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
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
##############################################################################
#
# Copyright (c) 2002-2006 Nexedi SARL and Contributors. All Rights Reserved.
#
# WARNING: This program as such is intended to be used by professional
# programmers who take the whole responsability of assessing all potential
# consequences resulting from its eventual inadequacies and bugs
# End users who are looking for a ready-to-use solution with commercial
# garantees and support are strongly adviced to contract a Free Software
# Service Company
#
# This program is Free Software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
#
##############################################################################
import xmlrpclib
from xmlrpclib import Fault
import base64
import re
import zipfile
import cStringIO
import socket
from DateTime import DateTime
from AccessControl import ClassSecurityInfo
from OFS.Image import Pdata
from Products.CMFCore.utils import getToolByName
from Products.CMFCore.utils import _setCacheHeaders
from Products.ERP5Type import Permissions, PropertySheet, Constraint, Interface
from Products.ERP5Type.Message import Message
from Products.ERP5Type.Cache import CachingMethod
from Products.ERP5Type.XMLObject import XMLObject
from Products.ERP5.Document.File import File
from Products.ERP5.Document.Document import ConversionCacheMixin, ConversionError
from Products.CMFCore.utils import getToolByName
from Products.DCWorkflow.DCWorkflow import ValidationFailed
from zLOG import LOG
enc=base64.encodestring
dec=base64.decodestring
_MARKER = []
class OOoDocument(File, ConversionCacheMixin):
"""
A file document able to convert OOo compatible files to
any OOo supported format, to capture metadata and to
update metadata in OOo documents.
This class can be used:
- to create an OOo document database with powerful indexing (r/o)
and metadata handling (r/w) features (ex. change title in ERP5 ->
title is changed in OOo document)
- to massively convert MS Office documents to OOo format
- to easily keep snapshots (in PDF and/or OOo format) of OOo documents
generated from OOo templates
This class may be used in the future:
- to create editable OOo templates (ex. by adding tags in WYSIWYG mode
and using tags to make document dynamic - ask kevin for more info)
- to automatically sign / encrypt OOo documents based on user
- to automatically sign / encrypt PDF generated from OOo documents based on user
This class should not be used:
- to store files in formats not supported by OOo
- to stored pure images (use Image for that)
- as a general file conversion system (use portal_transforms for that)
TODO:
- better permissions
"""
# CMF Type Definition
meta_type = 'ERP5 OOo Document'
portal_type = 'OOo Document'
isPortalContent = 1
isRADContent = 1
searchable_property_list = ('asTextContent', 'title', 'description', 'id', 'reference',
'version', 'short_title',
'subject', 'source_reference', 'source_project_title',)
# Declarative security
security = ClassSecurityInfo()
security.declareObjectProtected(Permissions.AccessContentsInformation)
# Default Properties
property_sheets = ( PropertySheet.Base
, PropertySheet.XMLObject
, PropertySheet.Reference
, PropertySheet.CategoryCore
, PropertySheet.DublinCore
, PropertySheet.Version
, PropertySheet.Document
, PropertySheet.Snapshot
, PropertySheet.ExternalDocument
, PropertySheet.Url
, PropertySheet.Periodicity
, PropertySheet.Snapshot
)
# regular expressions for stripping xml from ODF documents
rx_strip = re.compile('<[^>]*?>', re.DOTALL|re.MULTILINE)
rx_compr = re.compile('\s+')
def _setFile(self, data, precondition=None):
File._setFile(self, data, precondition=precondition)
if self.hasBaseData():
# This is a hack - XXX - new accessor needed to delete properties
delattr(self, 'base_data')
security.declareProtected(Permissions.View, 'index_html')
def index_html(self, REQUEST, RESPONSE, format=None, **kw):
"""
Default renderer with conversion support. Format is
a string. The list of available formats can be obtained
by calling getTargetFormatItemList.
"""
# Accelerate rendering in Web mode
_setCacheHeaders(self, {'format' : format})
# Return the original file by default
if format is None:
return File.index_html(self, REQUEST, RESPONSE)
# Make sure file is converted to base format
if not self.hasBaseData():
self.convertToBaseFormat()
# Else try to convert the document and return it
result = self.convert(format=format)
mime = getToolByName(self, 'mimetypes_registry').lookupExtension('name.%s' % format) # XXX Sad we can not get the mimetype from the conversion cache
RESPONSE.setHeader('Content-Length', len(result))
RESPONSE.setHeader('Content-Type', mime)
RESPONSE.setHeader('Accept-Ranges', 'bytes')
return result
# Format conversion implementation
def _getServerCoordinate(self):
"""
Returns the oood conversion server coordinates
as defined in preferences.
"""
preference_tool = getToolByName(self, 'portal_preferences')
address = preference_tool.getPreferredOoodocServerAddress()
port = preference_tool.getPreferredOoodocServerPortNumber()
if not address or not port:
raise ConversionError('Can not proceed with conversion: '
'conversion server host and port is not defined in preferences')
return address, port
def _mkProxy(self):
"""
Create an XML-RPC proxy to access the conversion server.
"""
server_proxy = xmlrpclib.ServerProxy('http://%s:%d' % self._getServerCoordinate(),
allow_none=True)
return server_proxy
security.declareProtected(Permissions.AccessContentsInformation,'getTargetFormatList')
def getTargetFormatItemList(self):
"""
Returns a list of acceptable formats for conversion
in the form of tuples (for listfield in ERP5Form)
NOTE: it is the responsability of the conversion server
to provide an extensive list of conversion formats.
