[AArch64] Enable the mnemonic spell checker

[SjoerdMeijer]

Summary

The AsmParser mnemonic spell checker was introduced in r307148 and enabled only for ARM. This patch enables it for AArch64.

[t.p.northover]

Looks reasonable to me.

[SjoerdMeijer]

Thanks for the review!

lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp

private:
   int tryParseRegister();
   int tryMatchVectorRegister(StringRef &Kind, bool expected);
   bool parseRegister(OperandVector &Operands);
   bool parseSymbolicImmVal(const MCExpr *&ImmVal);
   bool parseVectorList(OperandVector &Operands);
   bool parseOperand(OperandVector &Operands, bool isCondCode,
                     bool invertCondCode);
 
-  bool showMatchError(SMLoc Loc, unsigned ErrCode);
+  bool showMatchError(SMLoc Loc, unsigned ErrCode, OperandVector &Operands);
 
   bool parseDirectiveArch(SMLoc L);
   bool parseDirectiveCPU(SMLoc L);
   bool parseDirectiveWord(unsigned Size, SMLoc L);
   bool parseDirectiveInst(SMLoc L);
 
   bool parseDirectiveTLSDescCall(SMLoc L);
 
case AArch64::SUBXri: {
     }
     return false;
   }
   default:
     return false;
   }
 }
 
-bool AArch64AsmParser::showMatchError(SMLoc Loc, unsigned ErrCode) {
+std::string AArch64MnemonicSpellCheck(StringRef S, uint64_t FBS);
+
+bool AArch64AsmParser::showMatchError(SMLoc Loc, unsigned ErrCode,
+                                      OperandVector &Operands) {
   switch (ErrCode) {
   case Match_MissingFeature:
     return Error(Loc,
                  "instruction requires a CPU feature not currently enabled");
   case Match_InvalidOperand:
     return Error(Loc, "invalid operand for instruction");
   case Match_InvalidSuffix:
     return Error(Loc, "invalid type suffix for instruction");
bool AArch64AsmParser::showMatchError(SMLoc Loc, unsigned ErrCode,
   case Match_InvalidIndexD:
     return Error(Loc, "vector lane must be an integer in range [0, 1].");
   case Match_InvalidLabel:
     return Error(Loc, "expected label or encodable integer pc offset");
   case Match_MRS:
     return Error(Loc, "expected readable system register");
   case Match_MSR:
     return Error(Loc, "expected writable system register or pstate");
-  case Match_MnemonicFail:
-    return Error(Loc, "unrecognized instruction mnemonic");
+  case Match_MnemonicFail: {
+    std::string Suggestion = AArch64MnemonicSpellCheck(
+        ((AArch64Operand &)*Operands[0]).getToken(),
+        ComputeAvailableFeatures(STI->getFeatureBits()));
+    return Error(Loc, "unrecognized instruction mnemonic" + Suggestion);
+  }
   default:
     llvm_unreachable("unexpected error code!");
   }
 }
 
 static const char *getSubtargetFeatureName(uint64_t Val);
 
 bool AArch64AsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
for (unsigned i = 0; i < (sizeof(ErrorInfo)*8-1); ++i) {
         Msg += " ";
         Msg += getSubtargetFeatureName(ErrorInfo & Mask);
       }
       Mask <<= 1;
     }
     return Error(IDLoc, Msg);
   }
   case Match_MnemonicFail:
-    return showMatchError(IDLoc, MatchResult);
+    return showMatchError(IDLoc, MatchResult, Operands);
   case Match_InvalidOperand: {
     SMLoc ErrorLoc = IDLoc;
 
     if (ErrorInfo != ~0ULL) {
       if (ErrorInfo >= Operands.size())
         return Error(IDLoc, "too few operands for instruction",
                      SMRange(IDLoc, getTok().getLoc()));
 
       ErrorLoc = ((AArch64Operand &)*Operands[ErrorInfo]).getStartLoc();
       if (ErrorLoc == SMLoc())
         ErrorLoc = IDLoc;
     }
     // If the match failed on a suffix token operand, tweak the diagnostic
     // accordingly.
     if (((AArch64Operand &)*Operands[ErrorInfo]).isToken() &&
         ((AArch64Operand &)*Operands[ErrorInfo]).isTokenSuffix())
       MatchResult = Match_InvalidSuffix;
 
-    return showMatchError(ErrorLoc, MatchResult);
+    return showMatchError(ErrorLoc, MatchResult, Operands);
   }
   case Match_InvalidMemoryIndexed1:
   case Match_InvalidMemoryIndexed2:
   case Match_InvalidMemoryIndexed4:
   case Match_InvalidMemoryIndexed8:
   case Match_InvalidMemoryIndexed16:
   case Match_InvalidCondCode:
   case Match_AddSubRegExtendSmall:
bool AArch64AsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
   case Match_MRS: {
     if (ErrorInfo >= Operands.size())
       return Error(IDLoc, "too few operands for instruction", SMRange(IDLoc, (*Operands.back()).getEndLoc()));
     // Any time we get here, there's nothing fancy to do. Just get the
     // operand SMLoc and display the diagnostic.
     SMLoc ErrorLoc = ((AArch64Operand &)*Operands[ErrorInfo]).getStartLoc();
     if (ErrorLoc == SMLoc())
       ErrorLoc = IDLoc;
-    return showMatchError(ErrorLoc, MatchResult);
+    return showMatchError(ErrorLoc, MatchResult, Operands);
   }
   }
 
   llvm_unreachable("Implement any new match types added!");
 }
 
 /// ParseDirective parses the arm specific directives
 bool AArch64AsmParser::ParseDirective(AsmToken DirectiveID) {

test/MC/AArch64/invalid-instructions-spellcheck.s

+// RUN: not llvm-mc -triple=aarch64 -show-encoding < %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=aarch64 -mattr=-neon -show-encoding < %s 2>&1 | FileCheck %s --check-prefix=CHECK-NO-NEON
+
+// This tests the mnemonic spell checker.
+
+// First check what happens when an instruction is omitted:
+
+  w1, w2, w3
+
+// CHECK:      error: unknown token in expression
+// CHECK-NEXT: w1, w2, w3
+// CHECK-NEXT:   ^
+// CHECK-NEXT: error: invalid operand
+// CHECK-NEXT: w1, w2, w3
+// CHECK-NEXT:   ^
+
+// We don't want to see a suggestion here; the edit distance is too large to
+// give sensible suggestions:
+
+  addddddddd w1, w2, w3
+
+// CHECK:      error: unrecognized instruction mnemonic
+// CHECK-NEXT: addddddddd w1, w2, w3
+// CHECK-NEXT: ^
+
+  addd w1, w2, w3
+
+// CHECK:      error: unrecognized instruction mnemonic, did you mean: add, addp, adds, addv, fadd, madd?
+// CHECK-NEXT: addd w1, w2, w3
+// CHECK-NEXT: ^
+
+// Instructions 'addv' and 'addp' are only available when NEON is enabled, so we
+// don't want to see them here:
+
+// CHECK-NO-NEON:      error: unrecognized instruction mnemonic, did you mean: add, adds, fadd, madd?
+// CHECK-NO-NEON-NEXT: addd w1, w2, w3
+// CHECK-NO-NEON-NEXT: ^