Remove support of (de)serializing binary byte data between raw data buffer and a UTF-8 string. With TextDecoder and eager handling of 0 as a terminator byte that never quite worked, so it is unlikely that anyone would have ever depended on that feature.

Author: juj

src/preamble.js

@@ -458,36 +458,27 @@ function UTF8ArrayToString(u8Array, idx) {
     return UTF8Decoder.decode(u8Array.subarray(idx, endPtr));
   } else {
 #endif // TEXTDECODER
-    var u0, u1, u2, u3, u4, u5;
-
     var str = '';
     while (1) {
       // For UTF8 byte structure, see:
       // http://en.wikipedia.org/wiki/UTF-8#Description
       // https://www.ietf.org/rfc/rfc2279.txt
       // https://tools.ietf.org/html/rfc3629
-      u0 = u8Array[idx++];
+      var u0 = u8Array[idx++];
       if (!u0) return str;
       if (!(u0 & 0x80)) { str += String.fromCharCode(u0); continue; }
-      u1 = u8Array[idx++] & 63;
+      var u1 = u8Array[idx++] & 63;
       if ((u0 & 0xE0) == 0xC0) { str += String.fromCharCode(((u0 & 31) << 6) | u1); continue; }
-      u2 = u8Array[idx++] & 63;
+      var u2 = u8Array[idx++] & 63;
       if ((u0 & 0xF0) == 0xE0) {
         u0 = ((u0 & 15) << 12) | (u1 << 6) | u2;
       } else {
-        u3 = u8Array[idx++] & 63;
-        if ((u0 & 0xF8) == 0xF0) {
-          u0 = ((u0 & 7) << 18) | (u1 << 12) | (u2 << 6) | u3;
-        } else {
-          u4 = u8Array[idx++] & 63;
-          if ((u0 & 0xFC) == 0xF8) {
-            u0 = ((u0 & 3) << 24) | (u1 << 18) | (u2 << 12) | (u3 << 6) | u4;
-          } else {
-            u5 = u8Array[idx++] & 63;
-            u0 = ((u0 & 1) << 30) | (u1 << 24) | (u2 << 18) | (u3 << 12) | (u4 << 6) | u5;
-          }
-        }
+#if ASSERTIONS
+        if ((u0 & 0xF8) != 0xF0) warnOnce('Invalid UTF-8 leading byte 0x' + u0.toString(16) + ' encountered when deserializing a UTF-8 string on the asm.js/wasm heap to a JS string!');
+#endif
+        u0 = ((u0 & 7) << 18) | (u1 << 12) | (u2 << 6) | (u8Array[idx++] & 63);
       }
+
       if (u0 < 0x10000) {
         str += String.fromCharCode(u0);
       } else {
@@ -548,27 +539,15 @@ function stringToUTF8Array(str, outU8Array, outIdx, maxBytesToWrite) {
       outU8Array[outIdx++] = 0xE0 | (u >> 12);
       outU8Array[outIdx++] = 0x80 | ((u >> 6) & 63);
       outU8Array[outIdx++] = 0x80 | (u & 63);
-    } else if (u <= 0x1FFFFF) {
+    } else {
       if (outIdx + 3 >= endIdx) break;
+#if ASSERTIONS
+      if (u >= 0x200000) warnOnce('Invalid Unicode code point 0x' + u.toString(16) + ' encountered when serializing a JS string to an UTF-8 string on the asm.js/wasm heap! (Valid unicode code points should be in range 0-0x1FFFFF).');
+#endif
       outU8Array[outIdx++] = 0xF0 | (u >> 18);
       outU8Array[outIdx++] = 0x80 | ((u >> 12) & 63);
       outU8Array[outIdx++] = 0x80 | ((u >> 6) & 63);
       outU8Array[outIdx++] = 0x80 | (u & 63);
-    } else if (u <= 0x3FFFFFF) {
-      if (outIdx + 4 >= endIdx) break;
-      outU8Array[outIdx++] = 0xF8 | (u >> 24);
-      outU8Array[outIdx++] = 0x80 | ((u >> 18) & 63);
-      outU8Array[outIdx++] = 0x80 | ((u >> 12) & 63);
-      outU8Array[outIdx++] = 0x80 | ((u >> 6) & 63);
-      outU8Array[outIdx++] = 0x80 | (u & 63);
-    } else {
-      if (outIdx + 5 >= endIdx) break;
-      outU8Array[outIdx++] = 0xFC | (u >> 30);
-      outU8Array[outIdx++] = 0x80 | ((u >> 24) & 63);
-      outU8Array[outIdx++] = 0x80 | ((u >> 18) & 63);
-      outU8Array[outIdx++] = 0x80 | ((u >> 12) & 63);
-      outU8Array[outIdx++] = 0x80 | ((u >> 6) & 63);
-      outU8Array[outIdx++] = 0x80 | (u & 63);
     }
   }
   // Null-terminate the pointer to the buffer.