1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
|
import os
import shutil
import tempfile
import unittest
import PIL
import PIL.Image
import openpaperwork_core
import openpaperwork_core.fs
class TestPyocr(unittest.TestCase):
def setUp(self):
self.tmp_paperwork_dir = tempfile.mkdtemp(
prefix="paperwork_backend_tests"
)
self.test_img = PIL.Image.open(
os.path.join(
os.path.dirname(os.path.abspath(__file__)),
"test_img.png"
)
)
self.core = openpaperwork_core.Core(auto_load_dependencies=True)
class FakeModule(object):
class Plugin(openpaperwork_core.PluginBase):
PRIORITY = 999999999999999999999
def data_dir_handler_get_individual_data_dir(s):
return openpaperwork_core.fs.CommonFsPluginBase.fs_safe(
self.tmp_paperwork_dir
)
self.core._load_module("fake_module", FakeModule)
self.core.load("openpaperwork_core.config.fake")
self.core.load("paperwork_backend.model.fake")
self.core.load("paperwork_backend.doctracker")
self.core.load("paperwork_backend.pagetracker")
self.core.load("paperwork_backend.guesswork.ocr.pyocr")
self.core.init()
self.model = self.core.get_by_name("paperwork_backend.model.fake")
self.core.call_all("config_put", "ocr_langs", ["eng"])
def tearDown(self):
self.core.call_all("tests_cleanup")
shutil.rmtree(self.tmp_paperwork_dir)
def test_ocr(self):
self.model.docs = [
{
"id": 'some_id',
"url": 'file:///some_work_dir/some_doc_id',
"mtime": 12345,
"labels": [],
"page_boxes": [],
"page_imgs": [
("file:///some_image.png", self.test_img)
],
"page_hashes": [
("file:///some_image.png", 0),
]
},
]
self.core.call_all(
"ocr_page_by_url", "file:///some_work_dir/some_doc_id", page_idx=0
)
self.assertNotEqual(len(self.model.docs[0]['page_boxes']), 0)
self.assertEqual(
self.model.docs[0]['text'],
"This is a test\n"
"image created\n"
"by Flesch\n"
)
def test_transaction(self):
self.model.docs = [
{
"id": 'some_doc_with_text',
"url": 'file:///some_work_dir/some_doc_id',
"mtime": 12345,
"labels": [],
"page_boxes": [
# Should be list of LineBoxes, but meh.
"putsomething",
"here"
],
"page_imgs": [
("file:///paper.0.png", None),
("file:///paper.1.png", None),
],
"page_hashes": [
("file:///paper.0.png", 0),
("file:///paper.1.png", 1),
],
},
{
"id": 'some_doc',
"url": 'file:///some_work_dir/some_2',
"mtime": 12345,
"labels": [],
"page_boxes": [],
"page_imgs": [
("file:///some_image.png", self.test_img)
],
"page_hashes": [
("file:///some_image.png", 3),
],
},
]
transactions = []
self.core.call_all("doc_transaction_start", transactions)
transactions.sort(key=lambda transaction: -transaction.priority)
self.assertNotEqual(transactions, [])
for t in transactions:
t.add_doc('some_doc_with_text')
for t in transactions:
t.add_doc('some_doc')
for t in transactions:
t.commit()
# first doc already had boxes --> no boxes or text added
self.assertNotIn('text', self.model.docs[0])
self.assertEqual(self.model.docs[0]['page_boxes'], [
"putsomething", "here" # unchanged
])
# but OCR should be run on the other doc
self.assertNotEqual(len(self.model.docs[1]['page_boxes']), 0)
self.assertEqual(
self.model.docs[1]['text'],
"This is a test\n"
"image created\n"
"by Flesch\n"
)
def test_tricky(self):
self.model.docs = [
{
"id": 'some_doc_with_text',
"url": 'file:///some_work_dir/some_doc_id',
"mtime": 12345,
"labels": [],
"page_boxes": [
# Should be list of LineBoxes, but meh.
"putsomething",
"here"
],
"page_imgs": [
("file:///paper.0.png", self.test_img),
("file:///paper.1.png", self.test_img),
],
"page_hashes": [
("file:///paper.0.png", 0),
("file:///paper.1.png", 1),
],
},
]
transactions = []
self.core.call_all("doc_transaction_start", transactions)
self.assertNotEqual(transactions, [])
for t in transactions:
t.add_doc('some_doc_with_text')
for t in transactions:
t.commit()
# first doc already had boxes --> no boxes or text added
self.assertNotIn('text', self.model.docs[0])
self.assertEqual(self.model.docs[0]['page_boxes'], [
"putsomething", "here" # unchanged
])
self.model.docs = [
{
"id": 'some_doc_with_text',
"url": 'file:///some_work_dir/some_doc_id',
"mtime": 12346,
"labels": [],
"page_boxes": [],
"page_imgs": [
("file:///paper.0.png", self.test_img), # new page
("file:///paper.1.png", self.test_img),
("file:///paper.2.png", self.test_img), # modified
],
"page_hashes": [
("file:///paper.0.png", 0xDEADBEEF), # new page
("file:///paper.1.png", 0),
("file:///paper.2.png", 0xBEEFDEAD), # modified
],
},
]
transactions = []
self.core.call_all("doc_transaction_start", transactions)
self.assertNotEqual(transactions, [])
for t in transactions:
t.upd_doc('some_doc_with_text')
for t in transactions:
t.commit()
self.assertNotEqual(len(self.model.docs[0]['page_boxes']), 0)
self.assertEqual(
self.model.docs[0]['text'],
"This is a test\n" # new page
"image created\n" # new page
"by Flesch\n" # new page
"\n\n"
# unchanged page --> no OCR
"\n\n"
"This is a test\n" # modified page
"image created\n" # modified page
"by Flesch\n" # modified page
)
|
