def list(request):
# Handle file upload
if request.method == 'POST':
form = DocumentForm(request.POST, request.FILES)
tests=Detail.objects.all()
for test in tests:
if test.is_active==True:
testset=test.test_id
if form.is_valid():
newdoc = Document(docfile = request.FILES['docfile'], user=User.objects.get(username=request.user.username), test_set=Detail.objects.get(test_id=testset))
newdoc.save()
# Redirect to the document list after POST
return HttpResponseRedirect(reverse('uploads.views.list'))
else:
form = DocumentForm() # A empty, unbound form
# Load documents for the list page
documents = Document.objects.all()
# Render list page with the documents and the form
return render_to_response(
'list.html',
{'documents': documents, 'form': form},
context_instance=RequestContext(request))
class TestAddDocMetaView(unittest.TestCase):
def setUp(self):
self.client = Client()
self.existing_document = Document(court='nysd', casenum='1234', docnum='1', subdocnum='0')
self.existing_document.save()
self.adddocparams = { 'court': 'nysd', 'casenum': '1234',
'docnum': '1', 'de_seq_num': '1111',
'dm_id': '2222', 'docid': '3330'}
def tearDown(self):
Document.objects.all().delete()
def test_adddoc_only_post_requests_allowed(self):
response = self.client.get('/recap/adddocmeta/')
self.assertEquals("adddocmeta: Not a POST request.", response.content)
def test_adddoc_request_data_missing(self):
response = self.client.post('/recap/adddocmeta/', {'docid': '1234'})
self.assertTrue(response.content.startswith("adddocmeta: \"Key 'court' not found"))
def test_adddoc_updates_meta(self):
self.assertEquals(None, self.existing_document.docid)
response = self.client.post('/recap/adddocmeta/', self.adddocparams)
self.assertEquals("adddocmeta: DB updated for docid=3330", response.content)
query = Document.objects.filter(court='nysd', casenum='1234',
docnum='1', subdocnum='0')
saved_document = query[0]
self.assertEquals(1111, saved_document.de_seq_num)
self.assertEquals(2222, saved_document.dm_id)
self.assertEquals('3330', saved_document.docid)
def test_adddoc_coerces_doc_id(self):
self.adddocparams['docid'] = '123456789'
response = self.client.post('/recap/adddocmeta/', self.adddocparams)
query = Document.objects.filter(court='nysd', casenum='1234',
docnum='1', subdocnum='0')
saved_document = query[0]
self.assertEquals('123056789', saved_document.docid)
def test_adddoc_creates_new_document(self):
query = Document.objects.filter(court='nysd', casenum='5678',
docnum='1', subdocnum='0')
self.adddocparams['casenum'] = '5678'
self.assertEquals(0, query.count())
response = self.client.post('/recap/adddocmeta/', self.adddocparams)
self.assertEquals(1, query.count())
created_doc = query[0]
created_doc.docid = self.adddocparams['docid']
def test_adddoc_responds_with_document_dict(self):
self.adddocparams['add_case_info'] = True
response = self.client.post('/recap/adddocmeta/', self.adddocparams)
response_dict = simplejson.loads(response.content)
self.assertEquals(1, len(response_dict['documents']))
self.assertTrue(self.adddocparams['docid'] in response_dict['documents'])
def test_heartbeat_correct_key_with_db_connection(self):
document = Document(court='cand', casenum='215270', docnum='1', subdocnum='0')
document.save()
response = self.client.get('/recap/heartbeat/', {'key' : config['API_KEYS'][0]})
self.assertEquals(200, response.status_code)
self.assertEquals("It's Alive!", response.content)
def test_update_local_db_updates_existing(self):
d1 = Document(court='nysd', casenum='1234', docnum='1', subdocnum='2')
d1.save()
self.assertEquals(1, Document.objects.count())
doc_meta = self.doc_xml.get_document_metadict('1', '2')
doc_meta['pacer_doc_id'] = '12'
