hgext/blackbox.py

dirstate: drop all logic around the "non-normal" sets

The dirstate has a lot of code to compute a set of all "non-normal" and
"from_other_parent" entries.

This is all used in one, unique, location, when `setparent` is called and moved
from a merge to a non merge. At that time, any "merge related" information has
to be dropped. This is mostly useful for command like `graft` or `shelve` that
move to a single-parent state -before- the commit. Otherwise the commit will
already have removed all traces of the merge information in the dirstate (e.g.
for a regular merges).

The bookkeeping for these sets is quite invasive. And it seems simpler to just
drop it and do the full computation in the single location where we actually
use it (since we have to do the computation at least once anyway).

This simplify the code a lot, and clarify why this kind of computation is
needed.

The possible drawback compared to the previous code are:
- if the operation happens in a loop, we will end up doing it multiple time,
- the C code to detect entry of interest have been dropped, for now. It will be
  re-introduced later, with a processing code directly in C for even faster
  operation.

Differential Revision: https://phab.mercurial-scm.org/D11507

# blackbox.py - log repository events to a file for post-mortem debugging
#
# Copyright 2010 Nicolas Dumazet
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

"""log repository events to a blackbox for debugging

Logs event information to .hg/blackbox.log to help debug and diagnose problems.
The events that get logged can be configured via the blackbox.track and
blackbox.ignore config keys.

Examples::

  [blackbox]
  track = *
  ignore = pythonhook
  # dirty is *EXPENSIVE* (slow);
  # each log entry indicates `+` if the repository is dirty, like :hg:`id`.
  dirty = True
  # record the source of log messages
  logsource = True

  [blackbox]
  track = command, commandfinish, commandexception, exthook, pythonhook

  [blackbox]
  track = incoming

  [blackbox]
  # limit the size of a log file
  maxsize = 1.5 MB
  # rotate up to N log files when the current one gets too big
  maxfiles = 3

  [blackbox]
  # Include nanoseconds in log entries with %f (see Python function
  # datetime.datetime.strftime)
  date-format = %Y-%m-%d @ %H:%M:%S.%f

"""

from __future__ import absolute_import

import re

from mercurial.i18n import _
from mercurial.node import hex

from mercurial import (
    encoding,
    loggingutil,
    registrar,
)
from mercurial.utils import (
    dateutil,
    procutil,
)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'

cmdtable = {}
command = registrar.command(cmdtable)

configtable = {}
configitem = registrar.configitem(configtable)

configitem(
    b'blackbox',
    b'dirty',
    default=False,
)
configitem(
    b'blackbox',
    b'maxsize',
    default=b'1 MB',
)
configitem(
    b'blackbox',
    b'logsource',
    default=False,
)
configitem(
    b'blackbox',
    b'maxfiles',
    default=7,
)
configitem(
    b'blackbox',
    b'track',
    default=lambda: [b'*'],
)
configitem(
    b'blackbox',
    b'ignore',
    default=lambda: [b'chgserver', b'cmdserver', b'extension'],
)
configitem(
    b'blackbox',
    b'date-format',
    default=b'%Y/%m/%d %H:%M:%S',
)

_lastlogger = loggingutil.proxylogger()


class blackboxlogger(object):
    def __init__(self, ui, repo):
        self._repo = repo
        self._trackedevents = set(ui.configlist(b'blackbox', b'track'))
        self._ignoredevents = set(ui.configlist(b'blackbox', b'ignore'))
        self._maxfiles = ui.configint(b'blackbox', b'maxfiles')
        self._maxsize = ui.configbytes(b'blackbox', b'maxsize')
        self._inlog = False

    def tracked(self, event):
        return (
            b'*' in self._trackedevents and event not in self._ignoredevents
        ) or event in self._trackedevents

    def log(self, ui, event, msg, opts):
        # self._log() -> ctx.dirty() may create new subrepo instance, which
        # ui is derived from baseui. So the recursion guard in ui.log()
        # doesn't work as it's local to the ui instance.
        if self._inlog:
            return
        self._inlog = True
        try:
            self._log(ui, event, msg, opts)
        finally:
            self._inlog = False

    def _log(self, ui, event, msg, opts):
        default = ui.configdate(b'devel', b'default-date')
        date = dateutil.datestr(default, ui.config(b'blackbox', b'date-format'))
        user = procutil.getuser()
        pid = b'%d' % procutil.getpid()
        changed = b''
        ctx = self._repo[None]
        parents = ctx.parents()
        rev = b'+'.join([hex(p.node()) for p in parents])
        if ui.configbool(b'blackbox', b'dirty') and ctx.dirty(
            missing=True, merge=False, branch=False
        ):
            changed = b'+'
        if ui.configbool(b'blackbox', b'logsource'):
            src = b' [%s]' % event
        else:
            src = b''
        try:
            fmt = b'%s %s @%s%s (%s)%s> %s'
            args = (date, user, rev, changed, pid, src, msg)
            with loggingutil.openlogfile(
                ui,
                self._repo.vfs,
                name=b'blackbox.log',
                maxfiles=self._maxfiles,
                maxsize=self._maxsize,
            ) as fp:
                fp.write(fmt % args)
        except (IOError, OSError) as err:
            # deactivate this to avoid failed logging again
            self._trackedevents.clear()
            ui.debug(
                b'warning: cannot write to blackbox.log: %s\n'
                % encoding.strtolocal(err.strerror)
            )
            return
        _lastlogger.logger = self


def uipopulate(ui):
    ui.setlogger(b'blackbox', _lastlogger)


def reposetup(ui, repo):
    # During 'hg pull' a httppeer repo is created to represent the remote repo.
    # It doesn't have a .hg directory to put a blackbox in, so we don't do
    # the blackbox setup for it.
    if not repo.local():
        return

    # Since blackbox.log is stored in the repo directory, the logger should be
    # instantiated per repository.
    logger = blackboxlogger(ui, repo)
    ui.setlogger(b'blackbox', logger)

    # Set _lastlogger even if ui.log is not called. This gives blackbox a
    # fallback place to log
    if _lastlogger.logger is None:
        _lastlogger.logger = logger

    repo._wlockfreeprefix.add(b'blackbox.log')


@command(
    b'blackbox',
    [
        (b'l', b'limit', 10, _(b'the number of events to show')),
    ],
    _(b'hg blackbox [OPTION]...'),
    helpcategory=command.CATEGORY_MAINTENANCE,
    helpbasic=True,
)
def blackbox(ui, repo, *revs, **opts):
    """view the recent repository events"""

    if not repo.vfs.exists(b'blackbox.log'):
        return

    limit = opts.get('limit')
    fp = repo.vfs(b'blackbox.log', b'r')
    lines = fp.read().split(b'\n')

    count = 0
    output = []
    for line in reversed(lines):
        if count >= limit:
            break

        # count the commands by matching lines like: 2013/01/23 19:13:36 root>
        if re.match(br'^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
            count += 1
        output.append(line)

    ui.status(b'\n'.join(reversed(output)))