root / pkpgcounter / trunk / pkpgpdls / ooo.py @ 508

Revision 491, 2.3 kB (checked in by jerome, 17 years ago)

Major code cleaning. Now clearer, although probably a bit slower since
a file can be opened several times.
Now universal line opening mode is only used when needed (PS, PDF and plain
text), and binary opening mode is used for the other formats.
This mean we will be able to remove mmap calls wherever possible, finally.

  • 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 modules implements a page counter for OpenDocument documents."""
24
25import sys
26import zipfile
27
28import pdlparser
29
30class Parser(pdlparser.PDLParser) :
31    """A parser for OpenOffice.org documents."""
32    def isValid(self) :       
33        """Returns True if data is OpenDocument, else False."""
34        if self.firstblock[:2] == "PK" :
35            try :
36                self.archive = zipfile.ZipFile(self.infile)
37                self.contentxml = self.archive.read("content.xml")
38                self.metaxml = self.archive.read("meta.xml")
39            except :   
40                return False
41            else :
42                self.logdebug("DEBUG: Input file is in the OpenDocument (ISO/IEC DIS 26300) format.")
43                return True
44        else :   
45            return False
46           
47    def getJobSize(self) :
48        """Counts pages in an OpenOffice.org document.
49       
50           Algorithm by Jerome Alet.
51        """
52        pagecount = 0
53        try :
54            # First try with Text documents
55            index = self.metaxml.index("meta:page-count=")
56            pagecount = int(self.metaxml[index:].split('"')[1])
57        except :
58            # Now try with Impress documents
59            pagecount = self.contentxml.count("<draw:page ")
60            if not pagecount :
61                # Probably a Spreadsheet document
62                raise pdlparser.PDLParserError, "OpenOffice.org's spreadsheet documents are not yet supported."
63        return pagecount
Note: See TracBrowser for help on using the browser.