1 | # -*- coding: utf-8 -*- |
---|
2 | ## $Id: test_batching.py 12438 2015-01-11 08:27:37Z henrik $ |
---|
3 | ## |
---|
4 | ## Copyright (C) 2014 Uli Fouquet & Henrik Bettermann |
---|
5 | ## This program is free software; you can redistribute it and/or modify |
---|
6 | ## it under the terms of the GNU General Public License as published by |
---|
7 | ## the Free Software Foundation; either version 2 of the License, or |
---|
8 | ## (at your option) any later version. |
---|
9 | ## |
---|
10 | ## This program is distributed in the hope that it will be useful, |
---|
11 | ## but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
12 | ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
13 | ## GNU General Public License for more details. |
---|
14 | ## |
---|
15 | ## You should have received a copy of the GNU General Public License |
---|
16 | ## along with this program; if not, write to the Free Software |
---|
17 | ## Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
---|
18 | ## |
---|
19 | """Unit tests for document data processors. |
---|
20 | """ |
---|
21 | import os |
---|
22 | import shutil |
---|
23 | import tempfile |
---|
24 | import unittest |
---|
25 | import datetime |
---|
26 | import grok |
---|
27 | from time import time |
---|
28 | from zope.event import notify |
---|
29 | from zope.component import createObject, queryUtility |
---|
30 | from zope.component.hooks import setSite, clearSite |
---|
31 | from zope.catalog.interfaces import ICatalog |
---|
32 | from zope.interface.verify import verifyClass, verifyObject |
---|
33 | from zope.securitypolicy.interfaces import IPrincipalRoleManager |
---|
34 | |
---|
35 | from waeup.kofa.app import University |
---|
36 | from waeup.kofa.interfaces import IBatchProcessor, FatalCSVError, IUserAccount |
---|
37 | from waeup.kofa.documents.batching import PDFDocumentProcessor |
---|
38 | from waeup.kofa.documents.document import PDFDocument, HTMLDocument |
---|
39 | from waeup.kofa.testing import FunctionalLayer, FunctionalTestCase |
---|
40 | |
---|
41 | DOCUMENT_SAMPLE_DATA = open( |
---|
42 | os.path.join(os.path.dirname(__file__), 'sample_document_data.csv'), |
---|
43 | 'rb').read() |
---|
44 | |
---|
45 | DOCUMENT_HEADER_FIELDS = DOCUMENT_SAMPLE_DATA.split( |
---|
46 | '\n')[0].split(',') |
---|
47 | |
---|
48 | DOCUMENT_SAMPLE_DATA_UPDATE = open( |
---|
49 | os.path.join(os.path.dirname(__file__), 'sample_document_data_update.csv'), |
---|
50 | 'rb').read() |
---|
51 | |
---|
52 | DOCUMENT_HEADER_FIELDS_UPDATE = DOCUMENT_SAMPLE_DATA_UPDATE.split( |
---|
53 | '\n')[0].split(',') |
---|
54 | |
---|
55 | class DocumentImportExportSetup(FunctionalTestCase): |
---|
56 | |
---|
57 | layer = FunctionalLayer |
---|
58 | |
---|
59 | def setUp(self): |
---|
60 | super(DocumentImportExportSetup, self).setUp() |
---|
61 | self.dc_root = tempfile.mkdtemp() |
---|
62 | self.workdir = tempfile.mkdtemp() |
---|
63 | app = University() |
---|
64 | app['datacenter'].setStoragePath(self.dc_root) |
---|
65 | self.getRootFolder()['app'] = app |
---|
66 | self.app = self.getRootFolder()['app'] |
---|
67 | setSite(app) |
---|
68 | |
---|
69 | self.logfile = os.path.join( |
---|
70 | self.app['datacenter'].storage, 'logs', 'main.log') |
---|
71 | return |
---|
72 | |
---|
73 | def tearDown(self): |
---|
74 | super(DocumentImportExportSetup, self).tearDown() |
