O+ for i in range(19, -1, -1):+ new_key = b_('')+ for l in range(len(key)):+ new_key += b_(chr(utils.ord_(key[l]) ^ i))+ val = utils.RC4_encrypt(new_key, val)+ userpass = val+ owner_password, key = self._authenticateUserPassword(userpass)+ if owner_password:+ self._decryption_key = key+ return 2+ return 0++ def _authenticateUserPassword(self, password):+ encrypt = self.trailer['/Encrypt'].getObject()+ rev = encrypt['/R'].getObject()+ owner_entry = encrypt['/O'].getObject()+ p_entry = encrypt['/P'].getObject()+ id_entry = self.trailer['/ID'].getObject()+ id1_entry = id_entry[0].getObject()+ real_U = encrypt['/U'].getObject().original_bytes+ if rev == 2:+ U, key = _alg34(password, owner_entry, p_entry, id1_entry)+ elif rev >= 3:+ U, key = _alg35(password, rev,+ encrypt["/Length"].getObject() // 8, owner_entry,+ p_entry, id1_entry,+ encrypt.get("/EncryptMetadata", BooleanObject(False)).getObject())+ U, real_U = U[:16], real_U[:16]+ return U == real_U, key++ def getIsEncrypted(self):+ return "/Encrypt" in self.trailer++ isEncrypted = property(lambda self: self.getIsEncrypted(), None, None)+ """+ Read-only boolean property showing whether this PDF file is encrypted.+ Note that this property, if true, will remain true even after the+ :meth:`decrypt()<PdfFileReader.decrypt>` method is called.+ """+++def getRectangle(self, name, defaults):+ retval = self.get(name)+ if isinstance(retval, RectangleObject):+ return retval+ if retval == None:+ for d in defaults:+ retval = self.get(d)+ if retval != None:+ break+ if isinstance(retval, IndirectObject):+ retval = self.pdf.getObject(retval)+ retval = RectangleObject(retval)+ setRectangle(self, name, retval)+ return retval+++def setRectangle(self, name, value):+ if not isinstance(name, NameObject):+ name = NameObject(name)+ self[name] = value+++def deleteRectangle(self, name):+ del self[name]+++def createRectangleAccessor(name, fallback):+ return \+ property(+ lambda self: getRectangle(self, name, fallback),+ lambda self, value: setRectangle(self, name, value),+ lambda self: deleteRectangle(self, name)+ )+++class PageObject(DictionaryObject):+ """+ This class represents a single page within a PDF file. Typically this+ object will be created by accessing the+ :meth:`getPage()<PyPDF2.PdfFileReader.getPage>` method of the+ :class:`PdfFileReader<PyPDF2.PdfFileReader>` class, but it is+ also possible to create an empty page with the+ :meth:`createBlankPage()<PageObject.createBlankPage>` static method.++ :param pdf: PDF file the page belongs to.+ :param indirectRef: Stores the original indirect reference to+ this object in its source PDF+ """+ def __init__(self, pdf=None, indirectRef=None):+ DictionaryObject.__init__(self)+ self.pdf = pdf+ self.indirectRef = indirectRef++ def createBlankPage(pdf=None, width=None, height=None):+ """+ Returns a new blank page.+ If ``width`` or ``height`` is ``None``, try to get the page size+ from the last page of *pdf*.++ :param pdf: PDF file the page belongs to+ :param float width: The width of the new page expressed in default user+ space units.+ :param float height: The height of the new page expressed in default user+ space units.+ :return: the new blank page:+ :rtype: :class:`PageObject<PageObject>`+ :raises PageSizeNotDefinedError: if ``pdf`` is ``None`` or contains+ no page+ """+ page = PageObject(pdf)++ # Creates a new page (cf PDF Reference 7.7.3.3)+ page.__setitem__(NameObject('/Type'), NameObject('/Page'))+ page.__setitem__(NameObject('/Parent'), NullObject())+ page.__setitem__(NameObject('/Resources'), DictionaryObject())+ if width is None or height is None:+ if pdf is not None and pdf.getNumPages() > 0:+ lastpage = pdf.getPage(pdf.getNumPages() - 1)+ width = lastpage.mediaBox.getWidth()+ height = lastpage.mediaBox.getHeight()+ else:+ raise utils.PageSizeNotDefinedError()+ page.__setitem__(NameObject('/MediaBox'),+ RectangleObject([0, 0, width, height]))++ return page+ createBlankPage = staticmethod(createBlankPage)++ def rotateClockwise(self, angle):+ """+ Rotates a page clockwise by increments of 90 degrees.++ :param int angle: Angle to rotate the page. Must be an increment+ of 90 deg.+ """+ assert angle % 90 == 0+ self._rotate(angle)+ return self++ def rotateCounterClockwise(self, angle):+ """+ Rotates a page counter-clockwise by increments of 90 degrees.++ :param int angle: Angle to rotate the page. Must be an increment+ of 90 deg.+ """+ assert angle % 90 == 0+ self._rotate(-angle)+ return self++ def _rotate(self, angle):+ currentAngle = self.get("/Rotate", 0)+ self[NameObject("/Rotate")] = NumberObject(currentAngle + angle)++ def _mergeResources(res1, res2, resource):+ newRes = DictionaryObject()+ newRes.update(res1.get(resource, DictionaryObject()).getObject())+ page2Res = res2.get(resource, DictionaryObject()).getObject()+ renameRes = {}+ for key in list(page2Res.keys()):+ if key in newRes and newRes.raw_get(key) != page2Res.raw_get(key):+ newname = NameObject(key + str(uuid.uuid4()))+ renameRes[key] = newname+ newRes[newname] = page2Res[key]+ elif key not in newRes:+ newRes[key] = page2Res.raw_get(key)+ return newRes, renameRes+ _mergeResources = staticmethod(_mergeResources)++ def _contentStreamRename(stream, rename, pdf):+ if not rename:+ return stream+ stream = ContentStream(stream, pdf)+ for operands, operator in stream.operations:+ for i in range(len(operands)):+ op = operands[i]+ if isinstance(op, NameObject):+ operands[i] = rename.get(op,op)+ return stream+ _contentStreamRename = staticmethod(_contentStreamRename)++ def _pushPopGS(contents, pdf):+ # adds a graphics state "push" and "pop" to the beginning and end+ # of a content stream. This isolates it from changes such as+ # transformation matricies.+ stream = ContentStream(contents, pdf)+ stream.operations.insert(0, [[], "q"])+ stream.operations.append([[], "Q"])+ return stream+ _pushPopGS = staticmethod(_pushPopGS)++ def _addTransformationMatrix(contents, pdf, ctm):+ # adds transformation matrix at the beginning of the given+ # contents stream.+ a, b, c, d, e, f = ctm+ contents = ContentStream(contents, pdf)+ contents.operations.insert(0, [[FloatObject(a), FloatObject(b),+ FloatObject(c), FloatObject(d), FloatObject(e),+ FloatObject(f)], " cm"])+ return contents+ _addTransformationMatrix = staticmethod(_addTransformationMatrix)++ def getContents(self):+ """+ Accesses the page contents.++ :return: the ``/Contents`` object, or ``None`` if it doesn't exist.+ ``/Contents`` is optional, as described in PDF Reference 7.7.3.3+ """+ if "/Contents" in self:+ return self["/Contents"].getObject()+ else:+ return None++ def mergePage(self, page2):+ """+ Merges the content streams of two pages into one. Resource references+ (i.e. fonts) are maintained from both pages. The mediabox/cropbox/etc+ of this page are not altered. The parameter page's content stream will+ be added to the end of this page's content stream, meaning that it will+ be drawn after, or "on top" of this page.++ :param PageObject page2: The page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ """+ self._mergePage(page2)++ def _mergePage(self, page2, page2transformation=None, ctm=None, expand=False):+ # First we work on merging the resource dictionaries. This allows us+ # to find out what symbols in the content streams we might need to+ # rename.++ newResources = DictionaryObject()+ rename = {}+ originalResources = self["/Resources"].getObject()+ page2Resources = page2["/Resources"].getObject()+ newAnnots = ArrayObject()++ for page in (self, page2):+ if "/Annots" in page:+ annots = page["/Annots"]+ if isinstance(annots, ArrayObject):+ for ref in annots:+ newAnnots.append(ref)++ for res in "/ExtGState", "/Font", "/XObject", "/ColorSpace", "/Pattern", "/Shading", "/Properties":+ new, newrename = PageObject._mergeResources(originalResources, page2Resources, res)+ if new:+ newResources[NameObject(res)] = new+ rename.update(newrename)++ # Combine /ProcSet sets.+ newResources[NameObject("/ProcSet")] = ArrayObject(+ frozenset(originalResources.get("/ProcSet", ArrayObject()).getObject()).union(+ frozenset(page2Resources.get("/ProcSet", ArrayObject()).getObject())+ )+ )++ newContentArray = ArrayObject()++ originalContent = self.getContents()+ if originalContent is not None:+ newContentArray.append(PageObject._pushPopGS(+ originalContent, self.pdf))++ page2Content = page2.getContents()+ if page2Content is not None:+ if page2transformation is not None:+ page2Content = page2transformation(page2Content)+ page2Content = PageObject._contentStreamRename(+ page2Content, rename, self.pdf)+ page2Content = PageObject._pushPopGS(page2Content, self.pdf)+ newContentArray.append(page2Content)++ # if expanding the page to fit a new page, calculate the new media box size+ if expand:+ corners1 = [self.mediaBox.getLowerLeft_x().as_numeric(), self.mediaBox.getLowerLeft_y().as_numeric(),+ self.mediaBox.getUpperRight_x().as_numeric(), self.mediaBox.getUpperRight_y().as_numeric()]+ corners2 = [page2.mediaBox.getLowerLeft_x().as_numeric(), page2.mediaBox.getLowerLeft_y().as_numeric(),+ page2.mediaBox.getUpperLeft_x().as_numeric(), page2.mediaBox.getUpperLeft_y().as_numeric(),+ page2.mediaBox.getUpperRight_x().as_numeric(), page2.mediaBox.getUpperRight_y().as_numeric(),+ page2.mediaBox.getLowerRight_x().as_numeric(), page2.mediaBox.getLowerRight_y().as_numeric()]+ if ctm is not None:+ ctm = [float(x) for x in ctm]+ new_x = [ctm[0]*corners2[i] + ctm[2]*corners2[i+1] + ctm[4] for i in range(0, 8, 2)]+ new_y = [ctm[1]*corners2[i] + ctm[3]*corners2[i+1] + ctm[5] for i in range(0, 8, 2)]+ else:+ new_x = corners2[0:8:2]+ new_y = corners2[1:8:2]+ lowerleft = [min(new_x), min(new_y)]+ upperright = [max(new_x), max(new_y)]+ lowerleft = [min(corners1[0], lowerleft[0]), min(corners1[1], lowerleft[1])]+ upperright = [max(corners1[2], upperright[0]), max(corners1[3], upperright[1])]++ self.mediaBox.setLowerLeft(lowerleft)+ self.mediaBox.setUpperRight(upperright)++ self[NameObject('/Contents')] = ContentStream(newContentArray, self.pdf)+ self[NameObject('/Resources')] = newResources+ self[NameObject('/Annots')] = newAnnots++ def mergeTransformedPage(self, page2, ctm, expand=False):+ """+ This is similar to mergePage, but a transformation matrix is+ applied to the merged stream.++ :param PageObject page2: The page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param tuple ctm: a 6-element tuple containing the operands of the+ transformation matrix+ :param bool expand: Whether the page should be expanded to fit the dimensions+ of the page to be merged.+ """+ self._mergePage(page2, lambda page2Content:+ PageObject._addTransformationMatrix(page2Content, page2.pdf, ctm), ctm, expand)++ def mergeScaledPage(self, page2, scale, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is scaled+ by appling a transformation matrix.++ :param PageObject page2: The page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float scale: The scaling factor+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """+ # CTM to scale : [ sx 0 0 sy 0 0 ]+ return self.mergeTransformedPage(page2, [scale, 0,+ 0, scale,+ 0, 0], expand)++ def mergeRotatedPage(self, page2, rotation, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is rotated+ by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float rotation: The angle of the rotation, in degrees+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """+ rotation = math.radians(rotation)+ return self.mergeTransformedPage(page2,+ [math.cos(rotation), math.sin(rotation),+ -math.sin(rotation), math.cos(rotation),+ 0, 0], expand)++ def mergeTranslatedPage(self, page2, tx, ty, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is translated+ by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float tx: The translation on X axis+ :param float ty: The translation on Y axis+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """+ return self.mergeTransformedPage(page2, [1, 0,+ 0, 1,+ tx, ty], expand)++ def mergeRotatedTranslatedPage(self, page2, rotation, tx, ty, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is rotated+ and translated by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float tx: The translation on X axis+ :param float ty: The translation on Y axis+ :param float rotation: The angle of the rotation, in degrees+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """++ translation = [[1, 0, 0],+ [0, 1, 0],+ [-tx, -ty, 1]]+ rotation = math.radians(rotation)+ rotating = [[math.cos(rotation), math.sin(rotation), 0],+ [-math.sin(rotation), math.cos(rotation), 0],+ [0, 0, 1]]+ rtranslation = [[1, 0, 0],+ [0, 1, 0],+ [tx, ty, 1]]+ ctm = utils.matrixMultiply(translation, rotating)+ ctm = utils.matrixMultiply(ctm, rtranslation)++ return self.mergeTransformedPage(page2, [ctm[0][0], ctm[0][1],+ ctm[1][0], ctm[1][1],+ ctm[2][0], ctm[2][1]], expand)++ def mergeRotatedScaledPage(self, page2, rotation, scale, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is rotated+ and scaled by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float rotation: The angle of the rotation, in degrees+ :param float scale: The scaling factor+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """+ rotation = math.radians(rotation)+ rotating = [[math.cos(rotation), math.sin(rotation), 0],+ [-math.sin(rotation), math.cos(rotation), 0],+ [0, 0, 1]]+ scaling = [[scale, 0, 0],+ [0, scale, 0],+ [0, 0, 1]]+ ctm = utils.matrixMultiply(rotating, scaling)++ return self.mergeTransformedPage(page2,+ [ctm[0][0], ctm[0][1],+ ctm[1][0], ctm[1][1],+ ctm[2][0], ctm[2][1]], expand)++ def mergeScaledTranslatedPage(self, page2, scale, tx, ty, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is translated+ and scaled by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float scale: The scaling factor+ :param float tx: The translation on X axis+ :param float ty: The translation on Y axis+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """++ translation = [[1, 0, 0],+ [0, 1, 0],+ [tx, ty, 1]]+ scaling = [[scale, 0, 0],+ [0, scale, 0],+ [0, 0, 1]]+ ctm = utils.matrixMultiply(scaling, translation)++ return self.mergeTransformedPage(page2, [ctm[0][0], ctm[0][1],+ ctm[1][0], ctm[1][1],+ ctm[2][0], ctm[2][1]], expand)++ def mergeRotatedScaledTranslatedPage(self, page2, rotation, scale, tx, ty, expand=False):+ """+ This is similar to mergePage, but the stream to be merged is translated,+ rotated and scaled by appling a transformation matrix.++ :param PageObject page2: the page to be merged into this one. Should be+ an instance of :class:`PageObject<PageObject>`.+ :param float tx: The translation on X axis+ :param float ty: The translation on Y axis+ :param float rotation: The angle of the rotation, in degrees+ :param float scale: The scaling factor+ :param bool expand: Whether the page should be expanded to fit the+ dimensions of the page to be merged.+ """+ translation = [[1, 0, 0],+ [0, 1, 0],+ [tx, ty, 1]]+ rotation = math.radians(rotation)+ rotating = [[math.cos(rotation), math.sin(rotation), 0],+ [-math.sin(rotation), math.cos(rotation), 0],+ [0, 0, 1]]+ scaling = [[scale, 0, 0],+ [0, scale, 0],+ [0, 0, 1]]+ ctm = utils.matrixMultiply(rotating, scaling)+ ctm = utils.matrixMultiply(ctm, translation)++ return self.mergeTransformedPage(page2, [ctm[0][0], ctm[0][1],+ ctm[1][0], ctm[1][1],+ ctm[2][0], ctm[2][1]], expand)++ ##+ # Applys a transformation matrix the page.+ #+ # @param ctm A 6 elements tuple containing the operands of the+ # transformation matrix+ def addTransformation(self, ctm):+ """+ Applies a transformation matrix to the page.++ :param tuple ctm: A 6-element tuple containing the operands of the+ transformation matrix.+ """+ originalContent = self.getContents()+ if originalContent is not None:+ newContent = PageObject._addTransformationMatrix(+ originalContent, self.pdf, ctm)+ newContent = PageObject._pushPopGS(newContent, self.pdf)+ self[NameObject('/Contents')] = newContent++ def scale(self, sx, sy):+ """+ Scales a page by the given factors by appling a transformation+ matrix to its content and updating the page size.++ :param float sx: The scaling factor on horizontal axis.+ :param float sy: The scaling factor on vertical axis.+ """+ self.addTransformation([sx, 0,+ 0, sy,+ 0, 0])+ self.mediaBox = RectangleObject([+ float(self.mediaBox.getLowerLeft_x()) * sx,+ float(self.mediaBox.getLowerLeft_y()) * sy,+ float(self.mediaBox.getUpperRight_x()) * sx,+ float(self.mediaBox.getUpperRight_y()) * sy])+ if "/VP" in self:+ viewport = self["/VP"]+ if isinstance(viewport, ArrayObject):+ bbox = viewport[0]["/BBox"]+ else:+ bbox = viewport["/BBox"]+ scaled_bbox = RectangleObject([+ float(bbox[0]) * sx,+ float(bbox[1]) * sy,+ float(bbox[2]) * sx,+ float(bbox[3]) * sy])+ if isinstance(viewport, ArrayObject):+ self[NameObject("/VP")][NumberObject(0)][NameObject("/BBox")] = scaled_bbox+ else:+ self[NameObject("/VP")][NameObject("/BBox")] = scaled_bbox++ def scaleBy(self, factor):+ """+ Scales a page by the given factor by appling a transformation+ matrix to its content and updating the page size.++ :param float factor: The scaling factor (for both X and Y axis).+ """+ self.scale(factor, factor)++ def scaleTo(self, width, height):+ """+ Scales a page to the specified dimentions by appling a+ transformation matrix to its content and updating the page size.++ :param float width: The new width.+ :param float height: The new heigth.+ """+ sx = width / float(self.mediaBox.getUpperRight_x() -+ self.mediaBox.getLowerLeft_x ())+ sy = height / float(self.mediaBox.getUpperRight_y() -+ self.mediaBox.getLowerLeft_y ())+ self.scale(sx, sy)++ def compressContentStreams(self):+ """+ Compresses the size of this page by joining all content streams and+ applying a FlateDecode filter.++ However, it is possible that this function will perform no action if+ content stream compression becomes "automatic" for some reason.+ """+ content = self.getContents()+ if content is not None:+ if not isinstance(content, ContentStream):+ content = ContentStream(content, self.pdf)+ self[NameObject("/Contents")] = content.flateEncode()++ def extractText(self):+ """+ Locate all text drawing commands, in the order they are provided in the+ content stream, and extract the text. This works well for some PDF+ files, but poorly for others, depending on the generator used. This will+ be refined in the future. Do not rely on the order of text coming out of+ this function, as it will change if this function is made more+ sophisticated.++ :return: a unicode string object.+ """+ text = u_("")+ content = self["/Contents"].getObject()+ if not isinstance(content, ContentStream):+ content = ContentStream(content, self.pdf)+ # Note: we check all strings are TextStringObjects. ByteStringObjects+ # are strings where the byte->string encoding was unknown, so adding+ # them to the text here would be gibberish.+ for operands, operator in content.operations:+ if operator == b_("Tj"):+ _text = operands[0]+ if isinstance(_text, TextStringObject):+ text += _text+ elif operator == b_("T*"):+ text += "\n"+ elif operator == b_("'"):+ text += "\n"+ _text = operands[0]+ if isinstance(_text, TextStringObject):+ text += operands[0]+ elif operator == b_('"'):+ _text = operands[2]+ if isinstance(_text, TextStringObject):+ text += "\n"+ text += _text+ elif operator == b_("TJ"):+ for i in operands[0]:+ if isinstance(i, TextStringObject):+ text += i+ text += "\n"+ return text++ mediaBox = createRectangleAccessor("/MediaBox", ())+ """+ A :class:`RectangleObject<PyPDF2.generic.RectangleObject>`, expressed in default user space units,+ defining the boundaries of the physical medium on which the page is+ intended to be displayed or printed.+ """++ cropBox = createRectangleAccessor("/CropBox", ("/MediaBox",))+ """+ A :class:`RectangleObject<PyPDF2.generic.RectangleObject>`, expressed in default user space units,+ defining the visible region of default user space. When the page is+ displayed or printed, its contents are to be clipped (cropped) to this+ rectangle and then imposed on the output medium in some+ implementation-defined manner. Default value: same as :attr:`mediaBox<mediaBox>`.+ """++ bleedBox = createRectangleAccessor("/BleedBox", ("/CropBox", "/MediaBox"))+ """+ A :class:`RectangleObject<PyPDF2.generic.RectangleObject>`, expressed in default user space units,+ defining the region to which the contents of the page should be clipped+ when output in a production enviroment.+ """++ trimBox = createRectangleAccessor("/TrimBox", ("/CropBox", "/MediaBox"))+ """+ A :class:`RectangleObject<PyPDF2.generic.RectangleObject>`, expressed in default user space units,+ defining the intended dimensions of the finished page after trimming.