1 | # -*- coding: UTF-8 -*- |
---|
2 | # |
---|
3 | # pkpgcounter : a generic Page Description Language parser |
---|
4 | # |
---|
5 | # (c) 2003, 2004, 2005, 2006, 2007, 2008 Jerome Alet <alet@librelogiciel.com> |
---|
6 | # This program is free software: you can redistribute it and/or modify |
---|
7 | # it under the terms of the GNU General Public License as published by |
---|
8 | # the Free Software Foundation, either version 3 of the License, or |
---|
9 | # (at your option) any later version. |
---|
10 | # |
---|
11 | # This program is distributed in the hope that it will be useful, |
---|
12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
14 | # GNU General Public License for more details. |
---|
15 | # |
---|
16 | # You should have received a copy of the GNU General Public License |
---|
17 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
---|
18 | # |
---|
19 | # $Id$ |
---|
20 | # |
---|
21 | |
---|
22 | """This module implements a page counter for Microsoft Word (r) (tm) (c) (etc...) documents""" |
---|
23 | |
---|
24 | import os |
---|
25 | import tempfile |
---|
26 | |
---|
27 | import pdlparser |
---|
28 | import version |
---|
29 | |
---|
30 | class Parser(pdlparser.PDLParser) : |
---|
31 | """A parser for that MS crap thing.""" |
---|
32 | totiffcommands = [ 'xvfb-run -a abiword --import-extension=.doc --print="| gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r\"%(dpi)i\" -sOutputFile=\"%(outfname)s\" -" "%(infname)s"' ] |
---|
33 | required = [ "xvfb-run", "xauth", "abiword", "gs" ] |
---|
34 | format = "Microsoft shitty" |
---|
35 | def isValid(self) : |
---|
36 | """Returns True if data is MS crap, else False. |
---|
37 | |
---|
38 | Identifying datas taken from the file command's magic database. |
---|
39 | IMPORTANT : some magic values are not reused here because they |
---|
40 | IMPORTANT : seem to be specific to some particular i18n release. |
---|
41 | """ |
---|
42 | if self.firstblock.startswith("PO^Q`") \ |
---|
43 | or self.firstblock.startswith("\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1") \ |
---|
44 | or self.firstblock.startswith("\xfe7\x00#") \ |
---|
45 | or self.firstblock.startswith("\xdb\xa5-\x00\x00\x00") \ |
---|
46 | or self.firstblock.startswith("\x31\xbe\x00\x00") \ |
---|
47 | or self.firstblock[2112:].startswith("MSWordDoc") : |
---|
48 | # Here we do the missing test because all commands will be needed even in page counting mode |
---|
49 | if self.isMissing(self.required) : |
---|
50 | return False |
---|
51 | else : |
---|
52 | return True |
---|
53 | else : |
---|
54 | return False |
---|
55 | |
---|
56 | def getJobSize(self) : |
---|
57 | """Counts pages in a Microsoft Word (r) (tm) (c) (etc...) document. |
---|
58 | |
---|
59 | First we convert from .doc to .ps, then we use the PostScript parser. |
---|
60 | """ |
---|
61 | doctops = 'xvfb-run -a abiword --import-extension=.doc --print="%(outfname)s" "%(infname)s"' |
---|
62 | workfile = tempfile.NamedTemporaryFile(mode="w+b") |
---|
63 | try : |
---|
64 | outfname = workfile.name |
---|
65 | infname = self.filename |
---|
66 | status = os.system(doctops % locals()) |
---|
67 | if status or not os.stat(outfname).st_size : |
---|
68 | raise pdlparser.PDLParserError, "Impossible to convert input document %(infname)s to PostScript" % locals() |
---|
69 | psinputfile = open(outfname, "rb") |
---|
70 | try : |
---|
71 | (first, last) = self.parent.readFirstAndLastBlocks(psinputfile) |
---|
72 | import postscript |
---|
73 | return postscript.Parser(self.parent, |
---|
74 | outfname, |
---|
75 | (first, last)).getJobSize() |
---|
76 | finally : |
---|
77 | psinputfile.close() |
---|
78 | finally : |
---|
79 | workfile.close() |
---|
80 | raise pdlparser.PDLParserError, "Impossible to count pages in %(infname)s" % locals() |
---|