[Syntax] Merge overlapping top-level macros in TokenBuffer

[sammccall]

Summary

Our previous definition of "top-level" was too informal, and didn't
allow for overlapping macros that each directly produce expanded tokens.
See D77507 for previous discussion.

Fixes http://bugs.llvm.org/show_bug.cgi?id=45428

[kadircet]

LGTM, thanks!

clang/lib/Tooling/Syntax/Tokens.cpp

452

instead of saying A and B maybe say something like, a the last token for a top-level macro expansion must be inside a file and invert the following condition:

if(!Range.getEnd().isFileID()) return;

462

maybe put As and Bs in parentheses, i.e:

// If the macro invocation (B) starts in a macro (A) but ends in a file, we'll
    // create a merged mapping (for A & B) by overwriting the endpoint for parent's (A's)
    // startpoint.

[sammccall]

clang/lib/Tooling/Syntax/Tokens.cpp

462

Done, except for "parent" - the point here is there isn't really a parent/child relationship here: the arg list isn't part of the A expansion in any sense.

clang/lib/Tooling/Syntax/Tokens.cpp

public:
   /// This ensures that uses of the preprocessor after TokenCollector::consume()
   /// is called do not access the (possibly invalid) collector instance.
   void disable() { Collector = nullptr; }
 
   void MacroExpands(const clang::Token &MacroNameTok, const MacroDefinition &MD,
                     SourceRange Range, const MacroArgs *Args) override {
     if (!Collector)
       return;
-    // Only record top-level expansions, not those where:
+    const auto &SM = Collector->PP.getSourceManager();
+    // Only record top-level expansions that directly produce expanded tokens.
+    // This excludes those where:
     //   - the macro use is inside a macro body,
     //   - the macro appears in an argument to another macro.
-    if (!MacroNameTok.getLocation().isFileID() ||
-        (LastExpansionEnd.isValid() &&
-         Collector->PP.getSourceManager().isBeforeInTranslationUnit(
-             Range.getBegin(), LastExpansionEnd)))
+    // However macro expansion isn't really a tree, it's token rewrite rules,
+    // so there are other cases, e.g.
+    //   #define B(X) X
+    //   #define A 1 + B
+    //   A(2)
+    // Both A and B produce expanded tokens, though the macro name 'B' comes
+    // from an expansion. The best we can do is merge the mappings for both.
+
+    // The *last* token of any top-level macro expansion must be in a file.
+    // (In the example above, see the closing paren of the expansion of B).
+    if (!Range.getEnd().isFileID())
       return;
+    // If there's a current expansion that encloses this one, this one can't be
+    // top-level.
+    if (LastExpansionEnd.isValid() &&
+        !SM.isBeforeInTranslationUnit(LastExpansionEnd, Range.getEnd()))
+      return;
+
+    // If the macro invocation (B) starts in a macro (A) but ends in a file,
+    // we'll create a merged mapping for A + B by overwriting the endpoint for
+    // A's startpoint.
+    if (!Range.getBegin().isFileID()) {
+      Range.setBegin(SM.getExpansionLoc(Range.getBegin()));
+      assert(Collector->Expansions.count(Range.getBegin().getRawEncoding()) &&
+             "Overlapping macros should have same expansion location");
+    }
+
     Collector->Expansions[Range.getBegin().getRawEncoding()] = Range.getEnd();
     LastExpansionEnd = Range.getEnd();
   }
   // FIXME: handle directives like #pragma, #include, etc.
 private:
   TokenCollector *Collector;
   /// Used to detect recursive macro expansions.
   SourceLocation LastExpansionEnd;

clang/unittests/Tooling/Syntax/TokensTest.cpp

)cpp",
        R"(expanded tokens:
   int a = 10 + 10 ;
 file './input.cpp'
   spelled tokens:
     # define FOO 10 + 10 ; int a = FOO
   mappings:
     ['#'_0, 'int'_7) => ['int'_0, 'int'_0)
     ['FOO'_10, '<eof>'_11) => ['10'_3, '<eof>'_7)
-)"}};
+)"},
+      {R"cpp(
+         #define NUM 42
+         #define ID(a) a
+         #define M 1 + ID
+         M(NUM)
+       )cpp",
+       R"(expanded tokens:
+  1 + 42
+file './input.cpp'
+  spelled tokens:
+    # define NUM 42 # define ID ( a ) a # define M 1 + ID M ( NUM )
+  mappings:
+    ['#'_0, 'M'_17) => ['1'_0, '1'_0)
+    ['M'_17, '<eof>'_21) => ['1'_0, '<eof>'_3)
+)"},
+  };
 
-  for (auto &Test : TestCases)
-    EXPECT_EQ(Test.second, collectAndDump(Test.first))
-        << collectAndDump(Test.first);
+  for (auto &Test : TestCases) {
+    std::string Dump = collectAndDump(Test.first);
+    EXPECT_EQ(Test.second, Dump) << Dump;
+  }
 }
 
 TEST_F(TokenCollectorTest, SpecialTokens) {
   // Tokens coming from concatenations.
   recordTokens(R"cpp(
     #define CONCAT(a, b) a ## b
     int a = CONCAT(1, 2);
   )cpp");