def test_enqueue_opinions(self):
test_date = date(2011, 06, 17)
expected_html = open(TEST_OPINION_PATH + "nysd.2011_06_17.opinions.html").read()
expected_dockets = PP.parse_opinions(expected_html, 'nysd')
expected_pdf_bits = open(TEST_PDF_PATH + 'gov.uscourts.nysd.351385.14.0.pdf').read()
# Set up the test environment
# monkey patch out dependencies on pacer and rabbitmq
self.downloader.get_opinions = Mock(return_value=expected_dockets)
self.downloader.get_document = Mock(return_value=expected_pdf_bits)
self.downloader.channel.basic_publish = mock_publish_call = Mock()
self.downloader.enqueue_opinions('nysd', test_date, test_date)
self.assertEquals(2, mock_publish_call.call_count)
messages = [pickle.loads(args[1]['body']) \
for args in mock_publish_call.call_args_list]
filenames = [m['docket_filename'] for m in messages]
document_maps = [m['docnums_to_filename'] for m in messages]
#print filenames
for filename in filenames:
with open(filename) as f:
self.assertTrue(f.read() != None)
# cleanup
os.unlink(filename)
for docmap in document_maps:
self.assertEquals(1, len(docmap))
self.assertTrue(re.match(r'\d+-0', docmap.keys()[0]))
def test_enqueue_opinions(self):
test_date = date(2011, 06, 17)
expected_html = open(TEST_OPINION_PATH +
"nysd.2011_06_17.opinions.html").read()
expected_dockets = PP.parse_opinions(expected_html, 'nysd')
expected_pdf_bits = open(TEST_PDF_PATH +
'gov.uscourts.nysd.351385.14.0.pdf').read()
# Set up the test environment
# monkey patch out dependencies on pacer and rabbitmq
self.downloader.get_opinions = Mock(return_value=expected_dockets)
self.downloader.get_document = Mock(return_value=expected_pdf_bits)
self.downloader.channel.basic_publish = mock_publish_call = Mock()
self.downloader.enqueue_opinions('nysd', test_date, test_date)
self.assertEquals(2, mock_publish_call.call_count)
messages = [pickle.loads(args[1]['body']) \
for args in mock_publish_call.call_args_list]
filenames = [m['docket_filename'] for m in messages]
document_maps = [m['docnums_to_filename'] for m in messages]
#print filenames
for filename in filenames:
with open(filename) as f:
self.assertTrue(f.read() != None)
# cleanup
os.unlink(filename)
for docmap in document_maps:
self.assertEquals(1, len(docmap))
self.assertTrue(re.match(r'\d+-0', docmap.keys()[0]))
def test_download_opinions(self):
#TODO: Change this test to only use html tests.
# Pacer client tests shouldn't depend on parse pacer
test_date = date(2011, 06, 17)
expected_html = open(TEST_OPINION_PATH + "nysd.2011_06_17.opinions.html").read()
expected_dockets = PP.parse_opinions(expected_html, 'nysd')
opinions_html = self.pacer_client.get_opinions_html(court='nysd',
start_date = test_date,
end_date = test_date)
dockets = PP.parse_opinions(opinions_html, 'nysd')
self.assertEquals(len(expected_dockets), len(dockets))
for d in dockets:
self.assertTrue(d.get_casenum() in [e.get_casenum() for e in expected_dockets])
casemeta = d.get_casemeta()
self.assertTrue(casemeta['case_name'] in [e.get_casemeta()['case_name']
for e in expected_dockets])
def test_download_opinions(self):
#TODO: Change this test to only use html tests.
# Pacer client tests shouldn't depend on parse pacer
test_date = date(2011, 06, 17)
expected_html = open(TEST_OPINION_PATH +
"nysd.2011_06_17.opinions.html").read()
expected_dockets = PP.parse_opinions(expected_html, 'nysd')
opinions_html = self.pacer_client.get_opinions_html(
court='nysd', start_date=test_date, end_date=test_date)
dockets = PP.parse_opinions(opinions_html, 'nysd')
self.assertEquals(len(expected_dockets), len(dockets))
for d in dockets:
self.assertTrue(
d.get_casenum() in [e.get_casenum() for e in expected_dockets])
casemeta = d.get_casemeta()
self.assertTrue(
casemeta['case_name'] in
[e.get_casemeta()['case_name'] for e in expected_dockets])
def test_parse_opinions(self):
opinion_filelist = ["akd.1900", "akd.2010", "nysd.2009"]
#test empty file
filebits = open('/dev/null').read()
dockets = PP.parse_opinions(filebits, 'test')
self.assertEquals([], dockets)
filebits = {}
for opinion_file in opinion_filelist:
f = open(TEST_OPINION_PATH + opinion_file + ".opinions.html")
filebits[opinion_file] = f.read()
f.close()
#test valid opinion file with no entries
dockets = PP.parse_opinions(filebits["akd.1900"], "akd")
self.assertEquals([], dockets)
dockets = PP.parse_opinions(filebits["akd.2010"], "akd")
self.assertEquals(78, len(dockets) ) # number of entries in the opinions table
#check basic metadata
self.assertEquals("akd", dockets[0].get_court())
self.assertEquals("12460", dockets[0].get_casenum())
casemeta = dockets[0].get_casemeta()
self.assertEquals("Steffensen v. City of Fairbanks et al", casemeta['case_name'])
