def test_parsing_results(self):
"""Can we do a simple query and parse?"""
paths = []
path_root = os.path.join(TESTS_ROOT, "examples", "pacer",
"attachment_pages")
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, '*.html'):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
court = filename_sans_ext.split('_')[0]
report = AttachmentPage(court)
with open(path, 'r') as f:
report._parse_text(f.read().decode('utf-8'))
data = report.data
if not os.path.exists(json_path):
with open(json_path, 'w') as f:
print("Creating new file at %s" % json_path)
json.dump(data, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, data)
sys.stdout.write("✓\n")
def parse_files(self, path_root, file_ext):
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, file_ext):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
t1 = time.time()
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
with open(path, 'rb') as f:
text = f.read()
result = check_if_logged_in_page(text)
if not os.path.exists(json_path):
with open(json_path, 'w') as f:
print("Creating new file at %s" % json_path)
json.dump(result, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, result)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=0.5)
sys.stdout.write("✓\n")
def parse_files(self, path_root, file_ext):
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, file_ext):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
t1 = time.time()
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
with open(path, 'rb') as f:
text = f.read()
result = check_if_logged_in_page(text)
if not os.path.exists(json_path):
with open(json_path, 'w') as f:
print("Creating new file at %s" % json_path)
json.dump(result, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, result)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=0.5)
sys.stdout.write("✓\n")
def run_parsers_on_path(self, path):
"""Test all the parsers on a given local path
:param path: The path where you can find the files
"""
file_paths = glob.glob(path)
file_paths.sort()
path_max_len = max(len(path) for path in file_paths) + 2
for i, path in enumerate(file_paths):
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
t1 = time.time()
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split(".")[0]
json_path = os.path.join(
dirname, "%s_result.json" % filename_sans_ext
)
lasc = LASCSearch(session=None)
with open(path, "rb") as f:
data = json.load(f)
clean_data = lasc._parse_case_data(data)
if not os.path.isfile(json_path):
# First time testing this docket
bar = "*" * 50
print(
"\n\n%s\nJSON FILE DID NOT EXIST. CREATING IT AT:"
"\n\n %s\n\n"
"Please test the data in this file before assuming "
"everything worked.\n%s\n" % (bar, json_path, bar)
)
with open(json_path, "w") as f:
json.dump(clean_data, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, clean_data)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=1)
sys.stdout.write("✓ - %0.1fs\n" % (t2 - t1))
def parse_files(self,
path_root,
file_ext,
test_class,
initialize_with_court=True):
"""Can we do a simple query and parse?"""
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, file_ext):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
t1 = time.time()
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
if initialize_with_court:
court = filename_sans_ext.split('_')[0]
report = test_class(court)
else:
report = test_class()
with open(path, 'rb') as f:
report._parse_text(f.read().decode('utf-8'))
data = report.data
if not os.path.exists(json_path):
with open(json_path, 'w') as f:
print("Creating new file at %s" % json_path)
json.dump(data, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, data)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=2)
sys.stdout.write("✓\n")
def parse_files(self, path_root, file_ext, test_class,
initialize_with_court=True):
"""Can we do a simple query and parse?"""
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, file_ext):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
t1 = time.time()
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
if initialize_with_court:
court = filename_sans_ext.split('_')[0]
report = test_class(court)
else:
report = test_class()
with open(path, 'r') as f:
report._parse_text(f.read().decode('utf-8'))
data = report.data
if not os.path.exists(json_path):
with open(json_path, 'w') as f:
print("Creating new file at %s" % json_path)
json.dump(data, f, indent=2, sort_keys=True)
continue
with open(json_path) as f:
j = json.load(f)
self.assertEqual(j, data)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=2)
sys.stdout.write("✓\n")
def persist_data(data):
json.dump(data, file(fname, "w"))
def run_parsers_on_path(
self,
path_root,
required_fields=['date_filed', 'case_name', 'docket_number']):
"""Test all the parsers, faking the network query."""