---|
75 | shutil.rmtree(self.workdir) |
---|
76 | shutil.rmtree(self.dc_root) |
---|
77 | clearSite() |
---|
78 | return |
---|
79 | |
---|
80 | def setup_for_export(self): |
---|
81 | document1 = PDFDocument() |
---|
82 | document1.document_id = u'DOC1' |
---|
83 | self.app['documents'].addDocument(document1) |
---|
84 | self.pdfdocument = document1 |
---|
85 | self.outfile = os.path.join(self.workdir, 'myoutput.csv') |
---|
86 | role_manager = IPrincipalRoleManager(document1) |
---|
87 | role_manager.assignRoleToPrincipal(u'johnsrole', u'john') |
---|
88 | |
---|
89 | document2 = HTMLDocument() |
---|
90 | document2.document_id = u'DOC2' |
---|
91 | self.app['documents'].addDocument(document2) |
---|
92 | self.htmldocument = document2 |
---|
93 | self.outfile = os.path.join(self.workdir, 'myoutput.csv') |
---|
94 | role_manager = IPrincipalRoleManager(document2) |
---|
95 | role_manager.assignRoleToPrincipal(u'johnsrole', u'john') |
---|
96 | return |
---|
97 | |
---|
98 | |
---|
99 | class PDFDocumentProcessorTest(DocumentImportExportSetup): |
---|
100 | |
---|
101 | layer = FunctionalLayer |
---|
102 | |
---|
103 | def setUp(self): |
---|
104 | super(PDFDocumentProcessorTest, self).setUp() |
---|
105 | |
---|
106 | # Add document |
---|
107 | document = PDFDocument() |
---|
108 | document.document_id = u'DOC1' |
---|
109 | self.app['documents'].addDocument(document) |
---|
110 | document.title = u'Our PDF Document' |
---|
111 | notify(grok.ObjectModifiedEvent(document)) |
---|
112 | self.document = self.app['documents'][document.document_id] |
---|
113 | |
---|
114 | self.processor = PDFDocumentProcessor() |
---|
115 | self.csv_file = os.path.join(self.workdir, 'sample_document_data.csv') |
---|
116 | self.csv_file_update = os.path.join( |
---|
117 | self.workdir, 'sample_document_data_update.csv') |
---|
118 | open(self.csv_file, 'wb').write(DOCUMENT_SAMPLE_DATA) |
---|
119 | open(self.csv_file_update, 'wb').write(DOCUMENT_SAMPLE_DATA_UPDATE) |
---|
120 | |
---|
121 | def test_interface(self): |
---|
122 | # Make sure we fulfill the interface contracts. |
---|
123 | assert verifyObject(IBatchProcessor, self.processor) is True |
---|
124 | assert verifyClass( |
---|
125 | IBatchProcessor, PDFDocumentProcessor) is True |
---|
126 | |
---|
127 | def test_parentsExist(self): |
---|
128 | self.assertFalse(self.processor.parentsExist(None, dict())) |
---|
129 | self.assertTrue(self.processor.parentsExist(None, self.app)) |
---|
130 | |
---|
131 | def test_entryExists(self): |
---|
132 | assert self.processor.entryExists( |
---|
133 | dict(document_id='ID_NONE'), self.app) is False |
---|
134 | assert self.processor.entryExists( |
---|
135 | dict(document_id=self.document.document_id), self.app) is True |
---|
136 | |
---|
137 | def test_getParent(self): |
---|
138 | parent = self.processor.getParent(None, self.app) |
---|
139 | assert parent is self.app['documents'] |
---|
140 | |
---|
141 | def test_getEntry(self): |
---|
142 | assert self.processor.getEntry( |
---|
143 | dict(document_id='ID_NONE'), self.app) is None |
---|
144 | assert self.processor.getEntry( |
---|
145 | dict(document_id=self.document.document_id), self.app) is self.document |
---|
146 | |
---|
147 | def test_addEntry(self): |
---|
148 | new_document = PDFDocument() |
---|