+ """++ artBox = createRectangleAccessor("/ArtBox", ("/CropBox", "/MediaBox"))+ """+ A :class:`RectangleObject<PyPDF2.generic.RectangleObject>`, expressed in default user space units,+ defining the extent of the page's meaningful content as intended by the+ page's creator.+ """+++class ContentStream(DecodedStreamObject):+ def __init__(self, stream, pdf):+ self.pdf = pdf+ self.operations = []+ # stream may be a StreamObject or an ArrayObject containing+ # multiple StreamObjects to be cat'd together.+ stream = stream.getObject()+ if isinstance(stream, ArrayObject):+ data = b_("")+ for s in stream:+ data += s.getObject().getData()+ stream = BytesIO(b_(data))+ else:+ stream = BytesIO(b_(stream.getData()))+ self.__parseContentStream(stream)++ def __parseContentStream(self, stream):+ # file("f:\\tmp.txt", "w").write(stream.read())+ stream.seek(0, 0)+ operands = []+ while True:+ peek = readNonWhitespace(stream)+ if peek == b_('') or ord_(peek) == 0:+ break+ stream.seek(-1, 1)+ if peek.isalpha() or peek == b_("'") or peek == b_('"'):+ operator = utils.readUntilRegex(stream,+ NameObject.delimiterPattern, True)+ if operator == b_("BI"):+ # begin inline image - a completely different parsing+ # mechanism is required, of course... thanks buddy...+ assert operands == []+ ii = self._readInlineImage(stream)+ self.operations.append((ii, b_("INLINE IMAGE")))+ else:+ self.operations.append((operands, operator))+ operands = []+ elif peek == b_('%'):+ # If we encounter a comment in the content stream, we have to+ # handle it here. Typically, readObject will handle+ # encountering a comment -- but readObject assumes that+ # following the comment must be the object we're trying to+ # read. In this case, it could be an operator instead.+ while peek not in (b_('\r'), b_('\n')):+ peek = stream.read(1)+ else:+ operands.append(readObject(stream, None))++ def _readInlineImage(self, stream):+ # begin reading just after the "BI" - begin image+ # first read the dictionary of settings.+ settings = DictionaryObject()+ while True:+ tok = readNonWhitespace(stream)+ stream.seek(-1, 1)+ if tok == b_("I"):+ # "ID" - begin of image data+ break+ key = readObject(stream, self.pdf)+ tok = readNonWhitespace(stream)+ stream.seek(-1, 1)+ value = readObject(stream, self.pdf)+ settings[key] = value+ # left at beginning of ID+ tmp = stream.read(3)+ assert tmp[:2] == b_("ID")+ data = b_("")+ while True:+ # Read the inline image, while checking for EI (End Image) operator.+ tok = stream.read(1)+ if tok == b_("E"):+ # Check for End Image+ tok2 = stream.read(1)+ if tok2 == b_("I"):+ # Data can contain EI, so check for the Q operator.+ tok3 = stream.read(1)+ info = tok + tok2+ # We need to find whitespace between EI and Q.+ has_q_whitespace = False+ while tok3 in utils.WHITESPACES:+ has_q_whitespace = True+ info += tok3+ tok3 = stream.read(1)+ if tok3 == b_("Q") and has_q_whitespace:+ stream.seek(-1, 1)+ break+ else:+ stream.seek(-1,1)+ data += info+ else:+ stream.seek(-1, 1)+ data += tok+ else:+ data += tok+ return {"settings": settings, "data": data}++ def _getData(self):+ newdata = BytesIO()+ for operands, operator in self.operations:+ if operator == b_("INLINE IMAGE"):+ newdata.write(b_("BI"))+ dicttext = BytesIO()+ operands["settings"].writeToStream(dicttext, None)+ newdata.write(dicttext.getvalue()[2:-2])+ newdata.write(b_("ID "))+ newdata.write(operands["data"])+ newdata.write(b_("EI"))+ else:+ for op in operands:+ op.writeToStream(newdata, None)+ newdata.write(b_(" "))+ newdata.write(b_(operator))+ newdata.write(b_("\n"))+ return newdata.getvalue()++ def _setData(self, value):+ self.__parseContentStream(BytesIO(b_(value)))++ _data = property(_getData, _setData)+++class DocumentInformation(DictionaryObject):+ """+ A class representing the basic document metadata provided in a PDF File.+ This class is accessible through+ :meth:`getDocumentInfo()<PyPDF2.PdfFileReader.getDocumentInfo()>`++ All text properties of the document metadata have+ *two* properties, eg. author and author_raw. The non-raw property will+ always return a ``TextStringObject``, making it ideal for a case where+ the metadata is being displayed. The raw property can sometimes return+ a ``ByteStringObject``, if PyPDF2 was unable to decode the string's+ text encoding; this requires additional safety in the caller and+ therefore is not as commonly accessed.+ """++ def __init__(self):+ DictionaryObject.__init__(self)++ def getText(self, key):+ retval = self.get(key, None)+ if isinstance(retval, TextStringObject):+ return retval+ return None++ title = property(lambda self: self.getText("/Title"))+ """Read-only property accessing the document's **title**.+ Returns a unicode string (``TextStringObject``) or ``None``+ if the title is not specified."""+ title_raw = property(lambda self: self.get("/Title"))+ """The "raw" version of title; can return a ``ByteStringObject``."""++ author = property(lambda self: self.getText("/Author"))+ """Read-only property accessing the document's **author**.+ Returns a unicode string (``TextStringObject``) or ``None``+ if the author is not specified."""+ author_raw = property(lambda self: self.get("/Author"))+ """The "raw" version of author; can return a ``ByteStringObject``."""++ subject = property(lambda self: self.getText("/Subject"))+ """Read-only property accessing the document's **subject**.+ Returns a unicode string (``TextStringObject``) or ``None``+ if the subject is not specified."""+ subject_raw = property(lambda self: self.get("/Subject"))+ """The "raw" version of subject; can return a ``ByteStringObject``."""++ creator = property(lambda self: self.getText("/Creator"))+ """Read-only property accessing the document's **creator**. If the+ document was converted to PDF from another format, this is the name of the+ application (e.g. OpenOffice) that created the original document from+ which it was converted. Returns a unicode string (``TextStringObject``)+ or ``None`` if the creator is not specified."""+ creator_raw = property(lambda self: self.get("/Creator"))+ """The "raw" version of creator; can return a ``ByteStringObject``."""++ producer = property(lambda self: self.getText("/Producer"))+ """Read-only property accessing the document's **producer**.+ If the document was converted to PDF from another format, this is+ the name of the application (for example, OSX Quartz) that converted+ it to PDF. Returns a unicode string (``TextStringObject``)+ or ``None`` if the producer is not specified."""+ producer_raw = property(lambda self: self.get("/Producer"))+ """The "raw" version of producer; can return a ``ByteStringObject``."""+++def convertToInt(d, size):+ if size > 8:+ raise utils.PdfReadError("invalid size in convertToInt")+ d = b_("\x00\x00\x00\x00\x00\x00\x00\x00") + b_(d)+ d = d[-8:]+ return struct.unpack(">q", d)[0]++# ref: pdf1.8 spec section 3.5.2 algorithm 3.2+_encryption_padding = b_('\x28\xbf\x4e\x5e\x4e\x75\x8a\x41\x64\x00\x4e\x56') + \+ b_('\xff\xfa\x01\x08\x2e\x2e\x00\xb6\xd0\x68\x3e\x80\x2f\x0c') + \+ b_('\xa9\xfe\x64\x53\x69\x7a')+++# Implementation of algorithm 3.2 of the PDF standard security handler,+# section 3.5.2 of the PDF 1.6 reference.+def _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encrypt=True):+ # 1. Pad or truncate the password string to exactly 32 bytes. If the+ # password string is more than 32 bytes long, use only its first 32 bytes;+ # if it is less than 32 bytes long, pad it by appending the required number+ # of additional bytes from the beginning of the padding string+ # (_encryption_padding).+ password = b_((str_(password) + str_(_encryption_padding))[:32])+ # 2. Initialize the MD5 hash function and pass the result of step 1 as+ # input to this function.+ import struct+ m = md5(password)+ # 3. Pass the value of the encryption dictionary's /O entry to the MD5 hash+ # function.+ m.update(owner_entry.original_bytes)+ # 4. Treat the value of the /P entry as an unsigned 4-byte integer and pass+ # these bytes to the MD5 hash function, low-order byte first.+ p_entry = struct.pack('<i', p_entry)+ m.update(p_entry)+ # 5. Pass the first element of the file's file identifier array to the MD5+ # hash function.+ m.update(id1_entry.original_bytes)+ # 6. (Revision 3 or greater) If document metadata is not being encrypted,+ # pass 4 bytes with the value 0xFFFFFFFF to the MD5 hash function.+ if rev >= 3 and not metadata_encrypt:+ m.update(b_("\xff\xff\xff\xff"))+ # 7. Finish the hash.+ md5_hash = m.digest()+ # 8. (Revision 3 or greater) Do the following 50 times: Take the output+ # from the previous MD5 hash and pass the first n bytes of the output as+ # input into a new MD5 hash, where n is the number of bytes of the+ # encryption key as defined by the value of the encryption dictionary's+ # /Length entry.+ if rev >= 3:+ for i in range(50):+ md5_hash = md5(md5_hash[:keylen]).digest()+ # 9. Set the encryption key to the first n bytes of the output from the+ # final MD5 hash, where n is always 5 for revision 2 but, for revision 3 or+ # greater, depends on the value of the encryption dictionary's /Length+ # entry.+ return md5_hash[:keylen]+++# Implementation of algorithm 3.3 of the PDF standard security handler,+# section 3.5.2 of the PDF 1.6 reference.+def _alg33(owner_pwd, user_pwd, rev, keylen):+ # steps 1 - 4+ key = _alg33_1(owner_pwd, rev, keylen)+ # 5. Pad or truncate the user password string as described in step 1 of+ # algorithm 3.2.+ user_pwd = b_((user_pwd + str_(_encryption_padding))[:32])+ # 6. Encrypt the result of step 5, using an RC4 encryption function with+ # the encryption key obtained in step 4.+ val = utils.RC4_encrypt(key, user_pwd)+ # 7. (Revision 3 or greater) Do the following 19 times: Take the output+ # from the previous invocation of the RC4 function and pass it as input to+ # a new invocation of the function; use an encryption key generated by+ # taking each byte of the encryption key obtained in step 4 and performing+ # an XOR operation between that byte and the single-byte value of the+ # iteration counter (from 1 to 19).+ if rev >= 3:+ for i in range(1, 20):+ new_key = ''+ for l in range(len(key)):+ new_key += chr(ord_(key[l]) ^ i)+ val = utils.RC4_encrypt(new_key, val)+ # 8. Store the output from the final invocation of the RC4 as the value of+ # the /O entry in the encryption dictionary.+ return val+++# Steps 1-4 of algorithm 3.3+def _alg33_1(password, rev, keylen):+ # 1. Pad or truncate the owner password string as described in step 1 of+ # algorithm 3.2. If there is no owner password, use the user password+ # instead.+ password = b_((password + str_(_encryption_padding))[:32])+ # 2. Initialize the MD5 hash function and pass the result of step 1 as+ # input to this function.+ m = md5(password)+ # 3. (Revision 3 or greater) Do the following 50 times: Take the output+ # from the previous MD5 hash and pass it as input into a new MD5 hash.+ md5_hash = m.digest()+ if rev >= 3:+ for i in range(50):+ md5_hash = md5(md5_hash).digest()+ # 4. Create an RC4 encryption key using the first n bytes of the output+ # from the final MD5 hash, where n is always 5 for revision 2 but, for+ # revision 3 or greater, depends on the value of the encryption+ # dictionary's /Length entry.+ key = md5_hash[:keylen]+ return key+++# Implementation of algorithm 3.4 of the PDF standard security handler,+# section 3.5.2 of the PDF 1.6 reference.+def _alg34(password, owner_entry, p_entry, id1_entry):+ # 1. Create an encryption key based on the user password string, as+ # described in algorithm 3.2.+ key = _alg32(password, 2, 5, owner_entry, p_entry, id1_entry)+ # 2. Encrypt the 32-byte padding string shown in step 1 of algorithm 3.2,+ # using an RC4 encryption function with the encryption key from the+ # preceding step.+ U = utils.RC4_encrypt(key, _encryption_padding)+ # 3. Store the result of step 2 as the value of the /U entry in the+ # encryption dictionary.+ return U, key+++# Implementation of algorithm 3.4 of the PDF standard security handler,+# section 3.5.2 of the PDF 1.6 reference.+def _alg35(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encrypt):+ # 1. Create an encryption key based on the user password string, as+ # described in Algorithm 3.2.+ key = _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry)+ # 2. Initialize the MD5 hash function and pass the 32-byte padding string+ # shown in step 1 of Algorithm 3.2 as input to this function.+ m = md5()+ m.update(_encryption_padding)+ # 3. Pass the first element of the file's file identifier array (the value+ # of the ID entry in the document's trailer dictionary; see Table 3.13 on+ # page 73) to the hash function and finish the hash. (See implementation+ # note 25 in Appendix H.)+ m.update(id1_entry.original_bytes)+ md5_hash = m.digest()+ # 4. Encrypt the 16-byte result of the hash, using an RC4 encryption+ # function with the encryption key from step 1.+ val = utils.RC4_encrypt(key, md5_hash)+ # 5. Do the following 19 times: Take the output from the previous+ # invocation of the RC4 function and pass it as input to a new invocation+ # of the function; use an encryption key generated by taking each byte of+ # the original encryption key (obtained in step 2) and performing an XOR+ # operation between that byte and the single-byte value of the iteration+ # counter (from 1 to 19).+ for i in range(1, 20):+ new_key = b_('')+ for l in range(len(key)):+ new_key += b_(chr(ord_(key[l]) ^ i))+ val = utils.RC4_encrypt(new_key, val)+ # 6. Append 16 bytes of arbitrary padding to the output from the final+ # invocation of the RC4 function and store the 32-byte result as the value+ # of the U entry in the encryption dictionary.+ # (implementator note: I don't know what "arbitrary padding" is supposed to+ # mean, so I have used null bytes. This seems to match a few other+ # people's implementations)+ return val + (b_('\x00') * 16), keydiff --git a/ext/PyPDF2/utils.py b/ext/PyPDF2/utils.pynew file mode 100755index 00000000..718a875c--- /dev/null+++ b/ext/PyPDF2/utils.py@@ -0,0 +1,295 @@+# Copyright (c) 2006, Mathieu Fenniak+# All rights reserved.+#+# Redistribution and use in source and binary forms, with or without+# modification, are permitted provided that the following conditions are+# met:+#+# * Redistributions of source code must retain the above copyright notice,+# this list of conditions and the following disclaimer.+# * Redistributions in binary form must reproduce the above copyright notice,+# this list of conditions and the following disclaimer in the documentation+# and/or other materials provided with the distribution.+# * The name of the author may not be used to endorse or promote products+# derived from this software without specific prior written permission.+#+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+# POSSIBILITY OF SUCH DAMAGE.++"""+Utility functions for PDF library.+"""+__author__ = "Mathieu Fenniak"+__author_email__ = "[email protected]"+++import sys++try:+ import __builtin__ as builtins+except ImportError: # Py3+ import builtins+++xrange_fn = getattr(builtins, "xrange", range)+_basestring = getattr(builtins, "basestring", str)++bytes_type = type(bytes()) # Works the same in Python 2.X and 3.X+string_type = getattr(builtins, "unicode", str)+int_types = (int, long) if sys.version_info[0] < 3 else (int,)+++# Make basic type tests more consistent+def isString(s):+ """Test if arg is a string. Compatible with Python 2 and 3."""+ return isinstance(s, _basestring)+++def isInt(n):+ """Test if arg is an int. Compatible with Python 2 and 3."""+ return isinstance(n, int_types)+++def isBytes(b):+ """Test if arg is a bytes instance. Compatible with Python 2 and 3."""+ return isinstance(b, bytes_type)+++#custom implementation of warnings.formatwarning+def formatWarning(message, category, filename, lineno, line=None):+ file = filename.replace("/", "\\").rsplit("\\", 1)[1] # find the file name+ return "%s: %s [%s:%s]\n" % (category.__name__, message, file, lineno)+++def readUntilWhitespace(stream, maxchars=None):+ """+ Reads non-whitespace characters and returns them.+ Stops upon encountering whitespace or when maxchars is reached.+ """+ txt = b_("")+ while True:+ tok = stream.read(1)+ if tok.isspace() or not tok:+ break+ txt += tok+ if len(txt) == maxchars:+ break+ return txt+++def readNonWhitespace(stream):+ """+ Finds and reads the next non-whitespace character (ignores whitespace).+ """+ tok = WHITESPACES[0]+ while tok in WHITESPACES:+ tok = stream.read(1)+ return tok+++def skipOverWhitespace(stream):+ """+ Similar to readNonWhitespace, but returns a Boolean if more than+ one whitespace character was read.+ """+ tok = WHITESPACES[0]+ cnt = 0;+ while tok in WHITESPACES:+ tok = stream.read(1)+ cnt+=1+ return (cnt > 1)+++def skipOverComment(stream):+ tok = stream.read(1)+ stream.seek(-1, 1)+ if tok == b_('%'):+ while tok not in (b_('\n'), b_('\r')):+ tok = stream.read(1)+++def readUntilRegex(stream, regex, ignore_eof=False):+ """+ Reads until the regular expression pattern matched (ignore the match)+ Raise PdfStreamError on premature end-of-file.+ :param bool ignore_eof: If true, ignore end-of-line and return immediately+ """+ name = b_('')+ while True:+ tok = stream.read(16)+ if not tok:+ # stream has truncated prematurely+ if ignore_eof == True:+ return name+ else:+ raise PdfStreamError("Stream has ended unexpectedly")+ m = regex.search(tok)+ if m is not None:+ name += tok[:m.start()]+ stream.seek(m.start()-len(tok), 1)+ break+ name += tok+ return name+++class ConvertFunctionsToVirtualList(object):+ def __init__(self, lengthFunction, getFunction):+ self.lengthFunction = lengthFunction+ self.getFunction = getFunction++ def __len__(self):+ return self.lengthFunction()++ def __getitem__(self, index):+ if isinstance(index, slice):+ indices = xrange_fn(*index.indices(len(self)))+ cls = type(self)+ return cls(indices.__len__, lambda idx: self[indices[idx]])+ if not isInt(index):+ raise TypeError("sequence indices must be integers")+ len_self = len(self)+ if index < 0:+ # support negative indexes+ index = len_self + index+ if index < 0 or index >= len_self:+ raise IndexError("sequence index out of range")+ return self.getFunction(index)+++def RC4_encrypt(key, plaintext):+ S = [i for i in range(256)]+ j = 0+ for i in range(256):+ j = (j + S[i] + ord_(key[i % len(key)])) % 256+ S[i], S[j] = S[j], S[i]+ i, j = 0, 0+ retval = b_("")+ for x in range(len(plaintext)):+ i = (i + 1) % 256+ j = (j + S[i]) % 256+ S[i], S[j] = S[j], S[i]+ t = S[(S[i] + S[j]) % 256]+ retval += b_(chr(ord_(plaintext[x]) ^ t))+ return retval+++def matrixMultiply(a, b):+ return [[sum([float(i)*float(j)+ for i, j in zip(row, col)]+ ) for col in zip(*b)]+ for row in a]+++def markLocation(stream):+ """Creates text file showing current location in context."""+ # Mainly for debugging+ RADIUS = 5000+ stream.seek(-RADIUS, 1)+ outputDoc = open('PyPDF2_pdfLocation.txt', 'w')+ outputDoc.write(stream.read(RADIUS))+ outputDoc.write('HERE')+ outputDoc.write(stream.read(RADIUS))+ outputDoc.close()+ stream.seek(-RADIUS, 1)+++class PyPdfError(Exception):+ pass+++class PdfReadError(PyPdfError):+ pass+++class PageSizeNotDefinedError(PyPdfError):+ pass+++class PdfReadWarning(UserWarning):+ pass+++class PdfStreamError(PdfReadError):+ pass+++if sys.version_info[0] < 3:+ def b_(s):+ return s+else:+ B_CACHE = {}++ def b_(s):+ bc = B_CACHE+ if s in bc:+ return bc[s]+ if type(s) == bytes:+ return s+ else:+ r = s.encode('latin-1')+ if len(s) < 2:+ bc[s] = r+ return r+++def u_(s):+ if sys.version_info[0] < 3:+ return unicode(s, 'unicode_escape')+ else:+ return s+++def str_(b):+ if sys.version_info[0] < 3:+ return b+ else:+ if type(b) == bytes:+ return b.decode('latin-1')+ else:+ return b+++def ord_(b):+ if sys.version_info[0] < 3 or type(b) == str:+ return ord(b)+ else:+ return b+++def chr_(c):+ if sys.version_info[0] < 3:+ return c+ else:+ return chr(c)+++def barray(b):+ if sys.version_info[0] < 3:+ return b+ else:+ return bytearray(b)+++def hexencode(b):+ if sys.version_info[0] < 3:+ return b.encode('hex')+ else:+ import codecs+ coder = codecs.getencoder('hex_codec')+ return coder(b)[0]+++def hexStr(num):+ return hex(num).replace('L', '')+++WHITESPACES = [b_(x) for x in [' ', '\n', '\r', '\t', '\x00']]diff --git a/ext/pyPdf/xmp.py b/ext/PyPDF2/xmp.pyold mode 100644new mode 100755similarity index 69%rename from ext/pyPdf/xmp.pyrename to ext/PyPDF2/xmp.pyindex b070df90..7ba62f0d--- a/ext/pyPdf/xmp.py+++ b/ext/PyPDF2/xmp.py@@ -1,355 +1,358 @@-import re-import datetime-import decimal-from generic import PdfObject-from xml.dom import getDOMImplementation-from xml.dom.minidom import parseString--RDF_NAMESPACE = "http://www.w3.org/1999/02/22-rdf-syntax-ns#"-DC_NAMESPACE = "http://purl.org/dc/elements/1.1/"-XMP_NAMESPACE = "http://ns.adobe.com/xap/1.0/"-PDF_NAMESPACE = "http://ns.adobe.com/pdf/1.3/"-XMPMM_NAMESPACE = "http://ns.adobe.com/xap/1.0/mm/"--# What is the PDFX namespace, you might ask? I might ask that too. It's-# a completely undocumented namespace used to place "custom metadata"-# properties, which are arbitrary metadata properties with no semantic or-# documented meaning. Elements in the namespace are key/value-style storage,-# where the element name is the key and the content is the value. The keys-# are transformed into valid XML identifiers by substituting an invalid-# identifier character with \u2182 followed by the unicode hex ID of the-# original character. A key like "my car" is therefore "my\u21820020car".