mercurial/lsprof.py

diffstat: fix parsing of filenames with spaces

The patch changes the output of "hg diff --stat" when one file whose filename
has spaces has changed, making it get the full filename instead of just the
substring between the last space and the end of the filename.

It also changes the diffstat generated by "hg email -d" when one of the commit
messages starts with "diff". Because of the regex used to parse the filename,
the diffstat generated by "hg email -d" will still be not correct if a commit
message starts with "diff -r ".

Before the patch Mercurial has the following behavior:

$ echo "foobar">"file with spaces"
$ hg add "file with spaces"
$ hg diff --stat
 spaces |  1 +
 1 files changed, 1 insertions(+), 0 deletions(-)
$ hg diff --git --stat
 file with spaces |  1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

After the patch:

$ echo "foobar">"file with spaces"
$ hg add "file with spaces"
$ hg diff --stat
 file with spaces |  1 +
 1 files changed, 1 insertions(+), 0 deletions(-)
$ hg diff --git --stat
 file with spaces |  1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

Before the patch:

$ hg add mercurial/patch.py tests/tests-diffstat.t
$ hg commit -m "diffstat: fix parsing of filenames"

$ hg email -d --test tip
This patch series consists of 1 patches.

diffstat: fix parsing of filenames
[...]

 filenames             |    0
 mercurial/patch.py    |    6 ++++--
 tests/test-diffstat.t |   17 +++++++++++++++++
 3 files changed, 21 insertions(+), 2 deletions(-)
[...]

After the patch:

$ hg email -d --test tip
This patch series consists of 1 patches.

diffstat: fix parsing of filenames

[...]

 mercurial/patch.py    |    6 ++++--
 tests/test-diffstat.t |   17 +++++++++++++++++
 3 files changed, 21 insertions(+), 2 deletions(-)
[...]

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(ms)",
                            "Inline(ms)", "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 e.calls:
                for se in e.calls:
                    file.write(cols % ("+%s" % 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 hasattr(v, '__file__'):
                continue
            if not isinstance(v.__file__, 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()