diff -r 490d5cc509ed -r cf61fcea0001 wp/wp-includes/ID3/module.tag.id3v2.php --- a/wp/wp-includes/ID3/module.tag.id3v2.php Tue Jun 09 11:14:17 2015 +0000 +++ b/wp/wp-includes/ID3/module.tag.id3v2.php Mon Oct 14 17:39:30 2019 +0200 @@ -71,7 +71,7 @@ if ($id3v2_majorversion > 4) { // this script probably won't correctly parse ID3v2.5.x and above (if it ever exists) - $info['error'][] = 'this script only parses up to ID3v2.4.x - this tag is ID3v2.'.$id3v2_majorversion.'.'.$thisfile_id3v2['minorversion']; + $this->error('this script only parses up to ID3v2.4.x - this tag is ID3v2.'.$id3v2_majorversion.'.'.$thisfile_id3v2['minorversion']); return false; } @@ -241,7 +241,7 @@ } if ($thisfile_id3v2['exthead']['length'] != $extended_header_offset) { - $info['warning'][] = 'ID3v2.4 extended header length mismatch (expecting '.intval($thisfile_id3v2['exthead']['length']).', found '.intval($extended_header_offset).')'; + $this->warning('ID3v2.4 extended header length mismatch (expecting '.intval($thisfile_id3v2['exthead']['length']).', found '.intval($extended_header_offset).')'); } } @@ -260,7 +260,7 @@ if ($framedata{$i} != "\x00") { $thisfile_id3v2['padding']['valid'] = false; $thisfile_id3v2['padding']['errorpos'] = $thisfile_id3v2['padding']['start'] + $i; - $info['warning'][] = 'Invalid ID3v2 padding found at offset '.$thisfile_id3v2['padding']['errorpos'].' (the remaining '.($thisfile_id3v2['padding']['length'] - $i).' bytes are considered invalid)'; + $this->warning('Invalid ID3v2 padding found at offset '.$thisfile_id3v2['padding']['errorpos'].' (the remaining '.($thisfile_id3v2['padding']['length'] - $i).' bytes are considered invalid)'); break; } } @@ -300,7 +300,7 @@ } elseif (($frame_name == "\x00".'MP3') || ($frame_name == "\x00\x00".'MP') || ($frame_name == ' MP3') || ($frame_name == 'MP3e')) { // MP3ext known broken frames - "ok" for the purposes of this test } elseif (($id3v2_majorversion == 4) && ($this->IsValidID3v2FrameName(substr($framedata, getid3_lib::BigEndian2Int(substr($frame_header, 4, 4), 0), 4), 3))) { - $info['warning'][] = 'ID3v2 tag written as ID3v2.4, but with non-synchsafe integers (ID3v2.3 style). Older versions of (Helium2; iTunes) are known culprits of this. Tag has been parsed as ID3v2.3'; + $this->warning('ID3v2 tag written as ID3v2.4, but with non-synchsafe integers (ID3v2.3 style). Older versions of (Helium2; iTunes) are known culprits of this. Tag has been parsed as ID3v2.3'); $id3v2_majorversion = 3; $frame_size = getid3_lib::BigEndian2Int(substr($frame_header, 4, 4), 0); // 32-bit integer } @@ -322,16 +322,16 @@ if ($framedata{$i} != "\x00") { $thisfile_id3v2['padding']['valid'] = false; $thisfile_id3v2['padding']['errorpos'] = $thisfile_id3v2['padding']['start'] + $i; - $info['warning'][] = 'Invalid ID3v2 padding found at offset '.$thisfile_id3v2['padding']['errorpos'].' (the remaining '.($thisfile_id3v2['padding']['length'] - $i).' bytes are considered invalid)'; + $this->warning('Invalid ID3v2 padding found at offset '.$thisfile_id3v2['padding']['errorpos'].' (the remaining '.($thisfile_id3v2['padding']['length'] - $i).' bytes are considered invalid)'); break; } } break; // skip rest of ID3v2 header } - if ($frame_name == 'COM ') { - $info['warning'][] = 'error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))). [Note: this particular error has been known to happen with tags edited by iTunes (versions "X v2.0.3", "v3.0.1" are known-guilty, probably others too)]'; - $frame_name = 'COMM'; + if ($iTunesBrokenFrameNameFixed = self::ID3v22iTunesBrokenFrameName($frame_name)) { + $this->warning('error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))). [Note: this particular error has been known to happen with tags edited by iTunes (versions "X v2.0.3", "v3.0.1", "v7.0.0.70" are known-guilty, probably others too)]. Translated frame name from "'.str_replace("\x00", ' ', $frame_name).'" to "'.$iTunesBrokenFrameNameFixed.'" for parsing.'); + $frame_name = $iTunesBrokenFrameNameFixed; } if (($frame_size <= strlen($framedata)) && ($this->IsValidID3v2FrameName($frame_name, $id3v2_majorversion))) { @@ -355,28 +355,28 @@ // next frame is valid, just skip the current frame $framedata = substr($framedata, $frame_size); - $info['warning'][] = 'Next ID3v2 frame is valid, skipping current frame.'; + $this->warning('Next ID3v2 frame is valid, skipping current frame.'); } else { // next frame is invalid too, abort processing //unset($framedata); $framedata = null; - $info['error'][] = 'Next ID3v2 frame is also invalid, aborting processing.'; + $this->error('Next ID3v2 frame is also invalid, aborting processing.'); } } elseif ($frame_size == strlen($framedata)) { // this is the last frame, just skip - $info['warning'][] = 'This was the last ID3v2 frame.'; + $this->warning('This was the last ID3v2 frame.'); } else { // next frame is invalid too, abort processing //unset($framedata); $framedata = null; - $info['warning'][] = 'Invalid ID3v2 frame size, aborting.'; + $this->warning('Invalid ID3v2 frame size, aborting.'); } if (!