Clean up assembly statement separator support.

The MC asm lexer wasn't honoring a non-default (anything but ';') statement
separator. Fix that, and generalize a bit to support multi-character
statement separators.

llvm-svn: 128227

include/llvm/MC/MCAsmInfo.h

@@ -66,10 +66,9 @@ namespace llvm {
     /// relative expressions.
     const char *PCSymbol;                    // Defaults to "$".
 
-    /// SeparatorChar - This character, if specified, is used to separate
-    /// instructions from each other when on the same line.  This is used to
-    /// measure inline asm instructions.
-    char SeparatorChar;                      // Defaults to ';'
+    /// SeparatorString - This string, if specified, is used to separate
+    /// instructions from each other when on the same line.
+    const char *SeparatorString;             // Defaults to ';'
 
     /// CommentColumn - This indicates the comment num (zero-based) at
     /// which asm comments should be printed.
@@ -350,8 +349,8 @@ namespace llvm {
     const char *getPCSymbol() const {
       return PCSymbol;
     }
-    char getSeparatorChar() const {
-      return SeparatorChar;
+    const char *getSeparatorString() const {
+      return SeparatorString;
     }
     unsigned getCommentColumn() const {
       return CommentColumn;

include/llvm/MC/MCParser/AsmLexer.h

@@ -49,6 +49,7 @@ public:
   virtual StringRef LexUntilEndOfStatement();
 
   bool isAtStartOfComment(char Char);
+  bool isAtStatementSeparator(const char *Ptr);
 
   const MCAsmInfo &getMAI() const { return MAI; }
 

lib/MC/MCAsmInfo.cpp

@@ -26,7 +26,7 @@ MCAsmInfo::MCAsmInfo() {
   LinkerRequiresNonEmptyDwarfLines = false;
   MaxInstLength = 4;
   PCSymbol = "$";
-  SeparatorChar = ';';
+  SeparatorString = ";";
   CommentColumn = 40;
   CommentString = "#";
   LabelSuffix = ":";

lib/MC/MCParser/AsmLexer.cpp

@@ -324,8 +324,8 @@ AsmToken AsmLexer::LexQuote() {
 StringRef AsmLexer::LexUntilEndOfStatement() {
   TokStart = CurPtr;
 
-  while (!isAtStartOfComment(*CurPtr) && // Start of line comment.
-          *CurPtr != ';' &&  // End of statement marker.
+  while (!isAtStartOfComment(*CurPtr) &&    // Start of line comment.
+         !isAtStatementSeparator(CurPtr) && // End of statement marker.
          *CurPtr != '\n' &&
          *CurPtr != '\r' &&
          (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) {
@@ -339,6 +339,11 @@ bool AsmLexer::isAtStartOfComment(char Char) {
   return Char == *MAI.getCommentString();
 }
 
+bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
+  return strncmp(Ptr, MAI.getSeparatorString(),
+                 strlen(MAI.getSeparatorString())) == 0;
+}
+
 AsmToken AsmLexer::LexToken() {
   TokStart = CurPtr;
   // This always consumes at least one character.
@@ -346,6 +351,11 @@ AsmToken AsmLexer::LexToken() {
 
   if (isAtStartOfComment(CurChar))
     return LexLineComment();
+  if (isAtStatementSeparator(TokStart)) {
+    CurPtr += strlen(MAI.getSeparatorString()) - 1;
+    return AsmToken(AsmToken::EndOfStatement,
+                    StringRef(TokStart, strlen(MAI.getSeparatorString())));
+  }
 
   switch (CurChar) {
   default:
@@ -362,8 +372,8 @@ AsmToken AsmLexer::LexToken() {
     // Ignore whitespace.
     return LexToken();
   case '\n': // FALL THROUGH.
-  case '\r': // FALL THROUGH.
-  case ';': return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
+  case '\r':
+    return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
   case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1));
   case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1));
   case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1));

lib/Target/TargetInstrInfo.cpp

@@ -149,10 +149,10 @@ bool TargetInstrInfo::isUnpredicatedTerminator(const MachineInstr *MI) const {
 
 /// Measure the specified inline asm to determine an approximation of its
 /// length.
-/// Comments (which run till the next SeparatorChar or newline) do not
+/// Comments (which run till the next SeparatorString or newline) do not
 /// count as an instruction.
 /// Any other non-whitespace text is considered an instruction, with
-/// multiple instructions separated by SeparatorChar or newlines.
+/// multiple instructions separated by SeparatorString or newlines.
 /// Variable-length instructions are not handled here; this function
 /// may be overloaded in the target code to do that.
 unsigned TargetInstrInfo::getInlineAsmLength(const char *Str,
@@ -163,7 +163,8 @@ unsigned TargetInstrInfo::getInlineAsmLength(const char *Str,
   bool atInsnStart = true;
   unsigned Length = 0;
   for (; *Str; ++Str) {
-    if (*Str == '\n' || *Str == MAI.getSeparatorChar())
+    if (*Str == '\n' || strncmp(Str, MAI.getSeparatorString(),
+                                strlen(MAI.getSeparatorString())) == 0)
       atInsnStart = true;
     if (atInsnStart && !std::isspace(*Str)) {
       Length += MAI.getMaxInstLength();