Fixed#2823 - Make it so that a semicolon appearing after an invocation of GTEST_SUPPRESS_UNREACHABLE_CODE_WARNING_BELOW_ does not trigger a redundant semicolon warning.
This works by introducing an else block with a statement that intentionally does not end with a semicolon, forcing users to place the semicolon after the expansion. The approach here is preferred as opposed to removing semicolons that appear after each invocation because complete statements that do not have a visible semicolon or braces confuse users and code formatters, since the macro invocation looks superficially like an expression.
PiperOrigin-RevId: 311327491
The documentation for IsDebuggerPresent says that one just should
include windows.h, as that one is an umbrella header that includes
the header that declares IsDebuggerPresent. In older Windows SDKs,
debugapi.h didn't exist and IsDebuggerPresent was declared in
winbase.h (also included by windows.h).
This should fix issue #2822 properly.
This reverts commit a9f6c1ed14.
That commit cannot fix the issue it sets out to fix.
The original issue, #2822, was that building with a toolset
targeting XP compatibility is missing the debugapi.h header -
as debugapi.h didn't exist in older Windows SDKs.
Commit a9f6c1ed14 misinterpreted
the Microsoft documentation about IsDebuggerPresent. The information
about which header to use, "debugapi.h (include Windows.h)" means
that the function declaration currently lives in debugapi.h, but
for compatibility, just include the Windows.h umbrella header.
In older Windows SDKs (e.g. the v6.0a SDK), IsDebuggerPresent
is declared in winbase.h, and debugapi.h doesn't exist at all in those
versions.
Including Windows.h with a different capitalization than the existing
include won't help finding headers that don't exist.
Including Windows.h with a capital W breaks cross compilation with mingw
toolchains, where the header always has been spelled with a lower case
W. When building on native windows, the file system is case insensitive
and the capitalization doesn't matter.
This fixes issue #2840.
Explicitly define copy constructors used in googletest tests
As of C++11, providing a user-declared copy assignment operator should
suppress the availability of an implicit default copy constructor.
Classes that provide (or delete) a copy assignment operator must provide
their own copy constructor if one is desired. This may be an explicit
default copy constructor if appropriate.
As googletest is a C++11 codebase, this change should be made without
qualification.
This addresses the -Wdeprecated-copy warnings issued by trunk clang:
While compiling googletest/test/googletest-death-test-test.cc:
In file included from .../googletest/test/googletest-death-test-test.cc:33:
.../googletest/include/gtest/gtest-death-test.h:196:8: error: definition of implicit copy constructor for 'ExitedWithCode' is deprecated because it has a user-declared copy assignment operator [-Werror,-Wdeprecated-copy]
void operator=(const ExitedWithCode& other);
^
.../googletest/test/googletest-death-test-test.cc:279:16: note: in implicit copy constructor for 'testing::ExitedWithCode' first required here
EXPECT_PRED1(pred0, status0);
^
While compiling googletest/test/googletest-param-test-test.cc:
.../googletest/test/googletest-param-test-test.cc:502:8: error: definition of implicit copy constructor for 'NonDefaultConstructAssignString' is deprecated because it has a user-declared copy assignment operator [-Werror,-Wdeprecated-copy]
void operator=(const NonDefaultConstructAssignString&);
^
.../googletest/test/googletest-param-test-test.cc:507:36: note: in implicit copy constructor for 'NonDefaultConstructAssignString' first required here
Combine(Values(0, 1), Values(NonDefaultConstructAssignString("A"),
This matches other changes made elsewhere in the googletest codebase,
such as 306f3754a7. Perhaps those previous changes did not consider
test code.
PiperOrigin-RevId: 307495126
googletest-param-test-test.cc:502:8: error:
definition of implicit copy constructor for
'NonDefaultConstructAssignString' is deprecated because it has a
user-declared copy assignment operator [-Werror,-Wdeprecated]
void operator=(const NonDefaultConstructAssignString&);
^
googletest-port-test.cc:97:11: error:
definition of implicit copy constructor for 'Base' is deprecated because
it has a user-declared destructor [-Werror,-Wdeprecated]
virtual ~Base() {}
^
None of these are strictly needed for correctness.
