* Write docs for inline dependency-versions
* Change the `inline` keyword to `packages` for better readability
* Implement inline package constraints
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Add schema for TOML properties
* Change the parsing of the option to parse filenames as-is
* Add a unit test for table-parsing of the option
* Remove unneeded shlex.quote on the dependency-version test
* Tidy-ups, comments, docs fixes
* Add test for empty packages option value
* Fix empty packages scenario
And, remove some optionals to reduce the problem space
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* optimise unit tests - Cache loading the config TOML
Unit test time: 13.1s -> 10.5s
* optimise unit tests - use the same pyproject validator across the tests
Unit test time: 10.5s -> 5.7s
* optimise unit tests - selector optimisation
Unit test time: 5.7s -> 5.1s
* optimise unit tests - build options computation cache
Unit test time: 5.1s -> 3.2s
* Use functools.cache rather than functools.lru_cache
* Don't overwrite build_options when applying functools.cache
* chore: use SPEC 0 schedule for cibuildwheel
* remove support for {python} and {pip} in commands
* Remove specific Python versions from the update-dependencies job
The requirements pinning is done by uv now, so we don't need to
run the versions of Python to do the pinning anymore.
---------
Co-authored-by: Joe Rickerby <joerick@mac.com>
* Add test_sources configuration option.
* Add pyodide implementation.
* Modify default test behavior to run in the project directory.
* Update the test for running in the project directory.
* Apply suggestions from code review
Co-authored-by: Joe Rickerby <joerick@mac.com>
* Add shlex quoting to test-sources.
* Restructure ctypes example to avoid issues running from the project folder.
---------
Co-authored-by: Joe Rickerby <joerick@mac.com>
Fix for #1803, where the method used for merging the config-settings option - string concatenation - was of little use.
I broke out the TableFmt object into a protocol-like object called OptionFormat, where the formatting and merge rules can be customised more deeply. This is more explicit, and lets us be a bit more precise with how TOML object get converted into the options.
I intend to use the flexibility of the OptionsFormat structure to tackle the remaining abiguity around environment variable quoting, as seen in the xfails in the options_test.py unit test and discussed in #1271.
Co-authored-by: Matthieu Darbois <mayeut@users.noreply.github.com>
* Refactor error handling to use exceptions
cibuildwheel has up until now handled most errors by printing an error message to sys.stderr and calling sys.exit. Others were handled using Logger.error, depending on the context. We also had return codes, but these weren't explicitly defined anywhere.
This makes that convention more explicit and codified. Now to halt the program, the correct thing to do is to throw a cibuildwheel.errors.FatalError exception - that is caught in main() and printed before exiting. The existing behaviour was kept - if an error occurs within a build step (probably something to do with the build itself), the Logger.error() method is used. Outside of a build step (e.g. a misconfiguration), the behaviour is still to print 'cibuildwheel: <message>'
I also took the opportunity to add a debugging option `--debug-traceback` (and `CIBW_DEBUG_TRACEBACK`), which you can enable to see a full traceback on errors.
(I've deactivated the flake8-errmsg lint rule, as it was throwing loads of errors and these error messages aren't generally seen in a traceback context)
* add noqa rule
* Apply suggestions from code review
Co-authored-by: Henry Schreiner <HenrySchreinerIII@gmail.com>
* Return to flake8-errmsg conformance
* Code review suggestions
* Subclass Exception rather than SystemExit
* apply error handling to new code and fix merge issues
* Apply review suggestion
* fix: merge issue
* Update cibuildwheel/errors.py
---------
Co-authored-by: Henry Schreiner <HenrySchreinerIII@gmail.com>
Co-authored-by: mayeut <mayeut@users.noreply.github.com>
* feat: add inherit to override
Signed-off-by: Henry Schreiner <henryschreineriii@gmail.com>
* refactor: use dict and support prepend
Signed-off-by: Henry Schreiner <henryschreineriii@gmail.com>
* Refactor: simplifying by splitting the responsibilities of _dig_first
* Refactor to allow merging of string settings, and preserve table cascades
* docs: add some docs for inherit
Signed-off-by: Henry Schreiner <henryschreineriii@gmail.com>
* Apply suggestions from code review
Co-authored-by: Joe Rickerby <joerick@mac.com>
---------
Signed-off-by: Henry Schreiner <henryschreineriii@gmail.com>
Co-authored-by: Joe Rickerby <joerick@mac.com>
Instead of using pip as the default, set it to default. This way
each platform can choose independently what to do as the default
behavior.
This is intended as part of adding Pyodide support. Pyodide cannot
use pip as the build frontend. It always uses a modified pypa/build.
So if the build_frontend is explicitly set to pip we want to raise
an error. But if it's unset, then we should be able to tell and just
do what we want.