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, '*.html'):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
t1 = time.time()
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
court = filename_sans_ext.split('_')[0]
report = DocketReport(court)
with open(path, 'rb') as f:
report._parse_text(f.read().decode('utf-8'))
data = report.data
if data != {}:
# If the docket is a valid docket, make sure some required
# fields are populated.
for field in required_fields:
self.assertTrue(
data[field],
msg="Unable to find truthy value for field %s" % field,
)
self.assertEqual(data['court_id'], court)
# Party-specific tests...
for party in data['parties']:
self.assertTrue(
party.get('name', False),
msg="Every party must have a name attribute. Did not "
"get a value for:\n\n%s" % party)
# Protect against effed up adversary proceedings cases that
# don't parse properly. See: cacb, 2:08-ap-01570-BB
self.assertNotIn('----', party['name'])
if not os.path.isfile(json_path):
bar = "*" * 50
print("\n\n%s\nJSON FILE DID NOT EXIST. CREATING IT AT:"
"\n\n %s\n\n"
"Please test the data in this file before assuming "
"everything worked.\n%s\n" % (bar, json_path, bar))
with open(json_path, 'w') as f:
json.dump(data, f, indent=2, sort_keys=True)
#self.assertFalse(True)
continue
with open(json_path) as f:
j = json.load(f)
if j != {}:
# Compare docket entries and parties first, for easier
# debugging, then compare whole objects to be sure.
self.assertEqual(j['docket_entries'],
data['docket_entries'])
self.assertEqual(j['parties'], data['parties'])
self.assertEqual(j, data)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=1)
sys.stdout.write("✓ - %0.1fs\n" % (t2 - t1))
def run_parsers_on_path(self, path_root,
required_fields=[
'date_filed', 'case_name', 'docket_number']):
"""Test all the parsers, faking the network query."""
paths = []
for root, dirnames, filenames in os.walk(path_root):
for filename in fnmatch.filter(filenames, '*.html'):
paths.append(os.path.join(root, filename))
paths.sort()
path_max_len = max(len(path) for path in paths) + 2
for i, path in enumerate(paths):
sys.stdout.write("%s. Doing %s" % (i, path.ljust(path_max_len)))
t1 = time.time()
dirname, filename = os.path.split(path)
filename_sans_ext = filename.split('.')[0]
json_path = os.path.join(dirname, '%s.json' % filename_sans_ext)
court = filename_sans_ext.split('_')[0]
report = DocketReport(court)
with open(path, 'r') as f:
report._parse_text(f.read().decode('utf-8'))
data = report.data
if data != {}:
# If the docket is a valid docket, make sure some required
# fields are populated.
for field in required_fields:
self.assertTrue(
data[field],
msg="Unable to find truthy value for field %s" % field,
)
self.assertEqual(data['court_id'], court)
# Party-specific tests...
for party in data['parties']:
self.assertTrue(
party.get('name', False),
msg="Every party must have a name attribute. Did not "
"get a value for:\n\n%s" % party
)
# Protect against effed up adversary proceedings cases that
# don't parse properly. See: cacb, 2:08-ap-01570-BB
self.assertNotIn('----', party['name'])
if not os.path.isfile(json_path):
bar = "*" * 50
print("\n\n%s\nJSON FILE DID NOT EXIST. CREATING IT AT:"
"\n\n %s\n\n"
"Please test the data in this file before assuming "
"everything worked.\n%s\n" % (bar, json_path, bar))
with open(json_path, 'w') as f:
json.dump(data, f, indent=2, sort_keys=True)
#self.assertFalse(True)
continue
with open(json_path) as f:
j = json.load(f)
if j != {}:
# Compare docket entries and parties first, for easier
# debugging, then compare whole objects to be sure.
self.assertEqual(j['docket_entries'], data['docket_entries'])
self.assertEqual(j['parties'], data['parties'])
self.assertEqual(j, data)
t2 = time.time()
duration = t2 - t1
warn_or_crash_slow_parser(duration, max_duration=1)
sys.stdout.write("✓ - %0.1fs\n" % (t2-t1))
def roundtrip(input):
fileobj = six.StringIO()
jsondate.dump(input, fileobj)
fileobj.seek(0)
return jsondate.load(fileobj)
import excel_dict
# import json
import pickle
import jsondate
# import jsonpickle
rows = excel_dict.read_sheet('Research Sessions.xlsx',
'Research Sessions',
start_row=5)
with open('data_workfile.bin', 'wb') as file:
pickle.dump(rows, file)
# with open('data_workfile.bin', 'rb') as file2:
# rows2 = pickle.load(file2)
# print(rows2)
with open('data_workfile.txt', 'w') as file3:
jsondate.dump(rows, file3)
def test_dump_datetime_roundtrips(self):
orig_dict = dict(created_at=datetime.date(2011, 1, 1))
fileobj = StringIO.StringIO()
jsondate.dump(orig_dict, fileobj)
fileobj.seek(0)
self.assertEqual(orig_dict, jsondate.load(fileobj))