testIngestion.py 54.3 KB
Newer Older
1 2
##############################################################################
#
3 4 5
# Copyright (c) 2007 Nexedi SA and Contributors. All Rights Reserved.
#                    Bartek Gorny <bg@erp5.pl>
#                    Jean-Paul Smets <jp@nexedi.com>
6
#                    Ivan Tyagov <ivan@nexedi.com>
7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
#
# 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.
#
##############################################################################

Jérome Perrin's avatar
Jérome Perrin committed
31 32
import unittest
import os, cStringIO, zipfile
33
from xml.dom.minidom import parseString
34 35
from Testing import ZopeTestCase
from DateTime import DateTime
36
from AccessControl.SecurityManagement import newSecurityManager
37 38 39
from Products.ERP5Type.Utils import convertToUpperCase
from Products.ERP5Type.tests.ERP5TypeTestCase import ERP5TypeTestCase
from Products.ERP5Type.tests.Sequence import SequenceList
40
from Products.ERP5Type.tests.utils import FileUpload
41
from Products.ERP5OOo.Document.OOoDocument import ConversionError
42
from Products.ERP5.Document.File import _unpackData
43
from zLOG import LOG, INFO, ERROR
44

45 46
# Define the conversion server host
conversion_server_host = ('127.0.0.1', 8008)
47

48
# test files' home
49
TEST_FILES_HOME = os.path.join(os.path.dirname(__file__), 'test_document')
50 51
FILE_NAME_REGULAR_EXPRESSION = "(?P<reference>[A-Z&é@{]{3,7})-(?P<language>[a-z]{2})-(?P<version>[0-9]{3})"
REFERENCE_REGULAR_EXPRESSION = "(?P<reference>[A-Z&é@{]{3,7})(-(?P<language>[a-z]{2}))?(-(?P<version>[0-9]{3}))?"
52

53 54 55 56 57 58
def printAndLog(msg):
  """
  A utility function to print a message
  to the standard output and to the LOG
  at the same time
  """
59 60 61 62
  msg = str(msg)
  ZopeTestCase._print('\n ' + msg)
  LOG('Testing... ', 0, msg)

63 64

def makeFilePath(name):
65
  return os.path.join(TEST_FILES_HOME, name)
66 67

def makeFileUpload(name):
68
  path = makeFilePath(name)
69
  return FileUpload(path, name)
70 71 72 73 74 75 76

class TestIngestion(ERP5TypeTestCase):
  """
    ERP5 Document Management System - test file ingestion mechanism
  """

  # pseudo constants
77
  RUN_ALL_TEST = 1
78 79 80 81 82 83 84 85 86 87
  QUIET = 0

  ##################################
  ##  ZopeTestCase Skeleton
  ##################################

  def getTitle(self):
    """
      Return the title of the current test set.
    """
88
    return "ERP5 DMS - Ingestion"
89 90 91 92 93

  def getBusinessTemplateList(self):
    """
      Return the list of required business templates.
    """
94 95 96
    return ('erp5_base',
            'erp5_ingestion', 'erp5_ingestion_mysql_innodb_catalog',
            'erp5_web', 'erp5_crm',
97
            'erp5_dms_mysql_innodb_catalog', 'erp5_dms')
98 99 100 101 102 103

  def afterSetUp(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Initialize the ERP5 site.
    """
    self.login()
104 105
    self.datetime = DateTime()
    self.portal = self.getPortal()
106
    self.portal_categories = self.getCategoryTool()
107 108 109
    self.portal_catalog = self.getCatalogTool()
    self.createDefaultCategoryList()
    self.setSystemPreference()
110
    self.setSimulatedNotificationScript()
111
    self.setTools()
112

113 114 115
  def beforeTearDown(self):
    self.portal.portal_caches.clearAllCache()

116
  def setSystemPreference(self):
117
    default_pref = self.portal.portal_preferences.default_site_preference
118 119
    default_pref.setPreferredOoodocServerAddress(conversion_server_host[0])
    default_pref.setPreferredOoodocServerPortNumber(conversion_server_host[1])
120 121
    default_pref.setPreferredDocumentFileNameRegularExpression(FILE_NAME_REGULAR_EXPRESSION)
    default_pref.setPreferredDocumentReferenceRegularExpression(REFERENCE_REGULAR_EXPRESSION)
122 123
    default_pref.enable()

124 125 126 127 128 129 130 131 132 133 134 135
  def setSimulatedNotificationScript(self, sequence=None, sequence_list=None, **kw):
    """
      Create simulated (empty) email notification script
    """
    context = self.portal.portal_skins.custom
    script_id = 'Document_notifyByEmail'
    if not hasattr(context, script_id):
      factory = context.manage_addProduct['PythonScripts'].manage_addPythonScript
      factory(id=script_id)
    script = getattr(context, script_id)
    script.ZPythonScript_edit('email_to, event, doc, **kw', 'return')

136 137 138 139 140 141 142
  def setTools(self):
    # XXX FIX ME
    # XXX We should use business template to install these tools.(Yusei)
    if getattr(self.portal, 'mimetypes_registry', None) is None:
      self.portal.manage_addProduct['MimetypesRegistry'].manage_addTool(type='MimeTypes Registry')
    if getattr(self.portal, 'portal_transforms', None) is None:
      self.portal.manage_addProduct['PortalTransforms'].manage_addTool(type='Portal Transforms')
143 144 145 146 147 148 149 150 151

  ##################################
  ##  Useful methods
  ##################################

  def login(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Create a new manager user and login.
    """
152
    user_name = 'dms_user'
153
    user_folder = self.portal.acl_users
154 155 156 157
    user_folder._doAddUser(user_name, '', ['Manager', 'Owner', 'Assignor'], [])
    user = user_folder.getUserById(user_name).__of__(user_folder)
    newSecurityManager(None, user)

158
  def createDefaultCategoryList(self):
159
    """
160 161 162 163 164 165
      Create some categories for testing. DMS security
      is based on group, site, function, publication_section
      and projects.

