The error had not be caught be specs because `bundle install` was
returning a zero exit code when plugin installation errors happened. So
I fixed that issue too.
https://github.com/rubygems/rubygems/commit/90cde87856
As part of a recent bug fix where bundler was accidentally hitting the
network when not supposed to, I made some refactoring, and the commit I'm
reverting here
(d74830d00b)
was some cleanup that those refactorings allowed according to "past me".
That was completely wrong, `bundle check` should never consider cached
gems, only installed gems, so the code that was removed was necessary.
https://github.com/rubygems/rubygems/commit/5483e98305
Use the `git branch --list` rather than the `git branch -l` for better
compatibility. Because the `git branch -l` is used to create a new branch in
Git version < 2.20.0.
https://github.com/rubygems/rubygems/commit/eac5be7d06
When setting the `RUBYGEMS_GEMDEPS` environment variable to allow
skipping `bundle exec`, `bundler` will print a warning about potential
incompatibility.
Initially the `RUBYGEMS_GEMDEPS` variable used a completely different
(re)implementation of `bundler` functionality. That implementation was
not battle tested and could potentially differ in behaviour from what
`bundler` does. That's why print a warning.
However, these days, all `rubygems` does when `RUBYGEMS_GEMDEPS` is set
is to require `bundler/setup`, so there's no risk of any
incompatibility, since that's just plain `bundler`.
https://github.com/rubygems/rubygems/commit/bbddc27016
When printing sources inside these error messages, it's useful to only
consider the current state of the source. For example, when requiring
`bundler/setup`, the source shouldn't be configured to be able to hit
the network, so the error message should only mention "locally installed
gems" to make that more clear.
https://github.com/rubygems/rubygems/commit/30eb14f853
In the case of path sources, the path the source is pointing to should
be added directly to the `$LOAD_PATH` without any modifications.
https://github.com/rubygems/rubygems/commit/d3bba936f0
Co-authored-by: Daniel Niknam <mhmd.niknam@gmail.com>
TSort was released as a library so we can install it, and also other
gems that are loaded by the spec. Also, Ruby on Windows apparently loads
fiddle 1.0.6, so we need to also install that to make that not fail.
https://github.com/rubygems/rubygems/commit/2b8dcab99e
Call `IOSpecs.io_fixture` with the default encoding explicitly.
`IOSpecs.closed_io` calls the method without optional `mode` which
is set to UTF-8 by default, while the default external encoding
depends on the locale environment variables.
Mashalling a closed IO object raised "closed stream (IOError)" before instead of TypeError.
This changes IO#(in|ex)ternal_encoding to still return the encoding even if the underlying FD is closed.
Fixes bug #18077
This updates the trace instructions to directly dispatch to
opt_send_without_block. So this should cause no slowdown in
non-trace mode.
To enable the tracing of the optimized methods, RUBY_EVENT_C_CALL
and RUBY_EVENT_C_RETURN are added as events to the specialized
instructions.
Fixes [Bug #14870]
Co-authored-by: Takashi Kokubun <takashikkbn@gmail.com>
* Hide read function warning in string_spec_RSTRING_PTR_read function
* The type of `read` may be `ssize_t`
Co-authored-by: Nobuyoshi Nakada <nobu@ruby-lang.org>
This changes Thread::Location::Backtrace#absolute_path to return
nil for methods/procs defined in eval. If the realpath of an iseq
is nil, that indicates it was defined in eval, in which case you
cannot use RubyVM::AbstractSyntaxTree.of.
Fixes [Bug #16983]
Co-authored-by: Koichi Sasada <ko1@atdot.net>
