tests/check-perf-code.py

dirstate-tree: Add tree traversal/iteration

Like Python’s, Rust’s iterators are "external" in that they are driven
by a caller who calls a `next` method. This is as opposed to "internal"
iterators who drive themselves and call a callback for each item.

Writing an internal iterator traversing a tree is easy with recursion,
but internal iterators cannot rely on the call stack in that way,
they must save in an explicit object all state that they need to be
preserved across two `next` calls.

This algorithm uses a `Vec` as a stack that contains what would be
local variables on the call stack if we could use recursion.

Differential Revision: https://phab.mercurial-scm.org/D10370

#!/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())