root/trunk/wp-includes/formatting.php

<?php

function wptexturize($text) {
    global $wp_cockneyreplace;
    $next = true;
    $has_pre_parent = false;
    $output = '';
    $curl = '';
    $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
    $stop = count($textarr);

    // if a plugin has provided an autocorrect array, use it
    if ( isset($wp_cockneyreplace) ) {
        $cockney = array_keys($wp_cockneyreplace);
        $cockneyreplace = array_values($wp_cockneyreplace);
    } else {
        $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
        $cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round","&#8217;cause");
    }

    $static_characters = array_merge(array('---', ' -- ', '--', 'xn&#8211;', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
    $static_replacements = array_merge(array('&#8212;', ' &#8212; ', '&#8211;', 'xn--', '&#8230;', '&#8220;', '&#8217;s', '&#8221;', ' &#8482;'), $cockneyreplace);

    $dynamic_characters = array('/\'(\d\d(?:&#8217;|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
    $dynamic_replacements = array('&#8217;$1','$1&#8216;', '$1&#8243;', '$1&#8242;', '$1&#8217;$2', '$1&#8220;$2', '&#8221;$1', '&#8217;$1', '$1&#215;$2');

    for ( $i = 0; $i < $stop; $i++ ) {
         $curl = $textarr[$i];

        if (isset($curl{0}) && '<' != $curl{0} && '[' != $curl{0} && $next && !$has_pre_parent) { // If it's not a tag
            // static strings
            $curl = str_replace($static_characters, $static_replacements, $curl);
            // regular expressions
            $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
        } elseif (strpos($curl, '<code') !== false || strpos($curl, '<kbd') !== false || strpos($curl, '<style') !== false || strpos($curl, '<script') !== false) {
            $next = false;
        } elseif (strpos($curl, '<pre') !== false) {
            $has_pre_parent = true;
        } elseif (strpos($curl, '</pre>') !== false) {
            $has_pre_parent = false;
        } else {
            $next = true;
        }

        $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&#038;$1', $curl);
        $output .= $curl;
    }

      return $output;
}

// Accepts matches array from preg_replace_callback in wpautop()
// or a string
function clean_pre($matches) {
    if ( is_array($matches) )
        $text = $matches[1] . $matches[2] . "</pre>";
    else
        $text = $matches;

    $text = str_replace('<br />', '', $text);
    $text = str_replace('<p>', "\n", $text);
    $text = str_replace('</p>', '', $text);

    return $text;
}

function wpautop($pee, $br = 1) {
    $pee = $pee . "\n"; // just to make things a little easier, pad the end
    $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
    // Space things out a little
    $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
    $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
    $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
    $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
    if ( strpos($pee, '<object') !== false ) {
        $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
        $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
    }
    $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
    $pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $pee); // make paragraphs, including one at the end
    $pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
    $pee = preg_replace('!<p>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee);
    $pee = preg_replace( '|<p>|', "$1<p>", $pee );
    $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
    $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
    $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
    $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
    $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
    $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
    if ($br) {
        $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee);
        $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
        $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
    }
    $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
    $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
    if (strpos($pee, '<pre') !== false)
        $pee = preg_replace_callback('!(<pre.*?>)(.*?)</pre>!is', 'clean_pre', $pee );
    $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
    $pee = preg_replace('/<p>\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone

    return $pee;
}


function seems_utf8($Str) { # by bmorel at ssi dot fr
    $length = strlen($Str);
    for ($i=0; $i < $length; $i++) {
        if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
        elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
        elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
        elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
        elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
        elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
        else return false; # Does not match any model
        for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
            if ((++$i == $length) || ((ord($Str[$i]) & 0xC0) != 0x80))
            return false;
        }
    }
    return true;
}

function wp_specialchars( $text, $quotes = 0 ) {
    // Like htmlspecialchars except don't double-encode HTML entities
    $text = str_replace('&&', '&#038;&', $text);
    $text = str_replace('&&', '&#038;&', $text);
    $text = preg_replace('/&(?:$|([^#])(?![a-z1-4]{1,8};))/', '&#038;$1', $text);
    $text = str_replace('<', '&lt;', $text);
    $text = str_replace('>', '&gt;', $text);
    if ( 'double' === $quotes ) {
        $text = str_replace('"', '&quot;', $text);
    } elseif ( 'single' === $quotes ) {
        $text = str_replace("'", '&#039;', $text);
    } elseif ( $quotes ) {
        $text = str_replace('"', '&quot;', $text);
        $text = str_replace("'", '&#039;', $text);
    }
    return $text;
}

function utf8_uri_encode( $utf8_string, $length = 0 ) {
    $unicode = '';
    $values = array();
    $num_octets = 1;
    $unicode_length = 0;

    $string_length = strlen( $utf8_string );
    for ($i = 0; $i < $string_length; $i++ ) {

        $value = ord( $utf8_string[ $i ] );

        if ( $value < 128 ) {
            if ( $length && ( $unicode_length >= $length ) )
                break;
            $unicode .= chr($value);
            $unicode_length++;
        } else {
            if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;

            $values[] = $value;

            if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
                break;
            if ( count( $values ) == $num_octets ) {
                if ($num_octets == 3) {
                    $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
                    $unicode_length += 9;
                } else {
                    $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
                    $unicode_length += 6;
                }

                $values = array();
                $num_octets = 1;
            }
        }
    }

    return $unicode;
}

function remove_accents($string) {
    if ( !preg_match('/[\x80-\xff]/', $string) )
        return $string;

    if (seems_utf8($string)) {
        $chars = array(
        // Decompositions for Latin-1 Supplement
        chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
        chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
        chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
        chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
        chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
        chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
        chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
        chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
        chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
        chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
        chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
        chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
        chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
        chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
        chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
        chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
        chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
        chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
        chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
        chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
        chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
        chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
        chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
        chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
        chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
        chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
        chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
        chr(195).chr(191) => 'y',
        // Decompositions for Latin Extended-A
        chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
        chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
        chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
        chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
        chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
        chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
        chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
        chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
        chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
        chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
        chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
        chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
        chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
        chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
        chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
        chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
        chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
        chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
        chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
        chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
        chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
        chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
        chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
        chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
        chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
        chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
        chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
        chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
        chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
        chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
        chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
        chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
        chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
        chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
        chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
        chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
        chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
        chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
        chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
        chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
        chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
        chr(197).chr(146) => 'OE',chr(197).chr(