changelog: add class to represent parsed changelog revisions
Currently, changelog entries are parsed into their respective
components at read time. Many operations are only interested
in a subset of fields of a changelog entry. The parsing and
storing of all the fields adds avoidable overhead.
This patch introduces the "changelogrevision" class. It takes
changelog raw text and exposes the parsed results as attributes.
The code for parsing changelog entries has been moved into its
construction function. changelog.read() has been modified to use
the new class internally while maintaining its existing API.
Future patches will make revision parsing lazy.
We implement the construction function of the new class with
__new__ instead of __init__ so we can use a named tuple to
represent the empty revision. This saves overhead and complexity
of coercing later versions of this class to represent an empty
instance.
While we are here, we add a method on changelog to obtain an
instance of the new type.
The overhead of constructing the new class regresses performance
of revsets accessing this data:
author(mpm)
0.896565
0.929984
desc(bug)
0.887169
0.935642 105%
date(2015)
0.878797
0.908094
extra(rebase_source)
0.865446
0.922624 106%
author(mpm) or author(greg)
1.801832
1.902112 105%
author(mpm) or desc(bug)
1.812438
1.860977
date(2015) or branch(default)
0.968276
1.005824
author(mpm) or desc(bug) or date(2015) or extra(rebase_source)
3.656193
3.743381
Once lazy parsing is implemented, these revsets will all be faster
than before. There is no performance change on revsets that do not
access this data. There /could/ be a performance regression on
operations that perform several changelog reads. However, I can't
think of anything outside of revsets and `hg log` (basically the
same as a revset) that would be impacted.
# peer.py - repository base classes for mercurial
#
# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
from .i18n import _
from . import (
error,
util,
)
# abstract batching support
class future(object):
'''placeholder for a value to be set later'''
def set(self, value):
if util.safehasattr(self, 'value'):
raise error.RepoError("future is already set")
self.value = value
class batcher(object):
'''base class for batches of commands submittable in a single request
All methods invoked on instances of this class are simply queued and
return a a future for the result. Once you call submit(), all the queued
calls are performed and the results set in their respective futures.
'''
def __init__(self):
self.calls = []
def __getattr__(self, name):
def call(*args, **opts):
resref = future()
self.calls.append((name, args, opts, resref,))
return resref
return call
def submit(self):
raise NotImplementedError()
class iterbatcher(batcher):
def submit(self):
raise NotImplementedError()
def results(self):
raise NotImplementedError()
class localbatch(batcher):
'''performs the queued calls directly'''
def __init__(self, local):
batcher.__init__(self)
self.local = local
def submit(self):
for name, args, opts, resref in self.calls:
resref.set(getattr(self.local, name)(*args, **opts))
class localiterbatcher(iterbatcher):
def __init__(self, local):
super(iterbatcher, self).__init__()
self.local = local
def submit(self):
# submit for a local iter batcher is a noop
pass
def results(self):
for name, args, opts, resref in self.calls:
yield getattr(self.local, name)(*args, **opts)
def batchable(f):
'''annotation for batchable methods
Such methods must implement a coroutine as follows:
@batchable
def sample(self, one, two=None):
# Handle locally computable results first:
if not one:
yield "a local result", None
# Build list of encoded arguments suitable for your wire protocol:
encargs = [('one', encode(one),), ('two', encode(two),)]
# Create future for injection of encoded result:
encresref = future()
# Return encoded arguments and future:
yield encargs, encresref
# Assuming the future to be filled with the result from the batched
# request now. Decode it:
yield decode(encresref.value)
The decorator returns a function which wraps this coroutine as a plain
method, but adds the original method as an attribute called "batchable",
which is used by remotebatch to split the call into separate encoding and
decoding phases.
'''
def plain(*args, **opts):
batchable = f(*args, **opts)
encargsorres, encresref = batchable.next()
if not encresref:
return encargsorres # a local result in this case
self = args[0]
encresref.set(self._submitone(f.func_name, encargsorres))
return batchable.next()
setattr(plain, 'batchable', f)
return plain
class peerrepository(object):
def batch(self):
return localbatch(self)
def iterbatch(self):
"""Batch requests but allow iterating over the results.
This is to allow interleaving responses with things like
progress updates for clients.
"""
return localiterbatcher(self)
def capable(self, name):
'''tell whether repo supports named capability.
return False if not supported.
if boolean capability, return True.
if string capability, return string.'''
caps = self._capabilities()
if name in caps:
return True
name_eq = name + '='
for cap in caps:
if cap.startswith(name_eq):
return cap[len(name_eq):]
return False
def requirecap(self, name, purpose):
'''raise an exception if the given capability is not present'''
if not self.capable(name):
raise error.CapabilityError(
_('cannot %s; remote repository does not '
'support the %r capability') % (purpose, name))
def local(self):
'''return peer as a localrepo, or None'''
return None
def peer(self):
return self
def canpush(self):
return True
def close(self):
pass