From 3d879d529107c0c9d3f1e6b894d9ed17b6e6c54f Mon Sep 17 00:00:00 2001 From: Derek Allard Date: Fri, 18 Jan 2008 19:41:32 +0000 Subject: ExpressionEngine Dev Team in credit --- system/helpers/text_helper.php | 422 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 421 insertions(+), 1 deletion(-) (limited to 'system/helpers/text_helper.php') diff --git a/system/helpers/text_helper.php b/system/helpers/text_helper.php index b75cd8f78..211ef1055 100644 --- a/system/helpers/text_helper.php +++ b/system/helpers/text_helper.php @@ -1 +1,421 @@ -= $n) { return trim($out).$end_char; } } } // ------------------------------------------------------------------------ /** * High ASCII to Entities * * Converts High ascii text and MS Word special characters to character entities * * @access public * @param string * @return string */ function ascii_to_entities($str) { $count = 1; $out = ''; $temp = array(); for ($i = 0, $s = strlen($str); $i < $s; $i++) { $ordinal = ord($str[$i]); if ($ordinal < 128) { $out .= $str[$i]; } else { if (count($temp) == 0) { $count = ($ordinal < 224) ? 2 : 3; } $temp[] = $ordinal; if (count($temp) == $count) { $number = ($count == 3) ? (($temp['0'] % 16) * 4096) + (($temp['1'] % 64) * 64) + ($temp['2'] % 64) : (($temp['0'] % 32) * 64) + ($temp['1'] % 64); $out .= '&#'.$number.';'; $count = 1; $temp = array(); } } } return $out; } // ------------------------------------------------------------------------ /** * Entities to ASCII * * Converts character entities back to ASCII * * @access public * @param string * @param bool * @return string */ function entities_to_ascii($str, $all = TRUE) { if (preg_match_all('/\&#(\d+)\;/', $str, $matches)) { for ($i = 0, $s = count($matches['0']); $i < $s; $i++) { $digits = $matches['1'][$i]; $out = ''; if ($digits < 128) { $out .= chr($digits); } elseif ($digits < 2048) { $out .= chr(192 + (($digits - ($digits % 64)) / 64)); $out .= chr(128 + ($digits % 64)); } else { $out .= chr(224 + (($digits - ($digits % 4096)) / 4096)); $out .= chr(128 + ((($digits % 4096) - ($digits % 64)) / 64)); $out .= chr(128 + ($digits % 64)); } $str = str_replace($matches['0'][$i], $out, $str); } } if ($all) { $str = str_replace(array("&", "<", ">", """, "'", "-"), array("&","<",">","\"", "'", "-"), $str); } return $str; } // ------------------------------------------------------------------------ /** * Word Censoring Function * * Supply a string and an array of disallowed words and any * matched words will be converted to #### or to the replacement * word you've submitted. * * @access public * @param string the text string * @param string the array of censoered words * @param string the optional replacement value * @return string */ function word_censor($str, $censored, $replacement = '') { if ( ! is_array($censored)) { return $str; } $str = ' '.$str.' '; foreach ($censored as $badword) { if ($replacement != '') { $str = preg_replace("/\b(".str_replace('\*', '\w*?', preg_quote($badword)).")\b/i", $replacement, $str); } else { $str = preg_replace("/\b(".str_replace('\*', '\w*?', preg_quote($badword)).")\b/ie", "str_repeat('#', strlen('\\1'))", $str); } } return trim($str); } // ------------------------------------------------------------------------ /** * Code Highlighter * * Colorizes code strings * * @access public * @param string the text string * @return string */ function highlight_code($str) { // The highlight string function encodes and highlights // brackets so we need them to start raw $str = str_replace(array('<', '>'), array('<', '>'), $str); // Replace any existing PHP tags to temporary markers so they don't accidentally // break the string out of PHP, and thus, thwart the highlighting. $str = str_replace(array('<?php', '?>', '\\'), array('phptagopen', 'phptagclose', 'backslashtmp'), $str); // The highlight_string function requires that the text be surrounded // by PHP tags. Since we don't know if A) the submitted text has PHP tags, // or B) whether the PHP tags enclose the entire string, we will add our // own PHP tags around the string along with some markers to make replacement easier later $str = ''; // All the magic happens here, baby! $str = highlight_string($str, TRUE); // Prior to PHP 5, the highlight function used icky font tags // so we'll replace them with span tags. if (abs(phpversion()) < 5) { $str = str_replace(array(''), array(''), $str); $str = preg_replace('#color="(.*?)"#', 'style="color: \\1"', $str); } // Remove our artificially added PHP $str = preg_replace("#\.+?//tempstart\
\#is", "\n", $str); $str = preg_replace("#\.+?//tempstart\
