testIngestion.py 54.2 KB
Newer Older
1
##############################################################################
2
# -*- coding: utf-8 -*-
3
#
4 5 6
# Copyright (c) 2007 Nexedi SA and Contributors. All Rights Reserved.
#                    Bartek Gorny <bg@erp5.pl>
#                    Jean-Paul Smets <jp@nexedi.com>
7
#                    Ivan Tyagov <ivan@nexedi.com>
8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
#
# 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
32 33
import unittest
import os, cStringIO, zipfile
34
from xml.dom.minidom import parseString
35
import transaction
36 37
from Testing import ZopeTestCase
from DateTime import DateTime
38
from AccessControl.SecurityManagement import newSecurityManager
39 40 41
from Products.ERP5Type.Utils import convertToUpperCase
from Products.ERP5Type.tests.ERP5TypeTestCase import ERP5TypeTestCase
from Products.ERP5Type.tests.Sequence import SequenceList
42
from Products.ERP5Type.tests.utils import FileUpload
43
from Products.ERP5OOo.Document.OOoDocument import ConversionError
44
from Products.ERP5.Document.File import _unpackData
45
from zLOG import LOG, INFO, ERROR
46

47 48
# Define the conversion server host
conversion_server_host = ('127.0.0.1', 8008)
49

50
# test files' home
51
TEST_FILES_HOME = os.path.join(os.path.dirname(__file__), 'test_document')
52 53
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}))?"
54

55 56 57 58 59 60
def printAndLog(msg):
  """
  A utility function to print a message
  to the standard output and to the LOG
  at the same time
  """
61 62 63 64
  msg = str(msg)
  ZopeTestCase._print('\n ' + msg)
  LOG('Testing... ', 0, msg)

65 66

def makeFilePath(name):
67
  return os.path.join(TEST_FILES_HOME, name)
68

69 70 71
def makeFileUpload(name, as_name=None):
  if as_name is None:
    as_name = name
72
  path = makeFilePath(name)
73
  return FileUpload(path, as_name)
74 75 76 77 78 79 80

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

  # pseudo constants
81
  RUN_ALL_TEST = 1
82 83 84 85 86 87 88 89 90 91
  QUIET = 0

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

  def getTitle(self):
    """
      Return the title of the current test set.
    """
92
    return "ERP5 DMS - Ingestion"
93 94 95 96 97

  def getBusinessTemplateList(self):
    """
      Return the list of required business templates.
    """
98 99
    return ('erp5_base',
            'erp5_ingestion', 'erp5_ingestion_mysql_innodb_catalog',
100
            'erp5_web', 'erp5_crm', 'erp5_dms')
101 102 103 104 105 106

  def afterSetUp(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Initialize the ERP5 site.
    """
    self.login()
107 108
    self.datetime = DateTime()
    self.portal = self.getPortal()
109
    self.portal_categories = self.getCategoryTool()
110 111 112
    self.portal_catalog = self.getCatalogTool()
    self.createDefaultCategoryList()
    self.setSystemPreference()
113
    self.setSimulatedNotificationScript()
114
    self.setTools()
115

116 117 118
  def beforeTearDown(self):
    self.portal.portal_caches.clearAllCache()

119
  def setSystemPreference(self):
120
    default_pref = self.portal.portal_preferences.default_site_preference
121 122
    default_pref.setPreferredOoodocServerAddress(conversion_server_host[0])
    default_pref.setPreferredOoodocServerPortNumber(conversion_server_host[1])
123 124
    default_pref.setPreferredDocumentFileNameRegularExpression(FILE_NAME_REGULAR_EXPRESSION)
    default_pref.setPreferredDocumentReferenceRegularExpression(REFERENCE_REGULAR_EXPRESSION)
125 126
    if default_pref.getPreferenceState() != 'global':
      default_pref.enable()
127

128 129 130 131 132 133 134 135 136 137 138 139
  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')

140 141 142 143 144 145 146
  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')
147 148 149 150 151 152 153 154 155

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

  def login(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
      Create a new manager user and login.
    """
156
    user_name = 'dms_user'
157
    user_folder = self.portal.acl_users
158 159 160 161
    user_folder._doAddUser(user_name, '', ['Manager', 'Owner', 'Assignor'], [])
    user = user_folder.getUserById(user_name).__of__(user_folder)
    newSecurityManager(None, user)

