[LLVM][inline-asm][Altmacor] Altmacro string delimiter '<..>'

In this patch, I introduce a new altmacro string delimiter. 
This review is the second review in a series of four reviews.
(one for each altmacro feature: LOCAL, string delimiter, string '!' escape sign and absolute expression as a string '%' ).

In the alternate macro mode, you can delimit strings with matching angle brackets <..> 
when using it as a part of calling macro arguments.

As described in the https://sourceware.org/binutils/docs-2.27/as/Altmacro.html
"<string>
You can delimit strings with matching angle brackets."

assumptions:

1. If an argument begins with '<' and ends with '>'. The argument is considered as a string.
2. Except adding new string mark '<..>', a regular macro behavior is expected.
3. The altmacro cannot affect the regular less/greater behavior.
4. If a comma is present inside an angle brackets it considered as a character and not as a separator.

Differential Revision: https://reviews.llvm.org/D32701


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@302135 91177308-0d34-0410-b5e6-96231b3b80d8

lib/MC/MCParser/AsmParser.cpp

@@ -287,6 +287,7 @@ class AsmParser : public MCAsmParser {
   /// }
 
 private:
+  bool isAltmacroString(SMLoc &StrLoc, SMLoc &EndLoc);
   bool parseStatement(ParseStatementInfo &Info,
                       MCAsmParserSemaCallback *SI);
   bool parseCurlyBlockScope(SmallVectorImpl<AsmRewrite>& AsmStrRewrites);
@@ -1192,6 +1193,31 @@ AsmParser::applyModifierToExpr(const MCExpr *E,
   llvm_unreachable("Invalid expression kind!");
 }
 
+/// This function checks if the next token is <string> type or arithmetic.
+/// string that begin with character '<' must end with character '>'.
+/// otherwise it is arithmetics.
+/// If the function returns a 'true' value,
+/// the End argument will be filled with the last location pointed to the '>'
+/// character.
+
+/// There is a gap between the AltMacro's documentation and the single quote implementation. 
+/// GCC does not fully support this feature and so we will not support it.
+/// TODO: Adding single quote as a string.
+bool AsmParser::isAltmacroString(SMLoc &StrLoc, SMLoc &EndLoc) {
+  assert((StrLoc.getPointer() != NULL) &&
+         "Argument to the function cannot be a NULL value");
+  const char *CharPtr = StrLoc.getPointer();
+  while ((*CharPtr != '>') && (*CharPtr != '\n') &&
+         (*CharPtr != '\r') && (*CharPtr != '\0')){
+    CharPtr++;
+  }
+  if (*CharPtr == '>') {
+    EndLoc = StrLoc.getFromPointer(CharPtr + 1);
+    return true;
+  }
+  return false;
+}
+
 /// \brief Parse an expression and return it.
 ///
 ///  expr ::= expr &&,|| expr               -> lowest.
@@ -2461,9 +2487,9 @@ bool AsmParser::parseMacroArguments(const MCAsmMacro *M,
     if (NamedParametersFound && FA.Name.empty())
       return Error(IDLoc, "cannot mix positional and keyword arguments");
 
+    SMLoc StrLoc = Lexer.getLoc();
+    SMLoc EndLoc;
     if (Lexer.IsaAltMacroMode() && Lexer.is(AsmToken::Percent)) {
-        SMLoc StrLoc = Lexer.getLoc();
-        SMLoc EndLoc;
         const MCExpr *AbsoluteExp;
         int64_t Value;
         /// Eat '%'
@@ -2476,8 +2502,16 @@ bool AsmParser::parseMacroArguments(const MCAsmMacro *M,
         const char *EndChar = EndLoc.getPointer();
         AsmToken newToken(AsmToken::Integer, StringRef(StrChar , EndChar - StrChar), Value);
         FA.Value.push_back(newToken);
-    }
-    else if(parseMacroArgument(FA.Value, Vararg))
+    } else if (Lexer.IsaAltMacroMode() && Lexer.is(AsmToken::Less) &&
+               isAltmacroString(StrLoc, EndLoc)) {
+        const char *StrChar = StrLoc.getPointer();
+        const char *EndChar = EndLoc.getPointer();
+        jumpToLoc(EndLoc, CurBuffer);
+        /// Eat from '<' to '>'
+        Lex();
+        AsmToken newToken(AsmToken::String, StringRef(StrChar, EndChar - StrChar));
+        FA.Value.push_back(newToken);
+    } else if(parseMacroArgument(FA.Value, Vararg))
         return true;
 
