arkindex-base-worker 0.4.0rc3__py3-none-any.whl → 0.4.0rc4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {arkindex_base_worker-0.4.0rc3.dist-info → arkindex_base_worker-0.4.0rc4.dist-info}/METADATA +15 -14
- {arkindex_base_worker-0.4.0rc3.dist-info → arkindex_base_worker-0.4.0rc4.dist-info}/RECORD +21 -13
- {arkindex_base_worker-0.4.0rc3.dist-info → arkindex_base_worker-0.4.0rc4.dist-info}/WHEEL +1 -1
- arkindex_worker/cache.py +1 -1
- tests/test_elements_worker/{test_classifications.py → test_classification.py} +86 -0
- tests/test_elements_worker/test_corpus.py +31 -31
- tests/test_elements_worker/test_element.py +427 -0
- tests/test_elements_worker/test_element_create_multiple.py +715 -0
- tests/test_elements_worker/test_element_create_single.py +528 -0
- tests/test_elements_worker/test_element_list_children.py +969 -0
- tests/test_elements_worker/test_element_list_parents.py +530 -0
- tests/test_elements_worker/{test_entities.py → test_entity_create.py} +0 -153
- tests/test_elements_worker/test_entity_list_and_check.py +160 -0
- tests/test_elements_worker/test_transcription_create.py +873 -0
- tests/test_elements_worker/test_transcription_create_with_elements.py +951 -0
- tests/test_elements_worker/test_transcription_list.py +450 -0
- tests/test_elements_worker/test_version.py +60 -0
- tests/test_elements_worker/test_worker.py +525 -88
- tests/test_image.py +181 -198
- tests/test_elements_worker/test_elements.py +0 -3704
- tests/test_elements_worker/test_transcriptions.py +0 -2252
- {arkindex_base_worker-0.4.0rc3.dist-info → arkindex_base_worker-0.4.0rc4.dist-info}/LICENSE +0 -0
- {arkindex_base_worker-0.4.0rc3.dist-info → arkindex_base_worker-0.4.0rc4.dist-info}/top_level.txt +0 -0
|
@@ -1,2252 +0,0 @@
|
|
|
1
|
-
import json
|
|
2
|
-
import re
|
|
3
|
-
from uuid import UUID
|
|
4
|
-
|
|
5
|
-
import pytest
|
|
6
|
-
from playhouse.shortcuts import model_to_dict
|
|
7
|
-
|
|
8
|
-
from arkindex.exceptions import ErrorResponse
|
|
9
|
-
from arkindex_worker.cache import CachedElement, CachedTranscription
|
|
10
|
-
from arkindex_worker.models import Element
|
|
11
|
-
from arkindex_worker.utils import DEFAULT_BATCH_SIZE
|
|
12
|
-
from arkindex_worker.worker.transcription import TextOrientation
|
|
13
|
-
|
|
14
|
-
from . import BASE_API_CALLS
|
|
15
|
-
|
|
16
|
-
TRANSCRIPTIONS_SAMPLE = [
|
|
17
|
-
{
|
|
18
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
19
|
-
"confidence": 0.5,
|
|
20
|
-
"text": "The",
|
|
21
|
-
},
|
|
22
|
-
{
|
|
23
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
24
|
-
"confidence": 0.75,
|
|
25
|
-
"text": "first",
|
|
26
|
-
"element_confidence": 0.75,
|
|
27
|
-
},
|
|
28
|
-
{
|
|
29
|
-
"polygon": [[1000, 300], [1200, 300], [1200, 500], [1000, 500]],
|
|
30
|
-
"confidence": 0.9,
|
|
31
|
-
"text": "line",
|
|
32
|
-
},
|
|
33
|
-
]
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
def test_create_transcription_wrong_element(mock_elements_worker):
|
|
37
|
-
with pytest.raises(
|
|
38
|
-
AssertionError,
|
|
39
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
40
|
-
):
|
|
41
|
-
mock_elements_worker.create_transcription(
|
|
42
|
-
element=None,
|
|
43
|
-
text="i am a line",
|
|
44
|
-
confidence=0.42,
|
|
45
|
-
)
|
|
46
|
-
|
|
47
|
-
with pytest.raises(
|
|
48
|
-
AssertionError,
|
|
49
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
50
|
-
):
|
|
51
|
-
mock_elements_worker.create_transcription(
|
|
52
|
-
element="not element type",
|
|
53
|
-
text="i am a line",
|
|
54
|
-
confidence=0.42,
|
|
55
|
-
)
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
def test_create_transcription_wrong_text(mock_elements_worker):
|
|
59
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
60
|
-
|
|
61
|
-
with pytest.raises(
|
|
62
|
-
AssertionError, match="text shouldn't be null and should be of type str"
|
|
63
|
-
):
|
|
64
|
-
mock_elements_worker.create_transcription(
|
|
65
|
-
element=elt,
|
|
66
|
-
text=None,
|
|
67
|
-
confidence=0.42,
|
|
68
|
-
)
|
|
69
|
-
|
|
70
|
-
with pytest.raises(
|
|
71
|
-
AssertionError, match="text shouldn't be null and should be of type str"
|
|
72
|
-
):
|
|
73
|
-
mock_elements_worker.create_transcription(
|
|
74
|
-
element=elt,
|
|
75
|
-
text=1234,
|
|
76
|
-
confidence=0.42,
|
|
77
|
-
)
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
def test_create_transcription_wrong_confidence(mock_elements_worker):
|
|
81
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
82
|
-
|
|
83
|
-
with pytest.raises(
|
|
84
|
-
AssertionError,
|
|
85
|
-
match=re.escape(
|
|
86
|
-
"confidence shouldn't be null and should be a float in [0..1] range"
|
|
87
|
-
),
|
|
88
|
-
):
|
|
89
|
-
mock_elements_worker.create_transcription(
|
|
90
|
-
element=elt,
|
|
91
|
-
text="i am a line",
|
|
92
|
-
confidence=None,
|
|
93
|
-
)
|
|
94
|
-
|
|
95
|
-
with pytest.raises(
|
|
96
|
-
AssertionError,
|
|
97
|
-
match=re.escape(
|
|
98
|
-
"confidence shouldn't be null and should be a float in [0..1] range"
|
|
99
|
-
),
|
|
100
|
-
):
|
|
101
|
-
mock_elements_worker.create_transcription(
|
|
102
|
-
element=elt,
|
|
103
|
-
text="i am a line",
|
|
104
|
-
confidence="wrong confidence",
|
|
105
|
-
)
|
|
106
|
-
|
|
107
|
-
with pytest.raises(
|
|
108
|
-
AssertionError,
|
|
109
|
-
match=re.escape(
|
|
110
|
-
"confidence shouldn't be null and should be a float in [0..1] range"
|
|
111
|
-
),
|
|
112
|
-
):
|
|
113
|
-
mock_elements_worker.create_transcription(
|
|
114
|
-
element=elt,
|
|
115
|
-
text="i am a line",
|
|
116
|
-
confidence=0,
|
|
117
|
-
)
|
|
118
|
-
|
|
119
|
-
with pytest.raises(
|
|
120
|
-
AssertionError,
|
|
121
|
-
match=re.escape(
|
|
122
|
-
"confidence shouldn't be null and should be a float in [0..1] range"
|
|
123
|
-
),
|
|
124
|
-
):
|
|
125
|
-
mock_elements_worker.create_transcription(
|
|
126
|
-
element=elt,
|
|
127
|
-
text="i am a line",
|
|
128
|
-
confidence=2.00,
|
|
129
|
-
)
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
def test_create_transcription_default_orientation(responses, mock_elements_worker):
|
|
133
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
134
|
-
responses.add(
|
|
135
|
-
responses.POST,
|
|
136
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
137
|
-
status=200,
|
|
138
|
-
json={
|
|
139
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
140
|
-
"text": "Animula vagula blandula",
|
|
141
|
-
"confidence": 0.42,
|
|
142
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
143
|
-
},
|
|
144
|
-
)
|
|
145
|
-
mock_elements_worker.create_transcription(
|
|
146
|
-
element=elt,
|
|
147
|
-
text="Animula vagula blandula",
|
|
148
|
-
confidence=0.42,
|
|
149
|
-
)
|
|
150
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
151
|
-
"text": "Animula vagula blandula",
|
|
152
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
153
|
-
"confidence": 0.42,
|
|
154
|
-
"orientation": "horizontal-lr",
|
|
155
|
-
}
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
def test_create_transcription_orientation(responses, mock_elements_worker):
|
|
159
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
160
|
-
responses.add(
|
|
161
|
-
responses.POST,
|
|
162
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
163
|
-
status=200,
|
|
164
|
-
json={
|
|
165
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
166
|
-
"text": "Animula vagula blandula",
|
|
167
|
-
"confidence": 0.42,
|
|
168
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
169
|
-
},
|
|
170
|
-
)
|
|
171
|
-
mock_elements_worker.create_transcription(
|
|
172
|
-
element=elt,
|
|
173
|
-
text="Animula vagula blandula",
|
|
174
|
-
orientation=TextOrientation.VerticalLeftToRight,
|
|
175
|
-
confidence=0.42,
|
|
176
|
-
)
|
|
177
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
178
|
-
"text": "Animula vagula blandula",
|
|
179
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
180
|
-
"confidence": 0.42,
|
|
181
|
-
"orientation": "vertical-lr",
|
|
182
|
-
}
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
def test_create_transcription_wrong_orientation(mock_elements_worker):
|
|
186
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
187
|
-
with pytest.raises(
|
|
188
|
-
AssertionError,
|
|
189
|
-
match="orientation shouldn't be null and should be of type TextOrientation",
|
|
190
|
-
):
|
|
191
|
-
mock_elements_worker.create_transcription(
|
|
192
|
-
element=elt,
|
|
193
|
-
text="Animula vagula blandula",
|
|
194
|
-
confidence=0.26,
|
|
195
|
-
orientation="elliptical",
|
|
196
|
-
)
|
|
197
|
-
|
|
198
|
-
|
|
199
|
-
def test_create_transcription_api_error(responses, mock_elements_worker):
|
|
200
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
201
|
-
responses.add(
|
|
202
|
-
responses.POST,
|
|
203
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
204
|
-
status=418,
|
|
205
|
-
)
|
|
206
|
-
|
|
207
|
-
with pytest.raises(ErrorResponse):
|
|
208
|
-
mock_elements_worker.create_transcription(
|
|
209
|
-
element=elt,
|
|
210
|
-
text="i am a line",
|
|
211
|
-
confidence=0.42,
|
|
212
|
-
)
|
|
213
|
-
|
|
214
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
215
|
-
assert [
|
|
216
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
217
|
-
] == BASE_API_CALLS + [
|
|
218
|
-
("POST", f"http://testserver/api/v1/element/{elt.id}/transcription/")
|
|
219
|
-
]
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
def test_create_transcription(responses, mock_elements_worker):
|
|
223
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
224
|
-
responses.add(
|
|
225
|
-
responses.POST,
|
|
226
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
227
|
-
status=200,
|
|
228
|
-
json={
|
|
229
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
230
|
-
"text": "i am a line",
|
|
231
|
-
"confidence": 0.42,
|
|
232
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
233
|
-
},
|
|
234
|
-
)
|
|
235
|
-
|
|
236
|
-
mock_elements_worker.create_transcription(
|
|
237
|
-
element=elt,
|
|
238
|
-
text="i am a line",
|
|
239
|
-
confidence=0.42,
|
|
240
|
-
)
|
|
241
|
-
|
|
242
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
