OLD | NEW |
(Empty) | |
| 1 # -*- coding: utf-8 -*- |
| 2 # copyright 2003-2011 LOGILAB S.A. (Paris, FRANCE), all rights reserved. |
| 3 # contact http://www.logilab.fr/ -- mailto:contact@logilab.fr |
| 4 # |
| 5 # This file is part of logilab-common. |
| 6 # |
| 7 # logilab-common is free software: you can redistribute it and/or modify it unde
r |
| 8 # the terms of the GNU Lesser General Public License as published by the Free |
| 9 # Software Foundation, either version 2.1 of the License, or (at your option) an
y |
| 10 # later version. |
| 11 # |
| 12 # logilab-common is distributed in the hope that it will be useful, but WITHOUT |
| 13 # ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS |
| 14 # FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more |
| 15 # details. |
| 16 # |
| 17 # You should have received a copy of the GNU Lesser General Public License along |
| 18 # with logilab-common. If not, see <http://www.gnu.org/licenses/>. |
| 19 """XML utilities. |
| 20 |
| 21 This module contains useful functions for parsing and using XML data. For the |
| 22 moment, there is only one function that can parse the data inside a processing |
| 23 instruction and return a Python dictionary. |
| 24 |
| 25 |
| 26 |
| 27 |
| 28 """ |
| 29 __docformat__ = "restructuredtext en" |
| 30 |
| 31 import re |
| 32 |
| 33 RE_DOUBLE_QUOTE = re.compile('([\w\-\.]+)="([^"]+)"') |
| 34 RE_SIMPLE_QUOTE = re.compile("([\w\-\.]+)='([^']+)'") |
| 35 |
| 36 def parse_pi_data(pi_data): |
| 37 """ |
| 38 Utility function that parses the data contained in an XML |
| 39 processing instruction and returns a dictionary of keywords and their |
| 40 associated values (most of the time, the processing instructions contain |
| 41 data like ``keyword="value"``, if a keyword is not associated to a value, |
| 42 for example ``keyword``, it will be associated to ``None``). |
| 43 |
| 44 :param pi_data: data contained in an XML processing instruction. |
| 45 :type pi_data: unicode |
| 46 |
| 47 :returns: Dictionary of the keywords (Unicode strings) associated to |
| 48 their values (Unicode strings) as they were defined in the |
| 49 data. |
| 50 :rtype: dict |
| 51 """ |
| 52 results = {} |
| 53 for elt in pi_data.split(): |
| 54 if RE_DOUBLE_QUOTE.match(elt): |
| 55 kwd, val = RE_DOUBLE_QUOTE.match(elt).groups() |
| 56 elif RE_SIMPLE_QUOTE.match(elt): |
| 57 kwd, val = RE_SIMPLE_QUOTE.match(elt).groups() |
| 58 else: |
| 59 kwd, val = elt, None |
| 60 results[kwd] = val |
| 61 return results |
OLD | NEW |