     unsigned PI = Parameter;

test/MC/AsmParser/altmacro_string.s

@@ -0,0 +1,73 @@
+# RUN: llvm-mc -triple i386-linux-gnu  %s| FileCheck %s
+
+# This test checks the altmacro string delimiter '<' and '>'.
+
+.altmacro
+
+# Test #1:
+# You can delimit strings with matching angle brackets '<' '>'.
+# If an argument begins with '<' and ends with '>'.
+# The argument is considered as a string.
+
+# CHECK: simpleCheck:
+.macro simple_check_0 name
+    \name:
+   addl $5,%eax
+.endm
+
+simple_check_0 <simpleCheck>
+
+# Test #2:
+# Except adding new string marks '<..>', a regular macro behavior is expected.
+
+# CHECK:  simpleCheck0:
+# CHECK: addl    $0, %eax
+.macro concat string1 string2 string3
+   \string1\string2\string3:
+        addl $\string3, %eax
+.endm
+
+concat <simple>,<Check>,<0>
+
+# Test #3:
+# The altmacro cannot affect the regular less/greater behavior.
+
+# CHECK: addl $1, %eax
+# CHECK: addl $0, %eax
+
+.macro fun3 arg1 arg2
+   addl $\arg1,%eax
+   addl $\arg2,%eax
+.endm
+
+fun3 5<6 , 5>8
+
+# Test #4:
+# If a comma is present inside an angle brackets,
+# the comma considered as a character and not as a separator.
+# This check checks the ability to split the string to different
+# arguments according to the use of the comma.
+# Fun2 sees the comma as a character.
+# Fun3 sees the comma as a separator.
+
+# CHECK: addl $5, %eax
+# CHECK: addl $6, %eax
+.macro fun2 arg
+   fun3 \arg
+.endm
+
+fun2 <5,6>
+
+# Test #5:
+# If argument begin with '<' and there is no '>' to close it.
+# A regular macro behavior is expected.
+
+# CHECK: addl $4, %eax
+.macro fun4 arg1 arg2
+   .if \arg2\arg1
+   addl $\arg2,%eax
+   .endif
+.endm
+
+fun4 <5,4
+.noaltmacro

test/MC/AsmParser/negative_altmacro_string.s

@@ -0,0 +1,29 @@
+# RUN: not llvm-mc -triple i386-linux-gnu %s 2>&1 | FileCheck %s
+
+# This test checks the altmacro string delimiter '<' and '>'.
+# In this test we check the '.noaltmacro' directive.
+# We expect that '.altmacro' and '.noaltmacro' will act as a switch on/off directives to the alternate macro mode.
+# .noaltmacro returns the format into a regular macro handling.
+# The default mode is ".noaltmacro". 
+
+# Test #1: default mode
+# CHECK:  error: unexpected token at start of statement
+# CHECK-NEXT: <simpleCheck>:
+.macro simple_check_0 name
+    \name:
+.endm
+
+simple_check_0 <simpleCheck>
+
+
+.altmacro
+.noaltmacro
+
+# Test #2: Switching from alternate mode to default mode
+# CHECK:  error: unexpected token at start of statement
+# CHECK-NEXT: <simpleCheck1>:
+.macro simple_check_1 name
+    \name:
+.endm
+
+simple_check_1 <simpleCheck1>