      NOTE (XXX): some parts of this method could be either
      moved to Category Tool or to ERP5 Test Case.
166 167 168 169 170 171
    """
    self.category_list = [
                         # Role categories
                          {'path' : 'role/internal'
                           ,'title': 'Internal'
                           }
172 173 174 175 176 177 178 179 180
                          ,{'path' : 'function/musician/wind/saxophone'
                           ,'title': 'Saxophone'
                           }
                          ,{'path' : 'group/medium'
                           ,'title': 'Medium'
                           }
                          ,{'path' : 'site/arctic/spitsbergen'
                           ,'title': 'Spitsbergen'
                           }
181 182 183
                          ,{'path' : 'group/anybody'
                           ,'title': 'Anybody'
                           }
184 185 186 187 188 189
                          ,{'path' : 'publication_section/cop'
                           ,'title': 'COPs'
                           }
                          ,{'path' : 'publication_section/cop/one'
                           ,'title': 'COP one'
                           }
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
                         ]

    # Create categories
    # Note : this code was taken from the CategoryTool_importCategoryFile python
    #        script (packaged in erp5_core).
    for category in self.category_list:
      keys = category.keys()
      if 'path' in keys:
        base_path_obj = self.portal_categories
        is_base_category = True
        for category_id in category['path'].split('/'):
          # The current category is not existing
          if category_id not in base_path_obj.contentIds():
            # Create the category
            if is_base_category:
              category_type = 'Base Category'
            else:
              category_type = 'Category'
            base_path_obj.newContent( portal_type       = category_type
                                    , id                = category_id
                                    , immediate_reindex = 1
                                    )
          base_path_obj = base_path_obj[category_id]
          is_base_category = False
        new_category = base_path_obj

        # Set the category properties
        for key in keys:
          if key != 'path':
            method_id = "set" + convertToUpperCase(key)
            value = category[key]
            if value not in ('', None):
              if hasattr(new_category, method_id):
                method = getattr(new_category, method_id)
                method(value.encode('UTF-8'))
225 226
    get_transaction().commit()
    self.tic()
227 228 229 230 231 232

  def getCategoryList(self, base_category=None):
    """
      Get a list of categories with same base categories.
    """
    categories = []
233
    if base_category is not None:
234 235 236 237 238
      for category in self.category_list:
        if category["path"].split('/')[0] == base_category:
          categories.append(category)
    return categories

239
  def getDocument(self, id):
240 241 242 243 244 245
    """
      Returns a document with given ID in the
      document module.
    """
    document_module = self.portal.document_module
    return getattr(document_module, id)
246

247
  def checkIsObjectCatalogged(self, portal_type, **kw):
248
    """
249 250 251 252 253
      Make sure that a document with given portal type
      and kw properties is already present in the catalog.

      Typical use of this method consists in providing
      an id or reference.
254
    """
255
    res = self.portal_catalog(portal_type=portal_type, **kw.copy())
256
    self.assertEquals(len(res), 1)
257 258
    for key, value in kw.items():
      self.assertEquals(res[0].getProperty(key), value)
259

260
  def newEmptyCataloggedDocument(self, portal_type, id):
261
    """
262 263 264 265 266 267
      Create an empty document of given portal type
      and given ID. 

      Documents are immediately catalogged and verified
      both form catalog point of view and from their
      presence in the document module.
268
    """
269 270 271 272 273 274 275 276 277 278 279
    document_module = self.portal.getDefaultModule(portal_type)
    document = getattr(document_module, id, None)
    if document is not None:
      document_module.manage_delObjects([id,])
    document = document_module.newContent(portal_type=portal_type, id=id)
    document.reindexObject()
    get_transaction().commit()
    self.tic()
    self.checkIsObjectCatalogged(portal_type, id=id, parent_uid=document_module.getUid())
    self.assert_(hasattr(document_module, id))
    return document
280

281
  def ingestFormatList(self, document_id, format_list, portal_type=None):
282
    """
283 284 285 286 287 288 289 290 291
      Upload in document document_id all test files which match
      any of the formats in format_list.

      portal_type can be specified to force the use of
      the default module for a given portal type instead
      of the document module.

      For every file, this checks is the word "magic"
      is present in both SearchableText and asText.
292 293
    """
    if portal_type is None:
294
      document_module = self.portal.document_module
295
    else:
296 297 298
      document_module = self.portal.getDefaultModule(portal_type)
    context = getattr(document_module, document_id)
    for revision, format in enumerate(format_list):
299
      filename = 'TEST-en-002.' + format
300
      printAndLog('Ingesting file: ' + filename)
301 302
      f = makeFileUpload(filename)
      context.edit(file=f)
303
      context.convertToBaseFormat()
304 305 306
      context.reindexObject()
      get_transaction().commit()
      self.tic()
307
      self.failUnless(context.hasFile())
308
      if context.getPortalType() in ('Image', 'File', 'PDF'):
309
        # File and images do not support conversion to text in DMS
310
        # PDF has not implemented _convertToBaseFormat() so can not be converted
311 312 313 314
        self.assertEquals(context.getExternalProcessingState(), 'uploaded')
      else:
        self.assertEquals(context.getExternalProcessingState(), 'converted') # this is how we know if it was ok or not
        self.assert_('magic' in context.SearchableText())
315
        self.assert_('magic' in str(context.asText()))
316

317
  def checkDocumentExportList(self, document_id, format, asserted_target_list):
318
    """
319 320 321
      Upload document ID document_id with
      a test file of given format and assert that the document
      can be converted to any of the formats in asserted_target_list
322
    """
323
    context = self.getDocument(document_id)
324 325 326
    filename = 'TEST-en-002.' + format
    f = makeFileUpload(filename)
    context.edit(file=f)
327
    context.convertToBaseFormat()
328 329 330
    context.reindexObject()
    get_transaction().commit()
    self.tic()
331 332
    # We call clear cache to be sure that the target list is updated
    self.getPortal().portal_caches.clearCache()
333 334
    target_list = context.getTargetFormatList()
    for target in asserted_target_list:
335 336
      self.assert_(target in target_list)

Bartek Górny's avatar
Bartek Górny committed
337
  def contributeFileList(self, with_portal_type=False):
338
    """
339 340 341
      Tries to a create new content through portal_contributions
      for every possible file type. If with_portal_type is set
      to true, portal_type is specified when calling newContent
342 343
      on portal_contributions.
      http://framework.openoffice.org/documentation/mimetypes/mimetypes.html
344
    """
345 346 347 348
    created_documents = []
    extension_to_type = (('ppt', 'Presentation')
                        ,('doc', 'Text')
                        ,('sdc', 'Spreadsheet')
349
                        ,('sxc', 'Spreadsheet')
350 351 352 353
                        ,('pdf', 'PDF')
                        ,('jpg', 'Image')
                        ,('py', 'File')
                        )
354 355
    counter = 1
    old_portal_type = ''
356 357
    for extension, portal_type in extension_to_type:
      filename = 'TEST-en-002.' + extension
358
      printAndLog(filename)
359
      file = makeFileUpload(filename)
360 361 362 363 364 365 366
      # if we change portal type we must change version because 
      # mergeRevision would fail
      if portal_type != old_portal_type:
        counter += 1
        old_portal_type = portal_type
      file.filename = 'TEST-en-00%d.%s' % (counter, extension)
      printAndLog(file.filename)
367
      if with_portal_type:
368
        ob = self.portal.portal_contributions.newContent(portal_type=portal_type, file=file)
369 370
      else:
        ob = self.portal.portal_contributions.newContent(file=file)
371
      # reindex
372 373 374 375 376 377 378 379 380
      ob.immediateReindexObject()
      created_documents.append(ob)
    get_transaction().commit()
    self.tic()
    # inspect created objects
    count = 0
    for extension, portal_type in extension_to_type:
      ob = created_documents[count]
      count+=1
381
      self.assertEquals(ob.getPortalType(), portal_type)
382
      self.assertEquals(ob.getReference(), 'TEST')
383 384
      if ob.getPortalType() in ('Image', 'File', 'PDF'):
        # Image, File and PDF are not converted to a base format
385 386
        self.assertEquals(ob.getExternalProcessingState(), 'uploaded')
      else:
387 388 389
        # We check if conversion has succeeded by looking
        # at the external_processing workflow
        self.assertEquals(ob.getExternalProcessingState(), 'converted')
390
        self.assert_('magic' in ob.SearchableText())
391 392 393 394 395 396

