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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Copyright (C) 2006 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 odf.xml import make_parser
from xml.sax import handler
from xml.sax.xmlreader import InputSource
import xml.sax.saxutils
import sys
from odf.namespaces import *
RELAXNS=u"http://relaxng.org/ns/structure/1.0"
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
currdef = None
definitions = {}
ignore = 0
def __init__(self):
self.data = []
self.level = 0
def text(self):
return ''.join(self.data).strip()
def characters(self, data):
self.data.append(data)
def startElementNS(self, tag, qname, attrs):
if self.ignore == 1:
return
#print "START ",tag
if tag == (RELAXNS, 'define'):
self.currdef = {}
self.currdef['name'] = attrs.get( (None, 'name'))
self.currdef['type'] = None
self.currdef['datatypeLibrary'] = None
self.currdef['elements'] = []
elif tag in ((RELAXNS, 'attribute'), (RELAXNS, 'start')):
self.ignore = 1
elif tag == (RELAXNS, 'name'):
self.currdef['ns'] = attrs.get( (None, 'ns'))
self.data = []
elif tag == (RELAXNS, 'data'):
self.currdef['type'] = attrs.get( (None, 'type'))
self.currdef['datatypeLibrary'] = attrs.get( (None, 'datatypeLibrary'))
elif tag == (RELAXNS, 'text'):
self.currdef['type'] = "text"
def endElementNS(self, tag, qname):
if tag in ((RELAXNS, 'attribute'), (RELAXNS, 'start')):
self.ignore = 0
return
if self.ignore == 1:
return
#print "END ",tag
if tag == (RELAXNS, 'define'):
if len(self.currdef['elements']):
self.definitions[self.currdef['name']] = self.currdef
elif tag == (RELAXNS, 'name'):
self.currdef['elements'].append(self.text())
elif tag == (RELAXNS, 'anyName'):
self.currdef['elements'].append("__ANYNAME__")
self.data = []
if __name__ == "__main__":
parser = make_parser()
parser.setFeature(handler.feature_namespaces, 1)
p = S22RelaxParser()
parser.setContentHandler(p)
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)
defs = p.definitions
keys= defs.keys()
keys.sort()
print "allows_text = ("
for key in keys:
val = defs[key]
if val.get('type') is None:
continue
ns = val.get('ns','UNKNOWN')
if ns == DBNS: continue
for elmname in sorted(val['elements']):
if elmname == u'__ANYNAME__':
continue
print "\t(%sNS,u'%s')," % (nsdict.get(ns,'unknown').upper(), elmname)
print ")"
|