$this->IsValidID3v2FrameName($frame_name, $id3v2_majorversion)) { @@ -389,21 +389,21 @@ case "\x00".'MP': case ' MP': case 'MP3': - $info['warning'][] = 'error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: !IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))). [Note: this particular error has been known to happen with tags edited by "MP3ext (www.mutschler.de/mp3ext/)"]'; + $this->warning('error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: !IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))). [Note: this particular error has been known to happen with tags edited by "MP3ext (www.mutschler.de/mp3ext/)"]'); break; default: - $info['warning'][] = 'error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: !IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))).'; + $this->warning('error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: !IsValidID3v2FrameName("'.str_replace("\x00", ' ', $frame_name).'", '.$id3v2_majorversion.'))).'); break; } } elseif (!isset($framedata) || ($frame_size > strlen($framedata))) { - $info['error'][] = 'error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: $frame_size ('.$frame_size.') > strlen($framedata) ('.(isset($framedata) ? strlen($framedata) : 'null').')).'; + $this->error('error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag). (ERROR: $frame_size ('.$frame_size.') > strlen($framedata) ('.(isset($framedata) ? strlen($framedata) : 'null').')).'); } else { - $info['error'][] = 'error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag).'; + $this->error('error parsing "'.$frame_name.'" ('.$framedataoffset.' bytes into the ID3v2.'.$id3v2_majorversion.' tag).'); } @@ -442,10 +442,14 @@ } // end footer if (isset($thisfile_id3v2['comments']['genre'])) { + $genres = array(); foreach ($thisfile_id3v2['comments']['genre'] as $key => $value) { - unset($thisfile_id3v2['comments']['genre'][$key]); - $thisfile_id3v2['comments'] = getid3_lib::array_merge_noclobber($thisfile_id3v2['comments'], array('genre'=>$this->ParseID3v2GenreString($value))); + foreach ($this->ParseID3v2GenreString($value) as $genre) { + $genres[] = $genre; + } } + $thisfile_id3v2['comments']['genre'] = array_unique($genres); + unset($key, $value, $genres, $genre); } if (isset($thisfile_id3v2['comments']['track'])) { @@ -500,9 +504,28 @@ // ID3v2.2.x, ID3v2.3.x: '(21)' or '(4)Eurodisco' or '(51)(39)' or '(55)((I think...)' // ID3v2.4.x: '21' $00 'Eurodisco' $00 $clean_genres = array(); + + // hack-fixes for some badly-written ID3v2.3 taggers, while trying not to break correctly-written tags + if (($this->getid3->info['id3v2']['majorversion'] == 3) && !preg_match('#[\x00]#', $genrestring)) { + // note: MusicBrainz Picard incorrectly stores plaintext genres separated by "/" when writing in ID3v2.3 mode, hack-fix here: + // replace / with NULL, then replace back the two ID3v1 genres that legitimately have "/" as part of the single genre name + if (preg_match('#/#', $genrestring)) { + $genrestring = str_replace('/', "\x00", $genrestring); + $genrestring = str_replace('Pop'."\x00".'Funk', 'Pop/Funk', $genrestring); + $genrestring = str_replace('Rock'."\x00".'Rock', 'Folk/Rock', $genrestring); + } + + // some other taggers separate multiple genres with semicolon, e.g. "Heavy Metal;Thrash Metal;Metal" + if (preg_match('#;#', $genrestring)) { + $genrestring = str_replace(';', "\x00", $genrestring); + } + } + + if (strpos($genrestring, "\x00") === false) { $genrestring = preg_replace('#\(([0-9]{1,3})\)#', '$1'."\x00", $genrestring); } + $genre_elements = explode("\x00", $genrestring); foreach ($genre_elements as $element) { $element = trim($element); @@ -571,14 +594,14 @@ if ($parsedFrame['flags']['compression']) { $parsedFrame['decompressed_size'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], 0, 4)); if (!function_exists('gzuncompress')) { - $info['warning'][] = 'gzuncompress() support required to decompress ID3v2 frame "'.$parsedFrame['frame_name'].'"'; + $this->warning('gzuncompress() support required to decompress ID3v2 frame "'.$parsedFrame['frame_name'].'"'); } else { if ($decompresseddata = @gzuncompress(substr($parsedFrame['data'], 4))) { //if ($decompresseddata = @gzuncompress($parsedFrame['data'])) { $parsedFrame['data'] = $decompresseddata; unset($decompresseddata); } else { - $info['warning'][] = 'gzuncompress() failed on compressed contents of ID3v2 frame "'.