public function Analyze() { $info =& $this->getid3->info; // Overall tag structure: // +-----------------------------+ // | Header (10 bytes) | // +-----------------------------+ // | Extended Header | // | (variable length, OPTIONAL) | // +-----------------------------+ // | Frames (variable length) | // +-----------------------------+ // | Padding | // | (variable length, OPTIONAL) | // +-----------------------------+ // | Footer (10 bytes, OPTIONAL) | // +-----------------------------+ // Header // ID3v2/file identifier "ID3" // ID3v2 version $04 00 // ID3v2 flags (%ab000000 in v2.2, %abc00000 in v2.3, %abcd0000 in v2.4.x) // ID3v2 size 4 * %0xxxxxxx // shortcuts $info['id3v2']['header'] = true; $thisfile_id3v2 =& $info['id3v2']; $thisfile_id3v2['flags'] = array(); $thisfile_id3v2_flags =& $thisfile_id3v2['flags']; $this->fseek($this->StartingOffset); $header = $this->fread(10); if (substr($header, 0, 3) == 'ID3' && strlen($header) == 10) { $thisfile_id3v2['majorversion'] = ord($header[3]); $thisfile_id3v2['minorversion'] = ord($header[4]); // shortcut $id3v2_majorversion =& $thisfile_id3v2['majorversion']; } else { unset($info['id3v2']); return false; } 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']; return false; } $id3_flags = ord($header[5]); switch ($id3v2_majorversion) { case 2: // %ab000000 in v2.2 $thisfile_id3v2_flags['unsynch'] = (bool) ($id3_flags & 0x80); // a - Unsynchronisation $thisfile_id3v2_flags['compression'] = (bool) ($id3_flags & 0x40); // b - Compression break; case 3: // %abc00000 in v2.3 $thisfile_id3v2_flags['unsynch'] = (bool) ($id3_flags & 0x80); // a - Unsynchronisation $thisfile_id3v2_flags['exthead'] = (bool) ($id3_flags & 0x40); // b - Extended header $thisfile_id3v2_flags['experim'] = (bool) ($id3_flags & 0x20); // c - Experimental indicator break; case 4: // %abcd0000 in v2.4 $thisfile_id3v2_flags['unsynch'] = (bool) ($id3_flags & 0x80); // a - Unsynchronisation $thisfile_id3v2_flags['exthead'] = (bool) ($id3_flags & 0x40); // b - Extended header $thisfile_id3v2_flags['experim'] = (bool) ($id3_flags & 0x20); // c - Experimental indicator $thisfile_id3v2_flags['isfooter'] = (bool) ($id3_flags & 0x10); // d - Footer present break; } $thisfile_id3v2['headerlength'] = getid3_lib::BigEndian2Int(substr($header, 6, 4), 1) + 10; // length of ID3v2 tag in 10-byte header doesn't include 10-byte header length $thisfile_id3v2['tag_offset_start'] = $this->StartingOffset; $thisfile_id3v2['tag_offset_end'] = $thisfile_id3v2['tag_offset_start'] + $thisfile_id3v2['headerlength']; // create 'encoding' key - used by getid3::HandleAllTags() // in ID3v2 every field can have it's own encoding type // so force everything to UTF-8 so it can be handled consistantly $thisfile_id3v2['encoding'] = 'UTF-8'; // Frames // All ID3v2 frames consists of one frame header followed by one or more // fields containing the actual information. The header is always 10 // bytes and laid out as follows: // // Frame ID $xx xx xx xx (four characters) // Size 4 * %0xxxxxxx // Flags $xx xx $sizeofframes = $thisfile_id3v2['headerlength'] - 10; // not including 10-byte initial header if (!empty($thisfile_id3v2['exthead']['length'])) { $sizeofframes -= $thisfile_id3v2['exthead']['length'] + 4; } if (!empty($thisfile_id3v2_flags['isfooter'])) { $sizeofframes -= 10; // footer takes last 10 bytes of ID3v2 header, after frame data, before audio } if ($sizeofframes > 0) { $framedata = $this->fread($sizeofframes); // read all frames from file into $framedata variable // if entire