[AsmParser][SystemZ][z/OS] Reject character and string literals for HLASM

- As per the HLASM support we are providing, i.e. support only for the first parameter of the inline asm block, only pertaining to Z machine instructions defined in LLVM, character literals and string literals are not supported (see Figure 4 - https://www-01.ibm.com/servers/resourcelink/svc00100.nsf/pages/zOSV2R3sc264940/$file/asmr1023.pdf for more information)
- This patch explicitly rejects the usage of char literals and string literals (for example "abc 'a'") when the relevant field is set
- This is achieved by introducing a field called `LexHLASMStrings` in MCAsmLexer similar to `LexMasmStrings`

Reviewed By: abhina.sreeskantharajan, Kai

Differential Revision: https://reviews.llvm.org/D101660

diff --git a/llvm/include/llvm/MC/MCParser/MCAsmLexer.h b/llvm/include/llvm/MC/MCParser/MCAsmLexer.h
index 6a60401..0679697 100644 (file)
--- a/llvm/include/llvm/MC/MCParser/MCAsmLexer.h
+++ b/llvm/include/llvm/MC/MCParser/MCAsmLexer.h
@@ -57,6 +57,7 @@ protected: // Can only create subclasses.
   bool UseMasmDefaultRadix = false;
   unsigned DefaultRadix = 10;
   bool LexHLASMIntegers = false;
+  bool LexHLASMStrings = false;
   AsmCommentConsumer *CommentConsumer = nullptr;
 
   MCAsmLexer();
@@ -180,6 +181,11 @@ public:
 
   /// Set whether to lex HLASM-flavour integers. For now this is only [0-9]*
   void setLexHLASMIntegers(bool V) { LexHLASMIntegers = V; }
+
+  /// Set whether to "lex" HLASM-flavour character and string literals. For now,
+  /// setting this option to true, will disable lexing for character and string
+  /// literals.
+  void setLexHLASMStrings(bool V) { LexHLASMStrings = V; }
 };
 
 } // end namespace llvm

diff --git a/llvm/lib/MC/MCParser/AsmLexer.cpp b/llvm/lib/MC/MCParser/AsmLexer.cpp
index 9d97837..e328ba5 100644 (file)
--- a/llvm/lib/MC/MCParser/AsmLexer.cpp
+++ b/llvm/lib/MC/MCParser/AsmLexer.cpp
@@ -567,6 +567,9 @@ AsmToken AsmLexer::LexDigit() {
 AsmToken AsmLexer::LexSingleQuote() {
   int CurChar = getNextChar();
 
+  if (LexHLASMStrings)
+    return ReturnError(TokStart, "invalid usage of character literals");
+
   if (LexMasmStrings) {
     while (CurChar != EOF) {
       if (CurChar != '\'') {
@@ -621,6 +624,9 @@ AsmToken AsmLexer::LexSingleQuote() {
 /// LexQuote: String: "..."
 AsmToken AsmLexer::LexQuote() {
   int CurChar = getNextChar();
+  if (LexHLASMStrings)
+    return ReturnError(TokStart, "invalid usage of string literals");
+
   if (LexMasmStrings) {
     while (CurChar != EOF) {
       if (CurChar != '"') {

diff --git a/llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp b/llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
index 353084a..a93bf8d 100644 (file)
--- a/llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
+++ b/llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
@@ -700,4 +700,36 @@ TEST_F(SystemZAsmLexerTest, CheckRejectStarAsCurrentPC) {
   EXPECT_EQ(ParsePrimaryExpr, true);
   EXPECT_EQ(Parser->hasPendingError(), true);
 }
+
+TEST_F(SystemZAsmLexerTest, CheckRejectCharLiterals) {
+  StringRef AsmStr = "abc 'd'";
+
+  // Setup.
+  setupCallToAsmParser(AsmStr);
+  Parser->getLexer().setLexHLASMStrings(true);
+
+  // Lex initially to get the string.
+  Parser->getLexer().Lex();
+
+  SmallVector<AsmToken::TokenKind> ExpectedTokens(
+      {AsmToken::Identifier, AsmToken::Error, AsmToken::Error,
+       AsmToken::EndOfStatement, AsmToken::Eof});
+  lexAndCheckTokens(AsmStr, ExpectedTokens);
+}
+
+TEST_F(SystemZAsmLexerTest, CheckRejectStringLiterals) {
+  StringRef AsmStr = "abc \"ef\"";
+
+  // Setup.
+  setupCallToAsmParser(AsmStr);
+  Parser->getLexer().setLexHLASMStrings(true);
+
+  // Lex initially to get the string.
+  Parser->getLexer().Lex();
+
+  SmallVector<AsmToken::TokenKind> ExpectedTokens(
+      {AsmToken::Identifier, AsmToken::Error, AsmToken::Identifier,
+       AsmToken::Error, AsmToken::EndOfStatement, AsmToken::Eof});
+  lexAndCheckTokens(AsmStr, ExpectedTokens);
+}
 } // end anonymous namespace