149 | new_document.document_id = u'DOC2' |
---|
150 | self.processor.addEntry( |
---|
151 | new_document, {}, self.app) |
---|
152 | assert len(self.app['documents'].keys()) == 2 |
---|
153 | self.assertEqual(self.app['documents']['DOC2'].document_id, 'DOC2') |
---|
154 | |
---|
155 | def test_checkConversion(self): |
---|
156 | errs, inv_errs, conv_dict = self.processor.checkConversion( |
---|
157 | dict(document_id='DOC4', class_name='PDFDocument')) |
---|
158 | self.assertEqual(len(errs),0) |
---|
159 | errs, inv_errs, conv_dict = self.processor.checkConversion( |
---|
160 | dict(document_id='id with spaces', class_name='PDFDocument')) |
---|
161 | self.assertEqual(len(errs),1) |
---|
162 | errs, inv_errs, conv_dict = self.processor.checkConversion( |
---|
163 | dict(document_id='DOC4', class_name='WrongDocument'), mode='create') |
---|
164 | self.assertEqual(len(errs),1) |
---|
165 | |
---|
166 | def test_delEntry(self): |
---|
167 | assert self.document.document_id in self.app['documents'].keys() |
---|
168 | self.processor.delEntry( |
---|
169 | dict(document_id=self.document.document_id), self.app) |
---|
170 | assert self.document.document_id not in self.app['documents'].keys() |
---|
171 | |
---|
172 | def test_import(self): |
---|
173 | num, num_warns, fin_file, fail_file = self.processor.doImport( |
---|
174 | self.csv_file, DOCUMENT_HEADER_FIELDS) |
---|
175 | self.assertEqual(num_warns,2) |
---|
176 | self.assertEqual(len(self.app['documents']), 4) |
---|
177 | self.assertEqual(self.app['documents']['ABC'].title,'ABC title') |
---|
178 | logcontent = open(self.logfile).read() |
---|
179 | # Logging message from updateEntry |
---|
180 | self.assertTrue( |
---|
181 | 'INFO - system - Public PDF Document Processor - sample_document_data - ' |
---|
182 | 'EFG - updated: document_id=EFG, title=EFG title\n' |
---|
183 | in logcontent) |
---|
184 | failcontent = open(fail_file).read() |
---|
185 | self.assertTrue( |
---|
186 | 'PDFDocument,ABC,Duplicate document,This object already exists.' |
---|
187 | in failcontent) |
---|
188 | self.assertTrue( |
---|
189 | 'HTMLDocument,HIJ,HIJ title,class_name: wrong processor' |
---|
190 | in failcontent) |
---|
191 | shutil.rmtree(os.path.dirname(fin_file)) |
---|
192 | |
---|
193 | def test_import_update(self): |
---|
194 | num, num_warns, fin_file, fail_file = self.processor.doImport( |
---|
195 | self.csv_file, DOCUMENT_HEADER_FIELDS) |
---|
196 | shutil.rmtree(os.path.dirname(fin_file)) |
---|
197 | num, num_warns, fin_file, fail_file = self.processor.doImport( |
---|
198 | self.csv_file_update, DOCUMENT_HEADER_FIELDS_UPDATE, 'update') |
---|
199 | self.assertEqual(num_warns,1) |
---|
200 | # title has changed |
---|
201 | self.assertEqual(self.app['documents']['ABC'].title,'ABC new title') |
---|
202 | logcontent = open(self.logfile).read() |
---|
203 | # Logging message from updateEntry |
---|
204 | self.assertTrue( |
---|
205 | 'INFO - system - Public PDF Document Processor - sample_document_data_update - ' |
---|
206 | 'ABC - updated: document_id=ABC, title=ABC new title\n' |
---|
207 | in logcontent) |
---|
208 | failcontent = open(fail_file).read() |
---|
209 | self.assertTrue( |
---|
210 | 'XYZ,Non-existing document,Cannot update: no such entry' |
---|
211 | in failcontent) |
---|
212 | shutil.rmtree(os.path.dirname(fin_file)) |
---|