porffor 0.2.0-aea77ff → 0.2.0-c597461

package/README.md

@@ -209,10 +209,13 @@ Porffor can run Test262 via some hacks/transforms which remove unsupported featu
 - `test262`: test262 runner and utils
 
 ## Usecases
-Basically none (other than giving people headaches). Potential ideas to come?
+Basically none right now (other than giving people headaches). Potential ideas:
+- Safety. As Porffor is written in JS, a memory-safe language\*, and compiles JS to Wasm, a fully sandboxed environment\*, it is quite safe. (\* These rely on the underlying implementations being secure. You could also run Wasm, or even Porffor itself, with an interpreter instead of a JIT for bonus security points too.)
+- Compiling JS to native binaries. This is still very early, [`2c`](#2c) is not that good yet :(
+- More in future probably?
 
 ## Usage
-Basically nothing will work :). See files in `test` for examples.
+Basically nothing will work :). See files in `test` and `bench` for examples.
 
 1. Clone repo
 2. `npm install`

package/compiler/codeGen.js

@@ -55,7 +55,7 @@ const todo = msg => {
 };
 
 const isFuncType = type => type === 'FunctionDeclaration' || type === 'FunctionExpression' || type === 'ArrowFunctionExpression';
-const generate = (scope, decl, global = false, name = undefined) => {
+const generate = (scope, decl, global = false, name = undefined, valueUnused = false) => {
   switch (decl.type) {
     case 'BinaryExpression':
       return generateBinaryExp(scope, decl, global, name);
@@ -86,7 +86,7 @@ const generate = (scope, decl, global = false, name = undefined) => {
       return generateExp(scope, decl);
 
     case 'CallExpression':
-      return generateCall(scope, decl, global, name);
+      return generateCall(scope, decl, global, name, valueUnused);
 
     case 'NewExpression':
       return generateNew(scope, decl, global, name);
@@ -685,6 +685,15 @@ const truthy = (scope, wasm, type, intIn = false, intOut = false) => {
         [ Opcodes.i32_eqz ], */
         ...(intOut ? [] : [ Opcodes.i32_from_u ])
       ],
+      [TYPES._bytestring]: [ // duplicate of string
+        [ Opcodes.local_get, tmp ],
+        ...(intIn ? [] : [ Opcodes.i32_to_u ]),
+
+        // get length
+        [ Opcodes.i32_load, Math.log2(ValtypeSize.i32) - 1, 0 ],
+
+        ...(intOut ? [] : [ Opcodes.i32_from_u ])
+      ],
       default: def
     }, intOut ? Valtype.i32 : valtypeBinary)
   ];
@@ -712,6 +721,17 @@ const falsy = (scope, wasm, type, intIn = false, intOut = false) => {
         [ Opcodes.i32_eqz ],
         ...(intOut ? [] : [ Opcodes.i32_from_u ])
       ],
+      [TYPES._bytestring]: [ // duplicate of string
+        [ Opcodes.local_get, tmp ],
+        ...(intIn ? [] : [ Opcodes.i32_to_u ]),
+
+        // get length
+        [ Opcodes.i32_load, Math.log2(ValtypeSize.i32) - 1, 0 ],
+
+        // if length == 0
+        [ Opcodes.i32_eqz ],
+        ...(intOut ? [] : [ Opcodes.i32_from_u ])
+      ],
       default: [
         // if value == 0
         [ Opcodes.local_get, tmp ],
@@ -1044,7 +1064,8 @@ const TYPES = {
 
   // these are not "typeof" types but tracked internally
   _array: 0x10,
-  _regexp: 0x11
+  _regexp: 0x11,
+  _bytestring: 0x12
 };
 
 const TYPE_NAMES = {
@@ -1058,7 +1079,8 @@ const TYPE_NAMES = {
   [TYPES.bigint]: 'BigInt',
 
   [TYPES._array]: 'Array',
-  [TYPES._regexp]: 'RegExp'
+  [TYPES._regexp]: 'RegExp',
+  [TYPES._bytestring]: 'ByteString'
 };
 
 const getType = (scope, _name) => {
@@ -1111,6 +1133,8 @@ const getNodeType = (scope, node) => {
     if (node.type === 'Literal') {
       if (node.regex) return TYPES._regexp;
 