A large number of them (maybe all of them?) trigger `-Wdeprecated`
warnings on Clang trunk as soon as you try to use the implicitly
defaulted (but deprecated) copy constructor of a class that has
deleted its copy assignment operator.
By declaring a deleted copy assignment operator, the old code
also caused the move constructor and move assignment operator
to be non-declared. This means that the old code never got move
semantics -- "move-construction" would simply call the defaulted
(but deprecated) copy constructor instead. With the new code,
"move-construction" calls the defaulted move constructor, which
I believe is what we want to happen. So this is a runtime
performance optimization.
Unfortunately we can't yet physically remove the definitions
of these macros from gtest-port.h, because they are being used
by other code internally at Google (according to zhangxy988).
But no new uses should be added going forward.
This change updates testing::internal::IsAProtocolMessage to return true not
just for full proto messages but also for lite ones (i.e. those inheriting
directly from MessageLite).
PiperOrigin-RevId: 304286535
The extra tests check that the xml output is correct when a failure occurs before skipping, and that the right skip message is added to the file.
The json file had to be fixed because it's the same executable.
Add --gtest_fail_fast support to googletest.
- Analogous functionality to to golang -test.failfast and python --failfast
- Stops test execution upon first test failure.
- Also add support Bazel equivalent env var (TESTBRIDGE_TEST_RUNNER_FAIL_FAST)
PiperOrigin-RevId: 302488880
Google Test and Google Mock require matching versions to work,
so this requirement should be described in the pkgconfig files.
This change is derived from the one used for the Fedora gtest package.
Signed-off-by: Neal Gompa <ngompa13@gmail.com>
When building packaged shared libraries for use, having the version
set makes it so that the soname is set correctly for parallel installation.
This change is derived from the one used for the Fedora gtest package.
Signed-off-by: Neal Gompa <ngompa13@gmail.com>
Exposition of the problem:
> cat main.cpp
TEST(errnoTest, errnoTest)
{
ASSERT_EQ(errno, 0);
}
int main(int argc, char** argv)
{
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}
Compiled with gcc 10 like this:
> g++ -pthread -o runtest main.cpp -Wl,-Bstatic -lgtest -Wl,-Bdynamic
Before patch:
> ./runtest
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from errnoTest
[ RUN ] errnoTest.errnoTest
[ OK ] errnoTest.errnoTest (0 ms)
[----------] 1 test from errnoTest (0 ms total)
[----------] Global test environment tear-down
[==========] 1 test from 1 test suite ran. (0 ms total)
[ PASSED ] 1 test.
(output is colored, I run this inside an interactive terminal).
> ./runtest | cat
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from errnoTest
[ RUN ] errnoTest.errnoTest
main.cpp:5: Failure
Expected equality of these values:
(*__errno_location ())
Which is: 25
0
[ FAILED ] errnoTest.errnoTest (0 ms)
[----------] 1 test from errnoTest (0 ms total)
[----------] Global test environment tear-down
[==========] 1 test from 1 test suite ran. (0 ms total)
[ PASSED ] 0 tests.
[ FAILED ] 1 test, listed below:
[ FAILED ] errnoTest.errnoTest
1 FAILED TEST
(output is not colored, since IsTTY return false, because of the pipe,
however it also clobbered errno for the tests).
After the patch, both cases are working fine:
> ./runtest
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from errnoTest
[ RUN ] errnoTest.errnoTest
[ OK ] errnoTest.errnoTest (0 ms)
[----------] 1 test from errnoTest (0 ms total)
[----------] Global test environment tear-down
[==========] 1 test from 1 test suite ran. (0 ms total)
[ PASSED ] 1 test.
> ./runtest | cat
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from errnoTest
[ RUN ] errnoTest.errnoTest
[ OK ] errnoTest.errnoTest (0 ms)
[----------] 1 test from errnoTest (0 ms total)
[----------] Global test environment tear-down
[==========] 1 test from 1 test suite ran. (0 ms total)
[ PASSED ] 1 test.
Refactor function GetNextPrime so that the loop precondition is checked before
loop instead of during every loop run. Also by removing the loop condition,
it shows that the only exit from the loop is the return statement.
PiperOrigin-RevId: 293932783
Disable warning C4800 for Visual Studio 2019.
The compiler warning C4800 is disabled by default in Visual Studio 2019,
but it can be enabled on the command line. The only version of
Visual Studio that does not support warning C4800 is Visual Studio 2017.