DocumentManager.update_local_db(self.doc_xml)
created_doc = Document.objects.all()[0]
self.assertEquals(1, Document.objects.count())
self.assertEquals('12', created_doc.docid)
def test_update_local_db_updates_existing(self):
d1 = Document(court='nysd', casenum='1234', docnum='1', subdocnum='2')
d1.save()
self.assertEquals(1, Document.objects.count())
doc_meta = self.doc_xml.get_document_metadict('1', '2')
doc_meta['pacer_doc_id'] = '12'
DocumentManager.update_local_db(self.doc_xml)
created_doc = Document.objects.all()[0]
self.assertEquals(1, Document.objects.count())
self.assertEquals('12', created_doc.docid)
def test_update_local_db_doesnt_overwrite_local(self):
d1 = Document(court='nysd', casenum='1234',
docnum='1', subdocnum='2',
docid='120')
d1.save()
self.assertEquals(1, Document.objects.count())
# This document doesn't have docid, but we shouldn't overwrite
DocumentManager.update_local_db(self.doc_xml)
created_doc = Document.objects.all()[0]
self.assertEquals(1, Document.objects.count())
self.assertEquals('120', created_doc.docid)
def update_local_db(docket, ignore_available=1):
court = docket.casemeta["court"]
casenum = docket.casemeta["pacer_case_num"]
for docmeta in docket.documents.values():
docnum = docmeta["doc_num"]
subdocnum = docmeta["attachment_num"]
docquery = Document.objects.filter(court=court, casenum=casenum, docnum=docnum, subdocnum=subdocnum)
try:
docentry = docquery[0]
except IndexError:
# Add this new document to our DB
docentry = Document(court=court, casenum=casenum, docnum=docnum, subdocnum=subdocnum)
try:
docentry.docid = docmeta["pacer_doc_id"]
except KeyError:
pass
try:
docentry.de_seq_num = docmeta["pacer_de_seq_num"]
except KeyError:
pass
try:
docentry.dm_id = docmeta["pacer_dm_id"]
except KeyError:
pass
try:
docentry.sha1 = docmeta["sha1"]
except KeyError:
pass
if not ignore_available:
try:
docentry.available = docmeta["available"]
except KeyError:
pass
try:
docentry.lastdate = docmeta["upload_date"]
except KeyError:
pass
try:
docentry.free_import = docmeta["free_import"]
except KeyError:
pass
try:
docentry.save()
except IntegrityError:
logging.error("update_local_db: could not save %s %s %s %s" % (court, casenum, docnum, subdocnum))
def handle_adddocmeta(docid, court, casenum, de_seq_num, dm_id, docnum,
subdocnum):
docid = ParsePacer.coerce_docid(docid)
query = Document.objects.filter(court=court,
casenum=casenum,
docnum=docnum,
subdocnum=subdocnum)
try:
doc = query[0]
except IndexError:
doc = Document(docid=docid,
court=court,
casenum=casenum,
de_seq_num=de_seq_num,
dm_id=dm_id,
docnum=docnum,
subdocnum=subdocnum)
else:
doc.de_seq_num = de_seq_num
doc.dm_id = dm_id
doc.docnum = docnum
doc.docid = docid
try:
doc.save()
except IntegrityError:
logging.error("handle_adddocmeta: could not save docid %s" % (docid))
def test_update_local_db_doesnt_overwrite_local(self):
d1 = Document(court='nysd',
casenum='1234',
docnum='1',
subdocnum='2',
docid='120')
d1.save()
self.assertEquals(1, Document.objects.count())
# This document doesn't have docid, but we shouldn't overwrite
DocumentManager.update_local_db(self.doc_xml)
created_doc = Document.objects.all()[0]
self.assertEquals(1, Document.objects.count())
self.assertEquals('120', created_doc.docid)
def test_add_document_object(self):
d1 = Document(court='nysd',
casenum='1234',
docnum='2',
subdocnum='3',
de_seq_num='20',
dm_id='12',
docid='789',
sha1='hash',
available='1',
free_import=1,
lastdate='lastdate',
modified='1')
expected_dict = {
'doc_num': '2',
'attachment_num': '3',
'pacer_doc_id': '789',
'pacer_de_seq_num': '20',
'pacer_dm_id': '12',
'upload_date': 'lastdate',
'available': '1',
'free_import': '1',
'sha1': 'hash'
}
self.doc_xml.add_document_object(d1)