243
|
-
assert [
|
|
244
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
245
|
-
] == BASE_API_CALLS + [
|
|
246
|
-
("POST", f"http://testserver/api/v1/element/{elt.id}/transcription/"),
|
|
247
|
-
]
|
|
248
|
-
|
|
249
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
250
|
-
"text": "i am a line",
|
|
251
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
252
|
-
"confidence": 0.42,
|
|
253
|
-
"orientation": "horizontal-lr",
|
|
254
|
-
}
|
|
255
|
-
|
|
256
|
-
|
|
257
|
-
def test_create_transcription_with_cache(responses, mock_elements_worker_with_cache):
|
|
258
|
-
elt = CachedElement.create(id="12341234-1234-1234-1234-123412341234", type="thing")
|
|
259
|
-
|
|
260
|
-
responses.add(
|
|
261
|
-
responses.POST,
|
|
262
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
263
|
-
status=200,
|
|
264
|
-
json={
|
|
265
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
266
|
-
"text": "i am a line",
|
|
267
|
-
"confidence": 0.42,
|
|
268
|
-
"orientation": "horizontal-lr",
|
|
269
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
270
|
-
},
|
|
271
|
-
)
|
|
272
|
-
|
|
273
|
-
mock_elements_worker_with_cache.create_transcription(
|
|
274
|
-
element=elt,
|
|
275
|
-
text="i am a line",
|
|
276
|
-
confidence=0.42,
|
|
277
|
-
)
|
|
278
|
-
|
|
279
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
280
|
-
assert [
|
|
281
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
282
|
-
] == BASE_API_CALLS + [
|
|
283
|
-
("POST", f"http://testserver/api/v1/element/{elt.id}/transcription/"),
|
|
284
|
-
]
|
|
285
|
-
|
|
286
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
287
|
-
"text": "i am a line",
|
|
288
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
289
|
-
"orientation": "horizontal-lr",
|
|
290
|
-
"confidence": 0.42,
|
|
291
|
-
}
|
|
292
|
-
|
|
293
|
-
# Check that created transcription was properly stored in SQLite cache
|
|
294
|
-
assert list(CachedTranscription.select()) == [
|
|
295
|
-
CachedTranscription(
|
|
296
|
-
id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
297
|
-
element_id=UUID(elt.id),
|
|
298
|
-
text="i am a line",
|
|
299
|
-
confidence=0.42,
|
|
300
|
-
orientation=TextOrientation.HorizontalLeftToRight,
|
|
301
|
-
worker_version_id=None,
|
|
302
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
303
|
-
)
|
|
304
|
-
]
|
|
305
|
-
|
|
306
|
-
|
|
307
|
-
def test_create_transcription_orientation_with_cache(
|
|
308
|
-
responses, mock_elements_worker_with_cache
|
|
309
|
-
):
|
|
310
|
-
elt = CachedElement.create(id="12341234-1234-1234-1234-123412341234", type="thing")
|
|
311
|
-
responses.add(
|
|
312
|
-
responses.POST,
|
|
313
|
-
f"http://testserver/api/v1/element/{elt.id}/transcription/",
|
|
314
|
-
status=200,
|
|
315
|
-
json={
|
|
316
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
317
|
-
"text": "Animula vagula blandula",
|
|
318
|
-
"confidence": 0.42,
|
|
319
|
-
"orientation": "vertical-lr",
|
|
320
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
321
|
-
},
|
|
322
|
-
)
|
|
323
|
-
mock_elements_worker_with_cache.create_transcription(
|
|
324
|
-
element=elt,
|
|
325
|
-
text="Animula vagula blandula",
|
|
326
|
-
orientation=TextOrientation.VerticalLeftToRight,
|
|
327
|
-
confidence=0.42,
|
|
328
|
-
)
|
|
329
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
330
|
-
"text": "Animula vagula blandula",
|
|
331
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
332
|
-
"orientation": "vertical-lr",
|
|
333
|
-
"confidence": 0.42,
|
|
334
|
-
}
|
|
335
|
-
# Check that the text orientation was properly stored in SQLite cache
|
|
336
|
-
assert list(map(model_to_dict, CachedTranscription.select())) == [
|
|
337
|
-
{
|
|
338
|
-
"id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
339
|
-
"element": {
|
|
340
|
-
"id": UUID("12341234-1234-1234-1234-123412341234"),
|
|
341
|
-
"parent_id": None,
|
|
342
|
-
"type": "thing",
|
|
343
|
-
"image": None,
|
|
344
|
-
"polygon": None,
|
|
345
|
-
"rotation_angle": 0,
|
|
346
|
-
"mirrored": False,
|
|
347
|
-
"initial": False,
|
|
348
|
-
"worker_version_id": None,
|
|
349
|
-
"worker_run_id": None,
|
|
350
|
-
"confidence": None,
|
|
351
|
-
},
|
|
352
|
-
"text": "Animula vagula blandula",
|
|
353
|
-
"confidence": 0.42,
|
|
354
|
-
"orientation": TextOrientation.VerticalLeftToRight.value,
|
|
355
|
-
"worker_version_id": None,
|
|
356
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
357
|
-
}
|
|
358
|
-
]
|
|
359
|
-
|
|
360
|
-
|
|
361
|
-
def test_create_transcriptions_wrong_transcriptions(mock_elements_worker):
|
|
362
|
-
with pytest.raises(
|
|
363
|
-
AssertionError,
|
|
364
|
-
match="transcriptions shouldn't be null and should be of type list",
|
|
365
|
-
):
|
|
366
|
-
mock_elements_worker.create_transcriptions(
|
|
367
|
-
transcriptions=None,
|
|
368
|
-
)
|
|
369
|
-
|
|
370
|
-
with pytest.raises(
|
|
371
|
-
AssertionError,
|
|
372
|
-
match="transcriptions shouldn't be null and should be of type list",
|
|
373
|
-
):
|
|
374
|
-
mock_elements_worker.create_transcriptions(
|
|
375
|
-
transcriptions=1234,
|
|
376
|
-
)
|
|
377
|
-
|
|
378
|
-
with pytest.raises(
|
|
379
|
-
AssertionError,
|
|
380
|
-
match="Transcription at index 1 in transcriptions: element_id shouldn't be null and should be of type str",
|
|
381
|
-
):
|
|
382
|
-
mock_elements_worker.create_transcriptions(
|
|
383
|
-
transcriptions=[
|
|
384
|
-
{
|
|
385
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
386
|
-
"text": "The",
|
|
387
|
-
"confidence": 0.75,
|
|
388
|
-
},
|
|
389
|
-
{
|
|
390
|
-
"text": "word",
|
|
391
|
-
"confidence": 0.5,
|
|
392
|
-
},
|
|
393
|
-
],
|
|
394
|
-
)
|
|
395
|
-
|
|
396
|
-
with pytest.raises(
|
|
397
|
-
AssertionError,
|
|
398
|
-
match="Transcription at index 1 in transcriptions: element_id shouldn't be null and should be of type str",
|
|
399
|
-
):
|
|
400
|
-
mock_elements_worker.create_transcriptions(
|
|
401
|
-
transcriptions=[
|
|
402
|
-
{
|
|
403
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
404
|
-
"text": "The",
|
|
405
|
-
"confidence": 0.75,
|
|
406
|
-
},
|
|
407
|
-
{
|
|
408
|
-
"element_id": None,
|
|
409
|
-
"text": "word",
|
|
410
|
-
"confidence": 0.5,
|
|
411
|
-
},
|
|
412
|
-
],
|
|
413
|
-
)
|
|
414
|
-
|
|
415
|
-
with pytest.raises(
|
|
416
|
-
AssertionError,
|
|
417
|
-
match="Transcription at index 1 in transcriptions: element_id shouldn't be null and should be of type str",
|
|
418
|
-
):
|
|
419
|
-
mock_elements_worker.create_transcriptions(
|
|
420
|
-
transcriptions=[
|
|
421
|
-
{
|
|
422
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
423
|
-
"text": "The",
|
|
424
|
-
"confidence": 0.75,
|
|
425
|
-
},
|
|
426
|
-
{
|
|
427
|
-
"element_id": 1234,
|
|
428
|
-
"text": "word",
|
|
429
|
-
"confidence": 0.5,
|
|
430
|
-
},
|
|
431
|
-
],
|
|
432
|
-
)
|
|
433
|
-
|
|
434
|
-
with pytest.raises(
|
|
435
|
-
AssertionError,
|
|
436
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
437
|
-
):
|
|
438
|
-
mock_elements_worker.create_transcriptions(
|
|
439
|
-
transcriptions=[
|
|
440
|
-
{
|
|
441
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
442
|
-
"text": "The",
|
|
443
|
-
"confidence": 0.75,
|
|
444
|
-
},
|
|
445
|
-
{
|
|
446
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
447
|
-
"confidence": 0.5,
|
|
448
|
-
},
|
|
449
|
-
],
|
|
450
|
-
)
|
|
451
|
-
|
|
452
|
-
with pytest.raises(
|
|
453
|
-
AssertionError,
|
|
454
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
455
|
-
):
|
|
456
|
-
mock_elements_worker.create_transcriptions(
|
|
457
|
-
transcriptions=[
|
|
458
|
-
{
|
|
459
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
460
|
-
"text": "The",
|
|
461
|
-
"confidence": 0.75,
|
|
462
|
-
},
|
|
463
|
-
{
|
|
464
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
465
|
-
"text": None,
|
|
466
|
-
"confidence": 0.5,
|
|
467
|
-
},
|
|
468
|
-
],
|
|
469
|
-
)
|
|
470
|
-
|
|
471
|
-
with pytest.raises(
|
|
472
|
-
AssertionError,
|
|
473
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
474
|
-
):
|
|
475
|
-
mock_elements_worker.create_transcriptions(
|
|
476
|
-
transcriptions=[
|
|
477
|
-
{
|
|
478
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
479
|
-
"text": "The",
|
|
480
|
-
"confidence": 0.75,
|
|
481
|
-
},
|
|
482
|
-
{
|
|
483
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
484
|
-
"text": 1234,
|
|
485
|
-
"confidence": 0.5,
|
|
486
|
-
},
|
|
487
|
-
],
|
|
488
|
-
)
|
|
489
|
-
|
|
490
|
-
with pytest.raises(
|
|
491
|
-
AssertionError,
|
|
492
|
-
match=re.escape(
|
|
493
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
494
|
-
),
|
|
495
|
-
):
|
|
496
|
-
mock_elements_worker.create_transcriptions(
|
|
497
|
-
transcriptions=[
|
|
498
|
-
{
|
|
499
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
500
|
-
"text": "The",
|
|
501
|
-
"confidence": 0.75,
|
|
502
|
-
},
|
|
503
|
-
{
|
|
504
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
505
|
-
"text": "word",
|
|
506
|
-
},
|
|
507
|
-
],
|
|
508
|
-
)
|
|
509
|
-
|
|
510
|
-
with pytest.raises(
|
|
511
|
-
AssertionError,
|
|
512
|
-
match=re.escape(
|
|
513
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
514
|
-
),
|
|
515
|
-
):
|
|
516
|
-
mock_elements_worker.create_transcriptions(
|
|
517
|
-
transcriptions=[
|
|
518
|
-
{
|
|
519
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
520
|
-
"text": "The",
|
|
521
|
-
"confidence": 0.75,
|
|
522
|
-
},
|
|
523
|
-
{
|
|
524
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
525
|
-
"text": "word",
|
|
526
|
-
"confidence": None,
|
|
527
|
-
},
|
|
528
|
-
],
|
|
529
|
-
)
|
|
530
|
-
|
|
531
|
-
with pytest.raises(
|
|
532
|
-
AssertionError,
|
|
533
|
-
match=re.escape(
|
|
534
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
535
|
-
),
|
|
536
|
-
):
|
|
537
|
-
mock_elements_worker.create_transcriptions(
|
|
538
|
-
transcriptions=[
|
|
539
|
-
{
|
|
540
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
541
|
-
"text": "The",
|
|
542
|
-
"confidence": 0.75,
|
|
543
|
-
},
|
|
544
|
-
{
|
|
545
