Add support for encoding option

git-svn-id: http://php-reader.googlecode.com/svn/trunk@129 51a70ab9-7547-0410-9469-37e369ee0574

src/ID3/Frame.php

@@ -183,7 +183,7 @@ class ID3_Frame extends ID3_Object
       $this->_size = $dataLength;
       
       if ($this->hasFlag(self::UNSYNCHRONISATION) ||
-          $this->getOption("unsyncronisation", false) === true)
+          $this->getOption("unsynchronisation", false) === true)
         $this->_data = $this->decodeUnsynchronisation($this->_data);
     }
   }
@@ -246,7 +246,7 @@ class ID3_Frame extends ID3_Object
     $this->_data = $data;
     $this->_size = strlen($data);
   }
-
+  
   /**
    * Returns the frame raw data.
    *
@@ -285,8 +285,9 @@ class ID3_Frame extends ID3_Object
         $data = Transform::toUInt32BE($this->encodeSynchsafe32($this->_size)) .
           $data;
         $flags |= self::DATA_LENGTH_INDICATOR | self::UNSYNCHRONISATION;
-        $this->setOption("unsyncronisation", true);
+        $this->setOption("unsynchronisation", true);
-      }
+      } else
+        $flags &= ~(self::DATA_LENGTH_INDICATOR | self::UNSYNCHRONISATION);
     }
     return Transform::toString8(substr($this->_identifier, 0, 4), 4) .
       Transform::toUInt32BE($this->encodeSynchsafe32($size)) .

src/ID3/Frame/APIC.php

@@ -80,7 +80,7 @@ final class ID3_Frame_APIC extends ID3_Frame
      "Publisher/Studio logotype");
   
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_mimeType = "image/unknown";
@@ -107,29 +107,41 @@ final class ID3_Frame_APIC extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
 
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_mimeType = substr
       ($this->_data, 1, ($pos = strpos($this->_data, "\0", 1)) - 1);
     $this->_imageType = Transform::fromUInt8($this->_data[++$pos]);
     $this->_data = substr($this->_data, $pos + 1);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list ($this->_description, $this->_imageData) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16($this->_description), "utf-16");
       break;
     case self::UTF16BE:
       list ($this->_description, $this->_imageData) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      break;
+    case self::UTF8:
+      list ($this->_description, $this->_imageData) =
+        $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString
+        ($this->_description, "utf-8");
       break;
     default:
       list ($this->_description, $this->_imageData) =
         $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString
+        ($this->_description, "iso-8859-1");
     }
     
     $this->_imageSize = strlen($this->_imageData);
@@ -138,6 +150,11 @@ final class ID3_Frame_APIC extends ID3_Frame
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -145,6 +162,12 @@ final class ID3_Frame_APIC extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/AbstractText.php

@@ -59,7 +59,7 @@ abstract class ID3_Frame_AbstractText extends ID3_Frame
    *
    * @var integer
    */
-  protected $_encoding = ID3_Encoding::UTF8;
+  protected $_encoding;
   
   /**
    * The text array.
@@ -78,29 +78,43 @@ abstract class ID3_Frame_AbstractText extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_data = substr($this->_data, 1);
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
-      $this->_text =
+      $this->_text = $this->convertString
-        $this->explodeString16(Transform::fromString16($this->_data));
+        ($this->explodeString16(Transform::fromString16($this->_data)),
+         "utf-16");
       break;
     case self::UTF16BE:
-      $this->_text =
+      $this->_text = $this->convertString
-        $this->explodeString16(Transform::fromString16BE($this->_data));
+        ($this->explodeString16(Transform::fromString16BE($this->_data)),
+         "utf-16be");
+      break;
+    case self::UTF8:
+      $this->_text = $this->convertString
+        ($this->explodeString8(Transform::fromString8($this->_data)), "utf-8");
       break;
     default:
-      $this->_text =
+      $this->_text = $this->convertString
-        $this->explodeString8(Transform::fromString8($this->_data));
+        ($this->explodeString8(Transform::fromString8($this->_data)),
+         "iso-8859-1");
     }
   }
   
