tests/printrevset.py

cborutil: change buffering strategy

Profiling revealed that we were spending a lot of time on the
line that was concatenating the old buffer with the incoming data
when attempting to decode long byte strings, such as manifest
revisions.

Essentially, we were feeding N chunks of size len(X) << len(Y) into
decode() and continuously allocating a new, larger buffer to hold
the undecoded input. This created substantial memory churn and
slowed down execution.

Changing the code to aggregate pending chunks in a list until we
have enough data to fully decode the next atom makes things much
more efficient.

I don't have exact data, but I recall the old code spending >1s
on manifest fulltexts from the mozilla-unified repo. The new code
doesn't significantly appear in profile output.

Differential Revision: https://phab.mercurial-scm.org/D4854

from __future__ import absolute_import
from mercurial import (
  cmdutil,
  commands,
  extensions,
  logcmdutil,
  revsetlang,
  smartset,
)

from mercurial.utils import (
  stringutil,
)

def logrevset(repo, pats, opts):
    revs = logcmdutil._initialrevs(repo, opts)
    if not revs:
        return None
    match, pats, slowpath = logcmdutil._makematcher(repo, revs, pats, opts)
    return logcmdutil._makerevset(repo, match, pats, slowpath, opts)

def uisetup(ui):
    def printrevset(orig, repo, pats, opts):
        revs, filematcher = orig(repo, pats, opts)
        if opts.get(b'print_revset'):
            expr = logrevset(repo, pats, opts)
            if expr:
                tree = revsetlang.parse(expr)
                tree = revsetlang.analyze(tree)
            else:
                tree = []
            ui = repo.ui
            ui.write(b'%s\n' % stringutil.pprint(opts.get(b'rev', [])))
            ui.write(revsetlang.prettyformat(tree) + b'\n')
            ui.write(stringutil.prettyrepr(revs) + b'\n')
            revs = smartset.baseset()  # display no revisions
        return revs, filematcher
    extensions.wrapfunction(logcmdutil, 'getrevs', printrevset)
    aliases, entry = cmdutil.findcmd(b'log', commands.table)
    entry[1].append((b'', b'print-revset', False,
                     b'print generated revset and exit (DEPRECATED)'))