summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
...
* Use a new event loopNed Batchelder2018-10-241-2/+2
|
* Add 3.7, and other appveyor changesNed Batchelder2018-10-241-15/+37
|
* Always include a documentation link at the end of help messagesNed Batchelder2018-10-212-14/+24
|
* Make directories for the data file if needed. #721Ned Batchelder2018-10-213-0/+14
|
* Helpers for making directoriesNed Batchelder2018-10-213-7/+20
|
* Clean __pycache__ before .pyc (a little faster?)Ned Batchelder2018-10-191-1/+1
|
* PyPy3 fixed an obscure bug long ago, we don't need this overrideNed Batchelder2018-10-191-7/+3
|
* One more error case for the command lineNed Batchelder2018-10-192-3/+21
|
* Clean up a metacov .pth file that could get left behind.Ned Batchelder2018-10-192-0/+2
|
* `[run] command_line` is the command line to use for 'coverage run'. #695Ned Batchelder2018-10-185-4/+64
|
* This was in the wrong placeNed Batchelder2018-10-181-3/+3
|
* We weren't using this argumentNed Batchelder2018-10-181-2/+2
|
* This is literally what setdefault is forNed Batchelder2018-10-181-2/+1
|
* Clean some lintNed Batchelder2018-10-172-4/+8
|
* Don't clobber sys.path[0]. #715Ned Batchelder2018-10-162-4/+4
|
* A test for 'no such table: meta' as in #716.Ned Batchelder2018-10-161-0/+12
|
* Allow later DebugOutputFile to replace earlier onesNed Batchelder2018-10-161-6/+12
| | | | | | When logging calls, get_one() is called with no filters. It would be the_one, so a later get_one with filters for pids wouldn't take effect. Now the earlier is only interim, and the later one wins.
* Put this helper in the right placeNed Batchelder2018-10-161-6/+7
|
* Note a bug we closedNed Batchelder2018-10-161-1/+3
|
* Do we need more than 10 tries?Ned Batchelder2018-10-151-1/+1
|
* Use one transaction to speed combiningNed Batchelder2018-10-152-40/+50
|
* Michał suggested this would make the information easier to find.Ned Batchelder2018-10-142-3/+4
|
* Defer using the database when calling set_context #716Ned Batchelder2018-10-143-14/+19
| | | | | | | | | | | The collector calls set_context() before any code is run. If we touch the database there, it will get created *very* early. This causes problems with pytest-cov, which will delete those early-created files when erasing data. By deferring the database access until add_lines is called, the data file stays off the disk until the collection is done (or until the context switches), which avoids the problem.
* Use --source to ensure tests are showing what we want.Ned Batchelder2018-10-143-8/+10
| | | | | | | | | | | Travis started having these extra files in coverage reports from our tests: site-packages/pkg_resources/_vendor/six.py site-packages/pkg_resources/extern/__init__.py I don't know why they are being pulled in, but the tests aren't interested in them, and it is throwing off the results.
* Have to rethink how to use contexts ourselvesNed Batchelder2018-10-142-4/+0
| | | | | | Contexts fail when using PYTRACER, and we want to measure coverage under PYTRACER (at least for PyPy), so we need a more sophisticated strategy for how to use contexts.
* Missed one file when updating license linksNed Batchelder2018-10-141-1/+1
|
* Not sure how I went for so long without one of these creeping inNed Batchelder2018-10-141-0/+3
|
* Oops, we were always measuring coverage on TravisNed Batchelder2018-10-131-1/+1
|
* Fewer conditionals for debug outputNed Batchelder2018-10-133-23/+30
|
* Debugging improvementsNed Batchelder2018-10-132-6/+6
|
* Sphinx complains about app.info now, and what's wrong with print?Ned Batchelder2018-10-071-5/+1
|
* Finish updating requirementsNed Batchelder2018-10-071-3/+3
|
* All-in on contexts for ourselvesNed Batchelder2018-10-072-3/+7
|
* Update dependenciesNed Batchelder2018-10-066-15/+19
|
* Version bumpNed Batchelder2018-10-063-6/+8
|
* Look up names so we don't care about casecoverage-5.0a3Ned Batchelder2018-10-061-6/+4
|
* Diagnose an appveyor problemNed Batchelder2018-10-061-0/+4
|
* Prep for 5.0a3Ned Batchelder2018-10-064-73/+12
|
* Add words about 3.8Ned Batchelder2018-10-063-2/+8
|
* Finally jumps back to exiting linesNed Batchelder2018-10-064-45/+151
| | | | | | In Python 3.8, when a finally clause is run because a line in the try block is exiting the block, the exiting line is visited again after the finally block.
* Python 3.8 uses Constant nodes in the ASTNed Batchelder2018-10-041-1/+1
|
* Python 3.6 changed lnotab to signed bytesNed Batchelder2018-10-041-0/+2
|
* Add 3.8 to toxNed Batchelder2018-10-041-3/+6
|
* Pin everythingNed Batchelder2018-10-031-0/+1
|
* More tests of qualname_from_frameNed Batchelder2018-09-301-0/+19
|
* The idea of checking the mro explicitly in qualname_from_frame was Aleksi'sNed Batchelder2018-09-281-0/+1
|
* SimplifyNed Batchelder2018-09-281-6/+2
|
* LintNed Batchelder2018-09-281-3/+3
|
* Deal with properties in qualname_from_frameNed Batchelder2018-09-282-2/+18
|
* Get qualified names for method contextsNed Batchelder2018-09-282-1/+80
|
View Lorry Controller Status