Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support multiple regex matches #62

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Support multiple regex matches #62

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
abdef4c
tests: Modify regex test to expose too broad replacement
jplitza Jan 4, 2022
02ff47c
Support multiple regexp matches per line
jplitza Jan 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 30 additions & 17 deletions anonip.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,35 @@ def process_ip(self, ip):
)
return trunc_ip

def process_regex_match(self, match):
"""
This function processes a single regex match.

It returns the anonymized match as string and can be called with re.sub.

:param match: re.Match
:return: str
"""
ret = []
last_pos = 0

for i, g in enumerate(match.groups(), start=1):
if not g:
continue
ip_str, ip = self.extract_ip(g)
replacement = (
self.process_ip(ip) if ip
else self.replace or g
)
ret.extend((
match.group(0)[last_pos:match.start(i) - match.start(0)],
str(replacement),
))
last_pos = match.end(i) - match.start(0)

ret.append(match.group(0)[last_pos:])
return "".join(ret)

def process_line_regex(self, line):
"""
This function processes a single line based on the provided regex.
Expand All @@ -189,23 +218,7 @@ def process_line_regex(self, line):
:param line: str
:return: str
"""
match = re.match(self.regex, line)
if not match:
logger.debug("Regex did not match!")
return line
groups = match.groups()

for m in set(groups):
if not m:
continue
ip_str, ip = self.extract_ip(m)
if ip:
trunc_ip = self.process_ip(ip)
line = line.replace(ip_str, str(trunc_ip))
elif self.replace:
line = line.replace(m, self.replace)

return line
return re.sub(self.regex, self.process_regex_match, line)

def process_line_column(self, line):
"""
Expand Down
10 changes: 8 additions & 2 deletions tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,11 +133,17 @@ def test_column(line, columns, expected):
"line,regex,expected,replace",
[
(
'3.3.3.3 - - [20/May/2015:21:05:01 +0000] "GET / HTTP/1.1" 200 13358 "-" "useragent"',
'3.3.3.3 - - [20/May/2015:21:05:01 +0000] "GET /723.3.3.357 HTTP/1.1" 200 13358 "-" "useragent"',
re.compile(
r"(?:^([^,]+) - - |.* - somefixedstring: ([^,]+) - .* - ([^,]+))"
),
'3.3.0.0 - - [20/May/2015:21:05:01 +0000] "GET / HTTP/1.1" 200 13358 "-" "useragent"',
'3.3.0.0 - - [20/May/2015:21:05:01 +0000] "GET /723.3.3.357 HTTP/1.1" 200 13358 "-" "useragent"',
None,
),
(
'3.3.3.3 - - [20/May/2015:21:05:01 +0000] "GET /723.3.3.357 HTTP/1.1" 200 13358 "-" "useragent [ip:1.2.3.4]"',
re.compile(r"\b([0-9a-fA-F][0-9a-fA-F:\.]*|::[0-9a-fA-F:\.]+)\b"),
'3.3.0.0 - - [20/May/2015:21:05:01 +0000] "GET /723.3.3.357 HTTP/1.1" 200 13358 "-" "useragent [ip:1.2.0.0]"',
None,
),
(
Expand Down