diff options
| author | Olivier Dony <odo@openerp.com> | 2011-01-11 17:53:11 +0100 |
|---|---|---|
| committer | Olivier Dony <odo@openerp.com> | 2011-01-11 17:53:11 +0100 |
| commit | d47b0969fa9e9a42031e9dbf60e20ed9cfd4e799 (patch) | |
| tree | e9c11c6d97e23dbb658af948e7cc1664270360ac /bin | |
| parent | 480026aa89572869911bd6ebae6d24eb52a3d5df (diff) | |
| parent | 73af237c8b40dd6f57b54273f731576713a877ba (diff) | |
[MERGE] report: updated pyPdf library to release 1.13 (pending change to pure dependency)
bzr revid: odo@openerp.com-20110111165311-6bwk8qdtskful0yd
Diffstat (limited to 'bin')
| -rw-r--r-- | bin/report/pyPdf/__init__.py | 1 | ||||
| -rw-r--r-- | bin/report/pyPdf/filters.py | 505 | ||||
| -rw-r--r-- | bin/report/pyPdf/generic.py | 35 | ||||
| -rw-r--r-- | bin/report/pyPdf/pdf.py | 418 | ||||
| -rw-r--r-- | bin/report/pyPdf/utils.py | 233 | ||||
| -rw-r--r-- | bin/report/pyPdf/xmp.py | 711 |
6 files changed, 1136 insertions, 767 deletions
diff --git a/bin/report/pyPdf/__init__.py b/bin/report/pyPdf/__init__.py index 28360a93847..af02553da69 100644 --- a/bin/report/pyPdf/__init__.py +++ b/bin/report/pyPdf/__init__.py @@ -1,3 +1,2 @@ -# -*- coding: utf-8 -*- from pdf import PdfFileReader, PdfFileWriter __all__ = ["pdf"] diff --git a/bin/report/pyPdf/filters.py b/bin/report/pyPdf/filters.py index 04bb7d9df55..7fe10fb4819 100644 --- a/bin/report/pyPdf/filters.py +++ b/bin/report/pyPdf/filters.py @@ -1,253 +1,252 @@ -# -*- coding: utf-8 -*- -# 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__ = "biziqe@mathieu.fenniak.net" - -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>Cj@.4Gp$d7F!,L7@<6@)/0JDEF<G%<+EV:2F!, - O<DJ+*.@<*K0@<6L(Df-\\0Ec5e;DffZ(EZee.Bl.9pF"AGXBPCsi+DGm>@3BB/F*&OCAfu2/AKY - i(DIb:@FD,*)+C]U=@3BN#EcYf8ATD3s@q?d$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 - +# 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__ = "biziqe@mathieu.fenniak.net"
+
+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>Cj@.4Gp$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/bin/report/pyPdf/generic.py b/bin/report/pyPdf/generic.py index f216732a85d..aaf503180f8 100644 --- a/bin/report/pyPdf/generic.py +++ b/bin/report/pyPdf/generic.py @@ -1,4 +1,3 @@ -# -*- coding: utf-8 -*- # vim: sw=4:expandtab:foldmethod=marker # # Copyright (c) 2006, Mathieu Fenniak @@ -207,15 +206,18 @@ class FloatObject(decimal.Decimal, PdfObject): def __new__(cls, value="0", context=None): return decimal.Decimal.__new__(cls, str(value), context) def __repr__(self): - return str(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(str(self)) + stream.write(repr(self)) class NumberObject(int, PdfObject): def __init__(self, value): - int.__init__(self) - self = value + int.__init__(value) def writeToStream(self, stream, encryption_key): stream.write(repr(self)) @@ -301,7 +303,7 @@ def readStringFromStream(stream): elif tok == "t": tok = "\t" elif tok == "b": - tok == "\b" + tok = "\b" elif tok == "f": tok = "\f" elif tok == "(": @@ -311,7 +313,17 @@ def readStringFromStream(stream): elif tok == "\\": tok = "\\" elif tok.isdigit(): - tok += stream.read(2) + # "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 @@ -405,8 +417,7 @@ class NameObject(str, PdfObject): delimiterCharacters = "(", ")", "<", ">", "[", "]", "{", "}", "/", "%" def __init__(self, data): - str.__init__(self) - self = data + str.