-#-# \u2182, in case you're wondering, is the unicode character-# \u{ROMAN NUMERAL TEN THOUSAND}, a straightforward and obvious choice for-# escaping characters.-#-# Intentional users of the pdfx namespace should be shot on sight. A-# custom data schema and sensical XML elements could be used instead, as is-# suggested by Adobe's own documentation on XMP (under "Extensibility of-# Schemas").-#-# Information presented here on the /pdfx/ schema is a result of limited-# reverse engineering, and does not constitute a full specification.-PDFX_NAMESPACE = "http://ns.adobe.com/pdfx/1.3/"--iso8601 = re.compile("""- (?P<year>[0-9]{4})- (-- (?P<month>[0-9]{2})- (-- (?P<day>[0-9]+)- (T- (?P<hour>[0-9]{2}):- (?P<minute>[0-9]{2})- (:(?P<second>[0-9]{2}(.[0-9]+)?))?- (?P<tzd>Z|[-+][0-9]{2}:[0-9]{2})- )?- )?- )?- """, re.VERBOSE)--##-# An object that represents Adobe XMP metadata.-class XmpInformation(PdfObject):-- def __init__(self, stream):- self.stream = stream- docRoot = parseString(self.stream.getData())- self.rdfRoot = docRoot.getElementsByTagNameNS(RDF_NAMESPACE, "RDF")[0]- self.cache = {}-- def writeToStream(self, stream, encryption_key):- self.stream.writeToStream(stream, encryption_key)-- def getElement(self, aboutUri, namespace, name):- for desc in self.rdfRoot.getElementsByTagNameNS(RDF_NAMESPACE, "Description"):- if desc.getAttributeNS(RDF_NAMESPACE, "about") == aboutUri:- attr = desc.getAttributeNodeNS(namespace, name)- if attr != None:- yield attr- for element in desc.getElementsByTagNameNS(namespace, name):- yield element-- def getNodesInNamespace(self, aboutUri, namespace):- for desc in self.rdfRoot.getElementsByTagNameNS(RDF_NAMESPACE, "Description"):- if desc.getAttributeNS(RDF_NAMESPACE, "about") == aboutUri:- for i in range(desc.attributes.length):- attr = desc.attributes.item(i)- if attr.namespaceURI == namespace:- yield attr- for child in desc.childNodes:- if child.namespaceURI == namespace:- yield child-- def _getText(self, element):- text = ""- for child in element.childNodes:- if child.nodeType == child.TEXT_NODE:- text += child.data- return text-- def _converter_string(value):- return value-- def _converter_date(value):- m = iso8601.match(value)- year = int(m.group("year"))- month = int(m.group("month") or "1")- day = int(m.group("day") or "1")- hour = int(m.group("hour") or "0")- minute = int(m.group("minute") or "0")- second = decimal.Decimal(m.group("second") or "0")- seconds = second.to_integral(decimal.ROUND_FLOOR)- milliseconds = (second - seconds) * 1000000- tzd = m.group("tzd") or "Z"- dt = datetime.datetime(year, month, day, hour, minute, seconds, milliseconds)- if tzd != "Z":- tzd_hours, tzd_minutes = [int(x) for x in tzd.split(":")]- tzd_hours *= -1- if tzd_hours < 0:- tzd_minutes *= -1- dt = dt + datetime.timedelta(hours=tzd_hours, minutes=tzd_minutes)- return dt- _test_converter_date = staticmethod(_converter_date)-- def _getter_bag(namespace, name, converter):- def get(self):- cached = self.cache.get(namespace, {}).get(name)- if cached:- return cached- retval = []- for element in self.getElement("", namespace, name):- bags = element.getElementsByTagNameNS(RDF_NAMESPACE, "Bag")- if len(bags):- for bag in bags:- for item in bag.getElementsByTagNameNS(RDF_NAMESPACE, "li"):- value = self._getText(item)- value = converter(value)- retval.append(value)- ns_cache = self.cache.setdefault(namespace, {})- ns_cache[name] = retval- return retval- return get-- def _getter_seq(namespace, name, converter):- def get(self):- cached = self.cache.get(namespace, {}).get(name)- if cached:- return cached- retval = []- for element in self.getElement("", namespace, name):- seqs = element.getElementsByTagNameNS(RDF_NAMESPACE, "Seq")- if len(seqs):- for seq in seqs:- for item in seq.getElementsByTagNameNS(RDF_NAMESPACE, "li"):- value = self._getText(item)- value = converter(value)- retval.append(value)- else:- value = converter(self._getText(element))- retval.append(value)- ns_cache = self.cache.setdefault(namespace, {})- ns_cache[name] = retval- return retval- return get-- def _getter_langalt(namespace, name, converter):- def get(self):- cached = self.cache.get(namespace, {}).get(name)- if cached:- return cached- retval = {}- for element in self.getElement("", namespace, name):- alts = element.getElementsByTagNameNS(RDF_NAMESPACE, "Alt")- if len(alts):- for alt in alts:- for item in alt.getElementsByTagNameNS(RDF_NAMESPACE, "li"):- value = self._getText(item)- value = converter(value)- retval[item.getAttribute("xml:lang")] = value- else:- retval["x-default"] = converter(self._getText(element))- ns_cache = self.cache.setdefault(namespace, {})- ns_cache[name] = retval- return retval- return get-- def _getter_single(namespace, name, converter):- def get(self):- cached = self.cache.get(namespace, {}).get(name)- if cached:- return cached- value = None- for element in self.getElement("", namespace, name):- if element.nodeType == element.ATTRIBUTE_NODE:- value = element.nodeValue- else:- value = self._getText(element)- break- if value != None:- value = converter(value)- ns_cache = self.cache.setdefault(namespace, {})- ns_cache[name] = value- return value- return get-- ##- # Contributors to the resource (other than the authors). An unsorted- # array of names.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_contributor = property(_getter_bag(DC_NAMESPACE, "contributor", _converter_string))-- ##- # Text describing the extent or scope of the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_coverage = property(_getter_single(DC_NAMESPACE, "coverage", _converter_string))-- ##- # A sorted array of names of the authors of the resource, listed in order- # of precedence.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_creator = property(_getter_seq(DC_NAMESPACE, "creator", _converter_string))-- ##- # A sorted array of dates (datetime.datetime instances) of signifigance to- # the resource. The dates and times are in UTC.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_date = property(_getter_seq(DC_NAMESPACE, "date", _converter_date))-- ##- # A language-keyed dictionary of textual descriptions of the content of the- # resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_description = property(_getter_langalt(DC_NAMESPACE, "description", _converter_string))-- ##- # The mime-type of the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_format = property(_getter_single(DC_NAMESPACE, "format", _converter_string))-- ##- # Unique identifier of the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_identifier = property(_getter_single(DC_NAMESPACE, "identifier", _converter_string))-- ##- # An unordered array specifying the languages used in the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_language = property(_getter_bag(DC_NAMESPACE, "language", _converter_string))-- ##- # An unordered array of publisher names.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_publisher = property(_getter_bag(DC_NAMESPACE, "publisher", _converter_string))-- ##- # An unordered array of text descriptions of relationships to other- # documents.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_relation = property(_getter_bag(DC_NAMESPACE, "relation", _converter_string))-- ##- # A language-keyed dictionary of textual descriptions of the rights the- # user has to this resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_rights = property(_getter_langalt(DC_NAMESPACE, "rights", _converter_string))-- ##- # Unique identifier of the work from which this resource was derived.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_source = property(_getter_single(DC_NAMESPACE, "source", _converter_string))-- ##- # An unordered array of descriptive phrases or keywrods that specify the- # topic of the content of the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_subject = property(_getter_bag(DC_NAMESPACE, "subject", _converter_string))-- ##- # A language-keyed dictionary of the title of the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_title = property(_getter_langalt(DC_NAMESPACE, "title", _converter_string))-- ##- # An unordered array of textual descriptions of the document type.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- dc_type = property(_getter_bag(DC_NAMESPACE, "type", _converter_string))-- ##- # An unformatted text string representing document keywords.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- pdf_keywords = property(_getter_single(PDF_NAMESPACE, "Keywords", _converter_string))-- ##- # The PDF file version, for example 1.0, 1.3.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- pdf_pdfversion = property(_getter_single(PDF_NAMESPACE, "PDFVersion", _converter_string))-- ##- # The name of the tool that created the PDF document.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- pdf_producer = property(_getter_single(PDF_NAMESPACE, "Producer", _converter_string))-- ##- # The date and time the resource was originally created. The date and- # time are returned as a UTC datetime.datetime object.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmp_createDate = property(_getter_single(XMP_NAMESPACE, "CreateDate", _converter_date))-- ##- # The date and time the resource was last modified. The date and time- # are returned as a UTC datetime.datetime object.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmp_modifyDate = property(_getter_single(XMP_NAMESPACE, "ModifyDate", _converter_date))-- ##- # The date and time that any metadata for this resource was last- # changed. The date and time are returned as a UTC datetime.datetime- # object.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmp_metadataDate = property(_getter_single(XMP_NAMESPACE, "MetadataDate", _converter_date))-- ##- # The name of the first known tool used to create the resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmp_creatorTool = property(_getter_single(XMP_NAMESPACE, "CreatorTool", _converter_string))-- ##- # The common identifier for all versions and renditions of this resource.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmpmm_documentId = property(_getter_single(XMPMM_NAMESPACE, "DocumentID", _converter_string))-- ##- # An identifier for a specific incarnation of a document, updated each- # time a file is saved.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- xmpmm_instanceId = property(_getter_single(XMPMM_NAMESPACE, "InstanceID", _converter_string))-- def custom_properties(self):- if not hasattr(self, "_custom_properties"):- self._custom_properties = {}- for node in self.getNodesInNamespace("", PDFX_NAMESPACE):- key = node.localName- while True:- # see documentation about PDFX_NAMESPACE earlier in file- idx = key.find(u"\u2182")- if idx == -1:- break- key = key[:idx] + chr(int(key[idx+1:idx+5], base=16)) + key[idx+5:]- if node.nodeType == node.ATTRIBUTE_NODE:- value = node.nodeValue- else:- value = self._getText(node)- self._custom_properties[key] = value- return self._custom_properties-- ##- # Retrieves custom metadata properties defined in the undocumented pdfx- # metadata schema.- # <p>Stability: Added in v1.12, will exist for all future v1.x releases.- # @return Returns a dictionary of key/value items for custom metadata- # properties.- custom_properties = property(custom_properties)--+import re+import datetime+import decimal+from .generic import PdfObject+from xml.dom import getDOMImplementation+from xml.dom.minidom import parseString+from .utils import u_++RDF_NAMESPACE = "http://www.w3.org/1999/02/22-rdf-syntax-ns#"+DC_NAMESPACE = "http://purl.org/dc/elements/1.1/"+XMP_NAMESPACE = "http://ns.adobe.com/xap/1.0/"+PDF_NAMESPACE = "http://ns.adobe.com/pdf/1.3/"+XMPMM_NAMESPACE = "http://ns.adobe.com/xap/1.0/mm/"++# What is the PDFX namespace, you might ask? I might ask that too. It's+# a completely undocumented namespace used to place "custom metadata"+# properties, which are arbitrary metadata properties with no semantic or+# documented meaning. Elements in the namespace are key/value-style storage,+# where the element name is the key and the content is the value. The keys+# are transformed into valid XML identifiers by substituting an invalid+# identifier character with \u2182 followed by the unicode hex ID of the+# original character. A key like "my car" is therefore "my\u21820020car".+#+# \u2182, in case you're wondering, is the unicode character+# \u{ROMAN NUMERAL TEN THOUSAND}, a straightforward and obvious choice for+# escaping characters.+#+# Intentional users of the pdfx namespace should be shot on sight. A+# custom data schema and sensical XML elements could be used instead, as is+# suggested by Adobe's own documentation on XMP (under "Extensibility of+# Schemas").+#+# Information presented here on the /pdfx/ schema is a result of limited+# reverse engineering, and does not constitute a full specification.+PDFX_NAMESPACE = "http://ns.adobe.com/pdfx/1.3/"++iso8601 = re.compile("""+ (?P<year>[0-9]{4})+ (-+ (?P<month>[0-9]{2})+ (-+ (?P<day>[0-9]+)+ (T+ (?P<hour>[0-9]{2}):+ (?P<minute>[0-9]{2})+ (:(?P<second>[0-9]{2}(.[0-9]+)?))?+ (?P<tzd>Z|[-+][0-9]{2}:[0-9]{2})+ )?+ )?+ )?+ """, re.VERBOSE)+++class XmpInformation(PdfObject):+ """+ An object that represents Adobe XMP metadata.+ Usually accessed by :meth:`getXmpMetadata()<PyPDF2.PdfFileReader.getXmpMetadata>`+ """++ def __init__(self, stream):+ self.stream = stream+ docRoot = parseString(self.stream.getData())+ self.rdfRoot = docRoot.getElementsByTagNameNS(RDF_NAMESPACE, "RDF")[0]+ self.cache = {}++ def writeToStream(self, stream, encryption_key):+ self.stream.writeToStream(stream, encryption_key)++ def getElement(self, aboutUri, namespace, name):+ for desc in self.rdfRoot.getElementsByTagNameNS(RDF_NAMESPACE, "Description"):+ if desc.getAttributeNS(RDF_NAMESPACE, "about") == aboutUri:+ attr = desc.getAttributeNodeNS(namespace, name)+ if attr != None:+ yield attr+ for element in desc.getElementsByTagNameNS(namespace, name):+ yield element++ def getNodesInNamespace(self, aboutUri, namespace):+ for desc in self.rdfRoot.getElementsByTagNameNS(RDF_NAMESPACE, "Description"):+ if desc.getAttributeNS(RDF_NAMESPACE, "about") == aboutUri:+ for i in range(desc.attributes.length):+ attr = desc.attributes.item(i)+ if attr.namespaceURI == namespace:+ yield attr+ for child in desc.childNodes:+ if child.namespaceURI == namespace:+ yield child++ def _getText(self, element):+ text = ""+ for child in element.childNodes:+ if child.nodeType == child.TEXT_NODE:+ text += child.data+ return text++ def _converter_string(value):+ return value++ def _converter_date(value):+ m = iso8601.match(value)+ year = int(m.group("year"))+ month = int(m.group("month") or "1")+ day = int(m.group("day") or "1")+ hour = int(m.group("hour") or "0")+ minute = int(m.group("minute") or "0")+ second = decimal.Decimal(m.group("second") or "0")+ seconds = second.to_integral(decimal.ROUND_FLOOR)+ milliseconds = (second - seconds) * 1000000+ tzd = m.group("tzd") or "Z"+ dt = datetime.datetime(year, month, day, hour, minute, seconds, milliseconds)+ if tzd != "Z":+ tzd_hours, tzd_minutes = [int(x) for x in tzd.split(":")]+ tzd_hours *= -1+ if tzd_hours < 0:+ tzd_minutes *= -1+ dt = dt + datetime.timedelta(hours=tzd_hours, minutes=tzd_minutes)+ return dt+ _test_converter_date = staticmethod(_converter_date)++ def _getter_bag(namespace, name, converter):+ def get(self):+ cached = self.cache.get(namespace, {}).get(name)+ if cached:+ return cached+ retval = []+ for element in self.getElement("", namespace, name):+ bags = element.getElementsByTagNameNS(RDF_NAMESPACE, "Bag")+ if len(bags):+ for bag in bags:+ for item in bag.getElementsByTagNameNS(RDF_NAMESPACE, "li"):+ value = self._getText(item)+ value = converter(value)+ retval.append(value)+ ns_cache = self.cache.setdefault(namespace, {})+ ns_cache[name] = retval+ return retval+ return get++ def _getter_seq(namespace, name, converter):+ def get(self):+ cached = self.cache.get(namespace, {}).get(name)+ if cached:+ return cached+ retval = []+ for element in self.getElement("", namespace, name):+ seqs = element.getElementsByTagNameNS(RDF_NAMESPACE, "Seq")+ if len(seqs):+ for seq in seqs:+ for item in seq.getElementsByTagNameNS(RDF_NAMESPACE, "li"):+ value = self._getText(item)+ value = converter(value)+ retval.append(value)+ else:+ value = converter(self._getText(element))+ retval.append(value)+ ns_cache = self.cache.setdefault(namespace, {})+ ns_cache[name] = retval+ return retval+ return get++ def _getter_langalt(namespace, name, converter):+ def get(self):+ cached = self.cache.get(namespace, {}).get(name)+ if cached:+ return cached+ retval = {}+ for element in self.getElement("", namespace, name):+ alts = element.getElementsByTagNameNS(RDF_NAMESPACE, "Alt")+ if len(alts):+ for alt in alts:+ for item in alt.getElementsByTagNameNS(RDF_NAMESPACE, "li"):+ value = self._getText(item)+ value = converter(value)+ retval[item.getAttribute("xml:lang")] = value+ else:+ retval["x-default"] = converter(self._getText(element))+ ns_cache = self.cache.setdefault(namespace, {})+ ns_cache[name] = retval+ return retval+ return get++ def _getter_single(namespace, name, converter):+ def get(self):+ cached = self.cache.get(namespace, {}).get(name)+ if cached:+ return cached+ value = None+ for element in self.getElement("", namespace, name):+ if element.nodeType == element.ATTRIBUTE_NODE:+ value = element.nodeValue+ else:+ value = self._getText(element)+ break+ if value != None:+ value = converter(value)+ ns_cache = self.cache.setdefault(namespace, {})+ ns_cache[name] = value+ return value+ return get++ dc_contributor = property(_getter_bag(DC_NAMESPACE, "contributor", _converter_string))+ """+ Contributors to the resource (other than the authors). An unsorted+ array of names.+ """++ dc_coverage = property(_getter_single(DC_NAMESPACE, "coverage", _converter_string))+ """+ Text describing the extent or scope of the resource.+ """++ dc_creator = property(_getter_seq(DC_NAMESPACE, "creator", _converter_string))+ """+ A sorted array of names of the authors of the resource, listed in order+ of precedence.+ """++ dc_date = property(_getter_seq(DC_NAMESPACE, "date", _converter_date))+ """+ A sorted array of dates (datetime.datetime instances) of signifigance to+ the resource. The dates and times are in UTC.+ """++ dc_description = property(_getter_langalt(DC_NAMESPACE, "description", _converter_string))+ """+ A language-keyed dictionary of textual descriptions of the content of the+ resource.+ """++ dc_format = property(_getter_single(DC_NAMESPACE, "format", _converter_string))+ """+ The mime-type of the resource.+ """++ dc_identifier = property(_getter_single(DC_NAMESPACE, "identifier", _converter_string))+ """+ Unique identifier of the resource.+ """++ dc_language = property(_getter_bag(DC_NAMESPACE, "language", _converter_string))+ """+ An unordered array specifying the languages used in the resource.+ """++ dc_publisher = property(_getter_bag(DC_NAMESPACE, "publisher", _converter_string))+ """+ An unordered array of publisher names.+ """++ dc_relation = property(_getter_bag(DC_NAMESPACE, "relation", _converter_string))+ """+ An unordered array of text descriptions of relationships to other+ documents.+ """++ dc_rights = property(_getter_langalt(DC_NAMESPACE, "rights", _converter_string))+ """+ A language-keyed dictionary of textual descriptions of the rights the+ user has to this resource.+ """++ dc_source = property(_getter_single(DC_NAMESPACE, "source", _converter_string))+ """+ Unique identifier of the work from which this resource was derived.+ """++ dc_subject = property(_getter_bag(DC_NAMESPACE, "subject", _converter_string))+ """+ An unordered array of descriptive phrases or keywrods that specify the+ topic of the content of the resource.+ """++ dc_title = property(_getter_langalt(DC_NAMESPACE, "title", _converter_string))+ """+ A language-keyed dictionary of the title of the resource.+ """++ dc_type = property(_getter_bag(DC_NAMESPACE, "type", _converter_string))+ """+ An unordered array of textual descriptions of the document type.+ """++ pdf_keywords = property(_getter_single(PDF_NAMESPACE, "Keywords", _converter_string))+ """+ An unformatted text string representing document keywords.