162
  def createDefaultCategoryList(self):
163
    """
164 165 166 167 168 169
      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.
170 171 172 173 174 175
    """
    self.category_list = [
                         # Role categories
                          {'path' : 'role/internal'
                           ,'title': 'Internal'
                           }
176 177 178 179 180 181 182 183 184
                          ,{'path' : 'function/musician/wind/saxophone'
                           ,'title': 'Saxophone'
                           }
                          ,{'path' : 'group/medium'
                           ,'title': 'Medium'
                           }
                          ,{'path' : 'site/arctic/spitsbergen'
                           ,'title': 'Spitsbergen'
                           }
185 186 187
                          ,{'path' : 'group/anybody'
                           ,'title': 'Anybody'
                           }
188 189 190 191 192 193
                          ,{'path' : 'publication_section/cop'
                           ,'title': 'COPs'
                           }
                          ,{'path' : 'publication_section/cop/one'
                           ,'title': 'COP one'
                           }
194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
                         ]

    # 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'))
229
    transaction.commit()
230
    self.tic()
231 232 233 234 235 236

  def getCategoryList(self, base_category=None):
    """
      Get a list of categories with same base categories.
    """
    categories = []
237
    if base_category is not None:
238 239 240 241 242
      for category in self.category_list:
        if category["path"].split('/')[0] == base_category:
          categories.append(category)
    return categories

243
  def getDocument(self, id):
244 245 246 247 248 249
    """
      Returns a document with given ID in the
      document module.
    """
    document_module = self.portal.document_module
    return getattr(document_module, id)
250

251
  def checkIsObjectCatalogged(self, portal_type, **kw):
252
    """
253 254 255 256 257
      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.
258
    """
259
    res = self.portal_catalog(portal_type=portal_type, **kw.copy())
260
    self.assertEquals(len(res), 1)
261 262
    for key, value in kw.items():
      self.assertEquals(res[0].getProperty(key), value)
263

264
  def newEmptyCataloggedDocument(self, portal_type, id):
265
    """
266 267 268 269 270 271
      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.
272
    """
273 274 275 276 277 278
    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()
279
    transaction.commit()
280 281 282 283
    self.tic()
    self.checkIsObjectCatalogged(portal_type, id=id, parent_uid=document_module.getUid())
    self.assert_(hasattr(document_module, id))
    return document
284

285
  def ingestFormatList(self, document_id, format_list, portal_type=None):
286
    """
287 288 289 290 291 292 293 294 295
      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.
296 297
    """
    if portal_type is None:
298
      document_module = self.portal.document_module
299
    else:
300 301 302
      document_module = self.portal.getDefaultModule(portal_type)
    context = getattr(document_module, document_id)
    for revision, format in enumerate(format_list):
303
      filename = 'TEST-en-002.' + format
304
      printAndLog('Ingesting file: ' + filename)
305 306
      f = makeFileUpload(filename)
      context.edit(file=f)
307
      context.reindexObject()
308
      transaction.commit()
309
      self.tic()
310
      self.failUnless(context.hasFile())
311
      if context.getPortalType() in ('Image', 'File', 'PDF'):
312
        # File and images do not support conversion to text in DMS
313
        # PDF has not implemented _convertToBaseFormat() so can not be converted
314 315 316 317
        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())
318
        self.assert_('magic' in str(context.asText()))
319

320
  def checkDocumentExportList(self, document_id, format, asserted_target_list):
321
    """
322 323 324
      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
325
    """
326
    context = self.getDocument(document_id)
327 328 329
    filename = 'TEST-en-002.' + format
    f = makeFileUpload(filename)
    context.edit(file=f)
330
    context.reindexObject()
331
    transaction.commit()
332
    self.tic()
333 334
    # We call clear cache to be sure that the target list is updated
    self.getPortal().portal_caches.clearCache()
335 336
    target_list = context.getTargetFormatList()
    for target in asserted_target_list:
337 338
      self.assert_(target in target_list)

Bartek Górny's avatar
Bartek Górny committed
339
  def contributeFileList(self, with_portal_type=False):
340
    """
341 342 343
      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
344 345
      on portal_contributions.
      http://framework.openoffice.org/documentation/mimetypes/mimetypes.html
346
    """
347 348 349 350
    created_documents = []
    extension_to_type = (('ppt', 'Presentation')
                        ,('doc', 'Text')
                        ,('sdc', 'Spreadsheet')
351
                        ,('sxc', 'Spreadsheet')
352 353 354 355
                        ,('pdf', 'PDF')
                        ,('jpg', 'Image')
                        ,('py', 'File')
                        )
356 357
    counter = 1
    old_portal_type = ''
358 359
    for extension, portal_type in extension_to_type:
      filename = 'TEST-en-002.' + extension
360
      printAndLog(filename)
361
      file = makeFileUpload(filename)
362 363 364 365 366 367 368
      # 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)
369
      if with_portal_type:
370
        ob = self.portal.portal_contributions.newContent(portal_type=portal_type, file=file)
371 372
      else:
        ob = self.portal.portal_contributions.newContent(file=file)
373
      # reindex
374 375
      ob.immediateReindexObject()
      created_documents.append(ob)
376
    transaction.commit()
377 378 379 380 381 382
    self.tic()
    # inspect created objects
    count = 0
    for extension, portal_type in extension_to_type:
      ob = created_documents[count]
      count+=1
383
      self.assertEquals(ob.getPortalType(), portal_type)
384
      self.assertEquals(ob.getReference(), 'TEST')
385 386
      if ob.getPortalType() in ('Image', 'File', 'PDF'):
        # Image, File and PDF are not converted to a base format
387 388
        self.assertEquals(ob.getExternalProcessingState(), 'uploaded')
      else:
389 390 391
        # We check if conversion has succeeded by looking
        # at the external_processing workflow
        self.assertEquals(ob.getExternalProcessingState(), 'converted')
392
        self.assert_('magic' in ob.SearchableText())
393 394 395 396 397 398

