hgweb: when constructing or adding to a wsgi environ dict, use native strs That's what's required of us to work with the WSGI API on Python 3. Differential Revision: https://phab.mercurial-scm.org/D967

hgweb: produce native string for etag value Also use %d since we know mtime is numeric. Differential Revision: https://phab.mercurial-scm.org/D966

hgweb: in protocol adapter, look for bytes instances, not str Differential Revision: https://phab.mercurial-scm.org/D963

hgweb: in protocol adapter, avoid control reaching end of non-void function This greatly confounded some Python 3 porting work, once it was managing to get this far. Differential Revision: https://phab.mercurial-scm.org/D962

test-check-code: fail new commits which use 'atexit' instead of 'ui.atexit' Callbacks registered with 'atexit' are sometimes not called (like when hg aborts and calls os._exit). On the other hand, callbacks registered with 'ui.atexit' are called in most cases. Therefore, encouraging the use of 'ui.atexit' by failing the test 'test-check-code.t' appropriately. Test Plan: Ran the test 'test-check-code.t' after importing 'atexit' in one of the py files and confirmed that the test fails. Differential Revision: https://phab.mercurial-scm.org/D961

test-push-race: use 'ui.atexit' instead of python's 'atexit' Callbacks registered with 'atexit' are sometimes not called (like when a process is killed by the SIGTERM signal). Therefore, this commit replaces it with 'ui.atexit' which ensures that the callbacks are always called. This also makes the test compatible with chg. Test Plan: Ran the test 'test-push-race.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D957

py3: use '%d' for integers instead of '%s' Differential Revision: https://phab.mercurial-scm.org/D973