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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
|
# coding=utf-8
# ------------------------------------
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
# ------------------------------------
import pytest
import functools
from devtools_testutils import recorded_by_proxy, get_credential, set_bodiless_matcher
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import (
DocumentAnalysisFeature,
AnalyzeDocumentRequest,
AnalyzeResult,
AnalyzeOutputOption,
)
from testcase import DocumentIntelligenceTest
from conftest import skip_flaky_test
from preparers import DocumentIntelligencePreparer, GlobalClientPreparer as _GlobalClientPreparer
DocumentIntelligenceClientPreparer = functools.partial(_GlobalClientPreparer, DocumentIntelligenceClient)
class TestDACAnalyzeLayout(DocumentIntelligenceTest):
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_incorrect_feature_format(self, client):
with open(self.invoice_pdf, "rb") as fd:
document = fd.read()
with pytest.raises(TypeError) as e:
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
features=DocumentAnalysisFeature.STYLE_FONT,
)
assert "features must be type [str]." in str(e.value)
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_stream_transform_pdf(self, client):
with open(self.invoice_pdf, "rb") as fd:
document = fd.read()
def callback(raw_response, _, headers):
return raw_response
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
features=[DocumentAnalysisFeature.STYLE_FONT],
cls=callback,
)
raw_response = poller.result()
raw_analyze_result = AnalyzeResult._deserialize(raw_response.http_response.json()["analyzeResult"], [])
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
features=[DocumentAnalysisFeature.STYLE_FONT],
)
returned_model = poller.result()
assert returned_model.model_id == raw_analyze_result.model_id
assert returned_model.api_version == raw_analyze_result.api_version
assert returned_model.content == raw_analyze_result.content
assert len(returned_model.pages) == len(raw_analyze_result.pages)
assert len(returned_model.tables) == len(raw_analyze_result.tables)
assert len(returned_model.paragraphs) == len(raw_analyze_result.paragraphs)
assert len(returned_model.styles) == len(raw_analyze_result.styles)
self.assertDocumentPagesTransformCorrect(returned_model.pages, raw_analyze_result.pages)
self.assertDocumentTransformCorrect(returned_model.documents, raw_analyze_result.documents)
self.assertDocumentTablesTransformCorrect(returned_model.tables, raw_analyze_result.tables)
self.assertDocumentKeyValuePairsTransformCorrect(
returned_model.key_value_pairs, raw_analyze_result.key_value_pairs
)
self.assertDocumentStylesTransformCorrect(returned_model.styles, raw_analyze_result.styles)
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_stream_transform_jpg(self, client):
with open(self.form_jpg, "rb") as fd:
document = fd.read()
def callback(raw_response, _, headers):
return raw_response
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
cls=callback,
)
raw_response = poller.result()
raw_analyze_result = AnalyzeResult._deserialize(raw_response.http_response.json()["analyzeResult"], [])
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
)
returned_model = poller.result()
assert returned_model.model_id == raw_analyze_result.model_id
assert returned_model.api_version == raw_analyze_result.api_version
assert returned_model.content == raw_analyze_result.content
assert len(returned_model.pages) == len(raw_analyze_result.pages)
assert len(returned_model.tables) == len(raw_analyze_result.tables)
assert len(returned_model.paragraphs) == len(raw_analyze_result.paragraphs)
assert len(returned_model.styles) == len(raw_analyze_result.styles)
self.assertDocumentPagesTransformCorrect(returned_model.pages, raw_analyze_result.pages)
self.assertDocumentTransformCorrect(returned_model.documents, raw_analyze_result.documents)
self.assertDocumentTablesTransformCorrect(returned_model.tables, raw_analyze_result.tables)
self.assertDocumentKeyValuePairsTransformCorrect(
returned_model.key_value_pairs, raw_analyze_result.key_value_pairs
)
self.assertDocumentStylesTransformCorrect(returned_model.styles, raw_analyze_result.styles)
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_multipage_transform(self, client):
with open(self.multipage_invoice_pdf, "rb") as fd:
document = fd.read()
def callback(raw_response, _, headers):
return raw_response
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
cls=callback,
)
raw_response = poller.result()
raw_analyze_result = AnalyzeResult._deserialize(raw_response.http_response.json()["analyzeResult"], [])
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
)
returned_model = poller.result()
assert returned_model.model_id == raw_analyze_result.model_id