__init__(data) def writeToStream(self, stream, encryption_key): stream.write(self) @@ -710,6 +721,12 @@ class RectangleObject(ArrayObject): 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) diff --git a/bin/report/pyPdf/pdf.py b/bin/report/pyPdf/pdf.py index 9bc56cf8b05..bf60d0157dc 100644 --- a/bin/report/pyPdf/pdf.py +++ b/bin/report/pyPdf/pdf.py @@ -1,4 +1,5 @@ # -*- coding: utf-8 -*- +# # vim: sw=4:expandtab:foldmethod=marker # # Copyright (c) 2006, Mathieu Fenniak @@ -39,7 +40,9 @@ It may be a solid base for future PDF file work in Python. __author__ = "Mathieu Fenniak" __author_email__ = "biziqe@mathieu.fenniak.net" +import math import struct +from sys import version_info try: from cStringIO import StringIO except ImportError: @@ -51,6 +54,14 @@ 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}). @@ -93,6 +104,21 @@ class PdfFileWriter(object): 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> @@ -101,12 +127,64 @@ class PdfFileWriter(object): # @param page The page to add to the document. This argument should be # an instance of {@link #PageObject PageObject}. def addPage(self, page): - assert page["/Type"] == "/Page" - page[NameObject("/Parent")] = self._pages - page = self._addObject(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) - pages["/Kids"].append(page) - pages[NameObject("/Count")] = NumberObject(pages["/Count"] + 1) + # 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. @@ -119,7 +197,7 @@ class PdfFileWriter(object): # 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 md5, time, random + import time, random if owner_pwd == None: owner_pwd = user_pwd if use_128bit: @@ -133,8 +211,8 @@ class PdfFileWriter(object): # permit everything: P = -1 O = ByteStringObject(_alg33(owner_pwd, user_pwd, rev, keylen)) - ID_1 = md5.new(repr(time.time())).digest() - ID_2 = md5.new(repr(random.random())).digest() + 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) @@ -160,9 +238,28 @@ class PdfFileWriter(object): # @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, md5 + 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 @@ -181,7 +278,7 @@ class PdfFileWriter(object): pack2 = struct.pack("<i", 0)[:2] key = self._encrypt_key + pack1 + pack2 assert len(key) == (len(self._encrypt_key) + 5) - md5_hash = md5.new(key).digest() + md5_hash = md5(key).digest() key = md5_hash[:min(16, len(self._encrypt_key) + 5)] obj.writeToStream(stream, key) stream.write("\nendobj\n") @@ -487,7 +584,7 @@ class PdfFileReader(object): pages = property(lambda self: ConvertFunctionsToVirtualList(self.getNumPages, self.getPage), None, None) - def _flatten(self, pages=None, inherit=None): + def _flatten(self, pages=None, inherit=None, indirectRef=None): inheritablePageAttributes = ( NameObject("/Resources"), NameObject("/MediaBox"), NameObject("/CropBox"), NameObject("/Rotate") @@ -504,14 +601,17 @@ class PdfFileReader(object): if pages.has_key(attr): inherit[attr] = pages[attr] for page in pages["/Kids"]: - self._flatten(page.getObject(), inherit) + 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) + pageObj = PageObject(self, indirectRef) pageObj.update(pages) self.flattenedPages.append(pageObj) @@ -554,12 +654,12 @@ class PdfFileReader(object): if not hasattr(self, '_decryption_key'): raise Exception, "file has not been decrypted" # otherwise, decrypt here... - import struct, md5 + 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.new(key).digest() + md5_hash = md5(key).digest() key = md5_hash[:min(16, len(self._decryption_key) + 5)] retval = self._decryptObject(retval, key) @@ -890,11 +990,46 @@ def createRectangleAccessor(name, fallback): ## # 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. +# 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): + 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. @@ -931,7 +1066,7 @@ class PageObject(DictionaryObject): renameRes[key] = newname newRes[newname] = page2Res[key] elif not newRes.has_key(key): - newRes[key] = page2Res[key] + newRes[key] = page2Res.raw_get(key) return newRes, renameRes _mergeResources = staticmethod(_mergeResources) @@ -957,6 +1092,26 @@ class PageObject(DictionaryObject): 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 @@ -968,7 +1123,23 @@ class PageObject(DictionaryObject): # @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. @@ -978,7 +1149,7 @@ class PageObject(DictionaryObject): originalResources = self["/Resources"].getObject() page2Resources = page2["/Resources"].getObject() - for res in "/ExtGState", "/Font", "/XObject", "/ColorSpace", "/Pattern", "/Shading": + for res in "/ExtGState", "/Font", "/XObject", "/ColorSpace", "/Pattern", "/Shading", "/Properties": new, newrename = PageObject._mergeResources(originalResources, page2Resources, res) if new: newResources[NameObject(res)] = new @@ -993,18 +1164,192 @@ class PageObject(DictionaryObject): newContentArray = ArrayObject() - originalContent = self["/Contents"].getObject() - newContentArray.append(PageObject._pushPopGS(originalContent, self.pdf)) + originalContent = self.getContents() + if originalContent is not None: + newContentArray.append(PageObject._pushPopGS( + originalContent, self.pdf)) - page2Content = page2['/Contents'].getObject() - page2Content = PageObject._contentStreamRename(page2Content, rename, self.pdf) - page2Content = PageObject._pushPopGS(page2Content, self.pdf) - newContentArray.append(page2Content) + 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> @@ -1012,10 +1357,11 @@ class PageObject(DictionaryObject): # 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["/Contents"].getObject() - if not isinstance(content, ContentStream): - content = ContentStream(content, self.pdf) - self[NameObject("/Contents")] = content.flateEncode() + 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 @@ -1369,8 +1715,8 @@ def _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encr password = (password + _encryption_padding)[:32] # 2. Initialize the MD5 hash function and pass the result of step 1 as # input to this function. - import md5, struct - m = md5.new(password) + 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) @@ -1394,7 +1740,7 @@ def _alg32(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encr # /Length entry. if rev >= 3: for i in range(50): - md5_hash = md5.new(md5_hash[:keylen]).digest() + 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 @@ -1436,14 +1782,13 @@ def _alg33_1(password, rev, keylen): password = (password + _encryption_padding)[:32] # 2. Initialize the MD5 hash function and pass the result of step 1 as # input to this function. - import md5 - m = md5.new(password) + 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.new(md5_hash).digest() + 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 @@ -1473,8 +1818,7 @@ def _alg35(password, rev, keylen, owner_entry, p_entry, id1_entry, metadata_encr 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. - import md5 - m = md5.new() + 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 diff --git a/bin/report/pyPdf/utils.py b/bin/report/pyPdf/utils.py index 2a778dd0c05..7c1d472d0b7 100644 --- a/bin/report/pyPdf/utils.py +++ b/bin/report/pyPdf/utils.py @@ -1,111 +1,122 @@ -# -*- coding: utf-8 -*- -# 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__ = "biziqe@mathieu.fenniak.net" - -#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 - -class PdfReadError(Exception): - pass - -if __name__ == "__main__": - # test RC4 - out = RC4_encrypt("Key", "Plaintext") - print repr(out) - pt = RC4_encrypt("Key", out) - print repr(pt) +# 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__ = "biziqe@mathieu.fenniak.net"
+
+#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/bin/report/pyPdf/xmp.py b/bin/report/pyPdf/xmp.py index 5018b7825ed..b070df9093e 100644 --- a/bin/report/pyPdf/xmp.py +++ b/bin/report/pyPdf/xmp.py @@ -1,356 +1,355 @@ -# -*- coding: utf-8 -*- -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
+
+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)
+
+
|