testIngestion.py 50 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 52
FILE_NAME_REGULAR_EXPRESSION = "(?P<reference>[A-Z]{3,6})-(?P<language>[a-z]{2})-(?P<version>[0-9]{3})"
REFERENCE_REGULAR_EXPRESSION = "(?P<reference>[A-Z]{3,6})(-(?P<language>[a-z]{2}))?(-(?P<version>[0-9]{3}))?"

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
    return ('erp5_base', 'erp5_web', 'erp5_crm',
            'erp5_dms_mysql_innodb_catalog', 'erp5_dms')
96 97 98 99 100 101

  def afterSetUp(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Initialize the ERP5 site.
    """
    self.login()
102 103
    self.datetime = DateTime()
    self.portal = self.getPortal()
104
    self.portal_categories = self.getCategoryTool()
105 106 107
    self.portal_catalog = self.getCatalogTool()
    self.createDefaultCategoryList()
    self.setSystemPreference()
108
    self.setSimulatedNotificationScript()
109
    self.setTools()
110
    self.setContentTypeRegistry()
111

112 113 114
  def beforeTearDown(self):
    self.portal.portal_caches.clearAllCache()

115
  def setSystemPreference(self):
116
    default_pref = self.portal.portal_preferences.default_site_preference
117 118
    default_pref.setPreferredOoodocServerAddress(conversion_server_host[0])
    default_pref.setPreferredOoodocServerPortNumber(conversion_server_host[1])
119 120
    default_pref.setPreferredDocumentFileNameRegularExpression(FILE_NAME_REGULAR_EXPRESSION)
    default_pref.setPreferredDocumentReferenceRegularExpression(REFERENCE_REGULAR_EXPRESSION)
121 122
    default_pref.enable()

123 124 125 126 127 128 129 130 131 132 133 134
  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')

135 136 137 138 139 140 141
  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')
142

143 144 145 146 147 148 149 150 151 152
  def setContentTypeRegistry(self):
    content_type_registry = self.portal.content_type_registry
    predicate_id = 'Ingested Document'
    if predicate_id not in content_type_registry.predicate_ids:
      content_type_registry.addPredicate(predicate_id, 'extension')
      content_type_registry.predicates[predicate_id][0].edit('emx')
      content_type_registry.assignTypeName(predicate_id,
                                            'Document Ingestion Message')
      content_type_registry.reorderPredicate(predicate_id, 0)

153 154 155 156 157 158 159 160
  ##################################
  ##  Useful methods
  ##################################

  def login(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Create a new manager user and login.
    """
161
    user_name = 'dms_user'
162
    user_folder = self.portal.acl_users
163 164 165 166
    user_folder._doAddUser(user_name, '', ['Manager', 'Owner', 'Assignor'], [])
    user = user_folder.getUserById(user_name).__of__(user_folder)
    newSecurityManager(None, user)

167
  def createDefaultCategoryList(self):
168
    """
169 170 171 172 173 174
      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.
175 176 177 178 179 180
    """
    self.category_list = [
                         # Role categories
                          {'path' : 'role/internal'
                           ,'title': 'Internal'
                           }
181 182 183 184 185 186 187 188 189
                          ,{'path' : 'function/musician/wind/saxophone'
                           ,'title': 'Saxophone'
                           }
                          ,{'path' : 'group/medium'
                           ,'title': 'Medium'
                           }
                          ,{'path' : 'site/arctic/spitsbergen'
                           ,'title': 'Spitsbergen'
                           }
190 191 192
                          ,{'path' : 'group/anybody'
                           ,'title': 'Anybody'
                           }
193 194 195 196 197 198
                          ,{'path' : 'publication_section/cop'
                           ,'title': 'COPs'
                           }
                          ,{'path' : 'publication_section/cop/one'
                           ,'title': 'COP one'
                           }
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
                         ]

    # 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'))
234 235
    get_transaction().commit()
    self.tic()
236 237 238 239 240 241

  def getCategoryList(self, base_category=None):
    """
      Get a list of categories with same base categories.
    """
    categories = []
242
    if base_category is not None:
243 244 245 246 247
      for category in self.category_list:
        if category["path"].split('/')[0] == base_category:
          categories.append(category)
    return categories

248
  def getDocument(self, id):
249 250 251 252 253 254
    """
      Returns a document with given ID in the
      document module.
    """
    document_module = self.portal.document_module
    return getattr(document_module, id)
255