actual_dict = self.doc_xml.get_document_metadict('2', '3')
self.assertEquals(expected_dict, actual_dict)
def setUp(self):
self.client = Client()
self.existing_document = Document(court='nysd', casenum='1234', docnum='1', subdocnum='0')
self.existing_document.save()
self.adddocparams = { 'court': 'nysd', 'casenum': '1234',
'docnum': '1', 'de_seq_num': '1111',
'dm_id': '2222', 'docid': '3330'}
def handle_adddocmeta(docid, court, casenum, de_seq_num, dm_id, docnum, subdocnum):
docid = ParsePacer.coerce_docid(docid)
query = Document.objects.filter(court=court, casenum=casenum, docnum=docnum, subdocnum=subdocnum)
try:
doc = query[0]
except IndexError:
doc = Document(
docid=docid,
court=court,
casenum=casenum,
de_seq_num=de_seq_num,
dm_id=dm_id,
docnum=docnum,
subdocnum=subdocnum,
)
else:
doc.de_seq_num = de_seq_num
doc.dm_id = dm_id
doc.docnum = docnum
doc.docid = docid
try:
doc.save()
except IntegrityError:
logging.error("handle_adddocmeta: could not save docid %s" % (docid))
def setUp(self):
self.client = Client()
self.not_avail_doc = Document(
court="nysd", casenum="1234", docnum="1", subdocnum="0", dm_id="1234", de_seq_num="111", docid="12304213"
)
self.not_avail_doc.save()
self.available_doc = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="0", dm_id="1234", de_seq_num="111", docid="1230445"
)
self.available_doc.available = "1"
self.available_doc.lastdate = datetime.datetime.now()
self.available_doc.save()
self.docs = [self.not_avail_doc, self.available_doc]
self.valid_params = {"court": "nysd", "urls": [self._show_doc_url_for_document(d) for d in self.docs]}
self.valid_params_doc1 = {"court": "nysd", "urls": [self._doc1_url_for_document(d) for d in self.docs]}
def setUp(self):
self.client = Client()
self.valid_params = {'court': 'nysd',
'casenum' : '1234'}
self.available_doc = Document(court='nysd', casenum='1234', docnum='2', subdocnum='0',
dm_id = '1234', de_seq_num = '111', docid = '1230445')
self.available_doc.available = '1'
self.available_doc.lastdate = datetime.datetime.now()
self.available_doc.save()
def list(request):
# Handle file upload
if request.method == 'POST':
form = DocumentForm(request.POST, request.FILES)
if form.is_valid():
newdoc = Document(docfile = request.FILES['docfile'])
newdoc.save()
# Redirect to the document list after POST
return HttpResponseRedirect('/')
else:
form = DocumentForm() # A empty, unbound form
# Load documents for the list page
documents = Document.objects.all()
# Render list page with the documents and the form
return render_to_response(
'uploads/list.html',
{'documents': documents, 'form': form},
context_instance=RequestContext(request)
)
def test_valid_query_response_with_subdocuments(self):
subdoc1 = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="1", available=1, lastdate=datetime.datetime.now()
)
subdoc2 = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="2", available=1, lastdate=datetime.datetime.now()
)
subdoc3 = Document(court="nysd", casenum="1234", docnum="2", subdocnum="3")
subdoc1.save()
subdoc2.save()
subdoc3.save()
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params)})
output = simplejson.loads(response.content)
avail_show_doc_url = self._show_doc_url_for_document(self.available_doc)
self.assertTrue(avail_show_doc_url in output)
self.assertTrue("subDocuments" in output[avail_show_doc_url])
subdoc_dict = output[avail_show_doc_url]["subDocuments"]
self.assertEquals(2, len(subdoc_dict))
self.assertEquals(self._ia_url_for_doc(subdoc1), subdoc_dict["1"]["filename"])
def test_get_updated_cases_valid_request(self):
d1 = Document(court='nysd', casenum='1234', docnum='1', subdocnum='0')
d1.save()
d2 = Document(court='dcd', casenum='100', docnum='1', subdocnum='0')
d2.save()
