1 # -*- encoding: utf-8 -*-
2 ##############################################################################
4 # OpenERP, Open Source Management Solution
5 # Copyright (C) 2004-2009 Tiny SPRL (<http://tiny.be>). All Rights Reserved
8 # This program is free software: you can redistribute it and/or modify
9 # it under the terms of the GNU General Public License as published by
10 # the Free Software Foundation, either version 3 of the License, or
11 # (at your option) any later version.
13 # This program is distributed in the hope that it will be useful,
14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 # GNU General Public License for more details.
18 # You should have received a copy of the GNU General Public License
19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
21 ##############################################################################
29 # This should be the indexer
33 return s.decode('utf-8')
36 return s.decode('latin')
39 return s.encode('ascii')
44 def content_index(content, filename=None, content_type=None):
45 fname,ext = os.path.splitext(filename)
47 if ext in ('.doc'): #or content_type ?
48 (stdin,stdout) = os.popen2('antiword -', 'b')
51 result = _to_unicode(stdout.read())
53 file_descriptor, file_name = tempfile.mkstemp(suffix=ext)
54 os.write(file_descriptor, content)
55 os.close(file_descriptor)
56 fp = os.popen('pdftotext -enc UTF-8 -nopgbrk '+file_name+' -', 'r')
59 elif ext in ('.xls','.ods','.odt','.odp'):
60 s = StringIO.StringIO(content)
61 o = odt2txt.OpenDocumentTextFile(s)
62 result = _to_unicode(o.toString())
64 elif ext in ('.txt','.py','.patch','.html','.csv','.xml'):
70 # vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4: