aboutsummaryrefslogtreecommitdiffstats
path: root/python/tests
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2019-09-26 12:00:01 -0700
committerBryan Newbold <bnewbold@archive.org>2019-09-26 12:00:01 -0700
commit37bf997dc0220a30605249655056e90f04e33366 (patch)
tree3f6a3586462d25c02b5fd219b0c754aef2976e3c /python/tests
parentc3c5a6ef57e83ff4395f9f87e7e372c6c371e4a5 (diff)
downloadsandcrawler-37bf997dc0220a30605249655056e90f04e33366.tar.gz
sandcrawler-37bf997dc0220a30605249655056e90f04e33366.zip
lots of grobid tool implementation (still WIP)
Diffstat (limited to 'python/tests')
-rw-r--r--python/tests/test_grobid.py30
-rw-r--r--python/tests/test_misc.py6
2 files changed, 29 insertions, 7 deletions
diff --git a/python/tests/test_grobid.py b/python/tests/test_grobid.py
index fca234a..10560cd 100644
--- a/python/tests/test_grobid.py
+++ b/python/tests/test_grobid.py
@@ -3,7 +3,7 @@ import pytest
import struct
import responses
-from sandcrawler import GrobidClient
+from sandcrawler import GrobidClient, GrobidWorker, CdxLinePusher, BlackholeSink, WaybackClient
FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843)
@@ -28,11 +28,10 @@ def test_grobid_503():
assert resp['status_code'] == 503
assert resp['status'] == "error"
- print(resp)
- assert False
@responses.activate
-def test_grobid_503():
+@pytest.mark.skip(reason="XXX: need to fix unicode/bytes something something")
+def test_grobid_success():
client = GrobidClient(host_url="http://localhost:8070")
@@ -51,3 +50,26 @@ def test_grobid_503():
print(type(REAL_TEI_XML))
assert resp['tei_xml'] == REAL_TEI_XML.decode('utf-8')
#assert resp['tei_xml'].split('\n')[:3] == REAL_TEI_XML.split('\n')[:3]
+
+@responses.activate
+def test_grobid_worker_cdx():
+
+ sink = BlackholeSink()
+ grobid_client = GrobidClient(host_url="http://localhost:8070")
+ wayback_client = WaybackClient()
+ worker = GrobidWorker(grobid_client, wayback_client, sink=sink)
+
+ responses.add(responses.POST,
+ 'http://localhost:8070/api/processFulltextDocument', status=200,
+ body=REAL_TEI_XML, content_type='text/xml')
+
+ with open('tests/files/example.cdx', 'r') as cdx_file:
+ pusher = CdxLinePusher(worker, cdx_file,
+ filter_http_statuses=[200], filter_mimetypes=['application/pdf'])
+ pusher_counts = pusher.run()
+ assert pusher_counts['total']
+ assert pusher_counts['pushed'] == 7
+ assert pusher_counts['pushed'] == worker.counts['total']
+
+ assert len(responses.calls) == worker.counts['total']
+
diff --git a/python/tests/test_misc.py b/python/tests/test_misc.py
index 02deec9..420bc07 100644
--- a/python/tests/test_misc.py
+++ b/python/tests/test_misc.py
@@ -50,9 +50,9 @@ def test_parse_cdx_line():
'surt': "edu,upenn,ldc)/sites/www.ldc.upenn.edu/files/medar2009-large-arabic-broadcast-collection.pdf",
'url': "https://www.ldc.upenn.edu/sites/www.ldc.upenn.edu/files/medar2009-large-arabic-broadcast-collection.pdf",
'datetime': "20170828233154",
- 'warc': "SEMSCHOLAR-PDF-CRAWL-2017-08-04-20170828231135742-00000-00009-wbgrp-svc284/SEMSCHOLAR-PDF-CRAWL-2017-08-04-20170828232253025-00005-3480~wbgrp-svc284.us.archive.org~8443.warc.gz",
- 'offset': 931661233,
- 'c_size': 210251,
+ 'warc_path': "SEMSCHOLAR-PDF-CRAWL-2017-08-04-20170828231135742-00000-00009-wbgrp-svc284/SEMSCHOLAR-PDF-CRAWL-2017-08-04-20170828232253025-00005-3480~wbgrp-svc284.us.archive.org~8443.warc.gz",
+ 'warc_offset': 931661233,
+ 'warc_csize': 210251,
'http_status': 200,
}