frame data is unsynched, de-unsynch it now (ID3v2.3.x) if (!empty($thisfile_id3v2_flags['unsynch']) && $id3v2_majorversion <= 3) { $framedata = $this->DeUnsynchronise($framedata); } // [in ID3v2.4.0] Unsynchronisation [S:6.1] is done on frame level, instead // of on tag level, making it easier to skip frames, increasing the streamability // of the tag. The unsynchronisation flag in the header [S:3.1] indicates that // there exists an unsynchronised frame, while the new unsynchronisation flag in // the frame header [S:4.1.2] indicates unsynchronisation. //$framedataoffset = 10 + ($thisfile_id3v2['exthead']['length'] ? $thisfile_id3v2['exthead']['length'] + 4 : 0); // how many bytes into the stream - start from after the 10-byte header (and extended header length+4, if present) $framedataoffset = 10; // how many bytes into the stream - start from after the 10-byte header // Extended Header if (!empty($thisfile_id3v2_flags['exthead'])) { $extended_header_offset = 0; if ($id3v2_majorversion == 3) { // v2.3 definition: //Extended header size $xx xx xx xx // 32-bit integer //Extended Flags $xx xx // %x0000000 %00000000 // v2.3 // x - CRC data present //Size of padding $xx xx xx xx $thisfile_id3v2['exthead']['length'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 4), 0); $extended_header_offset += 4; $thisfile_id3v2['exthead']['flag_bytes'] = 2; $thisfile_id3v2['exthead']['flag_raw'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, $thisfile_id3v2['exthead']['flag_bytes'])); $extended_header_offset += $thisfile_id3v2['exthead']['flag_bytes']; $thisfile_id3v2['exthead']['flags']['crc'] = (bool) ($thisfile_id3v2['exthead']['flag_raw'] & 0x8000); $thisfile_id3v2['exthead']['padding_size'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 4)); $extended_header_offset += 4; if ($thisfile_id3v2['exthead']['flags']['crc']) { $thisfile_id3v2['exthead']['flag_data']['crc'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 4)); $extended_header_offset += 4; } $extended_header_offset += $thisfile_id3v2['exthead']['padding_size']; } elseif ($id3v2_majorversion == 4) { // v2.4 definition: //Extended header size 4 * %0xxxxxxx // 28-bit synchsafe integer //Number of flag bytes $01 //Extended Flags $xx // %0bcd0000 // v2.4 // b - Tag is an update // Flag data length $00 // c - CRC data present // Flag data length $05 // Total frame CRC 5 * %0xxxxxxx // d - Tag restrictions // Flag data length $01 $thisfile_id3v2['exthead']['length'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 4), true); $extended_header_offset += 4; $thisfile_id3v2['exthead']['flag_bytes'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 1)); // should always be 1 $extended_header_offset += 1; $thisfile_id3v2['exthead']['flag_raw'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, $thisfile_id3v2['exthead']['flag_bytes'])); $extended_header_offset += $thisfile_id3v2['exthead']['flag_bytes']; $thisfile_id3v2['exthead']['flags']['update'] = (bool) ($thisfile_id3v2['exthead']['flag_raw'] & 0x40); $thisfile_id3v2['exthead']['flags']['crc'] = (bool) ($thisfile_id3v2['exthead']['flag_raw'] & 0x20); $thisfile_id3v2['exthead']['flags']['restrictions'] = (bool) ($thisfile_id3v2['exthead']['flag_raw'] & 0x10); if ($thisfile_id3v2['exthead']['flags']['update']) { $ext_header_chunk_length = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 1)); // should be 0 $extended_header_offset += 1; } if ($thisfile_id3v2['exthead']['flags']['crc']) { $ext_header_chunk_length = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 