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
|
import json
import pytest
import responses
from sandcrawler import *
from test_wayback import *
from test_savepagenow import *
from test_grobid import REAL_TEI_XML
@pytest.fixture
def ingest_worker(wayback_client, spn_client):
grobid_client = GrobidClient(
host_url="http://dummy-grobid",
)
worker = IngestFileWorker(
wayback_client=wayback_client,
spn_client=spn_client,
grobid_client=grobid_client,
)
return worker
@pytest.fixture
def ingest_worker_pdf(wayback_client_pdf, spn_client):
grobid_client = GrobidClient(
host_url="http://dummy-grobid",
)
pgrest_client = SandcrawlerPostgrestClient(
api_url="http://dummy-postgrest",
)
worker = IngestFileWorker(
wayback_client=wayback_client_pdf,
spn_client=spn_client,
grobid_client=grobid_client,
pgrest_client=pgrest_client,
)
return worker
@responses.activate
def test_ingest_success(ingest_worker_pdf):
with open('tests/files/dummy.pdf', 'rb') as f:
pdf_bytes = f.read()
request = {
'ingest_type': 'pdf',
'base_url': "http://dummy-host/",
}
responses.add(responses.POST,
'http://dummy-spnv2/save',
status=200,
body=json.dumps({"url": TARGET, "job_id": JOB_ID}))
responses.add(responses.GET,
'http://dummy-spnv2/save/status/' + JOB_ID,
status=200,
body=json.dumps(PENDING_BODY))
responses.add(responses.GET,
'http://dummy-spnv2/save/status/' + JOB_ID,
status=200,
body=json.dumps(SUCCESS_BODY))
responses.add(responses.GET,
'http://dummy-cdx/cdx',
status=200,
body=json.dumps(CDX_SPN_HIT))
responses.add(responses.GET,
'https://web.archive.org/web/{}id_/{}'.format("20180326070330", TARGET + "/redirect"),
status=200,
headers={"X-Archive-Src": "liveweb-whatever.warc.gz"},
body=pdf_bytes)
responses.add(responses.GET,
'http://dummy-postgrest/grobid?sha1hex=eq.{}'.format("90ffd2359008d82298821d16b21778c5c39aec36"),
status=200,
body=json.dumps([]))
responses.add(responses.GET,
'http://dummy-postgrest/pdf_meta?sha1hex=eq.{}'.format("90ffd2359008d82298821d16b21778c5c39aec36"),
status=200,
body=json.dumps([]))
responses.add(responses.POST,
'http://dummy-grobid/api/processFulltextDocument', status=200,
body=REAL_TEI_XML, content_type='text/xml')
resp = ingest_worker_pdf.process(request)
print(resp)
assert resp['hit'] == True
assert resp['status'] == "success"
assert resp['request'] == request
assert resp['terminal']['terminal_sha1hex'] == resp['file_meta']['sha1hex']
assert type(resp['terminal']['terminal_dt']) == str
assert resp['terminal']['terminal_url'] == TARGET + "/redirect"
assert resp['terminal']['terminal_status_code']
assert type(resp['file_meta']['size_bytes']) == int
assert resp['file_meta']['mimetype'] == "application/pdf"
assert resp['cdx']['url'] == TARGET + "/redirect"
assert 'warc_path' not in resp['cdx']
assert 'revisit_cdx' not in resp
assert resp['grobid']['status'] == "success"
assert resp['grobid']['status_code'] == 200
assert resp['grobid']['grobid_version']
assert 'fatcat_release' in resp['grobid']
assert 'grobid_version' not in resp['grobid']['metadata']
assert 'fatcat_release' not in resp['grobid']['metadata']
assert not 'tei_xml' in resp['grobid']
assert resp['pdf_meta']['status'] == "success"
assert resp['pdf_meta']['pdf_extra']['page_count'] == 1
assert resp['pdf_meta'].get('text') is None
@responses.activate
def test_ingest_landing(ingest_worker):
request = {
'ingest_type': 'pdf',
'base_url': "http://dummy-host/",
}
responses.add(responses.POST,
'http://dummy-spnv2/save',
status=200,
body=json.dumps({"url": TARGET, "job_id": JOB_ID}))
responses.add(responses.GET,
'http://dummy-spnv2/save/status/' + JOB_ID,
status=200,
body=json.dumps(PENDING_BODY))
responses.add(responses.GET,
'http://dummy-spnv2/save/status/' + JOB_ID,
status=200,
body=json.dumps(SUCCESS_BODY))
responses.add(responses.GET,
'http://dummy-cdx/cdx',
status=200,
body=json.dumps(CDX_SPN_HIT))
responses.add(responses.GET,
'https://web.archive.org/web/{}id_/{}'.format("20180326070330", TARGET + "/redirect"),
status=200,
headers={"X-Archive-Src": "liveweb-whatever.warc.gz"},
body=WARC_BODY)
# this is for second time around; don't want to fetch same landing page
# HTML again and result in a loop
responses.add(responses.GET,
'https://web.archive.org/web/{}id_/{}'.format("20180326070330", TARGET + "/redirect"),
status=200,
headers={"X-Archive-Src": "liveweb-whatever.warc.gz"},
body="<html></html>")
resp = ingest_worker.process(request)
print(resp)
assert resp['hit'] == False
assert resp['status'] == "no-pdf-link"
assert resp['request'] == request
assert 'terminal' in resp
assert 'file_meta' not in resp
assert 'cdx' not in resp
assert 'revisit_cdx' not in resp
assert 'grobid' not in resp
@responses.activate
def test_ingest_blocklist(ingest_worker):
ingest_worker.base_url_blocklist = [
'://test.fatcat.wiki/',
]
request = {
'ingest_type': 'pdf',
'base_url': "https://test.fatcat.wiki/asdfasdf.pdf",
}
resp = ingest_worker.process(request)
assert resp['hit'] == False
assert resp['status'] == "skip-url-blocklist"
assert resp['request'] == request
@responses.activate
def test_ingest_wall_blocklist(ingest_worker):
ingest_worker.wall_blocklist = [
'://test.fatcat.wiki/',
]
request = {
'ingest_type': 'pdf',
'base_url': "https://test.fatcat.wiki/asdfasdf.pdf",
}
resp = ingest_worker.process(request)
assert resp['hit'] == False
assert resp['status'] == "skip-wall"
assert resp['request'] == request
|
