llvm-project/clang-tools-extra/test/CMakeLists.txt

84 lines
2.1 KiB
CMake
Raw Normal View History

# Test runner infrastructure for Clang-based tools. This configures the Clang
# test trees for use by Lit, and delegates to LLVM's lit test handlers.
#
# Note that currently we don't support stand-alone builds of Clang, you must
# be building Clang from within a combined LLVM+Clang checkout..
set(CLANG_TOOLS_SOURCE_DIR "${CMAKE_CURRENT_SOURCE_DIR}/..")
set(CLANG_TOOLS_BINARY_DIR "${CMAKE_CURRENT_BINARY_DIR}/..")
if (CMAKE_CFG_INTDIR STREQUAL ".")
set(LLVM_BUILD_MODE ".")
else ()
set(LLVM_BUILD_MODE "%(build_mode)s")
endif ()
string(REPLACE ${CMAKE_CFG_INTDIR} ${LLVM_BUILD_MODE} CLANG_TOOLS_DIR ${LLVM_RUNTIME_OUTPUT_INTDIR})
llvm_canonicalize_cmake_booleans(
CLANG_ENABLE_STATIC_ANALYZER)
configure_lit_site_cfg(
${CMAKE_CURRENT_SOURCE_DIR}/lit.site.cfg.in
${CMAKE_CURRENT_BINARY_DIR}/lit.site.cfg
)
configure_lit_site_cfg(
${CMAKE_CURRENT_SOURCE_DIR}/Unit/lit.site.cfg.in
${CMAKE_CURRENT_BINARY_DIR}/Unit/lit.site.cfg
)
Switch from autogenerating tests to using the preprocessor. NOTE: You may need to run 'make clean' or 'ninja -t clean' etc!!! This is due to really nasty bug/interactions between CMake/configure/make/Ninja/LIT... This commit tries to back out the support for generating test cases as part of the build system due to the issues I brought up in post-commit review: 1) It adds a *lot* of complexity and fragility to the build system. See the number of commits required to try to get all the bots happy. 2) It isn't really necessary -- we can already run scripts to generate things with the RUN lines of a test. 3) It makes the tests somewhat harder to debug as they cross between more domains. 4) In almost all cases it isn't really needed or it can be done directly using the preprocessor. I should have been more proactive reviewing this, and I'm really sorry about the churn here. =/ To help keep track of what commits are going where, this backs out most of the non-test-changes from these revisions: r176397 r176373 r176293 r176184 r175744 r175624 r175545 r175544 There were several trivial or cleanup changes to the lit files or other files. Some of these looked ok, but I didn't try to tease them apart... Edwin, if you know what to look for, please carry on with the cleanups there, and sorry for hosing stuff here but I'm not much of a Python person, and so I was erring on the side of cautiously backing out the change. I've tried to preserve the test changes everywhere I could, but review is appreciated here in case I missed some. I then re-wrote the tests to use the preprocessor rather than python to expand to the various bits of code. The nicest part of this is that now all the files are just C++ code. They edit and behave like C++ code, etc. RUN lines with different -D flags are used to run the same test over multiple different configurations, and includes bracketed in special defines are used to flesh out a collection of standard interface stubs to test interactions between pieces. These probably aren't perfect yet, but I think its an improvement (at least in terms of build system complexity) and will hopefully be a useful demonstration of the technique I prefer for these types of tests. llvm-svn: 176627
2013-03-07 18:09:47 +08:00
option(CLANG_TOOLS_TEST_USE_VG "Run Clang tools' tests under Valgrind" OFF)
if(CLANG_TOOLS_TEST_USE_VG)
set(CLANG_TOOLS_TEST_EXTRA_ARGS ${CLANG_TEST_EXTRA_ARGS} "--vg")
endif()
set(CLANG_TOOLS_TEST_DEPS
# For the clang-apply-replacements test that uses clang-rename.
clang-rename
Switch from autogenerating tests to using the preprocessor. NOTE: You may need to run 'make clean' or 'ninja -t clean' etc!!! This is due to really nasty bug/interactions between CMake/configure/make/Ninja/LIT... This commit tries to back out the support for generating test cases as part of the build system due to the issues I brought up in post-commit review: 1) It adds a *lot* of complexity and fragility to the build system. See the number of commits required to try to get all the bots happy. 2) It isn't really necessary -- we can already run scripts to generate things with the RUN lines of a test. 3) It makes the tests somewhat harder to debug as they cross between more domains. 4) In almost all cases it isn't really needed or it can be done directly using the preprocessor. I should have been more proactive reviewing this, and I'm really sorry about the churn here. =/ To help keep track of what commits are going where, this backs out most of the non-test-changes from these revisions: r176397 r176373 r176293 r176184 r175744 r175624 r175545 r175544 There were several trivial or cleanup changes to the lit files or other files. Some of these looked ok, but I didn't try to tease them apart... Edwin, if you know what to look for, please carry on with the cleanups there, and sorry for hosing stuff here but I'm not much of a Python person, and so I was erring on the side of cautiously backing out the change. I've tried to preserve the test changes everywhere I could, but review is appreciated here in case I missed some. I then re-wrote the tests to use the preprocessor rather than python to expand to the various bits of code. The nicest part of this is that now all the files are just C++ code. They edit and behave like C++ code, etc. RUN lines with different -D flags are used to run the same test over multiple different configurations, and includes bracketed in special defines are used to flesh out a collection of standard interface stubs to test interactions between pieces. These probably aren't perfect yet, but I think its an improvement (at least in terms of build system complexity) and will hopefully be a useful demonstration of the technique I prefer for these types of tests. llvm-svn: 176627