256
  def checkIsObjectCatalogged(self, portal_type, **kw):
257
    """
258 259 260 261 262
      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.
263
    """
264
    res = self.portal_catalog(portal_type=portal_type, **kw.copy())
265
    self.assertEquals(len(res), 1)
266 267
    for key, value in kw.items():
      self.assertEquals(res[0].getProperty(key), value)
268

269
  def newEmptyCataloggedDocument(self, portal_type, id):
270
    """
271 272 273 274 275 276
      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.
277
    """
278 279 280 281 282 283 284 285 286 287 288
    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
289

290
  def ingestFormatList(self, document_id, format_list, portal_type=None):
291
    """
292 293 294 295 296 297 298 299 300
      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.
301 302
    """
    if portal_type is None:
303
      document_module = self.portal.document_module
304
    else:
305 306 307
      document_module = self.portal.getDefaultModule(portal_type)
    context = getattr(document_module, document_id)
    for revision, format in enumerate(format_list):
308
      filename = 'TEST-en-002.' + format
309
      printAndLog('Ingesting file: ' + filename)
310 311
      f = makeFileUpload(filename)
      context.edit(file=f)
312
      context.convertToBaseFormat()
313 314 315
      context.reindexObject()
      get_transaction().commit()
      self.tic()
316
      self.failUnless(context.hasFile())
317
      if context.getPortalType() in ('Image', 'File', 'PDF'):
318
        # File and images do not support conversion to text in DMS
319
        # PDF has not implemented _convertToBaseFormat() so can not be converted
320 321
        self.assertEquals(context.getExternalProcessingState(), 'uploaded')
      else:
322 323
        if context.getExternalProcessingState()=='uploaded':
          import pdb;pdb.set_trace()
324 325
        self.assertEquals(context.getExternalProcessingState(), 'converted') # this is how we know if it was ok or not
        self.assert_('magic' in context.SearchableText())
326
        self.assert_('magic' in str(context.asText()))
327

328
  def checkDocumentExportList(self, document_id, format, asserted_target_list):
329
    """
330 331 332
      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
333
    """
334
    context = self.getDocument(document_id)
335 336 337
    filename = 'TEST-en-002.' + format
    f = makeFileUpload(filename)
    context.edit(file=f)
338
    context.convertToBaseFormat()
339 340 341
    context.reindexObject()
    get_transaction().commit()
    self.tic()
342 343
    # We call clear cache to be sure that the target list is updated
    self.getPortal().portal_caches.clearCache()
344 345
    target_list = context.getTargetFormatList()
    for target in asserted_target_list:
346 347
      self.assert_(target in target_list)

Bartek Górny's avatar
Bartek Górny committed
348
  def contributeFileList(self, with_portal_type=False):
349
    """
350 351 352
      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
353 354
      on portal_contributions.
      http://framework.openoffice.org/documentation/mimetypes/mimetypes.html
355
    """
356 357 358 359
    created_documents = []
    extension_to_type = (('ppt', 'Presentation')
                        ,('doc', 'Text')
                        ,('sdc', 'Spreadsheet')
360
                        ,('sxc', 'Spreadsheet')
361 362 363 364
                        ,('pdf', 'PDF')
                        ,('jpg', 'Image')
                        ,('py', 'File')
                        )
365 366
    counter = 1
    old_portal_type = ''
367 368
    for extension, portal_type in extension_to_type:
      filename = 'TEST-en-002.' + extension
369
      printAndLog(filename)
370
      file = makeFileUpload(filename)
371 372 373 374 375 376 377
      # 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)
378
      if with_portal_type:
379
        ob = self.portal.portal_contributions.newContent(portal_type=portal_type, file=file)
380 381
      else:
        ob = self.portal.portal_contributions.newContent(file=file)
382
      # reindex
383 384 385 386 387 388 389 390 391
      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
392
      self.assertEquals(ob.getPortalType(), portal_type)
393
      self.assertEquals(ob.getReference(), 'TEST')
394 395
      if ob.getPortalType() in ('Image', 'File', 'PDF'):
        # Image, File and PDF are not converted to a base format
396 397
        self.assertEquals(ob.getExternalProcessingState(), 'uploaded')
      else:
398 399 400
        # We check if conversion has succeeded by looking
        # at the external_processing workflow
        self.assertEquals(ob.getExternalProcessingState(), 'converted')
401
        self.assert_('magic' in ob.SearchableText())
402 403 404 405 406 407

  def newPythonScript(self, object_id, script_id, argument_list, code):
    """
      Creates a new python script with given argument_list
      and source code.
    """
408 409 410 411
    context = self.getDocument(object_id)
    factory = context.manage_addProduct['PythonScripts'].manage_addPythonScript
    factory(id=script_id)
    script = getattr(context, script_id)
412
    script.ZPythonScript_edit(argument_list, code)
413

