forked from smuehlst/jbig2enc
-
Notifications
You must be signed in to change notification settings - Fork 1
/
pdf.py
170 lines (139 loc) · 4.26 KB
/
pdf.py
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
#!/usr/bin/python
import sys
import re
import struct
import glob
import os
# This is a very simple script to make a PDF file out of the output of a
# multipage symbol compression.
# Run ./jbig2 -s -p <other options> image1.jpeg image1.jpeg ...
# python pdf.py output > out.pdf
class Ref:
def __init__(self, x):
self.x = x
def __str__(self):
return "%d 0 R" % self.x
class Dict:
def __init__(self, values = {}):
self.d = {}
self.d.update(values)
def __str__(self):
s = ['<< ']
for (x, y) in self.d.items():
s.append('/%s ' % x)
s.append(str(y))
s.append("\n")
s.append(">>\n")
return ''.join(s)
global_next_id = 1
class Obj:
next_id = 1
def __init__(self, d = {}, stream = None):
global global_next_id
if stream is not None:
d['Length'] = str(len(stream))
self.d = Dict(d)
self.stream = stream
self.id = global_next_id
global_next_id += 1
def __str__(self):
s = []
s.append(str(self.d))
if self.stream is not None:
s.append('stream\n')
s.append(self.stream)
s.append('\nendstream\n')
s.append('endobj\n')
return ''.join(s)
class Doc:
def __init__(self):
self.objs = []
self.pages = []
def add_object(self, o):
self.objs.append(o)
return o
def add_page(self, o):
self.pages.append(o)
return self.add_object(o)
def __str__(self):
a = []
j = [0]
offsets = []
def add(x):
a.append(x)
j[0] += len(x) + 1
add('%PDF-1.4')
for o in self.objs:
offsets.append(j[0])
add('%d 0 obj' % o.id)
add(str(o))
xrefstart = j[0]
a.append('xref')
a.append('0 %d' % (len(offsets) + 1))
a.append('0000000000 65535 f ')
for o in offsets:
a.append('%010d 00000 n ' % o)
a.append('')
a.append('trailer')
a.append('<< /Size %d\n/Root 1 0 R >>' % (len(offsets) + 1))
a.append('startxref')
a.append(str(xrefstart))
a.append('%%EOF')
# sys.stderr.write(str(offsets) + "\n")
return '\n'.join(a)
def ref(x):
return '%d 0 R' % x
def main(symboltable='symboltable', pagefiles=glob.glob('page-*')):
doc = Doc()
doc.add_object(Obj({'Type' : '/Catalog', 'Outlines' : ref(2), 'Pages' : ref(3)}))
doc.add_object(Obj({'Type' : '/Outlines', 'Count': '0'}))
pages = Obj({'Type' : '/Pages'})
doc.add_object(pages)
symd = doc.add_object(Obj({}, file(symboltable, 'rb').read()))
page_objs = []
pagefiles.sort()
for p in pagefiles:
try:
contents = file(p).read()
except IOError:
sys.stderr.write("error reading page file %s\n"% p)
continue
(width, height,xres,yres) = struct.unpack('>IIII', contents[11:27])
xobj = Obj({'Type': '/XObject', 'Subtype': '/Image', 'Width':
str(width), 'Height': str(height), 'ColorSpace': '/DeviceGray',
'BitsPerComponent': '1', 'Filter': '/JBIG2Decode', 'DecodeParms':
' << /JBIG2Globals %d 0 R >>' % symd.id}, contents)
contents = Obj({}, 'q %f 0 0 %f 0 0 cm /Im1 Do Q' % (float(width * 72) / xres, float(height * 72) / yres))
resources = Obj({'ProcSet': '[/PDF /ImageB]',
'XObject': '<< /Im1 %d 0 R >>' % xobj.id})
page = Obj({'Type': '/Page', 'Parent': '3 0 R',
'MediaBox': '[ 0 0 %f %f ]' % (float(width * 72) / xres, float(height * 72) / yres),
'Contents': ref(contents.id),
'Resources': ref(resources.id)})
[doc.add_object(x) for x in [xobj, contents, resources, page]]
page_objs.append(page)
pages.d.d['Count'] = str(len(page_objs))
pages.d.d['Kids'] = '[' + ' '.join([ref(x.id) for x in page_objs]) + ']'
print str(doc)
def usage(script, msg):
if msg:
sys.stderr.write("%s: %s\n"% (script, msg))
sys.stderr.write("Usage: %s [file_basename] > out.pdf\n"% script)
sys.exit(1)
if __name__ == '__main__':
if sys.platform == "win32":
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
if len(sys.argv) == 2:
sym = sys.argv[1] + '.sym'
pages = glob.glob(sys.argv[1] + '.[0-9]*')
elif len(sys.argv) == 1:
sym = 'symboltable'
pages = glob.glob('page-*')
else:
usage(sys.argv[0], "wrong number of args!")
if not os.path.exists(sym):
usage(sys.argv[0], "symbol table %s not found!"% sym)
elif len(pages) == 0:
usage(sys.argv[0], "no pages found!")
main(sym, pages)