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -108,6 +122,12 @@ abstract class ID3_Frame_AbstractText extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/COMM.php

@@ -62,7 +62,7 @@ final class ID3_Frame_COMM extends ID3_Frame
   implements ID3_Encoding, ID3_Language
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_language = "und";
@@ -83,39 +83,60 @@ final class ID3_Frame_COMM extends ID3_Frame
   {
     parent::__construct($reader, $options);
 
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_language = substr($this->_data, 1, 3);
     if ($this->_language == "XXX")
       $this->_language = "und";
     $this->_data = substr($this->_data, 4);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list ($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString16($this->_text);
+        (Transform::fromString16($this->_description), "utf-16");
+      $this->_text = $this->convertString
+        (Transform::fromString16($this->_text), "utf-16");
       break;
     case self::UTF16BE:
       list ($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString16BE($this->_text);
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      $this->_text = $this->convertString
+        (Transform::fromString16BE($this->_text), "utf-16be");
+      break;
+    case self::UTF8:
+      list ($this->_description, $this->_text) =
+        $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "utf-8");
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_text), "utf-8");
       break;
     default:
       list ($this->_description, $this->_text) =
         $this->explodeString8($this->_data, 2);
-      $this->_description = Transform::fromString8($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString8($this->_text);
+        (Transform::fromString8($this->_description), "iso-8859-1");
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_text), "iso-8859-1");
     }
   }
   
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -123,6 +144,12 @@ final class ID3_Frame_COMM extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/COMR.php

@@ -72,7 +72,7 @@ final class ID3_Frame_COMR extends ID3_Frame
      "Non-musical merchandise");
 
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_currency = "EUR";
@@ -114,10 +114,12 @@ final class ID3_Frame_COMR extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
 
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     list($pricing, $this->_data) =
       $this->explodeString8(substr($this->_data, 1), 2);
     $this->_currency = substr($pricing, 0, 3);
@@ -128,24 +130,38 @@ final class ID3_Frame_COMR extends ID3_Frame
     $this->_delivery = Transform::fromUInt8($this->_data[0]);
     $this->_data = substr($this->_data, 1);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list ($this->_seller, $this->_description, $this->_data) =
         $this->explodeString16($this->_data, 3);
-      $this->_seller = Transform::fromString16($this->_seller);
+      $this->_seller = $this->convertString
-      $this->_description = Transform::fromString16($this->_description);
+        (Transform::fromString16($this->_seller), "utf-16");
+      $this->_description = $this->convertString
+        (Transform::fromString16($this->_description), "utf-16");
       break;
     case self::UTF16BE:
       list ($this->_seller, $this->_description, $this->_data) =
         $this->explodeString16($this->_data, 3);
-      $this->_seller = Transform::fromString16BE($this->_seller);
+      $this->_seller = $this->convertString
-      $this->_description = Transform::fromString16BE($this->_description);
+        (Transform::fromString16BE($this->_seller), "utf-16be");
+      $this->_description = $this->convertString
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      break;
+    case self::UTF8:
+      list ($this->_seller, $this->_description, $this->_data) =
+        $this->explodeString8($this->_data, 3);
+      $this->_seller = $this->convertString
+        (Transform::fromString8($this->_seller), "utf-8");
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "utf-8");
       break;
     default:
       list ($this->_seller, $this->_description, $this->_data) =
         $this->explodeString8($this->_data, 3);
-      $this->_seller = Transform::fromString8($this->_seller);
+      $this->_seller = $this->convertString
-      $this->_description = Transform::fromString8($this->_description);
+        (Transform::fromString8($this->_seller), "iso-8859-1");
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "iso-8859-1");
     }
     
     if (strlen($this->_data) == 0)
@@ -160,6 +176,11 @@ final class ID3_Frame_COMR extends ID3_Frame
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -167,6 +188,12 @@ final class ID3_Frame_COMR extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/GEOB.php

@@ -56,7 +56,7 @@ final class ID3_Frame_GEOB extends ID3_Frame
   implements ID3_Encoding
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_mimeType;
@@ -80,38 +80,59 @@ final class ID3_Frame_GEOB extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
 
