Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
def join_action(namespace):
if namespace.large_cells:
csv.field_size_limit(sys.maxsize)
file1_headers, file1_position, file1_reader = custom_reader(
namespace.file1, namespace.column1)
file2_headers, file2_position, file2_reader = custom_reader(
namespace.file2, namespace.column2)
if namespace.select:
headers = namespace.select + file2_headers
else:
headers = file1_headers + file2_headers
writer = csv.writer(namespace.output)
writer.writerow(headers)
trie = LRUTrie()
for line in file1_reader:
url = line[file1_position]
if namespace.select:
try:
def join_action(namespace):
if namespace.large_cells:
csv.field_size_limit(sys.maxsize)
file1_headers, file1_position, file1_reader = custom_reader(
namespace.file1, namespace.column1)
file2_headers, file2_position, file2_reader = custom_reader(
namespace.file2, namespace.column2)
if namespace.select:
headers = namespace.select + file2_headers
else:
headers = file1_headers + file2_headers
writer = csv.writer(namespace.output)
writer.writerow(headers)
trie = LRUTrie()
for line in file1_reader:
url = line[file1_position]
if namespace.select:
try:
metadata = [line[file1_headers.index(
x)] for x in namespace.select]
def normalize_action(namespace):
sort_query = not namespace.no_query_sort
strip_authentication = not namespace.keep_authentication
strip_trailing_slash = namespace.strip_trailing_slash
strip_index = not namespace.keep_index
headers, position, reader = custom_reader(namespace.file, namespace.column)
headers.append(namespace.column + "_normalized")
writer = csv.writer(namespace.output)
writer.writerow(headers)
for line in reader:
url = line[position]
line.append(normalize_url(url, sort_query=sort_query, strip_authentication=strip_authentication,
strip_trailing_slash=strip_trailing_slash, strip_index=strip_index))
writer.writerow(line)