mercurial/diffhelper.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 05 Apr 2024 11:05:54 +0200
changeset 51576 de5bf3fe0233
parent 49284 d44e3c45f0e4
child 51863 f4733654f144
permissions -rw-r--r--
revset: stop serializing node when using "%ln" Turning hundred of thousand of node from node to hex and back can be slow… what about we stop doing it? In many case were we are using node id we should be using revision id. However this is not a good reason to have a stupidly slow implementation of "%ln". This caught my attention again because the phase discovery during push make an extensive use of "%ln" or huge set. In absolute, that phase discovery probably should use "%ld" and need to improves its algorithmic complexity, but improving "%ln" seems simple and long overdue. This greatly speeds up `hg push` on repository with many drafts. Here are some relevant poulpe benchmarks: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 44.235070 after: 20.416329 (-53.85%, -23.82) ## benchmark.variants.revs = any-100-extra-rev before: 49.234697 after: 26.519829 (-46.14%, -22.71) ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 10.138396 after: 7.750458 (-23.55%, -2.39) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 1.263859 after: 0.700229 (-44.60%, -0.56) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 399.484481 after: 346.5089 (-13.26%, -52.98) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 4.540080 after: 3.401700 (-25.07%, -1.14) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 2.975765 after: 1.870798 (-37.13%, -1.10)

# diffhelper.py - helper routines for patch
#
# Copyright 2009 Olivia Mackall <olivia@selenic.com> and others
#
# 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 _

from . import (
    error,
)

MISSING_NEWLINE_MARKER = b'\\ No newline at end of file\n'


def addlines(fp, hunk, lena, lenb, a, b):
    """Read lines from fp into the hunk

    The hunk is parsed into two arrays, a and b. a gets the old state of
    the text, b gets the new state. The control char from the hunk is saved
    when inserting into a, but not b (for performance while deleting files.)
    """
    while True:
        todoa = lena - len(a)
        todob = lenb - len(b)
        num = max(todoa, todob)
        if num == 0:
            break
        for i in range(num):
            s = fp.readline()
            if not s:
                raise error.ParseError(_(b'incomplete hunk'))
            if s == MISSING_NEWLINE_MARKER:
                fixnewline(hunk, a, b)
                continue
            if s == b'\n' or s == b'\r\n':
                # Some patches may be missing the control char
                # on empty lines. Supply a leading space.
                s = b' ' + s
            hunk.append(s)
            if s.startswith(b'+'):
                b.append(s[1:])
            elif s.startswith(b'-'):
                a.append(s)
            else:
                b.append(s[1:])
                a.append(s)


def fixnewline(hunk, a, b):
    """Fix up the last lines of a and b when the patch has no newline at EOF"""
    l = hunk[-1]
    # tolerate CRLF in last line
    if l.endswith(b'\r\n'):
        hline = l[:-2]
    else:
        hline = l[:-1]

    if hline.startswith((b' ', b'+')):
        b[-1] = hline[1:]
    if hline.startswith((b' ', b'-')):
        a[-1] = hline
    hunk[-1] = hline


def testhunk(a, b, bstart):
    """Compare the lines in a with the lines in b

    a is assumed to have a control char at the start of each line, this char
    is ignored in the compare.
    """
    alen = len(a)
    blen = len(b)
    if alen > blen - bstart or bstart < 0:
        return False
    for i in range(alen):
        if a[i][1:] != b[i + bstart]:
            return False
    return True