Example #1
0
def __main__():
    parser = argparse.ArgumentParser()

    parser.add_argument("query", type=str, help="S-exp query to execute")
    parser.add_argument("-v",
                        "--verbose",
                        help="Increase output verbosity",
                        action="store_true")
    parser.add_argument("--node-text",
                        help="Show the text content of the matched nodes",
                        action="store_true")
    args = parser.parse_args()

    if args.verbose:
        log.setLevel(log.DEBUG)
        log.debug("Verbose logging enabled.")

    parsed_s_query = sexp.parseString(args.query)

    log.debug(parsed_s_query)

    r = find_nodes_by_query(parsed_s_query)
    rl = []
    for n in r:
        log.info(f"{n} in {n.file.fetch()}")
        n_sexp = node_as_sexp(n, maxdepth=3, indent=2, show_start_coords=True)
        log.info(f"{n_sexp}")
        if args.node_text:
            log.info(f"{n.text.fetch()}")
        rl.append(n)

    log.info(f"{len(rl)} results returned")
def __main__():
    parser = argparse.ArgumentParser()

    parser.add_argument("--nworkers",
                        type=int,
                        help="number of workers",
                        default=os.cpu_count())
    parser.add_argument("--jobitems",
                        type=int,
                        help="items in a single job",
                        default=200)
    parser.add_argument("--njobs",
                        type=int,
                        help="number of total jobs to complete",
                        default=200)
    parser.add_argument("--itemtime",
                        type=float,
                        help="time taken per item in a job",
                        default=0.1)
    parser.add_argument("-v",
                        "--verbose",
                        help="Increase output verbosity",
                        action="store_true")
    args = parser.parse_args()

    if args.verbose:
        log.setLevel(log.DEBUG)
        log.debug("Verbose logging enabled.")

    with ProcessPool(max_workers=args.nworkers) as executor:
        multiprogress.main_proc_setup()
        multiprogress.start_server_thread()

        en_manager_proxy = multiprogress.get_manager_proxy()
        en_manager = multiprogress.get_manager()

        ret_futures = []
        # log.debug(f"counter_generator: {repr(counter_generator)}")
        log.info(f"Starting jobs...")
        for i in range(args.njobs):
            ret_futures.append(
                executor.schedule(
                    slow_worker,
                    (i, args.jobitems, args.itemtime, en_manager_proxy)))
        log.info(f"Waiting for jobs to complete...")
        cntr_all_jobs = en_manager.counter(desc="all jobs",
                                           total=args.njobs,
                                           color='blue')
        log.debug(f"cntr_all_jobs: {repr(cntr_all_jobs)}")
        for f in futures.as_completed(ret_futures):
            f.result()
            log.debug(f"finished a job!")
            cntr_all_jobs.update()
        log.info(f"All jobs completed!")
Example #3
0
def __main__():
    parser = argparse.ArgumentParser()

    parser.add_argument("--db",
                        "--database",
                        type=str,
                        help="Database connection string",
                        default=os.environ.get(
                            'WST_DB_URI', "http://*****:*****@localhost:8529/wst"))
    parser.add_argument("-v",
                        "--verbose",
                        help="Increase output verbosity",
                        action="store_true")
    parser.set_defaults(en_manager=enlighten.get_manager())
    subcmds = parser.add_subparsers(title="Collector commands")

    # analysis
    cmd_analyze = subcmds.add_parser('analyze',
                                     aliases=['add', 'a'],
                                     help="Analyze repositories")
    cmd_analyze.set_defaults(func=analyze)
    cmd_analyze.add_argument("repo_url",
                             type=str,
                             help="URI for cloning the repository")
    cmd_analyze.add_argument(
        "-w",
        "--workers",
        type=int,
        help=
        "Number of workers to use for processing files, default: os.cpu_count()",
        default=None)
    cmd_analyze.add_argument(
        "--skip-exists",
        "--skip-existing",
        action="store_true",
        help=
        "Skip the analysis if the repo document already exists in the database"
    )
    cmd_analyze.add_argument(
        "--interactive-debug",
        action="store_true",
        help="Start the interactive debugger after repo setup")
    cmd_analyze.add_argument(
        "--overwrite-incomplete",
        action="store_true",
        help="Overwrite existing but incomplete / unfinished data in the DB")
    cmd_analyze.add_argument(
        "-t",
        "--target-commit",
        type=str,
        help="Checkout and analyze a specific commit from the repo",
        default=None)
    # batch analysis
    cmd_batch = subcmds.add_parser(
        'batch',
        aliases=['addbatch', 'addmulti'],
        help="Analyze multiple repos from a JSON specification list")
    set_batch_analyze_args(cmd_batch)
    # delete data selectively
    cmd_delete = subcmds.add_parser('delete',
                                    aliases=['del'],
                                    help="Delete tree data selectively")
    cmd_delete.set_defaults(func=delete)
    cmd_delete.add_argument(
        "which_repo",
        type=str,
        help="URI or commit SHA for which repo's data to delete")
    # db setup
    cmd_db = subcmds.add_parser('db',
                                aliases=['database'],
                                help="Manage the database")
    subcmds_db = cmd_db.add_subparsers(title="Manage the database")
    cmd_db_init = subcmds_db.add_parser('initialize',
                                        aliases=['init', 'setup'],
                                        help="Set up the database")
    cmd_db_init.set_defaults(func=database_init)
    cmd_db_init.add_argument(
        "-d",
        "--delete",
        help="Delete any existing data in the database",
        action="store_true",
    )
    args = parser.parse_args()

    if args.verbose:
        log.setLevel(log.DEBUG)
        log.debug("Verbose logging enabled.")

    log.info(f"DB connection: {desensitize_url(args.db)}")

    if 'func' not in args:
        log.warn(f"Please supply a valid subcommand!")
        return

    try:
        args.func(args)
    except KeyboardInterrupt as e:
        log.warn(f"Stopping all child processes...")
        cur_proc = psutil.Process()
        children = cur_proc.children(recursive=True)
        for c in children:
            os.kill(c.pid, signal.SIGINT)
        psutil.wait_procs(children, timeout=5)
        children = cur_proc.children(recursive=True)
        for c in children:
            c.terminate()
        raise e
Example #4
0
    parser.add_argument("file_path", type=str, help="File to parse")
    parser.add_argument(
        "-v",
        "--verbose",
        action="store_true",
    )
    parser.add_argument("--db",
                        "--database",
                        type=str,
                        help="Database connection string",
                        default=os.environ.get(
                            'WST_DB_URI', "http://*****:*****@localhost:8529/wst"))

    args = parser.parse_args()
    if args.verbose:
        log.setLevel(log.DEBUG)

    client = ArangoClient(hosts=strip_url(args.db))
    p = urlparse(args.db)
    db = client.db(p.path[1:], username=p.username, password=p.password)

    lang = TreeSitterAutoBuiltLanguage(args.language)

    tree = lang.parse_file(args.file_path)

    cur = tree.walk()
    cur = TreeSitterCursorIterator(cur, nodefilter=lambda x: True)

    log.debug(cur)

    root = cur.peek()