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_mimeType = substr
       ($this->_data, 1, ($pos = strpos($this->_data, "\0", 1)) - 1);
     $this->_data = substr($this->_data, $pos + 1);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list ($this->_filename, $this->_description, $this->_objectData) =
         $this->explodeString16($this->_data, 3);
-      $this->_filename = Transform::fromString16($this->_filename);
+      $this->_filename = $this->convertString
-      $this->_description = Transform::fromString16($this->_description);
+        (Transform::fromString16($this->_filename), "utf-16");
+      $this->_description = $this->convertString
+        (Transform::fromString16($this->_description), "utf-16");
       break;
     case self::UTF16BE:
       list ($this->_filename, $this->_description, $this->_objectData) =
         $this->explodeString16($this->_data, 3);
-      $this->_filename = Transform::fromString16BE($this->_filename);
+      $this->_filename = $this->convertString
-      $this->_description = Transform::fromString16BE($this->_description);
+        (Transform::fromString16BE($this->_filename), "utf-16be");
+      $this->_description = $this->convertString
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      break;
+    case self::UTF8:
+      list ($this->_filename, $this->_description, $this->_objectData) =
+        $this->explodeString8($this->_data, 3);
+      $this->_filename = $this->convertString
+        (Transform::fromString8($this->_filename), "utf-8");
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "utf-8");
       break;
     default:
       list ($this->_filename, $this->_description, $this->_objectData) =
         $this->explodeString8($this->_data, 3);
-      $this->_filename = Transform::fromString8($this->_filename);
+      $this->_filename = $this->convertString
-      $this->_description = Transform::fromString8($this->_description);
+        (Transform::fromString8($this->_filename), "iso-8859-1");
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "iso-8859-1");
     }
   }
   
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -119,6 +140,12 @@ final class ID3_Frame_GEOB extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/IPLS.php

@@ -59,7 +59,7 @@ final class ID3_Frame_IPLS extends ID3_Frame
   implements ID3_Encoding
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
 
   /** @var Array */
   private $_people = array();
@@ -74,25 +74,32 @@ final class ID3_Frame_IPLS extends ID3_Frame
   {
     parent::__construct($reader, $options);
 
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
 
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $data = substr($this->_data, 1);
     $order = Transform::MACHINE_ENDIAN_ORDER;
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       $data = $this->explodeString16($data);
       foreach ($data as &$str)
-        $str = Transform::fromString16($str, $order);
+        $str = $this->convertString
+          (Transform::fromString16($str, $order), "utf-16");
       break;
     case self::UTF16BE:
       $data = $this->explodeString16($data);
       foreach ($data as &$str)
-        $str = Transform::fromString16BE($str);
+        $str = $this->convertString
+          (Transform::fromString16BE($str), "utf-16be");
+      break;
+    case self::UTF8:
+      $data = $this->convertString($this->explodeString8($data), "utf-8");
       break;
     default:
-      $data = $this->explodeString8($data);
+      $data = $this->convertString($this->explodeString8($data), "iso-8859-1");
     }
 
     for ($i = 0; $i < count($data) - 1; $i += 2)
@@ -101,14 +108,25 @@ final class ID3_Frame_IPLS extends ID3_Frame
 
   /**
    * Returns the text encoding.
-   *
+   * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
 
   /**
    * Sets the text encoding.
-   *
+   * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/OWNE.php

@@ -59,7 +59,7 @@ final class ID3_Frame_OWNE extends ID3_Frame
   implements ID3_Encoding
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_currency = "EUR";
@@ -83,10 +83,12 @@ final class ID3_Frame_OWNE extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
 