self.assertEquals("4:09-cv-00004-RJB", casemeta['docket_num'])
self.assertEquals("42:1983 Prisoner Civil Rights", casemeta["case_cause"])
self.assertEquals("Civil Rights: Other", casemeta["nature_of_suit"])
self.assertEquals(1, len(dockets[0].documents))
document = dockets[0].documents['98-0']
self.assertEquals("98", document['doc_num'])
self.assertEquals("0", document['attachment_num'])
self.assertEquals("563", document['pacer_de_seq_num'])
self.assertEquals("602530", document['pacer_dm_id'])
self.assertEquals("2010-01-05", document['date_filed'])
self.assertEquals("Order Dismissing Case", document['long_desc'])
self.assertEquals("akd", dockets[1].get_court())
self.assertEquals("18239", dockets[1].get_casenum())
casemeta = dockets[1].get_casemeta()
self.assertEquals("Kahle v. Executive Force Australia PTY LTD", casemeta['case_name'])
self.assertEquals("2:09-cv-00008-JWS", casemeta['docket_num'])
self.assertEquals("28:1441 Petition for Removal- Personal Injury", casemeta["case_cause"])
self.assertEquals("Personal Inj. Prod. Liability", casemeta["nature_of_suit"])
self.assertEquals(1, len(dockets[1].documents))
document = dockets[1].documents['27-0']
self.assertEquals("27", document['doc_num'])
self.assertEquals("0", document['attachment_num'])
self.assertEquals("142", document['pacer_de_seq_num'])
self.assertEquals("603861", document['pacer_dm_id'])
self.assertEquals("2010-01-07", document['date_filed'])
self.assertEquals("Order on Motion for Hearing, Order on Motion to Amend/Correct, Order on Motion to Remand to State Court, Order on Motion to Strike", document['long_desc'])
self.assertEquals("akd", dockets[5].get_court())
self.assertEquals("15580", dockets[5].get_casenum())
casemeta = dockets[5].get_casemeta()
self.assertEquals("USA v. Celestine et al", casemeta['case_name'])
self.assertEquals("3:2009-cr-00065-HRH", casemeta['docket_num'])
self.assertEquals(None, casemeta.get("case_cause"))
self.assertEquals(None, casemeta.get("nature_of_suit"))
self.assertEquals(1, len(dockets[5].documents))
document = dockets[5].documents['135-0']
self.assertEquals("135", document['doc_num'])
self.assertEquals("0", document['attachment_num'])
self.assertEquals("794", document['pacer_de_seq_num'])
self.assertEquals("616260", document['pacer_dm_id'])
self.assertEquals(datetime.date.today().isoformat(), document['date_filed'])
self.assertEquals("Order on Motion for Bill of Particulars, Order on Motion for Joinder", document['long_desc'])
#Sometimes the document url case id does not match the court case id
# In these cases we want to use the parent case number, but also have access to the child casenum
self.assertEquals("akd", dockets[2].get_court())
self.assertEquals("4655", dockets[2].get_casenum())
casemeta = dockets[2].get_casemeta()
self.assertEquals("USA v. Kott et al", casemeta['case_name'])
self.assertEquals("3:2007-cr-00056-JWS", casemeta['docket_num'])
self.assertEquals(1, len(dockets[2].documents))
document = dockets[2].documents['429-0']
self.assertEquals("429", document['doc_num'])
self.assertEquals("0", document['attachment_num'])
self.assertEquals("1946", document['pacer_de_seq_num'])
self.assertEquals("606429", document['pacer_dm_id'])
self.assertEquals("2010-01-13", document['date_filed'])
self.assertEquals("Order on Motion to Dismiss", document['long_desc'])
self.assertEquals("4656", document['casenum'])
# Some dockets have a different linking format from akd. Let's test these out
dockets = PP.parse_opinions(filebits["nysd.2009"], "nysd")
self.assertEquals(5916, len(dockets) ) # number of entries in the opinions table
self.assertEquals("nysd", dockets[0].get_court())
self.assertEquals("53122", dockets[0].get_casenum())
casemeta = dockets[0].get_casemeta()
self.assertEquals("Kingsway Financial v. Pricewaterhouse, et al", casemeta['case_name'])
self.assertEquals("1:03-cv-05560-RMB-HBP", casemeta['docket_num'])
self.assertEquals("15:78m(a) Securities Exchange Act", casemeta["case_cause"])
self.assertEquals("Securities/Commodities", casemeta["nature_of_suit"])
self.assertEquals(1, len(dockets[0].documents))
document = dockets[0].documents['380-0']
self.assertEquals("380", document['doc_num'])
self.assertEquals("0", document['attachment_num'])
self.assertEquals("6095482", document['pacer_de_seq_num'])
self.assertEquals("5453339", document['pacer_dm_id'])
self.assertEquals("2009-01-05", document['date_filed'])
self.assertEquals("Memorandum & Opinion", document['long_desc'])
# Some sanity checks about iquery type opinion pages
for docket in dockets:
self.assertEquals(1, len(docket.documents))
document = docket.documents.values()[0]
casenum_diff = int(docket.get_casenum()) - int(document['casenum'])
self.assertTrue(casenum_diff <= 0)