  def newPythonScript(self, object_id, script_id, argument_list, code):
    """
      Creates a new python script with given argument_list
      and source code.
    """
399 400 401 402
    context = self.getDocument(object_id)
    factory = context.manage_addProduct['PythonScripts'].manage_addPythonScript
    factory(id=script_id)
    script = getattr(context, script_id)
403
    script.ZPythonScript_edit(argument_list, code)
404

405
  def setDiscoveryOrder(self, order, id='one'):
406
    """
407 408
      Creates a script to define the metadata discovery order
      for Text documents.
409 410
    """
    script_code = "return %s" % str(order)
411
    self.newPythonScript(id, 'Text_getPreferredDocumentMetadataDiscoveryOrderList', '', script_code)
412
    
413 414 415 416 417 418
  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)
419 420 421 422 423
    # simulate user input
    context._backup_input = dict(reference='INPUT', 
                                 language='in',
                                 version='004', 
                                 short_title='from_input',
424
                                 contributor='person_module/james')
425 426
    # pass to discovery file_name and user_login
    context.discoverMetadata(context.getSourceReference(), 'john_doe') 
427
    context.reindexObject()
428
    transaction.commit()
429
    self.tic()
430

431 432 433 434 435 436 437
  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():
438
      self.assertEquals(context.getProperty(k), v)
439

440 441 442 443 444 445 446 447 448
  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)

449 450 451
  ##################################
  ##  Basic steps
  ##################################
452 453 454
 
  def stepTic(self, sequence=None, sequence_list=None, **kw):
    self.tic()
455 456 457

  def stepCreatePerson(self, sequence=None, sequence_list=None, **kw):
    """
458
      Create a person with ID "john" if it does not exists already
459 460
    """
    portal_type = 'Person'
461
    person_id = 'john'
462
    reference = 'john_doe'
463
    person_module = self.portal.person_module
464 465 466 467 468 469 470 471
    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'
                                      )
472
    person.setDefaultEmailText('john@doe.com')
473
    person.reindexObject()
474
    transaction.commit()
475
    self.tic()
476 477 478

  def stepCreateTextDocument(self, sequence=None, sequence_list=None, **kw):
    """
479 480
      Create an empty Text document with ID 'one'
      This document will be used in most tests.
481
    """
482
    self.newEmptyCataloggedDocument('Text', 'one')
483

484 485
  def stepCreateSpreadsheetDocument(self, sequence=None, sequence_list=None, **kw):
    """
486 487
      Create an empty Spreadsheet document with ID 'two'
      This document will be used in most tests.
488
    """
489
    self.newEmptyCataloggedDocument('Spreadsheet', 'two')
490 491 492

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

  def stepCreateDrawingDocument(self, sequence=None, sequence_list=None, **kw):
    """
500 501
      Create an empty Drawing document with ID 'four'
      This document will be used in most tests.
502
    """
503
    self.newEmptyCataloggedDocument('Drawing', 'four')
504

505 506
  def stepCreatePDFDocument(self, sequence=None, sequence_list=None, **kw):
    """
507 508
      Create an empty PDF document with ID 'five'
      This document will be used in most tests.
509
    """
510
    self.newEmptyCataloggedDocument('PDF', 'five')
511 512 513

  def stepCreateImageDocument(self, sequence=None, sequence_list=None, **kw):
    """
514 515
      Create an empty Image document with ID 'six'
      This document will be used in most tests.
516
    """
517
    self.newEmptyCataloggedDocument('Image', 'six')
518

519 520
  def stepCheckEmptyState(self, sequence=None, sequence_list=None, **kw):
    """
521 522
      Check if the document is in "empty" processing state
      (ie. no file upload has been done yet)
523
    """
524
    context = self.getDocument('one')
525 526 527 528
    return self.assertEquals(context.getExternalProcessingState(), 'empty')

  def stepCheckUploadedState(self, sequence=None, sequence_list=None, **kw):
    """
529 530
      Check if the document is in "uploaded" processing state
      (ie. a file upload has been done)
531
    """
532
    context = self.getDocument('one')
533 534
    return self.assertEquals(context.getExternalProcessingState(), 'uploaded')