  def newPythonScript(self, object_id, script_id, argument_list, code):
    """
      Creates a new python script with given argument_list
      and source code.
    """
397 398 399 400
    context = self.getDocument(object_id)
    factory = context.manage_addProduct['PythonScripts'].manage_addPythonScript
    factory(id=script_id)
    script = getattr(context, script_id)
401
    script.ZPythonScript_edit(argument_list, code)
402

403
  def setDiscoveryOrder(self, order, id='one'):
404
    """
405 406
      Creates a script to define the metadata discovery order
      for Text documents.
407 408
    """
    script_code = "return %s" % str(order)
409
    self.newPythonScript(id, 'Text_getPreferredDocumentMetadataDiscoveryOrderList', '', script_code)
410
    
411 412 413 414 415 416
  def discoverMetadata(self, document_id='one'):
    """
      Sets input parameters and on the document ID document_id
      and discover metadata. For reindexing
    """
    context = self.getDocument(document_id)
417 418 419 420 421
    # simulate user input
    context._backup_input = dict(reference='INPUT', 
                                 language='in',
                                 version='004', 
                                 short_title='from_input',
422
                                 contributor='person_module/james')
423 424
    # pass to discovery file_name and user_login
    context.discoverMetadata(context.getSourceReference(), 'john_doe') 
425 426 427
    context.reindexObject()
    get_transaction().commit()
    self.tic()
428

429 430 431 432 433 434 435
  def checkMetadataOrder(self, expected_metadata, document_id='one'):
    """
    Asserts that metadata of document ID document_id
    is the same as expected_metadata
    """
    context = self.getDocument(document_id)
    for k, v in expected_metadata.items():
436
      self.assertEquals(context.getProperty(k), v)
437

438 439 440 441 442 443 444 445 446
  def receiveEmail(self, data,
                   portal_type='Document Ingestion Message',
                   container_path='document_ingestion_module',
                   file_name='email.emx'):
    return self.portal.portal_contributions.newContent(data=data,
                                                       portal_type=portal_type,
                                                       container_path=container_path,
                                                       file_name=file_name)

447 448 449
  ##################################
  ##  Basic steps
  ##################################
450 451 452
 
  def stepTic(self, sequence=None, sequence_list=None, **kw):
    self.tic()
453 454 455

  def stepCreatePerson(self, sequence=None, sequence_list=None, **kw):
    """
456
      Create a person with ID "john" if it does not exists already
457 458
    """
    portal_type = 'Person'
459
    person_id = 'john'
460
    reference = 'john_doe'
461
    person_module = self.portal.person_module
462 463 464 465 466 467 468 469
    if getattr(person_module, person_id, None) is not None:
      return
    person = person_module.newContent(portal_type='Person',
                                      id=person_id,
                                      reference=reference,
                                      first_name='John',
                                      last_name='Doe'
                                      )
470
    person.setDefaultEmailText('john@doe.com')
471 472 473
    person.reindexObject()
    get_transaction().commit()
    self.tic()
474 475 476

  def stepCreateTextDocument(self, sequence=None, sequence_list=None, **kw):
    """
477 478
      Create an empty Text document with ID 'one'
      This document will be used in most tests.
479
    """
480
    self.newEmptyCataloggedDocument('Text', 'one')
481

482 483
  def stepCreateSpreadsheetDocument(self, sequence=None, sequence_list=None, **kw):
    """
484 485
      Create an empty Spreadsheet document with ID 'two'
      This document will be used in most tests.
486
    """
487
    self.newEmptyCataloggedDocument('Spreadsheet', 'two')
488 489 490

  def stepCreatePresentationDocument(self, sequence=None, sequence_list=None, **kw):
    """
491 492
      Create an empty Presentation document with ID 'three'
      This document will be used in most tests.
493
    """
494
    self.newEmptyCataloggedDocument('Presentation', 'three')
495 496 497

  def stepCreateDrawingDocument(self, sequence=None, sequence_list=None, **kw):
    """
498 499
      Create an empty Drawing document with ID 'four'
      This document will be used in most tests.
500
    """
501
    self.newEmptyCataloggedDocument('Drawing', 'four')
502

503 504
  def stepCreatePDFDocument(self, sequence=None, sequence_list=None, **kw):
    """
505 506
      Create an empty PDF document with ID 'five'
      This document will be used in most tests.
507
    """
508
    self.newEmptyCataloggedDocument('PDF', 'five')
509 510 511

  def stepCreateImageDocument(self, sequence=None, sequence_list=None, **kw):
    """
512 513
      Create an empty Image document with ID 'six'
      This document will be used in most tests.
514
    """
515
    self.newEmptyCataloggedDocument('Image', 'six')
516

517 518
  def stepCheckEmptyState(self, sequence=None, sequence_list=None, **kw):
    """
519 520
      Check if the document is in "empty" processing state
      (ie. no file upload has been done yet)
521
    """
522
    context = self.getDocument('one')
523 524 525 526
    return self.assertEquals(context.getExternalProcessingState(), 'empty')

  def stepCheckUploadedState(self, sequence=None, sequence_list=None, **kw):
    """
527 528
      Check if the document is in "uploaded" processing state
      (ie. a file upload has been done)
529
    """
530
    context = self.getDocument('one')
531 532
    return self.assertEquals(context.getExternalProcessingState(), 'uploaded')

533 534 535 536 537 538 539 540
  def stepCheckConvertingState(self, sequence=None, sequence_list=None, **kw):
    """
      Check if the document is in "converting" processing state
      (ie. a file upload has been done and the document is converting)
    """
    context = self.getDocument('one')
    return self.assertEquals(context.getExternalProcessingState(), 'converting')

541 542
  def stepCheckConvertedState(self, sequence=None, sequence_list=None, **kw):
    """
543
      Check if the document is in "converted" processing state
544
      (ie. a file conversion has been done and the document has
545
      been converted)
546
    """
547
    context = self.getDocument('one')
548 549
    return self.assertEquals(context.getExternalProcessingState(), 'converted')

