This is relevant when using runpytest in-process.
Fixes:
E def test_1(testdir):
E testdir.runpytest()
E > __import__('pdb').set_trace()
E
E ../../test_trace_after_runpytest.py:3:
E …/Vcs/pytest/src/_pytest/debugging.py:81: in set_trace
E tw = _pytest.config.create_terminal_writer(cls._config)
E
E config = None, args = (), kwargs = {}, tw = <py._io.terminalwriter.TerminalWriter object at 0x7f1097088160>
E
E def create_terminal_writer(config, *args, **kwargs):
E """Create a TerminalWriter instance configured according to the options
E in the config object. Every code which requires a TerminalWriter object
E and has access to a config object should use this function.
E """
E tw = py.io.TerminalWriter(*args, **kwargs)
E > if config.option.color == "yes":
E E AttributeError: 'NoneType' object has no attribute 'option'
The type `bytes` is available on all supported Python versions. On
Python 2.7, it is an alias of str, same as six.binary_type.
Makes the code slightly more forward compatible.
After `pdb.set_trace()` capturing is turned off.
This patch resumes it after using the `continue` (or `c` / `cont`)
command.
Store _pytest_capman on the class, for pdbpp's do_debug hack to keep it.
Without this, `debug …` would fail like this:
/usr/lib/python3.6/cmd.py:217: in onecmd
return func(arg)
.venv/lib/python3.6/site-packages/pdb.py:608: in do_debug
return orig_do_debug(self, arg)
/usr/lib/python3.6/pdb.py:1099: in do_debug
sys.call_tracing(p.run, (arg, globals, locals))
/usr/lib/python3.6/bdb.py:434: in run
exec(cmd, globals, locals)
/usr/lib/python3.6/bdb.py:51: in trace_dispatch
return self.dispatch_line(frame)
/usr/lib/python3.6/bdb.py:69: in dispatch_line
self.user_line(frame)
/usr/lib/python3.6/pdb.py:261: in user_line
self.interaction(frame, None)
.venv/lib/python3.6/site-packages/pdb.py:203: in interaction
self.setup(frame, traceback)
E AttributeError: 'PytestPdb' object has no attribute '_pytest_capman'
- add pytest_leave_pdb hook
- fixes test_pdb_interaction_capturing_twice: would fail on master now,
but works here
Running `pytest -k doesnotmatch` on pytest's own tests takes ~3s with
Kitty terminal for me, but only ~1s with `-q`.
It also is faster with urxvt, but still takes 2.2s there.
This patch only calls `report_collect` every 0.1s, which is good enough
for reporting collection progress, and improves the time with both Kitty
and urxvt to ~1.2s for me.