Skip to content

Change python re dependency to google's re2 #143

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

Open
LDiazN wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Change python re dependency to google's re2 #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion oonipipeline/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,8 @@ dependencies = [
"opentelemetry-exporter-otlp-proto-grpc ~= 1.29.0",
"uvicorn ~= 0.25.0",
"pydantic-settings ~= 2.4.0",
"apache-airflow == 2.10.4"
"apache-airflow == 2.10.4",
"google-re2==1.1.20251105"
]

[project.optional-dependencies]
Expand Down
11 changes: 6 additions & 5 deletions oonipipeline/src/oonipipeline/fingerprintdb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import re
import re2
import csv

from pathlib import Path
Expand All @@ -24,8 +24,7 @@ class Fingerprint:
scope: Optional[str] = ""
notes: Optional[str] = ""
expected_countries: Optional[List[str]] = field(default_factory=list)

regexp: Optional[re.Pattern] = None
regexp: Optional[re2._Regexp] = None

def matches_pattern(self, s: str) -> bool:
if self.pattern_type == "full":
Expand All @@ -41,7 +40,7 @@ def matches_pattern(self, s: str) -> bool:
assert (
self.regexp is not None
), "regexp is not set for a regexp type pattern"
return self.regexp.search(s) != None
return self.regexp.search(s) is not None

raise Exception(
f"Found unknown fingerprint matching pattern {self.pattern_type}"
Expand Down Expand Up @@ -74,7 +73,9 @@ def _load_fingerprints(filepath: Path) -> Dict[str, Fingerprint]:
for row in csv_reader:
fp = Fingerprint(**row)
if fp.pattern_type == "regexp":
fp.regexp = re.compile(fp.pattern, re.DOTALL)
options = re2.Options()
options.dot_nl = True
fp.regexp = re2.compile(fp.pattern, options)
fingerprints[fp.name] = fp
return fingerprints

Expand Down