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
546
|
-
"text": "word",
|
|
547
|
-
"confidence": "a wrong confidence",
|
|
548
|
-
},
|
|
549
|
-
],
|
|
550
|
-
)
|
|
551
|
-
|
|
552
|
-
with pytest.raises(
|
|
553
|
-
AssertionError,
|
|
554
|
-
match=re.escape(
|
|
555
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
556
|
-
),
|
|
557
|
-
):
|
|
558
|
-
mock_elements_worker.create_transcriptions(
|
|
559
|
-
transcriptions=[
|
|
560
|
-
{
|
|
561
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
562
|
-
"text": "The",
|
|
563
|
-
"confidence": 0.75,
|
|
564
|
-
},
|
|
565
|
-
{
|
|
566
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
567
|
-
"text": "word",
|
|
568
|
-
"confidence": 0,
|
|
569
|
-
},
|
|
570
|
-
],
|
|
571
|
-
)
|
|
572
|
-
|
|
573
|
-
with pytest.raises(
|
|
574
|
-
AssertionError,
|
|
575
|
-
match=re.escape(
|
|
576
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
577
|
-
),
|
|
578
|
-
):
|
|
579
|
-
mock_elements_worker.create_transcriptions(
|
|
580
|
-
transcriptions=[
|
|
581
|
-
{
|
|
582
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
583
|
-
"text": "The",
|
|
584
|
-
"confidence": 0.75,
|
|
585
|
-
},
|
|
586
|
-
{
|
|
587
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
588
|
-
"text": "word",
|
|
589
|
-
"confidence": 2.00,
|
|
590
|
-
},
|
|
591
|
-
],
|
|
592
|
-
)
|
|
593
|
-
|
|
594
|
-
with pytest.raises(
|
|
595
|
-
AssertionError,
|
|
596
|
-
match="Transcription at index 1 in transcriptions: orientation shouldn't be null and should be of type TextOrientation",
|
|
597
|
-
):
|
|
598
|
-
mock_elements_worker.create_transcriptions(
|
|
599
|
-
transcriptions=[
|
|
600
|
-
{
|
|
601
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
602
|
-
"text": "The",
|
|
603
|
-
"confidence": 0.75,
|
|
604
|
-
},
|
|
605
|
-
{
|
|
606
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
607
|
-
"text": "word",
|
|
608
|
-
"confidence": 0.28,
|
|
609
|
-
"orientation": "wobble",
|
|
610
|
-
},
|
|
611
|
-
],
|
|
612
|
-
)
|
|
613
|
-
|
|
614
|
-
|
|
615
|
-
def test_create_transcriptions_api_error(responses, mock_elements_worker):
|
|
616
|
-
responses.add(
|
|
617
|
-
responses.POST,
|
|
618
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
619
|
-
status=418,
|
|
620
|
-
)
|
|
621
|
-
trans = [
|
|
622
|
-
{
|
|
623
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
624
|
-
"text": "The",
|
|
625
|
-
"confidence": 0.75,
|
|
626
|
-
},
|
|
627
|
-
{
|
|
628
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
629
|
-
"text": "word",
|
|
630
|
-
"confidence": 0.42,
|
|
631
|
-
},
|
|
632
|
-
]
|
|
633
|
-
|
|
634
|
-
with pytest.raises(ErrorResponse):
|
|
635
|
-
mock_elements_worker.create_transcriptions(transcriptions=trans)
|
|
636
|
-
|
|
637
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
638
|
-
assert [
|
|
639
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
640
|
-
] == BASE_API_CALLS + [("POST", "http://testserver/api/v1/transcription/bulk/")]
|
|
641
|
-
|
|
642
|
-
|
|
643
|
-
@pytest.mark.parametrize("batch_size", [DEFAULT_BATCH_SIZE, 1])
|
|
644
|
-
def test_create_transcriptions(batch_size, responses, mock_elements_worker_with_cache):
|
|
645
|
-
CachedElement.create(id="11111111-1111-1111-1111-111111111111", type="thing")
|
|
646
|
-
transcriptions = [
|
|
647
|
-
{
|
|
648
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
649
|
-
"text": "The",
|
|
650
|
-
"confidence": 0.75,
|
|
651
|
-
},
|
|
652
|
-
{
|
|
653
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
654
|
-
"text": "word",
|
|
655
|
-
"confidence": 0.42,
|
|
656
|
-
},
|
|
657
|
-
]
|
|
658
|
-
|
|
659
|
-
if batch_size > 1:
|
|
660
|
-
responses.add(
|
|
661
|
-
responses.POST,
|
|
662
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
663
|
-
status=200,
|
|
664
|
-
json={
|
|
665
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
666
|
-
"transcriptions": [
|
|
667
|
-
{
|
|
668
|
-
"id": "00000000-0000-0000-0000-000000000000",
|
|
669
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
670
|
-
"text": "The",
|
|
671
|
-
"orientation": "horizontal-lr",
|
|
672
|
-
"confidence": 0.75,
|
|
673
|
-
},
|
|
674
|
-
{
|
|
675
|
-
"id": "11111111-1111-1111-1111-111111111111",
|
|
676
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
677
|
-
"text": "word",
|
|
678
|
-
"orientation": "horizontal-lr",
|
|
679
|
-
"confidence": 0.42,
|
|
680
|
-
},
|
|
681
|
-
],
|
|
682
|
-
},
|
|
683
|
-
)
|
|
684
|
-
else:
|
|
685
|
-
for tr, tr_id in zip(
|
|
686
|
-
transcriptions,
|
|
687
|
-
[
|
|
688
|
-
"00000000-0000-0000-0000-000000000000",
|
|
689
|
-
"11111111-1111-1111-1111-111111111111",
|
|
690
|
-
],
|
|
691
|
-
strict=False,
|
|
692
|
-
):
|
|
693
|
-
responses.add(
|
|
694
|
-
responses.POST,
|
|
695
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
696
|
-
status=200,
|
|
697
|
-
json={
|
|
698
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
699
|
-
"transcriptions": [
|
|
700
|
-
{
|
|
701
|
-
"id": tr_id,
|
|
702
|
-
"element_id": tr["element_id"],
|
|
703
|
-
"text": tr["text"],
|
|
704
|
-
"orientation": "horizontal-lr",
|
|
705
|
-
"confidence": tr["confidence"],
|
|
706
|
-
}
|
|
707
|
-
],
|
|
708
|
-
},
|
|
709
|
-
)
|
|
710
|
-
|
|
711
|
-
mock_elements_worker_with_cache.create_transcriptions(
|
|
712
|
-
transcriptions=transcriptions,
|
|
713
|
-
batch_size=batch_size,
|
|
714
|
-
)
|
|
715
|
-
|
|
716
|
-
bulk_api_calls = [
|
|
717
|
-
(
|
|
718
|
-
"POST",
|
|
719
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
720
|
-
)
|
|
721
|
-
]
|
|
722
|
-
if batch_size != DEFAULT_BATCH_SIZE:
|
|
723
|
-
bulk_api_calls.append(
|
|
724
|
-
(
|
|
725
|
-
"POST",
|
|
726
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
727
|
-
)
|
|
728
|
-
)
|
|
729
|
-
|
|
730
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + len(bulk_api_calls)
|
|
731
|
-
assert [
|
|
732
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
733
|
-
] == BASE_API_CALLS + bulk_api_calls
|
|
734
|
-
|
|
735
|
-
first_tr = {
|
|
736
|
-
**transcriptions[0],
|
|
737
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
738
|
-
}
|
|
739
|
-
second_tr = {
|
|
740
|
-
**transcriptions[1],
|
|
741
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
742
|
-
}
|
|
743
|
-
empty_payload = {
|
|
744
|
-
"transcriptions": [],
|
|
745
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
746
|
-
}
|
|
747
|
-
|
|
748
|
-
bodies = []
|
|
749
|
-
first_call_idx = None
|
|
750
|
-
if batch_size > 1:
|
|
751
|
-
first_call_idx = -1
|
|
752
|
-
bodies.append({**empty_payload, "transcriptions": [first_tr, second_tr]})
|
|
753
|
-
else:
|
|
754
|
-
first_call_idx = -2
|
|
755
|
-
bodies.append({**empty_payload, "transcriptions": [first_tr]})
|
|
756
|
-
bodies.append({**empty_payload, "transcriptions": [second_tr]})
|
|
757
|
-
|
|
758
|
-
assert [
|
|
759
|
-
json.loads(bulk_call.request.body)
|
|
760
|
-
for bulk_call in responses.calls[first_call_idx:]
|
|
761
|
-
] == bodies
|
|
762
|
-
|
|
763
|
-
# Check that created transcriptions were properly stored in SQLite cache
|
|
764
|
-
assert list(CachedTranscription.select()) == [
|
|
765
|
-
CachedTranscription(
|
|
766
|
-
id=UUID("00000000-0000-0000-0000-000000000000"),
|
|
767
|
-
element_id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
768
|
-
text="The",
|
|
769
|
-
confidence=0.75,
|
|
770
|
-
orientation=TextOrientation.HorizontalLeftToRight,
|
|
771
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
772
|
-
),
|
|
773
|
-
CachedTranscription(
|
|
774
|
-
id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
775
|
-
element_id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
776
|
-
text="word",
|
|
777
|
-
confidence=0.42,
|
|
778
|
-
orientation=TextOrientation.HorizontalLeftToRight,
|
|
779
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
780
|
-
),
|
|
781
|
-
]
|
|
782
|
-
|
|
783
|
-
|
|
784
|
-
def test_create_transcriptions_orientation(responses, mock_elements_worker_with_cache):
|
|
785
|
-
CachedElement.create(id="11111111-1111-1111-1111-111111111111", type="thing")
|
|
786
|
-
trans = [
|
|
787
|
-
{
|
|
788
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
789
|
-
"text": "Animula vagula blandula",
|
|
790
|
-
"confidence": 0.12,
|
|
791
|
-
"orientation": TextOrientation.HorizontalRightToLeft,
|
|
792
|
-
},
|
|
793
|
-
{
|
|
794
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
795
|
-
"text": "Hospes comesque corporis",
|
|
796
|
-
"confidence": 0.21,
|
|
797
|
-
"orientation": TextOrientation.VerticalLeftToRight,
|
|
798
|
-
},
|
|
799
|
-
]
|
|
800
|
-
|
|
801
|
-
responses.add(
|
|
802
|
-
responses.POST,
|
|
803
|
-
"http://testserver/api/v1/transcription/bulk/",
|
|
804
|
-
status=200,
|
|
805
|
-
json={
|
|
806
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
807
|
-
"transcriptions": [
|
|
808
|
-
{
|
|
809
|
-
"id": "00000000-0000-0000-0000-000000000000",
|
|
810
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
811
|
-
"text": "Animula vagula blandula",
|
|
812
|
-
"orientation": "horizontal-rl",
|
|
813
|
-
"confidence": 0.12,
|
|
814
|
-
},
|
|
815
|
-
{
|
|
816
|
-
"id": "11111111-1111-1111-1111-111111111111",
|
|
817
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
818
|
-
"text": "Hospes comesque corporis",
|
|
819
|
-
"orientation": "vertical-lr",
|
|
820
|
-
"confidence": 0.21,
|
|
821
|
-
},
|
|
822
|
-
],
|
|
823
|
-
},
|
|
824
|
-
)
|
|
825
|
-
|
|
826
|
-
mock_elements_worker_with_cache.create_transcriptions(
|
|
827
|
-
transcriptions=trans,
|
|
828
|
-
)
|
|
829
|
-
|
|
830
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
831
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
832
|
-
"transcriptions": [
|
|
833
|
-
{
|
|
834
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
835
|
-
"text": "Animula vagula blandula",
|
|
836
|
-
"confidence": 0.12,
|
|
837
|
-
"orientation": TextOrientation.HorizontalRightToLeft.value,
|
|
838
|
-
},
|
|
839
|
-
{
|
|
840
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
841
|
-
"text": "Hospes comesque corporis",
|
|
842
|
-
"confidence": 0.21,
|
|
843
|
-
