From f559f5ca70de1658bbf69fb78c31cace215e532c Mon Sep 17 00:00:00 2001
From: Michael Jumper <mjumper@apache.org>
Date: Fri, 11 Feb 2022 16:33:02 -0800
Subject: [PATCH] GUACAMOLE-896: Add JavaScript UTF-8 parser implementation.

---
 .../src/main/webapp/modules/StringReader.js   | 101 ++------------
 .../src/main/webapp/modules/UTF8Parser.js     | 126 ++++++++++++++++++
 2 files changed, 134 insertions(+), 93 deletions(-)
 create mode 100644 guacamole-common-js/src/main/webapp/modules/UTF8Parser.js

diff --git a/guacamole-common-js/src/main/webapp/modules/StringReader.js b/guacamole-common-js/src/main/webapp/modules/StringReader.js
index 247b8b9a2..37b555c06 100644
--- a/guacamole-common-js/src/main/webapp/modules/StringReader.js
+++ b/guacamole-common-js/src/main/webapp/modules/StringReader.js
@@ -38,6 +38,13 @@ Guacamole.StringReader = function(stream) {
      */
     var guac_reader = this;
 
+    /**
+     * Parser for received UTF-8 data.
+     *
+     * @type {!Guacamole.UTF8Parser}
+     */
+    var utf8Parser = new Guacamole.UTF8Parser();
+
     /**
      * Wrapped Guacamole.ArrayBufferReader.
      *
@@ -46,103 +53,11 @@ Guacamole.StringReader = function(stream) {
      */
     var array_reader = new Guacamole.ArrayBufferReader(stream);
 
-    /**
-     * The number of bytes remaining for the current codepoint.
-     *
-     * @private
-     * @type {!number}
-     */
-    var bytes_remaining = 0;
-
-    /**
-     * The current codepoint value, as calculated from bytes read so far.
-     *
-     * @private
-     * @type {!number}
-     */
-    var codepoint = 0;
-
-    /**
-     * Decodes the given UTF-8 data into a Unicode string. The data may end in
-     * the middle of a multibyte character.
-     * 
-     * @private
-     * @param {!ArrayBuffer} buffer
-     *     Arbitrary UTF-8 data.
-     *
-     * @return {!string}
-     *     A decoded Unicode string.
-     */
-    function __decode_utf8(buffer) {
-
-        var text = "";
-
-        var bytes = new Uint8Array(buffer);
-        for (var i=0; i<bytes.length; i++) {
-
-            // Get current byte
-            var value = bytes[i];
-
-            // Start new codepoint if nothing yet read
-            if (bytes_remaining === 0) {
-
-                // 1 byte (0xxxxxxx)
-                if ((value | 0x7F) === 0x7F)
-                    text += String.fromCharCode(value);
-
-                // 2 byte (110xxxxx)
-                else if ((value | 0x1F) === 0xDF) {
-                    codepoint = value & 0x1F;
-                    bytes_remaining = 1;
-                }
-
-                // 3 byte (1110xxxx)
-                else if ((value | 0x0F )=== 0xEF) {
-                    codepoint = value & 0x0F;
-                    bytes_remaining = 2;
-                }
-
-                // 4 byte (11110xxx)
-                else if ((value | 0x07) === 0xF7) {
-                    codepoint = value & 0x07;
-                    bytes_remaining = 3;
-                }
-
-                // Invalid byte
-                else
-                    text += "\uFFFD";
-
-            }
-
-            // Continue existing codepoint (10xxxxxx)
-            else if ((value | 0x3F) === 0xBF) {
-
-                codepoint = (codepoint << 6) | (value & 0x3F);
-                bytes_remaining--;
-
-                // Write codepoint if finished
-                if (bytes_remaining === 0)
-                    text += String.fromCharCode(codepoint);
-
-            }
-
-            // Invalid byte
-            else {
-                bytes_remaining = 0;
-                text += "\uFFFD";
-            }
-
-        }
-
-        return text;
-
-    }
-
     // Receive blobs as strings
     array_reader.ondata = function(buffer) {
 
         // Decode UTF-8
-        var text = __decode_utf8(buffer);
+        var text = utf8Parser.decode(buffer);
 
         // Call handler, if present
         if (guac_reader.ontext)
diff --git a/guacamole-common-js/src/main/webapp/modules/UTF8Parser.js b/guacamole-common-js/src/main/webapp/modules/UTF8Parser.js
new file mode 100644
index 000000000..e5fd94585
--- /dev/null
+++ b/guacamole-common-js/src/main/webapp/modules/UTF8Parser.js
@@ -0,0 +1,126 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+var Guacamole = Guacamole || {};
+
+/**
+ * Parser that decodes UTF-8 text from a series of provided ArrayBuffers.
+ * Multi-byte characters that continue from one buffer to the next are handled
+ * correctly.
+ *
+ * @constructor
+ */
+Guacamole.UTF8Parser = function UTF8Parser() {
+
+    /**
+     * The number of bytes remaining for the current codepoint.
+     *
+     * @private
+     * @type {!number}
+     */
+    var bytesRemaining = 0;
+
+    /**
+     * The current codepoint value, as calculated from bytes read so far.
+     *
+     * @private
+     * @type {!number}
+     */
+    var codepoint = 0;
+
+    /**
+     * Decodes the given UTF-8 data into a Unicode string, returning a string
+     * containing all complete UTF-8 characters within the provided data. The
+     * data may end in the middle of a multi-byte character, in which case the
+     * complete character will be returned from a later call to decode() after
+     * enough bytes have been provided.
+     *
+     * @private
+     * @param {!ArrayBuffer} buffer
+     *     Arbitrary UTF-8 data.
+     *
+     * @return {!string}
+     *     The decoded Unicode string.
+     */
+    this.decode = function decode(buffer) {
+
+        var text = '';
+
+        var bytes = new Uint8Array(buffer);
+        for (var i=0; i<bytes.length; i++) {
+
+            // Get current byte
+            var value = bytes[i];
+
+            // Start new codepoint if nothing yet read
+            if (bytesRemaining === 0) {
+
+                // 1 byte (0xxxxxxx)
+                if ((value | 0x7F) === 0x7F)
+                    text += String.fromCharCode(value);
+
+                // 2 byte (110xxxxx)
+                else if ((value | 0x1F) === 0xDF) {
+                    codepoint = value & 0x1F;
+                    bytesRemaining = 1;
+                }
+
+                // 3 byte (1110xxxx)
+                else if ((value | 0x0F )=== 0xEF) {
+                    codepoint = value & 0x0F;
+                    bytesRemaining = 2;
+                }
+
+                // 4 byte (11110xxx)
+                else if ((value | 0x07) === 0xF7) {
+                    codepoint = value & 0x07;
+                    bytesRemaining = 3;
+                }
+
+                // Invalid byte
+                else
+                    text += '\uFFFD';
+
+            }
+
+            // Continue existing codepoint (10xxxxxx)
+            else if ((value | 0x3F) === 0xBF) {
+
+                codepoint = (codepoint << 6) | (value & 0x3F);
+                bytesRemaining--;
+
+                // Write codepoint if finished
+                if (bytesRemaining === 0)
+                    text += String.fromCharCode(codepoint);
+
+            }
+
+            // Invalid byte
+            else {
+                bytesRemaining = 0;
+                text += '\uFFFD';
+            }
+
+        }
+
+        return text;
+
+    };
+
+};
\ No newline at end of file