Newer
Older
<?php
/*********************************************************************
class.format.php
Collection of helper function used for formatting
http://www.osticket.com
Released under the GNU General Public License WITHOUT ANY WARRANTY.
See LICENSE.TXT for details.
vim: expandtab sw=4 ts=4 sts=4:
**********************************************************************/
class Format {
function file_size($bytes) {
if(!is_numeric($bytes))
return $bytes;
if($bytes<1024)
return $bytes.' bytes';
if($bytes <102400)
return round(($bytes/1024),1).' kb';
return round(($bytes/1024000),1).' mb';
}
function file_name($filename) {
return preg_replace('/\s+/', '_', $filename);
/* encode text into desired encoding - taking into accout charset when available. */
function encode($text, $charset=null, $encoding='utf-8') {
//Try auto-detecting charset/encoding
if(!$charset && function_exists('mb_detect_encoding'))
$charset = mb_detect_encoding($text);
// Cleanup - incorrect, bogus, or ambiguous charsets
if($charset && in_array(strtolower(trim($charset)),
array('default','x-user-defined','iso','us-ascii')))
$charset = 'ISO-8859-1';
if ($charset && strcasecmp($charset, $encoding) === 0)
if(function_exists('iconv') && $charset)
$text = iconv($charset, $encoding.'//IGNORE', $text);
elseif(function_exists('mb_convert_encoding') && $charset && $encoding)
$text = mb_convert_encoding($text, $encoding, $charset);
elseif(!strcasecmp($encoding, 'utf-8')) //forced blind utf8 encoding.
$text = function_exists('imap_utf8')?imap_utf8($text):utf8_encode($text);
// If $text is false, then we have a (likely) invalid charset, use
// the original text and assume 8-bit (latin-1 / iso-8859-1)
// encoding
return (!$text && $original) ? $original : $text;
}
//Wrapper for utf-8 encoding.
function utf8encode($text, $charset=null) {
Peter Rotich
committed
return Format::encode($text, $charset, 'utf-8');
function mimedecode($text, $encoding='UTF-8') {
if(function_exists('imap_mime_header_decode')
&& ($parts = imap_mime_header_decode($text))) {
$str ='';
foreach ($parts as $part)
$str.= Format::encode($part->text, $part->charset, $encoding);
$text = $str;
} elseif(function_exists('iconv_mime_decode')) {
$text = iconv_mime_decode($text, 0, $encoding);
} elseif(!strcasecmp($encoding, 'utf-8') && function_exists('imap_utf8')) {
$text = imap_utf8($text);
}
return $text;
}
/**
* Decodes filenames given in the content-disposition header according
* to RFC5987, such as filename*=utf-8''filename.png. Note that the
* language sub-component is defined in RFC5646, and that the filename
* is URL encoded (in the charset specified)
*/
function decodeRfc5987($filename) {
$match = array();
if (preg_match("/([\w!#$%&+^_`{}~-]+)'([\w-]*)'(.*)$/",
$filename, $match))
// XXX: Currently we don't care about the language component.
// The encoding hint is sufficient.
return self::utf8encode(urldecode($match[3]), $match[1]);
else
return $filename;
}
function phone($phone) {
$stripped= preg_replace("/[^0-9]/", "", $phone);
if(strlen($stripped) == 7)
return preg_replace("/([0-9]{3})([0-9]{4})/", "$1-$2",$stripped);
elseif(strlen($stripped) == 10)
return preg_replace("/([0-9]{3})([0-9]{3})([0-9]{4})/", "($1) $2-$3",$stripped);
else
return $phone;
}
function truncate($string,$len,$hard=false) {
if(!$len || $len>strlen($string))
return $string;
$string = substr($string,0,$len);
return $hard?$string:(substr($string,0,strrpos($string,' ')).' ...');
}
function strip_slashes($var) {
return is_array($var)?array_map(array('Format','strip_slashes'),$var):stripslashes($var);
}
function wrap($text, $len=75) {
return $len ? wordwrap($text, $len, "\n", true) : $text;
}
function html($html, $config=array('balance'=>1)) {
require_once(INCLUDE_DIR.'htmLawed.php');
return htmLawed($html, $config);
}
function html2text($html, $width=74, $tidy=true) {
# Tidy html: decode, balance, sanitize tags
if($tidy)
$html = Format::html(Format::htmldecode($html), array('balance' => 1));
# See if advanced html2text is available (requires xml extension)
if (function_exists('convert_html_to_text')
&& extension_loaded('xml'))
return convert_html_to_text($html, $width);