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     list($tmp, $this->_data) =
       $this->explodeString8(substr($this->_data, 1), 2);
     $this->_currency = substr($tmp, 0, 3);
@@ -94,21 +96,33 @@ final class ID3_Frame_OWNE extends ID3_Frame
     $this->_date = substr($this->_data, 0, 8);
     $this->_data = substr($this->_data, 8);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
-      $this->_seller = Transform::fromString16($this->_data);
+      $this->_seller = $this->convertString
+        (Transform::fromString16($this->_data), "utf-16");
       break;
     case self::UTF16BE:
-      $this->_seller = Transform::fromString16BE($this->_data);
+      $this->_seller = $this->convertString
+        (Transform::fromString16BE($this->_data), "utf-16be");
+      break;
+    case self::UTF8:
+      $this->_seller = $this->convertString
+        (Transform::fromString8($this->_data), "utf-8");
       break;
     default:
-      $this->_seller = Transform::fromString8($this->_data);
+      $this->_seller = $this->convertString
+        (Transform::fromString8($this->_data), "iso-8859-1");
     }
   }
 
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -116,6 +130,12 @@ final class ID3_Frame_OWNE extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/SYLT.php

@@ -72,7 +72,7 @@ final class ID3_Frame_SYLT extends ID3_Frame
      "Chord", "Trivia", "URLs to webpages", "URLs to images");
   
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_language = "und";
@@ -99,10 +99,12 @@ final class ID3_Frame_SYLT extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_language = substr($this->_data, 1, 3);
     if ($this->_language == "XXX")
       $this->_language = "und";
@@ -110,39 +112,57 @@ final class ID3_Frame_SYLT extends ID3_Frame
     $this->_type = Transform::fromUInt8($this->_data[5]);
     $this->_data = substr($this->_data, 6);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list($this->_description, $this->_data) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16($this->_description), "utf-16");
       break;
     case self::UTF16BE:
       list($this->_description, $this->_data) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      break;
+    case self::UTF8:
+      list($this->_description, $this->_data) =
+        $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "utf-8");
       break;
     default:
       list($this->_description, $this->_data) =
         $this->explodeString8($this->_data, 2);
-      $this->_description = Transform::fromString8($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "iso-8859-1");
     }
     
     while (strlen($this->_data) > 0) {
-      switch ($this->_encoding) {
+      switch ($encoding) {
       case self::UTF16:
         list($syllable, $this->_data) = 
           $this->explodeString16($this->_data, 2);
-        $syllable = Transform::fromString16($syllable);
+        $syllable = $this->convertString
+          (Transform::fromString16($syllable), "utf-16");
         break;
       case self::UTF16BE:
         list($syllable, $this->_data) = 
           $this->explodeString16($this->_data, 2);
-        $syllable = Transform::fromString16BE($syllable);
+        $syllable = $this->convertString
+          (Transform::fromString16BE($syllable), "utf-16be");
+        break;
+      case self::UTF8:
+        list($syllable, $this->_data) = 
+          $this->explodeString8($this->_data, 2);
+        $syllable = $this->convertString
+          (Transform::fromString8($syllable), "utf-8");
         break;
       default:
         list($syllable, $this->_data) = 
           $this->explodeString8($this->_data, 2);
-        $syllable = Transform::fromString8($syllable);
+        $syllable = $this->convertString
+          (Transform::fromString8($syllable), "iso-8859-1");
       }
       $this->_events[Transform::fromUInt32BE(substr($this->_data, 0, 4))] =
         $syllable;
@@ -154,6 +174,11 @@ final class ID3_Frame_SYLT extends ID3_Frame
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -161,6 +186,12 @@ final class ID3_Frame_SYLT extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/TXXX.php

@@ -72,28 +72,39 @@ final class ID3_Frame_TXXX extends ID3_Frame_AbstractText
   {
     ID3_Frame::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_data = substr($this->_data, 1);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = array(Transform::fromString16($this->_text));
+        (Transform::fromString16($this->_description), "utf-16");
+      $this->_text = $this->convertString
+        (array(Transform::fromString16($this->_text)), "utf-16");
       break;
     case self::UTF16BE:
       list($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = array(Transform::fromString16BE($this->_text));
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      $this->_text = $this->convertString
+        (array(Transform::fromString16BE($this->_text)), "utf-16be");
+      break;
+    case self::UTF8:
+      list($this->_description, $this->_text) = $this->convertString
+        ($this->explodeString8($this->_data, 2), "utf-8");
+      $this->_text = array($this->_text);
       break;
     default:
-      list($this->_description, $this->_text) =
+      list($this->_description, $this->_text) = $this->convertString
-        $this->explodeString8($this->_data, 2);
+        ($this->explodeString8($this->_data, 2), "iso-8859-1");
       $this->_text = array($this->_text);
     }
   }