+ """++ pdf_pdfversion = property(_getter_single(PDF_NAMESPACE, "PDFVersion", _converter_string))+ """+ The PDF file version, for example 1.0, 1.3.+ """++ pdf_producer = property(_getter_single(PDF_NAMESPACE, "Producer", _converter_string))+ """+ The name of the tool that created the PDF document.+ """++ xmp_createDate = property(_getter_single(XMP_NAMESPACE, "CreateDate", _converter_date))+ """+ The date and time the resource was originally created. The date and+ time are returned as a UTC datetime.datetime object.+ """++ xmp_modifyDate = property(_getter_single(XMP_NAMESPACE, "ModifyDate", _converter_date))+ """+ The date and time the resource was last modified. The date and time+ are returned as a UTC datetime.datetime object.+ """++ xmp_metadataDate = property(_getter_single(XMP_NAMESPACE, "MetadataDate", _converter_date))+ """+ The date and time that any metadata for this resource was last+ changed. The date and time are returned as a UTC datetime.datetime+ object.+ """++ xmp_creatorTool = property(_getter_single(XMP_NAMESPACE, "CreatorTool", _converter_string))+ """+ The name of the first known tool used to create the resource.+ """++ xmpmm_documentId = property(_getter_single(XMPMM_NAMESPACE, "DocumentID", _converter_string))+ """+ The common identifier for all versions and renditions of this resource.+ """++ xmpmm_instanceId = property(_getter_single(XMPMM_NAMESPACE, "InstanceID", _converter_string))+ """+ An identifier for a specific incarnation of a document, updated each+ time a file is saved.+ """++ def custom_properties(self):+ if not hasattr(self, "_custom_properties"):+ self._custom_properties = {}+ for node in self.getNodesInNamespace("", PDFX_NAMESPACE):+ key = node.localName+ while True:+ # see documentation about PDFX_NAMESPACE earlier in file+ idx = key.find(u_("\u2182"))+ if idx == -1:+ break+ key = key[:idx] + chr(int(key[idx+1:idx+5], base=16)) + key[idx+5:]+ if node.nodeType == node.ATTRIBUTE_NODE:+ value = node.nodeValue+ else:+ value = self._getText(node)+ self._custom_properties[key] = value+ return self._custom_properties++ custom_properties = property(custom_properties)+ """+ Retrieves custom metadata properties defined in the undocumented pdfx+ metadata schema.++ :return: a dictionary of key/value items for custom metadata properties.+ :rtype: dict+ """diff --git a/ext/metapdf/__init__.py b/ext/metapdf/__init__.pydeleted file mode 100644index 96b926c0..00000000--- a/ext/metapdf/__init__.py+++ /dev/null@@ -1,2 +0,0 @@-from metapdf import MetaPdfReader-__all__ = ["metapdf"]diff --git a/ext/metapdf/metapdf.py b/ext/metapdf/metapdf.pydeleted file mode 100755index 7352ce8a..00000000--- a/ext/metapdf/metapdf.py+++ /dev/null@@ -1,78 +0,0 @@-#!/usr/bin/env python-# -*- coding: utf-8 -*--#-# Copyright (c) 2012 Ali Anari-#-# Permission is hereby granted, free of charge, to any person obtaining a copy-# of this software and associated documentation files (the "Software"), to deal-# in the Software without restriction, including without limitation the rights-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell-# copies of the Software, and to permit persons to whom the Software is-# furnished to do so, subject to the following conditions:--# The above copyright notice and this permission notice shall be included in-# all copies or substantial portions of the Software.--# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE-# SOFTWARE.---"""-.. module:: metapdf- :platform: Unix, Windows- :synopsis: The metapdf class implementation.--.. moduleauthor:: Ali Anari <[email protected]>--"""--__author__ = "Ali Anari"-__author_email__ = "[email protected]"---import os, re-from pyPdf import PdfFileReader---class _meta_pdf_reader(object):-- def __init__(self):- self.instance = self.__hash__()- self.metadata_regex = re.compile('(?:\/(\w+)\s?\(([^\n\r]*)\)\n?\r?)', re.S)- self.metadata_offset = 2048-- def read_metadata(self, stream):-- """This function reads a PDF file stream and returns its metadata.- :param file_name: The PDF file stream to read.- :type file_name: str- :returns: dict -- The returned metadata as a dictionary of properties.-- """-- # Scan the last 2048 bytes, the most- # frequent metadata density block- stream.seek(-self.metadata_offset, os.SEEK_END)- properties = dict()- try:- properties = dict(('/' + p.group(1), p.group(2).decode('utf-8')) \- for p in self.metadata_regex.finditer(stream.read(self.metadata_offset)))- if '/Author' in properties:- return properties- except UnicodeDecodeError:- properties.clear()-- # Parse the xref table using pyPdf- properties = PdfFileReader(stream).documentInfo- if properties:- return properties-- return {}--_metaPdfReader = _meta_pdf_reader()-def MetaPdfReader(): return _metaPdfReaderdiff --git a/ext/pyPdf/__init__.py b/ext/pyPdf/__init__.pydeleted file mode 100644index af02553d..00000000--- a/ext/pyPdf/__init__.py+++ /dev/null@@ -1,2 +0,0 @@-from pdf import PdfFileReader, PdfFileWriter-__all__ = ["pdf"]diff --git a/ext/pyPdf/filters.py b/ext/pyPdf/filters.pydeleted file mode 100644index 7fe10fb4..00000000--- a/ext/pyPdf/filters.py+++ /dev/null@@ -1,252 +0,0 @@-# vim: sw=4:expandtab:foldmethod=marker-#-# Copyright (c) 2006, Mathieu Fenniak-# All rights reserved.-#-# Redistribution and use in source and binary forms, with or without-# modification, are permitted provided that the following conditions are-# met:-#-# * Redistributions of source code must retain the above copyright notice,-# this list of conditions and the following disclaimer.-# * Redistributions in binary form must reproduce the above copyright notice,-# this list of conditions and the following disclaimer in the documentation-# and/or other materials provided with the distribution.-# * The name of the author may not be used to endorse or promote products-# derived from this software without specific prior written permission.-#-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"-# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE-# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE-# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR-# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF-# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS-# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN-# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)-# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE-# POSSIBILITY OF SUCH DAMAGE.---"""-Implementation of stream filters for PDF.-"""-__author__ = "Mathieu Fenniak"-__author_email__ = "[email protected]"--from utils import PdfReadError-try:- from cStringIO import StringIO-except ImportError:- from StringIO import StringIO--try:- import zlib- def decompress(data):- return zlib.decompress(data)- def compress(data):- return zlib.compress(data)-except ImportError:- # Unable to import zlib. Attempt to use the System.IO.Compression- # library from the .NET framework. (IronPython only)- import System- from System import IO, Collections, Array- def _string_to_bytearr(buf):- retval = Array.CreateInstance(System.Byte, len(buf))- for i in range(len(buf)):- retval[i] = ord(buf[i])- return retval- def _bytearr_to_string(bytes):- retval = ""- for i in range(bytes.Length):- retval += chr(bytes[i])- return retval- def _read_bytes(stream):- ms = IO.MemoryStream()- buf = Array.CreateInstance(System.Byte, 2048)- while True:- bytes = stream.Read(buf, 0, buf.Length)- if bytes == 0:- break- else:- ms.Write(buf, 0, bytes)- retval = ms.ToArray()- ms.Close()- return retval- def decompress(data):- bytes = _string_to_bytearr(data)- ms = IO.MemoryStream()- ms.Write(bytes, 0, bytes.Length)- ms.Position = 0 # fseek 0- gz = IO.Compression.DeflateStream(ms, IO.Compression.CompressionMode.Decompress)- bytes = _read_bytes(gz)- retval = _bytearr_to_string(bytes)- gz.Close()- return retval- def compress(data):- bytes = _string_to_bytearr(data)- ms = IO.MemoryStream()- gz = IO.Compression.DeflateStream(ms, IO.Compression.CompressionMode.Compress, True)- gz.Write(bytes, 0, bytes.Length)- gz.Close()- ms.Position = 0 # fseek 0- bytes = ms.ToArray()- retval = _bytearr_to_string(bytes)- ms.Close()- return retval---class FlateDecode(object):- def decode(data, decodeParms):- data = decompress(data)- predictor = 1- if decodeParms:- predictor = decodeParms.get("/Predictor", 1)- # predictor 1 == no predictor- if predictor != 1:- columns = decodeParms["/Columns"]- # PNG prediction:- if predictor >= 10 and predictor <= 15:- output = StringIO()- # PNG prediction can vary from row to row- rowlength = columns + 1- assert len(data) % rowlength == 0- prev_rowdata = (0,) * rowlength- for row in xrange(len(data) / rowlength):- rowdata = [ord(x) for x in data[(row*rowlength):((row+1)*rowlength)]]- filterByte = rowdata[0]- if filterByte == 0:- pass- elif filterByte == 1:- for i in range(2, rowlength):- rowdata[i] = (rowdata[i] + rowdata[i-1]) % 256- elif filterByte == 2:- for i in range(1, rowlength):- rowdata[i] = (rowdata[i] + prev_rowdata[i]) % 256- else:- # unsupported PNG filter- raise PdfReadError("Unsupported PNG filter %r" % filterByte)- prev_rowdata = rowdata- output.write(''.join([chr(x) for x in rowdata[1:]]))- data = output.getvalue()- else:- # unsupported predictor- raise PdfReadError("Unsupported flatedecode predictor %r" % predictor)- return data- decode = staticmethod(decode)-- def encode(data):- return compress(data)- encode = staticmethod(encode)--class ASCIIHexDecode(object):- def decode(data, decodeParms=None):- retval = ""- char = ""- x = 0- while True:- c = data[x]- if c == ">":- break- elif c.isspace():- x += 1- continue- char += c- if len(char) == 2:- retval += chr(int(char, base=16))- char = ""- x += 1- assert char == ""- return retval- decode = staticmethod(decode)--class ASCII85Decode(object):- def decode(data, decodeParms=None):- retval = ""- group = []- x = 0- hitEod = False- # remove all whitespace from data- data = [y for y in data if not (y in ' \n\r\t')]- while not hitEod:- c = data[x]- if len(retval) == 0 and c == "<" and data[x+1] == "~":- x += 2- continue- #elif c.isspace():- # x += 1- # continue- elif c == 'z':- assert len(group) == 0- retval += '\x00\x00\x00\x00'- continue- elif c == "~" and data[x+1] == ">":- if len(group) != 0:- # cannot have a final group of just 1 char- assert len(group) > 1- cnt = len(group) - 1- group += [ 85, 85, 85 ]- hitEod = cnt- else:- break- else:- c = ord(c) - 33- assert c >= 0 and c < 85- group += [ c ]- if len(group) >= 5:- b = group[0] * (85**4) + \- group[1] * (85**3) + \- group[2] * (85**2) + \- group[3] * 85 + \- group[4]- assert b < (2**32 - 1)- c4 = chr((b >> 0) % 256)- c3 = chr((b >> 8) % 256)- c2 = chr((b >> 16) % 256)- c1 = chr(b >> 24)- retval += (c1 + c2 + c3 + c4)- if hitEod:- retval = retval[:-4+hitEod]- group = []- x += 1- return retval- decode = staticmethod(decode)--def decodeStreamData(stream):- from generic import NameObject- filters = stream.get("/Filter", ())- if len(filters) and not isinstance(filters[0], NameObject):- # we have a single filter instance- filters = (filters,)- data = stream._data- for filterType in filters:- if filterType == "/FlateDecode":- data = FlateDecode.decode(data, stream.get("/DecodeParms"))- elif filterType == "/ASCIIHexDecode":- data = ASCIIHexDecode.decode(data)- elif filterType == "/ASCII85Decode":- data = ASCII85Decode.decode(data)- elif filterType == "/Crypt":- decodeParams = stream.get("/DecodeParams", {})- if "/Name" not in decodeParams and "/Type" not in decodeParams:- pass- else:- raise NotImplementedError("/Crypt filter with /Name or /Type not supported yet")- else:- # unsupported filter- raise NotImplementedError("unsupported filter %s" % filterType)- return data--if __name__ == "__main__":- assert "abc" == ASCIIHexDecode.decode('61\n626\n3>')-- ascii85Test = """- <~9jqo^BlbD-BleB1DJ+*+F(f,q/0JhKF<GL>[email protected]$d7F!,L7@<6@)/0JDEF<G%<+EV:2F!,- O<DJ+*.@<*K0@<6L(Df-\\0Ec5e;DffZ(EZee.Bl.9pF"AGXBPCsi+DGm>@3BB/F*&OCAfu2/AKY- i(DIb:@FD,*)+C]U=@3BN#EcYf8ATD3s@q?d$AftVqCh[NqF<G:8+EV:.+Cf>-FD5W8ARlolDIa- l(DId<j@<?3r@:F%a+D58'ATD4$Bl@l3De:,-DJs`8ARoFb/0JMK@qB4^F!,R<AKZ&-DfTqBG%G- >uD.RTpAKYo'+CT/5+Cei#DII?(E,9)oF*2M7/c~>- """- ascii85_originalText="Man is distinguished, not only by his reason, but by this singular passion from other animals, which is a lust of the mind, that by a perseverance of delight in the continued and indefatigable generation of knowledge, exceeds the short vehemence of any carnal pleasure."- assert ASCII85Decode.decode(ascii85Test) == ascii85_originalText-diff --git a/ext/pyPdf/generic.py b/ext/pyPdf/generic.pydeleted file mode 100644index aaf50318..00000000--- a/ext/pyPdf/generic.py+++ /dev/null@@ -1,800 +0,0 @@-# vim: sw=4:expandtab:foldmethod=marker-#-# Copyright (c) 2006, Mathieu Fenniak-# All rights reserved.-#-# Redistribution and use in source and binary forms, with or without-# modification, are permitted provided that the following conditions are-# met:-#-# * Redistributions of source code must retain the above copyright notice,-# this list of conditions and the following disclaimer.-# * Redistributions in binary form must reproduce the above copyright notice,-# this list of conditions and the following disclaimer in the documentation-# and/or other materials provided with the distribution.-# * The name of the author may not be used to endorse or promote products-# derived from this software without specific prior written permission.-#-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"-# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE-# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE-# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR-# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF-# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS-# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN-# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)-# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE-# POSSIBILITY OF SUCH DAMAGE.---"""-Implementation of generic PDF objects (dictionary, number, string, and so on)-"""-__author__ = "Mathieu Fenniak"-__author_email__ = "[email protected]"--import re-from utils import readNonWhitespace, RC4_encrypt-import filters-import utils-import decimal-import codecs--def readObject(stream, pdf):- tok = stream.read(1)- stream.seek(-1, 1) # reset to start- if tok == 't' or tok == 'f':- # boolean object- return BooleanObject.readFromStream(stream)- elif tok == '(':- # string object- return readStringFromStream(stream)- elif tok == '/':- # name object- return NameObject.readFromStream(stream)- elif tok == '[':- # array object- return ArrayObject.readFromStream(stream, pdf)- elif tok == 'n':- # null object- return NullObject.readFromStream(stream)- elif tok == '<':- # hexadecimal string OR dictionary- peek = stream.read(2)- stream.seek(-2, 1) # reset to start- if peek == '<<':- return DictionaryObject.readFromStream(stream, pdf)- else:- return readHexStringFromStream(stream)- elif tok == '%':- # comment- while tok not in ('\r', '\n'):- tok = stream.read(1)- tok = readNonWhitespace(stream)- stream.seek(-1, 1)- return readObject(stream, pdf)- else:- # number object OR indirect reference- if tok == '+' or tok == '-':- # number- return NumberObject.readFromStream(stream)- peek = stream.read(20)- stream.seek(-len(peek), 1) # reset to start- if re.match(r"(\d+)\s(\d+)\sR[^a-zA-Z]", peek) != None:- return IndirectObject.readFromStream(stream, pdf)- else:- return NumberObject.readFromStream(stream)--class PdfObject(object):- def getObject(self):- """Resolves indirect references."""- return self---class NullObject(PdfObject):- def writeToStream(self, stream, encryption_key):- stream.write("null")-- def readFromStream(stream):- nulltxt = stream.read(4)- if nulltxt != "null":- raise utils.PdfReadError, "error reading null object"- return NullObject()- readFromStream = staticmethod(readFromStream)---class BooleanObject(PdfObject):- def __init__(self, value):- self.value = value-- def writeToStream(self, stream, encryption_key):- if self.value:- stream.write("true")- else:- stream.write("false")-- def readFromStream(stream):- word = stream.read(4)- if word == "true":- return BooleanObject(True)- elif word == "fals":- stream.read(1)- return BooleanObject(False)- assert False- readFromStream = staticmethod(readFromStream)---class ArrayObject(list, PdfObject):- def writeToStream(self, stream, encryption_key):- stream.write("[")- for data in self:- stream.write(" ")- data.writeToStream(stream, encryption_key)- stream.write(" ]")-- def readFromStream(stream, pdf):- arr = ArrayObject()- tmp = stream.read(1)- if tmp != "[":- raise utils.PdfReadError, "error reading array"- while True:- # skip leading whitespace- tok = stream.read(1)- while tok.isspace():- tok = stream.read(1)- stream.seek(-1, 1)- # check for array ending- peekahead = stream.read(1)- if peekahead == "]":- break- stream.seek(-1, 1)- # read and append obj- arr.append(readObject(stream, pdf))- return arr- readFromStream = staticmethod(readFromStream)---class IndirectObject(PdfObject):- def __init__(self, idnum, generation, pdf):- self.idnum = idnum- self.generation = generation- self.pdf = pdf-- def getObject(self):- return self.pdf.getObject(self).getObject()-- def __repr__(self):- return "IndirectObject(%r, %r)" % (self.idnum, self.generation)-- def __eq__(self, other):- return (- other != None and- isinstance(other, IndirectObject) and- self.idnum == other.idnum and- self.generation == other.generation and- self.pdf is other.pdf- )-- def __ne__(self, other):- return not self.__eq__(other)-- def writeToStream(self, stream, encryption_key):- stream.write("%s %s R" % (self.idnum, self.generation))-- def readFromStream(stream, pdf):- idnum = ""- while True:- tok = stream.read(1)- if tok.isspace():- break- idnum += tok- generation = ""- while True:- tok = stream.read(1)- if tok.isspace():- break- generation += tok- r = stream.read(1)- if r != "R":- raise utils.PdfReadError("error reading indirect object reference")- return IndirectObject(int(idnum), int(generation), pdf)- readFromStream = staticmethod(readFromStream)---class FloatObject(decimal.Decimal, PdfObject):- def __new__(cls, value="0", context=None):- return decimal.Decimal.__new__(cls, str(value), context)- def __repr__(self):- if self == self.to_integral():- return str(self.quantize(decimal.Decimal(1)))- else:- # XXX: this adds useless extraneous zeros.- return "%.5f" % self- def writeToStream(self, stream, encryption_key):- stream.write(repr(self))---class NumberObject(int, PdfObject):- def __init__(self, value):- int.__init__(value)-- def writeToStream(self, stream, encryption_key):- stream.write(repr(self))-- def readFromStream(stream):- name = ""- while True:- tok = stream.read(1)- if tok != '+' and tok != '-' and tok != '.' and not tok.isdigit():- stream.seek(-1, 1)- break- name += tok- if name.find(".") != -1:- return FloatObject(name)- else:- return NumberObject(name)- readFromStream = staticmethod(readFromStream)---##-# Given a string (either a "str" or "unicode"), create a ByteStringObject or a-# TextStringObject to represent the string.-def createStringObject(string):- if isinstance(string, unicode):- return TextStringObject(string)- elif isinstance(string, str):- if string.startswith(codecs.BOM_UTF16_BE):- retval = TextStringObject(string.decode("utf-16"))- retval.autodetect_utf16 = True- return retval- else:- # This is probably a big performance hit here, but we need to- # convert string objects into the text/unicode-aware version if- # possible... and the only way to check if that's possible is- # to try. Some strings are strings, some are just byte arrays.- try:- retval = TextStringObject(decode_pdfdocencoding(string))- retval.autodetect_pdfdocencoding = True- return retval- except UnicodeDecodeError:- return ByteStringObject(string)- else:- raise TypeError("createStringObject should have str or unicode arg")---def readHexStringFromStream(stream):- stream.read(1)- txt = ""- x = ""- while True:- tok = readNonWhitespace(stream)- if tok == ">":- break- x += tok- if len(x) == 2:- txt += chr(int(x, base=16))- x = ""- if len(x) == 1:- x += "0"- if len(x) == 2:- txt += chr(int(x, base=16))- return createStringObject(txt)---def readStringFromStream(stream):- tok = stream.read(1)- parens = 1- txt = ""- while True:- tok = stream.read(1)- if tok == "(":- parens += 1- elif tok == ")":- parens -= 1- if parens == 0:- break- elif tok == "\\":- tok = stream.read(1)- if tok == "n":- tok = "\n"- elif tok == "r":- tok = "\r"- elif tok == "t":- tok = "\t"- elif tok == "b":- tok = "\b"- elif tok == "f":- tok = "\f"- elif tok == "(":- tok = "("- elif tok == ")":- tok = ")"- elif tok == "\\":- tok = "\\"- elif tok.isdigit():- # "The number ddd may consist of one, two, or three- # octal digits; high-order overflow shall be ignored.