$parsedFrame['frame_name'].'"'; + $this->warning('gzuncompress() failed on compressed contents of ID3v2 frame "'.$parsedFrame['frame_name'].'"'); } } } @@ -586,7 +609,7 @@ if (!empty($parsedFrame['flags']['DataLengthIndicator'])) { if ($parsedFrame['data_length_indicator'] != strlen($parsedFrame['data'])) { - $info['warning'][] = 'ID3v2 frame "'.$parsedFrame['frame_name'].'" should be '.$parsedFrame['data_length_indicator'].' bytes long according to DataLengthIndicator, but found '.strlen($parsedFrame['data']).' bytes of data'; + $this->warning('ID3v2 frame "'.$parsedFrame['frame_name'].'" should be '.$parsedFrame['data_length_indicator'].' bytes long according to DataLengthIndicator, but found '.strlen($parsedFrame['data']).' bytes of data'); } } @@ -601,7 +624,7 @@ default: break; } - $info['warning'][] = $warning; + $this->warning($warning); } elseif ((($id3v2_majorversion >= 3) && ($parsedFrame['frame_name'] == 'UFID')) || // 4.1 UFID Unique file identifier (($id3v2_majorversion == 2) && ($parsedFrame['frame_name'] == 'UFI'))) { // 4.1 UFI Unique file identifier @@ -625,23 +648,25 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); - + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } $parsedFrame['encodingid'] = $frame_textencoding; $parsedFrame['encoding'] = $this->TextEncodingNameLookup($frame_textencoding); - $parsedFrame['description'] = $frame_description; - $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); + $parsedFrame['description'] = trim(getid3_lib::iconv_fallback($parsedFrame['encoding'], $info['id3v2']['encoding'], $frame_description)); + $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator)); if (!empty($parsedFrame['framenameshort']) && !empty($parsedFrame['data'])) { $commentkey = ($parsedFrame['description'] ? $parsedFrame['description'] : (isset($info['id3v2']['comments'][$parsedFrame['framenameshort']]) ? count($info['id3v2']['comments'][$parsedFrame['framenameshort']]) : 0)); if (!isset($info['id3v2']['comments'][$parsedFrame['framenameshort']]) || !array_key_exists($commentkey, $info['id3v2']['comments'][$parsedFrame['framenameshort']])) { @@ -663,7 +688,7 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); } $parsedFrame['data'] = (string) substr($parsedFrame['data'], $frame_offset); @@ -717,22 +742,24 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } - $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); - - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding)); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator)); + + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } if ($frame_terminatorpos) { @@ -780,7 +807,7 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); } $parsedFrame['encodingid'] = $frame_textencoding; $parsedFrame['encoding'] = $this->TextEncodingNameLookup($parsedFrame['encodingid']); @@ -956,25 +983,27 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } $frame_language = substr($parsedFrame['data'], $frame_offset, 3); $frame_offset += 3; - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } - $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); + $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator)); $parsedFrame['encodingid'] = $frame_textencoding; $parsedFrame['encoding'] = $this->TextEncodingNameLookup($frame_textencoding); - $parsedFrame['data'] = $parsedFrame['data']; $parsedFrame['language'] = $frame_language; $parsedFrame['languagename'] = $this->LanguageLookup($frame_language, false); $parsedFrame['description'] = $frame_description; @@ -1002,8 +1031,10 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } $frame_language = substr($parsedFrame['data'], $frame_offset, 3); $frame_offset += 3; @@ -1020,16 +1051,16 @@ $frame_remainingdata = substr($parsedFrame['data'], $frame_offset); while (strlen($frame_remainingdata)) { $frame_offset = 0; - $frame_terminatorpos = strpos($frame_remainingdata, $this->TextEncodingTerminatorLookup($frame_textencoding)); + $frame_terminatorpos = strpos($frame_remainingdata, $frame_textencoding_terminator); if ($frame_terminatorpos === false) { $frame_remainingdata = ''; } else { - if (ord(substr($frame_remainingdata, $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + if (ord(substr($frame_remainingdata, $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $parsedFrame['lyrics'][$timestampindex]['data'] = substr($frame_remainingdata, $frame_offset, $frame_terminatorpos - $frame_offset); - $frame_remainingdata = substr($frame_remainingdata, $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); + $frame_remainingdata = substr($frame_remainingdata, $frame_terminatorpos + strlen($frame_textencoding_terminator)); if (($timestampindex == 0) && (ord($frame_remainingdata{0}) != 0)) { // timestamp probably omitted for first data item } else { @@ -1054,26 +1085,29 @@ if (strlen($parsedFrame['data']) < 5) { - $info['warning'][] = 'Invalid data (too short) for "'.