1)); // should be 5 $extended_header_offset += 1; $thisfile_id3v2['exthead']['flag_data']['crc'] = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, $ext_header_chunk_length), true, false); $extended_header_offset += $ext_header_chunk_length; } if ($thisfile_id3v2['exthead']['flags']['restrictions']) { $ext_header_chunk_length = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 1)); // should be 1 $extended_header_offset += 1; // %ppqrrstt $restrictions_raw = getid3_lib::BigEndian2Int(substr($framedata, $extended_header_offset, 1)); $extended_header_offset += 1; $thisfile_id3v2['exthead']['flags']['restrictions']['tagsize'] = ($restrictions_raw & 0xc0) >> 6; // p - Tag size restrictions $thisfile_id3v2['exthead']['flags']['restrictions']['textenc'] = ($restrictions_raw & 0x20) >> 5; // q - Text encoding restrictions $thisfile_id3v2['exthead']['flags']['restrictions']['textsize'] = ($restrictions_raw & 0x18) >> 3; // r - Text fields size restrictions $thisfile_id3v2['exthead']['flags']['restrictions']['imgenc'] = ($restrictions_raw & 0x4) >> 2; // s - Image encoding restrictions $thisfile_id3v2['exthead']['flags']['restrictions']['imgsize'] = ($restrictions_raw & 0x3) >> 0; // t - Image size restrictions $thisfile_id3v2['exthead']['flags']['restrictions_text']['tagsize'] = $this->LookupExtendedHeaderRestrictionsTagSizeLimits($thisfile_id3v2['exthead']['flags']['restrictions']['tagsize']); $thisfile_id3v2['exthead']['flags']['restrictions_text']['textenc'] = $this->LookupExtendedHeaderRestrictionsTextEncodings($thisfile_id3v2['exthead']['flags']['restrictions']['textenc']); $thisfile_id3v2['exthead']['flags']['restrictions_text']['textsize'] = $this->LookupExtendedHeaderRestrictionsTextFieldSize($thisfile_id3v2['exthead']['flags']['restrictions']['textsize']); $thisfile_id3v2['exthead']['flags']['restrictions_text']['imgenc'] = $this->LookupExtendedHeaderRestrictionsImageEncoding($thisfile_id3v2['exthead']['flags']['restrictions']['imgenc']); $thisfile_id3v2['exthead']['flags']['restrictions_text']['imgsize'] = $this->LookupExtendedHeaderRestrictionsImageSizeSize($thisfile_id3v2['exthead']['flags']['restrictions']['imgsize']); } 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) . ')'; } } $framedataoffset += $extended_header_offset; $framedata = substr($framedata, $extended_header_offset); } // end extended header while (isset($framedata) && strlen($framedata) > 0) { // cycle through until no more frame data is left to parse if (strlen($framedata) <= $this->ID3v2HeaderLength($id3v2_majorversion)) { // insufficient room left in ID3v2 header for actual data - must be padding $thisfile_id3v2['padding']['start'] = $framedataoffset; $thisfile_id3v2['padding']['length'] = strlen($framedata); $thisfile_id3v2['padding']['valid'] = true; for ($i = 0; $i < $thisfile_id3v2['padding']['length']; $i++) { if ($framedata[$i] != "") { $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'] - $i) . ' bytes are considered invalid)'; break; } } break; // skip rest of ID3v2 header } if ($id3v2_majorversion == 2) { // Frame ID $xx xx xx (three characters) // Size $xx xx xx (24-bit integer) // Flags $xx xx $frame_header = substr($framedata, 0, 6); // take next 6 bytes for header $framedata = substr($framedata, 6); // and leave the rest in $framedata $frame_name = substr($frame_header, 0, 3); $frame_size = getid3_lib::BigEndian2Int(substr($frame_header, 3, 3), 0); $frame_flags = 0; // not used for anything in ID3v2.2, just set to avoid E_NOTICEs } elseif ($id3v2_majorversion > 2) { // Frame ID $xx xx xx xx (four characters) // Size $xx xx xx xx (32-bit integer in v2.3, 28-bit synchsafe in v2.4+) // Flags $xx xx $frame_header = substr($framedata, 0, 10); // take next 10 bytes for header $framedata = substr($framedata, 10); // and leave the rest in $framedata $frame_name = substr($frame_header, 0, 4); if ($id3v2_majorversion == 3) { $frame_size = getid3_lib::BigEndian2Int(substr($frame_header, 4, 4), 0); // 32-bit integer } else { // ID3v2.4+ $frame_size = getid3_lib::BigEndian2Int(substr($frame_header, 4, 4), 1); // 32-bit synchsafe integer (28-bit value) } if ($frame_size < strlen($framedata) + 4) { $nextFrameID = substr($framedata, $frame_size, 4); if ($this->IsValidID3v2FrameName($nextFrameID, $id3v2_majorversion)) { // next frame is OK } elseif ($frame_name == "" . 'MP3' || $frame_name == "" . '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'; $id3v2_majorversion = 3; $frame_size = getid3_lib::BigEndian2Int(substr($frame_header, 4, 4), 0); // 32-bit integer } } $frame_flags = getid3_lib::BigEndian2Int(substr($frame_header, 8, 2)); } if ($id3v2_majorversion == 2 && $frame_name == "" || $frame_name == "") { // padding encountered $thisfile_id3v2['padding']['start'] = $framedataoffset; $thisfile_id3v2['padding']['length'] = strlen($frame_header) + strlen($framedata); $thisfile_id3v2['padding']['valid'] = true; $len = strlen($framedata); for ($i = 0; $i < $len; $i++) { if ($framedata[$i] != "") { $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'] - $i) . ' bytes are considered invalid)'; break; } } break; // skip rest of ID3v2 header } if ($frame_name == 'COM ') { $info['warning'][] = 'error parsing "' . $frame_name . '" (' . $framedataoffset . ' bytes into the ID3v2.' . $id3v2_majorversion . ' tag). (ERROR: IsValidID3v2FrameName("' . str_replace("", ' ', $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)]'; $frame_name = 'COMM'; } if ($frame_size <= strlen($framedata) && $this->IsValidID3v2FrameName($frame_name, $id3v2_majorversion)) { unset($parsedFrame); $parsedFrame['frame_name'] = $frame_name; $parsedFrame['frame_flags_raw'] = $frame_flags; $parsedFrame['data'] = substr($framedata, 0, $frame_size); $parsedFrame['datalength'] = getid3_lib::CastAsInt($frame_size); $parsedFrame['dataoffset'] = $framedataoffset; $this->ParseID3v2Frame($parsedFrame); $thisfile_id3v2[$frame_name][] = $parsedFrame; $framedata = substr($framedata, $frame_size); } else { // invalid frame length or FrameID if ($frame_size <= strlen($framedata)) { if ($this->IsValidID3v2FrameName(substr($framedata, $frame_size, 4), $id3v2_majorversion)) { // next frame is valid, just skip the current frame $framedata = substr($framedata, $frame_size); $info['warning'][] = 'Next ID3v2 frame is valid, skipping current frame.'; } else { // next frame is invalid too, abort processing //unset($framedata); $framedata = null; $info['error'][] = 'Next ID3v2 frame is also invalid, aborting processing.'; } } elseif ($frame_size == strlen($framedata)) { // this is the last frame, just skip $info['warning'][] = 'This was the last ID3v2 frame.'; } else { // next frame is invalid too, abort processing //unset($framedata); $framedata = null; $info['warning'][] = 'Invalid ID3v2 frame size, aborting.'; } if (!$this->IsValidID3v2FrameName($frame_name, $id3v2_majorversion)) { switch ($frame_name) { case "" . 'MP': case "" . 'MP3': case ' MP3': case 'MP3e': case "" . 