535 536 537 538 539 540 541 542
  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')

543 544
  def stepCheckConvertedState(self, sequence=None, sequence_list=None, **kw):
    """
545
      Check if the document is in "converted" processing state
546
      (ie. a file conversion has been done and the document has
547
      been converted)
548
    """
549
    context = self.getDocument('one')
550 551
    return self.assertEquals(context.getExternalProcessingState(), 'converted')

552 553 554 555 556
  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
    """
557
    filename = 'TEST-en-002.doc'
558
    document = self.getDocument('one')
Julien Muchembled's avatar
Julien Muchembled committed
559 560
    # First revision is 1 (like web pages)
    self.assertEquals(document.getRevision(), '1')
561
    f = makeFileUpload(filename)
562
    document.edit(file=f)
563 564
    # set source
    document.setSourceReference(filename)
565
    self.assert_(document.hasFile())
566 567
    # source_reference set to file name ?
    self.assertEquals(document.getSourceReference(), filename) 
568
    # Revision is 1 after upload (revisions are strings)
Julien Muchembled's avatar
Julien Muchembled committed
569
    self.assertEquals(document.getRevision(), '2')
570
    document.reindexObject()
571
    transaction.commit()
572

573
  def stepUploadFromViewForm(self, sequence=None, sequence_list=None, **kw):
574
    """
575
      Upload a file from view form and make sure this increases the revision
576
    """
577
    context = self.getDocument('one')
578
    f = makeFileUpload('TEST-en-002.doc')
579
    revision = context.getRevision()
580 581 582
    context.edit(file=f)
    self.assertEquals(context.getRevision(), str(int(revision) + 1))
    context.reindexObject()
583
    transaction.commit()
584 585 586 587 588 589 590

  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)
591
    transaction.commit()
592 593 594 595 596 597 598 599 600 601 602 603 604 605 606

  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)
607
    transaction.commit()
608
    self.tic()
609
    transaction.commit()
610
    self.assertEquals(context.getRevision(), str(int(revision) + 1))
611 612 613 614
    self.assert_('This document is modified.' in context.asText())
    self.assertEquals(len(self.portal.document_module.objectIds()),
                      number_of_document)

615
    context.reindexObject()
616
    transaction.commit()
617 618 619 620 621 622 623 624

  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)

625
    transaction.commit()
626
    self.tic()
627
    transaction.commit()
628 629 630 631 632 633

    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')
634 635 636

  def stepDiscoverFromFilename(self, sequence=None, sequence_list=None, **kw):
    """
637 638 639
      Upload a file using contribution tool. This should trigger metadata
      discovery and we should have basic coordinates immediately,
      from first stage.
640
    """
641
    context = self.getDocument('one')
642 643 644 645 646 647 648 649 650 651 652 653 654 655
    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)
656
    context.edit(file=f)
657 658 659
    self.assertEquals(context.getReference(), 'TEST')
    self.assertEquals(context.getLanguage(), 'en')
    self.assertEquals(context.getVersion(), '002')
660
    self.assertEquals(context.getSourceReference(), file_name)
661

662 663
  def stepCheckConvertedContent(self, sequence=None, sequence_list=None, **kw):
    """
664 665 666
      Check that the input file was successfully converted
      and that its SearchableText and asText contain
      the word "magic"
667 668
    """
    self.tic()
669
    context = self.getDocument('one')
670
    self.assert_(context.hasBaseData())
671
    self.assert_('magic' in context.SearchableText())
672
    self.assert_('magic' in str(context.asText()))
673

674
  def stepSetSimulatedDiscoveryScript(self, sequence=None, sequence_list=None, **kw):
675 676 677 678
    """
      Create Text_getPropertyDictFrom[source] scripts
      to simulate custom site's configuration
    """
679 680 681
    self.newPythonScript('one', 'Text_getPropertyDictFromUserLogin',
                         'user_name=None', "return {'contributor':'person_module/john'}")
    self.newPythonScript('one', 'Text_getPropertyDictFromContent', '',
682
                         "return {'short_title':'short', 'title':'title', 'contributor':'person_module/john',}")
683 684 685 686 687 688