$parsedFrame['frame_name'].'" frame at offset '.$parsedFrame['dataoffset']; + $this->warning('Invalid data (too short) for "'.$parsedFrame['frame_name'].'" frame at offset '.$parsedFrame['dataoffset']); } else { $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } $frame_language = substr($parsedFrame['data'], $frame_offset, 3); $frame_offset += 3; - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } - $frame_text = (string) substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); + $frame_text = (string) substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator)); $parsedFrame['encodingid'] = $frame_textencoding; $parsedFrame['encoding'] = $this->TextEncodingNameLookup($frame_textencoding); @@ -1123,7 +1157,7 @@ $frame_offset += 2; $parsedFrame[$RVA2channelcounter]['bitspeakvolume'] = ord(substr($frame_remainingdata, $frame_offset++, 1)); if (($parsedFrame[$RVA2channelcounter]['bitspeakvolume'] < 1) || ($parsedFrame[$RVA2channelcounter]['bitspeakvolume'] > 4)) { - $info['warning'][] = 'ID3v2::RVA2 frame['.$RVA2channelcounter.'] contains invalid '.$parsedFrame[$RVA2channelcounter]['bitspeakvolume'].'-byte bits-representing-peak value'; + $this->warning('ID3v2::RVA2 frame['.$RVA2channelcounter.'] contains invalid '.$parsedFrame[$RVA2channelcounter]['bitspeakvolume'].'-byte bits-representing-peak value'); break; } $frame_bytespeakvolume = ceil($parsedFrame[$RVA2channelcounter]['bitspeakvolume'] / 8); @@ -1330,8 +1364,10 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } if ($id3v2_majorversion == 2 && strlen($parsedFrame['data']) > $frame_offset) { @@ -1365,14 +1401,15 @@ $frame_picturetype = ord(substr($parsedFrame['data'], $frame_offset++, 1)); if ($frame_offset >= $parsedFrame['datalength']) { - $info['warning'][] = 'data portion of APIC frame is missing at offset '.($parsedFrame['dataoffset'] + 8 + $frame_offset); + $this->warning('data portion of APIC frame is missing at offset '.($parsedFrame['dataoffset'] + 8 + $frame_offset)); } else { - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } $parsedFrame['encodingid'] = $frame_textencoding; @@ -1386,19 +1423,20 @@ $parsedFrame['picturetypeid'] = $frame_picturetype; $parsedFrame['picturetype'] = $this->APICPictureTypeLookup($frame_picturetype); $parsedFrame['description'] = $frame_description; - $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding))); + $parsedFrame['data'] = substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator)); $parsedFrame['datalength'] = strlen($parsedFrame['data']); $parsedFrame['image_mime'] = ''; $imageinfo = array(); - $imagechunkcheck = getid3_lib::GetDataImageSize($parsedFrame['data'], $imageinfo); - if (($imagechunkcheck[2] >= 1) && ($imagechunkcheck[2] <= 3)) { - $parsedFrame['image_mime'] = 'image/'.getid3_lib::ImageTypesLookup($imagechunkcheck[2]); - if ($imagechunkcheck[0]) { - $parsedFrame['image_width'] = $imagechunkcheck[0]; - } - if ($imagechunkcheck[1]) { - $parsedFrame['image_height'] = $imagechunkcheck[1]; + if ($imagechunkcheck = getid3_lib::GetDataImageSize($parsedFrame['data'], $imageinfo)) { + if (($imagechunkcheck[2] >= 1) && ($imagechunkcheck[2] <= 3)) { + $parsedFrame['image_mime'] = 'image/'.getid3_lib::ImageTypesLookup($imagechunkcheck[2]); + if ($imagechunkcheck[0]) { + $parsedFrame['image_width'] = $imagechunkcheck[0]; + } + if ($imagechunkcheck[1]) { + $parsedFrame['image_height'] = $imagechunkcheck[1]; + } } } @@ -1414,16 +1452,16 @@ } elseif (is_int($this->getid3->option_save_attachments)) { if ($this->getid3->option_save_attachments < $parsedFrame['data_length']) { // too big, skip - $info['warning'][] = 'attachment at '.$frame_offset.' is too large to process inline ('.number_format($parsedFrame['data_length']).' bytes)'; + $this->warning('attachment at '.$frame_offset.' is too large to process inline ('.number_format($parsedFrame['data_length']).' bytes)'); unset($parsedFrame['data']); break; } */ } elseif (is_string($this->getid3->option_save_attachments)) { $dir = rtrim(str_replace(array('/', '\\'), DIRECTORY_SEPARATOR, $this->getid3->option_save_attachments), DIRECTORY_SEPARATOR); - if (!is_dir($dir) || !is_writable($dir)) { + if (!is_dir($dir) || !getID3::is_writable($dir)) { // cannot write, skip - $info['warning'][] = 'attachment at '.$frame_offset.' cannot be saved to "'.$dir.'" (not writable)'; + $this->warning('attachment at '.$frame_offset.' cannot be saved to "'.