550 551 552 553 554
  def stepStraightUpload(self, sequence=None, sequence_list=None, **kw):
    """
      Upload a file directly from the form
      check if it has the data and source_reference
    """
555
    filename = 'TEST-en-002.doc'
556 557 558
    document = self.getDocument('one')
    # Revision is 0 before upload (revisions are strings)
    self.assertEquals(document.getRevision(), '0')
559
    f = makeFileUpload(filename)
560
    document.edit(file=f)
561 562
    # set source
    document.setSourceReference(filename)
563
    self.assert_(document.hasFile())
564 565
    # source_reference set to file name ?
    self.assertEquals(document.getSourceReference(), filename) 
566 567 568 569
    # Revision is 1 after upload (revisions are strings)
    self.assertEquals(document.getRevision(), '1')
    document.reindexObject()
    get_transaction().commit()
570

571
  def stepUploadFromViewForm(self, sequence=None, sequence_list=None, **kw):
572
    """
573
      Upload a file from view form and make sure this increases the revision
574
    """
575
    context = self.getDocument('one')
576
    f = makeFileUpload('TEST-en-002.doc')
577
    revision = context.getRevision()
578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607
    context.edit(file=f)
    self.assertEquals(context.getRevision(), str(int(revision) + 1))
    context.reindexObject()
    get_transaction().commit()

  def stepUploadTextFromContributionTool(self, sequence=None, sequence_list=None, **kw):
    """
      Upload a file from contribution.
    """
    f = makeFileUpload('TEST-en-002.doc')
    self.portal.portal_contributions.newContent(id='one', file=f)
    get_transaction().commit()

  def stepReuploadTextFromContributionTool(self, sequence=None, sequence_list=None, **kw):
    """
      Upload a file from contribution form and make sure this update existing
      document and don't make a new document.
    """
    context = self.getDocument('one')
    revision = context.getRevision()
    number_of_document = len(self.portal.document_module.objectIds())
    self.assert_('This document is modified.' not in context.asText())

    f = makeFileUpload('TEST-en-002-modified.doc')
    f.filename = 'TEST-en-002.doc'

    self.portal.portal_contributions.newContent(file=f)
    get_transaction().commit()
    self.tic()
    get_transaction().commit()
608
    self.assertEquals(context.getRevision(), str(int(revision) + 1))
609 610 611 612
    self.assert_('This document is modified.' in context.asText())
    self.assertEquals(len(self.portal.document_module.objectIds()),
                      number_of_document)

613 614
    context.reindexObject()
    get_transaction().commit()
615 616 617 618 619 620 621 622 623

  def stepUploadAnotherTextFromContributionTool(self, sequence=None, sequence_list=None, **kw):
    """
      Upload another file from contribution.
    """
    f = makeFileUpload('ANOTHE-en-001.doc')
    self.portal.portal_contributions.newContent(id='two', file=f)

    get_transaction().commit()
624
    self.tic()
625 626 627 628 629 630 631
    get_transaction().commit()

    context = self.getDocument('two')
    self.assert_('This is a another very interesting document.' in context.asText())
    self.assertEquals(context.getReference(), 'ANOTHE')
    self.assertEquals(context.getVersion(), '001')
    self.assertEquals(context.getLanguage(), 'en')
632 633 634

  def stepDiscoverFromFilename(self, sequence=None, sequence_list=None, **kw):
    """
635 636 637
      Upload a file using contribution tool. This should trigger metadata
      discovery and we should have basic coordinates immediately,
      from first stage.
638
    """
639
    context = self.getDocument('one')
640 641 642 643 644 645 646 647 648 649 650 651 652 653
    file_name = 'TEST-en-002.doc'
    # First make sure the regular expressions work
    property_dict = context.getPropertyDictFromFileName(file_name)
    self.assertEquals(property_dict['reference'], 'TEST')
    self.assertEquals(property_dict['language'], 'en')
    self.assertEquals(property_dict['version'], '002')
    # Then make sure content discover works
    # XXX - This part must be extended
    property_dict = context.getPropertyDictFromContent()
    self.assertEquals(property_dict['title'], 'title')
    self.assertEquals(property_dict['description'], 'comments')
    self.assertEquals(property_dict['subject_list'], ['keywords'])
    # Then make sure metadata discovery works
    f = makeFileUpload(file_name)
654
    context.edit(file=f)
655 656 657
    self.assertEquals(context.getReference(), 'TEST')
    self.assertEquals(context.getLanguage(), 'en')
    self.assertEquals(context.getVersion(), '002')
658
    self.assertEquals(context.getSourceReference(), file_name)
659

660 661
  def stepCheckConvertedContent(self, sequence=None, sequence_list=None, **kw):
    """
662 663 664
      Check that the input file was successfully converted
      and that its SearchableText and asText contain
      the word "magic"
665 666
    """
    self.tic()
667
    context = self.getDocument('one')
668
    self.assert_(context.hasBaseData())
669
    self.assert_('magic' in context.SearchableText())
670
    self.assert_('magic' in str(context.asText()))
671

672
  def stepSetSimulatedDiscoveryScript(self, sequence=None, sequence_list=None, **kw):
673 674 675 676
    """
      Create Text_getPropertyDictFrom[source] scripts
      to simulate custom site's configuration
    """
677 678 679
    self.newPythonScript('one', 'Text_getPropertyDictFromUserLogin',
                         'user_name=None', "return {'contributor':'person_module/john'}")
    self.newPythonScript('one', 'Text_getPropertyDictFromContent', '',
680
                         "return {'short_title':'short', 'title':'title', 'contributor':'person_module/john',}")
681 682 683 684 685 686

  def stepTestMetadataSetting(self, sequence=None, sequence_list=None, **kw):
    """
      Upload with custom getPropertyDict methods
      check that all metadata are correct
    """
687
    context = self.getDocument('one')
688
    f = makeFileUpload('TEST-en-002.doc')
689
    context.edit(file=f)
690 691
    get_transaction().commit()
    self.tic()
692 693 694
    # Then make sure content discover works
    property_dict = context.getPropertyDictFromUserLogin()
    self.assertEquals(property_dict['contributor'], 'person_module/john')
695 696 697 698
    # reference from filename (the rest was checked some other place)
    self.assertEquals(context.getReference(), 'TEST')
    # short_title from content
    self.assertEquals(context.getShortTitle(), 'short')
699
    # title from metadata inside the document
700
    self.assertEquals(context.getTitle(),  'title')
701 702 703 704 705
    # contributors from user
    self.assertEquals(context.getContributor(), 'person_module/john')

  def stepEditMetadata(self, sequence=None, sequence_list=None, **kw):
    """
706
      we change metadata in a document which has ODF
707
    """
708
    context = self.getDocument('one')
709 710 711
    kw = dict(title='another title',
              subject='another subject',
              description='another description')
712
    context.edit(**kw)
713
    context.reindexObject(); get_transaction().commit();
Bartek Górny's avatar
Bartek Górny committed
714
    self.tic();
715 716 717 718 719 720 721 722

