string_decoder: Add more comments

felixge · tjfontaine · commit 80eff968292a · 2014-06-06T15:07:29.000-07:00
diff --git a/lib/string_decoder.js b/lib/string_decoder.js
@@ -25,6 +25,14 @@ function assertEncoding(encoding) {
   }
 }
 
+// StringDecoder provides an interface for efficiently splitting a series of
+// buffers into a series of JS strings without breaking apart multi-byte
+// characters. CESU-8 is handled as part of the UTF-8 encoding.
+//
+// @TODO Handling all encodings inside a single object makes it very difficult
+// to reason about this code, so it should be split up in the future.
+// @TODO There should be a utf8-strict encoding that rejects invalid UTF-8 code
+// points as used by CESU-8.
 var StringDecoder = exports.StringDecoder = function(encoding) {
   this.encoding = (encoding || 'utf8').toLowerCase().replace(/[-_]/, '');
   assertEncoding(encoding);
@@ -49,12 +57,25 @@ var StringDecoder = exports.StringDecoder = function(encoding) {
       return;
   }
 
+  // Enough space to store all bytes of a single character. UTF-8 needs 4
+  // bytes, but CESU-8 may require up to 6 (3 bytes per surrogate).
   this.charBuffer = new Buffer(6);
+  // Number of bytes received for the current incomplete multi-byte character.
   this.charReceived = 0;
+  // Number of bytes expected for the current incomplete multi-byte character.
   this.charLength = 0;
 };
 
 
+// write decodes the given buffer and returns it as JS string that is
+// guaranteed to not contain any partial multi-byte characters. Any partial
+// character found at the end of the buffer is buffered up, and will be
+// returned when calling write again with the remaining bytes.
+//
+// Note: Converting a Buffer containing an orphan surrogate to a String
+// currently works, but converting a String to a Buffer (via `new Buffer`, or
+// Buffer#write) will replace incomplete surrogates with the unicode
+// replacement character. See https://codereview.chromium.org/121173009/ .
 StringDecoder.prototype.write = function(buffer) {
   var charStr = '';
   // if our last write ended with an incomplete multibyte character
@@ -123,6 +144,10 @@ StringDecoder.prototype.write = function(buffer) {
   return charStr;
 };
 
+// detectIncompleteChar determines if there is an incomplete UTF-8 character at
+// the end of the given buffer. If so, it sets this.charLength to the byte
+// length that character, and sets this.charReceived to the number of bytes
+// that are available for this character.
 StringDecoder.prototype.detectIncompleteChar = function(buffer) {
   // determine how many bytes we have to check at the end of this buffer
   var i = (buffer.length >= 3) ? 3 : buffer.length;