PiperOrigin-RevId: 292624510
Deleted an orphaned duplicate file and exclude another that shouldn't be part of :gtest_all_test.
This showed up while trying to debug the presubmit failure for: https://github.com/google/googletest/pull/2683
PiperOrigin-RevId: 291398123
Add extra filtering so that the reported message differentiates between the case where INSTANTIATE_TEST_SUITE_P is missing vs. the case where TEST_P is missing.
PiperOrigin-RevId: 290114508
Add GTEST_ALLOW_UNINSTANTIATED_PARAMTERIZED_TEST to mark a paramaterized test as allowed to be un-instantiated.
This allows test suites, that are defined in libraries and, for other reasons, get linked in (which should probably be avoided, but isn't always possible) to be marked as allowed to go uninstantiated.
This can also be used to grandfather existing issues and expedite adoption of the checks with regards to new cases before they can be fixed.
PiperOrigin-RevId: 289581573
Removing GTEST_API from TrueWithString.
This type is only used in test code on one side of a DLL boundary so it is not
necessary.
PiperOrigin-RevId: 288927929
Add option (default to disabled) to make C++ type parameterized tests (TYPED_TEST_P) fail when they're not instantiated.
When an un-instantiated TYPED_TEST_P is found, a new test will be inserted that emits a suitable message. For now, that is just a notice, but the hope it to flip the bit to make it fail by default.
PiperOrigin-RevId: 286408038
This reverts commit 20b5b8ecc7.
Reason for revert: Breaks existing applications, such as ANGLE
(angleproject.org), requires adding an extra prefix that needs to be
typed for no reason (when testing from command line) and increases the
logs' sizes by a non-trivial amount due to the very large number of
tests ANGLE runs.
Original commit message:
Add a compile time check to ensure that the parameters to TEST_P and
INSTANTIATE_TEST_SUITE_P are not empty. Some compilers already fail
in that case and, even where it works, it's likely to result in
technically invalid code by virtue of creating reserved identifiers:
https://en.cppreference.com/w/cpp/language/identifiers
First, every project is perfectly capable of adding a prefix if they
want to support such a compiler. This change penalizes every
project.
Second, using a prefix such as `_p` also results in reserved
identifiers, so this change is not really solving the problem. For that
matter, instead of generating `gtest_##prefix##...`, you can generate
`gtest_x##prefix##...` to correctly fix the issue, including when empty
prefixes are used.
This reverts commit 4c25e2b87f.
Reason for revert: Reverting the commit that disallows empty prefixes.
Original commit message:
Remove a test case rendered obsolete by disallowing empty argument for INSTANTIATE_TEST_SUITE_P.
Remove the code that it was testing.
Empty arguments can be passed to macros per C99 and C++11 specs, which
can then be forwarded to other macros.
Visual Studio's compiler has a bug in the following situation:
#define A(x) #x
#define B(x, y) A(x)
B(, b)
In the above case, Visual Studio first expands x to nothing, then
complains that A is not invoked with the right amount of arguments.
However, x in A(x) is still one argument, even if it expands to no
preprocessing tokens. See also https://stackoverflow.com/a/7674214.
Detect when C++ parametric tests (TEST_P) are not instantiated.
When an un-instantiated TEST_P is found, a new test will be inserted that will emit a warning message.
This can be made to error with minor code edits.
In the future, that is intended to be the default.
PiperOrigin-RevId: 284901666
Change googletest to notice failures during SetUpTestSuite() and TearDownTestSuite().
Previously, errors that occurred during those functions were logged but otherwise ignored. After this change, such failures will cause the test to fail and a brief summary will be printed at the bottom of the test log.
See https://github.com/google/googletest/issues/2330.
PiperOrigin-RevId: 284033342
Make generating goldens work with Python 3
golden_file.write(output) fails with Python 3 with:
TypeError: a bytes-like object is required, not 'str'
PiperOrigin-RevId: 282316101
Use standard C++11 integer types in gtest-port.h.
Remove testing::internal::{Int,Uint}{32,64} in favor of types
guaranteed to be in <cstdint> since C++11.
Tests for built-in integer type coverage are switched from
{Int,Uint}64 to [unsigned] long long, which is guaranteed by
C++11 to exist and be at least 64-bit wide.