"""
def cached_getTargetFormatItemList(content_type):
server_proxy = self._mkProxy()
allowed = server_proxy.getAllowedTargets(content_type) # oood API needs naming convention update
return [(y, x) for x, y in allowed] # tuple order is reversed to be compatible with ERP5 Form
# Cache valid format list
cached_getTargetFormatItemList = CachingMethod(cached_getTargetFormatItemList,
id = "OOoDocument_getTargetFormatItemList",
cache_factory='erp5_ui_medium')
return cached_getTargetFormatItemList(self.getBaseContentType())
security.declareProtected(Permissions.AccessContentsInformation, 'getTargetFormatTitleList')
def getTargetFormatTitleList(self):
"""
Returns a list of acceptable formats for conversion
"""
return map(lambda x: x[0], self.getTargetFormatItemList())
security.declareProtected(Permissions.AccessContentsInformation, 'getTargetFormatList')
def getTargetFormatList(self):
"""
Returns a list of acceptable formats for conversion
"""
return map(lambda x: x[1], self.getTargetFormatItemList())
security.declareProtected(Permissions.ModifyPortalContent,'isTargetFormatAllowed')
def isTargetFormatAllowed(self, format):
"""
Checks if the current document can be converted
into the specified target format.
"""
return format in self.getTargetFormatList()
security.declarePrivate('_convert')
def _convert(self, format):
"""
Communicates with server to convert a file
"""
if format == 'text-content':
# Extract text from the ODF file
cs = cStringIO.StringIO()
cs.write(self._unpackData(self.oo_data))
z = zipfile.ZipFile(cs)
s = z.read('content.xml')
s = self.rx_strip.sub(" ", s) # strip xml
s = self.rx_compr.sub(" ", s) # compress multiple spaces
cs.close()
z.close()
return 'text/text', s
server_proxy = self._mkProxy()
kw = server_proxy.run_generate(self.getId(),
enc(self._unpackData(self.getBaseData())),
None, format)
return kw['mime'], Pdata(dec(kw['data']))
# Conversion API
security.declareProtected(Permissions.View, 'convert')
def convert(self, format, **kw):
"""
Implementation of thGet file in a given format.
Runs makeFile to make sure we have the requested version cached,
then returns from cache.
"""
# Make sure we can support html and pdf by default
is_html = 0
if format == 'pdf':
format_list = [x for x in self.getTargetFormatList() if x.endswith('pdf')]
format = format_list[0]
elif format == 'html':
format_list = [x for x in self.getTargetFormatList() if x.startswith('html')]
format = format_list[0]
is_html = 1
# Raise an error if the format is not supported
if not self.isTargetFormatAllowed(format):
raise ConversionError, 'Target format %s is not supported' % format
# Check if we have already a base conversion
if not self.hasBaseData():
self.convertToBaseFormat()
# Return converted file
if not self.hasConversion(format=format):
# Do real conversion
mime, data = self._convert(format)
if is_html:
# Extra processing required since
# we receive a zip file
cs = cStringIO.StringIO()
cs.write(self._unpackData(data))
z = zipfile.ZipFile(cs)
for f in z.infolist():
fn = f.filename
if fn.endswith('html'):
data = z.read(fn)
break
mime = 'text/html'
self.populateContent(zip_file=z)
z.close()
cs.close()
self.setConversion(data, mime, format=format)
return self.getConversion(format=format)
security.declareProtected(Permissions.View, 'asTextContent')
def asTextContent(self):
"""
Extract plain text from ooo docs by stripping the XML file.
This is the simplest way, the most universal and it is compatible
will all formats.
"""
return self.convert(format='text-content')
security.declareProtected(Permissions.ModifyPortalContent, 'populateContent')
def populateContent(self, zip_file=None):
"""
Extract content from the ODF zip file and populate the document.
Optional parameter zip_file prevents from converting content twice.
"""
if zip_file is None:
format_list = [x for x in self.getTargetFormatList() if x.startswith('html')]
format = format_list[0]
mime, data = self._convert(format)
archive_file = cStringIO.StringIO()
archive_file.write(self._unpackData(data))
zip_file = zipfile.ZipFile(archive_file)
must_close = 1
else:
must_close = 0
for f in zip_file.infolist():
file_name = f.filename
if not file_name.endswith('html'):
document = self.get(file_name, None)
if document is not None:
self.manage_delObjects([file_name])
self.portal_contributions.newContent(id=file_name, container=self,
file_name=file_name,
data=zip_file.read(file_name))
if must_close:
zip_file.close()
archive_file.close()
# Base format implementation
security.declarePrivate('_convertToBaseFormat')
def _convertToBaseFormat(self):
"""
Converts the original document into ODF
by invoking the conversion server. Store the result
on the object. Update metadata information.
"""
# LOG('in _convertToBaseFormat', 0, self.getRelativeUrl())
server_proxy = self._mkProxy()
kw = server_proxy.run_convert(self.getSourceReference() or self.getId(),
enc(self._unpackData(self.getData())))
self._setBaseData(dec(kw['data']))
metadata = kw['meta']
self._base_metadata = metadata
if metadata.get('MIMEType', None):
self._setBaseContentType(metadata['MIMEType'])
security.declareProtected(Permissions.AccessContentsInformation, 'getContentInformation')
def getContentInformation(self):
"""
Returns the metadata extracted by the conversion
server.
"""
# LOG('in getContentInformation', 0, self.getRelativeUrl())
return self._base_metadata
security.declareProtected(Permissions.ModifyPortalContent, 'updateBaseMetadata')
def updateBaseMetadata(self, **kw):
"""
Updates metadata information in the converted OOo document
based on the values provided by the user. This is implemented
through the invocation of the conversion server.
"""
server_proxy = self._mkProxy()
kw = server_proxy.run_setmetadata(self.getId(),
enc(self._unpackData(self.getBaseData())),
kw)
self._setBaseData(dec(kw['data']))