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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
#!/usr/bin/python3
# -*- coding: utf-8 -*-
# Copyright (C) 2006-2009 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):
#
import zipfile, time, sys, getopt, re
import xml.sax, xml.sax.saxutils
from odf.namespaces import TOOLSVERSION, OFFICENS, XLINKNS, DCNS, METANS
from io import BytesIO
OUTENCODING="utf-8"
whitespace = re.compile(r'\s+')
fields = {
'title': (DCNS,u'title'),
'description': (DCNS,u'description'),
'subject': (DCNS,u'subject'),
'creator': (DCNS,u'creator'),
'date': (DCNS,u'date'),
'language': (DCNS,u'language'),
'generator': (METANS,u'generator'),
'initial-creator': (METANS,u'initial-creator'),
'keyword': (METANS,u'keyword'),
'editing-duration': (METANS,u'editing-duration'),
'editing-cycles': (METANS,u'editing-cycles'),
'printed-by': (METANS,u'printed-by'),
'print-date': (METANS,u'print-date'),
'creation-date': (METANS,u'creation-date'),
'user-defined': (METANS,u'user-defined'),
#'template': (METANS,u'template'),
}
xfields = []
Xfields = []
addfields = {}
deletefields = {}
yieldfields = {}
showversion = None
def exitwithusage(exitcode=2):
""" print out usage information """
sys.stderr.write("Usage: %s [-cdlvV] [-xXaAI metafield]... [-o output] [inputfile]\n" % sys.argv[0])
sys.stderr.write("\tInputfile must be OpenDocument format\n")
sys.exit(exitcode)
def normalize(str):
"""
The normalize-space function returns the argument string with whitespace
normalized by stripping leading and trailing whitespace and replacing
sequences of whitespace characters by a single space.
"""
return whitespace.sub(' ', str).strip()
class MetaCollector:
"""
The MetaCollector is a pseudo file object, that can temporarily ignore write-calls
It could probably be replaced with a StringIO object.
"""
def __init__(self):
self._content = []
self.dowrite = True
def write(self, str):
if self.dowrite:
self._content.append(str)
def content(self):
return ''.join(self._content)
base = xml.sax.saxutils.XMLGenerator
class odfmetaparser(base):
""" Parse a meta.xml file with an event-driven parser and replace elements.
It would probably be a cleaner approach to use a DOM based parser and
then manipulate in memory.
Small issue: Reorders elements
"""
version = 'Unknown'
def __init__(self):
self._mimetype = ''
self.output = MetaCollector()
self._data = []
self.seenfields = {}
base.__init__(self, self.output, OUTENCODING)
def startElementNS(self, name, qname, attrs):
self._data = []
field = name
# I can't modify the template until the tool replaces elements at the same
# location and not at the end
# if name == (METANS,u'template'):
# self._data = [attrs.get((XLINKNS,u'title'),'')]
if showversion and name == (OFFICENS,u'document-meta'):
if showversion == '-V':
print ("version:%s" % attrs.get((OFFICENS,u'version'),'Unknown').decode('utf-8'))
else:
print ("%s" % attrs.get((OFFICENS,u'version'),'Unknown').decode('utf-8'))
if name == (METANS,u'user-defined'):
field = attrs.get((METANS,u'name'))
if field in deletefields:
self.output.dowrite = False
elif field in yieldfields:
del addfields[field]
base.startElementNS(self, name, qname, attrs)
else:
base.startElementNS(self, name, qname, attrs)
self._tag = field
def endElementNS(self, name, qname):
field = name
if name == (METANS,u'user-defined'):
field = self._tag
if name == (OFFICENS,u'meta'):
for k,v in addfields.items():
if len(v) > 0:
if type(k) == type(''):
base.startElementNS(self,(METANS,u'user-defined'),None,{(METANS,u'name'):k})
base.characters(self, v)
base.endElementNS(self, (METANS,u'user-defined'),None)
else:
base.startElementNS(self, k, None, {})
base.characters(self, v)
base.endElementNS(self, k, None)
if name in xfields:
print ("%s" % self.data())
if name in Xfields:
if isinstance(self._tag, tuple):
texttag = self._tag[1]
else:
texttag = self._tag
print ("%s:%s" % (texttag, self.data()))
if field in deletefields:
self.output.dowrite = True
else:
base.endElementNS(self, name, qname)
def characters(self, content):
base.characters(self, content)
self._data.append(content)
def meta(self):
return self.output.content()
def data(self):
if usenormalize:
return normalize(''.join(self._data))
else:
return ''.join(self._data)
now = time.localtime()[:6]
outputfile = "-"
writemeta = False # Do we change any meta data?
usenormalize = False
try:
opts, args = getopt.getopt(sys.argv[1:], "cdlvVI:A:a:o:x:X:")
except getopt.GetoptError:
exitwithusage()
if len(opts) == 0:
opts = [ ('-l','') ]
for o, a in opts:
if o in ('-a','-A','-I'):
writemeta = True
if a.find(":") >= 0:
k,v = a.split(":",1)
else:
k,v = (a, "")
if len(k) == 0:
exitwithusage()
k = fields.get(k,k)
addfields[k] = unicode(v,'utf-8')
if o == '-a':
yieldfields[k] = True
if o == '-I':
deletefields[k] = True
if o == '-d':
writemeta = True
addfields[(DCNS,u'date')] = "%04d-%02d-%02dT%02d:%02d:%02d" % now
deletefields[(DCNS,u'date')] = True
if o == '-c':
usenormalize = True
if o in ('-v', '-V'):
showversion = o
if o == '-l':
Xfields = fields.values()
if o == "-x":
xfields.append(fields.get(a,a))
if o == "-X":
Xfields.append(fields.get(a,a))
if o == "-o":
outputfile = a
# The specification says we should change the element to our own,
# and must not export the original identifier.
if writemeta:
addfields[(METANS,u'generator')] = TOOLSVERSION
deletefields[(METANS,u'generator')] = True
odfs = odfmetaparser()
parser = xml.sax.make_parser()
parser.setFeature(xml.sax.handler.feature_namespaces, 1)
parser.setContentHandler(odfs)
if len(args) == 0:
zin = zipfile.ZipFile(sys.stdin,'r')
else:
if not zipfile.is_zipfile(args[0]):
exitwithusage()
zin = zipfile.ZipFile(args[0], 'r')
try:
content = zin.read('meta.xml').decode('utf-8')
except:
sys.stderr.write("File has no meta data\n")
sys.exit(1)
parser.parse(BytesIO(content.encode('utf-8')))
if writemeta:
if outputfile == '-':
if sys.stdout.isatty():
sys.stderr.write("Won't write ODF file to terminal\n")
sys.exit(1)
zout = zipfile.ZipFile(sys.stdout,"w")
else:
zout = zipfile.ZipFile(outputfile,"w")
# Loop through the input zipfile and copy the content to the output until we
# get to the meta.xml. Then substitute.
for zinfo in zin.infolist():
if zinfo.filename == "meta.xml":
# Write meta
zi = zipfile.ZipInfo("meta.xml", now)
zi.compress_type = zipfile.ZIP_DEFLATED
zout.writestr(zi,odfs.meta() )
else:
payload = zin.read(zinfo.filename)
zout.writestr(zinfo, payload)
zout.close()
zin.close()
# Local Variables: ***
# mode: python ***
# End: ***
|