mercurial/diffhelper.py

copies: choose target directory based on longest match

If one side of a merge renames `dir1/` to `dir2/` and the subdirectory
`dir1/subdir1/` to `dir2/subdir2/`, and the other side of the merge
adds a file in `dir1/subdir1/`, we should clearly move that into
`dir2/subdir2/`. We already detect the directories correctly before
this patch, but we iterate over them in arbitrary order. That results
in the new file sometimes ending up in `dir2/subdir1/` instead. This
patch fixes it by iterating over the source directories by visiting
subdirectories first. That's achieved by simply iterating over them in
reverse lexicographical order.

Without the fix, the test case still passes on Python 2 but fails on
Python 3. It depends on the iteration order of the dict. I did not
look into how it's built up and why it behaved differently before the
fix. I could probably have gotten it to fail on Python 2 as well by
choosing different directory names.

Differential Revision: https://phab.mercurial-scm.org/D10115

# diffhelper.py - helper routines for patch
#
# Copyright 2009 Matt Mackall <[e-mail]> 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 __future__ import absolute_import

from .i18n import _

from . import (
    error,
    pycompat,
)

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 pycompat.xrange(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 pycompat.xrange(alen):
        if a[i][1:] != b[i + bstart]:
            return False
    return True