mercurial/lsprof.py

match: add a subclass for dirstate normalizing of the matched patterns

This class is only needed on case insensitive filesystems, and only
for wdir context matches. It allows the user to not match the case of
the items in the filesystem- especially for naming directories, which
dirstate doesn't handle[1]. Making dirstate handle mismatched
directory cases is too expensive[2].

Since dirstate doesn't apply to committed csets, this is only created by
overriding basectx.match() in workingctx, and only on icasefs.  The default
arguments have been dropped, because the ctx must be passed to the matcher in
order to function.

For operations that can apply to both wdir and some other context, this ends up
normalizing the filename to the case as it exists in the filesystem, and using
that case for the lookup in the other context.  See the diff example in the
test.

Previously, given a directory with an inexact case:

  - add worked as expected

  - diff, forget and status would silently ignore the request

  - files would exit with 1

  - commit, revert and remove would fail (even when the commands leading up to
    them worked):

        $ hg ci -m "AbCDef" capsdir1/capsdir
        abort: CapsDir1/CapsDir: no match under directory!

        $ hg revert -r '.^' capsdir1/capsdir
        capsdir1\capsdir: no such file in rev 64dae27060b7

        $ hg remove capsdir1/capsdir
        not removing capsdir1\capsdir: no tracked files
        [1]

Globs are normalized, so that the -I and -X don't need to be specified with a
case match.  Without that, the second last remove (with -X) removes the files,
leaving nothing for the last remove.  However, specifying the files as
'glob:**.Txt' does not work.  Perhaps this requires 're.IGNORECASE'?

There are only a handful of places that create matchers directly, instead of
being routed through the context.match() method.  Some may benefit from changing
over to using ctx.match() as a factory function:

  revset.checkstatus()
  revset.contains()
  revset.filelog()
  revset._matchfiles()
  localrepository._loadfilter()
  ignore.ignore()
  fileset.subrepo()
  filemerge._picktool()
  overrides.addlargefiles()
  lfcommands.lfconvert()
  kwtemplate.__init__()
  eolfile.__init__()
  eolfile.checkrev()
  acl.buildmatch()

Currently, a toplevel subrepo can be named with an inexact case.  However, the
path auditor gets in the way of naming _anything_ in the subrepo if the top
level case doesn't match.  That is trickier to handle, because there's the user
provided case, the case in the filesystem, and the case stored in .hgsub.  This
can be fixed next cycle.

  --- a/tests/test-subrepo-deep-nested-change.t
  +++ b/tests/test-subrepo-deep-nested-change.t
  @@ -170,8 +170,15 @@
     R sub1/sub2/test.txt
     $ hg update -Cq
     $ touch sub1/sub2/folder/bar
  +#if icasefs
  +  $ hg addremove Sub1/sub2
  +  abort: path 'Sub1\sub2' is inside nested repo 'Sub1'
  +  [255]
  +  $ hg -q addremove sub1/sub2
  +#else
     $ hg addremove sub1/sub2
     adding sub1/sub2/folder/bar (glob)
  +#endif
     $ hg status -S
     A sub1/sub2/folder/bar
     ? foo/bar/abc

The narrowmatcher class may need to be tweaked when that is fixed.


[1] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068183.html
[2] http://www.selenic.com/pipermail/mercurial-devel/2015-April/068191.html

import sys
from _lsprof import Profiler, profiler_entry

__all__ = ['profile', 'Stats']

def profile(f, *args, **kwds):
    """XXX docstring"""
    p = Profiler()
    p.enable(subcalls=True, builtins=True)
    try:
        f(*args, **kwds)
    finally:
        p.disable()
    return Stats(p.getstats())


class Stats(object):
    """XXX docstring"""

    def __init__(self, data):
        self.data = data

    def sort(self, crit="inlinetime"):
        """XXX docstring"""
        if crit not in profiler_entry.__dict__:
            raise ValueError("Can't sort by %s" % crit)
        self.data.sort(key=lambda x: getattr(x, crit), reverse=True)
        for e in self.data:
            if e.calls:
                e.calls.sort(key=lambda x: getattr(x, crit), reverse=True)

    def pprint(self, top=None, file=None, limit=None, climit=None):
        """XXX docstring"""
        if file is None:
            file = sys.stdout
        d = self.data
        if top is not None:
            d = d[:top]
        cols = "% 12s %12s %11.4f %11.4f   %s\n"
        hcols = "% 12s %12s %12s %12s %s\n"
        file.write(hcols % ("CallCount", "Recursive", "Total(s)",
                            "Inline(s)", "module:lineno(function)"))
        count = 0
        for e in d:
            file.write(cols % (e.callcount, e.reccallcount, e.totaltime,
                               e.inlinetime, label(e.code)))
            count += 1
            if limit is not None and count == limit:
                return
            ccount = 0
            if climit and e.calls:
                for se in e.calls:
                    file.write(cols % (se.callcount, se.reccallcount,
                                       se.totaltime, se.inlinetime,
                                       "    %s" % label(se.code)))
                    count += 1
                    ccount += 1
                    if limit is not None and count == limit:
                        return
                    if climit is not None and ccount == climit:
                        break

    def freeze(self):
        """Replace all references to code objects with string
        descriptions; this makes it possible to pickle the instance."""

        # this code is probably rather ickier than it needs to be!
        for i in range(len(self.data)):
            e = self.data[i]
            if not isinstance(e.code, str):
                self.data[i] = type(e)((label(e.code),) + e[1:])
            if e.calls:
                for j in range(len(e.calls)):
                    se = e.calls[j]
                    if not isinstance(se.code, str):
                        e.calls[j] = type(se)((label(se.code),) + se[1:])

_fn2mod = {}

def label(code):
    if isinstance(code, str):
        return code
    try:
        mname = _fn2mod[code.co_filename]
    except KeyError:
        for k, v in list(sys.modules.iteritems()):
            if v is None:
                continue
            if not isinstance(getattr(v, '__file__', None), str):
                continue
            if v.__file__.startswith(code.co_filename):
                mname = _fn2mod[code.co_filename] = k
                break
        else:
            mname = _fn2mod[code.co_filename] = '<%s>' % code.co_filename

    return '%s:%d(%s)' % (mname, code.co_firstlineno, code.co_name)


if __name__ == '__main__':
    import os
    sys.argv = sys.argv[1:]
    if not sys.argv:
        print >> sys.stderr, "usage: lsprof.py <script> <arguments...>"
        sys.exit(2)
    sys.path.insert(0, os.path.abspath(os.path.dirname(sys.argv[0])))
    stats = profile(execfile, sys.argv[0], globals(), locals())
    stats.sort()
    stats.pprint()