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
|
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Copyright (C) 2006-2007 Søren Roug, European Environment Agency
#
# 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
#
# Contributor(s):
#
# This script is to be embedded in opendocument.py later
# The purpose is to read an ODT/ODP/ODS file and create the datastructure
# in memory. The user should then be able to make operations and then save
# the structure again.
import zipfile
from xml.sax import make_parser,handler
from xml.sax.xmlreader import InputSource
import xml.sax.saxutils
import sys
from ocrfeeder.odf.opendocument import OpenDocument
from ocrfeeder.odf import element
from ocrfeeder.odf.namespaces import STYLENS, OFFICENS
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
#
# Parse the XML files
#
class ODFParser(handler.ContentHandler):
""" Extract headings from content.xml of an ODT file """
def __init__(self, document):
self.doc = document
self.data = []
self.level = 0
self.parse = False
def characters(self, data):
if self.parse == False:
return
self.data.append(data)
def startElementNS(self, tag, qname, attrs):
if tag in ((OFFICENS, 'body'), (OFFICENS, 'styles')):
self.parse = True
if self.parse == False:
return
self.level = self.level + 1
# Add any accumulated text content
content = ''.join(self.data).strip()
if len(content) > 0:
self.parent.addText(content)
self.data = []
# Create the element
attrdict = {}
for (att,value) in attrs.items():
attrdict[att] = value
try:
e = element.Element(qname = tag, qattributes=attrdict)
self.curr = e
except AttributeError, v:
print "Error: %s" % v
if tag == (OFFICENS,'styles'):
self.doc.styles = e
elif tag == (OFFICENS, 'body'):
self.doc.body = e
else:
self.parent.addElement(e)
self.parent = e
def endElementNS(self, tag, qname):
if tag in ((OFFICENS, 'body'), (OFFICENS, 'styles')):
self.parse = False
if self.parse == False:
return
self.level = self.level - 1
str = ''.join(self.data)
self.data = []
self.parent = self.curr.parentNode
def _getxmlpart(odffile, xmlfile):
""" Get the content out of the ODT file"""
z = zipfile.ZipFile(odffile)
content = z.read(xmlfile)
z.close()
return content
def load(odtfile):
mimetype = _getxmlpart(odtfile,'mimetype')
d = OpenDocument(mimetype)
for xmlfile in ('content.xml',):
xmlpart = _getxmlpart(odtfile, xmlfile)
parser = make_parser()
parser.setFeature(handler.feature_namespaces, 1)
parser.setContentHandler(ODFParser(d))
parser.setErrorHandler(handler.ErrorHandler())
inpsrc = InputSource()
inpsrc.setByteStream(StringIO(xmlpart))
parser.parse(inpsrc)
return d
|
