view tests/autodiff.py @ 50400:95acba2c29f6

encoding: avoid quadratic time complexity when json-encoding non-UTF8 strings

Apparently the code uses "+=" with a bytes object, which is linear-time, so the
whole encoding is quadratic-time. This patch makes us use a bytearray object,
instead, which has a(n amortized-)constant-time append operation.

The encoding is still not particularly fast, but at least a 10MB file
takes tens of seconds, not many hours to encode.

# Extension dedicated to test patch.diff() upgrade modes


from mercurial import (
    error,
    logcmdutil,
    patch,
    pycompat,
    registrar,
    scmutil,
)

cmdtable = {}
command = registrar.command(cmdtable)


@command(
    b'autodiff',
    [(b'', b'git', b'', b'git upgrade mode (yes/no/auto/warn/abort)')],
    b'[OPTION]... [FILE]...',
)
def autodiff(ui, repo, *pats, **opts):
    opts = pycompat.byteskwargs(opts)
    diffopts = patch.difffeatureopts(ui, opts)
    git = opts.get(b'git', b'no')
    brokenfiles = set()
    losedatafn = None
    if git in (b'yes', b'no'):
        diffopts.git = git == b'yes'
        diffopts.upgrade = False
    elif git == b'auto':
        diffopts.git = False
        diffopts.upgrade = True
    elif git == b'warn':
        diffopts.git = False
        diffopts.upgrade = True

        def losedatafn(fn=None, **kwargs):
            brokenfiles.add(fn)
            return True

    elif git == b'abort':
        diffopts.git = False
        diffopts.upgrade = True

        def losedatafn(fn=None, **kwargs):
            raise error.Abort(b'losing data for %s' % fn)

    else:
        raise error.Abort(b'--git must be yes, no or auto')

    ctx1, ctx2 = logcmdutil.revpair(repo, [])
    m = scmutil.match(ctx2, pats, opts)
    it = patch.diff(
        repo,
        ctx1.node(),
        ctx2.node(),
        match=m,
        opts=diffopts,
        losedatafn=losedatafn,
    )
    for chunk in it:
        ui.write(chunk)
    for fn in sorted(brokenfiles):
        ui.write((b'data lost for: %s\n' % fn))