1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
# A part of pdfrw (https://github.com/pmaupin/pdfrw)
# Copyright (C) 2006-2015 Patrick Maupin, Austin, Texas
# MIT license -- See LICENSE.txt for details
from .pdfname import PdfName, BasePdfName
from .pdfindirect import PdfIndirect
from .pdfobject import PdfObject
from ..py23_diffs import iteritems
from ..errors import PdfParseError
class _DictSearch(object):
''' Used to search for inheritable attributes.
'''
def __init__(self, basedict):
self.basedict = basedict
def __getattr__(self, name, PdfName=PdfName):
return self[PdfName(name)]
def __getitem__(self, name, set=set, getattr=getattr, id=id):
visited = set()
mydict = self.basedict
while 1:
value = mydict[name]
if value is not None:
return value
myid = id(mydict)
assert myid not in visited
visited.add(myid)
mydict = mydict.Parent
if mydict is None:
return
class _Private(object):
''' Used to store private attributes (not output to PDF files)
on PdfDict classes
'''
def __init__(self, pdfdict):
vars(self)['pdfdict'] = pdfdict
def __setattr__(self, name, value):
vars(self.pdfdict)[name] = value
class PdfDict(dict):
''' PdfDict objects are subclassed dictionaries
with the following features:
- Every key in the dictionary starts with "/"
- A dictionary item can be deleted by assigning it to None
- Keys that (after the initial "/") conform to Python
naming conventions can also be accessed (set and retrieved)
as attributes of the dictionary. E.g. mydict.Page is the
same thing as mydict['/Page']
- Private attributes (not in the PDF space) can be set
on the dictionary object attribute dictionary by using
the private attribute:
mydict.private.foo = 3
mydict.foo = 5
x = mydict.foo # x will now contain 3
y = mydict['/foo'] # y will now contain 5
Most standard adobe dictionary keys start with an upper case letter,
so to avoid conflicts, it is best to start private attributes with
lower case letters.
- PdfDicts have the following read-only properties:
- private -- as discussed above, provides write access to
dictionary's attributes
- inheritable -- this creates and returns a "view" attribute
that will search through the object hierarchy for
any desired attribute, such as /Rotate or /MediaBox
- PdfDicts also have the following special attributes:
- indirect is not stored in the PDF dictionary, but in the object's
attribute dictionary
- stream is also stored in the object's attribute dictionary
and will also update the stream length.
- _stream will store in the object's attribute dictionary without
updating the stream length.
It is possible, for example, to have a PDF name such as "/indirect"
or "/stream", but you cannot access such a name as an attribute:
mydict.indirect -- accesses object's attribute dictionary
mydict["/indirect"] -- accesses actual PDF dictionary
'''
indirect = False
stream = None
_special = dict(indirect=('indirect', False),
stream=('stream', True),
_stream=('stream', False),
)
def __setitem__(self, name, value, setter=dict.__setitem__,
BasePdfName=BasePdfName, isinstance=isinstance):
if not isinstance(name, BasePdfName):
raise PdfParseError('Dict key %s is not a PdfName' % repr(name))
if value is not None:
setter(self, name, value)
elif name in self:
del self[name]
def __init__(self, *args, **kw):
if args:
if len(args) == 1:
args = args[0]
self.update(args)
if isinstance(args, PdfDict):
self.indirect = args.indirect
self._stream = args.stream
for key, value in iteritems(kw):
setattr(self, key, value)
def __getattr__(self, name, PdfName=PdfName):
''' If the attribute doesn't exist on the dictionary object,
try to slap a '/' in front of it and get it out
of the actual dictionary itself.
'''
return self.get(PdfName(name))
def get(self, key, dictget=dict.get, isinstance=isinstance,
PdfIndirect=PdfIndirect):
''' Get a value out of the dictionary,
after resolving any indirect objects.
'''
value = dictget(self, key)
if isinstance(value, PdfIndirect):
self[key] = value = value.real_value()
return value
def __getitem__(self, key):
return self.get(key)
def __setattr__(self, name, value, special=_special.get,
PdfName=PdfName, vars=vars):
''' Set an attribute on the dictionary. Handle the keywords
indirect, stream, and _stream specially (for content objects)
'''
info = special(name)
if info is None:
self[PdfName(name)] = value
else:
name, setlen = info
vars(self)[name] = value
if setlen:
notnone = value is not None
self.Length = notnone and PdfObject(len(value)) or None
def iteritems(self, dictiter=iteritems,
isinstance=isinstance, PdfIndirect=PdfIndirect,
BasePdfName=BasePdfName):
''' Iterate over the dictionary, resolving any unresolved objects
'''
for key, value in list(dictiter(self)):
if isinstance(value, PdfIndirect):
self[key] = value = value.real_value()
if value is not None:
if not isinstance(key, BasePdfName):
raise PdfParseError('Dict key %s is not a PdfName' %
repr(key))
yield key, value
def items(self):
return list(self.iteritems())
def itervalues(self):
for key, value in self.iteritems():
yield value
def values(self):
return list((value for key, value in self.iteritems()))
def keys(self):
return list((key for key, value in self.iteritems()))
def __iter__(self):
for key, value in self.iteritems():
yield key
def iterkeys(self):
return iter(self)
def copy(self):
return type(self)(self)
def pop(self, key):
value = self.get(key)
del self[key]
return value
def popitem(self):
key, value = dict.pop(self)
if isinstance(value, PdfIndirect):
value = value.real_value()
return value
def inheritable(self):
''' Search through ancestors as needed for inheritable
dictionary items.
NOTE: You might think it would be a good idea
to cache this class, but then you'd have to worry
about it pointing to the wrong dictionary if you
made a copy of the object...
'''
return _DictSearch(self)
inheritable = property(inheritable)
def private(self):
''' Allows setting private metadata for use in
processing (not sent to PDF file).
See note on inheritable
'''
return _Private(self)
private = property(private)
class IndirectPdfDict(PdfDict):
''' IndirectPdfDict is a convenience class. You could
create a direct PdfDict and then set indirect = True on it,
or you could just create an IndirectPdfDict.
'''
indirect = True
|