Commit Graph

6 Commits

Author SHA1 Message Date
Paul Sokolovsky 5cb524673e tests/ffi_float: Split tgammaf() testcase to a separate test.
Some libc's may implement tgammaf as a header macro using tgamma(), so
don't assume it'll be in the library.
2015-08-29 17:24:29 +03:00
Damien George 936e25b164 tests: For unix ffi float test, add libm.so.6 to library search list.
Latest Arch Linux doesn't have libm.so as a proper shared object and so
we need to load libm.so.6.
2015-08-25 18:14:53 +01:00
Damien George 6bbbb1ab41 unix/modffi: Support passing float/double args. 2015-04-28 19:40:34 +01:00
Paul Sokolovsky 5dc8f9b28a tests: Skip ffi_float.py if module ffi is not available. 2014-10-06 22:37:40 +03:00
blmorris 4f449120e1 Change allows tests/unix/ffi_float.py to pass on OSX 2014-09-25 16:31:30 +01:00
Damien George 17598d49e1 unix: Don't use -Wno-error=cpp or #warning; fix strict alias warning.
For the sake of older versions of gcc (and other compilers), don't use
the #warning CPP directive, nor the -Wno-error=cpp option.

Also, fix a strict alias warning in modffi.c for older compilers, and
add a test for ffi module.

Addresses issue #847.
2014-09-06 17:46:52 +01:00