"orientation": TextOrientation.VerticalLeftToRight.value,
|
|
844
|
-
},
|
|
845
|
-
],
|
|
846
|
-
}
|
|
847
|
-
|
|
848
|
-
# Check that oriented transcriptions were properly stored in SQLite cache
|
|
849
|
-
assert list(map(model_to_dict, CachedTranscription.select())) == [
|
|
850
|
-
{
|
|
851
|
-
"id": UUID("00000000-0000-0000-0000-000000000000"),
|
|
852
|
-
"element": {
|
|
853
|
-
"id": UUID("11111111-1111-1111-1111-111111111111"),
|
|
854
|
-
"parent_id": None,
|
|
855
|
-
"type": "thing",
|
|
856
|
-
"image": None,
|
|
857
|
-
"polygon": None,
|
|
858
|
-
"rotation_angle": 0,
|
|
859
|
-
"mirrored": False,
|
|
860
|
-
"initial": False,
|
|
861
|
-
"worker_version_id": None,
|
|
862
|
-
"worker_run_id": None,
|
|
863
|
-
"confidence": None,
|
|
864
|
-
},
|
|
865
|
-
"text": "Animula vagula blandula",
|
|
866
|
-
"confidence": 0.12,
|
|
867
|
-
"orientation": TextOrientation.HorizontalRightToLeft.value,
|
|
868
|
-
"worker_version_id": None,
|
|
869
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
870
|
-
},
|
|
871
|
-
{
|
|
872
|
-
"id": UUID("11111111-1111-1111-1111-111111111111"),
|
|
873
|
-
"element": {
|
|
874
|
-
"id": UUID("11111111-1111-1111-1111-111111111111"),
|
|
875
|
-
"parent_id": None,
|
|
876
|
-
"type": "thing",
|
|
877
|
-
"image": None,
|
|
878
|
-
"polygon": None,
|
|
879
|
-
"rotation_angle": 0,
|
|
880
|
-
"mirrored": False,
|
|
881
|
-
"initial": False,
|
|
882
|
-
"worker_version_id": None,
|
|
883
|
-
"worker_run_id": None,
|
|
884
|
-
"confidence": None,
|
|
885
|
-
},
|
|
886
|
-
"text": "Hospes comesque corporis",
|
|
887
|
-
"confidence": 0.21,
|
|
888
|
-
"orientation": TextOrientation.VerticalLeftToRight.value,
|
|
889
|
-
"worker_version_id": None,
|
|
890
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
891
|
-
},
|
|
892
|
-
]
|
|
893
|
-
|
|
894
|
-
|
|
895
|
-
def test_create_element_transcriptions_wrong_element(mock_elements_worker):
|
|
896
|
-
with pytest.raises(
|
|
897
|
-
AssertionError,
|
|
898
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
899
|
-
):
|
|
900
|
-
mock_elements_worker.create_element_transcriptions(
|
|
901
|
-
element=None,
|
|
902
|
-
sub_element_type="page",
|
|
903
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
904
|
-
)
|
|
905
|
-
|
|
906
|
-
with pytest.raises(
|
|
907
|
-
AssertionError,
|
|
908
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
909
|
-
):
|
|
910
|
-
mock_elements_worker.create_element_transcriptions(
|
|
911
|
-
element="not element type",
|
|
912
|
-
sub_element_type="page",
|
|
913
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
914
|
-
)
|
|
915
|
-
|
|
916
|
-
|
|
917
|
-
def test_create_element_transcriptions_wrong_sub_element_type(mock_elements_worker):
|
|
918
|
-
elt = Element({"zone": None})
|
|
919
|
-
|
|
920
|
-
with pytest.raises(
|
|
921
|
-
AssertionError,
|
|
922
|
-
match="sub_element_type shouldn't be null and should be of type str",
|
|
923
|
-
):
|
|
924
|
-
mock_elements_worker.create_element_transcriptions(
|
|
925
|
-
element=elt,
|
|
926
|
-
sub_element_type=None,
|
|
927
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
928
|
-
)
|
|
929
|
-
|
|
930
|
-
with pytest.raises(
|
|
931
|
-
AssertionError,
|
|
932
|
-
match="sub_element_type shouldn't be null and should be of type str",
|
|
933
|
-
):
|
|
934
|
-
mock_elements_worker.create_element_transcriptions(
|
|
935
|
-
element=elt,
|
|
936
|
-
sub_element_type=1234,
|
|
937
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
938
|
-
)
|
|
939
|
-
|
|
940
|
-
|
|
941
|
-
def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker):
|
|
942
|
-
elt = Element({"zone": None})
|
|
943
|
-
|
|
944
|
-
with pytest.raises(
|
|
945
|
-
AssertionError,
|
|
946
|
-
match="transcriptions shouldn't be null and should be of type list",
|
|
947
|
-
):
|
|
948
|
-
mock_elements_worker.create_element_transcriptions(
|
|
949
|
-
element=elt,
|
|
950
|
-
sub_element_type="page",
|
|
951
|
-
transcriptions=None,
|
|
952
|
-
)
|
|
953
|
-
|
|
954
|
-
with pytest.raises(
|
|
955
|
-
AssertionError,
|
|
956
|
-
match="transcriptions shouldn't be null and should be of type list",
|
|
957
|
-
):
|
|
958
|
-
mock_elements_worker.create_element_transcriptions(
|
|
959
|
-
element=elt,
|
|
960
|
-
sub_element_type="page",
|
|
961
|
-
transcriptions=1234,
|
|
962
|
-
)
|
|
963
|
-
|
|
964
|
-
with pytest.raises(
|
|
965
|
-
AssertionError,
|
|
966
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
967
|
-
):
|
|
968
|
-
mock_elements_worker.create_element_transcriptions(
|
|
969
|
-
element=elt,
|
|
970
|
-
sub_element_type="page",
|
|
971
|
-
transcriptions=[
|
|
972
|
-
{
|
|
973
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
974
|
-
"confidence": 0.75,
|
|
975
|
-
"text": "The",
|
|
976
|
-
},
|
|
977
|
-
{
|
|
978
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
979
|
-
"confidence": 0.5,
|
|
980
|
-
},
|
|
981
|
-
],
|
|
982
|
-
)
|
|
983
|
-
|
|
984
|
-
with pytest.raises(
|
|
985
|
-
AssertionError,
|
|
986
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
987
|
-
):
|
|
988
|
-
mock_elements_worker.create_element_transcriptions(
|
|
989
|
-
element=elt,
|
|
990
|
-
sub_element_type="page",
|
|
991
|
-
transcriptions=[
|
|
992
|
-
{
|
|
993
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
994
|
-
"confidence": 0.75,
|
|
995
|
-
"text": "The",
|
|
996
|
-
},
|
|
997
|
-
{
|
|
998
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
999
|
-
"confidence": 0.5,
|
|
1000
|
-
"text": None,
|
|
1001
|
-
},
|
|
1002
|
-
],
|
|
1003
|
-
)
|
|
1004
|
-
|
|
1005
|
-
with pytest.raises(
|
|
1006
|
-
AssertionError,
|
|
1007
|
-
match="Transcription at index 1 in transcriptions: text shouldn't be null and should be of type str",
|
|
1008
|
-
):
|
|
1009
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1010
|
-
element=elt,
|
|
1011
|
-
sub_element_type="page",
|
|
1012
|
-
transcriptions=[
|
|
1013
|
-
{
|
|
1014
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1015
|
-
"confidence": 0.75,
|
|
1016
|
-
"text": "The",
|
|
1017
|
-
},
|
|
1018
|
-
{
|
|
1019
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1020
|
-
"confidence": 0.5,
|
|
1021
|
-
"text": 1234,
|
|
1022
|
-
},
|
|
1023
|
-
],
|
|
1024
|
-
)
|
|
1025
|
-
|
|
1026
|
-
with pytest.raises(
|
|
1027
|
-
AssertionError,
|
|
1028
|
-
match=re.escape(
|
|
1029
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
1030
|
-
),
|
|
1031
|
-
):
|
|
1032
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1033
|
-
element=elt,
|
|
1034
|
-
sub_element_type="page",
|
|
1035
|
-
transcriptions=[
|
|
1036
|
-
{
|
|
1037
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1038
|
-
"confidence": 0.75,
|
|
1039
|
-
"text": "The",
|
|
1040
|
-
},
|
|
1041
|
-
{
|
|
1042
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1043
|
-
"text": "word",
|
|
1044
|
-
},
|
|
1045
|
-
],
|
|
1046
|
-
)
|
|
1047
|
-
|
|
1048
|
-
with pytest.raises(
|
|
1049
|
-
AssertionError,
|
|
1050
|
-
match=re.escape(
|
|
1051
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
1052
|
-
),
|
|
1053
|
-
):
|
|
1054
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1055
|
-
element=elt,
|
|
1056
|
-
sub_element_type="page",
|
|
1057
|
-
transcriptions=[
|
|
1058
|
-
{
|
|
1059
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1060
|
-
"confidence": 0.75,
|
|
1061
|
-
"text": "The",
|
|
1062
|
-
},
|
|
1063
|
-
{
|
|
1064
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1065
|
-
"confidence": None,
|
|
1066
|
-
"text": "word",
|
|
1067
|
-
},
|
|
1068
|
-
],
|
|
1069
|
-
)
|
|
1070
|
-
|
|
1071
|
-
with pytest.raises(
|
|
1072
|
-
AssertionError,
|
|
1073
|
-
match=re.escape(
|
|
1074
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
1075
|
-
),
|
|
1076
|
-
):
|
|
1077
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1078
|
-
element=elt,
|
|
1079
|
-
sub_element_type="page",
|
|
1080
|
-
transcriptions=[
|
|
1081
|
-
{
|
|
1082
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1083
|
-
"confidence": 0.75,
|
|
1084
|
-
"text": "The",
|
|
1085
|
-
},
|
|
1086
|
-
{
|
|
1087
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1088
|
-
"confidence": "a wrong confidence",
|
|
1089
|
-
"text": "word",
|
|
1090
|
-
},
|
|
1091
|
-
],
|
|
1092
|
-
)
|
|
1093
|
-
|
|
1094
|
-
with pytest.raises(
|
|
1095
|
-
AssertionError,
|
|
1096
|
-
match=re.escape(
|
|
1097
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
1098
|
-
),
|
|
1099
|
-
):
|
|
1100
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1101
|
-
element=elt,
|
|
1102
|
-
sub_element_type="page",
|
|
1103
|
-
transcriptions=[
|
|
1104
|
-
{
|
|
1105
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1106
|
-
"confidence": 0.75,
|
|
1107
|
-
"text": "The",
|
|
1108
|
-
},
|
|
1109
|
-
{
|
|
1110
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1111
|
-
"confidence": 0,
|
|
1112
|
-
"text": "word",
|
|
1113
|
-
},
|
|
1114
|
-
],
|
|
1115
|
-
)
|
|
1116
|
-
|
|
1117
|
-
with pytest.raises(
|
|
1118
|
-
AssertionError,
|
|
1119
|
-
match=re.escape(
|
|
1120
|
-
"Transcription at index 1 in transcriptions: confidence shouldn't be null and should be a float in [0..1] range"
|
|
1121
|
-
),
|
|
1122
|
-
):
|
|
1123
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1124
|
-
element=elt,
|
|
1125
|
-
sub_element_type="page",
|
|
1126
|
-
transcriptions=[
|
|
1127
|
-
{
|
|
1128
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1129
|
-
"confidence": 0.75,
|
|
1130
|
-
"text": "The",
|
|
1131
|
-
},
|
|
1132
|
-
{
|
|
1133
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1134
|
-
"confidence": 2.00,
|
|
1135
|
-
"text": "word",
|
|
1136
|
-
},
|
|
1137
|
-
],
|
|
1138
|
-
)
|
|
1139
|
-
|
|
1140
|
-
with pytest.raises(
|
|
1141
|
-
AssertionError,
|
|
1142
|
-
match="Transcription at index 1 in transcriptions: polygon shouldn't be null and should be of type list",
|
|
1143
|
-
):
|
|
1144
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1145
|
-
element=elt,
|
|
1146
|
-
sub_element_type="page",
|
|
1147
|
-
transcriptions=[
|
|
1148
|
-
{
|
|
1149
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1150
