diff options
| -rw-r--r-- | python/tests/test_extraction_ungrobided.py | 52 |
1 files changed, 51 insertions, 1 deletions
diff --git a/python/tests/test_extraction_ungrobided.py b/python/tests/test_extraction_ungrobided.py index fb681c2..0ec47bc 100644 --- a/python/tests/test_extraction_ungrobided.py +++ b/python/tests/test_extraction_ungrobided.py @@ -41,7 +41,7 @@ def job(): @mock.patch('extraction_ungrobided.MRExtractUnGrobided.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) @responses.activate -def test_mapper_lines(mock_fetch, job): +def test_mapper_single_line(mock_fetch, job): responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, body=REAL_TEI_XML, content_type='text/xml') @@ -85,6 +85,56 @@ def test_mapper_lines(mock_fetch, job): assert 'body' in tei_json assert 'body' not in metadata +@mock.patch('extraction_ungrobided.MRExtractUnGrobided.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) +@responses.activate +def test_mapper_lines(mock_fetch, job): + + responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, + body=REAL_TEI_XML, content_type='text/xml') + + raw = io.BytesIO(b"""sha1:23PTUXWSNSVE4HS5J7ELDUUG63J2FPCI\t{"c": 1, "d": "2016-06-09T00:27:36", "f": "WIDE-20160609001810-06993.warc.gz", "o": 287880616, "u": "http://www.case-research.eu/sites/default/files/publications/18092393_E-brief_Dabrowski_Monetary_Policy_final_0.pdf"}\tapplication/pdf\t{"c_size": 68262, "dt": "20160609002736", "offset": 287880616, "surt": "eu,case-research)/sites/default/files/publications/18092393_e-brief_dabrowski_monetary_policy_final_0.pdf", "url": "http://www.case-research.eu/sites/default/files/publications/18092393_E-brief_Dabrowski_Monetary_Policy_final_0.pdf", "warc": "WIDE-20160609000312-crawl427/WIDE-20160609001810-06993.warc.gz"} +sha1:23PW2APYHNBPIBRIVNQ6TMKUNY53UL3D\t{"c": 1, "d": "2016-01-07T03:29:03", "f": "MUSEUM-20160107025230-02354.warc.gz", "o": 413484441, "u": "http://www.portlandoregon.gov/fire/article/363695"}\tapplication/pdf\t{"c_size": 44600, "dt": "20160107032903", "offset": 413484441, "surt": "gov,portlandoregon)/fire/article/363695", "url": "http://www.portlandoregon.gov/fire/article/363695", "warc": "MUSEUM-20160107004301-crawl891/MUSEUM-20160107025230-02354.warc.gz"} +sha1:23RJIHUIOYY5747CR6YYCTMACXDCFYTT\t{"c": 1, "d": "2014-06-07T18:00:56", "f": "ARCHIVEIT-219-QUARTERLY-20047-20140607125555378-00017-wbgrp-crawl051.us.archive.org-6442.warc.gz", "o": 720590380, "u": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=36&id=264&artlang=en"}\tapplication/pdf\t{"c_size": 3727, "dt": "20140607180056", "offset": 720590380, "surt": "edu,indiana)/~orafaq/faq/pdf.php?artlang=en&cat=36&id=264", "url": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=36&id=264&artlang=en", "warc": "ARCHIVEIT-219-QUARTERLY-20047-00001/ARCHIVEIT-219-QUARTERLY-20047-20140607125555378-00017-wbgrp-crawl051.us.archive.org-6442.warc.gz"}""") + + + output = io.BytesIO() + job.sandbox(stdin=raw, stdout=output) + + job.run_mapper() + + # for debugging tests + #print(output.getvalue().decode('utf-8')) + #print(list(job.hb_table.scan())) + + # grobid gets POST 3x times + assert len(responses.calls) == 3 + + # wayback gets FETCH 3x times + mock_fetch.assert_has_calls(( + mock.call("WIDE-20160609000312-crawl427/WIDE-20160609001810-06993.warc.gz", 287880616, 68262), + mock.call("MUSEUM-20160107004301-crawl891/MUSEUM-20160107025230-02354.warc.gz", 413484441, 44600), + mock.call("ARCHIVEIT-219-QUARTERLY-20047-00001/ARCHIVEIT-219-QUARTERLY-20047-20140607125555378-00017-wbgrp-crawl051.us.archive.org-6442.warc.gz", 720590380, 3727), + )) + + # Saved extraction info + assert job.hb_table.row(b'sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ') == {} + assert job.hb_table.row(b'sha1:23PTUXWSNSVE4HS5J7ELDUUG63J2FPCI') != {} + assert job.hb_table.row(b'sha1:23PW2APYHNBPIBRIVNQ6TMKUNY53UL3D') != {} + assert job.hb_table.row(b'sha1:23RJIHUIOYY5747CR6YYCTMACXDCFYTT') != {} + + row = job.hb_table.row(b'sha1:23RJIHUIOYY5747CR6YYCTMACXDCFYTT') + assert struct.unpack("!q", row[b'file:size'])[0] == len(FAKE_PDF_BYTES) + assert row[b'file:mime'] == b"application/pdf" + assert struct.unpack("!q", row[b'grobid0:status_code'])[0] == 200 + status = json.loads(row[b'grobid0:status'].decode('utf-8')) + assert type(status) == type(dict()) + assert row[b'grobid0:tei_xml'].decode('utf-8') == REAL_TEI_XML + tei_json = json.loads(row[b'grobid0:tei_json'].decode('utf-8')) + metadata = json.loads(row[b'grobid0:metadata'].decode('utf-8')) + assert tei_json['title'] == metadata['title'] + assert 'body' in tei_json + assert 'body' not in metadata + def test_parse_ungrobided_invalid(job): print("space-prefixed line") |