414
  def setDiscoveryOrder(self, order, id='one'):
415
    """
416 417
      Creates a script to define the metadata discovery order
      for Text documents.
418 419
    """
    script_code = "return %s" % str(order)
420
    self.newPythonScript(id, 'Text_getPreferredDocumentMetadataDiscoveryOrderList', '', script_code)
421
    
422 423 424 425 426 427
  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)
428 429 430 431 432
    # simulate user input
    context._backup_input = dict(reference='INPUT', 
                                 language='in',
                                 version='004', 
                                 short_title='from_input',
433
                                 contributor='person_module/james')
434 435
    # pass to discovery file_name and user_login
    context.discoverMetadata(context.getSourceReference(), 'john_doe') 
436 437 438
    context.reindexObject()
    get_transaction().commit()
    self.tic()
439

440 441 442 443 444 445 446
  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():
447
      self.assertEquals(context.getProperty(k), v)
448

449 450 451 452 453 454 455 456 457
  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)

458 459 460
  ##################################
  ##  Basic steps
  ##################################
461 462 463
 
  def stepTic(self, sequence=None, sequence_list=None, **kw):
    self.tic()
464 465 466

  def stepCreatePerson(self, sequence=None, sequence_list=None, **kw):
    """
467
      Create a person with ID "john" if it does not exists already
468 469
    """
    portal_type = 'Person'
470
    person_id = 'john'
471
    reference = 'john_doe'
472
    person_module = self.portal.person_module
473 474 475 476 477 478 479 480
    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'
                                      )
481
    person.setDefaultEmailText('john@doe.com')
482 483 484
    person.reindexObject()
    get_transaction().commit()
    self.tic()
485 486 487

  def stepCreateTextDocument(self, sequence=None, sequence_list=None, **kw):
    """
488 489
      Create an empty Text document with ID 'one'
      This document will be used in most tests.
490
    """
491
    self.newEmptyCataloggedDocument('Text', 'one')
492

493 494
  def stepCreateSpreadsheetDocument(self, sequence=None, sequence_list=None, **kw):
    """
495 496
      Create an empty Spreadsheet document with ID 'two'
      This document will be used in most tests.
497
    """
498
    self.newEmptyCataloggedDocument('Spreadsheet', 'two')
499 500 501

  def stepCreatePresentationDocument(self, sequence=None, sequence_list=None, **kw):
    """
502 503
      Create an empty Presentation document with ID 'three'
      This document will be used in most tests.
504
    """
505
    self.newEmptyCataloggedDocument('Presentation', 'three')
506 507 508

  def stepCreateDrawingDocument(self, sequence=None, sequence_list=None, **kw):
    """
509 510
      Create an empty Drawing document with ID 'four'
      This document will be used in most tests.
511
    """
512
    self.newEmptyCataloggedDocument('Drawing', 'four')
513

514 515
  def stepCreatePDFDocument(self, sequence=None, sequence_list=None, **kw):
    """
516 517
      Create an empty PDF document with ID 'five'
      This document will be used in most tests.
518
    """
519
    self.newEmptyCataloggedDocument('PDF', 'five')
520 521 522

  def stepCreateImageDocument(self, sequence=None, sequence_list=None, **kw):
    """
523 524
      Create an empty Image document with ID 'six'
      This document will be used in most tests.
525
    """
526
    self.newEmptyCataloggedDocument('Image', 'six')
527

528 529
  def stepCheckEmptyState(self, sequence=None, sequence_list=None, **kw):
    """
530 531
      Check if the document is in "empty" processing state
      (ie. no file upload has been done yet)
532
    """
533
    context = self.getDocument('one')
534 535 536 537
    return self.assertEquals(context.getExternalProcessingState(), 'empty')

  def stepCheckUploadedState(self, sequence=None, sequence_list=None, **kw):
    """
538 539
      Check if the document is in "uploaded" processing state
      (ie. a file upload has been done)
540
    """
541
    context = self.getDocument('one')
542 543
    return self.assertEquals(context.getExternalProcessingState(), 'uploaded')