yesterday = time.time() - 60 * 60 * 24
response = self.client.post('/recap/get_updated_cases/', {'key' : config['API_KEYS'][0],
'tpq' : yesterday})
self.assertEquals(200, response.status_code)
self.assertEquals('%s,%s\r\n%s,%s\r\n' % (d1.court, d1.casenum, d2.court, d2.casenum), response.content)
self.assertEquals({'Content-Type': 'text/csv'}, response.headers)
def create_profile(request):
if request.method == 'POST':
form = DocumentForm(request.POST, request.FILES)
employee_id=""
if form.is_valid():
image_validator, origin_image, image_drawn = form.cleaned_data['photo']
#def the uploaded image has 1 face and is valid
if (image_validator==1):
record = Document()
record.photo=origin_image
record.firstname=form.cleaned_data['firstname']
record.lastname=form.cleaned_data['lastname']
record.department=form.cleaned_data['department']
record.save()
employee_id=record.employee_id
buffered = BytesIO()
#face_no, image_drawn = draw_face(image.file.read())
image_drawn.save(buffered, format="JPEG")
b64_img = base64.b64encode((buffered.getvalue()))
one_face= image_validator==1
#multi_face = image_validator>1
no_face = image_validator==0
return render(request, 'view_form.html', {
'form': form, 'image_drawn':b64_img,'one_face':one_face, 'no_face': no_face, 'employee_id': employee_id
})
else:
form = DocumentForm()
return render(request, 'create_form.html', {
'form': form
})
def setUp(self):
self.client = Client()
self.f = open(TEST_DOCKET_PATH + 'DktRpt_111111.html')
self.valid_params = {'court': 'nysd',
'casenum' : '1234',
'mimetype' : 'text/html',
'data': self.f}
self.f_pdf = open(TEST_DOCUMENT_PATH + 'gov.uscourts.cand.206019.18.0.pdf')
self.valid_params_pdf = {'court': 'cand',
'casenum': '206019',
'mimetype': 'application/pdf',
'url': 'https://ecf.cand.uscourts.gov/doc1/123456', #docid
'data': self.f_pdf}
#Doc id is 'coerced', so doesn't match one above
self.pdf_doc = Document(court='cand', casenum='206019',
docnum='18', subdocnum='0', docid=123056)
self.pdf_doc.save()
self.f_doc1 = open(TEST_DOC1_PATH + 'ecf.cand.uscourts.gov.03517852828')
self.valid_params_doc1 = {'court': 'cand',
'casenum': '206019',
'mimetype': 'text/html',
'data': self.f_doc1}
def update_local_db(docket, ignore_available=1, team_name=None):
court = docket.casemeta["court"]
casenum = docket.casemeta["pacer_case_num"]
for docmeta in docket.documents.values():
docnum = docmeta["doc_num"]
subdocnum = docmeta["attachment_num"]
docquery = Document.objects.filter(court=court,
casenum=casenum,
docnum=docnum,
subdocnum=subdocnum)
try:
docentry = docquery[0]
except IndexError:
# New item: Add it to our DB
docentry = Document(court=court, casenum=casenum,
docnum=docnum, subdocnum=subdocnum)
if team_name is not None:
# Only add the team_name to new items
docentry.team_name = team_name
except OperationalError:
logging.error("update_local_db: could not save %s %s %s %s"
% (court, casenum, docnum, subdocnum))
return
try:
docentry.docid = docmeta["pacer_doc_id"]
except KeyError:
pass
try:
docentry.de_seq_num = docmeta["pacer_de_seq_num"]
except KeyError:
pass
try:
docentry.dm_id = docmeta["pacer_dm_id"]
except KeyError:
pass
try:
docentry.sha1 = docmeta["sha1"]
except KeyError:
pass
if not ignore_available:
try:
docentry.available = docmeta["available"]
except KeyError:
pass
try:
docentry.lastdate = docmeta["upload_date"]
except KeyError:
pass
try:
docentry.free_import = docmeta["free_import"]
except KeyError:
pass
try:
docentry.save()
except IntegrityError:
logging.error("update_local_db: could not save %s %s %s %s"
% (court, casenum, docnum, subdocnum))
class TestQueryCasesView(unittest.TestCase):
def setUp(self):
self.client = Client()
self.valid_params = {'court': 'nysd',
'casenum' : '1234'}
