view mercurial/lsprof.py @ 21933:8ecbe55fd09d stable

largefiles: invoke "normallookup" on "lfdirstate" for merged files

Before this patch, largefiles gotten from "other" revision (with
conflict) at "hg merge" become "clean" unexpectedly in steps below:

    1. "repo.status()" is invoked (for status check before merging)
      1-1 "dirstate" entry for standinfile SF is "normal"-ed
      1-2 "lfdirstate" entry of largefile LF (for SF) is "normal"-ed

    2. "merge.update()" is invoked
      2-1 SF is updated in the working directory
          (ASSUMPTION: user choice "other" at conflict)
      2-2 "dirstate" entry for SF is "merge"-ed

    3. "lfcommands.updatelfiles()" is invoked (by "overrides.hgmerge()")
      3-1 largefile LF (for SF) is updated in the working directory
      3-2 "dirstate" returns "m" for SF (by 2-2)
      3-3 "lfdirstate" entry for LF is left as it is
      3-4 "lfdirstate" is written into ".hg/largefiles/dirstate", and
          timestamp of LF is stored into "lfdirstate" file (by 1-2)
          (ASSUMPTION: timestamp of LF differs from one of "lfdirstate" file)

Then, "hs status" treats LF as "clean", even though LF is updated by
"other" revision (by 3-1), because "lfilesrepo.status()" always treats
"normal"-ed files (by 1-2 and 3-4) as "clean".

When state of standinfile in "dirstate" is "m", largefile should be
"normallookup"-ed.

This patch invokes "normallookup" on "lfdirstate" for merged files.

This patch uses "[debug] dirstate.delaywrite" feature in the test, to
ensure that timestamp of the largefile gotten from "other" revision is
stored into ".hg/largefiles/dirstate". (for ASSUMPTION at 3-4)

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()