def addBookmark(self, title, pagenum, parent=None):
"""
Add a bookmark to the pdf, using the specified title and pointing at
the specified page number. A parent can be specified to make this a
nested bookmark below the parent.
"""
pageRef = self.getObject(self._pages)['/Kids'][pagenum]
action = DictionaryObject()
action.update({
NameObject('/D'):
ArrayObject([pageRef,
NameObject('/FitH'),
NumberObject(826)]),
NameObject('/S'):
NameObject('/GoTo')
})
actionRef = self._addObject(action)
outlineRef = self.getOutlineRoot()
if parent is None:
parent = outlineRef
bookmark = TreeObject()
bookmark.update({
NameObject('/A'): actionRef,
NameObject('/Title'): createStringObject(title)
})
bookmarkRef = self._addObject(bookmark)
parent = parent.getObject()
parent.addChild(bookmarkRef, self)
return bookmarkRef
def addBookmark(self, title, pagenum, parent=None):
"""
Add a bookmark to the pdf, using the specified title and pointing at
the specified page number. A parent can be specified to make this a
nested bookmark below the parent.
"""
pageRef = self.getObject(self._pages)['/Kids'][pagenum]
action = DictionaryObject()
action.update({NameObject('/D'): ArrayObject([pageRef,
NameObject('/FitH'),
NumberObject(826)]),
NameObject('/S'): NameObject('/GoTo')})
actionRef = self._addObject(action)
outlineRef = self.getOutlineRoot()
if parent is None:
parent = outlineRef
bookmark = TreeObject()
bookmark.update({NameObject('/A'): actionRef,
NameObject('/Title'): createStringObject(title)})
bookmarkRef = self._addObject(bookmark)
parent = parent.getObject()
parent.addChild(bookmarkRef, self)
return bookmarkRef
def addNamedDestination(self, title, pagenum):
pageRef = self.getObject(self._pages)['/Kids'][pagenum]
dest = DictionaryObject()
dest.update({NameObject('/D'): ArrayObject([pageRef,
NameObject('/FitH'),
NumberObject(826)]),
NameObject('/S'): NameObject('/GoTo')})
destRef = self._addObject(dest)
nd = self.getNamedDestRoot()
nd.extend([title, destRef])
return destRef
def _mergeResources(res1, res2, resource):
newRes = DictionaryObject()
newRes.update(res1.get(resource, DictionaryObject()).getObject())
page2Res = res2.get(resource, DictionaryObject()).getObject()
renameRes = {}
for key in page2Res.keys():
if key in newRes and newRes[key] != page2Res[key]:
newname = NameObject(key + "renamed")
renameRes[key] = newname
newRes[newname] = page2Res[key]
elif key not in newRes:
newRes[key] = page2Res.raw_get(key)
return newRes, renameRes
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 _mergeResources(res1, res2, resource):
newRes = DictionaryObject()
newRes.update(res1.get(resource, DictionaryObject()).getObject())
page2Res = res2.get(resource, DictionaryObject()).getObject()
renameRes = {}
for key in page2Res.keys():
if key in newRes and newRes[key] != page2Res[key]:
newname = NameObject(key + "renamed")
renameRes[key] = newname
newRes[newname] = page2Res[key]
elif key not in newRes:
newRes[key] = page2Res.raw_get(key)
return newRes, renameRes
def addNamedDestination(self, title, pagenum):
pageRef = self.getObject(self._pages)['/Kids'][pagenum]
dest = DictionaryObject()
dest.update({
NameObject('/D'):
ArrayObject([pageRef,
NameObject('/FitH'),
NumberObject(826)]),
NameObject('/S'):
NameObject('/GoTo')
})
destRef = self._addObject(dest)
nd = self.getNamedDestRoot()
nd.extend([title, destRef])
return destRef
def __init__(self):
self._header = b_("%PDF-1.3")
self._objects = [] # array of indirect objects
# The root of our page tree node.
pages = DictionaryObject()
pages.update({
NameObject("/Type"): NameObject("/Pages"),
NameObject("/Count"): NumberObject(0),
NameObject("/Kids"): ArrayObject()
})
self._pages = self._addObject(pages)
# info object
info = DictionaryObject()
info.update({
NameObject("/Producer"):
createStringObject(
u"Python PDF Library - http://pybrary.net/pyPdf/")
})
self._info = self._addObject(info)
# root object
root = DictionaryObject()
root.update({
NameObject("/Type"): NameObject("/Catalog"),
NameObject("/Pages"): self._pages
})
self._root = self._addObject(root)
def __init__(self):
self._header = b_("%PDF-1.3")
