mirror of
https://github.com/ansible-collections/community.general.git
synced 2024-09-14 20:13:21 +02:00
Fix exponential regex performance issue
filter_leading_non_json_lines effectively does re.match(".*\w+=\w+.*", line) for every line of output. This has abysmal performance in case of large Base64-encoded data (which ultimately does not match the regex but does match the .*\w+= part) as returned e.g. by the template module (diffs). Replacing the match with re.search("\w=\w", line) drops the complexity back to linear, and actually usable with large diffs from the template module (a 150 KB Base64 diff kept Ansible spinning at 100% cpu for minutes). Also, check the easy cases (line.startswith) first while we're here. Closes: #8932
This commit is contained in:
parent
c93b89fa63
commit
7f33580eba
1 changed files with 2 additions and 2 deletions
|
@ -1041,11 +1041,11 @@ def filter_leading_non_json_lines(buf):
|
|||
filter only leading lines since multiline JSON is valid.
|
||||
'''
|
||||
|
||||
kv_regex = re.compile(r'.*\w+=\w+.*')
|
||||
kv_regex = re.compile(r'\w=\w')
|
||||
filtered_lines = StringIO.StringIO()
|
||||
stop_filtering = False
|
||||
for line in buf.splitlines():
|
||||
if stop_filtering or kv_regex.match(line) or line.startswith('{') or line.startswith('['):
|
||||
if stop_filtering or line.startswith('{') or line.startswith('[') or kv_regex.search(line):
|
||||
stop_filtering = True
|
||||
filtered_lines.write(line + '\n')
|
||||
return filtered_lines.getvalue()
|
||||
|
|
Loading…
Reference in a new issue