+      if (typeof node.value === 'string' && byteStringable(node.value)) return TYPES._bytestring;
+
       return TYPES[typeof node.value];
     }
 
@@ -1124,6 +1148,15 @@ const getNodeType = (scope, node) => {
 
     if (node.type === 'CallExpression' || node.type === 'NewExpression') {
       const name = node.callee.name;
+      if (!name) {
+        // iife
+        if (scope.locals['#last_type']) return [ getLastType(scope) ];
+
+        // presume
+        // todo: warn here?
+        return TYPES.number;
+      }
+
       const func = funcs.find(x => x.name === name);
 
       if (func) {
@@ -1218,7 +1251,7 @@ const getNodeType = (scope, node) => {
       if (node.operator === '!') return TYPES.boolean;
       if (node.operator === 'void') return TYPES.undefined;
       if (node.operator === 'delete') return TYPES.boolean;
-      if (node.operator === 'typeof') return TYPES.string;
+      if (node.operator === 'typeof') return process.argv.includes('-bytestring') ? TYPES._bytestring : TYPES.string;
 
       return TYPES.number;
     }
@@ -1278,16 +1311,7 @@ const generateLiteral = (scope, decl, global, name) => {
       return number(decl.value ? 1 : 0);
 
     case 'string':
-      const str = decl.value;
-      const rawElements = new Array(str.length);
-      let j = 0;
-      for (let i = 0; i < str.length; i++) {
-        rawElements[i] = str.charCodeAt(i);
-      }
-
-      return makeArray(scope, {
-        rawElements
-      }, global, name, false, 'i16')[0];
+      return makeString(scope, decl.value, global, name);
 
     default:
       return todo(`cannot generate literal of type ${typeof decl.value}`);
@@ -1308,9 +1332,9 @@ const countLeftover = wasm => {
 
     if (depth === 0)
       if ([Opcodes.throw,Opcodes.drop, Opcodes.local_set, Opcodes.global_set].includes(inst[0])) count--;
-        else if ([null, Opcodes.i32_eqz, Opcodes.i64_eqz, Opcodes.f64_ceil, Opcodes.f64_floor, Opcodes.f64_trunc, Opcodes.f64_nearest, Opcodes.f64_sqrt, Opcodes.local_tee, Opcodes.i32_wrap_i64, Opcodes.i64_extend_i32_s, Opcodes.i64_extend_i32_u, Opcodes.f32_demote_f64, Opcodes.f64_promote_f32, Opcodes.f64_convert_i32_s, Opcodes.f64_convert_i32_u, Opcodes.i32_clz, Opcodes.i32_ctz, Opcodes.i32_popcnt, Opcodes.f64_neg, Opcodes.end, Opcodes.i32_trunc_sat_f64_s[0], Opcodes.i32x4_extract_lane, Opcodes.i16x8_extract_lane, Opcodes.i32_load, Opcodes.i64_load, Opcodes.f64_load, Opcodes.v128_load, Opcodes.i32_load16_u, Opcodes.i32_load16_s, Opcodes.memory_grow].includes(inst[0]) && (inst[0] !== 0xfc || inst[1] < 0x0a)) {}
+        else if ([null, Opcodes.i32_eqz, Opcodes.i64_eqz, Opcodes.f64_ceil, Opcodes.f64_floor, Opcodes.f64_trunc, Opcodes.f64_nearest, Opcodes.f64_sqrt, Opcodes.local_tee, Opcodes.i32_wrap_i64, Opcodes.i64_extend_i32_s, Opcodes.i64_extend_i32_u, Opcodes.f32_demote_f64, Opcodes.f64_promote_f32, Opcodes.f64_convert_i32_s, Opcodes.f64_convert_i32_u, Opcodes.i32_clz, Opcodes.i32_ctz, Opcodes.i32_popcnt, Opcodes.f64_neg, Opcodes.end, Opcodes.i32_trunc_sat_f64_s[0], Opcodes.i32x4_extract_lane, Opcodes.i16x8_extract_lane, Opcodes.i32_load, Opcodes.i64_load, Opcodes.f64_load, Opcodes.v128_load, Opcodes.i32_load16_u, Opcodes.i32_load16_s, Opcodes.i32_load8_u, Opcodes.i32_load8_s, Opcodes.memory_grow].includes(inst[0]) && (inst[0] !== 0xfc || inst[1] < 0x0a)) {}
         else if ([Opcodes.local_get, Opcodes.global_get, Opcodes.f64_const, Opcodes.i32_const, Opcodes.i64_const, Opcodes.v128_const].includes(inst[0])) count++;
-        else if ([Opcodes.i32_store, Opcodes.i64_store, Opcodes.f64_store, Opcodes.i32_store16].includes(inst[0])) count -= 2;
+        else if ([Opcodes.i32_store, Opcodes.i64_store, Opcodes.f64_store, Opcodes.i32_store16, Opcodes.i32_store8].includes(inst[0])) count -= 2;
         else if (Opcodes.memory_copy[0] === inst[0] && Opcodes.memory_copy[1] === inst[1]) count -= 3;
         else if (inst[0] === Opcodes.return) count = 0;
         else if (inst[0] === Opcodes.call) {
@@ -1336,7 +1360,7 @@ const disposeLeftover = wasm => {
 const generateExp = (scope, decl) => {
   const expression = decl.expression;
 
