comparison mercurial/copies.py @ 46109:2f357d053df2

copies: make calculating lazy for dir move detection's "addedfiles"

The information calculated here was only needed if (a) --debug was specified, or
(b) a directory move was plausibly detected. With tree manifests (especially in
my pathological repo and with our custom setup), pre-calculating the `u1` and
`u2` can be quite slow, and it's not even necessary in many cases. Let's delay
calculating it until we know it's actually necessary. This should have no
observable differences in output.

### Performance

I ran a rebase command in my pathological repo, rebasing two nodes across
several public phase commits, but where no directory copies exist in any of the
paths I'm tracking.

#### Before

```
  Time (mean ± σ):      3.711 s ±  0.061 s    [User: 0.3 ms, System: 1.5 ms]
  Range (min … max):    3.640 s …  3.827 s    10 runs
```

#### After

```
  Time (mean ± σ):     868.3 ms ±  10.1 ms    [User: 0.5 ms, System: 1.2 ms]
  Range (min … max):   856.6 ms … 883.6 ms    10 runs
```

Differential Revision: https://phab.mercurial-scm.org/D9567

46108:bdc2bf68f19e

            _checksinglesidecopies(
                src, dsts2, m2, m1, mb, c1, base, copy2, renamedelete2
            )

    # find interesting file sets from manifests
    addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
    addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
    u1 = sorted(addedinm1 - addedinm2)
    u2 = sorted(addedinm2 - addedinm1)

    header = b"  unmatched files in %s"
    if u1:
        repo.ui.debug(b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1)))
    if u2:
        repo.ui.debug(b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2)))

    if repo.ui.debugflag:
        renamedeleteset = set()
        divergeset = set()
        for dsts in diverge.values():
            divergeset.update(dsts)
        for dsts in renamedelete1.values():

        del renamedeleteset
        del divergeset

    repo.ui.debug(b"  checking for directory renames\n")

    dirmove1, movewithdir2 = _dir_renames(repo, c1, copy1, copies1, u2)
    dirmove2, movewithdir1 = _dir_renames(repo, c2, copy2, copies2, u1)

    branch_copies1 = branch_copies(copy1, renamedelete1, dirmove1, movewithdir1)
    branch_copies2 = branch_copies(copy2, renamedelete2, dirmove2, movewithdir2)

    return branch_copies1, branch_copies2, diverge


def _dir_renames(repo, ctx, copy, fullcopy, addedfiles):
    """Finds moved directories and files that should move with them.

    ctx: the context for one of the sides
    copy: files copied on the same side (as ctx)
    fullcopy: files copied on the same side (as ctx), including those that
              merge.manifestmerge() won't care about
    addedfiles: added files on the other side (compared to ctx)
    """
    # generate a directory move map
    invalid = set()
    dirmove = {}

            b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
        )

    movewithdir = {}
    # check unaccounted nonoverlapping files against directory moves
    for f in addedfiles:
        if f not in fullcopy:
            for d in dirmove:
                if f.startswith(d):
                    # new file added in a directory that was moved, move it
                    df = dirmove[d] + f[len(d) :]

46109:2f357d053df2

            _checksinglesidecopies(
                src, dsts2, m2, m1, mb, c1, base, copy2, renamedelete2
            )

    # find interesting file sets from manifests
    cache = []

    def _get_addedfiles(idx):
        if not cache:
            addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
            addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
            u1 = sorted(addedinm1 - addedinm2)
            u2 = sorted(addedinm2 - addedinm1)
            cache.extend((u1, u2))
        return cache[idx]

    u1fn = lambda: _get_addedfiles(0)
    u2fn = lambda: _get_addedfiles(1)
    if repo.ui.debugflag:
        u1 = u1fn()
        u2 = u2fn()

        header = b"  unmatched files in %s"
        if u1:
            repo.ui.debug(
                b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1))
            )
        if u2:
            repo.ui.debug(
                b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2))
            )

        renamedeleteset = set()
        divergeset = set()
        for dsts in diverge.values():
            divergeset.update(dsts)
        for dsts in renamedelete1.values():

        del renamedeleteset
        del divergeset

    repo.ui.debug(b"  checking for directory renames\n")

    dirmove1, movewithdir2 = _dir_renames(repo, c1, copy1, copies1, u2fn)
    dirmove2, movewithdir1 = _dir_renames(repo, c2, copy2, copies2, u1fn)

    branch_copies1 = branch_copies(copy1, renamedelete1, dirmove1, movewithdir1)
    branch_copies2 = branch_copies(copy2, renamedelete2, dirmove2, movewithdir2)

    return branch_copies1, branch_copies2, diverge


def _dir_renames(repo, ctx, copy, fullcopy, addedfilesfn):
    """Finds moved directories and files that should move with them.

    ctx: the context for one of the sides
    copy: files copied on the same side (as ctx)
    fullcopy: files copied on the same side (as ctx), including those that
              merge.manifestmerge() won't care about
    addedfilesfn: function returning added files on the other side (compared to
                  ctx)
    """
    # generate a directory move map
    invalid = set()
    dirmove = {}

            b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
        )

    movewithdir = {}
    # check unaccounted nonoverlapping files against directory moves
    for f in addedfilesfn():
        if f not in fullcopy:
            for d in dirmove:
                if f.startswith(d):
                    # new file added in a directory that was moved, move it
                    df = dirmove[d] + f[len(d) :]