root / pkpgcounter / trunk / pkpgpdls / mstrash.py @ 519

Revision 519, 2.0 kB (checked in by jerome, 16 years ago)

Added a skeleton for Microsoft Word (c) (tm) (r) (etc...) documents.

  • Property svn:eol-style set to native
  • Property svn:keywords set to Author Date Id Revision
Line 
1#! /usr/bin/env python
2# -*- coding: ISO-8859-15 -*-
3#
4# pkpgcounter : a generic Page Description Language parser
5#
6# (c) 2003, 2004, 2005, 2006, 2007 Jerome Alet <alet@librelogiciel.com>
7# This program is free software: you can redistribute it and/or modify
8# it under the terms of the GNU General Public License as published by
9# the Free Software Foundation, either version 3 of the License, or
10# (at your option) any later version.
11#
12# This program is distributed in the hope that it will be useful,
13# but WITHOUT ANY WARRANTY; without even the implied warranty of
14# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
15# GNU General Public License for more details.
16#
17# You should have received a copy of the GNU General Public License
18# along with this program.  If not, see <http://www.gnu.org/licenses/>.
19#
20# $Id$
21#
22
23"""This module implements a page counter for Microsoft Word (r) (tm) (c) (etc...) documents"""
24
25import os
26import urllib2
27
28import pdlparser
29import version
30
31class Parser(pdlparser.PDLParser) :
32    """A parser for that MS crap thing."""
33    totiffcommands = [ ]
34    def isValid(self) :   
35        """Returns True if data is MS crap, else False.
36       
37           Identifying datas taken from the file command's magic database.
38           IMPORTANT : some magic values are not reused here because they
39           IMPORTANT : seem to be specific to some particular i18n release.
40        """   
41        if self.firstblock.startswith("PO^Q`") \
42           or self.firstblock.startswith("\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1") \
43           or self.firstblock.startswith("\xfe7\x00#") \
44           or self.firstblock.startswith("\xdb\xa5-\x00\x00\x00") \
45           or self.firstblock.startswith("\x31\xbe\x00\x00") \
46           or self.firstblock[2112:].startswith("MSWordDoc") :
47            self.logdebug("DEBUG: Input file seems to be in a Microsoft shitty file format.")
48            return True
49        else :   
50            return False
51           
52    def getJobSize(self) :
53        """Counts pages in a Microsoft Word (r) (tm) (c) (etc...) document."""
54        return 0
Note: See TracBrowser for help on using the browser.