-  const out = generate(scope, expression);
+  const out = generate(scope, expression, undefined, undefined, true);
   disposeLeftover(out);
 
   return out;
@@ -1394,7 +1418,7 @@ const RTArrayUtil = {
   ]
 };
 
-const generateCall = (scope, decl, _global, _name) => {
+const generateCall = (scope, decl, _global, _name, unusedValue = false) => {
   /* const callee = decl.callee;
   const args = decl.arguments;
 
@@ -1513,10 +1537,18 @@ const generateCall = (scope, decl, _global, _name) => {
       // use local for cached i32 length as commonly used
       const lengthLocal = localTmp(scope, '__proto_length_cache', Valtype.i32);
       const pointerLocal = localTmp(scope, '__proto_pointer_cache', Valtype.i32);
-      const getPointer = [ [ Opcodes.local_get, pointerLocal ] ];
 
       // TODO: long-term, prototypes should be their individual separate funcs
 
+      const rawPointer = [
+        ...generate(scope, target),
+        Opcodes.i32_to_u
+      ];
+
+      const usePointerCache = !Object.values(protoCands).every(x => x.noPointerCache === true);
+      const getPointer = usePointerCache ? [ [ Opcodes.local_get, pointerLocal ] ] : rawPointer;
+
+      let allOptUnused = true;
       let lengthI32CacheUsed = false;
       const protoBC = {};
       for (const x in protoCands) {
@@ -1536,6 +1568,7 @@ const generateCall = (scope, decl, _global, _name) => {
         const protoLocal = protoFunc.local ? localTmp(scope, `__${protoName}_tmp`, protoFunc.local) : -1;
         const protoLocal2 = protoFunc.local2 ? localTmp(scope, `__${protoName}_tmp2`, protoFunc.local2) : -1;
 
+        let optUnused = false;
         const protoOut = protoFunc(getPointer, {
           getCachedI32: () => {
             lengthI32CacheUsed = true;
@@ -1550,10 +1583,15 @@ const generateCall = (scope, decl, _global, _name) => {
           return makeArray(scope, {
             rawElements: new Array(length)
           }, _global, _name, true, itemType);
+        }, () => {
+          optUnused = true;
+          return unusedValue;
         });
 
+        if (!optUnused) allOptUnused = false;
+
         protoBC[x] = [
-          [ Opcodes.block, valtypeBinary ],
+          [ Opcodes.block, unusedValue && optUnused ? Blocktype.void : valtypeBinary ],
           ...protoOut,
 
           ...number(protoFunc.returnType ?? TYPES.number, Valtype.i32),
@@ -1562,11 +1600,13 @@ const generateCall = (scope, decl, _global, _name) => {
         ];
       }
 
-      return [
-        ...generate(scope, target),
+      // todo: if some cands use optUnused and some don't, we will probably crash
 