self.available_doc = Document(court='nysd', casenum='1234', docnum='2', subdocnum='0',
dm_id = '1234', de_seq_num = '111', docid = '1230445')
self.available_doc.available = '1'
self.available_doc.lastdate = datetime.datetime.now()
self.available_doc.save()
def tearDown(self):
Document.objects.all().delete()
def test_query_cases_post_request_only(self):
response = self.client.get('/recap/query_cases/', {'blah' : 'foo'})
self.assertEquals('query_cases: Not a POST request.', response.content)
def test_query_cases_no_params(self):
response = self.client.post('/recap/query_cases/')
self.assertEquals("query_cases: no 'json' POST argument", response.content)
def test_query_cases_missing_court_param(self):
del self.valid_params['court']
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
self.assertEquals("query_cases: missing json 'court' argument.", response.content)
def test_query_cases_missing_casenum_param(self):
del self.valid_params['casenum']
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
self.assertEquals("query_cases: missing json 'casenum' argument.", response.content)
def test_valid_query_cases_response_no_match(self):
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
self.assertEquals("{}", response.content)
def test_valid_query_cases_response_no_match(self):
self.valid_params['casenum'] = '99999'
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
self.assertEquals("{}", response.content)
def test_valid_query_cases_response_available_doc_match(self):
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
output= simplejson.loads(response.content)
self.assertEquals(2, len(output))
self.assertEquals(self.available_doc.lastdate.strftime("%m/%d/%y"), output['timestamp'])
self.assertEquals(IACommon.get_dockethtml_url('nysd', '1234'), output['docket_url'])
def test_valid_query_cases_response_unavailable_doc_currently_uploading(self):
self.available_doc.available = 0
self.available_doc.save()
ppquery = PickledPut(filename=IACommon.get_docketxml_name('nysd', '1234'))
ppquery.save()
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
self.assertEquals("{}", response.content)
PickledPut.objects.all().delete()
def test_valid_query_cases_response_old_doc_currently_uploading(self):
self.available_doc.available = 0
two_days_ago = datetime.datetime.now() - datetime.timedelta(2)
self.available_doc.modified= two_days_ago
self.available_doc.save()
ppquery = PickledPut(filename=IACommon.get_docketxml_name('nysd', '1234'))
ppquery.save()
response = self.client.post('/recap/query_cases/', {'json': simplejson.dumps(self.valid_params)})
output= simplejson.loads(response.content)
self.assertEquals(2, len(output))
self.assertEquals(self.available_doc.lastdate.strftime("%m/%d/%y"), output['timestamp'])
self.assertEquals(IACommon.get_dockethtml_url('nysd', '1234'), output['docket_url'])
PickledPut.objects.all().delete()
class TestQueryView(unittest.TestCase):
def setUp(self):
self.client = Client()
self.not_avail_doc = Document(
court="nysd", casenum="1234", docnum="1", subdocnum="0", dm_id="1234", de_seq_num="111", docid="12304213"
)
self.not_avail_doc.save()
self.available_doc = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="0", dm_id="1234", de_seq_num="111", docid="1230445"
)
self.available_doc.available = "1"
self.available_doc.lastdate = datetime.datetime.now()
self.available_doc.save()
self.docs = [self.not_avail_doc, self.available_doc]
self.valid_params = {"court": "nysd", "urls": [self._show_doc_url_for_document(d) for d in self.docs]}
self.valid_params_doc1 = {"court": "nysd", "urls": [self._doc1_url_for_document(d) for d in self.docs]}
def tearDown(self):
Document.objects.all().delete()
def _show_doc_url_for_document(self, doc):