544 545 546 547 548 549 550 551
  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')

552 553
  def stepCheckConvertedState(self, sequence=None, sequence_list=None, **kw):
    """
554
      Check if the document is in "converted" processing state
555
      (ie. a file conversion has been done and the document has
556
      been converted)
557
    """
558
    context = self.getDocument('one')
559 560
    return self.assertEquals(context.getExternalProcessingState(), 'converted')

561 562 563 564 565
  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
    """
566
    filename = 'TEST-en-002.doc'
567 568 569
    document = self.getDocument('one')
    # Revision is 0 before upload (revisions are strings)
    self.assertEquals(document.getRevision(), '0')
570
    f = makeFileUpload(filename)
571
    document.edit(file=f)
572 573
    # set source
    document.setSourceReference(filename)
574
    self.assert_(document.hasFile())
575 576
    # source_reference set to file name ?
    self.assertEquals(document.getSourceReference(), filename) 
577 578 579 580
    # Revision is 1 after upload (revisions are strings)
    self.assertEquals(document.getRevision(), '1')
    document.reindexObject()
    get_transaction().commit()
581

582
  def stepUploadFromViewForm(self, sequence=None, sequence_list=None, **kw):
583
    """
584
      Upload a file from view form and make sure this increases the revision
585
    """
586
    context = self.getDocument('one')
587
    f = makeFileUpload('TEST-en-002.doc')
588
    revision = context.getRevision()
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618
    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()
619
    self.assertEquals(context.getRevision(), str(int(revision) + 1))
620 621 622 623
    self.assert_('This document is modified.' in context.asText())
    self.assertEquals(len(self.portal.document_module.objectIds()),
                      number_of_document)

624 625
    context.reindexObject()
    get_transaction().commit()
626 627 628 629 630 631 632 633 634

  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()
635
    self.tic()
636 637 638 639 640 641 642
    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')
643 644 645

  def stepDiscoverFromFilename(self, sequence=None, sequence_list=None, **kw):
    """
646 647 648
      Upload a file using contribution tool. This should trigger metadata
      discovery and we should have basic coordinates immediately,
      from first stage.
649
    """
650
    context = self.getDocument('one')
651 652 653 654 655 656 657 658 659 660 661 662 663 664
    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)
665
    context.edit(file=f)
666 667 668 669
    self.assertEquals(context.getReference(), 'TEST')
    self.assertEquals(context.getLanguage(), 'en')
    self.assertEquals(context.getVersion(), '002')

670 671
  def stepCheckConvertedContent(self, sequence=None, sequence_list=None, **kw):
    """
672 673 674
      Check that the input file was successfully converted
      and that its SearchableText and asText contain
      the word "magic"
675 676
    """
    self.tic()
677
    context = self.getDocument('one')
678
    self.assert_(context.hasBaseData())
679
    self.assert_('magic' in context.SearchableText())
680
    self.assert_('magic' in str(context.asText()))
681

682
  def stepSetSimulatedDiscoveryScript(self, sequence=None, sequence_list=None, **kw):
683 684 685 686
    """
      Create Text_getPropertyDictFrom[source] scripts
      to simulate custom site's configuration
    """
687 688 689
    self.newPythonScript('one', 'Text_getPropertyDictFromUserLogin',
                         'user_name=None', "return {'contributor':'person_module/john'}")
    self.newPythonScript('one', 'Text_getPropertyDictFromContent', '',
690
                         "return {'short_title':'short', 'title':'title', 'contributor':'person_module/john',}")
691 692 693 694 695 696

  def stepTestMetadataSetting(self, sequence=None, sequence_list=None, **kw):
    """
      Upload with custom getPropertyDict methods
      check that all metadata are correct
    """
697
    context = self.getDocument('one')
698
    f = makeFileUpload('TEST-en-002.doc')
699
    context.edit(file=f)
700 701
    get_transaction().commit()
    self.tic()
702 703 704
    # Then make sure content discover works
    property_dict = context.getPropertyDictFromUserLogin()
    self.assertEquals(property_dict['contributor'], 'person_module/john')
705 706 707 708
    # reference from filename (the rest was checked some other place)
    self.assertEquals(context.getReference(), 'TEST')
    # short_title from content
    self.assertEquals(context.getShortTitle(), 'short')
709
    # title from metadata inside the document
710
    self.assertEquals(context.getTitle(), 'TEST-en-002')
711 712 713 714 715
    # contributors from user
    self.assertEquals(context.getContributor(), 'person_module/john')

