view mercurial/diffhelper.py @ 43325:7d4f2e4899c5 stable

py3: fix headencode() with display=False

We previously called str() on a email.header.Header object. On Python 2,
this returns a bytestring and the __str__ method is actually an alias to
.encode() method. On Python 3, __str__ does not perform encoding (and
returns a unicode string). To keep a consistent behavior across Python
versions, we explicitly use .encode() and we wrap the result with
encoding.strtolocal() to get a bytestring in all cases. As a side effect
of forcing bytes conversion, we need to decode back in _addressencode().

This is to make test-notify.t pass on Python 3.

Also note that headers are now encoded in some patchbomb tests; this is
because the charset is not always "us-ascii" ("iso-8859-1" otherwise) on
Python 3.

# 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,
)


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 == b"\\ No newline at end of file\n":
                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