2016-11-08 19:01:11 +00:00
|
|
|
|
2009-11-04 11:28:32 +00:00
|
|
|
|
|
|
|
""" Python implementation of ASCII85/ASCIIHex decoder (Adobe version).
|
|
|
|
|
|
|
|
This code is in the public domain.
|
|
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
import re
|
|
|
|
import struct
|
2008-08-30 07:40:52 +00:00
|
|
|
|
2014-09-03 11:17:41 +00:00
|
|
|
import six #Python 2+3 compatibility
|
|
|
|
|
2013-11-07 08:35:04 +00:00
|
|
|
|
2008-08-30 07:40:52 +00:00
|
|
|
# ascii85decode(data)
|
|
|
|
def ascii85decode(data):
|
2009-11-04 11:28:32 +00:00
|
|
|
"""
|
|
|
|
In ASCII85 encoding, every four bytes are encoded with five ASCII
|
|
|
|
letters, using 85 different types of characters (as 256**4 < 85**5).
|
|
|
|
When the length of the original bytes is not a multiple of 4, a special
|
|
|
|
rule is used for round up.
|
2013-11-07 07:14:53 +00:00
|
|
|
|
2009-11-04 11:28:32 +00:00
|
|
|
The Adobe's ASCII85 implementation is slightly different from
|
|
|
|
its original in handling the last characters.
|
2013-11-07 07:14:53 +00:00
|
|
|
|
2009-11-04 11:28:32 +00:00
|
|
|
"""
|
2009-10-24 04:41:59 +00:00
|
|
|
n = b = 0
|
2014-06-30 10:05:56 +00:00
|
|
|
out = b''
|
2014-09-03 11:17:41 +00:00
|
|
|
for i in six.iterbytes(data):
|
|
|
|
c=six.int2byte(i)
|
2014-06-30 10:05:56 +00:00
|
|
|
if b'!' <= c and c <= b'u':
|
2009-10-24 04:41:59 +00:00
|
|
|
n += 1
|
|
|
|
b = b*85+(ord(c)-33)
|
|
|
|
if n == 5:
|
2013-11-07 08:35:04 +00:00
|
|
|
out += struct.pack('>L', b)
|
2009-10-24 04:41:59 +00:00
|
|
|
n = b = 0
|
2014-06-30 10:05:56 +00:00
|
|
|
elif c == b'z':
|
2017-05-29 07:06:09 +00:00
|
|
|
assert n == 0, str(n)
|
2014-06-30 10:05:56 +00:00
|
|
|
out += b'\0\0\0\0'
|
|
|
|
elif c == b'~':
|
2009-10-24 04:41:59 +00:00
|
|
|
if n:
|
|
|
|
for _ in range(5-n):
|
|
|
|
b = b*85+84
|
2013-11-07 08:35:04 +00:00
|
|
|
out += struct.pack('>L', b)[:n-1]
|
2009-10-24 04:41:59 +00:00
|
|
|
break
|
|
|
|
return out
|
2008-08-30 07:40:52 +00:00
|
|
|
|
2009-04-08 10:55:01 +00:00
|
|
|
# asciihexdecode(data)
|
2014-09-04 07:36:19 +00:00
|
|
|
hex_re = re.compile(b'([a-f\d]{2})', re.IGNORECASE)
|
|
|
|
trail_re = re.compile(b'^(?:[a-f\d]{2}|\s)*([a-f\d])[\s>]*$', re.IGNORECASE)
|
2013-11-07 08:35:04 +00:00
|
|
|
|
|
|
|
|
2009-04-08 10:55:01 +00:00
|
|
|
def asciihexdecode(data):
|
2009-10-24 04:41:59 +00:00
|
|
|
"""
|
|
|
|
ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
|
|
|
|
For each pair of ASCII hexadecimal digits (0-9 and A-F or a-f), the
|
|
|
|
ASCIIHexDecode filter produces one byte of binary data. All white-space
|
|
|
|
characters are ignored. A right angle bracket character (>) indicates
|
|
|
|
EOD. Any other characters will cause an error. If the filter encounters
|
|
|
|
the EOD marker after reading an odd number of hexadecimal digits, it
|
|
|
|
will behave as if a 0 followed the last digit.
|
|
|
|
"""
|
2014-09-04 07:36:19 +00:00
|
|
|
def decode(x):
|
|
|
|
i=int(x,16)
|
|
|
|
return six.int2byte(i)
|
2017-05-29 07:06:09 +00:00
|
|
|
|
|
|
|
out=b''
|
2014-09-04 07:36:19 +00:00
|
|
|
for x in hex_re.findall(data):
|
|
|
|
out+=decode(x)
|
2017-05-29 07:06:09 +00:00
|
|
|
|
2009-10-24 04:41:59 +00:00
|
|
|
m = trail_re.search(data)
|
|
|
|
if m:
|
2014-09-04 07:36:19 +00:00
|
|
|
out+=decode(m.group(1)+b'0')
|
|
|
|
return out
|