[clang-scan-deps] add skip excluded conditional preprocessor block preprocessing optimization

This commit adds an optimization to clang-scan-deps and clang's preprocessor that skips excluded preprocessor
blocks by bumping the lexer pointer, and not lexing the tokens until reaching appropriate #else/#endif directive.
The skip positions and lexer offsets are computed when the file is minimized, directly from the minimized tokens.

On an 18-core iMacPro with macOS Catalina Beta I got 10-15% speed-up from this optimization when running clang-scan-deps on
the compilation database for a recent LLVM and Clang (3511 files).

Differential Revision: https://reviews.llvm.org/D67127

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@371656 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 42 insertions, 0 deletions

diff --git a/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp b/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
index 8770050c86..530519573a 100644
--- a/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
+++ b/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
@@ -617,4 +617,46 @@ ort \
             minimize_source_to_dependency_directives::cxx_module_decl);
 }
 
+TEST(MinimizeSourceToDependencyDirectivesTest, SkippedPPRangesBasic) {
+  SmallString<128> Out;
+  SmallVector<Token, 32> Toks;
+  StringRef Source = "#ifndef GUARD\n"
+                     "#define GUARD\n"
+                     "void foo();\n"
+                     "#endif\n";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out, Toks));
+  SmallVector<SkippedRange, 4> Ranges;
+  ASSERT_FALSE(computeSkippedRanges(Toks, Ranges));
+  EXPECT_EQ(Ranges.size(), 1u);
+  EXPECT_EQ(Ranges[0].Offset, 0);
+  EXPECT_EQ(Ranges[0].Length, (int)Out.find("#endif"));
+}
+
+TEST(MinimizeSourceToDependencyDirectivesTest, SkippedPPRangesNested) {
+  SmallString<128> Out;
+  SmallVector<Token, 32> Toks;
+  StringRef Source = "#ifndef GUARD\n"
+                     "#define GUARD\n"
+                     "#if FOO\n"
+                     "#include hello\n"
+                     "#elif BAR\n"
+                     "#include bye\n"
+                     "#endif\n"
+                     "#else\n"
+                     "#include nothing\n"
+                     "#endif\n";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out, Toks));
+  SmallVector<SkippedRange, 4> Ranges;
+  ASSERT_FALSE(computeSkippedRanges(Toks, Ranges));
+  EXPECT_EQ(Ranges.size(), 4u);
+  EXPECT_EQ(Ranges[0].Offset, (int)Out.find("#if FOO"));
+  EXPECT_EQ(Ranges[0].Offset + Ranges[0].Length, (int)Out.find("#elif"));
+  EXPECT_EQ(Ranges[1].Offset, (int)Out.find("#elif BAR"));
+  EXPECT_EQ(Ranges[1].Offset + Ranges[1].Length, (int)Out.find("#endif"));
+  EXPECT_EQ(Ranges[2].Offset, 0);
+  EXPECT_EQ(Ranges[2].Length, (int)Out.find("#else"));
+  EXPECT_EQ(Ranges[3].Offset, (int)Out.find("#else"));
+  EXPECT_EQ(Ranges[3].Offset + Ranges[3].Length, (int)Out.rfind("#endif"));
+}
+
 } // end anonymous namespace