[Strings] string.is_usv_sequence (#4783)

This implements it as a StringMeasure opcode. They do have the same number of
operands, same trapping behavior, and same return type. They both get a string and
do some inspection of it to return an i32. Perhaps the name could be StringInspect
or something like that, rather than StringMeasure..? But I think for now this might be
good enough, and the spec may change anyhow later.

Author: kripken

scripts/gen-s-parser.py

@@ -619,6 +619,7 @@
     ("string.const",         "makeStringConst(s)"),
     ("string.measure_wtf8",  "makeStringMeasure(s, StringMeasureWTF8)"),
     ("string.measure_wtf16", "makeStringMeasure(s, StringMeasureWTF16)"),
+    ("string.is_usv_sequence", "makeStringMeasure(s, StringMeasureIsUSV)"),
     ("string.encode_wtf8",   "makeStringEncode(s, StringEncodeWTF8)"),
     ("string.encode_wtf16",  "makeStringEncode(s, StringEncodeWTF16)"),
     ("string.concat",        "makeStringConcat(s)"),

src/gen-s-parser.inc

@@ -3159,6 +3159,9 @@ switch (op[0]) {
                   default: goto parse_error;
                 }
               }
+              case 'i':
+                if (strcmp(op, "string.is_usv_sequence") == 0) { return makeStringMeasure(s, StringMeasureIsUSV); }
+                goto parse_error;
               case 'm': {
                 switch (op[18]) {
                   case '1':

src/passes/Print.cpp

@@ -2253,6 +2253,9 @@ struct PrintExpressionContents
       case StringMeasureWTF16:
         printMedium(o, "string.measure_wtf16");
         break;
+      case StringMeasureIsUSV:
+        printMedium(o, "string.is_usv_sequence");
+        break;
       default:
         WASM_UNREACHABLE("invalid string.measure*");
     }

src/wasm-binary.h

@@ -1146,6 +1146,7 @@ enum ASTNodes {
   StringEncodeWTF16 = 0x87,
   StringConcat = 0x88,
   StringEq = 0x89,
+  StringIsUSV = 0x8a,
 };
 
 enum MemoryAccess {

src/wasm.h

@@ -594,6 +594,7 @@ enum StringMeasureOp {
   StringMeasureUTF8,
   StringMeasureWTF8,
   StringMeasureWTF16,
+  StringMeasureIsUSV,
 };
 
 enum StringEncodeOp {

src/wasm/wasm-binary.cpp

@@ -7191,6 +7191,8 @@ bool WasmBinaryBuilder::maybeVisitStringMeasure(Expression*& out,
     }
   } else if (code == BinaryConsts::StringMeasureWTF16) {
     op = StringMeasureWTF16;
+  } else if (code == BinaryConsts::StringIsUSV) {
+    op = StringMeasureIsUSV;
   } else {
     return false;
   }

src/wasm/wasm-stack.cpp

@@ -2276,6 +2276,9 @@ void BinaryInstWriter::visitStringMeasure(StringMeasure* curr) {
     case StringMeasureWTF16:
       o << U32LEB(BinaryConsts::StringMeasureWTF16);
       break;
+    case StringMeasureIsUSV:
+      o << U32LEB(BinaryConsts::StringIsUSV);
+      break;
     default:
       WASM_UNREACHABLE("invalid string.new*");
   }

test/lit/strings.wast

@@ -225,4 +225,23 @@
       )
     )
   )
+
+  ;; CHECK:      (func $string.is_usv_sequence (param $ref stringref)
+  ;; CHECK-NEXT:  (drop
+  ;; CHECK-NEXT:   (i32.eqz
+  ;; CHECK-NEXT:    (string.is_usv_sequence
+  ;; CHECK-NEXT:     (local.get $ref)
+  ;; CHECK-NEXT:    )
+  ;; CHECK-NEXT:   )
+  ;; CHECK-NEXT:  )
+  ;; CHECK-NEXT: )
+  (func $string.is_usv_sequence (param $ref stringref)
+    (drop
+      (i32.eqz ;; validate the output is i32
+        (string.is_usv_sequence
+          (local.get $ref)
+        )
+      )
+    )
+  )
 )