Skip to content

feat: Add CVE extraction utility and standardize YAML handling in vulntotal #2242

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

Closed
ogubuikeAlex wants to merge 2 commits into from
Closed

feat: Add CVE extraction utility and standardize YAML handling in vulntotal #2242

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
670f183
refactor: replace yaml with saneyaml in vulntotal CLI
ogubuikeAlex Mar 28, 2026
f7df41d
Feat: Add functionality To extract deduplicated, normalized CVE ident…
ogubuikeAlex Mar 30, 2026
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
20 changes: 20 additions & 0 deletions vulnerabilities/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,26 @@
find_all_cve = cve_regex.findall
cwe_regex = r"CWE-\d+"


def extract_cve_ids(text):
"""
Extract deduplicated, normalized CVE identifiers from unstructured text.

Returns a sorted list of unique CVE IDs found in the text, normalized to
uppercase. Handles CVE IDs embedded in URLs, surrounded by punctuation,
or appearing multiple times.

>>> extract_cve_ids("Fixed CVE-2023-1234 and cve-2023-5678.")
['CVE-2023-1234', 'CVE-2023-5678']
>>> extract_cve_ids("See https://nvd.nist.gov/vuln/detail/CVE-2021-44228")
['CVE-2021-44228']
>>> extract_cve_ids("No vulnerabilities here.")
[]
"""
if not text:
return []
return sorted(set(cve.upper() for cve in find_all_cve(text)))

commit_regex = re.compile(r"\b[0-9a-f]{5,40}\b", re.IGNORECASE)
is_commit = commit_regex.fullmatch

Expand Down
7 changes: 3 additions & 4 deletions vulntotal/vulntotal_cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,7 @@

import click

# TODO: use saneyaml
import yaml
import saneyaml
from fetchcode import package_versions
from packageurl import PackageURL
from texttable import Texttable
Expand Down Expand Up @@ -313,7 +312,7 @@ def noop(self, *args, **kw):
pass


yaml.emitter.Emitter.process_tag = noop
saneyaml.emitter.Emitter.process_tag = noop


def write_yaml_output(purl, datasources, yaml_output, no_threading, no_group, no_compare):
Expand All @@ -327,7 +326,7 @@ def write_yaml_output(purl, datasources, yaml_output, no_threading, no_group, no
serialize_version_range(grouped_by_cve, no_compare)
results.update(grouped_by_cve)

return yaml.dump(results, yaml_output, default_flow_style=False, indent=2, sort_keys=False)
return saneyaml.dump(results, yaml_output, default_flow_style=False, indent=2, sort_keys=False)


def serialize_version_range(grouped_by_cve, no_compare):
Expand Down