'MP': case ' MP': case 'MP3': $info['warning'][] = 'error parsing "' . $frame_name . '" (' . $framedataoffset . ' bytes into the ID3v2.' . $id3v2_majorversion . ' tag). (ERROR: !IsValidID3v2FrameName("' . str_replace("", ' ', $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("", ' ', $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') . ')).'; } else { $info['error'][] = 'error parsing "' . $frame_name . '" (' . $framedataoffset . ' bytes into the ID3v2.' . $id3v2_majorversion . ' tag).'; } } $framedataoffset += $frame_size + $this->ID3v2HeaderLength($id3v2_majorversion); } } // Footer // The footer is a copy of the header, but with a different identifier. // ID3v2 identifier "3DI" // ID3v2 version $04 00 // ID3v2 flags %abcd0000 // ID3v2 size 4 * %0xxxxxxx if (isset($thisfile_id3v2_flags['isfooter']) && $thisfile_id3v2_flags['isfooter']) { $footer = $this->fread(10); if (substr($footer, 0, 3) == '3DI') { $thisfile_id3v2['footer'] = true; $thisfile_id3v2['majorversion_footer'] = ord($footer[3]); $thisfile_id3v2['minorversion_footer'] = ord($footer[4]); } if ($thisfile_id3v2['majorversion_footer'] <= 4) { $id3_flags = ord(substr($footer[5])); $thisfile_id3v2_flags['unsynch_footer'] = (bool) ($id3_flags & 0x80); $thisfile_id3v2_flags['extfoot_footer'] = (bool) ($id3_flags & 0x40); $thisfile_id3v2_flags['experim_footer'] = (bool) ($id3_flags & 0x20); $thisfile_id3v2_flags['isfooter_footer'] = (bool) ($id3_flags & 0x10); $thisfile_id3v2['footerlength'] = getid3_lib::BigEndian2Int(substr($footer, 6, 4), 1); } } // end footer if (isset($thisfile_id3v2['comments']['genre'])) { $genre = array(); foreach ($thisfile_id3v2['comments']['genre'] as $key => $value) { unset($thisfile_id3v2['comments']['genre'][$key]); $genre = getid3_lib::flipped_array_merge_noclobber($genre, $this->ParseID3v2GenreString($value)); } $thisfile_id3v2['comments']['genre'] = getid3_lib::flipped_array_merge_noclobber($thisfile_id3v2['comments']['genre'], $genre); } if (isset($thisfile_id3v2['comments']['track'])) { foreach ($thisfile_id3v2['comments']['track'] as $key => $value) { if (strstr($value, '/')) { list($thisfile_id3v2['comments']['tracknum'][$key], $thisfile_id3v2['comments']['totaltracks'][$key]) = explode('/', $thisfile_id3v2['comments']['track'][$key]); } } } if (!isset($thisfile_id3v2['comments']['year']) && !empty($thisfile_id3v2['comments']['recording_time'][0]) && preg_match('#^([0-9]{4})#', trim($thisfile_id3v2['comments']['recording_time'][0]), $matches)) { $thisfile_id3v2['comments']['year'] = array($matches[1]); } if (!empty($thisfile_id3v2['TXXX'])) { // MediaMonkey does this, maybe others: write a blank RGAD frame, but put replay-gain adjustment values in TXXX frames foreach ($thisfile_id3v2['TXXX'] as $txxx_array) { switch ($txxx_array['description']) { case 'replaygain_track_gain': if (empty($info['replay_gain']['track']['adjustment']) && !empty($txxx_array['data'])) { $info['replay_gain']['track']['adjustment'] = floatval(trim(str_replace('dB', '', $txxx_array['data']))); } break; case 'replaygain_track_peak': if (empty($info['replay_gain']['track']['peak']) && !empty($txxx_array['data'])) { $info['replay_gain']['track']['peak'] = floatval($txxx_array['data']); } break; case 'replaygain_album_gain': if (empty($info['replay_gain']['album']['adjustment']) && !empty($txxx_array['data'])) { $info['replay_gain']['album']['adjustment'] = floatval(trim(str_replace('dB', '', $txxx_array['data']))); } break; } } } // Set avdataoffset $info['avdataoffset'] = $thisfile_id3v2['headerlength']; if (isset($thisfile_id3v2['footer'])) { $info['avdataoffset'] += 10; } return true; }