1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
|
# -*- coding: iso-8859-1 -*-
# Tools class
#
# LanguageTool -- A Rule-Based Style and Grammar Checker
# Copyright (C) 2002,2003,2004 Daniel Naber <daniel.naber@t-online.de>
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import sys
import re
class Tools:
def __init__(self):
return
def getXML(node, xmlstr=""):
"""Get the XML content of a node, but only elements and text."""
if node and node.nodeType == node.ELEMENT_NODE:
l = []
for child in node.childNodes:
l.append(Tools.getXML(child, xmlstr))
xmlstr = "<%s>%s</%s>" % (node.tagName, str.join('', l), node.tagName)
elif node and node.nodeType == node.TEXT_NODE:
xmlstr = "%s%s" % (xmlstr, node.data)
return xmlstr
getXML = staticmethod(getXML)
def countLinebreaks(s):
matches = re.findall("[\n\r]", s)
#print "#%s -> %s" % (s, len(matches))
return len(matches)
countLinebreaks = staticmethod(countLinebreaks)
def getLanguageName(shortName):
if shortName == 'en':
return 'English'
elif shortName == 'de':
return 'German'
elif shortName == 'hu':
return 'Hungarian'
return None
getLanguageName = staticmethod(getLanguageName)
|