# Try simple html2text - insert line breaks after new line tags.
$html = preg_replace(
array(':<br ?/?\>:i', ':(</div>)\s*:i', ':(</p>)\s*:i'),
array("\n", "$1\n", "$1\n\n"),
$html);
# Strip tags, decode html chars and wrap resulting text.
return Format::wrap(
Format::htmldecode( Format::striptags($html, false)),
$width);
}
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
static function __html_cleanup($el, $attributes) {
static $eE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1,
'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1);
// Clean unexpected class values
if (isset($attributes['class'])) {
$classes = explode(' ', $attributes['class']);
foreach ($classes as $i=>$a)
// Unset all unsupported style classes -- anything by M$
if (strpos($a, 'Mso') !== 0)
unset($classes[$i]);
if ($classes)
$attributes['class'] = implode(' ', $classes);
else
unset($attributes['class']);
}
// Clean browser-specific style attributes
if (isset($attributes['style'])) {
$styles = explode(';', $attributes['style']);
foreach ($styles as $i=>$s) {
list($prop, $val) = explode(':', $s);
if (!$val || !$prop || $prop[0] == '-')
unset($styles[$i]);
}
if ($styles)
$attributes['style'] = implode(';', $styles);
else
unset($attributes['style']);
}
$at = '';
if (is_array($attributes)) {
foreach ($attributes as $k=>$v)
$at .= " $k=\"$v\"";
return "<{$el}{$at}".(isset($eE[$el])?" /":"").">";
}
else {
return "</{$el}>";
}
}
$html = preg_replace(
array(':<(head|style).+</\1>:is', # <head> and <style> sections
':<!\[[^]<]+\]>:'), # <![if !mso]> and friends
array('', ''),
$html);
$config = array(
'safe' => 1, //Exclude applet, embed, iframe, object and script tags.
'balance' => 1, //balance and close unclosed tags.
'comment' => 1, //Remove html comments (OUTLOOK LOVE THEM)
'deny_attribute' => 'id',
'schemes' => 'href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; *:file, http, https; src: cid, http, https, data',
'hook_tag' => array('Format', '__html_cleanup'),
return Format::html($html, $config);
function localizeInlineImages($text) {
// Change image.php urls back to content-id's
return preg_replace('/image\\.php\\?h=([\\w.-]{32})\\w{32}/',
'cid:$1', $text);
}
function sanitize($text, $striptags=false) {
Peter Rotich
committed
//balance and neutralize unsafe tags.
$text = Format::safe_html($text);
$text = self::localizeInlineImages($text);
Peter Rotich
committed
//If requested - strip tags with decoding disabled.
return $striptags?Format::striptags($text, false):$text;
}
Peter Rotich
committed
return Format::htmlencode($var);
}
function htmlencode($var) {
$flags = ENT_COMPAT | ENT_QUOTES;
if (phpversion() >= '5.4.0')
$flags |= ENT_HTML401;
Peter Rotich
committed
Peter Rotich
committed
? array_map(array('Format','htmlencode'), $var)
: htmlentities($var, $flags, 'UTF-8');
Peter Rotich
committed
function htmldecode($var) {
if(is_array($var))
return array_map(array('Format','htmldecode'), $var);
$flags = ENT_COMPAT;
if (phpversion() >= '5.4.0')
$flags |= ENT_HTML401;
Peter Rotich
committed
return html_entity_decode($var, $flags, 'UTF-8');
}
Peter Rotich
committed
return Format::htmlencode($var);
function display($text, $inline_images=true) {
Peter Rotich
committed
//make urls clickable.
if($cfg && $cfg->clickableURLS() && $text)
$text=Format::clickableurls($text);
//Wrap long words...
#$text=preg_replace_callback('/\w{75,}/',
# create_function(
# '$matches',
# 'return wordwrap($matches[0],70,"\n",true);'),
# $text);
// Make showing offsite images optional
$text = preg_replace_callback('/<img ([^>]*)(src="http[^"]+")([^>]*)\/>/',
function($match) {
// Drop embedded classes -- they don't refer to ours
$match = preg_replace('/class="[^"]*"/', '', $match);
return sprintf('<div %s class="non-local-image" data-%s %s></div>',
$match[1], $match[2], $match[3]);
if ($inline_images)
return self::viewableImages($text);
return $text;
Peter Rotich
committed
function striptags($var, $decode=true) {
if(is_array($var))
return array_map(array('Format','striptags'), $var, array_fill(0, count($var), $decode));
return strip_tags($decode?Format::htmldecode($var):$var);
//make urls clickable. Mainly for display
global $ost;
$token = $ost->getLinkToken();
//Not perfect but it works - please help improve it.
$text=preg_replace_callback('/(?<!"|>)(((f|ht)tp(s?):\/\/)[-a-zA-Z0-9@:%_\+.~#?&;\/\/=]+)/',
create_function('$matches',
sprintf('return "<a href=\"l.php?url=".urlencode($matches[1])."&auth=%s\" target=\"_blank\">".$matches[1]."</a>";',
$token)),
$text);
$text=preg_replace_callback("/(^|[ \\n\\r\\t])(www\.([a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+)+)(\/[^\/ \\n\\r]*)*)/",
create_function('$matches',
sprintf('return "<a href=\"l.php?url=".urlencode("http://".$matches[2])."&auth=%s\" target=\"_blank\">".$matches[2]."</a>";',
$token)),
$text);
$text=preg_replace("/(^|[ \\n\\r\\t])([_\.0-9a-z-]+@([0-9a-z][0-9a-z-]+\.)+[a-z]{2,4})/",
'\\1<a href="mailto:\\2" target="_blank">\\2</a>', $text);
//return preg_replace("/(^[\r\n]*|[\r\n]+)[\s\t]*[\r\n]+/", "\n", $string);
//return preg_replace('/\s\s+/',"\n",$string); //Too strict??