2013-03-07 18:09:47 +08:00
# Individual tools we test.
clang-apply-replacements
clang-change-namespace
clangd
clang-include-fixer
clang-move
clang-query
clang-reorder-fields
find-all-symbols
modularize
pp-trace
# Unit tests
ExtraToolsUnitTests
)
if(CLANG_ENABLE_STATIC_ANALYZER)
list(APPEND CLANG_TOOLS_TEST_DEPS
# For the clang-tidy libclang integration test.
c-index-test
# clang-tidy tests require it.
clang-headers
clang-tidy
)
endif()
set(llvm_utils
FileCheck count not
)
foreach(t ${llvm_utils})
if(TARGET ${t})
list(APPEND CLANG_TOOLS_TEST_DEPS ${t})
endif()
endforeach()
Switch from autogenerating tests to using the preprocessor. NOTE: You may need to run 'make clean' or 'ninja -t clean' etc!!! This is due to really nasty bug/interactions between CMake/configure/make/Ninja/LIT... This commit tries to back out the support for generating test cases as part of the build system due to the issues I brought up in post-commit review: 1) It adds a *lot* of complexity and fragility to the build system. See the number of commits required to try to get all the bots happy. 2) It isn't really necessary -- we can already run scripts to generate things with the RUN lines of a test. 3) It makes the tests somewhat harder to debug as they cross between more domains. 4) In almost all cases it isn't really needed or it can be done directly using the preprocessor. I should have been more proactive reviewing this, and I'm really sorry about the churn here. =/ To help keep track of what commits are going where, this backs out most of the non-test-changes from these revisions: r176397 r176373 r176293 r176184 r175744 r175624 r175545 r175544 There were several trivial or cleanup changes to the lit files or other files. Some of these looked ok, but I didn't try to tease them apart... Edwin, if you know what to look for, please carry on with the cleanups there, and sorry for hosing stuff here but I'm not much of a Python person, and so I was erring on the side of cautiously backing out the change. I've tried to preserve the test changes everywhere I could, but review is appreciated here in case I missed some. I then re-wrote the tests to use the preprocessor rather than python to expand to the various bits of code. The nicest part of this is that now all the files are just C++ code. They edit and behave like C++ code, etc. RUN lines with different -D flags are used to run the same test over multiple different configurations, and includes bracketed in special defines are used to flesh out a collection of standard interface stubs to test interactions between pieces. These probably aren't perfect yet, but I think its an improvement (at least in terms of build system complexity) and will hopefully be a useful demonstration of the technique I prefer for these types of tests. llvm-svn: 176627
2013-03-07 18:09:47 +08:00
add_lit_testsuite(check-clang-tools "Running the Clang extra tools' regression tests"
${CMAKE_CURRENT_BINARY_DIR}
DEPENDS ${CLANG_TOOLS_TEST_DEPS}
ARGS ${CLANG_TOOLS_TEST_EXTRA_ARGS}
)
Switch from autogenerating tests to using the preprocessor. NOTE: You may need to run 'make clean' or 'ninja -t clean' etc!!! This is due to really nasty bug/interactions between CMake/configure/make/Ninja/LIT... This commit tries to back out the support for generating test cases as part of the build system due to the issues I brought up in post-commit review: 1) It adds a *lot* of complexity and fragility to the build system. See the number of commits required to try to get all the bots happy. 2) It isn't really necessary -- we can already run scripts to generate things with the RUN lines of a test. 3) It makes the tests somewhat harder to debug as they cross between more domains. 4) In almost all cases it isn't really needed or it can be done directly using the preprocessor. I should have been more proactive reviewing this, and I'm really sorry about the churn here. =/ To help keep track of what commits are going where, this backs out most of the non-test-changes from these revisions: r176397 r176373 r176293 r176184 r175744 r175624 r175545 r175544 There were several trivial or cleanup changes to the lit files or other files. Some of these looked ok, but I didn't try to tease them apart... Edwin, if you know what to look for, please carry on with the cleanups there, and sorry for hosing stuff here but I'm not much of a Python person, and so I was erring on the side of cautiously backing out the change. I've tried to preserve the test changes everywhere I could, but review is appreciated here in case I missed some. I then re-wrote the tests to use the preprocessor rather than python to expand to the various bits of code. The nicest part of this is that now all the files are just C++ code. They edit and behave like C++ code, etc. RUN lines with different -D flags are used to run the same test over multiple different configurations, and includes bracketed in special defines are used to flesh out a collection of standard interface stubs to test interactions between pieces. These probably aren't perfect yet, but I think its an improvement (at least in terms of build system complexity) and will hopefully be a useful demonstration of the technique I prefer for these types of tests. llvm-svn: 176627
2013-03-07 18:09:47 +08:00
set_target_properties(check-clang-tools PROPERTIES FOLDER "Clang extra tools' tests")