hgext/closehead.py

rhg: Don’t compare ambiguous files one byte at a time

Even though the use of `BufReader` reduces the number of syscalls to read
the file from disk, `.bytes()` yields a separate `Result` for every byte.
Creating those results and dispatching on them is most likely costly.

Instead, this commit opts for simplicity by reading the entire file into memory
and comparing a single pair of byte strings. Note that memory already needs to
contain the entire previous contents of the file, as read from the filelog.
So with an extremely large file this doubles memory use but does not make it
grow by orders of magnitude.

At first I wrote code that still avoids reading the entire file into memory
and compares one buffer at a time with `BufReader`. Find this code below for
posterity. However its correctness is subtle. I ended up preferring the
simplicity of the obviously-correct single comparison.

```rust
let mut reader = BufReader::new(fobj);
let mut expected = &contents_in_p1[..];
loop {
    let buf = reader.fill_buf().when_reading_file(&fs_path)?;
    if buf.is_empty() {
        // Found EOF
        return Ok(expected.is_empty());
    } else if let Some(rest) = expected.drop_prefix(buf) {
        // What we read so far matches the expected content, continue reading
        let buf_len = buf.len();
        reader.consume(buf_len);
        expected = rest
    } else {
        // Found different content
        return Ok(false);
    }
}
```

Differential Revision: https://phab.mercurial-scm.org/D11412

# closehead.py - Close arbitrary heads without checking them out first
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''close arbitrary heads without checking them out first'''

from __future__ import absolute_import

from mercurial.i18n import _
from mercurial import (
    bookmarks,
    cmdutil,
    context,
    error,
    pycompat,
    registrar,
    scmutil,
)

cmdtable = {}
command = registrar.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = b'ships-with-hg-core'

commitopts = cmdutil.commitopts
commitopts2 = cmdutil.commitopts2
commitopts3 = [(b'r', b'rev', [], _(b'revision to check'), _(b'REV'))]


@command(
    b'close-head|close-heads',
    commitopts + commitopts2 + commitopts3,
    _(b'[OPTION]... [REV]...'),
    helpcategory=command.CATEGORY_CHANGE_MANAGEMENT,
    inferrepo=True,
)
def close_branch(ui, repo, *revs, **opts):
    """close the given head revisions

    This is equivalent to checking out each revision in a clean tree and running
    ``hg commit --close-branch``, except that it doesn't change the working
    directory.

    The commit message must be specified with -l or -m.
    """

    def docommit(rev):
        cctx = context.memctx(
            repo,
            parents=[rev, None],
            text=message,
            files=[],
            filectxfn=None,
            user=opts.get(b'user'),
            date=opts.get(b'date'),
            extra=extra,
        )
        tr = repo.transaction(b'commit')
        ret = repo.commitctx(cctx, True)
        bookmarks.update(repo, [rev, None], ret)
        cctx.markcommitted(ret)
        tr.close()

    opts = pycompat.byteskwargs(opts)

    revs += tuple(opts.get(b'rev', []))
    revs = scmutil.revrange(repo, revs)

    if not revs:
        raise error.Abort(_(b'no revisions specified'))

    heads = []
    for branch in repo.branchmap():
        heads.extend(repo.branchheads(branch))
    heads = {repo[h].rev() for h in heads}
    for rev in revs:
        if rev not in heads:
            raise error.Abort(_(b'revision is not an open head: %d') % rev)

    message = cmdutil.logmessage(ui, opts)
    if not message:
        raise error.Abort(_(b"no commit message specified with -l or -m"))
    extra = {b'close': b'1'}

    with repo.wlock(), repo.lock():
        for rev in revs:
            r = repo[rev]
            branch = r.branch()
            extra[b'branch'] = branch
            docommit(r)
    return 0