  def stepEditMetadata(self, sequence=None, sequence_list=None, **kw):
    """
716
      we change metadata in a document which has ODF
717
    """
718
    context = self.getDocument('one')
719 720 721
    kw = dict(title='another title',
              subject='another subject',
              description='another description')
722
    context.edit(**kw)
723
    context.reindexObject(); get_transaction().commit();
Bartek Górny's avatar
Bartek Górny committed
724
    self.tic();
725 726 727 728 729 730 731 732

  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...
733
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
734
    newcontent = context.getBaseData()
735
    cs = cStringIO.StringIO()
736
    cs.write(_unpackData(newcontent))
737 738 739 740 741
    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')
742
    subject = xmlob.getElementsByTagName('meta:keyword')[0].childNodes[0].data
743 744 745 746 747 748 749 750 751
    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
    """
752 753
    format_list = ['rtf', 'doc', 'txt', 'sxw', 'sdw']
    self.ingestFormatList('one', format_list)
754 755 756 757 758 759

  def stepIngestSpreadsheetFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported spreadsheet formats
      make sure they are converted
    """
760 761
    format_list = ['xls', 'sxc', 'sdc']
    self.ingestFormatList('two', format_list)
762 763 764 765 766 767

  def stepIngestPresentationFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported presentation formats
      make sure they are converted
    """
768 769
    format_list = ['ppt', 'sxi', 'sdd']
    self.ingestFormatList('three', format_list)
770

771 772 773 774 775
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported PDF formats
      make sure they are converted
    """
776 777
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
778

779 780 781 782 783
  def stepIngestDrawingFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported presentation formats
      make sure they are converted
    """
784
    format_list = ['sxd',]
785
    self.ingestFormatList('four', format_list)
786

787
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
788
    """
789 790
      ingest all supported pdf formats
      make sure they are converted
791
    """
792 793
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
794 795 796 797 798

  def stepIngestImageFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported image formats
    """
799 800
    format_list = ['jpg', 'gif', 'bmp', 'png']
    self.ingestFormatList('six', format_list, 'Image')
801 802

  def stepCheckTextDocumentExportList(self, sequence=None, sequence_list=None, **kw):
803
    self.checkDocumentExportList('one', 'doc', ['pdf', 'doc', 'rtf', 'writer.html', 'txt'])
804 805

  def stepCheckSpreadsheetDocumentExportList(self, sequence=None, sequence_list=None, **kw):
806
    self.checkDocumentExportList('two', 'xls', ['csv', 'calc.html', 'xls', 'calc.pdf'])
807 808 809 810 811 812 813

  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'])

814
  def stepExportPDF(self, sequence=None, sequence_list=None, **kw):
815
    """
816
      Try to export PDF to text and HTML
817
    """
818
    document = self.getDocument('five')
819
    f = makeFileUpload('TEST-en-002.pdf')
820
    document.edit(file=f)
821 822 823 824 825 826
    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')
827 828

  def stepExportImage(self, sequence=None, sequence_list=None, **kw):
829 830 831 832 833
    """
      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
    """
834
    printAndLog('stepExportImage not implemented')
835

836
  def stepCheckHasSnapshot(self, sequence=None, sequence_list=None, **kw):
837
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
838
    self.failUnless(context.hasSnapshotData())
839 840

  def stepCheckHasNoSnapshot(self, sequence=None, sequence_list=None, **kw):
841
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
842
    self.failIf(context.hasSnapshotData())
843 844

  def stepCreateSnapshot(self, sequence=None, sequence_list=None, **kw):
845
    context = self.getDocument('one')
846 847 848
    context.createSnapshot()

  def stepTryRecreateSnapshot(self, sequence=None, sequence_list=None, **kw):
849
    context = self.getDocument('one')
850 851 852 853
    # XXX this always fails, don't know why
    #self.assertRaises(ConversionError, context.createSnapshot)

  def stepDeleteSnapshot(self, sequence=None, sequence_list=None, **kw):
854
    context = self.getDocument('one')
855 856
    context.deleteSnapshot()

