Commit Graph

1771 Commits

Author SHA1 Message Date
holger krekel 7084313408 factor out session main loop so that distribute testing can make use of it
--HG--
branch : trunk
2010-04-26 17:56:39 +02:00
Benjamin Peterson 7629b8fda7 make test source syntax valid
--HG--
branch : trunk
2010-04-23 20:49:00 -05:00
Benjamin Peterson 1771cb0af8 fetch code object compatibly
--HG--
branch : trunk
2010-04-23 20:43:49 -05:00
Benjamin Peterson d1b45ef3d4 add a helper to get a function's code
--HG--
branch : trunk
2010-04-23 20:39:40 -05:00
Benjamin Peterson f16d54f9a8 merge main
--HG--
branch : trunk
2010-04-23 20:28:32 -05:00
Benjamin Peterson d909aead4e provide encoding to dupfile() for py3
--HG--
branch : trunk
2010-04-23 20:27:34 -05:00
holger krekel 0b24a70279 this should test and fix the same issue that was committed in
the pypy svn-repo as r72534

--HG--
branch : trunk
2010-04-23 19:28:41 +02:00
holger krekel b3a05b545e another couple of checks on jython, still some problems
--HG--
branch : trunk
2010-04-23 19:05:22 +02:00
holger krekel 221ac3e466 a couple of more mostly jython-related fixes
--HG--
branch : trunk
2010-04-23 13:29:28 +02:00
holger krekel 2ee6653ff7 update distribute
--HG--
branch : trunk
2010-04-23 12:31:11 +02:00
hpk@tannit.openend.se 4337702a6a fixes for testrun on jython
--HG--
branch : trunk
2010-04-23 12:05:29 +02:00
holger krekel ff90b1b4fb fix version numbers
--HG--
branch : trunk
2010-04-22 16:51:42 +02:00
holger krekel 85d35f7418 introduce an experimental approach for allowing dynamic addition of hooks from plugin. Plugins may register new hooks by implementing the new
pytest_registerhooks(pluginmanager)

and call

    pluginmanager.registerhooks(module)

with the referenced 'module' object containing the hooks.

The new pytest_registerhooks is called after pytest_addoption
and before pytest_configure.

--HG--
branch : trunk
2010-04-22 11:57:57 +02:00
holger krekel cbb4c0dadc use taskkill cmdline for jython/win32 but skip test on jython because it does not return a subprocess PID
--HG--
branch : trunk
2010-04-21 06:23:19 -07:00
holger krekel c10f0c2c36 merge in fixes
--HG--
branch : trunk
2010-04-21 14:49:38 +02:00
holger krekel 6e84b487ca robustify a check to not randomly fail
--HG--
branch : trunk
2010-04-21 14:47:44 +02:00
holger krekel 061f4c1515 robustify check
--HG--
branch : trunk
2010-04-21 14:46:41 +02:00
holger krekel fe34a8a15a a couple of more fixes/refinements for getting py.test to run better on jython/win32
--HG--
branch : trunk
2010-04-21 03:50:03 -07:00
holger krekel 5715bbd6f5 refining the win32 checks some further
--HG--
branch : trunk
2010-04-20 20:08:52 +02:00
holger krekel 10f6c3a432 fix check to work when there is no jython
--HG--
branch : trunk
2010-04-20 10:48:49 -07:00
holger krekel 536252cb2e refine win32 checks to also work on top of jython/win32
--HG--
branch : trunk
2010-04-20 10:45:41 -07:00
holger krekel 7cd899fd3c add capturelog generated plugin text
--HG--
branch : trunk
2010-04-19 14:44:11 +02:00
holger krekel e45cd7e35e fix issue86 - point to pytest-xdist plugin for looponfailing feature.
--HG--
branch : trunk
2010-04-14 15:05:39 +02:00
holger krekel 75a6bf2395 fix issue78 - strike superflous "import sys" that cause unbound
local var errors.

--HG--
branch : trunk
2010-04-14 13:30:12 +02:00
holger krekel 1d28dcf140 add links to new plugins
--HG--
branch : trunk
2010-04-12 16:08:12 +02:00
Benjamin Peterson d994c51ccd actually skip doc tests if pygments is not available
--HG--
branch : trunk
2010-03-09 16:18:27 -06:00
Benjamin Peterson fe95ad0aa6 fix typo
--HG--
branch : trunk
2010-03-03 15:54:39 -06:00
holger krekel c75d0faa6f remove cover and xmlresult plugins as they are not easily installable
and lead to frustration (thanks again to prologic for getting back on it)

--HG--
branch : trunk
2010-02-10 16:11:19 +01:00
holger krekel 3608d722fa fix docs to not point to a downloadable plugin if the
plugin is external (thanks to prologic for feedbacking
on this confusion)

--HG--
branch : trunk
2010-02-10 14:21:49 +01:00
holger krekel 18b5ddc4dd note down two issues after having helped prologic - also related to
earlier discussions with ronny and others.

