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
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
|
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Copyright (C) 2008 Søren Roug, European Environment Agency
#
# This is free software. You may redistribute it under the terms
# of the Apache license and the GNU General Public License Version
# 2 or at your option any later version.
#
# This program 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public
# License along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
#
# Contributor(s):
#
from xml.sax import make_parser,handler
from xml.sax.xmlreader import InputSource
import xml.sax.saxutils
import sys
RELAXNS=u"http://relaxng.org/ns/structure/1.0"
from odf.namespaces import *
class Node:
ns = None
name = None
class Element(Node):
" Element "
def __init__(self):
self.attrs = {}
class Attribute(Node):
" Attribute "
#
#
class S22RelaxParser(handler.ContentHandler):
""" Extract headings from content.xml of an ODT file """
optional = 0
currattr = None
currelem = None
currnode = None
def __init__(self, elements):
self.data = []
self.level = 0
self.elements = elements
def text(self):
return ''.join(self.data)
def characters(self, data):
self.data.append(data)
def startElementNS(self, tag, qname, attrs):
if tag == (RELAXNS, 'element'):
self.currelem = self.currnode = Element()
elif tag == (RELAXNS, 'attribute'):
self.currattr = self.currnode = Attribute()
elif tag == (RELAXNS, 'name'):
self.currnode.ns = attrs.get((None,'ns'),'')
self.data = []
elif tag == (RELAXNS, 'choice') and self.currattr is None:
self.optional = self.optional + 1
def endElementNS(self, tag, qname):
if tag == (RELAXNS, 'element'):
self.elements[(self.currelem.ns, self.currelem.name)] = self.currelem
self.currelem = None
elif tag == (RELAXNS, 'attribute'):
if self.optional == 0:
self.currelem.attrs[self.currnode.name] = self.currnode
self.currattr = self.currnode = None
elif tag == (RELAXNS, 'name'):
self.currnode.name = self.text()
elif tag == (RELAXNS, 'anyName'):
self.currnode.name = "__ANYNAME__"
elif tag == (RELAXNS, 'choice') and self.currattr is None:
self.optional = self.optional - 1
self.data = []
if __name__ == "__main__":
elements = {}
parser = make_parser()
parser.setFeature(handler.feature_namespaces, 1)
parser.setContentHandler(S22RelaxParser(elements))
parser.setErrorHandler(handler.ErrorHandler())
for relaxfile in ["simple-manifest-7-22.rng","simple-schema-7-22.rng"]:
content = file(relaxfile)
inpsrc = InputSource()
inpsrc.setByteStream(content)
parser.parse(inpsrc)
slist = elements.keys()
slist.sort()
print "required_attributes = {"
for s in slist:
e = elements[s]
if e.ns == DBNS: continue
if len(e.attrs) > 0:
print "# required_attributes"
print "\t(%sNS,u'%s'):" % (nsdict.get(e.ns,'unknown').upper(), e.name),
print "("
for a in e.attrs.values():
print "\t\t(%sNS,u'%s')," % (nsdict.get(a.ns,'unknown').upper(), a.name)
print "\t),"
print "}"
|
