source: mesh_mapper.py @ 37:cfb19c3c4214

Revision 37:cfb19c3c4214, 1.8 KB checked in by andre.hagenbruch@rub.de, 7 years ago (diff)

Further improvements on bibliographic templates; integration of DBpedia information based on MESH

Line 
1#!/usr/bin/env python
2# encoding: utf-8
3
4#  The MIT License
5#
6#  Copyright 2010 Andre Hagenbruch <andre.hagenbruch@ruhr-uni-bochum.de>.
7#
8#  Permission is hereby granted, free of charge, to any person obtaining a copy
9#  of this software and associated documentation files (the "Software"), to deal
10#  in the Software without restriction, including without limitation the rights
11#  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
12#  copies of the Software, and to permit persons to whom the Software is
13#  furnished to do so, subject to the following conditions:
14#
15#  The above copyright notice and this permission notice shall be included in
16#  all copies or substantial portions of the Software.
17#
18#  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
19#  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
20#  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
21#  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
22#  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
23#  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
24#  THE SOFTWARE.
25
26__author__="Andre Hagenbruch <andre.hagenbruch@ruhr-uni-bochum.de>"
27__date__ ="$27.07.2010 16:30:22$"
28
29from lxml import etree
30import cPickle as pickle
31
32def make_mapping(filename):
33    mesh = etree.parse(filename)
34    records = mesh.findall('.//DescriptorRecord')
35
36    mapping = {}
37
38    for record in records:
39        mapping.setdefault(record.find('.//DescriptorUI').text, record.find('.//DescriptorName/String').text)
40
41    return mapping
42
43def main():
44    pckl = open('mesh_map.pkl', 'wb')
45    mapping = make_mapping('mesh/desc2010.xml')
46    pickle.dump(mapping, pckl, -1)
47
48if __name__ == '__main__':
49    main()
Note: See TracBrowser for help on using the repository browser.