[clang-scan-deps] Dependency directives source minimizer:

single quotes are not digit separators after a valid character literal prefix

The single quote character can act as a c++ digit separator.
However, the minimizer shouldn't treat it as such when it's actually following
a valid character literal prefix, like L, U, u, or u8.

Differential Revision: https://reviews.llvm.org/D64525

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@365700 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Lex/DependencyDirectivesSourceMinimizer.cpp

@@ -262,7 +262,14 @@ static bool isQuoteCppDigitSeparator(const char *const Start,
   if (Start == Cur)
     return false;
   // The previous character must be a valid PP number character.
-  if (!isPreprocessingNumberBody(*(Cur - 1)))
+  // Make sure that the L, u, U, u8 prefixes don't get marked as a
+  // separator though.
+  char Prev = *(Cur - 1);
+  if (Prev == 'L' || Prev == 'U' || Prev == 'u')
+    return false;
+  if (Prev == '8' && (Cur - 1 != Start) && *(Cur - 2) == 'u')
+    return false;
+  if (!isPreprocessingNumberBody(Prev))
     return false;
   // The next character should be a valid identifier body character.
   return (Cur + 1) < End && isIdentifierBody(*(Cur + 1));

unittests/Lex/DependencyDirectivesSourceMinimizerTest.cpp

@@ -507,4 +507,41 @@ int c = 12 ' ';
   EXPECT_STREQ("#include <bob>\n#include <foo>\n", Out.data());
 }
 
+TEST(MinimizeSourceToDependencyDirectivesTest, CharacterLiteralPrefixL) {
+  SmallVector<char, 128> Out;
+
+  StringRef Source = R"(L'P'
+#if DEBUG
+// '
+#endif
+#include <test.h>
+)";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#include <test.h>\n", Out.data());
+}
+
+TEST(MinimizeSourceToDependencyDirectivesTest, CharacterLiteralPrefixU) {
+  SmallVector<char, 128> Out;
+
+  StringRef Source = R"(int x = U'P';
+#include <test.h>
+// '
+)";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#include <test.h>\n", Out.data());
+}
+
+TEST(MinimizeSourceToDependencyDirectivesTest, CharacterLiteralPrefixu) {
+  SmallVector<char, 128> Out;
+
+  StringRef Source = R"(int x = u'b';
+int y = u8'a';
+int z = 128'78;
+#include <test.h>
+// '
+)";
+  ASSERT_FALSE(minimizeSourceToDependencyDirectives(Source, Out));
+  EXPECT_STREQ("#include <test.h>\n", Out.data());
+}
+
 } // end anonymous namespace