From d7830b4a5aad0a59a588e98798711f0e694d50d6 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 25 Sep 2019 17:51:07 -0700 Subject: refactor old python hadoop code into new directory --- python/tests/files/example_ungrobided.tsv | 20 -- python/tests/test_backfill_hbase_from_cdx.py | 74 ------- python/tests/test_extraction_cdx_grobid.py | 319 --------------------------- python/tests/test_extraction_ungrobided.py | 178 --------------- 4 files changed, 591 deletions(-) delete mode 100644 python/tests/files/example_ungrobided.tsv delete mode 100644 python/tests/test_backfill_hbase_from_cdx.py delete mode 100644 python/tests/test_extraction_cdx_grobid.py delete mode 100644 python/tests/test_extraction_ungrobided.py (limited to 'python/tests') diff --git a/python/tests/files/example_ungrobided.tsv b/python/tests/files/example_ungrobided.tsv deleted file mode 100644 index 9263b6f..0000000 --- a/python/tests/files/example_ungrobided.tsv +++ /dev/null @@ -1,20 +0,0 @@ -sha1:23LOSW2QVMKUYXPFZBXQHBBNQR45WTMU {"c": 1, "d": "2017-10-27T22:21:13", "f": "PDFS-20171027214658-00155.warc.gz", "o": 984263791, "u": "http://circ.ahajournals.org/content/circulationaha/53/6/965.full.pdf"} application/pdf {"c_size": 1050532, "dt": "20171027222113", "offset": 984263791, "surt": "org,ahajournals,circ)/content/circulationaha/53/6/965.full.pdf", "url": "http://circ.ahajournals.org/content/circulationaha/53/6/965.full.pdf", "warc": "PDFS-20171027125450-crawl815/PDFS-20171027214658-00155.warc.gz"} -sha1:23M2N262M5TWB7F3BVB6ESD3Q26SMPFA {"c": 1, "d": "2012-09-29T07:05:16", "f": "ARCHIVEIT-219-QUARTERLY-FWGZDI-20120929065657-00119-crawling203.us.archive.org-6680.warc.gz", "o": 83570746, "u": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=37&id=225&artlang=en"} application/pdf {"c_size": 3590, "dt": "20120929070516", "offset": 83570746, "surt": "edu,indiana)/~orafaq/faq/pdf.php?artlang=en&cat=37&id=225", "url": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=37&id=225&artlang=en", "warc": "ARCHIVEIT-219-QUARTERLY-FWGZDI-00001/ARCHIVEIT-219-QUARTERLY-FWGZDI-20120929065657-00119-crawling203.us.archive.org-6680.warc.gz"} -sha1:23MFQLDGP4WJD67BS7ERMYQUF7TGCG5X {"c": 1, "d": "2017-08-25T15:19:28", "f": "MSAG-PDF-CRAWL-2017-08-04-20170825143335512-08107-3480~wbgrp-svc284.us.archive.org~8443.warc.gz", "o": 573475485, "u": "http://www.bloodjournal.org/content/bloodjournal/77/7/1484.full.pdf?sso-checked=true"} application/pdf {"c_size": 3411470, "dt": "20170825151928", "offset": 573475485, "surt": "org,bloodjournal)/content/bloodjournal/77/7/1484.full.pdf?sso-checked=true", "url": "http://www.bloodjournal.org/content/bloodjournal/77/7/1484.full.pdf?sso-checked=true", "warc": "MSAG-PDF-CRAWL-2017-08-04-20170825114428485-08102-08111-wbgrp-svc284/MSAG-PDF-CRAWL-2017-08-04-20170825143335512-08107-3480~wbgrp-svc284.us.archive.org~8443.warc.gz"} -sha1:23MG6K5Z3JENYCZ2OGTNOJ7QPYANJRCZ {"c": 1, "d": "2017-10-10T11:29:50", "f": "PDFS-20171010110639-00278.warc.gz", "o": 665222706, "u": "http://circ.ahajournals.org/content/circulationaha/53/5/797.full.pdf?download=true"} application/pdf {"c_size": 1107121, "dt": "20171010112950", "offset": 665222706, "surt": "org,ahajournals,circ)/content/circulationaha/53/5/797.full.pdf?download=true", "url": "http://circ.ahajournals.org/content/circulationaha/53/5/797.full.pdf?download=true", "warc": "PDFS-20171010110639-crawl815/PDFS-20171010110639-00278.warc.gz"} -sha1:23MN67JQKDWRUXJMXXJ2GX6O43SQIV76 {"c": 1, "d": "2015-06-06T18:17:08", "f": "ARCHIVEIT-219-QUARTERLY-9582-20150606125000169-00071-wbgrp-crawl067.us.archive.org-6440.warc.gz", "o": 