comparison mercurial/mdiff.py @ 36414:44c4a38bf563

diff: do not split function name if character encoding is unknown

Only ASCII characters can be split reliably at any byte positions, so let's
just leave long multi-byte sequence long. It's probably less bad than putting
an invalid byte sequence into a diff.

This doesn't try to split the first ASCII slice from multi-byte sequence
because a combining character may follow.

36413:f493829b74dd

import struct
import zlib

from .i18n import _
from . import (
    error,
    policy,
    pycompat,
    util,
)

            # walk backwards from the start of the context up to the start of
            # the previous hunk context until we find a line starting with an
            # alphanumeric char.
            for i in xrange(astart - 1, lastpos - 1, -1):
                if l1[i][0:1].isalnum():
                    func = ' ' + l1[i].rstrip()[:40]
                    lastfunc[1] = func
                    break
            # by recording this hunk's starting point as the next place to
            # start looking for function lines, we avoid reading any line in
            # the file more than once.

36414:44c4a38bf563

import struct
import zlib

from .i18n import _
from . import (
    encoding,
    error,
    policy,
    pycompat,
    util,
)

            # walk backwards from the start of the context up to the start of
            # the previous hunk context until we find a line starting with an
            # alphanumeric char.
            for i in xrange(astart - 1, lastpos - 1, -1):
                if l1[i][0:1].isalnum():
                    func = b' ' + l1[i].rstrip()
                    # split long function name if ASCII. otherwise we have no
                    # idea where the multi-byte boundary is, so just leave it.
                    if encoding.isasciistr(func):
                        func = func[:41]
                    lastfunc[1] = func
                    break
            # by recording this hunk's starting point as the next place to
            # start looking for function lines, we avoid reading any line in
            # the file more than once.