- # Three octal digits shall be used, with leading zeros- # as needed, if the next character of the string is also- # a digit." (PDF reference 7.3.4.2, p 16)- for i in range(2):- ntok = stream.read(1)- if ntok.isdigit():- tok += ntok- else:- break- tok = chr(int(tok, base=8))- elif tok in "\n\r":- # This case is hit when a backslash followed by a line- # break occurs. If it's a multi-char EOL, consume the- # second character:- tok = stream.read(1)- if not tok in "\n\r":- stream.seek(-1, 1)- # Then don't add anything to the actual string, since this- # line break was escaped:- tok = ''- else:- raise utils.PdfReadError("Unexpected escaped string")- txt += tok- return createStringObject(txt)---##-# Represents a string object where the text encoding could not be determined.-# This occurs quite often, as the PDF spec doesn't provide an alternate way to-# represent strings -- for example, the encryption data stored in files (like-# /O) is clearly not text, but is still stored in a "String" object.-class ByteStringObject(str, PdfObject):-- ##- # For compatibility with TextStringObject.original_bytes. This method- # returns self.- original_bytes = property(lambda self: self)-- def writeToStream(self, stream, encryption_key):- bytearr = self- if encryption_key:- bytearr = RC4_encrypt(encryption_key, bytearr)- stream.write("<")- stream.write(bytearr.encode("hex"))- stream.write(">")---##-# Represents a string object that has been decoded into a real unicode string.-# If read from a PDF document, this string appeared to match the-# PDFDocEncoding, or contained a UTF-16BE BOM mark to cause UTF-16 decoding to-# occur.-class TextStringObject(unicode, PdfObject):- autodetect_pdfdocencoding = False- autodetect_utf16 = False-- ##- # It is occasionally possible that a text string object gets created where- # a byte string object was expected due to the autodetection mechanism --- # if that occurs, this "original_bytes" property can be used to- # back-calculate what the original encoded bytes were.- original_bytes = property(lambda self: self.get_original_bytes())-- def get_original_bytes(self):- # We're a text string object, but the library is trying to get our raw- # bytes. This can happen if we auto-detected this string as text, but- # we were wrong. It's pretty common. Return the original bytes that- # would have been used to create this object, based upon the autodetect- # method.- if self.autodetect_utf16:- return codecs.BOM_UTF16_BE + self.encode("utf-16be")- elif self.autodetect_pdfdocencoding:- return encode_pdfdocencoding(self)- else:- raise Exception("no information about original bytes")-- def writeToStream(self, stream, encryption_key):- # Try to write the string out as a PDFDocEncoding encoded string. It's- # nicer to look at in the PDF file. Sadly, we take a performance hit- # here for trying...- try:- bytearr = encode_pdfdocencoding(self)- except UnicodeEncodeError:- bytearr = codecs.BOM_UTF16_BE + self.encode("utf-16be")- if encryption_key:- bytearr = RC4_encrypt(encryption_key, bytearr)- obj = ByteStringObject(bytearr)- obj.writeToStream(stream, None)- else:- stream.write("(")- for c in bytearr:- if not c.isalnum() and c != ' ':- stream.write("\\%03o" % ord(c))- else:- stream.write(c)- stream.write(")")---class NameObject(str, PdfObject):- delimiterCharacters = "(", ")", "<", ">", "[", "]", "{", "}", "/", "%"-- def __init__(self, data):- str.__init__(data)-- def writeToStream(self, stream, encryption_key):- stream.write(self)-- def readFromStream(stream):- name = stream.read(1)- if name != "/":- raise utils.PdfReadError, "name read error"- while True:- tok = stream.read(1)- if tok.isspace() or tok in NameObject.delimiterCharacters:- stream.seek(-1, 1)- break- name += tok- return NameObject(name)- readFromStream = staticmethod(readFromStream)---class DictionaryObject(dict, PdfObject):-- def __init__(self, *args, **kwargs):- if len(args) == 0:- self.update(kwargs)- elif len(args) == 1:- arr = args[0]- # If we're passed a list/tuple, make a dict out of it- if not hasattr(arr, "iteritems"):- newarr = {}- for k, v in arr:- newarr[k] = v- arr = newarr- self.update(arr)- else:- raise TypeError("dict expected at most 1 argument, got 3")-- def update(self, arr):- # note, a ValueError halfway through copying values- # will leave half the values in this dict.- for k, v in arr.iteritems():- self.__setitem__(k, v)-- def raw_get(self, key):- return dict.__getitem__(self, key)-- def __setitem__(self, key, value):- if not isinstance(key, PdfObject):- raise ValueError("key must be PdfObject")- if not isinstance(value, PdfObject):- raise ValueError("value must be PdfObject")- return dict.__setitem__(self, key, value)-- def setdefault(self, key, value=None):- if not isinstance(key, PdfObject):- raise ValueError("key must be PdfObject")- if not isinstance(value, PdfObject):- raise ValueError("value must be PdfObject")- return dict.setdefault(self, key, value)-- def __getitem__(self, key):- return dict.__getitem__(self, key).getObject()-- ##- # Retrieves XMP (Extensible Metadata Platform) data relevant to the- # this object, if available.- # <p>- # Stability: Added in v1.12, will exist for all future v1.x releases.- # @return Returns a {@link #xmp.XmpInformation XmlInformation} instance- # that can be used to access XMP metadata from the document. Can also- # return None if no metadata was found on the document root.- def getXmpMetadata(self):- metadata = self.get("/Metadata", None)- if metadata == None:- return None- metadata = metadata.getObject()- import xmp- if not isinstance(metadata, xmp.XmpInformation):- metadata = xmp.XmpInformation(metadata)- self[NameObject("/Metadata")] = metadata- return metadata-- ##- # Read-only property that accesses the {@link- # #DictionaryObject.getXmpData getXmpData} function.- # <p>- # Stability: Added in v1.12, will exist for all future v1.x releases.- xmpMetadata = property(lambda self: self.getXmpMetadata(), None, None)-- def writeToStream(self, stream, encryption_key):- stream.write("<<\n")- for key, value in self.items():- key.writeToStream(stream, encryption_key)- stream.write(" ")- value.writeToStream(stream, encryption_key)- stream.write("\n")- stream.write(">>")-- def readFromStream(stream, pdf):- tmp = stream.read(2)- if tmp != "<<":- raise utils.PdfReadError, "dictionary read error"- data = {}- while True:- tok = readNonWhitespace(stream)- 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"- 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 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) != "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:- stream.seek(pos, 0)- raise utils.PdfReadError, "Unable to find 'endstream' marker after stream."- else:- stream.seek(pos, 0)- if data.has_key("__streamdata__"):- return StreamObject.initializeFromDictionary(data)- else:- retval = DictionaryObject()- retval.update(data)- return retval- readFromStream = staticmethod(readFromStream)---class StreamObject(DictionaryObject):- def __init__(self):- self._data = None- self.decodedSelf = None-- def writeToStream(self, stream, encryption_key):- self[NameObject("/Length")] = NumberObject(len(self._data))- DictionaryObject.writeToStream(self, stream, encryption_key)- del self["/Length"]- stream.write("\nstream\n")- data = self._data- if encryption_key:- data = RC4_encrypt(encryption_key, data)- stream.write(data)- stream.write("\nendstream")-- def initializeFromDictionary(data):- if data.has_key("/Filter"):- retval = EncodedStreamObject()- else:- retval = DecodedStreamObject()- retval._data = data["__streamdata__"]- del data["__streamdata__"]- del data["/Length"]- retval.update(data)- return retval- initializeFromDictionary = staticmethod(initializeFromDictionary)-- def flateEncode(self):- if self.has_key("/Filter"):- f = self["/Filter"]- if isinstance(f, ArrayObject):- f.insert(0, NameObject("/FlateDecode"))- else:- newf = ArrayObject()- newf.append(NameObject("/FlateDecode"))- newf.append(f)- f = newf- else:- f = NameObject("/FlateDecode")- retval = EncodedStreamObject()- retval[NameObject("/Filter")] = f- retval._data = filters.FlateDecode.encode(self._data)- return retval---class DecodedStreamObject(StreamObject):- def getData(self):- return self._data-- def setData(self, data):- self._data = data---class EncodedStreamObject(StreamObject):- def __init__(self):- self.decodedSelf = None-- def getData(self):- if self.decodedSelf:- # cached version of decoded object- return self.decodedSelf.getData()- else:- # create decoded object- decoded = DecodedStreamObject()- decoded._data = filters.decodeStreamData(self)- for key, value in self.items():- if not key in ("/Length", "/Filter", "/DecodeParms"):- decoded[key] = value- self.decodedSelf = decoded- return decoded._data-- def setData(self, data):- raise utils.PdfReadError, "Creating EncodedStreamObject is not currently supported"---class RectangleObject(ArrayObject):- def __init__(self, arr):- # must have four points- assert len(arr) == 4- # automatically convert arr[x] into NumberObject(arr[x]) if necessary- ArrayObject.__init__(self, [self.ensureIsNumber(x) for x in arr])-- def ensureIsNumber(self, value):- if not isinstance(value, (NumberObject, FloatObject)):- value = FloatObject(value)- return value-- def __repr__(self):- return "RectangleObject(%s)" % repr(list(self))-- def getLowerLeft_x(self):- return self[0]-- def getLowerLeft_y(self):- return self[1]-- def getUpperRight_x(self):- return self[2]-- def getUpperRight_y(self):- return self[3]-- def getUpperLeft_x(self):- return self.getLowerLeft_x()-- def getUpperLeft_y(self):- return self.getUpperRight_y()-- def getLowerRight_x(self):- return self.getUpperRight_x()-- def getLowerRight_y(self):- return self.getLowerLeft_y()-- def getLowerLeft(self):- return self.getLowerLeft_x(), self.getLowerLeft_y()-- def getLowerRight(self):- return self.getLowerRight_x(), self.getLowerRight_y()-- def getUpperLeft(self):- return self.getUpperLeft_x(), self.getUpperLeft_y()-- def getUpperRight(self):- return self.getUpperRight_x(), self.getUpperRight_y()-- def setLowerLeft(self, value):- self[0], self[1] = [self.ensureIsNumber(x) for x in value]-- def setLowerRight(self, value):- self[2], self[1] = [self.ensureIsNumber(x) for x in value]-- def setUpperLeft(self, value):- self[0], self[3] = [self.ensureIsNumber(x) for x in value]-- def setUpperRight(self, value):- self[2], self[3] = [self.ensureIsNumber(x) for x in value]-- def getWidth(self):- return self.getUpperRight_x() - self.getLowerLeft_x()-- def getHeight(self):- return self.getUpperRight_y() - self.getLowerLeft_x()-- lowerLeft = property(getLowerLeft, setLowerLeft, None, None)- lowerRight = property(getLowerRight, setLowerRight, None, None)- upperLeft = property(getUpperLeft, setUpperLeft, None, None)- upperRight = property(getUpperRight, setUpperRight, None, None)---def encode_pdfdocencoding(unicode_string):- retval = ''- for c in unicode_string:- try:- retval += chr(_pdfDocEncoding_rev[c])- except KeyError:- raise UnicodeEncodeError("pdfdocencoding", c, -1, -1,- "does not exist in translation table")- return retval--def decode_pdfdocencoding(byte_array):- retval = u''- for b in byte_array:- c = _pdfDocEncoding[ord(b)]- if c == u'\u0000':- raise UnicodeDecodeError("pdfdocencoding", b, -1, -1,- "does not exist in translation table")- retval += c- return retval--_pdfDocEncoding = (- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',- u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000', u'\u0000',- u'\u02d8', u'\u02c7', u'\u02c6', u'\u02d9', u'\u02dd', u'\u02db', u'\u02da', u'\u02dc',- u'\u0020', u'\u0021', u'\u0022', u'\u0023', u'\u0024', u'\u0025', u'\u0026', u'\u0027',- u'\u0028', u'\u0029', u'\u002a', u'\u002b', u'\u002c', u'\u002d', u'\u002e', u'\u002f',- u'\u0030', u'\u0031', u'\u0032', u'\u0033', u'\u0034', u'\u0035', u'\u0036', u'\u0037',- u'\u0038', u'\u0039', u'\u003a', u'\u003b', u'\u003c', u'\u003d', u'\u003e', u'\u003f',- u'\u0040', u'\u0041', u'\u0042', u'\u0043', u'\u0044', u'\u0045', u'\u0046', u'\u0047',- u'\u0048', u'\u0049', u'\u004a', u'\u004b', u'\u004c', u'\u004d', u'\u004e', u'\u004f',- u'\u0050', u'\u0051', u'\u0052', u'\u0053', u'\u0054', u'\u0055', u'\u0056', u'\u0057',- u'\u0058', u'\u0059', u'\u005a', u'\u005b', u'\u005c', u'\u005d', u'\u005e', u'\u005f',- u'\u0060', u'\u0061', u'\u0062', u'\u0063', u'\u0064', u'\u0065', u'\u0066', u'\u0067',- u'\u0068', u'\u0069', u'\u006a', u'\u006b', u'\u006c', u'\u006d', u'\u006e', u'\u006f',- u'\u0070', u'\u0071', u'\u0072', u'\u0073', u'\u0074', u'\u0075', u'\u0076', u'\u0077',- u'\u0078', u'\u0079', u'\u007a', u'\u007b', u'\u007c', u'\u007d', u'\u007e', u'\u0000',- u'\u2022', u'\u2020', u'\u2021', u'\u2026', u'\u2014', u'\u2013', u'\u0192', u'\u2044',- u'\u2039', u'\u203a', u'\u2212', u'\u2030', u'\u201e', u'\u201c', u'\u201d', u'\u2018',- u'\u2019', u'\u201a', u'\u2122', u'\ufb01', u'\ufb02', u'\u0141', u'\u0152', u'\u0160',- u'\u0178', u'\u017d', u'\u0131', u'\u0142', u'\u0153', u'\u0161', u'\u017e', u'\u0000',- u'\u20ac', u'\u00a1', u'\u00a2', u'\u00a3', u'\u00a4', u'\u00a5', u'\u00a6', u'\u00a7',- u'\u00a8', u'\u00a9', u'\u00aa', u'\u00ab', u'\u00ac', u'\u0000', u'\u00ae', u'\u00af',- u'\u00b0', u'\u00b1', u'\u00b2', u'\u00b3', u'\u00b4', u'\u00b5', u'\u00b6', u'\u00b7',- u'\u00b8', u'\u00b9', u'\u00ba', u'\u00bb', u'\u00bc', u'\u00bd', u'\u00be', u'\u00bf',- u'\u00c0', u'\u00c1', u'\u00c2', u'\u00c3', u'\u00c4', u'\u00c5', u'\u00c6', u'\u00c7',- u'\u00c8', u'\u00c9', u'\u00ca', u'\u00cb', u'\u00cc', u'\u00cd', u'\u00ce', u'\u00cf',- u'\u00d0', u'\u00d1', u'\u00d2', u'\u00d3', u'\u00d4', u'\u00d5', u'\u00d6', u'\u00d7',- u'\u00d8', u'\u00d9', u'\u00da', u'\u00db', u'\u00dc', u'\u00dd', u'\u00de', u'\u00df',- u'\u00e0', u'\u00e1', u'\u00e2', u'\u00e3', u'\u00e4', u'\u00e5', u'\u00e6', u'\u00e7',- u'\u00e8', u'\u00e9', u'\u00ea', u'\u00eb', u'\u00ec', u'\u00ed', u'\u00ee', u'\u00ef',- u'\u00f0', u'\u00f1', u'\u00f2', u'\u00f3', u'\u00f4', u'\u00f5', u'\u00f6', u'\u00f7',- u'\u00f8', u'\u00f9', u'\u00fa', u'\u00fb', u'\u00fc', u'\u00fd', u'\u00fe', u'\u00ff'-)--assert len(_pdfDocEncoding) == 256--_pdfDocEncoding_rev = {}-for i in xrange(256):- char = _pdfDocEncoding[i]- if char == u"\u0000":- continue- assert char not in _pdfDocEncoding_rev- _pdfDocEncoding_rev[char] = i-diff --git a/ext/pyPdf/pdf.py b/ext/pyPdf/pdf.pydeleted file mode 100644index bf60d015..00000000--- a/ext/pyPdf/pdf.py+++ /dev/null@@ -1,1871 +0,0 @@-# -*- coding: utf-8 -*--#-# vim: sw=4:expandtab:foldmethod=marker-#-# Copyright (c) 2006, Mathieu Fenniak-# Copyright (c) 2007, Ashish Kulkarni <[email protected]>-#-# All rights reserved.-#-# Redistribution and use in source and binary forms, with or without-# modification, are permitted provided that the following conditions are-# met:-#-# * Redistributions of source code must retain the above copyright notice,-# this list of conditions and the following disclaimer.-# * Redistributions in binary form must reproduce the above copyright notice,-# this list of conditions and the following disclaimer in the documentation-# and/or other materials provided with the distribution.-# * The name of the author may not be used to endorse or promote products-# derived from this software without specific prior written permission.-#-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"-# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE-# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE-# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR-# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF-# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS-# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN-# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)-# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE-# POSSIBILITY OF SUCH DAMAGE.---"""-A pure-Python PDF library with very minimal capabilities. It was designed to-be able to split and merge PDF files by page, and that's about all it can do.-It may be a solid base for future PDF file work in Python.-"""-__author__ = "Mathieu Fenniak"-__author_email__ = "[email protected]"--import math-import struct-from sys import version_info-try:- from cStringIO import StringIO-except ImportError:- from StringIO import StringIO--import filters-import utils-import warnings-from generic import *-from utils import readNonWhitespace, readUntilWhitespace, ConvertFunctionsToVirtualList--if version_info < ( 2, 4 ):- from sets import ImmutableSet as frozenset--if version_info < ( 2, 5 ):- from md5 import md5-else:- from hashlib import md5--##-# This class supports writing PDF files out, given pages produced by another-# class (typically {@link #PdfFileReader PdfFileReader}).-class PdfFileWriter(object):- def __init__(self):- self._header = "%PDF-1.3"- self._objects = [] # array of indirect objects-- # The root of our page tree node.- pages = DictionaryObject()- pages.update({- NameObject("/Type"): NameObject("/Pages"),- NameObject("/Count"): NumberObject(0),- NameObject("/Kids"): ArrayObject(),- })- self._pages = self._addObject(pages)-- # info object- info = DictionaryObject()- info.update({- NameObject("/Producer"): createStringObject(u"Python PDF Library - http://pybrary.net/pyPdf/")- })- self._info = self._addObject(info)-- # root object- root = DictionaryObject()- root.update({- NameObject("/Type"): NameObject("/Catalog"),- NameObject("/Pages"): self._pages,- })- self._root = self._addObject(root)-- def _addObject(self, obj):- self._objects.append(obj)- return IndirectObject(len(self._objects), 0, self)-- def getObject(self, ido):- if ido.pdf != self:- raise ValueError("pdf must be self")- return self._objects[ido.idnum - 1]-- ##- # Common method for inserting or adding a page to this PDF file.- #- # @param page The page to add to the document. This argument should be- # an instance of {@link #PageObject PageObject}.- # @param action The function which will insert the page in the dictionnary.- # Takes: page list, page to add.- def _addPage(self, page, action):- assert page["/Type"] == "/Page"- page[NameObject("/Parent")] = self._pages- page = self._addObject(page)- pages = self.getObject(self._pages)- action(pages["/Kids"], page)- pages[NameObject("/Count")] = NumberObject(pages["/Count"] + 1)-- ##- # Adds a page to this PDF file. The page is usually acquired from a- # {@link #PdfFileReader PdfFileReader} instance.- # <p>- # Stability: Added in v1.0, will exist for all v1.x releases.- #- # @param page The page to add to the document. This argument should be- # an instance of {@link #PageObject PageObject}.- def addPage(self, page):- self._addPage(page, list.append)-- ##- # Insert a page in this PDF file. The page is usually acquired from a- # {@link #PdfFileReader PdfFileReader} instance.- #- # @param page The page to add to the document. This argument should be- # an instance of {@link #PageObject PageObject}.- # @param index Position at which the page will be inserted.- def insertPage(self, page, index=0):- self._addPage(page, lambda l, p: l.insert(index, p))-- ##- # Retrieves a page by number from this PDF file.- # @return Returns a {@link #PageObject PageObject} instance.- def getPage(self, pageNumber):- pages = self.getObject(self._pages)- # XXX: crude hack- return pages["/Kids"][pageNumber].getObject()-- ##- # Return the number of pages.- # @return The number of pages.- def getNumPages(self):- pages = self.getObject(self._pages)- return int(pages[NameObject("/Count")])-- ##- # Append a blank page to this PDF file and returns it. If no page size- # is specified, use the size of the last page; throw- # PageSizeNotDefinedError if it doesn't exist.- # @param width The width of the new page expressed in default user- # space units.- # @param height The height of the new page expressed in default user- # space units.- def addBlankPage(self, width=None, height=None):- page = PageObject.createBlankPage(self, width, height)- self.addPage(page)- return page-- ##- # Insert a blank page to this PDF file and returns it. If no page size- # is specified, use the size of the page in the given index; throw- # PageSizeNotDefinedError if it doesn't exist.- # @param width The width of the new page expressed in default user- # space units.- # @param height The height of the new page expressed in default user- # space units.- # @param index Position to add the page.- def insertBlankPage(self, width=None, height=None, index=0):- if width is None or height is None and \- (self.getNumPages() - 1) >= index:- oldpage = self.getPage(index)- width = oldpage.mediaBox.getWidth()- height = oldpage.mediaBox.getHeight()- page = PageObject.createBlankPage(self, width, height)- self.insertPage(page, index)- return page-- ##- # Encrypt this PDF file with the PDF Standard encryption handler.