#is", "\n", $str); $str = preg_replace("#//tempend.+#is", "\n", $str); // Replace our markers back to PHP tags. $str = str_replace(array('phptagopen', 'phptagclose', 'backslashtmp'), array('<?php', '?>', '\\'), $str); //', $tag_close = '') { if ($str == '') { return ''; } if ($phrase != '') { return preg_replace('/('.preg_quote($phrase, '/').')/i', $tag_open."\\1".$tag_close, $str); } return $str; } // ------------------------------------------------------------------------ /** * Word Wrap * * Wraps text at the specified character. Maintains the integrity of words. * Anything placed between {unwrap}{/unwrap} will not be word wrapped, nor * will URLs. * * @access public * @param string the text string * @param integer the number of characters to wrap at * @return string */ function word_wrap($str, $charlim = '76') { // Se the character limit if ( ! is_numeric($charlim)) $charlim = 76; // Reduce multiple spaces $str = preg_replace("| +|", " ", $str); // Standardize newlines $str = preg_replace("/\r\n|\r/", "\n", $str); // If the current word is surrounded by {unwrap} tags we'll // strip the entire chunk and replace it with a marker. $unwrap = array(); if (preg_match_all("|(\{unwrap\}.+?\{/unwrap\})|s", $str, $matches)) { for ($i = 0; $i < count($matches['0']); $i++) { $unwrap[] = $matches['1'][$i]; $str = str_replace($matches['1'][$i], "{{unwrapped".$i."}}", $str); } } // Use PHP's native function to do the initial wordwrap. // We set the cut flag to FALSE so that any individual words that are // too long get left alone. In the next step we'll deal with them. $str = wordwrap($str, $charlim, "\n", FALSE); // Split the string into individual lines of text and cycle through them $output = ""; foreach (explode("\n", $str) as $line) { // Is the line within the allowed character count? // If so we'll join it to the output and continue if (strlen($line) <= $charlim) { $output .= $line."\n"; continue; } $temp = ''; while((strlen($line)) > $charlim) { // If the over-length word is a URL we won't wrap it if (preg_match("!\[url.+\]|://|wwww.!", $line)) { break; } // Trim the word down $temp .= substr($line, 0, $charlim-1); $line = substr($line, $charlim-1); } // If $temp contains data it means we had to split up an over-length // word into smaller chunks so we'll add it back to our current line if ($temp != '') { $output .= $temp . "\n" . $line; } else { $output .= $line; } $output .= "\n"; } // Put our markers back if (count($unwrap) > 0) { foreach ($unwrap as $key => $val) { $output = str_replace("{{unwrapped".$key."}}", $val, $output); } } // Remove the unwrap tags $output = str_replace(array('{unwrap}', '{/unwrap}'), '', $output); return $output; } ?> \ No newline at end of file += $n) + { + return trim($out).$end_char; + } + } +} + +// ------------------------------------------------------------------------ + +/** + * High ASCII to Entities + * + * Converts High ascii text and MS Word special characters to character entities + * + * @access public + * @param string + * @return string + */ +function ascii_to_entities($str) +{ + $count = 1; + $out = ''; + $temp = array(); + + for ($i = 0, $s = strlen($str); $i < $s; $i++) + { + $ordinal = ord($str[$i]); + + if ($ordinal < 128) + { + $out .= $str[$i]; + } + else + { + if (count($temp) == 0) + { + $count = ($ordinal < 224) ? 2 : 3; + } + + $temp[] = $ordinal; + + if (count($temp) == $count) + { + $number = ($count == 3) ? (($temp['0'] % 16) * 4096) + (($temp['1'] % 64) * 64) + ($temp['2'] % 64) : (($temp['0'] % 32) * 64) + ($temp['1'] % 64); + + $out .= '&#'.$number.';'; + $count = 1; + $temp = array(); + } + } + } + + return $out; +} + +// ------------------------------------------------------------------------ + +/** + * Entities to ASCII + * + * Converts character entities back to ASCII + * + * @access public + * @param string + * @param bool + * @return string + */ +function entities_to_ascii($str, $all = TRUE) +{ + if (preg_match_all('/\&#(\d+)\;/', $str, $matches)) + { + for ($i = 0, $s = count($matches['0']); $i < $s; $i++) + { + $digits = $matches['1'][$i]; + + $out = ''; + + if ($digits < 128) + { + $out .= chr($digits); + + } + elseif ($digits < 2048) + { + $out .= chr(192 + (($digits - ($digits % 64)) / 64)); + $out .= chr(128 + ($digits % 64)); + } + else + { + $out .= chr(224 + (($digits - ($digits % 4096)) / 4096)); + $out .= chr(128 + ((($digits % 4096) - ($digits % 64)) / 64)); + $out .= chr(128 + ($digits % 64)); + } + + $str = str_replace($matches['0'][$i], $out, $str); + } + } + + if ($all) + { + $str = str_replace(array("&", "<", ">", """, "'", "-"), + array("&","<",">","\"", "'", "-"), + $str); + } + + return $str; +} + +// ------------------------------------------------------------------------ + +/** + * Word Censoring Function + * + * Supply a string and an array of disallowed words and any + * matched words will be converted to #### or to the replacement + * word you've submitted. + * + * @access public + * @param string the text string + * @param string the array of censoered words + * @param string the optional replacement value + * @return string + */ +function word_censor($str, $censored, $replacement = '') +{ + if ( ! is_array($censored)) + { + return $str; + } + + $str = ' '.