nodejs · mcollina · Jun 27, 2017
diff --git a/README.md b/README.md
@@ -15,7 +15,7 @@ npm install --save string_decoder
 
 This package is a mirror of the string_decoder implementation in Node-core.
 
-Full documentation may be found on the [Node.js website](https://nodejs.org/dist/v7.8.0/docs/api/).
+Full documentation may be found on the [Node.js website](https://nodejs.org/dist/v8.1.2/docs/api/).
 
 As of version 1.0.0 **string_decoder** uses semantic versioning.
 

diff --git a/build/build.js b/build/build.js
@@ -138,7 +138,7 @@ pump(
     // Grab the nodejs/node test/common.js
 
     processFile(
-        testsrcurl.replace(/parallel\/$/, 'common.js')
+        testsrcurl.replace(/parallel\/$/, 'common/index.js')
       , path.join(testourroot, '../common.js')
       , testReplace['common.js']
     )

diff --git a/build/test-replacements.js b/build/test-replacements.js
@@ -56,7 +56,23 @@ module.exports['common.js'] = [
 module.exports['test-string-decoder.js'] = [
     // test removed because it is V8-version dependant.
     [
-        /test\('utf-8', bufferShim.from\('EDA0B5EDB08D'.*\n.*\n/
+        /test\('utf-8', bufferShim\.from\('EDA0B5EDB08D'.*\n.*\n/
+      , ''
+    ],
+  , [
+        /test\('utf-8', bufferShim\.from\('F0B841', 'hex'.*\n/
+      , ''
+    ]
+  , [
+        /test\('utf-8', bufferShim\.from\('CCE2B8B8', 'hex'.*\n/
+      , ''
+    ]
+  , [
+        /test\('utf-8', bufferShim\.from\('E2B8CCB8', 'hex'.*\n/
+      , ''
+    ]
+  , [
+        /assert\.strictEqual\(decoder\.end(), '\ufffd'\);\n/
       , ''
     ]
 ]
diff --git a/lib/string_decoder.js b/lib/string_decoder.js
@@ -1,3 +1,24 @@
+// Copyright Joyent, Inc. and other Node contributors.
+//
+// Permission is hereby granted, free of charge, to any person obtaining a
+// copy of this software and associated documentation files (the
+// "Software"), to deal in the Software without restriction, including
+// without limitation the rights to use, copy, modify, merge, publish,
+// distribute, sublicense, and/or sell copies of the Software, and to permit
+// persons to whom the Software is furnished to do so, subject to the
+// following conditions:
+//
+// The above copyright notice and this permission notice shall be included
+// in all copies or substantial portions of the Software.
+//
+// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+// USE OR OTHER DEALINGS IN THE SOFTWARE.
+
 'use strict';
 
 var Buffer = require('safe-buffer').Buffer;
@@ -112,10 +133,10 @@ StringDecoder.prototype.fillLast = function (buf) {
 };
 
 // Checks the type of a UTF-8 byte, whether it's ASCII, a leading byte, or a
-// continuation byte.
+// continuation byte. If an invalid byte is detected, -2 is returned.
 function utf8CheckByte(byte) {
   if (byte <= 0x7F) return 0;else if (byte >> 5 === 0x06) return 2;else if (byte >> 4 === 0x0E) return 3;else if (byte >> 3 === 0x1E) return 4;
-  return -1;
+  return byte >> 6 === 0x02 ? -1 : -2;
 }
 
 // Checks at most 3 bytes at the end of a Buffer in order to detect an
@@ -129,13 +150,13 @@ function utf8CheckIncomplete(self, buf, i) {
     if (nb > 0) self.lastNeed = nb - 1;
     return nb;
   }
-  if (--j < i) return 0;
+  if (--j < i || nb === -2) return 0;
   nb = utf8CheckByte(buf[j]);
   if (nb >= 0) {
     if (nb > 0) self.lastNeed = nb - 2;
     return nb;
   }
-  if (--j < i) return 0;
+  if (--j < i || nb === -2) return 0;
   nb = utf8CheckByte(buf[j]);
   if (nb >= 0) {
     if (nb > 0) {
@@ -149,25 +170,25 @@ function utf8CheckIncomplete(self, buf, i) {
 // Validates as many continuation bytes for a multi-byte UTF-8 character as
 // needed or are available. If we see a non-continuation byte where we expect
 // one, we "replace" the validated continuation bytes we've seen so far with
-// UTF-8 replacement characters ('\ufffd'), to match v8's UTF-8 decoding
+// a single UTF-8 replacement character ('\ufffd'), to match v8's UTF-8 decoding
 // behavior. The continuation byte check is included three times in the case
 // where all of the continuation bytes for a character exist in the same buffer.
 // It is also done this way as a slight performance increase instead of using a
 // loop.
 function utf8CheckExtraBytes(self, buf, p) {
   if ((buf[0] & 0xC0) !== 0x80) {
     self.lastNeed = 0;
-    return '\ufffd'.repeat(p);
+    return '\ufffd';
   }
   if (self.lastNeed > 1 && buf.length > 1) {
     if ((buf[1] & 0xC0) !== 0x80) {
       self.lastNeed = 1;
-      return '\ufffd'.repeat(p + 1);
+      return '\ufffd';
     }
     if (self.lastNeed > 2 && buf.length > 2) {
       if ((buf[2] & 0xC0) !== 0x80) {
         self.lastNeed = 2;
-        return '\ufffd'.repeat(p + 2);
+        return '\ufffd';
       }
     }
   }
@@ -198,11 +219,11 @@ function utf8Text(buf, i) {
   return buf.toString('utf8', i, end);
 }
 
-// For UTF-8, a replacement character for each buffered byte of a (partial)
-// character needs to be added to the output.
+// For UTF-8, a replacement character is added when ending on a partial
+// character.
 function utf8End(buf) {
   var r = buf && buf.length ? this.write(buf) : '';
-  if (this.lastNeed) return r + '\ufffd'.repeat(this.lastTotal - this.lastNeed);
+  if (this.lastNeed) return r + '\ufffd';
   return r;
 }