[PATCH] D100959: [AsmParser][SystemZ][z/OS] Use updated framework in AsmLexer to accept special tokens as Identifiers

Anirudh Prasad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Apr 21 07:51:38 PDT 2021


anirudhp created this revision.
anirudhp added reviewers: abhina.sreeskantharajan, Jonathan.Crowther, fanbo-meng, epastor, rnk, MaskRay, thakis, myiwanch, yusra.syeda, neumannh, DanielMcIntosh-IBM, scott.linder, Kai, uweigand.
Herald added a subscriber: hiraditya.
anirudhp requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

- Previously, https://reviews.llvm.org/D99889 changed the framework in the AsmLexer to treat special tokens, if they occur at the start of the string, as Identifiers.
- These are used by the MASM Parser implementation in LLVM, and we can extend some of the changes made in the previous patch to SystemZ.
- In SystemZ, the special "tokens" referred to here are "_", "$", "@", "#". [_|$|@|#] are already supported as "part" of an Identifier.
- The changes in this patch ensure that these special tokens, when they occur at the start of the Identifier, are treated as Identifiers.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D100959

Files:
  llvm/include/llvm/MC/MCAsmInfo.h
  llvm/lib/MC/MCParser/AsmLexer.cpp
  llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
  llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp


Index: llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
===================================================================
--- llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
+++ llvm/unittests/MC/SystemZ/SystemZAsmLexerTest.cpp
@@ -44,6 +44,9 @@
   void setAllowDollarAtStartOfIdentifier(bool Value) {
     AllowDollarAtStartOfIdentifier = Value;
   }
+  void setAllowHashAtStartOfIdentifier(bool Value) {
+    AllowHashAtStartOfIdentifier = Value;
+  }
 };
 
 // Setup a testing class that the GTest framework can call.
@@ -571,4 +574,22 @@
       {AsmToken::Identifier, AsmToken::EndOfStatement, AsmToken::Eof});
   lexAndCheckTokens(AsmStr, ExpectedTokens);
 }
+
+TEST_F(SystemZAsmLexerTest, CheckAcceptHashAtStartOfIdentifier) {
+  StringRef AsmStr = "##a#b$c";
+
+  // Setup.
+  MUPMAI->setAllowHashAtStartOfIdentifier(true);
+  MUPMAI->setCommentString("*");
+  MUPMAI->setAllowAdditionalComments(false);
+  setupCallToAsmParser(AsmStr);
+  Parser->getLexer().setAllowHashInIdentifier(true);
+
+  // Lex initially to get the string.
+  Parser->getLexer().Lex();
+
+  SmallVector<AsmToken::TokenKind> ExpectedTokens(
+      {AsmToken::Identifier, AsmToken::EndOfStatement, AsmToken::Eof});
+  lexAndCheckTokens(AsmStr, ExpectedTokens);
+}
 } // end anonymous namespace
Index: llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
===================================================================
--- llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
+++ llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
@@ -24,6 +24,10 @@
   CommentString = AssemblerDialect == AD_HLASM ? "*" : "#";
   RestrictCommentStringToStartOfStatement = (AssemblerDialect == AD_HLASM);
   AllowAdditionalComments = (AssemblerDialect == AD_ATT);
+  AllowAtAtStartOfIdentifier = (AssemblerDialect == AD_HLASM);
+  AllowDollarAtStartOfIdentifier = (AssemblerDialect == AD_HLASM);
+  AllowHashAtStartOfIdentifier = (AssemblerDialect == AD_HLASM);
+
   ZeroDirective = "\t.space\t";
   Data64bitsDirective = "\t.quad\t";
   UsesELFSectionDirectiveForBSS = true;
Index: llvm/lib/MC/MCParser/AsmLexer.cpp
===================================================================
--- llvm/lib/MC/MCParser/AsmLexer.cpp
+++ llvm/lib/MC/MCParser/AsmLexer.cpp
@@ -907,7 +907,11 @@
   case '/':
     IsAtStartOfStatement = OldIsAtStartOfStatement;
     return LexSlash();
-  case '#': return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
+  case '#': {
+    if (MAI.doesAllowHashAtStartOfIdentifier())
+      return LexIdentifier();
+    return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
+  }
   case '\'': return LexSingleQuote();
   case '"': return LexQuote();
   case '0': case '1': case '2': case '3': case '4':
Index: llvm/include/llvm/MC/MCAsmInfo.h
===================================================================
--- llvm/include/llvm/MC/MCAsmInfo.h
+++ llvm/include/llvm/MC/MCAsmInfo.h
@@ -202,6 +202,13 @@
   /// Defaults to false.
   bool AllowAtAtStartOfIdentifier = false;
 
+  /// This is true if the assembler allows the "#" character at the start of
+  /// a string to be lexed as an AsmToken::Identifier.
+  /// If the CommentString is also set to "#", setting this option will have
+  /// no effect, and the string will be lexed as a comment.
+  /// Defaults to false.
+  bool AllowHashAtStartOfIdentifier = false;
+
   /// If this is true, symbol names with invalid characters will be printed in
   /// quotes.
   bool SupportsQuotedNames = true;
@@ -626,6 +633,9 @@
   bool doesAllowDollarAtStartOfIdentifier() const {
     return AllowDollarAtStartOfIdentifier;
   }
+  bool doesAllowHashAtStartOfIdentifier() const {
+    return AllowHashAtStartOfIdentifier;
+  }
   bool supportsNameQuoting() const { return SupportsQuotedNames; }
 
   bool doesSupportDataRegionDirectives() const {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D100959.339238.patch
Type: text/x-patch
Size: 3809 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210421/cf2ddbad/attachment.bin>


More information about the llvm-commits mailing list