-        Opcodes.i32_to_u,
-        [ Opcodes.local_set, pointerLocal ],
+      return [
+        ...(usePointerCache ? [
+          ...rawPointer,
+          [ Opcodes.local_set, pointerLocal ],
+        ] : []),
 
         ...(!lengthI32CacheUsed ? [] : [
           ...RTArrayUtil.getLengthI32(getPointer),
@@ -1578,7 +1618,7 @@ const generateCall = (scope, decl, _global, _name) => {
 
           // TODO: error better
           default: internalThrow(scope, 'TypeError', `'${protoName}' proto func tried to be called on a type without an impl`)
-        }, valtypeBinary),
+        }, allOptUnused && unusedValue ? Blocktype.void : valtypeBinary),
       ];
     }
   }
@@ -1786,6 +1826,8 @@ const brTable = (input, bc, returns) => {
 };
 
 const typeSwitch = (scope, type, bc, returns = valtypeBinary) => {
+  if (!process.argv.includes('-bytestring')) delete bc[TYPES._bytestring];
+
   const known = knownType(scope, type);
   if (known != null) {
     return bc[known] ?? bc.default;
@@ -2176,6 +2218,8 @@ const generateUnary = (scope, decl) => {
         [TYPES.undefined]: makeString(scope, 'undefined', false, '#typeof_result'),
         [TYPES.function]: makeString(scope, 'function', false, '#typeof_result'),
 
+        [TYPES._bytestring]: makeString(scope, 'string', false, '#typeof_result'),
+
         // object and internal types
         default: makeString(scope, 'object', false, '#typeof_result'),
       });
@@ -2364,6 +2408,7 @@ const generateForOf = (scope, decl) => {
   }
 
   // set type for local
+  // todo: optimize away counter and use end pointer
   out.push(...typeSwitch(scope, getNodeType(scope, decl.right), {
     [TYPES._array]: [
       ...setType(scope, leftName, TYPES.number),
@@ -2582,7 +2627,8 @@ const StoreOps = {
   f64: Opcodes.f64_store,
 
   // expects i32 input!
-  i16: Opcodes.i32_store16
+  i8: Opcodes.i32_store8,
+  i16: Opcodes.i32_store16,
 };
 
 let data = [];
@@ -2601,6 +2647,15 @@ const compileBytes = (val, itemType, signed = true) => {
   }
 };
 
+const getAllocType = itemType => {
+  switch (itemType) {
+    case 'i8': return 'bytestring';
+    case 'i16': return 'string';
+
+    default: return 'array';
+  }
+};
+
 const makeArray = (scope, decl, global = false, name = '$undeclared', initEmpty = false, itemType = valtype) => {
   const out = [];
 
@@ -2610,7 +2665,7 @@ const makeArray = (scope, decl, global = false, name = '$undeclared', initEmpty
 
     // todo: can we just have 1 undeclared array? probably not? but this is not really memory efficient
     const uniqueName = name === '$undeclared' ? name + Math.random().toString().slice(2) : name;
-    arrays.set(name, allocPage(`${itemType === 'i16' ? 'string' : 'array'}: ${uniqueName}`, itemType) * pageSize);
+    arrays.set(name, allocPage(`${getAllocType(itemType)}: ${uniqueName}`, itemType) * pageSize);
   }
 
   const pointer = arrays.get(name);
@@ -2656,7 +2711,7 @@ const makeArray = (scope, decl, global = false, name = '$undeclared', initEmpty
     out.push(
       ...number(0, Valtype.i32),
       ...(useRawElements ? number(elements[i], Valtype[valtype]) : generate(scope, elements[i])),
-      [ storeOp, Math.log2(ValtypeSize[itemType]) - 1, ...unsignedLEB128(pointer + ValtypeSize.i32 + i * ValtypeSize[itemType]) ]
+      [ storeOp, (Math.log2(ValtypeSize[itemType]) || 1) - 1, ...unsignedLEB128(pointer + ValtypeSize.i32 + i * ValtypeSize[itemType]) ]
     );
   }
 
@@ -2666,15 +2721,29 @@ const makeArray = (scope, decl, global = false, name = '$undeclared', initEmpty
   return [ out, pointer ];
 };
 
