Merge branch 'master' into add_typeurl

Author: Taylor McIntyre

README.md

@@ -285,11 +285,15 @@ The library utilizes JSON descriptors that are equivalent to a .proto definition
 // awesome.json
 {
   "nested": {
-    "AwesomeMessage": {
-      "fields": {
-        "awesomeField": {
-          "type": "string",
-          "id": 1
+    "awesomepackage": {
+      "nested": {
+        "AwesomeMessage": {
+          "fields": {
+            "awesomeField": {
+              "type": "string",
+              "id": 1
+            }
+          }
         }
       }
     }

lib/utf8/index.js

@@ -38,36 +38,27 @@ utf8.length = function utf8_length(string) {
  * @returns {string} String read
  */
 utf8.read = function utf8_read(buffer, start, end) {
-    var len = end - start;
-    if (len < 1)
+    if (end - start < 1) {
         return "";
-    var parts = null,
-        chunk = [],
-        i = 0, // char offset
-        t;     // temporary
-    while (start < end) {
-        t = buffer[start++];
-        if (t < 128)
-            chunk[i++] = t;
-        else if (t > 191 && t < 224)
-            chunk[i++] = (t & 31) << 6 | buffer[start++] & 63;
-        else if (t > 239 && t < 365) {
-            t = ((t & 7) << 18 | (buffer[start++] & 63) << 12 | (buffer[start++] & 63) << 6 | buffer[start++] & 63) - 0x10000;
-            chunk[i++] = 0xD800 + (t >> 10);
-            chunk[i++] = 0xDC00 + (t & 1023);
-        } else
-            chunk[i++] = (t & 15) << 12 | (buffer[start++] & 63) << 6 | buffer[start++] & 63;
-        if (i > 8191) {
-            (parts || (parts = [])).push(String.fromCharCode.apply(String, chunk));
-            i = 0;
-        }
     }
-    if (parts) {
-        if (i)
-            parts.push(String.fromCharCode.apply(String, chunk.slice(0, i)));
-        return parts.join("");
+
+    var str = "";
+    for (var i = start; i < end;) {
+        var t = buffer[i++];
+        if (t <= 0x7F) {
+            str += String.fromCharCode(t);
+        } else if (t >= 0xC0 && t < 0xE0) {
+            str += String.fromCharCode((t & 0x1F) << 6 | buffer[i++] & 0x3F);
+        } else if (t >= 0xE0 && t < 0xF0) {
+            str += String.fromCharCode((t & 0xF) << 12 | (buffer[i++] & 0x3F) << 6 | buffer[i++] & 0x3F);
+        } else if (t >= 0xF0) {
+            var t2 = ((t & 7) << 18 | (buffer[i++] & 0x3F) << 12 | (buffer[i++] & 0x3F) << 6 | buffer[i++] & 0x3F) - 0x10000;
+            str += String.fromCharCode(0xD800 + (t2 >> 10));
+            str += String.fromCharCode(0xDC00 + (t2 & 0x3FF));
+        }
     }
-    return String.fromCharCode.apply(String, chunk.slice(0, i));
+
+    return str;
 };
 
 /**

lib/utf8/tests/data/surrogate_pair_bug.txt

@@ -5,6 +5,9 @@ var utf8 = require("..");
 var data = require("fs").readFileSync(require.resolve("./data/utf8.txt")),
     dataStr = data.toString("utf8");
 
+var surrogatePairErr = require("fs").readFileSync(require.resolve("./data/surrogate_pair_bug.txt")),
+    surrogatePairErrStr = data.toString("utf8");
+
 tape.test("utf8", function(test) {
 
     test.test(test.name + " - length", function(test) {
@@ -30,6 +33,9 @@ tape.test("utf8", function(test) {
         comp = utf8.read(chunkData, 0, chunkData.length);
         test.equal(comp, chunkData.toString("utf8"), "should decode to the same byte data as node buffers (chunk size)");
 
+        comp = utf8.read(surrogatePairErr, 0, surrogatePairErr.length);
+        test.equal(comp, surrogatePairErr.toString("utf8"), "should decode to the same byte data as node buffers (surrogate pair over chunk)");
+
         test.end();
     });