  def stepCheckChangedMetadata(self, sequence=None, sequence_list=None, **kw):
    """
      then we download it and check if it is changed
    """
    # XXX actually this is an example of how it should be
    # implemented in OOoDocument class - we don't really
    # need oood for getting/setting metadata...
723
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
724
    newcontent = context.getBaseData()
725
    cs = cStringIO.StringIO()
726
    cs.write(_unpackData(newcontent))
727 728 729 730 731
    z = zipfile.ZipFile(cs)
    s = z.read('meta.xml')
    xmlob = parseString(s)
    title = xmlob.getElementsByTagName('dc:title')[0].childNodes[0].data
    self.assertEquals(title, u'another title')
732
    subject = xmlob.getElementsByTagName('meta:keyword')[0].childNodes[0].data
733 734 735 736 737 738 739 740 741
    self.assertEquals(subject, u'another subject')
    description = xmlob.getElementsByTagName('dc:description')[0].childNodes[0].data
    self.assertEquals(description, u'another description')
    
  def stepIngestTextFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported text formats
      make sure they are converted
    """
742 743
    format_list = ['rtf', 'doc', 'txt', 'sxw', 'sdw']
    self.ingestFormatList('one', format_list)
744 745 746 747 748 749

  def stepIngestSpreadsheetFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported spreadsheet formats
      make sure they are converted
    """
750 751
    format_list = ['xls', 'sxc', 'sdc']
    self.ingestFormatList('two', format_list)
752 753 754 755 756 757

  def stepIngestPresentationFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported presentation formats
      make sure they are converted
    """
758 759
    format_list = ['ppt', 'sxi', 'sdd']
    self.ingestFormatList('three', format_list)
760

761 762 763 764 765
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported PDF formats
      make sure they are converted
    """
766 767
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
768

769 770 771 772 773
  def stepIngestDrawingFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported presentation formats
      make sure they are converted
    """
774
    format_list = ['sxd',]
775
    self.ingestFormatList('four', format_list)
776

777
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
778
    """
779 780
      ingest all supported pdf formats
      make sure they are converted
781
    """
782 783
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
784 785 786 787 788

  def stepIngestImageFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported image formats
    """
789 790
    format_list = ['jpg', 'gif', 'bmp', 'png']
    self.ingestFormatList('six', format_list, 'Image')
791 792

  def stepCheckTextDocumentExportList(self, sequence=None, sequence_list=None, **kw):
793
    self.checkDocumentExportList('one', 'doc', ['pdf', 'doc', 'rtf', 'writer.html', 'txt'])
794 795

  def stepCheckSpreadsheetDocumentExportList(self, sequence=None, sequence_list=None, **kw):
796
    self.checkDocumentExportList('two', 'xls', ['csv', 'calc.html', 'xls', 'calc.pdf'])
797 798 799 800 801 802 803

  def stepCheckPresentationDocumentExportList(self, sequence=None, sequence_list=None, **kw):
    self.checkDocumentExportList('three', 'ppt', ['impr.pdf', 'ppt'])

  def stepCheckDrawingDocumentExportList(self, sequence=None, sequence_list=None, **kw):
    self.checkDocumentExportList('four', 'sxd', ['jpg', 'draw.pdf', 'svg'])

804
  def stepExportPDF(self, sequence=None, sequence_list=None, **kw):
805
    """
806
      Try to export PDF to text and HTML
807
    """
808
    document = self.getDocument('five')
809
    f = makeFileUpload('TEST-en-002.pdf')
810
    document.edit(file=f)
811 812 813 814 815 816
    mime, text = document.convert('text')
    self.failUnless('magic' in text)
    self.failUnless(mime == 'text/plain')
    mime, html = document.convert('html')
    self.failUnless('magic' in html)
    self.failUnless(mime == 'text/html')
817 818

  def stepExportImage(self, sequence=None, sequence_list=None, **kw):
819 820 821 822 823
    """
      Don't see a way to test it here, Image.index_html makes heavy use 
      of REQUEST and RESPONSE, and the rest of the implementation is way down
      in Zope core
    """
824
    printAndLog('stepExportImage not implemented')
825

826
  def stepCheckHasSnapshot(self, sequence=None, sequence_list=None, **kw):
827
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
828
    self.failUnless(context.hasSnapshotData())
829 830

  def stepCheckHasNoSnapshot(self, sequence=None, sequence_list=None, **kw):
831
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
832
    self.failIf(context.hasSnapshotData())
833 834

  def stepCreateSnapshot(self, sequence=None, sequence_list=None, **kw):
835
    context = self.getDocument('one')
836 837 838
    context.createSnapshot()

  def stepTryRecreateSnapshot(self, sequence=None, sequence_list=None, **kw):
839
    context = self.getDocument('one')
840 841 842 843
    # XXX this always fails, don't know why
    #self.assertRaises(ConversionError, context.createSnapshot)

  def stepDeleteSnapshot(self, sequence=None, sequence_list=None, **kw):
844
    context = self.getDocument('one')
845 846
    context.deleteSnapshot()

847 848 849 850 851
  def stepCleanUp(self, sequence=None, sequence_list=None, **kw):
    """
        Clean up DMS system from old content.
    """
    portal = self.getPortal()
852
    for module in (portal.document_module, portal.image_module, portal.document_ingestion_module):
853 854
      module.manage_delObjects(map(None, module.objectIds()))
    
Bartek Górny's avatar
Bartek Górny committed
855
  def stepContributeFileListWithType(self, sequence=None, sequence_list=None, **kw):
856 857 858 859
    """
      Contribute all kinds of files giving portal type explicitly
      TODO: test situation whereby portal_type given explicitly is wrong
    """
Bartek Górny's avatar
Bartek Górny committed
860
    self.contributeFileList(with_portal_type=True)
861

Bartek Górny's avatar
Bartek Górny committed
862
  def stepContributeFileListWithNoType(self, sequence=None, sequence_list=None, **kw):
863 864 865 866
    """
      Contribute all kinds of files
      let the system figure out portal type by itself
    """
Bartek Górny's avatar
Bartek Górny committed
867
    self.contributeFileList(with_portal_type=False)
868

869
  def stepSetSimulatedDiscoveryScriptForOrdering(self, sequence=None, sequence_list=None, **kw):
870 871 872 873 874 875 876 877 878 879
    """
      set scripts which are supposed to overwrite each other's metadata
      desing is the following:
                    File Name     User    Content        Input
      reference     TEST          USER    CONT           INPUT
      language      en            us                     in
      version       002                   003            004
      contributor                 john    jack           james
      short_title                         from_content   from_input
    """
880 881
    self.newPythonScript('one', 'Text_getPropertyDictFromUserLogin', 'user_name=None', "return {'reference':'USER', 'language':'us', 'contributor':'person_module/john'}")
    self.newPythonScript('one', 'Text_getPropertyDictFromContent', '', "return {'reference':'CONT', 'version':'003', 'contributor':'person_module/jack', 'short_title':'from_content'}")
882

Bartek Górny's avatar
Bartek Górny committed
883
  def stepCheckMetadataSettingOrderFICU(self, sequence=None, sequence_list=None, **kw):
884 885
    """
     This is the default
886
    """  
887
    expected_metadata = dict(reference='TEST', language='en', version='002', short_title='from_input', contributor='person_module/james')
888 889
    self.setDiscoveryOrder(['file_name', 'input', 'content', 'user_login'])
    self.discoverMetadata()
890
    self.checkMetadataOrder(expected_metadata)
891 892 893 894 895

  def stepCheckMetadataSettingOrderCUFI(self, sequence=None, sequence_list=None, **kw):
    """
     Content - User - Filename - Input
    """
896
    expected_metadata = dict(reference='CONT', language='us', version='003', short_title='from_content', contributor='person_module/jack')
897 898
    self.setDiscoveryOrder(['content', 'user_login', 'file_name', 'input'])
    self.discoverMetadata()
899
    self.checkMetadataOrder(expected_metadata)
900 901 902 903 904

  def stepCheckMetadataSettingOrderUIFC(self, sequence=None, sequence_list=None, **kw):
    """
     User - Input - Filename - Content
    """
905
    expected_metadata = dict(reference='USER', language='us', version='004', short_title='from_input', contributor='person_module/john')
906 907
    self.setDiscoveryOrder(['user_login', 'input', 'file_name', 'content'])
    self.discoverMetadata()
908
    self.checkMetadataOrder(expected_metadata)
909 910 911 912 913

  def stepCheckMetadataSettingOrderICUF(self, sequence=None, sequence_list=None, **kw):
    """
     Input - Content - User - Filename
    """
914
    expected_metadata = dict(reference='INPUT', language='in', version='004', short_title='from_input', contributor='person_module/james')
915 916
    self.setDiscoveryOrder(['input', 'content', 'user_login', 'file_name'])
    self.discoverMetadata()
917
    self.checkMetadataOrder(expected_metadata)
918 919 920 921 922

  def stepCheckMetadataSettingOrderUFCI(self, sequence=None, sequence_list=None, **kw):
    """
     User - Filename - Content - Input
    """
923
    expected_metadata = dict(reference='USER', language='us', version='002', short_title='from_content', contributor='person_module/john')
924 925
    self.setDiscoveryOrder(['user_login', 'file_name', 'content', 'input'])
    self.discoverMetadata()
926
    self.checkMetadataOrder(expected_metadata)
927

928
  def stepReceiveEmailFromUnknown(self, sequence=None, sequence_list=None, **kw):
929 930 931 932
    """
      email was sent in by someone who is not in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
933 934 935
    document = self.receiveEmail(data=f.read())
    get_transaction().commit()
    self.tic()
936 937

  def stepReceiveEmailFromJohn(self, sequence=None, sequence_list=None, **kw):
938 939 940 941
    """
      email was sent in by someone who is in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
942
    document = self.receiveEmail(f.read())
943 944
    get_transaction().commit()
    self.tic()
945 946

  def stepVerifyEmailedDocuments(self, sequence=None, sequence_list=None, **kw):
947 948 949 950
    """
      find the newly mailed-in document by its reference
      check its properties
    """
951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968
    # First, check document ingestion message
    result = self.portal_catalog(portal_type='Document Ingestion Message',
                                 title='A Test Mail',
                                 source_title='John Doe'
                                 )
    self.assertEqual(len(result), 1)
    ingestion_message = result[0].getObject()

    # Second, check attachments
    attachment_list = ingestion_message.getAggregateValueList()
    self.assertEqual(len(attachment_list), 1)

    # Third, check document
    result = self.portal_catalog(portal_type='Text')
    self.assertEqual(len(result), 1)
    document = result[0].getObject()
    self.assertEqual(document.getRelativeUrl(), result[0].getRelativeUrl())

969

970 971 972 973 974
  def playSequence(self, step_list, quiet):
    sequence_list = SequenceList()
    sequence_string = ' '.join(step_list)
    sequence_list.addSequenceString(sequence_string)
    sequence_list.play(self, quiet=quiet)
975
  
976 977 978 979
  ##################################
  ##  Tests
  ##################################

980
  def test_01_PreferenceSetup(self, quiet=QUIET, run=RUN_ALL_TEST):
981 982 983
    """
      Make sure that preferences are set up properly and accessible
    """
984
    if not run: return
985 986 987 988
    if not quiet: printAndLog('test_01_PreferenceSetup')
    preference_tool = self.portal.portal_preferences
    self.assertEquals(preference_tool.getPreferredOoodocServerAddress(), conversion_server_host[0])
    self.assertEquals(preference_tool.getPreferredOoodocServerPortNumber(), conversion_server_host[1])
989 990 991
    self.assertEquals(preference_tool.getPreferredDocumentFileNameRegularExpression(), FILE_NAME_REGULAR_EXPRESSION)
    self.assertEquals(preference_tool.getPreferredDocumentReferenceRegularExpression(), REFERENCE_REGULAR_EXPRESSION)
    
992
  def test_02_FileExtensionRegistry(self, quiet=QUIET, run=RUN_ALL_TEST):
993 994 995
    """
      check if we successfully imported registry
      and that it has all the entries we need
996
    """
997 998
    if not run: return
    if not quiet: printAndLog('test_02_FileExtensionRegistry')
999
    reg = self.portal.portal_contribution_registry
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016
    correct_type_mapping = {
            'doc' : 'Text',
            'txt' : 'Text',
            'odt' : 'Text',
            'sxw' : 'Text',
            'rtf' : 'Text',
            'gif' : 'Image',
            'jpg' : 'Image',
            'png' : 'Image',
            'bmp' : 'Image',
            'pdf' : 'PDF',
            'xls' : 'Spreadsheet',
            'ods' : 'Spreadsheet',
            'sdc' : 'Spreadsheet',
            'ppt' : 'Presentation',
            'odp' : 'Presentation',
            'sxi' : 'Presentation',
1017
            'sxd' : 'Drawing',
1018 1019 1020 1021
            'xxx' : 'File',
          }
    for type, portal_type in correct_type_mapping.items():
      file_name = 'aaa.' + type
1022 1023
      self.assertEquals(reg.findPortalTypeName(file_name, None, None),
                        portal_type)
1024

1025
  def test_03_TextDoc(self, quiet=QUIET, run=RUN_ALL_TEST):
1026
    """
1027
      Test basic behaviour of a document:
1028
      - create empty document
1029 1030 1031 1032 1033
      - upload a file directly
      - upload a file using upload dialog
      - make sure revision was increased
      - check that it was properly converted
      - check if coordinates were extracted from file name
1034 1035
    """
    if not run: return
1036
    if not quiet: printAndLog('test_03_TextDoc')
1037 1038
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1039
                 ,'stepCheckEmptyState'
1040
                 ,'stepStraightUpload'
1041 1042
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1043
                 ,'stepCheckConvertedState'
1044 1045 1046
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1047 1048
                 ,'stepCheckConvertedState'
                ]
1049
    self.playSequence(step_list, quiet)
1050

1051
  def test_04_MetadataExtraction(self, quiet=QUIET, run=RUN_ALL_TEST):
1052 1053
    """
      Test metadata extraction from various sources:
1054 1055 1056 1057 1058
      - from file name (doublecheck)
      - from user (by overwriting type-based method
                   and simulating the result)
      - from content (by overwriting type-based method
                      and simulating the result)
1059
      - from file metadata
1060 1061 1062 1063

      NOTE: metadata of document (title, subject, description)
      are no longer retrieved and set upon conversion
    """
1064
    if not run: return
1065
    if not quiet: printAndLog('test_04_MetadataExtraction')
1066
    step_list = [ 'stepCleanUp'
1067
                 ,'stepUploadTextFromContributionTool'
1068
                 ,'stepSetSimulatedDiscoveryScript'
1069
                 ,'stepTic'
1070 1071
                 ,'stepTestMetadataSetting'
                ]
1072
    self.playSequence(step_list, quiet)
1073

1074
  def test_041_MetadataEditing(self, quiet=QUIET, run=RUN_ALL_TEST):
1075 1076 1077 1078 1079 1080
    """
      Check metadata in the object and in the ODF document
      Edit metadata on the object
      Download ODF, make sure it is changed
    """
    if not run: return
1081
    if not quiet: printAndLog('test_04_MetadataEditing')
1082 1083
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1084 1085 1086 1087
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1088 1089
                 ,'stepEditMetadata'
                 ,'stepCheckChangedMetadata'
1090
                ]
1091
    self.playSequence(step_list, quiet)
1092

1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104


  #    Ingest various formats (xls, doc, sxi, ppt etc)
  #    Verify that they are successfully converted
  #    - have ODF data and contain magic word in SearchableText
  #    - or have text data and contain magic word in SearchableText
  #      TODO:
  #    - or were not moved in processing_status_workflow if the don't
  #      implement _convertToBase (e.g. Image)
  #    Verify that you can not upload file of the wrong format.

  def test_05_FormatIngestionText(self, quiet=QUIET, run=RUN_ALL_TEST):
1105 1106
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1107
                 ,'stepIngestTextFormats'
1108 1109 1110 1111 1112 1113 1114
                ]
    self.playSequence(step_list, quiet)

  def test_05_FormatIngestionSpreadSheet(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_05_FormatIngestion')
    step_list = ['stepCleanUp'
1115 1116
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepIngestSpreadsheetFormats'
1117 1118 1119 1120 1121 1122 1123
                ]
    self.playSequence(step_list, quiet)

  def test_05_FormatIngestionPresentation(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_05_FormatIngestion')
    step_list = ['stepCleanUp'
1124 1125
                 ,'stepCreatePresentationDocument'
                 ,'stepIngestPresentationFormats'
1126 1127 1128 1129 1130 1131 1132
                ]
    self.playSequence(step_list, quiet)

  def test_05_FormatIngestionDrawing(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_05_FormatIngestion')
    step_list = ['stepCleanUp'
1133 1134
                 ,'stepCreateDrawingDocument'
                 ,'stepIngestDrawingFormats'
1135 1136 1137 1138 1139 1140 1141
                ]
    self.playSequence(step_list, quiet)

  def test_05_FormatIngestionPDF(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_05_FormatIngestion')
    step_list = ['stepCleanUp'
1142 1143
                 ,'stepCreatePDFDocument'
                 ,'stepIngestPDFFormats'
1144 1145 1146 1147 1148 1149 1150
                ]
    self.playSequence(step_list, quiet)

  def test_05_FormatIngestionImage(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_05_FormatIngestion')
    step_list = ['stepCleanUp'
1151 1152
                 ,'stepCreateImageDocument'
                 ,'stepIngestImageFormats'
1153
                ]
1154
    self.playSequence(step_list, quiet)
1155

1156 1157 1158 1159 1160 1161

  # Test generation of files in all possible formats
  # which means check if they have correct lists of available formats for export
  # actual generation is tested in oood tests
  # PDF and Image should be tested here
  def test_06_FormatGenerationText(self, quiet=QUIET, run=RUN_ALL_TEST):
1162
    if not run: return
1163
    if not quiet: printAndLog('test_06_FormatGeneration')
1164 1165
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1166
                 ,'stepCheckTextDocumentExportList'
1167 1168 1169 1170 1171 1172 1173
                ]
    self.playSequence(step_list, quiet)

  def test_06_FormatGenerationSpreadsheet(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_06_FormatGeneration')
    step_list = [ 'stepCleanUp'
1174 1175
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepCheckSpreadsheetDocumentExportList'
1176 1177 1178 1179 1180 1181 1182
                ]
    self.playSequence(step_list, quiet)

  def test_06_FormatGenerationPresentation(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_06_FormatGeneration')
    step_list = [ 'stepCleanUp'
1183 1184
                 ,'stepCreatePresentationDocument'
                 ,'stepCheckPresentationDocumentExportList'
1185 1186 1187 1188 1189 1190 1191
                ]
    self.playSequence(step_list, quiet)

  def test_06_FormatGenerationDrawing(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_06_FormatGeneration')
    step_list = [ 'stepCleanUp'
1192 1193
                 ,'stepCreateDrawingDocument'
                 ,'stepCheckDrawingDocumentExportList'
1194 1195 1196 1197 1198 1199 1200
                ]
    self.playSequence(step_list, quiet)

  def test_06_FormatGenerationPdf(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_06_FormatGeneration')
    step_list = [ 'stepCleanUp'
1201 1202
                 ,'stepCreatePDFDocument'
                 ,'stepExportPDF'
1203 1204 1205 1206 1207 1208 1209
                ]
    self.playSequence(step_list, quiet)

  def test_06_FormatGenerationImage(self, quiet=QUIET, run=RUN_ALL_TEST):
    if not run: return
    if not quiet: printAndLog('test_06_FormatGeneration')
    step_list = [ 'stepCleanUp'
1210 1211
                 ,'stepCreateImageDocument'
                 ,'stepExportImage'
1212
                ]
1213
    self.playSequence(step_list, quiet)
1214

