view mercurial/diffhelper.py @ 51492:2e8a88e5809f

branchcache: stop writing more branchcache file on disk than needed Before this change, we were unconditionally writing a branchmap file for the filter level passed to `update_disk`. This is actually counter productive if no update were needed for this filter level. In many case, the branch cache for a filter level is identical to its parent "subset" and it is better to simply keep the subset update and reuse it every time instead of having to do identical work for similar subset. So we change the `update_disk` method to only write a file when that filter level differ from its parent. This removes many cases where identical files were written, requiring multiple boring update in the test suite. The only notable changes is the change to `test-strip-branch-cache.t`, this case was checking a scenario that no longer reproduce the bug as writing less branchmap file result in less stalled cache on disk. Strictly speaking, we could create a more convoluted scenario that create a similar issue. However the next changeset would also cover that scenario so we directly updated that test case to a "no longer buggy" state.
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Sun, 10 Mar 2024 04:53:17 +0100
parents d44e3c45f0e4
children f4733654f144
line wrap: on
line source

# 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