603211220, "u": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=36&id=95&artlang=en"} application/pdf {"c_size": 3450, "dt": "20150606181708", "offset": 603211220, "surt": "edu,indiana)/~orafaq/faq/pdf.php?artlang=en&cat=36&id=95", "url": "https://www.indiana.edu/~orafaq/faq/pdf.php?cat=36&id=95&artlang=en", "warc": "ARCHIVEIT-219-QUARTERLY-9582-00007/ARCHIVEIT-219-QUARTERLY-9582-20150606125000169-00071-wbgrp-crawl067.us.archive.org-6440.warc.gz"} -sha1:23MQCEOMQS5SMZCXIPNQ4E3ZKOCF6DIM {"c": 1, "d": "2004-01-02T19:45:22", "f": "DU_crawl10.20040102194453.arc.gz", "o": 38062592, "u": "http://www.csupomona.edu:80/~darsadmin/ACTIONITEMS.pdf"} application/pdf {"c_size": 15406, "dt": "20040102194522", "offset": 38062592, "surt": "edu,csupomona)/~darsadmin/actionitems.pdf", "url": "http://www.csupomona.edu:80/~darsadmin/ACTIONITEMS.pdf", "warc": "DU_crawl10.20040102181929-c/DU_crawl10.20040102194453.arc.gz"} -sha1:23NKO4TW6XCESXMSUOOICI3AXVK6Z5BL {"c": 1, "d": "2015-04-27T11:16:33", "f": "eric.ed.gov-inf-20150409-030712-1648j-00064.warc.gz", "o": 3872820483, "u": "http://files.eric.ed.gov/fulltext/ED088632.pdf"} application/pdf {"c_size": 2223528, "dt": "20150427111633", "offset": 3872820483, "surt": "gov,ed,eric,files)/fulltext/ed088632.pdf", "url": "http://files.eric.ed.gov/fulltext/ED088632.pdf", "warc": "archiveteam_archivebot_go_20150427150006/eric.ed.gov-inf-20150409-030712-1648j-00064.warc.gz"} -sha1:23NW2EPLXDA6UBIJLQMM2DJ2K3GL3WTB {"c": 1, "d": "2014-08-13T09:04:30", "f": "WIDE-20140813084304-09684.warc.gz", "o": 726289594, "u": "http://research.sdccd.edu/docs/Accreditation/2012%20Surveys/Employee%20-%20Briefing/Mesa%20College%202012%20Employee%20Feedback%20Survey%20Briefing.pdf"} application/pdf {"c_size": 3472527, "dt": "20140813090430", "offset": 726289594, "surt": "edu,sdccd,research)/docs/accreditation/2012%20surveys/employee%20-%20briefing/mesa%20college%202012%20employee%20feedback%20survey%20briefing.pdf", "url": "http://research.sdccd.edu/docs/Accreditation/2012%20Surveys/Employee%20-%20Briefing/Mesa%20College%202012%20Employee%20Feedback%20Survey%20Briefing.pdf", "warc": "WIDE-20140813074743-crawl424/WIDE-20140813084304-09684.warc.gz"} -sha1:23OQICQ4IBVNHJBWJX5ON3QR26KNMQNT {"c": 1, "d": "2010-06-29T00:35:17", "f": "EDG-20100628234135-01241-ia360918.us.archive.org.warc.gz", "o": 572430160, "u": "http://journalism.arizona.edu/news/rockypt6.pdf"} application/pdf {"c_size": 194706, "dt": "20100629003517", "offset": 572430160, "surt": "edu,arizona,journalism)/news/rockypt6.pdf", "url": "http://journalism.arizona.edu/news/rockypt6.pdf", "warc": "EDG-20100628214935-01235-01243-ia360918-20100629023741-00000/EDG-20100628234135-01241-ia360918.us.archive.org.warc.gz"} -sha1:23OT2AAYPJ3Z5ZOQXVJJTVTKY6QUPICI {"c": 1, "d": "2007-02-25T17:49:01", "f": "38_0_20070225174831_crawl28.arc.gz", "o": 93868066, "u": "http://www.ece.tufts.edu:80/~hopwood/tampa-proceedings.pdf"} application/pdf {"c_size": 162157, "dt": "20070225174901", "offset": 93868066, "surt": "edu,tufts,ece)/~hopwood/tampa-proceedings.pdf", "url": "http://www.ece.tufts.edu:80/~hopwood/tampa-proceedings.pdf", "warc": "38_0_20070225173722_crawl28-c/38_0_20070225174831_crawl28.arc.gz"} -sha1:23OUFX3ZYMF53HY4RUONR5PKN4HXN4O3 {"c": 1, "d": "2004-05-26T06:45:34", "f": "DW_crawl10.20040526064432.arc.gz", "o": 67593910, "u": "http://207.36.165.114:80/NewOrleans/Papers/1301466.pdf"} application/pdf {"c_size": 306879, "dt": "20040526064534", "offset": 67593910, "surt": "114,165,36,207)/neworleans/papers/1301466.pdf", "url": "http://207.36.165.114:80/NewOrleans/Papers/1301466.pdf", "warc": "DW_crawl10.20040525230808-c/DW_crawl10.20040526064432.arc.gz"} -sha1:23PA23UIWCBA3CSTDK2JYX7ZIVOHULFG {"c": 1, "d": "2016-02-05T21:48:33", "f": "NLNZ-NZ-CRAWL-005-20160205211003375-02839-6291~wbgrp-crawl007.us.archive.org~8443.warc.gz", "o": 630386943, "u": "http://homepages.engineering.auckland.ac.nz/~smohan/Outreach/Docs/2013/TTU_REU2013.pdf"} application/pdf {"c_size": 2979614, "dt": "20160205214833", "offset": 630386943, "surt": "nz,ac,auckland,engineering,homepages)/~smohan/outreach/docs/2013/ttu_reu2013.pdf", "url": "http://homepages.engineering.auckland.ac.nz/~smohan/Outreach/Docs/2013/TTU_REU2013.pdf", "warc": "NLNZ-NZ-CRAWL-005-20160205211003375-02839-02848-wbgrp-crawl007/NLNZ-NZ-CRAWL-005-20160205211003375-02839-6291~wbgrp-crawl007.us.archive.org~8443.warc.gz"} -sha1:23PGC74CTD7P6PCF3MZZZJMPYFXRK3OB {"c": 1, "d": "2005-03-17T15:05:51", "f": "EC_binary1_crawl30.20050317150502.arc.gz", "o": 75675778, "u": "http://www.csupomona.edu:80/%7Eengineering/programs/courses/aro/course_outlines/aro_407.pdf"} application/pdf {"c_size": 4842, "dt": "20050317150551", "offset": 75675778, "surt": "edu,csupomona)/~engineering/programs/courses/aro/course_outlines/aro_407.pdf", "url": "http://www.csupomona.edu:80/%7Eengineering/programs/courses/aro/course_outlines/aro_407.pdf", "warc": "EC_binary1_crawl30.20050317135651-c/EC_binary1_crawl30.20050317150502.arc.gz"} -sha1:23PKJEQWUJAIQQSLP3GCCC5VDXN4RFCX {"c": 1, "d": "2017-10-10T23:50:37", "f": "WIDE-20171010214240-16560.warc.gz", "o": 962106404, "u": "http://www.nbrb.by/bv/articles/8997.pdf"} application/pdf {"c_size": 273375, "dt": "20171010235037", "offset": 962106404, "surt": "by,nbrb)/bv/articles/8997.pdf", "url": "http://www.nbrb.by/bv/articles/8997.pdf", "warc": "WIDE-20171010202419-crawl424/WIDE-20171010214240-16560.warc.gz"} -sha1:23PRILJUIQUKHRYQIUYAKSBFPH53FOGT {"c": 1, "d": "2017-07-14T18:51:38", "f": "WIDE-20170714181144-06521.warc.gz", "o": 820382225, "u": "http://carsandracingstuff.com/library/articles/32538.pdf"} application/pdf {"c_size": 125426, "dt": "20170714185138", "offset": 820382225, "surt": "com,carsandracingstuff)/library/articles/32538.pdf", "url": "http://carsandracingstuff.com/library/articles/32538.pdf", "warc": "WIDE-20170714174218-crawl426/WIDE-20170714181144-06521.warc.gz"} -sha1:23PTUXWSNSVE4HS5J7ELDUUG63J2FPCI {"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"} application/pdf {"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 {"c": 1, "d": "2016-01-07T03:29:03", "f": "MUSEUM-20160107025230-02354.warc.gz", "o": 413484441, "u": "http://www.portlandoregon.gov/fire/article/363695"} application/pdf {"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 {"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"} application/pdf {"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"} -sha1:23SMLYPFEGIRV6M37FJ5D364TXQXCSMR {"c": 1, "d": "2011-07-12T22:20:32", "f": "WIDE-20110712221302-03146.warc.gz", "o": 222089710, "u": "http://media.dailyuw.com/papers/_091030_7-14_color_web.pdf"} application/pdf {"c_size": 4654708, "dt": "20110712222032", "offset": 222089710, "surt": "com,dailyuw,media)/papers/_091030_7-14_color_web.pdf", "url": "http://media.dailyuw.com/papers/_091030_7-14_color_web.pdf", "warc": "WIDE-20110712221302-crawl413/WIDE-20110712221302-03146.warc.gz"} -sha1:23SN4XBPSCRPRIHH5UAV45LFCP3VDV3V {"c": 1, "d": "2010-10-28T09:03:57", "f": "WIDE-20101028084449158-00409-23450~ia360921.us.archive.org~9443.warc.gz", "o": 756726028, "u": "http://cdacnoida.in/ASCNT-2010/Language%20Technology/Paper/Reducing%20Errors%20in%20Translation%20using%20Pre-editor%20for%20Indian%20English%20Sentences.pdf"} application/pdf {"c_size": 98408, "dt": "20101028090357", "offset": 