assert returned_model.api_version == raw_analyze_result.api_version
assert returned_model.content == raw_analyze_result.content
assert len(returned_model.pages) == len(raw_analyze_result.pages)
assert len(returned_model.tables) == len(raw_analyze_result.tables)
assert len(returned_model.paragraphs) == len(raw_analyze_result.paragraphs)
assert len(returned_model.styles) == len(raw_analyze_result.styles)
self.assertDocumentPagesTransformCorrect(returned_model.pages, raw_analyze_result.pages)
self.assertDocumentTransformCorrect(returned_model.documents, raw_analyze_result.documents)
self.assertDocumentTablesTransformCorrect(returned_model.tables, raw_analyze_result.tables)
self.assertDocumentKeyValuePairsTransformCorrect(
returned_model.key_value_pairs, raw_analyze_result.key_value_pairs
)
self.assertDocumentStylesTransformCorrect(returned_model.styles, raw_analyze_result.styles)
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_multipage_table_span_pdf(self, client):
with open(self.multipage_table_pdf, "rb") as fd:
document = fd.read()
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
)
layout = poller.result()
assert len(layout.tables) == 3
assert layout.tables[0].row_count == 30
assert layout.tables[0].column_count == 5
assert layout.tables[1].row_count == 6
assert layout.tables[1].column_count == 5
assert layout.tables[2].row_count == 24
assert layout.tables[2].column_count == 5
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_multipage_table_span_pdf_with_continuation_token(self, client):
with open(self.multipage_table_pdf, "rb") as fd:
document = fd.read()
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
)
continuation_token = poller.continuation_token()
layout = client.begin_analyze_document(None, None, continuation_token=continuation_token).result()
assert len(layout.tables) == 3
assert layout.tables[0].row_count == 30
assert layout.tables[0].column_count == 5
assert layout.tables[1].row_count == 6
assert layout.tables[1].column_count == 5
assert layout.tables[2].row_count == 24
assert layout.tables[2].column_count == 5
@skip_flaky_test
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_layout_url_barcode(self, client):
set_bodiless_matcher()
poller = client.begin_analyze_document(
"prebuilt-layout",
AnalyzeDocumentRequest(url_source=self.barcode_url_tif),
features=[DocumentAnalysisFeature.BARCODES],
)
layout = poller.result()
assert len(layout.pages) > 0
assert len(layout.pages[0].barcodes) == 2
assert layout.pages[0].barcodes[0].kind == "Code39"
assert layout.pages[0].barcodes[0].polygon
assert layout.pages[0].barcodes[0].confidence > 0.8
@skip_flaky_test
@DocumentIntelligencePreparer()
@recorded_by_proxy
def test_polling_interval(self, documentintelligence_endpoint, **kwargs):
client = DocumentIntelligenceClient(documentintelligence_endpoint, get_credential())
assert client._config.polling_interval == 1
client = DocumentIntelligenceClient(documentintelligence_endpoint, get_credential(), polling_interval=7)
assert client._config.polling_interval == 7
poller = client.begin_analyze_document(
"prebuilt-receipt", AnalyzeDocumentRequest(url_source=self.receipt_url_jpg), polling_interval=6
)
poller.wait()
assert poller._polling_method._timeout == 6
poller2 = client.begin_analyze_document(
"prebuilt-receipt",
AnalyzeDocumentRequest(url_source=self.receipt_url_jpg),
)
poller2.wait()
assert poller2._polling_method._timeout == 7 # goes back to client default
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_get_analyze_result_pdf(self, client):
with open(self.layout_sample, "rb") as fd:
document = fd.read()
poller = client.begin_analyze_document(
"prebuilt-read",
document,
output=[AnalyzeOutputOption.PDF],
)
result = poller.result()
response = client.get_analyze_result_pdf(model_id=result.model_id, result_id=poller.details["operation_id"])
first_chunk_pdf_bytes = response.__next__()
assert first_chunk_pdf_bytes.startswith(b"%PDF-") # A PDF's header is expected to be: %PDF-
@pytest.mark.live_test_only("Needs to remove sanitizer on figure id in request url.")
@DocumentIntelligencePreparer()
@DocumentIntelligenceClientPreparer()
@recorded_by_proxy
def test_get_analyze_result_figures(self, client):
with open(self.layout_sample, "rb") as fd:
document = fd.read()
poller = client.begin_analyze_document(
"prebuilt-layout",
document,
output=[AnalyzeOutputOption.FIGURES],
)
result = poller.result()
assert result.figures is not None
figure_id = result.figures[0].id
response = client.get_analyze_result_figure(
model_id=result.model_id, result_id=poller.details["operation_id"], figure_id=figure_id
)
first_chunk_figure_bytes = response.__next__()
assert first_chunk_figure_bytes.startswith(b"\x89PNG") # A PNG's header is expected to start with: ‰PNG
|