$dir.'" (not writable)'); unset($parsedFrame['data']); break; } @@ -1431,10 +1469,10 @@ // if we get this far, must be OK if (is_string($this->getid3->option_save_attachments)) { $destination_filename = $dir.DIRECTORY_SEPARATOR.md5($info['filenamepath']).'_'.$frame_offset; - if (!file_exists($destination_filename) || is_writable($destination_filename)) { + if (!file_exists($destination_filename) || getID3::is_writable($destination_filename)) { file_put_contents($destination_filename, $parsedFrame['data']); } else { - $info['warning'][] = 'attachment at '.$frame_offset.' cannot be saved to "'.$destination_filename.'" (not writable)'; + $this->warning('attachment at '.$frame_offset.' cannot be saved to "'.$destination_filename.'" (not writable)'); } $parsedFrame['data_filename'] = $destination_filename; unset($parsedFrame['data']); @@ -1443,7 +1481,14 @@ if (!isset($info['id3v2']['comments']['picture'])) { $info['id3v2']['comments']['picture'] = array(); } - $info['id3v2']['comments']['picture'][] = array('data'=>$parsedFrame['data'], 'image_mime'=>$parsedFrame['image_mime']); + $comments_picture_data = array(); + foreach (array('data', 'image_mime', 'image_width', 'image_height', 'imagetype', 'picturetype', 'description', 'datalength') as $picture_key) { + if (isset($parsedFrame[$picture_key])) { + $comments_picture_data[$picture_key] = $parsedFrame[$picture_key]; + } + } + $info['id3v2']['comments']['picture'][] = $comments_picture_data; + unset($comments_picture_data); } } } while (false); @@ -1462,8 +1507,10 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } $frame_terminatorpos = strpos($parsedFrame['data'], "\x00", $frame_offset); $frame_mimetype = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); @@ -1472,25 +1519,26 @@ } $frame_offset = $frame_terminatorpos + strlen("\x00"); - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_filename = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); if (ord($frame_filename) === 0) { $frame_filename = ''; } - $frame_offset = $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)); - - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_offset = $frame_terminatorpos + strlen($frame_textencoding_terminator); + + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } - $frame_offset = $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)); + $frame_offset = $frame_terminatorpos + strlen($frame_textencoding_terminator); $parsedFrame['objectdata'] = (string) substr($parsedFrame['data'], $frame_offset); $parsedFrame['encodingid'] = $frame_textencoding; @@ -1569,7 +1617,8 @@ $frame_terminatorpos = strpos($parsedFrame['data'], "\x00", $frame_offset); $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } $frame_offset = $frame_terminatorpos + strlen("\x00"); @@ -1594,7 +1643,7 @@ $frame_terminatorpos = strpos($parsedFrame['data'], "\x00", $frame_offset); $frame_ownerid = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); if (ord($frame_ownerid) === 0) { - $frame_ownerid == ''; + $frame_ownerid = ''; } $frame_offset = $frame_terminatorpos + strlen("\x00"); $parsedFrame['ownerid'] = $frame_ownerid; @@ -1607,7 +1656,7 @@ } elseif ((($id3v2_majorversion >= 3) && ($parsedFrame['frame_name'] == 'LINK')) || // 4.20 LINK Linked information - (($id3v2_majorversion == 2) && ($parsedFrame['frame_name'] == 'LNK'))) { // 4.22 LNK Linked information + (($id3v2_majorversion == 2) && ($parsedFrame['frame_name'] == 'LNK'))) { // 4.22 LNK Linked information // There may be more than one 'LINK' frame in a tag, // but only one with the same contents //
@@ -1635,7 +1684,7 @@ $parsedFrame['additionaldata'] = (string) substr($parsedFrame['data'], $frame_offset); if (!empty($parsedFrame['framenameshort']) && $parsedFrame['url']) { - $info['id3v2']['comments'][$parsedFrame['framenameshort']][] = utf8_encode($parsedFrame['url']); + $info['id3v2']['comments'][$parsedFrame['framenameshort']][] = getid3_lib::iconv_fallback_iso88591_utf8($parsedFrame['url']); } unset($parsedFrame['data']); @@ -1663,7 +1712,7 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); } $frame_language = substr($parsedFrame['data'], $frame_offset, 3); $frame_offset += 3; @@ -1690,7 +1739,7 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); } $parsedFrame['encodingid'] = $frame_textencoding; $parsedFrame['encoding'] = $this->TextEncodingNameLookup($frame_textencoding); @@ -1704,7 +1753,7 @@ $parsedFrame['pricepaid']['value'] = substr($frame_pricepaid, 3); $parsedFrame['purchasedate'] = substr($parsedFrame['data'], $frame_offset, 8); - if (!