view tests/check-perf-code.py @ 46095:93e09d370003

treemanifest: stop storing full path for each item in manifest._lazydirs

This information is obtainable, if needed, based on the lazydirs key (which is
the entry name) and the manifest's `dir()` method.

### Performance

This is actually both a memory and a performance improvement, but it's likely to
be a very small one in most situations. In the pathological repo I've been using
for testing other performance work I've done recently, this reduced the time for
a rebase operation (rebasing two commits across a public-phase change that
touches a sibling of one of my tracked directories where the common parent is
massive (>>10k entries)):

#### Before

```
  Time (mean ± σ):      4.059 s ±  0.121 s    [User: 0.9 ms, System: 0.6 ms]
  Range (min … max):    3.941 s …  4.352 s    10 runs
```

#### After

```
  Time (mean ± σ):      3.707 s ±  0.060 s    [User: 0.8 ms, System: 0.8 ms]
  Range (min … max):    3.648 s …  3.818 s    10 runs
```

Differential Revision: https://phab.mercurial-scm.org/D9553

#!/usr/bin/env python3
#
# check-perf-code - (historical) portability checker for contrib/perf.py

from __future__ import absolute_import

import os
import sys

# write static check patterns here
perfpypats = [
    [
        (
            r'(branchmap|repoview|repoviewutil)\.subsettable',
            "use getbranchmapsubsettable() for early Mercurial",
        ),
        (
            r'\.(vfs|svfs|opener|sopener)',
            "use getvfs()/getsvfs() for early Mercurial",
        ),
        (
            r'ui\.configint',
            "use getint() instead of ui.configint() for early Mercurial",
        ),
    ],
    # warnings
    [],
]


def modulewhitelist(names):
    replacement = [
        ('.py', ''),
        ('.c', ''),  # trim suffix
        ('mercurial%s' % '/', ''),  # trim "mercurial/" path
    ]
    ignored = {'__init__'}
    modules = {}

    # convert from file name to module name, and count # of appearances
    for name in names:
        name = name.strip()
        for old, new in replacement:
            name = name.replace(old, new)
        if name not in ignored:
            modules[name] = modules.get(name, 0) + 1

    # list up module names, which appear multiple times
    whitelist = []
    for name, count in modules.items():
        if count > 1:
            whitelist.append(name)

    return whitelist


if __name__ == "__main__":
    # in this case, it is assumed that result of "hg files" at
    # multiple revisions is given via stdin
    whitelist = modulewhitelist(sys.stdin)
    assert whitelist, "module whitelist is empty"

    # build up module whitelist check from file names given at runtime
    perfpypats[0].append(
        # this matching pattern assumes importing modules from
        # "mercurial" package in the current style below, for simplicity
        #
        #    from mercurial import (
        #        foo,
        #        bar,
        #        baz
        #    )
        (
            (
                r'from mercurial import [(][a-z0-9, \n#]*\n(?! *%s,|^[ #]*\n|[)])'
                % ',| *'.join(whitelist)
            ),
            "import newer module separately in try clause for early Mercurial",
        )
    )

    # import contrib/check-code.py as checkcode
    assert 'RUNTESTDIR' in os.environ, "use check-perf-code.py in *.t script"
    contribpath = os.path.join(os.environ['RUNTESTDIR'], '..', 'contrib')
    sys.path.insert(0, contribpath)
    checkcode = __import__('check-code')

    # register perf.py specific entry with "checks" in check-code.py
    checkcode.checks.append(
        ('perf.py', r'contrib/perf.py$', '', checkcode.pyfilters, perfpypats)
    )

    sys.exit(checkcode.main())