--HG--
branch : trunk
2010-02-09 18:32:17 +01:00
holger krekel a2fbe31a26 Added tag 1.2.1 for changeset c143a8c8840a
--HG--
branch : trunk
2010-02-08 17:39:55 +01:00
holger krekel 222a08ec03 going for the 1.2.1 release
--HG--
branch : trunk
2010-02-08 16:39:29 +01:00
holger krekel c7326f1949 fix a pdb problem when dropping to a "raises" related failure
--HG--
branch : trunk
2010-02-08 14:17:01 +01:00
holger krekel 3bca6be46d add some issues
--HG--
branch : trunk
2010-02-07 02:55:50 +01:00
holger krekel 13488dd540 if a funcarg is misspelled/missing, hint at using "--funcargs"
--HG--
branch : trunk
2010-02-07 02:15:47 +01:00
holger krekel ac1eed545c nice-ify --funcarg reporting, show paths instead of useless python reprs
--HG--
branch : trunk
2010-02-07 02:09:14 +01:00
holger krekel e09e7148a3 fix docstring
--HG--
branch : trunk
2010-02-07 01:56:43 +01:00
holger krekel d163d92b33 actually look into all non-dot subdirs for conftest.py files - recursive walk would be too heavy for large source trees but first-level subdirs are fine IMO. Note that prior to py.test 1.0 doing this "look-ahead" was not easily doable because it was hard to avoid global state in conftest.py, this is not true anymore - so i feel ok telling people to cleanup their conftest files if they get problems (you can imagine people doing all kinds of things at global conftest.py module scope, can't you?)
--HG--
branch : trunk
2010-02-06 22:37:04 +01:00
holger krekel 105ed6dcaa fix this test
--HG--
branch : trunk
2010-02-05 22:57:46 +01:00
holger krekel a3d15b2c60 refined usage and options for "py.cleanup":
py.cleanup     # remove "*.pyc" and "*$py.class" (jython) files
    py.cleanup -e .swp -e .cache # also remove files with these extensions
    py.cleanup -s  # remove "build" and "dist" directory next to setup.py files
    py.cleanup -d  # also remove empty directories
    py.cleanup -a  # synonym for "-s -d -e 'pip-log.txt'"
    py.cleanup -n  # dry run, only show what would be removed

--HG--
branch : trunk
2010-02-05 22:50:41 +01:00
holger krekel 3234e6e978 add a --funcargs option showing available funcargs
--HG--
branch : trunk
2010-02-04 23:45:07 +01:00
holger krekel 02c129df7a fix a test
--HG--
branch : trunk
2010-02-04 16:13:30 +01:00
holger krekel f95877a09b show a short and nice traceback for funcarg lookup errors
--HG--
branch : trunk
2010-02-04 16:01:02 +01:00
holger krekel 7bd60b5abb check and load test*/conftest.py early from anchors -
this makes it a bit more convenient to have command line options
available from a root directory of a project that does not
directly contain a conftest.py

--HG--
branch : trunk
2010-02-04 12:26:53 +01:00
holger krekel 33d78f41b2 fix title to not mention distributed programming which
is separated out into execnet.

--HG--
branch : trunk
2010-02-02 11:32:21 +01:00
holger krekel 9d64d7e27a refine setup ordering some more - test and avoid a problem with funcarg setups where the
surrounding setup_module would fail, but the funcarg setup still be called (which might
assume that setup_module has been called so would raise a confusing error)

--HG--
branch : trunk
2010-01-28 15:36:27 +01:00
holger krekel a2af204687 again addresses issue78 : we now call teardown also if setup raised a Skipped exception.
I also made sure, setup_module/class will only be called once - before they'd be call again
and again if they raise an error or a skip - for each test in their scope.

--HG--
branch : trunk
2010-01-28 14:20:58 +01:00
holger krekel 4d5ea7be43 install pygments for tests
--HG--
branch : trunk
2010-01-27 13:02:02 +01:00
holger krekel 98608611af closes #67 new super-short traceback-printing option: "--tb=line" will print a single line for each failing (python) test indicating its filename, lineno and the failure value
--HG--
branch : trunk
2010-01-27 12:52:19 +01:00
holger krekel b18ab6e03b fix issue78 - now python-level teardown functions are now called even if the setup failed.
Important detail: if the setup raises a Skipped exception, teardown will not be called.  This helps
to avoid breaking setup_module/class that performs a skip - it would otherwise internally
be considered as a "successful" setup in order to have teardown called later.  I guess
it also makes sense to treat Skip specially because it is unlikely a teardown should be
called if a Skip was raised on setup.

In any case, failing setups and teardowns will be reported separately.

--HG--
branch : trunk
2010-01-27 12:09:30 +01:00