tests/hypothesishelpers.py

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

# Helper module to use the Hypothesis tool in tests
#
# Copyright 2015 David R. MacIver
#
# For details see http://hypothesis.readthedocs.org

from __future__ import absolute_import, print_function
import os
import sys
import traceback

try:
    # hypothesis 2.x
    from hypothesis.configuration import set_hypothesis_home_dir
    from hypothesis import settings
except ImportError:
    # hypothesis 1.x
    from hypothesis.settings import set_hypothesis_home_dir
    from hypothesis import Settings as settings
import hypothesis.strategies as st
from hypothesis import given

# hypothesis store data regarding generate example and code
set_hypothesis_home_dir(os.path.join(
    os.getenv('TESTTMP'), ".hypothesis"
))

def check(*args, **kwargs):
    """decorator to make a function a hypothesis test

    Decorated function are run immediately (to be used doctest style)"""
    def accept(f):
        # Workaround for https://github.com/DRMacIver/hypothesis/issues/206
        # Fixed in version 1.13 (released 2015 october 29th)
        f.__module__ = '__anon__'
        try:
            with settings(max_examples=2000):
                given(*args, **kwargs)(f)()
        except Exception:
            traceback.print_exc(file=sys.stdout)
            sys.exit(1)
    return accept


def roundtrips(data, decode, encode):
    """helper to tests function that must do proper encode/decode roundtripping
    """
    @given(data)
    def testroundtrips(value):
        encoded = encode(value)
        decoded = decode(encoded)
        if decoded != value:
            raise ValueError(
                "Round trip failed: %s(%r) -> %s(%r) -> %r" % (
                    encode.__name__, value, decode.__name__, encoded,
                    decoded
                ))
    try:
        testroundtrips()
    except Exception:
        # heredoc swallow traceback, we work around it
        traceback.print_exc(file=sys.stdout)
        raise
    print("Round trip OK")


# strategy for generating bytestring that might be an issue for Mercurial
bytestrings = (
    st.builds(lambda s, e: s.encode(e), st.text(), st.sampled_from([
        'utf-8', 'utf-16',
    ]))) | st.binary()