aboutsummaryrefslogtreecommitdiffstats
path: root/python
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2019-09-25 18:02:43 -0700
committerBryan Newbold <bnewbold@archive.org>2019-09-25 18:02:43 -0700
commitbd508b4ffbab3ea56134f753a9746ff9d582fde3 (patch)
treeb7b0163b73069fd4c05265f64139bff3c03cf348 /python
parent716483103dd7fdfe7aab2982c51abae6d3f4271b (diff)
downloadsandcrawler-bd508b4ffbab3ea56134f753a9746ff9d582fde3.tar.gz
sandcrawler-bd508b4ffbab3ea56134f753a9746ff9d582fde3.zip
test of GROBID client
Diffstat (limited to 'python')
-rw-r--r--python/tests/test_grobid.py53
1 files changed, 53 insertions, 0 deletions
diff --git a/python/tests/test_grobid.py b/python/tests/test_grobid.py
new file mode 100644
index 0000000..fca234a
--- /dev/null
+++ b/python/tests/test_grobid.py
@@ -0,0 +1,53 @@
+
+import pytest
+import struct
+import responses
+
+from sandcrawler import GrobidClient
+
+
+FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843)
+
+with open('tests/files/23b29ea36382680716be08fc71aa81bd226e8a85.xml', 'rb') as f:
+ REAL_TEI_XML = f.read()
+
+@responses.activate
+def test_grobid_503():
+
+ client = GrobidClient(host_url="http://localhost:8070")
+
+ status = b'{"status": "done broke due to 503"}'
+ responses.add(responses.POST,
+ 'http://localhost:8070/api/processFulltextDocument', status=503,
+ body=status)
+
+ resp = client.process_fulltext(FAKE_PDF_BYTES)
+
+ # grobid gets POST 1x times
+ assert len(responses.calls) == 1
+
+ assert resp['status_code'] == 503
+ assert resp['status'] == "error"
+ print(resp)
+ assert False
+
+@responses.activate
+def test_grobid_503():
+
+ client = GrobidClient(host_url="http://localhost:8070")
+
+ responses.add(responses.POST,
+ 'http://localhost:8070/api/processFulltextDocument', status=200,
+ body=REAL_TEI_XML, content_type='text/xml')
+
+ resp = client.process_fulltext(FAKE_PDF_BYTES)
+
+ # grobid gets POST 1x times
+ assert len(responses.calls) == 1
+
+ assert resp['status_code'] == 200
+ assert resp['status'] == "success"
+ print(type(resp['tei_xml']))
+ 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]