show_doc_url = "".join(
[
"/cgi-bin/show_doc.pl?",
"caseid=%(casenum)s",
"&de_seq_num=%(de_seq_num)s",
"&dm_id=%(dm_id)s",
"&doc_num=%(docnum)s",
"&pdf_header=2",
]
)
show_doc_dict = {"casenum": doc.casenum, "de_seq_num": doc.de_seq_num, "dm_id": doc.dm_id, "docnum": doc.docnum}
return show_doc_url % show_doc_dict
def _doc1_url_for_document(self, doc):
return "/doc1/%s" % doc.docid
def _ia_url_for_doc(self, doc):
return IACommon.get_pdf_url(doc.court, doc.casenum, doc.docnum, doc.subdocnum)
def test_query_post_request_only(self):
response = self.client.get("/recap/query/", {"blah": "foo"})
self.assertEquals("query: Not a POST request.", response.content)
def test_query_no_params(self):
response = self.client.post("/recap/query/")
self.assertEquals("query: no 'json' POST argument", response.content)
def test_query_invalid_json(self):
response = self.client.post("/recap/query/", {"json": "dkkfkdk"})
self.assertEquals("query: malformed 'json' POST argument", response.content)
def test_query_missing_court_param(self):
del self.valid_params["court"]
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params)})
self.assertEquals("query: missing json 'court' argument.", response.content)
def test_query_missing_url_param(self):
del self.valid_params["urls"]
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params)})
self.assertEquals("query: missing json 'urls' argument.", response.content)
def test_valid_show_doc_query_response(self):
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params)})
output = simplejson.loads(response.content)
avail_show_doc_url = self._show_doc_url_for_document(self.available_doc)
self.assertTrue(avail_show_doc_url in output)
self.assertFalse(self._show_doc_url_for_document(self.not_avail_doc) in output)
self.assertEquals(self.available_doc.lastdate.strftime("%m/%d/%y"), output[avail_show_doc_url]["timestamp"])
self.assertEquals(self._ia_url_for_doc(self.available_doc), output[avail_show_doc_url]["filename"])
def test_valid_doc1_url_query_response(self):
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params_doc1)})
output = simplejson.loads(response.content)
avail_show_doc_url = self._doc1_url_for_document(self.available_doc)
self.assertFalse(self._doc1_url_for_document(self.not_avail_doc) in output)
self.assertEquals(self.available_doc.lastdate.strftime("%m/%d/%y"), output[avail_show_doc_url]["timestamp"])
self.assertEquals(self._ia_url_for_doc(self.available_doc), output[avail_show_doc_url]["filename"])
def test_valid_query_response_with_subdocuments(self):
subdoc1 = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="1", available=1, lastdate=datetime.datetime.now()
)
subdoc2 = Document(
court="nysd", casenum="1234", docnum="2", subdocnum="2", available=1, lastdate=datetime.datetime.now()
)
subdoc3 = Document(court="nysd", casenum="1234", docnum="2", subdocnum="3")
subdoc1.save()
subdoc2.save()
subdoc3.save()
response = self.client.post("/recap/query/", {"json": simplejson.dumps(self.valid_params)})
output = simplejson.loads(response.content)
avail_show_doc_url = self._show_doc_url_for_document(self.available_doc)
self.assertTrue(avail_show_doc_url in output)
self.assertTrue("subDocuments" in output[avail_show_doc_url])
subdoc_dict = output[avail_show_doc_url]["subDocuments"]
self.assertEquals(2, len(subdoc_dict))
self.assertEquals(self._ia_url_for_doc(subdoc1), subdoc_dict["1"]["filename"])
def update_local_db(docket, ignore_available=1, team_name=None):
court = docket.casemeta["court"]
casenum = docket.casemeta["pacer_case_num"]
for docmeta in docket.documents.values():
docnum = docmeta["doc_num"]
subdocnum = docmeta["attachment_num"]
docquery = Document.objects.filter(court=court,