PiperOrigin-RevId: 281565263
We use "MemoryIsNotDeallocated" to aovid internal expected leak reported
in Windows _Crt report, like:
{
#ifdef _MSC_VER
MemoryIsNotDeallocated memory_is_not_deeallocated;
#endif
static ThreadIdToThreadLocals* map = new
ThreadIdToThreadLocals();
return map;
}
But int the above code, only "new ThreadIdToThreadLocals()" is
protected, if we invoke "insert()" function of the return value,
the memory allocated in "insert()" will be reported to _Crt report
also. This change try to fix this issue.
googletest 1.10.0 fails to compile on msvc version 19.00.23917
with one compilation error:
src\googletest\include\gtest\internal\gtest-internal.h(1188) : error C2039:
'FlatTupleBase<testing::internal::FlatTuple<bool,bool>,testing::internal::IndexSequence<0,1> >':
is not a member of 'testing::internal::FlatTuple<bool,bool>'
This PR fixes the compilation error by explicitly specifying the full type that Indices is
located in the base type.
Correctly deal with stringification, and forbid empty arguments where they could slip thought, in the type parameterized test API.
Note: even where empty args work, it's likely to result in technically invalid code by virtue of creating reserved identifiers:
https://en.cppreference.com/w/cpp/language/identifiers
PiperOrigin-RevId: 279330971
Clone+exec death test allocates a single page of stack to run chdir + exec on.
This is not enough when gtest is built with ASan and run on particular
hardware.
With ASan on x86_64, ExecDeathTestChildMain has frame size of 1728 bytes.
Call to chdir() in ExecDeathTestChildMain ends up in
_dl_runtime_resolve_xsavec, which attempts to save register state on the stack;
according to cpuid(0xd) XSAVE register save area size is 2568 on my machine.
This results in something like this in all death tests:
Result: died but not with expected error.
...
[ DEATH ] AddressSanitizer:DEADLYSIGNAL
[ DEATH ] =================================================================
[ DEATH ] ==178637==ERROR: AddressSanitizer: stack-overflow on address ...
PiperOrigin-RevId: 278709790
Remove the threads link library variable references from the pkg-config
Cflags: field, removing -lpthread(s) from the compile flags.
"-l*" linker flags should only be part of the Libs: section and should
not be part of the Cflags: section in pkg-config files.
This was first suggested in
https://github.com/google/googletest/pull/2006 and further discussed in
https://github.com/google/googletest/pull/2483 .
Add a matcher `testing::ReturnRoundRobin` which, on each call, returns the next element in the sequence, restarting at the beginning once it has reached the end.
PiperOrigin-RevId: 276312136
Split the scoped trace examples into two snippets.
This doesn't have an effect in the github markdown renderer, but in some other renderers/templates, this leads them to be independently copy-pastable. In particular, the markdown rendering that Google uses internally has a copy button for each code snippet, which, before this change, would copy both lines. Bad copy button, no cookie! After this change, there will be two such buttons, one per line, and clicking a copy button will copy only the one snippet it is next to, and not the other. This is desirable because nobody will ever want to copy both lines, only one or the other.
PiperOrigin-RevId: 276079009
Remove bool_constant in favor of std::integral_constant<bool, ...>;
The one non-trivial use of bool_constant has been changed to have significantly
fewer template specializations.
PiperOrigin-RevId: 275842490
Closes#2208
Previously, skip messages were invisible, so debugging skips was hard.
Now we have this:
```
$ ./googletest/gtest_skip_test
Running main() from /home/lesha/github/snarkmaster/googletest/googletest/src/gtest_main.cc
[==========] Running 3 tests from 2 test suites.
[----------] Global test environment set-up.
[----------] 1 test from SkipTest
[ RUN ] SkipTest.DoesSkip
/home/lesha/github/snarkmaster/googletest/googletest/test/gtest_skip_test.cc:38: Skipped
skipping single test
[ SKIPPED ] SkipTest.DoesSkip (0 ms)
[----------] 1 test from SkipTest (1 ms total)
...
```
Remove a test case rendered obsolete by disallowing empty argument for INSTANTIATE_TEST_SUITE_P.
Remove the code that it was testing.
