view tests/autodiff.py @ 48671:f1ed5c304f45

encoding: fix trim() to be O(n) instead of O(n^2)

`encoding.trim()` iterated over the possible lengths smaller than the
input and created a slice for each. It then calculated the column
width of the result, which is of course O(n), so the overall algorithm
was O(n). This patch rewrites it to iterate over the unicode
characters, keeping track of the length so far. Also, the old
algorithm started from the end of the string, which made it much worse
when the input is large and the limit is small (such as the typical 72
we pass to it).

You can time it by running something like this:

```
time python3 -c 'from mercurial.utils import stringutil; print(stringutil.ellipsis(b"0123456789" * 1000, 5))'
```

That drops from 4.05 s to 83 ms with this patch (and most of that is
of course startup time).

Differential Revision: https://phab.mercurial-scm.org/D12089

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

from __future__ import absolute_import

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))