+const byteStringable = str => {
+  if (!process.argv.includes('-bytestring')) return false;
+
+  for (let i = 0; i < str.length; i++) {
+    if (str.charCodeAt(i) > 0xFF) return false;
+  }
+
+  return true;
+};
+
 const makeString = (scope, str, global = false, name = '$undeclared') => {
   const rawElements = new Array(str.length);
+  let byteStringable = process.argv.includes('-bytestring');
   for (let i = 0; i < str.length; i++) {
-    rawElements[i] = str.charCodeAt(i);
+    const c = str.charCodeAt(i);
+    rawElements[i] = c;
+
+    if (byteStringable && c > 0xFF) byteStringable = false;
   }
 
   return makeArray(scope, {
     rawElements
-  }, global, name, false, 'i16')[0];
+  }, global, name, false, byteStringable ? 'i8' : 'i16')[0];
 };
 
 let arrays = new Map();
@@ -2765,6 +2834,34 @@ export const generateMember = (scope, decl, _global, _name) => {
       ...number(TYPES.string, Valtype.i32),
       setLastType(scope)
     ],
+    [TYPES._bytestring]: [
+      // setup new/out array
+      ...newOut,
+      [ Opcodes.drop ],
+
+      ...number(0, Valtype.i32), // base 0 for store later
+
+      ...generate(scope, decl.property),
+      Opcodes.i32_to_u,
+
+      ...(aotPointer ? [] : [
+        ...generate(scope, decl.object),
+        Opcodes.i32_to_u,
+        [ Opcodes.i32_add ]
+      ]),
+
+      // load current string ind {arg}
+      [ Opcodes.i32_load8_u, Math.log2(ValtypeSize.i16) - 1, ...unsignedLEB128((aotPointer ? pointer : 0) + ValtypeSize.i32) ],
+
+      // store to new string ind 0
+      [ Opcodes.i32_store8, Math.log2(ValtypeSize.i16) - 1, ...unsignedLEB128(newPointer + ValtypeSize.i32) ],
+
+      // return new string (page)
+      ...number(newPointer),
+
+      ...number(TYPES._bytestring, Valtype.i32),
+      setLastType(scope)
+    ],
 
     default: [ [ Opcodes.unreachable ] ]
   });

package/compiler/prototype.js

@@ -16,7 +16,8 @@ const TYPES = {
 
   // these are not "typeof" types but tracked internally
   _array: 0x10,
-  _regexp: 0x11
+  _regexp: 0x11,
+  _bytestring: 0x12
 };
 
 // todo: turn these into built-ins once arrays and these become less hacky
@@ -71,7 +72,7 @@ export const PrototypeFuncs = function() {
     ],
 
     // todo: only for 1 argument
-    push: (pointer, length, wNewMember) => [
+    push: (pointer, length, wNewMember, _1, _2, _3, unusedValue) => [
       // get memory offset of array at last index (length)
       ...length.getCachedI32(),
       ...number(ValtypeSize[valtype], Valtype.i32),
@@ -92,22 +93,28 @@ export const PrototypeFuncs = function() {
         ...number(1, Valtype.i32),
         [ Opcodes.i32_add ],
 
-        ...length.setCachedI32(),
-        ...length.getCachedI32(),
+        ...(unusedValue() ? [] : [
+          ...length.setCachedI32(),
+          ...length.getCachedI32(),
+        ])
       ]),
 
-      ...length.getCachedI32(),
-      Opcodes.i32_from_u
+      ...(unusedValue() ? [] : [
+        ...length.getCachedI32(),
+        Opcodes.i32_from_u
+      ])
 
       // ...length.get()
     ],
 
-    pop: (pointer, length) => [
+    pop: (pointer, length, _1, _2, _3, _4, unusedValue) => [
       // if length == 0, noop
       ...length.getCachedI32(),
       [ Opcodes.i32_eqz ],
       [ Opcodes.if, Blocktype.void ],
-      ...number(UNDEFINED),
+      ...(unusedValue() ? [] : [
+        ...number(UNDEFINED),
+      ]),
       [ Opcodes.br, 1 ],
       [ Opcodes.end ],
 