857 858 859 860 861
  def stepCleanUp(self, sequence=None, sequence_list=None, **kw):
    """
        Clean up DMS system from old content.
    """
    portal = self.getPortal()
862
    for module in (portal.document_module, portal.image_module, portal.document_ingestion_module):
863 864
      module.manage_delObjects(map(None, module.objectIds()))
    
Bartek Górny's avatar
Bartek Górny committed
865
  def stepContributeFileListWithType(self, sequence=None, sequence_list=None, **kw):
866 867 868 869
    """
      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
870
    self.contributeFileList(with_portal_type=True)
871

Bartek Górny's avatar
Bartek Górny committed
872
  def stepContributeFileListWithNoType(self, sequence=None, sequence_list=None, **kw):
873 874 875 876
    """
      Contribute all kinds of files
      let the system figure out portal type by itself
    """
Bartek Górny's avatar
Bartek Górny committed
877
    self.contributeFileList(with_portal_type=False)
878

879
  def stepSetSimulatedDiscoveryScriptForOrdering(self, sequence=None, sequence_list=None, **kw):
880 881 882 883 884 885 886 887 888 889
    """
      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
    """
890 891
    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'}")
892

Bartek Górny's avatar
Bartek Górny committed
893
  def stepCheckMetadataSettingOrderFICU(self, sequence=None, sequence_list=None, **kw):
894 895
    """
     This is the default
896
    """  
897
    expected_metadata = dict(reference='TEST', language='en', version='002', short_title='from_input', contributor='person_module/james')
898 899
    self.setDiscoveryOrder(['file_name', 'input', 'content', 'user_login'])
    self.discoverMetadata()
900
    self.checkMetadataOrder(expected_metadata)
901 902 903 904 905

  def stepCheckMetadataSettingOrderCUFI(self, sequence=None, sequence_list=None, **kw):
    """
     Content - User - Filename - Input
    """
906
    expected_metadata = dict(reference='CONT', language='us', version='003', short_title='from_content', contributor='person_module/jack')
907 908
    self.setDiscoveryOrder(['content', 'user_login', 'file_name', 'input'])
    self.discoverMetadata()
909
    self.checkMetadataOrder(expected_metadata)
910 911 912 913 914

  def stepCheckMetadataSettingOrderUIFC(self, sequence=None, sequence_list=None, **kw):
    """
     User - Input - Filename - Content
    """
915
    expected_metadata = dict(reference='USER', language='us', version='004', short_title='from_input', contributor='person_module/john')
916 917
    self.setDiscoveryOrder(['user_login', 'input', 'file_name', 'content'])
    self.discoverMetadata()
918
    self.checkMetadataOrder(expected_metadata)
919 920 921 922 923

  def stepCheckMetadataSettingOrderICUF(self, sequence=None, sequence_list=None, **kw):
    """
     Input - Content - User - Filename
    """
924
    expected_metadata = dict(reference='INPUT', language='in', version='004', short_title='from_input', contributor='person_module/james')
925 926
    self.setDiscoveryOrder(['input', 'content', 'user_login', 'file_name'])
    self.discoverMetadata()
927
    self.checkMetadataOrder(expected_metadata)
928 929 930 931 932

  def stepCheckMetadataSettingOrderUFCI(self, sequence=None, sequence_list=None, **kw):
    """
     User - Filename - Content - Input
    """
933
    expected_metadata = dict(reference='USER', language='us', version='002', short_title='from_content', contributor='person_module/john')
934 935
    self.setDiscoveryOrder(['user_login', 'file_name', 'content', 'input'])
    self.discoverMetadata()
936
    self.checkMetadataOrder(expected_metadata)
937

938
  def stepReceiveEmailFromUnknown(self, sequence=None, sequence_list=None, **kw):
939 940 941 942
    """
      email was sent in by someone who is not in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
943 944 945
    document = self.receiveEmail(data=f.read())
    get_transaction().commit()
    self.tic()
946 947

  def stepReceiveEmailFromJohn(self, sequence=None, sequence_list=None, **kw):
948 949 950 951
    """
      email was sent in by someone who is in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
952
    document = self.receiveEmail(f.read())
953 954
    get_transaction().commit()
    self.tic()
955 956

  def stepVerifyEmailedDocuments(self, sequence=None, sequence_list=None, **kw):
957 958 959 960
    """
      find the newly mailed-in document by its reference
      check its properties
    """
961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978
    # 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())