$this->IsValidDateStampString($parsedFrame['purchasedate'])) { + if ($this->IsValidDateStampString($parsedFrame['purchasedate'])) { $parsedFrame['purchasedateunix'] = mktime (0, 0, 0, substr($parsedFrame['purchasedate'], 4, 2), substr($parsedFrame['purchasedate'], 6, 2), substr($parsedFrame['purchasedate'], 0, 4)); } $frame_offset += 8; @@ -1729,8 +1778,10 @@ $frame_offset = 0; $frame_textencoding = ord(substr($parsedFrame['data'], $frame_offset++, 1)); + $frame_textencoding_terminator = $this->TextEncodingTerminatorLookup($frame_textencoding); if ((($id3v2_majorversion <= 3) && ($frame_textencoding > 1)) || (($id3v2_majorversion == 4) && ($frame_textencoding > 3))) { - $info['warning'][] = 'Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'; + $this->warning('Invalid text encoding byte ('.$frame_textencoding.') in frame "'.$parsedFrame['frame_name'].'" - defaulting to ISO-8859-1 encoding'); + $frame_textencoding_terminator = "\x00"; } $frame_terminatorpos = strpos($parsedFrame['data'], "\x00", $frame_offset); @@ -1752,25 +1803,26 @@ $frame_receivedasid = ord(substr($parsedFrame['data'], $frame_offset++, 1)); - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_sellername = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); if (ord($frame_sellername) === 0) { $frame_sellername = ''; } - $frame_offset = $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)); - - $frame_terminatorpos = strpos($parsedFrame['data'], $this->TextEncodingTerminatorLookup($frame_textencoding), $frame_offset); - if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)), 1)) === 0) { + $frame_offset = $frame_terminatorpos + strlen($frame_textencoding_terminator); + + $frame_terminatorpos = strpos($parsedFrame['data'], $frame_textencoding_terminator, $frame_offset); + if (ord(substr($parsedFrame['data'], $frame_terminatorpos + strlen($frame_textencoding_terminator), 1)) === 0) { $frame_terminatorpos++; // strpos() fooled because 2nd byte of Unicode chars are often 0x00 } $frame_description = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); - if (ord($frame_description) === 0) { + if (in_array($frame_description, array("\x00", "\x00\x00", "\xFF\xFE", "\xFE\xFF"))) { + // if description only contains a BOM or terminator then make it blank $frame_description = ''; } - $frame_offset = $frame_terminatorpos + strlen($this->TextEncodingTerminatorLookup($frame_textencoding)); + $frame_offset = $frame_terminatorpos + strlen($frame_textencoding_terminator); $frame_terminatorpos = strpos($parsedFrame['data'], "\x00", $frame_offset); $frame_mimetype = substr($parsedFrame['data'], $frame_offset, $frame_terminatorpos - $frame_offset); @@ -1944,6 +1996,186 @@ unset($parsedFrame['data']); + } elseif (($id3v2_majorversion >= 3) && ($parsedFrame['frame_name'] == 'CHAP')) { // CHAP Chapters frame (ID3v2.3+ only) + // http://id3.org/id3v2-chapters-1.0 + // (10 bytes) + // Element ID $00 + // Start time $xx xx xx xx + // End time $xx xx xx xx + // Start offset $xx xx xx xx + // End offset $xx xx xx xx + // + + $frame_offset = 0; + @list($parsedFrame['element_id']) = explode("\x00", $parsedFrame['data'], 2); + $frame_offset += strlen($parsedFrame['element_id']."\x00"); + $parsedFrame['time_begin'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + $frame_offset += 4; + $parsedFrame['time_end'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + $frame_offset += 4; + if (substr($parsedFrame['data'], $frame_offset, 4) != "\xFF\xFF\xFF\xFF") { + // "If these bytes are all set to 0xFF then the value should be ignored and the start time value should be utilized." + $parsedFrame['offset_begin'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + } + $frame_offset += 4; + if (substr($parsedFrame['data'], $frame_offset, 4) != "\xFF\xFF\xFF\xFF") { + // "If these bytes are all set to 0xFF then the value should be ignored and the start time value should be utilized." + $parsedFrame['offset_end'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + } + $frame_offset += 4; + + if ($frame_offset < strlen($parsedFrame['data'])) { + $parsedFrame['subframes'] = array(); + while ($frame_offset < strlen($parsedFrame['data'])) { + // + $subframe = array(); + $subframe['name'] = substr($parsedFrame['data'], $frame_offset, 4); + $frame_offset += 4; + $subframe['size'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + $frame_offset += 4; + $subframe['flags_raw'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 2)); + $frame_offset += 2; + if ($subframe['size'] > (strlen($parsedFrame['data']) - $frame_offset)) { + $this->warning('CHAP subframe "'.$subframe['name'].'" at frame offset '.$frame_offset.' claims to be "'.$subframe['size'].'" bytes, which is more than the available data ('.