$str.' '; + foreach ($censored as $badword) + { + if ($replacement != '') + { + $str = preg_replace("/\b(".str_replace('\*', '\w*?', preg_quote($badword)).")\b/i", $replacement, $str); + } + else + { + $str = preg_replace("/\b(".str_replace('\*', '\w*?', preg_quote($badword)).")\b/ie", "str_repeat('#', strlen('\\1'))", $str); + } + } + + return trim($str); +} + +// ------------------------------------------------------------------------ + +/** + * Code Highlighter + * + * Colorizes code strings + * + * @access public + * @param string the text string + * @return string + */ +function highlight_code($str) +{ + // The highlight string function encodes and highlights + // brackets so we need them to start raw + $str = str_replace(array('<', '>'), array('<', '>'), $str); + + // Replace any existing PHP tags to temporary markers so they don't accidentally + // break the string out of PHP, and thus, thwart the highlighting. + + $str = str_replace(array('<?php', '?>', '\\'), array('phptagopen', 'phptagclose', 'backslashtmp'), $str); + + // The highlight_string function requires that the text be surrounded + // by PHP tags. Since we don't know if A) the submitted text has PHP tags, + // or B) whether the PHP tags enclose the entire string, we will add our + // own PHP tags around the string along with some markers to make replacement easier later + + $str = ''; + + // All the magic happens here, baby! + $str = highlight_string($str, TRUE); + + // Prior to PHP 5, the highlight function used icky font tags + // so we'll replace them with span tags. + if (abs(phpversion()) < 5) + { + $str = str_replace(array(''), array(''), $str); + $str = preg_replace('#color="(.*?)"#', 'style="color: \\1"', $str); + } + + // Remove our artificially added PHP + $str = preg_replace("#\.+?//tempstart\
\#is", "\n", $str); + $str = preg_replace("#\.+?//tempstart\
#is", "\n", $str); + $str = preg_replace("#//tempend.+#is", "\n", $str); + + // Replace our markers back to PHP tags. + $str = str_replace(array('phptagopen', 'phptagclose', 'backslashtmp'), array('<?php', '?>', '\\'), $str); //', $tag_close = '') +{ + if ($str == '') + { + return ''; + } + + if ($phrase != '') + { + return preg_replace('/('.preg_quote($phrase, '/').')/i', $tag_open."\\1".$tag_close, $str); + } + + return $str; +} + +// ------------------------------------------------------------------------ + +/** + * Word Wrap + * + * Wraps text at the specified character. Maintains the integrity of words. + * Anything placed between {unwrap}{/unwrap} will not be word wrapped, nor + * will URLs. + * + * @access public + * @param string the text string + * @param integer the number of characters to wrap at + * @return string + */ +function word_wrap($str, $charlim = '76') +{ + // Se the character limit + if ( ! is_numeric($charlim)) + $charlim = 76; + + // Reduce multiple spaces + $str = preg_replace("| +|", " ", $str); + + // Standardize newlines + $str = preg_replace("/\r\n|\r/", "\n", $str); + + // If the current word is surrounded by {unwrap} tags we'll + // strip the entire chunk and replace it with a marker. + $unwrap = array(); + if (preg_match_all("|(\{unwrap\}.+?\{/unwrap\})|s", $str, $matches)) + { + for ($i = 0; $i < count($matches['0']); $i++) + { + $unwrap[] = $matches['1'][$i]; + $str = str_replace($matches['1'][$i], "{{unwrapped".$i."}}", $str); + } + } + + // Use PHP's native function to do the initial wordwrap. + // We set the cut flag to FALSE so that any individual words that are + // too long get left alone. In the next step we'll deal with them. + $str = wordwrap($str, $charlim, "\n", FALSE); + + // Split the string into individual lines of text and cycle through them + $output = ""; + foreach (explode("\n", $str) as $line) + { + // Is the line within the allowed character count? + // If so we'll join it to the output and continue + if (strlen($line) <= $charlim) + { + $output .= $line."\n"; + continue; + } + + $temp = ''; + while((strlen($line)) > $charlim) + { + // If the over-length word is a URL we won't wrap it + if (preg_match("!\[url.+\]|://|wwww.!", $line)) + { + break; + } + + // Trim the word down + $temp .= substr($line, 0, $charlim-1); + $line = substr($line, $charlim-1); + } + + // If $temp contains data it means we had to split up an over-length + // word into smaller chunks so we'll add it back to our current line + if ($temp != '') + { + $output .= $temp . "\n" . $line; + } + else + { + $output .= $line; + } + + $output .= "\n"; + } + + // Put our markers back + if (count($unwrap) > 0) + { + foreach ($unwrap as $key => $val) + { + $output = str_replace("{{unwrapped".$key."}}", $val, $output); + } + } + + // Remove the unwrap tags + $output = str_replace(array('{unwrap}', '{/unwrap}'), '', $output); + + return $output; +} + + +?> \ No newline at end of file -- cgit v1.2.3-24-g4f1b