756726028, "surt": "in,cdacnoida)/ascnt-2010/language%20technology/paper/reducing%20errors%20in%20translation%20using%20pre-editor%20for%20indian%20english%20sentences.pdf", "url": "http://cdacnoida.in/ASCNT-2010/Language%20Technology/Paper/Reducing%20Errors%20in%20Translation%20using%20Pre-editor%20for%20Indian%20English%20Sentences.pdf", "warc": "WIDE-20101028063239344-00397-00415-ia360921/WIDE-20101028084449158-00409-23450~ia360921.us.archive.org~9443.warc.gz"} diff --git a/python/tests/test_backfill_hbase_from_cdx.py b/python/tests/test_backfill_hbase_from_cdx.py deleted file mode 100644 index 070662b..0000000 --- a/python/tests/test_backfill_hbase_from_cdx.py +++ /dev/null @@ -1,74 +0,0 @@ -""" -TODO: could probably refactor to use unittest.mock.patch('happybase') -""" - -import io -import json -import pytest -import mrjob -import happybase_mock -from backfill_hbase_from_cdx import MRCDXBackfillHBase - -@pytest.fixture -def job(): - """ - Note: this mock only seems to work with job.run_mapper(), not job.run(); - the later results in a separate instantiation without the mock? - """ - job = MRCDXBackfillHBase(['--no-conf', '-']) - - conn = happybase_mock.Connection() - conn.create_table('wbgrp-journal-extract-test', - {'file': {}, 'grobid0': {}, 'f': {}}) - job.hb_table = conn.table('wbgrp-journal-extract-test') - - return job - - -def test_some_lines(job): - - raw = io.BytesIO(b""" -com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 301 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz -eu,eui,cadmus)/bitstream/handle/1814/36635/rscas_2015_03.pdf;jsessionid=761393014319a39f40d32ae3eb3a853f?sequence=1 20170705062202 http://cadmus.eui.eu/bitstream/handle/1814/36635/RSCAS_2015_03.pdf%3Bjsessionid%3D761393014319A39F40D32AE3EB3A853F?sequence%3D1 application/PDF 200 MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J - - 854156 328850624 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz -com,pbworks,educ333b)/robots.txt 20170705063311 http://educ333b.pbworks.com/robots.txt text/plain 200 6VAUYENMOU2SK2OWNRPDD6WTQTECGZAD - - 638 398190140 CITESEERX-CRAWL-2017-06-20-20170705062707827-00049-00058-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705063158203-00053-31209~wbgrp-svc284.us.archive.org~8443.warc.gz -""") - - job.sandbox(stdin=raw) - job.run_mapper() - - assert job.hb_table.row(b'1') == {} - # HTTP 301 - assert job.hb_table.row(b'sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ') == {} - # valid - assert job.hb_table.row(b'sha1:MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J') != {} - # text/plain - assert job.hb_table.row(b'sha1:6VAUYENMOU2SK2OWNRPDD6WTQTECGZAD') == {} - - row = job.hb_table.row(b'sha1:MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J') - assert row[b'file:mime'] == b"application/pdf" - - file_cdx = json.loads(row[b'file:cdx'].decode('utf-8')) - assert int(file_cdx['offset']) == 328850624 - - f_c = json.loads(row[b'f:c'].decode('utf-8')) - assert f_c['u'] == "http://cadmus.eui.eu/bitstream/handle/1814/36635/RSCAS_2015_03.pdf%3Bjsessionid%3D761393014319A39F40D32AE3EB3A853F?sequence%3D1" - assert b'i' not in f_c - -def test_parse_cdx_skip(job): - - job.mapper_init() - - print("CDX prefix") - raw = " com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.mapper(None, raw).__next__() - assert info is None - assert status['status'] == "invalid" - assert 'prefix' in status['reason'] - - print("mimetype") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf text/html 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.mapper(None, raw).