[LLVM][AsmParser] Add support for C style comments (#111554)

Add support for C style comments in LLVM assembly.

---------

Co-authored-by: Nikita Popov <[email protected]>

Author: jurahul

llvm/docs/LangRef.rst

@@ -122,13 +122,14 @@ And the hard way:
 .. code-block:: llvm
 
     %0 = add i32 %X, %X           ; yields i32:%0
-    %1 = add i32 %0, %0           ; yields i32:%1
+    %1 = add i32 %0, %0           /* yields i32:%1 */
     %result = add i32 %1, %1
 
 This last way of multiplying ``%X`` by 8 illustrates several important
 lexical features of LLVM:
 
 #. Comments are delimited with a '``;``' and go until the end of line.
+   Alternatively, comments can start with ``/*`` and terminate with ``*/``.
 #. Unnamed temporaries are created when the result of a computation is
    not assigned to a named value.
 #. By default, unnamed temporaries are numbered sequentially (using a

llvm/include/llvm/AsmParser/LLLexer.h

@@ -95,6 +95,7 @@ namespace llvm {
 
     int getNextChar();
     void SkipLineComment();
+    bool SkipCComment();
     lltok::Kind ReadString(lltok::Kind kind);
     bool ReadVarName();
 

llvm/lib/AsmParser/LLLexer.cpp

@@ -200,7 +200,6 @@ lltok::Kind LLLexer::LexToken() {
       // Handle letters: [a-zA-Z_]
       if (isalpha(static_cast<unsigned char>(CurChar)) || CurChar == '_')
         return LexIdentifier();
-
       return lltok::Error;
     case EOF: return lltok::Eof;
     case 0:
@@ -251,6 +250,12 @@ lltok::Kind LLLexer::LexToken() {
     case ',': return lltok::comma;
     case '*': return lltok::star;
     case '|': return lltok::bar;
+    case '/':
+      if (getNextChar() != '*')
+        return lltok::Error;
+      if (SkipCComment())
+        return lltok::Error;
+      continue;
     }
   }
 }
@@ -262,6 +267,28 @@ void LLLexer::SkipLineComment() {
   }
 }
 
+/// This skips C-style /**/ comments. Returns true if there
+/// was an error.
+bool LLLexer::SkipCComment() {
+  while (true) {
+    int CurChar = getNextChar();
+    switch (CurChar) {
+    case EOF:
+      LexError("unterminated comment");
+      return true;
+    case '*':
+      // End of the comment?
+      CurChar = getNextChar();
+      if (CurChar == '/')
+        return false;
+      if (CurChar == EOF) {
+        LexError("unterminated comment");
+        return true;
+      }
+    }
+  }
+}
+
 /// Lex all tokens that start with an @ character.
 ///   GlobalVar   @\"[^\"]*\"
 ///   GlobalVar   @[-a-zA-Z$._][-a-zA-Z$._0-9]*

llvm/test/Assembler/c-style-comment.ll

@@ -0,0 +1,22 @@
+; RUN: llvm-as < %s | llvm-dis | FileCheck %s
+
+/* Simple C style comment */
+
+; CHECK: @B = external global i32
+@B = external global i32
+
+/* multiline C ctyle comment at "top-level"
+ * This is the second line
+ * and this is third
+ */
+
+
+; CHECK: @foo
+define <4 x i1> @foo(<4 x float> %a, <4 x float> %b) nounwind {
+entry: /* inline comment */
+  %cmp = fcmp olt <4 x float> %a, /* to be ignored */ %b
+  ret <4 x i1> %cmp /* ignore */
+}
+
+/* End of the assembly file */
+

llvm/test/Assembler/invalid-c-style-comment0.ll

@@ -0,0 +1,6 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+@B = external global i32
+
+; CHECK: [[FILE]]:[[@LINE+1]]:1: error: unterminated comment
+/* End of the assembly file

llvm/test/Assembler/invalid-c-style-comment1.ll

@@ -0,0 +1,8 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+@B = external global i32
+
+/*   /* Nested comments not supported */
+
+; CHECK: [[FILE]]:[[@LINE+1]]:1: error: redefinition of global '@B'
+@B = external global i32

llvm/test/Assembler/invalid-c-style-comment2.ll

@@ -0,0 +1,7 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+@B = external global i32
+
+; CHECK: [[FILE]]:[[@LINE+1]]:2: error: expected top-level entity
+*/
+

llvm/test/Assembler/invalid-c-style-comment3.ll

@@ -0,0 +1,6 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+@B = external global i32
+
+; CHECK: [[FILE]]:[[@LINE+1]]:1: error: unterminated comment
+/* End of the assembly file *