Source code for swh.osv.identifiers

# Copyright (C) 2025-2026  The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU Affero General Public License version 3, or any later version
# See top-level LICENSE file for more information

from collections import Counter
import datetime
import sqlite3

import tqdm

CURRENT_YEAR = datetime.datetime.now().year




def main(conn: sqlite3.Connection) -> None:
    cur = conn.cursor()
    cur.execute("SELECT COUNT(*) FROM vulnerability_ids")
    ((row_count,),) = cur

    cve_in_nvd = set()
    cve_in_nonnvd = set()

    id_types: Counter[str] = Counter()

    cur.execute("SELECT id, vulnerability_filename FROM vulnerability_ids")
    for id_, filename in tqdm.tqdm(cur, total=row_count, desc="Reading"):
        id_type = id_.split("-")[0]
        if not id_type.isdigit():
            id_types[id_type] += 1
        if id_.startswith("CVE-"):
            if filename.startswith("CVE-"):
                cve_in_nvd.add(id_)
            else:
                cve_in_nonnvd.add(id_)

    print("* CVEs in NVD only:", len(cve_in_nvd - cve_in_nonnvd))
    print("* CVEs not in NVD:", len(cve_in_nonnvd - cve_in_nvd))
    print("* CVEs in both:", len(cve_in_nonnvd & cve_in_nvd))
    print()
    print("| Identifier database | Count |")
    print("| ------------------- | ----- |")
    for id_type, count in id_types.most_common():
        print(f"| {id_type} | {count} |")



if __name__ == "__main__":
    with sqlite3.connect("all.sqlite") as conn:
        main(conn)