__next__() - assert info is None - assert status['status'] == "skip" - assert 'mimetype' in status['reason'] - diff --git a/python/tests/test_extraction_cdx_grobid.py b/python/tests/test_extraction_cdx_grobid.py deleted file mode 100644 index 471d94a..0000000 --- a/python/tests/test_extraction_cdx_grobid.py +++ /dev/null @@ -1,319 +0,0 @@ - -import io -import json -import mrjob -import pytest -import struct -import responses -import happybase_mock -import wayback.exception -from unittest import mock -from extraction_cdx_grobid import MRExtractCdxGrobid - - -FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843) -OK_CDX_LINE = b"""com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz""" - -with open('tests/files/23b29ea36382680716be08fc71aa81bd226e8a85.xml', 'r') as f: - REAL_TEI_XML = f.read() - -@pytest.fixture -def job(): - """ - Note: this mock only seems to work with job.run_mapper(), not job.run(); - the later results in a separate instantiation without the mock? - """ - job = MRExtractCdxGrobid(['--no-conf', '-']) - - conn = happybase_mock.Connection() - conn.create_table('wbgrp-journal-extract-test', - {'file': {}, 'grobid0': {}, 'f': {}}) - job.hb_table = conn.table('wbgrp-journal-extract-test') - - return job - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.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""" -com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 301 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz -eu,eui,cadmus)/bitstream/handle/1814/36635/rscas_2015_03.pdf;jsessionid=761393014319a39f40d32ae3eb3a853f?sequence=1 20170705062202 http://cadmus.eui.eu/bitstream/handle/1814/36635/RSCAS_2015_03.pdf%3Bjsessionid%3D761393014319A39F40D32AE3EB3A853F?sequence%3D1 application/PDF 200 MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J - - 854156 328850624 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz -com,pbworks,educ333b)/robots.txt 20170705063311 http://educ333b.pbworks.com/robots.txt text/plain 200 6VAUYENMOU2SK2OWNRPDD6WTQTECGZAD - - 638 398190140 CITESEERX-CRAWL-2017-06-20-20170705062707827-00049-00058-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705063158203-00053-31209~wbgrp-svc284.us.archive.org~8443.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())) - - # wayback gets FETCH 1x times - mock_fetch.assert_called_once_with( - "CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz", - 328850624, - 854156) - - # grobid gets POST 1x times - assert len(responses.calls) == 1 - - # HBase - assert job.hb_table.row(b'1') == {} - # HTTP 301 - assert job.hb_table.row(b'sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ') == {} - # valid - assert job.hb_table.row(b'sha1:MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J') != {} - # text/plain - assert job.hb_table.row(b'sha1:6VAUYENMOU2SK2OWNRPDD6WTQTECGZAD') == {} - - # Saved extraction info - row = job.hb_table.row(b'sha1:MPCXVWMUTRUGFP36SLPHKDLY6NGU4S3J') - - 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 - # TODO: assert row[b'grobid0:quality'] == None - 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_cdx_invalid(job): - - print("valid") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert status is None - - print("space-prefixed line") - raw = " com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'prefix' in status['reason'] - - print("commented line") - raw = "#com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'prefix' in status['reason'] - - print("wrong column count") - raw = "a b c d" - info, status = job.parse_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'parse' in status['reason'] - - print("missing mimetype") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf - 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert info is None - print(status) - assert status['status'] == "invalid" - assert 'parse' in status['reason'] - - print("HTTP status") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 501 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert info is None - assert status['status'] == "invalid" - - print("datetime") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 501 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_line(raw) - assert info is None - assert status['status'] == "invalid" - - -def test_parse_cdx_skip(job): - - job.mapper_init() - - print("warc format") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.mapper(None, raw).__next__() - assert info is None - assert status['status'] == "skip" - assert 'WARC' in status['reason'] - - print("mimetype") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf text/html 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.mapper(None, raw).__next__() - assert info is None - assert status['status'] == "skip" - assert 'mimetype' in status['reason'] - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -def test_grobid_503(mock_fetch, job): - - status = b'{"status": "done broke due to 503"}' - responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=503, - body=status) - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - row = job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') - status = json.loads(row[b'grobid0:status'].decode('utf-8')) - assert json.loads(row[b'grobid0:status'].decode('utf-8')) == status - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -def test_grobid_not_xml(mock_fetch, job): - - payload = b'this is not XML' - responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, - body=payload) - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - output = output.getvalue().decode('utf-8') - row = job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') - assert struct.unpack("!q", row[b'grobid0:status_code'])[0] == 200 - assert row[b'grobid0:tei_xml'] == payload - assert b'grobid0:tei_json' not in row - assert "XML parse error" in output - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -def test_grobid_not_tei(mock_fetch, job): - - payload = b'' - responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, - body=payload) - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - output = output.getvalue().decode('utf-8') - row = job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') - assert struct.unpack("!q", row[b'grobid0:status_code'])[0] == 200 - assert row[b'grobid0:tei_xml'] == payload - assert b'grobid0:tei_json' not in row - assert "non-TEI content" in output - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -def test_grobid_invalid_connection(mock_fetch, job): - - status = b'{"status": "done broke"}' - job.options.grobid_uri = 'http://host.invalid:8070/api/processFulltextDocument' - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - output = output.getvalue().decode('utf-8') - assert 'error' in output - assert 'GROBID' in output - assert job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') == {} - - -def test_wayback_failure(job): - - job.options.warc_uri_prefix = 'http://host.invalid/' - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - output = output.getvalue().decode('utf-8') - assert 'error' in output - assert 'wayback' in output - assert job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') == {} - - -@mock.patch('extraction_cdx_grobid.ResourceStore') -def test_wayback_not_found(mock_rs, job): - - # This is... a little convoluded. Basically creating a 404 situation for - # reading a wayback resource. - mock_resource = mock.MagicMock() - mock_resource.get_status.return_value = (404, "Not Found") - mock_rso = mock.MagicMock() - mock_rso.load_resource.return_value = mock_resource - mock_rs.return_value = mock_rso - print(mock_rs().load_resource().get_status()) - - job.options.warc_uri_prefix = 'http://dummy-archive.org/' - - output = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output) - job.run_mapper() - output = output.getvalue().decode('utf-8') - - print(output) - assert 'error' in output - assert 'not 200' in output - assert job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') == {} - - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -def test_mapper_rerun(mock_fetch, job): - - responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, - body=REAL_TEI_XML, content_type='text/xml') - - output1 = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output1) - job.run_mapper() - output1 = output1.getvalue().decode('utf-8') - - # wayback gets FETCH 1x times - assert mock_fetch.call_count == 1 - # grobid gets POST 1x times - assert len(responses.calls) == 1 - # HBase - assert job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') != {} - assert 'success' in output1 - - # Run again, same line - output2 = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output2) - job.run_mapper() - output2 = output2.getvalue().decode('utf-8') - - # wayback still only FETCH 1x times - assert mock_fetch.call_count == 1 - # grobid still only POST 1x times - assert len(responses.calls) == 1 - assert 'existing' in output2 - -@mock.patch('extraction_cdx_grobid.MRExtractCdxGrobid.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -def test_mapper_previously_backfilled(mock_fetch, job): - - responses.add(responses.POST, 'http://localhost:8070/api/processFulltextDocument', status=200, - body=REAL_TEI_XML, content_type='text/xml') - - job.hb_table.put(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ', - {b'f:c': b'{"some": "dict"}', b'file:col': b'bogus'}) - assert job.hb_table.row(b'sha1:ABCDEF12345Q2MSVX7XZKYAYSCX5QBYJ') != {} - - output1 = io.BytesIO() - job.sandbox(stdin=io.BytesIO(OK_CDX_LINE), stdout=output1) - job.run_mapper() - output1 = output1.getvalue().decode('utf-8') - - # wayback gets FETCH 1x times - assert mock_fetch.call_count == 1 - # grobid gets POST 1x times - assert len(responses.calls) == 1 - assert 'success' in output1 diff --git a/python/tests/test_extraction_ungrobided.py b/python/tests/test_extraction_ungrobided.py deleted file mode 100644 index cb46d29..0000000 --- a/python/tests/test_extraction_ungrobided.py +++ /dev/null @@ -1,178 +0,0 @@ - -import io -import json -import mrjob -import pytest -import struct -import responses -import happybase_mock -import wayback.exception -from unittest import mock -from common import parse_ungrobided_line -from extraction_ungrobided import MRExtractUnGrobided - - -FAKE_PDF_BYTES = b"%PDF SOME JUNK" + struct.pack("!q", 112853843) -OK_UNGROBIDED_LINE = b"\t".join(( - b"sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ", - b"""{"c": 1, "d": "2017-07-06T07:54:11", "f": "CITESEERX-CRAWL-2017-06-20-20170706075012840-00388-3671~wbgrp-svc285.us.archive.org~8443.warc.gz", "o": 914718776, "u": "http://www.ibc7.org/article/file_down.php?mode%3Darticle_print%26pid%3D250"}""", - b"application/pdf", - b"""{"c_size": 501, "dt": "20170706075411", "offset": 914718776, "surt": "org,ibc7)/article/file_down.php?mode=article_print&pid=250", "url": "http://www.ibc7.org/article/file_down.php?mode%3Darticle_print%26pid%3D250", "warc": "CITESEERX-CRAWL-2017-06-20-20170706074206206-00379-00388-wbgrp-svc285/CITESEERX-CRAWL-2017-06-20-20170706075012840-00388-3671~wbgrp-svc285.us.archive.org~8443.warc.gz"}""", -)) - -with