view mercurial/lsprof.py @ 23845:0a7fd54d4e60

revset: introduce "_parsealiasdecl" to parse alias declarations strictly

This patch introduces "_parsealiasdecl" to parse alias declarations
strictly. For example, "_parsealiasdecl" can detect problems below,
which current implementation can't.

  - un-closed parenthesis causes being treated as "alias symbol"

    because all of declarations not in "func(....)" style are
    recognized as "alias symbol".

    for example, "foo($1, $2" is treated as the alias symbol.

  - alias symbol/function names aren't examined whether they are valid
    as symbol or not

    for example, "foo bar" can be treated as the alias symbol, but of
    course such invalid symbol can't be referred in revset.

  - just splitting argument list by "," causes overlooking syntax
    problems in the declaration

    for example, all of invalid declarations below are overlooked:

    - foo("bar")     => taking one argument named as '"bar"'
    - foo("unclosed) => taking one argument named as '"unclosed'
    - foo(bar::baz)  => taking one argument named as 'bar::baz'
    - foo(bar($1))   => taking one argument named as 'bar($1)'

To decrease complication of patch, current implementation for alias
declarations is replaced by "_parsealiasdecl" in the subsequent
patch. This patch just introduces it.

This patch defines "_parsealiasdecl" not as a method of "revsetalias"
class but as a one of "revset" module, because of ease of testing by
doctest.

This patch factors some helper functions for "tree" out, because:

  - direct accessing like "if tree[0] == 'func' and len(tree) > 1"
    decreases readability

  - subsequent patch (and also existing code paths, in the future) can
    use them for readability

This patch also factors "_tokenizealias" out, because it can be used
also for parsing alias definitions strictly.

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()