  def stepTestMetadataSetting(self, sequence=None, sequence_list=None, **kw):
    """
      Upload with custom getPropertyDict methods
      check that all metadata are correct
    """
689
    context = self.getDocument('one')
690
    f = makeFileUpload('TEST-en-002.doc')
691
    context.edit(file=f)
692
    transaction.commit()
693
    self.tic()
694 695 696
    # Then make sure content discover works
    property_dict = context.getPropertyDictFromUserLogin()
    self.assertEquals(property_dict['contributor'], 'person_module/john')
697 698 699 700
    # reference from filename (the rest was checked some other place)
    self.assertEquals(context.getReference(), 'TEST')
    # short_title from content
    self.assertEquals(context.getShortTitle(), 'short')
701
    # title from metadata inside the document
702
    self.assertEquals(context.getTitle(),  'title')
703 704 705 706 707
    # contributors from user
    self.assertEquals(context.getContributor(), 'person_module/john')

  def stepEditMetadata(self, sequence=None, sequence_list=None, **kw):
    """
708
      we change metadata in a document which has ODF
709
    """
710
    context = self.getDocument('one')
711 712 713
    kw = dict(title='another title',
              subject='another subject',
              description='another description')
714
    context.edit(**kw)
715
    context.reindexObject(); transaction.commit();
Bartek Górny's avatar
Bartek Górny committed
716
    self.tic();
717 718 719 720 721 722 723 724

  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...
725
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
726
    newcontent = context.getBaseData()
727
    cs = cStringIO.StringIO()
728
    cs.write(_unpackData(newcontent))
729 730 731 732 733
    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')
734
    subject = xmlob.getElementsByTagName('meta:keyword')[0].childNodes[0].data
735 736 737 738 739 740 741 742 743
    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
    """
744 745
    format_list = ['rtf', 'doc', 'txt', 'sxw', 'sdw']
    self.ingestFormatList('one', format_list)
746 747 748 749 750 751

  def stepIngestSpreadsheetFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported spreadsheet formats
      make sure they are converted
    """
752 753
    format_list = ['xls', 'sxc', 'sdc']
    self.ingestFormatList('two', format_list)
754 755 756 757 758 759

  def stepIngestPresentationFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported presentation formats
      make sure they are converted
    """
760 761
    format_list = ['ppt', 'sxi', 'sdd']
    self.ingestFormatList('three', format_list)
762

763 764 765 766 767
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported PDF formats
      make sure they are converted
    """
768 769
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
770

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

779
  def stepIngestPDFFormats(self, sequence=None, sequence_list=None, **kw):
780
    """
781 782
      ingest all supported pdf formats
      make sure they are converted
783
    """
784 785
    format_list = ['pdf']
    self.ingestFormatList('five', format_list)
786 787 788 789 790

  def stepIngestImageFormats(self, sequence=None, sequence_list=None, **kw):
    """
      ingest all supported image formats
    """
791 792
    format_list = ['jpg', 'gif', 'bmp', 'png']
    self.ingestFormatList('six', format_list, 'Image')
793 794

  def stepCheckTextDocumentExportList(self, sequence=None, sequence_list=None, **kw):
795
    self.checkDocumentExportList('one', 'doc', ['pdf', 'doc', 'rtf', 'writer.html', 'txt'])
796 797

  def stepCheckSpreadsheetDocumentExportList(self, sequence=None, sequence_list=None, **kw):
798
    self.checkDocumentExportList('two', 'xls', ['csv', 'calc.html', 'xls', 'calc.pdf'])
799 800 801 802 803 804 805

  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'])

806
  def stepExportPDF(self, sequence=None, sequence_list=None, **kw):
807
    """
808
      Try to export PDF to text and HTML
809
    """
810
    document = self.getDocument('five')
811
    f = makeFileUpload('TEST-en-002.pdf')
812
    document.edit(file=f)
813 814 815 816 817 818
    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')
819 820

  def stepExportImage(self, sequence=None, sequence_list=None, **kw):
821 822 823 824 825
    """
      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
    """
826
    printAndLog('stepExportImage not implemented')
827

828
  def stepCheckHasSnapshot(self, sequence=None, sequence_list=None, **kw):
829
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
830
    self.failUnless(context.hasSnapshotData())
831 832

  def stepCheckHasNoSnapshot(self, sequence=None, sequence_list=None, **kw):
833
    context = self.getDocument('one')
Bartek Górny's avatar
Bartek Górny committed
834
    self.failIf(context.hasSnapshotData())
835 836

  def stepCreateSnapshot(self, sequence=None, sequence_list=None, **kw):
837
    context = self.getDocument('one')
838 839 840
    context.createSnapshot()

  def stepTryRecreateSnapshot(self, sequence=None, sequence_list=None, **kw):
841
    context = self.getDocument('one')
842 843 844 845
    # XXX this always fails, don't know why
    #self.assertRaises(ConversionError, context.createSnapshot)

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

849 850 851 852 853
  def stepCleanUp(self, sequence=None, sequence_list=None, **kw):
    """
        Clean up DMS system from old content.
    """
    portal = self.getPortal()
854
    for module in (portal.document_module, portal.image_module, portal.document_ingestion_module):
855 856
      module.manage_delObjects(map(None, module.objectIds()))
    
