[llvm] 7a46d34 - [SystemZ][z/OS] Add support to validate a HLASM Label.

[Kai Nacke via llvm-commits]

Author: Anirudh Prasad
Date: 2021-03-08T09:55:39-05:00
New Revision: 7a46d34a1953625f03b71494c0f33fe00316e4ba

URL: https://github.com/llvm/llvm-project/commit/7a46d34a1953625f03b71494c0f33fe00316e4ba
DIFF: https://github.com/llvm/llvm-project/commit/7a46d34a1953625f03b71494c0f33fe00316e4ba.diff

LOG: [SystemZ][z/OS] Add support to validate a HLASM Label.

- This patch adds in support to determine whether a particular label
  is valid for the hlasm variant
- The label syntax being checked is that of an ordinary HLASM symbol
  (Reference, Chapter 2 (Coding and Structure) - Terms, Literals and
  Expressions - Terms - Symbols - Ordinary Symbol)
- To achieve this, the virtual function isLabel defined in
  MCTargetAsmParser.h is made use of
- The isLabel function is overridden in SystemZAsmParser for the
  hlasm variant, and the syntax is checked appropriately
- Things remain unchanged for the att variant
- Further patches will add in support to emit the label. These future
  patches will make use of this isLabel function

Reviewed By: uweigand, Kai

Differential Revision: https://reviews.llvm.org/D97748

Added: 
    

Modified: 
    llvm/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
    llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
    llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.h

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp b/llvm/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
index 92a35e22007e..c600842c7f44 100644
--- a/llvm/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
+++ b/llvm/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "MCTargetDesc/SystemZInstPrinter.h"
+#include "MCTargetDesc/SystemZMCAsmInfo.h"
 #include "MCTargetDesc/SystemZMCTargetDesc.h"
 #include "TargetInfo/SystemZTargetInfo.h"
 #include "llvm/ADT/STLExtras.h"
@@ -450,6 +451,15 @@ class SystemZAsmParser : public MCTargetAsmParser {
     return Parser.getContext().getAsmInfo()->getAssemblerDialect();
   }
 
+  // An alphabetic character in HLASM is a letter from 'A' through 'Z',
+  // or from 'a' through 'z', or '$', '_','#', or '@'.
+  inline bool isHLASMAlpha(char C) {
+    return isAlpha(C) || llvm::is_contained("_@#$", C);
+  }
+
+  // A digit in HLASM is a number from 0 to 9.
+  inline bool isHLASMAlnum(char C) { return isHLASMAlpha(C) || isDigit(C); }
+
 public:
   SystemZAsmParser(const MCSubtargetInfo &sti, MCAsmParser &parser,
                    const MCInstrInfo &MII,
@@ -477,6 +487,7 @@ class SystemZAsmParser : public MCTargetAsmParser {
                                OperandVector &Operands, MCStreamer &Out,
                                uint64_t &ErrorInfo,
                                bool MatchingInlineAsm) override;
+  bool isLabel(AsmToken &Token) override;
 
   // Used by the TableGen code to parse particular operand types.
   OperandMatchResultTy parseGR32(OperandVector &Operands) {
@@ -1594,6 +1605,47 @@ SystemZAsmParser::parsePCRel(OperandVector &Operands, int64_t MinVal,
   return MatchOperand_Success;
 }
 
+bool SystemZAsmParser::isLabel(AsmToken &Token) {
+  if (getMAIAssemblerDialect() == AD_ATT)
+    return true;
+
+  // HLASM labels are ordinary symbols.
+  // An HLASM label always starts at column 1.
+  // An ordinary symbol syntax is laid out as follows:
+  // Rules:
+  // 1. Has to start with an "alphabetic character". Can be followed by up to
+  //    62 alphanumeric characters. An "alphabetic character", in this scenario,
+  //    is a letter from 'A' through 'Z', or from 'a' through 'z',
+  //    or '$', '_', '#', or '@'
+  // 2. Labels are case-insensitive. E.g. "lab123", "LAB123", "lAb123", etc.
+  //    are all treated as the same symbol. However, the processing for the case
+  //    folding will not be done in this function.
+  StringRef RawLabel = Token.getString();
+  SMLoc Loc = Token.getLoc();
+
+  // An HLASM label cannot be empty.
+  if (!RawLabel.size())
+    return !Error(Loc, "HLASM Label cannot be empty");
+
+  // An HLASM label cannot exceed greater than 63 characters.
+  if (RawLabel.size() > 63)
+    return !Error(Loc, "Maximum length for HLASM Label is 63 characters");
+
+  // A label must start with an "alphabetic character".
+  if (!isHLASMAlpha(RawLabel[0]))
+    return !Error(Loc, "HLASM Label has to start with an alphabetic "
+                       "character or the underscore character");
+
+  // Now, we've established that the length is valid
+  // and the first character is alphabetic.
+  // Check whether remaining string is alphanumeric.
+  for (unsigned I = 1; I < RawLabel.size(); ++I)
+    if (!isHLASMAlnum(RawLabel[I]))
+      return !Error(Loc, "HLASM Label has to be alphanumeric");
+
+  return true;
+}
+
 // Force static initialization.
 extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeSystemZAsmParser() {
   RegisterMCAsmParser<SystemZAsmParser> X(getTheSystemZTarget());

diff  --git a/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp b/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
index d0330b9cf40f..c537020cdee8 100644
--- a/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
+++ b/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.cpp
@@ -12,8 +12,6 @@
 
 using namespace llvm;
 
-enum AsmDialect { AD_ATT = 0, AD_HLASM = 1 };
-
 SystemZMCAsmInfo::SystemZMCAsmInfo(const Triple &TT) {
   CodePointerSize = 8;
   CalleeSaveStackSlotSize = 8;

diff  --git a/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.h b/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.h
index b8818a65f9e3..8b42dea1303d 100644
--- a/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.h
+++ b/llvm/lib/Target/SystemZ/MCTargetDesc/SystemZMCAsmInfo.h
@@ -14,6 +14,7 @@
 
 namespace llvm {
 class Triple;
+enum SystemZAsmDialect { AD_ATT = 0, AD_HLASM = 1 };
 
 class SystemZMCAsmInfo : public MCAsmInfoELF {
 public: