Add PyPDF2 to vendor
This commit is contained in:
Cervinko Cera
parent
2b2d485730
commit
829e926770
|
|
@ -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"]
|
||||
|
|
@ -0,0 +1 @@
|
|||
__version__ = '1.26.0'
|
||||
|
|
@ -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__ = "biziqe@mathieu.fenniak.net"
|
||||
|
||||
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 data
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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()
|
||||
|
|
@ -0,0 +1,152 @@
|
|||
#!/usr/bin/env python
|
||||
"""
|
||||
Representation and utils for ranges of PDF file pages.
|
||||
|
||||
Copyright (c) 2014, Steve Witham <switham_github@mac-guyver.com>.
|
||||
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 pairs
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -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__ = "biziqe@mathieu.fenniak.net"
|
||||
|
||||
|
||||
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']]
|
||||
|
|
@ -0,0 +1,358 @@
|
|||
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
|
||||
"""
|
||||
Loading…
Reference in New Issue