PiperOrigin-RevId: 275040108
* Added support for ESP8266
* Removed previous Arduino defines in favor
of GTEST_OS_* syntax
* Improved PlatformIO library file to be more
stable when consumed in client applications.
Mark more functions with "override" keyword, just like
it was done in commit 2460f97152.
This should prevent compiler from complaining while compiling both
user code, and the googletest code itself with the -Wsuggest-override
option turned on; with the exception of:
* calls to new MOCK_METHOD() in test/gmock-function-mocker_test.cc
* calls to old MOCK_METHODx()/MOCK_CONST_METHODx() in other
unit test files.
Closes#2493
- Fix a bug in dealing with paramaterized tests where the name is it self a macro expansion.
- Add a compile time check to ensure that the parameters to TEST_P and INSTANTIATE_TEST_SUITE_P are not empty. The above fix causes some compilers to fail in that case and even where it works, it's likely to result in technically invalid code by virtue of creating reserved identifiers:
https://en.cppreference.com/w/cpp/language/identifiers
PiperOrigin-RevId: 274047249
Add a compile time check to ensure that the parameters to TEST_P and INSTANTIATE_TEST_SUITE_P are not empty. Some compilers already fail in that case and, even where it works, it's likely to result in technically invalid code by virtue of creating reserved identifiers:
https://en.cppreference.com/w/cpp/language/identifiers
PiperOrigin-RevId: 273832263
The change makes implicit assumptions on the layout of the install
tree, which is going to break in many ways.
The correct solution is to use the `PKG_CONFIG_SYSROOT_DIR` variable
to inject the cross-compiled sysroot into `-I` and `-L` paths.
Add a compile time check to ensure that the parameters to TEST and TEST_F are not empty
Some compilers may already fail in that case and even where it works, it's likely to result in technically invalid code by virtue of creating reserved identifiers:
https://en.cppreference.com/w/cpp/language/identifiers
PiperOrigin-RevId: 272543242
Use a more portable path for Android to write temp files to.
/sdcard is *not* guaranteed to be available, but /data/local/tmp is.
In some emulated situations, /sdcard may not be mounted, may not be R/W, or
mounting may be delayed until *after* the test process begins.
This is fairly common location to use. See e.g.:
https://reviews.llvm.org/D9569
PiperOrigin-RevId: 270909282
This macro didn't work when an array was passed to a function by pointer,
in which case the information about its size was lost.
Better alternatives are:
* std::extent<T>::value (compile-time)
* std::array<T, N>::size() (compile-time)
* std::distance(std::begin(array), std::end(array)) (run-time)
Merge 3bdefdb473d304803d2a38e2a2cd5cdc1827c3bd into fb49e6c164Closes#2407
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/googletest/pull/2407 from kuzkry:StaticAssertTypeEq 3bdefdb473d304803d2a38e2a2cd5cdc1827c3bd
PiperOrigin-RevId: 269255328
Merge 4c9ef099b29d2c840c04643cd9662fd7be712f7b into 565f1b8482Closes#2403
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/googletest/pull/2403 from IYP-Programer-Yeah:remove-compile-assert-type-equal 4c9ef099b29d2c840c04643cd9662fd7be712f7b
PiperOrigin-RevId: 268681883
Extend gtest-port and stubs for ESP_PLATFORM
ESP_PLATFORM is the macro used to indicate compilation for the ESP32
using the esp-idf. This isn't a fully posix compatible system so
various features of google test need to be stubbed out in order for
it to work. It's oddly similar to the GTEST_OS_WINDOWS_PHONE setup.
PiperOrigin-RevId: 267471968
Merge 7f4f58da20e1066a888d3e4bcbef541db798a605 into 90a443f9c2Closes#2395
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/googletest/pull/2395 from kuzkry:custom-type-traits-remove_reference 7f4f58da20e1066a888d3e4bcbef541db798a605
PiperOrigin-RevId: 266189044
Merge b8ca465e73ac0954a0c9eec2a84bdd8913d5763b into 90a443f9c2Closes#2396
COPYBARA_INTEGRATE_REVIEW=https://github.com/google/googletest/pull/2396 from kuzkry:custom-type-traits-true/false_type-and-bool_constant b8ca465e73ac0954a0c9eec2a84bdd8913d5763b
PiperOrigin-RevId: 265064856
Adds ISO8601 timestamps to XML output and RFC3339 timestamps to JSON output.