- # @param user_pwd The "user password", which allows for opening and reading- # the PDF file with the restrictions provided.- # @param owner_pwd The "owner password", which allows for opening the PDF- # files without any restrictions. By default, the owner password is the- # same as the user password.- # @param use_128bit Boolean argument as to whether to use 128bit- # encryption. When false, 40bit encryption will be used. By default, this- # flag is on.- def encrypt(self, user_pwd, owner_pwd = None, use_128bit = True):- import time, random- if owner_pwd == None:- owner_pwd = user_pwd- if use_128bit:- V = 2- rev = 3- keylen = 128 / 8- else:- V = 1- rev = 2- keylen = 40 / 8- # permit everything:- P = -1- O = ByteStringObject(_alg33(owner_pwd, user_pwd, rev, keylen))- ID_1 = md5(repr(time.time())).digest()- ID_2 = md5(repr(random.random())).digest()- self._ID = ArrayObject((ByteStringObject(ID_1), ByteStringObject(ID_2)))- if rev == 2:- U, key = _alg34(user_pwd, O, P, ID_1)- else:- assert rev == 3- U, key = _alg35(user_pwd, rev, keylen, O, P, ID_1, False)- encrypt = DictionaryObject()- encrypt[NameObject("/Filter")] = NameObject("/Standard")- encrypt[NameObject("/V")] = NumberObject(V)- if V == 2:- encrypt[NameObject("/Length")] = NumberObject(keylen * 8)- encrypt[NameObject("/R")] = NumberObject(rev)- encrypt[NameObject("/O")] = ByteStringObject(O)- encrypt[NameObject("/U")] = ByteStringObject(U)- encrypt[NameObject("/P")] = NumberObject(P)- self._encrypt = self._addObject(encrypt)- self._encrypt_key = key-- ##- # Writes the collection of pages added to this object out as a PDF file.- # <p>- # Stability: Added in v1.0, will exist for all v1.x releases.- # @param stream An object to write the file to. The object must support- # the write method, and the tell method, similar to a file object.- def write(self, stream):- import struct-- externalReferenceMap = {}-- # PDF objects sometimes have circular references to their /Page objects- # inside their object tree (for example, annotations). Those will be- # indirect references to objects that we've recreated in this PDF. To- # address this problem, PageObject's store their original object- # reference number, and we add it to the external reference map before- # we sweep for indirect references. This forces self-page-referencing- # trees to reference the correct new object location, rather than- # copying in a new copy of the page object.- for objIndex in xrange(len(self._objects)):- obj = self._objects[objIndex]- if isinstance(obj, PageObject) and obj.indirectRef != None:- data = obj.indirectRef- if not externalReferenceMap.has_key(data.pdf):- externalReferenceMap[data.pdf] = {}- if not externalReferenceMap[data.pdf].has_key(data.generation):- externalReferenceMap[data.pdf][data.generation] = {}- externalReferenceMap[data.pdf][data.generation][data.idnum] = IndirectObject(objIndex + 1, 0, self)-- self.stack = []- self._sweepIndirectReferences(externalReferenceMap, self._root)- del self.stack-- # Begin writing:- object_positions = []- stream.write(self._header + "\n")- for i in range(len(self._objects)):- idnum = (i + 1)- obj = self._objects[i]- object_positions.append(stream.tell())- stream.write(str(idnum) + " 0 obj\n")- key = None- if hasattr(self, "_encrypt") and idnum != self._encrypt.idnum:- pack1 = struct.pack("<i", i + 1)[:3]- pack2 = struct.pack("<i", 0)[:2]- key = self._encrypt_key + pack1 + pack2- assert len(key) == (len(self._encrypt_key) + 5)- md5_hash = md5(key).digest()- key = md5_hash[:min(16, len(self._encrypt_key) + 5)]- obj.writeToStream(stream, key)- stream.write("\nendobj\n")-- # xref table- xref_location = stream.tell()- stream.write("xref\n")- stream.write("0 %s\n" % (len(self._objects) + 1))- stream.write("%010d %05d f \n" % (0, 65535))- for offset in object_positions:- stream.write("%010d %05d n \n" % (offset, 0))-- # trailer- stream.write("trailer\n")- trailer = DictionaryObject()- trailer.update({- NameObject("/Size"): NumberObject(len(self._objects) + 1),- NameObject("/Root"): self._root,- NameObject("/Info"): self._info,- })- if hasattr(self, "_ID"):- trailer[NameObject("/ID")] = self._ID- if hasattr(self, "_encrypt"):- trailer[NameObject("/Encrypt")] = self._encrypt- trailer.writeToStream(stream, None)-- # eof- stream.write("\nstartxref\n%s\n%%%%EOF\n" % (xref_location))-- def _sweepIndirectReferences(self, externMap, data):- if isinstance(data, DictionaryObject):- for key, value in data.items():- origvalue = value- value = self._sweepIndirectReferences(externMap, value)- if isinstance(value, StreamObject):- # a dictionary value is a stream. streams must be indirect- # objects, so we need to change this value.- value = self._addObject(value)- data[key] = value- return data- elif isinstance(data, ArrayObject):- for i in range(len(data)):- value = self._sweepIndirectReferences(externMap, data[i])- if isinstance(value, StreamObject):- # an array value is a stream. streams must be indirect- # objects, so we need to change this value- value = self._addObject(value)- data[i] = value- return data- elif isinstance(data, IndirectObject):- # internal indirect references are fine- if data.pdf == self:- if data.idnum in self.stack:- return data- else:- self.stack.append(data.idnum)- realdata = self.getObject(data)- self._sweepIndirectReferences(externMap, realdata)- self.stack.pop()- return data- else:- newobj = externMap.get(data.pdf, {}).get(data.generation, {}).get(data.idnum, None)- if newobj == None:- newobj = data.pdf.getObject(data)- self._objects.append(None) # placeholder- idnum = len(self._objects)- newobj_ido = IndirectObject(idnum, 0, self)- if not externMap.has_key(data.pdf):- externMap[data.pdf] = {}- if not externMap[data.pdf].has_key(data.generation):- externMap[data.pdf][data.generation] = {}- externMap[data.pdf][data.generation][data.idnum] = newobj_ido- newobj = self._sweepIndirectReferences(externMap, newobj)- self._objects[idnum-1] = newobj- return newobj_ido- return newobj- else:- return data---##-# Initializes a PdfFileReader object. This operation can take some time, as-# the PDF stream's cross-reference tables are read into memory.-# <p>-# Stability: Added in v1.0, will exist for all v1.x releases.-#-# @param stream An object that supports the standard read and seek methods-# similar to a file object.-class PdfFileReader(object):- def __init__(self, stream):- self.flattenedPages = None- self.resolvedObjects = {}- self.read(stream)- self.stream = stream- self._override_encryption = False-- ##- # Retrieves the PDF file's document information dictionary, if it exists.- # Note that some PDF files use metadata streams instead of docinfo- # dictionaries, and these metadata streams will not be accessed by this- # function.- # <p>- # Stability: Added in v1.6, will exist for all future v1.x releases.- # @return Returns a {@link #DocumentInformation DocumentInformation}- # instance, or None if none exists.- def getDocumentInfo(self):- if not self.trailer.has_key("/Info"):- return None- obj = self.trailer['/Info']- retval = DocumentInformation()- retval.update(obj)- return retval-- ##- # Read-only property that accesses the {@link- # #PdfFileReader.getDocumentInfo getDocumentInfo} function.- # <p>- # Stability: Added in v1.7, will exist for all future v1.x releases.- documentInfo = property(lambda self: self.getDocumentInfo(), None, None)-- ##- # Retrieves XMP (Extensible Metadata Platform) data from the PDF document- # root.- # <p>- # Stability: Added in v1.12, will exist for all future v1.x releases.- # @return Returns a {@link #generic.XmpInformation XmlInformation}- # instance that can be used to access XMP metadata from the document.- # Can also return None if no metadata was found on the document root.- def getXmpMetadata(self):- try:- self._override_encryption = True- return self.trailer["/Root"].getXmpMetadata()- finally:- self._override_encryption = False-- ##- # Read-only property that accesses the {@link #PdfFileReader.getXmpData- # getXmpData} function.- # <p>- # Stability: Added in v1.12, will exist for all future v1.x releases.- xmpMetadata = property(lambda self: self.getXmpMetadata(), None, None)-- ##- # Calculates the number of pages in this PDF file.- # <p>- # Stability: Added in v1.0, will exist for all v1.x releases.- # @return Returns an integer.- def getNumPages(self):- if self.flattenedPages == None:- self._flatten()- return len(self.flattenedPages)-- ##- # Read-only property that accesses the {@link #PdfFileReader.getNumPages- # getNumPages} function.- # <p>- # Stability: Added in v1.7, will exist for all future v1.x releases.- numPages = property(lambda self: self.getNumPages(), None, None)-- ##- # Retrieves a page by number from this PDF file.- # <p>- # Stability: Added in v1.0, will exist for all v1.x releases.- # @return Returns a {@link #PageObject PageObject} instance.- def getPage(self, pageNumber):- ## ensure that we're not trying to access an encrypted PDF- #assert not self.trailer.has_key("/Encrypt")- if self.flattenedPages == None:- self._flatten()- return self.flattenedPages[pageNumber]-- ##- # Read-only property that accesses the- # {@link #PdfFileReader.getNamedDestinations- # getNamedDestinations} function.- # <p>- # Stability: Added in v1.10, will exist for all future v1.x releases.- namedDestinations = property(lambda self:- self.getNamedDestinations(), None, None)-- ##- # Retrieves the named destinations present in the document.- # <p>- # Stability: Added in v1.10, will exist for all future v1.x releases.- # @return Returns a dict which maps names to {@link #Destination- # destinations}.- def getNamedDestinations(self, tree=None, retval=None):- if retval == None:- retval = {}- catalog = self.trailer["/Root"]-- # get the name tree- if catalog.has_key("/Dests"):- tree = catalog["/Dests"]- elif catalog.has_key("/Names"):- names = catalog['/Names']- if names.has_key("/Dests"):- tree = names['/Dests']-- if tree == None:- return retval-- if tree.has_key("/Kids"):- # recurse down the tree- for kid in tree["/Kids"]:- self.getNamedDestinations(kid.getObject(), retval)-- if tree.has_key("/Names"):- names = tree["/Names"]- for i in range(0, len(names), 2):- key = names[i].getObject()- val = names[i+1].getObject()- if isinstance(val, DictionaryObject) and val.has_key('/D'):- val = val['/D']- dest = self._buildDestination(key, val)- if dest != None:- retval[key] = dest-- return retval-- ##- # Read-only property that accesses the {@link #PdfFileReader.getOutlines- # getOutlines} function.- # <p>- # Stability: Added in v1.10, will exist for all future v1.x releases.- outlines = property(lambda self: self.getOutlines(), None, None)-- ##- # Retrieves the document outline present in the document.- # <p>- # Stability: Added in v1.10, will exist for all future v1.x releases.- # @return Returns a nested list of {@link #Destination destinations}.- def getOutlines(self, node=None, outlines=None):- if outlines == None:- outlines = []- catalog = self.trailer["/Root"]-- # get the outline dictionary and named destinations- if catalog.has_key("/Outlines"):- lines = catalog["/Outlines"]- if lines.has_key("/First"):- node = lines["/First"]- self._namedDests = self.getNamedDestinations()-- if node == None:- return outlines-- # see if there are any more outlines- while 1:- outline = self._buildOutline(node)- if outline:- outlines.append(outline)-- # check for sub-outlines- if node.has_key("/First"):- subOutlines = []- self.getOutlines(node["/First"], subOutlines)- if subOutlines:- outlines.append(subOutlines)-- if not node.has_key("/Next"):- break- node = node["/Next"]-- return outlines-- def _buildDestination(self, title, array):- page, typ = array[0:2]- array = array[2:]- return Destination(title, page, typ, *array)-- def _buildOutline(self, node):- dest, title, outline = None, None, None-- if node.has_key("/A") and node.has_key("/Title"):- # Action, section 8.5 (only type GoTo supported)- title = node["/Title"]- action = node["/A"]- if action["/S"] == "/GoTo":- dest = action["/D"]- elif node.has_key("/Dest") and node.has_key("/Title"):- # Destination, section 8.2.1- title = node["/Title"]- dest = node["/Dest"]-- # if destination found, then create outline- if dest:- if isinstance(dest, ArrayObject):- outline = self._buildDestination(title, dest)- elif isinstance(dest, unicode) and self._namedDests.has_key(dest):- outline = self._namedDests[dest]- outline[NameObject("/Title")] = title- else:- raise utils.PdfReadError("Unexpected destination %r" % dest)- return outline-- ##- # Read-only property that emulates a list based upon the {@link- # #PdfFileReader.getNumPages getNumPages} and {@link #PdfFileReader.getPage- # getPage} functions.- # <p>- # Stability: Added in v1.7, and will exist for all future v1.x releases.- pages = property(lambda self: ConvertFunctionsToVirtualList(self.getNumPages, self.getPage),- None, None)-- def _flatten(self, pages=None, inherit=None, indirectRef=None):- inheritablePageAttributes = (- NameObject("/Resources"), NameObject("/MediaBox"),- NameObject("/CropBox"), NameObject("/Rotate")- )- if inherit == None:- inherit = dict()- if pages == None:- self.flattenedPages = []- catalog = self.trailer["/Root"].getObject()- pages = catalog["/Pages"].getObject()- t = pages["/Type"]- if t == "/Pages":- for attr in inheritablePageAttributes:- if pages.has_key(attr):- inherit[attr] = pages[attr]- for page in pages["/Kids"]:- addt = {}- if isinstance(page, IndirectObject):- addt["indirectRef"] = page- self._flatten(page.getObject(), inherit, **addt)- elif t == "/Page":- for attr,value in inherit.items():- # if the page has it's own value, it does not inherit the- # parent's value:- if not pages.has_key(attr):- pages[attr] = value- pageObj = PageObject(self, indirectRef)- pageObj.update(pages)- self.flattenedPages.append(pageObj)-- def getObject(self, indirectReference):- retval = self.resolvedObjects.get(indirectReference.generation, {}).get(indirectReference.idnum, None)- if retval != None:- return retval- if indirectReference.generation == 0 and \- self.xref_objStm.has_key(indirectReference.idnum):- # indirect reference to object in object stream- # read the entire object stream into memory- stmnum,idx = self.xref_objStm[indirectReference.idnum]- objStm = IndirectObject(stmnum, 0, self).getObject()- assert objStm['/Type'] == '/ObjStm'- assert idx < objStm['/N']- streamData = StringIO(objStm.getData())- for i in range(objStm['/N']):- objnum = NumberObject.readFromStream(streamData)- readNonWhitespace(streamData)- streamData.seek(-1, 1)- offset = NumberObject.readFromStream(streamData)- readNonWhitespace(streamData)- streamData.seek(-1, 1)- t = streamData.tell()- streamData.seek(objStm['/First']+offset, 0)- obj = readObject(streamData, self)- self.resolvedObjects[0][objnum] = obj- streamData.seek(t, 0)- return self.resolvedObjects[0][indirectReference.idnum]- start = self.xref[indirectReference.generation][indirectReference.idnum]- self.stream.seek(start, 0)- idnum, generation = self.readObjectHeader(self.stream)- assert idnum == indirectReference.idnum- assert generation == indirectReference.generation- retval = readObject(self.stream, self)-- # override encryption is used for the /Encrypt dictionary- if not self._override_encryption and self.isEncrypted:- # if we don't have the encryption key:- if not hasattr(self, '_decryption_key'):- raise Exception, "file has not been decrypted"- # otherwise, decrypt here...- import struct- pack1 = struct.pack("<i", indirectReference.idnum)[:3]- pack2 = struct.pack("<i", indirectReference.generation)[:2]- key = self._decryption_key + pack1 + pack2- assert len(key) == (len(self._decryption_key) + 5)- md5_hash = md5(key).digest()- key = md5_hash[:min(16, len(self._decryption_key) + 5)]- retval = self._decryptObject(retval, key)-- self.cacheIndirectObject(generation, idnum, retval)- return retval-- def _decryptObject(self, obj, key):- if isinstance(obj, ByteStringObject) or isinstance(obj, TextStringObject):- obj = createStringObject(utils.RC4_encrypt(key, obj.original_bytes))- elif isinstance(obj, StreamObject):- obj._data = utils.RC4_encrypt(key, obj._data)- elif isinstance(obj, DictionaryObject):- for dictkey, value in obj.items():- obj[dictkey] = self._decryptObject(value, key)- elif isinstance(obj, ArrayObject):- for i in range(len(obj)):- obj[i] = self._decryptObject(obj[i], key)- return obj-- def readObjectHeader(self, stream):- # Should never be necessary to read out whitespace, since the- # cross-reference table should put us in the right spot to read the- # object header. In reality... some files have stupid cross reference- # tables that are off by whitespace bytes.- readNonWhitespace(stream); stream.seek(-1, 1)- idnum = readUntilWhitespace(stream)- generation = readUntilWhitespace(stream)- obj = stream.read(3)- readNonWhitespace(stream)- stream.seek(-1, 1)- return int(idnum), int(generation)-- def cacheIndirectObject(self, generation, idnum, obj):- if not self.resolvedObjects.has_key(generation):- self.resolvedObjects[generation] = {}- self.resolvedObjects[generation][idnum] = obj-- def read(self, stream):- # start at the end:- stream.seek(-1, 2)- line = ''- while not line:- line = self.readNextEndLine(stream)- if line[:5] != "%%EOF":- raise utils.PdfReadError, "EOF marker not found"-- # find startxref entry - the location of the xref table- line = self.readNextEndLine(stream)- startxref = int(line)- line = self.readNextEndLine(stream)- if line[:9] != "startxref":- raise utils.PdfReadError, "startxref not found"-- # read all cross reference tables and their trailers- self.xref = {}- self.xref_objStm = {}- self.trailer = DictionaryObject()- while 1:- # load the xref table- stream.seek(startxref, 0)- x = stream.read(1)- if x == "x":- # standard cross-reference table- ref = stream.read(4)- if ref[:3] != "ref":- raise utils.PdfReadError, "xref table read error"- readNonWhitespace(stream)- stream.seek(-1, 1)- while 1:- num = readObject(stream, self)- readNonWhitespace(stream)- stream.seek(-1, 1)- size = readObject(stream, self)- readNonWhitespace(stream)- stream.seek(-1, 1)- cnt = 0- while cnt < size:- line = stream.read(20)- # It's very clear in section 3.4.3 of the PDF spec- # that all cross-reference table lines are a fixed- # 20 bytes. However... some malformed PDF files- # use a single character EOL without a preceeding- # space. Detect that case, and seek the stream- # back one character. (0-9 means we've bled into- # the next xref entry, t means we've bled into the- # text "trailer"):- if line[-1] in "0123456789t":- stream.seek(-1, 1)- offset, generation = line[:16].split(" ")- offset, generation = int(offset), int(generation)- if not self.xref.has_key(generation):- self.xref[generation] = {}- if self.xref[generation].has_key(num):- # It really seems like we should allow the last- # xref table in the file to override previous- # ones. Since we read the file backwards, assume- # any existing key is already set correctly.- pass- else:- self.xref[generation][num] = offset- cnt += 1- num += 1- readNonWhitespace(stream)- stream.seek(-1, 1)- trailertag = stream.read(7)- if trailertag != "trailer":- # more xrefs!- stream.seek(-7, 1)- else:- break- readNonWhitespace(stream)- stream.seek(-1, 1)- newTrailer = readObject(stream, self)- for key, value in newTrailer.items():- if not self.trailer.has_key(key):- self.trailer[key] = value- if newTrailer.has_key("/Prev"):- startxref = newTrailer["/Prev"]- else:- break- elif x.isdigit():- # PDF 1.5+ Cross-Reference Stream- stream.seek(-1, 1)- idnum, generation = self.readObjectHeader(stream)- xrefstream = readObject(stream, self)- assert xrefstream["/Type"] == "/XRef"- self.cacheIndirectObject(generation, idnum, xrefstream)- streamData = StringIO(xrefstream.getData())- idx_pairs = xrefstream.get("/Index", [0, xrefstream.get("/Size")])- entrySizes = xrefstream.get("/W")- for num, size in self._pairs(idx_pairs):- cnt = 0- while cnt < size:- for i in range(len(entrySizes)):- d = streamData.read(entrySizes[i])- di = convertToInt(d, entrySizes[i])- if i == 0:- xref_type = di- elif i == 1:- if xref_type == 0:- next_free_object = di- elif xref_type == 1:- byte_offset = di- elif xref_type == 2:- objstr_num = di- elif i == 2:- if xref_type == 0:- next_generation = di- elif xref_type == 1:- generation = di- elif xref_type == 2:- obstr_idx = di- if xref_type == 0:- pass- elif xref_type == 1:- if not self.xref.has_key(generation):- self.xref[generation] = {}- if not num in self.xref[generation]:- self.xref[generation][num] = byte_offset- elif xref_type == 2:- if not num in self.xref_objStm:- self.xref_objStm[num] = [objstr_num, obstr_idx]- cnt += 1- num += 1- trailerKeys = "/Root", "/Encrypt", "/Info", "/ID"- for key in trailerKeys:- if xrefstream.has_key(key) and not self.trailer.has_key(key):- self.trailer[NameObject(key)] = xrefstream.raw_get(key)- if xrefstream.has_key("/Prev"):- startxref = xrefstream["/Prev"]- else:- break- else:- # bad xref character at startxref. Let's see if we can find- # the xref table nearby, as we've observed this error with an- # off-by-one before.