view mercurial/diffutil.py @ 42237:9f45d3d526f9

hgtagsfnodescache: inherit fnode from parent when possible

If a changeset does not update the content of `.hgtags`, it means it will use
the same file-node (for `.hgtags`) as its parents. In this case we can
directly reuse the parent's file-node.

We use this property when updating the `hgtagsfnodescache` taking a faster path
if we already have a cached value for the parents of the node we are looking
at.

Doing so provides a large performance boost when looking at a lot of fnodes,
especially on repository with very large manifest:

timing for `tagsmod.fnoderevs(ui, repo, repo.changelog.revs())`

mercurial: (41907 revisions, 1923 files)

    before: 6.9 seconds
    after:  2.7 seconds (-54%)

pypy: (96266 revisions, 5198 files)

    before: 80 seconds
    after:  20 seconds (-75%)

mozilla-central: (463411 revisions, 272080 files)

    before: 7166.4 seconds
    after:    47.8 seconds (-99%, x150 speedup)

On a copy of mozilla-try with about 35K heads ans 1.7M changesets, this moves
the computation from many hours to a couple of minutes, making it more
interesting to do a full warm up of this cache before computing tags (from a
cold cache).

There seems to be other performance low hanging fruits, like avoiding the use of
changectx or a more revision centric logic. However, the new code is fast enough
for my needs right now.

# diffutil.py - utility functions related to diff and patch
#
# Copyright 2006 Brendan Cully <[e-mail]>
# Copyright 2007 Chris Mason <[e-mail]>
# Copyright 2018 Octobus <[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 __future__ import absolute_import

from .i18n import _

from . import (
    mdiff,
    pycompat,
)

def diffallopts(ui, opts=None, untrusted=False, section='diff',
                configprefix=''):
    '''return diffopts with all features supported and parsed'''
    return difffeatureopts(ui, opts=opts, untrusted=untrusted, section=section,
                           git=True, whitespace=True, formatchanging=True,
                           configprefix=configprefix)

def difffeatureopts(ui, opts=None, untrusted=False, section='diff', git=False,
                    whitespace=False, formatchanging=False, configprefix=''):
    '''return diffopts with only opted-in features parsed

    Features:
    - git: git-style diffs
    - whitespace: whitespace options like ignoreblanklines and ignorews
    - formatchanging: options that will likely break or cause correctness issues
      with most diff parsers
    '''
    def get(key, name=None, getter=ui.configbool, forceplain=None):
        if opts:
            v = opts.get(key)
            # diffopts flags are either None-default (which is passed
            # through unchanged, so we can identify unset values), or
            # some other falsey default (eg --unified, which defaults
            # to an empty string). We only want to override the config
            # entries from hgrc with command line values if they
            # appear to have been set, which is any truthy value,
            # True, or False.
            if v or isinstance(v, bool):
                return v
        if forceplain is not None and ui.plain():
            return forceplain
        return getter(section, configprefix + (name or key),
                      untrusted=untrusted)

    # core options, expected to be understood by every diff parser
    buildopts = {
        'nodates': get('nodates'),
        'showfunc': get('show_function', 'showfunc'),
        'context': get('unified', getter=ui.config),
    }
    buildopts['xdiff'] = ui.configbool('experimental', 'xdiff')

    if git:
        buildopts['git'] = get('git')

        # since this is in the experimental section, we need to call
        # ui.configbool directory
        buildopts['showsimilarity'] = ui.configbool('experimental',
                                                    'extendedheader.similarity')

        # need to inspect the ui object instead of using get() since we want to
        # test for an int
        hconf = ui.config('experimental', 'extendedheader.index')
        if hconf is not None:
            hlen = None
            try:
                # the hash config could be an integer (for length of hash) or a
                # word (e.g. short, full, none)
                hlen = int(hconf)
                if hlen < 0 or hlen > 40:
                    msg = _("invalid length for extendedheader.index: '%d'\n")
                    ui.warn(msg % hlen)
            except ValueError:
                # default value
                if hconf == 'short' or hconf == '':
                    hlen = 12
                elif hconf == 'full':
                    hlen = 40
                elif hconf != 'none':
                    msg = _("invalid value for extendedheader.index: '%s'\n")
                    ui.warn(msg % hconf)
            finally:
                buildopts['index'] = hlen

    if whitespace:
        buildopts['ignorews'] = get('ignore_all_space', 'ignorews')
        buildopts['ignorewsamount'] = get('ignore_space_change',
                                          'ignorewsamount')
        buildopts['ignoreblanklines'] = get('ignore_blank_lines',
                                            'ignoreblanklines')
        buildopts['ignorewseol'] = get('ignore_space_at_eol', 'ignorewseol')
    if formatchanging:
        buildopts['text'] = opts and opts.get('text')
        binary = None if opts is None else opts.get('binary')
        buildopts['nobinary'] = (not binary if binary is not None
                                 else get('nobinary', forceplain=False))
        buildopts['noprefix'] = get('noprefix', forceplain=False)
        buildopts['worddiff'] = get('word_diff', 'word-diff', forceplain=False)

    return mdiff.diffopts(**pycompat.strkwargs(buildopts))