casenum=casenum,
docnum=docnum,
subdocnum=subdocnum)
try:
docentry = docquery[0]
except IndexError:
# New item: Add it to our DB
docentry = Document(court=court,
casenum=casenum,
docnum=docnum,
subdocnum=subdocnum)
if team_name is not None:
# Only add the team_name to new items
docentry.team_name = team_name
except OperationalError:
logging.error("update_local_db: could not save %s %s %s %s" %
(court, casenum, docnum, subdocnum))
return
try:
docentry.docid = docmeta["pacer_doc_id"]
except KeyError:
pass
try:
docentry.de_seq_num = docmeta["pacer_de_seq_num"]
except KeyError:
pass
try:
docentry.dm_id = docmeta["pacer_dm_id"]
except KeyError:
pass
try:
docentry.sha1 = docmeta["sha1"]
except KeyError:
pass
if not ignore_available:
try:
docentry.available = docmeta["available"]
except KeyError:
pass
try:
docentry.lastdate = docmeta["upload_date"]
except KeyError:
pass
try:
docentry.free_import = docmeta["free_import"]
except KeyError:
pass
try:
docentry.save()
except IntegrityError:
logging.error("update_local_db: could not save %s %s %s %s" %
(court, casenum, docnum, subdocnum))
class TestUploadView(unittest.TestCase):
def setUp(self):
self.client = Client()
self.f = open(TEST_DOCKET_PATH + 'DktRpt_111111.html')
self.valid_params = {'court': 'nysd',
'casenum' : '1234',
'mimetype' : 'text/html',
'data': self.f}
self.f_pdf = open(TEST_DOCUMENT_PATH + 'gov.uscourts.cand.206019.18.0.pdf')
self.valid_params_pdf = {'court': 'cand',
'casenum': '206019',
'mimetype': 'application/pdf',
'url': 'https://ecf.cand.uscourts.gov/doc1/123456', #docid
'data': self.f_pdf}
#Doc id is 'coerced', so doesn't match one above
self.pdf_doc = Document(court='cand', casenum='206019',
docnum='18', subdocnum='0', docid=123056)
self.pdf_doc.save()
self.f_doc1 = open(TEST_DOC1_PATH + 'ecf.cand.uscourts.gov.03517852828')
self.valid_params_doc1 = {'court': 'cand',
'casenum': '206019',
'mimetype': 'text/html',
'data': self.f_doc1}
def tearDown(self):
self.f.close()
self.f_pdf.close()
self.f_doc1.close()
for p in PickledPut.objects.all():
IA.delete_pickle(p.filename)
p.delete()
Document.objects.all().delete()
def test_upload_post_request_only(self):
response = self.client.get('/recap/upload/', {'blah' : 'foo'})
self.assertEquals('upload: Not a POST request.', response.content)
def test_upload_no_params(self):
response = self.client.post('/recap/upload/')
self.assertEquals("upload: No request.FILES attribute.", response.content)
def test_upload_docket_no_court_param(self):
del self.valid_params['court']
response = self.client.post('/recap/upload/', self.valid_params)
self.assertEquals("upload: No POST 'court' attribute.", response.content)
def test_upload_docket_invalid_casenum_param(self):
self.valid_params['casenum'] = 'garbage_data'
response = self.client.post('/recap/upload/', self.valid_params)
self.assertEquals("upload: 'casenum' invalid: garbage_data", response.content)
def test_upload_docket_no_casenum_param(self):
del self.valid_params['casenum']
response = self.client.post('/recap/upload/', self.valid_params)
self.assertEquals("upload: docket has no casenum.", response.content)
def test_upload_docket_no_mimetype_param(self):
del self.valid_params['mimetype']
response = self.client.post('/recap/upload/', self.valid_params)
self.assertEquals("upload: No POST 'mimetype' attribute.", response.content)
def test_upload_docket_report(self):
response = self.client.post('/recap/upload/', self.valid_params)
output = simplejson.loads(response.content)
self.assertEquals(3, len(output))
self.assertEquals("DktRpt successfully parsed.", output['message'])
# After upload, a pickled put should be created
# If this fails, make sure you've created a picklejar directory
self.assertEquals(1, PickledPut.objects.all().count())
