tests/hypothesishelpers.py
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
Fri, 03 Mar 2017 02:57:06 +0900
changeset 31220 e1d035905b2e
parent 28728 8699c89f3ae9
child 43076 2372284d9457
permissions -rw-r--r--
similar: compare between actual file contents for exact identity Before this patch, similarity detection logic (for addremove and automv) depends entirely on SHA-1 digesting. But this causes incorrect rename detection, if: - removing file A and adding file B occur at same committing, and - SHA-1 hash values of file A and B are same This may prevent security experts from managing sample files for SHAttered issue in Mercurial repository, for example. https://security.googleblog.com/2017/02/announcing-first-sha1-collision.html https://shattered.it/ Hash collision itself isn't so serious for core repository functionality of Mercurial, described by mpm as below, though. https://www.mercurial-scm.org/wiki/mpm/SHA1 This patch compares between actual file contents after hash comparison for exact identity. Even after this patch, SHA-1 is still used, because it is reasonable enough to quickly detect existence of "(almost) same" file. - replacing SHA-1 causes decreasing performance, and - replacement of it has ambiguity, yet Getting content of removed file (= rfctx.data()) at each exact comparison should be cheap enough, even though getting content of added one costs much. ======= ============== ===================== file fctx data() reads from ======= ============== ===================== removed filectx in-memory revlog data added workingfilectx storage ======= ============== =====================

# 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()