- stream.seek(-11, 1)- tmp = stream.read(20)- xref_loc = tmp.find("xref")- if xref_loc != -1:- startxref -= (10 - xref_loc)- continue- else:- # no xref table found at specified location- assert False- break-- def _pairs(self, array):- i = 0- while True:- yield array[i], array[i+1]- i += 2- if (i+1) >= len(array):- break-- def readNextEndLine(self, stream):- line = ""- while True:- x = stream.read(1)- stream.seek(-2, 1)- if x == '\n' or x == '\r':- while x == '\n' or x == '\r':- x = stream.read(1)- stream.seek(-2, 1)- stream.seek(1, 1)- break- else:- line = x + line- return line-- ##- # When using an encrypted / secured PDF file with the PDF Standard- # encryption handler, this function will allow the file to be decrypted.- # It checks the given password against the document's user password and- # owner password, and then stores the resulting decryption key if either- # password is correct.- # <p>- # It does not matter which password was matched. Both passwords provide- # the correct decryption key that will allow the document to be used with- # this library.- # <p>- # Stability: Added in v1.8, will exist for all future v1.x releases.- #- # @return 0 if the password failed, 1 if the password matched the user- # password, and 2 if the password matched the owner password.- #- # @exception NotImplementedError Document uses an unsupported encryption- # method.- def decrypt(self, password):- self._override_encryption = True- try:- return self._decrypt(password)- finally:- self._override_encryption = False-- def _decrypt(self, password):- encrypt = self.trailer['/Encrypt'].getObject()- if encrypt['/Filter'] != '/Standard':- raise NotImplementedError, "only Standard PDF encryption handler is available"- if not (encrypt['/V'] in (1, 2)):- raise NotImplementedError, "only algorithm code 1 and 2 are supported"- user_password, key = self._authenticateUserPassword(password)- if user_password:- self._decryption_key = key- return 1- else:- rev = encrypt['/R'].getObject()- if rev == 2:- keylen = 5- else:- keylen = encrypt['/Length'].getObject() / 8- key = _alg33_1(password, rev, keylen)- real_O = encrypt["/O"].getObject()- if rev == 2:- userpass = utils.RC4_encrypt(key, real_O)- else:- val = real_O- for i in range(19, -1, -1):- new_key = ''- for l in range(len(key)):- new_key += chr(ord(key[l]) ^ i)- val = utils.RC4_encrypt(new_key, val)- userpass = val- owner_password, key = self._authenticateUserPassword(userpass)- if owner_password:- self._decryption_key = key- return 2- return 0-- def _authenticateUserPassword(self, password):- encrypt = self.trailer['/Encrypt'].getObject()- rev = encrypt['/R'].getObject()- owner_entry = encrypt['/O'].getObject().original_bytes- p_entry = encrypt['/P'].getObject()- id_entry = self.trailer['/ID'].getObject()- id1_entry = id_entry[0].getObject()- if rev == 2:- U, key = _alg34(password, owner_entry, p_entry, id1_entry)- elif rev >= 3:- U, key = _alg35(password, rev,- encrypt["/Length"].getObject() / 8, owner_entry,- p_entry, id1_entry,- encrypt.get("/EncryptMetadata", BooleanObject(False)).getObject())- real_U = encrypt['/U'].getObject().original_bytes- return U == real_U, key-- def getIsEncrypted(self):- return self.trailer.has_key("/Encrypt")-- ##- # Read-only boolean property showing whether this PDF file is encrypted.- # Note that this property, if true, will remain true even after the {@link- # #PdfFileReader.decrypt decrypt} function is called.- isEncrypted = property(lambda self: self.getIsEncrypted(), None, None)---def getRectangle(self, name, defaults):- retval = self.get(name)- if isinstance(retval, RectangleObject):- return retval- if retval == None:- for d in defaults:- retval = self.get(d)- if retval != None:- break- if isinstance(retval, IndirectObject):- retval = self.pdf.getObject(retval)- retval = RectangleObject(retval)- setRectangle(self, name, retval)- return retval--def setRectangle(self, name, value):- if not isinstance(name, NameObject):- name = NameObject(name)- self[name] = value--def deleteRectangle(self, name):- del self[name]--def createRectangleAccessor(name, fallback):- return \- property(- lambda self: getRectangle(self, name, fallback),- lambda self, value: setRectangle(self, name, value),- lambda self: deleteRectangle(self, name)- )--##-# This class represents a single page within a PDF file. Typically this object-# will be created by accessing the {@link #PdfFileReader.getPage getPage}-# function of the {@link #PdfFileReader PdfFileReader} class, but it is-# also possible to create an empty page with the createBlankPage static-# method.-# @param pdf PDF file the page belongs to (optional, defaults to None).-class PageObject(DictionaryObject):- def __init__(self, pdf=None, indirectRef=None):- DictionaryObject.__init__(self)- self.pdf = pdf- # Stores the original indirect reference to this object in its source PDF- self.indirectRef = indirectRef-- ##- # Returns a new blank page.- # If width or height is None, try to get the page size from the- # last page of pdf. If pdf is None or contains no page, a- # PageSizeNotDefinedError is raised.- # @param pdf PDF file the page belongs to- # @param width The width of the new page expressed in default user- # space units.- # @param height The height of the new page expressed in default user- # space units.- def createBlankPage(pdf=None, width=None, height=None):- page = PageObject(pdf)-- # Creates a new page (cf PDF Reference 7.7.3.3)- page.__setitem__(NameObject('/Type'), NameObject('/Page'))- page.__setitem__(NameObject('/Parent'), NullObject())- page.__setitem__(NameObject('/Resources'), DictionaryObject())- if width is None or height is None:- if pdf is not None and pdf.getNumPages() > 0:- lastpage = pdf.getPage(pdf.getNumPages() - 1)- width = lastpage.mediaBox.getWidth()- height = lastpage.mediaBox.getHeight()- else:- raise utils.PageSizeNotDefinedError()- page.__setitem__(NameObject('/MediaBox'),- RectangleObject([0, 0, width, height]))-- return page- createBlankPage = staticmethod(createBlankPage)-- ##- # Rotates a page clockwise by increments of 90 degrees.- # <p>- # Stability: Added in v1.1, will exist for all future v1.x releases.- # @param angle Angle to rotate the page. Must be an increment of 90 deg.- def rotateClockwise(self, angle):- assert angle % 90 == 0- self._rotate(angle)- return self-- ##- # Rotates a page counter-clockwise by increments of 90 degrees.- # <p>- # Stability: Added in v1.1, will exist for all future v1.x releases.- # @param angle Angle to rotate the page. Must be an increment of 90 deg.- def rotateCounterClockwise(self, angle):- assert angle % 90 == 0- self._rotate(-angle)- return self-- def _rotate(self, angle):- currentAngle = self.get("/Rotate", 0)- self[NameObject("/Rotate")] = NumberObject(currentAngle + angle)-- def _mergeResources(res1, res2, resource):- newRes = DictionaryObject()- newRes.update(res1.get(resource, DictionaryObject()).getObject())- page2Res = res2.get(resource, DictionaryObject()).getObject()- renameRes = {}- for key in page2Res.keys():- if newRes.has_key(key) and newRes[key] != page2Res[key]:- newname = NameObject(key + "renamed")- renameRes[key] = newname- newRes[newname] = page2Res[key]- elif not newRes.has_key(key):- newRes[key] = page2Res.raw_get(key)- return newRes, renameRes- _mergeResources = staticmethod(_mergeResources)-- def _contentStreamRename(stream, rename, pdf):- if not rename:- return stream- stream = ContentStream(stream, pdf)- for operands,operator in stream.operations:- for i in range(len(operands)):- op = operands[i]- if isinstance(op, NameObject):- operands[i] = rename.get(op, op)- return stream- _contentStreamRename = staticmethod(_contentStreamRename)-- def _pushPopGS(contents, pdf):- # adds a graphics state "push" and "pop" to the beginning and end- # of a content stream. This isolates it from changes such as- # transformation matricies.- stream = ContentStream(contents, pdf)- stream.operations.insert(0, [[], "q"])- stream.operations.append([[], "Q"])- return stream- _pushPopGS = staticmethod(_pushPopGS)-- def _addTransformationMatrix(contents, pdf, ctm):- # adds transformation matrix at the beginning of the given- # contents stream.- a, b, c, d, e, f = ctm- contents = ContentStream(contents, pdf)- contents.operations.insert(0, [[FloatObject(a), FloatObject(b),- FloatObject(c), FloatObject(d), FloatObject(e),- FloatObject(f)], " cm"])- return contents- _addTransformationMatrix = staticmethod(_addTransformationMatrix)-- ##- # Returns the /Contents object, or None if it doesn't exist.- # /Contents is optionnal, as described in PDF Reference 7.7.3.3- def getContents(self):- if self.has_key("/Contents"):- return self["/Contents"].getObject()- else:- return None-- ##- # Merges the content streams of two pages into one. Resource references- # (i.e. fonts) are maintained from both pages. The mediabox/cropbox/etc- # of this page are not altered. The parameter page's content stream will- # be added to the end of this page's content stream, meaning that it will- # be drawn after, or "on top" of this page.- # <p>- # Stability: Added in v1.4, will exist for all future 1.x releases.- # @param page2 An instance of {@link #PageObject PageObject} to be merged- # into this one.- def mergePage(self, page2):- self._mergePage(page2)-- ##- # Actually merges the content streams of two pages into one. Resource- # references (i.e. fonts) are maintained from both pages. The- # mediabox/cropbox/etc of this page are not altered. The parameter page's- # content stream will be added to the end of this page's content stream,- # meaning that it will be drawn after, or "on top" of this page.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged- # into this one.- # @param page2transformation A fuction which applies a transformation to- # the content stream of page2. Takes: page2- # contents stream. Must return: new contents- # stream. If omitted, the content stream will- # not be modified.- def _mergePage(self, page2, page2transformation=None):- # First we work on merging the resource dictionaries. This allows us- # to find out what symbols in the content streams we might need to- # rename.-- newResources = DictionaryObject()- rename = {}- originalResources = self["/Resources"].getObject()- page2Resources = page2["/Resources"].getObject()-- for res in "/ExtGState", "/Font", "/XObject", "/ColorSpace", "/Pattern", "/Shading", "/Properties":- new, newrename = PageObject._mergeResources(originalResources, page2Resources, res)- if new:- newResources[NameObject(res)] = new- rename.update(newrename)-- # Combine /ProcSet sets.- newResources[NameObject("/ProcSet")] = ArrayObject(- frozenset(originalResources.get("/ProcSet", ArrayObject()).getObject()).union(- frozenset(page2Resources.get("/ProcSet", ArrayObject()).getObject())- )- )-- newContentArray = ArrayObject()-- originalContent = self.getContents()- if originalContent is not None:- newContentArray.append(PageObject._pushPopGS(- originalContent, self.pdf))-- page2Content = page2.getContents()- if page2Content is not None:- if page2transformation is not None:- page2Content = page2transformation(page2Content)- page2Content = PageObject._contentStreamRename(- page2Content, rename, self.pdf)- page2Content = PageObject._pushPopGS(page2Content, self.pdf)- newContentArray.append(page2Content)-- self[NameObject('/Contents')] = ContentStream(newContentArray, self.pdf)- self[NameObject('/Resources')] = newResources-- ##- # This is similar to mergePage, but a transformation matrix is- # applied to the merged stream.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param ctm A 6 elements tuple containing the operands of the- # transformation matrix- def mergeTransformedPage(self, page2, ctm):- self._mergePage(page2, lambda page2Content:- PageObject._addTransformationMatrix(page2Content, page2.pdf, ctm))-- ##- # This is similar to mergePage, but the stream to be merged is scaled- # by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param factor The scaling factor- def mergeScaledPage(self, page2, factor):- # CTM to scale : [ sx 0 0 sy 0 0 ]- return self.mergeTransformedPage(page2, [factor, 0,- 0, factor,- 0, 0])-- ##- # This is similar to mergePage, but the stream to be merged is rotated- # by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param rotation The angle of the rotation, in degrees- def mergeRotatedPage(self, page2, rotation):- rotation = math.radians(rotation)- return self.mergeTransformedPage(page2,- [math.cos(rotation), math.sin(rotation),- -math.sin(rotation), math.cos(rotation),- 0, 0])-- ##- # This is similar to mergePage, but the stream to be merged is translated- # by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param tx The translation on X axis- # @param tx The translation on Y axis- def mergeTranslatedPage(self, page2, tx, ty):- return self.mergeTransformedPage(page2, [1, 0,- 0, 1,- tx, ty])-- ##- # This is similar to mergePage, but the stream to be merged is rotated- # and scaled by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param rotation The angle of the rotation, in degrees- # @param factor The scaling factor- def mergeRotatedScaledPage(self, page2, rotation, scale):- rotation = math.radians(rotation)- rotating = [[math.cos(rotation), math.sin(rotation),0],- [-math.sin(rotation),math.cos(rotation), 0],- [0, 0, 1]]- scaling = [[scale,0, 0],- [0, scale,0],- [0, 0, 1]]- ctm = utils.matrixMultiply(rotating, scaling)-- return self.mergeTransformedPage(page2,- [ctm[0][0], ctm[0][1],- ctm[1][0], ctm[1][1],- ctm[2][0], ctm[2][1]])-- ##- # This is similar to mergePage, but the stream to be merged is translated- # and scaled by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param scale The scaling factor- # @param tx The translation on X axis- # @param tx The translation on Y axis- def mergeScaledTranslatedPage(self, page2, scale, tx, ty):- translation = [[1, 0, 0],- [0, 1, 0],- [tx,ty,1]]- scaling = [[scale,0, 0],- [0, scale,0],- [0, 0, 1]]- ctm = utils.matrixMultiply(scaling, translation)-- return self.mergeTransformedPage(page2, [ctm[0][0], ctm[0][1],- ctm[1][0], ctm[1][1],- ctm[2][0], ctm[2][1]])-- ##- # This is similar to mergePage, but the stream to be merged is translated,- # rotated and scaled by appling a transformation matrix.- #- # @param page2 An instance of {@link #PageObject PageObject} to be merged.- # @param tx The translation on X axis- # @param ty The translation on Y axis- # @param rotation The angle of the rotation, in degrees- # @param scale The scaling factor- def mergeRotatedScaledTranslatedPage(self, page2, rotation, scale, tx, ty):- translation = [[1, 0, 0],- [0, 1, 0],- [tx,ty,1]]- rotation = math.radians(rotation)- rotating = [[math.cos(rotation), math.sin(rotation),0],- [-math.sin(rotation),math.cos(rotation), 0],- [0, 0, 1]]- scaling = [[scale,0, 0],- [0, scale,0],- [0, 0, 1]]- ctm = utils.matrixMultiply(rotating, scaling)- ctm = utils.matrixMultiply(ctm, translation)-- return self.mergeTransformedPage(page2, [ctm[0][0], ctm[0][1],- ctm[1][0], ctm[1][1],- ctm[2][0], ctm[2][1]])-- ##- # Applys a transformation matrix the page.- #- # @param ctm A 6 elements tuple containing the operands of the- # transformation matrix- def addTransformation(self, ctm):- originalContent = self.getContents()- if originalContent is not None:- newContent = PageObject._addTransformationMatrix(- originalContent, self.pdf, ctm)- newContent = PageObject._pushPopGS(newContent, self.pdf)- self[NameObject('/Contents')] = newContent-- ##- # Scales a page by the given factors by appling a transformation- # matrix to its content and updating the page size.- #- # @param sx The scaling factor on horizontal axis- # @param sy The scaling factor on vertical axis- def scale(self, sx, sy):- self.addTransformation([sx, 0,- 0, sy,- 0, 0])- self.mediaBox = RectangleObject([- float(self.mediaBox.getLowerLeft_x()) * sx,- float(self.mediaBox.getLowerLeft_y()) * sy,- float(self.mediaBox.getUpperRight_x()) * sx,- float(self.mediaBox.getUpperRight_y()) * sy])-- ##- # Scales a page by the given factor by appling a transformation- # matrix to its content and updating the page size.- #- # @param factor The scaling factor- def scaleBy(self, factor):- self.scale(factor, factor)-- ##- # Scales a page to the specified dimentions by appling a- # transformation matrix to its content and updating the page size.- #- # @param width The new width- # @param height The new heigth- def scaleTo(self, width, height):- sx = width / (self.mediaBox.getUpperRight_x() -- self.mediaBox.getLowerLeft_x ())- sy = height / (self.mediaBox.getUpperRight_y() -- self.mediaBox.getLowerLeft_x ())- self.scale(sx, sy)-- ##- # Compresses the size of this page by joining all content streams and- # applying a FlateDecode filter.- # <p>- # Stability: Added in v1.6, will exist for all future v1.x releases.- # However, it is possible that this function will perform no action if- # content stream compression becomes "automatic" for some reason.- def compressContentStreams(self):- content = self.getContents()- if content is not None:- if not isinstance(content, ContentStream):- content = ContentStream(content, self.pdf)- self[NameObject("/Contents")] = content.flateEncode()-- ##- # Locate all text drawing commands, in the order they are provided in the- # content stream, and extract the text. This works well for some PDF- # files, but poorly for others, depending on the generator used. This will- # be refined in the future. Do not rely on the order of text coming out of- # this function, as it will change if this function is made more- # sophisticated.- # <p>- # Stability: Added in v1.7, will exist for all future v1.x releases. May- # be overhauled to provide more ordered text in the future.- # @return a unicode string object- def extractText(self):- text = u""- content = self["/Contents"].getObject()- if not isinstance(content, ContentStream):- content = ContentStream(content, self.pdf)- # Note: we check all strings are TextStringObjects. ByteStringObjects- # are strings where the byte->string encoding was unknown, so adding- # them to the text here would be gibberish.- for operands,operator in content.operations:- if operator == "Tj":- _text = operands[0]- if isinstance(_text, TextStringObject):- text += _text- elif operator == "T*":- text += "\n"- elif operator == "'":- text += "\n"- _text = operands[0]- if isinstance(_text, TextStringObject):- text += operands[0]- elif operator == '"':- _text = operands[2]- if isinstance(_text, TextStringObject):- text += "\n"- text += _text- elif operator == "TJ":- for i in operands[0]:- if isinstance(i, TextStringObject):- text += i- return text-- ##- # A rectangle (RectangleObject), expressed in default user space units,- # defining the boundaries of the physical medium on which the page is- # intended to be displayed or printed.- # <p>- # Stability: Added in v1.4, will exist for all future v1.x releases.- mediaBox = createRectangleAccessor("/MediaBox", ())-- ##- # A rectangle (RectangleObject), expressed in default user space units,- # defining the visible region of default user space. When the page is- # displayed or printed, its contents are to be clipped (cropped) to this- # rectangle and then imposed on the output medium in some- # implementation-defined manner. Default value: same as MediaBox.- # <p>- # Stability: Added in v1.4, will exist for all future v1.x releases.- cropBox = createRectangleAccessor("/CropBox", ("/MediaBox",))-- ##- # A rectangle (RectangleObject), expressed in default user space units,- # defining the region to which the contents of the page should be clipped- # when output in a production enviroment.- # <p>- # Stability: Added in v1.4, will exist for all future v1.x releases.- bleedBox = createRectangleAccessor("/BleedBox", ("/CropBox", "/MediaBox"))-- ##- # A rectangle (RectangleObject), expressed in default user space units,- # defining the intended dimensions of the finished page after trimming.- # <p>- # Stability: Added in v1.4, will exist for all future v1.x releases.- trimBox = createRectangleAccessor("/TrimBox", ("/CropBox", "/MediaBox"))-- ##- # A rectangle (RectangleObject), expressed in default user space units,- # defining the extent of the page's meaningful content as intended by the- # page's creator.- # <p>- # Stability: Added in v1.4, will exist for all future v1.x releases.