view contrib/simplemerge @ 52284:f4aede0f01af

rust-manifest: use `memchr` crate for all byte-finding needs

While writing a very dumb manifest diffing algorithm for a proof-of-concept
I saw that `Manifest::find_by_path` was much slower than I was expecting.

It turns out that the Rust stdlib uses slow (all is relative) code when
searching for byte positions for reasons ranging from portability, SIMD
API stability, nobody doing the work, etc. `memch` is much faster for these
purposes, so let's use it.

I was measuring ~670ms of profile time in `find_by_path`, after this patch
it went down to ~230ms.

#!/usr/bin/env python3

import getopt
import sys

import hgdemandimport

hgdemandimport.enable()

from mercurial.i18n import _
from mercurial import (
    context,
    error,
    fancyopts,
    simplemerge,
    ui as uimod,
    util,
)
from mercurial.utils import procutil, stringutil

options = [
    (b'L', b'label', [], _(b'labels to use on conflict markers')),
    (b'a', b'text', None, _(b'treat all files as text')),
    (b'p', b'print', None, _(b'print results instead of overwriting LOCAL')),
    (b'', b'no-minimal', None, _(b'no effect (DEPRECATED)')),
    (b'h', b'help', None, _(b'display help and exit')),
    (b'q', b'quiet', None, _(b'suppress output')),
]

usage = _(
    b'''simplemerge [OPTS] LOCAL BASE OTHER

    Simple three-way file merge utility with a minimal feature set.

    Apply to LOCAL the changes necessary to go from BASE to OTHER.

    By default, LOCAL is overwritten with the results of this operation.
'''
)


class ParseError(Exception):
    """Exception raised on errors in parsing the command line."""


def showhelp():
    procutil.stdout.write(usage)
    procutil.stdout.write(b'\noptions:\n')

    out_opts = []
    for shortopt, longopt, default, desc in options:
        out_opts.append(
            (
                b'%2s%s'
                % (
                    shortopt and b'-%s' % shortopt,
                    longopt and b' --%s' % longopt,
                ),
                b'%s' % desc,
            )
        )
    opts_len = max([len(opt[0]) for opt in out_opts])
    for first, second in out_opts:
        procutil.stdout.write(b' %-*s  %s\n' % (opts_len, first, second))


def _verifytext(input, ui, quiet=False, allow_binary=False):
    """verifies that text is non-binary (unless opts[text] is passed,
    then we just warn)"""
    if stringutil.binary(input.text()):
        msg = _(b"%s looks like a binary file.") % input.fctx.path()
        if not quiet:
            ui.warn(_(b'warning: %s\n') % msg)
        if not allow_binary:
            sys.exit(1)


try:
    for fp in (sys.stdin, procutil.stdout, sys.stderr):
        procutil.setbinary(fp)

    opts = {}
    try:
        bargv = [a.encode('utf8') for a in sys.argv[1:]]
        args = fancyopts.fancyopts(bargv, options, opts)
    except getopt.GetoptError as e:
        raise ParseError(e)
    if opts[b'help']:
        showhelp()
        sys.exit(0)
    if len(args) != 3:
        raise ParseError(_(b'wrong number of arguments').decode('utf8'))
    mode = b'merge'
    if len(opts[b'label']) > 2:
        mode = b'merge3'
    local, base, other = args
    overrides = opts[b'label']
    if len(overrides) > 3:
        raise error.InputError(b'can only specify three labels.')
    labels = [local, other, base]
    labels[: len(overrides)] = overrides
    local_input = simplemerge.MergeInput(
        context.arbitraryfilectx(local), labels[0]
    )
    other_input = simplemerge.MergeInput(
        context.arbitraryfilectx(other), labels[1]
    )
    base_input = simplemerge.MergeInput(
        context.arbitraryfilectx(base), labels[2]
    )

    quiet = opts.get(b'quiet')
    allow_binary = opts.get(b'text')
    ui = uimod.ui.load()
    _verifytext(local_input, ui, quiet=quiet, allow_binary=allow_binary)
    _verifytext(base_input, ui, quiet=quiet, allow_binary=allow_binary)
    _verifytext(other_input, ui, quiet=quiet, allow_binary=allow_binary)

    merged_text, conflicts = simplemerge.simplemerge(
        local_input,
        base_input,
        other_input,
        mode,
        allow_binary=allow_binary,
    )
    if opts.get(b'print'):
        ui.fout.write(merged_text)
    else:
        util.writefile(local, merged_text)
    sys.exit(1 if conflicts else 0)
except ParseError as e:
    e = stringutil.forcebytestr(e)
    procutil.stdout.write(b"%s: %s\n" % (sys.argv[0].encode('utf8'), e))
    showhelp()
    sys.exit(1)
except error.Abort as e:
    procutil.stderr.write(b"abort: %s\n" % e)
    sys.exit(255)
except KeyboardInterrupt:
    sys.exit(255)