view mercurial/hook.py @ 21809:e250b8300e6e

parsers: inline fields of dirstate values in C version

Previously, while unpacking the dirstate we'd create 3-4 new CPython objects
for most dirstate values:

- the state is a single character string, which is pooled by CPython
- the mode is a new object if it isn't 0 due to being in the lookup set
- the size is a new object if it is greater than 255
- the mtime is a new object if it isn't -1 due to being in the lookup set
- the tuple to contain them all

In some cases such as regular hg status, we actually look at all the objects.
In other cases like hg add, hg status for a subdirectory, or hg status with the
third-party hgwatchman enabled, we look at almost none of the objects.

This patch eliminates most object creation in these cases by defining a custom
C struct that is exposed to Python with an interface similar to a tuple. Only
when tuple elements are actually requested are the respective objects created.

The gains, where they're expected, are significant. The following tests are run
against a working copy with over 270,000 files.

parse_dirstate becomes significantly faster:

$ hg perfdirstate
before: wall 0.186437 comb 0.180000 user 0.160000 sys 0.020000 (best of 35)
after:  wall 0.093158 comb 0.100000 user 0.090000 sys 0.010000 (best of 95)

and as a result, several commands benefit:

$ time hg status  # with hgwatchman enabled
before: 0.42s user 0.14s system 99% cpu 0.563 total
after:  0.34s user 0.12s system 99% cpu 0.471 total

$ time hg add new-file
before: 0.85s user 0.18s system 99% cpu 1.033 total
after:  0.76s user 0.17s system 99% cpu 0.931 total

There is a slight regression in regular status performance, but this is fixed
in an upcoming patch.

# hook.py - hook support for mercurial
#
# Copyright 2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from i18n import _
import os, sys, time
import extensions, util, demandimport

def _pythonhook(ui, repo, name, hname, funcname, args, throw):
    '''call python hook. hook is callable object, looked up as
    name in python module. if callable returns "true", hook
    fails, else passes. if hook raises exception, treated as
    hook failure. exception propagates if throw is "true".

    reason for "true" meaning "hook failed" is so that
    unmodified commands (e.g. mercurial.commands.update) can
    be run as hooks without wrappers to convert return values.'''

    if callable(funcname):
        obj = funcname
        funcname = obj.__module__ + "." + obj.__name__
    else:
        d = funcname.rfind('.')
        if d == -1:
            raise util.Abort(_('%s hook is invalid ("%s" not in '
                               'a module)') % (hname, funcname))
        modname = funcname[:d]
        oldpaths = sys.path
        if util.mainfrozen():
            # binary installs require sys.path manipulation
            modpath, modfile = os.path.split(modname)
            if modpath and modfile:
                sys.path = sys.path[:] + [modpath]
                modname = modfile
        demandimportenabled = demandimport.isenabled()
        if demandimportenabled:
            demandimport.disable()
        try:
            try:
                obj = __import__(modname)
            except ImportError:
                e1 = sys.exc_type, sys.exc_value, sys.exc_traceback
                try:
                    # extensions are loaded with hgext_ prefix
                    obj = __import__("hgext_%s" % modname)
                except ImportError:
                    e2 = sys.exc_type, sys.exc_value, sys.exc_traceback
                    if ui.tracebackflag:
                        ui.warn(_('exception from first failed import '
                                  'attempt:\n'))
                    ui.traceback(e1)
                    if ui.tracebackflag:
                        ui.warn(_('exception from second failed import '
                                  'attempt:\n'))
                    ui.traceback(e2)
                    raise util.Abort(_('%s hook is invalid '
                                       '(import of "%s" failed)') %
                                     (hname, modname))
        finally:
            if demandimportenabled:
                demandimport.enable()
        sys.path = oldpaths
        try:
            for p in funcname.split('.')[1:]:
                obj = getattr(obj, p)
        except AttributeError:
            raise util.Abort(_('%s hook is invalid '
                               '("%s" is not defined)') %
                             (hname, funcname))
        if not callable(obj):
            raise util.Abort(_('%s hook is invalid '
                               '("%s" is not callable)') %
                             (hname, funcname))

    ui.note(_("calling hook %s: %s\n") % (hname, funcname))
    starttime = time.time()