|
-
"confidence": 0.75,
|
|
1151
|
-
"text": "The",
|
|
1152
|
-
},
|
|
1153
|
-
{"confidence": 0.5, "text": "word"},
|
|
1154
|
-
],
|
|
1155
|
-
)
|
|
1156
|
-
|
|
1157
|
-
with pytest.raises(
|
|
1158
|
-
AssertionError,
|
|
1159
|
-
match="Transcription at index 1 in transcriptions: polygon shouldn't be null and should be of type list",
|
|
1160
|
-
):
|
|
1161
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1162
|
-
element=elt,
|
|
1163
|
-
sub_element_type="page",
|
|
1164
|
-
transcriptions=[
|
|
1165
|
-
{
|
|
1166
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1167
|
-
"confidence": 0.75,
|
|
1168
|
-
"text": "The",
|
|
1169
|
-
},
|
|
1170
|
-
{"polygon": None, "confidence": 0.5, "text": "word"},
|
|
1171
|
-
],
|
|
1172
|
-
)
|
|
1173
|
-
|
|
1174
|
-
with pytest.raises(
|
|
1175
|
-
AssertionError,
|
|
1176
|
-
match="Transcription at index 1 in transcriptions: polygon shouldn't be null and should be of type list",
|
|
1177
|
-
):
|
|
1178
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1179
|
-
element=elt,
|
|
1180
|
-
sub_element_type="page",
|
|
1181
|
-
transcriptions=[
|
|
1182
|
-
{
|
|
1183
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1184
|
-
"confidence": 0.75,
|
|
1185
|
-
"text": "The",
|
|
1186
|
-
},
|
|
1187
|
-
{"polygon": "not a polygon", "confidence": 0.5, "text": "word"},
|
|
1188
|
-
],
|
|
1189
|
-
)
|
|
1190
|
-
|
|
1191
|
-
with pytest.raises(
|
|
1192
|
-
AssertionError,
|
|
1193
|
-
match="Transcription at index 1 in transcriptions: polygon should have at least three points",
|
|
1194
|
-
):
|
|
1195
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1196
|
-
element=elt,
|
|
1197
|
-
sub_element_type="page",
|
|
1198
|
-
transcriptions=[
|
|
1199
|
-
{
|
|
1200
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1201
|
-
"confidence": 0.75,
|
|
1202
|
-
"text": "The",
|
|
1203
|
-
},
|
|
1204
|
-
{"polygon": [[1, 1], [2, 2]], "confidence": 0.5, "text": "word"},
|
|
1205
|
-
],
|
|
1206
|
-
)
|
|
1207
|
-
with pytest.raises(
|
|
1208
|
-
AssertionError,
|
|
1209
|
-
match="Transcription at index 1 in transcriptions: polygon points should be lists of two items",
|
|
1210
|
-
):
|
|
1211
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1212
|
-
element=elt,
|
|
1213
|
-
sub_element_type="page",
|
|
1214
|
-
transcriptions=[
|
|
1215
|
-
{
|
|
1216
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1217
|
-
"confidence": 0.75,
|
|
1218
|
-
"text": "The",
|
|
1219
|
-
},
|
|
1220
|
-
{
|
|
1221
|
-
"polygon": [[1, 1, 1], [2, 2, 1], [2, 1, 1], [1, 2, 1]],
|
|
1222
|
-
"confidence": 0.5,
|
|
1223
|
-
"text": "word",
|
|
1224
|
-
},
|
|
1225
|
-
],
|
|
1226
|
-
)
|
|
1227
|
-
|
|
1228
|
-
with pytest.raises(
|
|
1229
|
-
AssertionError,
|
|
1230
|
-
match="Transcription at index 1 in transcriptions: polygon points should be lists of two items",
|
|
1231
|
-
):
|
|
1232
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1233
|
-
element=elt,
|
|
1234
|
-
sub_element_type="page",
|
|
1235
|
-
transcriptions=[
|
|
1236
|
-
{
|
|
1237
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1238
|
-
"confidence": 0.75,
|
|
1239
|
-
"text": "The",
|
|
1240
|
-
},
|
|
1241
|
-
{"polygon": [[1], [2], [2], [1]], "confidence": 0.5, "text": "word"},
|
|
1242
|
-
],
|
|
1243
|
-
)
|
|
1244
|
-
|
|
1245
|
-
with pytest.raises(
|
|
1246
|
-
AssertionError,
|
|
1247
|
-
match="Transcription at index 1 in transcriptions: polygon points should be lists of two numbers",
|
|
1248
|
-
):
|
|
1249
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1250
|
-
element=elt,
|
|
1251
|
-
sub_element_type="page",
|
|
1252
|
-
transcriptions=[
|
|
1253
|
-
{
|
|
1254
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1255
|
-
"confidence": 0.75,
|
|
1256
|
-
"text": "The",
|
|
1257
|
-
},
|
|
1258
|
-
{
|
|
1259
|
-
"polygon": [["not a coord", 1], [2, 2], [2, 1], [1, 2]],
|
|
1260
|
-
"confidence": 0.5,
|
|
1261
|
-
"text": "word",
|
|
1262
|
-
},
|
|
1263
|
-
],
|
|
1264
|
-
)
|
|
1265
|
-
|
|
1266
|
-
with pytest.raises(
|
|
1267
|
-
AssertionError,
|
|
1268
|
-
match="Transcription at index 1 in transcriptions: orientation shouldn't be null and should be of type TextOrientation",
|
|
1269
|
-
):
|
|
1270
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1271
|
-
element=elt,
|
|
1272
|
-
sub_element_type="page",
|
|
1273
|
-
transcriptions=[
|
|
1274
|
-
{
|
|
1275
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1276
|
-
"confidence": 0.75,
|
|
1277
|
-
"text": "The",
|
|
1278
|
-
},
|
|
1279
|
-
{
|
|
1280
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1281
|
-
"confidence": 0.35,
|
|
1282
|
-
"text": "word",
|
|
1283
|
-
"orientation": "uptown",
|
|
1284
|
-
},
|
|
1285
|
-
],
|
|
1286
|
-
)
|
|
1287
|
-
|
|
1288
|
-
with pytest.raises(
|
|
1289
|
-
AssertionError,
|
|
1290
|
-
match=re.escape(
|
|
1291
|
-
"Transcription at index 1 in transcriptions: element_confidence should be either null or a float in [0..1] range"
|
|
1292
|
-
),
|
|
1293
|
-
):
|
|
1294
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1295
|
-
element=elt,
|
|
1296
|
-
sub_element_type="page",
|
|
1297
|
-
transcriptions=[
|
|
1298
|
-
{
|
|
1299
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1300
|
-
"confidence": 0.75,
|
|
1301
|
-
"text": "The",
|
|
1302
|
-
},
|
|
1303
|
-
{
|
|
1304
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1305
|
-
"confidence": 0.75,
|
|
1306
|
-
"text": "word",
|
|
1307
|
-
"element_confidence": "not a confidence",
|
|
1308
|
-
},
|
|
1309
|
-
],
|
|
1310
|
-
)
|
|
1311
|
-
|
|
1312
|
-
|
|
1313
|
-
def test_create_element_transcriptions_api_error(responses, mock_elements_worker):
|
|
1314
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1315
|
-
responses.add(
|
|
1316
|
-
responses.POST,
|
|
1317
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1318
|
-
status=418,
|
|
1319
|
-
)
|
|
1320
|
-
|
|
1321
|
-
with pytest.raises(ErrorResponse):
|
|
1322
|
-
mock_elements_worker.create_element_transcriptions(
|
|
1323
|
-
element=elt,
|
|
1324
|
-
sub_element_type="page",
|
|
1325
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
1326
|
-
)
|
|
1327
|
-
|
|
1328
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
1329
|
-
assert [
|
|
1330
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
1331
|
-
] == BASE_API_CALLS + [
|
|
1332
|
-
("POST", f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/")
|
|
1333
|
-
]
|
|
1334
|
-
|
|
1335
|
-
|
|
1336
|
-
@pytest.mark.parametrize("batch_size", [DEFAULT_BATCH_SIZE, 2])
|
|
1337
|
-
def test_create_element_transcriptions(batch_size, responses, mock_elements_worker):
|
|
1338
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1339
|
-
|
|
1340
|
-
if batch_size > 2:
|
|
1341
|
-
responses.add(
|
|
1342
|
-
responses.POST,
|
|
1343
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1344
|
-
status=200,
|
|
1345
|
-
json=[
|
|
1346
|
-
{
|
|
1347
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1348
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1349
|
-
"created": True,
|
|
1350
|
-
},
|
|
1351
|
-
{
|
|
1352
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1353
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1354
|
-
"created": False,
|
|
1355
|
-
},
|
|
1356
|
-
{
|
|
1357
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1358
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1359
|
-
"created": True,
|
|
1360
|
-
},
|
|
1361
|
-
],
|
|
1362
|
-
)
|
|
1363
|
-
else:
|
|
1364
|
-
for transcriptions in [
|
|
1365
|
-
[
|
|
1366
|
-
("56785678-5678-5678-5678-567856785678", True),
|
|
1367
|
-
("67896789-6789-6789-6789-678967896789", False),
|
|
1368
|
-
],
|
|
1369
|
-
[("78907890-7890-7890-7890-789078907890", True)],
|
|
1370
|
-
]:
|
|
1371
|
-
responses.add(
|
|
1372
|
-
responses.POST,
|
|
1373
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1374
|
-
status=200,
|
|
1375
|
-
json=[
|
|
1376
|
-
{
|
|
1377
|
-
"id": tr_id,
|
|
1378
|
-
"element_id": "11111111-1111-1111-1111-111111111111"
|
|
1379
|
-
if created
|
|
1380
|
-
else "22222222-2222-2222-2222-222222222222",
|
|
1381
|
-
"created": created,
|
|
1382
|
-
}
|
|
1383
|
-
for tr_id, created in transcriptions
|
|
1384
|
-
],
|
|
1385
|
-
)
|
|
1386
|
-
|
|
1387
|
-
annotations = mock_elements_worker.create_element_transcriptions(
|
|
1388
|
-
element=elt,
|
|
1389
|
-
sub_element_type="page",
|
|
1390
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
1391
|
-
batch_size=batch_size,
|
|
1392
|
-
)
|
|
1393
|
-
|
|
1394
|
-
bulk_api_calls = [
|
|
1395
|
-
(
|
|
1396
|
-
"POST",
|
|
1397
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1398
|
-
)
|
|
1399
|
-
]
|
|
1400
|
-
if batch_size != DEFAULT_BATCH_SIZE:
|
|
1401
|
-
bulk_api_calls.append(
|
|
1402
|
-
(
|
|
1403
|
-
"POST",
|
|
1404
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1405
|
-
)
|
|
1406
|
-
)
|
|
1407
|
-
|
|
1408
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + len(bulk_api_calls)
|
|
1409
|
-
assert [
|
|
1410
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
1411
|
-
] == BASE_API_CALLS + bulk_api_calls
|
|
1412
|
-
|
|
1413
|
-
first_tr = {
|
|
1414
|
-
**TRANSCRIPTIONS_SAMPLE[0],
|
|
1415
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1416
|
-
}
|
|
1417
|
-
second_tr = {
|
|
1418
|
-
**TRANSCRIPTIONS_SAMPLE[1],
|
|
1419
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1420
|
-
}
|
|
1421
|
-
third_tr = {
|
|
1422
|
-
**TRANSCRIPTIONS_SAMPLE[2],
|
|
1423
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1424
|
-
}
|
|
1425
|
-
empty_payload = {
|
|
1426
|
-
"element_type": "page",
|
|
1427
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1428
|
-
"transcriptions": [],
|
|
1429
|
-
"return_elements": True,
|
|
1430
|
-
}
|
|
1431
|
-
|
|
1432
|
-
bodies = []
|
|
1433
|
-
first_call_idx = None
|
|
1434
|
-
if batch_size > 2:
|
|
1435
|
-
first_call_idx = -1
|
|
1436
|
-
bodies.append(
|
|
1437
|
-
{**empty_payload, "transcriptions": [first_tr, second_tr, third_tr]}
|
|
1438
|
-
)
|
|
1439
|
-
else:
|
|
1440
|
-
first_call_idx = -2
|
|
1441
|
-