@@ -119,19 +126,23 @@ export const PrototypeFuncs = function() {
         ...number(1, Valtype.i32),
         [ Opcodes.i32_sub ],
 
-        ...length.setCachedI32(),
-        ...length.getCachedI32(),
+        ...(unusedValue() ? [] : [
+          ...length.setCachedI32(),
+          ...length.getCachedI32(),
+        ])
       ]),
 
       // load last element
-      ...length.getCachedI32(),
-      ...number(ValtypeSize[valtype], Valtype.i32),
-      [ Opcodes.i32_mul ],
+      ...(unusedValue() ? [] : [
+        ...length.getCachedI32(),
+        ...number(ValtypeSize[valtype], Valtype.i32),
+        [ Opcodes.i32_mul ],
 
-      ...pointer,
-      [ Opcodes.i32_add ],
+        ...pointer,
+        [ Opcodes.i32_add ],
 
-      [ Opcodes.load, Math.log2(ValtypeSize[valtype]) - 1, ...unsignedLEB128(ValtypeSize.i32) ]
+        [ Opcodes.load, Math.log2(ValtypeSize[valtype]) - 1, ...unsignedLEB128(ValtypeSize.i32) ]
+      ])
     ],
 
     shift: (pointer, length) => [
@@ -472,8 +483,152 @@ export const PrototypeFuncs = function() {
   this[TYPES.string].at.returnType = TYPES.string;
   this[TYPES.string].charAt.returnType = TYPES.string;
   this[TYPES.string].charCodeAt.local = Valtype.i32;
+  this[TYPES.string].charCodeAt.noPointerCache = zeroChecks.charcodeat;
 
   this[TYPES.string].isWellFormed.local = Valtype.i32;
   this[TYPES.string].isWellFormed.local2 = Valtype.i32;
   this[TYPES.string].isWellFormed.returnType = TYPES.boolean;
+
+  if (process.argv.includes('-bytestring')) {
+    this[TYPES._bytestring] = {
+      at: (pointer, length, wIndex, iTmp, _, arrayShell) => {
+        const [ newOut, newPointer ] = arrayShell(1, 'i16');
+
+        return [
+          // setup new/out array
+          ...newOut,
+          [ Opcodes.drop ],
+
+          ...number(0, Valtype.i32), // base 0 for store later
+
+          ...wIndex,
+          Opcodes.i32_to_u,
+          [ Opcodes.local_tee, iTmp ],
+
+          // if index < 0: access index + array length
+          ...number(0, Valtype.i32),
+          [ Opcodes.i32_lt_s ],
+          [ Opcodes.if, Blocktype.void ],
+          [ Opcodes.local_get, iTmp ],
+          ...length.getCachedI32(),
+          [ Opcodes.i32_add ],
+          [ Opcodes.local_set, iTmp ],
+          [ Opcodes.end ],
+
+          // if still < 0 or >= length: return undefined
+          [ Opcodes.local_get, iTmp ],
+          ...number(0, Valtype.i32),
+          [ Opcodes.i32_lt_s ],
+
+          [ Opcodes.local_get, iTmp ],
+          ...length.getCachedI32(),
+          [ Opcodes.i32_ge_s ],
+          [ Opcodes.i32_or ],
+
+          [ Opcodes.if, Blocktype.void ],
+          ...number(UNDEFINED),
+          [ Opcodes.br, 1 ],
+          [ Opcodes.end ],
+
+          [ Opcodes.local_get, iTmp ],
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+
+          // store to new string ind 0
+          [ Opcodes.i32_store8, 0, ...unsignedLEB128(newPointer + ValtypeSize.i32) ],
+
+          // return new string (pointer)
+          ...number(newPointer)
+        ];
+      },
+
+      // todo: out of bounds properly
+      charAt: (pointer, length, wIndex, _1, _2, arrayShell) => {
+        const [ newOut, newPointer ] = arrayShell(1, 'i16');
+
+        return [
+          // setup new/out array
+          ...newOut,
+          [ Opcodes.drop ],
+
+          ...number(0, Valtype.i32), // base 0 for store later
+
+          ...wIndex,
+
+          Opcodes.i32_to,
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+
+          // store to new string ind 0
+          [ Opcodes.i32_store8, 0, ...unsignedLEB128(newPointer + ValtypeSize.i32) ],
+
+          // return new string (page)
+          ...number(newPointer)
+        ];
+      },
+
+      charCodeAt: (pointer, length, wIndex, iTmp) => {
+        return [
+          ...wIndex,
+          Opcodes.i32_to,
+
+          ...(zeroChecks.charcodeat ? [] : [
+            [ Opcodes.local_set, iTmp ],
+
+            // index < 0
+            ...(noUnlikelyChecks ? [] : [
+              [ Opcodes.local_get, iTmp ],
+              ...number(0, Valtype.i32),
+              [ Opcodes.i32_lt_s ],
+            ]),
+
+            // index >= length
+            [ Opcodes.local_get, iTmp ],
+            ...length.getCachedI32(),
+            [ Opcodes.i32_ge_s ],
+
+            ...(noUnlikelyChecks ? [] : [ [ Opcodes.i32_or ] ]),
+            [ Opcodes.if, Blocktype.void ],
+            ...number(NaN),
+            [ Opcodes.br, 1 ],
+            [ Opcodes.end ],
+
+            [ Opcodes.local_get, iTmp ],
+          ]),
+
+          ...pointer,
+          [ Opcodes.i32_add ],
+
+          // load current string ind {arg}
+          [ Opcodes.i32_load8_u, 0, ...unsignedLEB128(ValtypeSize.i32) ],
+          Opcodes.i32_from_u
+        ];
+      },
+
+      isWellFormed: () => {
+        return [
+          // we know it must be true as it is a bytestring lol
+          ...number(1)
+        ]
+      }
+    };
+
+    this[TYPES._bytestring].at.local = Valtype.i32;
+    this[TYPES._bytestring].at.returnType = TYPES._bytestring;
+    this[TYPES._bytestring].charAt.returnType = TYPES._bytestring;
+    this[TYPES._bytestring].charCodeAt.local = Valtype.i32;
+    this[TYPES._bytestring].charCodeAt.noPointerCache = zeroChecks.charcodeat;
+
+    this[TYPES._bytestring].isWellFormed.local = Valtype.i32;
+    this[TYPES._bytestring].isWellFormed.local2 = Valtype.i32;
+    this[TYPES._bytestring].isWellFormed.returnType = TYPES.boolean;
+  }
 };