src/ID3/Frame/USER.php

@@ -60,7 +60,7 @@ final class ID3_Frame_USER extends ID3_Frame
   implements ID3_Encoding, ID3_Language
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_language = "und";
@@ -78,30 +78,44 @@ final class ID3_Frame_USER extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_language = substr($this->_data, 1, 3);
     if ($this->_language == "XXX")
       $this->_language = "und";
     $this->_data = substr($this->_data, 4);
 
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
-      $this->_text = Transform::fromString16($this->_data);
+      $this->_text = $this->convertString
+        (Transform::fromString16($this->_data), "utf-16");
       break;
     case self::UTF16BE:
-      $this->_text = Transform::fromString16BE($this->_data);
+      $this->_text = $this->convertString
+        (Transform::fromString16BE($this->_data), "utf-16be");
+      break;
+    case self::UTF8:
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_data), "utf-8");
       break;
     default:
-      $this->_text = Transform::fromString8($this->_data);
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_data), "iso-8859-1");
     }
   }
   
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -109,6 +123,12 @@ final class ID3_Frame_USER extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/USLT.php

@@ -59,7 +59,7 @@ final class ID3_Frame_USLT extends ID3_Frame
   implements ID3_Encoding, ID3_Language
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_language = "und";
@@ -80,39 +80,60 @@ final class ID3_Frame_USLT extends ID3_Frame
   {
     parent::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_language = substr($this->_data, 1, 3);
     if ($this->_language == "XXX")
       $this->_language = "und";
     $this->_data = substr($this->_data, 4);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list ($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString16($this->_text);
+        (Transform::fromString16($this->_description), "utf-16");
+      $this->_text = $this->convertString
+        (Transform::fromString16($this->_text), "utf-16");
       break;
     case self::UTF16BE:
       list ($this->_description, $this->_text) =
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString16BE($this->_text);
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      $this->_text = $this->convertString
+        (Transform::fromString16BE($this->_text), "utf-16be");
+      break;
+    case self::UTF8:
+      list ($this->_description, $this->_text) =
+        $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString
+        (Transform::fromString8($this->_description), "utf-8");
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_text), "utf-8");
       break;
     default:
       list ($this->_description, $this->_text) =
         $this->explodeString8($this->_data, 2);
-      $this->_description = Transform::fromString8($this->_description);
+      $this->_description = $this->convertString
-      $this->_text = Transform::fromString8($this->_text);
+        (Transform::fromString8($this->_description), "iso-8859-1");
+      $this->_text = $this->convertString
+        (Transform::fromString8($this->_text), "iso-8859-1");
     }
   }
   
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer
    */
   public function getEncoding() { return $this->_encoding; }
@@ -120,6 +141,12 @@ final class ID3_Frame_USLT extends ID3_Frame
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Frame/WXXX.php

@@ -59,7 +59,7 @@ final class ID3_Frame_WXXX extends ID3_Frame_AbstractLink
   implements ID3_Encoding
 {
   /** @var integer */
-  private $_encoding = ID3_Encoding::UTF8;
+  private $_encoding;
   
   /** @var string */
   private $_description;
@@ -74,27 +74,37 @@ final class ID3_Frame_WXXX extends ID3_Frame_AbstractLink
   {
     ID3_Frame::__construct($reader, $options);
     
+    $this->_encoding = $this->getOption("encoding", ID3_Encoding::UTF8);
+    
     if ($reader === null)
       return;
     
-    $this->_encoding = Transform::fromUInt8($this->_data[0]);
+    $encoding = Transform::fromUInt8($this->_data[0]);
     $this->_data = substr($this->_data, 1);
     