1215

1216 1217 1218 1219 1220 1221 1222
  def test_07_SnapshotGeneration(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Generate snapshot, make sure it is there, 
      try to generate it again, remove and 
      generate once more
    """
    if not run: return
1223
    if not quiet: printAndLog('test_07_SnapshotGeneration')
1224 1225
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1226 1227 1228 1229
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1230 1231 1232 1233 1234 1235 1236 1237
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                 ,'stepTryRecreateSnapshot'
                 ,'stepCheckHasSnapshot'
                 ,'stepDeleteSnapshot'
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                ]
1238
    self.playSequence(step_list, quiet)
1239

1240 1241
  def test_08_Cache(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1242
      I don't know how to verify how cache works
1243 1244
    """

1245
  def test_09_Contribute(self, quiet=QUIET, run=RUN_ALL_TEST):
1246 1247 1248 1249 1250 1251 1252 1253 1254 1255
    """
      Create content through portal_contributions
      - use newContent to ingest various types 
        also to test content_type_registry setup
      - verify that
        - appropriate portal_types were created
        - the files were converted
        - metadata was read
    """
    if not run: return
1256
    if not quiet: printAndLog('test_09_Contribute')
1257 1258
    step_list = [ 'stepCleanUp'
                 ,'stepContributeFileListWithNoType'
1259
                 ,'stepCleanUp'
Bartek Górny's avatar
Bartek Górny committed
1260
                 ,'stepContributeFileListWithType'
1261
                ]
1262
    self.playSequence(step_list, quiet)
1263 1264 1265

  def test_10_MetadataSettingPreferenceOrder(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1266
      Set some metadata discovery scripts
1267
      Contribute a document, let it get metadata using default setup
1268 1269 1270
      (default is FUC)

      check that the right ones are there
1271 1272
      change preference order, check again
    """
1273
    if not run: return
1274
    if not quiet: printAndLog('test_10_MetadataSettingPreferenceOrder')
1275 1276
    step_list = [ 'stepCleanUp' 
                 ,'stepCreateTextDocument'
1277
                 ,'stepStraightUpload'
1278 1279 1280
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1281
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
Bartek Górny's avatar
Bartek Górny committed
1282
                 ,'stepCheckMetadataSettingOrderFICU'
1283 1284
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1285 1286 1287
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1288
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1289 1290 1291
                 ,'stepCheckMetadataSettingOrderCUFI'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1292 1293 1294
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1295
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1296 1297 1298
                 ,'stepCheckMetadataSettingOrderUIFC'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1299 1300 1301
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1302
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1303 1304 1305
                 ,'stepCheckMetadataSettingOrderICUF'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1306 1307 1308
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1309
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1310 1311
                 ,'stepCheckMetadataSettingOrderUFCI'
                ]
1312
    self.playSequence(step_list, quiet)
1313

1314 1315 1316 1317 1318 1319 1320
  def test_11_EmailIngestion(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Simulate email piped to ERP5 by an MTA by uploading test email from file
      Check that document objects are created and appropriate data are set
      (owner, and anything discovered from user and mail body)
    """
    if not run: return
1321
    if not quiet: printAndLog('test_11_EmailIngestion')
1322 1323
    step_list = [ 'stepCleanUp'
                 ,'stepReceiveEmailFromUnknown'
1324 1325 1326 1327
                 ,'stepCreatePerson'
                 ,'stepReceiveEmailFromJohn'
                 ,'stepVerifyEmailedDocuments'
                ]
1328
    self.playSequence(step_list, quiet)
1329

1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348
  def test_12_UploadTextFromContributionTool(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Make sure that when upload file from contribution tool, it creates a new
      document in document module. when reupload same filename file, then it
      does not create a new document and update existing document.
    """
    if not run: return
    if not quiet: printAndLog('test_12_ReUploadSameFilenameFile')
    step_list = [ 'stepCleanUp'
                 ,'stepUploadTextFromContributionTool'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
                 ,'stepDiscoverFromFilename'
                 ,'stepTic'
                 ,'stepReuploadTextFromContributionTool'
                 ,'stepUploadAnotherTextFromContributionTool'
                ]
    self.playSequence(step_list, quiet)
1349

1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402
  def stepUploadTextFromContributionToolWithNonASCIIFilename(self, 
                                 sequence=None, sequence_list=None, **kw):
    """
      Upload a file from contribution.
    """
    f = makeFileUpload('T&é@{T-en-002.doc')
    document = self.portal.portal_contributions.newContent(file=f)
    sequence.edit(document_id=document.getId())
    get_transaction().commit()

  def stepDiscoverFromFilenameWithNonASCIIFilename(self, 
                                 sequence=None, sequence_list=None, **kw):
    """
      Upload a file using contribution tool. This should trigger metadata
      discovery and we should have basic coordinates immediately,
      from first stage.
    """
    context = self.getDocument(sequence.get('document_id'))
    file_name = 'T&é@{T-en-002.doc'
    # First make sure the regular expressions work
    property_dict = context.getPropertyDictFromFileName(file_name)
    self.assertEquals(property_dict['reference'], 'T&é@{T')
    self.assertEquals(property_dict['language'], 'en')
    self.assertEquals(property_dict['version'], '002')
    # Then make sure content discover works
    # XXX - This part must be extended
    property_dict = context.getPropertyDictFromContent()
    self.assertEquals(property_dict['title'], 'title')
    self.assertEquals(property_dict['description'], 'comments')
    self.assertEquals(property_dict['subject_list'], ['keywords'])
    # Then make sure metadata discovery works
    self.assertEquals(context.getReference(), 'T&é@{T')
    self.assertEquals(context.getLanguage(), 'en')
    self.assertEquals(context.getVersion(), '002')
    self.assertEquals(context.getSourceReference(), file_name)

  def test_13_UploadTextFromContributionToolWithNonASCIIFilename(self, 
                                           quiet=QUIET, run=RUN_ALL_TEST):
    """
      Make sure that when upload file from contribution tool, it creates a new
      document in document module. when reupload same filename file, then it
      does not create a new document and update existing document.
    """
    if not run: return
    if not quiet:
      printAndLog('test_13_UploadTextFromContributionToolWithNonASCIIFilename')
    step_list = [ 'stepCleanUp'
                 ,'stepUploadTextFromContributionToolWithNonASCIIFilename'
                 ,'stepTic'
                 ,'stepDiscoverFromFilenameWithNonASCIIFilename'
                ]
    self.playSequence(step_list, quiet)

1403 1404 1405 1406
# Missing tests
"""
    property_dict = context.getPropertyDictFromUserLogin()
    property_dict = context.getPropertyDictFromInput()
1407
"""
Jérome Perrin's avatar
Jérome Perrin committed
1408 1409 1410 1411 1412

def test_suite():
  suite = unittest.TestSuite()
  suite.addTest(unittest.makeSuite(TestIngestion))
  return suite