* io.c (argf_next_argv): set init flag if succeeded to forward, after
skipping.
* io.c (argf_block_call_i, argf_block_call): no more forwarding if
forwarded after skipping. [ruby-list:49185]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39997 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (argf_close): deal with init flag.
* io.c (argf_block_call_i, argf_block_call): forward next file if
skipped while iteration, to get rid of IOError. [ruby-list:49185]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39996 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Because musl libc doesn't have it. [Bug #8051] [ruby-core:53229]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39818 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c: here. because __syscall() is only used from io.c.
* include/ruby/missing.h: move "#include <sys/type.h>" to ....
* include/ruby/intern.h: here. because it was introduced for
fixing NFDBITS issue. [ruby-core:05179].
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39774 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* file.c (rb_sys_fail_path_with_func): share same function, and path
may be nil.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@39760 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (pipe_open): envp is not used if only spawnv is defined right
now.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38835 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (rb_cloexec_fcntl_dupfd) Use an emulation with dup(2) when
fcntl(2) and/or F_DUPFD is unavailable.
Suggested by akr.
* configure.in (HAVE_FCNTL): NativeClient does not provide fcntl(2).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38713 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
bootstrap_test/test_io.rb. NativeClient does not support F_DUPFD
but supports dup2(2).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38683 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* error.c (compile_err_append, compile_warn_print, warn_print): use
rb_write_error_str() instead of writing to rb_stderr directly.
* io.c (rb_write_error_str): a stopgap measure not to unblock GVL.
warning from require seems to still have race condition errors.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38590 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
because it is for waiting until io readable.
* io.c (rb_io_wait_writable): always use rb_thread_fd_writable()
instaed of bare rb_wait_for_single_fd(). we shouldn't ignore
return value.
* io.c (rb_io_wait_readable): ditto. always use rb_thread_wait_fd().
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38448 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (io_flush_buffer): don't hold mutex if already have.
Now recursive lock may occur when following scenario.
fptr_finalize -> finish_writeconv_sync -> finish_writeconv
-> io_fflush.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38400 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
io_flush_buffer_async.
* io.c (io_flush_buffer_async2): new helper function for
io_flush_buffer. It uses rb_thread_call_without_gvl2() instead
of rb_thread_io_blocking_region.
* io.c (io_flush_buffer_sync2): new helper function for
io_flush_buffer_async2.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38399 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
when EINTR. EINTR mean signal interrupt was happen. We don't
need any wait.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38396 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
temporary async_interrupt_timing(Object => :defer)
* io.c (rb_f_p): use rb_uninterruptible.
* io.c (rb_f_p_internal): helper function for rb_f_p().
* io.c (struct rb_f_p_arg): new struct for rb_f_p_internal.
* test/ruby/test_thread.rb (test_async_interrupt_and_p): test for
the above.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38225 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* test/ruby/test_thread.rb (test_async_interrupt_and_io):
test for the above.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@38224 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* internal.h (rb_mutex_allow_trap): added.
* thread.c (rb_mutex_lock, rb_mutex_unlock): check mutex->allow_trap.
* thread.c (mutex_sleep): remove trap check because it uses
rb_mutex_lock and rb_mutex_unlock internally.
* thread.c (rb_mutex_allow_trap): new helper function for the above.
* io.c (io_binwrite): mark fptr->write_lock as writable in trap.
* test/ruby/test_signal.rb (test_trap_puts): test for the above.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37930 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* file.c (Init_File): replace with rb_file_const() with
rb_define_const() because RDoc don't care rb_file_const.
[Bug #5530]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37746 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
because if there is no allocated console at the moment Windows does
not automatically associate it for child process's standard handle.
this is adhoc workaround.
reported by Martin Thiede at [ruby-core:48542] [Bug #7239].
* io.c (rb_cloexec_dup2): ditto.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37388 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (rb_io_reopen): accept File::Constants as well as mode string.
based on the patch by Glass_saga (Masaki Matsushita) in
[ruby-core:47694]. [Feature #7067]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@37041 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* io.c (io_set_read_length): if the read length equals to the buffer
string size then nothing to do. or ensure the string modifiable
before setting the length only when the former is shorter. based on
the patch in [ruby-core:47541] by Hiroshi Shirosaki.
[ruby-core:46586] [Bug #6764]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36980 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