Bartek Górny's avatar
Bartek Górny committed
857
  def stepContributeFileListWithType(self, sequence=None, sequence_list=None, **kw):
858 859 860 861
    """
      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
862
    self.contributeFileList(with_portal_type=True)
863

Bartek Górny's avatar
Bartek Górny committed
864
  def stepContributeFileListWithNoType(self, sequence=None, sequence_list=None, **kw):
865 866 867 868
    """
      Contribute all kinds of files
      let the system figure out portal type by itself
    """
Bartek Górny's avatar
Bartek Górny committed
869
    self.contributeFileList(with_portal_type=False)
870

871
  def stepSetSimulatedDiscoveryScriptForOrdering(self, sequence=None, sequence_list=None, **kw):
872 873 874 875 876 877 878 879 880 881
    """
      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
    """
882 883
    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'}")
884

Bartek Górny's avatar
Bartek Górny committed
885
  def stepCheckMetadataSettingOrderFICU(self, sequence=None, sequence_list=None, **kw):
886 887
    """
     This is the default
888
    """  
889
    expected_metadata = dict(reference='TEST', language='en', version='002', short_title='from_input', contributor='person_module/james')
890 891
    self.setDiscoveryOrder(['file_name', 'input', 'content', 'user_login'])
    self.discoverMetadata()
892
    self.checkMetadataOrder(expected_metadata)
893 894 895 896 897

  def stepCheckMetadataSettingOrderCUFI(self, sequence=None, sequence_list=None, **kw):
    """
     Content - User - Filename - Input
    """
898
    expected_metadata = dict(reference='CONT', language='us', version='003', short_title='from_content', contributor='person_module/jack')
899 900
    self.setDiscoveryOrder(['content', 'user_login', 'file_name', 'input'])
    self.discoverMetadata()
901
    self.checkMetadataOrder(expected_metadata)
902 903 904 905 906

  def stepCheckMetadataSettingOrderUIFC(self, sequence=None, sequence_list=None, **kw):
    """
     User - Input - Filename - Content
    """
907
    expected_metadata = dict(reference='USER', language='us', version='004', short_title='from_input', contributor='person_module/john')
908 909
    self.setDiscoveryOrder(['user_login', 'input', 'file_name', 'content'])
    self.discoverMetadata()
910
    self.checkMetadataOrder(expected_metadata)
911 912 913 914 915

  def stepCheckMetadataSettingOrderICUF(self, sequence=None, sequence_list=None, **kw):
    """
     Input - Content - User - Filename
    """
916
    expected_metadata = dict(reference='INPUT', language='in', version='004', short_title='from_input', contributor='person_module/james')
917 918
    self.setDiscoveryOrder(['input', 'content', 'user_login', 'file_name'])
    self.discoverMetadata()
919
    self.checkMetadataOrder(expected_metadata)
920 921 922 923 924

  def stepCheckMetadataSettingOrderUFCI(self, sequence=None, sequence_list=None, **kw):
    """
     User - Filename - Content - Input
    """
925
    expected_metadata = dict(reference='USER', language='us', version='002', short_title='from_content', contributor='person_module/john')
926 927
    self.setDiscoveryOrder(['user_login', 'file_name', 'content', 'input'])
    self.discoverMetadata()
928
    self.checkMetadataOrder(expected_metadata)
929

930
  def stepReceiveEmailFromUnknown(self, sequence=None, sequence_list=None, **kw):
931 932 933 934
    """
      email was sent in by someone who is not in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
935
    document = self.receiveEmail(data=f.read())
936
    transaction.commit()
937
    self.tic()
938 939

  def stepReceiveEmailFromJohn(self, sequence=None, sequence_list=None, **kw):
940 941 942 943
    """
      email was sent in by someone who is in the person_module
    """
    f = open(makeFilePath('email_from.txt'))
944
    document = self.receiveEmail(f.read())
945
    transaction.commit()
946
    self.tic()
947 948

  def stepVerifyEmailedDocuments(self, sequence=None, sequence_list=None, **kw):
949 950 951 952
    """
      find the newly mailed-in document by its reference
      check its properties
    """
953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970
    # 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())

971

972 973 974 975 976
  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)
977
  
978 979 980 981
  ##################################
  ##  Tests
  ##################################

982
  def test_01_PreferenceSetup(self, quiet=QUIET, run=RUN_ALL_TEST):
983 984 985
    """
      Make sure that preferences are set up properly and accessible
    """
986
    if not run: return
987 988 989 990
    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])
991 992 993
    self.assertEquals(preference_tool.getPreferredDocumentFileNameRegularExpression(), FILE_NAME_REGULAR_EXPRESSION)
    self.assertEquals(preference_tool.getPreferredDocumentReferenceRegularExpression(), REFERENCE_REGULAR_EXPRESSION)
    