self._objects = [] # array of indirect objects
# The root of our page tree node.
pages = DictionaryObject()
pages.update({NameObject("/Type"): NameObject("/Pages"),
NameObject("/Count"): NumberObject(0),
NameObject("/Kids"): ArrayObject()})
self._pages = self._addObject(pages)
# info object
info = DictionaryObject()
info.update({NameObject("/Producer"): createStringObject(
u"Python PDF Library - http://pybrary.net/pyPdf/")})
self._info = self._addObject(info)
# root object
root = DictionaryObject()
root.update({NameObject("/Type"): NameObject("/Catalog"),
NameObject("/Pages"): self._pages})
self._root = self._addObject(root)
def write(self, stream):
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 is not None:
data = obj.indirectRef
externalReferenceMap.setdefault(data.pdf, {})
externalReferenceMap[data.pdf].setdefault(data.generation, {})
externalReferenceMap[data.pdf][data.generation][data.idnum] = \
IndirectObject(objIndex + 1, 0, self)
self.stack = []
self._sweepIndirectReferences(externalReferenceMap, self._root)
del self.stack
# Begin writing:
object_positions = []
stream.write(self._header + b_("\n"))
for i in range(len(self._objects)):
idnum = (i + 1)
obj = self._objects[i]
object_positions.append(stream.tell())
stream.write(b_(str(idnum) + " 0 obj\n"))
key = None
if hasattr(self, "_encrypt") and idnum != self._encrypt.idnum:
pack1 = struct.pack("<i", i + 1)[:3]
pack2 = struct.pack("<i", 0)[:2]
key = self._encrypt_key + pack1 + pack2
assert len(key) == (len(self._encrypt_key) + 5)
md5_hash = md5(key).digest()
key = md5_hash[:min(16, len(self._encrypt_key) + 5)]
if obj is not None:
obj.writeToStream(stream, key)
stream.write(b_("\nendobj\n"))
# xref table
xref_location = stream.tell()
stream.write(b_("xref\n"))
stream.write(b_("0 %s\n" % (len(self._objects) + 1)))
stream.write(b_("%010d %05d f \n" % (0, 65535)))
for offset in object_positions:
stream.write(b_("%010d %05d n \n" % (offset, 0)))
# trailer
stream.write(b_("trailer\n"))
trailer = DictionaryObject()
trailer.update({
NameObject("/Size"):
NumberObject(len(self._objects) + 1),
NameObject("/Root"):
self._root,
NameObject("/Info"):
self._info
})
if hasattr(self, "_ID"):
trailer[NameObject("/ID")] = self._ID
if hasattr(self, "_encrypt"):
trailer[NameObject("/Encrypt")] = self._encrypt
trailer.writeToStream(stream, None)
# eof
stream.write(b_("\nstartxref\n%s\n%%%%EOF\n" % (xref_location)))
def write(self, stream):
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 is not None:
data = obj.indirectRef
externalReferenceMap.setdefault(data.pdf, {})
externalReferenceMap[data.pdf].setdefault(data.generation, {})
externalReferenceMap[data.pdf][data.generation][data.idnum] = \
IndirectObject(objIndex + 1, 0, self)
self.stack = []
self._sweepIndirectReferences(externalReferenceMap, self._root)
del self.stack
# Begin writing:
object_positions = []
stream.write(self._header + b_("\n"))
for i in range(len(self._objects)):
idnum = (i + 1)
obj = self._objects[i]
object_positions.append(stream.tell())
stream.write(b_(str(idnum) + " 0 obj\n"))
key = None
if hasattr(self, "_encrypt") and idnum != self._encrypt.idnum:
pack1 = struct.pack("<i", i + 1)[:3]
pack2 = struct.pack("<i", 0)[:2]
key = self._encrypt_key + pack1 + pack2
assert len(key) == (len(self._encrypt_key) + 5)
md5_hash = md5(key).digest()
key = md5_hash[:min(16, len(self._encrypt_key) + 5)]
if obj is not None:
obj.writeToStream(stream, key)
stream.write(b_("\nendobj\n"))
# xref table
xref_location = stream.tell()
stream.write(b_("xref\n"))
stream.write(b_("0 %s\n" % (len(self._objects) + 1)))
stream.write(b_("%010d %05d f \n" % (0, 65535)))
for offset in object_positions:
stream.write(b_("%010d %05d n \n" % (offset, 0)))
# trailer
stream.write(b_("trailer\n"))
trailer = DictionaryObject()
trailer.update({NameObject("/Size"): NumberObject(
len(self._objects) + 1),
NameObject("/Root"): self._root,
NameObject("/Info"): self._info})
if hasattr(self, "_ID"):
trailer[NameObject("/ID")] = self._ID
if hasattr(self, "_encrypt"):
trailer[NameObject("/Encrypt")] = self._encrypt
trailer.writeToStream(stream, None)
# eof
stream.write(b_("\nstartxref\n%s\n%%%%EOF\n" % (xref_location)))