[clang-scan-deps] Improve string/character literal skipping

The existing string/character literal skipping code in the
dependency directives source minimizer has two issues:

- It doesn't stop the scanning when a newline is reached before the terminating character,
unlike the lexer which considers the token to be done (even if it's invalid) at the end of the line.

- It doesn't support whitespace between '\' and the newline when looking if the '\' is used as a line continuation character.

This commit fixes both issues.

Differential Revision: https://reviews.llvm.org/D68436

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@374127 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 44 insertions, 0 deletions

diff --git a/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp b/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
index 5eb7d256a3..ed44cd86b3 100644
--- a/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
+++ b/unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp
@@ -594,6 +594,50 @@ TEST(MinimizeSourceToDependencyDirectivesTest, PragmaOnce) {
   EXPECT_STREQ("#pragma once\n#include <test.h>\n", Out.data());
 }
 
+TEST(MinimizeSourceToDependencyDirectivesTest,
+     SkipLineStringCharLiteralsUntilNewline) {
+  SmallVector<char, 128> Out;
+
+  StringRef Source = R"(#if NEVER_ENABLED
+    #define why(fmt, ...) #error don't try me
+    #endif
+
+    void foo();
+)";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ(
+      "#if NEVER_ENABLED\n#define why(fmt,...) #error don't try me\n#endif\n",
+      Out.data());
+
+  Source = R"(#if NEVER_ENABLED
+      #define why(fmt, ...) "quote dropped
+      #endif
+
+      void foo();
+  )";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ(
+      "#if NEVER_ENABLED\n#define why(fmt,...) \"quote dropped\n#endif\n",
+      Out.data());
+}
+
+TEST(MinimizeSourceToDependencyDirectivesTest,
+     SupportWhitespaceBeforeLineContinuationInStringSkipping) {
+  SmallVector<char, 128> Out;
+
+  StringRef Source = "#define X '\\ \t\nx'\nvoid foo() {}";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#define X '\\ \t\nx'\n", Out.data());
+
+  Source = "#define X \"\\ \r\nx\"\nvoid foo() {}";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#define X \"\\ \r\nx\"\n", Out.data());
+
+  Source = "#define X \"\\ \r\nx\n#include <x>\n";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#define X \"\\ \r\nx\n#include <x>\n", Out.data());
+}
+
 TEST(MinimizeSourceToDependencyDirectivesTest, CxxModules) {
   SmallVector<char, 128> Out;
   SmallVector<Token, 4> Tokens;