Closes GH-695 Add 'hex' encoding to Buffer

Author: isaacs

doc/api/buffers.markdown

@@ -26,6 +26,8 @@ the first 8 bits of each character. This encoding method is depreciated and
 should be avoided in favor of `Buffer` objects where possible. This encoding
 will be removed in future versions of Node.
 
+* `'hex'` - Encode each byte as two hexidecimal characters.
+
 
 ### new Buffer(size)
 

lib/buffer.js

@@ -17,6 +17,21 @@ SlowBuffer.prototype.inspect = function() {
 };
 
 
+SlowBuffer.prototype.hexSlice = function(start, end) {
+  var len = this.length;
+
+  if (!start || start < 0) start = 0;
+  if (end < 0 || start + end > len) end = len - start;
+
+  var out = '';
+  for (var i = start; i < end; i ++) {
+    out += toHex(this[i]);
+  }
+  return out;
+};
+
+
+
 SlowBuffer.prototype.toString = function(encoding, start, end) {
   encoding = String(encoding || 'utf8').toLowerCase();
   start = +start || 0;
@@ -28,6 +43,9 @@ SlowBuffer.prototype.toString = function(encoding, start, end) {
   }
 
   switch (encoding) {
+    case 'hex':
+      return this.hexSlice(start, end);
+
     case 'utf8':
     case 'utf-8':
       return this.utf8Slice(start, end);
@@ -51,6 +69,23 @@ SlowBuffer.prototype.toString = function(encoding, start, end) {
 };
 
 
+SlowBuffer.prototype.hexWrite = function(string, offset) {
+  var len = string.length;
+  offset = +offset || 0;
+
+  // must be an even number of digits
+  if (len % 2) {
+    throw new Error('Invalid hex string');
+  }
+  for (var i = 0; i < len / 2; i ++) {
+    var byte = parseInt(string.substr(i * 2, 2), 16);
+    if (isNaN(byte)) throw new Error('Invalid hex string');
+    this[offset + i] = byte;
+  }
+  return i;
+}
+
+
 SlowBuffer.prototype.write = function(string, offset, encoding) {
   // Support both (string, offset, encoding)
   // and the legacy (string, encoding, offset)
@@ -64,6 +99,9 @@ SlowBuffer.prototype.write = function(string, offset, encoding) {
   encoding = String(encoding || 'utf8').toLowerCase();
 
   switch (encoding) {
+    case 'hex':
+      return this.hexWrite(string, offset);
+
     case 'utf8':
     case 'utf-8':
       return this.utf8Write(string, offset);
@@ -224,6 +262,10 @@ Buffer.prototype.write = function(string, offset, encoding) {
 
   var ret;
   switch (encoding) {
+    case 'hex':
+      ret = this.parent.hexWrite(string, this.offset + offset, maxLength);
+      break;
+
     case 'utf8':
     case 'utf-8':
       ret = this.parent.utf8Write(string, this.offset + offset, maxLength);
@@ -277,6 +319,9 @@ Buffer.prototype.toString = function(encoding, start, end) {
   end = end + this.offset;
 
   switch (encoding) {
+    case 'hex':
+      return this.parent.hexSlice(start, end);
+
     case 'utf8':
     case 'utf-8':
       return this.parent.utf8Slice(start, end);

src/node.cc

@@ -1084,6 +1084,8 @@ enum encoding ParseEncoding(Handle<Value> encoding_v, enum encoding _default) {
     return UCS2;
   } else if (strcasecmp(*encoding, "binary") == 0) {
     return BINARY;
+  } else if (strcasecmp(*encoding, "hex") == 0) {
+    return HEX;
   } else if (strcasecmp(*encoding, "raw") == 0) {
     fprintf(stderr, "'raw' (array of integers) has been removed. "
                     "Use 'binary'.\n");
@@ -1134,6 +1136,7 @@ ssize_t DecodeBytes(v8::Handle<v8::Value> val, enum encoding encoding) {
 
   if (encoding == UTF8) return str->Utf8Length();
   else if (encoding == UCS2) return str->Length() * 2;
+  else if (encoding == HEX) return str->Length() / 2;
 
   return str->Length();
 }

src/node.h

@@ -44,7 +44,7 @@ do {                                                                      \
                                   __callback##_TEM);                      \
 } while (0)
 
-enum encoding {ASCII, UTF8, BASE64, UCS2, BINARY};
+enum encoding {ASCII, UTF8, BASE64, UCS2, BINARY, HEX};
 enum encoding ParseEncoding(v8::Handle<v8::Value> encoding_v,
                             enum encoding _default = BINARY);
 void FatalException(v8::TryCatch &try_catch);

src/node_buffer.cc

@@ -86,6 +86,8 @@ static size_t ByteLength (Handle<String> string, enum encoding enc) {
     return base64_decoded_size(*v, v.length());
   } else if (enc == UCS2) {
     return string->Length() * 2;
+  } else if (enc == HEX) {
+    return string->Length() / 2;
   } else {
     return string->Length();
   }

test/simple/test-buffer.js

@@ -410,3 +410,34 @@ assert.equal(12, Buffer.byteLength('Il était tué', 'binary'));
 
 // slice(0,0).length === 0
 assert.equal(0, Buffer('hello').slice(0, 0).length);
+
+// test hex toString
+console.log('Create hex string from buffer');
+var hexb = new Buffer(256);
+for (var i = 0; i < 256; i ++) {
+  hexb[i] = i;
+}
+var hexStr = hexb.toString('hex');
+assert.equal(hexStr,
+             '000102030405060708090a0b0c0d0e0f'+
+             '101112131415161718191a1b1c1d1e1f'+
+             '202122232425262728292a2b2c2d2e2f'+
+             '303132333435363738393a3b3c3d3e3f'+
+             '404142434445464748494a4b4c4d4e4f'+
+             '505152535455565758595a5b5c5d5e5f'+
+             '606162636465666768696a6b6c6d6e6f'+
+             '707172737475767778797a7b7c7d7e7f'+
+             '808182838485868788898a8b8c8d8e8f'+
+             '909192939495969798999a9b9c9d9e9f'+
+             'a0a1a2a3a4a5a6a7a8a9aaabacadaeaf'+
+             'b0b1b2b3b4b5b6b7b8b9babbbcbdbebf'+
+             'c0c1c2c3c4c5c6c7c8c9cacbcccdcecf'+
+             'd0d1d2d3d4d5d6d7d8d9dadbdcdddedf'+
+             'e0e1e2e3e4e5e6e7e8e9eaebecedeeef'+
+             'f0f1f2f3f4f5f6f7f8f9fafbfcfdfeff');
+
+console.log('Create buffer from hex string');
+var hexb2 = new Buffer(hexStr, 'hex');
+for (var i = 0; i < 256; i ++) {
+  assert.equal(hexb2[i], hexb[i]);
+}