open('tests/files/23b29ea36382680716be08fc71aa81bd226e8a85.xml', 'r') as f: - REAL_TEI_XML = f.read() - -@pytest.fixture -def job(): - """ - Note: this mock only seems to work with job.run_mapper(), not job.run(); - the later results in a separate instantiation without the mock? - """ - job = MRExtractUnGrobided(['--no-conf', '-']) - - conn = happybase_mock.Connection() - conn.create_table('wbgrp-journal-extract-test', - {'file': {}, 'grobid0': {}, 'f': {}}) - job.hb_table = conn.table('wbgrp-journal-extract-test') - - return job - - -@mock.patch('extraction_ungrobided.MRExtractUnGrobided.fetch_warc_content', return_value=(FAKE_PDF_BYTES, None)) -@responses.activate -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') - - raw = io.BytesIO(OK_UNGROBIDED_LINE) - - 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())) - - # wayback gets FETCH 1x times - mock_fetch.assert_called_once_with( - "CITESEERX-CRAWL-2017-06-20-20170706074206206-00379-00388-wbgrp-svc285/CITESEERX-CRAWL-2017-06-20-20170706075012840-00388-3671~wbgrp-svc285.us.archive.org~8443.warc.gz", - 914718776, - 501) - - # grobid gets POST 1x times - assert len(responses.calls) == 1 - - # HBase - assert job.hb_table.row(b'1') == {} - - # Saved extraction info - row = job.hb_table.row(b'sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ') - - assert struct.unpack("!q", row[b'file:size'])[0] == len(FAKE_PDF_BYTES) - # file:mime should actually not get clobbered by GROBID updater - #assert row[b'file:mime'] == b"application/pdf" - assert struct.unpack("!q", row[b'grobid0:status_code'])[0] == 200 - # TODO: assert row[b'grobid0:quality'] == None - 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 - -@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) - # file:mime should actually not get clobbered by GROBID updater - #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") - raw = " com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_ungrobided_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'prefix' in status['reason'] - - print("commented line") - raw = "#com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf application/pdf 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_ungrobided_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'prefix' in status['reason'] - - print("wrong column count") - raw = "a b c d e" - info, status = job.parse_ungrobided_line(raw) - assert info is None - assert status['status'] == "invalid" - assert 'parse' in status['reason'] - - print("CDX line, somehow") - raw = "com,sagepub,cep)/content/28/9/960.full.pdf 20170705062200 http://cep.sagepub.com/content/28/9/960.full.pdf - 200 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 401 313356621 CITESEERX-CRAWL-2017-06-20-20170705061647307-00039-00048-wbgrp-svc284/CITESEERX-CRAWL-2017-06-20-20170705062052659-00043-31209~wbgrp-svc284.us.archive.org~8443.warc.gz" - info, status = job.parse_ungrobided_line(raw) - assert info is None - print(status) - assert status['status'] == "invalid" - assert 'parse' in status['reason'] - -def test_parse_ungrobided_valid(): - - parsed = parse_ungrobided_line(OK_UNGROBIDED_LINE.decode('utf-8')) - assert parsed['key'] == "sha1:3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ" - assert parsed['f:c']['u'] == "http://www.ibc7.org/article/file_down.php?mode%3Darticle_print%26pid%3D250" - assert parsed['file:mime'] == "application/pdf" - assert parsed['file:cdx']['c_size'] == 501 - assert parsed['file:cdx']['dt'] == "20170706075411" -- cgit v1.2.3