view mercurial/lsprof.py @ 35616:706aa203b396

fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

from __future__ import absolute_import, print_function

import _lsprof
import sys

Profiler = _lsprof.Profiler

# PyPy doesn't expose profiler_entry from the module.
profiler_entry = getattr(_lsprof, 'profiler_entry', None)

__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"""
        # profiler_entries isn't defined when running under PyPy.
        if profiler_entry:
            if crit not in profiler_entry.__dict__:
                raise ValueError("Can't sort by %s" % crit)
        elif self.data and not getattr(self.data[0], crit, None):
            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("usage: lsprof.py <script> <arguments...>", file=sys.stderr)
        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()