-    switch ($this->_encoding) {
+    switch ($encoding) {
     case self::UTF16:
       list($this->_description, $this->_link) = 
         $this->explodeString16($this->_data, 2);
-      $this->_description = Transform::fromString16($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16($this->_description), "utf-16");
       break;
     case self::UTF16BE:
-        list($this->_description, $this->_link) = 
+      list($this->_description, $this->_link) = 
-          $this->explodeString16($this->_data, 2);
+        $this->explodeString16($this->_data, 2);
-        $this->_description = Transform::fromString16BE($this->_description);
+      $this->_description = $this->convertString
+        (Transform::fromString16BE($this->_description), "utf-16be");
+      break;
+    case self::UTF8:
+      list($this->_description, $this->_link) =
+        $this->explodeString8($this->_data, 2);
+      $this->_description = $this->convertString($this->_description, "utf-8");
       break;
     default:
       list($this->_description, $this->_link) =
         $this->explodeString8($this->_data, 2);
-      break;
+      $this->_description = $this->convertString
+        ($this->_description, "iso-8859-1");
     }
     $this->_link = implode($this->explodeString8($this->_link, 1), "");
   }
@@ -102,6 +112,11 @@ final class ID3_Frame_WXXX extends ID3_Frame_AbstractLink
   /**
    * Returns the text encoding.
    * 
+   * All the strings read from a file are automatically converted to the
+   * character encoding specified with the <var>encoding</var> option. See
+   * {@link ID3v2} for details. This method returns the original text encoding
+   * used to write the frame.
+   * 
    * @return integer The encoding.
    */
   public function getEncoding() { return $this->_encoding; }
@@ -109,6 +124,12 @@ final class ID3_Frame_WXXX extends ID3_Frame_AbstractLink
   /**
    * Sets the text encoding.
    * 
+   * All the string written to the frame are done so using given character
+   * encoding. No conversions of existing data take place upon the call to this
+   * method thus all texts must be given in given character encoding.
+   * 
+   * The default character encoding used to write the frame is UTF-8.
+   * 
    * @see ID3_Encoding
    * @param integer $encoding The text encoding.
    */

src/ID3/Object.php

@@ -195,7 +195,7 @@ abstract class ID3_Object
   /**
    * Reverses the unsynchronisation scheme from the given data string.
    * 
-   * @see encodeUnsyncronisation
+   * @see encodeUnsynchronisation
    * @param string $data The input data.
    * @return string
    */
@@ -248,4 +248,42 @@ abstract class ID3_Object
   {
     return preg_split("/\\x00/", $value, $limit);
   }
+  
+  /**
+   * Converts string to requested character encoding and returns it. See the
+   * documentation of iconv for accepted values for encoding.
+   *
+   * @param string|Array $string
+   * @param string $encoding
+   */
+  protected function convertString($string, $encoding)
+  {
+    $target = $this->getOption("encoding", ID3_Encoding::UTF8);
+    switch ($target) {
+    case ID3_Encoding::UTF16:
+      $target = "utf-16";
+      break;
+    case ID3_Encoding::UTF16LE:
+      $target = "utf-16le";
+      break;
+    case ID3_Encoding::UTF16BE:
+      $target = "utf-16be";
+      break;
+    case ID3_Encoding::UTF8:
+      $target = "utf-8";
+      break;
+    default:
+      $target = "iso-8859-1";
+    }
+
+    if (strtolower($target) == strtolower($encoding))
+      return $string;
+    
+    if (is_array($string))
+      foreach ($string as $key => $value)
+        $string[$key] = iconv($encoding, $target, $value);
+    else
+      $string = iconv($encoding, $target, $string);
+    return $string;
+  }
 }

src/ID3v2.php

@@ -96,6 +96,10 @@ final class ID3v2
    * may also be given as the only parameter.
    *
    * The following options are currently recognized:
+   *   o encoding -- Indicates the encoding that all the texts are presented
+   *     with. By default this is set to ID3_Encoding::UTF8. See the
+   *     documentation of the {@link ID3_Encoding} interface for accepted
+   *     values. Conversions are carried out using iconv.
    *   o version -- The ID3v2 tag version to use in write operation. This option
    *     is automatically set when a tag is read from a file and defaults to
    *     version 4.0 for tag write.