view mercurial/lsprofcalltree.py @ 29322:66dbdd3cc2b9 stable

bdiff: extend matches across popular lines

For very large diffs that have large numbers of identical lines (JSON
dumps) that also have large blocks of identical text, bdiff could become
confused about which block matches which because it can only match
very limited regions. The result is very large diffs for small sets of edits.

The earlier recursion rebalancing fix made this behavior more frequent because
it's now more prone to match block 1 to block 2. One frequent user of
large JSON files reported being unable to pass the resulting diffs
through their code review system.

Prior to this change, bdiff would calculate the length of a match at
(i, j) as 1 + length found at (i-1, j-1). With large number of popular
(ignored) lines, this often meant matches couldn't be extended
backwards at all and thus all matching regions were very small.
Disabling the popularity threshold is not an option because it brings
back quadratic behavior.

Instead, we extend a match backwards until we either found a previously
discovered match or we find a mismatching line. This thus successfully
bridges over any popular lines inside and before a matching region.
The larger regions then significant reduce the probability of confusion.

"""
lsprofcalltree.py - lsprof output which is readable by kcachegrind

Authors:
    * David Allouche <david <at> allouche.net>
    * Jp Calderone & Itamar Shtull-Trauring
    * Johan Dahlin

This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""

from __future__ import absolute_import, print_function

def label(code):
    if isinstance(code, str):
        return '~' + code    # built-in functions ('~' sorts at the end)
    else:
        return '%s %s:%d' % (code.co_name,
                             code.co_filename,
                             code.co_firstlineno)

class KCacheGrind(object):
    def __init__(self, profiler):
        self.data = profiler.getstats()
        self.out_file = None

    def output(self, out_file):
        self.out_file = out_file
        print('events: Ticks', file=out_file)
        self._print_summary()
        for entry in self.data:
            self._entry(entry)

    def _print_summary(self):
        max_cost = 0
        for entry in self.data:
            totaltime = int(entry.totaltime * 1000)
            max_cost = max(max_cost, totaltime)
        print('summary: %d' % max_cost, file=self.out_file)

    def _entry(self, entry):
        out_file = self.out_file

        code = entry.code
        if isinstance(code, str):
            print('fi=~', file=out_file)
        else:
            print('fi=%s' % code.co_filename, file=out_file)
        print('fn=%s' % label(code), file=out_file)

        inlinetime = int(entry.inlinetime * 1000)
        if isinstance(code, str):
            print('0 ', inlinetime, file=out_file)
        else:
            print('%d %d' % (code.co_firstlineno, inlinetime), file=out_file)

        # recursive calls are counted in entry.calls
        if entry.calls:
            calls = entry.calls
        else:
            calls = []

        if isinstance(code, str):
            lineno = 0
        else:
            lineno = code.co_firstlineno

        for subentry in calls:
            self._subentry(lineno, subentry)
        print(file=out_file)

    def _subentry(self, lineno, subentry):
        out_file = self.out_file
        code = subentry.code
        print('cfn=%s' % label(code), file=out_file)
        if isinstance(code, str):
            print('cfi=~', file=out_file)
            print('calls=%d 0' % subentry.callcount, file=out_file)
        else:
            print('cfi=%s' % code.co_filename, file=out_file)
            print('calls=%d %d' % (
                subentry.callcount, code.co_firstlineno), file=out_file)

        totaltime = int(subentry.totaltime * 1000)
        print('%d %d' % (lineno, totaltime), file=out_file)