root / pkpgcounter / trunk / pkpgpdls / ooo.py @ 1097

Revision 564, 2.4 kB (checked in by jerome, 17 years ago)

Changed copyright years.
Removed unnecessary shebang lines.
Changed default encoding to UTF-8 from ISO-8859-15 (only
ascii is used anyway).

  • Property svn:eol-style set to native
  • Property svn:keywords set to Author Date Id Revision
Line 
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 modules implements a page counter for OpenDocument documents."""
23
24import sys
25import zipfile
26
27import pdlparser
28
29class Parser(pdlparser.PDLParser) :
30    """A parser for OpenOffice.org documents."""
31    totiffcommands = [ 'xvfb-run -a abiword --import-extension=.odt --print="| gs -sDEVICE=tiff24nc -dPARANOIDSAFER -dNOPAUSE -dBATCH -dQUIET -r\"%(dpi)i\" -sOutputFile=\"%(outfname)s\" -" "%(infname)s"' ]
32    required = [ "xvfb-run", "xauth", "abiword", "gs" ]
33    format = "ISO/IEC DIS 26300"
34    def isValid(self) :       
35        """Returns True if data is OpenDocument, else False."""
36        if self.firstblock[:2] == "PK" :
37            try :
38                self.archive = zipfile.ZipFile(self.filename)
39                self.contentxml = self.archive.read("content.xml")
40                self.metaxml = self.archive.read("meta.xml")
41            except :   
42                return False
43            else :
44                return True
45        else :   
46            return False
47           
48    def getJobSize(self) :
49        """Counts pages in an OpenOffice.org document.
50       
51           Algorithm by Jerome Alet.
52        """
53        pagecount = 0
54        try :
55            # First try with Text documents
56            index = self.metaxml.index("meta:page-count=")
57            pagecount = int(self.metaxml[index:].split('"')[1])
58        except :
59            # Now try with Impress documents
60            pagecount = self.contentxml.count("<draw:page ")
61            if not pagecount :
62                # Probably a Spreadsheet document
63                raise pdlparser.PDLParserError, "OpenOffice.org's spreadsheet documents are not yet supported."
64        return pagecount
Note: See TracBrowser for help on using the browser.