- artBox = createRectangleAccessor("/ArtBox", ("/CropBox", "/MediaBox"))---class ContentStream(DecodedStreamObject):- def __init__(self, stream, pdf):- self.pdf = pdf- self.operations = []- # stream may be a StreamObject or an ArrayObject containing- # multiple StreamObjects to be cat'd together.- stream = stream.getObject()- if isinstance(stream, ArrayObject):- data = ""- for s in stream:- data += s.getObject().getData()- stream = StringIO(data)- else:- stream = StringIO(stream.getData())- self.__parseContentStream(stream)-- def __parseContentStream(self, stream):- # file("f:\\tmp.txt", "w").write(stream.read())- stream.seek(0, 0)- operands = []- while True:- peek = readNonWhitespace(stream)- if peek == '':- break- stream.seek(-1, 1)- if peek.isalpha() or peek == "'" or peek == '"':- operator = ""- while True:- tok = stream.read(1)- if tok.isspace() or tok in NameObject.delimiterCharacters:- stream.seek(-1, 1)- break- elif tok == '':- break- operator += tok- if operator == "BI":- # begin inline image - a completely different parsing- # mechanism is required, of course... thanks buddy...- assert operands == []- ii = self._readInlineImage(stream)- self.operations.append((ii, "INLINE IMAGE"))- else:- self.operations.append((operands, operator))- operands = []- elif peek == '%':- # If we encounter a comment in the content stream, we have to- # handle it here. Typically, readObject will handle- # encountering a comment -- but readObject assumes that- # following the comment must be the object we're trying to- # read. In this case, it could be an operator instead.- while peek not in ('\r', '\n'):- peek = stream.read(1)- else:- operands.append(readObject(stream, None))-- def _readInlineImage(self, stream):- # begin reading just after the "BI" - begin image- # first read the dictionary of settings.- settings = DictionaryObject()- while True:- tok = readNonWhitespace(stream)- stream.seek(-1, 1)- if tok == "I":- # "ID" - begin of image data- break- key = readObject(stream, self.pdf)- tok = readNonWhitespace(stream)- stream.seek(-1, 1)- value = readObject(stream, self.pdf)- settings[key] = value- # left at beginning of ID- tmp = stream.read(3)- assert tmp[:2] == "ID"- data = ""- while True:- tok = stream.read(1)- if tok == "E":- next = stream.read(1)- if next == "I":- break- else:- stream.seek(-1, 1)- data += tok- else:- data += tok- x = readNonWhitespace(stream)- stream.seek(-1, 1)- return {"settings": settings, "data": data}-- def _getData(self):- newdata = StringIO()- for operands,operator in self.operations:- if operator == "INLINE IMAGE":- newdata.write("BI")- dicttext = StringIO()- operands["settings"].writeToStream(dicttext, None)- newdata.write(dicttext.getvalue()[2:-2])- newdata.write("ID ")- newdata.write(operands["data"])- newdata.write("EI")- else:- for op in operands:- op.writeToStream(newdata, None)- newdata.write(" ")- newdata.write(operator)- newdata.write("\n")- return newdata.getvalue()-- def _setData(self, value):- self.__parseContentStream(StringIO(value))-- _data = property(_getData, _setData)---##-# A class representing the basic document metadata provided in a PDF File.-# <p>-# As of pyPdf v1.10, all text properties of the document metadata have two-# properties, eg. author and author_raw. The non-raw property will always-# return a TextStringObject, making it ideal for a case where the metadata is-# being displayed. The raw property can sometimes return a ByteStringObject,-# if pyPdf was unable to decode the string's text encoding; this requires-# additional safety in the caller and therefore is not as commonly accessed.-class DocumentInformation(DictionaryObject):- def __init__(self):- DictionaryObject.__init__(self)-- def getText(self, key):- retval = self.get(key, None)- if isinstance(retval, TextStringObject):- return retval- return None-- ##- # Read-only property accessing the document's title. Added in v1.6, will- # exist for all future v1.x releases. Modified in v1.10 to always return a- # unicode string (TextStringObject).- # @return A unicode string, or None if the title is not provided.- title = property(lambda self: self.getText("/Title"))- title_raw = property(lambda self: self.get("/Title"))-- ##- # Read-only property accessing the document's author. Added in v1.6, will- # exist for all future v1.x releases. Modified in v1.10 to always return a- # unicode string (TextStringObject).- # @return A unicode string, or None if the author is not provided.- author = property(lambda self: self.getText("/Author"))- author_raw = property(lambda self: self.get("/Author"))-- ##- # Read-only property accessing the subject of the document. Added in v1.6,- # will exist for all future v1.x releases. Modified in v1.10 to always- # return a unicode string (TextStringObject).- # @return A unicode string, or None if the subject is not provided.- subject = property(lambda self: self.getText("/Subject"))- subject_raw = property(lambda self: self.get("/Subject"))-- ##- # Read-only property accessing the document's creator. If the document was- # converted to PDF from another format, the name of the application (for- # example, OpenOffice) that created the original document from which it was- # converted. Added in v1.6, will exist for all future v1.x releases.- # Modified in v1.10 to always return a unicode string (TextStringObject).- # @return A unicode string, or None if the creator is not provided.- creator = property(lambda self: self.getText("/Creator"))- creator_raw = property(lambda self: self.get("/Creator"))-- ##- # Read-only property accessing the document's producer. If the document- # was converted to PDF from another format, the name of the application- # (for example, OSX Quartz) that converted it to PDF. Added in v1.6, will- # exist for all future v1.x releases. Modified in v1.10 to always return a- # unicode string (TextStringObject).- # @return A unicode string, or None if the producer is not provided.- producer = property(lambda self: self.getText("/Producer"))- producer_raw = property(lambda self: self.get("/Producer"))---##-# A class representing a destination within a PDF file.-# See section 8.2.1 of the PDF 1.6 reference.-# Stability: Added in v1.10, will exist for all v1.x releases.-class Destination(DictionaryObject):- def __init__(self, title, page, typ, *args):- DictionaryObject.__init__(self)- self[NameObject("/Title")] = title- self[NameObject("/Page")] = page- self[NameObject("/Type")] = typ-- # from table 8.2 of the PDF 1.6 reference.- if typ == "/XYZ":- (self[NameObject("/Left")], self[NameObject("/Top")],- self[NameObject("/Zoom")]) = args- elif typ == "/FitR":- (self[NameObject("/Left")], self[NameObject("/Bottom")],- self[NameObject("/Right")], self[NameObject("/Top")]) = args- elif typ in ["/FitH", "FitBH"]:- self[NameObject("/Top")], = args- elif typ in ["/FitV", "FitBV"]:- self[NameObject("/Left")], = args- elif typ in ["/Fit", "FitB"]:- pass- else:- raise utils.PdfReadError("Unknown Destination Type: %r" % typ)-- ##- # Read-only property accessing the destination title.- # @return A string.- title = property(lambda self: self.get("/Title"))-- ##- # Read-only property accessing the destination page.- # @return An integer.- page = property(lambda self: self.get("/Page"))-- ##- # Read-only property accessing the destination type.- # @return A string.- typ = property(lambda self: self.get("/Type"))-- ##- # Read-only property accessing the zoom factor.- # @return A number, or None if not available.- zoom = property(lambda self: self.get("/Zoom", None))-- ##- # Read-only property accessing the left horizontal coordinate.- # @return A number, or None if not available.- left = property(lambda self: self.get("/Left", None))-- ##- # Read-only property accessing the right horizontal coordinate.- # @return A number, or None if not available.- right = property(lambda self: self.get("/Right", None))-- ##- # Read-only property accessing the top vertical coordinate.- # @return A number, or None if not available.- top = property(lambda self: self.get("/Top", None))-- ##- # Read-only property accessing the bottom vertical coordinate.- # @return A number, or None if not available.- bottom = property(lambda self: self.get("/Bottom", None))--def convertToInt(d, size):- if size > 8:- raise utils.PdfReadError("invalid size in convertToInt")- d = "\x00\x00\x00\x00\x00\x00\x00\x00" + d- d = d[-8:]- return struct.unpack(">q", d)[0]--# ref: pdf1.8 spec section 3.5.2 algorithm 3.2-_encryption_padding = '\x28\xbf\x4e\x5e\x4e\x75\x8a\x41\x64\x00\x4e\x56' + \- '\xff\xfa\x01\x08\x2e\x2e\x00\xb6\xd0\x68\x3e\x80\x2f\x0c' + \- '\xa9\xfe\x64\x53\x69\x7a'--# Implementation of algorithm 3.2 of the PDF standard security handler,-# section 3.5.2 of the PDF 1.6 reference.-def _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encrypt=True):- # 1. Pad or truncate the password string to exactly 32 bytes. If the- # password string is more than 32 bytes long, use only its first 32 bytes;- # if it is less than 32 bytes long, pad it by appending the required number- # of additional bytes from the beginning of the padding string- # (_encryption_padding).- password = (password + _encryption_padding)[:32]- # 2. Initialize the MD5 hash function and pass the result of step 1 as- # input to this function.- import struct- m = md5(password)- # 3. Pass the value of the encryption dictionary's /O entry to the MD5 hash- # function.- m.update(owner_entry)- # 4. Treat the value of the /P entry as an unsigned 4-byte integer and pass- # these bytes to the MD5 hash function, low-order byte first.- p_entry = struct.pack('<i', p_entry)- m.update(p_entry)- # 5. Pass the first element of the file's file identifier array to the MD5- # hash function.- m.update(id1_entry)- # 6. (Revision 3 or greater) If document metadata is not being encrypted,- # pass 4 bytes with the value 0xFFFFFFFF to the MD5 hash function.- if rev >= 3 and not metadata_encrypt:- m.update("\xff\xff\xff\xff")- # 7. Finish the hash.- md5_hash = m.digest()- # 8. (Revision 3 or greater) Do the following 50 times: Take the output- # from the previous MD5 hash and pass the first n bytes of the output as- # input into a new MD5 hash, where n is the number of bytes of the- # encryption key as defined by the value of the encryption dictionary's- # /Length entry.- if rev >= 3:- for i in range(50):- md5_hash = md5(md5_hash[:keylen]).digest()- # 9. Set the encryption key to the first n bytes of the output from the- # final MD5 hash, where n is always 5 for revision 2 but, for revision 3 or- # greater, depends on the value of the encryption dictionary's /Length- # entry.- return md5_hash[:keylen]--# Implementation of algorithm 3.3 of the PDF standard security handler,-# section 3.5.2 of the PDF 1.6 reference.-def _alg33(owner_pwd, user_pwd, rev, keylen):- # steps 1 - 4- key = _alg33_1(owner_pwd, rev, keylen)- # 5. Pad or truncate the user password string as described in step 1 of- # algorithm 3.2.- user_pwd = (user_pwd + _encryption_padding)[:32]- # 6. Encrypt the result of step 5, using an RC4 encryption function with- # the encryption key obtained in step 4.- val = utils.RC4_encrypt(key, user_pwd)- # 7. (Revision 3 or greater) Do the following 19 times: Take the output- # from the previous invocation of the RC4 function and pass it as input to- # a new invocation of the function; use an encryption key generated by- # taking each byte of the encryption key obtained in step 4 and performing- # an XOR operation between that byte and the single-byte value of the- # iteration counter (from 1 to 19).- if rev >= 3:- for i in range(1, 20):- new_key = ''- for l in range(len(key)):- new_key += chr(ord(key[l]) ^ i)- val = utils.RC4_encrypt(new_key, val)- # 8. Store the output from the final invocation of the RC4 as the value of- # the /O entry in the encryption dictionary.- return val--# Steps 1-4 of algorithm 3.3-def _alg33_1(password, rev, keylen):- # 1. Pad or truncate the owner password string as described in step 1 of- # algorithm 3.2. If there is no owner password, use the user password- # instead.- password = (password + _encryption_padding)[:32]- # 2. Initialize the MD5 hash function and pass the result of step 1 as- # input to this function.- m = md5(password)- # 3. (Revision 3 or greater) Do the following 50 times: Take the output- # from the previous MD5 hash and pass it as input into a new MD5 hash.- md5_hash = m.digest()- if rev >= 3:- for i in range(50):- md5_hash = md5(md5_hash).digest()- # 4. Create an RC4 encryption key using the first n bytes of the output- # from the final MD5 hash, where n is always 5 for revision 2 but, for- # revision 3 or greater, depends on the value of the encryption- # dictionary's /Length entry.- key = md5_hash[:keylen]- return key--# Implementation of algorithm 3.4 of the PDF standard security handler,-# section 3.5.2 of the PDF 1.6 reference.-def _alg34(password, owner_entry, p_entry, id1_entry):- # 1. Create an encryption key based on the user password string, as- # described in algorithm 3.2.- key = _alg32(password, 2, 5, owner_entry, p_entry, id1_entry)- # 2. Encrypt the 32-byte padding string shown in step 1 of algorithm 3.2,- # using an RC4 encryption function with the encryption key from the- # preceding step.- U = utils.RC4_encrypt(key, _encryption_padding)- # 3. Store the result of step 2 as the value of the /U entry in the- # encryption dictionary.- return U, key--# Implementation of algorithm 3.4 of the PDF standard security handler,-# section 3.5.2 of the PDF 1.6 reference.-def _alg35(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encrypt):- # 1. Create an encryption key based on the user password string, as- # described in Algorithm 3.2.- key = _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry)- # 2. Initialize the MD5 hash function and pass the 32-byte padding string- # shown in step 1 of Algorithm 3.2 as input to this function.- m = md5()- m.update(_encryption_padding)- # 3. Pass the first element of the file's file identifier array (the value- # of the ID entry in the document's trailer dictionary; see Table 3.13 on- # page 73) to the hash function and finish the hash. (See implementation- # note 25 in Appendix H.)- m.update(id1_entry)- md5_hash = m.digest()- # 4. Encrypt the 16-byte result of the hash, using an RC4 encryption- # function with the encryption key from step 1.- val = utils.RC4_encrypt(key, md5_hash)- # 5. Do the following 19 times: Take the output from the previous- # invocation of the RC4 function and pass it as input to a new invocation- # of the function; use an encryption key generated by taking each byte of- # the original encryption key (obtained in step 2) and performing an XOR- # operation between that byte and the single-byte value of the iteration- # counter (from 1 to 19).- for i in range(1, 20):- new_key = ''- for l in range(len(key)):- new_key += chr(ord(key[l]) ^ i)- val = utils.RC4_encrypt(new_key, val)- # 6. Append 16 bytes of arbitrary padding to the output from the final- # invocation of the RC4 function and store the 32-byte result as the value- # of the U entry in the encryption dictionary.- # (implementator note: I don't know what "arbitrary padding" is supposed to- # mean, so I have used null bytes. This seems to match a few other- # people's implementations)- return val + ('\x00' * 16), key--#if __name__ == "__main__":-# output = PdfFileWriter()-#-# input1 = PdfFileReader(file("test\\5000-s1-05e.pdf", "rb"))-# page1 = input1.getPage(0)-#-# input2 = PdfFileReader(file("test\\PDFReference16.pdf", "rb"))-# page2 = input2.getPage(0)-# page3 = input2.getPage(1)-# page1.mergePage(page2)-# page1.mergePage(page3)-#-# input3 = PdfFileReader(file("test\\cc-cc.pdf", "rb"))-# page1.mergePage(input3.getPage(0))-#-# page1.compressContentStreams()-#-# output.addPage(page1)-# output.write(file("test\\merge-test.pdf", "wb"))--diff --git a/ext/pyPdf/utils.py b/ext/pyPdf/utils.pydeleted file mode 100644index 7c1d472d..00000000--- a/ext/pyPdf/utils.py+++ /dev/null@@ -1,122 +0,0 @@-# vim: sw=4:expandtab:foldmethod=marker-#-# Copyright (c) 2006, Mathieu Fenniak-# All rights reserved.-#-# Redistribution and use in source and binary forms, with or without-# modification, are permitted provided that the following conditions are-# met:-#-# * Redistributions of source code must retain the above copyright notice,-# this list of conditions and the following disclaimer.-# * Redistributions in binary form must reproduce the above copyright notice,-# this list of conditions and the following disclaimer in the documentation-# and/or other materials provided with the distribution.-# * The name of the author may not be used to endorse or promote products-# derived from this software without specific prior written permission.-#-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"-# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE-# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE-# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE-# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR-# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF-# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS-# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN-# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)-# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE-# POSSIBILITY OF SUCH DAMAGE.---"""-Utility functions for PDF library.-"""-__author__ = "Mathieu Fenniak"-__author_email__ = "[email protected]"--#ENABLE_PSYCO = False-#if ENABLE_PSYCO:-# try:-# import psyco-# except ImportError:-# ENABLE_PSYCO = False-#-#if not ENABLE_PSYCO:-# class psyco:-# def proxy(func):-# return func-# proxy = staticmethod(proxy)--def readUntilWhitespace(stream, maxchars=None):- txt = ""- while True:- tok = stream.read(1)- if tok.isspace() or not tok:- break- txt += tok- if len(txt) == maxchars:- break- return txt--def readNonWhitespace(stream):- tok = ' '- while tok == '\n' or tok == '\r' or tok == ' ' or tok == '\t':- tok = stream.read(1)- return tok--class ConvertFunctionsToVirtualList(object):- def __init__(self, lengthFunction, getFunction):- self.lengthFunction = lengthFunction- self.getFunction = getFunction-- def __len__(self):- return self.lengthFunction()-- def __getitem__(self, index):- if not isinstance(index, int):- raise TypeError, "sequence indices must be integers"- len_self = len(self)- if index < 0:- # support negative indexes- index = len_self + index- if index < 0 or index >= len_self:- raise IndexError, "sequence index out of range"- return self.getFunction(index)--def RC4_encrypt(key, plaintext):- S = [i for i in range(256)]- j = 0- for i in range(256):- j = (j + S[i] + ord(key[i % len(key)])) % 256- S[i], S[j] = S[j], S[i]- i, j = 0, 0- retval = ""- for x in range(len(plaintext)):- i = (i + 1) % 256- j = (j + S[i]) % 256- S[i], S[j] = S[j], S[i]- t = S[(S[i] + S[j]) % 256]- retval += chr(ord(plaintext[x]) ^ t)- return retval--def matrixMultiply(a, b):- return [[sum([float(i)*float(j)- for i, j in zip(row, col)]- ) for col in zip(*b)]- for row in a]--class PyPdfError(Exception):- pass--class PdfReadError(PyPdfError):- pass--class PageSizeNotDefinedError(PyPdfError):- pass--if __name__ == "__main__":- # test RC4- out = RC4_encrypt("Key", "Plaintext")- print repr(out)- pt = RC4_encrypt("Key", out)- print repr(pt)diff --git a/modules/sfp_filemeta.py b/modules/sfp_filemeta.pyindex 77b5002f..4f9ff449 100644--- a/modules/sfp_filemeta.py+++ b/modules/sfp_filemeta.py@@ -12,7 +12,7 @@# -------------------------------------------------------------------------------import mimetypes-import metapdf+import PyPDF2import openxmllibimport exifreadimport lxml@@ -75,7 +75,8 @@ class sfp_filemeta(SpiderFootPlugin):# Fetch the file, allow much more time given that these files are# typically large.ret = self.sf.fetchUrl(eventData, timeout=self.opts['timeout'],- useragent=self.opts['_useragent'], dontMangle=True)+ useragent=self.opts['_useragent'], dontMangle=True,+ sizeLimit=10000000)if ret['content'] is None:self.sf.error("Unable to fetch file for meta analysis: " +eventData, False)@@ -92,7 +93,9 @@ class sfp_filemeta(SpiderFootPlugin):if fileExt.lower() == "pdf":try:raw = StringIO(ret['content'])- data = metapdf.MetaPdfReader().read_metadata(raw)+ #data = metapdf.MetaPdfReader().read_metadata(raw)+ pdf = PyPDF2.PdfFileReader(raw, strict=False)+ data = pdf.getDocumentInfo()meta = str(data)self.sf.debug("Obtained meta data from " + eventData)except BaseException as e:@@ -127,7 +130,7 @@ class sfp_filemeta(SpiderFootPlugin):self.sf.error("Unable to parse meta data from: " +eventData + "(" + str(e) + ")", False)- if meta is not None:+ if meta is not None and data is not None:evt = SpiderFootEvent("RAW_FILE_META_DATA", meta,self.__name__, event)self.notifyListeners(evt)