994
  def test_02_FileExtensionRegistry(self, quiet=QUIET, run=RUN_ALL_TEST):
995 996 997
    """
      check if we successfully imported registry
      and that it has all the entries we need
998
    """
999 1000
    if not run: return
    if not quiet: printAndLog('test_02_FileExtensionRegistry')
1001
    reg = self.portal.portal_contribution_registry
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018
    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',
1019
            'sxd' : 'Drawing',
1020 1021 1022 1023
            'xxx' : 'File',
          }
    for type, portal_type in correct_type_mapping.items():
      file_name = 'aaa.' + type
1024 1025
      self.assertEquals(reg.findPortalTypeName(file_name, None, None),
                        portal_type)
1026

1027
  def test_03_TextDoc(self, quiet=QUIET, run=RUN_ALL_TEST):
1028
    """
1029
      Test basic behaviour of a document:
1030
      - create empty document
1031 1032 1033 1034 1035
      - 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
1036 1037
    """
    if not run: return
1038
    if not quiet: printAndLog('test_03_TextDoc')
1039 1040
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1041
                 ,'stepCheckEmptyState'
1042
                 ,'stepStraightUpload'
1043 1044
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1045
                 ,'stepCheckConvertedState'
1046 1047 1048
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
1049 1050
                 ,'stepCheckConvertedState'
                ]
1051
    self.playSequence(step_list, quiet)
1052

1053
  def test_04_MetadataExtraction(self, quiet=QUIET, run=RUN_ALL_TEST):
1054 1055
    """
      Test metadata extraction from various sources:
1056 1057 1058 1059 1060
      - 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)
1061
      - from file metadata
1062 1063 1064 1065

      NOTE: metadata of document (title, subject, description)
      are no longer retrieved and set upon conversion
    """
1066
    if not run: return
1067
    if not quiet: printAndLog('test_04_MetadataExtraction')
1068
    step_list = [ 'stepCleanUp'
1069
                 ,'stepUploadTextFromContributionTool'
1070
                 ,'stepSetSimulatedDiscoveryScript'
1071
                 ,'stepTic'
1072 1073
                 ,'stepTestMetadataSetting'
                ]
1074
    self.playSequence(step_list, quiet)
1075

1076
  def test_041_MetadataEditing(self, quiet=QUIET, run=RUN_ALL_TEST):
1077 1078 1079 1080 1081 1082
    """
      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
1083
    if not quiet: printAndLog('test_04_MetadataEditing')
1084 1085
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1086 1087 1088 1089
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1090 1091
                 ,'stepEditMetadata'
                 ,'stepCheckChangedMetadata'
1092
                ]
1093
    self.playSequence(step_list, quiet)
1094

1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106


  #    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):
1107 1108
    step_list = ['stepCleanUp'
                 ,'stepCreateTextDocument'
1109
                 ,'stepIngestTextFormats'
1110 1111 1112 1113 1114 1115 1116
                ]
    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'
1117 1118
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepIngestSpreadsheetFormats'
1119 1120 1121 1122 1123 1124 1125
                ]
    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'
1126 1127
                 ,'stepCreatePresentationDocument'
                 ,'stepIngestPresentationFormats'
1128 1129 1130 1131 1132 1133 1134
                ]
    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'
1135 1136
                 ,'stepCreateDrawingDocument'
                 ,'stepIngestDrawingFormats'
1137 1138 1139 1140 1141 1142 1143
                ]
    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'
1144 1145
                 ,'stepCreatePDFDocument'
                 ,'stepIngestPDFFormats'
1146 1147 1148 1149 1150 1151 1152
                ]
    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'
1153 1154
                 ,'stepCreateImageDocument'
                 ,'stepIngestImageFormats'
1155
                ]
1156
    self.playSequence(step_list, quiet)
1157

1158 1159 1160 1161 1162 1163

  # 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):
1164
    if not run: return
1165
    if not quiet: printAndLog('test_06_FormatGeneration')
1166 1167
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1168
                 ,'stepCheckTextDocumentExportList'
1169 1170 1171 1172 1173 1174 1175
                ]
    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'
1176 1177
                 ,'stepCreateSpreadsheetDocument'
                 ,'stepCheckSpreadsheetDocumentExportList'
1178 1179 1180 1181 1182 1183 1184
                ]
    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'
1185 1186
                 ,'stepCreatePresentationDocument'
                 ,'stepCheckPresentationDocumentExportList'
1187 1188 1189 1190 1191 1192 1193
                ]
    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'
1194 1195
                 ,'stepCreateDrawingDocument'
                 ,'stepCheckDrawingDocumentExportList'
1196 1197 1198 1199 1200 1201 1202
                ]
    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'
1203 1204
                 ,'stepCreatePDFDocument'
                 ,'stepExportPDF'
1205 1206 1207 1208 1209 1210 1211
                ]
    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'
1212 1213
                 ,'stepCreateImageDocument'
                 ,'stepExportImage'
1214
                ]
1215
    self.playSequence(step_list, quiet)
1216