Adds timestamps to testsuites, testsuite and testcases structured JSON/XML output for better reporting how/where time is spent on tests.
PiperOrigin-RevId: 260039817
[Fuchsia] Update exception APIs used by death test.
Migrates to the new channel-based exception APIs as the
port APIs are deprecated and will be removed.
PiperOrigin-RevId: 258175830
Some Windows users builds were broken after a0d60be. This change
addresses the lingering -Wsign-conversion issues with those platforms
by adding some missing `static_cast` calls as needed.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
This is useful to let a subsystem generate test names based on parameterized tests
without exposing them as such to the user.
Signed-off-by: Knut Omang <knut.omang@oracle.com>
Add GTEST_FAIL_AT, an equivalent to ADD_FAILURE_AT but that
spawns a fatal failure rather than a non-fatal, eg. the equivalent
of an ASSERT* failure rather than an EXPECT* failure.
PiperOrigin-RevId: 244746609
Migrate ZX_WAIT_ASYNC_REPEATING to ZX_WAIT_ASYNC_ONCE
ZX_WAIT_ASYNC_REPEATING is deprecated so convert code to use
ZX_WAIT_ASYNC_ONCE instead.
PiperOrigin-RevId: 243707147
Cast some values as their unsigned equivalents or `size_t` to match the
parameter type used for the template object under test. Also, provide
UInt32 equivalent delegate methods for some callers (with
int-equivalents for backwards compatibility).
This closes#2146.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
[fdio] Improve fdio_pipe_half signature, step 3.
The return value on fdio_pipe_half conflated two things: the error code
on failure (as a zx_status_t) or a file descriptor on success. This
technically worked, because they're both ints, the error code was always
negative, and the file descriptor always positive. However, the stated
return type of zx_status_t was misleading. This changes the signature
such that it always returns an actual zx_status_t, and the file
descriptor is returned through a pointer argument.
Also remove the last argument, since it was always given the same value.
This needs to be done as a soft transition because it's called from the
Dart runtime, from googletest, and from Crashpad, and Crashpad and
Chromium both depend on googletest on Fuchsia. The steps are as follows:
1) Add fdio_pipe_half2.
2) Update Dart to use fdio_pipe_half2.
3) Update googletest to use fdio_pipe_half2.
4) Roll updated googletest into Chronium.
5) Update Crashpad to use fdio_pipe_half2 and roll updated googletest into it.
6) Update fdio_pipe_half to match fdio_pipe_half2.
7) Update Dart to use fdio_pipe_half again.
8) Update googletest to use fdio_pipe_half again.
9) Roll updated googletest into Chronium.
10) Update Crashpad to use fdio_pipe_half again and roll updated googletest into it.
11) Remove fdio_pipe_half2.
This is step 3.
PiperOrigin-RevId: 241957137
Add `-frtti` to the compiler with the base flags case so that RTTI is
enabled by default with clang. Add its inverse analog,
`cxx_no_rtti_flags` in order to test the case with RTTI off, similar to
gcc.
This reduces the amount of testing/support overhead needed in the
non-RTTI case with clang, as the tests currently fail when these two
features are off with version 1.8.1. This something I used in when
investigating test failures on FreeBSD, as the tests that rely on
RTTI were failing with googletest 1.8.1 on the OS platform.
More investigation is being done to determine how this should be fixed
on FreeBSD 11.2-RELEASE with ports, as the package doesn't currently
compile the tests, and when enabled (based on my WIP diff), the tests
fail in similar ways.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
Add HWASan annotations.
These mirror existing ASan annotations.
HWASan uses memory (address) tagging to detect memory errors:
https://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html
It inserts a random tag in the MSB of heap and stack allocation addresses. This tag dominates pointer comparison in StackGrowsDown(), making the result non-deterministic, and entirely unrelated to the actual stack growth direction. The function attribute disables this behavior.
The annotations in gtest-printers are there because the printers are used to basically dump memory. The sanitizers may have ideas why this memory should not be accessed, and that is counter productive. In particular, the test may access only part of an array, but in case of a test failure gtest will dump the entire array which may contain uninitialized bytes - that's what SANITIZE_MEMORY annotation is for. There are similar reasons for ADDRESS and THREAD annotations. HWADDRESS in its current implementation can not cause issues there, I believe, but it falls under the same umbrella of tools whose checking should not apply to test printers because it is not the code under test.