return preg_replace("/\n{3,}/", "\n\n", $string);
}
function linebreaks($string) {
return urldecode(ereg_replace("%0D", " ", urlencode($string)));
}
function viewableImages($html, $script='image.php') {
return preg_replace_callback('/"cid:([\\w.-]{32})"/',
function($match) use ($script) {
$hash = $match[1];
if (!($file = AttachmentFile::lookup($hash)))
return $match[0];
return sprintf('"%s?h=%s" data-cid="%s"',
$script, $file->getDownloadHash(), $match[1]);
}, $html);
}
/**
* Thanks, http://us2.php.net/manual/en/function.implode.php
* Implode an array with the key and value pair giving
* a glue, a separator between pairs and the array
* to implode.
* @param string $glue The glue between key and value
* @param string $separator Separator between pairs
* @param array $array The array to implode
* @return string The imploded array
*/
function array_implode( $glue, $separator, $array ) {
if ( !is_array( $array ) ) return $array;
$string = array();
foreach ( $array as $key => $val ) {
if ( is_array( $val ) )
$val = implode( ',', $val );
return implode( $separator, $string );
}
/* elapsed time */
if(!$sec || !is_numeric($sec)) return "";
$days = floor($sec / 86400);
$hrs = floor(bcmod($sec,86400)/3600);
$mins = round(bcmod(bcmod($sec,86400),3600)/60);
if($days > 0) $tstring = $days . 'd,';
if($hrs > 0) $tstring = $tstring . $hrs . 'h,';
$tstring =$tstring . $mins . 'm';
return $tstring;
}
/* Dates helpers...most of this crap will change once we move to PHP 5*/
function db_date($time) {
global $cfg;
return Format::userdate($cfg->getDateFormat(), Misc::db2gmtime($time));
}
function db_datetime($time) {
global $cfg;
return Format::userdate($cfg->getDateTimeFormat(), Misc::db2gmtime($time));
function db_daydatetime($time) {
global $cfg;
return Format::userdate($cfg->getDayDateTimeFormat(), Misc::db2gmtime($time));
function userdate($format, $gmtime) {
return Format::date($format, $gmtime, $_SESSION['TZ_OFFSET'], $_SESSION['TZ_DST']);
function date($format, $gmtimestamp, $offset=0, $daylight=false){
return "";
$offset+=$daylight?date('I', $gmtimestamp):0; //Daylight savings crap.
return date($format, ($gmtimestamp+ ($offset*3600)));
}
// Thanks, http://stackoverflow.com/a/2955878/1025836
/* static */
function slugify($text) {
// replace non letter or digits by -
$text = preg_replace('~[^\p{L}\p{N}]+~u', '-', $text);
// trim
$text = trim($text, '-');
// lowercase
$text = strtolower($text);
return (empty($text)) ? 'n-a' : $text;
}
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
/**
* Parse RFC 2397 formatted data strings. Format according to the RFC
* should look something like:
*
* data:[type/subtype][;charset=utf-8][;base64],data
*
* Parameters:
* $data - (string) RFC2397 formatted data string
* $output_encoding - (string:optional) Character set the input data
* should be encoded to.
* $always_convert - (bool|default:true) If the input data string does
* not specify an input encding, assume iso-8859-1. If this flag is
* set, the output will always be transcoded to the declared
* output_encoding, if set.
*
* Returs:
* array (data=>parsed and transcoded data string, type=>MIME type
* declared in the data string or text/plain otherwise)
*
* References:
* http://www.ietf.org/rfc/rfc2397.txt
*/
function parseRfc2397($data, $output_encoding=false, $always_convert=true) {
if (substr($data, 0, 5) != "data:")
return array('data'=>$data, 'type'=>'text/plain');
$data = substr($data, 5);
list($meta, $contents) = explode(",", $data, 2);
if ($meta)
list($type, $extra) = explode(";", $meta, 2);
else
$extra = '';
if (!isset($type) || !$type)
$type = 'text/plain';
$parameters = explode(";", $extra);
# Handle 'charset' hint in $extra, such as
# data:text/plain;charset=iso-8859-1,Blah
# Convert to utf-8 since it's the encoding scheme for the database.
$charset = ($always_convert) ? 'iso-8859-1' : false;
foreach ($parameters as $p) {
list($param, $value) = explode('=', $extra);
if ($param == 'charset')
$charset = $value;
elseif ($param == 'base64')
$contents = base64_decode($contents);
}
if ($output_encoding && $charset)
$contents = Format::encode($contents, $charset, $output_encoding);
return array(
'data' => $contents,
'type' => $type
);
}