Esempio n. 1
0
def test_do_not_add_policy_breaks_to_last_found(client):
    """
    GIVEN 2 policy breaks on different files with the same ignore sha
    WHEN add_found_policy_break is called
    THEN only one element should be added
    """
    policy_break = PolicyBreak("a", "gitignore",
                               [Match("apikey", "apikey", 0, 0, 0, 0)])
    cache = Cache()

    cache.add_found_policy_break(policy_break, "a")

    assert len(cache.last_found_secrets) == 0
Esempio n. 2
0
    def scan(
        self,
        client: GGClient,
        cache: Cache,
        matches_ignore: Iterable[str],
        all_policies: bool,
        verbose: bool,
    ) -> List[Result]:
        cache.purge()
        scannable_list = self.scannable_list
        results = []
        chunks = []
        for i in range(0, len(scannable_list), MULTI_DOCUMENT_LIMIT):
            chunks.append(scannable_list[i:i + MULTI_DOCUMENT_LIMIT])

        with concurrent.futures.ThreadPoolExecutor(
                max_workers=min(CPU_COUNT, 4),
                thread_name_prefix="content_scan") as executor:
            future_to_scan = {
                executor.submit(client.multi_content_scan, chunk): chunk
                for chunk in chunks
            }

            for future in concurrent.futures.as_completed(future_to_scan):
                chunk = future_to_scan[future]
                scan = future.result()
                if not scan.success:
                    handle_scan_error(scan, chunk)
                    continue
                for index, scanned in enumerate(scan.scan_results):
                    remove_ignored_from_result(scanned, all_policies,
                                               matches_ignore)
                    if scanned.has_policy_breaks:
                        for policy_break in scanned.policy_breaks:
                            cache.add_found_policy_break(
                                policy_break, chunk[index]["filename"])
                        results.append(
                            Result(
                                content=chunk[index]["document"],
                                scan=scanned,
                                filemode=chunk[index]["filemode"],
                                filename=chunk[index]["filename"],
                            ))
        cache.save()
        return results