pp = PickledPut.objects.all()[0]
self.assertEquals(1, pp.ready)
def test_upload_docket_report_for_unlocked_bucket(self):
# Setup - Upload a docket
response = self.client.post('/recap/upload/', self.valid_params)
# After upload, a pickled put should be created
self.assertEquals(1, PickledPut.objects.all().count())
#Do it again, to test whether merges are handled correctly
response = self.client.post('/recap/upload/', self.valid_params)
output = simplejson.loads(response.content)
self.assertEquals("DktRpt successfully parsed.", output['message'])
self.assertEquals(1, PickledPut.objects.all().count())
pp = PickledPut.objects.all()[0]
self.assertEquals(1, pp.ready)
#TK: This case seems wrong, we discard the newer docket if an old docket
# on the same case is being uploaded. Might be too edge casey to worry about
# The function test behavior is the same as the one above, so going to leave it
# unimplemented for now
def test_upload_docket_report_for_locked_bucket(self):
pass
def test_upload_document_without_url(self):
del self.valid_params_pdf['url']
response = self.client.post('/recap/upload/', self.valid_params_pdf)
self.assertEquals('upload: pdf failed. no url supplied.', response.content)
#TK: Handle this case better? Most likely isn't possible
def test_upload_document_no_associated_document_with_docid(self):
self.pdf_doc.delete()
response = self.client.post('/recap/upload/', self.valid_params_pdf)
self.assertEquals('upload: pdf ignored.', response.content)
def test_upload_document_no_record_of_docid(self):
self.pdf_doc.docid=99999
self.pdf_doc.save()
response = self.client.post('/recap/upload/', self.valid_params_pdf)
self.assertEquals('upload: pdf ignored.', response.content)
def test_upload_document_metadata_mismatch(self):
self.valid_params_pdf['court'] = 'azb'
response = self.client.post('/recap/upload/', self.valid_params_pdf)
self.assertEquals('upload: pdf metadata mismatch.', response.content)
def test_upload_document(self):
response = self.client.post('/recap/upload/', self.valid_params_pdf)
output = simplejson.loads(response.content)
self.assertEquals('pdf uploaded.', output['message'])
self.assertEquals(2, PickledPut.objects.all().count())
self.pdf_doc = Document.objects.all()[0]
self.assertTrue(self.pdf_doc.sha1 != None)
self.assertEquals("5741373aff552f22fa2f14f2bd39fea4564aa49c", self.pdf_doc.sha1)
def test_upload_document_no_sha1_difference(self):
#set the sha1 to what we know it to be
self.pdf_doc.sha1 = "5741373aff552f22fa2f14f2bd39fea4564aa49c"
self.pdf_doc.save()
response = self.client.post('/recap/upload/', self.valid_params_pdf)
output = simplejson.loads(response.content)
self.assertEquals('pdf uploaded.', output['message'])
# we only upload a docket update if the doc is the same
self.assertEquals(1, PickledPut.objects.all().count())
# have to do some patching to get around the filename issue
@patch('uploads.UploadHandler.is_doc1_html', Mock(return_value=True))
@patch('uploads.UploadHandler.docid_from_url_name', Mock(return_value='9999999'))
def test_upload_doc1_no_matching_docid(self):
response = self.client.post('/recap/upload/', self.valid_params_doc1)
self.assertEquals('upload: doc1 ignored.', response.content)
# have to do some patching to get around the filename issue
@patch('uploads.UploadHandler.is_doc1_html', Mock(return_value=True))
@patch('uploads.UploadHandler.docid_from_url_name', Mock(return_value='123056'))
def test_upload_doc1(self):
response = self.client.post('/recap/upload/', self.valid_params_doc1)
output = simplejson.loads(response.content)
self.assertEquals('doc1 successfully parsed.', output['message'])
self.assertTrue('cases' in output)