(strlen($parsedFrame['data']) - $frame_offset).' bytes)'); + break; + } + $subframe_rawdata = substr($parsedFrame['data'], $frame_offset, $subframe['size']); + $frame_offset += $subframe['size']; + + $subframe['encodingid'] = ord(substr($subframe_rawdata, 0, 1)); + $subframe['text'] = substr($subframe_rawdata, 1); + $subframe['encoding'] = $this->TextEncodingNameLookup($subframe['encodingid']); + $encoding_converted_text = trim(getid3_lib::iconv_fallback($subframe['encoding'], $info['encoding'], $subframe['text']));; + switch (substr($encoding_converted_text, 0, 2)) { + case "\xFF\xFE": + case "\xFE\xFF": + switch (strtoupper($info['id3v2']['encoding'])) { + case 'ISO-8859-1': + case 'UTF-8': + $encoding_converted_text = substr($encoding_converted_text, 2); + // remove unwanted byte-order-marks + break; + default: + // ignore + break; + } + break; + default: + // do not remove BOM + break; + } + + if (($subframe['name'] == 'TIT2') || ($subframe['name'] == 'TIT3')) { + if ($subframe['name'] == 'TIT2') { + $parsedFrame['chapter_name'] = $encoding_converted_text; + } elseif ($subframe['name'] == 'TIT3') { + $parsedFrame['chapter_description'] = $encoding_converted_text; + } + $parsedFrame['subframes'][] = $subframe; + } else { + $this->warning('ID3v2.CHAP subframe "'.$subframe['name'].'" not handled (only TIT2 and TIT3)'); + } + } + unset($subframe_rawdata, $subframe, $encoding_converted_text); + } + + $id3v2_chapter_entry = array(); + foreach (array('id', 'time_begin', 'time_end', 'offset_begin', 'offset_end', 'chapter_name', 'chapter_description') as $id3v2_chapter_key) { + if (isset($parsedFrame[$id3v2_chapter_key])) { + $id3v2_chapter_entry[$id3v2_chapter_key] = $parsedFrame[$id3v2_chapter_key]; + } + } + if (!isset($info['id3v2']['chapters'])) { + $info['id3v2']['chapters'] = array(); + } + $info['id3v2']['chapters'][] = $id3v2_chapter_entry; + unset($id3v2_chapter_entry, $id3v2_chapter_key); + + + } elseif (($id3v2_majorversion >= 3) && ($parsedFrame['frame_name'] == 'CTOC')) { // CTOC Chapters Table Of Contents frame (ID3v2.3+ only) + // http://id3.org/id3v2-chapters-1.0 + // (10 bytes) + // Element ID $00 + // CTOC flags %xx + // Entry count $xx + // Child Element ID $00 /* zero or more child CHAP or CTOC entries */ + // + + $frame_offset = 0; + @list($parsedFrame['element_id']) = explode("\x00", $parsedFrame['data'], 2); + $frame_offset += strlen($parsedFrame['element_id']."\x00"); + $ctoc_flags_raw = ord(substr($parsedFrame['data'], $frame_offset, 1)); + $frame_offset += 1; + $parsedFrame['entry_count'] = ord(substr($parsedFrame['data'], $frame_offset, 1)); + $frame_offset += 1; + + $terminator_position = null; + for ($i = 0; $i < $parsedFrame['entry_count']; $i++) { + $terminator_position = strpos($parsedFrame['data'], "\x00", $frame_offset); + $parsedFrame['child_element_ids'][$i] = substr($parsedFrame['data'], $frame_offset, $terminator_position - $frame_offset); + $frame_offset = $terminator_position + 1; + } + + $parsedFrame['ctoc_flags']['ordered'] = (bool) ($ctoc_flags_raw & 0x01); + $parsedFrame['ctoc_flags']['top_level'] = (bool) ($ctoc_flags_raw & 0x03); + + unset($ctoc_flags_raw, $terminator_position); + + if ($frame_offset < strlen($parsedFrame['data'])) { + $parsedFrame['subframes'] = array(); + while ($frame_offset < strlen($parsedFrame['data'])) { + // + $subframe = array(); + $subframe['name'] = substr($parsedFrame['data'], $frame_offset, 4); + $frame_offset += 4; + $subframe['size'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 4)); + $frame_offset += 4; + $subframe['flags_raw'] = getid3_lib::BigEndian2Int(substr($parsedFrame['data'], $frame_offset, 2)); + $frame_offset += 2; + if ($subframe['size'] > (strlen($parsedFrame['data']) - $frame_offset)) { + $this->warning('CTOS subframe "'.$subframe['name'].'" at frame offset '.$frame_offset.' claims to be "'.$subframe['size'].'" bytes, which is more than the available data ('.(strlen($parsedFrame['data']) - $frame_offset).' bytes)'); + break; + } + $subframe_rawdata = substr($parsedFrame['data'], $frame_offset, $subframe['size']); + $frame_offset += $subframe['size']; + + $subframe['encodingid'] = ord(substr($subframe_rawdata, 0, 1)); + $subframe['text'] = substr($subframe_rawdata, 1); + $subframe['encoding'] = $this->TextEncodingNameLookup($subframe['encodingid']); + $encoding_converted_text = trim(getid3_lib::iconv_fallback($subframe['encoding'], $info['encoding'], $subframe['text']));; + switch (substr($encoding_converted_text, 0, 2)) { + case "\xFF\xFE": + case "\xFE\xFF": + switch (strtoupper($info['id3v2']['encoding'])) { + case 'ISO-8859-1': + case 'UTF-8': + $encoding_converted_text = substr($encoding_converted_text, 2); + // remove unwanted byte-order-marks + break; + default: + // ignore + break; + } + break; + default: + // do not remove BOM + break; + } + + if (($subframe['name'] == 'TIT2') || ($subframe['name'] == 'TIT3')) { + if ($subframe['name'] == 'TIT2') { + $parsedFrame['toc_name'] = $encoding_converted_text; + } elseif ($subframe['name'] == 'TIT3') { + $parsedFrame['toc_description'] = $encoding_converted_text; + } + $parsedFrame['subframes'][] = $subframe; + } else { + $this->warning('ID3v2.CTOC subframe "'.