PiperOrigin-RevId: 241379822
Remove support for "global" ::string and ::wstring types.
This support existed for legacy codebases that existed from before namespaces
where a thing. It is no longer necessary.
PiperOrigin-RevId: 241335738
gtest prior to this change would completely ignore `GTEST_SKIP()` if
called in `Environment::SetUp()`, instead of bailing out early, unlike
`Test::SetUp()`, which would cause the tests themselves to be skipped.
The only way (prior to this change) to skip the tests would be to
trigger a fatal error via `GTEST_FAIL()`.
Desirable behavior, in this case, when dealing with
`Environment::SetUp()` is to check for prerequisites on a system
(example, kernel supports a particular featureset, e.g., capsicum), and
skip the tests. The alternatives prior to this change would be
undesirable:
- Failing sends the wrong message to the test user, as the result of the
tests is indeterminate, not failed.
- Having to add per-test class abstractions that override `SetUp()` to
test for the capsicum feature set, then skip all of the tests in their
respective SetUp fixtures, would be a lot of human and computational
work; checking for the feature would need to be done for all of the
tests, instead of once for all of the tests.
For those reasons, making `Environment::SetUp()` handle `GTEST_SKIP()`,
by not executing the testcases, is the most desirable solution.
In order to properly diagnose what happened when running the tests if
they are skipped, print out the diagnostics in an ad hoc manner.
Update the documentation to note this change and integrate a new test,
gtest_skip_in_environment_setup_test, into the test suite.
This change addresses #2189.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
Fix emission of -Wzero-as-null-pointer-constant when comparing integers.
The following code fails to compile:
#pragma clang diagnostic error "-Wzero-as-null-pointer-constant"
void foo() {
EXPECT_EQ(0, 0);
}
This happens because gtest checks the first argument to EXPECT_EQ and
ASSERT_EQ is a null pointer constant. The magic it does to do this causes the
warning to be emitted.
This patch removes that check. It replaces the explicit check with a Compare
overload that can only be selected when 0 or nullptr is passed on the LHS
with a pointer on the right.
This patch does not suppress -Wzero-as-null-pointer-constant when users
are actually using it as NULL.
PiperOrigin-RevId: 236654634
Let embedders customize GTEST_INTERNAL_DEPRECATED().
GTEST_INTERNAL_DEPRECATED is currently used to nudge googletest users to migrate off old TEST_CASE macros to the new TEST_SUITE macros. This move is non-trivial for Chromium (see https://crbug.com/925652), and might be difficult for other big projects with many dependencies.
This CL facilitates moving off of deprecated APIs by making it possible for an embedder to define GTEST_INTERNAL_DEPRECATED() in gtest/internal/custom/gtest-port.h. Example usage:
1) #define GTEST_INTERNAL_DEPRECATED() to nothing, to disable deprecation warnings while migrating off googletest's deprecated APIs. This can be preferable to having to disable all deprecation warnings (-Wno-error=deprecated or -Wno-deprecated-declarations).
2) #define GTEST_INTERNAL_DEPRECATED() for an unsupported compiler.
PiperOrigin-RevId: 236171043
Due to some caveats in the FreeBSD build system and the fact that the
source file is used to compile 2 different death tests with different
flags, I needed (as a shortterm workaround) to copy the test to 2
differently named files.
While this works for compiling the test, as I discovered, this doesn't
work with running `CxxExceptionDeathTest.PrintsMessageForStdException`,
as the testcase hardcodes `googletest-death-test_ex_test.cc`. Use `__FILE__`
when looking for failures, as opposed to looking for the hardcoded name
as it can vary depending on how the test was built.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
Update gtest-death-test to use new Fuchsia API
Fuchsia has renamed this API and removed the need for several parameters. We now use the newer, simpler API.
PiperOrigin-RevId: 234617715
clang++ compilation when `-Wsign-conversion` is currently broken and the
issues within the code are varied and widespread. For the time being
ignore `-Wsign-conversion` issues, even though some of them are valid
and bleed over into issues that would be found with
`-Wtautological-compare`, et al.
Signed-off-by: Enji Cooper <yaneurabeya@gmail.com>