bodies.append({**empty_payload, "transcriptions": [first_tr, second_tr]})
|
|
1442
|
-
bodies.append({**empty_payload, "transcriptions": [third_tr]})
|
|
1443
|
-
|
|
1444
|
-
assert [
|
|
1445
|
-
json.loads(bulk_call.request.body)
|
|
1446
|
-
for bulk_call in responses.calls[first_call_idx:]
|
|
1447
|
-
] == bodies
|
|
1448
|
-
|
|
1449
|
-
assert annotations == [
|
|
1450
|
-
{
|
|
1451
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1452
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1453
|
-
"created": True,
|
|
1454
|
-
},
|
|
1455
|
-
{
|
|
1456
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1457
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1458
|
-
"created": False,
|
|
1459
|
-
},
|
|
1460
|
-
{
|
|
1461
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1462
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1463
|
-
"created": True,
|
|
1464
|
-
},
|
|
1465
|
-
]
|
|
1466
|
-
|
|
1467
|
-
|
|
1468
|
-
@pytest.mark.parametrize("batch_size", [DEFAULT_BATCH_SIZE, 2])
|
|
1469
|
-
def test_create_element_transcriptions_with_cache(
|
|
1470
|
-
batch_size, responses, mock_elements_worker_with_cache
|
|
1471
|
-
):
|
|
1472
|
-
elt = CachedElement(id="12341234-1234-1234-1234-123412341234", type="thing")
|
|
1473
|
-
|
|
1474
|
-
if batch_size > 2:
|
|
1475
|
-
responses.add(
|
|
1476
|
-
responses.POST,
|
|
1477
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1478
|
-
status=200,
|
|
1479
|
-
json=[
|
|
1480
|
-
{
|
|
1481
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1482
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1483
|
-
"created": True,
|
|
1484
|
-
},
|
|
1485
|
-
{
|
|
1486
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1487
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1488
|
-
"created": False,
|
|
1489
|
-
},
|
|
1490
|
-
{
|
|
1491
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1492
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1493
|
-
"created": True,
|
|
1494
|
-
},
|
|
1495
|
-
],
|
|
1496
|
-
)
|
|
1497
|
-
else:
|
|
1498
|
-
for transcriptions in [
|
|
1499
|
-
[
|
|
1500
|
-
("56785678-5678-5678-5678-567856785678", True),
|
|
1501
|
-
("67896789-6789-6789-6789-678967896789", False),
|
|
1502
|
-
],
|
|
1503
|
-
[("78907890-7890-7890-7890-789078907890", True)],
|
|
1504
|
-
]:
|
|
1505
|
-
responses.add(
|
|
1506
|
-
responses.POST,
|
|
1507
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1508
|
-
status=200,
|
|
1509
|
-
json=[
|
|
1510
|
-
{
|
|
1511
|
-
"id": tr_id,
|
|
1512
|
-
"element_id": "11111111-1111-1111-1111-111111111111"
|
|
1513
|
-
if created
|
|
1514
|
-
else "22222222-2222-2222-2222-222222222222",
|
|
1515
|
-
"created": created,
|
|
1516
|
-
}
|
|
1517
|
-
for tr_id, created in transcriptions
|
|
1518
|
-
],
|
|
1519
|
-
)
|
|
1520
|
-
|
|
1521
|
-
annotations = mock_elements_worker_with_cache.create_element_transcriptions(
|
|
1522
|
-
element=elt,
|
|
1523
|
-
sub_element_type="page",
|
|
1524
|
-
transcriptions=TRANSCRIPTIONS_SAMPLE,
|
|
1525
|
-
batch_size=batch_size,
|
|
1526
|
-
)
|
|
1527
|
-
|
|
1528
|
-
bulk_api_calls = [
|
|
1529
|
-
(
|
|
1530
|
-
"POST",
|
|
1531
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1532
|
-
)
|
|
1533
|
-
]
|
|
1534
|
-
if batch_size != DEFAULT_BATCH_SIZE:
|
|
1535
|
-
bulk_api_calls.append(
|
|
1536
|
-
(
|
|
1537
|
-
"POST",
|
|
1538
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1539
|
-
)
|
|
1540
|
-
)
|
|
1541
|
-
|
|
1542
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + len(bulk_api_calls)
|
|
1543
|
-
assert [
|
|
1544
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
1545
|
-
] == BASE_API_CALLS + bulk_api_calls
|
|
1546
|
-
|
|
1547
|
-
first_tr = {
|
|
1548
|
-
**TRANSCRIPTIONS_SAMPLE[0],
|
|
1549
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1550
|
-
}
|
|
1551
|
-
second_tr = {
|
|
1552
|
-
**TRANSCRIPTIONS_SAMPLE[1],
|
|
1553
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1554
|
-
"element_confidence": 0.75,
|
|
1555
|
-
}
|
|
1556
|
-
third_tr = {
|
|
1557
|
-
**TRANSCRIPTIONS_SAMPLE[2],
|
|
1558
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1559
|
-
}
|
|
1560
|
-
empty_payload = {
|
|
1561
|
-
"element_type": "page",
|
|
1562
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1563
|
-
"transcriptions": [],
|
|
1564
|
-
"return_elements": True,
|
|
1565
|
-
}
|
|
1566
|
-
|
|
1567
|
-
bodies = []
|
|
1568
|
-
first_call_idx = None
|
|
1569
|
-
if batch_size > 2:
|
|
1570
|
-
first_call_idx = -1
|
|
1571
|
-
bodies.append(
|
|
1572
|
-
{**empty_payload, "transcriptions": [first_tr, second_tr, third_tr]}
|
|
1573
|
-
)
|
|
1574
|
-
else:
|
|
1575
|
-
first_call_idx = -2
|
|
1576
|
-
bodies.append({**empty_payload, "transcriptions": [first_tr, second_tr]})
|
|
1577
|
-
bodies.append({**empty_payload, "transcriptions": [third_tr]})
|
|
1578
|
-
|
|
1579
|
-
assert [
|
|
1580
|
-
json.loads(bulk_call.request.body)
|
|
1581
|
-
for bulk_call in responses.calls[first_call_idx:]
|
|
1582
|
-
] == bodies
|
|
1583
|
-
|
|
1584
|
-
assert annotations == [
|
|
1585
|
-
{
|
|
1586
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1587
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1588
|
-
"created": True,
|
|
1589
|
-
},
|
|
1590
|
-
{
|
|
1591
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1592
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1593
|
-
"created": False,
|
|
1594
|
-
},
|
|
1595
|
-
{
|
|
1596
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1597
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1598
|
-
"created": True,
|
|
1599
|
-
},
|
|
1600
|
-
]
|
|
1601
|
-
|
|
1602
|
-
# Check that created transcriptions and elements were properly stored in SQLite cache
|
|
1603
|
-
assert list(CachedElement.select()) == [
|
|
1604
|
-
CachedElement(
|
|
1605
|
-
id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
1606
|
-
parent_id=UUID("12341234-1234-1234-1234-123412341234"),
|
|
1607
|
-
type="page",
|
|
1608
|
-
polygon="[[100, 150], [700, 150], [700, 200], [100, 200]]",
|
|
1609
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1610
|
-
),
|
|
1611
|
-
CachedElement(
|
|
1612
|
-
id=UUID("22222222-2222-2222-2222-222222222222"),
|
|
1613
|
-
parent_id=UUID("12341234-1234-1234-1234-123412341234"),
|
|
1614
|
-
type="page",
|
|
1615
|
-
polygon="[[0, 0], [2000, 0], [2000, 3000], [0, 3000]]",
|
|
1616
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1617
|
-
confidence=0.75,
|
|
1618
|
-
),
|
|
1619
|
-
]
|
|
1620
|
-
assert list(CachedTranscription.select()) == [
|
|
1621
|
-
CachedTranscription(
|
|
1622
|
-
id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1623
|
-
element_id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
1624
|
-
text="The",
|
|
1625
|
-
confidence=0.5,
|
|
1626
|
-
orientation=TextOrientation.HorizontalLeftToRight.value,
|
|
1627
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1628
|
-
),
|
|
1629
|
-
CachedTranscription(
|
|
1630
|
-
id=UUID("67896789-6789-6789-6789-678967896789"),
|
|
1631
|
-
element_id=UUID("22222222-2222-2222-2222-222222222222"),
|
|
1632
|
-
text="first",
|
|
1633
|
-
confidence=0.75,
|
|
1634
|
-
orientation=TextOrientation.HorizontalLeftToRight.value,
|
|
1635
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1636
|
-
),
|
|
1637
|
-
CachedTranscription(
|
|
1638
|
-
id=UUID("78907890-7890-7890-7890-789078907890"),
|
|
1639
|
-
element_id=UUID("11111111-1111-1111-1111-111111111111"),
|
|
1640
|
-
text="line",
|
|
1641
|
-
confidence=0.9,
|
|
1642
|
-
orientation=TextOrientation.HorizontalLeftToRight.value,
|
|
1643
|
-
worker_run_id=UUID("56785678-5678-5678-5678-567856785678"),
|
|
1644
|
-
),
|
|
1645
|
-
]
|
|
1646
|
-
|
|
1647
|
-
|
|
1648
|
-
def test_create_transcriptions_orientation_with_cache(
|
|
1649
|
-
responses, mock_elements_worker_with_cache
|
|
1650
|
-
):
|
|
1651
|
-
elt = CachedElement(id="12341234-1234-1234-1234-123412341234", type="thing")
|
|
1652
|
-
|
|
1653
|
-
responses.add(
|
|
1654
|
-
responses.POST,
|
|
1655
|
-
f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
|
|
1656
|
-
status=200,
|
|
1657
|
-
json=[
|
|
1658
|
-
{
|
|
1659
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1660
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1661
|
-
"created": True,
|
|
1662
|
-
},
|
|
1663
|
-
{
|
|
1664
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1665
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1666
|
-
"created": False,
|
|
1667
|
-
},
|
|
1668
|
-
{
|
|
1669
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1670
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1671
|
-
"created": True,
|
|
1672
|
-
},
|
|
1673
|
-
],
|
|
1674
|
-
)
|
|
1675
|
-
|
|
1676
|
-
oriented_transcriptions = [
|
|
1677
|
-
{
|
|
1678
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1679
|
-
"confidence": 0.5,
|
|
1680
|
-
"text": "Animula vagula blandula",
|
|
1681
|
-
},
|
|
1682
|
-
{
|
|
1683
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1684
|
-
"confidence": 0.75,
|
|
1685
|
-
"text": "Hospes comesque corporis",
|
|
1686
|
-
"orientation": TextOrientation.VerticalLeftToRight,
|
|
1687
|
-
},
|
|
1688
|
-
{
|
|
1689
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1690
|
-
"confidence": 0.9,
|
|
1691
|
-
"text": "Quae nunc abibis in loca",
|
|
1692
|
-
"orientation": TextOrientation.HorizontalRightToLeft,
|
|
1693
|
-
},
|
|
1694
|
-
]
|
|
1695
|
-
|
|
1696
|
-
annotations = mock_elements_worker_with_cache.create_element_transcriptions(
|
|
1697
|
-
element=elt,
|
|
1698
|
-
sub_element_type="page",
|
|
1699
|
-
transcriptions=oriented_transcriptions,
|
|
1700
|
-
)
|
|
1701
|
-
|
|
1702
|
-
assert json.loads(responses.calls[-1].request.body) == {
|
|
1703
|
-
"element_type": "page",
|
|
1704
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1705
|
-
"transcriptions": [
|
|
1706
|
-
{
|
|
1707
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1708
|
-
"confidence": 0.5,
|
|
1709
|
-
"text": "Animula vagula blandula",
|
|
1710
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1711
|
-
},
|
|
1712
|
-
{
|
|
1713
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1714