979

980 981 982 983 984
  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)
985
  
986 987 988 989
  ##################################
  ##  Tests
  ##################################

990
  def test_01_PreferenceSetup(self, quiet=QUIET, run=RUN_ALL_TEST):
991 992 993
    """
      Make sure that preferences are set up properly and accessible
    """
994
    if not run: return
995 996 997 998
    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])
999 1000 1001
    self.assertEquals(preference_tool.getPreferredDocumentFileNameRegularExpression(), FILE_NAME_REGULAR_EXPRESSION)
    self.assertEquals(preference_tool.getPreferredDocumentReferenceRegularExpression(), REFERENCE_REGULAR_EXPRESSION)
    
1002
  def test_02_FileExtensionRegistry(self, quiet=QUIET, run=RUN_ALL_TEST):
1003 1004 1005
    """
      check if we successfully imported registry
      and that it has all the entries we need
1006
    """
1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026
    if not run: return
    if not quiet: printAndLog('test_02_FileExtensionRegistry')
    reg = self.portal.content_type_registry
    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',
1027
            'sxd' : 'Drawing',
1028 1029 1030 1031 1032 1033
            'xxx' : 'File',
          }
    for type, portal_type in correct_type_mapping.items():
      file_name = 'aaa.' + type
      self.assertEquals(reg.findTypeName(file_name, None, None), portal_type)

1034
  def test_03_TextDoc(self, quiet=QUIET, run=RUN_ALL_TEST):
1035
    """
1036
      Test basic behaviour of a document:
1037
      - create empty document
1038 1039 1040 1041 1042
      - 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
1043 1044
    """
    if not run: return
1045
    if not quiet: printAndLog('test_03_TextDoc')
1046 1047
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1048
                 ,'stepCheckEmptyState'
1049
                 ,'stepStraightUpload'
1050 1051
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1052
                 ,'stepCheckConvertedState'
1053 1054 1055
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1056 1057
                 ,'stepCheckConvertedState'
                ]
1058
    self.playSequence(step_list, quiet)
1059

1060
  def test_04_MetadataExtraction(self, quiet=QUIET, run=RUN_ALL_TEST):
1061 1062
    """
      Test metadata extraction from various sources:
1063 1064 1065 1066 1067
      - 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)
1068
      - from file metadata
1069 1070 1071 1072

      NOTE: metadata of document (title, subject, description)
      are no longer retrieved and set upon conversion
    """
1073
    if not run: return
1074
    if not quiet: printAndLog('test_04_MetadataExtraction')
1075
    step_list = [ 'stepCleanUp'
1076
                 ,'stepUploadTextFromContributionTool'
1077
                 ,'stepSetSimulatedDiscoveryScript'
1078
                 ,'stepTic'
1079 1080
                 ,'stepTestMetadataSetting'
                ]
1081
    self.playSequence(step_list, quiet)
1082

1083
  def test_041_MetadataEditing(self, quiet=QUIET, run=RUN_ALL_TEST):
1084 1085 1086 1087 1088 1089
    """
      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
1090
    if not quiet: printAndLog('test_04_MetadataEditing')
1091 1092
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1093 1094 1095 1096
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1097 1098
                 ,'stepEditMetadata'
                 ,'stepCheckChangedMetadata'
1099
                ]
1100
    self.playSequence(step_list, quiet)
1101

1102 1103 1104 1105 1106
  def test_05_FormatIngestion(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Ingest various formats (xls, doc, sxi, ppt etc)
      Verify that they are successfully converted
      - have ODF data and contain magic word in SearchableText
1107 1108 1109 1110 1111
      - 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.
1112 1113
    """
    if not run: return
1114
    if not quiet: printAndLog('test_05_FormatIngestion')
1115 1116
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1117 1118 1119 1120 1121 1122 1123
                 ,'stepIngestTextFormats'
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepIngestSpreadsheetFormats'
                 ,'stepCreatePresentationDocument'
                 ,'stepIngestPresentationFormats'
                 ,'stepCreateDrawingDocument'
                 ,'stepIngestDrawingFormats'
1124 1125 1126 1127
                 ,'stepCreatePDFDocument'
                 ,'stepIngestPDFFormats'
                 ,'stepCreateImageDocument'
                 ,'stepIngestImageFormats'
1128
                ]
1129
    self.playSequence(step_list, quiet)
1130