    try:
        try:
            # redirect IO descriptors to the ui descriptors so hooks
            # that write directly to these don't mess up the command
            # protocol when running through the command server
            old = sys.stdout, sys.stderr, sys.stdin
            sys.stdout, sys.stderr, sys.stdin = ui.fout, ui.ferr, ui.fin

            r = obj(ui=ui, repo=repo, hooktype=name, **args)
        except KeyboardInterrupt:
            raise
        except Exception, exc:
            if isinstance(exc, util.Abort):
                ui.warn(_('error: %s hook failed: %s\n') %
                             (hname, exc.args[0]))
            else:
                ui.warn(_('error: %s hook raised an exception: '
                               '%s\n') % (hname, exc))
            if throw:
                raise
            ui.traceback()
            return True
    finally:
        sys.stdout, sys.stderr, sys.stdin = old
        duration = time.time() - starttime
        ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n',
               name, funcname, duration)
    if r:
        if throw:
            raise util.Abort(_('%s hook failed') % hname)
        ui.warn(_('warning: %s hook failed\n') % hname)
    return r

def _exthook(ui, repo, name, cmd, args, throw):
    ui.note(_("running hook %s: %s\n") % (name, cmd))

    starttime = time.time()
    env = {}
    for k, v in args.iteritems():
        if callable(v):
            v = v()
        if isinstance(v, dict):
            # make the dictionary element order stable across Python
            # implementations
            v = ('{' +
                 ', '.join('%r: %r' % i for i in sorted(v.iteritems())) +
                 '}')
        env['HG_' + k.upper()] = v

    if repo:
        cwd = repo.root
    else:
        cwd = os.getcwd()
    if 'HG_URL' in env and env['HG_URL'].startswith('remote:http'):
        r = util.system(cmd, environ=env, cwd=cwd, out=ui)
    else:
        r = util.system(cmd, environ=env, cwd=cwd, out=ui.fout)

    duration = time.time() - starttime
    ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n',
           name, cmd, duration)
    if r:
        desc, r = util.explainexit(r)
        if throw:
            raise util.Abort(_('%s hook %s') % (name, desc))
        ui.warn(_('warning: %s hook %s\n') % (name, desc))
    return r

def _allhooks(ui):
    hooks = []
    for name, cmd in ui.configitems('hooks'):
        if not name.startswith('priority'):
            priority = ui.configint('hooks', 'priority.%s' % name, 0)
            hooks.append((-priority, len(hooks), name, cmd))
    return [(k, v) for p, o, k, v in sorted(hooks)]

_redirect = False
def redirect(state):
    global _redirect
    _redirect = state

def hook(ui, repo, name, throw=False, **args):
    if not ui.callhooks:
        return False

    r = False
    oldstdout = -1

    try:
        for hname, cmd in _allhooks(ui):
            if hname.split('.')[0] != name or not cmd:
                continue

            if oldstdout == -1 and _redirect:
                try:
                    stdoutno = sys.__stdout__.fileno()
                    stderrno = sys.__stderr__.fileno()
                    # temporarily redirect stdout to stderr, if possible
                    if stdoutno >= 0 and stderrno >= 0:
                        sys.__stdout__.flush()
                        oldstdout = os.dup(stdoutno)
                        os.dup2(stderrno, stdoutno)
                except (OSError, AttributeError):
                    # files seem to be bogus, give up on redirecting (WSGI, etc)
                    pass

            if callable(cmd):
                r = _pythonhook(ui, repo, name, hname, cmd, args, throw) or r
            elif cmd.startswith('python:'):
                if cmd.count(':') >= 2:
                    path, cmd = cmd[7:].rsplit(':', 1)
                    path = util.expandpath(path)
                    if repo:
                        path = os.path.join(repo.root, path)
                    try:
                        mod = extensions.loadpath(path, 'hghook.%s' % hname)
                    except Exception:
                        ui.write(_("loading %s hook failed:\n") % hname)
                        raise
                    hookfn = getattr(mod, cmd)
                else:
                    hookfn = cmd[7:].strip()
                r = _pythonhook(ui, repo, name, hname, hookfn, args, throw) or r
            else:
                r = _exthook(ui, repo, hname, cmd, args, throw) or r
    finally:
        if _redirect and oldstdout >= 0:
            os.dup2(oldstdout, stdoutno)
            os.close(oldstdout)

    return r