|
-
"confidence": 0.75,
|
|
1715
|
-
"text": "Hospes comesque corporis",
|
|
1716
|
-
"orientation": TextOrientation.VerticalLeftToRight.value,
|
|
1717
|
-
},
|
|
1718
|
-
{
|
|
1719
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1720
|
-
"confidence": 0.9,
|
|
1721
|
-
"text": "Quae nunc abibis in loca",
|
|
1722
|
-
"orientation": TextOrientation.HorizontalRightToLeft.value,
|
|
1723
|
-
},
|
|
1724
|
-
],
|
|
1725
|
-
"return_elements": True,
|
|
1726
|
-
}
|
|
1727
|
-
assert annotations == [
|
|
1728
|
-
{
|
|
1729
|
-
"id": "56785678-5678-5678-5678-567856785678",
|
|
1730
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1731
|
-
"created": True,
|
|
1732
|
-
},
|
|
1733
|
-
{
|
|
1734
|
-
"id": "67896789-6789-6789-6789-678967896789",
|
|
1735
|
-
"element_id": "22222222-2222-2222-2222-222222222222",
|
|
1736
|
-
"created": False,
|
|
1737
|
-
},
|
|
1738
|
-
{
|
|
1739
|
-
"id": "78907890-7890-7890-7890-789078907890",
|
|
1740
|
-
"element_id": "11111111-1111-1111-1111-111111111111",
|
|
1741
|
-
"created": True,
|
|
1742
|
-
},
|
|
1743
|
-
]
|
|
1744
|
-
|
|
1745
|
-
# Check that the text orientation was properly stored in SQLite cache
|
|
1746
|
-
assert list(map(model_to_dict, CachedTranscription.select())) == [
|
|
1747
|
-
{
|
|
1748
|
-
"id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1749
|
-
"element": {
|
|
1750
|
-
"id": UUID("11111111-1111-1111-1111-111111111111"),
|
|
1751
|
-
"parent_id": UUID(elt.id),
|
|
1752
|
-
"type": "page",
|
|
1753
|
-
"image": None,
|
|
1754
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1755
|
-
"rotation_angle": 0,
|
|
1756
|
-
"mirrored": False,
|
|
1757
|
-
"initial": False,
|
|
1758
|
-
"worker_version_id": None,
|
|
1759
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1760
|
-
"confidence": None,
|
|
1761
|
-
},
|
|
1762
|
-
"text": "Animula vagula blandula",
|
|
1763
|
-
"confidence": 0.5,
|
|
1764
|
-
"orientation": TextOrientation.HorizontalLeftToRight.value,
|
|
1765
|
-
"worker_version_id": None,
|
|
1766
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1767
|
-
},
|
|
1768
|
-
{
|
|
1769
|
-
"id": UUID("67896789-6789-6789-6789-678967896789"),
|
|
1770
|
-
"element": {
|
|
1771
|
-
"id": UUID("22222222-2222-2222-2222-222222222222"),
|
|
1772
|
-
"parent_id": UUID(elt.id),
|
|
1773
|
-
"type": "page",
|
|
1774
|
-
"image": None,
|
|
1775
|
-
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
|
|
1776
|
-
"rotation_angle": 0,
|
|
1777
|
-
"mirrored": False,
|
|
1778
|
-
"initial": False,
|
|
1779
|
-
"worker_version_id": None,
|
|
1780
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1781
|
-
"confidence": None,
|
|
1782
|
-
},
|
|
1783
|
-
"text": "Hospes comesque corporis",
|
|
1784
|
-
"confidence": 0.75,
|
|
1785
|
-
"orientation": TextOrientation.VerticalLeftToRight.value,
|
|
1786
|
-
"worker_version_id": None,
|
|
1787
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1788
|
-
},
|
|
1789
|
-
{
|
|
1790
|
-
"id": UUID("78907890-7890-7890-7890-789078907890"),
|
|
1791
|
-
"element": {
|
|
1792
|
-
"id": UUID("11111111-1111-1111-1111-111111111111"),
|
|
1793
|
-
"parent_id": UUID(elt.id),
|
|
1794
|
-
"type": "page",
|
|
1795
|
-
"image": None,
|
|
1796
|
-
"polygon": [[100, 150], [700, 150], [700, 200], [100, 200]],
|
|
1797
|
-
"rotation_angle": 0,
|
|
1798
|
-
"mirrored": False,
|
|
1799
|
-
"initial": False,
|
|
1800
|
-
"worker_version_id": None,
|
|
1801
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1802
|
-
"confidence": None,
|
|
1803
|
-
},
|
|
1804
|
-
"text": "Quae nunc abibis in loca",
|
|
1805
|
-
"confidence": 0.9,
|
|
1806
|
-
"orientation": TextOrientation.HorizontalRightToLeft.value,
|
|
1807
|
-
"worker_version_id": None,
|
|
1808
|
-
"worker_run_id": UUID("56785678-5678-5678-5678-567856785678"),
|
|
1809
|
-
},
|
|
1810
|
-
]
|
|
1811
|
-
|
|
1812
|
-
|
|
1813
|
-
def test_list_transcriptions_wrong_element(mock_elements_worker):
|
|
1814
|
-
with pytest.raises(
|
|
1815
|
-
AssertionError,
|
|
1816
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
1817
|
-
):
|
|
1818
|
-
mock_elements_worker.list_transcriptions(element=None)
|
|
1819
|
-
|
|
1820
|
-
with pytest.raises(
|
|
1821
|
-
AssertionError,
|
|
1822
|
-
match="element shouldn't be null and should be an Element or CachedElement",
|
|
1823
|
-
):
|
|
1824
|
-
mock_elements_worker.list_transcriptions(element="not element type")
|
|
1825
|
-
|
|
1826
|
-
|
|
1827
|
-
def test_list_transcriptions_wrong_element_type(mock_elements_worker):
|
|
1828
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1829
|
-
|
|
1830
|
-
with pytest.raises(AssertionError, match="element_type should be of type str"):
|
|
1831
|
-
mock_elements_worker.list_transcriptions(
|
|
1832
|
-
element=elt,
|
|
1833
|
-
element_type=1234,
|
|
1834
|
-
)
|
|
1835
|
-
|
|
1836
|
-
|
|
1837
|
-
def test_list_transcriptions_wrong_recursive(mock_elements_worker):
|
|
1838
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1839
|
-
|
|
1840
|
-
with pytest.raises(AssertionError, match="recursive should be of type bool"):
|
|
1841
|
-
mock_elements_worker.list_transcriptions(
|
|
1842
|
-
element=elt,
|
|
1843
|
-
recursive="not bool",
|
|
1844
|
-
)
|
|
1845
|
-
|
|
1846
|
-
|
|
1847
|
-
def test_list_transcriptions_wrong_worker_run(mock_elements_worker):
|
|
1848
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1849
|
-
|
|
1850
|
-
with pytest.raises(
|
|
1851
|
-
AssertionError, match="worker_run should be of type str or bool"
|
|
1852
|
-
):
|
|
1853
|
-
mock_elements_worker.list_transcriptions(
|
|
1854
|
-
element=elt,
|
|
1855
|
-
worker_run=1234,
|
|
1856
|
-
)
|
|
1857
|
-
|
|
1858
|
-
|
|
1859
|
-
def test_list_transcriptions_wrong_worker_version(mock_elements_worker):
|
|
1860
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1861
|
-
|
|
1862
|
-
# WARNING: pytest.deprecated_call must be placed BEFORE pytest.raises, otherwise `match` argument won't be checked
|
|
1863
|
-
with (
|
|
1864
|
-
pytest.deprecated_call(
|
|
1865
|
-
match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
|
|
1866
|
-
),
|
|
1867
|
-
pytest.raises(
|
|
1868
|
-
AssertionError, match="worker_version should be of type str or bool"
|
|
1869
|
-
),
|
|
1870
|
-
):
|
|
1871
|
-
mock_elements_worker.list_transcriptions(
|
|
1872
|
-
element=elt,
|
|
1873
|
-
worker_version=1234,
|
|
1874
|
-
)
|
|
1875
|
-
|
|
1876
|
-
|
|
1877
|
-
def test_list_transcriptions_wrong_bool_worker_run(mock_elements_worker):
|
|
1878
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1879
|
-
|
|
1880
|
-
with pytest.raises(
|
|
1881
|
-
AssertionError, match="if of type bool, worker_run can only be set to False"
|
|
1882
|
-
):
|
|
1883
|
-
mock_elements_worker.list_transcriptions(
|
|
1884
|
-
element=elt,
|
|
1885
|
-
worker_run=True,
|
|
1886
|
-
)
|
|
1887
|
-
|
|
1888
|
-
|
|
1889
|
-
def test_list_transcriptions_wrong_bool_worker_version(mock_elements_worker):
|
|
1890
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1891
|
-
|
|
1892
|
-
# WARNING: pytest.deprecated_call must be placed BEFORE pytest.raises, otherwise `match` argument won't be checked
|
|
1893
|
-
with (
|
|
1894
|
-
pytest.deprecated_call(
|
|
1895
|
-
match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
|
|
1896
|
-
),
|
|
1897
|
-
pytest.raises(
|
|
1898
|
-
AssertionError,
|
|
1899
|
-
match="if of type bool, worker_version can only be set to False",
|
|
1900
|
-
),
|
|
1901
|
-
):
|
|
1902
|
-
mock_elements_worker.list_transcriptions(
|
|
1903
|
-
element=elt,
|
|
1904
|
-
worker_version=True,
|
|
1905
|
-
)
|
|
1906
|
-
|
|
1907
|
-
|
|
1908
|
-
def test_list_transcriptions_api_error(responses, mock_elements_worker):
|
|
1909
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1910
|
-
responses.add(
|
|
1911
|
-
responses.GET,
|
|
1912
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1913
|
-
status=418,
|
|
1914
|
-
)
|
|
1915
|
-
|
|
1916
|
-
with pytest.raises(
|
|
1917
|
-
Exception, match="Stopping pagination as data will be incomplete"
|
|
1918
|
-
):
|
|
1919
|
-
next(mock_elements_worker.list_transcriptions(element=elt))
|
|
1920
|
-
|
|
1921
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 5
|
|
1922
|
-
assert [
|
|
1923
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
1924
|
-
] == BASE_API_CALLS + [
|
|
1925
|
-
# We do 5 retries
|
|
1926
|
-
(
|
|
1927
|
-
"GET",
|
|
1928
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1929
|
-
),
|
|
1930
|
-
(
|
|
1931
|
-
"GET",
|
|
1932
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1933
|
-
),
|
|
1934
|
-
(
|
|
1935
|
-
"GET",
|
|
1936
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1937
|
-
),
|
|
1938
|
-
(
|
|
1939
|
-
"GET",
|
|
1940
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1941
|
-
),
|
|
1942
|
-
(
|
|
1943
|
-
"GET",
|
|
1944
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1945
|
-
),
|
|
1946
|
-
]
|
|
1947
|
-
|
|
1948
|
-
|
|
1949
|
-
def test_list_transcriptions(responses, mock_elements_worker):
|
|
1950
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
1951
|
-
trans = [
|
|
1952
|
-
{
|
|
1953
|
-
"id": "0000",
|
|
1954
|
-
"text": "hey",
|
|
1955
|
-
"confidence": 0.42,
|
|
1956
|
-
"worker_version_id": "56785678-5678-5678-5678-567856785678",
|
|
1957
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1958
|
-
"element": None,
|
|
1959
|
-
},
|
|
1960
|
-
{
|
|
1961
|
-
"id": "1111",
|
|
1962
|
-
"text": "it's",
|
|
1963
|
-
"confidence": 0.42,
|
|
1964
|
-
"worker_version_id": "56785678-5678-5678-5678-567856785678",
|
|
1965
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1966
|
-
"element": None,
|
|
1967
|
-
},
|
|
1968
|
-
{
|
|
1969
|
-
"id": "2222",
|
|
1970
|
-
"text": "me",
|
|
1971
|
-
"confidence": 0.42,
|
|
1972
|
-
"worker_version_id": "56785678-5678-5678-5678-567856785678",
|
|
1973
|
-
"worker_run_id": "56785678-5678-5678-5678-567856785678",
|
|
1974
|
-
"element": None,
|
|
1975
|
-
},
|
|
1976
|
-
]
|
|
1977
|
-
responses.add(
|
|
1978
|
-
responses.GET,
|
|
1979
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
1980
|
-