1131
  def test_06_FormatGeneration(self, quiet=QUIET, run=RUN_ALL_TEST):
1132
    """
1133 1134 1135 1136
      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
1137 1138
    """
    if not run: return
1139
    if not quiet: printAndLog('test_06_FormatGeneration')
1140 1141
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1142 1143 1144 1145 1146 1147 1148
                 ,'stepCheckTextDocumentExportList'
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepCheckSpreadsheetDocumentExportList'
                 ,'stepCreatePresentationDocument'
                 ,'stepCheckPresentationDocumentExportList'
                 ,'stepCreateDrawingDocument'
                 ,'stepCheckDrawingDocumentExportList'
1149 1150 1151 1152
                 ,'stepCreatePDFDocument'
                 ,'stepExportPDF'
                 ,'stepCreateImageDocument'
                 ,'stepExportImage'
1153
                ]
1154
    self.playSequence(step_list, quiet)
1155 1156 1157 1158 1159 1160 1161 1162

  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
1163
    if not quiet: printAndLog('test_07_SnapshotGeneration')
1164 1165
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1166 1167 1168 1169
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1170 1171 1172 1173 1174 1175 1176 1177
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                 ,'stepTryRecreateSnapshot'
                 ,'stepCheckHasSnapshot'
                 ,'stepDeleteSnapshot'
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                ]
1178
    self.playSequence(step_list, quiet)
1179

1180 1181
  def test_08_Cache(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1182
      I don't know how to verify how cache works
1183 1184
    """

1185
  def test_09_Contribute(self, quiet=QUIET, run=RUN_ALL_TEST):
1186 1187 1188 1189 1190 1191 1192 1193 1194 1195
    """
      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
1196
    if not quiet: printAndLog('test_09_Contribute')
1197 1198
    step_list = [ 'stepCleanUp'
                 ,'stepContributeFileListWithNoType'
1199
                 ,'stepCleanUp'
Bartek Górny's avatar
Bartek Górny committed
1200
                 ,'stepContributeFileListWithType'
1201
                ]
1202
    self.playSequence(step_list, quiet)
1203 1204 1205

  def test_10_MetadataSettingPreferenceOrder(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1206
      Set some metadata discovery scripts
1207
      Contribute a document, let it get metadata using default setup
1208 1209 1210
      (default is FUC)

      check that the right ones are there
1211 1212
      change preference order, check again
    """
1213
    if not run: return
1214
    if not quiet: printAndLog('test_10_MetadataSettingPreferenceOrder')
1215 1216
    step_list = [ 'stepCleanUp' 
                 ,'stepCreateTextDocument'
1217
                 ,'stepStraightUpload'
1218 1219 1220
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1221
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
Bartek Górny's avatar
Bartek Górny committed
1222
                 ,'stepCheckMetadataSettingOrderFICU'
1223 1224
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1225 1226 1227
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1228
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1229 1230 1231
                 ,'stepCheckMetadataSettingOrderCUFI'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1232 1233 1234
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1235
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1236 1237 1238
                 ,'stepCheckMetadataSettingOrderUIFC'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1239 1240 1241
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1242
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1243 1244 1245
                 ,'stepCheckMetadataSettingOrderICUF'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1246 1247 1248
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1249
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1250 1251
                 ,'stepCheckMetadataSettingOrderUFCI'
                ]
1252
    self.playSequence(step_list, quiet)
1253

1254 1255 1256 1257 1258 1259 1260
  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
1261
    if not quiet: printAndLog('test_11_EmailIngestion')
1262 1263
    step_list = [ 'stepCleanUp'
                 ,'stepReceiveEmailFromUnknown'
1264 1265 1266 1267
                 ,'stepCreatePerson'
                 ,'stepReceiveEmailFromJohn'
                 ,'stepVerifyEmailedDocuments'
                ]
1268
    self.playSequence(step_list, quiet)
1269

1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
  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)
1289

1290 1291 1292 1293
# Missing tests
"""
    property_dict = context.getPropertyDictFromUserLogin()
    property_dict = context.getPropertyDictFromInput()
1294
"""
Jérome Perrin's avatar
Jérome Perrin committed
1295 1296 1297 1298 1299

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