$subframe['name'].'" not handled (only TIT2 and TIT3)'); + } + } + unset($subframe_rawdata, $subframe, $encoding_converted_text); + } + } return true; @@ -3344,7 +3576,7 @@ 3 => "\x00", // $03 UTF-8 encoded Unicode. Terminated with $00. 255 => "\x00\x00" ); - return (isset($TextEncodingTerminatorLookup[$encoding]) ? $TextEncodingTerminatorLookup[$encoding] : ''); + return (isset($TextEncodingTerminatorLookup[$encoding]) ? $TextEncodingTerminatorLookup[$encoding] : "\x00"); } public static function TextEncodingNameLookup($encoding) { @@ -3421,4 +3653,89 @@ return (($majorversion == 2) ? 6 : 10); } + public static function ID3v22iTunesBrokenFrameName($frame_name) { + // iTunes (multiple versions) has been known to write ID3v2.3 style frames + // but use ID3v2.2 frame names, right-padded using either [space] or [null] + // to make them fit in the 4-byte frame name space of the ID3v2.3 frame. + // This function will detect and translate the corrupt frame name into ID3v2.3 standard. + static $ID3v22_iTunes_BrokenFrames = array( + 'BUF' => 'RBUF', // Recommended buffer size + 'CNT' => 'PCNT', // Play counter + 'COM' => 'COMM', // Comments + 'CRA' => 'AENC', // Audio encryption + 'EQU' => 'EQUA', // Equalisation + 'ETC' => 'ETCO', // Event timing codes + 'GEO' => 'GEOB', // General encapsulated object + 'IPL' => 'IPLS', // Involved people list + 'LNK' => 'LINK', // Linked information + 'MCI' => 'MCDI', // Music CD identifier + 'MLL' => 'MLLT', // MPEG location lookup table + 'PIC' => 'APIC', // Attached picture + 'POP' => 'POPM', // Popularimeter + 'REV' => 'RVRB', // Reverb + 'RVA' => 'RVAD', // Relative volume adjustment + 'SLT' => 'SYLT', // Synchronised lyric/text + 'STC' => 'SYTC', // Synchronised tempo codes + 'TAL' => 'TALB', // Album/Movie/Show title + 'TBP' => 'TBPM', // BPM (beats per minute) + 'TCM' => 'TCOM', // Composer + 'TCO' => 'TCON', // Content type + 'TCP' => 'TCMP', // Part of a compilation + 'TCR' => 'TCOP', // Copyright message + 'TDA' => 'TDAT', // Date + 'TDY' => 'TDLY', // Playlist delay + 'TEN' => 'TENC', // Encoded by + 'TFT' => 'TFLT', // File type + 'TIM' => 'TIME', // Time + 'TKE' => 'TKEY', // Initial key + 'TLA' => 'TLAN', // Language(s) + 'TLE' => 'TLEN', // Length + 'TMT' => 'TMED', // Media type + 'TOA' => 'TOPE', // Original artist(s)/performer(s) + 'TOF' => 'TOFN', // Original filename + 'TOL' => 'TOLY', // Original lyricist(s)/text writer(s) + 'TOR' => 'TORY', // Original release year + 'TOT' => 'TOAL', // Original album/movie/show title + 'TP1' => 'TPE1', // Lead performer(s)/Soloist(s) + 'TP2' => 'TPE2', // Band/orchestra/accompaniment + 'TP3' => 'TPE3', // Conductor/performer refinement + 'TP4' => 'TPE4', // Interpreted, remixed, or otherwise modified by + 'TPA' => 'TPOS', // Part of a set + 'TPB' => 'TPUB', // Publisher + 'TRC' => 'TSRC', // ISRC (international standard recording code) + 'TRD' => 'TRDA', // Recording dates + 'TRK' => 'TRCK', // Track number/Position in set + 'TS2' => 'TSO2', // Album-Artist sort order + 'TSA' => 'TSOA', // Album sort order + 'TSC' => 'TSOC', // Composer sort order + 'TSI' => 'TSIZ', // Size + 'TSP' => 'TSOP', // Performer sort order + 'TSS' => 'TSSE', // Software/Hardware and settings used for encoding + 'TST' => 'TSOT', // Title sort order + 'TT1' => 'TIT1', // Content group description + 'TT2' => 'TIT2', // Title/songname/content description + 'TT3' => 'TIT3', // Subtitle/Description refinement + 'TXT' => 'TEXT', // Lyricist/Text writer + 'TXX' => 'TXXX', // User defined text information frame + 'TYE' => 'TYER', // Year + 'UFI' => 'UFID', // Unique file identifier + 'ULT' => 'USLT', // Unsynchronised lyric/text transcription + 'WAF' => 'WOAF', // Official audio file webpage + 'WAR' => 'WOAR', // Official artist/performer webpage + 'WAS' => 'WOAS', // Official audio source webpage + 'WCM' => 'WCOM', // Commercial information + 'WCP' => 'WCOP', // Copyright/Legal information + 'WPB' => 'WPUB', // Publishers official webpage + 'WXX' => 'WXXX', // User defined URL link frame + ); + if (strlen($frame_name) == 4) { + if ((substr($frame_name, 3, 1) == ' ') || (substr($frame_name, 3, 1) == "\x00")) { + if (isset($ID3v22_iTunes_BrokenFrames[substr($frame_name, 0, 3)])) { + return $ID3v22_iTunes_BrokenFrames[substr($frame_name, 0, 3)]; + } + } + } + return false; + } + }