package/compiler/wasmSpec.js

@@ -57,9 +57,12 @@ export const Opcodes = {
   i64_load: 0x29,
   f64_load: 0x2b,
 
+  i32_load8_s: 0x2c,
+  i32_load8_u: 0x2d,
   i32_load16_s: 0x2e,
   i32_load16_u: 0x2f,
 
+  i32_store8: 0x3a,
   i32_store16: 0x3b,
 
   i32_store: 0x36,

package/compiler/wrap.js

@@ -19,7 +19,8 @@ const TYPES = {
 
   // internal
   [internalTypeBase]: '_array',
-  [internalTypeBase + 1]: '_regexp'
+  [internalTypeBase + 1]: '_regexp',
+  [internalTypeBase + 2]: '_bytestring'
 };
 
 export default async (source, flags = [ 'module' ], customImports = {}, print = str => process.stdout.write(str)) => {
@@ -177,6 +178,13 @@ export default async (source, flags = [ 'module' ], customImports = {}, print =
             return Array.from(new Uint16Array(memory.buffer, pointer + 4, length)).map(x => String.fromCharCode(x)).join('');
           }
 
+          case '_bytestring': {
+            const pointer = ret;
+            const length = new Int32Array(memory.buffer, pointer, 1);
+
+            return Array.from(new Uint8Array(memory.buffer, pointer + 4, length)).map(x => String.fromCharCode(x)).join('');
+          }
+
           case 'function': {
             // wasm func index, including all imports
             const func = funcs.find(x => (x.originalIndex ?? x.index) === ret);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "porffor",
   "description": "a basic experimental wip aot optimizing js -> wasm engine/compiler/runtime in js",
-  "version": "0.2.0-aea77ff",
+  "version": "0.2.0-c597461",
   "author": "CanadaHonk",
   "license": "MIT",
   "dependencies": {