contrib/catapipe.py

hgweb: do not audit URL path as working-directory path

Since hgweb is an interface to repository data, we don't need to prohibit
any paths conflicting within the filesystem. Still an access to working
files is audited by filectx.

#!/usr/bin/env python3
#
# Copyright 2018 Google LLC.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Tool read primitive events from a pipe to produce a catapult trace.

For now the event stream supports

  START $SESSIONID ...

and

  END $SESSIONID ...

events. Everything after the SESSIONID (which must not contain spaces)
is used as a label for the event. Events are timestamped as of when
they arrive in this process and are then used to produce catapult
traces that can be loaded in Chrome's about:tracing utility. It's
important that the event stream *into* this process stay simple,
because we have to emit it from the shell scripts produced by
run-tests.py.

Typically you'll want to place the path to the named pipe in the
HGCATAPULTSERVERPIPE environment variable, which both run-tests and hg
understand.
"""
from __future__ import absolute_import, print_function

import argparse
import datetime
import json
import os

_TYPEMAP = {
    'START': 'B',
    'END': 'E',
}

_threadmap = {}

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('pipe', type=str, nargs=1,
                        help='Path of named pipe to create and listen on.')
    parser.add_argument('output', default='trace.json', type=str, nargs='?',
                        help='Path of named pipe to create and listen on.')
    parser.add_argument('--debug', default=False, action='store_true',
                        help='Print useful debug messages')
    args = parser.parse_args()
    fn = args.pipe[0]
    os.mkfifo(fn)
    try:
        with open(fn) as f, open(args.output, 'w') as out:
            out.write('[\n')
            start = datetime.datetime.now()
            while True:
                ev = f.readline().strip()
                if not ev:
                    continue
                now = datetime.datetime.now()
                if args.debug:
                    print(ev)
                verb, session, label = ev.split(' ', 2)
                if session not in _threadmap:
                    _threadmap[session] = len(_threadmap)
                pid = _threadmap[session]
                ts_micros = (now - start).total_seconds() * 1000000
                out.write(json.dumps(
                    {
                        "name": label,
                        "cat": "misc",
                        "ph": _TYPEMAP[verb],
                        "ts": ts_micros,
                        "pid": pid,
                        "tid": 1,
                        "args": {}
                    }))
                out.write(',\n')
    finally:
        os.unlink(fn)

if __name__ == '__main__':
    main()