1217

1218 1219 1220 1221 1222 1223 1224
  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
1225
    if not quiet: printAndLog('test_07_SnapshotGeneration')
1226 1227
    step_list = [ 'stepCleanUp'
                 ,'stepCreateTextDocument'
1228 1229 1230 1231
                 ,'stepUploadFromViewForm'
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1232 1233 1234 1235 1236 1237 1238 1239
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                 ,'stepTryRecreateSnapshot'
                 ,'stepCheckHasSnapshot'
                 ,'stepDeleteSnapshot'
                 ,'stepCheckHasNoSnapshot'
                 ,'stepCreateSnapshot'
                ]
1240
    self.playSequence(step_list, quiet)
1241

1242 1243
  def test_08_Cache(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1244
      I don't know how to verify how cache works
1245 1246
    """

1247
  def test_09_Contribute(self, quiet=QUIET, run=RUN_ALL_TEST):
1248 1249 1250 1251 1252 1253 1254 1255 1256 1257
    """
      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
1258
    if not quiet: printAndLog('test_09_Contribute')
1259 1260
    step_list = [ 'stepCleanUp'
                 ,'stepContributeFileListWithNoType'
1261
                 ,'stepCleanUp'
Bartek Górny's avatar
Bartek Górny committed
1262
                 ,'stepContributeFileListWithType'
1263
                ]
1264
    self.playSequence(step_list, quiet)
1265 1266 1267

  def test_10_MetadataSettingPreferenceOrder(self, quiet=QUIET, run=RUN_ALL_TEST):
    """
1268
      Set some metadata discovery scripts
1269
      Contribute a document, let it get metadata using default setup
1270 1271 1272
      (default is FUC)

      check that the right ones are there
1273 1274
      change preference order, check again
    """
1275
    if not run: return
1276
    if not quiet: printAndLog('test_10_MetadataSettingPreferenceOrder')
1277 1278
    step_list = [ 'stepCleanUp' 
                 ,'stepCreateTextDocument'
1279
                 ,'stepStraightUpload'
1280 1281 1282
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1283
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
Bartek Górny's avatar
Bartek Górny committed
1284
                 ,'stepCheckMetadataSettingOrderFICU'
1285 1286
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1287 1288 1289
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1290
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1291 1292 1293
                 ,'stepCheckMetadataSettingOrderCUFI'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1294 1295 1296
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1297
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1298 1299 1300
                 ,'stepCheckMetadataSettingOrderUIFC'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1301 1302 1303
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1304
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1305 1306 1307
                 ,'stepCheckMetadataSettingOrderICUF'
                 ,'stepCreateTextDocument'
                 ,'stepStraightUpload'
1308 1309 1310
                 ,'stepCheckConvertingState'
                 ,'stepTic'
                 ,'stepCheckConvertedState'
1311
                 ,'stepSetSimulatedDiscoveryScriptForOrdering'
1312 1313
                 ,'stepCheckMetadataSettingOrderUFCI'
                ]
1314
    self.playSequence(step_list, quiet)
1315

1316 1317 1318 1319 1320 1321 1322
  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
1323
    if not quiet: printAndLog('test_11_EmailIngestion')
1324 1325
    step_list = [ 'stepCleanUp'
                 ,'stepReceiveEmailFromUnknown'
1326 1327 1328 1329
                 ,'stepCreatePerson'
                 ,'stepReceiveEmailFromJohn'
                 ,'stepVerifyEmailedDocuments'
                ]
1330
    self.playSequence(step_list, quiet)
1331

1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350
  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)
1351

1352 1353 1354 1355 1356
  def stepUploadTextFromContributionToolWithNonASCIIFilename(self, 
                                 sequence=None, sequence_list=None, **kw):
    """
      Upload a file from contribution.
    """
1357
    f = makeFileUpload('TEST-en-002.doc', 'T&é@{T-en-002.doc')
1358 1359
    document = self.portal.portal_contributions.newContent(file=f)
    sequence.edit(document_id=document.getId())
1360
    transaction.commit()
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 1403 1404

  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)

1405 1406 1407 1408
# Missing tests
"""
    property_dict = context.getPropertyDictFromUserLogin()
    property_dict = context.getPropertyDictFromInput()
1409
"""
Jérome Perrin's avatar
Jérome Perrin committed
1410 1411 1412 1413 1414

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