status=200,
|
|
1981
|
-
json={
|
|
1982
|
-
"count": 3,
|
|
1983
|
-
"next": None,
|
|
1984
|
-
"results": trans,
|
|
1985
|
-
},
|
|
1986
|
-
)
|
|
1987
|
-
|
|
1988
|
-
for idx, transcription in enumerate(
|
|
1989
|
-
mock_elements_worker.list_transcriptions(element=elt)
|
|
1990
|
-
):
|
|
1991
|
-
assert transcription == trans[idx]
|
|
1992
|
-
|
|
1993
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
1994
|
-
assert [
|
|
1995
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
1996
|
-
] == BASE_API_CALLS + [
|
|
1997
|
-
(
|
|
1998
|
-
"GET",
|
|
1999
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/",
|
|
2000
|
-
),
|
|
2001
|
-
]
|
|
2002
|
-
|
|
2003
|
-
|
|
2004
|
-
def test_list_transcriptions_manual_worker_version(responses, mock_elements_worker):
|
|
2005
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
2006
|
-
trans = [
|
|
2007
|
-
{
|
|
2008
|
-
"id": "0000",
|
|
2009
|
-
"text": "hey",
|
|
2010
|
-
"confidence": 0.42,
|
|
2011
|
-
"worker_version_id": None,
|
|
2012
|
-
"worker_run_id": None,
|
|
2013
|
-
"element": None,
|
|
2014
|
-
}
|
|
2015
|
-
]
|
|
2016
|
-
responses.add(
|
|
2017
|
-
responses.GET,
|
|
2018
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/?worker_version=False",
|
|
2019
|
-
status=200,
|
|
2020
|
-
json={
|
|
2021
|
-
"count": 1,
|
|
2022
|
-
"next": None,
|
|
2023
|
-
"results": trans,
|
|
2024
|
-
},
|
|
2025
|
-
)
|
|
2026
|
-
|
|
2027
|
-
with pytest.deprecated_call(
|
|
2028
|
-
match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
|
|
2029
|
-
):
|
|
2030
|
-
for idx, transcription in enumerate(
|
|
2031
|
-
mock_elements_worker.list_transcriptions(element=elt, worker_version=False)
|
|
2032
|
-
):
|
|
2033
|
-
assert transcription == trans[idx]
|
|
2034
|
-
|
|
2035
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
2036
|
-
assert [
|
|
2037
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
2038
|
-
] == BASE_API_CALLS + [
|
|
2039
|
-
(
|
|
2040
|
-
"GET",
|
|
2041
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/?worker_version=False",
|
|
2042
|
-
),
|
|
2043
|
-
]
|
|
2044
|
-
|
|
2045
|
-
|
|
2046
|
-
def test_list_transcriptions_manual_worker_run(responses, mock_elements_worker):
|
|
2047
|
-
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
|
|
2048
|
-
trans = [
|
|
2049
|
-
{
|
|
2050
|
-
"id": "0000",
|
|
2051
|
-
"text": "hey",
|
|
2052
|
-
"confidence": 0.42,
|
|
2053
|
-
"worker_version_id": None,
|
|
2054
|
-
"worker_run_id": None,
|
|
2055
|
-
"element": None,
|
|
2056
|
-
}
|
|
2057
|
-
]
|
|
2058
|
-
responses.add(
|
|
2059
|
-
responses.GET,
|
|
2060
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/?worker_run=False",
|
|
2061
|
-
status=200,
|
|
2062
|
-
json={
|
|
2063
|
-
"count": 1,
|
|
2064
|
-
"next": None,
|
|
2065
|
-
"results": trans,
|
|
2066
|
-
},
|
|
2067
|
-
)
|
|
2068
|
-
|
|
2069
|
-
for idx, transcription in enumerate(
|
|
2070
|
-
mock_elements_worker.list_transcriptions(element=elt, worker_run=False)
|
|
2071
|
-
):
|
|
2072
|
-
assert transcription == trans[idx]
|
|
2073
|
-
|
|
2074
|
-
assert len(responses.calls) == len(BASE_API_CALLS) + 1
|
|
2075
|
-
assert [
|
|
2076
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
2077
|
-
] == BASE_API_CALLS + [
|
|
2078
|
-
(
|
|
2079
|
-
"GET",
|
|
2080
|
-
"http://testserver/api/v1/element/12341234-1234-1234-1234-123412341234/transcriptions/?worker_run=False",
|
|
2081
|
-
),
|
|
2082
|
-
]
|
|
2083
|
-
|
|
2084
|
-
|
|
2085
|
-
@pytest.mark.usefixtures("_mock_cached_transcriptions")
|
|
2086
|
-
@pytest.mark.parametrize(
|
|
2087
|
-
("filters", "expected_ids"),
|
|
2088
|
-
[
|
|
2089
|
-
# Filter on element should give first and sixth transcription
|
|
2090
|
-
(
|
|
2091
|
-
{
|
|
2092
|
-
"element": CachedElement(
|
|
2093
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2094
|
-
),
|
|
2095
|
-
},
|
|
2096
|
-
(
|
|
2097
|
-
"11111111-1111-1111-1111-111111111111",
|
|
2098
|
-
"66666666-6666-6666-6666-666666666666",
|
|
2099
|
-
),
|
|
2100
|
-
),
|
|
2101
|
-
# Filter on element and element_type should give first and sixth transcription
|
|
2102
|
-
(
|
|
2103
|
-
{
|
|
2104
|
-
"element": CachedElement(
|
|
2105
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2106
|
-
),
|
|
2107
|
-
"element_type": "page",
|
|
2108
|
-
},
|
|
2109
|
-
(
|
|
2110
|
-
"11111111-1111-1111-1111-111111111111",
|
|
2111
|
-
"66666666-6666-6666-6666-666666666666",
|
|
2112
|
-
),
|
|
2113
|
-
),
|
|
2114
|
-
# Filter on element and worker run should give the first transcription
|
|
2115
|
-
(
|
|
2116
|
-
{
|
|
2117
|
-
"element": CachedElement(
|
|
2118
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2119
|
-
),
|
|
2120
|
-
"worker_run": "56785678-5678-5678-5678-567856785678",
|
|
2121
|
-
},
|
|
2122
|
-
("11111111-1111-1111-1111-111111111111",),
|
|
2123
|
-
),
|
|
2124
|
-
# Filter on element, manual worker run should give the sixth transcription
|
|
2125
|
-
(
|
|
2126
|
-
{
|
|
2127
|
-
"element": CachedElement(
|
|
2128
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2129
|
-
),
|
|
2130
|
-
"worker_run": False,
|
|
2131
|
-
},
|
|
2132
|
-
("66666666-6666-6666-6666-666666666666",),
|
|
2133
|
-
),
|
|
2134
|
-
# Filter recursively on element should give all transcriptions inserted
|
|
2135
|
-
(
|
|
2136
|
-
{
|
|
2137
|
-
"element": CachedElement(
|
|
2138
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2139
|
-
),
|
|
2140
|
-
"recursive": True,
|
|
2141
|
-
},
|
|
2142
|
-
(
|
|
2143
|
-
"11111111-1111-1111-1111-111111111111",
|
|
2144
|
-
"22222222-2222-2222-2222-222222222222",
|
|
2145
|
-
"33333333-3333-3333-3333-333333333333",
|
|
2146
|
-
"44444444-4444-4444-4444-444444444444",
|
|
2147
|
-
"55555555-5555-5555-5555-555555555555",
|
|
2148
|
-
"66666666-6666-6666-6666-666666666666",
|
|
2149
|
-
),
|
|
2150
|
-
),
|
|
2151
|
-
# Filter recursively on element and element_type should give three transcriptions
|
|
2152
|
-
(
|
|
2153
|
-
{
|
|
2154
|
-
"element": CachedElement(
|
|
2155
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2156
|
-
),
|
|
2157
|
-
"element_type": "something_else",
|
|
2158
|
-
"recursive": True,
|
|
2159
|
-
},
|
|
2160
|
-
(
|
|
2161
|
-
"22222222-2222-2222-2222-222222222222",
|
|
2162
|
-
"44444444-4444-4444-4444-444444444444",
|
|
2163
|
-
"55555555-5555-5555-5555-555555555555",
|
|
2164
|
-
),
|
|
2165
|
-
),
|
|
2166
|
-
],
|
|
2167
|
-
)
|
|
2168
|
-
def test_list_transcriptions_with_cache(
|
|
2169
|
-
responses, mock_elements_worker_with_cache, filters, expected_ids
|
|
2170
|
-
):
|
|
2171
|
-
# Check we have 5 elements already present in database
|
|
2172
|
-
assert CachedTranscription.select().count() == 6
|
|
2173
|
-
|
|
2174
|
-
# Query database through cache
|
|
2175
|
-
transcriptions = mock_elements_worker_with_cache.list_transcriptions(**filters)
|
|
2176
|
-
assert transcriptions.count() == len(expected_ids)
|
|
2177
|
-
for transcription, expected_id in zip(
|
|
2178
|
-
transcriptions.order_by(CachedTranscription.id), expected_ids, strict=True
|
|
2179
|
-
):
|
|
2180
|
-
assert transcription.id == UUID(expected_id)
|
|
2181
|
-
|
|
2182
|
-
# Check the worker never hits the API for elements
|
|
2183
|
-
assert len(responses.calls) == len(BASE_API_CALLS)
|
|
2184
|
-
assert [
|
|
2185
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
2186
|
-
] == BASE_API_CALLS
|
|
2187
|
-
|
|
2188
|
-
|
|
2189
|
-
@pytest.mark.usefixtures("_mock_cached_transcriptions")
|
|
2190
|
-
@pytest.mark.parametrize(
|
|
2191
|
-
("filters", "expected_ids"),
|
|
2192
|
-
[
|
|
2193
|
-
# Filter on element and worker_version should give first transcription
|
|
2194
|
-
(
|
|
2195
|
-
{
|
|
2196
|
-
"element": CachedElement(
|
|
2197
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2198
|
-
),
|
|
2199
|
-
"worker_version": "56785678-5678-5678-5678-567856785678",
|
|
2200
|
-
},
|
|
2201
|
-
("11111111-1111-1111-1111-111111111111",),
|
|
2202
|
-
),
|
|
2203
|
-
# Filter recursively on element and worker_version should give four transcriptions
|
|
2204
|
-
(
|
|
2205
|
-
{
|
|
2206
|
-
"element": CachedElement(
|
|
2207
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2208
|
-
),
|
|
2209
|
-
"worker_version": "90129012-9012-9012-9012-901290129012",
|
|
2210
|
-
"recursive": True,
|
|
2211
|
-
},
|
|
2212
|
-
(
|
|
2213
|
-
"22222222-2222-2222-2222-222222222222",
|
|
2214
|
-
"33333333-3333-3333-3333-333333333333",
|
|
2215
|
-
"44444444-4444-4444-4444-444444444444",
|
|
2216
|
-
"55555555-5555-5555-5555-555555555555",
|
|
2217
|
-
),
|
|
2218
|
-
),
|
|
2219
|
-
# Filter on element with manually created transcription should give sixth transcription
|
|
2220
|
-
(
|
|
2221
|
-
{
|
|
2222
|
-
"element": CachedElement(
|
|
2223
|
-
id="11111111-1111-1111-1111-111111111111", type="page"
|
|
2224
|
-
),
|
|
2225
|
-
"worker_version": False,
|
|
2226
|
-
},
|
|
2227
|
-
("66666666-6666-6666-6666-666666666666",),
|
|
2228
|
-
),
|
|
2229
|
-
],
|
|
2230
|
-
)
|
|
2231
|
-
def test_list_transcriptions_with_cache_deprecation(
|
|
2232
|
-
responses, mock_elements_worker_with_cache, filters, expected_ids
|
|
2233
|
-
):
|
|
2234
|
-
# Check we have 5 elements already present in database
|
|
2235
|
-
assert CachedTranscription.select().count() == 6
|
|
2236
|
-
|
|
2237
|
-
with pytest.deprecated_call(
|
|
2238
|
-
match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
|
|
2239
|
-
):
|
|
2240
|
-
# Query database through cache
|
|
2241
|
-
transcriptions = mock_elements_worker_with_cache.list_transcriptions(**filters)
|
|
2242
|
-
assert transcriptions.count() == len(expected_ids)
|
|
2243
|
-
for transcription, expected_id in zip(
|
|
2244
|
-
transcriptions.order_by(CachedTranscription.id), expected_ids, strict=True
|
|
2245
|
-
):
|
|
2246
|
-
assert transcription.id == UUID(expected_id)
|
|
2247
|
-
|
|
2248
|
-
# Check the worker never hits the API for elements
|
|
2249
|
-
assert len(responses.calls) == len(BASE_API_CALLS)
|
|
2250
|
-
assert [
|
|
2251
|
-
(call.request.method, call.request.url) for call in responses.calls
|
|
2252
|
-
] == BASE_API_CALLS
|